From evan.cheng at apple.com Mon Apr 26 02:38:56 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 07:38:56 -0000 Subject: [llvm-commits] [llvm] r102323 - in /llvm/trunk: include/llvm/Target/TargetInstrInfo.h include/llvm/Target/TargetLowering.h lib/CodeGen/LiveIntervalAnalysis.cpp lib/CodeGen/SelectionDAG/InstrEmitter.cpp lib/CodeGen/SelectionDAG/InstrEmitter.h lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp lib/Target/X86/X86ISelLowering.cpp lib/Target/X86/X86ISelLowering.h lib/Target/X86/X86InstrInfo.cpp lib/Target/X86/X86InstrInfo.h Message-ID: <20100426073856.60001312800A@llvm.org> Author: evancheng Date: Mon Apr 26 02:38:55 2010 New Revision: 102323 URL: http://llvm.org/viewvc/llvm-project?rev=102323&view=rev Log: - Move TargetLowering::EmitTargetCodeForFrameDebugValue to TargetInstrInfo and rename it to emitFrameIndexDebugValue. - Teach spiller to modify DBG_VALUE instructions to reference spill slots. Modified: llvm/trunk/include/llvm/Target/TargetInstrInfo.h llvm/trunk/include/llvm/Target/TargetLowering.h llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.h llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp llvm/trunk/lib/Target/X86/X86ISelLowering.cpp llvm/trunk/lib/Target/X86/X86ISelLowering.h llvm/trunk/lib/Target/X86/X86InstrInfo.cpp llvm/trunk/lib/Target/X86/X86InstrInfo.h Modified: llvm/trunk/include/llvm/Target/TargetInstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetInstrInfo.h?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/include/llvm/Target/TargetInstrInfo.h (original) +++ llvm/trunk/include/llvm/Target/TargetInstrInfo.h Mon Apr 26 02:38:55 2010 @@ -23,6 +23,7 @@ class LiveVariables; class MCAsmInfo; class MachineMemOperand; +class MDNode; class SDNode; class SelectionDAG; class TargetRegisterClass; @@ -361,6 +362,19 @@ return false; } + /// emitFrameIndexDebugValue - Emit a target-dependent form of + /// DBG_VALUE encoding the address of a frame index. Addresses would + /// normally be lowered the same way as other addresses on the target, + /// e.g. in load instructions. For targets that do not support this + /// the debug info is simply lost. + virtual MachineInstr *emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, + uint64_t Offset, + const MDNode *MDPtr, + DebugLoc dl) const { + return 0; + } + /// foldMemoryOperand - Attempt to fold a load or store of the specified stack /// slot into the specified machine instruction for the specified operand(s). /// If this is possible, a new instruction is returned with the specified Modified: llvm/trunk/include/llvm/Target/TargetLowering.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetLowering.h?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/include/llvm/Target/TargetLowering.h (original) +++ llvm/trunk/include/llvm/Target/TargetLowering.h Mon Apr 26 02:38:55 2010 @@ -1255,16 +1255,6 @@ return SDValue(); } - /// EmitTargetCodeForFrameDebugValue - Emit a target-dependent form of - /// DBG_VALUE encoding the address of a frame index. Addresses would - /// normally be lowered the same way as other addresses on the target, - /// e.g. in load instructions. For targets that do not support this - /// the debug info is simply lost. - virtual void - EmitTargetCodeForFrameDebugValue(MachineBasicBlock* BB, unsigned FrameIx, - uint64_t Offset, MDNode *MDPtr, - DebugLoc dl) const {} - /// LowerOperationWrapper - This callback is invoked by the type legalizer /// to legalize nodes with an illegal operand type but legal result types. /// It replaces the LowerOperation callback in the type Legalizer. Modified: llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp (original) +++ llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Mon Apr 26 02:38:55 2010 @@ -1296,9 +1296,23 @@ MachineOperand &O = ri.getOperand(); ++ri; if (MI->isDebugValue()) { - // Remove debug info for now. - O.setReg(0U); - DEBUG(dbgs() << "Removing debug info due to spill:" << "\t" << *MI); + // Modify DBG_VALUE now that the value is in a spill slot. + uint64_t Offset = MI->getOperand(1).getImm(); + const MDNode *MDPtr = MI->getOperand(2).getMetadata(); + DebugLoc DL = MI->getDebugLoc(); + MachineInstr *NewDV = tii_->emitFrameIndexDebugValue(*mf_, Slot, Offset, + MDPtr, DL); + if (NewDV) { + DEBUG(dbgs() << "Modifying debug info due to spill:" << "\t" << *MI); + ReplaceMachineInstrInMaps(MI, NewDV); + MachineBasicBlock *MBB = MI->getParent(); + MBB->insert(MBB->erase(MI), NewDV); + } else { + DEBUG(dbgs() << "Removing debug info due to spill:" << "\t" << *MI); + RemoveMachineInstrFromMaps(MI); + vrm.RemoveMachineInstrFromMaps(MI); + MI->eraseFromParent(); + } continue; } assert(!O.isImplicit() && "Spilling register that's used as implicit use?"); Modified: llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp Mon Apr 26 02:38:55 2010 @@ -507,7 +507,6 @@ /// EmitDbgValue - Generate machine instruction for a dbg_value node. /// MachineInstr *InstrEmitter::EmitDbgValue(SDDbgValue *SD, - MachineBasicBlock *InsertBB, DenseMap &VRBaseMap, DenseMap *EM) { uint64_t Offset = SD->getOffset(); @@ -518,8 +517,7 @@ // Stack address; this needs to be lowered in target-dependent fashion. // EmitTargetCodeForFrameDebugValue is responsible for allocation. unsigned FrameIx = SD->getFrameIx(); - TLI->EmitTargetCodeForFrameDebugValue(InsertBB, FrameIx, Offset, MDPtr, DL); - return 0; + return TII->emitFrameIndexDebugValue(*MF, FrameIx, Offset, MDPtr, DL); } // Otherwise, we're going to create an instruction here. const TargetInstrDesc &II = TII->get(TargetOpcode::DBG_VALUE); Modified: llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.h?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.h (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.h Mon Apr 26 02:38:55 2010 @@ -103,7 +103,6 @@ /// EmitDbgValue - Generate machine instruction for a dbg_value node. /// MachineInstr *EmitDbgValue(SDDbgValue *SD, - MachineBasicBlock *InsertBB, DenseMap &VRBaseMap, DenseMap *EM); Modified: llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp Mon Apr 26 02:38:55 2010 @@ -449,9 +449,11 @@ continue; unsigned DVOrder = DVs[i]->getOrder(); if (DVOrder == ++Order) { - MachineInstr *DbgMI = Emitter.EmitDbgValue(DVs[i], BB, VRBaseMap, EM); - Orders.push_back(std::make_pair(DVOrder, DbgMI)); - BB->insert(InsertPos, DbgMI); + MachineInstr *DbgMI = Emitter.EmitDbgValue(DVs[i], VRBaseMap, EM); + if (DbgMI) { + Orders.push_back(std::make_pair(DVOrder, DbgMI)); + BB->insert(InsertPos, DbgMI); + } DVs[i]->setIsInvalidated(); } } @@ -540,13 +542,15 @@ #endif if ((*DI)->isInvalidated()) continue; - MachineInstr *DbgMI = Emitter.EmitDbgValue(*DI, MIBB, VRBaseMap, EM); - if (!LastOrder) - // Insert to start of the BB (after PHIs). - BB->insert(BBBegin, DbgMI); - else { - MachineBasicBlock::iterator Pos = MI; - MIBB->insert(llvm::next(Pos), DbgMI); + MachineInstr *DbgMI = Emitter.EmitDbgValue(*DI, VRBaseMap, EM); + if (DbgMI) { + if (!LastOrder) + // Insert to start of the BB (after PHIs). + BB->insert(BBBegin, DbgMI); + else { + MachineBasicBlock::iterator Pos = MI; + MIBB->insert(llvm::next(Pos), DbgMI); + } } } LastOrder = Order; @@ -558,8 +562,9 @@ MachineBasicBlock *InsertBB = Emitter.getBlock(); MachineBasicBlock::iterator Pos= Emitter.getBlock()->getFirstTerminator(); if (!(*DI)->isInvalidated()) { - MachineInstr *DbgMI= Emitter.EmitDbgValue(*DI, InsertBB, VRBaseMap, EM); - InsertBB->insert(Pos, DbgMI); + MachineInstr *DbgMI= Emitter.EmitDbgValue(*DI, VRBaseMap, EM); + if (DbgMI) + InsertBB->insert(Pos, DbgMI); } ++DI; } Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original) +++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Mon Apr 26 02:38:55 2010 @@ -8622,19 +8622,6 @@ return BB; } -void -X86TargetLowering::EmitTargetCodeForFrameDebugValue(MachineBasicBlock* BB, - unsigned FrameIx, uint64_t Offset, - MDNode *MDPtr, DebugLoc DL) const { - // Target dependent DBG_VALUE. Only the frame index case is done here. - const TargetInstrInfo *TII = getTargetMachine().getInstrInfo(); - X86AddressMode AM; - AM.BaseType = X86AddressMode::FrameIndexBase; - AM.Base.FrameIndex = FrameIx; - addFullAddress(BuildMI(BB, DL, TII->get(X86::DBG_VALUE)), AM). - addImm(Offset).addMetadata(MDPtr); -} - MachineBasicBlock * X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI, MachineBasicBlock *BB, Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.h?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.h (original) +++ llvm/trunk/lib/Target/X86/X86ISelLowering.h Mon Apr 26 02:38:55 2010 @@ -453,11 +453,6 @@ /// and some i16 instructions are slow. virtual bool IsDesirableToPromoteOp(SDValue Op, EVT &PVT) const; - virtual void - EmitTargetCodeForFrameDebugValue(MachineBasicBlock* BB, - unsigned FrameIx, uint64_t Offset, - MDNode *MDPtr, DebugLoc DL) const; - virtual MachineBasicBlock *EmitInstrWithCustomInserter(MachineInstr *MI, MachineBasicBlock *MBB, DenseMap *EM) const; Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original) +++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Mon Apr 26 02:38:55 2010 @@ -2319,6 +2319,20 @@ return true; } +MachineInstr* +X86InstrInfo::emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, uint64_t Offset, + const MDNode *MDPtr, + DebugLoc DL) const { + // Target dependent DBG_VALUE. Only the frame index case is done here. + X86AddressMode AM; + AM.BaseType = X86AddressMode::FrameIndexBase; + AM.Base.FrameIndex = FrameIx; + MachineInstrBuilder MIB = BuildMI(MF, DL, get(X86::DBG_VALUE)); + addFullAddress(MIB, AM).addImm(Offset).addMetadata(MDPtr); + return &*MIB; +} + static MachineInstr *FuseTwoAddrInst(MachineFunction &MF, unsigned Opcode, const SmallVectorImpl &MOs, MachineInstr *MI, Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.h?rev=102323&r1=102322&r2=102323&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86InstrInfo.h (original) +++ llvm/trunk/lib/Target/X86/X86InstrInfo.h Mon Apr 26 02:38:55 2010 @@ -623,6 +623,12 @@ MachineBasicBlock::iterator MI, const std::vector &CSI) const; + virtual + MachineInstr *emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, uint64_t Offset, + const MDNode *MDPtr, + DebugLoc DL) const; + /// foldMemoryOperand - If this target supports it, fold a load or store of /// the specified stack slot into the specified machine instruction for the /// specified operand(s). If this is possible, the target should perform the From evan.cheng at apple.com Mon Apr 26 02:39:25 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 07:39:25 -0000 Subject: [llvm-commits] [llvm] r102324 - in /llvm/trunk/lib/Target/ARM: ARMBaseInstrInfo.cpp ARMBaseInstrInfo.h ARMBaseRegisterInfo.cpp Message-ID: <20100426073925.9C473312800A@llvm.org> Author: evancheng Date: Mon Apr 26 02:39:25 2010 New Revision: 102324 URL: http://llvm.org/viewvc/llvm-project?rev=102324&view=rev Log: Add ARM specific emitFrameIndexDebugValue. Modified: llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.cpp llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.h llvm/trunk/lib/Target/ARM/ARMBaseRegisterInfo.cpp Modified: llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.cpp?rev=102324&r1=102323&r2=102324&view=diff ============================================================================== --- llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.cpp (original) +++ llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.cpp Mon Apr 26 02:39:25 2010 @@ -816,6 +816,16 @@ } } +MachineInstr* +ARMBaseInstrInfo::emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, uint64_t Offset, + const MDNode *MDPtr, + DebugLoc DL) const { + MachineInstrBuilder MIB = BuildMI(MF, DL, get(ARM::DBG_VALUE)) + .addFrameIndex(FrameIx).addImm(0).addImm(Offset).addMetadata(MDPtr); + return &*MIB; +} + MachineInstr *ARMBaseInstrInfo:: foldMemoryOperandImpl(MachineFunction &MF, MachineInstr *MI, const SmallVectorImpl &Ops, int FI) const { Modified: llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.h?rev=102324&r1=102323&r2=102324&view=diff ============================================================================== --- llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.h (original) +++ llvm/trunk/lib/Target/ARM/ARMBaseInstrInfo.h Mon Apr 26 02:39:25 2010 @@ -269,6 +269,12 @@ unsigned DestReg, int FrameIndex, const TargetRegisterClass *RC) const; + virtual MachineInstr *emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, + uint64_t Offset, + const MDNode *MDPtr, + DebugLoc DL) const; + virtual bool canFoldMemoryOperand(const MachineInstr *MI, const SmallVectorImpl &Ops) const; Modified: llvm/trunk/lib/Target/ARM/ARMBaseRegisterInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMBaseRegisterInfo.cpp?rev=102324&r1=102323&r2=102324&view=diff ============================================================================== --- llvm/trunk/lib/Target/ARM/ARMBaseRegisterInfo.cpp (original) +++ llvm/trunk/lib/Target/ARM/ARMBaseRegisterInfo.cpp Mon Apr 26 02:39:25 2010 @@ -1183,6 +1183,13 @@ SPAdj = 0; Offset += SPAdj; + // Special handling of dbg_value instructions. + if (MI.isDebugValue()) { + MI.getOperand(i). ChangeToRegister(FrameReg, false /*isDef*/); + MI.getOperand(i+1).ChangeToImmediate(Offset); + return 0; + } + // Modify MI as necessary to handle as much of 'Offset' as possible bool Done = false; if (!AFI->isThumbFunction()) From evan.cheng at apple.com Mon Apr 26 02:39:36 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 07:39:36 -0000 Subject: [llvm-commits] [llvm] r102325 - in /llvm/trunk/lib/Target/PowerPC: PPCInstrInfo.cpp PPCInstrInfo.h Message-ID: <20100426073936.C509D312800A@llvm.org> Author: evancheng Date: Mon Apr 26 02:39:36 2010 New Revision: 102325 URL: http://llvm.org/viewvc/llvm-project?rev=102325&view=rev Log: Add PPC specific emitFrameIndexDebugValue. Modified: llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.cpp llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.h Modified: llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.cpp?rev=102325&r1=102324&r2=102325&view=diff ============================================================================== --- llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.cpp (original) +++ llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.cpp Mon Apr 26 02:39:36 2010 @@ -645,6 +645,16 @@ MBB.insert(MI, NewMIs[i]); } +MachineInstr* +PPCInstrInfo::emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, uint64_t Offset, + const MDNode *MDPtr, + DebugLoc DL) const { + MachineInstrBuilder MIB = BuildMI(MF, DL, get(PPC::DBG_VALUE)); + addFrameReference(MIB, FrameIx, 0, false).addImm(Offset).addMetadata(MDPtr); + return &*MIB; +} + /// foldMemoryOperand - PowerPC (like most RISC's) can only fold spills into /// copy instructions, turning them into load/store instructions. MachineInstr *PPCInstrInfo::foldMemoryOperandImpl(MachineFunction &MF, Modified: llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.h?rev=102325&r1=102324&r2=102325&view=diff ============================================================================== --- llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.h (original) +++ llvm/trunk/lib/Target/PowerPC/PPCInstrInfo.h Mon Apr 26 02:39:36 2010 @@ -126,6 +126,12 @@ unsigned DestReg, int FrameIndex, const TargetRegisterClass *RC) const; + virtual MachineInstr *emitFrameIndexDebugValue(MachineFunction &MF, + unsigned FrameIx, + uint64_t Offset, + const MDNode *MDPtr, + DebugLoc DL) const; + /// foldMemoryOperand - PowerPC (like most RISC's) can only fold spills into /// copy instructions, turning them into load/store instructions. virtual MachineInstr* foldMemoryOperandImpl(MachineFunction &MF, From evan.cheng at apple.com Mon Apr 26 03:16:57 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 08:16:57 -0000 Subject: [llvm-commits] [llvm] r102326 - /llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Message-ID: <20100426081657.9565C312800A@llvm.org> Author: evancheng Date: Mon Apr 26 03:16:57 2010 New Revision: 102326 URL: http://llvm.org/viewvc/llvm-project?rev=102326&view=rev Log: Remove a redundant comment. Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=102326&r1=102325&r2=102326&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original) +++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Mon Apr 26 03:16:57 2010 @@ -2324,7 +2324,6 @@ unsigned FrameIx, uint64_t Offset, const MDNode *MDPtr, DebugLoc DL) const { - // Target dependent DBG_VALUE. Only the frame index case is done here. X86AddressMode AM; AM.BaseType = X86AddressMode::FrameIndexBase; AM.Base.FrameIndex = FrameIx; From evan.cheng at apple.com Mon Apr 26 03:24:08 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 08:24:08 -0000 Subject: [llvm-commits] [llvm] r102327 - /llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Message-ID: <20100426082408.0F996312800A@llvm.org> Author: evancheng Date: Mon Apr 26 03:24:07 2010 New Revision: 102327 URL: http://llvm.org/viewvc/llvm-project?rev=102327&view=rev Log: Temporary disable spiller modifying dbg_value. It's breaking build. Modified: llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Modified: llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp?rev=102327&r1=102326&r2=102327&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp (original) +++ llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Mon Apr 26 03:24:07 2010 @@ -1296,6 +1296,8 @@ MachineOperand &O = ri.getOperand(); ++ri; if (MI->isDebugValue()) { +#if 0 + // Disabled temporarily. // Modify DBG_VALUE now that the value is in a spill slot. uint64_t Offset = MI->getOperand(1).getImm(); const MDNode *MDPtr = MI->getOperand(2).getMetadata(); @@ -1308,11 +1310,14 @@ MachineBasicBlock *MBB = MI->getParent(); MBB->insert(MBB->erase(MI), NewDV); } else { +#endif DEBUG(dbgs() << "Removing debug info due to spill:" << "\t" << *MI); RemoveMachineInstrFromMaps(MI); vrm.RemoveMachineInstrFromMaps(MI); MI->eraseFromParent(); +#if 0 } +#endif continue; } assert(!O.isImplicit() && "Spilling register that's used as implicit use?"); From jyasskin at google.com Mon Apr 26 08:40:23 2010 From: jyasskin at google.com (Jeffrey Yasskin) Date: Mon, 26 Apr 2010 06:40:23 -0700 Subject: [llvm-commits] [llvm] r99160 - in /llvm/trunk: lib/VMCore/ConstantsContext.h lib/VMCore/LLVMContextImpl.cpp tools/bugpoint/BugDriver.cpp tools/bugpoint/BugDriver.h In-Reply-To: <4BD56464.5020402@nokia.com> References: <20100322052338.207252A6C12C@llvm.org> <4BD56464.5020402@nokia.com> Message-ID: Opening a PR would probably help. Please include your test case, the arguments you passed to bugpoint, and the result of uname -a (or some other way to identify your platform). . On Mon, Apr 26, 2010 at 3:01 AM, Kalle Raiskila wrote: > Hi, > > sorry to drag up this old commit, but this makes bugpoint segfault for me. > The testcase I have causes a misscompilation only on SPU, and I cannot > reproduce this error on the other platforms (i.e. x86). I'd be happy to help > to try to track down this issue, in case you don't have a CellBE handy :) Or > should I just open a PR? > > Last lines that bugpoint spews out are below. > > kalle > > *** Attempting to perform final cleanups: > Emitted bitcode to 'bugpoint-reduced-simplified.bc' > While deleting: [22 x float] % > Use still stuck around after Def is destroyed:@vconst = constant [22 x > float] [float 0 ?bugpoint ?0x104c6e08 > 1 ?bugpoint ?0x104c76f0 > 2 ? ? ? ? ? ?0x00100344 __kernel_sigtramp32 + 0 > 3 ?bugpoint ?0x100ca954 llvm::raw_ostream::operator<<(char) + 100 > 4 ?bugpoint ?0x103a8038 > 5 ?bugpoint ?0x103a2f38 > 6 ?bugpoint ?0x103a56e8 > 7 ?bugpoint ?0x103a2c6c llvm::Value::print(llvm::raw_ostream&, > llvm::AssemblyAnnotationWriter*) const + 1516 > 8 ?bugpoint ?0x10453ac8 llvm::Value::~Value() + 536 > 9 ?bugpoint ?0x103c90e4 llvm::ConstantArray::~ConstantArray() + 148 > 10 bugpoint ?0x1041488c llvm::LLVMContextImpl::~LLVMContextImpl() + 972 > 11 bugpoint ?0x10411658 llvm::LLVMContext::~LLVMContext() + 56 > 12 bugpoint ?0x10411d70 llvm::object_deleter::call(void*) > + 48 > 13 bugpoint ?0x104a0750 llvm::ManagedStaticBase::destroy() const + 96 > 14 bugpoint ?0x104a07e4 llvm::llvm_shutdown() + 68 > 15 bugpoint ?0x100d8e5c main + 396 > 16 libc.so.6 0x0fbfdb24 > 17 libc.so.6 0x0fbfdce0 > Stack dump: > 0. ? ? ?Program arguments: bugpoint mrfir-all.ll -run-llc -safe-run-cbe > --tool-args --march=cellspu > Segmentation fault > > > Jeffrey Yasskin skrev: >> >> Author: jyasskin >> Date: Mon Mar 22 00:23:37 2010 >> New Revision: 99160 >> >> URL: http://llvm.org/viewvc/llvm-project?rev=99160&view=rev >> Log: >> Free all Constants in ~LLVMConstantImpl. ?We avoid assertion failures >> by dropping all references from all constants that can use other >> constants before trying to destroy any of them. >> >> I also had to free bugpoint's Module in ~BugDriver(). >> >> >> Modified: >> ? ?llvm/trunk/lib/VMCore/ConstantsContext.h >> ? ?llvm/trunk/lib/VMCore/LLVMContextImpl.cpp >> ? ?llvm/trunk/tools/bugpoint/BugDriver.cpp >> ? ?llvm/trunk/tools/bugpoint/BugDriver.h >> >> Modified: llvm/trunk/lib/VMCore/ConstantsContext.h >> URL: >> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/VMCore/ConstantsContext.h?rev=99160&r1=99159&r2=99160&view=diff >> >> ============================================================================== >> --- llvm/trunk/lib/VMCore/ConstantsContext.h (original) >> +++ llvm/trunk/lib/VMCore/ConstantsContext.h Mon Mar 22 00:23:37 2010 >> @@ -600,8 +600,8 @@ >> ? void freeConstants() { >> ? ? for (typename MapTy::iterator I=Map.begin(), E=Map.end(); >> ? ? ? ? ?I != E; ++I) { >> - ? ? ?if (I->second->use_empty()) >> - ? ? ? ?delete I->second; >> + ? ? ?// Asserts that use_empty(). >> + ? ? ?delete I->second; >> ? ? } >> ? } >> >> Modified: llvm/trunk/lib/VMCore/LLVMContextImpl.cpp >> URL: >> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/VMCore/LLVMContextImpl.cpp?rev=99160&r1=99159&r2=99160&view=diff >> >> ============================================================================== >> --- llvm/trunk/lib/VMCore/LLVMContextImpl.cpp (original) >> +++ llvm/trunk/lib/VMCore/LLVMContextImpl.cpp Mon Mar 22 00:23:37 2010 >> @@ -12,6 +12,7 @@ >> >> ?//===----------------------------------------------------------------------===// >> ?#include "LLVMContextImpl.h" >> +#include >> ?LLVMContextImpl::LLVMContextImpl(LLVMContext &C) >> ? : TheTrueVal(0), TheFalseVal(0), >> @@ -34,10 +35,32 @@ >> ? OpaqueTypes.insert(AlwaysOpaqueTy); >> ?} >> ?+namespace { >> +struct DropReferences { >> + ?// Takes the value_type of a ConstantUniqueMap's internal map, whose >> 'second' >> + ?// is a Constant*. >> + ?template >> + ?void operator()(const PairT &P) { >> + ? ?P.second->dropAllReferences(); >> + ?} >> +}; >> +} >> + >> ?LLVMContextImpl::~LLVMContextImpl() { >> + ?std::for_each(ExprConstants.map_begin(), ExprConstants.map_end(), >> + ? ? ? ? ? ? ? ?DropReferences()); >> + ?std::for_each(ArrayConstants.map_begin(), ArrayConstants.map_end(), >> + ? ? ? ? ? ? ? ?DropReferences()); >> + ?std::for_each(StructConstants.map_begin(), StructConstants.map_end(), >> + ? ? ? ? ? ? ? ?DropReferences()); >> + ?std::for_each(UnionConstants.map_begin(), UnionConstants.map_end(), >> + ? ? ? ? ? ? ? ?DropReferences()); >> + ?std::for_each(VectorConstants.map_begin(), VectorConstants.map_end(), >> + ? ? ? ? ? ? ? ?DropReferences()); >> ? ExprConstants.freeConstants(); >> ? ArrayConstants.freeConstants(); >> ? StructConstants.freeConstants(); >> + ?UnionConstants.freeConstants(); >> ? VectorConstants.freeConstants(); >> ? AggZeroConstants.freeConstants(); >> ? NullPtrConstants.freeConstants(); >> @@ -45,13 +68,11 @@ >> ? InlineAsms.freeConstants(); >> ? for (IntMapTy::iterator I = IntConstants.begin(), E = >> IntConstants.end(); ? ? ? ? I != E; ++I) { >> - ? ?if (I->second->use_empty()) >> - ? ? ?delete I->second; >> + ? ?delete I->second; >> ? } >> ? for (FPMapTy::iterator I = FPConstants.begin(), E = FPConstants.end(); >> ? ? ? I != E; ++I) { >> - ? ?if (I->second->use_empty()) >> - ? ? ?delete I->second; >> + ? ?delete I->second; >> ? } >> ? AlwaysOpaqueTy->dropRef(); >> ? for (OpaqueTypesTy::iterator I = OpaqueTypes.begin(), E = >> OpaqueTypes.end(); >> >> Modified: llvm/trunk/tools/bugpoint/BugDriver.cpp >> URL: >> http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/bugpoint/BugDriver.cpp?rev=99160&r1=99159&r2=99160&view=diff >> >> ============================================================================== >> --- llvm/trunk/tools/bugpoint/BugDriver.cpp (original) >> +++ llvm/trunk/tools/bugpoint/BugDriver.cpp Mon Mar 22 00:23:37 2010 >> @@ -75,6 +75,10 @@ >> ? ? run_as_child(as_child), run_find_bugs(find_bugs), Timeout(timeout), >> ? ?MemoryLimit(memlimit), UseValgrind(use_valgrind) {} >> ?+BugDriver::~BugDriver() { >> + ?delete Program; >> +} >> + >> ?/// ParseInputFile - Given a bitcode or assembly input filename, parse >> and >> ?/// return it, or return null if not possible. >> >> Modified: llvm/trunk/tools/bugpoint/BugDriver.h >> URL: >> http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/bugpoint/BugDriver.h?rev=99160&r1=99159&r2=99160&view=diff >> >> ============================================================================== >> --- llvm/trunk/tools/bugpoint/BugDriver.h (original) >> +++ llvm/trunk/tools/bugpoint/BugDriver.h Mon Mar 22 00:23:37 2010 >> @@ -65,6 +65,7 @@ >> ? BugDriver(const char *toolname, bool as_child, bool find_bugs, >> ? ? ? ? ? ? unsigned timeout, unsigned memlimit, bool use_valgrind, >> ? ? ? ? ? ? LLVMContext& ctxt); >> + ?~BugDriver(); >> ? ?const char *getToolName() const { return ToolName; } >> >> >> _______________________________________________ >> llvm-commits mailing list >> llvm-commits at cs.uiuc.edu >> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits >> > > From daniel at zuster.org Mon Apr 26 08:48:36 2010 From: daniel at zuster.org (Daniel Dunbar) Date: Mon, 26 Apr 2010 06:48:36 -0700 Subject: [llvm-commits] [llvm] r102288 - in /llvm/trunk: autoconf/m4/link_options.m4 configure In-Reply-To: <20100425001220.622B0312836B@llvm.org> References: <20100425001220.622B0312836B@llvm.org> Message-ID: On Sat, Apr 24, 2010 at 5:12 PM, Dan Gohman wrote: > Author: djg > Date: Sat Apr 24 19:12:20 2010 > New Revision: 102288 > > URL: http://llvm.org/viewvc/llvm-project?rev=102288&view=rev > Log: > Fix an autoconf bug: The second argument to AC_LANG_PROGRAM is code that > gets placed inside a main function, and should not itself be a main > function. This is silently hidden in GCC-hosted builds because the > inner main looks like a nested function declaration, which GCC supports. > In builds with compilers which do not support nested functions (by default), > this was causing an error, which caused these autoconf checks to fail, > leaving their options disabled. Haha, that is crazy! Thanks for fixing this!!! - Daniel > This fixes test/Feature/load_module.ll on x86_64-unknown-linux-gnu > llvm-gcc selfhost builds, among other things. > > This also includes a regenerated configure, as the diff is small and telling. > > Modified: > ? ?llvm/trunk/autoconf/m4/link_options.m4 > ? ?llvm/trunk/configure > > Modified: llvm/trunk/autoconf/m4/link_options.m4 > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/autoconf/m4/link_options.m4?rev=102288&r1=102287&r2=102288&view=diff > ============================================================================== > --- llvm/trunk/autoconf/m4/link_options.m4 (original) > +++ llvm/trunk/autoconf/m4/link_options.m4 Sat Apr 24 19:12:20 2010 > @@ -8,7 +8,7 @@ > ?[ AC_LANG_PUSH([C]) > ? oldcflags="$CFLAGS" > ? CFLAGS="$CFLAGS -Wl,-R." > - ?AC_LINK_IFELSE([AC_LANG_PROGRAM([[]],[[int main() { return 0; }]])], > + ?AC_LINK_IFELSE([AC_LANG_PROGRAM([[]],[[]])], > ? ? [llvm_cv_link_use_r=yes],[llvm_cv_link_use_r=no]) > ? CFLAGS="$oldcflags" > ? AC_LANG_POP([C]) > @@ -29,7 +29,7 @@ > ?[ AC_LANG_PUSH([C]) > ? oldcflags="$CFLAGS" > ? CFLAGS="$CFLAGS -Wl,-export-dynamic" > - ?AC_LINK_IFELSE([AC_LANG_PROGRAM([[]],[[int main() { return 0; }]])], > + ?AC_LINK_IFELSE([AC_LANG_PROGRAM([[]],[[]])], > ? ? [llvm_cv_link_use_export_dynamic=yes],[llvm_cv_link_use_export_dynamic=no]) > ? CFLAGS="$oldcflags" > ? AC_LANG_POP([C]) > @@ -70,7 +70,7 @@ > ? echo "main" > "$tmp/exports" > > ? CFLAGS="$CFLAGS -Wl,-retain-symbols-file=$tmp/exports" > - ?AC_LINK_IFELSE([AC_LANG_PROGRAM([[]],[[int main() { return 0; }]])], > + ?AC_LINK_IFELSE([AC_LANG_PROGRAM([[]],[[]])], > ? ? [llvm_cv_link_use_retain_symbols_file=yes],[llvm_cv_link_use_retain_symbols_file=no]) > ? rm "$tmp/exports" > ? rmdir "$tmp" > > Modified: llvm/trunk/configure > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/configure?rev=102288&r1=102287&r2=102288&view=diff > ============================================================================== > --- llvm/trunk/configure (original) > +++ llvm/trunk/configure Sat Apr 24 19:12:20 2010 > @@ -8634,7 +8634,7 @@ > ?int > ?main () > ?{ > -int main() { return 0; } > + > ? ; > ? return 0; > ?} > @@ -8726,7 +8726,7 @@ > ?int > ?main () > ?{ > -int main() { return 0; } > + > ? ; > ? return 0; > ?} > @@ -8837,7 +8837,7 @@ > ?int > ?main () > ?{ > -int main() { return 0; } > + > ? ; > ? return 0; > ?} > > > _______________________________________________ > llvm-commits mailing list > llvm-commits at cs.uiuc.edu > http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits > From daniel at zuster.org Mon Apr 26 08:56:58 2010 From: daniel at zuster.org (Daniel Dunbar) Date: Mon, 26 Apr 2010 13:56:58 -0000 Subject: [llvm-commits] [zorg] r102333 - /zorg/trunk/buildbot/osuosl/master/config/builders.py Message-ID: <20100426135658.C70DD312800A@llvm.org> Author: ddunbar Date: Mon Apr 26 08:56:58 2010 New Revision: 102333 URL: http://llvm.org/viewvc/llvm-project?rev=102333&view=rev Log: buildbot: Enable clang-x86_64-linux-selfhost-rel by default, now that Dan fixed last remaining issues! Modified: zorg/trunk/buildbot/osuosl/master/config/builders.py Modified: zorg/trunk/buildbot/osuosl/master/config/builders.py URL: http://llvm.org/viewvc/llvm-project/zorg/trunk/buildbot/osuosl/master/config/builders.py?rev=102333&r1=102332&r2=102333&view=diff ============================================================================== --- zorg/trunk/buildbot/osuosl/master/config/builders.py (original) +++ zorg/trunk/buildbot/osuosl/master/config/builders.py Mon Apr 26 08:56:58 2010 @@ -180,6 +180,14 @@ stage1_config='Release', stage2_config='Debug')}, + {'name' : "clang-x86_64-linux-selfhost-rel", + 'slavenames' : ["osu7"], + 'builddir' : "clang-x86_64-linux-selfhost-rel", + 'factory' : ClangBuilder.getClangBuildFactory(triple='x86_64-pc-linux-gnu', + useTwoStage=True, + stage1_config='Release', + stage2_config='Release')}, + {'name' : "clang-i686-linux-fnt", 'slavenames' : ['balint1'], 'builddir' : "clang-i686-linux-fnt", @@ -262,15 +270,6 @@ extra_configure_args=['--disable-multilib']), 'category' : 'llvm-gcc.exp' }, - {'name' : "clang-x86_64-linux-selfhost-rel", - 'slavenames' : ["osu7"], - 'builddir' : "clang-x86_64-linux-selfhost-rel", - 'factory' : ClangBuilder.getClangBuildFactory(triple='x86_64-pc-linux-gnu', - useTwoStage=True, - stage1_config='Release', - stage2_config='Release'), - 'category' : 'clang.exp' }, - {'name' : "clang-i686-xp-msvc9_alt", 'slavenames' :['adobe1'], 'builddir' :"clang-i686-xp-msvc9_alt", From daniel at zuster.org Mon Apr 26 08:58:34 2010 From: daniel at zuster.org (Daniel Dunbar) Date: Mon, 26 Apr 2010 13:58:34 -0000 Subject: [llvm-commits] [zorg] r102334 - /zorg/trunk/buildbot/osuosl/master/config/builders.py Message-ID: <20100426135834.A4C63312800A@llvm.org> Author: ddunbar Date: Mon Apr 26 08:58:34 2010 New Revision: 102334 URL: http://llvm.org/viewvc/llvm-project?rev=102334&view=rev Log: buildbot: Reorder builders to put known failing builders on far right Modified: zorg/trunk/buildbot/osuosl/master/config/builders.py Modified: zorg/trunk/buildbot/osuosl/master/config/builders.py URL: http://llvm.org/viewvc/llvm-project/zorg/trunk/buildbot/osuosl/master/config/builders.py?rev=102334&r1=102333&r2=102334&view=diff ============================================================================== --- zorg/trunk/buildbot/osuosl/master/config/builders.py (original) +++ zorg/trunk/buildbot/osuosl/master/config/builders.py Mon Apr 26 08:58:34 2010 @@ -229,6 +229,22 @@ def _get_experimental_builders(): return [ + {'name' : "clang-x86_64-darwin10-selfhost-rel", + 'slavenames' : ["dunbar-darwin10"], + 'builddir' : "clang-x86_64-darwin10-selfhost-rel", + 'factory' : ClangBuilder.getClangBuildFactory(triple='x86_64-apple-darwin10', + useTwoStage=True, + stage1_config='Release', + stage2_config='Release'), + 'category' : 'clang.exp' }, + + {'name' : "llvm-gcc-x86_64-linux-selfhost", + 'slavenames':["osu7"], + 'builddir':"llvm-gcc-x86_64-linux-selfhost", + 'factory':LLVMGCCBuilder.getLLVMGCCBuildFactory(triple='x86_64-pc-linux-gnu', + extra_configure_args=['--disable-multilib']), + 'category' : 'llvm-gcc.exp' }, + {'name' : "llvm-gcc-x86_64-darwin10-cross-mingw32", 'slavenames':["kistanova1"], 'builddir': "llvm-gcc-x86_64-darwin10-cross-mingw32", @@ -245,15 +261,6 @@ ), 'category':'llvm-gcc'}, - {'name' : "clang-x86_64-darwin10-selfhost-rel", - 'slavenames' : ["dunbar-darwin10"], - 'builddir' : "clang-x86_64-darwin10-selfhost-rel", - 'factory' : ClangBuilder.getClangBuildFactory(triple='x86_64-apple-darwin10', - useTwoStage=True, - stage1_config='Release', - stage2_config='Release'), - 'category' : 'clang.exp' }, - {'name' : "clang-i686-linux-selfhost-rel", 'slavenames' : ["osu8"], 'builddir' : "clang-i686-linux-selfhost-rel", @@ -263,13 +270,6 @@ stage2_config='Release'), 'category' : 'clang.exp' }, - {'name' : "llvm-gcc-x86_64-linux-selfhost", - 'slavenames':["osu7"], - 'builddir':"llvm-gcc-x86_64-linux-selfhost", - 'factory':LLVMGCCBuilder.getLLVMGCCBuildFactory(triple='x86_64-pc-linux-gnu', - extra_configure_args=['--disable-multilib']), - 'category' : 'llvm-gcc.exp' }, - {'name' : "clang-i686-xp-msvc9_alt", 'slavenames' :['adobe1'], 'builddir' :"clang-i686-xp-msvc9_alt", From criswell at uiuc.edu Mon Apr 26 12:31:41 2010 From: criswell at uiuc.edu (John Criswell) Date: Mon, 26 Apr 2010 17:31:41 -0000 Subject: [llvm-commits] [poolalloc] r102345 - /poolalloc/branches/release_26/include/poolalloc/PoolAllocate.h Message-ID: <20100426173141.BDEC93128018@llvm.org> Author: criswell Date: Mon Apr 26 12:31:41 2010 New Revision: 102345 URL: http://llvm.org/viewvc/llvm-project?rev=102345&view=rev Log: Modified getPool() to fetch global pools as well as pools local to the function. Modified: poolalloc/branches/release_26/include/poolalloc/PoolAllocate.h Modified: poolalloc/branches/release_26/include/poolalloc/PoolAllocate.h URL: http://llvm.org/viewvc/llvm-project/poolalloc/branches/release_26/include/poolalloc/PoolAllocate.h?rev=102345&r1=102344&r2=102345&view=diff ============================================================================== --- poolalloc/branches/release_26/include/poolalloc/PoolAllocate.h (original) +++ poolalloc/branches/release_26/include/poolalloc/PoolAllocate.h Mon Apr 26 12:31:41 2010 @@ -353,10 +353,10 @@ } // - // We either do not have a pool, or the pool is not accessible from the - // specified function. Return NULL. + // Perhaps this is a global pool. If it isn't, then return a NULL + // pointer. // - return 0; + return getGlobalPool (N); } virtual Value * getGlobalPool (const DSNode * Node) { From criswell at uiuc.edu Mon Apr 26 12:32:07 2010 From: criswell at uiuc.edu (John Criswell) Date: Mon, 26 Apr 2010 17:32:07 -0000 Subject: [llvm-commits] [poolalloc] r102346 - /poolalloc/branches/release_26/lib/PoolAllocate/PASimple.cpp Message-ID: <20100426173207.F40CD312800A@llvm.org> Author: criswell Date: Mon Apr 26 12:32:07 2010 New Revision: 102346 URL: http://llvm.org/viewvc/llvm-project?rev=102346&view=rev Log: Have the simple pool allocation pass update the DSGraph results when it modifes an allocation site. Modified: poolalloc/branches/release_26/lib/PoolAllocate/PASimple.cpp Modified: poolalloc/branches/release_26/lib/PoolAllocate/PASimple.cpp URL: http://llvm.org/viewvc/llvm-project/poolalloc/branches/release_26/lib/PoolAllocate/PASimple.cpp?rev=102346&r1=102345&r2=102346&view=diff ============================================================================== --- poolalloc/branches/release_26/lib/PoolAllocate/PASimple.cpp (original) +++ poolalloc/branches/release_26/lib/PoolAllocate/PASimple.cpp Mon Apr 26 12:32:07 2010 @@ -207,9 +207,22 @@ TD.getTypeAllocSize(MI->getAllocatedType())); } + // + // Create the pool allocation call. + // Value* args[] = {TheGlobalPool, AllocSize}; Instruction* x = CallInst::Create(PoolAlloc, &args[0], &args[2], MI->getName(), ii); - ii->replaceAllUsesWith(CastInst::CreatePointerCast(x, ii->getType(), "", ii)); + + // + // Update the DSGraph. + // + CombinedDSGraph->getScalarMap().replaceScalar (ii, x); + + // + // Replace the old malloc instruction with the call to poolalloc(). + // + x = CastInst::CreatePointerCast(x, ii->getType(), "", ii); + ii->replaceAllUsesWith(x); } else if (CallInst * CI = dyn_cast(ii)) { CallSite CS(CI); Function *CF = CS.getCalledFunction(); @@ -252,6 +265,11 @@ Opts + 3, Name, InsertPt); + // + // Update the DSGraph. + // + CombinedDSGraph->getScalarMap().replaceScalar (CI, V); + Instruction *Casted = V; if (V->getType() != CI->getType()) Casted = CastInst::CreatePointerCast (V, CI->getType(), V->getName(), InsertPt); @@ -294,6 +312,11 @@ Name, InsertPt); + // + // Update the DSGraph. + // + CombinedDSGraph->getScalarMap().replaceScalar (CI, V); + Instruction *Casted = V; if (V->getType() != CI->getType()) Casted = CastInst::CreatePointerCast (V, CI->getType(), V->getName(), InsertPt); @@ -327,6 +350,12 @@ Opts + 2, Name, InsertPt); + + // + // Update the DSGraph. + // + CombinedDSGraph->getScalarMap().replaceScalar (CI, V); + Instruction *Casted = V; if (V->getType() != CI->getType()) Casted = CastInst::CreatePointerCast (V, CI->getType(), V->getName(), InsertPt); From sabre at nondot.org Mon Apr 26 12:38:10 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 17:38:10 -0000 Subject: [llvm-commits] [llvm] r102352 - /llvm/trunk/docs/ReleaseNotes.html Message-ID: <20100426173810.E38F6312800A@llvm.org> Author: lattner Date: Mon Apr 26 12:38:10 2010 New Revision: 102352 URL: http://llvm.org/viewvc/llvm-project?rev=102352&view=rev Log: add GHC, thanks to David Terei Modified: llvm/trunk/docs/ReleaseNotes.html Modified: llvm/trunk/docs/ReleaseNotes.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/ReleaseNotes.html?rev=102352&r1=102351&r2=102352&view=diff ============================================================================== --- llvm/trunk/docs/ReleaseNotes.html (original) +++ llvm/trunk/docs/ReleaseNotes.html Mon Apr 26 12:38:10 2010 @@ -439,6 +439,26 @@

+ +
+Glasgow Haskell Compiler (GHC) +
+ +
+

+GHC is an open source, +state-of-the-art programming suite for Haskell, a standard lazy +functional programming language. It includes an optimizing static +compiler generating good code for a variety of platforms, together +with an interactive system for convenient, quick development.

+ +

In addition to the existing C and native code generators, GHC now +supports an LLVM +code generator. GHC supports LLVM 2.7.

+ +
+
From bob.wilson at apple.com Mon Apr 26 12:40:49 2010 From: bob.wilson at apple.com (Bob Wilson) Date: Mon, 26 Apr 2010 17:40:49 -0000 Subject: [llvm-commits] [llvm] r102353 - in /llvm/trunk: include/llvm/CodeGen/MachineSSAUpdater.h lib/CodeGen/MachineSSAUpdater.cpp Message-ID: <20100426174049.B2F19312800A@llvm.org> Author: bwilson Date: Mon Apr 26 12:40:49 2010 New Revision: 102353 URL: http://llvm.org/viewvc/llvm-project?rev=102353&view=rev Log: Update MachineSSAUpdater with the same changes I made for the IR-level SSAUpdater. I'm going to try to refactor this to share most of the code between them. Modified: llvm/trunk/include/llvm/CodeGen/MachineSSAUpdater.h llvm/trunk/lib/CodeGen/MachineSSAUpdater.cpp Modified: llvm/trunk/include/llvm/CodeGen/MachineSSAUpdater.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/CodeGen/MachineSSAUpdater.h?rev=102353&r1=102352&r2=102353&view=diff ============================================================================== --- llvm/trunk/include/llvm/CodeGen/MachineSSAUpdater.h (original) +++ llvm/trunk/include/llvm/CodeGen/MachineSSAUpdater.h Mon Apr 26 12:40:49 2010 @@ -23,22 +23,27 @@ class TargetInstrInfo; class TargetRegisterClass; template class SmallVectorImpl; + class BumpPtrAllocator; /// MachineSSAUpdater - This class updates SSA form for a set of virtual /// registers defined in multiple blocks. This is used when code duplication /// or another unstructured transformation wants to rewrite a set of uses of one /// vreg with uses of a set of vregs. class MachineSSAUpdater { +public: + class BBInfo; + typedef SmallVectorImpl BlockListTy; + +private: /// AvailableVals - This keeps track of which value to use on a per-block /// basis. When we insert PHI nodes, we keep track of them here. //typedef DenseMap AvailableValsTy; void *AV; - /// IncomingPredInfo - We use this as scratch space when doing our recursive - /// walk. This should only be used in GetValueInBlockInternal, normally it - /// should be empty. - //std::vector > IncomingPredInfo; - void *IPI; + /// BBMap - The GetValueAtEndOfBlock method maintains this mapping from + /// basic blocks to BBInfo structures. + /// typedef DenseMap BBMapTy; + void *BM; /// VR - Current virtual register whose uses are being updated. unsigned VR; @@ -106,6 +111,15 @@ private: void ReplaceRegWith(unsigned OldReg, unsigned NewReg); unsigned GetValueAtEndOfBlockInternal(MachineBasicBlock *BB); + void BuildBlockList(MachineBasicBlock *BB, BlockListTy *BlockList, + BumpPtrAllocator *Allocator); + void FindDominators(BlockListTy *BlockList); + void FindPHIPlacement(BlockListTy *BlockList); + void FindAvailableVals(BlockListTy *BlockList); + void FindExistingPHI(MachineBasicBlock *BB, BlockListTy *BlockList); + bool CheckIfPHIMatches(MachineInstr *PHI); + void RecordMatchingPHI(MachineInstr *PHI); + void operator=(const MachineSSAUpdater&); // DO NOT IMPLEMENT MachineSSAUpdater(const MachineSSAUpdater&); // DO NOT IMPLEMENT }; Modified: llvm/trunk/lib/CodeGen/MachineSSAUpdater.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/MachineSSAUpdater.cpp?rev=102353&r1=102352&r2=102353&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/MachineSSAUpdater.cpp (original) +++ llvm/trunk/lib/CodeGen/MachineSSAUpdater.cpp Mon Apr 26 12:40:49 2010 @@ -21,34 +21,50 @@ #include "llvm/Target/TargetRegisterInfo.h" #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/SmallVector.h" +#include "llvm/Support/AlignOf.h" +#include "llvm/Support/Allocator.h" #include "llvm/Support/Debug.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/raw_ostream.h" using namespace llvm; -typedef DenseMap AvailableValsTy; -typedef std::vector > - IncomingPredInfoTy; +/// BBInfo - Per-basic block information used internally by MachineSSAUpdater. +class MachineSSAUpdater::BBInfo { +public: + MachineBasicBlock *BB; // Back-pointer to the corresponding block. + unsigned AvailableVal; // Value to use in this block. + BBInfo *DefBB; // Block that defines the available value. + int BlkNum; // Postorder number. + BBInfo *IDom; // Immediate dominator. + unsigned NumPreds; // Number of predecessor blocks. + BBInfo **Preds; // Array[NumPreds] of predecessor blocks. + MachineInstr *PHITag; // Marker for existing PHIs that match. + + BBInfo(MachineBasicBlock *ThisBB, unsigned V) + : BB(ThisBB), AvailableVal(V), DefBB(V ? this : 0), BlkNum(0), IDom(0), + NumPreds(0), Preds(0), PHITag(0) { } +}; + +typedef DenseMap BBMapTy; +typedef DenseMap AvailableValsTy; static AvailableValsTy &getAvailableVals(void *AV) { return *static_cast(AV); } -static IncomingPredInfoTy &getIncomingPredInfo(void *IPI) { - return *static_cast(IPI); +static BBMapTy *getBBMap(void *BM) { + return static_cast(BM); } - MachineSSAUpdater::MachineSSAUpdater(MachineFunction &MF, SmallVectorImpl *NewPHI) - : AV(0), IPI(0), InsertedPHIs(NewPHI) { + : AV(0), BM(0), InsertedPHIs(NewPHI) { TII = MF.getTarget().getInstrInfo(); MRI = &MF.getRegInfo(); } MachineSSAUpdater::~MachineSSAUpdater() { delete &getAvailableVals(AV); - delete &getIncomingPredInfo(IPI); } /// Initialize - Reset this object to get ready for a new set of SSA @@ -59,11 +75,6 @@ else getAvailableVals(AV).clear(); - if (IPI == 0) - IPI = new IncomingPredInfoTy(); - else - getIncomingPredInfo(IPI).clear(); - VR = V; VRC = MRI->getRegClass(VR); } @@ -127,7 +138,7 @@ unsigned NewVR = MRI->createVirtualRegister(RC); return BuildMI(*BB, I, DebugLoc(), TII->get(Opcode), NewVR); } - + /// GetValueInMiddleOfBlock - Construct SSA form, materializing a value that /// is live in the middle of the specified block. /// @@ -150,7 +161,7 @@ unsigned MachineSSAUpdater::GetValueInMiddleOfBlock(MachineBasicBlock *BB) { // If there is no definition of the renamed variable in this block, just use // GetValueAtEndOfBlock to do our work. - if (!getAvailableVals(AV).count(BB)) + if (!HasValueForBlock(BB)) return GetValueAtEndOfBlockInternal(BB); // If there are no predecessors, just return undef. @@ -254,141 +265,436 @@ /// GetValueAtEndOfBlockInternal - Check to see if AvailableVals has an entry /// for the specified BB and if so, return it. If not, construct SSA form by -/// walking predecessors inserting PHI nodes as needed until we get to a block -/// where the value is available. -/// +/// first calculating the required placement of PHIs and then inserting new +/// PHIs where needed. unsigned MachineSSAUpdater::GetValueAtEndOfBlockInternal(MachineBasicBlock *BB){ AvailableValsTy &AvailableVals = getAvailableVals(AV); + if (unsigned V = AvailableVals[BB]) + return V; - // Query AvailableVals by doing an insertion of null. - std::pair InsertRes = - AvailableVals.insert(std::make_pair(BB, 0)); - - // Handle the case when the insertion fails because we have already seen BB. - if (!InsertRes.second) { - // If the insertion failed, there are two cases. The first case is that the - // value is already available for the specified block. If we get this, just - // return the value. - if (InsertRes.first->second != 0) - return InsertRes.first->second; - - // Otherwise, if the value we find is null, then this is the value is not - // known but it is being computed elsewhere in our recursion. This means - // that we have a cycle. Handle this by inserting a PHI node and returning - // it. When we get back to the first instance of the recursion we will fill - // in the PHI node. - MachineBasicBlock::iterator Loc = BB->empty() ? BB->end() : BB->front(); - MachineInstr *NewPHI = InsertNewDef(TargetOpcode::PHI, BB, Loc, - VRC, MRI,TII); - unsigned NewVR = NewPHI->getOperand(0).getReg(); - InsertRes.first->second = NewVR; - return NewVR; - } - - // If there are no predecessors, then we must have found an unreachable block - // just return 'undef'. Since there are no predecessors, InsertRes must not - // be invalidated. - if (BB->pred_empty()) { + // Pool allocation used internally by GetValueAtEndOfBlock. + BumpPtrAllocator Allocator; + BBMapTy BBMapObj; + BM = &BBMapObj; + + SmallVector BlockList; + BuildBlockList(BB, &BlockList, &Allocator); + + // Special case: bail out if BB is unreachable. + if (BlockList.size() == 0) { + BM = 0; // Insert an implicit_def to represent an undef value. MachineInstr *NewDef = InsertNewDef(TargetOpcode::IMPLICIT_DEF, BB, BB->getFirstTerminator(), VRC, MRI, TII); - return InsertRes.first->second = NewDef->getOperand(0).getReg(); + unsigned V = NewDef->getOperand(0).getReg(); + AvailableVals[BB] = V; + return V; } - // Okay, the value isn't in the map and we just inserted a null in the entry - // to indicate that we're processing the block. Since we have no idea what - // value is in this block, we have to recurse through our predecessors. - // - // While we're walking our predecessors, we keep track of them in a vector, - // then insert a PHI node in the end if we actually need one. We could use a - // smallvector here, but that would take a lot of stack space for every level - // of the recursion, just use IncomingPredInfo as an explicit stack. - IncomingPredInfoTy &IncomingPredInfo = getIncomingPredInfo(IPI); - unsigned FirstPredInfoEntry = IncomingPredInfo.size(); - - // As we're walking the predecessors, keep track of whether they are all - // producing the same value. If so, this value will capture it, if not, it - // will get reset to null. We distinguish the no-predecessor case explicitly - // below. - unsigned SingularValue = 0; - bool isFirstPred = true; + FindDominators(&BlockList); + FindPHIPlacement(&BlockList); + FindAvailableVals(&BlockList); + + BM = 0; + return BBMapObj[BB]->DefBB->AvailableVal; +} + +/// FindPredecessorBlocks - Put the predecessors of Info->BB into the Preds +/// vector, set Info->NumPreds, and allocate space in Info->Preds. +static void FindPredecessorBlocks(MachineSSAUpdater::BBInfo *Info, + SmallVectorImpl *Preds, + BumpPtrAllocator *Allocator) { + MachineBasicBlock *BB = Info->BB; for (MachineBasicBlock::pred_iterator PI = BB->pred_begin(), - E = BB->pred_end(); PI != E; ++PI) { - MachineBasicBlock *PredBB = *PI; - unsigned PredVal = GetValueAtEndOfBlockInternal(PredBB); - IncomingPredInfo.push_back(std::make_pair(PredBB, PredVal)); + E = BB->pred_end(); PI != E; ++PI) + Preds->push_back(*PI); - // Compute SingularValue. - if (isFirstPred) { - SingularValue = PredVal; - isFirstPred = false; - } else if (PredVal != SingularValue) - SingularValue = 0; - } + Info->NumPreds = Preds->size(); + Info->Preds = static_cast + (Allocator->Allocate(Info->NumPreds * sizeof(MachineSSAUpdater::BBInfo*), + AlignOf::Alignment)); +} + +/// BuildBlockList - Starting from the specified basic block, traverse back +/// through its predecessors until reaching blocks with known values. Create +/// BBInfo structures for the blocks and append them to the block list. +void MachineSSAUpdater::BuildBlockList(MachineBasicBlock *BB, + BlockListTy *BlockList, + BumpPtrAllocator *Allocator) { + AvailableValsTy &AvailableVals = getAvailableVals(AV); + BBMapTy *BBMap = getBBMap(BM); + SmallVector RootList; + SmallVector WorkList; + + BBInfo *Info = new (*Allocator) BBInfo(BB, 0); + (*BBMap)[BB] = Info; + WorkList.push_back(Info); + + // Search backward from BB, creating BBInfos along the way and stopping when + // reaching blocks that define the value. Record those defining blocks on + // the RootList. + SmallVector Preds; + while (!WorkList.empty()) { + Info = WorkList.pop_back_val(); + Preds.clear(); + FindPredecessorBlocks(Info, &Preds, Allocator); + + // Treat an unreachable predecessor as a definition with 'undef'. + if (Info->NumPreds == 0) { + // Insert an implicit_def to represent an undef value. + MachineInstr *NewDef = InsertNewDef(TargetOpcode::IMPLICIT_DEF, + Info->BB, + Info->BB->getFirstTerminator(), + VRC, MRI, TII); + Info->AvailableVal = NewDef->getOperand(0).getReg(); + Info->DefBB = Info; + RootList.push_back(Info); + continue; + } - /// Look up BB's entry in AvailableVals. 'InsertRes' may be invalidated. If - /// this block is involved in a loop, a no-entry PHI node will have been - /// inserted as InsertedVal. Otherwise, we'll still have the null we inserted - /// above. - unsigned &InsertedVal = AvailableVals[BB]; - - // If all the predecessor values are the same then we don't need to insert a - // PHI. This is the simple and common case. - if (SingularValue) { - // If a PHI node got inserted, replace it with the singlar value and delete - // it. - if (InsertedVal) { - MachineInstr *OldVal = MRI->getVRegDef(InsertedVal); - // Be careful about dead loops. These RAUW's also update InsertedVal. - assert(InsertedVal != SingularValue && "Dead loop?"); - ReplaceRegWith(InsertedVal, SingularValue); - OldVal->eraseFromParent(); - } - - InsertedVal = SingularValue; - - // Drop the entries we added in IncomingPredInfo to restore the stack. - IncomingPredInfo.erase(IncomingPredInfo.begin()+FirstPredInfoEntry, - IncomingPredInfo.end()); - return InsertedVal; + for (unsigned p = 0; p != Info->NumPreds; ++p) { + MachineBasicBlock *Pred = Preds[p]; + // Check if BBMap already has a BBInfo for the predecessor block. + BBMapTy::value_type &BBMapBucket = BBMap->FindAndConstruct(Pred); + if (BBMapBucket.second) { + Info->Preds[p] = BBMapBucket.second; + continue; + } + + // Create a new BBInfo for the predecessor. + unsigned PredVal = AvailableVals.lookup(Pred); + BBInfo *PredInfo = new (*Allocator) BBInfo(Pred, PredVal); + BBMapBucket.second = PredInfo; + Info->Preds[p] = PredInfo; + + if (PredInfo->AvailableVal) { + RootList.push_back(PredInfo); + continue; + } + WorkList.push_back(PredInfo); + } } + // Now that we know what blocks are backwards-reachable from the starting + // block, do a forward depth-first traversal to assign postorder numbers + // to those blocks. + BBInfo *PseudoEntry = new (*Allocator) BBInfo(0, 0); + unsigned BlkNum = 1; + + // Initialize the worklist with the roots from the backward traversal. + while (!RootList.empty()) { + Info = RootList.pop_back_val(); + Info->IDom = PseudoEntry; + Info->BlkNum = -1; + WorkList.push_back(Info); + } + + while (!WorkList.empty()) { + Info = WorkList.back(); + + if (Info->BlkNum == -2) { + // All the successors have been handled; assign the postorder number. + Info->BlkNum = BlkNum++; + // If not a root, put it on the BlockList. + if (!Info->AvailableVal) + BlockList->push_back(Info); + WorkList.pop_back(); + continue; + } - // Otherwise, we do need a PHI: insert one now if we don't already have one. - MachineInstr *InsertedPHI; - if (InsertedVal == 0) { - MachineBasicBlock::iterator Loc = BB->empty() ? BB->end() : BB->front(); - InsertedPHI = InsertNewDef(TargetOpcode::PHI, BB, Loc, - VRC, MRI, TII); - InsertedVal = InsertedPHI->getOperand(0).getReg(); - } else { - InsertedPHI = MRI->getVRegDef(InsertedVal); + // Leave this entry on the worklist, but set its BlkNum to mark that its + // successors have been put on the worklist. When it returns to the top + // the list, after handling its successors, it will be assigned a number. + Info->BlkNum = -2; + + // Add unvisited successors to the work list. + for (MachineBasicBlock::succ_iterator SI = Info->BB->succ_begin(), + E = Info->BB->succ_end(); SI != E; ++SI) { + BBInfo *SuccInfo = (*BBMap)[*SI]; + if (!SuccInfo || SuccInfo->BlkNum) + continue; + SuccInfo->BlkNum = -1; + WorkList.push_back(SuccInfo); + } } + PseudoEntry->BlkNum = BlkNum; +} - // Fill in all the predecessors of the PHI. - MachineInstrBuilder MIB(InsertedPHI); - for (IncomingPredInfoTy::iterator I = - IncomingPredInfo.begin()+FirstPredInfoEntry, - E = IncomingPredInfo.end(); I != E; ++I) - MIB.addReg(I->second).addMBB(I->first); - - // Drop the entries we added in IncomingPredInfo to restore the stack. - IncomingPredInfo.erase(IncomingPredInfo.begin()+FirstPredInfoEntry, - IncomingPredInfo.end()); +/// IntersectDominators - This is the dataflow lattice "meet" operation for +/// finding dominators. Given two basic blocks, it walks up the dominator +/// tree until it finds a common dominator of both. It uses the postorder +/// number of the blocks to determine how to do that. +static MachineSSAUpdater::BBInfo * +IntersectDominators(MachineSSAUpdater::BBInfo *Blk1, + MachineSSAUpdater::BBInfo *Blk2) { + while (Blk1 != Blk2) { + while (Blk1->BlkNum < Blk2->BlkNum) { + Blk1 = Blk1->IDom; + if (!Blk1) + return Blk2; + } + while (Blk2->BlkNum < Blk1->BlkNum) { + Blk2 = Blk2->IDom; + if (!Blk2) + return Blk1; + } + } + return Blk1; +} + +/// FindDominators - Calculate the dominator tree for the subset of the CFG +/// corresponding to the basic blocks on the BlockList. This uses the +/// algorithm from: "A Simple, Fast Dominance Algorithm" by Cooper, Harvey and +/// Kennedy, published in Software--Practice and Experience, 2001, 4:1-10. +/// Because the CFG subset does not include any edges leading into blocks that +/// define the value, the results are not the usual dominator tree. The CFG +/// subset has a single pseudo-entry node with edges to a set of root nodes +/// for blocks that define the value. The dominators for this subset CFG are +/// not the standard dominators but they are adequate for placing PHIs within +/// the subset CFG. +void MachineSSAUpdater::FindDominators(BlockListTy *BlockList) { + bool Changed; + do { + Changed = false; + // Iterate over the list in reverse order, i.e., forward on CFG edges. + for (BlockListTy::reverse_iterator I = BlockList->rbegin(), + E = BlockList->rend(); I != E; ++I) { + BBInfo *Info = *I; + + // Start with the first predecessor. + assert(Info->NumPreds > 0 && "unreachable block"); + BBInfo *NewIDom = Info->Preds[0]; + + // Iterate through the block's other predecessors. + for (unsigned p = 1; p != Info->NumPreds; ++p) { + BBInfo *Pred = Info->Preds[p]; + NewIDom = IntersectDominators(NewIDom, Pred); + } + + // Check if the IDom value has changed. + if (NewIDom != Info->IDom) { + Info->IDom = NewIDom; + Changed = true; + } + } + } while (Changed); +} + +/// IsDefInDomFrontier - Search up the dominator tree from Pred to IDom for +/// any blocks containing definitions of the value. If one is found, then the +/// successor of Pred is in the dominance frontier for the definition, and +/// this function returns true. +static bool IsDefInDomFrontier(const MachineSSAUpdater::BBInfo *Pred, + const MachineSSAUpdater::BBInfo *IDom) { + for (; Pred != IDom; Pred = Pred->IDom) { + if (Pred->DefBB == Pred) + return true; + } + return false; +} + +/// FindPHIPlacement - PHIs are needed in the iterated dominance frontiers of +/// the known definitions. Iteratively add PHIs in the dom frontiers until +/// nothing changes. Along the way, keep track of the nearest dominating +/// definitions for non-PHI blocks. +void MachineSSAUpdater::FindPHIPlacement(BlockListTy *BlockList) { + bool Changed; + do { + Changed = false; + // Iterate over the list in reverse order, i.e., forward on CFG edges. + for (BlockListTy::reverse_iterator I = BlockList->rbegin(), + E = BlockList->rend(); I != E; ++I) { + BBInfo *Info = *I; + + // If this block already needs a PHI, there is nothing to do here. + if (Info->DefBB == Info) + continue; + + // Default to use the same def as the immediate dominator. + BBInfo *NewDefBB = Info->IDom->DefBB; + for (unsigned p = 0; p != Info->NumPreds; ++p) { + if (IsDefInDomFrontier(Info->Preds[p], Info->IDom)) { + // Need a PHI here. + NewDefBB = Info; + break; + } + } + + // Check if anything changed. + if (NewDefBB != Info->DefBB) { + Info->DefBB = NewDefBB; + Changed = true; + } + } + } while (Changed); +} + +/// FindAvailableVal - If this block requires a PHI, first check if an existing +/// PHI matches the PHI placement and reaching definitions computed earlier, +/// and if not, create a new PHI. Visit all the block's predecessors to +/// calculate the available value for each one and fill in the incoming values +/// for a new PHI. +void MachineSSAUpdater::FindAvailableVals(BlockListTy *BlockList) { + AvailableValsTy &AvailableVals = getAvailableVals(AV); + + // Go through the worklist in forward order (i.e., backward through the CFG) + // and check if existing PHIs can be used. If not, create empty PHIs where + // they are needed. + for (BlockListTy::iterator I = BlockList->begin(), E = BlockList->end(); + I != E; ++I) { + BBInfo *Info = *I; + // Check if there needs to be a PHI in BB. + if (Info->DefBB != Info) + continue; + + // Look for an existing PHI. + FindExistingPHI(Info->BB, BlockList); + if (Info->AvailableVal) + continue; + + MachineBasicBlock::iterator Loc = + Info->BB->empty() ? Info->BB->end() : Info->BB->front(); + MachineInstr *InsertedPHI = InsertNewDef(TargetOpcode::PHI, Info->BB, Loc, + VRC, MRI, TII); + unsigned PHI = InsertedPHI->getOperand(0).getReg(); + Info->AvailableVal = PHI; + AvailableVals[Info->BB] = PHI; + } + + // Now go back through the worklist in reverse order to fill in the arguments + // for any new PHIs added in the forward traversal. + for (BlockListTy::reverse_iterator I = BlockList->rbegin(), + E = BlockList->rend(); I != E; ++I) { + BBInfo *Info = *I; + + if (Info->DefBB != Info) { + // Record the available value at join nodes to speed up subsequent + // uses of this SSAUpdater for the same value. + if (Info->NumPreds > 1) + AvailableVals[Info->BB] = Info->DefBB->AvailableVal; + continue; + } + + // Check if this block contains a newly added PHI. + unsigned PHI = Info->AvailableVal; + MachineInstr *InsertedPHI = MRI->getVRegDef(PHI); + if (!InsertedPHI->isPHI() || InsertedPHI->getNumOperands() > 1) + continue; + + // Iterate through the block's predecessors. + MachineInstrBuilder MIB(InsertedPHI); + for (unsigned p = 0; p != Info->NumPreds; ++p) { + BBInfo *PredInfo = Info->Preds[p]; + MachineBasicBlock *Pred = PredInfo->BB; + // Skip to the nearest preceding definition. + if (PredInfo->DefBB != PredInfo) + PredInfo = PredInfo->DefBB; + MIB.addReg(PredInfo->AvailableVal).addMBB(Pred); + } - // See if the PHI node can be merged to a single value. This can happen in - // loop cases when we get a PHI of itself and one other value. - if (unsigned ConstVal = InsertedPHI->isConstantValuePHI()) { - MRI->replaceRegWith(InsertedVal, ConstVal); - InsertedPHI->eraseFromParent(); - InsertedVal = ConstVal; - } else { DEBUG(dbgs() << " Inserted PHI: " << *InsertedPHI << "\n"); // If the client wants to know about all new instructions, tell it. if (InsertedPHIs) InsertedPHIs->push_back(InsertedPHI); } +} + +/// FindExistingPHI - Look through the PHI nodes in a block to see if any of +/// them match what is needed. +void MachineSSAUpdater::FindExistingPHI(MachineBasicBlock *BB, + BlockListTy *BlockList) { + for (MachineBasicBlock::iterator BBI = BB->begin(), BBE = BB->end(); + BBI != BBE && BBI->isPHI(); ++BBI) { + if (CheckIfPHIMatches(BBI)) { + RecordMatchingPHI(BBI); + break; + } + // Match failed: clear all the PHITag values. + for (BlockListTy::iterator I = BlockList->begin(), E = BlockList->end(); + I != E; ++I) + (*I)->PHITag = 0; + } +} + +/// CheckIfPHIMatches - Check if a PHI node matches the placement and values +/// in the BBMap. +bool MachineSSAUpdater::CheckIfPHIMatches(MachineInstr *PHI) { + BBMapTy *BBMap = getBBMap(BM); + SmallVector WorkList; + WorkList.push_back(PHI); + + // Mark that the block containing this PHI has been visited. + (*BBMap)[PHI->getParent()]->PHITag = PHI; + + while (!WorkList.empty()) { + PHI = WorkList.pop_back_val(); + + // Iterate through the PHI's incoming values. + for (unsigned i = 1, e = PHI->getNumOperands(); i != e; i += 2) { + unsigned IncomingVal = PHI->getOperand(i).getReg(); + BBInfo *PredInfo = (*BBMap)[PHI->getOperand(i+1).getMBB()]; + // Skip to the nearest preceding definition. + if (PredInfo->DefBB != PredInfo) + PredInfo = PredInfo->DefBB; + + // Check if it matches the expected value. + if (PredInfo->AvailableVal) { + if (IncomingVal == PredInfo->AvailableVal) + continue; + return false; + } + + // Check if the value is a PHI in the correct block. + MachineInstr *IncomingPHIVal = MRI->getVRegDef(IncomingVal); + if (!IncomingPHIVal->isPHI() || + IncomingPHIVal->getParent() != PredInfo->BB) + return false; + + // If this block has already been visited, check if this PHI matches. + if (PredInfo->PHITag) { + if (IncomingPHIVal == PredInfo->PHITag) + continue; + return false; + } + PredInfo->PHITag = IncomingPHIVal; + + WorkList.push_back(IncomingPHIVal); + } + } + return true; +} + +/// RecordMatchingPHI - For a PHI node that matches, record it and its input +/// PHIs in both the BBMap and the AvailableVals mapping. +void MachineSSAUpdater::RecordMatchingPHI(MachineInstr *PHI) { + BBMapTy *BBMap = getBBMap(BM); + AvailableValsTy &AvailableVals = getAvailableVals(AV); + SmallVector WorkList; + WorkList.push_back(PHI); - return InsertedVal; + // Record this PHI. + MachineBasicBlock *BB = PHI->getParent(); + AvailableVals[BB] = PHI->getOperand(0).getReg(); + (*BBMap)[BB]->AvailableVal = PHI->getOperand(0).getReg(); + + while (!WorkList.empty()) { + PHI = WorkList.pop_back_val(); + + // Iterate through the PHI's incoming values. + for (unsigned i = 1, e = PHI->getNumOperands(); i != e; i += 2) { + unsigned IncomingVal = PHI->getOperand(i).getReg(); + MachineInstr *IncomingPHIVal = MRI->getVRegDef(IncomingVal); + if (!IncomingPHIVal->isPHI()) continue; + BB = IncomingPHIVal->getParent(); + BBInfo *Info = (*BBMap)[BB]; + if (!Info || Info->AvailableVal) + continue; + + // Record the PHI and add it to the worklist. + AvailableVals[BB] = IncomingVal; + Info->AvailableVal = IncomingVal; + WorkList.push_back(IncomingPHIVal); + } + } } From sabre at nondot.org Mon Apr 26 12:42:18 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 17:42:18 -0000 Subject: [llvm-commits] [llvm] r102354 - /llvm/trunk/docs/ReleaseNotes.html Message-ID: <20100426174218.D3CF1312800A@llvm.org> Author: lattner Date: Mon Apr 26 12:42:18 2010 New Revision: 102354 URL: http://llvm.org/viewvc/llvm-project?rev=102354&view=rev Log: wrap some long lines. Modified: llvm/trunk/docs/ReleaseNotes.html Modified: llvm/trunk/docs/ReleaseNotes.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/ReleaseNotes.html?rev=102354&r1=102353&r2=102354&view=diff ============================================================================== --- llvm/trunk/docs/ReleaseNotes.html (original) +++ llvm/trunk/docs/ReleaseNotes.html Mon Apr 26 12:42:18 2010 @@ -115,17 +115,36 @@
-

Clang is an LLVM front end for the C, C++, and Objective-C languages. Clang aims to provide a better user experience through expressive diagnostics, a high level of conformance to language standards, fast compilation, and low memory use. Like LLVM, Clang provides a modular, library-based architecture that makes it suitable for creating or integrating with other development tools. Clang is considered a production-quality compiler for C and Objective-C on x86 (32- and 64-bit).

+

Clang is an LLVM front end for the C, +C++, and Objective-C languages. Clang aims to provide a better user experience +through expressive diagnostics, a high level of conformance to language +standards, fast compilation, and low memory use. Like LLVM, Clang provides a +modular, library-based architecture that makes it suitable for creating or +integrating with other development tools. Clang is considered a +production-quality compiler for C and Objective-C on x86 (32- and 64-bit).

In the LLVM 2.7 time-frame, the Clang team has made many improvements:

    -
  • C++ Support: Clang is now capable of self-hosting! While still alpha-quality, Clang's C++ support has matured enough to build LLVM and Clang, and C++ is now enabled by default. See the Clang C++ compatibility page for common C++ migration issues.
    • - -
  • Objective-C: Clang now includes experimental support for an updated Objective-C ABI on non-Darwin platforms. This includes support for non-fragile instance variables and accelerated proxies, as well as greater potential for future optimisations. The new ABI is used when compiling with the -fobjc-nonfragile-abi and -fgnu-runtime options. Code compiled with these options may be mixed with code compiled with GCC or clang using the old GNU ABI, but requires the libobjc2 runtime from the GNUstep project.
    • - -
  • New warnings: Clang contains a number of new warnings, including control-flow warnings (unreachable code, missing return statements in a non-void function, etc.), sign-comparison warnings, and improved format-string warnings.
    • +
  • C++ Support: Clang is now capable of self-hosting! While still +alpha-quality, Clang's C++ support has matured enough to build LLVM and Clang, +and C++ is now enabled by default. See the Clang C++ compatibility +page for common C++ migration issues.
    • + +
  • Objective-C: Clang now includes experimental support for an updated +Objective-C ABI on non-Darwin platforms. This includes support for non-fragile +instance variables and accelerated proxies, as well as greater potential for +future optimisations. The new ABI is used when compiling with the +-fobjc-nonfragile-abi and -fgnu-runtime options. Code compiled with these +options may be mixed with code compiled with GCC or clang using the old GNU ABI, +but requires the libobjc2 runtime from the GNUstep project.
    • + +
  • New warnings: Clang contains a number of new warnings, including +control-flow warnings (unreachable code, missing return statements in a +non-void function, etc.), sign-comparison warnings, and improved +format-string warnings.
  • CIndex API and Python bindings: Clang now includes a C API as part of the CIndex library. Although we may make some changes to the API in the future, it From sabre at nondot.org Mon Apr 26 13:21:23 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 18:21:23 -0000 Subject: [llvm-commits] [llvm] r102358 - in /llvm/trunk: lib/Transforms/Scalar/SCCP.cpp test/Transforms/SCCP/undef-resolve.ll Message-ID: <20100426182123.95D1D312800A@llvm.org> Author: lattner Date: Mon Apr 26 13:21:23 2010 New Revision: 102358 URL: http://llvm.org/viewvc/llvm-project?rev=102358&view=rev Log: fix PR6940: sitofp(undef) folds to 0.0, not undef. Modified: llvm/trunk/lib/Transforms/Scalar/SCCP.cpp llvm/trunk/test/Transforms/SCCP/undef-resolve.ll Modified: llvm/trunk/lib/Transforms/Scalar/SCCP.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/SCCP.cpp?rev=102358&r1=102357&r2=102358&view=diff ============================================================================== --- llvm/trunk/lib/Transforms/Scalar/SCCP.cpp (original) +++ llvm/trunk/lib/Transforms/Scalar/SCCP.cpp Mon Apr 26 13:21:23 2010 @@ -1452,6 +1452,8 @@ // After a zero extend, we know the top part is zero. SExt doesn't have // to be handled here, because we don't know whether the top part is 1's // or 0's. + case Instruction::SIToFP: // some FP values are not possible, just use 0. + case Instruction::UIToFP: // some FP values are not possible, just use 0. markForcedConstant(I, Constant::getNullValue(ITy)); return true; case Instruction::Mul: Modified: llvm/trunk/test/Transforms/SCCP/undef-resolve.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SCCP/undef-resolve.ll?rev=102358&r1=102357&r2=102358&view=diff ============================================================================== --- llvm/trunk/test/Transforms/SCCP/undef-resolve.ll (original) +++ llvm/trunk/test/Transforms/SCCP/undef-resolve.ll Mon Apr 26 13:21:23 2010 @@ -1,8 +1,19 @@ ; RUN: opt %s -sccp -S | FileCheck %s + + +; PR6940 +define double @test1() { + %t = sitofp i32 undef to double + ret double %t +; CHECK: @test1 +; CHECK: ret double 0.0 +} + + ; rdar://7832370 ; Check that lots of stuff doesn't get turned into undef. - -define i32 @main() nounwind readnone ssp { +define i32 @test2() nounwind readnone ssp { +; CHECK: @test2 init: br label %control.outer.outer From sabre at nondot.org Mon Apr 26 13:30:45 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 18:30:45 -0000 Subject: [llvm-commits] [llvm] r102359 - in /llvm/trunk: lib/CodeGen/AsmPrinter/AsmPrinter.cpp test/CodeGen/X86/alignment.ll test/CodeGen/X86/unaligned-load.ll test/FrontendC/cstring-align.c Message-ID: <20100426183045.CD5F5312800A@llvm.org> Author: lattner Date: Mon Apr 26 13:30:45 2010 New Revision: 102359 URL: http://llvm.org/viewvc/llvm-project?rev=102359&view=rev Log: Revert r102300/102301, which serious broke objc apps. Removed: llvm/trunk/test/CodeGen/X86/alignment.ll Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp llvm/trunk/test/CodeGen/X86/unaligned-load.ll llvm/trunk/test/FrontendC/cstring-align.c Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp?rev=102359&r1=102358&r2=102359&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp (original) +++ llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp Mon Apr 26 13:30:45 2010 @@ -285,7 +285,7 @@ OutStreamer.SwitchSection(TheSection); EmitLinkage(GV->getLinkage(), GVSym); - EmitAlignment(AlignLog, GV, AlignLog); + EmitAlignment(AlignLog, GV); if (isVerbose()) { WriteAsOperand(OutStreamer.GetCommentOS(), GV, @@ -987,7 +987,7 @@ unsigned Align = Log2_32(TD->getPointerPrefAlignment()); if (GV->getName() == "llvm.global_ctors") { OutStreamer.SwitchSection(getObjFileLowering().getStaticCtorSection()); - EmitAlignment(Align); + EmitAlignment(Align, 0); EmitXXStructorList(GV->getInitializer()); if (TM.getRelocationModel() == Reloc::Static && @@ -1001,7 +1001,7 @@ if (GV->getName() == "llvm.global_dtors") { OutStreamer.SwitchSection(getObjFileLowering().getStaticDtorSection()); - EmitAlignment(Align); + EmitAlignment(Align, 0); EmitXXStructorList(GV->getInitializer()); if (TM.getRelocationModel() == Reloc::Static && Removed: llvm/trunk/test/CodeGen/X86/alignment.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/alignment.ll?rev=102358&view=auto ============================================================================== --- llvm/trunk/test/CodeGen/X86/alignment.ll (original) +++ llvm/trunk/test/CodeGen/X86/alignment.ll (removed) @@ -1,16 +0,0 @@ -; RUN: llc %s -o - -mtriple=x86_64-linux-gnu | FileCheck %s - -; This can get rounded up to the preferred alignment (16). -; PR6921 - at GlobalA = global { [384 x i8] } zeroinitializer, align 8 - -; CHECK: .bss -; CHECK: .globl GlobalA -; CHECK: .align 16 -; CHECK: GlobalA: -; CHECK: .zero 384 - -; Common variables should also get rounded up to the preferred alignment (16). - at GlobalB = common global { [384 x i8] } zeroinitializer, align 8 - -; CHECK: .comm GlobalB,384,16 \ No newline at end of file Modified: llvm/trunk/test/CodeGen/X86/unaligned-load.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/unaligned-load.ll?rev=102359&r1=102358&r2=102359&view=diff ============================================================================== --- llvm/trunk/test/CodeGen/X86/unaligned-load.ll (original) +++ llvm/trunk/test/CodeGen/X86/unaligned-load.ll Mon Apr 26 13:30:45 2010 @@ -28,9 +28,8 @@ declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind -; CORE2: .section -; CORE2: .align 4 +; CORE2: .align 3 ; CORE2-NEXT: _.str1: ; CORE2-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING" -; CORE2: .align 4 +; CORE2: .align 3 ; CORE2-NEXT: _.str3: Modified: llvm/trunk/test/FrontendC/cstring-align.c URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/FrontendC/cstring-align.c?rev=102359&r1=102358&r2=102359&view=diff ============================================================================== --- llvm/trunk/test/FrontendC/cstring-align.c (original) +++ llvm/trunk/test/FrontendC/cstring-align.c Mon Apr 26 13:30:45 2010 @@ -1,5 +1,6 @@ // RUN: %llvmgcc %s -c -Os -m32 -emit-llvm -o - | llc -march=x86 -mtriple=i386-apple-darwin10 | FileCheck %s -check-prefix=DARWIN32 // RUN: %llvmgcc %s -c -Os -m64 -emit-llvm -o - | llc -march=x86-64 -mtriple=x86_64-apple-darwin10 | FileCheck %s -check-prefix=DARWIN64 +// XFAIL: * // XTARGET: darwin extern void func(const char *, const char *); @@ -8,10 +9,10 @@ func("%s: the function name", __func__); } -// DARWIN64: .align 4 +// DARWIN64: .align 3 // DARWIN64: ___func__. // DARWIN64: .asciz "long_function_name" -// DARWIN32: .align 4 +// DARWIN32: .align 2 // DARWIN32: ___func__. // DARWIN32: .asciz "long_function_name" From sabre at nondot.org Mon Apr 26 13:31:13 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 18:31:13 -0000 Subject: [llvm-commits] [test-suite] r102360 - /test-suite/trunk/SingleSource/UnitTests/ObjC/trivial-interface.m Message-ID: <20100426183113.E24FC312800A@llvm.org> Author: lattner Date: Mon Apr 26 13:31:13 2010 New Revision: 102360 URL: http://llvm.org/viewvc/llvm-project?rev=102360&view=rev Log: add a silly testcase. Added: test-suite/trunk/SingleSource/UnitTests/ObjC/trivial-interface.m Added: test-suite/trunk/SingleSource/UnitTests/ObjC/trivial-interface.m URL: http://llvm.org/viewvc/llvm-project/test-suite/trunk/SingleSource/UnitTests/ObjC/trivial-interface.m?rev=102360&view=auto ============================================================================== --- test-suite/trunk/SingleSource/UnitTests/ObjC/trivial-interface.m (added) +++ test-suite/trunk/SingleSource/UnitTests/ObjC/trivial-interface.m Mon Apr 26 13:31:13 2010 @@ -0,0 +1,13 @@ +#include + + at interface BaseNode : NSObject { } + + at end + + at implementation BaseNode + + at end + +int main(int argc, char **argv) { + return 0; +} From evan.cheng at apple.com Mon Apr 26 13:37:21 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 18:37:21 -0000 Subject: [llvm-commits] [llvm] r102361 - /llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Message-ID: <20100426183721.9DAFA312800A@llvm.org> Author: evancheng Date: Mon Apr 26 13:37:21 2010 New Revision: 102361 URL: http://llvm.org/viewvc/llvm-project?rev=102361&view=rev Log: Re-enable 102323 with fix: do not update dbg_value's with incorrect frame indices when the live interval are being re-materialized. Modified: llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Modified: llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp?rev=102361&r1=102360&r2=102361&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp (original) +++ llvm/trunk/lib/CodeGen/LiveIntervalAnalysis.cpp Mon Apr 26 13:37:21 2010 @@ -1296,28 +1296,25 @@ MachineOperand &O = ri.getOperand(); ++ri; if (MI->isDebugValue()) { -#if 0 - // Disabled temporarily. // Modify DBG_VALUE now that the value is in a spill slot. - uint64_t Offset = MI->getOperand(1).getImm(); - const MDNode *MDPtr = MI->getOperand(2).getMetadata(); - DebugLoc DL = MI->getDebugLoc(); - MachineInstr *NewDV = tii_->emitFrameIndexDebugValue(*mf_, Slot, Offset, - MDPtr, DL); - if (NewDV) { - DEBUG(dbgs() << "Modifying debug info due to spill:" << "\t" << *MI); - ReplaceMachineInstrInMaps(MI, NewDV); - MachineBasicBlock *MBB = MI->getParent(); - MBB->insert(MBB->erase(MI), NewDV); - } else { -#endif - DEBUG(dbgs() << "Removing debug info due to spill:" << "\t" << *MI); - RemoveMachineInstrFromMaps(MI); - vrm.RemoveMachineInstrFromMaps(MI); - MI->eraseFromParent(); -#if 0 + if (Slot == VirtRegMap::NO_STACK_SLOT) { + uint64_t Offset = MI->getOperand(1).getImm(); + const MDNode *MDPtr = MI->getOperand(2).getMetadata(); + DebugLoc DL = MI->getDebugLoc(); + if (MachineInstr *NewDV = tii_->emitFrameIndexDebugValue(*mf_, Slot, + Offset, MDPtr, DL)) { + DEBUG(dbgs() << "Modifying debug info due to spill:" << "\t" << *MI); + ReplaceMachineInstrInMaps(MI, NewDV); + MachineBasicBlock *MBB = MI->getParent(); + MBB->insert(MBB->erase(MI), NewDV); + continue; + } } -#endif + + DEBUG(dbgs() << "Removing debug info due to spill:" << "\t" << *MI); + RemoveMachineInstrFromMaps(MI); + vrm.RemoveMachineInstrFromMaps(MI); + MI->eraseFromParent(); continue; } assert(!O.isImplicit() && "Spilling register that's used as implicit use?"); From sabre at nondot.org Mon Apr 26 13:46:46 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 18:46:46 -0000 Subject: [llvm-commits] [llvm] r102365 - in /llvm/trunk: lib/CodeGen/AsmPrinter/AsmPrinter.cpp test/CodeGen/X86/alignment.ll test/CodeGen/X86/unaligned-load.ll Message-ID: <20100426184646.49A48312800A@llvm.org> Author: lattner Date: Mon Apr 26 13:46:46 2010 New Revision: 102365 URL: http://llvm.org/viewvc/llvm-project?rev=102365&view=rev Log: fix PR6921 a different way. Intead of increasing the alignment of globals with a specified alignment, we fix common variables to obey their alignment. Add a comment explaining why this behavior is important. Added: llvm/trunk/test/CodeGen/X86/alignment.ll Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp llvm/trunk/test/CodeGen/X86/unaligned-load.ll Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp?rev=102365&r1=102364&r2=102365&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp (original) +++ llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp Mon Apr 26 13:46:46 2010 @@ -228,7 +228,15 @@ const TargetData *TD = TM.getTargetData(); unsigned Size = TD->getTypeAllocSize(GV->getType()->getElementType()); - unsigned AlignLog = TD->getPreferredAlignmentLog(GV); + + // If the alignment is specified, we *must* obey it. Overaligning a global + // with a specified alignment is a prompt way to break globals emitted to + // sections and expected to be contiguous (e.g. ObjC metadata). + unsigned AlignLog; + if (unsigned GVAlign = GV->getAlignment()) + AlignLog = Log2_32(GVAlign); + else + AlignLog = TD->getPreferredAlignmentLog(GV); // Handle common and BSS local symbols (.lcomm). if (GVKind.isCommon() || GVKind.isBSSLocal()) { Added: llvm/trunk/test/CodeGen/X86/alignment.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/alignment.ll?rev=102365&view=auto ============================================================================== --- llvm/trunk/test/CodeGen/X86/alignment.ll (added) +++ llvm/trunk/test/CodeGen/X86/alignment.ll Mon Apr 26 13:46:46 2010 @@ -0,0 +1,18 @@ +; RUN: llc %s -o - -mtriple=x86_64-linux-gnu | FileCheck %s + +; This cannot get rounded up to the preferred alignment (16) if they have an +; explicit alignment specified. + at GlobalA = global { [384 x i8] } zeroinitializer, align 8 + +; CHECK: .bss +; CHECK: .globl GlobalA +; CHECK: .align 8 +; CHECK: GlobalA: +; CHECK: .zero 384 + +; Common variables should not get rounded up to the preferred alignment (16) if +; they have an explicit alignment specified. +; PR6921 + at GlobalB = common global { [384 x i8] } zeroinitializer, align 8 + +; CHECK: .comm GlobalB,384,8 \ No newline at end of file Modified: llvm/trunk/test/CodeGen/X86/unaligned-load.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/unaligned-load.ll?rev=102365&r1=102364&r2=102365&view=diff ============================================================================== --- llvm/trunk/test/CodeGen/X86/unaligned-load.ll (original) +++ llvm/trunk/test/CodeGen/X86/unaligned-load.ll Mon Apr 26 13:46:46 2010 @@ -28,6 +28,7 @@ declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind +; CORE2: .section ; CORE2: .align 3 ; CORE2-NEXT: _.str1: ; CORE2-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING" From evan.cheng at apple.com Mon Apr 26 14:06:11 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 19:06:11 -0000 Subject: [llvm-commits] [llvm] r102366 - in /llvm/trunk/lib/Target/X86: X86ISelLowering.cpp X86ISelLowering.h Message-ID: <20100426190611.A8CB6312800A@llvm.org> Author: evancheng Date: Mon Apr 26 14:06:11 2010 New Revision: 102366 URL: http://llvm.org/viewvc/llvm-project?rev=102366&view=rev Log: Promoting 16-bit cmp / test aren't free. Don't do it. Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp llvm/trunk/lib/Target/X86/X86ISelLowering.h Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=102366&r1=102365&r2=102366&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original) +++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Mon Apr 26 14:06:11 2010 @@ -5887,33 +5887,10 @@ return DAG.getNode(X86ISD::FOR, dl, VT, Val, SignBit); } -// getSetCCPromoteOpcode - Return the opcode that should be used to promote -// operands of a setcc. FIXME: See DAGTypeLegalizer::PromoteSetCCOperands. -static unsigned getSetCCPromoteOpcode(ISD::CondCode CC) { - switch (CC) { - default: return 0; - case ISD::SETEQ: - case ISD::SETNE: - case ISD::SETUGE: - case ISD::SETUGT: - case ISD::SETULE: - case ISD::SETULT: - // ALL of these operations will work if we either sign or zero extend - // the operands (including the unsigned comparisons!). Zero extend is - // usually a simpler/cheaper operation, so prefer it. - return ISD::ZERO_EXTEND; - case ISD::SETGE: - case ISD::SETGT: - case ISD::SETLT: - case ISD::SETLE: - return ISD::SIGN_EXTEND; - } -} - /// Emit nodes that will be selected as "test Op0,Op0", or something /// equivalent. SDValue X86TargetLowering::EmitTest(SDValue Op, unsigned X86CC, - ISD::CondCode CC, SelectionDAG &DAG) const { + SelectionDAG &DAG) const { DebugLoc dl = Op.getDebugLoc(); // CF and OF aren't always set the way we want. Determine which @@ -6037,13 +6014,6 @@ } // Otherwise just emit a CMP with 0, which is the TEST pattern. - EVT PVT; - if (Subtarget->shouldPromote16Bit() && Op.getValueType() == MVT::i16 && - (isa(Op) || IsDesirableToPromoteOp(Op, PVT))) { - unsigned POpc = getSetCCPromoteOpcode(CC); - if (POpc) - Op = DAG.getNode(POpc, Op.getDebugLoc(), MVT::i32, Op); - } return DAG.getNode(X86ISD::CMP, dl, MVT::i32, Op, DAG.getConstant(0, Op.getValueType())); } @@ -6051,22 +6021,12 @@ /// Emit nodes that will be selected as "cmp Op0,Op1", or something /// equivalent. SDValue X86TargetLowering::EmitCmp(SDValue Op0, SDValue Op1, unsigned X86CC, - ISD::CondCode CC, SelectionDAG &DAG) const { + SelectionDAG &DAG) const { if (ConstantSDNode *C = dyn_cast(Op1)) if (C->getAPIntValue() == 0) - return EmitTest(Op0, X86CC, CC, DAG); + return EmitTest(Op0, X86CC, DAG); DebugLoc dl = Op0.getDebugLoc(); - EVT PVT; - if (Subtarget->shouldPromote16Bit() && Op0.getValueType() == MVT::i16 && - (isa(Op0) || IsDesirableToPromoteOp(Op0, PVT)) && - (isa(Op1) || IsDesirableToPromoteOp(Op1, PVT))) { - unsigned POpc = getSetCCPromoteOpcode(CC); - if (POpc) { - Op0 = DAG.getNode(POpc, Op0.getDebugLoc(), MVT::i32, Op0); - Op1 = DAG.getNode(POpc, Op1.getDebugLoc(), MVT::i32, Op1); - } - } return DAG.getNode(X86ISD::CMP, dl, MVT::i32, Op0, Op1); } @@ -6168,7 +6128,7 @@ if (X86CC == X86::COND_INVALID) return SDValue(); - SDValue Cond = EmitCmp(Op0, Op1, X86CC, CC, DAG); + SDValue Cond = EmitCmp(Op0, Op1, X86CC, DAG); // Use sbb x, x to materialize carry bit into a GPR. if (X86CC == X86::COND_B) @@ -6401,7 +6361,7 @@ if (addTest) { CC = DAG.getConstant(X86::COND_NE, MVT::i8); - Cond = EmitTest(Cond, X86::COND_NE, ISD::SETNE, DAG); + Cond = EmitTest(Cond, X86::COND_NE, DAG); } // X86ISD::CMOV means set the result (which is operand 1) to the RHS if @@ -6575,7 +6535,7 @@ if (addTest) { CC = DAG.getConstant(X86::COND_NE, MVT::i8); - Cond = EmitTest(Cond, X86::COND_NE, ISD::SETNE, DAG); + Cond = EmitTest(Cond, X86::COND_NE, DAG); } return DAG.getNode(X86ISD::BRCOND, dl, Op.getValueType(), Chain, Dest, CC, Cond); Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.h?rev=102366&r1=102365&r2=102366&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.h (original) +++ llvm/trunk/lib/Target/X86/X86ISelLowering.h Mon Apr 26 14:06:11 2010 @@ -815,12 +815,11 @@ /// Emit nodes that will be selected as "test Op0,Op0", or something /// equivalent, for use with the given x86 condition code. - SDValue EmitTest(SDValue Op0, unsigned X86CC, ISD::CondCode CC, - SelectionDAG &DAG) const; + SDValue EmitTest(SDValue Op0, unsigned X86CC, SelectionDAG &DAG) const; /// Emit nodes that will be selected as "cmp Op0,Op1", or something /// equivalent, for use with the given x86 condition code. - SDValue EmitCmp(SDValue Op0, SDValue Op1, unsigned X86CC, ISD::CondCode CC, + SDValue EmitCmp(SDValue Op0, SDValue Op1, unsigned X86CC, SelectionDAG &DAG) const; }; From jan_sjodin at yahoo.com Mon Apr 26 14:11:09 2010 From: jan_sjodin at yahoo.com (Jan Sjodin) Date: Mon, 26 Apr 2010 12:11:09 -0700 (PDT) Subject: [llvm-commits] Fix for assertion in DAGCombiner In-Reply-To: <805706E5-D6DB-41BE-B6F7-B985B60AD9AA@apple.com> References: <623530.48513.qm@web55607.mail.re4.yahoo.com> <805706E5-D6DB-41BE-B6F7-B985B60AD9AA@apple.com> Message-ID: <277854.61965.qm@web55602.mail.re4.yahoo.com> Below is one way of fixing the issue of sign extending a vector of smaller element types. I suppose it would be fairly trivial to include the case where the type is larger by replacing truncate with a second sign extend, but I wanted to get feedback on this code: Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp =================================================================== --- lib/CodeGen/SelectionDAG/DAGCombiner.cpp (revision 102340) +++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp (working copy) @@ -3495,20 +3495,34 @@ if (N0.getOpcode() == ISD::SETCC) { // sext(setcc) -> sext_in_reg(vsetcc) for vectors. - if (VT.isVector() && + // Only do this before legalize for now. + if (VT.isVector() && !LegalOperations) { + EVT N0VT = N0.getOperand(0).getValueType(); // We know that the # elements of the results is the same as the // # elements of the compare (and the # elements of the compare result // for that matter). Check to see that they are the same size. If so, // we know that the element size of the sext'd result matches the // element size of the compare operands. - VT.getSizeInBits() == N0.getOperand(0).getValueType().getSizeInBits() && - - // Only do this before legalize for now. - !LegalOperations) { - return DAG.getVSetCC(N->getDebugLoc(), VT, N0.getOperand(0), - N0.getOperand(1), - cast(N0.getOperand(2))->get()); - } + if(VT.getSizeInBits() == N0VT.getSizeInBits()) + return DAG.getVSetCC(N->getDebugLoc(), VT, N0.getOperand(0), + N0.getOperand(1), + cast(N0.getOperand(2))->get()); + // If the desired elements are smaller than the source elements we can + // use a matching integer vector type and then truncate + else if(VT.getSizeInBits() < N0VT.getSizeInBits()) { + EVT MatchingElementType = + EVT::getIntegerVT(*DAG.getContext(), + N0VT.getScalarType().getSizeInBits()); + EVT MatchingVectorType = + EVT::getVectorVT(*DAG.getContext(), MatchingElementType, + N0VT.getVectorNumElements()); + SDValue VsetCC = + DAG.getVSetCC(N->getDebugLoc(), MatchingVectorType, N0.getOperand(0), + N0.getOperand(1), + cast(N0.getOperand(2))->get()); + return DAG.getNode(ISD::TRUNCATE, N->getDebugLoc(), VT, VsetCC); + } + } // sext(setcc x, y, cc) -> (select_cc x, y, -1, 0, cc) unsigned ElementWidth = VT.getScalarType().getSizeInBits(); ----- Original Message ---- > From: Dan Gohman > To: Jan Sjodin > Cc: llvm-commits at cs.uiuc.edu > Sent: Fri, April 23, 2010 9:22:30 PM > Subject: Re: [llvm-commits] Fix for assertion in DAGCombiner > > On Apr 23, 2010, at 9:41 AM, Jan Sjodin wrote: > Small fix that > prevents an assertion in getConstant if VT is a vector type. > > > Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp > > =================================================================== > --- > lib/CodeGen/SelectionDAG/DAGCombiner.cpp (revision 102107) > > +++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp (working copy) > > @@ -3453,7 +3453,8 @@ > > // sext(setcc x, y, cc) > -> (select_cc x, y, -1, 0, cc) > SDValue NegOne = > > - > DAG.getConstant(APInt::getAllOnesValue(VT.getSizeInBits()), VT); > + > > DAG.getConstant(APInt::getAllOnesValue(VT.getScalarType().getSizeInBits()), > > + > VT); > SDValue SCC = > > SimplifySelectCC(N->getDebugLoc(), N0.getOperand(0), > N0.getOperand(1), > > NegOne, DAG.getConstant(0, VT), Thanks! This > is now applied (with a trivial edit for 80 columns). > > I was > going to use the example below, but there are still more errors to be fixed (see > below): > > ; ModuleID = 'minimal.bc' > target datalayout = > "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:6\ > > 4:64-f80:128:128" > target triple = "x86_64-pc-linux-gnu" > > > define void @myfunction(<3 x double>* %foo, <3 x double>* %bar, > <3 x i32>* %result) { > entry: > %foo.value = load <3 > x double>* %foo ; <<3 x > double>> [#uses=1] > %bar.value = load <3 x double>* > %bar ; <<3 x double>> > [#uses=1] > %cmp.i.i = fcmp oeq <3 x double> %foo.value, > %bar.value ; <<3 x i1>> [#uses=1] > %cmp.ext.i.i = sext > <3 x i1> %cmp.i.i to <3 x i32> ; <<3 x i32>> > [#uses=1] > store <3 x i32> %cmp.ext.i.i, <3 x i32>* > %result > ret void > } > > > llc > fails: > WidenVectorOperand op #0: 0xb7fc520: i8 = setcc 0xb7fbe38, > 0xb7fbec0, 0xb7fbf48 > [ID=0] > Do not know how to widen this > operator's operand! > UNREACHABLE executed at > LegalizeVectorTypes.cpp:1898! > > I will try and look into this as > well. On x86, support for vector SETCC is currently limited to cases > where the result is sign-extended to a vector of the same width as the SETCC > operand vector. In other words, if you change the <3 x i32> to <3 x > i64> here it'll work, because i64 is the same width as > double. Dan From evan.cheng at apple.com Mon Apr 26 14:16:00 2010 From: evan.cheng at apple.com (Evan Cheng) Date: Mon, 26 Apr 2010 19:16:00 -0000 Subject: [llvm-commits] [llvm] r102368 - /llvm/trunk/lib/CodeGen/MachineRegisterInfo.cpp Message-ID: <20100426191600.C1BD1312800A@llvm.org> Author: evancheng Date: Mon Apr 26 14:16:00 2010 New Revision: 102368 URL: http://llvm.org/viewvc/llvm-project?rev=102368&view=rev Log: Insert dbg_value instructions for function entry block liveins (i.e. function arguments). Modified: llvm/trunk/lib/CodeGen/MachineRegisterInfo.cpp Modified: llvm/trunk/lib/CodeGen/MachineRegisterInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/MachineRegisterInfo.cpp?rev=102368&r1=102367&r2=102368&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/MachineRegisterInfo.cpp (original) +++ llvm/trunk/lib/CodeGen/MachineRegisterInfo.cpp Mon Apr 26 14:16:00 2010 @@ -12,8 +12,9 @@ //===----------------------------------------------------------------------===// #include "llvm/CodeGen/MachineRegisterInfo.h" -#include "llvm/Support/CommandLine.h" +#include "llvm/CodeGen/MachineInstrBuilder.h" #include "llvm/Target/TargetInstrInfo.h" +#include "llvm/Support/CommandLine.h" using namespace llvm; MachineRegisterInfo::MachineRegisterInfo(const TargetRegisterInfo &TRI) { @@ -219,6 +220,30 @@ } } +/// InsertLiveInDbgValue - Insert a DBG_VALUE instruction for each live-in +/// register that has a corresponding source information metadata. e.g. +/// function parameters. +static void InsertLiveInDbgValue(MachineBasicBlock *MBB, + MachineBasicBlock::iterator InsertPos, + unsigned LiveInReg, unsigned VirtReg, + const MachineRegisterInfo &MRI, + const TargetInstrInfo &TII) { + for (MachineRegisterInfo::use_iterator UI = MRI.use_begin(VirtReg), + UE = MRI.use_end(); UI != UE; ++UI) { + MachineInstr *UseMI = &*UI; + if (!UseMI->isDebugValue() || UseMI->getParent() != MBB) + continue; + // Found local dbg_value. FIXME: Verify it's not possible to have multiple + // dbg_value's which reference the vr in the same mbb. + uint64_t Offset = UseMI->getOperand(1).getImm(); + const MDNode *MDPtr = UseMI->getOperand(2).getMetadata(); + BuildMI(*MBB, InsertPos, InsertPos->getDebugLoc(), + TII.get(TargetOpcode::DBG_VALUE)) + .addReg(LiveInReg).addImm(Offset).addMetadata(MDPtr); + return; + } +} + /// EmitLiveInCopies - Emit copies to initialize livein virtual registers /// into the given entry block. void @@ -235,6 +260,8 @@ const TargetRegisterClass *RC = getRegClass(LI->second); EmitLiveInCopy(EntryMBB, InsertPos, LI->second, LI->first, RC, CopyRegMap, *this, TRI, TII); + InsertLiveInDbgValue(EntryMBB, InsertPos, + LI->first, LI->second, *this, TII); } } else { // Emit the copies into the top of the block. @@ -246,6 +273,8 @@ LI->second, LI->first, RC, RC); assert(Emitted && "Unable to issue a live-in copy instruction!\n"); (void) Emitted; + InsertLiveInDbgValue(EntryMBB, EntryMBB->begin(), + LI->first, LI->second, *this, TII); } } From dalej at apple.com Mon Apr 26 15:05:01 2010 From: dalej at apple.com (Dale Johannesen) Date: Mon, 26 Apr 2010 20:05:01 -0000 Subject: [llvm-commits] [llvm] r102371 - in /llvm/trunk: include/llvm/Target/TargetInstrInfo.h lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp Message-ID: <20100426200501.33BFB312800A@llvm.org> Author: johannes Date: Mon Apr 26 15:05:01 2010 New Revision: 102371 URL: http://llvm.org/viewvc/llvm-project?rev=102371&view=rev Log: Add PPC AsmPrinter handling for target-specific form of DBG_VALUE, and a cautionary comment. Modified: llvm/trunk/include/llvm/Target/TargetInstrInfo.h llvm/trunk/lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp Modified: llvm/trunk/include/llvm/Target/TargetInstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetInstrInfo.h?rev=102371&r1=102370&r2=102371&view=diff ============================================================================== --- llvm/trunk/include/llvm/Target/TargetInstrInfo.h (original) +++ llvm/trunk/include/llvm/Target/TargetInstrInfo.h Mon Apr 26 15:05:01 2010 @@ -367,6 +367,9 @@ /// normally be lowered the same way as other addresses on the target, /// e.g. in load instructions. For targets that do not support this /// the debug info is simply lost. + /// If you add this for a target you should handle this DBG_VALUE in the + /// target-specific AsmPrinter code as well; you will probably get invalid + /// assembly output if you don't. virtual MachineInstr *emitFrameIndexDebugValue(MachineFunction &MF, unsigned FrameIx, uint64_t Offset, Modified: llvm/trunk/lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp?rev=102371&r1=102370&r2=102371&view=diff ============================================================================== --- llvm/trunk/lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp (original) +++ llvm/trunk/lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp Mon Apr 26 15:05:01 2010 @@ -21,6 +21,7 @@ #include "PPCPredicates.h" #include "PPCTargetMachine.h" #include "PPCSubtarget.h" +#include "llvm/Analysis/DebugInfo.h" #include "llvm/Constants.h" #include "llvm/DerivedTypes.h" #include "llvm/Module.h" @@ -535,6 +536,23 @@ SmallString<128> Str; raw_svector_ostream O(Str); + if (MI->getOpcode() == TargetOpcode::DBG_VALUE) { + unsigned NOps = MI->getNumOperands(); + assert(NOps==4); + O << '\t' << MAI->getCommentString() << "DEBUG_VALUE: "; + // cast away const; DIetc do not take const operands for some reason. + DIVariable V(const_cast(MI->getOperand(NOps-1).getMetadata())); + O << V.getName(); + O << " <- "; + // Frame address. Currently handles register +- offset only. + assert(MI->getOperand(0).isReg() && MI->getOperand(1).isImm()); + O << '['; printOperand(MI, 0, O); O << '+'; printOperand(MI, 1, O); + O << ']'; + O << "+"; + printOperand(MI, NOps-2, O); + OutStreamer.EmitRawText(O.str()); + return; + } // Check for slwi/srwi mnemonics. if (MI->getOpcode() == PPC::RLWINM) { unsigned char SH = MI->getOperand(2).getImm(); From dalej at apple.com Mon Apr 26 15:06:49 2010 From: dalej at apple.com (Dale Johannesen) Date: Mon, 26 Apr 2010 20:06:49 -0000 Subject: [llvm-commits] [llvm] r102372 - in /llvm/trunk: include/llvm/CodeGen/SelectionDAG.h lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp lib/CodeGen/SelectionDAG/SelectionDAG.cpp lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Message-ID: <20100426200649.97EAF312800A@llvm.org> Author: johannes Date: Mon Apr 26 15:06:49 2010 New Revision: 102372 URL: http://llvm.org/viewvc/llvm-project?rev=102372&view=rev Log: Add DBG_VALUE handling for byval parameters; this produces a comment on targets that support it, but the Dwarf writer is not hooked up yet. Modified: llvm/trunk/include/llvm/CodeGen/SelectionDAG.h llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Modified: llvm/trunk/include/llvm/CodeGen/SelectionDAG.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/CodeGen/SelectionDAG.h?rev=102372&r1=102371&r2=102372&view=diff ============================================================================== --- llvm/trunk/include/llvm/CodeGen/SelectionDAG.h (original) +++ llvm/trunk/include/llvm/CodeGen/SelectionDAG.h Mon Apr 26 15:06:49 2010 @@ -62,8 +62,15 @@ /// instead the info is kept off to the side in this structure. Each SDNode may /// have one or more associated dbg_value entries. This information is kept in /// DbgValMap. +/// Byval parameters are handled separately because they don't use alloca's, +/// which busts the normal mechanism. There is good reason for handling all +/// parameters separately: they may not have code generated for them, they +/// should always go at the beginning of the function regardless of other code +/// motion, and debug info for them is potentially useful even if the parameter +/// is unused. Right now only byval parameters are handled separately. class SDDbgInfo { SmallVector DbgValues; + SmallVector ByvalParmDbgValues; DenseMap > DbgValMap; void operator=(const SDDbgInfo&); // Do not implement. @@ -71,19 +78,22 @@ public: SDDbgInfo() {} - void add(SDDbgValue *V, const SDNode *Node = 0) { + void add(SDDbgValue *V, const SDNode *Node, bool isParameter) { + if (isParameter) { + ByvalParmDbgValues.push_back(V); + } else DbgValues.push_back(V); if (Node) DbgValMap[Node].push_back(V); - DbgValues.push_back(V); } void clear() { DbgValMap.clear(); DbgValues.clear(); + ByvalParmDbgValues.clear(); } bool empty() const { - return DbgValues.empty(); + return DbgValues.empty() && ByvalParmDbgValues.empty(); } SmallVector &getSDDbgValues(const SDNode *Node) { @@ -93,6 +103,8 @@ typedef SmallVector::iterator DbgIterator; DbgIterator DbgBegin() { return DbgValues.begin(); } DbgIterator DbgEnd() { return DbgValues.end(); } + DbgIterator ByvalParmDbgBegin() { return ByvalParmDbgValues.begin(); } + DbgIterator ByvalParmDbgEnd() { return ByvalParmDbgValues.end(); } }; enum CombineLevel { @@ -877,7 +889,7 @@ /// AddDbgValue - Add a dbg_value SDNode. If SD is non-null that means the /// value is produced by SD. - void AddDbgValue(SDDbgValue *DB, SDNode *SD = 0); + void AddDbgValue(SDDbgValue *DB, SDNode *SD, bool isParameter); /// GetDbgValues - Get the debug values which reference the given SDNode. SmallVector &GetDbgValues(const SDNode* SD) { @@ -890,6 +902,12 @@ SDDbgInfo::DbgIterator DbgBegin() { return DbgInfo->DbgBegin(); } SDDbgInfo::DbgIterator DbgEnd() { return DbgInfo->DbgEnd(); } + SDDbgInfo::DbgIterator ByvalParmDbgBegin() { + return DbgInfo->ByvalParmDbgBegin(); + } + SDDbgInfo::DbgIterator ByvalParmDbgEnd() { + return DbgInfo->ByvalParmDbgEnd(); + } void dump() const; Modified: llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp?rev=102372&r1=102371&r2=102372&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp Mon Apr 26 15:06:49 2010 @@ -470,6 +470,17 @@ SmallSet Seen; bool HasDbg = DAG->hasDebugValues(); + // If this is the first BB, emit byval parameter dbg_value's. + if (HasDbg && BB->getParent()->begin() == MachineFunction::iterator(BB)) { + SDDbgInfo::DbgIterator PDI = DAG->ByvalParmDbgBegin(); + SDDbgInfo::DbgIterator PDE = DAG->ByvalParmDbgEnd(); + for (; PDI != PDE; ++PDI) { + MachineInstr *DbgMI= Emitter.EmitDbgValue(*PDI, VRBaseMap, EM); + if (DbgMI) + BB->insert(BB->end(), DbgMI); + } + } + for (unsigned i = 0, e = Sequence.size(); i != e; i++) { SUnit *SU = Sequence[i]; if (!SU) { @@ -494,20 +505,20 @@ SDNode *N = FlaggedNodes.back(); Emitter.EmitNode(FlaggedNodes.back(), SU->OrigNode != SU, SU->isCloned, VRBaseMap, EM); - // Remember the the source order of the inserted instruction. + // Remember the source order of the inserted instruction. if (HasDbg) ProcessSourceNode(N, DAG, Emitter, EM, VRBaseMap, Orders, Seen); FlaggedNodes.pop_back(); } Emitter.EmitNode(SU->getNode(), SU->OrigNode != SU, SU->isCloned, VRBaseMap, EM); - // Remember the the source order of the inserted instruction. + // Remember the source order of the inserted instruction. if (HasDbg) ProcessSourceNode(SU->getNode(), DAG, Emitter, EM, VRBaseMap, Orders, Seen); } - // Insert all the dbg_value which have not already been inserted in source + // Insert all the dbg_values which have not already been inserted in source // order sequence. if (HasDbg) { MachineBasicBlock::iterator BBBegin = BB->empty() ? BB->end() : BB->begin(); Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp?rev=102372&r1=102371&r2=102372&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp Mon Apr 26 15:06:49 2010 @@ -5341,8 +5341,8 @@ /// AddDbgValue - Add a dbg_value SDNode. If SD is non-null that means the /// value is produced by SD. -void SelectionDAG::AddDbgValue(SDDbgValue *DB, SDNode *SD) { - DbgInfo->add(DB, SD); +void SelectionDAG::AddDbgValue(SDDbgValue *DB, SDNode *SD, bool isParameter) { + DbgInfo->add(DB, SD, isParameter); if (SD) SD->setHasDebugValue(true); } Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp?rev=102372&r1=102371&r2=102372&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Mon Apr 26 15:06:49 2010 @@ -3775,32 +3775,75 @@ case Intrinsic::dbg_declare: { // FIXME: currently, we get here only if OptLevel != CodeGenOpt::None. // The real handling of this intrinsic is in FastISel. - if (OptLevel != CodeGenOpt::None) +// if (OptLevel != CodeGenOpt::None) // FIXME: Variable debug info is not supported here. - return 0; +// return 0; const DbgDeclareInst &DI = cast(I); if (!DIDescriptor::ValidDebugInfo(DI.getVariable(), CodeGenOpt::None)) return 0; MDNode *Variable = DI.getVariable(); + // Parameters are handled specially. + bool isParameter = false; + ConstantInt *CI = dyn_cast_or_null(Variable->getOperand(0)); + if (CI) { + unsigned Val = CI->getZExtValue(); + unsigned Tag = Val & ~LLVMDebugVersionMask; + if (Tag == dwarf::DW_TAG_arg_variable) + isParameter = true; + } const Value *Address = DI.getAddress(); if (!Address) return 0; if (const BitCastInst *BCI = dyn_cast(Address)) Address = BCI->getOperand(0); const AllocaInst *AI = dyn_cast(Address); - // Don't handle byval struct arguments or VLAs, for example. - if (!AI) - return 0; - DenseMap::iterator SI = - FuncInfo.StaticAllocaMap.find(AI); - if (SI == FuncInfo.StaticAllocaMap.end()) - return 0; // VLAs. - int FI = SI->second; + if (AI) { + // Don't handle byval arguments or VLAs, for example. + // Non-byval arguments are handled here (they refer to the stack temporary + // alloca at this point). + DenseMap::iterator SI = + FuncInfo.StaticAllocaMap.find(AI); + if (SI == FuncInfo.StaticAllocaMap.end()) + return 0; // VLAs. + int FI = SI->second; + + MachineModuleInfo &MMI = DAG.getMachineFunction().getMMI(); + if (!DI.getDebugLoc().isUnknown() && MMI.hasDebugInfo()) + MMI.setVariableDbgInfo(Variable, FI, DI.getDebugLoc()); + } - MachineModuleInfo &MMI = DAG.getMachineFunction().getMMI(); - if (!DI.getDebugLoc().isUnknown() && MMI.hasDebugInfo()) - MMI.setVariableDbgInfo(Variable, FI, DI.getDebugLoc()); + // Build an entry in DbgOrdering. Debug info input nodes get an SDNodeOrder + // but do not always have a corresponding SDNode built. The SDNodeOrder + // absolute, but not relative, values are different depending on whether + // debug info exists. + ++SDNodeOrder; + SDValue &N = NodeMap[Address]; + SDDbgValue *SDV; + if (N.getNode()) { + if (isParameter && !AI) { + FrameIndexSDNode *FINode = dyn_cast(N.getNode()); + if (FINode) + // Byval parameter. We have a frame index at this point. + SDV = DAG.getDbgValue(Variable, FINode->getIndex(), + 0, dl, SDNodeOrder); + else + // Can't do anything with other non-AI cases yet. This might be a + // parameter of a callee function that got inlined, for example. + return 0; + } else if (AI) + SDV = DAG.getDbgValue(Variable, N.getNode(), N.getResNo(), + 0, dl, SDNodeOrder); + else + // Can't do anything with other non-AI cases yet. + return 0; + DAG.AddDbgValue(SDV, N.getNode(), isParameter); + } else { + // This isn't useful, but it shows what we're missing. + SDV = DAG.getDbgValue(Variable, UndefValue::get(Address->getType()), + 0, dl, SDNodeOrder); + DAG.AddDbgValue(SDV, 0, isParameter); + } return 0; } case Intrinsic::dbg_value: { @@ -3819,20 +3862,23 @@ // absolute, but not relative, values are different depending on whether // debug info exists. ++SDNodeOrder; + SDDbgValue *SDV; if (isa(V) || isa(V)) { - DAG.AddDbgValue(DAG.getDbgValue(Variable, V, Offset, dl, SDNodeOrder)); + SDV = DAG.getDbgValue(Variable, V, Offset, dl, SDNodeOrder); + DAG.AddDbgValue(SDV, 0, false); } else { SDValue &N = NodeMap[V]; - if (N.getNode()) - DAG.AddDbgValue(DAG.getDbgValue(Variable, N.getNode(), - N.getResNo(), Offset, dl, SDNodeOrder), - N.getNode()); - else + if (N.getNode()) { + SDV = DAG.getDbgValue(Variable, N.getNode(), + N.getResNo(), Offset, dl, SDNodeOrder); + DAG.AddDbgValue(SDV, N.getNode(), false); + } else { // We may expand this to cover more cases. One case where we have no // data available is an unreferenced parameter; we need this fallback. - DAG.AddDbgValue(DAG.getDbgValue(Variable, - UndefValue::get(V->getType()), - Offset, dl, SDNodeOrder)); + SDV = DAG.getDbgValue(Variable, UndefValue::get(V->getType()), + Offset, dl, SDNodeOrder); + DAG.AddDbgValue(SDV, 0, false); + } } // Build a debug info table entry. From dalej at apple.com Mon Apr 26 15:07:31 2010 From: dalej at apple.com (Dale Johannesen) Date: Mon, 26 Apr 2010 20:07:31 -0000 Subject: [llvm-commits] [llvm] r102373 - /llvm/trunk/lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp Message-ID: <20100426200731.C7F6F312800A@llvm.org> Author: johannes Date: Mon Apr 26 15:07:31 2010 New Revision: 102373 URL: http://llvm.org/viewvc/llvm-project?rev=102373&view=rev Log: Handle target-specific form of DBG_VALUE in AsmPrinter. Modified: llvm/trunk/lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp Modified: llvm/trunk/lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp?rev=102373&r1=102372&r2=102373&view=diff ============================================================================== --- llvm/trunk/lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp (original) +++ llvm/trunk/lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp Mon Apr 26 15:07:31 2010 @@ -21,6 +21,7 @@ #include "ARMMachineFunctionInfo.h" #include "ARMMCInstLower.h" #include "ARMTargetMachine.h" +#include "llvm/Analysis/DebugInfo.h" #include "llvm/Constants.h" #include "llvm/Module.h" #include "llvm/Type.h" @@ -1108,6 +1109,24 @@ SmallString<128> Str; raw_svector_ostream OS(Str); + if (MI->getOpcode() == ARM::DBG_VALUE) { + unsigned NOps = MI->getNumOperands(); + assert(NOps==4); + OS << '\t' << MAI->getCommentString() << "DEBUG_VALUE: "; + // cast away const; DIetc do not take const operands for some reason. + DIVariable V(const_cast(MI->getOperand(NOps-1).getMetadata())); + OS << V.getName(); + OS << " <- "; + // Frame address. Currently handles register +- offset only. + assert(MI->getOperand(0).isReg() && MI->getOperand(1).isImm()); + OS << '['; printOperand(MI, 0, OS); OS << '+'; printOperand(MI, 1, OS); + OS << ']'; + OS << "+"; + printOperand(MI, NOps-2, OS); + OutStreamer.EmitRawText(OS.str()); + return; + } + printInstruction(MI, OS); OutStreamer.EmitRawText(OS.str()); From gohman at apple.com Mon Apr 26 15:11:08 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 13:11:08 -0700 Subject: [llvm-commits] Fix for assertion in DAGCombiner In-Reply-To: <20881.85783.qm@web55606.mail.re4.yahoo.com> References: <623530.48513.qm@web55607.mail.re4.yahoo.com> <805706E5-D6DB-41BE-B6F7-B985B60AD9AA@apple.com> <20881.85783.qm@web55606.mail.re4.yahoo.com> Message-ID: <12119F7F-AA5E-4F3F-8C05-FD7387349C43@apple.com> On Apr 24, 2010, at 7:42 AM, Jan Sjodin wrote: > > >> On x86, support for vector SETCC is currently limited to cases where the >> result is sign-extended to a vector of the same width as the SETCC >> operand vector. In other words, if you change the <3 x i32> to <3 x >> i64 here it'll work, because i64 is the same width as double. >> >> Dan > > That is unfortunate. Is conversion from a vector to another of smaller size > supported? It might be possible to sign extend to i64, then convert to i32. > Even if the support is direct, the code generation will have to do something > like this anyway. The IR supports this for its part, but overall, this is relatively new territory for LLVM in general. If you find things that don't work, bugs and patches are welcome. Dan From gohman at apple.com Mon Apr 26 15:21:21 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 20:21:21 -0000 Subject: [llvm-commits] [llvm] r102376 - /llvm/trunk/docs/LangRef.html Message-ID: <20100426202122.16500312800A@llvm.org> Author: djg Date: Mon Apr 26 15:21:21 2010 New Revision: 102376 URL: http://llvm.org/viewvc/llvm-project?rev=102376&view=rev Log: Fix HTML errors that Jeffery Yasskin noticed. Modified: llvm/trunk/docs/LangRef.html Modified: llvm/trunk/docs/LangRef.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/LangRef.html?rev=102376&r1=102375&r2=102376&view=diff ============================================================================== --- llvm/trunk/docs/LangRef.html (original) +++ llvm/trunk/docs/LangRef.html Mon Apr 26 15:21:21 2010 @@ -2307,11 +2307,11 @@
    Trap Values
    -

    Trap values are similar to undef values, however +

    Trap values are similar to undef values, however instead of representing an unspecified bit pattern, they represent the fact that an instruction or constant expression which cannot evoke side effects has nevertheless detected a condition which results in undefined - behavior.

    + behavior.

    Any non-void instruction or constant expression other than a non-intrinsic call, invoke, or phi with a trap operand has trap as its result value. From Micah.Villmow at amd.com Mon Apr 26 15:37:46 2010 From: Micah.Villmow at amd.com (Villmow, Micah) Date: Mon, 26 Apr 2010 15:37:46 -0500 Subject: [llvm-commits] Fix for assertion in DAGCombiner In-Reply-To: <277854.61965.qm@web55602.mail.re4.yahoo.com> References: <623530.48513.qm@web55607.mail.re4.yahoo.com> <805706E5-D6DB-41BE-B6F7-B985B60AD9AA@apple.com> <277854.61965.qm@web55602.mail.re4.yahoo.com> Message-ID: Jan, One thing you can try is to use the helper function DAG.gteSExtOrTrunc() instead of return DAG.getNode(ISD::TRUNCATE, N->getDebugLoc(), VT, VsetCC); This should fix the problem of the case where the type is larger without duplicating code. Micah -----Original Message----- From: llvm-commits-bounces at cs.uiuc.edu [mailto:llvm-commits-bounces at cs.uiuc.edu] On Behalf Of Jan Sjodin Sent: Monday, April 26, 2010 12:11 PM To: Dan Gohman Cc: llvm-commits at cs.uiuc.edu Subject: Re: [llvm-commits] Fix for assertion in DAGCombiner Below is one way of fixing the issue of sign extending a vector of smaller element types. I suppose it would be fairly trivial to include the case where the type is larger by replacing truncate with a second sign extend, but I wanted to get feedback on this code: Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp =================================================================== --- lib/CodeGen/SelectionDAG/DAGCombiner.cpp (revision 102340) +++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp (working copy) @@ -3495,20 +3495,34 @@ if (N0.getOpcode() == ISD::SETCC) { // sext(setcc) -> sext_in_reg(vsetcc) for vectors. - if (VT.isVector() && + // Only do this before legalize for now. + if (VT.isVector() && !LegalOperations) { + EVT N0VT = N0.getOperand(0).getValueType(); // We know that the # elements of the results is the same as the // # elements of the compare (and the # elements of the compare result // for that matter). Check to see that they are the same size. If so, // we know that the element size of the sext'd result matches the // element size of the compare operands. - VT.getSizeInBits() == N0.getOperand(0).getValueType().getSizeInBits() && - - // Only do this before legalize for now. - !LegalOperations) { - return DAG.getVSetCC(N->getDebugLoc(), VT, N0.getOperand(0), - N0.getOperand(1), - cast(N0.getOperand(2))->get()); - } + if(VT.getSizeInBits() == N0VT.getSizeInBits()) + return DAG.getVSetCC(N->getDebugLoc(), VT, N0.getOperand(0), + N0.getOperand(1), + cast(N0.getOperand(2))->get()); + // If the desired elements are smaller than the source elements we can + // use a matching integer vector type and then truncate + else if(VT.getSizeInBits() < N0VT.getSizeInBits()) { + EVT MatchingElementType = + EVT::getIntegerVT(*DAG.getContext(), + N0VT.getScalarType().getSizeInBits()); + EVT MatchingVectorType = + EVT::getVectorVT(*DAG.getContext(), MatchingElementType, + N0VT.getVectorNumElements()); + SDValue VsetCC = + DAG.getVSetCC(N->getDebugLoc(), MatchingVectorType, N0.getOperand(0), + N0.getOperand(1), + cast(N0.getOperand(2))->get()); + return DAG.getNode(ISD::TRUNCATE, N->getDebugLoc(), VT, VsetCC); + } + } // sext(setcc x, y, cc) -> (select_cc x, y, -1, 0, cc) unsigned ElementWidth = VT.getScalarType().getSizeInBits(); ----- Original Message ---- > From: Dan Gohman > To: Jan Sjodin > Cc: llvm-commits at cs.uiuc.edu > Sent: Fri, April 23, 2010 9:22:30 PM > Subject: Re: [llvm-commits] Fix for assertion in DAGCombiner > > On Apr 23, 2010, at 9:41 AM, Jan Sjodin wrote: > Small fix that > prevents an assertion in getConstant if VT is a vector type. > > > Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp > > =================================================================== > --- > lib/CodeGen/SelectionDAG/DAGCombiner.cpp (revision 102107) > > +++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp (working copy) > > @@ -3453,7 +3453,8 @@ > > // sext(setcc x, y, cc) > -> (select_cc x, y, -1, 0, cc) > SDValue NegOne = > > - > DAG.getConstant(APInt::getAllOnesValue(VT.getSizeInBits()), VT); > + > > DAG.getConstant(APInt::getAllOnesValue(VT.getScalarType().getSizeInBits()), > > + > VT); > SDValue SCC = > > SimplifySelectCC(N->getDebugLoc(), N0.getOperand(0), > N0.getOperand(1), > > NegOne, DAG.getConstant(0, VT), Thanks! This > is now applied (with a trivial edit for 80 columns). > > I was > going to use the example below, but there are still more errors to be fixed (see > below): > > ; ModuleID = 'minimal.bc' > target datalayout = > "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:6\ > > 4:64-f80:128:128" > target triple = "x86_64-pc-linux-gnu" > > > define void @myfunction(<3 x double>* %foo, <3 x double>* %bar, > <3 x i32>* %result) { > entry: > %foo.value = load <3 > x double>* %foo ; <<3 x > double>> [#uses=1] > %bar.value = load <3 x double>* > %bar ; <<3 x double>> > [#uses=1] > %cmp.i.i = fcmp oeq <3 x double> %foo.value, > %bar.value ; <<3 x i1>> [#uses=1] > %cmp.ext.i.i = sext > <3 x i1> %cmp.i.i to <3 x i32> ; <<3 x i32>> > [#uses=1] > store <3 x i32> %cmp.ext.i.i, <3 x i32>* > %result > ret void > } > > > llc > fails: > WidenVectorOperand op #0: 0xb7fc520: i8 = setcc 0xb7fbe38, > 0xb7fbec0, 0xb7fbf48 > [ID=0] > Do not know how to widen this > operator's operand! > UNREACHABLE executed at > LegalizeVectorTypes.cpp:1898! > > I will try and look into this as > well. On x86, support for vector SETCC is currently limited to cases > where the result is sign-extended to a vector of the same width as the SETCC > operand vector. In other words, if you change the <3 x i32> to <3 x > i64> here it'll work, because i64 is the same width as > double. Dan _______________________________________________ llvm-commits mailing list llvm-commits at cs.uiuc.edu http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits From dalej at apple.com Mon Apr 26 15:48:54 2010 From: dalej at apple.com (Dale Johannesen) Date: Mon, 26 Apr 2010 20:48:54 -0000 Subject: [llvm-commits] [llvm] r102380 - /llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Message-ID: <20100426204854.908BC3128018@llvm.org> Author: johannes Date: Mon Apr 26 15:48:54 2010 New Revision: 102380 URL: http://llvm.org/viewvc/llvm-project?rev=102380&view=rev Log: Remove crufty comments. Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp?rev=102380&r1=102379&r2=102380&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Mon Apr 26 15:48:54 2010 @@ -3773,11 +3773,6 @@ return 0; } case Intrinsic::dbg_declare: { - // FIXME: currently, we get here only if OptLevel != CodeGenOpt::None. - // The real handling of this intrinsic is in FastISel. -// if (OptLevel != CodeGenOpt::None) - // FIXME: Variable debug info is not supported here. -// return 0; const DbgDeclareInst &DI = cast(I); if (!DIDescriptor::ValidDebugInfo(DI.getVariable(), CodeGenOpt::None)) return 0; From ggreif at gmail.com Mon Apr 26 15:46:04 2010 From: ggreif at gmail.com (Gabor Greif) Date: Mon, 26 Apr 2010 20:46:04 -0000 Subject: [llvm-commits] [llvm] r102378 - /llvm/trunk/docs/ReleaseNotes.html Message-ID: <20100426204604.3492A312800A@llvm.org> Author: ggreif Date: Mon Apr 26 15:46:03 2010 New Revision: 102378 URL: http://llvm.org/viewvc/llvm-project?rev=102378&view=rev Log: add some typewriter tags Modified: llvm/trunk/docs/ReleaseNotes.html Modified: llvm/trunk/docs/ReleaseNotes.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/ReleaseNotes.html?rev=102378&r1=102377&r2=102378&view=diff ============================================================================== --- llvm/trunk/docs/ReleaseNotes.html (original) +++ llvm/trunk/docs/ReleaseNotes.html Mon Apr 26 15:46:03 2010 @@ -929,13 +929,13 @@ API changes are:

      -
    • Just about everything has been converted to use raw_ostream instead of - std::ostream.
      • -
    • llvm/ADT/iterator.h has been removed, just use <iterator> +
    • Just about everything has been converted to use raw_ostream instead of + std::ostream.
      • +
    • llvm/ADT/iterator.h has been removed, just use <iterator> instead.
      • -
    • The Streams.h file and "DOUT" got removed, use "DEBUG(errs() << ...);" +
    • The Streams.h file and DOUT got removed, use DEBUG(errs() << ...); instead.
      • -
    • The TargetAsmInfo interface was renamed to MCAsmInfo.
      • +
    • The TargetAsmInfo interface was renamed to MCAsmInfo.
    • ModuleProvider has been removed and its methods moved to Module and GlobalValue. From jan_sjodin at yahoo.com Mon Apr 26 15:54:52 2010 From: jan_sjodin at yahoo.com (Jan Sjodin) Date: Mon, 26 Apr 2010 13:54:52 -0700 (PDT) Subject: [llvm-commits] Fix for assertion in DAGCombiner In-Reply-To: References: <623530.48513.qm@web55607.mail.re4.yahoo.com> <805706E5-D6DB-41BE-B6F7-B985B60AD9AA@apple.com> <277854.61965.qm@web55602.mail.re4.yahoo.com> Message-ID: <163178.26809.qm@web55608.mail.re4.yahoo.com> Thanks for the pointer. I changed the patch to include the use of this method: Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp =================================================================== --- lib/CodeGen/SelectionDAG/DAGCombiner.cpp (revision 102340) +++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp (working copy) @@ -3495,20 +3495,35 @@ if (N0.getOpcode() == ISD::SETCC) { // sext(setcc) -> sext_in_reg(vsetcc) for vectors. - if (VT.isVector() && + // Only do this before legalize for now. + if (VT.isVector() && !LegalOperations) { + EVT N0VT = N0.getOperand(0).getValueType(); // We know that the # elements of the results is the same as the // # elements of the compare (and the # elements of the compare result // for that matter). Check to see that they are the same size. If so, // we know that the element size of the sext'd result matches the // element size of the compare operands. - VT.getSizeInBits() == N0.getOperand(0).getValueType().getSizeInBits() && - - // Only do this before legalize for now. - !LegalOperations) { - return DAG.getVSetCC(N->getDebugLoc(), VT, N0.getOperand(0), - N0.getOperand(1), - cast(N0.getOperand(2))->get()); - } + if(VT.getSizeInBits() == N0VT.getSizeInBits()) + return DAG.getVSetCC(N->getDebugLoc(), VT, N0.getOperand(0), + N0.getOperand(1), + cast(N0.getOperand(2))->get()); + // If the desired elements are smaller or larger than the source + // elements we can use a matching integer vector type and then + // truncate/sign extend + else { + EVT MatchingElementType = + EVT::getIntegerVT(*DAG.getContext(), + N0VT.getScalarType().getSizeInBits()); + EVT MatchingVectorType = + EVT::getVectorVT(*DAG.getContext(), MatchingElementType, + N0VT.getVectorNumElements()); + SDValue VsetCC = + DAG.getVSetCC(N->getDebugLoc(), MatchingVectorType, N0.getOperand(0), + N0.getOperand(1), + cast(N0.getOperand(2))->get()); + return DAG.getSExtOrTrunc(VsetCC, N->getDebugLoc(), VT); + } + } // sext(setcc x, y, cc) -> (select_cc x, y, -1, 0, cc) unsigned ElementWidth = VT.getScalarType().getSizeInBits(); ----- Original Message ---- > From: "Villmow, Micah" > Cc: "llvm-commits at cs.uiuc.edu" > Sent: Mon, April 26, 2010 4:37:46 PM > Subject: Re: [llvm-commits] Fix for assertion in DAGCombiner > > Jan, One thing you can try is to use the helper function > DAG.gteSExtOrTrunc() instead of return DAG.getNode(ISD::TRUNCATE, > N->getDebugLoc(), VT, VsetCC); This should fix the problem of the > case where the type is larger without duplicating > code. From gohman at apple.com Mon Apr 26 15:54:53 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 20:54:53 -0000 Subject: [llvm-commits] [llvm] r102381 - /llvm/trunk/docs/LangRef.html Message-ID: <20100426205454.3D779312800A@llvm.org> Author: djg Date: Mon Apr 26 15:54:53 2010 New Revision: 102381 URL: http://llvm.org/viewvc/llvm-project?rev=102381&view=rev Log: Branching or switching on trap transfers imminent undefined behavior onto control-dependent instructions. Modified: llvm/trunk/docs/LangRef.html Modified: llvm/trunk/docs/LangRef.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/LangRef.html?rev=102381&r1=102380&r2=102381&view=diff ============================================================================== --- llvm/trunk/docs/LangRef.html (original) +++ llvm/trunk/docs/LangRef.html Mon Apr 26 15:54:53 2010 @@ -2318,6 +2318,15 @@ Any instruction with a trap operand which may have side effects emits those side effects as if it had an undef operand instead.

      +

      If a br or + switch instruction has a trap value + operand, all non-phi non-void instructions which control-depend on it + have trap as their result value. If any instruction which + control-depends on the br or switch invokes externally + visible side effects, the behavior of the program is undefined.

      + + +

      For example, an and of a trap value with zero still has a trap value result. Using that value as an index in a getelementptr yields a trap From gohman at apple.com Mon Apr 26 16:15:19 2010 From: gohman at apple.com (gohman at apple.com) Date: Mon, 26 Apr 2010 21:15:19 +0000 Subject: [llvm-commits] [PATCH] Consolidate the description of volatile operations (issue986042) Message-ID: <0016e68ee4b0342a2f04852a46e9@google.com> This looks good to me. There are some tricky issues with volatile not covered here, but they weren't covered by the original text either :-). http://codereview.appspot.com/986042/show From jyasskin at google.com Mon Apr 26 16:21:24 2010 From: jyasskin at google.com (Jeffrey Yasskin) Date: Mon, 26 Apr 2010 21:21:24 -0000 Subject: [llvm-commits] [llvm] r102384 - /llvm/trunk/docs/LangRef.html Message-ID: <20100426212125.4A00A312800A@llvm.org> Author: jyasskin Date: Mon Apr 26 16:21:24 2010 New Revision: 102384 URL: http://llvm.org/viewvc/llvm-project?rev=102384&view=rev Log: Consolidate the description of volatile operations, now that some of the intrinsics have volatile semantics in addition to the load and store instructions. Modified: llvm/trunk/docs/LangRef.html Modified: llvm/trunk/docs/LangRef.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/LangRef.html?rev=102384&r1=102383&r2=102384&view=diff ============================================================================== --- llvm/trunk/docs/LangRef.html (original) +++ llvm/trunk/docs/LangRef.html Mon Apr 26 16:21:24 2010 @@ -50,6 +50,7 @@

    • Module-Level Inline Assembly
    • Data Layout
    • Pointer Aliasing Rules
      • +
    • Volatile Memory Accesses
    • Type System @@ -1394,6 +1395,24 @@
    + +
    + Volatile Memory Accesses +
    + +
    + +

    Certain memory accesses, such as loads, stores, and llvm.memcpys may be marked volatile. +The optimizers must not change the number of volatile operations or change their +order of execution relative to other volatile operations. The optimizers +may change the order of volatile operations relative to non-volatile +operations. This is not Java's "volatile" and has no cross-thread +synchronization behavior.

    + +
    +
    Type System
    @@ -4199,9 +4218,8 @@ from which to load. The pointer must point to a first class type. If the load is marked as volatile, then the optimizer is not allowed to modify the - number or order of execution of this load with other - volatile load and store - instructions.

    + number or order of execution of this load with other volatile operations.

    The optional constant align argument specifies the alignment of the operation (that is, the alignment of the memory address). A value of 0 or an @@ -4257,11 +4275,10 @@ and an address at which to store it. The type of the '<pointer>' operand must be a pointer to the first class type of the - '<value>' operand. If the store is marked - as volatile, then the optimizer is not allowed to modify the number - or order of execution of this store with other - volatile load and store - instructions.

    + '<value>' operand. If the store is marked as + volatile, then the optimizer is not allowed to modify the number or + order of execution of this store with other volatile operations.

    The optional constant "align" argument specifies the alignment of the operation (that is, the alignment of the memory address). A value of 0 or an @@ -5962,8 +5979,10 @@ then the caller guarantees that both the source and destination pointers are aligned to that boundary.

    -

    Volatile accesses should not be deleted if dead, but the access behavior is - not very cleanly specified and it is unwise to depend on it.

    +

    If the isvolatile parameter is true, the + llvm.memcpy call is a volatile operation. + The detailed access behavior is not very cleanly specified and it is unwise + to depend on it.

    Semantics:
    @@ -6016,8 +6035,10 @@ then the caller guarantees that the source and destination pointers are aligned to that boundary.

    -

    Volatile accesses should not be deleted if dead, but the access behavior is - not very cleanly specified and it is unwise to depend on it.

    +

    If the isvolatile parameter is true, the + llvm.memmove call is a volatile operation. + The detailed access behavior is not very cleanly specified and it is unwise + to depend on it.

    Semantics:
    @@ -6066,8 +6087,10 @@ then the caller guarantees that the destination pointer is aligned to that boundary.

    -

    Volatile accesses should not be deleted if dead, but the access behavior is - not very cleanly specified and it is unwise to depend on it.

    +

    If the isvolatile parameter is true, the + llvm.memset call is a volatile operation. + The detailed access behavior is not very cleanly specified and it is unwise + to depend on it.

    Semantics:

    The 'llvm.memset.*' intrinsics fill "len" bytes of memory starting From jyasskin at google.com Mon Apr 26 16:22:47 2010 From: jyasskin at google.com (Jeffrey Yasskin) Date: Mon, 26 Apr 2010 14:22:47 -0700 Subject: [llvm-commits] [PATCH] Consolidate the description of volatile operations (issue986042) In-Reply-To: <0016e68ee4b0342a2f04852a46e9@google.com> References: <0016e68ee4b0342a2f04852a46e9@google.com> Message-ID: Thanks! On Mon, Apr 26, 2010 at 2:15 PM, wrote: > This looks good to me. ?There are some tricky issues with volatile not > covered here, but they weren't covered by the original text either :-). > > http://codereview.appspot.com/986042/show From tonic at nondot.org Mon Apr 26 16:23:14 2010 From: tonic at nondot.org (Tanya Lattner) Date: Mon, 26 Apr 2010 21:23:14 -0000 Subject: [llvm-commits] [www] r102385 - /www/trunk/index.html Message-ID: <20100426212314.28D2A312800A@llvm.org> Author: tbrethou Date: Mon Apr 26 16:23:13 2010 New Revision: 102385 URL: http://llvm.org/viewvc/llvm-project?rev=102385&view=rev Log: Update release schedule. Modified: www/trunk/index.html Modified: www/trunk/index.html URL: http://llvm.org/viewvc/llvm-project/www/trunk/index.html?rev=102385&r1=102384&r2=102385&view=diff ============================================================================== --- www/trunk/index.html (original) +++ www/trunk/index.html Mon Apr 26 16:23:13 2010 @@ -108,9 +108,7 @@ The release is current in progress. Important upcoming dates: -

  • Apr 18 - Pre-release2 testing begins
    • -
  • Apr 23 - Pre-release2 testing ends
    • -
  • Apr 25 - Release!
    • +
  • Apr 26 - Release! (evening PDT)

From gohman at apple.com Mon Apr 26 16:37:43 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 21:37:43 -0000 Subject: [llvm-commits] [llvm] r102387 - /llvm/trunk/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll Message-ID: <20100426213743.D2F2D312800A@llvm.org> Author: djg Date: Mon Apr 26 16:37:43 2010 New Revision: 102387 URL: http://llvm.org/viewvc/llvm-project?rev=102387&view=rev Log: Add a comment to this test. Modified: llvm/trunk/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll Modified: llvm/trunk/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll?rev=102387&r1=102386&r2=102387&view=diff ============================================================================== --- llvm/trunk/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll (original) +++ llvm/trunk/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll Mon Apr 26 16:37:43 2010 @@ -1,6 +1,9 @@ ; RUN: opt < %s -analyze -scalar-evolution |& grep {/u 3} ; XFAIL: * +; This is a tricky testcase for unsigned wrap detection which ScalarEvolution +; doesn't yet know how to do. + define i32 @f(i32 %x) nounwind readnone { entry: %0 = icmp ugt i32 %x, 999 ; [#uses=1] From gohman at apple.com Mon Apr 26 16:42:10 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 14:42:10 -0700 Subject: [llvm-commits] [zorg] r102333 - /zorg/trunk/buildbot/osuosl/master/config/builders.py In-Reply-To: <20100426135658.C70DD312800A@llvm.org> References: <20100426135658.C70DD312800A@llvm.org> Message-ID: On Apr 26, 2010, at 6:56 AM, Daniel Dunbar wrote: > Author: ddunbar > Date: Mon Apr 26 08:56:58 2010 > New Revision: 102333 > > URL: http://llvm.org/viewvc/llvm-project?rev=102333&view=rev > Log: > buildbot: Enable clang-x86_64-linux-selfhost-rel by default, now that Dan fixed last remaining issues! The bug fix fixed llvm-gcc-x86_64-linux-selfhost too. Should that also be enabled by default now? Dan From gohman at apple.com Mon Apr 26 16:46:36 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 21:46:36 -0000 Subject: [llvm-commits] [llvm] r102389 - in /llvm/trunk: lib/Analysis/README.txt lib/Analysis/ScalarEvolutionExpander.cpp test/CodeGen/X86/lsr-delayed-fold.ll Message-ID: <20100426214636.F273E312800A@llvm.org> Author: djg Date: Mon Apr 26 16:46:36 2010 New Revision: 102389 URL: http://llvm.org/viewvc/llvm-project?rev=102389&view=rev Log: When checking whether the special handling for an addrec increment which doesn't dominate the header is needed, don't check whether the increment expression has computable loop evolution. While the operands of an addrec are required to be loop-invariant, they're not required to dominate any part of the loop. This fixes PR6914. Modified: llvm/trunk/lib/Analysis/README.txt llvm/trunk/lib/Analysis/ScalarEvolutionExpander.cpp llvm/trunk/test/CodeGen/X86/lsr-delayed-fold.ll Modified: llvm/trunk/lib/Analysis/README.txt URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Analysis/README.txt?rev=102389&r1=102388&r2=102389&view=diff ============================================================================== --- llvm/trunk/lib/Analysis/README.txt (original) +++ llvm/trunk/lib/Analysis/README.txt Mon Apr 26 16:46:36 2010 @@ -17,7 +17,7 @@ //===---------------------------------------------------------------------===// -In test/CodeGen/X86/lsr-delayed-fold.ll, +In formatValue in test/CodeGen/X86/lsr-delayed-fold.ll, ScalarEvolution is forming this expression: Modified: llvm/trunk/lib/Analysis/ScalarEvolutionExpander.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Analysis/ScalarEvolutionExpander.cpp?rev=102389&r1=102388&r2=102389&view=diff ============================================================================== --- llvm/trunk/lib/Analysis/ScalarEvolutionExpander.cpp (original) +++ llvm/trunk/lib/Analysis/ScalarEvolutionExpander.cpp Mon Apr 26 16:46:36 2010 @@ -995,8 +995,7 @@ // Strip off any non-loop-dominating component from the addrec step. const SCEV *Step = Normalized->getStepRecurrence(SE); const SCEV *PostLoopScale = 0; - if (!Step->hasComputableLoopEvolution(L) && - !Step->dominates(L->getHeader(), SE.DT)) { + if (!Step->dominates(L->getHeader(), SE.DT)) { PostLoopScale = Step; Step = SE.getIntegerSCEV(1, Normalized->getType()); Normalized = Modified: llvm/trunk/test/CodeGen/X86/lsr-delayed-fold.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/lsr-delayed-fold.ll?rev=102389&r1=102388&r2=102389&view=diff ============================================================================== --- llvm/trunk/test/CodeGen/X86/lsr-delayed-fold.ll (original) +++ llvm/trunk/test/CodeGen/X86/lsr-delayed-fold.ll Mon Apr 26 16:46:36 2010 @@ -1,8 +1,8 @@ ; RUN: llc -march=x86-64 < %s > /dev/null -; rdar://7886751 ; ScalarEvolution misses an opportunity to fold ((trunc x) + (trunc -x) + y), ; but LSR should tolerate this. +; rdar://7886751 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64" target triple = "x86_64-apple-darwin11.0" @@ -26,3 +26,26 @@ bb24: ; preds = %bb21, %bb11 unreachable } + +; ScalarEvolution should be able to correctly expand the crazy addrec here. +; PR6914 + +define void @int323() nounwind { +entry: + br label %for.cond + +for.cond: ; preds = %lbl_264, %for.inc, %entry + %g_263.tmp.1 = phi i8 [ undef, %entry ], [ %g_263.tmp.1, %for.cond ] + %p_95.addr.0 = phi i8 [ 0, %entry ], [ %add, %for.cond ] + %add = add i8 %p_95.addr.0, 1 ; [#uses=1] + br i1 undef, label %for.cond, label %lbl_264 + +lbl_264: ; preds = %if.end, %lbl_264.preheader + %g_263.tmp.0 = phi i8 [ %g_263.tmp.1, %for.cond ] ; [#uses=1] + %tmp7 = load i16* undef ; [#uses=1] + %conv8 = trunc i16 %tmp7 to i8 ; [#uses=1] + %mul.i = mul i8 %p_95.addr.0, %p_95.addr.0 ; [#uses=1] + %mul.i18 = mul i8 %mul.i, %conv8 ; [#uses=1] + %tobool12 = icmp eq i8 %mul.i18, 0 ; [#uses=1] + unreachable +} From dpatel at apple.com Mon Apr 26 17:54:29 2010 From: dpatel at apple.com (Devang Patel) Date: Mon, 26 Apr 2010 22:54:29 -0000 Subject: [llvm-commits] [llvm] r102394 - in /llvm/trunk: lib/CodeGen/AsmPrinter/DwarfDebug.cpp test/DebugInfo/2010-03-22-CU-HighLow.ll test/DebugInfo/2010-04-25-CU-entry_pc.ll Message-ID: <20100426225429.1F48F312800A@llvm.org> Author: dpatel Date: Mon Apr 26 17:54:28 2010 New Revision: 102394 URL: http://llvm.org/viewvc/llvm-project?rev=102394&view=rev Log: Use DW_AT_entry_pc instead of DW_AT_low_pc/DW_AT_high_pc pair. This simplifies debug range entries. Added: llvm/trunk/test/DebugInfo/2010-04-25-CU-entry_pc.ll Removed: llvm/trunk/test/DebugInfo/2010-03-22-CU-HighLow.ll Modified: llvm/trunk/lib/CodeGen/AsmPrinter/DwarfDebug.cpp Modified: llvm/trunk/lib/CodeGen/AsmPrinter/DwarfDebug.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/AsmPrinter/DwarfDebug.cpp?rev=102394&r1=102393&r2=102394&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/AsmPrinter/DwarfDebug.cpp (original) +++ llvm/trunk/lib/CodeGen/AsmPrinter/DwarfDebug.cpp Mon Apr 26 17:54:28 2010 @@ -1734,9 +1734,9 @@ addUInt(Die, dwarf::DW_AT_language, dwarf::DW_FORM_data1, DIUnit.getLanguage()); addString(Die, dwarf::DW_AT_name, dwarf::DW_FORM_string, FN); - addLabel(Die, dwarf::DW_AT_low_pc, dwarf::DW_FORM_addr, TextSectionSym); - addLabel(Die, dwarf::DW_AT_high_pc, dwarf::DW_FORM_addr, - Asm->GetTempSymbol("text_end")); + // Use DW_AT_entry_pc instead of DW_AT_low_pc/DW_AT_high_pc pair. This + // simplifies debug range entries. + addUInt(Die, dwarf::DW_AT_entry_pc, dwarf::DW_FORM_data4, 0); // DW_AT_stmt_list is a offset of line number information for this // compile unit in debug_line section. It is always zero when only one // compile unit is emitted in one object file. Removed: llvm/trunk/test/DebugInfo/2010-03-22-CU-HighLow.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/DebugInfo/2010-03-22-CU-HighLow.ll?rev=102393&view=auto ============================================================================== --- llvm/trunk/test/DebugInfo/2010-03-22-CU-HighLow.ll (original) +++ llvm/trunk/test/DebugInfo/2010-03-22-CU-HighLow.ll (removed) @@ -1,9 +0,0 @@ -; RUN: llc < %s | grep low_pc | count 2 - at i = global i32 1 ; [#uses=0] - -!llvm.dbg.gv = !{!0} - -!0 = metadata !{i32 524340, i32 0, metadata !1, metadata !"i", metadata !"i", metadata !"", metadata !1, i32 1, metadata !3, i1 false, i1 true, i32* @i} ; [ DW_TAG_variable ] -!1 = metadata !{i32 524329, metadata !"b.c", metadata !"/tmp", metadata !2} ; [ DW_TAG_file_type ] -!2 = metadata !{i32 524305, i32 0, i32 1, metadata !"b.c", metadata !"/tmp", metadata !"4.2.1 (Based on Apple Inc. build 5658) (LLVM build)", i1 true, i1 false, metadata !"", i32 0} ; [ DW_TAG_compile_unit ] -!3 = metadata !{i32 524324, metadata !1, metadata !"int", metadata !1, i32 0, i64 32, i64 32, i64 0, i32 0, i32 5} ; [ DW_TAG_base_type ] Added: llvm/trunk/test/DebugInfo/2010-04-25-CU-entry_pc.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/DebugInfo/2010-04-25-CU-entry_pc.ll?rev=102394&view=auto ============================================================================== --- llvm/trunk/test/DebugInfo/2010-04-25-CU-entry_pc.ll (added) +++ llvm/trunk/test/DebugInfo/2010-04-25-CU-entry_pc.ll Mon Apr 26 17:54:28 2010 @@ -0,0 +1,9 @@ +; RUN: llc < %s | grep entry_pc | count 2 + at i = global i32 1 ; [#uses=0] + +!llvm.dbg.gv = !{!0} + +!0 = metadata !{i32 524340, i32 0, metadata !1, metadata !"i", metadata !"i", metadata !"", metadata !1, i32 1, metadata !3, i1 false, i1 true, i32* @i} ; [ DW_TAG_variable ] +!1 = metadata !{i32 524329, metadata !"b.c", metadata !"/tmp", metadata !2} ; [ DW_TAG_file_type ] +!2 = metadata !{i32 524305, i32 0, i32 1, metadata !"b.c", metadata !"/tmp", metadata !"4.2.1 (Based on Apple Inc. build 5658) (LLVM build)", i1 true, i1 false, metadata !"", i32 0} ; [ DW_TAG_compile_unit ] +!3 = metadata !{i32 524324, metadata !1, metadata !"int", metadata !1, i32 0, i64 32, i64 32, i64 0, i32 0, i32 5} ; [ DW_TAG_base_type ] From bob.wilson at apple.com Mon Apr 26 17:56:56 2010 From: bob.wilson at apple.com (Bob Wilson) Date: Mon, 26 Apr 2010 22:56:56 -0000 Subject: [llvm-commits] [llvm] r102395 - /llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp Message-ID: <20100426225656.DC5ED312800A@llvm.org> Author: bwilson Date: Mon Apr 26 17:56:56 2010 New Revision: 102395 URL: http://llvm.org/viewvc/llvm-project?rev=102395&view=rev Log: Avoid adding a null MD node operand, which crashes with "-debug" when trying to print the operand. Modified: llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp Modified: llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp?rev=102395&r1=102394&r2=102395&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/InstrEmitter.cpp Mon Apr 26 17:56:56 2010 @@ -769,7 +769,8 @@ // Get the mdnode from the asm if it exists and add it to the instruction. SDValue MDV = Node->getOperand(InlineAsm::Op_MDNode); const MDNode *MD = cast(MDV)->getMD(); - MI->addOperand(MachineOperand::CreateMetadata(MD)); + if (MD) + MI->addOperand(MachineOperand::CreateMetadata(MD)); MBB->insert(InsertPos, MI); break; From bob.wilson at apple.com Mon Apr 26 18:20:08 2010 From: bob.wilson at apple.com (Bob Wilson) Date: Mon, 26 Apr 2010 23:20:08 -0000 Subject: [llvm-commits] [llvm] r102396 - in /llvm/trunk: lib/Target/ARM/Thumb2InstrInfo.cpp test/CodeGen/Thumb2/2010-04-26-CopyRegCrash.ll Message-ID: <20100426232008.4FEBD312800A@llvm.org> Author: bwilson Date: Mon Apr 26 18:20:08 2010 New Revision: 102396 URL: http://llvm.org/viewvc/llvm-project?rev=102396&view=rev Log: Handle register-to-register copies within the tGPR class. Radar 7896289 Added: llvm/trunk/test/CodeGen/Thumb2/2010-04-26-CopyRegCrash.ll Modified: llvm/trunk/lib/Target/ARM/Thumb2InstrInfo.cpp Modified: llvm/trunk/lib/Target/ARM/Thumb2InstrInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/Thumb2InstrInfo.cpp?rev=102396&r1=102395&r2=102396&view=diff ============================================================================== --- llvm/trunk/lib/Target/ARM/Thumb2InstrInfo.cpp (original) +++ llvm/trunk/lib/Target/ARM/Thumb2InstrInfo.cpp Mon Apr 26 18:20:08 2010 @@ -44,18 +44,22 @@ DebugLoc DL; if (I != MBB.end()) DL = I->getDebugLoc(); - if (DestRC == ARM::GPRRegisterClass && - SrcRC == ARM::GPRRegisterClass) { - BuildMI(MBB, I, DL, get(ARM::tMOVgpr2gpr), DestReg).addReg(SrcReg); - return true; - } else if (DestRC == ARM::GPRRegisterClass && - SrcRC == ARM::tGPRRegisterClass) { - BuildMI(MBB, I, DL, get(ARM::tMOVtgpr2gpr), DestReg).addReg(SrcReg); - return true; - } else if (DestRC == ARM::tGPRRegisterClass && - SrcRC == ARM::GPRRegisterClass) { - BuildMI(MBB, I, DL, get(ARM::tMOVgpr2tgpr), DestReg).addReg(SrcReg); - return true; + if (DestRC == ARM::GPRRegisterClass) { + if (SrcRC == ARM::GPRRegisterClass) { + BuildMI(MBB, I, DL, get(ARM::tMOVgpr2gpr), DestReg).addReg(SrcReg); + return true; + } else if (SrcRC == ARM::tGPRRegisterClass) { + BuildMI(MBB, I, DL, get(ARM::tMOVtgpr2gpr), DestReg).addReg(SrcReg); + return true; + } + } else if (DestRC == ARM::tGPRRegisterClass) { + if (SrcRC == ARM::GPRRegisterClass) { + BuildMI(MBB, I, DL, get(ARM::tMOVgpr2tgpr), DestReg).addReg(SrcReg); + return true; + } else if (SrcRC == ARM::tGPRRegisterClass) { + BuildMI(MBB, I, DL, get(ARM::tMOVr), DestReg).addReg(SrcReg); + return true; + } } // Handle SPR, DPR, and QPR copies. Added: llvm/trunk/test/CodeGen/Thumb2/2010-04-26-CopyRegCrash.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/Thumb2/2010-04-26-CopyRegCrash.ll?rev=102396&view=auto ============================================================================== --- llvm/trunk/test/CodeGen/Thumb2/2010-04-26-CopyRegCrash.ll (added) +++ llvm/trunk/test/CodeGen/Thumb2/2010-04-26-CopyRegCrash.ll Mon Apr 26 18:20:08 2010 @@ -0,0 +1,73 @@ +; RUN: llc < %s -mtriple=thumbv7-apple-darwin +; Radar 7896289 + +target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:64:64-v128:128:128-a0:0:32-n32" +target triple = "thumbv7-apple-darwin10" + +define arm_apcscc void @test(i32 %mode) nounwind optsize noinline { +entry: + br i1 undef, label %return, label %bb3 + +bb3: ; preds = %entry + br i1 undef, label %bb15, label %bb18 + +bb15: ; preds = %bb3 + unreachable + +bb18: ; preds = %bb3 + switch i32 %mode, label %return [ + i32 0, label %bb26 + i32 1, label %bb56 + i32 2, label %bb107 + i32 6, label %bb150.preheader + i32 9, label %bb310.preheader + i32 13, label %bb414.preheader + i32 15, label %bb468.preheader + i32 16, label %bb522.preheader + ] + +bb150.preheader: ; preds = %bb18 + br i1 undef, label %bb154, label %bb160 + +bb310.preheader: ; preds = %bb18 + unreachable + +bb414.preheader: ; preds = %bb18 + unreachable + +bb468.preheader: ; preds = %bb18 + unreachable + +bb522.preheader: ; preds = %bb18 + unreachable + +bb26: ; preds = %bb18 + unreachable + +bb56: ; preds = %bb18 + unreachable + +bb107: ; preds = %bb18 + br label %bb110 + +bb110: ; preds = %bb122, %bb107 + %asmtmp.i.i179 = tail call i16 asm "rev16 $0, $1\0A", "=l,l"(i16 undef) nounwind ; [#uses=1] + %asmtmp.i.i178 = tail call i16 asm "rev16 $0, $1\0A", "=l,l"(i16 %asmtmp.i.i179) nounwind ; [#uses=1] + store i16 %asmtmp.i.i178, i16* undef, align 2 + br i1 undef, label %bb122, label %bb121 + +bb121: ; preds = %bb110 + br label %bb122 + +bb122: ; preds = %bb121, %bb110 + br label %bb110 + +bb154: ; preds = %bb150.preheader + unreachable + +bb160: ; preds = %bb150.preheader + unreachable + +return: ; preds = %bb18, %entry + ret void +} From gohman at apple.com Mon Apr 26 18:36:52 2010 From: gohman at apple.com (Dan Gohman) Date: Mon, 26 Apr 2010 23:36:52 -0000 Subject: [llvm-commits] [llvm] r102399 - /llvm/trunk/docs/LangRef.html Message-ID: <20100426233652.C4234312800A@llvm.org> Author: djg Date: Mon Apr 26 18:36:52 2010 New Revision: 102399 URL: http://llvm.org/viewvc/llvm-project?rev=102399&view=rev Log: Integrate Jeffery Yasskin's suggestions with respect to traps flowing through memory references, add some text to better cover phi nodes and externally-visible side effects, add an example of instructions being control-dependent on a trap value, and reword some of the existing trap rules. Modified: llvm/trunk/docs/LangRef.html Modified: llvm/trunk/docs/LangRef.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/LangRef.html?rev=102399&r1=102398&r2=102399&view=diff ============================================================================== --- llvm/trunk/docs/LangRef.html (original) +++ llvm/trunk/docs/LangRef.html Mon Apr 26 18:36:52 2010 @@ -2332,25 +2332,74 @@ effects has nevertheless detected a condition which results in undefined behavior.

-

Any non-void instruction or constant expression other than a non-intrinsic - call, invoke, or phi with a trap operand has trap as its result value. - Any instruction with a trap operand which may have side effects emits - those side effects as if it had an undef operand instead.

+

Any value other than a non-intrinsic call, invoke, or phi with a trap + operand has trap as its result value. Any instruction with + a trap operand which may have side effects emits those side effects as + if it had an undef operand instead. If the side effects are externally + visible, the behavior is undefined.

+ +

Trap values may be stored to memory; a load from memory including any + part of a trap value results in a (full) trap value.

+ +

For example:

+ + + +
+
+%trap = sub nuw i32 0, 1           ; Results in a trap value.
+%still_trap = and i32 %trap, 0     ; Whereas (and i32 undef, 0) would return 0.
+%trap_yet_again = getelementptr i32* @h, i32 %still_trap
+store i32 0, i32* %trap_yet_again  ; undefined behavior
+
+volatile store i32 %trap, i32* @g  ; External observation; undefined behavior.
+%trap2 = load i32* @g              ; Returns a trap value, not just undef.
+%narrowaddr = bitcast i32* @g to i16*
+%wideaddr = bitcast i32* @g to i64*
+%trap3 = load 16* %narrowaddr      ; Returns a trap value
+%trap4 = load i64* %widaddr        ; Returns a trap value, not partial trap.
+
+

If a br or switch instruction has a trap value operand, all non-phi non-void instructions which control-depend on it - have trap as their result value. If any instruction which - control-depends on the br or switch invokes externally - visible side effects, the behavior of the program is undefined.

+ have trap as their result value. A phi + node with an incoming value associated with a control edge which is + control-dependent on it has trap as its result value when control is + transferred from that block. If any instruction which control-depends + on the br or switch invokes externally visible side + effects, the behavior of the program is undefined. For example:

-

For example, an and of a trap value with - zero still has a trap value result. Using that value as an index in a - getelementptr yields a trap - result. Using that result as the address of a - store produces undefined behavior.

+
+
+entry:
+  %trap = sub nuw i32 0, 1           ; Results in a trap value.
+  %cmp = icmp i32 slt %trap, 0       ; Still trap.
+  %br i1 %cmp, %true, %end           ; Branch to either destination.
+
+true:
+  volatile store i32 0, i32* @g      ; Externally visible side effects
+                                     ; control-dependent on %cmp.
+                                     ; Undefined behavior.
+  br label %end
+
+end:
+  %p = phi i32 [ 0, %entry ], [ 1, %true ]
+                                     ; Both edges into this PHI are
+                                     ; control-dependent on %cmp, so this
+                                     ; results in a trap value.
+
+  volatile store i32 0, i32* @g      ; %end is control-equivalent to %entry
+                                     ; so this is defined (ignoring earlier
+                                     ; undefined behavior in this example).
+
+
+

There is currently no way of representing a trap constant in the IR; they only exist when produced by certain instructions, such as an From sabre at nondot.org Mon Apr 26 18:37:21 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 23:37:21 -0000 Subject: [llvm-commits] [llvm] r102400 - in /llvm/trunk: include/llvm/Target/TargetInstrInfo.h lib/CodeGen/AsmPrinter/AsmPrinter.cpp lib/Target/X86/X86InstrInfo.cpp lib/Target/X86/X86InstrInfo.h test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll test/CodeGen/X86/2008-01-25-EmptyFunction.ll Message-ID: <20100426233721.D61E1312800A@llvm.org> Author: lattner Date: Mon Apr 26 18:37:21 2010 New Revision: 102400 URL: http://llvm.org/viewvc/llvm-project?rev=102400&view=rev Log: on darwin empty functions need to codegen into something of non-zero length, otherwise labels get incorrectly merged. We handled this by emitting a ".byte 0", but this isn't correct on thumb/arm targets where the text segment needs to be a multiple of 2/4 bytes. Handle this by emitting a noop. This is more gross than it should be because arm/ppc are not fully mc'ized yet. This fixes rdar://7908505 Modified: llvm/trunk/include/llvm/Target/TargetInstrInfo.h llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp llvm/trunk/lib/Target/X86/X86InstrInfo.cpp llvm/trunk/lib/Target/X86/X86InstrInfo.h llvm/trunk/test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll llvm/trunk/test/CodeGen/X86/2008-01-25-EmptyFunction.ll Modified: llvm/trunk/include/llvm/Target/TargetInstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetInstrInfo.h?rev=102400&r1=102399&r2=102400&view=diff ============================================================================== --- llvm/trunk/include/llvm/Target/TargetInstrInfo.h (original) +++ llvm/trunk/include/llvm/Target/TargetInstrInfo.h Mon Apr 26 18:37:21 2010 @@ -24,6 +24,7 @@ class MCAsmInfo; class MachineMemOperand; class MDNode; +class MCInst; class SDNode; class SelectionDAG; class TargetRegisterClass; @@ -490,6 +491,13 @@ virtual void insertNoop(MachineBasicBlock &MBB, MachineBasicBlock::iterator MI) const; + + /// getNoopForMachoTarget - Return the noop instruction to use for a noop. + virtual void getNoopForMachoTarget(MCInst &NopInst) const { + // Default to just using 'nop' string. + } + + /// isPredicated - Returns true if the instruction is already predicated. /// virtual bool isPredicated(const MachineInstr *MI) const { Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp?rev=102400&r1=102399&r2=102400&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp (original) +++ llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp Mon Apr 26 18:37:21 2010 @@ -585,9 +585,15 @@ // If the function is empty and the object file uses .subsections_via_symbols, // then we need to emit *something* to the function body to prevent the - // labels from collapsing together. Just emit a 0 byte. - if (MAI->hasSubsectionsViaSymbols() && !HasAnyRealCode) - OutStreamer.EmitIntValue(0, 1, 0/*addrspace*/); + // labels from collapsing together. Just emit a noop. + if (MAI->hasSubsectionsViaSymbols() && !HasAnyRealCode) { + MCInst Noop; + TM.getInstrInfo()->getNoopForMachoTarget(Noop); + if (Noop.getOpcode()) + OutStreamer.EmitInstruction(Noop); + else // Target not mc-ized yet. + OutStreamer.EmitRawText(StringRef("\tnop\n")); + } // Emit target-specific gunk after the function body. EmitFunctionBodyEnd(); Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=102400&r1=102399&r2=102400&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original) +++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Mon Apr 26 18:37:21 2010 @@ -27,6 +27,7 @@ #include "llvm/CodeGen/MachineRegisterInfo.h" #include "llvm/CodeGen/LiveVariables.h" #include "llvm/CodeGen/PseudoSourceValue.h" +#include "llvm/MC/MCInst.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Debug.h" #include "llvm/Support/ErrorHandling.h" @@ -3766,3 +3767,9 @@ assert(table && "Cannot change domain"); MI->setDesc(get(table[Domain-1])); } + +/// getNoopForMachoTarget - Return the noop instruction to use for a noop. +void X86InstrInfo::getNoopForMachoTarget(MCInst &NopInst) const { + NopInst.setOpcode(X86::NOOP); +} + Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.h?rev=102400&r1=102399&r2=102400&view=diff ============================================================================== --- llvm/trunk/lib/Target/X86/X86InstrInfo.h (original) +++ llvm/trunk/lib/Target/X86/X86InstrInfo.h Mon Apr 26 18:37:21 2010 @@ -693,6 +693,8 @@ int64_t Offset1, int64_t Offset2, unsigned NumLoads) const; + virtual void getNoopForMachoTarget(MCInst &NopInst) const; + virtual bool ReverseBranchCondition(SmallVectorImpl &Cond) const; Modified: llvm/trunk/test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll?rev=102400&r1=102399&r2=102400&view=diff ============================================================================== --- llvm/trunk/test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll (original) +++ llvm/trunk/test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll Mon Apr 26 18:37:21 2010 @@ -1,4 +1,4 @@ -; RUN: llc < %s -march=ppc32 | grep .byte +; RUN: llc < %s -march=ppc32 | grep nop target triple = "powerpc-apple-darwin8" Modified: llvm/trunk/test/CodeGen/X86/2008-01-25-EmptyFunction.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/2008-01-25-EmptyFunction.ll?rev=102400&r1=102399&r2=102400&view=diff ============================================================================== --- llvm/trunk/test/CodeGen/X86/2008-01-25-EmptyFunction.ll (original) +++ llvm/trunk/test/CodeGen/X86/2008-01-25-EmptyFunction.ll Mon Apr 26 18:37:21 2010 @@ -1,4 +1,4 @@ -; RUN: llc < %s -march=x86 | grep {.byte 0} +; RUN: llc < %s -march=x86 | grep nop target triple = "i686-apple-darwin8" From sabre at nondot.org Mon Apr 26 18:41:43 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 23:41:43 -0000 Subject: [llvm-commits] [llvm] r102401 - /llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp Message-ID: <20100426234143.E9615312800A@llvm.org> Author: lattner Date: Mon Apr 26 18:41:43 2010 New Revision: 102401 URL: http://llvm.org/viewvc/llvm-project?rev=102401&view=rev Log: add a comment in verbose-asm mode indicating why a noop is being generated. Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp Modified: llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp?rev=102401&r1=102400&r2=102401&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp (original) +++ llvm/trunk/lib/CodeGen/AsmPrinter/AsmPrinter.cpp Mon Apr 26 18:41:43 2010 @@ -589,9 +589,10 @@ if (MAI->hasSubsectionsViaSymbols() && !HasAnyRealCode) { MCInst Noop; TM.getInstrInfo()->getNoopForMachoTarget(Noop); - if (Noop.getOpcode()) + if (Noop.getOpcode()) { + OutStreamer.AddComment("avoids zero-length function"); OutStreamer.EmitInstruction(Noop); - else // Target not mc-ized yet. + } else // Target not mc-ized yet. OutStreamer.EmitRawText(StringRef("\tnop\n")); } From sabre at nondot.org Mon Apr 26 18:49:33 2010 From: sabre at nondot.org (Chris Lattner) Date: Mon, 26 Apr 2010 23:49:33 -0000 Subject: [llvm-commits] [llvm] r102402 - in /llvm/trunk: include/llvm/Transforms/Scalar.h lib/Transforms/Utils/LowerInvoke.cpp Message-ID: <20100426234933.23EBA312800A@llvm.org> Author: lattner Date: Mon Apr 26 18:49:32 2010 New Revision: 102402 URL: http://llvm.org/viewvc/llvm-project?rev=102402&view=rev Log: Fix a problem that lower invoke has with allocas (PR6694), and add a version of createLowerInvokePass that allows the client to specify whether it wants "expensive" or "cheap" lowering. Patch by Alex Mac! Modified: llvm/trunk/include/llvm/Transforms/Scalar.h llvm/trunk/lib/Transforms/Utils/LowerInvoke.cpp Modified: llvm/trunk/include/llvm/Transforms/Scalar.h URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Transforms/Scalar.h?rev=102402&r1=102401&r2=102402&view=diff ============================================================================== --- llvm/trunk/include/llvm/Transforms/Scalar.h (original) +++ llvm/trunk/include/llvm/Transforms/Scalar.h Mon Apr 26 18:49:32 2010 @@ -241,6 +241,8 @@ // lowering pass. // FunctionPass *createLowerInvokePass(const TargetLowering *TLI = 0); +FunctionPass *createLowerInvokePass(const TargetLowering *TLI, + bool useExpensiveEHSupport); extern const PassInfo *const LowerInvokePassID; //===----------------------------------------------------------------------===// Modified: llvm/trunk/lib/Transforms/Utils/LowerInvoke.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Utils/LowerInvoke.cpp?rev=102402&r1=102401&r2=102402&view=diff ============================================================================== --- llvm/trunk/lib/Transforms/Utils/LowerInvoke.cpp (original) +++ llvm/trunk/lib/Transforms/Utils/LowerInvoke.cpp Mon Apr 26 18:49:32 2010 @@ -70,15 +70,18 @@ // Used for expensive EH support. const Type *JBLinkTy; GlobalVariable *JBListHead; - Constant *SetJmpFn, *LongJmpFn; + Constant *SetJmpFn, *LongJmpFn, *StackSaveFn, *StackRestoreFn; + bool useExpensiveEHSupport; // We peek in TLI to grab the target's jmp_buf size and alignment const TargetLowering *TLI; public: static char ID; // Pass identification, replacement for typeid - explicit LowerInvoke(const TargetLowering *tli = NULL) - : FunctionPass(&ID), TLI(tli) { } + explicit LowerInvoke(const TargetLowering *tli = NULL, + bool useExpensiveEHSupport = ExpensiveEHSupport) + : FunctionPass(&ID), useExpensiveEHSupport(useExpensiveEHSupport), + TLI(tli) { } bool doInitialization(Module &M); bool runOnFunction(Function &F); @@ -94,7 +97,8 @@ bool insertCheapEHSupport(Function &F); void splitLiveRangesLiveAcrossInvokes(std::vector &Invokes); void rewriteExpensiveInvoke(InvokeInst *II, unsigned InvokeNo, - AllocaInst *InvokeNum, SwitchInst *CatchSwitch); + AllocaInst *InvokeNum, AllocaInst *StackPtr, + SwitchInst *CatchSwitch); bool insertExpensiveEHSupport(Function &F); }; } @@ -107,7 +111,11 @@ // Public Interface To the LowerInvoke pass. FunctionPass *llvm::createLowerInvokePass(const TargetLowering *TLI) { - return new LowerInvoke(TLI); + return new LowerInvoke(TLI, ExpensiveEHSupport); +} +FunctionPass *llvm::createLowerInvokePass(const TargetLowering *TLI, + bool useExpensiveEHSupport) { + return new LowerInvoke(TLI, useExpensiveEHSupport); } // doInitialization - Make sure that there is a prototype for abort in the @@ -116,7 +124,7 @@ const Type *VoidPtrTy = Type::getInt8PtrTy(M.getContext()); AbortMessage = 0; - if (ExpensiveEHSupport) { + if (useExpensiveEHSupport) { // Insert a type for the linked list of jump buffers. unsigned JBSize = TLI ? TLI->getJumpBufSize() : 0; JBSize = JBSize ? JBSize : 200; @@ -160,6 +168,8 @@ #endif LongJmpFn = Intrinsic::getDeclaration(&M, Intrinsic::longjmp); + StackSaveFn = Intrinsic::getDeclaration(&M, Intrinsic::stacksave); + StackRestoreFn = Intrinsic::getDeclaration(&M, Intrinsic::stackrestore); } // We need the 'write' and 'abort' functions for both models. @@ -175,7 +185,7 @@ } void LowerInvoke::createAbortMessage(Module *M) { - if (ExpensiveEHSupport) { + if (useExpensiveEHSupport) { // The abort message for expensive EH support tells the user that the // program 'unwound' without an 'invoke' instruction. Constant *Msg = @@ -229,7 +239,8 @@ std::vector CallArgs(II->op_begin(), II->op_end() - 3); // Insert a normal call instruction... CallInst *NewCall = CallInst::Create(II->getCalledValue(), - CallArgs.begin(), CallArgs.end(), "",II); + CallArgs.begin(), CallArgs.end(), + "",II); NewCall->takeName(II); NewCall->setCallingConv(II->getCallingConv()); NewCall->setAttributes(II->getAttributes()); @@ -270,6 +281,7 @@ /// specified invoke instruction with a call. void LowerInvoke::rewriteExpensiveInvoke(InvokeInst *II, unsigned InvokeNo, AllocaInst *InvokeNum, + AllocaInst *StackPtr, SwitchInst *CatchSwitch) { ConstantInt *InvokeNoC = ConstantInt::get(Type::getInt32Ty(II->getContext()), InvokeNo); @@ -288,12 +300,22 @@ // Insert a store of the invoke num before the invoke and store zero into the // location afterward. new StoreInst(InvokeNoC, InvokeNum, true, II); // volatile + + // Insert a store of the stack ptr before the invoke, so we can restore it + // later in the exception case. + CallInst* StackSaveRet = CallInst::Create(StackSaveFn, "ssret", II); + new StoreInst(StackSaveRet, StackPtr, true, II); // volatile BasicBlock::iterator NI = II->getNormalDest()->getFirstNonPHI(); // nonvolatile. new StoreInst(Constant::getNullValue(Type::getInt32Ty(II->getContext())), InvokeNum, false, NI); + Instruction* StackPtrLoad = new LoadInst(StackPtr, "stackptr.restore", true, + II->getUnwindDest()->getFirstNonPHI() + ); + CallInst::Create(StackRestoreFn, StackPtrLoad, "")->insertAfter(StackPtrLoad); + // Add a switch case to our unwind block. CatchSwitch->addCase(InvokeNoC, II->getUnwindDest()); @@ -500,6 +522,12 @@ BasicBlock *CatchBB = BasicBlock::Create(F.getContext(), "setjmp.catch", &F); + // Create an alloca which keeps track of the stack pointer before every + // invoke, this allows us to properly restore the stack pointer after + // long jumping. + AllocaInst *StackPtr = new AllocaInst(Type::getInt8PtrTy(F.getContext()), 0, + "stackptr", EntryBB->begin()); + // Create an alloca which keeps track of which invoke is currently // executing. For normal calls it contains zero. AllocaInst *InvokeNum = new AllocaInst(Type::getInt32Ty(F.getContext()), 0, @@ -546,7 +574,7 @@ // At this point, we are all set up, rewrite each invoke instruction. for (unsigned i = 0, e = Invokes.size(); i != e; ++i) - rewriteExpensiveInvoke(Invokes[i], i+1, InvokeNum, CatchSwitch); + rewriteExpensiveInvoke(Invokes[i], i+1, InvokeNum, StackPtr, CatchSwitch); } // We know that there is at least one unwind. @@ -622,7 +650,7 @@ } bool LowerInvoke::runOnFunction(Function &F) { - if (ExpensiveEHSupport) + if (useExpensiveEHSupport) return insertExpensiveEHSupport(F); else return insertCheapEHSupport(F); From dalej at apple.com Mon Apr 26 19:01:42 2010 From: dalej at apple.com (Dale Johannesen) Date: Tue, 27 Apr 2010 00:01:42 -0000 Subject: [llvm-commits] [llvm] r102404 - /llvm/trunk/test/DebugInfo/2010-04-13-PubType.ll Message-ID: <20100427000142.70AE6312800A@llvm.org> Author: johannes Date: Mon Apr 26 19:01:42 2010 New Revision: 102404 URL: http://llvm.org/viewvc/llvm-project?rev=102404&view=rev Log: Un-XFAIL this on ppc. My enabling of dbg_declare handling in ISel fixed it. Modified: llvm/trunk/test/DebugInfo/2010-04-13-PubType.ll Modified: llvm/trunk/test/DebugInfo/2010-04-13-PubType.ll URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/DebugInfo/2010-04-13-PubType.ll?rev=102404&r1=102403&r2=102404&view=diff ============================================================================== --- llvm/trunk/test/DebugInfo/2010-04-13-PubType.ll (original) +++ llvm/trunk/test/DebugInfo/2010-04-13-PubType.ll Mon Apr 26 19:01:42 2010 @@ -2,7 +2,6 @@ ; RUN: grep "External Name" %t | grep -v X ; RUN: grep "External Name" %t | grep Y | count 1 ; Test to check type with no defintion is listed in pubtypes section. -; XFAIL: powerpc %struct.X = type opaque %struct.Y = type { i32 } From dalej at apple.com Mon Apr 26 19:36:05 2010 From: dalej at apple.com (Dale Johannesen) Date: Mon, 26 Apr 2010 17:36:05 -0700 Subject: [llvm-commits] [llvm] r102400 - in /llvm/trunk: include/llvm/Target/TargetInstrInfo.h lib/CodeGen/AsmPrinter/AsmPrinter.cpp lib/Target/X86/X86InstrInfo.cpp lib/Target/X86/X86InstrInfo.h test/CodeGen/PowerPC/2008-01-25-EmptyFunction.ll test/CodeGen/X86/2008-01-25-EmptyFunction.ll In-Reply-To: <20100426233721.D61E1312800A@llvm.org> References: <20100426233721.D61E1312800A@llvm.org> Message-ID: <95C9934A-9CA9-485C-8792-CEE2309B860B@apple.com> On Apr 26, 2010, at 4:37 PM, Chris Lattner wrote: > Author: lattner > Date: Mon Apr 26 18:37:21 2010 > New Revision: 102400 > > URL: http://llvm.org/viewvc/llvm-project?rev=102400&view=rev > Log: > on darwin empty functions need to codegen into something of non-zero > length, > otherwise labels get incorrectly merged. We handled this by > emitting a > ".byte 0", but this isn't correct on thumb/arm targets where the > text segment > needs to be a multiple of 2/4 bytes. Handle this by emitting a > noop. This > is more gross than it should be because arm/ppc are not fully > mc'ized yet. Interestingly enough, we have a similar regression with zero-length arrays. I don't suppose you fixed that too, did you? Looks more like a FE (llvm-gcc) bug. int x[0]; struct {} y; struct { struct {}a[0]; } s12; Works in C, not in C++. (Analyzed by Nick in 7886017.) From isanbard at gmail.com Mon Apr 26 19:55:25 2010 From: isanbard at gmail.com (Bill Wendling) Date: Tue, 27 Apr 2010 00:55:25 -0000 Subject: [llvm-commits] [llvm] r102405 - /llvm/trunk/tools/lto/LTOCodeGenerator.cpp Message-ID: <20100427005525.5235D312800A@llvm.org> Author: void Date: Mon Apr 26 19:55:25 2010 New Revision: 102405 URL: http://llvm.org/viewvc/llvm-project?rev=102405&view=rev Log: r98363 deleted a '!' when cleaning up whitespace. This caused globals which are *not* declarations to *not* be placed in the "preserve" list. Modified: llvm/trunk/tools/lto/LTOCodeGenerator.cpp Modified: llvm/trunk/tools/lto/LTOCodeGenerator.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/lto/LTOCodeGenerator.cpp?rev=102405&r1=102404&r2=102405&view=diff ============================================================================== --- llvm/trunk/tools/lto/LTOCodeGenerator.cpp (original) +++ llvm/trunk/tools/lto/LTOCodeGenerator.cpp Mon Apr 26 19:55:25 2010 @@ -328,7 +328,7 @@ } for (Module::global_iterator v = mergedModule->global_begin(), e = mergedModule->global_end(); v != e; ++v) { - if (v->isDeclaration() && + if (!v->isDeclaration() && _mustPreserveSymbols.count(mangler.getNameWithPrefix(v))) mustPreserveList.push_back(::strdup(v->getNameStr().c_str())); } From gohman at apple.com Mon Apr 26 20:23:48 2010 From: gohman at apple.com (Dan Gohman) Date: Tue, 27 Apr 2010 01:23:48 -0000 Subject: [llvm-commits] [test-suite] r102408 - /test-suite/trunk/TEST.nightly.Makefile Message-ID: <20100427012348.87119312800A@llvm.org> Author: djg Date: Mon Apr 26 20:23:48 2010 New Revision: 102408 URL: http://llvm.org/viewvc/llvm-project?rev=102408&view=rev Log: Add semicolons to fix an apparent cut+pasto. Modified: test-suite/trunk/TEST.nightly.Makefile Modified: test-suite/trunk/TEST.nightly.Makefile URL: http://llvm.org/viewvc/llvm-project/test-suite/trunk/TEST.nightly.Makefile?rev=102408&r1=102407&r2=102408&view=diff ============================================================================== --- test-suite/trunk/TEST.nightly.Makefile (original) +++ test-suite/trunk/TEST.nightly.Makefile Mon Apr 26 20:23:48 2010 @@ -61,7 +61,7 @@ Output/%.nightly.llc.report.txt: Output/%.exe-llc @echo > $@ @-if test -f Output/$*.exe-llc; then \ - head -n 100 Output/$*.exe-llc >> $@ \ + head -n 100 Output/$*.exe-llc >> $@; \ echo "TEST-PASS: llc $(RELDIR)/$*" >> $@;\ printf "TEST-RESULT-llc: " >> $@;\ grep "Total Execution Time" Output/$*.llc.s.info | tail -n 1 >> $@;\ @@ -77,7 +77,7 @@ Output/%.nightly.llc-beta.report.txt: Output/%.llvm.bc Output/%.exe-llc-beta @echo > $@ @-if test -f Output/$*.exe-llc-beta; then \ - head -n 100 Output/$*.exe-llc-beta >> $@ \ + head -n 100 Output/$*.exe-llc-beta >> $@; \ echo "TEST-PASS: llc-beta $(RELDIR)/$*" >> $@;\ printf "TEST-RESULT-llc-beta: " >> $@;\ grep "Total Execution Time" Output/$*.llc-beta.s.info | tail -n 1 >> $@;\ @@ -93,7 +93,7 @@ Output/%.nightly.opt-beta.report.txt: Output/%.exe-opt-beta @echo > $@ @-if test -f Output/$*.exe-opt-beta; then \ - head -n 100 Output/$*.exe-opt-beta >> $@ \ + head -n 100 Output/$*.exe-opt-beta >> $@; \ echo "TEST-PASS: opt-beta $(RELDIR)/$*" >> $@;\ printf "TEST-RESULT-opt-beta: " >> $@;\ grep "Total Execution Time" Output/$*.opt-beta.s.info | tail -n 1 >> $@;\ @@ -109,7 +109,7 @@ Output/%.nightly.cbe.report.txt: Output/%.exe-cbe @echo > $@ @-if test -f Output/$*.exe-cbe; then \ - head -n 100 Output/$*.exe-cbe >> $@ \ + head -n 100 Output/$*.exe-cbe >> $@; \ echo "TEST-PASS: cbe $(RELDIR)/$*" >> $@;\ printf "TEST-RESULT-cbe-time: " >> $@;\ grep "^program" Output/$*.out-cbe.time >> $@;\ @@ -123,7 +123,7 @@ Output/%.nightly.jit.report.txt: Output/%.exe-jit @echo > $@ @-if test -f Output/$*.exe-jit; then \ - head -n 100 Output/$*.exe-jit >> $@ \ + head -n 100 Output/$*.exe-jit >> $@; \ echo "TEST-PASS: jit $(RELDIR)/$*" >> $@;\ printf "TEST-RESULT-jit-time: " >> $@;\ grep "^program" Output/$*.out-jit.time >> $@;\ From dalej at apple.com Mon Apr 26 21:10:05 2010 From: dalej at apple.com (Dale Johannesen) Date: Tue, 27 Apr 2010 02:10:05 -0000 Subject: [llvm-commits] [llvm] r102410 - /llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Message-ID: <20100427021005.C6716312800A@llvm.org> Author: johannes Date: Mon Apr 26 21:10:05 2010 New Revision: 102410 URL: http://llvm.org/viewvc/llvm-project?rev=102410&view=rev Log: Revert a small part of 102372; this fixes at least one of the dbg testsuite regressions. I don't think this is really the right fix; this change exposed an existing problem upstream somewhere. Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp?rev=102410&r1=102409&r2=102410&view=diff ============================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp (original) +++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Mon Apr 26 21:10:05 2010 @@ -3834,10 +3834,15 @@ return 0; DAG.AddDbgValue(SDV, N.getNode(), isParameter); } else { + // Generating Undefs here seems to be actively harmful because it + // affects the line numbers. + return 0; +#if 0 // This isn't useful, but it shows what we're missing. SDV = DAG.getDbgValue(Variable, UndefValue::get(Address->getType()), 0, dl, SDNodeOrder); DAG.AddDbgValue(SDV, 0, isParameter); +#endif } return 0; } From kalle.raiskila at nokia.com Mon Apr 26 05:01:08 2010 From: kalle.raiskila at nokia.com (Kalle Raiskila) Date: Mon, 26 Apr 2010 13:01:08 +0300 Subject: [llvm-commits] [llvm] r99160 - in /llvm/trunk: lib/VMCore/ConstantsContext.h lib/VMCore/LLVMContextImpl.cpp tools/bugpoint/BugDriver.cpp tools/bugpoint/BugDriver.h In-Reply-To: <20100322052338.207252A6C12C@llvm.org> References: <20100322052338.207252A6C12C@llvm.org> Message-ID: <4BD56464.5020402@nokia.com> Hi, sorry to drag up this old commit, but this makes bugpoint segfault for me. The testcase I have causes a misscompilation only on SPU, and I cannot reproduce this error on the other platforms (i.e. x86). I'd be happy to help to try to track down this issue, in case you don't have a CellBE handy :) Or should I just open a PR? Last lines that bugpoint spews out are below. kalle *** Attempting to perform final cleanups: Emitted bitcode to 'bugpoint-reduced-simplified.bc' While deleting: [22 x float] % Use still stuck around after Def is destroyed:@vconst = constant [22 x float] [float 0 bugpoint 0x104c6e08 1 bugpoint 0x104c76f0 2 0x00100344 __kernel_sigtramp32 + 0 3 bugpoint 0x100ca954 llvm::raw_ostream::operator<<(char) + 100 4 bugpoint 0x103a8038 5 bugpoint 0x103a2f38 6 bugpoint 0x103a56e8 7 bugpoint 0x103a2c6c llvm::Value::print(llvm::raw_ostream&, llvm::AssemblyAnnotationWriter*) const + 1516 8 bugpoint 0x10453ac8 llvm::Value::~Value() + 536 9 bugpoint 0x103c90e4 llvm::ConstantArray::~ConstantArray() + 148 10 bugpoint 0x1041488c llvm::LLVMContextImpl::~LLVMContextImpl() + 972 11 bugpoint 0x10411658 llvm::LLVMContext::~LLVMContext() + 56 12 bugpoint 0x10411d70 llvm::object_deleter::call(void*) + 48 13 bugpoint 0x104a0750 llvm::ManagedStaticBase::destroy() const + 96 14 bugpoint 0x104a07e4 llvm::llvm_shutdown() + 68 15 bugpoint 0x100d8e5c main + 396 16 libc.so.6 0x0fbfdb24 17 libc.so.6 0x0fbfdce0 Stack dump: 0. Program arguments: bugpoint mrfir-all.ll -run-llc -safe-run-cbe --tool-args --march=cellspu Segmentation fault Jeffrey Yasskin skrev: > Author: jyasskin > Date: Mon Mar 22 00:23:37 2010 > New Revision: 99160 > > URL: http://llvm.org/viewvc/llvm-project?rev=99160&view=rev > Log: > Free all Constants in ~LLVMConstantImpl. We avoid assertion failures > by dropping all references from all constants that can use other > constants before trying to destroy any of them. > > I also had to free bugpoint's Module in ~BugDriver(). > > > Modified: > llvm/trunk/lib/VMCore/ConstantsContext.h > llvm/trunk/lib/VMCore/LLVMContextImpl.cpp > llvm/trunk/tools/bugpoint/BugDriver.cpp > llvm/trunk/tools/bugpoint/BugDriver.h > > Modified: llvm/trunk/lib/VMCore/ConstantsContext.h > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/VMCore/ConstantsContext.h?rev=99160&r1=99159&r2=99160&view=diff > ============================================================================== > --- llvm/trunk/lib/VMCore/ConstantsContext.h (original) > +++ llvm/trunk/lib/VMCore/ConstantsContext.h Mon Mar 22 00:23:37 2010 > @@ -600,8 +600,8 @@ > void freeConstants() { > for (typename MapTy::iterator I=Map.begin(), E=Map.end(); > I != E; ++I) { > - if (I->second->use_empty()) > - delete I->second; > + // Asserts that use_empty(). > + delete I->second; > } > } > > > Modified: llvm/trunk/lib/VMCore/LLVMContextImpl.cpp > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/VMCore/LLVMContextImpl.cpp?rev=99160&r1=99159&r2=99160&view=diff > ============================================================================== > --- llvm/trunk/lib/VMCore/LLVMContextImpl.cpp (original) > +++ llvm/trunk/lib/VMCore/LLVMContextImpl.cpp Mon Mar 22 00:23:37 2010 > @@ -12,6 +12,7 @@ > //===----------------------------------------------------------------------===// > > #include "LLVMContextImpl.h" > +#include > > LLVMContextImpl::LLVMContextImpl(LLVMContext &C) > : TheTrueVal(0), TheFalseVal(0), > @@ -34,10 +35,32 @@ > OpaqueTypes.insert(AlwaysOpaqueTy); > } > > +namespace { > +struct DropReferences { > + // Takes the value_type of a ConstantUniqueMap's internal map, whose 'second' > + // is a Constant*. > + template > + void operator()(const PairT &P) { > + P.second->dropAllReferences(); > + } > +}; > +} > + > LLVMContextImpl::~LLVMContextImpl() { > + std::for_each(ExprConstants.map_begin(), ExprConstants.map_end(), > + DropReferences()); > + std::for_each(ArrayConstants.map_begin(), ArrayConstants.map_end(), > + DropReferences()); > + std::for_each(StructConstants.map_begin(), StructConstants.map_end(), > + DropReferences()); > + std::for_each(UnionConstants.map_begin(), UnionConstants.map_end(), > + DropReferences()); > + std::for_each(VectorConstants.map_begin(), VectorConstants.map_end(), > + DropReferences()); > ExprConstants.freeConstants(); > ArrayConstants.freeConstants(); > StructConstants.freeConstants(); > + UnionConstants.freeConstants(); > VectorConstants.freeConstants(); > AggZeroConstants.freeConstants(); > NullPtrConstants.freeConstants(); > @@ -45,13 +68,11 @@ > InlineAsms.freeConstants(); > for (IntMapTy::iterator I = IntConstants.begin(), E = IntConstants.end(); > I != E; ++I) { > - if (I->second->use_empty()) > - delete I->second; > + delete I->second; > } > for (FPMapTy::iterator I = FPConstants.begin(), E = FPConstants.end(); > I != E; ++I) { > - if (I->second->use_empty()) > - delete I->second; > + delete I->second; > } > AlwaysOpaqueTy->dropRef(); > for (OpaqueTypesTy::iterator I = OpaqueTypes.begin(), E = OpaqueTypes.end(); > > Modified: llvm/trunk/tools/bugpoint/BugDriver.cpp > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/bugpoint/BugDriver.cpp?rev=99160&r1=99159&r2=99160&view=diff > ============================================================================== > --- llvm/trunk/tools/bugpoint/BugDriver.cpp (original) > +++ llvm/trunk/tools/bugpoint/BugDriver.cpp Mon Mar 22 00:23:37 2010 > @@ -75,6 +75,10 @@ > run_as_child(as_child), run_find_bugs(find_bugs), Timeout(timeout), > MemoryLimit(memlimit), UseValgrind(use_valgrind) {} > > +BugDriver::~BugDriver() { > + delete Program; > +} > + > > /// ParseInputFile - Given a bitcode or assembly input filename, parse and > /// return it, or return null if not possible. > > Modified: llvm/trunk/tools/bugpoint/BugDriver.h > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/bugpoint/BugDriver.h?rev=99160&r1=99159&r2=99160&view=diff > ============================================================================== > --- llvm/trunk/tools/bugpoint/BugDriver.h (original) > +++ llvm/trunk/tools/bugpoint/BugDriver.h Mon Mar 22 00:23:37 2010 > @@ -65,6 +65,7 @@ > BugDriver(const char *toolname, bool as_child, bool find_bugs, > unsigned timeout, unsigned memlimit, bool use_valgrind, > LLVMContext& ctxt); > + ~BugDriver(); > > const char *getToolName() const { return ToolName; } > > > > _______________________________________________ > llvm-commits mailing list > llvm-commits at cs.uiuc.edu > http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits > From tonic at nondot.org Tue Apr 27 01:56:14 2010 From: tonic at nondot.org (Tanya Lattner) Date: Tue, 27 Apr 2010 06:56:14 -0000 Subject: [llvm-commits] [test-suite] r102415 - /test-suite/tags/RELEASE_27/ Message-ID: <20100427065614.30E09312800A@llvm.org> Author: tbrethou Date: Tue Apr 27 01:56:14 2010 New Revision: 102415 URL: http://llvm.org/viewvc/llvm-project?rev=102415&view=rev Log: Tag 2.7 Added: test-suite/tags/RELEASE_27/ - copied from r102414, test-suite/branches/release_27/ From sabre at nondot.org Tue Apr 27 01:57:10 2010 From: sabre at nondot.org (Chris Lattner) Date: Tue, 27 Apr 2010 06:57:10 -0000 Subject: [llvm-commits] [llvm] r102417 - /llvm/trunk/docs/ReleaseNotes.html Message-ID: <20100427065710.5DFAA312800A@llvm.org> Author: lattner Date: Tue Apr 27 01:57:10 2010 New Revision: 102417 URL: http://llvm.org/viewvc/llvm-project?rev=102417&view=rev Log: remove some comments. Modified: llvm/trunk/docs/ReleaseNotes.html Modified: llvm/trunk/docs/ReleaseNotes.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/ReleaseNotes.html?rev=102417&r1=102416&r2=102417&view=diff ============================================================================== --- llvm/trunk/docs/ReleaseNotes.html (original) +++ llvm/trunk/docs/ReleaseNotes.html Tue Apr 27 01:57:10 2010 @@ -83,11 +83,7 @@ From sabre at nondot.org Tue Apr 27 02:28:12 2010 From: sabre at nondot.org (Chris Lattner) Date: Tue, 27 Apr 2010 07:28:12 -0000 Subject: [llvm-commits] [llvm] r102418 - /llvm/trunk/docs/ReleaseNotes.html Message-ID: <20100427072812.C1E67312800A@llvm.org> Author: lattner Date: Tue Apr 27 02:28:11 2010 New Revision: 102418 URL: http://llvm.org/viewvc/llvm-project?rev=102418&view=rev Log: fix wordo Modified: llvm/trunk/docs/ReleaseNotes.html Modified: llvm/trunk/docs/ReleaseNotes.html URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/ReleaseNotes.html?rev=102418&r1=102417&r2=102418&view=diff ============================================================================== --- llvm/trunk/docs/ReleaseNotes.html (original) +++ llvm/trunk/docs/ReleaseNotes.html Tue Apr 27 02:28:11 2010 @@ -621,7 +621,7 @@

+ + +
Array Type
+ +
+ +
Overview:
+

The array type is a very simple derived type that arranges elements + sequentially in memory. The array type requires a size (number of elements) + and an underlying data type.

+ +
Syntax:
+
+  [<# elements> x <elementtype>]
+
+ +

The number of elements is a constant integer value; elementtype may + be any type with a size.

+ +
Examples:
+ + + + + + + + + + + + + +
[40 x i32]Array of 40 32-bit integer values.
[41 x i32]Array of 41 32-bit integer values.
[4 x i8]Array of 4 8-bit integer values.
+

Here are some examples of multidimensional arrays:

+ + + + + + + + + + + + + +
[3 x [4 x i32]]3x4 array of 32-bit integer values.
[12 x [10 x float]]12x10 array of single precision floating point values.
[2 x [3 x [4 x i16]]]2x3x4 array of 16-bit integer values.
+ +

There is no restriction on indexing beyond the end of the array implied by + a static type (though there are restrictions on indexing beyond the bounds + of an allocated object in some cases). This means that single-dimension + 'variable sized array' addressing can be implemented in LLVM with a zero + length array type. An implementation of 'pascal style arrays' in LLVM could + use the type "{ i32, [0 x float]}", for example.

+ +
+ + +
Function Type
+ +
+ +
Overview:
+

The function type can be thought of as a function signature. It consists of + a return type and a list of formal parameter types. The return type of a + function type is a scalar type, a void type, a struct type, or a union + type. If the return type is a struct type then all struct elements must be + of first class types, and the struct must have at least one element.

+ +
Syntax:
+
+  <returntype> (<parameter list>)
+
+ +

...where '<parameter list>' is a comma-separated list of type + specifiers. Optionally, the parameter list may include a type ..., + which indicates that the function takes a variable number of arguments. + Variable argument functions can access their arguments with + the variable argument handling intrinsic + functions. '<returntype>' is any type except + label.

+ +
Examples:
+ + + + + + + + + + + + + + +
i32 (i32)function taking an i32, returning an i32 +
float (i16, i32 *) * + Pointer to a function that takes + an i16 and a pointer to i32, + returning float. +
i32 (i8*, ...)A vararg function that takes at least one + pointer to i8 (char in C), + which returns an integer. This is the signature for printf in + LLVM. +
{i32, i32} (i32)A function taking an i32, returning a + structure containing two i32 values +
+ +
+ + +
Structure Type
+ +
+ +
Overview:
+

The structure type is used to represent a collection of data members together + in memory. The packing of the field types is defined to match the ABI of the + underlying processor. The elements of a structure may be any type that has a + size.

+ +

Structures in memory are accessed using 'load' + and 'store' by getting a pointer to a field + with the 'getelementptr' instruction. + Structures in registers are accessed using the + 'extractvalue' and + 'insertvalue' instructions.

+
Syntax:
+
+  { <type list> }
+
+ +
Examples:
+ + + + + + + + +
{ i32, i32, i32 }A triple of three i32 values
{ float, i32 (i32) * }A pair, where the first element is a float and the + second element is a pointer to a + function that takes an i32, returning + an i32.
+ +
+ + +
Packed Structure Type +
+ +
+ +
Overview:
+

The packed structure type is used to represent a collection of data members + together in memory. There is no padding between fields. Further, the + alignment of a packed structure is 1 byte. The elements of a packed + structure may be any type that has a size.

+ +

Structures are accessed using 'load and + 'store' by getting a pointer to a field with + the 'getelementptr' instruction.

+ +
Syntax:
+
+  < { <type list> } >
+
+ +
Examples:
+ + + + + + + + +
< { i32, i32, i32 } >A triple of three i32 values
+< { float, i32 (i32)* } >A pair, where the first element is a float and the + second element is a pointer to a + function that takes an i32, returning + an i32.
+ +
+ + +
Union Type
+ +
+ +
Overview:
+

A union type describes an object with size and alignment suitable for + an object of any one of a given set of types (also known as an "untagged" + union). It is similar in concept and usage to a + struct, except that all members of the union + have an offset of zero. The elements of a union may be any type that has a + size. Unions must have at least one member - empty unions are not allowed. +

+ +

The size of the union as a whole will be the size of its largest member, + and the alignment requirements of the union as a whole will be the largest + alignment requirement of any member.

+ +

Union members are accessed using 'load and + 'store' by getting a pointer to a field with + the 'getelementptr' instruction. + Since all members are at offset zero, the getelementptr instruction does + not affect the address, only the type of the resulting pointer.

+ +
Syntax:
+
+  union { <type list> }
+
+ +
Examples:
+ + + + + + + + +
union { i32, i32*, float }A union of three types: an i32, a pointer to + an i32, and a float.
+ union { float, i32 (i32) * }A union, where the first element is a float and the + second element is a pointer to a + function that takes an i32, returning + an i32.
+ +
+ + +
Pointer Type
+ +
+ +
Overview:
+

The pointer type is used to specify memory locations. + Pointers are commonly used to reference objects in memory.

+ +

Pointer types may have an optional address space attribute defining the + numbered address space where the pointed-to object resides. The default + address space is number zero. The semantics of non-zero address + spaces are target-specific.

+ +

Note that LLVM does not permit pointers to void (void*) nor does it + permit pointers to labels (label*). Use i8* instead.

+ +
Syntax:
+
+  <type> *
+
+ +
Examples:
+ + + + + + + + + + + + + +
[4 x i32]*A pointer to array of four i32 values.
i32 (i32 *) * A pointer to a function that takes an i32*, returning an + i32.
i32 addrspace(5)*A pointer to an i32 value + that resides in address space #5.
+ +
+ + +
Vector Type
+ +
+ +
Overview:
+

A vector type is a simple derived type that represents a vector of elements. + Vector types are used when multiple primitive data are operated in parallel + using a single instruction (SIMD). A vector type requires a size (number of + elements) and an underlying primitive data type. Vector types are considered + first class.

+ +
Syntax:
+
+  < <# elements> x <elementtype> >
+
+ +

The number of elements is a constant integer value; elementtype may be any + integer or floating point type.

+ +
Examples:
+ + + + + + + + + + + + + +
<4 x i32>Vector of 4 32-bit integer values.
<8 x float>Vector of 8 32-bit floating-point values.
<2 x i64>Vector of 2 64-bit integer values.
+ +
+ + +
Opaque Type
+
+ +
Overview:
+

Opaque types are used to represent unknown types in the system. This + corresponds (for example) to the C notion of a forward declared structure + type. In LLVM, opaque types can eventually be resolved to any type (not just + a structure type).

+ +
Syntax:
+
+  opaque
+
+ +
Examples:
+ + + + + +
opaqueAn opaque type.
+ +
+ + +
+ Type Up-references +
+ +
+ +
Overview:
+

An "up reference" allows you to refer to a lexically enclosing type without + requiring it to have a name. For instance, a structure declaration may + contain a pointer to any of the types it is lexically a member of. Example + of up references (with their equivalent as named type declarations) + include:

+ +
+   { \2 * }                %x = type { %x* }
+   { \2 }*                 %y = type { %y }*
+   \1*                     %z = type %z*
+
+ +

An up reference is needed by the asmprinter for printing out cyclic types + when there is no declared name for a type in the cycle. Because the + asmprinter does not want to print out an infinite type string, it needs a + syntax to handle recursive types that have no names (all names are optional + in llvm IR).

+ +
Syntax:
+
+   \<level>
+
+ +

The level is the count of the lexical type that is being referred to.

+ +
Examples:
+ + + + + + + + + +
\1*Self-referential pointer.
{ { \3*, i8 }, i32 }Recursive structure where the upref refers to the out-most + structure.
+ +
+ + +
Constants
+ + +
+ +

LLVM has several different basic types of constants. This section describes + them all and their syntax.

+ +
+ + +
Simple Constants
+ +
+ +
+
Boolean constants
+
The two strings 'true' and 'false' are both valid + constants of the i1 type.
+ +
Integer constants
+
Standard integers (such as '4') are constants of + the integer type. Negative numbers may be used + with integer types.
+ +
Floating point constants
+
Floating point constants use standard decimal notation (e.g. 123.421), + exponential notation (e.g. 1.23421e+2), or a more precise hexadecimal + notation (see below). The assembler requires the exact decimal value of a + floating-point constant. For example, the assembler accepts 1.25 but + rejects 1.3 because 1.3 is a repeating decimal in binary. Floating point + constants must have a floating point type.
+ +
Null pointer constants
+
The identifier 'null' is recognized as a null pointer constant + and must be of pointer type.
+
+ +

The one non-intuitive notation for constants is the hexadecimal form of + floating point constants. For example, the form 'double + 0x432ff973cafa8000' is equivalent to (but harder to read than) + 'double 4.5e+15'. The only time hexadecimal floating point + constants are required (and the only time that they are generated by the + disassembler) is when a floating point constant must be emitted but it cannot + be represented as a decimal floating point number in a reasonable number of + digits. For example, NaN's, infinities, and other special values are + represented in their IEEE hexadecimal format so that assembly and disassembly + do not cause any bits to change in the constants.

+ +

When using the hexadecimal form, constants of types float and double are + represented using the 16-digit form shown above (which matches the IEEE754 + representation for double); float values must, however, be exactly + representable as IEE754 single precision. Hexadecimal format is always used + for long double, and there are three forms of long double. The 80-bit format + used by x86 is represented as 0xK followed by 20 hexadecimal digits. + The 128-bit format used by PowerPC (two adjacent doubles) is represented + by 0xM followed by 32 hexadecimal digits. The IEEE 128-bit format + is represented by 0xL followed by 32 hexadecimal digits; no + currently supported target uses this format. Long doubles will only work if + they match the long double format on your target. All hexadecimal formats + are big-endian (sign bit at the left).

+ +
+ + +
+ +Complex Constants +
+ +
+ +

Complex constants are a (potentially recursive) combination of simple + constants and smaller complex constants.

+ +
+
Structure constants
+
Structure constants are represented with notation similar to structure + type definitions (a comma separated list of elements, surrounded by braces + ({})). For example: "{ i32 4, float 17.0, i32* @G }", + where "@G" is declared as "@G = external global i32". + Structure constants must have structure type, and + the number and types of elements must match those specified by the + type.
+ +
Union constants
+
Union constants are represented with notation similar to a structure with + a single element - that is, a single typed element surrounded + by braces ({})). For example: "{ i32 4 }". The + union type can be initialized with a single-element + struct as long as the type of the struct element matches the type of + one of the union members.
+ +
Array constants
+
Array constants are represented with notation similar to array type + definitions (a comma separated list of elements, surrounded by square + brackets ([])). For example: "[ i32 42, i32 11, i32 74 + ]". Array constants must have array type, and + the number and types of elements must match those specified by the + type.
+ +
Vector constants
+
Vector constants are represented with notation similar to vector type + definitions (a comma separated list of elements, surrounded by + less-than/greater-than's (<>)). For example: "< i32 + 42, i32 11, i32 74, i32 100 >". Vector constants must + have vector type, and the number and types of + elements must match those specified by the type.
+ +
Zero initialization
+
The string 'zeroinitializer' can be used to zero initialize a + value to zero of any type, including scalar and + aggregate types. + This is often used to avoid having to print large zero initializers + (e.g. for large arrays) and is always exactly equivalent to using explicit + zero initializers.
+ +
Metadata node
+
A metadata node is a structure-like constant with + metadata type. For example: "metadata !{ + i32 0, metadata !"test" }". Unlike other constants that are meant to + be interpreted as part of the instruction stream, metadata is a place to + attach additional information such as debug info.
+
+ +
+ + +
+ Global Variable and Function Addresses +
+ +
+ +

The addresses of global variables + and functions are always implicitly valid + (link-time) constants. These constants are explicitly referenced when + the identifier for the global is used and always + have pointer type. For example, the following is a + legal LLVM file:

+ +
+
+ at X = global i32 17
+ at Y = global i32 42
+ at Z = global [2 x i32*] [ i32* @X, i32* @Y ]
+
+
+ +
+ + +
Undefined Values
+
+ +

The string 'undef' can be used anywhere a constant is expected, and + indicates that the user of the value may receive an unspecified bit-pattern. + Undefined values may be of any type (other than label or void) and be used + anywhere a constant is permitted.

+ +

Undefined values are useful because they indicate to the compiler that the + program is well defined no matter what value is used. This gives the + compiler more freedom to optimize. Here are some examples of (potentially + surprising) transformations that are valid (in pseudo IR):

+ + +
+
+  %A = add %X, undef
+  %B = sub %X, undef
+  %C = xor %X, undef
+Safe:
+  %A = undef
+  %B = undef
+  %C = undef
+
+
+ +

This is safe because all of the output bits are affected by the undef bits. +Any output bit can have a zero or one depending on the input bits.

+ +
+
+  %A = or %X, undef
+  %B = and %X, undef
+Safe:
+  %A = -1
+  %B = 0
+Unsafe:
+  %A = undef
+  %B = undef
+
+
+ +

These logical operations have bits that are not always affected by the input. +For example, if "%X" has a zero bit, then the output of the 'and' operation will +always be a zero, no matter what the corresponding bit from the undef is. As +such, it is unsafe to optimize or assume that the result of the and is undef. +However, it is safe to assume that all bits of the undef could be 0, and +optimize the and to 0. Likewise, it is safe to assume that all the bits of +the undef operand to the or could be set, allowing the or to be folded to +-1.

+ +
+
+  %A = select undef, %X, %Y
+  %B = select undef, 42, %Y
+  %C = select %X, %Y, undef
+Safe:
+  %A = %X     (or %Y)
+  %B = 42     (or %Y)
+  %C = %Y
+Unsafe:
+  %A = undef
+  %B = undef
+  %C = undef
+
+
+ +

This set of examples show that undefined select (and conditional branch) +conditions can go "either way" but they have to come from one of the two +operands. In the %A example, if %X and %Y were both known to have a clear low +bit, then %A would have to have a cleared low bit. However, in the %C example, +the optimizer is allowed to assume that the undef operand could be the same as +%Y, allowing the whole select to be eliminated.

+ + +
+
+  %A = xor undef, undef
+
+  %B = undef
+  %C = xor %B, %B
+
+  %D = undef
+  %E = icmp lt %D, 4
+  %F = icmp gte %D, 4
+
+Safe:
+  %A = undef
+  %B = undef
+  %C = undef
+  %D = undef
+  %E = undef
+  %F = undef
+
+
+ +

This example points out that two undef operands are not necessarily the same. +This can be surprising to people (and also matches C semantics) where they +assume that "X^X" is always zero, even if X is undef. This isn't true for a +number of reasons, but the short answer is that an undef "variable" can +arbitrarily change its value over its "live range". This is true because the +"variable" doesn't actually have a live range. Instead, the value is +logically read from arbitrary registers that happen to be around when needed, +so the value is not necessarily consistent over time. In fact, %A and %C need +to have the same semantics or the core LLVM "replace all uses with" concept +would not hold.

+ +
+
+  %A = fdiv undef, %X
+  %B = fdiv %X, undef
+Safe:
+  %A = undef
+b: unreachable
+
+
+ +

These examples show the crucial difference between an undefined +value and undefined behavior. An undefined value (like undef) is +allowed to have an arbitrary bit-pattern. This means that the %A operation +can be constant folded to undef because the undef could be an SNaN, and fdiv is +not (currently) defined on SNaN's. However, in the second example, we can make +a more aggressive assumption: because the undef is allowed to be an arbitrary +value, we are allowed to assume that it could be zero. Since a divide by zero +has undefined behavior, we are allowed to assume that the operation +does not execute at all. This allows us to delete the divide and all code after +it: since the undefined operation "can't happen", the optimizer can assume that +it occurs in dead code. +

+ +
+
+a:  store undef -> %X
+b:  store %X -> undef
+Safe:
+a: <deleted>
+b: unreachable
+
+
+ +

These examples reiterate the fdiv example: a store "of" an undefined value +can be assumed to not have any effect: we can assume that the value is +overwritten with bits that happen to match what was already there. However, a +store "to" an undefined location could clobber arbitrary memory, therefore, it +has undefined behavior.

+ +
+ + +
Addresses of Basic + Blocks
+
+ +

blockaddress(@function, %block)

+ +

The 'blockaddress' constant computes the address of the specified + basic block in the specified function, and always has an i8* type. Taking + the address of the entry block is illegal.

+ +

This value only has defined behavior when used as an operand to the + 'indirectbr' instruction or for comparisons + against null. Pointer equality tests between labels addresses is undefined + behavior - though, again, comparison against null is ok, and no label is + equal to the null pointer. This may also be passed around as an opaque + pointer sized value as long as the bits are not inspected. This allows + ptrtoint and arithmetic to be performed on these values so long as + the original value is reconstituted before the indirectbr.

+ +

Finally, some targets may provide defined semantics when + using the value as the operand to an inline assembly, but that is target + specific. +

+ +
+ + + +
Constant Expressions +
+ +
+ +

Constant expressions are used to allow expressions involving other constants + to be used as constants. Constant expressions may be of + any first class type and may involve any LLVM + operation that does not have side effects (e.g. load and call are not + supported). The following is the syntax for constant expressions:

+ +
+
trunc ( CST to TYPE )
+
Truncate a constant to another type. The bit size of CST must be larger + than the bit size of TYPE. Both types must be integers.
+ +
zext ( CST to TYPE )
+
Zero extend a constant to another type. The bit size of CST must be + smaller or equal to the bit size of TYPE. Both types must be + integers.
+ +
sext ( CST to TYPE )
+
Sign extend a constant to another type. The bit size of CST must be + smaller or equal to the bit size of TYPE. Both types must be + integers.
+ +
fptrunc ( CST to TYPE )
+
Truncate a floating point constant to another floating point type. The + size of CST must be larger than the size of TYPE. Both types must be + floating point.
+ +
fpext ( CST to TYPE )
+
Floating point extend a constant to another type. The size of CST must be + smaller or equal to the size of TYPE. Both types must be floating + point.
+ +
fptoui ( CST to TYPE )
+
Convert a floating point constant to the corresponding unsigned integer + constant. TYPE must be a scalar or vector integer type. CST must be of + scalar or vector floating point type. Both CST and TYPE must be scalars, + or vectors of the same number of elements. If the value won't fit in the + integer type, the results are undefined.
+ +
fptosi ( CST to TYPE )
+
Convert a floating point constant to the corresponding signed integer + constant. TYPE must be a scalar or vector integer type. CST must be of + scalar or vector floating point type. Both CST and TYPE must be scalars, + or vectors of the same number of elements. If the value won't fit in the + integer type, the results are undefined.
+ +
uitofp ( CST to TYPE )
+
Convert an unsigned integer constant to the corresponding floating point + constant. TYPE must be a scalar or vector floating point type. CST must be + of scalar or vector integer type. Both CST and TYPE must be scalars, or + vectors of the same number of elements. If the value won't fit in the + floating point type, the results are undefined.
+ +
sitofp ( CST to TYPE )
+
Convert a signed integer constant to the corresponding floating point + constant. TYPE must be a scalar or vector floating point type. CST must be + of scalar or vector integer type. Both CST and TYPE must be scalars, or + vectors of the same number of elements. If the value won't fit in the + floating point type, the results are undefined.
+ +
ptrtoint ( CST to TYPE )
+
Convert a pointer typed constant to the corresponding integer constant + TYPE must be an integer type. CST must be of pointer + type. The CST value is zero extended, truncated, or unchanged to + make it fit in TYPE.
+ +
inttoptr ( CST to TYPE )
+
Convert a integer constant to a pointer constant. TYPE must be a pointer + type. CST must be of integer type. The CST value is zero extended, + truncated, or unchanged to make it fit in a pointer size. This one is + really dangerous!
+ +
bitcast ( CST to TYPE )
+
Convert a constant, CST, to another TYPE. The constraints of the operands + are the same as those for the bitcast + instruction.
+ +
getelementptr ( CSTPTR, IDX0, IDX1, ... )
+
getelementptr inbounds ( CSTPTR, IDX0, IDX1, ... )
+
Perform the getelementptr operation on + constants. As with the getelementptr + instruction, the index list may have zero or more indexes, which are + required to make sense for the type of "CSTPTR".
+ +
select ( COND, VAL1, VAL2 )
+
Perform the select operation on constants.
+ +
icmp COND ( VAL1, VAL2 )
+
Performs the icmp operation on constants.
+ +
fcmp COND ( VAL1, VAL2 )
+
Performs the fcmp operation on constants.
+ +
extractelement ( VAL, IDX )
+
Perform the extractelement operation on + constants.
+ +
insertelement ( VAL, ELT, IDX )
+
Perform the insertelement operation on + constants.
+ +
shufflevector ( VEC1, VEC2, IDXMASK )
+
Perform the shufflevector operation on + constants.
+ +
OPCODE ( LHS, RHS )
+
Perform the specified operation of the LHS and RHS constants. OPCODE may + be any of the binary + or bitwise binary operations. The constraints + on operands are the same as those for the corresponding instruction + (e.g. no bitwise operations on floating point values are allowed).
+
+ +
+ + +
Other Values
+ + + +
+Inline Assembler Expressions +
+ +
+ +

LLVM supports inline assembler expressions (as opposed + to Module-Level Inline Assembly) through the use of + a special value. This value represents the inline assembler as a string + (containing the instructions to emit), a list of operand constraints (stored + as a string), a flag that indicates whether or not the inline asm + expression has side effects, and a flag indicating whether the function + containing the asm needs to align its stack conservatively. An example + inline assembler expression is:

+ +
+
+i32 (i32) asm "bswap $0", "=r,r"
+
+
+ +

Inline assembler expressions may only be used as the callee operand of + a call instruction. Thus, typically we + have:

+ +
+
+%X = call i32 asm "bswap $0", "=r,r"(i32 %Y)
+
+
+ +

Inline asms with side effects not visible in the constraint list must be + marked as having side effects. This is done through the use of the + 'sideeffect' keyword, like so:

+ +
+
+call void asm sideeffect "eieio", ""()
+
+
+ +

In some cases inline asms will contain code that will not work unless the + stack is aligned in some way, such as calls or SSE instructions on x86, + yet will not contain code that does that alignment within the asm. + The compiler should make conservative assumptions about what the asm might + contain and should generate its usual stack alignment code in the prologue + if the 'alignstack' keyword is present:

+ +
+
+call void asm alignstack "eieio", ""()
+
+
+ +

If both keywords appear the 'sideeffect' keyword must come + first.

+ +

TODO: The format of the asm and constraints string still need to be + documented here. Constraints on what can be done (e.g. duplication, moving, + etc need to be documented). This is probably best done by reference to + another document that covers inline asm from a holistic perspective.

+ +
+ + +
Metadata Nodes and Metadata + Strings +
+ +
+ +

LLVM IR allows metadata to be attached to instructions in the program that + can convey extra information about the code to the optimizers and code + generator. One example application of metadata is source-level debug + information. There are two metadata primitives: strings and nodes. All + metadata has the metadata type and is identified in syntax by a + preceding exclamation point ('!').

+ +

A metadata string is a string surrounded by double quotes. It can contain + any character by escaping non-printable characters with "\xx" where "xx" is + the two digit hex code. For example: "!"test\00"".

+ +

Metadata nodes are represented with notation similar to structure constants + (a comma separated list of elements, surrounded by braces and preceded by an + exclamation point). For example: "!{ metadata !"test\00", i32 + 10}". Metadata nodes can have any values as their operand.

+ +

A named metadata is a collection of + metadata nodes, which can be looked up in the module symbol table. For + example: "!foo = metadata !{!4, !3}". + +

Metadata can be used as function arguments. Here llvm.dbg.value + function is using two metadata arguments. + +

+ 
+       call void @llvm.dbg.value(metadata !24, i64 0, metadata !25)
+
+

+ +

Metadata can be attached with an instruction. Here metadata !21 is + attached with add instruction using !dbg identifier. + +

+ 
+      %indvar.next = add i64 %indvar, 1, !dbg !21
+
+

+
+ + + +
+ Intrinsic Global Variables +
+ + +

LLVM has a number of "magic" global variables that contain data that affect +code generation or other IR semantics. These are documented here. All globals +of this sort should have a section specified as "llvm.metadata". This +section and all globals that start with "llvm." are reserved for use +by LLVM.

+ + +
+The 'llvm.used' Global Variable +
+ +
+ +

The @llvm.used global is an array with i8* element type which has appending linkage. This array contains a list of +pointers to global variables and functions which may optionally have a pointer +cast formed of bitcast or getelementptr. For example, a legal use of it is:

+ +
+  @X = global i8 4
+  @Y = global i32 123
+
+  @llvm.used = appending global [2 x i8*] [
+     i8* @X,
+     i8* bitcast (i32* @Y to i8*)
+  ], section "llvm.metadata"
+
+ +

If a global variable appears in the @llvm.used list, then the +compiler, assembler, and linker are required to treat the symbol as if there is +a reference to the global that it cannot see. For example, if a variable has +internal linkage and no references other than that from the @llvm.used +list, it cannot be deleted. This is commonly used to represent references from +inline asms and other things the compiler cannot "see", and corresponds to +"attribute((used))" in GNU C.

+ +

On some targets, the code generator must emit a directive to the assembler or +object file to prevent the assembler and linker from molesting the symbol.

+ +
+ + +
+The 'llvm.compiler.used' Global Variable +
+ +
+ +

The @llvm.compiler.used directive is the same as the +@llvm.used directive, except that it only prevents the compiler from +touching the symbol. On targets that support it, this allows an intelligent +linker to optimize references to the symbol without being impeded as it would be +by @llvm.used.

+ +

This is a rare construct that should only be used in rare circumstances, and +should not be exposed to source languages.

+ +
+ + +
+The 'llvm.global_ctors' Global Variable +
+ +
+ +

TODO: Describe this.

+ +
+ + +
+The 'llvm.global_dtors' Global Variable +
+ +
+ +

TODO: Describe this.

+ +
+ + + +
Instruction Reference
+ + +
+ +

The LLVM instruction set consists of several different classifications of + instructions: terminator + instructions, binary instructions, + bitwise binary instructions, + memory instructions, and + other instructions.

+ +
+ + +
Terminator +Instructions
+ +
+ +

As mentioned previously, every basic block + in a program ends with a "Terminator" instruction, which indicates which + block should be executed after the current block is finished. These + terminator instructions typically yield a 'void' value: they produce + control flow, not values (the one exception being the + 'invoke' instruction).

+ +

There are six different terminator instructions: the + 'ret' instruction, the + 'br' instruction, the + 'switch' instruction, the + ''indirectbr' Instruction, the + 'invoke' instruction, the + 'unwind' instruction, and the + 'unreachable' instruction.

+ +
+ + +
'ret' +Instruction
+ +
+ +
Syntax:
+
+  ret <type> <value>       ; Return a value from a non-void function
+  ret void                 ; Return from void function
+
+ +
Overview:
+

The 'ret' instruction is used to return control flow (and optionally + a value) from a function back to the caller.

+ +

There are two forms of the 'ret' instruction: one that returns a + value and then causes control flow, and one that just causes control flow to + occur.

+ +
Arguments:
+

The 'ret' instruction optionally accepts a single argument, the + return value. The type of the return value must be a + 'first class' type.

+ +

A function is not well formed if it it has a + non-void return type and contains a 'ret' instruction with no return + value or a return value with a type that does not match its type, or if it + has a void return type and contains a 'ret' instruction with a + return value.

+ +
Semantics:
+

When the 'ret' instruction is executed, control flow returns back to + the calling function's context. If the caller is a + "call" instruction, execution continues at the + instruction after the call. If the caller was an + "invoke" instruction, execution continues at + the beginning of the "normal" destination block. If the instruction returns + a value, that value shall set the call or invoke instruction's return + value.

+ +
Example:
+
+  ret i32 5                       ; Return an integer value of 5
+  ret void                        ; Return from a void function
+  ret { i32, i8 } { i32 4, i8 2 } ; Return a struct of values 4 and 2
+
+ +
+ +
'br' Instruction
+ +
+ +
Syntax:
+
+  br i1 <cond>, label <iftrue>, label <iffalse>
  br label <dest>          ; Unconditional branch
+
+ +
Overview:
+

The 'br' instruction is used to cause control flow to transfer to a + different basic block in the current function. There are two forms of this + instruction, corresponding to a conditional branch and an unconditional + branch.

+ +
Arguments:
+

The conditional branch form of the 'br' instruction takes a single + 'i1' value and two 'label' values. The unconditional form + of the 'br' instruction takes a single 'label' value as a + target.

+ +
Semantics:
+

Upon execution of a conditional 'br' instruction, the 'i1' + argument is evaluated. If the value is true, control flows to the + 'iftrue' label argument. If "cond" is false, + control flows to the 'iffalse' label argument.

+ +
Example:
+
+Test:
+  %cond = icmp eq i32 %a, %b
+  br i1 %cond, label %IfEqual, label %IfUnequal
+IfEqual:
+  ret i32 1
+IfUnequal:
+  ret i32 0
+
+ +
+ + +
+ 'switch' Instruction +
+ +
+ +
Syntax:
+
+  switch <intty> <value>, label <defaultdest> [ <intty> <val>, label <dest> ... ]
+
+ +
Overview:
+

The 'switch' instruction is used to transfer control flow to one of + several different places. It is a generalization of the 'br' + instruction, allowing a branch to occur to one of many possible + destinations.

+ +
Arguments:
+

The 'switch' instruction uses three parameters: an integer + comparison value 'value', a default 'label' destination, + and an array of pairs of comparison value constants and 'label's. + The table is not allowed to contain duplicate constant entries.

+ +
Semantics:
+

The switch instruction specifies a table of values and + destinations. When the 'switch' instruction is executed, this table + is searched for the given value. If the value is found, control flow is + transferred to the corresponding destination; otherwise, control flow is + transferred to the default destination.

+ +
Implementation:
+

Depending on properties of the target machine and the particular + switch instruction, this instruction may be code generated in + different ways. For example, it could be generated as a series of chained + conditional branches or with a lookup table.

+ +
Example:
+
+ ; Emulate a conditional br instruction
+ %Val = zext i1 %value to i32
+ switch i32 %Val, label %truedest [ i32 0, label %falsedest ]
+
+ ; Emulate an unconditional br instruction
+ switch i32 0, label %dest [ ]
+
+ ; Implement a jump table:
+ switch i32 %val, label %otherwise [ i32 0, label %onzero
+                                     i32 1, label %onone
+                                     i32 2, label %ontwo ]
+
+ +
+ + + +
+ 'indirectbr' Instruction +
+ +
+ +
Syntax:
+
+  indirectbr <somety>* <address>, [ label <dest1>, label <dest2>, ... ]
+
+ +
Overview:
+ +

The 'indirectbr' instruction implements an indirect branch to a label + within the current function, whose address is specified by + "address". Address must be derived from a blockaddress constant.

+ +
Arguments:
+ +

The 'address' argument is the address of the label to jump to. The + rest of the arguments indicate the full set of possible destinations that the + address may point to. Blocks are allowed to occur multiple times in the + destination list, though this isn't particularly useful.

+ +

This destination list is required so that dataflow analysis has an accurate + understanding of the CFG.

+ +
Semantics:
+ +

Control transfers to the block specified in the address argument. All + possible destination blocks must be listed in the label list, otherwise this + instruction has undefined behavior. This implies that jumps to labels + defined in other functions have undefined behavior as well.

+ +
Implementation:
+ +

This is typically implemented with a jump through a register.

+ +
Example:
+
+ indirectbr i8* %Addr, [ label %bb1, label %bb2, label %bb3 ]
+
+ +
+ + + +
+ 'invoke' Instruction +
+ +
+ +
Syntax:
+
+  <result> = invoke [cconv] [ret attrs] <ptr to function ty> <function ptr val>(<function args>) [fn attrs]
+                to label <normal label> unwind label <exception label>
+
+ +
Overview:
+

The 'invoke' instruction causes control to transfer to a specified + function, with the possibility of control flow transfer to either the + 'normal' label or the 'exception' label. If the callee + function returns with the "ret" instruction, + control flow will return to the "normal" label. If the callee (or any + indirect callees) returns with the "unwind" + instruction, control is interrupted and continued at the dynamically nearest + "exception" label.

+ +
Arguments:
+

This instruction requires several arguments:

+ +
    +
  1. The optional "cconv" marker indicates which calling + convention the call should use. If none is specified, the call + defaults to using C calling conventions.
    2. + +
  2. The optional Parameter Attributes list for + return values. Only 'zeroext', 'signext', and + 'inreg' attributes are valid here.
    3. + +
  3. 'ptr to function ty': shall be the signature of the pointer to + function value being invoked. In most cases, this is a direct function + invocation, but indirect invokes are just as possible, branching + off an arbitrary pointer to function value.
    4. + +
  4. 'function ptr val': An LLVM value containing a pointer to a + function to be invoked.
    5. + +
  5. 'function args': argument list whose types match the function + signature argument types and parameter attributes. All arguments must be + of first class type. If the function + signature indicates the function accepts a variable number of arguments, + the extra arguments can be specified.
    6. + +
  6. 'normal label': the label reached when the called function + executes a 'ret' instruction.
    7. + +
  7. 'exception label': the label reached when a callee returns with + the unwind instruction.
    8. + +
  8. The optional function attributes list. Only + 'noreturn', 'nounwind', 'readonly' and + 'readnone' attributes are valid here.
    9. +
+ +
Semantics:
+

This instruction is designed to operate as a standard + 'call' instruction in most regards. The + primary difference is that it establishes an association with a label, which + is used by the runtime library to unwind the stack.

+ +

This instruction is used in languages with destructors to ensure that proper + cleanup is performed in the case of either a longjmp or a thrown + exception. Additionally, this is important for implementation of + 'catch' clauses in high-level languages that support them.

+ +

For the purposes of the SSA form, the definition of the value returned by the + 'invoke' instruction is deemed to occur on the edge from the current + block to the "normal" label. If the callee unwinds then no return value is + available.

+ +

Note that the code generator does not yet completely support unwind, and +that the invoke/unwind semantics are likely to change in future versions.

+ +
Example:
+
+  %retval = invoke i32 @Test(i32 15) to label %Continue
+              unwind label %TestCleanup              ; {i32}:retval set
+  %retval = invoke coldcc i32 %Testfnptr(i32 15) to label %Continue
+              unwind label %TestCleanup              ; {i32}:retval set
+
+ +
+ + + +
'unwind' +Instruction
+ +
+ +
Syntax:
+
+  unwind
+
+ +
Overview:
+

The 'unwind' instruction unwinds the stack, continuing control flow + at the first callee in the dynamic call stack which used + an invoke instruction to perform the call. + This is primarily used to implement exception handling.

+ +
Semantics:
+

The 'unwind' instruction causes execution of the current function to + immediately halt. The dynamic call stack is then searched for the + first invoke instruction on the call stack. + Once found, execution continues at the "exceptional" destination block + specified by the invoke instruction. If there is no invoke + instruction in the dynamic call chain, undefined behavior results.

+ +

Note that the code generator does not yet completely support unwind, and +that the invoke/unwind semantics are likely to change in future versions.

+ +
+ + + +
'unreachable' +Instruction
+ +
+ +
Syntax:
+
+  unreachable
+
+ +
Overview:
+

The 'unreachable' instruction has no defined semantics. This + instruction is used to inform the optimizer that a particular portion of the + code is not reachable. This can be used to indicate that the code after a + no-return function cannot be reached, and other facts.

+ +
Semantics:
+

The 'unreachable' instruction has no defined semantics.

+ +
+ + +
Binary Operations
+ +
+ +

Binary operators are used to do most of the computation in a program. They + require two operands of the same type, execute an operation on them, and + produce a single value. The operands might represent multiple data, as is + the case with the vector data type. The result value + has the same type as its operands.

+ +

There are several different binary operators:

+ +
+ + +
+ 'add' Instruction +
+ +
+ +
Syntax:
+
+  <result> = add <ty> <op1>, <op2>          ; yields {ty}:result
+  <result> = add nuw <ty> <op1>, <op2>      ; yields {ty}:result
+  <result> = add nsw <ty> <op1>, <op2>      ; yields {ty}:result
+  <result> = add nuw nsw <ty> <op1>, <op2>  ; yields {ty}:result
+
+ +
Overview:
+

The 'add' instruction returns the sum of its two operands.

+ +
Arguments:
+

The two arguments to the 'add' instruction must + be integer or vector of + integer values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the integer sum of the two operands.

+ +

If the sum has unsigned overflow, the result returned is the mathematical + result modulo 2n, where n is the bit width of the result.

+ +

Because LLVM integers use a two's complement representation, this instruction + is appropriate for both signed and unsigned integers.

+ +

nuw and nsw stand for "No Unsigned Wrap" + and "No Signed Wrap", respectively. If the nuw and/or + nsw keywords are present, the result value of the add + is undefined if unsigned and/or signed overflow, respectively, occurs.

+ +
Example:
+
+  <result> = add i32 4, %var          ; yields {i32}:result = 4 + %var
+
+ +
+ + +
+ 'fadd' Instruction +
+ +
+ +
Syntax:
+
+  <result> = fadd <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'fadd' instruction returns the sum of its two operands.

+ +
Arguments:
+

The two arguments to the 'fadd' instruction must be + floating point or vector of + floating point values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the floating point sum of the two operands.

+ +
Example:
+
+  <result> = fadd float 4.0, %var          ; yields {float}:result = 4.0 + %var
+
+ +
+ + +
+ 'sub' Instruction +
+ +
+ +
Syntax:
+
+  <result> = sub <ty> <op1>, <op2>          ; yields {ty}:result
+  <result> = sub nuw <ty> <op1>, <op2>      ; yields {ty}:result
+  <result> = sub nsw <ty> <op1>, <op2>      ; yields {ty}:result
+  <result> = sub nuw nsw <ty> <op1>, <op2>  ; yields {ty}:result
+
+ +
Overview:
+

The 'sub' instruction returns the difference of its two + operands.

+ +

Note that the 'sub' instruction is used to represent the + 'neg' instruction present in most other intermediate + representations.

+ +
Arguments:
+

The two arguments to the 'sub' instruction must + be integer or vector of + integer values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the integer difference of the two operands.

+ +

If the difference has unsigned overflow, the result returned is the + mathematical result modulo 2n, where n is the bit width of the + result.

+ +

Because LLVM integers use a two's complement representation, this instruction + is appropriate for both signed and unsigned integers.

+ +

nuw and nsw stand for "No Unsigned Wrap" + and "No Signed Wrap", respectively. If the nuw and/or + nsw keywords are present, the result value of the sub + is undefined if unsigned and/or signed overflow, respectively, occurs.

+ +
Example:
+
+  <result> = sub i32 4, %var          ; yields {i32}:result = 4 - %var
+  <result> = sub i32 0, %val          ; yields {i32}:result = -%var
+
+ +
+ + +
+ 'fsub' Instruction +
+ +
+ +
Syntax:
+
+  <result> = fsub <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'fsub' instruction returns the difference of its two + operands.

+ +

Note that the 'fsub' instruction is used to represent the + 'fneg' instruction present in most other intermediate + representations.

+ +
Arguments:
+

The two arguments to the 'fsub' instruction must be + floating point or vector of + floating point values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the floating point difference of the two operands.

+ +
Example:
+
+  <result> = fsub float 4.0, %var           ; yields {float}:result = 4.0 - %var
+  <result> = fsub float -0.0, %val          ; yields {float}:result = -%var
+
+ +
+ + +
+ 'mul' Instruction +
+ +
+ +
Syntax:
+
+  <result> = mul <ty> <op1>, <op2>          ; yields {ty}:result
+  <result> = mul nuw <ty> <op1>, <op2>      ; yields {ty}:result
+  <result> = mul nsw <ty> <op1>, <op2>      ; yields {ty}:result
+  <result> = mul nuw nsw <ty> <op1>, <op2>  ; yields {ty}:result
+
+ +
Overview:
+

The 'mul' instruction returns the product of its two operands.

+ +
Arguments:
+

The two arguments to the 'mul' instruction must + be integer or vector of + integer values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the integer product of the two operands.

+ +

If the result of the multiplication has unsigned overflow, the result + returned is the mathematical result modulo 2n, where n is the bit + width of the result.

+ +

Because LLVM integers use a two's complement representation, and the result + is the same width as the operands, this instruction returns the correct + result for both signed and unsigned integers. If a full product + (e.g. i32xi32->i64) is needed, the operands should + be sign-extended or zero-extended as appropriate to the width of the full + product.

+ +

nuw and nsw stand for "No Unsigned Wrap" + and "No Signed Wrap", respectively. If the nuw and/or + nsw keywords are present, the result value of the mul + is undefined if unsigned and/or signed overflow, respectively, occurs.

+ +
Example:
+
+  <result> = mul i32 4, %var          ; yields {i32}:result = 4 * %var
+
+ +
+ + +
+ 'fmul' Instruction +
+ +
+ +
Syntax:
+
+  <result> = fmul <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'fmul' instruction returns the product of its two operands.

+ +
Arguments:
+

The two arguments to the 'fmul' instruction must be + floating point or vector of + floating point values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the floating point product of the two operands.

+ +
Example:
+
+  <result> = fmul float 4.0, %var          ; yields {float}:result = 4.0 * %var
+
+ +
+ + +
'udiv' Instruction +
+ +
+ +
Syntax:
+
+  <result> = udiv <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'udiv' instruction returns the quotient of its two operands.

+ +
Arguments:
+

The two arguments to the 'udiv' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the unsigned integer quotient of the two operands.

+ +

Note that unsigned integer division and signed integer division are distinct + operations; for signed integer division, use 'sdiv'.

+ +

Division by zero leads to undefined behavior.

+ +
Example:
+
+  <result> = udiv i32 4, %var          ; yields {i32}:result = 4 / %var
+
+ +
+ + +
'sdiv' Instruction +
+ +
+ +
Syntax:
+
+  <result> = sdiv <ty> <op1>, <op2>         ; yields {ty}:result
+  <result> = sdiv exact <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'sdiv' instruction returns the quotient of its two operands.

+ +
Arguments:
+

The two arguments to the 'sdiv' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the signed integer quotient of the two operands rounded + towards zero.

+ +

Note that signed integer division and unsigned integer division are distinct + operations; for unsigned integer division, use 'udiv'.

+ +

Division by zero leads to undefined behavior. Overflow also leads to + undefined behavior; this is a rare case, but can occur, for example, by doing + a 32-bit division of -2147483648 by -1.

+ +

If the exact keyword is present, the result value of the + sdiv is undefined if the result would be rounded or if overflow + would occur.

+ +
Example:
+
+  <result> = sdiv i32 4, %var          ; yields {i32}:result = 4 / %var
+
+ +
+ + +
'fdiv' +Instruction
+ +
+ +
Syntax:
+
+  <result> = fdiv <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'fdiv' instruction returns the quotient of its two operands.

+ +
Arguments:
+

The two arguments to the 'fdiv' instruction must be + floating point or vector of + floating point values. Both arguments must have identical types.

+ +
Semantics:
+

The value produced is the floating point quotient of the two operands.

+ +
Example:
+
+  <result> = fdiv float 4.0, %var          ; yields {float}:result = 4.0 / %var
+
+ +
+ + +
'urem' Instruction +
+ +
+ +
Syntax:
+
+  <result> = urem <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'urem' instruction returns the remainder from the unsigned + division of its two arguments.

+ +
Arguments:
+

The two arguments to the 'urem' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

This instruction returns the unsigned integer remainder of a division. + This instruction always performs an unsigned division to get the + remainder.

+ +

Note that unsigned integer remainder and signed integer remainder are + distinct operations; for signed integer remainder, use 'srem'.

+ +

Taking the remainder of a division by zero leads to undefined behavior.

+ +
Example:
+
+  <result> = urem i32 4, %var          ; yields {i32}:result = 4 % %var
+
+ +
+ + +
+ 'srem' Instruction +
+ +
+ +
Syntax:
+
+  <result> = srem <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'srem' instruction returns the remainder from the signed + division of its two operands. This instruction can also take + vector versions of the values in which case the + elements must be integers.

+ +
Arguments:
+

The two arguments to the 'srem' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

This instruction returns the remainder of a division (where the result + has the same sign as the dividend, op1), not the modulo + operator (where the result has the same sign as the divisor, op2) of + a value. For more information about the difference, + see The + Math Forum. For a table of how this is implemented in various languages, + please see + Wikipedia: modulo operation.

+ +

Note that signed integer remainder and unsigned integer remainder are + distinct operations; for unsigned integer remainder, use 'urem'.

+ +

Taking the remainder of a division by zero leads to undefined behavior. + Overflow also leads to undefined behavior; this is a rare case, but can + occur, for example, by taking the remainder of a 32-bit division of + -2147483648 by -1. (The remainder doesn't actually overflow, but this rule + lets srem be implemented using instructions that return both the result of + the division and the remainder.)

+ +
Example:
+
+  <result> = srem i32 4, %var          ; yields {i32}:result = 4 % %var
+
+ +
+ + +
+ 'frem' Instruction
+ +
+ +
Syntax:
+
+  <result> = frem <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'frem' instruction returns the remainder from the division of + its two operands.

+ +
Arguments:
+

The two arguments to the 'frem' instruction must be + floating point or vector of + floating point values. Both arguments must have identical types.

+ +
Semantics:
+

This instruction returns the remainder of a division. The remainder + has the same sign as the dividend.

+ +
Example:
+
+  <result> = frem float 4.0, %var          ; yields {float}:result = 4.0 % %var
+
+ +
+ + +
Bitwise Binary +Operations
+ +
+ +

Bitwise binary operators are used to do various forms of bit-twiddling in a + program. They are generally very efficient instructions and can commonly be + strength reduced from other instructions. They require two operands of the + same type, execute an operation on them, and produce a single value. The + resulting value is the same type as its operands.

+ +
+ + +
'shl' +Instruction
+ +
+ +
Syntax:
+
+  <result> = shl <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'shl' instruction returns the first operand shifted to the left + a specified number of bits.

+ +
Arguments:
+

Both arguments to the 'shl' instruction must be the + same integer or vector of + integer type. 'op2' is treated as an unsigned value.

+ +
Semantics:
+

The value produced is op1 * 2op2 mod + 2n, where n is the width of the result. If op2 + is (statically or dynamically) negative or equal to or larger than the number + of bits in op1, the result is undefined. If the arguments are + vectors, each vector element of op1 is shifted by the corresponding + shift amount in op2.

+ +
Example:
+
+  <result> = shl i32 4, %var   ; yields {i32}: 4 << %var
+  <result> = shl i32 4, 2      ; yields {i32}: 16
+  <result> = shl i32 1, 10     ; yields {i32}: 1024
+  <result> = shl i32 1, 32     ; undefined
+  <result> = shl <2 x i32> < i32 1, i32 1>, < i32 1, i32 2>   ; yields: result=<2 x i32> < i32 2, i32 4>
+
+ +
+ + +
'lshr' +Instruction
+ +
+ +
Syntax:
+
+  <result> = lshr <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'lshr' instruction (logical shift right) returns the first + operand shifted to the right a specified number of bits with zero fill.

+ +
Arguments:
+

Both arguments to the 'lshr' instruction must be the same + integer or vector of integer + type. 'op2' is treated as an unsigned value.

+ +
Semantics:
+

This instruction always performs a logical shift right operation. The most + significant bits of the result will be filled with zero bits after the shift. + If op2 is (statically or dynamically) equal to or larger than the + number of bits in op1, the result is undefined. If the arguments are + vectors, each vector element of op1 is shifted by the corresponding + shift amount in op2.

+ +
Example:
+
+  <result> = lshr i32 4, 1   ; yields {i32}:result = 2
+  <result> = lshr i32 4, 2   ; yields {i32}:result = 1
+  <result> = lshr i8  4, 3   ; yields {i8}:result = 0
+  <result> = lshr i8 -2, 1   ; yields {i8}:result = 0x7FFFFFFF 
+  <result> = lshr i32 1, 32  ; undefined
+  <result> = lshr <2 x i32> < i32 -2, i32 4>, < i32 1, i32 2>   ; yields: result=<2 x i32> < i32 0x7FFFFFFF, i32 1>
+
+ +
+ + +
'ashr' +Instruction
+
+ +
Syntax:
+
+  <result> = ashr <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'ashr' instruction (arithmetic shift right) returns the first + operand shifted to the right a specified number of bits with sign + extension.

+ +
Arguments:
+

Both arguments to the 'ashr' instruction must be the same + integer or vector of integer + type. 'op2' is treated as an unsigned value.

+ +
Semantics:
+

This instruction always performs an arithmetic shift right operation, The + most significant bits of the result will be filled with the sign bit + of op1. If op2 is (statically or dynamically) equal to or + larger than the number of bits in op1, the result is undefined. If + the arguments are vectors, each vector element of op1 is shifted by + the corresponding shift amount in op2.

+ +
Example:
+
+  <result> = ashr i32 4, 1   ; yields {i32}:result = 2
+  <result> = ashr i32 4, 2   ; yields {i32}:result = 1
+  <result> = ashr i8  4, 3   ; yields {i8}:result = 0
+  <result> = ashr i8 -2, 1   ; yields {i8}:result = -1
+  <result> = ashr i32 1, 32  ; undefined
+  <result> = ashr <2 x i32> < i32 -2, i32 4>, < i32 1, i32 3>   ; yields: result=<2 x i32> < i32 -1, i32 0>
+
+ +
+ + +
'and' +Instruction
+ +
+ +
Syntax:
+
+  <result> = and <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'and' instruction returns the bitwise logical and of its two + operands.

+ +
Arguments:
+

The two arguments to the 'and' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

The truth table used for the 'and' instruction is:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
In0In1Out
000
010
100
111
+ +
Example:
+
+  <result> = and i32 4, %var         ; yields {i32}:result = 4 & %var
+  <result> = and i32 15, 40          ; yields {i32}:result = 8
+  <result> = and i32 4, 8            ; yields {i32}:result = 0
+
+
+ +
'or' Instruction
+ +
+ +
Syntax:
+
+  <result> = or <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'or' instruction returns the bitwise logical inclusive or of its + two operands.

+ +
Arguments:
+

The two arguments to the 'or' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

The truth table used for the 'or' instruction is:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
In0In1Out
000
011
101
111
+ +
Example:
+
+  <result> = or i32 4, %var         ; yields {i32}:result = 4 | %var
+  <result> = or i32 15, 40          ; yields {i32}:result = 47
+  <result> = or i32 4, 8            ; yields {i32}:result = 12
+
+ +
+ + +
'xor' +Instruction
+ +
+ +
Syntax:
+
+  <result> = xor <ty> <op1>, <op2>   ; yields {ty}:result
+
+ +
Overview:
+

The 'xor' instruction returns the bitwise logical exclusive or of + its two operands. The xor is used to implement the "one's + complement" operation, which is the "~" operator in C.

+ +
Arguments:
+

The two arguments to the 'xor' instruction must be + integer or vector of integer + values. Both arguments must have identical types.

+ +
Semantics:
+

The truth table used for the 'xor' instruction is:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
In0In1Out
000
011
101
110
+ +
Example:
+
+  <result> = xor i32 4, %var         ; yields {i32}:result = 4 ^ %var
+  <result> = xor i32 15, 40          ; yields {i32}:result = 39
+  <result> = xor i32 4, 8            ; yields {i32}:result = 12
+  <result> = xor i32 %V, -1          ; yields {i32}:result = ~%V
+
+ +
+ + +
+ Vector Operations +
+ +
+ +

LLVM supports several instructions to represent vector operations in a + target-independent manner. These instructions cover the element-access and + vector-specific operations needed to process vectors effectively. While LLVM + does directly support these vector operations, many sophisticated algorithms + will want to use target-specific intrinsics to take full advantage of a + specific target.

+ +
+ + +
+ 'extractelement' Instruction +
+ +
+ +
Syntax:
+
+  <result> = extractelement <n x <ty>> <val>, i32 <idx>    ; yields <ty>
+
+ +
Overview:
+

The 'extractelement' instruction extracts a single scalar element + from a vector at a specified index.

+ + +
Arguments:
+

The first operand of an 'extractelement' instruction is a value + of vector type. The second operand is an index + indicating the position from which to extract the element. The index may be + a variable.

+ +
Semantics:
+

The result is a scalar of the same type as the element type of + val. Its value is the value at position idx of + val. If idx exceeds the length of val, the + results are undefined.

+ +
Example:
+
+  <result> = extractelement <4 x i32> %vec, i32 0    ; yields i32
+
+ +
+ + +
+ 'insertelement' Instruction +
+ +
+ +
Syntax:
+
+  <result> = insertelement <n x <ty>> <val>, <ty> <elt>, i32 <idx>    ; yields <n x <ty>>
+
+ +
Overview:
+

The 'insertelement' instruction inserts a scalar element into a + vector at a specified index.

+ +
Arguments:
+

The first operand of an 'insertelement' instruction is a value + of vector type. The second operand is a scalar value + whose type must equal the element type of the first operand. The third + operand is an index indicating the position at which to insert the value. + The index may be a variable.

+ +
Semantics:
+

The result is a vector of the same type as val. Its element values + are those of val except at position idx, where it gets the + value elt. If idx exceeds the length of val, the + results are undefined.

+ +
Example:
+
+  <result> = insertelement <4 x i32> %vec, i32 1, i32 0    ; yields <4 x i32>
+
+ +
+ + +
+ 'shufflevector' Instruction +
+ +
+ +
Syntax:
+
+  <result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <m x i32> <mask>    ; yields <m x <ty>>
+
+ +
Overview:
+

The 'shufflevector' instruction constructs a permutation of elements + from two input vectors, returning a vector with the same element type as the + input and length that is the same as the shuffle mask.

+ +
Arguments:
+

The first two operands of a 'shufflevector' instruction are vectors + with types that match each other. The third argument is a shuffle mask whose + element type is always 'i32'. The result of the instruction is a vector + whose length is the same as the shuffle mask and whose element type is the + same as the element type of the first two operands.

+ +

The shuffle mask operand is required to be a constant vector with either + constant integer or undef values.

+ +
Semantics:
+

The elements of the two input vectors are numbered from left to right across + both of the vectors. The shuffle mask operand specifies, for each element of + the result vector, which element of the two input vectors the result element + gets. The element selector may be undef (meaning "don't care") and the + second operand may be undef if performing a shuffle from only one vector.

+ +
Example:
+
+  <result> = shufflevector <4 x i32> %v1, <4 x i32> %v2,
+                          <4 x i32> <i32 0, i32 4, i32 1, i32 5>  ; yields <4 x i32>
+  <result> = shufflevector <4 x i32> %v1, <4 x i32> undef,
+                          <4 x i32> <i32 0, i32 1, i32 2, i32 3>  ; yields <4 x i32> - Identity shuffle.
+  <result> = shufflevector <8 x i32> %v1, <8 x i32> undef,
+                          <4 x i32> <i32 0, i32 1, i32 2, i32 3>  ; yields <4 x i32>
+  <result> = shufflevector <4 x i32> %v1, <4 x i32> %v2,
+                          <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 >  ; yields <8 x i32>
+
+ +
+ + +
+ Aggregate Operations +
+ +
+ +

LLVM supports several instructions for working with + aggregate values.

+ +
+ + +
+ 'extractvalue' Instruction +
+ +
+ +
Syntax:
+
+  <result> = extractvalue <aggregate type> <val>, <idx>{, <idx>}*
+
+ +
Overview:
+

The 'extractvalue' instruction extracts the value of a member field + from an aggregate value.

+ +
Arguments:
+

The first operand of an 'extractvalue' instruction is a value + of struct, union or + array type. The operands are constant indices to + specify which value to extract in a similar manner as indices in a + 'getelementptr' instruction.

+ +
Semantics:
+

The result is the value at the position in the aggregate specified by the + index operands.

+ +
Example:
+
+  <result> = extractvalue {i32, float} %agg, 0    ; yields i32
+
+ +
+ + +
+ 'insertvalue' Instruction +
+ +
+ +
Syntax:
+
+  <result> = insertvalue <aggregate type> <val>, <ty> <elt>, <idx>    ; yields <aggregate type>
+
+ +
Overview:
+

The 'insertvalue' instruction inserts a value into a member field + in an aggregate value.

+ +
Arguments:
+

The first operand of an 'insertvalue' instruction is a value + of struct, union or + array type. The second operand is a first-class + value to insert. The following operands are constant indices indicating + the position at which to insert the value in a similar manner as indices in a + 'getelementptr' instruction. The + value to insert must have the same type as the value identified by the + indices.

+ +
Semantics:
+

The result is an aggregate of the same type as val. Its value is + that of val except that the value at the position specified by the + indices is that of elt.

+ +
Example:
+
+  %agg1 = insertvalue {i32, float} undef, i32 1, 0         ; yields {i32 1, float undef}
+  %agg2 = insertvalue {i32, float} %agg1, float %val, 1    ; yields {i32 1, float %val}
+
+ +
+ + + +
+ Memory Access and Addressing Operations +
+ +
+ +

A key design point of an SSA-based representation is how it represents + memory. In LLVM, no memory locations are in SSA form, which makes things + very simple. This section describes how to read, write, and allocate + memory in LLVM.

+ +
+ + +
+ 'alloca' Instruction +
+ +
+ +
Syntax:
+
+  <result> = alloca <type>[, i32 <NumElements>][, align <alignment>]     ; yields {type*}:result
+
+ +
Overview:
+

The 'alloca' instruction allocates memory on the stack frame of the + currently executing function, to be automatically released when this function + returns to its caller. The object is always allocated in the generic address + space (address space zero).

+ +
Arguments:
+

The 'alloca' instruction + allocates sizeof(<type>)*NumElements bytes of memory on the + runtime stack, returning a pointer of the appropriate type to the program. + If "NumElements" is specified, it is the number of elements allocated, + otherwise "NumElements" is defaulted to be one. If a constant alignment is + specified, the value result of the allocation is guaranteed to be aligned to + at least that boundary. If not specified, or if zero, the target can choose + to align the allocation on any convenient boundary compatible with the + type.

+ +

'type' may be any sized type.

+ +
Semantics:
+

Memory is allocated; a pointer is returned. The operation is undefined if + there is insufficient stack space for the allocation. 'alloca'd + memory is automatically released when the function returns. The + 'alloca' instruction is commonly used to represent automatic + variables that must have an address available. When the function returns + (either with the ret + or unwind instructions), the memory is + reclaimed. Allocating zero bytes is legal, but the result is undefined.

+ +
Example:
+
+  %ptr = alloca i32                             ; yields {i32*}:ptr
+  %ptr = alloca i32, i32 4                      ; yields {i32*}:ptr
+  %ptr = alloca i32, i32 4, align 1024          ; yields {i32*}:ptr
+  %ptr = alloca i32, align 1024                 ; yields {i32*}:ptr
+
+ +
+ + +
'load' +Instruction
+ +
+ +
Syntax:
+
+  <result> = load <ty>* <pointer>[, align <alignment>][, !nontemporal !<index>]
+  <result> = volatile load <ty>* <pointer>[, align <alignment>][, !nontemporal !<index>]
+  !<index> = !{ i32 1 }
+
+ +
Overview:
+

The 'load' instruction is used to read from memory.

+ +
Arguments:
+

The argument to the 'load' instruction specifies the memory address + from which to load. The pointer must point to + a first class type. If the load is + marked as volatile, then the optimizer is not allowed to modify the + number or order of execution of this load with other + volatile load and store + instructions.

+ +

The optional constant align argument specifies the alignment of the + operation (that is, the alignment of the memory address). A value of 0 or an + omitted align argument means that the operation has the preferential + alignment for the target. It is the responsibility of the code emitter to + ensure that the alignment information is correct. Overestimating the + alignment results in undefined behavior. Underestimating the alignment may + produce less efficient code. An alignment of 1 is always safe.

+ +

The optional !nontemporal metadata must reference a single + metatadata name <index> corresponding to a metadata node with + one i32 entry of value 1. The existence of + the !nontemporal metatadata on the instruction tells the optimizer + and code generator that this load is not expected to be reused in the cache. + The code generator may select special instructions to save cache bandwidth, + such as the MOVNT instruction on x86.

+ +
Semantics:
+

The location of memory pointed to is loaded. If the value being loaded is of + scalar type then the number of bytes read does not exceed the minimum number + of bytes needed to hold all bits of the type. For example, loading an + i24 reads at most three bytes. When loading a value of a type like + i20 with a size that is not an integral number of bytes, the result + is undefined if the value was not originally written using a store of the + same type.

+ +
Examples:
+
+  %ptr = alloca i32                               ; yields {i32*}:ptr
+  store i32 3, i32* %ptr                          ; yields {void}
+  %val = load i32* %ptr                           ; yields {i32}:val = i32 3
+
+ +
+ + +
'store' +Instruction
+ +
+ +
Syntax:
+
+  store <ty> <value>, <ty>* <pointer>[, align <alignment>][, !nontemporal !]                   ; yields {void}
+  volatile store <ty> <value>, <ty>* <pointer>[, align <alignment>][, !nontemporal !]          ; yields {void}
+
+ +
Overview:
+

The 'store' instruction is used to write to memory.

+ +
Arguments:
+

There are two arguments to the 'store' instruction: a value to store + and an address at which to store it. The type of the + '<pointer>' operand must be a pointer to + the first class type of the + '<value>' operand. If the store is marked + as volatile, then the optimizer is not allowed to modify the number + or order of execution of this store with other + volatile load and store + instructions.

+ +

The optional constant "align" argument specifies the alignment of the + operation (that is, the alignment of the memory address). A value of 0 or an + omitted "align" argument means that the operation has the preferential + alignment for the target. It is the responsibility of the code emitter to + ensure that the alignment information is correct. Overestimating the + alignment results in an undefined behavior. Underestimating the alignment may + produce less efficient code. An alignment of 1 is always safe.

+ +

The optional !nontemporal metadata must reference a single metatadata + name corresponding to a metadata node with one i32 entry of + value 1. The existence of the !nontemporal metatadata on the + instruction tells the optimizer and code generator that this load is + not expected to be reused in the cache. The code generator may + select special instructions to save cache bandwidth, such as the + MOVNT instruction on x86.

+ + +
Semantics:
+

The contents of memory are updated to contain '<value>' at the + location specified by the '<pointer>' operand. If + '<value>' is of scalar type then the number of bytes written + does not exceed the minimum number of bytes needed to hold all bits of the + type. For example, storing an i24 writes at most three bytes. When + writing a value of a type like i20 with a size that is not an + integral number of bytes, it is unspecified what happens to the extra bits + that do not belong to the type, but they will typically be overwritten.

+ +
Example:
+
+  %ptr = alloca i32                               ; yields {i32*}:ptr
+  store i32 3, i32* %ptr                          ; yields {void}
+  %val = load i32* %ptr                           ; yields {i32}:val = i32 3
+
+ +
+ + +
+ 'getelementptr' Instruction +
+ +
+ +
Syntax:
+
+  <result> = getelementptr <pty>* <ptrval>{, <ty> <idx>}*
+  <result> = getelementptr inbounds <pty>* <ptrval>{, <ty> <idx>}*
+
+ +
Overview:
+

The 'getelementptr' instruction is used to get the address of a + subelement of an aggregate data structure. + It performs address calculation only and does not access memory.

+ +
Arguments:
+

The first argument is always a pointer, and forms the basis of the + calculation. The remaining arguments are indices that indicate which of the + elements of the aggregate object are indexed. The interpretation of each + index is dependent on the type being indexed into. The first index always + indexes the pointer value given as the first argument, the second index + indexes a value of the type pointed to (not necessarily the value directly + pointed to, since the first index can be non-zero), etc. The first type + indexed into must be a pointer value, subsequent types can be arrays, + vectors, structs and unions. Note that subsequent types being indexed into + can never be pointers, since that would require loading the pointer before + continuing calculation.

+ +

The type of each index argument depends on the type it is indexing into. + When indexing into a (optionally packed) structure or union, only i32 + integer constants are allowed. When indexing into an array, pointer + or vector, integers of any width are allowed, and they are not required to be + constant.

+ +

For example, let's consider a C code fragment and how it gets compiled to + LLVM:

+ +
+
+struct RT {
+  char A;
+  int B[10][20];
+  char C;
+};
+struct ST {
+  int X;
+  double Y;
+  struct RT Z;
+};
+
+int *foo(struct ST *s) {
+  return &s[1].Z.B[5][13];
+}
+
+
+ +

The LLVM code generated by the GCC frontend is:

+ +
+
+%RT = type { i8 , [10 x [20 x i32]], i8  }
+%ST = type { i32, double, %RT }
+
+define i32* @foo(%ST* %s) {
+entry:
+  %reg = getelementptr %ST* %s, i32 1, i32 2, i32 1, i32 5, i32 13
+  ret i32* %reg
+}
+
+
+ +
Semantics:
+

In the example above, the first index is indexing into the '%ST*' + type, which is a pointer, yielding a '%ST' = '{ i32, double, %RT + }' type, a structure. The second index indexes into the third element + of the structure, yielding a '%RT' = '{ i8 , [10 x [20 x i32]], + i8 }' type, another structure. The third index indexes into the second + element of the structure, yielding a '[10 x [20 x i32]]' type, an + array. The two dimensions of the array are subscripted into, yielding an + 'i32' type. The 'getelementptr' instruction returns a + pointer to this element, thus computing a value of 'i32*' type.

+ +

Note that it is perfectly legal to index partially through a structure, + returning a pointer to an inner element. Because of this, the LLVM code for + the given testcase is equivalent to:

+ +
+  define i32* @foo(%ST* %s) {
+    %t1 = getelementptr %ST* %s, i32 1                        ; yields %ST*:%t1
+    %t2 = getelementptr %ST* %t1, i32 0, i32 2                ; yields %RT*:%t2
+    %t3 = getelementptr %RT* %t2, i32 0, i32 1                ; yields [10 x [20 x i32]]*:%t3
+    %t4 = getelementptr [10 x [20 x i32]]* %t3, i32 0, i32 5  ; yields [20 x i32]*:%t4
+    %t5 = getelementptr [20 x i32]* %t4, i32 0, i32 13        ; yields i32*:%t5
+    ret i32* %t5
+  }
+
+ +

If the inbounds keyword is present, the result value of the + getelementptr is undefined if the base pointer is not an + in bounds address of an allocated object, or if any of the addresses + that would be formed by successive addition of the offsets implied by the + indices to the base address with infinitely precise arithmetic are not an + in bounds address of that allocated object. + The in bounds addresses for an allocated object are all the addresses + that point into the object, plus the address one byte past the end.

+ +

If the inbounds keyword is not present, the offsets are added to + the base address with silently-wrapping two's complement arithmetic, and + the result value of the getelementptr may be outside the object + pointed to by the base pointer. The result value may not necessarily be + used to access memory though, even if it happens to point into allocated + storage. See the Pointer Aliasing Rules + section for more information.

+ +

The getelementptr instruction is often confusing. For some more insight into + how it works, see the getelementptr FAQ.

+ +
Example:
+
+    ; yields [12 x i8]*:aptr
+    %aptr = getelementptr {i32, [12 x i8]}* %saptr, i64 0, i32 1
+    ; yields i8*:vptr
+    %vptr = getelementptr {i32, <2 x i8>}* %svptr, i64 0, i32 1, i32 1
+    ; yields i8*:eptr
+    %eptr = getelementptr [12 x i8]* %aptr, i64 0, i32 1
+    ; yields i32*:iptr
+    %iptr = getelementptr [10 x i32]* @arr, i16 0, i16 0
+
+ +
+ + +
Conversion Operations +
+ +
+ +

The instructions in this category are the conversion instructions (casting) + which all take a single operand and a type. They perform various bit + conversions on the operand.

+ +
+ + +
+ 'trunc .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = trunc <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'trunc' instruction truncates its operand to the + type ty2.

+ +
Arguments:
+

The 'trunc' instruction takes a value to trunc, which must + be an integer type, and a type that specifies the + size and type of the result, which must be + an integer type. The bit size of value must + be larger than the bit size of ty2. Equal sized types are not + allowed.

+ +
Semantics:
+

The 'trunc' instruction truncates the high order bits + in value and converts the remaining bits to ty2. Since the + source size must be larger than the destination size, trunc cannot + be a no-op cast. It will always truncate bits.

+ +
Example:
+
+  %X = trunc i32 257 to i8              ; yields i8:1
+  %Y = trunc i32 123 to i1              ; yields i1:true
+  %Z = trunc i32 122 to i1              ; yields i1:false
+
+ +
+ + +
+ 'zext .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = zext <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'zext' instruction zero extends its operand to type + ty2.

+ + +
Arguments:
+

The 'zext' instruction takes a value to cast, which must be of + integer type, and a type to cast it to, which must + also be of integer type. The bit size of the + value must be smaller than the bit size of the destination type, + ty2.

+ +
Semantics:
+

The zext fills the high order bits of the value with zero + bits until it reaches the size of the destination type, ty2.

+ +

When zero extending from i1, the result will always be either 0 or 1.

+ +
Example:
+
+  %X = zext i32 257 to i64              ; yields i64:257
+  %Y = zext i1 true to i32              ; yields i32:1
+
+ +
+ + +
+ 'sext .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = sext <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'sext' sign extends value to the type ty2.

+ +
Arguments:
+

The 'sext' instruction takes a value to cast, which must be of + integer type, and a type to cast it to, which must + also be of integer type. The bit size of the + value must be smaller than the bit size of the destination type, + ty2.

+ +
Semantics:
+

The 'sext' instruction performs a sign extension by copying the sign + bit (highest order bit) of the value until it reaches the bit size + of the type ty2.

+ +

When sign extending from i1, the extension always results in -1 or 0.

+ +
Example:
+
+  %X = sext i8  -1 to i16              ; yields i16   :65535
+  %Y = sext i1 true to i32             ; yields i32:-1
+
+ +
+ + +
+ 'fptrunc .. to' Instruction +
+ +
+ +
Syntax:
+
+  <result> = fptrunc <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'fptrunc' instruction truncates value to type + ty2.

+ +
Arguments:
+

The 'fptrunc' instruction takes a floating + point value to cast and a floating point type + to cast it to. The size of value must be larger than the size of + ty2. This implies that fptrunc cannot be used to make a + no-op cast.

+ +
Semantics:
+

The 'fptrunc' instruction truncates a value from a larger + floating point type to a smaller + floating point type. If the value cannot fit + within the destination type, ty2, then the results are + undefined.

+ +
Example:
+
+  %X = fptrunc double 123.0 to float         ; yields float:123.0
+  %Y = fptrunc double 1.0E+300 to float      ; yields undefined
+
+ +
+ + +
+ 'fpext .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = fpext <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'fpext' extends a floating point value to a larger + floating point value.

+ +
Arguments:
+

The 'fpext' instruction takes a + floating point value to cast, and + a floating point type to cast it to. The source + type must be smaller than the destination type.

+ +
Semantics:
+

The 'fpext' instruction extends the value from a smaller + floating point type to a larger + floating point type. The fpext cannot be + used to make a no-op cast because it always changes bits. Use + bitcast to make a no-op cast for a floating point cast.

+ +
Example:
+
+  %X = fpext float 3.1415 to double        ; yields double:3.1415
+  %Y = fpext float 1.0 to float            ; yields float:1.0 (no-op)
+
+ +
+ + +
+ 'fptoui .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = fptoui <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'fptoui' converts a floating point value to its + unsigned integer equivalent of type ty2.

+ +
Arguments:
+

The 'fptoui' instruction takes a value to cast, which must be a + scalar or vector floating point value, and a type + to cast it to ty2, which must be an integer + type. If ty is a vector floating point type, ty2 must be a + vector integer type with the same number of elements as ty

+ +
Semantics:
+

The 'fptoui' instruction converts its + floating point operand into the nearest (rounding + towards zero) unsigned integer value. If the value cannot fit + in ty2, the results are undefined.

+ +
Example:
+
+  %X = fptoui double 123.0 to i32      ; yields i32:123
+  %Y = fptoui float 1.0E+300 to i1     ; yields undefined:1
+  %Z = fptoui float 1.04E+17 to i8     ; yields undefined:1
+
+ +
+ + +
+ 'fptosi .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = fptosi <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'fptosi' instruction converts + floating point value to + type ty2.

+ +
Arguments:
+

The 'fptosi' instruction takes a value to cast, which must be a + scalar or vector floating point value, and a type + to cast it to ty2, which must be an integer + type. If ty is a vector floating point type, ty2 must be a + vector integer type with the same number of elements as ty

+ +
Semantics:
+

The 'fptosi' instruction converts its + floating point operand into the nearest (rounding + towards zero) signed integer value. If the value cannot fit in ty2, + the results are undefined.

+ +
Example:
+
+  %X = fptosi double -123.0 to i32      ; yields i32:-123
+  %Y = fptosi float 1.0E-247 to i1      ; yields undefined:1
+  %Z = fptosi float 1.04E+17 to i8      ; yields undefined:1
+
+ +
+ + +
+ 'uitofp .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = uitofp <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'uitofp' instruction regards value as an unsigned + integer and converts that value to the ty2 type.

+ +
Arguments:
+

The 'uitofp' instruction takes a value to cast, which must be a + scalar or vector integer value, and a type to cast + it to ty2, which must be an floating point + type. If ty is a vector integer type, ty2 must be a vector + floating point type with the same number of elements as ty

+ +
Semantics:
+

The 'uitofp' instruction interprets its operand as an unsigned + integer quantity and converts it to the corresponding floating point + value. If the value cannot fit in the floating point value, the results are + undefined.

+ +
Example:
+
+  %X = uitofp i32 257 to float         ; yields float:257.0
+  %Y = uitofp i8 -1 to double          ; yields double:255.0
+
+ +
+ + +
+ 'sitofp .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = sitofp <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'sitofp' instruction regards value as a signed integer + and converts that value to the ty2 type.

+ +
Arguments:
+

The 'sitofp' instruction takes a value to cast, which must be a + scalar or vector integer value, and a type to cast + it to ty2, which must be an floating point + type. If ty is a vector integer type, ty2 must be a vector + floating point type with the same number of elements as ty

+ +
Semantics:
+

The 'sitofp' instruction interprets its operand as a signed integer + quantity and converts it to the corresponding floating point value. If the + value cannot fit in the floating point value, the results are undefined.

+ +
Example:
+
+  %X = sitofp i32 257 to float         ; yields float:257.0
+  %Y = sitofp i8 -1 to double          ; yields double:-1.0
+
+ +
+ + +
+ 'ptrtoint .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = ptrtoint <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'ptrtoint' instruction converts the pointer value to + the integer type ty2.

+ +
Arguments:
+

The 'ptrtoint' instruction takes a value to cast, which + must be a pointer value, and a type to cast it to + ty2, which must be an integer type.

+ +
Semantics:
+

The 'ptrtoint' instruction converts value to integer type + ty2 by interpreting the pointer value as an integer and either + truncating or zero extending that value to the size of the integer type. If + value is smaller than ty2 then a zero extension is done. If + value is larger than ty2 then a truncation is done. If they + are the same size, then nothing is done (no-op cast) other than a type + change.

+ +
Example:
+
+  %X = ptrtoint i32* %X to i8           ; yields truncation on 32-bit architecture
+  %Y = ptrtoint i32* %x to i64          ; yields zero extension on 32-bit architecture
+
+ +
+ + +
+ 'inttoptr .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = inttoptr <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'inttoptr' instruction converts an integer value to a + pointer type, ty2.

+ +
Arguments:
+

The 'inttoptr' instruction takes an integer + value to cast, and a type to cast it to, which must be a + pointer type.

+ +
Semantics:
+

The 'inttoptr' instruction converts value to type + ty2 by applying either a zero extension or a truncation depending on + the size of the integer value. If value is larger than the + size of a pointer then a truncation is done. If value is smaller + than the size of a pointer then a zero extension is done. If they are the + same size, nothing is done (no-op cast).

+ +
Example:
+
+  %X = inttoptr i32 255 to i32*          ; yields zero extension on 64-bit architecture
+  %Y = inttoptr i32 255 to i32*          ; yields no-op on 32-bit architecture
+  %Z = inttoptr i64 0 to i32*            ; yields truncation on 32-bit architecture
+
+ +
+ + +
+ 'bitcast .. to' Instruction +
+
+ +
Syntax:
+
+  <result> = bitcast <ty> <value> to <ty2>             ; yields ty2
+
+ +
Overview:
+

The 'bitcast' instruction converts value to type + ty2 without changing any bits.

+ +
Arguments:
+

The 'bitcast' instruction takes a value to cast, which must be a + non-aggregate first class value, and a type to cast it to, which must also be + a non-aggregate first class type. The bit sizes + of value and the destination type, ty2, must be + identical. If the source type is a pointer, the destination type must also be + a pointer. This instruction supports bitwise conversion of vectors to + integers and to vectors of other types (as long as they have the same + size).

+ +
Semantics:
+

The 'bitcast' instruction converts value to type + ty2. It is always a no-op cast because no bits change with + this conversion. The conversion is done as if the value had been + stored to memory and read back as type ty2. Pointer types may only + be converted to other pointer types with this instruction. To convert + pointers to other types, use the inttoptr or + ptrtoint instructions first.

+ +
Example:
+
+  %X = bitcast i8 255 to i8              ; yields i8 :-1
+  %Y = bitcast i32* %x to sint*          ; yields sint*:%x
+  %Z = bitcast <2 x int> %V to i64;      ; yields i64: %V
+
+ +
+ + +
Other Operations
+ +
+ +

The instructions in this category are the "miscellaneous" instructions, which + defy better classification.

+ +
+ + +
'icmp' Instruction +
+ +
+ +
Syntax:
+
+  <result> = icmp <cond> <ty> <op1>, <op2>   ; yields {i1} or {<N x i1>}:result
+
+ +
Overview:
+

The 'icmp' instruction returns a boolean value or a vector of + boolean values based on comparison of its two integer, integer vector, or + pointer operands.

+ +
Arguments:
+

The 'icmp' instruction takes three operands. The first operand is + the condition code indicating the kind of comparison to perform. It is not a + value, just a keyword. The possible condition code are:

+ +
    +
  1. eq: equal
    2. +
  2. ne: not equal
    3. +
  3. ugt: unsigned greater than
    4. +
  4. uge: unsigned greater or equal
    5. +
  5. ult: unsigned less than
    6. +
  6. ule: unsigned less or equal
    7. +
  7. sgt: signed greater than
    8. +
  8. sge: signed greater or equal
    9. +
  9. slt: signed less than
    10. +
  10. sle: signed less or equal
    11. +
+ +

The remaining two arguments must be integer or + pointer or integer vector + typed. They must also be identical types.

+ +
Semantics:
+

The 'icmp' compares op1 and op2 according to the + condition code given as cond. The comparison performed always yields + either an i1 or vector of i1 + result, as follows:

+ +
    +
  1. eq: yields true if the operands are equal, + false otherwise. No sign interpretation is necessary or + performed.
    2. + +
  2. ne: yields true if the operands are unequal, + false otherwise. No sign interpretation is necessary or + performed.
    3. + +
  3. ugt: interprets the operands as unsigned values and yields + true if op1 is greater than op2.
    4. + +
  4. uge: interprets the operands as unsigned values and yields + true if op1 is greater than or equal + to op2.
    5. + +
  5. ult: interprets the operands as unsigned values and yields + true if op1 is less than op2.
    6. + +
  6. ule: interprets the operands as unsigned values and yields + true if op1 is less than or equal to op2.
    7. + +
  7. sgt: interprets the operands as signed values and yields + true if op1 is greater than op2.
    8. + +
  8. sge: interprets the operands as signed values and yields + true if op1 is greater than or equal + to op2.
    9. + +
  9. slt: interprets the operands as signed values and yields + true if op1 is less than op2.
    10. + +
  10. sle: interprets the operands as signed values and yields + true if op1 is less than or equal to op2.
    11. +
+ +

If the operands are pointer typed, the pointer + values are compared as if they were integers.

+ +

If the operands are integer vectors, then they are compared element by + element. The result is an i1 vector with the same number of elements + as the values being compared. Otherwise, the result is an i1.

+ +
Example:
+
+  <result> = icmp eq i32 4, 5          ; yields: result=false
+  <result> = icmp ne float* %X, %X     ; yields: result=false
+  <result> = icmp ult i16  4, 5        ; yields: result=true
+  <result> = icmp sgt i16  4, 5        ; yields: result=false
+  <result> = icmp ule i16 -4, 5        ; yields: result=false
+  <result> = icmp sge i16  4, 5        ; yields: result=false
+
+ +

Note that the code generator does not yet support vector types with + the icmp instruction.

+ +
+ + +
'fcmp' Instruction +
+ +
+ +
Syntax:
+
+  <result> = fcmp <cond> <ty> <op1>, <op2>     ; yields {i1} or {<N x i1>}:result
+
+ +
Overview:
+

The 'fcmp' instruction returns a boolean value or vector of boolean + values based on comparison of its operands.

+ +

If the operands are floating point scalars, then the result type is a boolean +(i1).

+ +

If the operands are floating point vectors, then the result type is a vector + of boolean with the same number of elements as the operands being + compared.

+ +
Arguments:
+

The 'fcmp' instruction takes three operands. The first operand is + the condition code indicating the kind of comparison to perform. It is not a + value, just a keyword. The possible condition code are:

+ +
    +
  1. false: no comparison, always returns false
    2. +
  2. oeq: ordered and equal
    3. +
  3. ogt: ordered and greater than
    4. +
  4. oge: ordered and greater than or equal
    5. +
  5. olt: ordered and less than
    6. +
  6. ole: ordered and less than or equal
    7. +
  7. one: ordered and not equal
    8. +
  8. ord: ordered (no nans)
    9. +
  9. ueq: unordered or equal
    10. +
  10. ugt: unordered or greater than
    11. +
  11. uge: unordered or greater than or equal
    12. +
  12. ult: unordered or less than
    13. +
  13. ule: unordered or less than or equal
    14. +
  14. une: unordered or not equal
    15. +
  15. uno: unordered (either nans)
    16. +
  16. true: no comparison, always returns true
    17. +
+ +

Ordered means that neither operand is a QNAN while + unordered means that either operand may be a QNAN.

+ +

Each of val1 and val2 arguments must be either + a floating point type or + a vector of floating point type. They must have + identical types.

+ +
Semantics:
+

The 'fcmp' instruction compares op1 and op2 + according to the condition code given as cond. If the operands are + vectors, then the vectors are compared element by element. Each comparison + performed always yields an i1 result, as + follows:

+ +
    +
  1. false: always yields false, regardless of operands.
    2. + +
  2. oeq: yields true if both operands are not a QNAN and + op1 is equal to op2.
    3. + +
  3. ogt: yields true if both operands are not a QNAN and + op1 is greater than op2.
    4. + +
  4. oge: yields true if both operands are not a QNAN and + op1 is greater than or equal to op2.
    5. + +
  5. olt: yields true if both operands are not a QNAN and + op1 is less than op2.
    6. + +
  6. ole: yields true if both operands are not a QNAN and + op1 is less than or equal to op2.
    7. + +
  7. one: yields true if both operands are not a QNAN and + op1 is not equal to op2.
    8. + +
  8. ord: yields true if both operands are not a QNAN.
    9. + +
  9. ueq: yields true if either operand is a QNAN or + op1 is equal to op2.
    10. + +
  10. ugt: yields true if either operand is a QNAN or + op1 is greater than op2.
    11. + +
  11. uge: yields true if either operand is a QNAN or + op1 is greater than or equal to op2.
    12. + +
  12. ult: yields true if either operand is a QNAN or + op1 is less than op2.
    13. + +
  13. ule: yields true if either operand is a QNAN or + op1 is less than or equal to op2.
    14. + +
  14. une: yields true if either operand is a QNAN or + op1 is not equal to op2.
    15. + +
  15. uno: yields true if either operand is a QNAN.
    16. + +
  16. true: always yields true, regardless of operands.
    17. +
+ +
Example:
+
+  <result> = fcmp oeq float 4.0, 5.0    ; yields: result=false
+  <result> = fcmp one float 4.0, 5.0    ; yields: result=true
+  <result> = fcmp olt float 4.0, 5.0    ; yields: result=true
+  <result> = fcmp ueq double 1.0, 2.0   ; yields: result=false
+
+ +

Note that the code generator does not yet support vector types with + the fcmp instruction.

+ +
+ + +
+ 'phi' Instruction +
+ +
+ +
Syntax:
+
+  <result> = phi <ty> [ <val0>, <label0>], ...
+
+ +
Overview:
+

The 'phi' instruction is used to implement the φ node in the + SSA graph representing the function.

+ +
Arguments:
+

The type of the incoming values is specified with the first type field. After + this, the 'phi' instruction takes a list of pairs as arguments, with + one pair for each predecessor basic block of the current block. Only values + of first class type may be used as the value + arguments to the PHI node. Only labels may be used as the label + arguments.

+ +

There must be no non-phi instructions between the start of a basic block and + the PHI instructions: i.e. PHI instructions must be first in a basic + block.

+ +

For the purposes of the SSA form, the use of each incoming value is deemed to + occur on the edge from the corresponding predecessor block to the current + block (but after any definition of an 'invoke' instruction's return + value on the same edge).

+ +
Semantics:
+

At runtime, the 'phi' instruction logically takes on the value + specified by the pair corresponding to the predecessor basic block that + executed just prior to the current block.

+ +
Example:
+
+Loop:       ; Infinite loop that counts from 0 on up...
+  %indvar = phi i32 [ 0, %LoopHeader ], [ %nextindvar, %Loop ]
+  %nextindvar = add i32 %indvar, 1
+  br label %Loop
+
+ +
+ + +
+ 'select' Instruction +
+ +
+ +
Syntax:
+
+  <result> = select selty <cond>, <ty> <val1>, <ty> <val2>             ; yields ty
+
+  selty is either i1 or {<N x i1>}
+
+ +
Overview:
+

The 'select' instruction is used to choose one value based on a + condition, without branching.

+ + +
Arguments:
+

The 'select' instruction requires an 'i1' value or a vector of 'i1' + values indicating the condition, and two values of the + same first class type. If the val1/val2 are + vectors and the condition is a scalar, then entire vectors are selected, not + individual elements.

+ +
Semantics:
+

If the condition is an i1 and it evaluates to 1, the instruction returns the + first value argument; otherwise, it returns the second value argument.

+ +

If the condition is a vector of i1, then the value arguments must be vectors + of the same size, and the selection is done element by element.

+ +
Example:
+
+  %X = select i1 true, i8 17, i8 42          ; yields i8:17
+
+ +

Note that the code generator does not yet support conditions + with vector type.

+ +
+ + +
+ 'call' Instruction +
+ +
+ +
Syntax:
+
+  <result> = [tail] call [cconv] [ret attrs] <ty> [<fnty>*] <fnptrval>(<function args>) [fn attrs]
+
+ +
Overview:
+

The 'call' instruction represents a simple function call.

+ +
Arguments:
+

This instruction requires several arguments:

+ +
    +
  1. The optional "tail" marker indicates that the callee function does not + access any allocas or varargs in the caller. Note that calls may be + marked "tail" even if they do not occur before + a ret instruction. If the "tail" marker is + present, the function call is eligible for tail call optimization, + but might not in fact be + optimized into a jump. The code generator may optimize calls marked + "tail" with either 1) automatic + sibling call optimization when the caller and callee have + matching signatures, or 2) forced tail call optimization when the + following extra requirements are met: +
      +
    • Caller and callee both have the calling + convention fastcc.
      • +
    • The call is in tail position (ret immediately follows call and ret + uses value of call or is void).
      • +
    • Option -tailcallopt is enabled, + or llvm::GuaranteedTailCallOpt is true.
      • +
    • Platform specific + constraints are met.
      • +
    +
    2. + +
  2. The optional "cconv" marker indicates which calling + convention the call should use. If none is specified, the call + defaults to using C calling conventions. The calling convention of the + call must match the calling convention of the target function, or else the + behavior is undefined.
    3. + +
  3. The optional Parameter Attributes list for + return values. Only 'zeroext', 'signext', and + 'inreg' attributes are valid here.
    4. + +
  4. 'ty': the type of the call instruction itself which is also the + type of the return value. Functions that return no value are marked + void.
    5. + +
  5. 'fnty': shall be the signature of the pointer to function value + being invoked. The argument types must match the types implied by this + signature. This type can be omitted if the function is not varargs and if + the function type does not return a pointer to a function.
    6. + +
  6. 'fnptrval': An LLVM value containing a pointer to a function to + be invoked. In most cases, this is a direct function invocation, but + indirect calls are just as possible, calling an arbitrary pointer + to function value.
    7. + +
  7. 'function args': argument list whose types match the function + signature argument types and parameter attributes. All arguments must be + of first class type. If the function + signature indicates the function accepts a variable number of arguments, + the extra arguments can be specified.
    8. + +
  8. The optional function attributes list. Only + 'noreturn', 'nounwind', 'readonly' and + 'readnone' attributes are valid here.
    9. +
+ +
Semantics:
+

The 'call' instruction is used to cause control flow to transfer to + a specified function, with its incoming arguments bound to the specified + values. Upon a 'ret' instruction in the called + function, control flow continues with the instruction after the function + call, and the return value of the function is bound to the result + argument.

+ +
Example:
+
+  %retval = call i32 @test(i32 %argc)
+  call i32 (i8 *, ...)* @printf(i8 * %msg, i32 12, i8 42)      ; yields i32
+  %X = tail call i32 @foo()                                    ; yields i32
+  %Y = tail call fastcc i32 @foo()  ; yields i32
+  call void %foo(i8 97 signext)
+
+  %struct.A = type { i32, i8 }
+  %r = call %struct.A @foo()                        ; yields { 32, i8 }
+  %gr = extractvalue %struct.A %r, 0                ; yields i32
+  %gr1 = extractvalue %struct.A %r, 1               ; yields i8
+  %Z = call void @foo() noreturn                    ; indicates that %foo never returns normally
+  %ZZ = call zeroext i32 @bar()                     ; Return value is %zero extended
+
+ +

llvm treats calls to some functions with names and arguments that match the +standard C99 library as being the C99 library functions, and may perform +optimizations or generate code for them under that assumption. This is +something we'd like to change in the future to provide better support for +freestanding environments and non-C-based languages.

+ +
+ + +
+ 'va_arg' Instruction +
+ +
+ +
Syntax:
+
+  <resultval> = va_arg <va_list*> <arglist>, <argty>
+
+ +
Overview:
+

The 'va_arg' instruction is used to access arguments passed through + the "variable argument" area of a function call. It is used to implement the + va_arg macro in C.

+ +
Arguments:
+

This instruction takes a va_list* value and the type of the + argument. It returns a value of the specified argument type and increments + the va_list to point to the next argument. The actual type + of va_list is target specific.

+ +
Semantics:
+

The 'va_arg' instruction loads an argument of the specified type + from the specified va_list and causes the va_list to point + to the next argument. For more information, see the variable argument + handling Intrinsic Functions.

+ +

It is legal for this instruction to be called in a function which does not + take a variable number of arguments, for example, the vfprintf + function.

+ +

va_arg is an LLVM instruction instead of + an intrinsic function because it takes a type as an + argument.

+ +
Example:
+

See the variable argument processing section.

+ +

Note that the code generator does not yet fully support va_arg on many + targets. Also, it does not currently support va_arg with aggregate types on + any target.

+ +
+ + +
Intrinsic Functions
+ + +
+ +

LLVM supports the notion of an "intrinsic function". These functions have + well known names and semantics and are required to follow certain + restrictions. Overall, these intrinsics represent an extension mechanism for + the LLVM language that does not require changing all of the transformations + in LLVM when adding to the language (or the bitcode reader/writer, the + parser, etc...).

+ +

Intrinsic function names must all start with an "llvm." prefix. This + prefix is reserved in LLVM for intrinsic names; thus, function names may not + begin with this prefix. Intrinsic functions must always be external + functions: you cannot define the body of intrinsic functions. Intrinsic + functions may only be used in call or invoke instructions: it is illegal to + take the address of an intrinsic function. Additionally, because intrinsic + functions are part of the LLVM language, it is required if any are added that + they be documented here.

+ +

Some intrinsic functions can be overloaded, i.e., the intrinsic represents a + family of functions that perform the same operation but on different data + types. Because LLVM can represent over 8 million different integer types, + overloading is used commonly to allow an intrinsic function to operate on any + integer type. One or more of the argument types or the result type can be + overloaded to accept any integer type. Argument types may also be defined as + exactly matching a previous argument's type or the result type. This allows + an intrinsic function which accepts multiple arguments, but needs all of them + to be of the same type, to only be overloaded with respect to a single + argument or the result.

+ +

Overloaded intrinsics will have the names of its overloaded argument types + encoded into its function name, each preceded by a period. Only those types + which are overloaded result in a name suffix. Arguments whose type is matched + against another type do not. For example, the llvm.ctpop function + can take an integer of any width and returns an integer of exactly the same + integer width. This leads to a family of functions such as + i8 @llvm.ctpop.i8(i8 %val) and i29 @llvm.ctpop.i29(i29 + %val). Only one type, the return type, is overloaded, and only one type + suffix is required. Because the argument's type is matched against the return + type, it does not require its own name suffix.

+ +

To learn how to add an intrinsic function, please see the + Extending LLVM Guide.

+ +
+ + +
+ Variable Argument Handling Intrinsics +
+ +
+ +

Variable argument support is defined in LLVM with + the va_arg instruction and these three + intrinsic functions. These functions are related to the similarly named + macros defined in the <stdarg.h> header file.

+ +

All of these functions operate on arguments that use a target-specific value + type "va_list". The LLVM assembly language reference manual does + not define what this type is, so all transformations should be prepared to + handle these functions regardless of the type used.

+ +

This example shows how the va_arg + instruction and the variable argument handling intrinsic functions are + used.

+ +
+
+define i32 @test(i32 %X, ...) {
+  ; Initialize variable argument processing
+  %ap = alloca i8*
+  %ap2 = bitcast i8** %ap to i8*
+  call void @llvm.va_start(i8* %ap2)
+
+  ; Read a single integer argument
+  %tmp = va_arg i8** %ap, i32
+
+  ; Demonstrate usage of llvm.va_copy and llvm.va_end
+  %aq = alloca i8*
+  %aq2 = bitcast i8** %aq to i8*
+  call void @llvm.va_copy(i8* %aq2, i8* %ap2)
+  call void @llvm.va_end(i8* %aq2)
+
+  ; Stop processing of arguments.
+  call void @llvm.va_end(i8* %ap2)
+  ret i32 %tmp
+}
+
+declare void @llvm.va_start(i8*)
+declare void @llvm.va_copy(i8*, i8*)
+declare void @llvm.va_end(i8*)
+
+
+ +
+ + +
+ 'llvm.va_start' Intrinsic +
+ + +
+ +
Syntax:
+
+  declare void %llvm.va_start(i8* <arglist>)
+
+ +
Overview:
+

The 'llvm.va_start' intrinsic initializes *<arglist> + for subsequent use by va_arg.

+ +
Arguments:
+

The argument is a pointer to a va_list element to initialize.

+ +
Semantics:
+

The 'llvm.va_start' intrinsic works just like the va_start + macro available in C. In a target-dependent way, it initializes + the va_list element to which the argument points, so that the next + call to va_arg will produce the first variable argument passed to + the function. Unlike the C va_start macro, this intrinsic does not + need to know the last argument of the function as the compiler can figure + that out.

+ +
+ + +
+ 'llvm.va_end' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.va_end(i8* <arglist>)
+
+ +
Overview:
+

The 'llvm.va_end' intrinsic destroys *<arglist>, + which has been initialized previously + with llvm.va_start + or llvm.va_copy.

+ +
Arguments:
+

The argument is a pointer to a va_list to destroy.

+ +
Semantics:
+

The 'llvm.va_end' intrinsic works just like the va_end + macro available in C. In a target-dependent way, it destroys + the va_list element to which the argument points. Calls + to llvm.va_start + and llvm.va_copy must be matched exactly + with calls to llvm.va_end.

+ +
+ + +
+ 'llvm.va_copy' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.va_copy(i8* <destarglist>, i8* <srcarglist>)
+
+ +
Overview:
+

The 'llvm.va_copy' intrinsic copies the current argument position + from the source argument list to the destination argument list.

+ +
Arguments:
+

The first argument is a pointer to a va_list element to initialize. + The second argument is a pointer to a va_list element to copy + from.

+ +
Semantics:
+

The 'llvm.va_copy' intrinsic works just like the va_copy + macro available in C. In a target-dependent way, it copies the + source va_list element into the destination va_list + element. This intrinsic is necessary because + the llvm.va_start intrinsic may be + arbitrarily complex and require, for example, memory allocation.

+ +
+ + +
+ Accurate Garbage Collection Intrinsics +
+ +
+ +

LLVM support for Accurate Garbage +Collection (GC) requires the implementation and generation of these +intrinsics. These intrinsics allow identification of GC +roots on the stack, as well as garbage collector implementations that +require read and write +barriers. Front-ends for type-safe garbage collected languages should generate +these intrinsics to make use of the LLVM garbage collectors. For more details, +see Accurate Garbage Collection with +LLVM.

+ +

The garbage collection intrinsics only operate on objects in the generic + address space (address space zero).

+ +
+ + +
+ 'llvm.gcroot' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.gcroot(i8** %ptrloc, i8* %metadata)
+
+ +
Overview:
+

The 'llvm.gcroot' intrinsic declares the existence of a GC root to + the code generator, and allows some metadata to be associated with it.

+ +
Arguments:
+

The first argument specifies the address of a stack object that contains the + root pointer. The second pointer (which must be either a constant or a + global value address) contains the meta-data to be associated with the + root.

+ +
Semantics:
+

At runtime, a call to this intrinsic stores a null pointer into the "ptrloc" + location. At compile-time, the code generator generates information to allow + the runtime to find the pointer at GC safe points. The 'llvm.gcroot' + intrinsic may only be used in a function which specifies a GC + algorithm.

+ +
+ + +
+ 'llvm.gcread' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i8* @llvm.gcread(i8* %ObjPtr, i8** %Ptr)
+
+ +
Overview:
+

The 'llvm.gcread' intrinsic identifies reads of references from heap + locations, allowing garbage collector implementations that require read + barriers.

+ +
Arguments:
+

The second argument is the address to read from, which should be an address + allocated from the garbage collector. The first object is a pointer to the + start of the referenced object, if needed by the language runtime (otherwise + null).

+ +
Semantics:
+

The 'llvm.gcread' intrinsic has the same semantics as a load + instruction, but may be replaced with substantially more complex code by the + garbage collector runtime, as needed. The 'llvm.gcread' intrinsic + may only be used in a function which specifies a GC + algorithm.

+ +
+ + +
+ 'llvm.gcwrite' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.gcwrite(i8* %P1, i8* %Obj, i8** %P2)
+
+ +
Overview:
+

The 'llvm.gcwrite' intrinsic identifies writes of references to heap + locations, allowing garbage collector implementations that require write + barriers (such as generational or reference counting collectors).

+ +
Arguments:
+

The first argument is the reference to store, the second is the start of the + object to store it to, and the third is the address of the field of Obj to + store to. If the runtime does not require a pointer to the object, Obj may + be null.

+ +
Semantics:
+

The 'llvm.gcwrite' intrinsic has the same semantics as a store + instruction, but may be replaced with substantially more complex code by the + garbage collector runtime, as needed. The 'llvm.gcwrite' intrinsic + may only be used in a function which specifies a GC + algorithm.

+ +
+ + +
+ Code Generator Intrinsics +
+ +
+ +

These intrinsics are provided by LLVM to expose special features that may + only be implemented with code generator support.

+ +
+ + +
+ 'llvm.returnaddress' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i8  *@llvm.returnaddress(i32 <level>)
+
+ +
Overview:
+

The 'llvm.returnaddress' intrinsic attempts to compute a + target-specific value indicating the return address of the current function + or one of its callers.

+ +
Arguments:
+

The argument to this intrinsic indicates which function to return the address + for. Zero indicates the calling function, one indicates its caller, etc. + The argument is required to be a constant integer value.

+ +
Semantics:
+

The 'llvm.returnaddress' intrinsic either returns a pointer + indicating the return address of the specified call frame, or zero if it + cannot be identified. The value returned by this intrinsic is likely to be + incorrect or 0 for arguments other than zero, so it should only be used for + debugging purposes.

+ +

Note that calling this intrinsic does not prevent function inlining or other + aggressive transformations, so the value returned may not be that of the + obvious source-language caller.

+ +
+ + +
+ 'llvm.frameaddress' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i8 *@llvm.frameaddress(i32 <level>)
+
+ +
Overview:
+

The 'llvm.frameaddress' intrinsic attempts to return the + target-specific frame pointer value for the specified stack frame.

+ +
Arguments:
+

The argument to this intrinsic indicates which function to return the frame + pointer for. Zero indicates the calling function, one indicates its caller, + etc. The argument is required to be a constant integer value.

+ +
Semantics:
+

The 'llvm.frameaddress' intrinsic either returns a pointer + indicating the frame address of the specified call frame, or zero if it + cannot be identified. The value returned by this intrinsic is likely to be + incorrect or 0 for arguments other than zero, so it should only be used for + debugging purposes.

+ +

Note that calling this intrinsic does not prevent function inlining or other + aggressive transformations, so the value returned may not be that of the + obvious source-language caller.

+ +
+ + +
+ 'llvm.stacksave' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i8 *@llvm.stacksave()
+
+ +
Overview:
+

The 'llvm.stacksave' intrinsic is used to remember the current state + of the function stack, for use + with llvm.stackrestore. This is + useful for implementing language features like scoped automatic variable + sized arrays in C99.

+ +
Semantics:
+

This intrinsic returns a opaque pointer value that can be passed + to llvm.stackrestore. When + an llvm.stackrestore intrinsic is executed with a value saved + from llvm.stacksave, it effectively restores the state of the stack + to the state it was in when the llvm.stacksave intrinsic executed. + In practice, this pops any alloca blocks from the + stack that were allocated after the llvm.stacksave was executed.

+ +
+ + +
+ 'llvm.stackrestore' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.stackrestore(i8 * %ptr)
+
+ +
Overview:
+

The 'llvm.stackrestore' intrinsic is used to restore the state of + the function stack to the state it was in when the + corresponding llvm.stacksave intrinsic + executed. This is useful for implementing language features like scoped + automatic variable sized arrays in C99.

+ +
Semantics:
+

See the description + for llvm.stacksave.

+ +
+ + +
+ 'llvm.prefetch' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.prefetch(i8* <address>, i32 <rw>, i32 <locality>)
+
+ +
Overview:
+

The 'llvm.prefetch' intrinsic is a hint to the code generator to + insert a prefetch instruction if supported; otherwise, it is a noop. + Prefetches have no effect on the behavior of the program but can change its + performance characteristics.

+ +
Arguments:
+

address is the address to be prefetched, rw is the + specifier determining if the fetch should be for a read (0) or write (1), + and locality is a temporal locality specifier ranging from (0) - no + locality, to (3) - extremely local keep in cache. The rw + and locality arguments must be constant integers.

+ +
Semantics:
+

This intrinsic does not modify the behavior of the program. In particular, + prefetches cannot trap and do not produce a value. On targets that support + this intrinsic, the prefetch can provide hints to the processor cache for + better performance.

+ +
+ + +
+ 'llvm.pcmarker' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.pcmarker(i32 <id>)
+
+ +
Overview:
+

The 'llvm.pcmarker' intrinsic is a method to export a Program + Counter (PC) in a region of code to simulators and other tools. The method + is target specific, but it is expected that the marker will use exported + symbols to transmit the PC of the marker. The marker makes no guarantees + that it will remain with any specific instruction after optimizations. It is + possible that the presence of a marker will inhibit optimizations. The + intended use is to be inserted after optimizations to allow correlations of + simulation runs.

+ +
Arguments:
+

id is a numerical id identifying the marker.

+ +
Semantics:
+

This intrinsic does not modify the behavior of the program. Backends that do + not support this intrinsic may ignore it.

+ +
+ + +
+ 'llvm.readcyclecounter' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i64 @llvm.readcyclecounter( )
+
+ +
Overview:
+

The 'llvm.readcyclecounter' intrinsic provides access to the cycle + counter register (or similar low latency, high accuracy clocks) on those + targets that support it. On X86, it should map to RDTSC. On Alpha, it + should map to RPCC. As the backing counters overflow quickly (on the order + of 9 seconds on alpha), this should only be used for small timings.

+ +
Semantics:
+

When directly supported, reading the cycle counter should not modify any + memory. Implementations are allowed to either return a application specific + value or a system wide value. On backends without support, this is lowered + to a constant 0.

+ +
+ + +
+ Standard C Library Intrinsics +
+ +
+ +

LLVM provides intrinsics for a few important standard C library functions. + These intrinsics allow source-language front-ends to pass information about + the alignment of the pointer arguments to the code generator, providing + opportunity for more efficient code generation.

+ +
+ + +
+ 'llvm.memcpy' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.memcpy on any + integer bit width. Not all targets support all bit widths however.

+ +
+  declare void @llvm.memcpy.i8(i8 * <dest>, i8 * <src>,
+                               i8 <len>, i32 <align>)
+  declare void @llvm.memcpy.i16(i8 * <dest>, i8 * <src>,
+                                i16 <len>, i32 <align>)
+  declare void @llvm.memcpy.i32(i8 * <dest>, i8 * <src>,
+                                i32 <len>, i32 <align>)
+  declare void @llvm.memcpy.i64(i8 * <dest>, i8 * <src>,
+                                i64 <len>, i32 <align>)
+
+ +
Overview:
+

The 'llvm.memcpy.*' intrinsics copy a block of memory from the + source location to the destination location.

+ +

Note that, unlike the standard libc function, the llvm.memcpy.* + intrinsics do not return a value, and takes an extra alignment argument.

+ +
Arguments:
+

The first argument is a pointer to the destination, the second is a pointer + to the source. The third argument is an integer argument specifying the + number of bytes to copy, and the fourth argument is the alignment of the + source and destination locations.

+ +

If the call to this intrinsic has an alignment value that is not 0 or 1, + then the caller guarantees that both the source and destination pointers are + aligned to that boundary.

+ +
Semantics:
+

The 'llvm.memcpy.*' intrinsics copy a block of memory from the + source location to the destination location, which are not allowed to + overlap. It copies "len" bytes of memory over. If the argument is known to + be aligned to some boundary, this can be specified as the fourth argument, + otherwise it should be set to 0 or 1.

+ +
+ + +
+ 'llvm.memmove' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.memmove on any integer bit + width. Not all targets support all bit widths however.

+ +
+  declare void @llvm.memmove.i8(i8 * <dest>, i8 * <src>,
+                                i8 <len>, i32 <align>)
+  declare void @llvm.memmove.i16(i8 * <dest>, i8 * <src>,
+                                 i16 <len>, i32 <align>)
+  declare void @llvm.memmove.i32(i8 * <dest>, i8 * <src>,
+                                 i32 <len>, i32 <align>)
+  declare void @llvm.memmove.i64(i8 * <dest>, i8 * <src>,
+                                 i64 <len>, i32 <align>)
+
+ +
Overview:
+

The 'llvm.memmove.*' intrinsics move a block of memory from the + source location to the destination location. It is similar to the + 'llvm.memcpy' intrinsic but allows the two memory locations to + overlap.

+ +

Note that, unlike the standard libc function, the llvm.memmove.* + intrinsics do not return a value, and takes an extra alignment argument.

+ +
Arguments:
+

The first argument is a pointer to the destination, the second is a pointer + to the source. The third argument is an integer argument specifying the + number of bytes to copy, and the fourth argument is the alignment of the + source and destination locations.

+ +

If the call to this intrinsic has an alignment value that is not 0 or 1, + then the caller guarantees that the source and destination pointers are + aligned to that boundary.

+ +
Semantics:
+

The 'llvm.memmove.*' intrinsics copy a block of memory from the + source location to the destination location, which may overlap. It copies + "len" bytes of memory over. If the argument is known to be aligned to some + boundary, this can be specified as the fourth argument, otherwise it should + be set to 0 or 1.

+ +
+ + +
+ 'llvm.memset.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.memset on any integer bit + width. Not all targets support all bit widths however.

+ +
+  declare void @llvm.memset.i8(i8 * <dest>, i8 <val>,
+                               i8 <len>, i32 <align>)
+  declare void @llvm.memset.i16(i8 * <dest>, i8 <val>,
+                                i16 <len>, i32 <align>)
+  declare void @llvm.memset.i32(i8 * <dest>, i8 <val>,
+                                i32 <len>, i32 <align>)
+  declare void @llvm.memset.i64(i8 * <dest>, i8 <val>,
+                                i64 <len>, i32 <align>)
+
+ +
Overview:
+

The 'llvm.memset.*' intrinsics fill a block of memory with a + particular byte value.

+ +

Note that, unlike the standard libc function, the llvm.memset + intrinsic does not return a value, and takes an extra alignment argument.

+ +
Arguments:
+

The first argument is a pointer to the destination to fill, the second is the + byte value to fill it with, the third argument is an integer argument + specifying the number of bytes to fill, and the fourth argument is the known + alignment of destination location.

+ +

If the call to this intrinsic has an alignment value that is not 0 or 1, + then the caller guarantees that the destination pointer is aligned to that + boundary.

+ +
Semantics:
+

The 'llvm.memset.*' intrinsics fill "len" bytes of memory starting + at the destination location. If the argument is known to be aligned to some + boundary, this can be specified as the fourth argument, otherwise it should + be set to 0 or 1.

+ +
+ + +
+ 'llvm.sqrt.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.sqrt on any + floating point or vector of floating point type. Not all targets support all + types however.

+ +
+  declare float     @llvm.sqrt.f32(float %Val)
+  declare double    @llvm.sqrt.f64(double %Val)
+  declare x86_fp80  @llvm.sqrt.f80(x86_fp80 %Val)
+  declare fp128     @llvm.sqrt.f128(fp128 %Val)
+  declare ppc_fp128 @llvm.sqrt.ppcf128(ppc_fp128 %Val)
+
+ +
Overview:
+

The 'llvm.sqrt' intrinsics return the sqrt of the specified operand, + returning the same value as the libm 'sqrt' functions would. + Unlike sqrt in libm, however, llvm.sqrt has undefined + behavior for negative numbers other than -0.0 (which allows for better + optimization, because there is no need to worry about errno being + set). llvm.sqrt(-0.0) is defined to return -0.0 like IEEE sqrt.

+ +
Arguments:
+

The argument and return value are floating point numbers of the same + type.

+ +
Semantics:
+

This function returns the sqrt of the specified operand if it is a + nonnegative floating point number.

+ +
+ + +
+ 'llvm.powi.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.powi on any + floating point or vector of floating point type. Not all targets support all + types however.

+ +
+  declare float     @llvm.powi.f32(float  %Val, i32 %power)
+  declare double    @llvm.powi.f64(double %Val, i32 %power)
+  declare x86_fp80  @llvm.powi.f80(x86_fp80  %Val, i32 %power)
+  declare fp128     @llvm.powi.f128(fp128 %Val, i32 %power)
+  declare ppc_fp128 @llvm.powi.ppcf128(ppc_fp128  %Val, i32 %power)
+
+ +
Overview:
+

The 'llvm.powi.*' intrinsics return the first operand raised to the + specified (positive or negative) power. The order of evaluation of + multiplications is not defined. When a vector of floating point type is + used, the second argument remains a scalar integer value.

+ +
Arguments:
+

The second argument is an integer power, and the first is a value to raise to + that power.

+ +
Semantics:
+

This function returns the first value raised to the second power with an + unspecified sequence of rounding operations.

+ +
+ + +
+ 'llvm.sin.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.sin on any + floating point or vector of floating point type. Not all targets support all + types however.

+ +
+  declare float     @llvm.sin.f32(float  %Val)
+  declare double    @llvm.sin.f64(double %Val)
+  declare x86_fp80  @llvm.sin.f80(x86_fp80  %Val)
+  declare fp128     @llvm.sin.f128(fp128 %Val)
+  declare ppc_fp128 @llvm.sin.ppcf128(ppc_fp128  %Val)
+
+ +
Overview:
+

The 'llvm.sin.*' intrinsics return the sine of the operand.

+ +
Arguments:
+

The argument and return value are floating point numbers of the same + type.

+ +
Semantics:
+

This function returns the sine of the specified operand, returning the same + values as the libm sin functions would, and handles error conditions + in the same way.

+ +
+ + +
+ 'llvm.cos.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.cos on any + floating point or vector of floating point type. Not all targets support all + types however.

+ +
+  declare float     @llvm.cos.f32(float  %Val)
+  declare double    @llvm.cos.f64(double %Val)
+  declare x86_fp80  @llvm.cos.f80(x86_fp80  %Val)
+  declare fp128     @llvm.cos.f128(fp128 %Val)
+  declare ppc_fp128 @llvm.cos.ppcf128(ppc_fp128  %Val)
+
+ +
Overview:
+

The 'llvm.cos.*' intrinsics return the cosine of the operand.

+ +
Arguments:
+

The argument and return value are floating point numbers of the same + type.

+ +
Semantics:
+

This function returns the cosine of the specified operand, returning the same + values as the libm cos functions would, and handles error conditions + in the same way.

+ +
+ + +
+ 'llvm.pow.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.pow on any + floating point or vector of floating point type. Not all targets support all + types however.

+ +
+  declare float     @llvm.pow.f32(float  %Val, float %Power)
+  declare double    @llvm.pow.f64(double %Val, double %Power)
+  declare x86_fp80  @llvm.pow.f80(x86_fp80  %Val, x86_fp80 %Power)
+  declare fp128     @llvm.pow.f128(fp128 %Val, fp128 %Power)
+  declare ppc_fp128 @llvm.pow.ppcf128(ppc_fp128  %Val, ppc_fp128 Power)
+
+ +
Overview:
+

The 'llvm.pow.*' intrinsics return the first operand raised to the + specified (positive or negative) power.

+ +
Arguments:
+

The second argument is a floating point power, and the first is a value to + raise to that power.

+ +
Semantics:
+

This function returns the first value raised to the second power, returning + the same values as the libm pow functions would, and handles error + conditions in the same way.

+ +
+ + +
+ Bit Manipulation Intrinsics +
+ +
+ +

LLVM provides intrinsics for a few important bit manipulation operations. + These allow efficient code generation for some algorithms.

+ +
+ + +
+ 'llvm.bswap.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic function. You can use bswap on any integer + type that is an even number of bytes (i.e. BitWidth % 16 == 0).

+ +
+  declare i16 @llvm.bswap.i16(i16 <id>)
+  declare i32 @llvm.bswap.i32(i32 <id>)
+  declare i64 @llvm.bswap.i64(i64 <id>)
+
+ +
Overview:
+

The 'llvm.bswap' family of intrinsics is used to byte swap integer + values with an even number of bytes (positive multiple of 16 bits). These + are useful for performing operations on data that is not in the target's + native byte order.

+ +
Semantics:
+

The llvm.bswap.i16 intrinsic returns an i16 value that has the high + and low byte of the input i16 swapped. Similarly, + the llvm.bswap.i32 intrinsic returns an i32 value that has the four + bytes of the input i32 swapped, so that if the input bytes are numbered 0, 1, + 2, 3 then the returned i32 will have its bytes in 3, 2, 1, 0 order. + The llvm.bswap.i48, llvm.bswap.i64 and other intrinsics + extend this concept to additional even-byte lengths (6 bytes, 8 bytes and + more, respectively).

+ +
+ + +
+ 'llvm.ctpop.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.ctpop on any integer bit + width. Not all targets support all bit widths however.

+ +
+  declare i8 @llvm.ctpop.i8(i8  <src>)
+  declare i16 @llvm.ctpop.i16(i16 <src>)
+  declare i32 @llvm.ctpop.i32(i32 <src>)
+  declare i64 @llvm.ctpop.i64(i64 <src>)
+  declare i256 @llvm.ctpop.i256(i256 <src>)
+
+ +
Overview:
+

The 'llvm.ctpop' family of intrinsics counts the number of bits set + in a value.

+ +
Arguments:
+

The only argument is the value to be counted. The argument may be of any + integer type. The return type must match the argument type.

+ +
Semantics:
+

The 'llvm.ctpop' intrinsic counts the 1's in a variable.

+ +
+ + +
+ 'llvm.ctlz.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.ctlz on any + integer bit width. Not all targets support all bit widths however.

+ +
+  declare i8 @llvm.ctlz.i8 (i8  <src>)
+  declare i16 @llvm.ctlz.i16(i16 <src>)
+  declare i32 @llvm.ctlz.i32(i32 <src>)
+  declare i64 @llvm.ctlz.i64(i64 <src>)
+  declare i256 @llvm.ctlz.i256(i256 <src>)
+
+ +
Overview:
+

The 'llvm.ctlz' family of intrinsic functions counts the number of + leading zeros in a variable.

+ +
Arguments:
+

The only argument is the value to be counted. The argument may be of any + integer type. The return type must match the argument type.

+ +
Semantics:
+

The 'llvm.ctlz' intrinsic counts the leading (most significant) + zeros in a variable. If the src == 0 then the result is the size in bits of + the type of src. For example, llvm.ctlz(i32 2) = 30.

+ +
+ + +
+ 'llvm.cttz.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.cttz on any + integer bit width. Not all targets support all bit widths however.

+ +
+  declare i8 @llvm.cttz.i8 (i8  <src>)
+  declare i16 @llvm.cttz.i16(i16 <src>)
+  declare i32 @llvm.cttz.i32(i32 <src>)
+  declare i64 @llvm.cttz.i64(i64 <src>)
+  declare i256 @llvm.cttz.i256(i256 <src>)
+
+ +
Overview:
+

The 'llvm.cttz' family of intrinsic functions counts the number of + trailing zeros.

+ +
Arguments:
+

The only argument is the value to be counted. The argument may be of any + integer type. The return type must match the argument type.

+ +
Semantics:
+

The 'llvm.cttz' intrinsic counts the trailing (least significant) + zeros in a variable. If the src == 0 then the result is the size in bits of + the type of src. For example, llvm.cttz(2) = 1.

+ +
+ + +
+ Arithmetic with Overflow Intrinsics +
+ +
+ +

LLVM provides intrinsics for some arithmetic with overflow operations.

+ +
+ + +
+ 'llvm.sadd.with.overflow.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.sadd.with.overflow + on any integer bit width.

+ +
+  declare {i16, i1} @llvm.sadd.with.overflow.i16(i16 %a, i16 %b)
+  declare {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
+  declare {i64, i1} @llvm.sadd.with.overflow.i64(i64 %a, i64 %b)
+
+ +
Overview:
+

The 'llvm.sadd.with.overflow' family of intrinsic functions perform + a signed addition of the two arguments, and indicate whether an overflow + occurred during the signed summation.

+ +
Arguments:
+

The arguments (%a and %b) and the first element of the result structure may + be of integer types of any bit width, but they must have the same bit + width. The second element of the result structure must be of + type i1. %a and %b are the two values that will + undergo signed addition.

+ +
Semantics:
+

The 'llvm.sadd.with.overflow' family of intrinsic functions perform + a signed addition of the two variables. They return a structure — the + first element of which is the signed summation, and the second element of + which is a bit specifying if the signed summation resulted in an + overflow.

+ +
Examples:
+
+  %res = call {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
+  %sum = extractvalue {i32, i1} %res, 0
+  %obit = extractvalue {i32, i1} %res, 1
+  br i1 %obit, label %overflow, label %normal
+
+ +
+ + +
+ 'llvm.uadd.with.overflow.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.uadd.with.overflow + on any integer bit width.

+ +
+  declare {i16, i1} @llvm.uadd.with.overflow.i16(i16 %a, i16 %b)
+  declare {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+  declare {i64, i1} @llvm.uadd.with.overflow.i64(i64 %a, i64 %b)
+
+ +
Overview:
+

The 'llvm.uadd.with.overflow' family of intrinsic functions perform + an unsigned addition of the two arguments, and indicate whether a carry + occurred during the unsigned summation.

+ +
Arguments:
+

The arguments (%a and %b) and the first element of the result structure may + be of integer types of any bit width, but they must have the same bit + width. The second element of the result structure must be of + type i1. %a and %b are the two values that will + undergo unsigned addition.

+ +
Semantics:
+

The 'llvm.uadd.with.overflow' family of intrinsic functions perform + an unsigned addition of the two arguments. They return a structure — + the first element of which is the sum, and the second element of which is a + bit specifying if the unsigned summation resulted in a carry.

+ +
Examples:
+
+  %res = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+  %sum = extractvalue {i32, i1} %res, 0
+  %obit = extractvalue {i32, i1} %res, 1
+  br i1 %obit, label %carry, label %normal
+
+ +
+ + +
+ 'llvm.ssub.with.overflow.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.ssub.with.overflow + on any integer bit width.

+ +
+  declare {i16, i1} @llvm.ssub.with.overflow.i16(i16 %a, i16 %b)
+  declare {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
+  declare {i64, i1} @llvm.ssub.with.overflow.i64(i64 %a, i64 %b)
+
+ +
Overview:
+

The 'llvm.ssub.with.overflow' family of intrinsic functions perform + a signed subtraction of the two arguments, and indicate whether an overflow + occurred during the signed subtraction.

+ +
Arguments:
+

The arguments (%a and %b) and the first element of the result structure may + be of integer types of any bit width, but they must have the same bit + width. The second element of the result structure must be of + type i1. %a and %b are the two values that will + undergo signed subtraction.

+ +
Semantics:
+

The 'llvm.ssub.with.overflow' family of intrinsic functions perform + a signed subtraction of the two arguments. They return a structure — + the first element of which is the subtraction, and the second element of + which is a bit specifying if the signed subtraction resulted in an + overflow.

+ +
Examples:
+
+  %res = call {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
+  %sum = extractvalue {i32, i1} %res, 0
+  %obit = extractvalue {i32, i1} %res, 1
+  br i1 %obit, label %overflow, label %normal
+
+ +
+ + +
+ 'llvm.usub.with.overflow.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.usub.with.overflow + on any integer bit width.

+ +
+  declare {i16, i1} @llvm.usub.with.overflow.i16(i16 %a, i16 %b)
+  declare {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
+  declare {i64, i1} @llvm.usub.with.overflow.i64(i64 %a, i64 %b)
+
+ +
Overview:
+

The 'llvm.usub.with.overflow' family of intrinsic functions perform + an unsigned subtraction of the two arguments, and indicate whether an + overflow occurred during the unsigned subtraction.

+ +
Arguments:
+

The arguments (%a and %b) and the first element of the result structure may + be of integer types of any bit width, but they must have the same bit + width. The second element of the result structure must be of + type i1. %a and %b are the two values that will + undergo unsigned subtraction.

+ +
Semantics:
+

The 'llvm.usub.with.overflow' family of intrinsic functions perform + an unsigned subtraction of the two arguments. They return a structure — + the first element of which is the subtraction, and the second element of + which is a bit specifying if the unsigned subtraction resulted in an + overflow.

+ +
Examples:
+
+  %res = call {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
+  %sum = extractvalue {i32, i1} %res, 0
+  %obit = extractvalue {i32, i1} %res, 1
+  br i1 %obit, label %overflow, label %normal
+
+ +
+ + +
+ 'llvm.smul.with.overflow.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.smul.with.overflow + on any integer bit width.

+ +
+  declare {i16, i1} @llvm.smul.with.overflow.i16(i16 %a, i16 %b)
+  declare {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
+  declare {i64, i1} @llvm.smul.with.overflow.i64(i64 %a, i64 %b)
+
+ +
Overview:
+ +

The 'llvm.smul.with.overflow' family of intrinsic functions perform + a signed multiplication of the two arguments, and indicate whether an + overflow occurred during the signed multiplication.

+ +
Arguments:
+

The arguments (%a and %b) and the first element of the result structure may + be of integer types of any bit width, but they must have the same bit + width. The second element of the result structure must be of + type i1. %a and %b are the two values that will + undergo signed multiplication.

+ +
Semantics:
+

The 'llvm.smul.with.overflow' family of intrinsic functions perform + a signed multiplication of the two arguments. They return a structure — + the first element of which is the multiplication, and the second element of + which is a bit specifying if the signed multiplication resulted in an + overflow.

+ +
Examples:
+
+  %res = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
+  %sum = extractvalue {i32, i1} %res, 0
+  %obit = extractvalue {i32, i1} %res, 1
+  br i1 %obit, label %overflow, label %normal
+
+ +
+ + +
+ 'llvm.umul.with.overflow.*' Intrinsics +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.umul.with.overflow + on any integer bit width.

+ +
+  declare {i16, i1} @llvm.umul.with.overflow.i16(i16 %a, i16 %b)
+  declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
+  declare {i64, i1} @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
+
+ +
Overview:
+

The 'llvm.umul.with.overflow' family of intrinsic functions perform + a unsigned multiplication of the two arguments, and indicate whether an + overflow occurred during the unsigned multiplication.

+ +
Arguments:
+

The arguments (%a and %b) and the first element of the result structure may + be of integer types of any bit width, but they must have the same bit + width. The second element of the result structure must be of + type i1. %a and %b are the two values that will + undergo unsigned multiplication.

+ +
Semantics:
+

The 'llvm.umul.with.overflow' family of intrinsic functions perform + an unsigned multiplication of the two arguments. They return a structure + — the first element of which is the multiplication, and the second + element of which is a bit specifying if the unsigned multiplication resulted + in an overflow.

+ +
Examples:
+
+  %res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
+  %sum = extractvalue {i32, i1} %res, 0
+  %obit = extractvalue {i32, i1} %res, 1
+  br i1 %obit, label %overflow, label %normal
+
+ +
+ + +
+ Debugger Intrinsics +
+ +
+ +

The LLVM debugger intrinsics (which all start with llvm.dbg. + prefix), are described in + the LLVM Source + Level Debugging document.

+ +
+ + +
+ Exception Handling Intrinsics +
+ +
+ +

The LLVM exception handling intrinsics (which all start with + llvm.eh. prefix), are described in + the LLVM Exception + Handling document.

+ +
+ + +
+ Trampoline Intrinsic +
+ +
+ +

This intrinsic makes it possible to excise one parameter, marked with + the nest attribute, from a function. The result is a callable + function pointer lacking the nest parameter - the caller does not need to + provide a value for it. Instead, the value to use is stored in advance in a + "trampoline", a block of memory usually allocated on the stack, which also + contains code to splice the nest value into the argument list. This is used + to implement the GCC nested function address extension.

+ +

For example, if the function is + i32 f(i8* nest %c, i32 %x, i32 %y) then the resulting function + pointer has signature i32 (i32, i32)*. It can be created as + follows:

+ +
+
+  %tramp = alloca [10 x i8], align 4 ; size and alignment only correct for X86
+  %tramp1 = getelementptr [10 x i8]* %tramp, i32 0, i32 0
+  %p = call i8* @llvm.init.trampoline( i8* %tramp1, i8* bitcast (i32 (i8* nest , i32, i32)* @f to i8*), i8* %nval )
+  %fp = bitcast i8* %p to i32 (i32, i32)*
+
+
+ +

The call %val = call i32 %fp( i32 %x, i32 %y ) is then equivalent + to %val = call i32 %f( i8* %nval, i32 %x, i32 %y ).

+ +
+ + +
+ 'llvm.init.trampoline' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i8* @llvm.init.trampoline(i8* <tramp>, i8* <func>, i8* <nval>)
+
+ +
Overview:
+

This fills the memory pointed to by tramp with code and returns a + function pointer suitable for executing it.

+ +
Arguments:
+

The llvm.init.trampoline intrinsic takes three arguments, all + pointers. The tramp argument must point to a sufficiently large and + sufficiently aligned block of memory; this memory is written to by the + intrinsic. Note that the size and the alignment are target-specific - LLVM + currently provides no portable way of determining them, so a front-end that + generates this intrinsic needs to have some target-specific knowledge. + The func argument must hold a function bitcast to + an i8*.

+ +
Semantics:
+

The block of memory pointed to by tramp is filled with target + dependent code, turning it into a function. A pointer to this function is + returned, but needs to be bitcast to an appropriate + function pointer type before being called. The new function's signature + is the same as that of func with any arguments marked with + the nest attribute removed. At most one such nest argument + is allowed, and it must be of pointer type. Calling the new function is + equivalent to calling func with the same argument list, but + with nval used for the missing nest argument. If, after + calling llvm.init.trampoline, the memory pointed to + by tramp is modified, then the effect of any later call to the + returned function pointer is undefined.

+ +
+ + +
+ Atomic Operations and Synchronization Intrinsics +
+ +
+ +

These intrinsic functions expand the "universal IR" of LLVM to represent + hardware constructs for atomic operations and memory synchronization. This + provides an interface to the hardware, not an interface to the programmer. It + is aimed at a low enough level to allow any programming models or APIs + (Application Programming Interfaces) which need atomic behaviors to map + cleanly onto it. It is also modeled primarily on hardware behavior. Just as + hardware provides a "universal IR" for source languages, it also provides a + starting point for developing a "universal" atomic operation and + synchronization IR.

+ +

These do not form an API such as high-level threading libraries, + software transaction memory systems, atomic primitives, and intrinsic + functions as found in BSD, GNU libc, atomic_ops, APR, and other system and + application libraries. The hardware interface provided by LLVM should allow + a clean implementation of all of these APIs and parallel programming models. + No one model or paradigm should be selected above others unless the hardware + itself ubiquitously does so.

+ +
+ + +
+ 'llvm.memory.barrier' Intrinsic +
+
+
Syntax:
+
+  declare void @llvm.memory.barrier( i1 <ll>, i1 <ls>, i1 <sl>, i1 <ss>, i1 <device> )
+
+ +
Overview:
+

The llvm.memory.barrier intrinsic guarantees ordering between + specific pairs of memory access types.

+ +
Arguments:
+

The llvm.memory.barrier intrinsic requires five boolean arguments. + The first four arguments enables a specific barrier as listed below. The + fifth argument specifies that the barrier applies to io or device or uncached + memory.

+ +
    +
  • ll: load-load barrier
    • +
  • ls: load-store barrier
    • +
  • sl: store-load barrier
    • +
  • ss: store-store barrier
    • +
  • device: barrier applies to device and uncached memory also.
    • +
+ +
Semantics:
+

This intrinsic causes the system to enforce some ordering constraints upon + the loads and stores of the program. This barrier does not + indicate when any events will occur, it only enforces + an order in which they occur. For any of the specified pairs of load + and store operations (f.ex. load-load, or store-load), all of the first + operations preceding the barrier will complete before any of the second + operations succeeding the barrier begin. Specifically the semantics for each + pairing is as follows:

+ +
    +
  • ll: All loads before the barrier must complete before any load + after the barrier begins.
    • +
  • ls: All loads before the barrier must complete before any + store after the barrier begins.
    • +
  • ss: All stores before the barrier must complete before any + store after the barrier begins.
    • +
  • sl: All stores before the barrier must complete before any + load after the barrier begins.
    • +
+ +

These semantics are applied with a logical "and" behavior when more than one + is enabled in a single memory barrier intrinsic.

+ +

Backends may implement stronger barriers than those requested when they do + not support as fine grained a barrier as requested. Some architectures do + not need all types of barriers and on such architectures, these become + noops.

+ +
Example:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 4, %ptr
+
+%result1  = load i32* %ptr      ; yields {i32}:result1 = 4
+            call void @llvm.memory.barrier( i1 false, i1 true, i1 false, i1 false )
+                                ; guarantee the above finishes
+            store i32 8, %ptr   ; before this begins
+
+ +
+ + +
+ 'llvm.atomic.cmp.swap.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.atomic.cmp.swap on + any integer bit width and for different address spaces. Not all targets + support all bit widths however.

+ +
+  declare i8 @llvm.atomic.cmp.swap.i8.p0i8( i8* <ptr>, i8 <cmp>, i8 <val> )
+  declare i16 @llvm.atomic.cmp.swap.i16.p0i16( i16* <ptr>, i16 <cmp>, i16 <val> )
+  declare i32 @llvm.atomic.cmp.swap.i32.p0i32( i32* <ptr>, i32 <cmp>, i32 <val> )
+  declare i64 @llvm.atomic.cmp.swap.i64.p0i64( i64* <ptr>, i64 <cmp>, i64 <val> )
+
+ +
Overview:
+

This loads a value in memory and compares it to a given value. If they are + equal, it stores a new value into the memory.

+ +
Arguments:
+

The llvm.atomic.cmp.swap intrinsic takes three arguments. The result + as well as both cmp and val must be integer values with the + same bit width. The ptr argument must be a pointer to a value of + this integer type. While any bit width integer may be used, targets may only + lower representations they support in hardware.

+ +
Semantics:
+

This entire intrinsic must be executed atomically. It first loads the value + in memory pointed to by ptr and compares it with the + value cmp. If they are equal, val is stored into the + memory. The loaded value is yielded in all cases. This provides the + equivalent of an atomic compare-and-swap operation within the SSA + framework.

+ +
Examples:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 4, %ptr
+
+%val1     = add i32 4, 4
+%result1  = call i32 @llvm.atomic.cmp.swap.i32.p0i32( i32* %ptr, i32 4, %val1 )
+                                          ; yields {i32}:result1 = 4
+%stored1  = icmp eq i32 %result1, 4       ; yields {i1}:stored1 = true
+%memval1  = load i32* %ptr                ; yields {i32}:memval1 = 8
+
+%val2     = add i32 1, 1
+%result2  = call i32 @llvm.atomic.cmp.swap.i32.p0i32( i32* %ptr, i32 5, %val2 )
+                                          ; yields {i32}:result2 = 8
+%stored2  = icmp eq i32 %result2, 5       ; yields {i1}:stored2 = false
+
+%memval2  = load i32* %ptr                ; yields {i32}:memval2 = 8
+
+ +
+ + +
+ 'llvm.atomic.swap.*' Intrinsic +
+
+
Syntax:
+ +

This is an overloaded intrinsic. You can use llvm.atomic.swap on any + integer bit width. Not all targets support all bit widths however.

+ +
+  declare i8 @llvm.atomic.swap.i8.p0i8( i8* <ptr>, i8 <val> )
+  declare i16 @llvm.atomic.swap.i16.p0i16( i16* <ptr>, i16 <val> )
+  declare i32 @llvm.atomic.swap.i32.p0i32( i32* <ptr>, i32 <val> )
+  declare i64 @llvm.atomic.swap.i64.p0i64( i64* <ptr>, i64 <val> )
+
+ +
Overview:
+

This intrinsic loads the value stored in memory at ptr and yields + the value from memory. It then stores the value in val in the memory + at ptr.

+ +
Arguments:
+

The llvm.atomic.swap intrinsic takes two arguments. Both + the val argument and the result must be integers of the same bit + width. The first argument, ptr, must be a pointer to a value of this + integer type. The targets may only lower integer representations they + support.

+ +
Semantics:
+

This intrinsic loads the value pointed to by ptr, yields it, and + stores val back into ptr atomically. This provides the + equivalent of an atomic swap operation within the SSA framework.

+ +
Examples:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 4, %ptr
+
+%val1     = add i32 4, 4
+%result1  = call i32 @llvm.atomic.swap.i32.p0i32( i32* %ptr, i32 %val1 )
+                                        ; yields {i32}:result1 = 4
+%stored1  = icmp eq i32 %result1, 4     ; yields {i1}:stored1 = true
+%memval1  = load i32* %ptr              ; yields {i32}:memval1 = 8
+
+%val2     = add i32 1, 1
+%result2  = call i32 @llvm.atomic.swap.i32.p0i32( i32* %ptr, i32 %val2 )
+                                        ; yields {i32}:result2 = 8
+
+%stored2  = icmp eq i32 %result2, 8     ; yields {i1}:stored2 = true
+%memval2  = load i32* %ptr              ; yields {i32}:memval2 = 2
+
+ +
+ + +
+ 'llvm.atomic.load.add.*' Intrinsic + +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.atomic.load.add on + any integer bit width. Not all targets support all bit widths however.

+ +
+  declare i8 @llvm.atomic.load.add.i8..p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.add.i16..p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.add.i32..p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.add.i64..p0i64( i64* <ptr>, i64 <delta> )
+
+ +
Overview:
+

This intrinsic adds delta to the value stored in memory + at ptr. It yields the original value at ptr.

+ +
Arguments:
+

The intrinsic takes two arguments, the first a pointer to an integer value + and the second an integer value. The result is also an integer value. These + integer types can have any bit width, but they must all have the same bit + width. The targets may only lower integer representations they support.

+ +
Semantics:
+

This intrinsic does a series of operations atomically. It first loads the + value stored at ptr. It then adds delta, stores the result + to ptr. It yields the original value stored at ptr.

+ +
Examples:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 4, %ptr
+%result1  = call i32 @llvm.atomic.load.add.i32.p0i32( i32* %ptr, i32 4 )
+                                ; yields {i32}:result1 = 4
+%result2  = call i32 @llvm.atomic.load.add.i32.p0i32( i32* %ptr, i32 2 )
+                                ; yields {i32}:result2 = 8
+%result3  = call i32 @llvm.atomic.load.add.i32.p0i32( i32* %ptr, i32 5 )
+                                ; yields {i32}:result3 = 10
+%memval1  = load i32* %ptr      ; yields {i32}:memval1 = 15
+
+ +
+ + +
+ 'llvm.atomic.load.sub.*' Intrinsic + +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use llvm.atomic.load.sub on + any integer bit width and for different address spaces. Not all targets + support all bit widths however.

+ +
+  declare i8 @llvm.atomic.load.sub.i8.p0i32( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.sub.i16.p0i32( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.sub.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.sub.i64.p0i32( i64* <ptr>, i64 <delta> )
+
+ +
Overview:
+

This intrinsic subtracts delta to the value stored in memory at + ptr. It yields the original value at ptr.

+ +
Arguments:
+

The intrinsic takes two arguments, the first a pointer to an integer value + and the second an integer value. The result is also an integer value. These + integer types can have any bit width, but they must all have the same bit + width. The targets may only lower integer representations they support.

+ +
Semantics:
+

This intrinsic does a series of operations atomically. It first loads the + value stored at ptr. It then subtracts delta, stores the + result to ptr. It yields the original value stored + at ptr.

+ +
Examples:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 8, %ptr
+%result1  = call i32 @llvm.atomic.load.sub.i32.p0i32( i32* %ptr, i32 4 )
+                                ; yields {i32}:result1 = 8
+%result2  = call i32 @llvm.atomic.load.sub.i32.p0i32( i32* %ptr, i32 2 )
+                                ; yields {i32}:result2 = 4
+%result3  = call i32 @llvm.atomic.load.sub.i32.p0i32( i32* %ptr, i32 5 )
+                                ; yields {i32}:result3 = 2
+%memval1  = load i32* %ptr      ; yields {i32}:memval1 = -3
+
+ +
+ + +
+ 'llvm.atomic.load.and.*' Intrinsic
+ 'llvm.atomic.load.nand.*' Intrinsic
+ 'llvm.atomic.load.or.*' Intrinsic
+ 'llvm.atomic.load.xor.*' Intrinsic
+
+ +
+ +
Syntax:
+

These are overloaded intrinsics. You can + use llvm.atomic.load_and, llvm.atomic.load_nand, + llvm.atomic.load_or, and llvm.atomic.load_xor on any integer + bit width and for different address spaces. Not all targets support all bit + widths however.

+ +
+  declare i8 @llvm.atomic.load.and.i8.p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.and.i16.p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.and.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.and.i64.p0i64( i64* <ptr>, i64 <delta> )
+
+ +
+  declare i8 @llvm.atomic.load.or.i8.p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.or.i16.p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.or.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.or.i64.p0i64( i64* <ptr>, i64 <delta> )
+
+ +
+  declare i8 @llvm.atomic.load.nand.i8.p0i32( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.nand.i16.p0i32( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.nand.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.nand.i64.p0i32( i64* <ptr>, i64 <delta> )
+
+ +
+  declare i8 @llvm.atomic.load.xor.i8.p0i32( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.xor.i16.p0i32( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.xor.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.xor.i64.p0i32( i64* <ptr>, i64 <delta> )
+
+ +
Overview:
+

These intrinsics bitwise the operation (and, nand, or, xor) delta to + the value stored in memory at ptr. It yields the original value + at ptr.

+ +
Arguments:
+

These intrinsics take two arguments, the first a pointer to an integer value + and the second an integer value. The result is also an integer value. These + integer types can have any bit width, but they must all have the same bit + width. The targets may only lower integer representations they support.

+ +
Semantics:
+

These intrinsics does a series of operations atomically. They first load the + value stored at ptr. They then do the bitwise + operation delta, store the result to ptr. They yield the + original value stored at ptr.

+ +
Examples:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 0x0F0F, %ptr
+%result0  = call i32 @llvm.atomic.load.nand.i32.p0i32( i32* %ptr, i32 0xFF )
+                                ; yields {i32}:result0 = 0x0F0F
+%result1  = call i32 @llvm.atomic.load.and.i32.p0i32( i32* %ptr, i32 0xFF )
+                                ; yields {i32}:result1 = 0xFFFFFFF0
+%result2  = call i32 @llvm.atomic.load.or.i32.p0i32( i32* %ptr, i32 0F )
+                                ; yields {i32}:result2 = 0xF0
+%result3  = call i32 @llvm.atomic.load.xor.i32.p0i32( i32* %ptr, i32 0F )
+                                ; yields {i32}:result3 = FF
+%memval1  = load i32* %ptr      ; yields {i32}:memval1 = F0
+
+ +
+ + +
+ 'llvm.atomic.load.max.*' Intrinsic
+ 'llvm.atomic.load.min.*' Intrinsic
+ 'llvm.atomic.load.umax.*' Intrinsic
+ 'llvm.atomic.load.umin.*' Intrinsic
+
+ +
+ +
Syntax:
+

These are overloaded intrinsics. You can use llvm.atomic.load_max, + llvm.atomic.load_min, llvm.atomic.load_umax, and + llvm.atomic.load_umin on any integer bit width and for different + address spaces. Not all targets support all bit widths however.

+ +
+  declare i8 @llvm.atomic.load.max.i8.p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.max.i16.p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.max.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.max.i64.p0i64( i64* <ptr>, i64 <delta> )
+
+ +
+  declare i8 @llvm.atomic.load.min.i8.p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.min.i16.p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.min.i32..p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.min.i64..p0i64( i64* <ptr>, i64 <delta> )
+
+ +
+  declare i8 @llvm.atomic.load.umax.i8.p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.umax.i16.p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.umax.i32.p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.umax.i64.p0i64( i64* <ptr>, i64 <delta> )
+
+ +
+  declare i8 @llvm.atomic.load.umin.i8..p0i8( i8* <ptr>, i8 <delta> )
+  declare i16 @llvm.atomic.load.umin.i16.p0i16( i16* <ptr>, i16 <delta> )
+  declare i32 @llvm.atomic.load.umin.i32..p0i32( i32* <ptr>, i32 <delta> )
+  declare i64 @llvm.atomic.load.umin.i64..p0i64( i64* <ptr>, i64 <delta> )
+
+ +
Overview:
+

These intrinsics takes the signed or unsigned minimum or maximum of + delta and the value stored in memory at ptr. It yields the + original value at ptr.

+ +
Arguments:
+

These intrinsics take two arguments, the first a pointer to an integer value + and the second an integer value. The result is also an integer value. These + integer types can have any bit width, but they must all have the same bit + width. The targets may only lower integer representations they support.

+ +
Semantics:
+

These intrinsics does a series of operations atomically. They first load the + value stored at ptr. They then do the signed or unsigned min or + max delta and the value, store the result to ptr. They + yield the original value stored at ptr.

+ +
Examples:
+
+%mallocP  = tail call i8* @malloc(i32 ptrtoint (i32* getelementptr (i32* null, i32 1) to i32))
+%ptr      = bitcast i8* %mallocP to i32*
+            store i32 7, %ptr
+%result0  = call i32 @llvm.atomic.load.min.i32.p0i32( i32* %ptr, i32 -2 )
+                                ; yields {i32}:result0 = 7
+%result1  = call i32 @llvm.atomic.load.max.i32.p0i32( i32* %ptr, i32 8 )
+                                ; yields {i32}:result1 = -2
+%result2  = call i32 @llvm.atomic.load.umin.i32.p0i32( i32* %ptr, i32 10 )
+                                ; yields {i32}:result2 = 8
+%result3  = call i32 @llvm.atomic.load.umax.i32.p0i32( i32* %ptr, i32 30 )
+                                ; yields {i32}:result3 = 8
+%memval1  = load i32* %ptr      ; yields {i32}:memval1 = 30
+
+ +
+ + + +
+ Memory Use Markers +
+ +
+ +

This class of intrinsics exists to information about the lifetime of memory + objects and ranges where variables are immutable.

+ +
+ + +
+ 'llvm.lifetime.start' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.lifetime.start(i64 <size>, i8* nocapture <ptr>)
+
+ +
Overview:
+

The 'llvm.lifetime.start' intrinsic specifies the start of a memory + object's lifetime.

+ +
Arguments:
+

The first argument is a constant integer representing the size of the + object, or -1 if it is variable sized. The second argument is a pointer to + the object.

+ +
Semantics:
+

This intrinsic indicates that before this point in the code, the value of the + memory pointed to by ptr is dead. This means that it is known to + never be used and has an undefined value. A load from the pointer that + precedes this intrinsic can be replaced with + 'undef'.

+ +
+ + +
+ 'llvm.lifetime.end' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.lifetime.end(i64 <size>, i8* nocapture <ptr>)
+
+ +
Overview:
+

The 'llvm.lifetime.end' intrinsic specifies the end of a memory + object's lifetime.

+ +
Arguments:
+

The first argument is a constant integer representing the size of the + object, or -1 if it is variable sized. The second argument is a pointer to + the object.

+ +
Semantics:
+

This intrinsic indicates that after this point in the code, the value of the + memory pointed to by ptr is dead. This means that it is known to + never be used and has an undefined value. Any stores into the memory object + following this intrinsic may be removed as dead. + +

+ + +
+ 'llvm.invariant.start' Intrinsic +
+ +
+ +
Syntax:
+
+  declare {}* @llvm.invariant.start(i64 <size>, i8* nocapture <ptr>) readonly
+
+ +
Overview:
+

The 'llvm.invariant.start' intrinsic specifies that the contents of + a memory object will not change.

+ +
Arguments:
+

The first argument is a constant integer representing the size of the + object, or -1 if it is variable sized. The second argument is a pointer to + the object.

+ +
Semantics:
+

This intrinsic indicates that until an llvm.invariant.end that uses + the return value, the referenced memory location is constant and + unchanging.

+ +
+ + +
+ 'llvm.invariant.end' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.invariant.end({}* <start>, i64 <size>, i8* nocapture <ptr>)
+
+ +
Overview:
+

The 'llvm.invariant.end' intrinsic specifies that the contents of + a memory object are mutable.

+ +
Arguments:
+

The first argument is the matching llvm.invariant.start intrinsic. + The second argument is a constant integer representing the size of the + object, or -1 if it is variable sized and the third argument is a pointer + to the object.

+ +
Semantics:
+

This intrinsic indicates that the memory is mutable again.

+ +
+ + +
+ General Intrinsics +
+ +
+ +

This class of intrinsics is designed to be generic and has no specific + purpose.

+ +
+ + +
+ 'llvm.var.annotation' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.var.annotation(i8* <val>, i8* <str>, i8* <str>, i32  <int> )
+
+ +
Overview:
+

The 'llvm.var.annotation' intrinsic.

+ +
Arguments:
+

The first argument is a pointer to a value, the second is a pointer to a + global string, the third is a pointer to a global string which is the source + file name, and the last argument is the line number.

+ +
Semantics:
+

This intrinsic allows annotation of local variables with arbitrary strings. + This can be useful for special purpose optimizations that want to look for + these annotations. These have no other defined use, they are ignored by code + generation and optimization.

+ +
+ + +
+ 'llvm.annotation.*' Intrinsic +
+ +
+ +
Syntax:
+

This is an overloaded intrinsic. You can use 'llvm.annotation' on + any integer bit width.

+ +
+  declare i8 @llvm.annotation.i8(i8 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i16 @llvm.annotation.i16(i16 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i32 @llvm.annotation.i32(i32 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i64 @llvm.annotation.i64(i64 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i256 @llvm.annotation.i256(i256 <val>, i8* <str>, i8* <str>, i32  <int> )
+
+ +
Overview:
+

The 'llvm.annotation' intrinsic.

+ +
Arguments:
+

The first argument is an integer value (result of some expression), the + second is a pointer to a global string, the third is a pointer to a global + string which is the source file name, and the last argument is the line + number. It returns the value of the first argument.

+ +
Semantics:
+

This intrinsic allows annotations to be put on arbitrary expressions with + arbitrary strings. This can be useful for special purpose optimizations that + want to look for these annotations. These have no other defined use, they + are ignored by code generation and optimization.

+ +
+ + +
+ 'llvm.trap' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.trap()
+
+ +
Overview:
+

The 'llvm.trap' intrinsic.

+ +
Arguments:
+

None.

+ +
Semantics:
+

This intrinsics is lowered to the target dependent trap instruction. If the + target does not have a trap instruction, this intrinsic will be lowered to + the call of the abort() function.

+ +
+ + +
+ 'llvm.stackprotector' Intrinsic +
+ +
+ +
Syntax:
+
+  declare void @llvm.stackprotector( i8* <guard>, i8** <slot> )
+
+ +
Overview:
+

The llvm.stackprotector intrinsic takes the guard and + stores it onto the stack at slot. The stack slot is adjusted to + ensure that it is placed on the stack before local variables.

+ +
Arguments:
+

The llvm.stackprotector intrinsic requires two pointer + arguments. The first argument is the value loaded from the stack + guard @__stack_chk_guard. The second variable is an alloca + that has enough space to hold the value of the guard.

+ +
Semantics:
+

This intrinsic causes the prologue/epilogue inserter to force the position of + the AllocaInst stack slot to be before local variables on the + stack. This is to ensure that if a local variable on the stack is + overwritten, it will destroy the value of the guard. When the function exits, + the guard on the stack is checked against the original guard. If they're + different, then the program aborts by calling the __stack_chk_fail() + function.

+ +
+ + +
+ 'llvm.objectsize' Intrinsic +
+ +
+ +
Syntax:
+
+  declare i32 @llvm.objectsize.i32( i8* <object>, i1 <type> )
+  declare i64 @llvm.objectsize.i64( i8* <object>, i1 <type> )
+
+ +
Overview:
+

The llvm.objectsize intrinsic is designed to provide information + to the optimizers to discover at compile time either a) when an + operation like memcpy will either overflow a buffer that corresponds to + an object, or b) to determine that a runtime check for overflow isn't + necessary. An object in this context means an allocation of a + specific class, structure, array, or other object.

+ +
Arguments:
+

The llvm.objectsize intrinsic takes two arguments. The first + argument is a pointer to or into the object. The second argument + is a boolean 0 or 1. This argument determines whether you want the + maximum (0) or minimum (1) bytes remaining. This needs to be a literal 0 or + 1, variables are not allowed.

+ +
Semantics:
+

The llvm.objectsize intrinsic is lowered to either a constant + representing the size of the object concerned or i32/i64 -1 or 0 + (depending on the type argument if the size cannot be determined + at compile time.

+ +
+ + +
+
+ Valid CSS + Valid HTML 4.01 + + Chris Lattner
+ The LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-03-11 18:12:20 -0600 (Thu, 11 Mar 2010) $ +
+ + + Added: www-releases/trunk/2.7/docs/Lexicon.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/Lexicon.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/Lexicon.html (added) +++ www-releases/trunk/2.7/docs/Lexicon.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,263 @@ + + + + + The LLVM Lexicon + + + + + +
The LLVM Lexicon
+

NOTE: This document is a work in progress!

+ +
Table Of Contents
+ +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
- A -
ADCE
- B -
BURS
- C -
CSE
- D -
DAGDerived PointerDSADSE
- G -
GC
- I -
IPAIPOISel
- L -
LCSSALICMLoad-VN
- O -
Object Pointer
- P -
PRE
- R -
RAUWReassociationRoot
- S -
Safe PointSCCSCCPSDISelSRoAStack Map
+
+ + +
Definitions
+ + +
- A -
+
+
+
ADCE
+
Aggressive Dead Code Elimination
+
+
+ +
- B -
+
+
+
BURS
+
Bottom Up Rewriting System—A method of instruction selection for + code generation. An example is the BURG tool.
+
+
+ +
- C -
+
+
+
CSE
+
Common Subexpression Elimination. An optimization that removes common + subexpression compuation. For example (a+b)*(a+b) has two + subexpressions that are the same: (a+b). This optimization would + perform the addition only once and then perform the multiply (but only if + it's compulationally correct/safe). +
+
+ +
- D -
+
+
+
DAG
+
Directed Acyclic Graph
+
Derived Pointer
+
A pointer to the interior of an object, such that a garbage collector + is unable to use the pointer for reachability analysis. While a derived + pointer is live, the corresponding object pointer must be kept in a root, + otherwise the collector might free the referenced object. With copying + collectors, derived pointers pose an additional hazard that they may be + invalidated at any safe point. This term is used in + opposition to object pointer.
+
DSA
+
Data Structure Analysis
+
DSE
+
Dead Store Elimination
+
+
+ +
- G -
+
+
+
GC
+
Garbage Collection. The practice of using reachability analysis instead + of explicit memory management to reclaim unused memory.
+
+
+ +
- H -
+
+
+
Heap
+
In garbage collection, the region of memory which is managed using + reachability analysis.
+
+
+ +
- I -
+
+
+
IPA
+
Inter-Procedural Analysis. Refers to any variety of code analysis that + occurs between procedures, functions or compilation units (modules).
+
IPO
+
Inter-Procedural Optimization. Refers to any variety of code + optimization that occurs between procedures, functions or compilation units + (modules).
+
ISel
+
Instruction Selection.
+
+
+ +
- L -
+
+
+
LCSSA
+
Loop-Closed Static Single Assignment Form
+
LICM
+
Loop Invariant Code Motion
+
Load-VN
+
Load Value Numbering
+
+
+ + +
- O -
+
+
+
Object Pointer
+
A pointer to an object such that the garbage collector is able to trace + references contained within the object. This term is used in opposition to + derived pointer.
+
+
+ + +
- P -
+
+
+
PRE
+
Partial Redundancy Elimination
+
+
+ + +
- R -
+
+
+
RAUW
An abbreviation for Replace + All Uses With. The functions User::replaceUsesOfWith(), + Value::replaceAllUsesWith(), and Constant::replaceUsesOfWithOnConstant() + implement the replacement of one Value with another by iterating over its + def/use chain and fixing up all of the pointers to point to the new value. + See also def/use chains. +
+
Reassociation
Rearranging + associative expressions to promote better redundancy elimination and other + optimization. For example, changing (A+B-A) into (B+A-A), permitting it to + be optimized into (B+0) then (B).
+
Root
In garbage collection, a + pointer variable lying outside of the heap from which + the collector begins its reachability analysis. In the context of code + generation, "root" almost always refers to a "stack root" -- a local or + temporary variable within an executing function.
+
+
+ + +
- S -
+
+
+
Safe Point
+
In garbage collection, it is necessary to identify stack + roots so that reachability analysis may proceed. It may be infeasible to + provide this information for every instruction, so instead the information + may is calculated only at designated safe points. With a copying collector, + derived pointers must not be retained across + safe points and object pointers must be + reloaded from stack roots.
+
SDISel
+
Selection DAG Instruction Selection.
+
SCC
+
Strongly Connected Component
+
SCCP
+
Sparse Conditional Constant Propagation
+
SRoA
+
Scalar Replacement of Aggregates
+
SSA
+
Static Single Assignment
+
Stack Map
+
In garbage collection, metadata emitted by the code generator which + identifies roots within the stack frame of an executing + function.
+
+
+ +
+
Valid CSSValid HTML 4.01The LLVM Team
+The LLVM Compiler Infrastructure
+Last modified: $Date: 2008-12-14 02:01:51 -0600 (Sun, 14 Dec 2008) $ +
+ + + Added: www-releases/trunk/2.7/docs/LinkTimeOptimization.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/LinkTimeOptimization.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/LinkTimeOptimization.html (added) +++ www-releases/trunk/2.7/docs/LinkTimeOptimization.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,390 @@ + + + + LLVM Link Time Optimization: Design and Implementation + + + +
+ LLVM Link Time Optimization: Design and Implementation +
+ + + +
+

Written by Devang Patel and Nick Kledzik

+
+ + +
+Description +
+ + +
+

+LLVM features powerful intermodular optimizations which can be used at link +time. Link Time Optimization (LTO) is another name for intermodular optimization +when performed during the link stage. This document describes the interface +and design between the LTO optimizer and the linker.

+
+ + +
+Design Philosophy +
+ + +
+

+The LLVM Link Time Optimizer provides complete transparency, while doing +intermodular optimization, in the compiler tool chain. Its main goal is to let +the developer take advantage of intermodular optimizations without making any +significant changes to the developer's makefiles or build system. This is +achieved through tight integration with the linker. In this model, the linker +treates LLVM bitcode files like native object files and allows mixing and +matching among them. The linker uses libLTO, a shared +object, to handle LLVM bitcode files. This tight integration between +the linker and LLVM optimizer helps to do optimizations that are not possible +in other models. The linker input allows the optimizer to avoid relying on +conservative escape analysis. +

+
+ + +
+ Example of link time optimization +
+ +
+

The following example illustrates the advantages of LTO's integrated + approach and clean interface. This example requires a system linker which + supports LTO through the interface described in this document. Here, + llvm-gcc transparently invokes system linker.

+
    +
  • Input source file a.c is compiled into LLVM bitcode form. +
  • Input source file main.c is compiled into native object code. +
+
+--- a.h ---
+extern int foo1(void);
+extern void foo2(void);
+extern void foo4(void);
+--- a.c ---
+#include "a.h"
+
+static signed int i = 0;
+
+void foo2(void) {
+ i = -1;
+}
+
+static int foo3() {
+foo4();
+return 10;
+}
+
+int foo1(void) {
+int data = 0;
+
+if (i < 0) { data = foo3(); }
+
+data = data + 42;
+return data;
+}
+
+--- main.c ---
+#include <stdio.h>
+#include "a.h"
+
+void foo4(void) {
+ printf ("Hi\n");
+}
+
+int main() {
+ return foo1();
+}
+
+--- command lines ---
+$ llvm-gcc --emit-llvm -c a.c -o a.o  # <-- a.o is LLVM bitcode file
+$ llvm-gcc -c main.c -o main.o # <-- main.o is native object file
+$ llvm-gcc a.o main.o -o main # <-- standard link command without any modifications
+
+

In this example, the linker recognizes that foo2() is an + externally visible symbol defined in LLVM bitcode file. The linker completes + its usual symbol resolution + pass and finds that foo2() is not used anywhere. This information + is used by the LLVM optimizer and it removes foo2(). As soon as + foo2() is removed, the optimizer recognizes that condition + i < 0 is always false, which means foo3() is never + used. Hence, the optimizer removes foo3(), also. And this in turn, + enables linker to remove foo4(). This example illustrates the + advantage of tight integration with the linker. Here, the optimizer can not + remove foo3() without the linker's input. +

+
+ + +
+ Alternative Approaches +
+ +
+
+
Compiler driver invokes link time optimizer separately.
+
In this model the link time optimizer is not able to take advantage of + information collected during the linker's normal symbol resolution phase. + In the above example, the optimizer can not remove foo2() without + the linker's input because it is externally visible. This in turn prohibits + the optimizer from removing foo3().
+
Use separate tool to collect symbol information from all object + files.
+
In this model, a new, separate, tool or library replicates the linker's + capability to collect information for link time optimization. Not only is + this code duplication difficult to justify, but it also has several other + disadvantages. For example, the linking semantics and the features + provided by the linker on various platform are not unique. This means, + this new tool needs to support all such features and platforms in one + super tool or a separate tool per platform is required. This increases + maintenance cost for link time optimizer significantly, which is not + necessary. This approach also requires staying synchronized with linker + developements on various platforms, which is not the main focus of the link + time optimizer. Finally, this approach increases end user's build time due + to the duplication of work done by this separate tool and the linker itself. +
+
+
+ + +
+ Multi-phase communication between libLTO and linker +
+ +
+

The linker collects information about symbol defininitions and uses in + various link objects which is more accurate than any information collected + by other tools during typical build cycles. The linker collects this + information by looking at the definitions and uses of symbols in native .o + files and using symbol visibility information. The linker also uses + user-supplied information, such as a list of exported symbols. LLVM + optimizer collects control flow information, data flow information and knows + much more about program structure from the optimizer's point of view. + Our goal is to take advantage of tight integration between the linker and + the optimizer by sharing this information during various linking phases. +

+
+ + +
+ Phase 1 : Read LLVM Bitcode Files +
+ +
+

The linker first reads all object files in natural order and collects + symbol information. This includes native object files as well as LLVM bitcode + files. To minimize the cost to the linker in the case that all .o files + are native object files, the linker only calls lto_module_create() + when a supplied object file is found to not be a native object file. If + lto_module_create() returns that the file is an LLVM bitcode file, + the linker + then iterates over the module using lto_module_get_symbol_name() and + lto_module_get_symbol_attribute() to get all symbols defined and + referenced. + This information is added to the linker's global symbol table. +

+

The lto* functions are all implemented in a shared object libLTO. This + allows the LLVM LTO code to be updated independently of the linker tool. + On platforms that support it, the shared object is lazily loaded. +

+
+ + +
+ Phase 2 : Symbol Resolution +
+ +
+

In this stage, the linker resolves symbols using global symbol table. + It may report undefined symbol errors, read archive members, replace + weak symbols, etc. The linker is able to do this seamlessly even though it + does not know the exact content of input LLVM bitcode files. If dead code + stripping is enabled then the linker collects the list of live symbols. +

+
+ + +
+ Phase 3 : Optimize Bitcode Files +
+
+

After symbol resolution, the linker tells the LTO shared object which + symbols are needed by native object files. In the example above, the linker + reports that only foo1() is used by native object files using + lto_codegen_add_must_preserve_symbol(). Next the linker invokes + the LLVM optimizer and code generators using lto_codegen_compile() + which returns a native object file creating by merging the LLVM bitcode files + and applying various optimization passes. +

+
+ + +
+ Phase 4 : Symbol Resolution after optimization +
+ +
+

In this phase, the linker reads optimized a native object file and + updates the internal global symbol table to reflect any changes. The linker + also collects information about any changes in use of external symbols by + LLVM bitcode files. In the examle above, the linker notes that + foo4() is not used any more. If dead code stripping is enabled then + the linker refreshes the live symbol information appropriately and performs + dead code stripping.

+

After this phase, the linker continues linking as if it never saw LLVM + bitcode files.

+
+ + +
+libLTO +
+ +
+

libLTO is a shared object that is part of the LLVM tools, and + is intended for use by a linker. libLTO provides an abstract C + interface to use the LLVM interprocedural optimizer without exposing details + of LLVM's internals. The intention is to keep the interface as stable as + possible even when the LLVM optimizer continues to evolve. It should even + be possible for a completely different compilation technology to provide + a different libLTO that works with their object files and the standard + linker tool.

+
+ + +
+ lto_module_t +
+ +
+ +

A non-native object file is handled via an lto_module_t. +The following functions allow the linker to check if a file (on disk +or in a memory buffer) is a file which libLTO can process:

+ +
+lto_module_is_object_file(const char*)
+lto_module_is_object_file_for_target(const char*, const char*)
+lto_module_is_object_file_in_memory(const void*, size_t)
+lto_module_is_object_file_in_memory_for_target(const void*, size_t, const char*)
+
+ +

If the object file can be processed by libLTO, the linker creates a +lto_module_t by using one of

+ +
+lto_module_create(const char*)
+lto_module_create_from_memory(const void*, size_t)
+
+ +

and when done, the handle is released via

+ +
+lto_module_dispose(lto_module_t)
+
+ +

The linker can introspect the non-native object file by getting the number of +symbols and getting the name and attributes of each symbol via:

+ +
+lto_module_get_num_symbols(lto_module_t)
+lto_module_get_symbol_name(lto_module_t, unsigned int)
+lto_module_get_symbol_attribute(lto_module_t, unsigned int)
+
+ +

The attributes of a symbol include the alignment, visibility, and kind.

+
+ + +
+ lto_code_gen_t +
+ +
+ +

Once the linker has loaded each non-native object files into an +lto_module_t, it can request libLTO to process them all and +generate a native object file. This is done in a couple of steps. +First, a code generator is created with:

+ +
lto_codegen_create()
+ +

Then, each non-native object file is added to the code generator with:

+ +
+lto_codegen_add_module(lto_code_gen_t, lto_module_t)
+
+ +

The linker then has the option of setting some codegen options. Whether or +not to generate DWARF debug info is set with:

+ +
lto_codegen_set_debug_model(lto_code_gen_t)
+ +

Which kind of position independence is set with:

+ +
lto_codegen_set_pic_model(lto_code_gen_t)
+ +

And each symbol that is referenced by a native object file or otherwise must +not be optimized away is set with:

+ +
+lto_codegen_add_must_preserve_symbol(lto_code_gen_t, const char*)
+
+ +

After all these settings are done, the linker requests that a native object +file be created from the modules with the settings using:

+ +
lto_codegen_compile(lto_code_gen_t, size*)
+ +

which returns a pointer to a buffer containing the generated native +object file. The linker then parses that and links it with the rest +of the native object files.

+ +
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + Devang Patel and Nick Kledzik
+ LLVM Compiler Infrastructure
+ Last modified: $Date: 2009-10-12 09:46:08 -0500 (Mon, 12 Oct 2009) $ +
+ + + + Added: www-releases/trunk/2.7/docs/Makefile URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/Makefile?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/Makefile (added) +++ www-releases/trunk/2.7/docs/Makefile Tue Apr 27 02:30:52 2010 @@ -0,0 +1,123 @@ +##===- docs/Makefile ---------------------------------------*- Makefile -*-===## +# +# The LLVM Compiler Infrastructure +# +# This file is distributed under the University of Illinois Open Source +# License. See LICENSE.TXT for details. +# +##===----------------------------------------------------------------------===## + +LEVEL := .. +DIRS := CommandGuide tutorial + +ifdef BUILD_FOR_WEBSITE +PROJ_OBJ_DIR = . +DOXYGEN = doxygen + +$(PROJ_OBJ_DIR)/doxygen.cfg: doxygen.cfg.in + cat $< | sed \ + -e 's/@abs_top_srcdir@/../g' \ + -e 's/@DOT@/dot/g' \ + -e 's/@PACKAGE_VERSION@/mainline/' \ + -e 's/@abs_top_builddir@/../g' > $@ +endif + +include $(LEVEL)/Makefile.common + +HTML := $(wildcard $(PROJ_SRC_DIR)/*.html) \ + $(wildcard $(PROJ_SRC_DIR)/*.css) +IMAGES := $(wildcard $(PROJ_SRC_DIR)/img/*.*) +DOXYFILES := doxygen.cfg.in doxygen.css doxygen.footer doxygen.header \ + doxygen.intro +EXTRA_DIST := $(HTML) $(DOXYFILES) llvm.css CommandGuide img + +.PHONY: install-html install-doxygen doxygen install-ocamldoc ocamldoc generated + +install_targets := install-html +ifeq ($(ENABLE_DOXYGEN),1) +install_targets += install-doxygen +endif +ifneq (,$(filter ocaml,$(BINDINGS_TO_BUILD))) +install_targets += install-ocamldoc +endif +install-local:: $(install_targets) + +# Live documentation is generated for the web site using this target: +# 'make generated BUILD_FOR_WEBSITE=1' +generated:: doxygen ocamldoc + +install-html: $(PROJ_OBJ_DIR)/html.tar.gz + $(Echo) Installing HTML documentation + $(Verb) $(MKDIR) $(DESTDIR)$(PROJ_docsdir)/html + $(Verb) $(MKDIR) $(DESTDIR)$(PROJ_docsdir)/html/img + $(Verb) $(DataInstall) $(HTML) $(DESTDIR)$(PROJ_docsdir)/html + $(Verb) $(DataInstall) $(IMAGES) $(DESTDIR)$(PROJ_docsdir)/html/img + $(Verb) $(DataInstall) $(PROJ_OBJ_DIR)/html.tar.gz $(DESTDIR)$(PROJ_docsdir) + +$(PROJ_OBJ_DIR)/html.tar.gz: $(HTML) + $(Echo) Packaging HTML documentation + $(Verb) $(RM) -rf $@ $(PROJ_OBJ_DIR)/html.tar + $(Verb) cd $(PROJ_SRC_DIR) && \ + $(TAR) cf $(PROJ_OBJ_DIR)/html.tar *.html + $(Verb) $(GZIP) $(PROJ_OBJ_DIR)/html.tar + +install-doxygen: doxygen + $(Echo) Installing doxygen documentation + $(Verb) $(MKDIR) $(DESTDIR)$(PROJ_docsdir)/html/doxygen + $(Verb) $(DataInstall) $(PROJ_OBJ_DIR)/doxygen.tar.gz $(DESTDIR)$(PROJ_docsdir) + $(Verb) cd $(PROJ_OBJ_DIR)/doxygen && \ + $(FIND) . -type f -exec \ + $(DataInstall) {} $(DESTDIR)$(PROJ_docsdir)/html/doxygen \; + +doxygen: regendoc $(PROJ_OBJ_DIR)/doxygen.tar.gz + +regendoc: + $(Echo) Building doxygen documentation + $(Verb) if test -e $(PROJ_OBJ_DIR)/doxygen ; then \ + $(RM) -rf $(PROJ_OBJ_DIR)/doxygen ; \ + fi + $(Verb) $(DOXYGEN) $(PROJ_OBJ_DIR)/doxygen.cfg + +$(PROJ_OBJ_DIR)/doxygen.tar.gz: $(DOXYFILES) $(PROJ_OBJ_DIR)/doxygen.cfg + $(Echo) Packaging doxygen documentation + $(Verb) $(RM) -rf $@ $(PROJ_OBJ_DIR)/doxygen.tar + $(Verb) $(TAR) cf $(PROJ_OBJ_DIR)/doxygen.tar doxygen + $(Verb) $(GZIP) $(PROJ_OBJ_DIR)/doxygen.tar + $(Verb) $(CP) $(PROJ_OBJ_DIR)/doxygen.tar.gz $(PROJ_OBJ_DIR)/doxygen/html/ + +userloc: $(LLVM_SRC_ROOT)/docs/userloc.html + +$(LLVM_SRC_ROOT)/docs/userloc.html: + $(Echo) Making User LOC Table + $(Verb) cd $(LLVM_SRC_ROOT) ; ./utils/userloc.pl -details -recurse \ + -html lib include tools runtime utils examples autoconf test > docs/userloc.html + +install-ocamldoc: ocamldoc + $(Echo) Installing ocamldoc documentation + $(Verb) $(MKDIR) $(DESTDIR)$(PROJ_docsdir)/ocamldoc/html + $(Verb) $(DataInstall) $(PROJ_OBJ_DIR)/ocamldoc.tar.gz $(DESTDIR)$(PROJ_docsdir) + $(Verb) cd $(PROJ_OBJ_DIR)/ocamldoc && \ + $(FIND) . -type f -exec \ + $(DataInstall) {} $(DESTDIR)$(PROJ_docsdir)/ocamldoc/html \; + +ocamldoc: regen-ocamldoc + $(Echo) Packaging ocamldoc documentation + $(Verb) $(RM) -rf $(PROJ_OBJ_DIR)/ocamldoc.tar* + $(Verb) $(TAR) cf $(PROJ_OBJ_DIR)/ocamldoc.tar ocamldoc + $(Verb) $(GZIP) $(PROJ_OBJ_DIR)/ocamldoc.tar + $(Verb) $(CP) $(PROJ_OBJ_DIR)/ocamldoc.tar.gz $(PROJ_OBJ_DIR)/ocamldoc/html/ + +regen-ocamldoc: + $(Echo) Building ocamldoc documentation + $(Verb) if test -e $(PROJ_OBJ_DIR)/ocamldoc ; then \ + $(RM) -rf $(PROJ_OBJ_DIR)/ocamldoc ; \ + fi + $(Verb) $(MAKE) -C $(LEVEL)/bindings/ocaml ocamldoc + $(Verb) $(MKDIR) $(PROJ_OBJ_DIR)/ocamldoc/html + $(Verb) \ + $(OCAMLDOC) -d $(PROJ_OBJ_DIR)/ocamldoc/html -sort -colorize-code -html \ + `$(FIND) $(LEVEL)/bindings/ocaml -name "*.odoc" -exec echo -load '{}' ';'` + +uninstall-local:: + $(Echo) Uninstalling Documentation + $(Verb) $(RM) -rf $(DESTDIR)$(PROJ_docsdir) Added: www-releases/trunk/2.7/docs/MakefileGuide.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/MakefileGuide.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/MakefileGuide.html (added) +++ www-releases/trunk/2.7/docs/MakefileGuide.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,1031 @@ + + + + + LLVM Makefile Guide + + + + +
LLVM Makefile Guide
+ +
    +
  1. Introduction
    2. +
  2. General Concepts +
      +
    1. Projects
      2. +
    2. Variable Values
      3. +
    3. Including Makefiles +
        +
      1. Makefile
        2. +
      2. Makefile.common
        3. +
      3. Makefile.config
        4. +
      4. Makefile.rules
        5. +
      +
      4. +
    4. Comments
      5. +
    +
    3. +
  3. Tutorial +
      +
    1. Libraries +
        +
      1. Bitcode Modules
        2. +
      2. Loadable Modules
        3. +
      +
      2. +
    2. Tools +
        +
      1. JIT Tools
        2. +
      +
      3. +
    3. Projects
      4. +
    +
    4. +
  4. Targets Supported +
      +
    1. all
      2. +
    2. all-local
      3. +
    3. check
      4. +
    4. check-local
      5. +
    5. clean
      6. +
    6. clean-local
      7. +
    7. dist
      8. +
    8. dist-check
      9. +
    9. dist-clean
      10. +
    10. install
      11. +
    11. preconditions
      12. +
    12. printvars
      13. +
    13. reconfigure
      14. +
    14. spotless
      15. +
    15. tags
      16. +
    16. uninstall
      17. +
    +
    5. +
  5. Using Variables +
      +
    1. Control Variables
      2. +
    2. Override Variables
      3. +
    3. Readable Variables
      4. +
    4. Internal Variables
      5. +
    +
    6. +
+ +
+

Written by Reid Spencer

+
+ + +
Introduction
+ + +
+

This document provides usage information about the LLVM makefile + system. While loosely patterned after the BSD makefile system, LLVM has taken + a departure from BSD in order to implement additional features needed by LLVM. + Although makefile systems such as automake were attempted at one point, it + has become clear that the features needed by LLVM and the Makefile norm are + too great to use a more limited tool. Consequently, LLVM requires simply GNU + Make 3.79, a widely portable makefile processor. LLVM unabashedly makes heavy + use of the features of GNU Make so the dependency on GNU Make is firm. If + you're not familiar with make, it is recommended that you read the + GNU Makefile + Manual.

+

While this document is rightly part of the + LLVM Programmer's Manual, it is treated + separately here because of the volume of content and because it is often an + early source of bewilderment for new developers.

+
+ + +
General Concepts
+ + +
+

The LLVM Makefile System is the component of LLVM that is responsible for + building the software, testing it, generating distributions, checking those + distributions, installing and uninstalling, etc. It consists of a several + files throughout the source tree. These files and other general concepts are + described in this section.

+
+ + +
Projects
+
+

The LLVM Makefile System is quite generous. It not only builds its own + software, but it can build yours too. Built into the system is knowledge of + the llvm/projects directory. Any directory under projects + that has both a configure script and a Makefile is assumed + to be a project that uses the LLVM Makefile system. Building software that + uses LLVM does not require the LLVM Makefile System nor even placement in the + llvm/projects directory. However, doing so will allow your project + to get up and running quickly by utilizing the built-in features that are used + to compile LLVM. LLVM compiles itself using the same features of the makefile + system as used for projects.

+

For complete details on setting up your projects configuration, simply + mimic the llvm/projects/sample project or for further details, + consult the Projects.html page.

+
+ + +
Variable Values
+
+

To use the makefile system, you simply create a file named + Makefile in your directory and declare values for certain variables. + The variables and values that you select determine what the makefile system + will do. These variables enable rules and processing in the makefile system + that automatically Do The Right Thing™. +

+ + +
Including Makefiles
+
+

Setting variables alone is not enough. You must include into your Makefile + additional files that provide the rules of the LLVM Makefile system. The + various files involved are described in the sections that follow.

+
+ + +
Makefile
+
+

Each directory to participate in the build needs to have a file named + Makefile. This is the file first read by make. It has three + sections:

+
    +
  1. Settable Variables - Required that must be set + first.
    2. +
  2. include $(LEVEL)/Makefile.common + - include the LLVM Makefile system. +
  3. Override Variables - Override variables set by + the LLVM Makefile system. +
+
+ + +
Makefile.common +
+
+

Every project must have a Makefile.common file at its top source + directory. This file serves three purposes:

+
    +
  1. It includes the project's configuration makefile to obtain values + determined by the configure script. This is done by including the + $(LEVEL)/Makefile.config file.
    2. +
  2. It specifies any other (static) values that are needed throughout the + project. Only values that are used in all or a large proportion of the + project's directories should be placed here.
    3. +
  3. It includes the standard rules for the LLVM Makefile system, + $(LLVM_SRC_ROOT)/Makefile.rules. + This file is the "guts" of the LLVM Makefile system.
    4. +
+
+ + +
Makefile.config +
+
+

Every project must have a Makefile.config at the top of its + build directory. This file is generated by the + configure script from the pattern provided by the + Makefile.config.in file located at the top of the project's + source directory. The contents of this file depend largely on what + configuration items the project uses, however most projects can get what they + need by just relying on LLVM's configuration found in + $(LLVM_OBJ_ROOT)/Makefile.config. +

+ + +
Makefile.rules
+
+

This file, located at $(LLVM_SRC_ROOT)/Makefile.rules is the heart + of the LLVM Makefile System. It provides all the logic, dependencies, and + rules for building the targets supported by the system. What it does largely + depends on the values of make variables that + have been set before Makefile.rules is included. +

+ + +
Comments
+
+

User Makefiles need not have comments in them unless the construction is + unusual or it does not strictly follow the rules and patterns of the LLVM + makefile system. Makefile comments are invoked with the pound (#) character. + The # character and any text following it, to the end of the line, are ignored + by make.

+
+ + +
Tutorial
+ +
+

This section provides some examples of the different kinds of modules you + can build with the LLVM makefile system. In general, each directory you + provide will build a single object although that object may be composed of + additionally compiled components.

+
+ + +
Libraries
+
+

Only a few variable definitions are needed to build a regular library. + Normally, the makefile system will build all the software into a single + libname.o (pre-linked) object. This means the library is not + searchable and that the distinction between compilation units has been + dissolved. Optionally, you can ask for a shared library (.so) or archive + library (.a) built. Archive libraries are the default. For example:

+ 

+      LIBRARYNAME = mylib
+      SHARED_LIBRARY = 1
+      ARCHIVE_LIBRARY = 1
+
+

says to build a library named "mylib" with both a shared library + (mylib.so) and an archive library (mylib.a) version. The + contents of all the + libraries produced will be the same, they are just constructed differently. + Note that you normally do not need to specify the sources involved. The LLVM + Makefile system will infer the source files from the contents of the source + directory.

+

The LOADABLE_MODULE=1 directive can be used in conjunction with + SHARED_LIBRARY=1 to indicate that the resulting shared library should + be openable with the dlopen function and searchable with the + dlsym function (or your operating system's equivalents). While this + isn't strictly necessary on Linux and a few other platforms, it is required + on systems like HP-UX and Darwin. You should use LOADABLE_MODULE for + any shared library that you intend to be loaded into an tool via the + -load option. See the + WritingAnLLVMPass.html document + for an example of why you might want to do this. +

+ + +
Bitcode Modules
+
+

In some situations, it is desirable to build a single bitcode module from + a variety of sources, instead of an archive, shared library, or bitcode + library. Bitcode modules can be specified in addition to any of the other + types of libraries by defining the MODULE_NAME + variable. For example:

+ 

+      LIBRARYNAME = mylib
+      BYTECODE_LIBRARY = 1
+      MODULE_NAME = mymod
+
+

will build a module named mymod.bc from the sources in the + directory. This module will be an aggregation of all the bitcode modules + derived from the sources. The example will also build a bitcode archive + containing a bitcode module for each compiled source file. The difference is + subtle, but important depending on how the module or library is to be linked. +

+
+ + +
+ Loadable Modules +
+
+

In some situations, you need to create a loadable module. Loadable modules + can be loaded into programs like opt or llc to specify + additional passes to run or targets to support. Loadable modules are also + useful for debugging a pass or providing a pass with another package if that + pass can't be included in LLVM.

+

LLVM provides complete support for building such a module. All you need to + do is use the LOADABLE_MODULE variable in your Makefile. For example, to + build a loadable module named MyMod that uses the LLVM libraries + LLVMSupport.a and LLVMSystem.a, you would specify:

+ 

+     LIBRARYNAME := MyMod
+     LOADABLE_MODULE := 1
+     LINK_COMPONENTS := support system
+
+

Use of the LOADABLE_MODULE facility implies several things:

+
    +
  1. There will be no "lib" prefix on the module. This differentiates it from + a standard shared library of the same name.
    2. +
  2. The SHARED_LIBRARY variable is turned + on.
    3. +
  3. The LINK_LIBS_IN_SHARED variable + is turned on.
    4. +
+

A loadable module is loaded by LLVM via the facilities of libtool's libltdl + library which is part of lib/System implementation.

+
+ + +
Tools
+
+

For building executable programs (tools), you must provide the name of the + tool and the names of the libraries you wish to link with the tool. For + example:

+ 

+      TOOLNAME = mytool
+      USEDLIBS = mylib
+      LINK_COMPONENTS = support system
+
+

says that we are to build a tool name mytool and that it requires + three libraries: mylib, LLVMSupport.a and + LLVMSystem.a.

+

Note that two different variables are use to indicate which libraries are + linked: USEDLIBS and LLVMLIBS. This distinction is necessary + to support projects. LLVMLIBS refers to the LLVM libraries found in + the LLVM object directory. USEDLIBS refers to the libraries built by + your project. In the case of building LLVM tools, USEDLIBS and + LLVMLIBS can be used interchangeably since the "project" is LLVM + itself and USEDLIBS refers to the same place as LLVMLIBS. +

+

Also note that there are two different ways of specifying a library: with a + .a suffix and without. Without the suffix, the entry refers to the + re-linked (.o) file which will include all symbols of the library. + This is useful, for example, to include all passes from a library of passes. + If the .a suffix is used then the library is linked as a searchable + library (with the -l option). In this case, only the symbols that are + unresolved at that point will be resolved from the library, if they + exist. Other (unreferenced) symbols will not be included when the .a + syntax is used. Note that in order to use the .a suffix, the library + in question must have been built with the ARCHIVE_LIBRARY option set. +

+
+ + +
JIT Tools
+
+

Many tools will want to use the JIT features of LLVM. To do this, you + simply specify that you want an execution 'engine', and the makefiles will + automatically link in the appropriate JIT for the host or an interpreter + if none is available:

+ 

+      TOOLNAME = my_jit_tool
+      USEDLIBS = mylib
+      LINK_COMPONENTS = engine
+
+

Of course, any additional libraries may be listed as other components. To + get a full understanding of how this changes the linker command, it is + recommended that you:

+ 

+      cd examples/Fibonacci
+      make VERBOSE=1
+
+
+ + +
Targets Supported
+ + +
+

This section describes each of the targets that can be built using the LLVM + Makefile system. Any target can be invoked from any directory but not all are + applicable to a given directory (e.g. "check", "dist" and "install" will + always operate as if invoked from the top level directory).

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Target NameImplied TargetsTarget Description
allCompile the software recursively. Default target. +
all-localCompile the software in the local directory only. +
checkChange to the test directory in a project and run the + test suite there. +
check-localRun a local test suite. Generally this is only defined in the + Makefile of the project's test directory. +
cleanRemove built objects recursively. +
clean-localRemove built objects from the local directory only. +
distallPrepare a source distribution tarball. +
dist-checkallPrepare a source distribution tarball and check that it builds. +
dist-cleancleanClean source distribution tarball temporary files. +
installallCopy built objects to installation directory. +
preconditionsallCheck to make sure configuration and makefiles are up to date. +
printvarsallPrints variables defined by the makefile system (for debugging). +
tagsMake C and C++ tags files for emacs and vi. +
uninstallRemove built objects from installation directory. +
+
+ + +
all (default)
+
+

When you invoke make with no arguments, you are implicitly + instructing it to seek the "all" target (goal). This target is used for + building the software recursively and will do different things in different + directories. For example, in a lib directory, the "all" target will + compile source files and generate libraries. But, in a tools + directory, it will link libraries and generate executables.

+
+ + +
all-local
+
+

This target is the same as all but it operates only on + the current directory instead of recursively.

+
+ + +
check
+
+

This target can be invoked from anywhere within a project's directories + but always invokes the check-local target + in the project's test directory, if it exists and has a + Makefile. A warning is produced otherwise. If + TESTSUITE is defined on the make + command line, it will be passed down to the invocation of + make check-local in the test directory. The intended usage + for this is to assist in running specific suites of tests. If + TESTSUITE is not set, the implementation of check-local + should run all normal tests. It is up to the project to define what + different values for TESTSUTE will do. See the + TestingGuide for further details.

+
+ + +
check-local
+
+

This target should be implemented by the Makefile in the project's + test directory. It is invoked by the check target elsewhere. + Each project is free to define the actions of check-local as + appropriate for that project. The LLVM project itself uses dejagnu to run a + suite of feature and regresson tests. Other projects may choose to use + dejagnu or any other testing mechanism.

+
+ + +
clean
+
+

This target cleans the build directory, recursively removing all things + that the Makefile builds. The cleaning rules have been made guarded so they + shouldn't go awry (via rm -f $(UNSET_VARIABLE)/* which will attempt + to erase the entire directory structure.

+
+ + +
clean-local
+
+

This target does the same thing as clean but only for the current + (local) directory.

+
+ + +
dist
+
+

This target builds a distribution tarball. It first builds the entire + project using the all target and then tars up the necessary files and + compresses it. The generated tarball is sufficient for a casual source + distribution, but probably not for a release (see dist-check).

+
+ + +
dist-check
+
+

This target does the same thing as the dist target but also checks + the distribution tarball. The check is made by unpacking the tarball to a new + directory, configuring it, building it, installing it, and then verifying that + the installation results are correct (by comparing to the original build). + This target can take a long time to run but should be done before a release + goes out to make sure that the distributed tarball can actually be built into + a working release.

+
+ + +
dist-clean
+
+

This is a special form of the clean clean target. It performs a + normal clean but also removes things pertaining to building the + distribution.

+
+ + +
install
+
+

This target finalizes shared objects and executables and copies all + libraries, headers, executables and documentation to the directory given + with the --prefix option to configure. When completed, + the prefix directory will have everything needed to use LLVM.

+

The LLVM makefiles can generate complete internal documentation + for all the classes by using doxygen. By default, this feature is + not enabled because it takes a long time and generates a massive + amount of data (>100MB). If you want this feature, you must configure LLVM + with the --enable-doxygen switch and ensure that a modern version of doxygen + (1.3.7 or later) is available in your PATH. You can download + doxygen from + + here. +

+ + +
preconditions
+
+

This utility target checks to see if the Makefile in the object + directory is older than the Makefile in the source directory and + copies it if so. It also reruns the configure script if that needs to + be done and rebuilds the Makefile.config file similarly. Users may + overload this target to ensure that sanity checks are run before any + building of targets as all the targets depend on preconditions.

+
+ + +
printvars
+
+

This utility target just causes the LLVM makefiles to print out some of + the makefile variables so that you can double check how things are set.

+
+ + +
reconfigure
+
+

This utility target will force a reconfigure of LLVM or your project. It + simply runs $(PROJ_OBJ_ROOT)/config.status --recheck to rerun the + configuration tests and rebuild the configured files. This isn't generally + useful as the makefiles will reconfigure themselves whenever its necessary. +

+
+ + +
spotless
+
+

This utility target, only available when $(PROJ_OBJ_ROOT) is not + the same as $(PROJ_SRC_ROOT), will completely clean the + $(PROJ_OBJ_ROOT) directory by removing its content entirely and + reconfiguring the directory. This returns the $(PROJ_OBJ_ROOT) + directory to a completely fresh state. All content in the directory except + configured files and top-level makefiles will be lost.

+

Use with caution.

+
+ + +
tags
+
+

This target will generate a TAGS file in the top-level source + directory. It is meant for use with emacs, XEmacs, or ViM. The TAGS file + provides an index of symbol definitions so that the editor can jump you to the + definition quickly.

+
+ + +
uninstall
+
+

This target is the opposite of the install target. It removes the + header, library and executable files from the installation directories. Note + that the directories themselves are not removed because it is not guaranteed + that LLVM is the only thing installing there (e.g. --prefix=/usr).

+
+ + +
Variables
+ +
+

Variables are used to tell the LLVM Makefile System what to do and to + obtain information from it. Variables are also used internally by the LLVM + Makefile System. Variable names that contain only the upper case alphabetic + letters and underscore are intended for use by the end user. All other + variables are internal to the LLVM Makefile System and should not be relied + upon nor modified. The sections below describe how to use the LLVM Makefile + variables.

+
+ + +
Control Variables
+
+

Variables listed in the table below should be set before the + inclusion of $(LEVEL)/Makefile.common. + These variables provide input to the LLVM make system that tell it what to do + for the current directory.

+
+
BUILD_ARCHIVE
+
If set to any value, causes an archive (.a) library to be built.
+
BUILT_SOURCES
+
Specifies a set of source files that are generated from other source + files. These sources will be built before any other target processing to + ensure they are present.
+
BYTECODE_LIBRARY
+
If set to any value, causes a bitcode library (.bc) to be built.
+
CONFIG_FILES
+
Specifies a set of configuration files to be installed.
+
DEBUG_SYMBOLS
+
If set to any value, causes the build to include debugging + symbols even in optimized objects, libraries and executables. This + alters the flags specified to the compilers and linkers. Debugging + isn't fun in an optimized build, but it is possible.
+
DIRS
+
Specifies a set of directories, usually children of the current + directory, that should also be made using the same goal. These directories + will be built serially.
+
DISABLE_AUTO_DEPENDENCIES
+
If set to any value, causes the makefiles to not automatically + generate dependencies when running the compiler. Use of this feature is + discouraged and it may be removed at a later date.
+
ENABLE_OPTIMIZED
+
If set to any value, causes the build to generate optimized objects, + libraries and executables. This alters the flags specified to the compilers + and linkers. Generally debugging won't be a fun experience with an optimized + build.
+
ENABLE_PROFILING
+
If set to any value, causes the build to generate both optimized and + profiled objects, libraries and executables. This alters the flags specified + to the compilers and linkers to ensure that profile data can be collected + from the tools built. Use the gprof tool to analyze the output from + the profiled tools (gmon.out).
+
DISABLE_ASSERTIONS
+
If set to any value, causes the build to disable assertions, even if + building a release or profile build. This will exclude all assertion check + code from the build. LLVM will execute faster, but with little help when + things go wrong.
+
EXPERIMENTAL_DIRS
+
Specify a set of directories that should be built, but if they fail, it + should not cause the build to fail. Note that this should only be used + temporarily while code is being written.
+
EXPORTED_SYMBOL_FILE
+
Specifies the name of a single file that contains a list of the + symbols to be exported by the linker. One symbol per line.
+
EXPORTED_SYMBOL_LIST
+
Specifies a set of symbols to be exported by the linker.
+
EXTRA_DIST
+
Specifies additional files that should be distributed with LLVM. All + source files, all built sources, all Makefiles, and most documentation files + will be automatically distributed. Use this variable to distribute any + files that are not automatically distributed.
+
KEEP_SYMBOLS
+
If set to any value, specifies that when linking executables the + makefiles should retain debug symbols in the executable. Normally, symbols + are stripped from the executable.
+
LEVEL(required)
+
Specify the level of nesting from the top level. This variable must be + set in each makefile as it is used to find the top level and thus the other + makefiles.
+
LIBRARYNAME
+
Specify the name of the library to be built. (Required For + Libraries)
+
LINK_COMPONENTS
+
When specified for building a tool, the value of this variable will be + passed to the llvm-config tool to generate a link line for the + tool. Unlike USEDLIBS and LLVMLIBS, not all libraries need + to be specified. The llvm-config tool will figure out the library + dependencies and add any libraries that are needed. The USEDLIBS + variable can still be used in conjunction with LINK_COMPONENTS so + that additional project-specific libraries can be linked with the LLVM + libraries specified by LINK_COMPONENTS
+
LINK_LIBS_IN_SHARED
+
By default, shared library linking will ignore any libraries specified + with the LLVMLIBS or USEDLIBS. + This prevents shared libs from including things that will be in the LLVM + tool the shared library will be loaded into. However, sometimes it is useful + to link certain libraries into your shared library and this option enables + that feature.
+
LLVMLIBS
+
Specifies the set of libraries from the LLVM $(ObjDir) that will be + linked into the tool or library.
+
LOADABLE_MODULE
+
If set to any value, causes the shared library being built to also be + a loadable module. Loadable modules can be opened with the dlopen() function + and searched with dlsym (or the operating system's equivalent). Note that + setting this variable without also setting SHARED_LIBRARY will have + no effect.
+
MODULE_NAME
+
Specifies the name of a bitcode module to be created. A bitcode + module can be specified in conjunction with other kinds of library builds + or by itself. It constructs from the sources a single linked bitcode + file.
+
NO_INSTALL
+
Specifies that the build products of the directory should not be + installed but should be built even if the install target is given. + This is handy for directories that build libraries or tools that are only + used as part of the build process, such as code generators (e.g. + tblgen).
+
OPTIONAL_DIRS
+
Specify a set of directories that may be built, if they exist, but its + not an error for them not to exist.
+
PARALLEL_DIRS
+
Specify a set of directories to build recursively and in parallel if + the -j option was used with make.
+
SHARED_LIBRARY
+
If set to any value, causes a shared library (.so) to be built in + addition to any other kinds of libraries. Note that this option will cause + all source files to be built twice: once with options for position + independent code and once without. Use it only where you really need a + shared library.
+
SOURCES(optional)
+
Specifies the list of source files in the current directory to be + built. Source files of any type may be specified (programs, documentation, + config files, etc.). If not specified, the makefile system will infer the + set of source files from the files present in the current directory.
+
SUFFIXES
+
Specifies a set of filename suffixes that occur in suffix match rules. + Only set this if your local Makefile specifies additional suffix + match rules.
+
TARGET
+
Specifies the name of the LLVM code generation target that the + current directory builds. Setting this variable enables additional rules to + build .inc files from .td files.
+
TESTSUITE
+
Specifies the directory of tests to run in llvm/test.
+
TOOLNAME
+
Specifies the name of the tool that the current directory should + build.
+
TOOL_VERBOSE
+
Implies VERBOSE and also tells each tool invoked to be verbose. This is + handy when you're trying to see the sub-tools invoked by each tool invoked + by the makefile. For example, this will pass -v to the GCC + compilers which causes it to print out the command lines it uses to invoke + sub-tools (compiler, assembler, linker).
+
USEDLIBS
+
Specifies the list of project libraries that will be linked into the + tool or library.
+
VERBOSE
+
Tells the Makefile system to produce detailed output of what it is doing + instead of just summary comments. This will generate a LOT of output.
+
+
+ + +
Override Variables
+
+

Override variables can be used to override the default + values provided by the LLVM makefile system. These variables can be set in + several ways:

+
    +
  • In the environment (e.g. setenv, export) -- not recommended.
    • +
  • On the make command line -- recommended.
    • +
  • On the configure command line
    • +
  • In the Makefile (only after the inclusion of $(LEVEL)/Makefile.common).
    • +
+

The override variables are given below:

+
+
AR (defaulted)
+
Specifies the path to the ar tool.
+
PROJ_OBJ_DIR
+
The directory into which the products of build rules will be placed. + This might be the same as + PROJ_SRC_DIR but typically is + not.
+
PROJ_SRC_DIR
+
The directory which contains the source files to be built.
+
BZIP2(configured)
+
The path to the bzip2 tool.
+
CC(configured)
+
The path to the 'C' compiler.
+
CFLAGS
+
Additional flags to be passed to the 'C' compiler.
+
CXX
+
Specifies the path to the C++ compiler.
+
CXXFLAGS
+
Additional flags to be passed to the C++ compiler.
+
DATE(configured)
+
Specifies the path to the date program or any program that can + generate the current date and time on its standard output
+
DOT(configured)
+
Specifies the path to the dot tool or false if there + isn't one.
+
ECHO(configured)
+
Specifies the path to the echo tool for printing output.
+
EXEEXT(configured)
+
Provides the extension to be used on executables built by the makefiles. + The value may be empty on platforms that do not use file extensions for + executables (e.g. Unix).
+
INSTALL(configured)
+
Specifies the path to the install tool.
+
LDFLAGS(configured)
+
Allows users to specify additional flags to pass to the linker.
+
LIBS(configured)
+
The list of libraries that should be linked with each tool.
+
LIBTOOL(configured)
+
Specifies the path to the libtool tool. This tool is renamed + mklib by the configure script and always located in the +
LLVMAS(defaulted)
+
Specifies the path to the llvm-as tool.
+
LLVMCC
+
Specifies the path to the LLVM capable compiler.
+
LLVMCXX
+
Specifies the path to the LLVM C++ capable compiler.
+
LLVMGCC(defaulted)
+
Specifies the path to the LLVM version of the GCC 'C' Compiler
+
LLVMGXX(defaulted)
+
Specifies the path to the LLVM version of the GCC C++ Compiler
+
LLVMLD(defaulted)
+
Specifies the path to the LLVM bitcode linker tool
+
LLVM_OBJ_ROOT(configured) +
+
Specifies the top directory into which the output of the build is + placed.
+
LLVM_SRC_ROOT(configured) +
+
Specifies the top directory in which the sources are found.
+
LLVM_TARBALL_NAME + (configured)
+
Specifies the name of the distribution tarball to create. This is + configured from the name of the project and its version number.
+
MKDIR(defaulted)
+
Specifies the path to the mkdir tool that creates + directories.
+
ONLY_TOOLS
+
If set, specifies the list of tools to build.
+
PLATFORMSTRIPOPTS
+
The options to provide to the linker to specify that a stripped (no + symbols) executable should be built.
+
RANLIB(defaulted)
+
Specifies the path to the ranlib tool.
+
RM(defaulted)
+
Specifies the path to the rm tool.
+
SED(defaulted)
+
Specifies the path to the sed tool.
+
SHLIBEXT(configured)
+
Provides the filename extension to use for shared libraries.
+
TBLGEN(defaulted)
+
Specifies the path to the tblgen tool.
+
TAR(defaulted)
+
Specifies the path to the tar tool.
+
ZIP(defaulted)
+
Specifies the path to the zip tool.
+
+
+ + +
Readable Variables
+
+

Variables listed in the table below can be used by the user's Makefile but + should not be changed. Changing the value will generally cause the build to go + wrong, so don't do it.

+
+
bindir
+
The directory into which executables will ultimately be installed. This + value is derived from the --prefix option given to + configure.
+
BuildMode
+
The name of the type of build being performed: Debug, Release, or + Profile
+
bytecode_libdir
+
The directory into which bitcode libraries will ultimately be + installed. This value is derived from the --prefix option given to + configure.
+
ConfigureScriptFLAGS
+
Additional flags given to the configure script when + reconfiguring.
+
DistDir
+
The current directory for which a distribution copy is being + made.
+
Echo
+
The LLVM Makefile System output command. This provides the + llvm[n] prefix and starts with @ so the command itself is not + printed by make.
+
EchoCmd
+
Same as Echo but without the leading @. +
+
includedir
+
The directory into which include files will ultimately be installed. + This value is derived from the --prefix option given to + configure.
+
libdir
+
The directory into which native libraries will ultimately be installed. + This value is derived from the --prefix option given to + configure.
+
LibDir
+
The configuration specific directory into which libraries are placed + before installation.
+
MakefileConfig
+
Full path of the Makefile.config file.
+
MakefileConfigIn
+
Full path of the Makefile.config.in file.
+
ObjDir
+
The configuration and directory specific directory where build objects + (compilation results) are placed.
+
SubDirs
+
The complete list of sub-directories of the current directory as + specified by other variables.
+
Sources
+
The complete list of source files.
+
sysconfdir
+
The directory into which configuration files will ultimately be + installed. This value is derived from the --prefix option given to + configure.
+
ToolDir
+
The configuration specific directory into which executables are placed + before they are installed.
+
TopDistDir
+
The top most directory into which the distribution files are copied. +
+
Verb
+
Use this as the first thing on your build script lines to enable or + disable verbose mode. It expands to either an @ (quiet mode) or nothing + (verbose mode).
+
+
+ + +
Internal Variables
+
+

Variables listed below are used by the LLVM Makefile System + and considered internal. You should not use these variables under any + circumstances.

+

+ Archive + AR.Flags + BaseNameSources + BCCompile.C + BCCompile.CXX + BCLinkLib + C.Flags + Compile.C + CompileCommonOpts + Compile.CXX + ConfigStatusScript + ConfigureScript + CPP.Flags + CPP.Flags + CXX.Flags + DependFiles + DestArchiveLib + DestBitcodeLib + DestModule + DestSharedLib + DestTool + DistAlways + DistCheckDir + DistCheckTop + DistFiles + DistName + DistOther + DistSources + DistSubDirs + DistTarBZ2 + DistTarGZip + DistZip + ExtraLibs + FakeSources + INCFiles + InternalTargets + LD.Flags + LibName.A + LibName.BC + LibName.LA + LibName.O + LibTool.Flags + Link + LinkModule + LLVMLibDir + LLVMLibsOptions + LLVMLibsPaths + LLVMToolDir + LLVMUsedLibs + LocalTargets + Module + ObjectsBC + ObjectsLO + ObjectsO + ObjMakefiles + ParallelTargets + PreConditions + ProjLibsOptions + ProjLibsPaths + ProjUsedLibs + Ranlib + RecursiveTargets + SrcMakefiles + Strip + StripWarnMsg + TableGen + TDFiles + ToolBuildPath + TopLevelTargets + UserTargets +

+
+ + +
+
+ Valid CSS + Valid HTML 4.01 + + Reid Spencer
+ The LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-02-23 04:00:53 -0600 (Tue, 23 Feb 2010) $ +
+ + Added: www-releases/trunk/2.7/docs/Packaging.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/Packaging.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/Packaging.html (added) +++ www-releases/trunk/2.7/docs/Packaging.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,118 @@ + + + + Advice on Packaging LLVM + + + + +
Advice on Packaging LLVM
+
    +
  1. Overview
    2. +
  2. Compile Flags
    3. +
  3. C++ Features
    4. +
  4. Shared Library
    5. +
  5. Dependencies
    6. +
+ + +
Overview
+ +
+ +

LLVM sets certain default configure options to make sure our developers don't +break things for constrained platforms. These settings are not optimal for most +desktop systems, and we hope that packagers (e.g., Redhat, Debian, MacPorts, +etc.) will tweak them. This document lists settings we suggest you tweak. +

+ +

LLVM's API changes with each release, so users are likely to want, for +example, both LLVM-2.6 and LLVM-2.7 installed at the same time to support apps +developed against each. +

+
+ + +
Compile Flags
+ +
+ +

LLVM runs much more quickly when it's optimized and assertions are removed. +However, such a build is currently incompatible with users who build without +defining NDEBUG, and the lack of assertions makes it hard to debug problems in +user code. We recommend allowing users to install both optimized and debug +versions of LLVM in parallel. The following configure flags are relevant: +

+ +
+
--disable-assertions
Builds LLVM with NDEBUG + defined. Changes the LLVM ABI. Also available by setting + DISABLE_ASSERTIONS=0|1 in make's environment. This defaults + to enabled regardless of the optimization setting, but it slows things + down.
+ +
--enable-debug-symbols
Builds LLVM with -g. + Also available by setting DEBUG_SYMBOLS=0|1 in make's + environment. This defaults to disabled when optimizing, so you should turn it + back on to let users debug their programs.
+ +
--enable-optimized
(For svn checkouts) Builds LLVM with + -O2 and, by default, turns off debug symbols. Also available by + setting ENABLE_OPTIMIZED=0|1 in make's environment. This + defaults to enabled when not in a checkout.
+
+
+ + +
C++ Features
+ +
+ +
+
RTTI
LLVM disables RTTI by default. Add REQUIRES_RTTI=1 + to your environment while running make to re-enable it. This will + allow users to build with RTTI enabled and still inherit from LLVM + classes.
+
+
+ + +
Shared Library
+ +
+ +

Configure with --enable-shared to build +libLLVM-major.minor.(so|dylib) and link the tools +against it. This saves lots of binary size at the cost of some startup time. +

+
+ + +
Dependencies
+ +
+ +
+
--enable-libffi
Depend on libffi to allow the LLVM +interpreter to call external functions.
+
--with-oprofile
Depend on libopagent +(>=version 0.9.4) to let the LLVM JIT tell oprofile about function addresses and +line numbers.
+
+
+ + +
+
+ Valid CSS + Valid HTML 4.01 + The LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-02-26 16:25:06 -0600 (Fri, 26 Feb 2010) $ +
+ + Added: www-releases/trunk/2.7/docs/Passes.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/Passes.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/Passes.html (added) +++ www-releases/trunk/2.7/docs/Passes.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,1780 @@ + + + + LLVM's Analysis and Transform Passes + + + + + + + +
LLVM's Analysis and Transform Passes
+ +
    +
  1. Introduction
    2. +
  2. Analysis Passes +
  3. Transform Passes
    4. +
  4. Utility Passes
    5. +
+ +
+

Written by Reid Spencer + and Gordon Henriksen

+
+ + +
Introduction
+
+

This document serves as a high level summary of the optimization features + that LLVM provides. Optimizations are implemented as Passes that traverse some + portion of a program to either collect information or transform the program. + The table below divides the passes that LLVM provides into three categories. + Analysis passes compute information that other passes can use or for debugging + or program visualization purposes. Transform passes can use (or invalidate) + the analysis passes. Transform passes all mutate the program in some way. + Utility passes provides some utility but don't otherwise fit categorization. + For example passes to extract functions to bitcode or write a module to + bitcode are neither analysis nor transform passes. +

The table below provides a quick summary of each pass and links to the more + complete pass description later in the document.

+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ANALYSIS PASSES
OptionName
-aa-evalExhaustive Alias Analysis Precision Evaluator
-basicaaBasic Alias Analysis (default AA impl)
-basiccgBasic CallGraph Construction
-codegenprepareOptimize for code generation
-count-aaCount Alias Analysis Query Responses
-debug-aaAA use debugger
-domfrontierDominance Frontier Construction
-domtreeDominator Tree Construction
-dot-callgraphPrint Call Graph to 'dot' file
-dot-cfgPrint CFG of function to 'dot' file
-dot-cfg-onlyPrint CFG of function to 'dot' file (with no function bodies)
-globalsmodref-aaSimple mod/ref analysis for globals
-instcountCounts the various types of Instructions
-intervalsInterval Partition Construction
-loopsNatural Loop Construction
-memdepMemory Dependence Analysis
-no-aaNo Alias Analysis (always returns 'may' alias)
-no-profileNo Profile Information
-postdomfrontierPost-Dominance Frontier Construction
-postdomtreePost-Dominator Tree Construction
-print-alias-setsAlias Set Printer
-print-callgraphPrint a call graph
-print-callgraph-sccsPrint SCCs of the Call Graph
-print-cfg-sccsPrint SCCs of each function CFG
-print-externalfnconstantsPrint external fn callsites passed constants
-print-functionPrint function to stderr
-print-modulePrint module to stderr
-print-used-typesFind Used Types
-profile-loaderLoad profile information from llvmprof.out
-scalar-evolutionScalar Evolution Analysis
-targetdataTarget Data Layout
TRANSFORM PASSES
OptionName
-adceAggressive Dead Code Elimination
-argpromotionPromote 'by reference' arguments to scalars
-block-placementProfile Guided Basic Block Placement
-break-crit-edgesBreak critical edges in CFG
-codegenpreparePrepare a function for code generation
-condpropConditional Propagation
-constmergeMerge Duplicate Global Constants
-constpropSimple constant propagation
-dceDead Code Elimination
-deadargelimDead Argument Elimination
-deadtypeelimDead Type Elimination
-dieDead Instruction Elimination
-dseDead Store Elimination
-globaldceDead Global Elimination
-globaloptGlobal Variable Optimizer
-gvnGlobal Value Numbering
-indmemremIndirect Malloc and Free Removal
-indvarsCanonicalize Induction Variables
-inlineFunction Integration/Inlining
-insert-block-profilingInsert instrumentation for block profiling
-insert-edge-profilingInsert instrumentation for edge profiling
-insert-function-profilingInsert instrumentation for function profiling
-insert-null-profiling-rsMeasure profiling framework overhead
-insert-rs-profiling-frameworkInsert random sampling instrumentation framework
-instcombineCombine redundant instructions
-internalizeInternalize Global Symbols
-ipconstpropInterprocedural constant propagation
-ipsccpInterprocedural Sparse Conditional Constant Propagation
-jump-threadingThread control through conditional blocks
-lcssaLoop-Closed SSA Form Pass
-licmLoop Invariant Code Motion
-loop-deletionDead Loop Deletion Pass
-loop-extractExtract loops into new functions
-loop-extract-singleExtract at most one loop into a new function
-loop-index-splitIndex Split Loops
-loop-reduceLoop Strength Reduction
-loop-rotateRotate Loops
-loop-unrollUnroll loops
-loop-unswitchUnswitch loops
-loopsimplifyCanonicalize natural loops
-lowerallocsLower allocations from instructions to calls
-lowerinvokeLower invoke and unwind, for unwindless code generators
-lowersetjmpLower Set Jump
-lowerswitchLower SwitchInst's to branches
-mem2regPromote Memory to Register
-memcpyoptOptimize use of memcpy and friends
-mergereturnUnify function exit nodes
-prune-ehRemove unused exception handling info
-reassociateReassociate expressions
-reg2memDemote all values to stack slots
-scalarreplScalar Replacement of Aggregates
-sccpSparse Conditional Constant Propagation
-simplify-libcallsSimplify well-known library calls
-simplifycfgSimplify the CFG
-stripStrip all symbols from a module
-strip-dead-prototypesRemove unused function declarations
-sretpromotionPromote sret arguments
-tailcallelimTail Call Elimination
-tailduplicateTail Duplication
UTILITY PASSES
OptionName
-deadarghaX0rDead Argument Hacking (BUGPOINT USE ONLY; DO NOT USE)
-extract-blocksExtract Basic Blocks From Module (for bugpoint use)
-preverifyPreliminary module verification
-verifyModule Verifier
-view-cfgView CFG of function
-view-cfg-onlyView CFG of function (with no function bodies)
+
+ + +
Analysis Passes
+
+

This section describes the LLVM Analysis Passes.

+
+ + +
+ Exhaustive Alias Analysis Precision Evaluator +
+
+

This is a simple N^2 alias analysis accuracy evaluator. + Basically, for each function in the program, it simply queries to see how the + alias analysis implementation answers alias queries between each pair of + pointers in the function.

+ +

This is inspired and adapted from code by: Naveen Neelakantam, Francesco + Spadini, and Wojciech Stryjewski.

+
+ + +
+ Basic Alias Analysis (default AA impl) +
+
+

+ This is the default implementation of the Alias Analysis interface + that simply implements a few identities (two different globals cannot alias, + etc), but otherwise does no analysis. +

+
+ + +
+ Basic CallGraph Construction +
+
+

Yet to be written.

+
+ + +
+ Optimize for code generation +
+
+

+ This pass munges the code in the input function to better prepare it for + SelectionDAG-based code generation. This works around limitations in it's + basic-block-at-a-time approach. It should eventually be removed. +

+
+ + +
+ Count Alias Analysis Query Responses +
+
+

+ A pass which can be used to count how many alias queries + are being made and how the alias analysis implementation being used responds. +

+
+ + +
+ AA use debugger +
+
+

+ This simple pass checks alias analysis users to ensure that if they + create a new value, they do not query AA without informing it of the value. + It acts as a shim over any other AA pass you want. +

+ +

+ Yes keeping track of every value in the program is expensive, but this is + a debugging pass. +

+
+ + +
+ Dominance Frontier Construction +
+
+

+ This pass is a simple dominator construction algorithm for finding forward + dominator frontiers. +

+
+ + +
+ Dominator Tree Construction +
+
+

+ This pass is a simple dominator construction algorithm for finding forward + dominators. +

+
+ + +
+ Print Call Graph to 'dot' file +
+
+

+ This pass, only available in opt, prints the call graph into a + .dot graph. This graph can then be processed with the "dot" tool + to convert it to postscript or some other suitable format. +

+
+ + +
+ Print CFG of function to 'dot' file +
+
+

+ This pass, only available in opt, prints the control flow graph + into a .dot graph. This graph can then be processed with the + "dot" tool to convert it to postscript or some other suitable format. +

+
+ + +
+ Print CFG of function to 'dot' file (with no function bodies) +
+
+

+ This pass, only available in opt, prints the control flow graph + into a .dot graph, omitting the function bodies. This graph can + then be processed with the "dot" tool to convert it to postscript or some + other suitable format. +

+
+ + +
+ Simple mod/ref analysis for globals +
+
+

+ This simple pass provides alias and mod/ref information for global values + that do not have their address taken, and keeps track of whether functions + read or write memory (are "pure"). For this simple (but very common) case, + we can provide pretty accurate and useful information. +

+
+ + +
+ Counts the various types of Instructions +
+
+

+ This pass collects the count of all instructions and reports them +

+
+ + +
+ Interval Partition Construction +
+
+

+ This analysis calculates and represents the interval partition of a function, + or a preexisting interval partition. +

+ +

+ In this way, the interval partition may be used to reduce a flow graph down + to its degenerate single node interval partition (unless it is irreducible). +

+
+ + +
+ Natural Loop Construction +
+
+

+ This analysis is used to identify natural loops and determine the loop depth + of various nodes of the CFG. Note that the loops identified may actually be + several natural loops that share the same header node... not just a single + natural loop. +

+
+ + +
+ Memory Dependence Analysis +
+
+

+ An analysis that determines, for a given memory operation, what preceding + memory operations it depends on. It builds on alias analysis information, and + tries to provide a lazy, caching interface to a common kind of alias + information query. +

+
+ + +
+ No Alias Analysis (always returns 'may' alias) +
+
+

+ Always returns "I don't know" for alias queries. NoAA is unlike other alias + analysis implementations, in that it does not chain to a previous analysis. As + such it doesn't follow many of the rules that other alias analyses must. +

+
+ + +
+ No Profile Information +
+
+

+ The default "no profile" implementation of the abstract + ProfileInfo interface. +

+
+ + +
+ Post-Dominance Frontier Construction +
+
+

+ This pass is a simple post-dominator construction algorithm for finding + post-dominator frontiers. +

+
+ + +
+ Post-Dominator Tree Construction +
+
+

+ This pass is a simple post-dominator construction algorithm for finding + post-dominators. +

+
+ + +
+ Alias Set Printer +
+
+

Yet to be written.

+
+ + +
+ Print a call graph +
+
+

+ This pass, only available in opt, prints the call graph to + standard output in a human-readable form. +

+
+ + +
+ Print SCCs of the Call Graph +
+
+

+ This pass, only available in opt, prints the SCCs of the call + graph to standard output in a human-readable form. +

+
+ + +
+ Print SCCs of each function CFG +
+
+

+ This pass, only available in opt, prints the SCCs of each + function CFG to standard output in a human-readable form. +

+
+ + +
+ Print external fn callsites passed constants +
+
+

+ This pass, only available in opt, prints out call sites to + external functions that are called with constant arguments. This can be + useful when looking for standard library functions we should constant fold + or handle in alias analyses. +

+
+ + +
+ Print function to stderr +
+
+

+ The PrintFunctionPass class is designed to be pipelined with + other FunctionPasses, and prints out the functions of the module + as they are processed. +

+
+ + +
+ Print module to stderr +
+
+

+ This pass simply prints out the entire module when it is executed. +

+
+ + +
+ Find Used Types +
+
+

+ This pass is used to seek out all of the types in use by the program. Note + that this analysis explicitly does not include types only used by the symbol + table. +

+ + +
+ Load profile information from llvmprof.out +
+
+

+ A concrete implementation of profiling information that loads the information + from a profile dump file. +

+
+ + +
+ Scalar Evolution Analysis +
+
+

+ The ScalarEvolution analysis can be used to analyze and + catagorize scalar expressions in loops. It specializes in recognizing general + induction variables, representing them with the abstract and opaque + SCEV class. Given this analysis, trip counts of loops and other + important properties can be obtained. +

+ +

+ This analysis is primarily useful for induction variable substitution and + strength reduction. +

+
+ + +
+ Target Data Layout +
+
+

Provides other passes access to information on how the size and alignment + required by the the target ABI for various data types.

+
+ + +
Transform Passes
+
+

This section describes the LLVM Transform Passes.

+
+ + +
+ Aggressive Dead Code Elimination +
+
+

ADCE aggressively tries to eliminate code. This pass is similar to + DCE but it assumes that values are dead until proven + otherwise. This is similar to SCCP, except applied to + the liveness of values.

+
+ + +
+ Promote 'by reference' arguments to scalars +
+
+

+ This pass promotes "by reference" arguments to be "by value" arguments. In + practice, this means looking for internal functions that have pointer + arguments. If it can prove, through the use of alias analysis, that an + argument is *only* loaded, then it can pass the value into the function + instead of the address of the value. This can cause recursive simplification + of code and lead to the elimination of allocas (especially in C++ template + code like the STL). +

+ +

+ This pass also handles aggregate arguments that are passed into a function, + scalarizing them if the elements of the aggregate are only loaded. Note that + it refuses to scalarize aggregates which would require passing in more than + three operands to the function, because passing thousands of operands for a + large array or structure is unprofitable! +

+ +

+ Note that this transformation could also be done for arguments that are only + stored to (returning the value instead), but does not currently. This case + would be best handled when and if LLVM starts supporting multiple return + values from functions. +

+
+ + +
+ Profile Guided Basic Block Placement +
+
+

This pass is a very simple profile guided basic block placement algorithm. + The idea is to put frequently executed blocks together at the start of the + function and hopefully increase the number of fall-through conditional + branches. If there is no profile information for a particular function, this + pass basically orders blocks in depth-first order.

+
+ + +
+ Break critical edges in CFG +
+
+

+ Break all of the critical edges in the CFG by inserting a dummy basic block. + It may be "required" by passes that cannot deal with critical edges. This + transformation obviously invalidates the CFG, but can update forward dominator + (set, immediate dominators, tree, and frontier) information. +

+
+ + +
+ Prepare a function for code generation +
+
+ This pass munges the code in the input function to better prepare it for + SelectionDAG-based code generation. This works around limitations in it's + basic-block-at-a-time approach. It should eventually be removed. +
+ + +
+ Conditional Propagation +
+
+

This pass propagates information about conditional expressions through the + program, allowing it to eliminate conditional branches in some cases.

+
+ + +
+ Merge Duplicate Global Constants +
+
+

+ Merges duplicate global constants together into a single constant that is + shared. This is useful because some passes (ie TraceValues) insert a lot of + string constants into the program, regardless of whether or not an existing + string is available. +

+
+ + +
+ Simple constant propagation +
+
+

This file implements constant propagation and merging. It looks for + instructions involving only constant operands and replaces them with a + constant value instead of an instruction. For example:

+ 
add i32 1, 2
+

becomes

+ 
i32 3
+

NOTE: this pass has a habit of making definitions be dead. It is a good + idea to to run a DIE (Dead Instruction Elimination) pass + sometime after running this pass.

+
+ + +
+ Dead Code Elimination +
+
+

+ Dead code elimination is similar to dead instruction + elimination, but it rechecks instructions that were used by removed + instructions to see if they are newly dead. +

+
+ + +
+ Dead Argument Elimination +
+
+

+ This pass deletes dead arguments from internal functions. Dead argument + elimination removes arguments which are directly dead, as well as arguments + only passed into function calls as dead arguments of other functions. This + pass also deletes dead arguments in a similar way. +

+ +

+ This pass is often useful as a cleanup pass to run after aggressive + interprocedural passes, which add possibly-dead arguments. +

+
+ + +
+ Dead Type Elimination +
+
+

+ This pass is used to cleanup the output of GCC. It eliminate names for types + that are unused in the entire translation unit, using the find used types pass. +

+
+ + +
+ Dead Instruction Elimination +
+
+

+ Dead instruction elimination performs a single pass over the function, + removing instructions that are obviously dead. +

+
+ + +
+ Dead Store Elimination +
+
+

+ A trivial dead store elimination that only considers basic-block local + redundant stores. +

+
+ + +
+ Dead Global Elimination +
+
+

+ This transform is designed to eliminate unreachable internal globals from the + program. It uses an aggressive algorithm, searching out globals that are + known to be alive. After it finds all of the globals which are needed, it + deletes whatever is left over. This allows it to delete recursive chunks of + the program which are unreachable. +

+
+ + +
+ Global Variable Optimizer +
+
+

+ This pass transforms simple global variables that never have their address + taken. If obviously true, it marks read/write globals as constant, deletes + variables only stored to, etc. +

+
+ + +
+ Global Value Numbering +
+
+

+ This pass performs global value numbering to eliminate fully and partially + redundant instructions. It also performs redundant load elimination. +

+
+ + + +
+ Indirect Malloc and Free Removal +
+
+

+ This pass finds places where memory allocation functions may escape into + indirect land. Some transforms are much easier (aka possible) only if free + or malloc are not called indirectly. +

+ +

+ Thus find places where the address of memory functions are taken and construct + bounce functions with direct calls of those functions. +

+
+ + +
+ Canonicalize Induction Variables +
+
+

+ This transformation analyzes and transforms the induction variables (and + computations derived from them) into simpler forms suitable for subsequent + analysis and transformation. +

+ +

+ This transformation makes the following changes to each loop with an + identifiable induction variable: +

+ +
    +
  1. All loops are transformed to have a single canonical + induction variable which starts at zero and steps by one.
    2. +
  2. The canonical induction variable is guaranteed to be the first PHI node + in the loop header block.
    3. +
  3. Any pointer arithmetic recurrences are raised to use array + subscripts.
    4. +
+ +

+ If the trip count of a loop is computable, this pass also makes the following + changes: +

+ +
    +
  1. The exit condition for the loop is canonicalized to compare the + induction value against the exit value. This turns loops like: + 
    for (i = 7; i*i < 1000; ++i)
    + into + 
    for (i = 0; i != 25; ++i)
    2. +
  2. Any use outside of the loop of an expression derived from the indvar + is changed to compute the derived value outside of the loop, eliminating + the dependence on the exit value of the induction variable. If the only + purpose of the loop is to compute the exit value of some derived + expression, this transformation will make the loop dead.
    3. +
+ +

+ This transformation should be followed by strength reduction after all of the + desired loop transformations have been performed. Additionally, on targets + where it is profitable, the loop could be transformed to count down to zero + (the "do loop" optimization). +

+
+ + +
+ Function Integration/Inlining +
+
+

+ Bottom-up inlining of functions into callees. +

+
+ + +
+ Insert instrumentation for block profiling +
+
+

+ This pass instruments the specified program with counters for basic block + profiling, which counts the number of times each basic block executes. This + is the most basic form of profiling, which can tell which blocks are hot, but + cannot reliably detect hot paths through the CFG. +

+ +

+ Note that this implementation is very na??ve. Control equivalent regions of + the CFG should not require duplicate counters, but it does put duplicate + counters in. +

+
+ + +
+ Insert instrumentation for edge profiling +
+
+

+ This pass instruments the specified program with counters for edge profiling. + Edge profiling can give a reasonable approximation of the hot paths through a + program, and is used for a wide variety of program transformations. +

+ +

+ Note that this implementation is very na??ve. It inserts a counter for + every edge in the program, instead of using control flow information + to prune the number of counters inserted. +

+
+ + +
+ Insert instrumentation for function profiling +
+
+

+ This pass instruments the specified program with counters for function + profiling, which counts the number of times each function is called. +

+
+ + +
+ Measure profiling framework overhead +
+
+

+ The basic profiler that does nothing. It is the default profiler and thus + terminates RSProfiler chains. It is useful for measuring + framework overhead. +

+
+ + +
+ Insert random sampling instrumentation framework +
+
+

+ The second stage of the random-sampling instrumentation framework, duplicates + all instructions in a function, ignoring the profiling code, then connects the + two versions together at the entry and at backedges. At each connection point + a choice is made as to whether to jump to the profiled code (take a sample) or + execute the unprofiled code. +

+ +

+ After this pass, it is highly recommended to runmem2reg + and adce. instcombine, + load-vn, gdce, and + dse also are good to run afterwards. +

+
+ + +
+ Combine redundant instructions +
+
+

+ Combine instructions to form fewer, simple + instructions. This pass does not modify the CFG This pass is where algebraic + simplification happens. +

+ +

+ This pass combines things like: +

+ +
%Y = add i32 %X, 1
+%Z = add i32 %Y, 1
+ +

+ into: +

+ +
%Z = add i32 %X, 2
+ +

+ This is a simple worklist driven algorithm. +

+ +

+ This pass guarantees that the following canonicalizations are performed on + the program: +

+ +
    +
  • If a binary operator has a constant operand, it is moved to the right- + hand side.
    • +
  • Bitwise operators with constant operands are always grouped so that + shifts are performed first, then ors, then + ands, then xors.
    • +
  • Compare instructions are converted from <, + >, ???, or ??? to + = or ??? if possible.
    • +
  • All cmp instructions on boolean values are replaced with + logical operations.
    • +
  • add X, X is represented as + mul X, 2 ??? shl X, 1
    • +
  • Multiplies with a constant power-of-two argument are transformed into + shifts.
    • +
  • ??? etc.
    • +
+
+ + +
+ Internalize Global Symbols +
+
+

+ This pass loops over all of the functions in the input module, looking for a + main function. If a main function is found, all other functions and all + global variables with initializers are marked as internal. +

+
+ + +
+ Interprocedural constant propagation +
+
+

+ This pass implements an extremely simple interprocedural constant + propagation pass. It could certainly be improved in many different ways, + like using a worklist. This pass makes arguments dead, but does not remove + them. The existing dead argument elimination pass should be run after this + to clean up the mess. +

+
+ + +
+ Interprocedural Sparse Conditional Constant Propagation +
+
+

+ An interprocedural variant of Sparse Conditional Constant + Propagation. +

+
+ + +
+ Thread control through conditional blocks +
+
+

+ Jump threading tries to find distinct threads of control flow running through + a basic block. This pass looks at blocks that have multiple predecessors and + multiple successors. If one or more of the predecessors of the block can be + proven to always cause a jump to one of the successors, we forward the edge + from the predecessor to the successor by duplicating the contents of this + block. +

+

+ An example of when this can occur is code like this: +

+ + 
if () { ...
+  X = 4;
+}
+if (X < 3) {
+ +

+ In this case, the unconditional branch at the end of the first if can be + revectored to the false side of the second if. +

+
+ + +
+ Loop-Closed SSA Form Pass +
+
+

+ This pass transforms loops by placing phi nodes at the end of the loops for + all values that are live across the loop boundary. For example, it turns + the left into the right code: +

+ + 
for (...)                for (...)
+  if (c)                   if (c)
+    X1 = ...                 X1 = ...
+  else                     else
+    X2 = ...                 X2 = ...
+  X3 = phi(X1, X2)         X3 = phi(X1, X2)
+... = X3 + 4              X4 = phi(X3)
+                          ... = X4 + 4
+ +

+ This is still valid LLVM; the extra phi nodes are purely redundant, and will + be trivially eliminated by InstCombine. The major benefit of + this transformation is that it makes many other loop optimizations, such as + LoopUnswitching, simpler. +

+
+ + +
+ Loop Invariant Code Motion +
+
+

+ This pass performs loop invariant code motion, attempting to remove as much + code from the body of a loop as possible. It does this by either hoisting + code into the preheader block, or by sinking code to the exit blocks if it is + safe. This pass also promotes must-aliased memory locations in the loop to + live in registers, thus hoisting and sinking "invariant" loads and stores. +

+ +

+ This pass uses alias analysis for two purposes: +

+ +
    +
  • Moving loop invariant loads and calls out of loops. If we can determine + that a load or call inside of a loop never aliases anything stored to, + we can hoist it or sink it like any other instruction.
    • +
  • Scalar Promotion of Memory - If there is a store instruction inside of + the loop, we try to move the store to happen AFTER the loop instead of + inside of the loop. This can only happen if a few conditions are true: +
      +
    • The pointer stored through is loop invariant.
      • +
    • There are no stores or loads in the loop which may alias + the pointer. There are no calls in the loop which mod/ref the + pointer.
      • +
    + If these conditions are true, we can promote the loads and stores in the + loop of the pointer to use a temporary alloca'd variable. We then use + the mem2reg functionality to construct the appropriate SSA form for the + variable.
    • +
+
+ +
+ Dead Loop Deletion Pass +
+
+

+ This file implements the Dead Loop Deletion Pass. This pass is responsible + for eliminating loops with non-infinite computable trip counts that have no + side effects or volatile instructions, and do not contribute to the + computation of the function's return value. +

+
+ + +
+ Extract loops into new functions +
+
+

+ A pass wrapper around the ExtractLoop() scalar transformation to + extract each top-level loop into its own new function. If the loop is the + only loop in a given function, it is not touched. This is a pass most + useful for debugging via bugpoint. +

+
+ + +
+ Extract at most one loop into a new function +
+
+

+ Similar to Extract loops into new functions, + this pass extracts one natural loop from the program into a function if it + can. This is used by bugpoint. +

+
+ + +
+ Index Split Loops +
+
+

+ This pass divides loop's iteration range by spliting loop such that each + individual loop is executed efficiently. +

+
+ + +
+ Loop Strength Reduction +
+
+

+ This pass performs a strength reduction on array references inside loops that + have as one or more of their components the loop induction variable. This is + accomplished by creating a new value to hold the initial value of the array + access for the first iteration, and then creating a new GEP instruction in + the loop to increment the value by the appropriate amount. +

+
+ + +
+ Rotate Loops +
+
+

A simple loop rotation transformation.

+
+ + +
+ Unroll loops +
+
+

+ This pass implements a simple loop unroller. It works best when loops have + been canonicalized by the -indvars pass, + allowing it to determine the trip counts of loops easily. +

+
+ + +
+ Unswitch loops +
+
+

+ This pass transforms loops that contain branches on loop-invariant conditions + to have multiple loops. For example, it turns the left into the right code: +

+ + 
for (...)                  if (lic)
+  A                          for (...)
+  if (lic)                     A; B; C
+    B                      else
+  C                          for (...)
+                               A; C
+ +

+ This can increase the size of the code exponentially (doubling it every time + a loop is unswitched) so we only unswitch if the resultant code will be + smaller than a threshold. +

+ +

+ This pass expects LICM to be run before it to hoist invariant conditions out + of the loop, to make the unswitching opportunity obvious. +

+
+ + +
+ Canonicalize natural loops +
+
+

+ This pass performs several transformations to transform natural loops into a + simpler form, which makes subsequent analyses and transformations simpler and + more effective. +

+ +

+ Loop pre-header insertion guarantees that there is a single, non-critical + entry edge from outside of the loop to the loop header. This simplifies a + number of analyses and transformations, such as LICM. +

+ +

+ Loop exit-block insertion guarantees that all exit blocks from the loop + (blocks which are outside of the loop that have predecessors inside of the + loop) only have predecessors from inside of the loop (and are thus dominated + by the loop header). This simplifies transformations such as store-sinking + that are built into LICM. +

+ +

+ This pass also guarantees that loops will have exactly one backedge. +

+ +

+ Note that the simplifycfg pass will clean up blocks which are split out but + end up being unnecessary, so usage of this pass should not pessimize + generated code. +

+ +

+ This pass obviously modifies the CFG, but updates loop information and + dominator information. +

+
+ + +
+ Lower allocations from instructions to calls +
+
+

+ Turn malloc and free instructions into @malloc and + @free calls. +

+ +

+ This is a target-dependent tranformation because it depends on the size of + data types and alignment constraints. +

+
+ + +
+ Lower invoke and unwind, for unwindless code generators +
+
+

+ This transformation is designed for use by code generators which do not yet + support stack unwinding. This pass supports two models of exception handling + lowering, the 'cheap' support and the 'expensive' support. +

+ +

+ 'Cheap' exception handling support gives the program the ability to execute + any program which does not "throw an exception", by turning 'invoke' + instructions into calls and by turning 'unwind' instructions into calls to + abort(). If the program does dynamically use the unwind instruction, the + program will print a message then abort. +

+ +

+ 'Expensive' exception handling support gives the full exception handling + support to the program at the cost of making the 'invoke' instruction + really expensive. It basically inserts setjmp/longjmp calls to emulate the + exception handling as necessary. +

+ +

+ Because the 'expensive' support slows down programs a lot, and EH is only + used for a subset of the programs, it must be specifically enabled by the + -enable-correct-eh-support option. +

+ +

+ Note that after this pass runs the CFG is not entirely accurate (exceptional + control flow edges are not correct anymore) so only very simple things should + be done after the lowerinvoke pass has run (like generation of native code). + This should not be used as a general purpose "my LLVM-to-LLVM pass doesn't + support the invoke instruction yet" lowering pass. +

+
+ + +
+ Lower Set Jump +
+
+

+ Lowers setjmp and longjmp to use the LLVM invoke and unwind + instructions as necessary. +

+ +

+ Lowering of longjmp is fairly trivial. We replace the call with a + call to the LLVM library function __llvm_sjljeh_throw_longjmp(). + This unwinds the stack for us calling all of the destructors for + objects allocated on the stack. +

+ +

+ At a setjmp call, the basic block is split and the setjmp + removed. The calls in a function that have a setjmp are converted to + invoke where the except part checks to see if it's a longjmp + exception and, if so, if it's handled in the function. If it is, then it gets + the value returned by the longjmp and goes to where the basic block + was split. invoke instructions are handled in a similar fashion with + the original except block being executed if it isn't a longjmp + except that is handled by that function. +

+
+ + +
+ Lower SwitchInst's to branches +
+
+

+ Rewrites switch instructions with a sequence of branches, which + allows targets to get away with not implementing the switch instruction until + it is convenient. +

+
+ + +
+ Promote Memory to Register +
+
+

+ This file promotes memory references to be register references. It promotes + alloca instructions which only have loads and + stores as uses. An alloca is transformed by using dominator + frontiers to place phi nodes, then traversing the function in + depth-first order to rewrite loads and stores as + appropriate. This is just the standard SSA construction algorithm to construct + "pruned" SSA form. +

+
+ + +
+ Optimize use of memcpy and friend +
+
+

+ This pass performs various transformations related to eliminating memcpy + calls, or transforming sets of stores into memset's. +

+
+ + +
+ Unify function exit nodes +
+
+

+ Ensure that functions have at most one ret instruction in them. + Additionally, it keeps track of which node is the new exit node of the CFG. +

+
+ + +
+ Remove unused exception handling info +
+
+

+ This file implements a simple interprocedural pass which walks the call-graph, + turning invoke instructions into call instructions if and + only if the callee cannot throw an exception. It implements this as a + bottom-up traversal of the call-graph. +

+
+ + +
+ Reassociate expressions +
+
+

+ This pass reassociates commutative expressions in an order that is designed + to promote better constant propagation, GCSE, LICM, PRE, etc. +

+ +

+ For example: 4 + (x + 5) ??? x + (4 + 5) +

+ +

+ In the implementation of this algorithm, constants are assigned rank = 0, + function arguments are rank = 1, and other values are assigned ranks + corresponding to the reverse post order traversal of current function + (starting at 2), which effectively gives values in deep loops higher rank + than values not in loops. +

+
+ + +
+ Demote all values to stack slots +
+
+

+ This file demotes all registers to memory references. It is intented to be + the inverse of -mem2reg. By converting to + load instructions, the only values live across basic blocks are + alloca instructions and load instructions before + phi nodes. It is intended that this should make CFG hacking much + easier. To make later hacking easier, the entry block is split into two, such + that all introduced alloca instructions (and nothing else) are in the + entry block. +

+
+ + +
+ Scalar Replacement of Aggregates +
+
+

+ The well-known scalar replacement of aggregates transformation. This + transform breaks up alloca instructions of aggregate type (structure + or array) into individual alloca instructions for each member if + possible. Then, if possible, it transforms the individual alloca + instructions into nice clean scalar SSA form. +

+ +

+ This combines a simple scalar replacement of aggregates algorithm with the mem2reg algorithm because often interact, + especially for C++ programs. As such, iterating between scalarrepl, + then mem2reg until we run out of things to + promote works well. +

+
+ + +
+ Sparse Conditional Constant Propagation +
+
+

+ Sparse conditional constant propagation and merging, which can be summarized + as: +

+ +
    +
  1. Assumes values are constant unless proven otherwise
    2. +
  2. Assumes BasicBlocks are dead unless proven otherwise
    3. +
  3. Proves values to be constant, and replaces them with constants
    4. +
  4. Proves conditional branches to be unconditional
    5. +
+ +

+ Note that this pass has a habit of making definitions be dead. It is a good + idea to to run a DCE pass sometime after running this pass. +

+
+ + +
+ Simplify well-known library calls +
+
+

+ Applies a variety of small optimizations for calls to specific well-known + function calls (e.g. runtime library functions). For example, a call + exit(3) that occurs within the main() function can be + transformed into simply return 3. +

+
+ + +
+ Simplify the CFG +
+
+

+ Performs dead code elimination and basic block merging. Specifically: +

+ +
    +
  1. Removes basic blocks with no predecessors.
    2. +
  2. Merges a basic block into its predecessor if there is only one and the + predecessor only has one successor.
    3. +
  3. Eliminates PHI nodes for basic blocks with a single predecessor.
    4. +
  4. Eliminates a basic block that only contains an unconditional + branch.
    5. +
+
+ + +
+ Strip all symbols from a module +
+
+

+ Performs code stripping. This transformation can delete: +

+ +
    +
  1. names for virtual registers
    2. +
  2. symbols for internal globals and functions
    3. +
  3. debug information
    4. +
+ +

+ Note that this transformation makes code much less readable, so it should + only be used in situations where the strip utility would be used, + such as reducing code size or making it harder to reverse engineer code. +

+
+ + +
+ Remove unused function declarations +
+
+

+ This pass loops over all of the functions in the input module, looking for + dead declarations and removes them. Dead declarations are declarations of + functions for which no implementation is available (i.e., declarations for + unused library functions). +

+
+ + +
+ Promote sret arguments +
+
+

+ This pass finds functions that return a struct (using a pointer to the struct + as the first argument of the function, marked with the 'sret' attribute) and + replaces them with a new function that simply returns each of the elements of + that struct (using multiple return values). +

+ +

+ This pass works under a number of conditions: +

+ +
    +
  • The returned struct must not contain other structs
    • +
  • The returned struct must only be used to load values from
    • +
  • The placeholder struct passed in is the result of an alloca
    • +
+
+ + +
+ Tail Call Elimination +
+
+

+ This file transforms calls of the current function (self recursion) followed + by a return instruction with a branch to the entry of the function, creating + a loop. This pass also implements the following extensions to the basic + algorithm: +

+ +
    +
  • Trivial instructions between the call and return do not prevent the + transformation from taking place, though currently the analysis cannot + support moving any really useful instructions (only dead ones). +
  • This pass transforms functions that are prevented from being tail + recursive by an associative expression to use an accumulator variable, + thus compiling the typical naive factorial or fib implementation + into efficient code. +
  • TRE is performed if the function returns void, if the return + returns the result returned by the call, or if the function returns a + run-time constant on all exits from the function. It is possible, though + unlikely, that the return returns something else (like constant 0), and + can still be TRE'd. It can be TRE'd if all other return + instructions in the function return the exact same value. +
  • If it can prove that callees do not access theier caller stack frame, + they are marked as eligible for tail call elimination (by the code + generator). +
+
+ + +
+ Tail Duplication +
+
+

+ This pass performs a limited form of tail duplication, intended to simplify + CFGs by removing some unconditional branches. This pass is necessary to + straighten out loops created by the C front-end, but also is capable of + making other code nicer. After this pass is run, the CFG simplify pass + should be run to clean up the mess. +

+
+ + +
Utility Passes
+
+

This section describes the LLVM Utility Passes.

+
+ + +
+ Dead Argument Hacking (BUGPOINT USE ONLY; DO NOT USE) +
+
+

+ Same as dead argument elimination, but deletes arguments to functions which + are external. This is only for use by bugpoint.

+
+ + +
+ Extract Basic Blocks From Module (for bugpoint use) +
+
+

+ This pass is used by bugpoint to extract all blocks from the module into their + own functions.

+
+ + +
+ Preliminary module verification +
+
+

+ Ensures that the module is in the form required by the Module Verifier pass. +

+ +

+ Running the verifier runs this pass automatically, so there should be no need + to use it directly. +

+
+ + +
+ Module Verifier +
+
+

+ Verifies an LLVM IR code. This is useful to run after an optimization which is + undergoing testing. Note that llvm-as verifies its input before + emitting bitcode, and also that malformed bitcode is likely to make LLVM + crash. All language front-ends are therefore encouraged to verify their output + before performing optimizing transformations. +

+ +
    +
  • Both of a binary operator's parameters are of the same type.
    • +
  • Verify that the indices of mem access instructions match other + operands.
    • +
  • Verify that arithmetic and other things are only performed on + first-class types. Verify that shifts and logicals only happen on + integrals f.e.
    • +
  • All of the constants in a switch statement are of the correct type.
    • +
  • The code is in valid SSA form.
    • +
  • It is illegal to put a label into any other type (like a structure) or + to return one.
    • +
  • Only phi nodes can be self referential: %x = add i32 %x, %x is + invalid.
    • +
  • PHI nodes must have an entry for each predecessor, with no extras.
    • +
  • PHI nodes must be the first thing in a basic block, all grouped + together.
    • +
  • PHI nodes must have at least one entry.
    • +
  • All basic blocks should only end with terminator insts, not contain + them.
    • +
  • The entry node to a function must not have predecessors.
    • +
  • All Instructions must be embedded into a basic block.
    • +
  • Functions cannot take a void-typed parameter.
    • +
  • Verify that a function's argument list agrees with its declared + type.
    • +
  • It is illegal to specify a name for a void value.
    • +
  • It is illegal to have a internal global value with no initializer.
    • +
  • It is illegal to have a ret instruction that returns a value that does + not agree with the function return value type.
    • +
  • Function call argument types match the function prototype.
    • +
  • All other things that are tested by asserts spread about the code.
    • +
+ +

+ Note that this does not provide full security verification (like Java), but + instead just tries to ensure that code is well-formed. +

+
+ + +
+ View CFG of function +
+
+

+ Displays the control flow graph using the GraphViz tool. +

+
+ + +
+ View CFG of function (with no function bodies) +
+
+

+ Displays the control flow graph using the GraphViz tool, but omitting function + bodies. +

+
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + Reid Spencer
+ LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-03-01 13:24:17 -0600 (Mon, 01 Mar 2010) $ +
+ + + Added: www-releases/trunk/2.7/docs/ProgrammersManual.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/ProgrammersManual.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/ProgrammersManual.html (added) +++ www-releases/trunk/2.7/docs/ProgrammersManual.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,3928 @@ + + + + + LLVM Programmer's Manual + + + + +
+ LLVM Programmer's Manual +
+ +
    +
  1. Introduction
    2. +
  2. General Information + +
    3. +
  3. Important and useful LLVM APIs + +
    4. +
  4. Picking the Right Data Structure for a Task + +
    5. +
  5. Helpful Hints for Common Operations + +
    6. + +
  6. Threads and LLVM + +
    7. + +
  7. Advanced Topics +
    8. + +
  8. The Core LLVM Class Hierarchy Reference + +
    9. +
+ +
+

Written by Chris Lattner, + Dinakar Dhurjati, + Gabor Greif, + Joel Stanley, + Reid Spencer and + Owen Anderson

+
+ + +
+ Introduction +
+ + +
+ +

This document is meant to highlight some of the important classes and +interfaces available in the LLVM source-base. This manual is not +intended to explain what LLVM is, how it works, and what LLVM code looks +like. It assumes that you know the basics of LLVM and are interested +in writing transformations or otherwise analyzing or manipulating the +code.

+ +

This document should get you oriented so that you can find your +way in the continuously growing source code that makes up the LLVM +infrastructure. Note that this manual is not intended to serve as a +replacement for reading the source code, so if you think there should be +a method in one of these classes to do something, but it's not listed, +check the source. Links to the doxygen sources +are provided to make this as easy as possible.

+ +

The first section of this document describes general information that is +useful to know when working in the LLVM infrastructure, and the second describes +the Core LLVM classes. In the future this manual will be extended with +information describing how to use extension libraries, such as dominator +information, CFG traversal routines, and useful utilities like the InstVisitor template.

+ +
+ + +
+ General Information +
+ + +
+ +

This section contains general information that is useful if you are working +in the LLVM source-base, but that isn't specific to any particular API.

+ +
+ + +
+ The C++ Standard Template Library +
+ +
+ +

LLVM makes heavy use of the C++ Standard Template Library (STL), +perhaps much more than you are used to, or have seen before. Because of +this, you might want to do a little background reading in the +techniques used and capabilities of the library. There are many good +pages that discuss the STL, and several books on the subject that you +can get, so it will not be discussed in this document.

+ +

Here are some useful links:

+ +
    + +
  1. Dinkumware C++ Library +reference - an excellent reference for the STL and other parts of the +standard C++ library.
    2. + +
  2. C++ In a Nutshell - This is an +O'Reilly book in the making. It has a decent Standard Library +Reference that rivals Dinkumware's, and is unfortunately no longer free since the +book has been published.
    3. + +
  3. C++ Frequently Asked +Questions
    4. + +
  4. SGI's STL Programmer's Guide - +Contains a useful Introduction to the +STL.
    5. + +
  5. Bjarne Stroustrup's C++ +Page
    6. + +
  6. +Bruce Eckel's Thinking in C++, 2nd ed. Volume 2 Revision 4.0 (even better, get +the book).
    7. + +
+ +

You are also encouraged to take a look at the LLVM Coding Standards guide which focuses on how +to write maintainable code more than where to put your curly braces.

+ +
+ + +
+ Other useful references +
+ +
+ +
    +
  1. CVS +Branch and Tag Primer
    2. +
  2. Using +static and shared libraries across platforms
    3. +
+ +
+ + +
+ Important and useful LLVM APIs +
+ + +
+ +

Here we highlight some LLVM APIs that are generally useful and good to +know about when writing transformations.

+ +
+ + +
+ The isa<>, cast<> and + dyn_cast<> templates +
+ +
+ +

The LLVM source-base makes extensive use of a custom form of RTTI. +These templates have many similarities to the C++ dynamic_cast<> +operator, but they don't have some drawbacks (primarily stemming from +the fact that dynamic_cast<> only works on classes that +have a v-table). Because they are used so often, you must know what they +do and how they work. All of these templates are defined in the llvm/Support/Casting.h +file (note that you very rarely have to include this file directly).

+ +
+
isa<>:
+ +

The isa<> operator works exactly like the Java + "instanceof" operator. It returns true or false depending on whether + a reference or pointer points to an instance of the specified class. This can + be very useful for constraint checking of various sorts (example below).

+
+ +
cast<>:
+ +

The cast<> operator is a "checked cast" operation. It + converts a pointer or reference from a base class to a derived class, causing + an assertion failure if it is not really an instance of the right type. This + should be used in cases where you have some information that makes you believe + that something is of the right type. An example of the isa<> + and cast<> template is:

+ +
+
+static bool isLoopInvariant(const Value *V, const Loop *L) {
+  if (isa<Constant>(V) || isa<Argument>(V) || isa<GlobalValue>(V))
+    return true;
+
+  // Otherwise, it must be an instruction...
+  return !L->contains(cast<Instruction>(V)->getParent());
+}
+
+
+ +

Note that you should not use an isa<> test followed + by a cast<>, for that use the dyn_cast<> + operator.

+ +
+ +
dyn_cast<>:
+ +

The dyn_cast<> operator is a "checking cast" operation. + It checks to see if the operand is of the specified type, and if so, returns a + pointer to it (this operator does not work with references). If the operand is + not of the correct type, a null pointer is returned. Thus, this works very + much like the dynamic_cast<> operator in C++, and should be + used in the same circumstances. Typically, the dyn_cast<> + operator is used in an if statement or some other flow control + statement like this:

+ +
+
+if (AllocationInst *AI = dyn_cast<AllocationInst>(Val)) {
+  // ...
+}
+
+
+ +

This form of the if statement effectively combines together a call + to isa<> and a call to cast<> into one + statement, which is very convenient.

+ +

Note that the dyn_cast<> operator, like C++'s + dynamic_cast<> or Java's instanceof operator, can be + abused. In particular, you should not use big chained if/then/else + blocks to check for lots of different variants of classes. If you find + yourself wanting to do this, it is much cleaner and more efficient to use the + InstVisitor class to dispatch over the instruction type directly.

+ +
+ +
cast_or_null<>:
+ +

The cast_or_null<> operator works just like the + cast<> operator, except that it allows for a null pointer as an + argument (which it then propagates). This can sometimes be useful, allowing + you to combine several null checks into one.

+ +
dyn_cast_or_null<>:
+ +

The dyn_cast_or_null<> operator works just like the + dyn_cast<> operator, except that it allows for a null pointer + as an argument (which it then propagates). This can sometimes be useful, + allowing you to combine several null checks into one.

+ +
+ +

These five templates can be used with any classes, whether they have a +v-table or not. To add support for these templates, you simply need to add +classof static methods to the class you are interested casting +to. Describing this is currently outside the scope of this document, but there +are lots of examples in the LLVM source base.

+ +
+ + + +
+ Passing strings (the StringRef +and Twine classes) +
+ +
+ +

Although LLVM generally does not do much string manipulation, we do have +several important APIs which take strings. Two important examples are the +Value class -- which has names for instructions, functions, etc. -- and the +StringMap class which is used extensively in LLVM and Clang.

+ +

These are generic classes, and they need to be able to accept strings which +may have embedded null characters. Therefore, they cannot simply take +a const char *, and taking a const std::string& requires +clients to perform a heap allocation which is usually unnecessary. Instead, +many LLVM APIs use a const StringRef& or a const +Twine& for passing strings efficiently.

+ +
+ + +
+ The StringRef class +
+ +
+ +

The StringRef data type represents a reference to a constant string +(a character array and a length) and supports the common operations available +on std:string, but does not require heap allocation.

+ +

It can be implicitly constructed using a C style null-terminated string, +an std::string, or explicitly with a character pointer and length. +For example, the StringRef find function is declared as:

+ +
+ iterator find(const StringRef &Key); +
+ +

and clients can call it using any one of:

+ +
+
+  Map.find("foo");                 // Lookup "foo"
+  Map.find(std::string("bar"));    // Lookup "bar"
+  Map.find(StringRef("\0baz", 4)); // Lookup "\0baz"
+
+
+ +

Similarly, APIs which need to return a string may return a StringRef +instance, which can be used directly or converted to an std::string +using the str member function. See +"llvm/ADT/StringRef.h" +for more information.

+ +

You should rarely use the StringRef class directly, because it contains +pointers to external memory it is not generally safe to store an instance of the +class (unless you know that the external storage will not be freed).

+ +
+ + +
+ The Twine class +
+ +
+ +

The Twine class is an efficient way for APIs to accept concatenated +strings. For example, a common LLVM paradigm is to name one instruction based on +the name of another instruction with a suffix, for example:

+ +
+
+    New = CmpInst::Create(..., SO->getName() + ".cmp");
+
+
+ +

The Twine class is effectively a +lightweight rope +which points to temporary (stack allocated) objects. Twines can be implicitly +constructed as the result of the plus operator applied to strings (i.e., a C +strings, an std::string, or a StringRef). The twine delays the +actual concatenation of strings until it is actually required, at which point +it can be efficiently rendered directly into a character array. This avoids +unnecessary heap allocation involved in constructing the temporary results of +string concatenation. See +"llvm/ADT/Twine.h" +for more information.

+ +

As with a StringRef, Twine objects point to external memory +and should almost never be stored or mentioned directly. They are intended +solely for use when defining a function which should be able to efficiently +accept concatenated strings.

+ +
+ + + +
+ The DEBUG() macro and -debug option +
+ +
+ +

Often when working on your pass you will put a bunch of debugging printouts +and other code into your pass. After you get it working, you want to remove +it, but you may need it again in the future (to work out new bugs that you run +across).

+ +

Naturally, because of this, you don't want to delete the debug printouts, +but you don't want them to always be noisy. A standard compromise is to comment +them out, allowing you to enable them if you need them in the future.

+ +

The "llvm/Support/Debug.h" +file provides a macro named DEBUG() that is a much nicer solution to +this problem. Basically, you can put arbitrary code into the argument of the +DEBUG macro, and it is only executed if 'opt' (or any other +tool) is run with the '-debug' command line argument:

+ +
+
+DEBUG(errs() << "I am here!\n");
+
+
+ +

Then you can run your pass like this:

+ +
+
+$ opt < a.bc > /dev/null -mypass
+<no output>
+$ opt < a.bc > /dev/null -mypass -debug
+I am here!
+
+
+ +

Using the DEBUG() macro instead of a home-brewed solution allows you +to not have to create "yet another" command line option for the debug output for +your pass. Note that DEBUG() macros are disabled for optimized builds, +so they do not cause a performance impact at all (for the same reason, they +should also not contain side-effects!).

+ +

One additional nice thing about the DEBUG() macro is that you can +enable or disable it directly in gdb. Just use "set DebugFlag=0" or +"set DebugFlag=1" from the gdb if the program is running. If the +program hasn't been started yet, you can always just run it with +-debug.

+ +
+ + +
+ Fine grained debug info with DEBUG_TYPE and + the -debug-only option +
+ +
+ +

Sometimes you may find yourself in a situation where enabling -debug +just turns on too much information (such as when working on the code +generator). If you want to enable debug information with more fine-grained +control, you define the DEBUG_TYPE macro and the -debug only +option as follows:

+ +
+
+#undef  DEBUG_TYPE
+DEBUG(errs() << "No debug type\n");
+#define DEBUG_TYPE "foo"
+DEBUG(errs() << "'foo' debug type\n");
+#undef  DEBUG_TYPE
+#define DEBUG_TYPE "bar"
+DEBUG(errs() << "'bar' debug type\n"));
+#undef  DEBUG_TYPE
+#define DEBUG_TYPE ""
+DEBUG(errs() << "No debug type (2)\n");
+
+
+ +

Then you can run your pass like this:

+ +
+
+$ opt < a.bc > /dev/null -mypass
+<no output>
+$ opt < a.bc > /dev/null -mypass -debug
+No debug type
+'foo' debug type
+'bar' debug type
+No debug type (2)
+$ opt < a.bc > /dev/null -mypass -debug-only=foo
+'foo' debug type
+$ opt < a.bc > /dev/null -mypass -debug-only=bar
+'bar' debug type
+
+
+ +

Of course, in practice, you should only set DEBUG_TYPE at the top of +a file, to specify the debug type for the entire module (if you do this before +you #include "llvm/Support/Debug.h", you don't have to insert the ugly +#undef's). Also, you should use names more meaningful than "foo" and +"bar", because there is no system in place to ensure that names do not +conflict. If two different modules use the same string, they will all be turned +on when the name is specified. This allows, for example, all debug information +for instruction scheduling to be enabled with -debug-type=InstrSched, +even if the source lives in multiple files.

+ +

The DEBUG_WITH_TYPE macro is also available for situations where you +would like to set DEBUG_TYPE, but only for one specific DEBUG +statement. It takes an additional first parameter, which is the type to use. For +example, the preceding example could be written as:

+ + +
+
+DEBUG_WITH_TYPE("", errs() << "No debug type\n");
+DEBUG_WITH_TYPE("foo", errs() << "'foo' debug type\n");
+DEBUG_WITH_TYPE("bar", errs() << "'bar' debug type\n"));
+DEBUG_WITH_TYPE("", errs() << "No debug type (2)\n");
+
+
+ +
+ + +
+ The Statistic class & -stats + option +
+ +
+ +

The "llvm/ADT/Statistic.h" file +provides a class named Statistic that is used as a unified way to +keep track of what the LLVM compiler is doing and how effective various +optimizations are. It is useful to see what optimizations are contributing to +making a particular program run faster.

+ +

Often you may run your pass on some big program, and you're interested to see +how many times it makes a certain transformation. Although you can do this with +hand inspection, or some ad-hoc method, this is a real pain and not very useful +for big programs. Using the Statistic class makes it very easy to +keep track of this information, and the calculated information is presented in a +uniform manner with the rest of the passes being executed.

+ +

There are many examples of Statistic uses, but the basics of using +it are as follows:

+ +
    +

  1. Define your statistic like this:

    + +
    +
    +#define DEBUG_TYPE "mypassname"   // This goes before any #includes.
+STATISTIC(NumXForms, "The # of times I did stuff");
+
    +
    + +

    The STATISTIC macro defines a static variable, whose name is + specified by the first argument. The pass name is taken from the DEBUG_TYPE + macro, and the description is taken from the second argument. The variable + defined ("NumXForms" in this case) acts like an unsigned integer.

    2. + +

  2. Whenever you make a transformation, bump the counter:

    + +
    +
    +++NumXForms;   // I did stuff!
+
    +
    + +
    3. +
+ +

That's all you have to do. To get 'opt' to print out the + statistics gathered, use the '-stats' option:

+ +
+
+$ opt -stats -mypassname < program.bc > /dev/null
+... statistics output ...
+
+
+ +

When running opt on a C file from the SPEC benchmark +suite, it gives a report that looks like this:

+ +
+
+   7646 bitcodewriter   - Number of normal instructions
+    725 bitcodewriter   - Number of oversized instructions
+ 129996 bitcodewriter   - Number of bitcode bytes written
+   2817 raise           - Number of insts DCEd or constprop'd
+   3213 raise           - Number of cast-of-self removed
+   5046 raise           - Number of expression trees converted
+     75 raise           - Number of other getelementptr's formed
+    138 raise           - Number of load/store peepholes
+     42 deadtypeelim    - Number of unused typenames removed from symtab
+    392 funcresolve     - Number of varargs functions resolved
+     27 globaldce       - Number of global variables removed
+      2 adce            - Number of basic blocks removed
+    134 cee             - Number of branches revectored
+     49 cee             - Number of setcc instruction eliminated
+    532 gcse            - Number of loads removed
+   2919 gcse            - Number of instructions removed
+     86 indvars         - Number of canonical indvars added
+     87 indvars         - Number of aux indvars removed
+     25 instcombine     - Number of dead inst eliminate
+    434 instcombine     - Number of insts combined
+    248 licm            - Number of load insts hoisted
+   1298 licm            - Number of insts hoisted to a loop pre-header
+      3 licm            - Number of insts hoisted to multiple loop preds (bad, no loop pre-header)
+     75 mem2reg         - Number of alloca's promoted
+   1444 cfgsimplify     - Number of blocks simplified
+
+
+ +

Obviously, with so many optimizations, having a unified framework for this +stuff is very nice. Making your pass fit well into the framework makes it more +maintainable and useful.

+ +
+ + +
+ Viewing graphs while debugging code +
+ +
+ +

Several of the important data structures in LLVM are graphs: for example +CFGs made out of LLVM BasicBlocks, CFGs made out of +LLVM MachineBasicBlocks, and +Instruction Selection +DAGs. In many cases, while debugging various parts of the compiler, it is +nice to instantly visualize these graphs.

+ +

LLVM provides several callbacks that are available in a debug build to do +exactly that. If you call the Function::viewCFG() method, for example, +the current LLVM tool will pop up a window containing the CFG for the function +where each basic block is a node in the graph, and each node contains the +instructions in the block. Similarly, there also exists +Function::viewCFGOnly() (does not include the instructions), the +MachineFunction::viewCFG() and MachineFunction::viewCFGOnly(), +and the SelectionDAG::viewGraph() methods. Within GDB, for example, +you can usually use something like call DAG.viewGraph() to pop +up a window. Alternatively, you can sprinkle calls to these functions in your +code in places you want to debug.

+ +

Getting this to work requires a small amount of configuration. On Unix +systems with X11, install the graphviz +toolkit, and make sure 'dot' and 'gv' are in your path. If you are running on +Mac OS/X, download and install the Mac OS/X Graphviz program, and add +/Applications/Graphviz.app/Contents/MacOS/ (or wherever you install +it) to your path. Once in your system and path are set up, rerun the LLVM +configure script and rebuild LLVM to enable this functionality.

+ +

SelectionDAG has been extended to make it easier to locate +interesting nodes in large complex graphs. From gdb, if you +call DAG.setGraphColor(node, "color"), then the +next call DAG.viewGraph() would highlight the node in the +specified color (choices of colors can be found at colors.) More +complex node attributes can be provided with call +DAG.setGraphAttrs(node, "attributes") (choices can be +found at Graph +Attributes.) If you want to restart and clear all the current graph +attributes, then you can call DAG.clearGraphAttrs().

+ +
+ + +
+ Picking the Right Data Structure for a Task +
+ + +
+ +

LLVM has a plethora of data structures in the llvm/ADT/ directory, + and we commonly use STL data structures. This section describes the trade-offs + you should consider when you pick one.

+ +

+The first step is a choose your own adventure: do you want a sequential +container, a set-like container, or a map-like container? The most important +thing when choosing a container is the algorithmic properties of how you plan to +access the container. Based on that, you should use:

+ +
    +
  • a map-like container if you need efficient look-up + of an value based on another value. Map-like containers also support + efficient queries for containment (whether a key is in the map). Map-like + containers generally do not support efficient reverse mapping (values to + keys). If you need that, use two maps. Some map-like containers also + support efficient iteration through the keys in sorted order. Map-like + containers are the most expensive sort, only use them if you need one of + these capabilities.
    • + +
  • a set-like container if you need to put a bunch of + stuff into a container that automatically eliminates duplicates. Some + set-like containers support efficient iteration through the elements in + sorted order. Set-like containers are more expensive than sequential + containers. +
    • + +
  • a sequential container provides + the most efficient way to add elements and keeps track of the order they are + added to the collection. They permit duplicates and support efficient + iteration, but do not support efficient look-up based on a key. +
    • + +
  • a string container is a specialized sequential + container or reference structure that is used for character or byte + arrays.
    • + +
  • a bit container provides an efficient way to store and + perform set operations on sets of numeric id's, while automatically + eliminating duplicates. Bit containers require a maximum of 1 bit for each + identifier you want to store. +
    • +
+ +

+Once the proper category of container is determined, you can fine tune the +memory use, constant factors, and cache behaviors of access by intelligently +picking a member of the category. Note that constant factors and cache behavior +can be a big deal. If you have a vector that usually only contains a few +elements (but could contain many), for example, it's much better to use +SmallVector than vector +. Doing so avoids (relatively) expensive malloc/free calls, which dwarf the +cost of adding the elements to the container.

+ +
+ + +
+ Sequential Containers (std::vector, std::list, etc) +
+ +
+There are a variety of sequential containers available for you, based on your +needs. Pick the first in this section that will do what you want. +
+ + +
+ Fixed Size Arrays +
+ +
+

Fixed size arrays are very simple and very fast. They are good if you know +exactly how many elements you have, or you have a (low) upper bound on how many +you have.

+
+ + +
+ Heap Allocated Arrays +
+ +
+

Heap allocated arrays (new[] + delete[]) are also simple. They are good if +the number of elements is variable, if you know how many elements you will need +before the array is allocated, and if the array is usually large (if not, +consider a SmallVector). The cost of a heap +allocated array is the cost of the new/delete (aka malloc/free). Also note that +if you are allocating an array of a type with a constructor, the constructor and +destructors will be run for every element in the array (re-sizable vectors only +construct those elements actually used).

+
+ + +
+ "llvm/ADT/SmallVector.h" +
+ +
+

SmallVector<Type, N> is a simple class that looks and smells +just like vector<Type>: +it supports efficient iteration, lays out elements in memory order (so you can +do pointer arithmetic between elements), supports efficient push_back/pop_back +operations, supports efficient random access to its elements, etc.

+ +

The advantage of SmallVector is that it allocates space for +some number of elements (N) in the object itself. Because of this, if +the SmallVector is dynamically smaller than N, no malloc is performed. This can +be a big win in cases where the malloc/free call is far more expensive than the +code that fiddles around with the elements.

+ +

This is good for vectors that are "usually small" (e.g. the number of +predecessors/successors of a block is usually less than 8). On the other hand, +this makes the size of the SmallVector itself large, so you don't want to +allocate lots of them (doing so will waste a lot of space). As such, +SmallVectors are most useful when on the stack.

+ +

SmallVector also provides a nice portable and efficient replacement for +alloca.

+ +
+ + +
+ <vector> +
+ +
+

+std::vector is well loved and respected. It is useful when SmallVector isn't: +when the size of the vector is often large (thus the small optimization will +rarely be a benefit) or if you will be allocating many instances of the vector +itself (which would waste space for elements that aren't in the container). +vector is also useful when interfacing with code that expects vectors :). +

+ +

One worthwhile note about std::vector: avoid code like this:

+ +
+
+for ( ... ) {
+   std::vector<foo> V;
+   use V;
+}
+
+
+ +

Instead, write this as:

+ +
+
+std::vector<foo> V;
+for ( ... ) {
+   use V;
+   V.clear();
+}
+
+
+ +

Doing so will save (at least) one heap allocation and free per iteration of +the loop.

+ +
+ + +
+ <deque> +
+ +
+

std::deque is, in some senses, a generalized version of std::vector. Like +std::vector, it provides constant time random access and other similar +properties, but it also provides efficient access to the front of the list. It +does not guarantee continuity of elements within memory.

+ +

In exchange for this extra flexibility, std::deque has significantly higher +constant factor costs than std::vector. If possible, use std::vector or +something cheaper.

+
+ + +
+ <list> +
+ +
+

std::list is an extremely inefficient class that is rarely useful. +It performs a heap allocation for every element inserted into it, thus having an +extremely high constant factor, particularly for small data types. std::list +also only supports bidirectional iteration, not random access iteration.

+ +

In exchange for this high cost, std::list supports efficient access to both +ends of the list (like std::deque, but unlike std::vector or SmallVector). In +addition, the iterator invalidation characteristics of std::list are stronger +than that of a vector class: inserting or removing an element into the list does +not invalidate iterator or pointers to other elements in the list.

+
+ + +
+ llvm/ADT/ilist.h +
+ +
+

ilist<T> implements an 'intrusive' doubly-linked list. It is +intrusive, because it requires the element to store and provide access to the +prev/next pointers for the list.

+ +

ilist has the same drawbacks as std::list, and additionally +requires an ilist_traits implementation for the element type, but it +provides some novel characteristics. In particular, it can efficiently store +polymorphic objects, the traits class is informed when an element is inserted or +removed from the list, and ilists are guaranteed to support a +constant-time splice operation.

+ +

These properties are exactly what we want for things like +Instructions and basic blocks, which is why these are implemented with +ilists.

+ +Related classes of interest are explained in the following subsections: + +
+ + +
+ ilist_traits +
+ +
+

ilist_traits<T> is ilist<T>'s customization +mechanism. iplist<T> (and consequently ilist<T>) +publicly derive from this traits class.

+
+ + +
+ iplist +
+ +
+

iplist<T> is ilist<T>'s base and as such +supports a slightly narrower interface. Notably, inserters from +T& are absent.

+ +

ilist_traits<T> is a public base of this class and can be +used for a wide variety of customizations.

+
+ + +
+ llvm/ADT/ilist_node.h +
+ +
+

ilist_node<T> implements a the forward and backward links +that are expected by the ilist<T> (and analogous containers) +in the default manner.

+ +

ilist_node<T>s are meant to be embedded in the node type +T, usually T publicly derives from +ilist_node<T>.

+
+ + +
+ Sentinels +
+ +
+

ilists have another specialty that must be considered. To be a good +citizen in the C++ ecosystem, it needs to support the standard container +operations, such as begin and end iterators, etc. Also, the +operator-- must work correctly on the end iterator in the +case of non-empty ilists.

+ +

The only sensible solution to this problem is to allocate a so-called +sentinel along with the intrusive list, which serves as the end +iterator, providing the back-link to the last element. However conforming to the +C++ convention it is illegal to operator++ beyond the sentinel and it +also must not be dereferenced.

+ +

These constraints allow for some implementation freedom to the ilist +how to allocate and store the sentinel. The corresponding policy is dictated +by ilist_traits<T>. By default a T gets heap-allocated +whenever the need for a sentinel arises.

+ +

While the default policy is sufficient in most cases, it may break down when +T does not provide a default constructor. Also, in the case of many +instances of ilists, the memory overhead of the associated sentinels +is wasted. To alleviate the situation with numerous and voluminous +T-sentinels, sometimes a trick is employed, leading to ghostly +sentinels.

+ +

Ghostly sentinels are obtained by specially-crafted ilist_traits<T> +which superpose the sentinel with the ilist instance in memory. Pointer +arithmetic is used to obtain the sentinel, which is relative to the +ilist's this pointer. The ilist is augmented by an +extra pointer, which serves as the back-link of the sentinel. This is the only +field in the ghostly sentinel which can be legally accessed.

+
+ + +
+ Other Sequential Container options +
+ +
+

Other STL containers are available, such as std::string.

+ +

There are also various STL adapter classes such as std::queue, +std::priority_queue, std::stack, etc. These provide simplified access to an +underlying container but don't affect the cost of the container itself.

+ +
+ + + +
+ Set-Like Containers (std::set, SmallSet, SetVector, etc) +
+ +
+ +

Set-like containers are useful when you need to canonicalize multiple values +into a single representation. There are several different choices for how to do +this, providing various trade-offs.

+ +
+ + + +
+ A sorted 'vector' +
+ +
+ +

If you intend to insert a lot of elements, then do a lot of queries, a +great approach is to use a vector (or other sequential container) with +std::sort+std::unique to remove duplicates. This approach works really well if +your usage pattern has these two distinct phases (insert then query), and can be +coupled with a good choice of sequential container. +

+ +

+This combination provides the several nice properties: the result data is +contiguous in memory (good for cache locality), has few allocations, is easy to +address (iterators in the final vector are just indices or pointers), and can be +efficiently queried with a standard binary or radix search.

+ +
+ + +
+ "llvm/ADT/SmallSet.h" +
+ +
+ +

If you have a set-like data structure that is usually small and whose elements +are reasonably small, a SmallSet<Type, N> is a good choice. This set +has space for N elements in place (thus, if the set is dynamically smaller than +N, no malloc traffic is required) and accesses them with a simple linear search. +When the set grows beyond 'N' elements, it allocates a more expensive representation that +guarantees efficient access (for most types, it falls back to std::set, but for +pointers it uses something far better, SmallPtrSet).

+ +

The magic of this class is that it handles small sets extremely efficiently, +but gracefully handles extremely large sets without loss of efficiency. The +drawback is that the interface is quite small: it supports insertion, queries +and erasing, but does not support iteration.

+ +
+ + +
+ "llvm/ADT/SmallPtrSet.h" +
+ +
+ +

SmallPtrSet has all the advantages of SmallSet (and a SmallSet of pointers is +transparently implemented with a SmallPtrSet), but also supports iterators. If +more than 'N' insertions are performed, a single quadratically +probed hash table is allocated and grows as needed, providing extremely +efficient access (constant time insertion/deleting/queries with low constant +factors) and is very stingy with malloc traffic.

+ +

Note that, unlike std::set, the iterators of SmallPtrSet are invalidated +whenever an insertion occurs. Also, the values visited by the iterators are not +visited in sorted order.

+ +
+ + +
+ "llvm/ADT/DenseSet.h" +
+ +
+ +

+DenseSet is a simple quadratically probed hash table. It excels at supporting +small values: it uses a single allocation to hold all of the pairs that +are currently inserted in the set. DenseSet is a great way to unique small +values that are not simple pointers (use SmallPtrSet for pointers). Note that DenseSet has +the same requirements for the value type that DenseMap has. +

+ +
+ + +
+ "llvm/ADT/FoldingSet.h" +
+ +
+ +

+FoldingSet is an aggregate class that is really good at uniquing +expensive-to-create or polymorphic objects. It is a combination of a chained +hash table with intrusive links (uniqued objects are required to inherit from +FoldingSetNode) that uses SmallVector as part of +its ID process.

+ +

Consider a case where you want to implement a "getOrCreateFoo" method for +a complex object (for example, a node in the code generator). The client has a +description of *what* it wants to generate (it knows the opcode and all the +operands), but we don't want to 'new' a node, then try inserting it into a set +only to find out it already exists, at which point we would have to delete it +and return the node that already exists. +

+ +

To support this style of client, FoldingSet perform a query with a +FoldingSetNodeID (which wraps SmallVector) that can be used to describe the +element that we want to query for. The query either returns the element +matching the ID or it returns an opaque ID that indicates where insertion should +take place. Construction of the ID usually does not require heap traffic.

+ +

Because FoldingSet uses intrusive links, it can support polymorphic objects +in the set (for example, you can have SDNode instances mixed with LoadSDNodes). +Because the elements are individually allocated, pointers to the elements are +stable: inserting or removing elements does not invalidate any pointers to other +elements. +

+ +
+ + +
+ <set> +
+ +
+ +

std::set is a reasonable all-around set class, which is decent at +many things but great at nothing. std::set allocates memory for each element +inserted (thus it is very malloc intensive) and typically stores three pointers +per element in the set (thus adding a large amount of per-element space +overhead). It offers guaranteed log(n) performance, which is not particularly +fast from a complexity standpoint (particularly if the elements of the set are +expensive to compare, like strings), and has extremely high constant factors for +lookup, insertion and removal.

+ +

The advantages of std::set are that its iterators are stable (deleting or +inserting an element from the set does not affect iterators or pointers to other +elements) and that iteration over the set is guaranteed to be in sorted order. +If the elements in the set are large, then the relative overhead of the pointers +and malloc traffic is not a big deal, but if the elements of the set are small, +std::set is almost never a good choice.

+ +
+ + +
+ "llvm/ADT/SetVector.h" +
+ +
+

LLVM's SetVector<Type> is an adapter class that combines your choice of +a set-like container along with a Sequential +Container. The important property +that this provides is efficient insertion with uniquing (duplicate elements are +ignored) with iteration support. It implements this by inserting elements into +both a set-like container and the sequential container, using the set-like +container for uniquing and the sequential container for iteration. +

+ +

The difference between SetVector and other sets is that the order of +iteration is guaranteed to match the order of insertion into the SetVector. +This property is really important for things like sets of pointers. Because +pointer values are non-deterministic (e.g. vary across runs of the program on +different machines), iterating over the pointers in the set will +not be in a well-defined order.

+ +

+The drawback of SetVector is that it requires twice as much space as a normal +set and has the sum of constant factors from the set-like container and the +sequential container that it uses. Use it *only* if you need to iterate over +the elements in a deterministic order. SetVector is also expensive to delete +elements out of (linear time), unless you use it's "pop_back" method, which is +faster. +

+ +

SetVector is an adapter class that defaults to using std::vector and std::set +for the underlying containers, so it is quite expensive. However, +"llvm/ADT/SetVector.h" also provides a SmallSetVector class, which +defaults to using a SmallVector and SmallSet of a specified size. If you use +this, and if your sets are dynamically smaller than N, you will save a lot of +heap traffic.

+ +
+ + +
+ "llvm/ADT/UniqueVector.h" +
+ +
+ +

+UniqueVector is similar to SetVector, but it +retains a unique ID for each element inserted into the set. It internally +contains a map and a vector, and it assigns a unique ID for each value inserted +into the set.

+ +

UniqueVector is very expensive: its cost is the sum of the cost of +maintaining both the map and vector, it has high complexity, high constant +factors, and produces a lot of malloc traffic. It should be avoided.

+ +
+ + + +
+ Other Set-Like Container Options +
+ +
+ +

+The STL provides several other options, such as std::multiset and the various +"hash_set" like containers (whether from C++ TR1 or from the SGI library). We +never use hash_set and unordered_set because they are generally very expensive +(each insertion requires a malloc) and very non-portable. +

+ +

std::multiset is useful if you're not interested in elimination of +duplicates, but has all the drawbacks of std::set. A sorted vector (where you +don't delete duplicate entries) or some other approach is almost always +better.

+ +
+ + +
+ Map-Like Containers (std::map, DenseMap, etc) +
+ +
+Map-like containers are useful when you want to associate data to a key. As +usual, there are a lot of different ways to do this. :) +
+ + +
+ A sorted 'vector' +
+ +
+ +

+If your usage pattern follows a strict insert-then-query approach, you can +trivially use the same approach as sorted vectors +for set-like containers. The only difference is that your query function +(which uses std::lower_bound to get efficient log(n) lookup) should only compare +the key, not both the key and value. This yields the same advantages as sorted +vectors for sets. +

+
+ + +
+ "llvm/ADT/StringMap.h" +
+ +
+ +

+Strings are commonly used as keys in maps, and they are difficult to support +efficiently: they are variable length, inefficient to hash and compare when +long, expensive to copy, etc. StringMap is a specialized container designed to +cope with these issues. It supports mapping an arbitrary range of bytes to an +arbitrary other object.

+ +

The StringMap implementation uses a quadratically-probed hash table, where +the buckets store a pointer to the heap allocated entries (and some other +stuff). The entries in the map must be heap allocated because the strings are +variable length. The string data (key) and the element object (value) are +stored in the same allocation with the string data immediately after the element +object. This container guarantees the "(char*)(&Value+1)" points +to the key string for a value.

+ +

The StringMap is very fast for several reasons: quadratic probing is very +cache efficient for lookups, the hash value of strings in buckets is not +recomputed when lookup up an element, StringMap rarely has to touch the +memory for unrelated objects when looking up a value (even when hash collisions +happen), hash table growth does not recompute the hash values for strings +already in the table, and each pair in the map is store in a single allocation +(the string data is stored in the same allocation as the Value of a pair).

+ +

StringMap also provides query methods that take byte ranges, so it only ever +copies a string if a value is inserted into the table.

+
+ + +
+ "llvm/ADT/IndexedMap.h" +
+ +
+

+IndexedMap is a specialized container for mapping small dense integers (or +values that can be mapped to small dense integers) to some other type. It is +internally implemented as a vector with a mapping function that maps the keys to +the dense integer range. +

+ +

+This is useful for cases like virtual registers in the LLVM code generator: they +have a dense mapping that is offset by a compile-time constant (the first +virtual register ID).

+ +
+ + +
+ "llvm/ADT/DenseMap.h" +
+ +
+ +

+DenseMap is a simple quadratically probed hash table. It excels at supporting +small keys and values: it uses a single allocation to hold all of the pairs that +are currently inserted in the map. DenseMap is a great way to map pointers to +pointers, or map other small types to each other. +

+ +

+There are several aspects of DenseMap that you should be aware of, however. The +iterators in a densemap are invalidated whenever an insertion occurs, unlike +map. Also, because DenseMap allocates space for a large number of key/value +pairs (it starts with 64 by default), it will waste a lot of space if your keys +or values are large. Finally, you must implement a partial specialization of +DenseMapInfo for the key that you want, if it isn't already supported. This +is required to tell DenseMap about two special marker values (which can never be +inserted into the map) that it needs internally.

+ +
+ + +
+ "llvm/ADT/ValueMap.h" +
+ +
+ +

+ValueMap is a wrapper around a DenseMap mapping +Value*s (or subclasses) to another type. When a Value is deleted or RAUW'ed, +ValueMap will update itself so the new version of the key is mapped to the same +value, just as if the key were a WeakVH. You can configure exactly how this +happens, and what else happens on these two events, by passing +a Config parameter to the ValueMap template.

+ +
+ + +
+ <map> +
+ +
+ +

+std::map has similar characteristics to std::set: it uses +a single allocation per pair inserted into the map, it offers log(n) lookup with +an extremely large constant factor, imposes a space penalty of 3 pointers per +pair in the map, etc.

+ +

std::map is most useful when your keys or values are very large, if you need +to iterate over the collection in sorted order, or if you need stable iterators +into the map (i.e. they don't get invalidated if an insertion or deletion of +another element takes place).

+ +
+ + +
+ Other Map-Like Container Options +
+ +
+ +

+The STL provides several other options, such as std::multimap and the various +"hash_map" like containers (whether from C++ TR1 or from the SGI library). We +never use hash_set and unordered_set because they are generally very expensive +(each insertion requires a malloc) and very non-portable.

+ +

std::multimap is useful if you want to map a key to multiple values, but has +all the drawbacks of std::map. A sorted vector or some other approach is almost +always better.

+ +
+ + +
+ String-like containers +
+ +
+ +

+TODO: const char* vs stringref vs smallstring vs std::string. Describe twine, +xref to #string_apis. +

+ +
+ + +
+ Bit storage containers (BitVector, SparseBitVector) +
+ +
+

Unlike the other containers, there are only two bit storage containers, and +choosing when to use each is relatively straightforward.

+ +

One additional option is +std::vector<bool>: we discourage its use for two reasons 1) the +implementation in many common compilers (e.g. commonly available versions of +GCC) is extremely inefficient and 2) the C++ standards committee is likely to +deprecate this container and/or change it significantly somehow. In any case, +please don't use it.

+
+ + +
+ BitVector +
+ +
+

The BitVector container provides a dynamic size set of bits for manipulation. +It supports individual bit setting/testing, as well as set operations. The set +operations take time O(size of bitvector), but operations are performed one word +at a time, instead of one bit at a time. This makes the BitVector very fast for +set operations compared to other containers. Use the BitVector when you expect +the number of set bits to be high (IE a dense set). +

+
+ + +
+ SmallBitVector +
+ +
+

The SmallBitVector container provides the same interface as BitVector, but +it is optimized for the case where only a small number of bits, less than +25 or so, are needed. It also transparently supports larger bit counts, but +slightly less efficiently than a plain BitVector, so SmallBitVector should +only be used when larger counts are rare. +

+ +

+At this time, SmallBitVector does not support set operations (and, or, xor), +and its operator[] does not provide an assignable lvalue. +

+
+ + +
+ SparseBitVector +
+ +
+

The SparseBitVector container is much like BitVector, with one major +difference: Only the bits that are set, are stored. This makes the +SparseBitVector much more space efficient than BitVector when the set is sparse, +as well as making set operations O(number of set bits) instead of O(size of +universe). The downside to the SparseBitVector is that setting and testing of random bits is O(N), and on large SparseBitVectors, this can be slower than BitVector. In our implementation, setting or testing bits in sorted order +(either forwards or reverse) is O(1) worst case. Testing and setting bits within 128 bits (depends on size) of the current bit is also O(1). As a general statement, testing/setting bits in a SparseBitVector is O(distance away from last set bit). +

+
+ + +
+ Helpful Hints for Common Operations +
+ + +
+ +

This section describes how to perform some very simple transformations of +LLVM code. This is meant to give examples of common idioms used, showing the +practical side of LLVM transformations.

Because this is a "how-to" section, +you should also read about the main classes that you will be working with. The +Core LLVM Class Hierarchy Reference contains details +and descriptions of the main classes that you should know about.

+ +
+ + + +
+ Basic Inspection and Traversal Routines +
+ +
+ +

The LLVM compiler infrastructure have many different data structures that may +be traversed. Following the example of the C++ standard template library, the +techniques used to traverse these various data structures are all basically the +same. For a enumerable sequence of values, the XXXbegin() function (or +method) returns an iterator to the start of the sequence, the XXXend() +function returns an iterator pointing to one past the last valid element of the +sequence, and there is some XXXiterator data type that is common +between the two operations.

+ +

Because the pattern for iteration is common across many different aspects of +the program representation, the standard template library algorithms may be used +on them, and it is easier to remember how to iterate. First we show a few common +examples of the data structures that need to be traversed. Other data +structures are traversed in very similar ways.

+ +
+ + +
+ Iterating over the BasicBlocks in a Function +
+ +
+ +

It's quite common to have a Function instance that you'd like to +transform in some way; in particular, you'd like to manipulate its +BasicBlocks. To facilitate this, you'll need to iterate over all of +the BasicBlocks that constitute the Function. The following is +an example that prints the name of a BasicBlock and the number of +Instructions it contains:

+ +
+
+// func is a pointer to a Function instance
+for (Function::iterator i = func->begin(), e = func->end(); i != e; ++i)
+  // Print out the name of the basic block if it has one, and then the
+  // number of instructions that it contains
+  errs() << "Basic block (name=" << i->getName() << ") has "
+             << i->size() << " instructions.\n";
+
+
+ +

Note that i can be used as if it were a pointer for the purposes of +invoking member functions of the Instruction class. This is +because the indirection operator is overloaded for the iterator +classes. In the above code, the expression i->size() is +exactly equivalent to (*i).size() just like you'd expect.

+ +
+ + +
+ Iterating over the Instructions in a BasicBlock +
+ +
+ +

Just like when dealing with BasicBlocks in Functions, it's +easy to iterate over the individual instructions that make up +BasicBlocks. Here's a code snippet that prints out each instruction in +a BasicBlock:

+ +
+
+// blk is a pointer to a BasicBlock instance
+for (BasicBlock::iterator i = blk->begin(), e = blk->end(); i != e; ++i)
+   // The next statement works since operator<<(ostream&,...)
+   // is overloaded for Instruction&
+   errs() << *i << "\n";
+
+
+ +

However, this isn't really the best way to print out the contents of a +BasicBlock! Since the ostream operators are overloaded for virtually +anything you'll care about, you could have just invoked the print routine on the +basic block itself: errs() << *blk << "\n";.

+ +
+ + +
+ Iterating over the Instructions in a Function +
+ +
+ +

If you're finding that you commonly iterate over a Function's +BasicBlocks and then that BasicBlock's Instructions, +InstIterator should be used instead. You'll need to include llvm/Support/InstIterator.h, +and then instantiate InstIterators explicitly in your code. Here's a +small example that shows how to dump all instructions in a function to the standard error stream:

+ +

+
+#include "llvm/Support/InstIterator.h"
+
+// F is a pointer to a Function instance
+for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I)
+  errs() << *I << "\n";
+
+
+ +

Easy, isn't it? You can also use InstIterators to fill a +work list with its initial contents. For example, if you wanted to +initialize a work list to contain all instructions in a Function +F, all you would need to do is something like:

+ +
+
+std::set<Instruction*> worklist;
+// or better yet, SmallPtrSet<Instruction*, 64> worklist;
+
+for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I)
+   worklist.insert(&*I);
+
+
+ +

The STL set worklist would now contain all instructions in the +Function pointed to by F.

+ +
+ + +
+ Turning an iterator into a class pointer (and + vice-versa) +
+ +
+ +

Sometimes, it'll be useful to grab a reference (or pointer) to a class +instance when all you've got at hand is an iterator. Well, extracting +a reference or a pointer from an iterator is very straight-forward. +Assuming that i is a BasicBlock::iterator and j +is a BasicBlock::const_iterator:

+ +
+
+Instruction& inst = *i;   // Grab reference to instruction reference
+Instruction* pinst = &*i; // Grab pointer to instruction reference
+const Instruction& inst = *j;
+
+
+ +

However, the iterators you'll be working with in the LLVM framework are +special: they will automatically convert to a ptr-to-instance type whenever they +need to. Instead of dereferencing the iterator and then taking the address of +the result, you can simply assign the iterator to the proper pointer type and +you get the dereference and address-of operation as a result of the assignment +(behind the scenes, this is a result of overloading casting mechanisms). Thus +the last line of the last example,

+ +
+
+Instruction *pinst = &*i;
+
+
+ +

is semantically equivalent to

+ +
+
+Instruction *pinst = i;
+
+
+ +

It's also possible to turn a class pointer into the corresponding iterator, +and this is a constant time operation (very efficient). The following code +snippet illustrates use of the conversion constructors provided by LLVM +iterators. By using these, you can explicitly grab the iterator of something +without actually obtaining it via iteration over some structure:

+ +
+
+void printNextInstruction(Instruction* inst) {
+  BasicBlock::iterator it(inst);
+  ++it; // After this line, it refers to the instruction after *inst
+  if (it != inst->getParent()->end()) errs() << *it << "\n";
+}
+
+
+ +
+ + +
+ Finding call sites: a slightly more complex + example +
+ +
+ +

Say that you're writing a FunctionPass and would like to count all the +locations in the entire module (that is, across every Function) where a +certain function (i.e., some Function*) is already in scope. As you'll +learn later, you may want to use an InstVisitor to accomplish this in a +much more straight-forward manner, but this example will allow us to explore how +you'd do it if you didn't have InstVisitor around. In pseudo-code, this +is what we want to do:

+ +
+
+initialize callCounter to zero
+for each Function f in the Module
+  for each BasicBlock b in f
+    for each Instruction i in b
+      if (i is a CallInst and calls the given function)
+        increment callCounter
+
+
+ +

And the actual code is (remember, because we're writing a +FunctionPass, our FunctionPass-derived class simply has to +override the runOnFunction method):

+ +
+
+Function* targetFunc = ...;
+
+class OurFunctionPass : public FunctionPass {
+  public:
+    OurFunctionPass(): callCounter(0) { }
+
+    virtual runOnFunction(Function& F) {
+      for (Function::iterator b = F.begin(), be = F.end(); b != be; ++b) {
+        for (BasicBlock::iterator i = b->begin(), ie = b->end(); i != ie; ++i) {
+          if (CallInst* callInst = dyn_cast<CallInst>(&*i)) {
+            // We know we've encountered a call instruction, so we
+            // need to determine if it's a call to the
+            // function pointed to by m_func or not.
+            if (callInst->getCalledFunction() == targetFunc)
+              ++callCounter;
+          }
+        }
+      }
+    }
+
+  private:
+    unsigned callCounter;
+};
+
+
+ +
+ + +
+ Treating calls and invokes the same way +
+ +
+ +

You may have noticed that the previous example was a bit oversimplified in +that it did not deal with call sites generated by 'invoke' instructions. In +this, and in other situations, you may find that you want to treat +CallInsts and InvokeInsts the same way, even though their +most-specific common base class is Instruction, which includes lots of +less closely-related things. For these cases, LLVM provides a handy wrapper +class called CallSite. +It is essentially a wrapper around an Instruction pointer, with some +methods that provide functionality common to CallInsts and +InvokeInsts.

+ +

This class has "value semantics": it should be passed by value, not by +reference and it should not be dynamically allocated or deallocated using +operator new or operator delete. It is efficiently copyable, +assignable and constructable, with costs equivalents to that of a bare pointer. +If you look at its definition, it has only a single pointer member.

+ +
+ + +
+ Iterating over def-use & use-def chains +
+ +
+ +

Frequently, we might have an instance of the Value Class and we want to +determine which Users use the Value. The list of all +Users of a particular Value is called a def-use chain. +For example, let's say we have a Function* named F to a +particular function foo. Finding all of the instructions that +use foo is as simple as iterating over the def-use chain +of F:

+ +
+
+Function *F = ...;
+
+for (Value::use_iterator i = F->use_begin(), e = F->use_end(); i != e; ++i)
+  if (Instruction *Inst = dyn_cast<Instruction>(*i)) {
+    errs() << "F is used in instruction:\n";
+    errs() << *Inst << "\n";
+  }
+
+
+ +

Alternately, it's common to have an instance of the User Class and need to know what +Values are used by it. The list of all Values used by a +User is known as a use-def chain. Instances of class +Instruction are common Users, so we might want to iterate over +all of the values that a particular instruction uses (that is, the operands of +the particular Instruction):

+ +
+
+Instruction *pi = ...;
+
+for (User::op_iterator i = pi->op_begin(), e = pi->op_end(); i != e; ++i) {
+  Value *v = *i;
+  // ...
+}
+
+
+ + + +
+ + +
+ Iterating over predecessors & +successors of blocks +
+ +
+ +

Iterating over the predecessors and successors of a block is quite easy +with the routines defined in "llvm/Support/CFG.h". Just use code like +this to iterate over all predecessors of BB:

+ +
+
+#include "llvm/Support/CFG.h"
+BasicBlock *BB = ...;
+
+for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI) {
+  BasicBlock *Pred = *PI;
+  // ...
+}
+
+
+ +

Similarly, to iterate over successors use +succ_iterator/succ_begin/succ_end.

+ +
+ + + +
+ Making simple changes +
+ +
+ +

There are some primitive transformation operations present in the LLVM +infrastructure that are worth knowing about. When performing +transformations, it's fairly common to manipulate the contents of basic +blocks. This section describes some of the common methods for doing so +and gives example code.

+ +
+ + +
+ Creating and inserting new + Instructions +
+ +
+ +

Instantiating Instructions

+ +

Creation of Instructions is straight-forward: simply call the +constructor for the kind of instruction to instantiate and provide the necessary +parameters. For example, an AllocaInst only requires a +(const-ptr-to) Type. Thus:

+ +
+
+AllocaInst* ai = new AllocaInst(Type::Int32Ty);
+
+
+ +

will create an AllocaInst instance that represents the allocation of +one integer in the current stack frame, at run time. Each Instruction +subclass is likely to have varying default parameters which change the semantics +of the instruction, so refer to the doxygen documentation for the subclass of +Instruction that you're interested in instantiating.

+ +

Naming values

+ +

It is very useful to name the values of instructions when you're able to, as +this facilitates the debugging of your transformations. If you end up looking +at generated LLVM machine code, you definitely want to have logical names +associated with the results of instructions! By supplying a value for the +Name (default) parameter of the Instruction constructor, you +associate a logical name with the result of the instruction's execution at +run time. For example, say that I'm writing a transformation that dynamically +allocates space for an integer on the stack, and that integer is going to be +used as some kind of index by some other code. To accomplish this, I place an +AllocaInst at the first point in the first BasicBlock of some +Function, and I'm intending to use it within the same +Function. I might do:

+ +
+
+AllocaInst* pa = new AllocaInst(Type::Int32Ty, 0, "indexLoc");
+
+
+ +

where indexLoc is now the logical name of the instruction's +execution value, which is a pointer to an integer on the run time stack.

+ +

Inserting instructions

+ +

There are essentially two ways to insert an Instruction +into an existing sequence of instructions that form a BasicBlock:

+ +
    +
  • Insertion into an explicit instruction list + +

    Given a BasicBlock* pb, an Instruction* pi within that + BasicBlock, and a newly-created instruction we wish to insert + before *pi, we do the following:

    + +
    +
    +BasicBlock *pb = ...;
+Instruction *pi = ...;
+Instruction *newInst = new Instruction(...);
+
+pb->getInstList().insert(pi, newInst); // Inserts newInst before pi in pb
+
    +
    + +

    Appending to the end of a BasicBlock is so common that + the Instruction class and Instruction-derived + classes provide constructors which take a pointer to a + BasicBlock to be appended to. For example code that + looked like:

    + +
    +
    +BasicBlock *pb = ...;
+Instruction *newInst = new Instruction(...);
+
+pb->getInstList().push_back(newInst); // Appends newInst to pb
+
    +
    + +

    becomes:

    + +
    +
    +BasicBlock *pb = ...;
+Instruction *newInst = new Instruction(..., pb);
+
    +
    + +

    which is much cleaner, especially if you are creating + long instruction streams.

    • + +
  • Insertion into an implicit instruction list + +

    Instruction instances that are already in BasicBlocks + are implicitly associated with an existing instruction list: the instruction + list of the enclosing basic block. Thus, we could have accomplished the same + thing as the above code without being given a BasicBlock by doing: +

    + +
    +
    +Instruction *pi = ...;
+Instruction *newInst = new Instruction(...);
+
+pi->getParent()->getInstList().insert(pi, newInst);
+
    +
    + +

    In fact, this sequence of steps occurs so frequently that the + Instruction class and Instruction-derived classes provide + constructors which take (as a default parameter) a pointer to an + Instruction which the newly-created Instruction should + precede. That is, Instruction constructors are capable of + inserting the newly-created instance into the BasicBlock of a + provided instruction, immediately before that instruction. Using an + Instruction constructor with a insertBefore (default) + parameter, the above code becomes:

    + +
    +
    +Instruction* pi = ...;
+Instruction* newInst = new Instruction(..., pi);
+
    +
    + +

    which is much cleaner, especially if you're creating a lot of + instructions and adding them to BasicBlocks.

    • +
+ +
+ + +
+ Deleting Instructions +
+ +
+ +

Deleting an instruction from an existing sequence of instructions that form a +BasicBlock is very straight-forward. First, +you must have a pointer to the instruction that you wish to delete. Second, you +need to obtain the pointer to that instruction's basic block. You use the +pointer to the basic block to get its list of instructions and then use the +erase function to remove your instruction. For example:

+ +
+
+Instruction *I = .. ;
+I->eraseFromParent();
+
+
+ +
+ + +
+ Replacing an Instruction with another + Value +
+ +
+ +

Replacing individual instructions

+ +

Including "llvm/Transforms/Utils/BasicBlockUtils.h" +permits use of two very useful replace functions: ReplaceInstWithValue +and ReplaceInstWithInst.

+ +

Deleting Instructions

+ +
    +
  • ReplaceInstWithValue + +

    This function replaces all uses of a given instruction with a value, + and then removes the original instruction. The following example + illustrates the replacement of the result of a particular + AllocaInst that allocates memory for a single integer with a null + pointer to an integer.

    + +
    +
    +AllocaInst* instToReplace = ...;
+BasicBlock::iterator ii(instToReplace);
+
+ReplaceInstWithValue(instToReplace->getParent()->getInstList(), ii,
+                     Constant::getNullValue(PointerType::getUnqual(Type::Int32Ty)));
+
    • + +
  • ReplaceInstWithInst + +

    This function replaces a particular instruction with another + instruction, inserting the new instruction into the basic block at the + location where the old instruction was, and replacing any uses of the old + instruction with the new instruction. The following example illustrates + the replacement of one AllocaInst with another.

    + +
    +
    +AllocaInst* instToReplace = ...;
+BasicBlock::iterator ii(instToReplace);
+
+ReplaceInstWithInst(instToReplace->getParent()->getInstList(), ii,
+                    new AllocaInst(Type::Int32Ty, 0, "ptrToReplacedInt"));
+
    • +
+ +

Replacing multiple uses of Users and Values

+ +

You can use Value::replaceAllUsesWith and +User::replaceUsesOfWith to change more than one use at a time. See the +doxygen documentation for the Value Class +and User Class, respectively, for more +information.

+ + + +
+ + +
+ Deleting GlobalVariables +
+ +
+ +

Deleting a global variable from a module is just as easy as deleting an +Instruction. First, you must have a pointer to the global variable that you wish + to delete. You use this pointer to erase it from its parent, the module. + For example:

+ +
+
+GlobalVariable *GV = .. ;
+
+GV->eraseFromParent();
+
+
+ +
+ + +
+ How to Create Types +
+ +
+ +

In generating IR, you may need some complex types. If you know these types +statically, you can use TypeBuilder<...>::get(), defined +in llvm/Support/TypeBuilder.h, to retrieve them. TypeBuilder +has two forms depending on whether you're building types for cross-compilation +or native library use. TypeBuilder<T, true> requires +that T be independent of the host environment, meaning that it's built +out of types from +the llvm::types +namespace and pointers, functions, arrays, etc. built of +those. TypeBuilder<T, false> additionally allows native C types +whose size may depend on the host compiler. For example,

+ +
+
+FunctionType *ft = TypeBuilder<types::i<8>(types::i<32>*), true>::get();
+
+
+ +

is easier to read and write than the equivalent

+ +
+
+std::vector<const Type*> params;
+params.push_back(PointerType::getUnqual(Type::Int32Ty));
+FunctionType *ft = FunctionType::get(Type::Int8Ty, params, false);
+
+
+ +

See the class +comment for more details.

+ +
+ + +
+ Threads and LLVM +
+ + +
+

+This section describes the interaction of the LLVM APIs with multithreading, +both on the part of client applications, and in the JIT, in the hosted +application. +

+ +

+Note that LLVM's support for multithreading is still relatively young. Up +through version 2.5, the execution of threaded hosted applications was +supported, but not threaded client access to the APIs. While this use case is +now supported, clients must adhere to the guidelines specified below to +ensure proper operation in multithreaded mode. +

+ +

+Note that, on Unix-like platforms, LLVM requires the presence of GCC's atomic +intrinsics in order to support threaded operation. If you need a +multhreading-capable LLVM on a platform without a suitably modern system +compiler, consider compiling LLVM and LLVM-GCC in single-threaded mode, and +using the resultant compiler to build a copy of LLVM with multithreading +support. +

+
+ + +
+ Entering and Exiting Multithreaded Mode +
+ +
+ +

+In order to properly protect its internal data structures while avoiding +excessive locking overhead in the single-threaded case, the LLVM must intialize +certain data structures necessary to provide guards around its internals. To do +so, the client program must invoke llvm_start_multithreaded() before +making any concurrent LLVM API calls. To subsequently tear down these +structures, use the llvm_stop_multithreaded() call. You can also use +the llvm_is_multithreaded() call to check the status of multithreaded +mode. +

+ +

+Note that both of these calls must be made in isolation. That is to +say that no other LLVM API calls may be executing at any time during the +execution of llvm_start_multithreaded() or llvm_stop_multithreaded +. It's is the client's responsibility to enforce this isolation. +

+ +

+The return value of llvm_start_multithreaded() indicates the success or +failure of the initialization. Failure typically indicates that your copy of +LLVM was built without multithreading support, typically because GCC atomic +intrinsics were not found in your system compiler. In this case, the LLVM API +will not be safe for concurrent calls. However, it will be safe for +hosting threaded applications in the JIT, though care +must be taken to ensure that side exits and the like do not accidentally +result in concurrent LLVM API calls. +

+
+ + +
+ Ending Execution with llvm_shutdown() +
+ +
+

+When you are done using the LLVM APIs, you should call llvm_shutdown() +to deallocate memory used for internal structures. This will also invoke +llvm_stop_multithreaded() if LLVM is operating in multithreaded mode. +As such, llvm_shutdown() requires the same isolation guarantees as +llvm_stop_multithreaded(). +

+ +

+Note that, if you use scope-based shutdown, you can use the +llvm_shutdown_obj class, which calls llvm_shutdown() in its +destructor. +

+ + +
+ Lazy Initialization with ManagedStatic +
+ +
+

+ManagedStatic is a utility class in LLVM used to implement static +initialization of static resources, such as the global type tables. Before the +invocation of llvm_shutdown(), it implements a simple lazy +initialization scheme. Once llvm_start_multithreaded() returns, +however, it uses double-checked locking to implement thread-safe lazy +initialization. +

+ +

+Note that, because no other threads are allowed to issue LLVM API calls before +llvm_start_multithreaded() returns, it is possible to have +ManagedStatics of llvm::sys::Mutexs. +

+ +

+The llvm_acquire_global_lock() and llvm_release_global_lock +APIs provide access to the global lock used to implement the double-checked +locking for lazy initialization. These should only be used internally to LLVM, +and only if you know what you're doing! +

+
+ + +
+ Achieving Isolation with LLVMContext +
+ +
+

+LLVMContext is an opaque class in the LLVM API which clients can use +to operate multiple, isolated instances of LLVM concurrently within the same +address space. For instance, in a hypothetical compile-server, the compilation +of an individual translation unit is conceptually independent from all the +others, and it would be desirable to be able to compile incoming translation +units concurrently on independent server threads. Fortunately, +LLVMContext exists to enable just this kind of scenario! +

+ +

+Conceptually, LLVMContext provides isolation. Every LLVM entity +(Modules, Values, Types, Constants, etc.) +in LLVM's in-memory IR belongs to an LLVMContext. Entities in +different contexts cannot interact with each other: Modules in +different contexts cannot be linked together, Functions cannot be added +to Modules in different contexts, etc. What this means is that is is +safe to compile on multiple threads simultaneously, as long as no two threads +operate on entities within the same context. +

+ +

+In practice, very few places in the API require the explicit specification of a +LLVMContext, other than the Type creation/lookup APIs. +Because every Type carries a reference to its owning context, most +other entities can determine what context they belong to by looking at their +own Type. If you are adding new entities to LLVM IR, please try to +maintain this interface design. +

+ +

+For clients that do not require the benefits of isolation, LLVM +provides a convenience API getGlobalContext(). This returns a global, +lazily initialized LLVMContext that may be used in situations where +isolation is not a concern. +

+
+ + +
+ Threads and the JIT +
+ +
+

+LLVM's "eager" JIT compiler is safe to use in threaded programs. Multiple +threads can call ExecutionEngine::getPointerToFunction() or +ExecutionEngine::runFunction() concurrently, and multiple threads can +run code output by the JIT concurrently. The user must still ensure that only +one thread accesses IR in a given LLVMContext while another thread +might be modifying it. One way to do that is to always hold the JIT lock while +accessing IR outside the JIT (the JIT modifies the IR by adding +CallbackVHs). Another way is to only +call getPointerToFunction() from the LLVMContext's thread. +

+ +

When the JIT is configured to compile lazily (using +ExecutionEngine::DisableLazyCompilation(false)), there is currently a +race condition in +updating call sites after a function is lazily-jitted. It's still possible to +use the lazy JIT in a threaded program if you ensure that only one thread at a +time can call any particular lazy stub and that the JIT lock guards any IR +access, but we suggest using only the eager JIT in threaded programs. +

+
+ + +
+ Advanced Topics +
+ + +
+

+This section describes some of the advanced or obscure API's that most clients +do not need to be aware of. These API's tend manage the inner workings of the +LLVM system, and only need to be accessed in unusual circumstances. +

+
+ + +
+ LLVM Type Resolution +
+ +
+ +

+The LLVM type system has a very simple goal: allow clients to compare types for +structural equality with a simple pointer comparison (aka a shallow compare). +This goal makes clients much simpler and faster, and is used throughout the LLVM +system. +

+ +

+Unfortunately achieving this goal is not a simple matter. In particular, +recursive types and late resolution of opaque types makes the situation very +difficult to handle. Fortunately, for the most part, our implementation makes +most clients able to be completely unaware of the nasty internal details. The +primary case where clients are exposed to the inner workings of it are when +building a recursive type. In addition to this case, the LLVM bitcode reader, +assembly parser, and linker also have to be aware of the inner workings of this +system. +

+ +

+For our purposes below, we need three concepts. First, an "Opaque Type" is +exactly as defined in the language +reference. Second an "Abstract Type" is any type which includes an +opaque type as part of its type graph (for example "{ opaque, i32 }"). +Third, a concrete type is a type that is not an abstract type (e.g. "{ i32, +float }"). +

+ +
+ + +
+ Basic Recursive Type Construction +
+ +
+ +

+Because the most common question is "how do I build a recursive type with LLVM", +we answer it now and explain it as we go. Here we include enough to cause this +to be emitted to an output .ll file: +

+ +
+
+%mylist = type { %mylist*, i32 }
+
+
+ +

+To build this, use the following LLVM APIs: +

+ +
+
+// Create the initial outer struct
+PATypeHolder StructTy = OpaqueType::get();
+std::vector<const Type*> Elts;
+Elts.push_back(PointerType::getUnqual(StructTy));
+Elts.push_back(Type::Int32Ty);
+StructType *NewSTy = StructType::get(Elts);
+
+// At this point, NewSTy = "{ opaque*, i32 }". Tell VMCore that
+// the struct and the opaque type are actually the same.
+cast<OpaqueType>(StructTy.get())->refineAbstractTypeTo(NewSTy);
+
+// NewSTy is potentially invalidated, but StructTy (a PATypeHolder) is
+// kept up-to-date
+NewSTy = cast<StructType>(StructTy.get());
+
+// Add a name for the type to the module symbol table (optional)
+MyModule->addTypeName("mylist", NewSTy);
+
+
+ +

+This code shows the basic approach used to build recursive types: build a +non-recursive type using 'opaque', then use type unification to close the cycle. +The type unification step is performed by the refineAbstractTypeTo method, which is +described next. After that, we describe the PATypeHolder class. +

+ +
+ + +
+ The refineAbstractTypeTo method +
+ +
+

+The refineAbstractTypeTo method starts the type unification process. +While this method is actually a member of the DerivedType class, it is most +often used on OpaqueType instances. Type unification is actually a recursive +process. After unification, types can become structurally isomorphic to +existing types, and all duplicates are deleted (to preserve pointer equality). +

+ +

+In the example above, the OpaqueType object is definitely deleted. +Additionally, if there is an "{ \2*, i32}" type already created in the system, +the pointer and struct type created are also deleted. Obviously whenever +a type is deleted, any "Type*" pointers in the program are invalidated. As +such, it is safest to avoid having any "Type*" pointers to abstract types +live across a call to refineAbstractTypeTo (note that non-abstract +types can never move or be deleted). To deal with this, the PATypeHolder class is used to maintain a stable +reference to a possibly refined type, and the AbstractTypeUser class is used to update more +complex datastructures. +

+ +
+ + +
+ The PATypeHolder Class +
+ +
+

+PATypeHolder is a form of a "smart pointer" for Type objects. When VMCore +happily goes about nuking types that become isomorphic to existing types, it +automatically updates all PATypeHolder objects to point to the new type. In the +example above, this allows the code to maintain a pointer to the resultant +resolved recursive type, even though the Type*'s are potentially invalidated. +

+ +

+PATypeHolder is an extremely light-weight object that uses a lazy union-find +implementation to update pointers. For example the pointer from a Value to its +Type is maintained by PATypeHolder objects. +

+ +
+ + +
+ The AbstractTypeUser Class +
+ +
+ +

+Some data structures need more to perform more complex updates when types get +resolved. To support this, a class can derive from the AbstractTypeUser class. +This class +allows it to get callbacks when certain types are resolved. To register to get +callbacks for a particular type, the DerivedType::{add/remove}AbstractTypeUser +methods can be called on a type. Note that these methods only work for + abstract types. Concrete types (those that do not include any opaque +objects) can never be refined. +

+
+ + + +
+ The ValueSymbolTable and + TypeSymbolTable classes +
+ +
+

The +ValueSymbolTable class provides a symbol table that the Function and +Module classes use for naming value definitions. The symbol table +can provide a name for any Value. +The +TypeSymbolTable class is used by the Module class to store +names for types.

+ +

Note that the SymbolTable class should not be directly accessed +by most clients. It should only be used when iteration over the symbol table +names themselves are required, which is very special purpose. Note that not +all LLVM +Values have names, and those without names (i.e. they have +an empty name) do not exist in the symbol table. +

+ +

These symbol tables support iteration over the values/types in the symbol +table with begin/end/iterator and supports querying to see if a +specific name is in the symbol table (with lookup). The +ValueSymbolTable class exposes no public mutator methods, instead, +simply call setName on a value, which will autoinsert it into the +appropriate symbol table. For types, use the Module::addTypeName method to +insert entries into the symbol table.

+ +
+ + + + +
+ The User and owned Use classes' memory layout +
+ +
+

The +User class provides a basis for expressing the ownership of User +towards other +Values. The +Use helper class is employed to do the bookkeeping and to facilitate O(1) +addition and removal.

+ + +
+ Interaction and relationship between User and Use objects +
+ +
+

+A subclass of User can choose between incorporating its Use objects +or refer to them out-of-line by means of a pointer. A mixed variant +(some Uses inline others hung off) is impractical and breaks the invariant +that the Use objects belonging to the same User form a contiguous array. +

+
+ +

+We have 2 different layouts in the User (sub)classes: +

    +

  • Layout a) +The Use object(s) are inside (resp. at fixed offset) of the User +object and there are a fixed number of them.

    + +

  • Layout b) +The Use object(s) are referenced by a pointer to an +array from the User object and there may be a variable +number of them.

    +
+

+As of v2.4 each layout still possesses a direct pointer to the +start of the array of Uses. Though not mandatory for layout a), +we stick to this redundancy for the sake of simplicity. +The User object also stores the number of Use objects it +has. (Theoretically this information can also be calculated +given the scheme presented below.)

+

+Special forms of allocation operators (operator new) +enforce the following memory layouts:

+ +
    +

  • Layout a) is modelled by prepending the User object by the Use[] array.

    + +
    +...---.---.---.---.-------...
+  | P | P | P | P | User
+'''---'---'---'---'-------'''
+
    + +

  • Layout b) is modelled by pointing at the Use[] array.

    +
    +.-------...
+| User
+'-------'''
+    |
+    v
+    .---.---.---.---...
+    | P | P | P | P |
+    '---'---'---'---'''
+
    +
+(In the above figures 'P' stands for the Use** that + is stored in each Use object in the member Use::Prev) + + +
+ The waymarking algorithm +
+ +
+

+Since the Use objects are deprived of the direct (back)pointer to +their User objects, there must be a fast and exact method to +recover it. This is accomplished by the following scheme:

+
+ +A bit-encoding in the 2 LSBits (least significant bits) of the Use::Prev allows to find the +start of the User object: +
    +
  • 00 —> binary digit 0
    • +
  • 01 —> binary digit 1
    • +
  • 10 —> stop and calculate (s)
    • +
  • 11 —> full stop (S)
    • +
+

+Given a Use*, all we have to do is to walk till we get +a stop and we either have a User immediately behind or +we have to walk to the next stop picking up digits +and calculating the offset:

+
+.---.---.---.---.---.---.---.---.---.---.---.---.---.---.---.---.----------------
+| 1 | s | 1 | 0 | 1 | 0 | s | 1 | 1 | 0 | s | 1 | 1 | s | 1 | S | User (or User*)
+'---'---'---'---'---'---'---'---'---'---'---'---'---'---'---'---'----------------
+    |+15                |+10            |+6         |+3     |+1
+    |                   |               |           |       |__>
+    |                   |               |           |__________>
+    |                   |               |______________________>
+    |                   |______________________________________>
+    |__________________________________________________________>
+
+

+Only the significant number of bits need to be stored between the +stops, so that the worst case is 20 memory accesses when there are +1000 Use objects associated with a User.

+ + +
+ Reference implementation +
+ +
+

+The following literate Haskell fragment demonstrates the concept:

+
+ +
+
+> import Test.QuickCheck
+> 
+> digits :: Int -> [Char] -> [Char]
+> digits 0 acc = '0' : acc
+> digits 1 acc = '1' : acc
+> digits n acc = digits (n `div` 2) $ digits (n `mod` 2) acc
+> 
+> dist :: Int -> [Char] -> [Char]
+> dist 0 [] = ['S']
+> dist 0 acc = acc
+> dist 1 acc = let r = dist 0 acc in 's' : digits (length r) r
+> dist n acc = dist (n - 1) $ dist 1 acc
+> 
+> takeLast n ss = reverse $ take n $ reverse ss
+> 
+> test = takeLast 40 $ dist 20 []
+> 
+
+
+

+Printing <test> gives: "1s100000s11010s10100s1111s1010s110s11s1S"

+

+The reverse algorithm computes the length of the string just by examining +a certain prefix:

+ +
+
+> pref :: [Char] -> Int
+> pref "S" = 1
+> pref ('s':'1':rest) = decode 2 1 rest
+> pref (_:rest) = 1 + pref rest
+> 
+> decode walk acc ('0':rest) = decode (walk + 1) (acc * 2) rest
+> decode walk acc ('1':rest) = decode (walk + 1) (acc * 2 + 1) rest
+> decode walk acc _ = walk + acc
+> 
+
+
+

+Now, as expected, printing <pref test> gives 40.

+

+We can quickCheck this with following property:

+ +
+
+> testcase = dist 2000 []
+> testcaseLength = length testcase
+> 
+> identityProp n = n > 0 && n <= testcaseLength ==> length arr == pref arr
+>     where arr = takeLast n testcase
+> 
+
+
+

+As expected <quickCheck identityProp> gives:

+ +
+*Main> quickCheck identityProp
+OK, passed 100 tests.
+
+

+Let's be a bit more exhaustive:

+ +
+
+> 
+> deepCheck p = check (defaultConfig { configMaxTest = 500 }) p
+> 
+
+
+

+And here is the result of <deepCheck identityProp>:

+ +
+*Main> deepCheck identityProp
+OK, passed 500 tests.
+
+ + +
+ Tagging considerations +
+ +

+To maintain the invariant that the 2 LSBits of each Use** in Use +never change after being set up, setters of Use::Prev must re-tag the +new Use** on every modification. Accordingly getters must strip the +tag bits.

+

+For layout b) instead of the User we find a pointer (User* with LSBit set). +Following this pointer brings us to the User. A portable trick ensures +that the first bytes of User (if interpreted as a pointer) never has +the LSBit set. (Portability is relying on the fact that all known compilers place the +vptr in the first word of the instances.)

+ +
+ + +
+ The Core LLVM Class Hierarchy Reference +
+ + +
+

#include "llvm/Type.h" +
doxygen info: Type Class

+ +

The Core LLVM classes are the primary means of representing the program +being inspected or transformed. The core LLVM classes are defined in +header files in the include/llvm/ directory, and implemented in +the lib/VMCore directory.

+ +
+ + +
+ The Type class and Derived Types +
+ +
+ +

Type is a superclass of all type classes. Every Value has + a Type. Type cannot be instantiated directly but only + through its subclasses. Certain primitive types (VoidType, + LabelType, FloatType and DoubleType) have hidden + subclasses. They are hidden because they offer no useful functionality beyond + what the Type class offers except to distinguish themselves from + other subclasses of Type.

+

All other types are subclasses of DerivedType. Types can be + named, but this is not a requirement. There exists exactly + one instance of a given shape at any one time. This allows type equality to + be performed with address equality of the Type Instance. That is, given two + Type* values, the types are identical if the pointers are identical. +

+
+ + +
+ Important Public Methods +
+ +
+ +
    +
  • bool isIntegerTy() const: Returns true for any integer type.
    • + +
  • bool isFloatingPointTy(): Return true if this is one of the five + floating point types.
    • + +
  • bool isAbstract(): Return true if the type is abstract (contains + an OpaqueType anywhere in its definition).
    • + +
  • bool isSized(): Return true if the type has known size. Things + that don't have a size are abstract types, labels and void.
    • + +
+
+ + +
+ Important Derived Types +
+
+
+
IntegerType
+
Subclass of DerivedType that represents integer types of any bit width. + Any bit width between IntegerType::MIN_INT_BITS (1) and + IntegerType::MAX_INT_BITS (~8 million) can be represented. +
    +
  • static const IntegerType* get(unsigned NumBits): get an integer + type of a specific bit width.
    • +
  • unsigned getBitWidth() const: Get the bit width of an integer + type.
    • +
+
+
SequentialType
+
This is subclassed by ArrayType and PointerType +
    +
  • const Type * getElementType() const: Returns the type of each + of the elements in the sequential type.
    • +
+
+
ArrayType
+
This is a subclass of SequentialType and defines the interface for array + types. +
    +
  • unsigned getNumElements() const: Returns the number of + elements in the array.
    • +
+
+
PointerType
+
Subclass of SequentialType for pointer types.
+
VectorType
+
Subclass of SequentialType for vector types. A + vector type is similar to an ArrayType but is distinguished because it is + a first class type whereas ArrayType is not. Vector types are used for + vector operations and are usually small vectors of of an integer or floating + point type.
+
StructType
+
Subclass of DerivedTypes for struct types.
+
FunctionType
+
Subclass of DerivedTypes for function types. +
    +
  • bool isVarArg() const: Returns true if its a vararg + function
    • +
  • const Type * getReturnType() const: Returns the + return type of the function.
    • +
  • const Type * getParamType (unsigned i): Returns + the type of the ith parameter.
    • +
  • const unsigned getNumParams() const: Returns the + number of formal parameters.
    • +
+
+
OpaqueType
+
Sublcass of DerivedType for abstract types. This class + defines no content and is used as a placeholder for some other type. Note + that OpaqueType is used (temporarily) during type resolution for forward + references of types. Once the referenced type is resolved, the OpaqueType + is replaced with the actual type. OpaqueType can also be used for data + abstraction. At link time opaque types can be resolved to actual types + of the same name.
+
+
+ + + + +
+ The Module class +
+ +
+ +

#include "llvm/Module.h"
doxygen info: +Module Class

+ +

The Module class represents the top level structure present in LLVM +programs. An LLVM module is effectively either a translation unit of the +original program or a combination of several translation units merged by the +linker. The Module class keeps track of a list of Functions, a list of GlobalVariables, and a SymbolTable. Additionally, it contains a few +helpful member functions that try to make common operations easy.

+ +
+ + +
+ Important Public Members of the Module class +
+ +
+ +
    +
  • Module::Module(std::string name = "")
    • +
+ +

Constructing a Module is easy. You can optionally +provide a name for it (probably based on the name of the translation unit).

+ +
    +
  • Module::iterator - Typedef for function list iterator
    + Module::const_iterator - Typedef for const_iterator.
    + + begin(), end() + size(), empty() + +

    These are forwarding methods that make it easy to access the contents of + a Module object's Function + list.

    • + +
  • Module::FunctionListType &getFunctionList() + +

    Returns the list of Functions. This is + necessary to use when you need to update the list or perform a complex + action that doesn't have a forwarding method.

    + +

    • +
+ +
+ +
    +
  • Module::global_iterator - Typedef for global variable list iterator
    + + Module::const_global_iterator - Typedef for const_iterator.
    + + global_begin(), global_end() + global_size(), global_empty() + +

    These are forwarding methods that make it easy to access the contents of + a Module object's GlobalVariable list.

    • + +
  • Module::GlobalListType &getGlobalList() + +

    Returns the list of GlobalVariables. This is necessary to + use when you need to update the list or perform a complex action that + doesn't have a forwarding method.

    + +

    • +
+ +
+ + + +
+ +
    +
  • Function *getFunction(const std::string + &Name, const FunctionType *Ty) + +

    Look up the specified function in the Module SymbolTable. If it does not exist, return + null.

    • + +
  • Function *getOrInsertFunction(const + std::string &Name, const FunctionType *T) + +

    Look up the specified function in the Module SymbolTable. If it does not exist, add an + external declaration for the function and return it.

    • + +
  • std::string getTypeName(const Type *Ty) + +

    If there is at least one entry in the SymbolTable for the specified Type, return it. Otherwise return the empty + string.

    • + +
  • bool addTypeName(const std::string &Name, const Type *Ty) + +

    Insert an entry in the SymbolTable + mapping Name to Ty. If there is already an entry for this + name, true is returned and the SymbolTable is not modified.

    • +
+ +
+ + + +
+ The Value class +
+ +
+ +

#include "llvm/Value.h" +
+doxygen info: Value Class

+ +

The Value class is the most important class in the LLVM Source +base. It represents a typed value that may be used (among other things) as an +operand to an instruction. There are many different types of Values, +such as Constants,Arguments. Even Instructions and Functions are Values.

+ +

A particular Value may be used many times in the LLVM representation +for a program. For example, an incoming argument to a function (represented +with an instance of the Argument class) is "used" by +every instruction in the function that references the argument. To keep track +of this relationship, the Value class keeps a list of all of the Users that is using it (the User class is a base class for all nodes in the LLVM +graph that can refer to Values). This use list is how LLVM represents +def-use information in the program, and is accessible through the use_* +methods, shown below.

+ +

Because LLVM is a typed representation, every LLVM Value is typed, +and this Type is available through the getType() +method. In addition, all LLVM values can be named. The "name" of the +Value is a symbolic string printed in the LLVM code:

+ +
+
+%foo = add i32 1, 2
+
+
+ +

The name of this instruction is "foo". NOTE +that the name of any value may be missing (an empty string), so names should +ONLY be used for debugging (making the source code easier to read, +debugging printouts), they should not be used to keep track of values or map +between them. For this purpose, use a std::map of pointers to the +Value itself instead.

+ +

One important aspect of LLVM is that there is no distinction between an SSA +variable and the operation that produces it. Because of this, any reference to +the value produced by an instruction (or the value available as an incoming +argument, for example) is represented as a direct pointer to the instance of +the class that +represents this value. Although this may take some getting used to, it +simplifies the representation and makes it easier to manipulate.

+ +
+ + +
+ Important Public Members of the Value class +
+ +
+ +
    +
  • Value::use_iterator - Typedef for iterator over the +use-list
    + Value::use_const_iterator - Typedef for const_iterator over +the use-list
    + unsigned use_size() - Returns the number of users of the +value.
    + bool use_empty() - Returns true if there are no users.
    + use_iterator use_begin() - Get an iterator to the start of +the use-list.
    + use_iterator use_end() - Get an iterator to the end of the +use-list.
    + User *use_back() - Returns the last +element in the list. +

    These methods are the interface to access the def-use +information in LLVM. As with all other iterators in LLVM, the naming +conventions follow the conventions defined by the STL.

    +
    • +
  • Type *getType() const +

    This method returns the Type of the Value.

    +
    • +
  • bool hasName() const
    + std::string getName() const
    + void setName(const std::string &Name) +

    This family of methods is used to access and assign a name to a Value, +be aware of the precaution above.

    +
    • +
  • void replaceAllUsesWith(Value *V) + +

    This method traverses the use list of a Value changing all Users of the current value to refer to + "V" instead. For example, if you detect that an instruction always + produces a constant value (for example through constant folding), you can + replace all uses of the instruction with the constant like this:

    + +
    +
    +Inst->replaceAllUsesWith(ConstVal);
+
    +
    + +
+ +
+ + +
+ The User class +
+ +
+ +

+#include "llvm/User.h"
+doxygen info: User Class
+Superclass: Value

+ +

The User class is the common base class of all LLVM nodes that may +refer to Values. It exposes a list of "Operands" +that are all of the Values that the User is +referring to. The User class itself is a subclass of +Value.

+ +

The operands of a User point directly to the LLVM Value that it refers to. Because LLVM uses Static +Single Assignment (SSA) form, there can only be one definition referred to, +allowing this direct connection. This connection provides the use-def +information in LLVM.

+ +
+ + +
+ Important Public Members of the User class +
+ +
+ +

The User class exposes the operand list in two ways: through +an index access interface and through an iterator based interface.

+ +
    +
  • Value *getOperand(unsigned i)
    + unsigned getNumOperands() +

    These two methods expose the operands of the User in a +convenient form for direct access.

    • + +
  • User::op_iterator - Typedef for iterator over the operand +list
    + op_iterator op_begin() - Get an iterator to the start of +the operand list.
    + op_iterator op_end() - Get an iterator to the end of the +operand list. +

    Together, these methods make up the iterator based interface to +the operands of a User.

    • +
+ +
+ + +
+ The Instruction class +
+ +
+ +

#include "llvm/Instruction.h"
+doxygen info: Instruction Class
+Superclasses: User, Value

+ +

The Instruction class is the common base class for all LLVM +instructions. It provides only a few methods, but is a very commonly used +class. The primary data tracked by the Instruction class itself is the +opcode (instruction type) and the parent BasicBlock the Instruction is embedded +into. To represent a specific type of instruction, one of many subclasses of +Instruction are used.

+ +

Because the Instruction class subclasses the User class, its operands can be accessed in the same +way as for other Users (with the +getOperand()/getNumOperands() and +op_begin()/op_end() methods).

An important file for +the Instruction class is the llvm/Instruction.def file. This +file contains some meta-data about the various different types of instructions +in LLVM. It describes the enum values that are used as opcodes (for example +Instruction::Add and Instruction::ICmp), as well as the +concrete sub-classes of Instruction that implement the instruction (for +example BinaryOperator and CmpInst). Unfortunately, the use of macros in +this file confuses doxygen, so these enum values don't show up correctly in the +doxygen output.

+ +
+ + +
+ Important Subclasses of the Instruction + class +
+
+
    +
  • BinaryOperator +

    This subclasses represents all two operand instructions whose operands + must be the same type, except for the comparison instructions.

    • +
  • CastInst +

    This subclass is the parent of the 12 casting instructions. It provides + common operations on cast instructions.

    +
  • CmpInst +

    This subclass respresents the two comparison instructions, + ICmpInst (integer opreands), and + FCmpInst (floating point operands).

    +
  • TerminatorInst +

    This subclass is the parent of all terminator instructions (those which + can terminate a block).

    +
+
+ + +
+ Important Public Members of the Instruction + class +
+ +
+ +
    +
  • BasicBlock *getParent() +

    Returns the BasicBlock that +this Instruction is embedded into.

    • +
  • bool mayWriteToMemory() +

    Returns true if the instruction writes to memory, i.e. it is a + call,free,invoke, or store.

    • +
  • unsigned getOpcode() +

    Returns the opcode for the Instruction.

    • +
  • Instruction *clone() const +

    Returns another instance of the specified instruction, identical +in all ways to the original except that the instruction has no parent +(ie it's not embedded into a BasicBlock), +and it has no name

    • +
+ +
+ + +
+ The Constant class and subclasses +
+ +
+ +

Constant represents a base class for different types of constants. It +is subclassed by ConstantInt, ConstantArray, etc. for representing +the various types of Constants. GlobalValue is also +a subclass, which represents the address of a global variable or function. +

+ +
+ + +
Important Subclasses of Constant
+
+
    +
  • ConstantInt : This subclass of Constant represents an integer constant of + any width. +
      +
    • const APInt& getValue() const: Returns the underlying + value of this constant, an APInt value.
      • +
    • int64_t getSExtValue() const: Converts the underlying APInt + value to an int64_t via sign extension. If the value (not the bit width) + of the APInt is too large to fit in an int64_t, an assertion will result. + For this reason, use of this method is discouraged.
      • +
    • uint64_t getZExtValue() const: Converts the underlying APInt + value to a uint64_t via zero extension. IF the value (not the bit width) + of the APInt is too large to fit in a uint64_t, an assertion will result. + For this reason, use of this method is discouraged.
      • +
    • static ConstantInt* get(const APInt& Val): Returns the + ConstantInt object that represents the value provided by Val. + The type is implied as the IntegerType that corresponds to the bit width + of Val.
      • +
    • static ConstantInt* get(const Type *Ty, uint64_t Val): + Returns the ConstantInt object that represents the value provided by + Val for integer type Ty.
      • +
    +
    • +
  • ConstantFP : This class represents a floating point constant. +
      +
    • double getValue() const: Returns the underlying value of + this constant.
      • +
    +
    • +
  • ConstantArray : This represents a constant array. +
      +
    • const std::vector<Use> &getValues() const: Returns + a vector of component constants that makeup this array.
      • +
    +
    • +
  • ConstantStruct : This represents a constant struct. +
      +
    • const std::vector<Use> &getValues() const: Returns + a vector of component constants that makeup this array.
      • +
    +
    • +
  • GlobalValue : This represents either a global variable or a function. In + either case, the value is a constant fixed address (after linking). +
    • +
+
+ + + +
+ The GlobalValue class +
+ +
+ +

#include "llvm/GlobalValue.h"
+doxygen info: GlobalValue +Class
+Superclasses: Constant, +User, Value

+ +

Global values (GlobalVariables or Functions) are the only LLVM values that are +visible in the bodies of all Functions. +Because they are visible at global scope, they are also subject to linking with +other globals defined in different translation units. To control the linking +process, GlobalValues know their linkage rules. Specifically, +GlobalValues know whether they have internal or external linkage, as +defined by the LinkageTypes enumeration.

+ +

If a GlobalValue has internal linkage (equivalent to being +static in C), it is not visible to code outside the current translation +unit, and does not participate in linking. If it has external linkage, it is +visible to external code, and does participate in linking. In addition to +linkage information, GlobalValues keep track of which Module they are currently part of.

+ +

Because GlobalValues are memory objects, they are always referred to +by their address. As such, the Type of a +global is always a pointer to its contents. It is important to remember this +when using the GetElementPtrInst instruction because this pointer must +be dereferenced first. For example, if you have a GlobalVariable (a +subclass of GlobalValue) that is an array of 24 ints, type [24 x +i32], then the GlobalVariable is a pointer to that array. Although +the address of the first element of this array and the value of the +GlobalVariable are the same, they have different types. The +GlobalVariable's type is [24 x i32]. The first element's type +is i32. Because of this, accessing a global value requires you to +dereference the pointer with GetElementPtrInst first, then its elements +can be accessed. This is explained in the LLVM +Language Reference Manual.

+ +
+ + +
+ Important Public Members of the GlobalValue + class +
+ +
+ +
    +
  • bool hasInternalLinkage() const
    + bool hasExternalLinkage() const
    + void setInternalLinkage(bool HasInternalLinkage) +

    These methods manipulate the linkage characteristics of the GlobalValue.

    +

    +
    • +
  • Module *getParent() +

    This returns the Module that the +GlobalValue is currently embedded into.

    • +
+ +
+ + +
+ The Function class +
+ +
+ +

#include "llvm/Function.h"
doxygen +info: Function Class
+Superclasses: GlobalValue, +Constant, +User, +Value

+ +

The Function class represents a single procedure in LLVM. It is +actually one of the more complex classes in the LLVM hierarchy because it must +keep track of a large amount of data. The Function class keeps track +of a list of BasicBlocks, a list of formal +Arguments, and a +SymbolTable.

+ +

The list of BasicBlocks is the most +commonly used part of Function objects. The list imposes an implicit +ordering of the blocks in the function, which indicate how the code will be +laid out by the backend. Additionally, the first BasicBlock is the implicit entry node for the +Function. It is not legal in LLVM to explicitly branch to this initial +block. There are no implicit exit nodes, and in fact there may be multiple exit +nodes from a single Function. If the BasicBlock list is empty, this indicates that +the Function is actually a function declaration: the actual body of the +function hasn't been linked in yet.

+ +

In addition to a list of BasicBlocks, the +Function class also keeps track of the list of formal Arguments that the function receives. This +container manages the lifetime of the Argument +nodes, just like the BasicBlock list does for +the BasicBlocks.

+ +

The SymbolTable is a very rarely used +LLVM feature that is only used when you have to look up a value by name. Aside +from that, the SymbolTable is used +internally to make sure that there are not conflicts between the names of Instructions, BasicBlocks, or Arguments in the function body.

+ +

Note that Function is a GlobalValue +and therefore also a Constant. The value of the function +is its address (after linking) which is guaranteed to be constant.

+
+ + +
+ Important Public Members of the Function + class +
+ +
+ +
    +
  • Function(const FunctionType + *Ty, LinkageTypes Linkage, const std::string &N = "", Module* Parent = 0) + +

    Constructor used when you need to create new Functions to add + the the program. The constructor must specify the type of the function to + create and what type of linkage the function should have. The FunctionType argument + specifies the formal arguments and return value for the function. The same + FunctionType value can be used to + create multiple functions. The Parent argument specifies the Module + in which the function is defined. If this argument is provided, the function + will automatically be inserted into that module's list of + functions.

    • + +
  • bool isDeclaration() + +

    Return whether or not the Function has a body defined. If the + function is "external", it does not have a body, and thus must be resolved + by linking with a function defined in a different translation unit.

    • + +
  • Function::iterator - Typedef for basic block list iterator
    + Function::const_iterator - Typedef for const_iterator.
    + + begin(), end() + size(), empty() + +

    These are forwarding methods that make it easy to access the contents of + a Function object's BasicBlock + list.

    • + +
  • Function::BasicBlockListType &getBasicBlockList() + +

    Returns the list of BasicBlocks. This + is necessary to use when you need to update the list or perform a complex + action that doesn't have a forwarding method.

    • + +
  • Function::arg_iterator - Typedef for the argument list +iterator
    + Function::const_arg_iterator - Typedef for const_iterator.
    + + arg_begin(), arg_end() + arg_size(), arg_empty() + +

    These are forwarding methods that make it easy to access the contents of + a Function object's Argument + list.

    • + +
  • Function::ArgumentListType &getArgumentList() + +

    Returns the list of Arguments. This is + necessary to use when you need to update the list or perform a complex + action that doesn't have a forwarding method.

    • + +
  • BasicBlock &getEntryBlock() + +

    Returns the entry BasicBlock for the + function. Because the entry block for the function is always the first + block, this returns the first block of the Function.

    • + +
  • Type *getReturnType()
    + FunctionType *getFunctionType() + +

    This traverses the Type of the + Function and returns the return type of the function, or the FunctionType of the actual + function.

    • + +
  • SymbolTable *getSymbolTable() + +

    Return a pointer to the SymbolTable + for this Function.

    • +
+ +
+ + +
+ The GlobalVariable class +
+ +
+ +

#include "llvm/GlobalVariable.h" +
+doxygen info: GlobalVariable + Class
+Superclasses: GlobalValue, +Constant, +User, +Value

+ +

Global variables are represented with the (surprise surprise) +GlobalVariable class. Like functions, GlobalVariables are also +subclasses of GlobalValue, and as such are +always referenced by their address (global values must live in memory, so their +"name" refers to their constant address). See +GlobalValue for more on this. Global +variables may have an initial value (which must be a +Constant), and if they have an initializer, +they may be marked as "constant" themselves (indicating that their contents +never change at runtime).

+
+ + +
+ Important Public Members of the + GlobalVariable class +
+ +
+ +
    +
  • GlobalVariable(const Type *Ty, bool + isConstant, LinkageTypes& Linkage, Constant + *Initializer = 0, const std::string &Name = "", Module* Parent = 0) + +

    Create a new global variable of the specified type. If + isConstant is true then the global variable will be marked as + unchanging for the program. The Linkage parameter specifies the type of + linkage (internal, external, weak, linkonce, appending) for the variable. + If the linkage is InternalLinkage, WeakAnyLinkage, WeakODRLinkage, + LinkOnceAnyLinkage or LinkOnceODRLinkage,  then the resultant + global variable will have internal linkage. AppendingLinkage concatenates + together all instances (in different translation units) of the variable + into a single variable but is only applicable to arrays.  See + the LLVM Language Reference for + further details on linkage types. Optionally an initializer, a name, and the + module to put the variable into may be specified for the global variable as + well.

    • + +
  • bool isConstant() const + +

    Returns true if this is a global variable that is known not to + be modified at runtime.

    • + +
  • bool hasInitializer() + +

    Returns true if this GlobalVariable has an intializer.

    • + +
  • Constant *getInitializer() + +

    Returns the initial value for a GlobalVariable. It is not legal + to call this method if there is no initializer.

    • +
+ +
+ + + +
+ The BasicBlock class +
+ +
+ +

#include "llvm/BasicBlock.h"
+doxygen info: BasicBlock +Class
+Superclass: Value

+ +

This class represents a single entry multiple exit section of the code, +commonly known as a basic block by the compiler community. The +BasicBlock class maintains a list of Instructions, which form the body of the block. +Matching the language definition, the last element of this list of instructions +is always a terminator instruction (a subclass of the TerminatorInst class).

+ +

In addition to tracking the list of instructions that make up the block, the +BasicBlock class also keeps track of the Function that it is embedded into.

+ +

Note that BasicBlocks themselves are Values, because they are referenced by instructions +like branches and can go in the switch tables. BasicBlocks have type +label.

+ +
+ + +
+ Important Public Members of the BasicBlock + class +
+ +
+
    + +
  • BasicBlock(const std::string &Name = "", Function *Parent = 0) + +

    The BasicBlock constructor is used to create new basic blocks for +insertion into a function. The constructor optionally takes a name for the new +block, and a Function to insert it into. If +the Parent parameter is specified, the new BasicBlock is +automatically inserted at the end of the specified Function, if not specified, the BasicBlock must be +manually inserted into the Function.

    • + +
  • BasicBlock::iterator - Typedef for instruction list iterator
    +BasicBlock::const_iterator - Typedef for const_iterator.
    +begin(), end(), front(), back(), +size(), empty() +STL-style functions for accessing the instruction list. + +

    These methods and typedefs are forwarding functions that have the same +semantics as the standard library methods of the same names. These methods +expose the underlying instruction list of a basic block in a way that is easy to +manipulate. To get the full complement of container operations (including +operations to update the list), you must use the getInstList() +method.

    • + +
  • BasicBlock::InstListType &getInstList() + +

    This method is used to get access to the underlying container that actually +holds the Instructions. This method must be used when there isn't a forwarding +function in the BasicBlock class for the operation that you would like +to perform. Because there are no forwarding functions for "updating" +operations, you need to use this if you want to update the contents of a +BasicBlock.

    • + +
  • Function *getParent() + +

    Returns a pointer to Function the block is +embedded into, or a null pointer if it is homeless.

    • + +
  • TerminatorInst *getTerminator() + +

    Returns a pointer to the terminator instruction that appears at the end of +the BasicBlock. If there is no terminator instruction, or if the last +instruction in the block is not a terminator, then a null pointer is +returned.

    • + +
+ +
+ + + +
+ The Argument class +
+ +
+ +

This subclass of Value defines the interface for incoming formal +arguments to a function. A Function maintains a list of its formal +arguments. An argument has a pointer to the parent Function.

+ +
+ + +
+
+ Valid CSS + Valid HTML 4.01 Strict + + Dinakar Dhurjati and + Chris Lattner
+ The LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-02-25 17:51:27 -0600 (Thu, 25 Feb 2010) $ +
+ + + Added: www-releases/trunk/2.7/docs/Projects.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/Projects.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/Projects.html (added) +++ www-releases/trunk/2.7/docs/Projects.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,460 @@ + + + + Creating an LLVM Project + + + + +
Creating an LLVM Project
+ +
    +
  1. Overview
    2. +
  2. Create a project from the Sample Project
    3. +
  3. Source tree layout
    4. +
  4. Writing LLVM-style Makefiles +
      +
    1. Required Variables
      2. +
    2. Variables for Building Subdirectories
      3. +
    3. Variables for Building Libraries
      4. +
    4. Variables for Building Programs
      5. +
    5. Miscellaneous Variables
      6. +
    5. +
  5. Placement of object code
    6. +
  6. Further help
    7. +
+ +
+

Written by John Criswell

+
+ + +
Overview
+ + +
+ +

The LLVM build system is designed to facilitate the building of third party +projects that use LLVM header files, libraries, and tools. In order to use +these facilities, a Makefile from a project must do the following things:

+ +
    +
  1. Set make variables. There are several variables that a Makefile + needs to set to use the LLVM build system: +
      +
    • PROJECT_NAME - The name by which your project is known.
      • +
    • LLVM_SRC_ROOT - The root of the LLVM source tree.
      • +
    • LLVM_OBJ_ROOT - The root of the LLVM object tree.
      • +
    • PROJ_SRC_ROOT - The root of the project's source tree.
      • +
    • PROJ_OBJ_ROOT - The root of the project's object tree.
      • +
    • PROJ_INSTALL_ROOT - The root installation directory.
      • +
    • LEVEL - The relative path from the current directory to the + project's root ($PROJ_OBJ_ROOT).
      • +
    2. +
  2. Include Makefile.config from $(LLVM_OBJ_ROOT).
    3. +
  3. Include Makefile.rules from $(LLVM_SRC_ROOT).
    4. +
+ +

There are two ways that you can set all of these variables:

+
    +
  1. You can write your own Makefiles which hard-code these values.
    2. +
  2. You can use the pre-made LLVM sample project. This sample project + includes Makefiles, a configure script that can be used to configure the + location of LLVM, and the ability to support multiple object directories + from a single source directory.
    3. +
+ +

This document assumes that you will base your project on the LLVM sample +project found in llvm/projects/sample. If you want to devise your own +build system, studying the sample project and LLVM Makefiles will probably +provide enough information on how to write your own Makefiles.

+ +
+ + +
+ Create a Project from the Sample Project +
+ + +
+ +

Follow these simple steps to start your project:

+ +
    +
  1. Copy the llvm/projects/sample directory to any place of your +choosing. You can place it anywhere you like. Rename the directory to match +the name of your project.
    2. + +
  2. +If you downloaded LLVM using Subversion, remove all the directories named .svn +(and all the files therein) from your project's new source tree. This will +keep Subversion from thinking that your project is inside +llvm/trunk/projects/sample.
    3. + +
  3. Add your source code and Makefiles to your source tree.
    4. + +
  4. If you want your project to be configured with the configure script +then you need to edit autoconf/configure.ac as follows: +
      +
    • AC_INIT. Place the name of your project, its version number and + a contact email address for your project as the arguments to this macro
      • +
    • AC_CONFIG_AUX_DIR. If your project isn't in the + llvm/projects directory then you might need to adjust this so that + it specifies a relative path to the llvm/autoconf directory.
      • +
    • LLVM_CONFIG_PROJECT. Just leave this alone.
      • +
    • AC_CONFIG_SRCDIR. Specify a path to a file name that identifies + your project; or just leave it at Makefile.common.in
      • +
    • AC_CONFIG_FILES. Do not change.
      • +
    • AC_CONFIG_MAKEFILE. Use one of these macros for each Makefile + that your project uses. This macro arranges for your makefiles to be copied + from the source directory, unmodified, to the build directory.
      • +
    +
    5. + +
  5. After updating autoconf/configure.ac, regenerate the +configure script with these commands: + +
    +

    % cd autoconf
    + % ./AutoRegen.sh

    +
    + +

    You must be using Autoconf version 2.59 or later and your aclocal version +should be 1.9 or later.

    6. + +
  6. Run configure in the directory in which you want to place +object code. Use the following options to tell your project where it +can find LLVM: + +
    +
    --with-llvmsrc=<directory>
    +
    Tell your project where the LLVM source tree is located.
    +

    --with-llvmobj=<directory>
    +
    Tell your project where the LLVM object tree is located.
    +

    --prefix=<directory>
    +
    Tell your project where it should get installed.
    +
    +
+ +

That's it! Now all you have to do is type gmake (or make +if your on a GNU/Linux system) in the root of your object directory, and your +project should build.

+ +
+ + +
+ Source Tree Layout +
+ + +
+ +

In order to use the LLVM build system, you will want to organize your +source code so that it can benefit from the build system's features. +Mainly, you want your source tree layout to look similar to the LLVM +source tree layout. The best way to do this is to just copy the +project tree from llvm/projects/sample and modify it to meet +your needs, but you can certainly add to it if you want.

+ +

Underneath your top level directory, you should have the following +directories:

+ +
+
lib +
+ This subdirectory should contain all of your library source + code. For each library that you build, you will have one + directory in lib that will contain that library's source + code. + +

+ Libraries can be object files, archives, or dynamic libraries. + The lib directory is just a convenient place for libraries + as it places them all in a directory from which they can be linked + later. + +

include +
+ This subdirectory should contain any header files that are + global to your project. By global, we mean that they are used + by more than one library or executable of your project. +

+ By placing your header files in include, they will be + found automatically by the LLVM build system. For example, if + you have a file include/jazz/note.h, then your source + files can include it simply with #include "jazz/note.h". + +

tools +
+ This subdirectory should contain all of your source + code for executables. For each program that you build, you + will have one directory in tools that will contain that + program's source code. +

+ +

test +
+ This subdirectory should contain tests that verify that your code + works correctly. Automated tests are especially useful. +

+ Currently, the LLVM build system provides basic support for tests. + The LLVM system provides the following: +

    +
  • + LLVM provides a tcl procedure that is used by Dejagnu to run + tests. It can be found in llvm/lib/llvm-dg.exp. This + test procedure uses RUN lines in the actual test case to determine + how to run the test. See the TestingGuide for more details. You + can easily write Makefile support similar to the Makefiles in + llvm/test to use Dejagnu to run your project's tests.
    • +
  • + LLVM contains an optional package called llvm-test + which provides benchmarks and programs that are known to compile with the + LLVM GCC front ends. You can use these + programs to test your code, gather statistics information, and + compare it to the current LLVM performance statistics. +
    Currently, there is no way to hook your tests directly into the + llvm/test testing harness. You will simply + need to find a way to use the source provided within that directory + on your own. +
+
+ +

Typically, you will want to build your lib directory first followed by +your tools directory.

+ +
+ + +
+ Writing LLVM Style Makefiles +
+ + +
+ +

The LLVM build system provides a convenient way to build libraries and +executables. Most of your project Makefiles will only need to define a few +variables. Below is a list of the variables one can set and what they can +do:

+ +
+ + +
+ Required Variables +
+ +
+ +
+
LEVEL +
+ This variable is the relative path from this Makefile to the + top directory of your project's source code. For example, if + your source code is in /tmp/src, then the Makefile in + /tmp/src/jump/high would set LEVEL to "../..". +
+ +
+ + +
+ Variables for Building Subdirectories +
+ +
+ +
+
DIRS +
+ This is a space separated list of subdirectories that should be + built. They will be built, one at a time, in the order + specified. +

+ +

PARALLEL_DIRS +
+ This is a list of directories that can be built in parallel. + These will be built after the directories in DIRS have been + built. +

+ +

OPTIONAL_DIRS +
+ This is a list of directories that can be built if they exist, + but will not cause an error if they do not exist. They are + built serially in the order in which they are listed. +
+ +
+ + +
+ Variables for Building Libraries +
+ +
+ +
+
LIBRARYNAME +
+ This variable contains the base name of the library that will + be built. For example, to build a library named + libsample.a, LIBRARYNAME should be set to + sample. +

+ +

BUILD_ARCHIVE +
+ By default, a library is a .o file that is linked + directly into a program. To build an archive (also known as + a static library), set the BUILD_ARCHIVE variable. +

+ +

SHARED_LIBRARY +
+ If SHARED_LIBRARY is defined in your Makefile, a shared + (or dynamic) library will be built. +
+ +
+ + +
+ Variables for Building Programs +
+ +
+ +
+
TOOLNAME +
+ This variable contains the name of the program that will + be built. For example, to build an executable named + sample, TOOLNAME should be set to sample. +

+ +

USEDLIBS +
+ This variable holds a space separated list of libraries that + should be linked into the program. These libraries must either + be LLVM libraries or libraries that come from your lib + directory. The libraries must be specified by their base name. + For example, to link libsample.a, you would set USEDLIBS to + sample. +

+ Note that this works only for statically linked libraries. +

+ +

LIBS +
+ To link dynamic libraries, add -l<library base name> to + the LIBS variable. The LLVM build system will look in the same places + for dynamic libraries as it does for static libraries. +

+ For example, to link libsample.so, you would have the + following line in your Makefile: +

+ + LIBS += -lsample + +

+ +
+ + +
+ Miscellaneous Variables +
+ +
+ +
+
ExtraSource +
+ This variable contains a space separated list of extra source + files that need to be built. It is useful for including the + output of Lex and Yacc programs. +

+ +

CFLAGS +
CPPFLAGS +
+ This variable can be used to add options to the C and C++ + compiler, respectively. It is typically used to add options + that tell the compiler the location of additional directories + to search for header files. +

+ It is highly suggested that you append to CFLAGS and CPPFLAGS as + opposed to overwriting them. The master Makefiles may already + have useful options in them that you may not want to overwrite. +

+

+ +
+ + +
+ Placement of Object Code +
+ + +
+ +

The final location of built libraries and executables will depend upon +whether you do a Debug, Release, or Profile build.

+ +
+
Libraries +
+ All libraries (static and dynamic) will be stored in + PROJ_OBJ_ROOT/<type>/lib, where type is Debug, + Release, or Profile for a debug, optimized, or + profiled build, respectively.

+ +

Executables +
All executables will be stored in + PROJ_OBJ_ROOT/<type>/bin, where type is Debug, + Release, or Profile for a debug, optimized, or profiled + build, respectively. +
+ +
+ + +
+ Further Help +
+ + +
+ +

If you have any questions or need any help creating an LLVM project, +the LLVM team would be more than happy to help. You can always post your +questions to the LLVM Developers +Mailing List.

+ +
+ + +
+
+ Valid CSS + Valid HTML 4.01 + + John Criswell
+ The LLVM Compiler Infrastructure +
+ Last modified: $Date: 2009-08-13 15:08:52 -0500 (Thu, 13 Aug 2009) $ +
+ + + Added: www-releases/trunk/2.7/docs/ReleaseNotes.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/ReleaseNotes.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/ReleaseNotes.html (added) +++ www-releases/trunk/2.7/docs/ReleaseNotes.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,1281 @@ + + + + + + LLVM 2.7 Release Notes + + + +
LLVM 2.7 Release Notes
+ +LLVM Dragon Logo + +
    +
  1. Introduction
    2. +
  2. Sub-project Status Update
    3. +
  3. External Projects Using LLVM 2.7
    4. +
  4. What's New in LLVM 2.7?
    5. +
  5. Installation Instructions
    6. +
  6. Portability and Supported Platforms
    7. +
  7. Known Problems
    8. +
  8. Additional Information
    9. +
+ +
+

Written by the LLVM Team

+
+ + + + +
+ Introduction +
+ + +
+ +

This document contains the release notes for the LLVM Compiler +Infrastructure, release 2.7. Here we describe the status of LLVM, including +major improvements from the previous release and significant known problems. +All LLVM releases may be downloaded from the LLVM releases web site.

+ +

For more information about LLVM, including information about the latest +release, please check out the main LLVM +web site. If you have questions or comments, the LLVM Developer's +Mailing List is a good place to send them.

+ +

Note that if you are reading this file from a Subversion checkout or the +main LLVM web page, this document applies to the next release, not the +current one. To see the release notes for a specific release, please see the +releases page.

+ +
+ + + + + + + + + + +
+ Sub-project Status Update +
+ + +
+

+The LLVM 2.7 distribution currently consists of code from the core LLVM +repository (which roughly includes the LLVM optimizers, code generators +and supporting tools), the Clang repository and the llvm-gcc repository. In +addition to this code, the LLVM Project includes other sub-projects that are in +development. Here we include updates on these subprojects. +

+ +
+ + + +
+Clang: C/C++/Objective-C Frontend Toolkit +
+ +
+ +

Clang is an LLVM front end for the C, +C++, and Objective-C languages. Clang aims to provide a better user experience +through expressive diagnostics, a high level of conformance to language +standards, fast compilation, and low memory use. Like LLVM, Clang provides a +modular, library-based architecture that makes it suitable for creating or +integrating with other development tools. Clang is considered a +production-quality compiler for C and Objective-C on x86 (32- and 64-bit).

+ +

In the LLVM 2.7 time-frame, the Clang team has made many improvements:

+ +
    + +
  • C++ Support: Clang is now capable of self-hosting! While still +alpha-quality, Clang's C++ support has matured enough to build LLVM and Clang, +and C++ is now enabled by default. See the Clang C++ compatibility +page for common C++ migration issues.
    • + +
  • Objective-C: Clang now includes experimental support for an updated +Objective-C ABI on non-Darwin platforms. This includes support for non-fragile +instance variables and accelerated proxies, as well as greater potential for +future optimisations. The new ABI is used when compiling with the +-fobjc-nonfragile-abi and -fgnu-runtime options. Code compiled with these +options may be mixed with code compiled with GCC or clang using the old GNU ABI, +but requires the libobjc2 runtime from the GNUstep project.
    • + +
  • New warnings: Clang contains a number of new warnings, including +control-flow warnings (unreachable code, missing return statements in a +non-void function, etc.), sign-comparison warnings, and improved +format-string warnings.
    • + +
  • CIndex API and Python bindings: Clang now includes a C API as part of the +CIndex library. Although we may make some changes to the API in the future, it +is intended to be stable and has been designed for use by external projects. See +the Clang +doxygen CIndex +documentation for more details. The CIndex API also includes a preliminary +set of Python bindings.
    • + +
  • ARM Support: Clang now has ABI support for both the Darwin and Linux ARM +ABIs. Coupled with many improvements to the LLVM ARM backend, Clang is now +suitable for use as a beta quality ARM compiler.
    • + +
+
+ + +
+Clang Static Analyzer +
+ +
+ +

The Clang Static Analyzer + project is an effort to use static source code analysis techniques to + automatically find bugs in C and Objective-C programs (and hopefully C++ in the + future!). The tool is very good at finding bugs that occur on specific + paths through code, such as on error conditions.

+ +

In the LLVM 2.7 time-frame, the analyzer core has made several major and + minor improvements, including better support for tracking the fields of + structures, initial support (not enabled by default yet) for doing + interprocedural (cross-function) analysis, and new checks have been added. +

+ +
+ + +
+VMKit: JVM/CLI Virtual Machine Implementation +
+ +
+

+The VMKit project is an implementation of +a JVM and a CLI Virtual Machine (Microsoft .NET is an +implementation of the CLI) using LLVM for static and just-in-time +compilation.

+ +

+With the release of LLVM 2.7, VMKit has shifted to a great framework for writing +virtual machines. VMKit now offers precise and efficient garbage collection with +multi-threading support, thanks to the MMTk memory management toolkit, as well +as just in time and ahead of time compilation with LLVM. The major changes in +VMKit 0.27 are:

+ +
    + +
  • Garbage collection: VMKit now uses the MMTk toolkit for garbage collectors. + The first collector to be ported is the MarkSweep collector, which is precise, + and drastically improves the performance of VMKit.
    • +
  • Line number information in the JVM: by using the debug metadata of LLVM, the + JVM now supports precise line number information, useful when printing a stack + trace.
    • +
  • Interface calls in the JVM: we implemented a variant of the Interface Method + Table technique for interface calls in the JVM. +
    • + +
+
+ + + +
+compiler-rt: Compiler Runtime Library +
+ +
+

+The new LLVM compiler-rt project +is a simple library that provides an implementation of the low-level +target-specific hooks required by code generation and other runtime components. +For example, when compiling for a 32-bit target, converting a double to a 64-bit +unsigned integer is compiled into a runtime call to the "__fixunsdfdi" +function. The compiler-rt library provides highly optimized implementations of +this and other low-level routines (some are 3x faster than the equivalent +libgcc routines).

+ +

+All of the code in the compiler-rt project is available under the standard LLVM +License, a "BSD-style" license. New in LLVM 2.7: compiler_rt now +supports ARM targets.

+ +
+ + +
+DragonEgg: llvm-gcc ported to gcc-4.5 +
+ +
+

+DragonEgg is a port of llvm-gcc to +gcc-4.5. Unlike llvm-gcc, which makes many intrusive changes to the underlying +gcc-4.2 code, dragonegg in theory does not require any gcc-4.5 modifications +whatsoever (currently one small patch is needed). This is thanks to the new +gcc plugin architecture, which +makes it possible to modify the behaviour of gcc at runtime by loading a plugin, +which is nothing more than a dynamic library which conforms to the gcc plugin +interface. DragonEgg is a gcc plugin that causes the LLVM optimizers to be run +instead of the gcc optimizers, and the LLVM code generators instead of the gcc +code generators, just like llvm-gcc. To use it, you add +"-fplugin=path/dragonegg.so" to the gcc-4.5 command line, and gcc-4.5 magically +becomes llvm-gcc-4.5! +

+ +

+DragonEgg is still a work in progress. Currently C works very well, while C++, +Ada and Fortran work fairly well. All other languages either don't work at all, +or only work poorly. For the moment only the x86-32 and x86-64 targets are +supported, and only on linux and darwin (darwin needs an additional gcc patch). +

+ +

+DragonEgg is a new project which is seeing its first release with llvm-2.7. +

+ +
+ + + +
+llvm-mc: Machine Code Toolkit +
+ +
+

+The LLVM Machine Code (aka MC) sub-project of LLVM was created to solve a number +of problems in the realm of assembly, disassembly, object file format handling, +and a number of other related areas that CPU instruction-set level tools work +in. It is a sub-project of LLVM which provides it with a number of advantages +over other compilers that do not have tightly integrated assembly-level tools. +For a gentle introduction, please see the Intro to the +LLVM MC Project Blog Post. +

+ +

2.7 includes major parts of the work required by the new MC Project. A few + targets have been refactored to support it, and work is underway to support a + native assembler in LLVM. This work is not complete in LLVM 2.7, but it has + made substantially more progress on LLVM mainline.

+ +

One minor example of what MC can do is to transcode an AT&T syntax + X86 .s file into intel syntax. You can do this with something like:

+
+  llvm-mc foo.s -output-asm-variant=1 -o foo-intel.s
+
+ +
+ + + +
+ External Open Source Projects Using LLVM 2.7 +
+ + +
+ +

An exciting aspect of LLVM is that it is used as an enabling technology for + a lot of other language and tools projects. This section lists some of the + projects that have already been updated to work with LLVM 2.7.

+
+ + +
+Pure +
+ +
+

+Pure +is an algebraic/functional programming language based on term rewriting. +Programs are collections of equations which are used to evaluate expressions in +a symbolic fashion. Pure offers dynamic typing, eager and lazy evaluation, +lexical closures, a hygienic macro system (also based on term rewriting), +built-in list and matrix support (including list and matrix comprehensions) and +an easy-to-use C interface. The interpreter uses LLVM as a backend to + JIT-compile Pure programs to fast native code.

+ +

Pure versions 0.43 and later have been tested and are known to work with +LLVM 2.7 (and continue to work with older LLVM releases >= 2.5).

+ +
+ + +
+Roadsend PHP +
+ +
+

+Roadsend PHP (rphp) is an open +source implementation of the PHP programming +language that uses LLVM for its optimizer, JIT and static compiler. This is a +reimplementation of an earlier project that is now based on LLVM. +

+
+ + +
+Unladen Swallow +
+ +
+

+Unladen Swallow is a +branch of Python intended to be fully +compatible and significantly faster. It uses LLVM's optimization passes and JIT +compiler. +

+
+ + +
+TTA-based Codesign Environment (TCE) +
+ +
+

+TCE is a toolset for designing +application-specific processors (ASP) based on the Transport triggered +architecture (TTA). The toolset provides a complete co-design flow from C/C++ +programs down to synthesizable VHDL and parallel program binaries. Processor +customization points include the register files, function units, supported +operations, and the interconnection network.

+ +

TCE uses llvm-gcc/Clang and LLVM for C/C++ language support, target +independent optimizations and also for parts of code generation. It generates +new LLVM-based code generators "on the fly" for the designed TTA processors and +loads them in to the compiler backend as runtime libraries to avoid per-target +recompilation of larger parts of the compiler chain.

+ +
+ + +
+SAFECode Compiler +
+ +
+

+SAFECode is a memory safe C +compiler built using LLVM. It takes standard, unannotated C code, analyzes the +code to ensure that memory accesses and array indexing operations are safe, and +instruments the code with run-time checks when safety cannot be proven +statically. +

+
+ + +
+IcedTea Java Virtual Machine Implementation +
+ +
+

+IcedTea provides a +harness to build OpenJDK using only free software build tools and to provide +replacements for the not-yet free parts of OpenJDK. One of the extensions that +IcedTea provides is a new JIT compiler named Shark which uses LLVM +to provide native code generation without introducing processor-dependent +code. +

+

Icedtea6 1.8 and later have been tested and are known to work with +LLVM 2.7 (and continue to work with older LLVM releases >= 2.6 as well). +

+
+ + +
+LLVM-Lua +
+ +
+

+LLVM-Lua uses LLVM + to add JIT and static compiling support to the Lua VM. Lua +bytecode is analyzed to remove type checks, then LLVM is used to compile the +bytecode down to machine code. +

+

LLVM-Lua 1.2.0 have been tested and is known to work with LLVM 2.7. +

+
+ + +
+MacRuby +
+ +
+

+MacRuby is an implementation of Ruby based on +core Mac OS technologies, sponsored by Apple Inc. It uses LLVM at runtime for +optimization passes, JIT compilation and exception handling. It also allows +static (ahead-of-time) compilation of Ruby code straight to machine code. +

+

The upcoming MacRuby 0.6 release works with LLVM 2.7. +

+
+ + +
+Glasgow Haskell Compiler (GHC) +
+ +
+

+GHC is an open source, +state-of-the-art programming suite for Haskell, a standard lazy +functional programming language. It includes an optimizing static +compiler generating good code for a variety of platforms, together +with an interactive system for convenient, quick development.

+ +

In addition to the existing C and native code generators, GHC now +supports an LLVM +code generator. GHC supports LLVM 2.7.

+ +
+ + + +
+ What's New in LLVM 2.7? +
+ + +
+ +

This release includes a huge number of bug fixes, performance tweaks and +minor improvements. Some of the major improvements and new features are listed +in this section. +

+ +
+ + +
+LLVM Community Changes +
+ +
+ +

In addition to changes to the code, between LLVM 2.6 and 2.7, a number of +organization changes have happened: +

+ +
    +
  • LLVM has a new official logo!
    • + +
  • Ted Kremenek and Doug Gregor have stepped forward as Code Owners of the + Clang static analyzer and the Clang frontend, respectively.
    • + +
  • LLVM now has an official Blog at + http://blog.llvm.org. This is a great way + to learn about new LLVM-related features as they are implemented. Several + features in this release are already explained on the blog.
    • + +
  • The LLVM web pages are now checked into the SVN server, in the "www", + "www-pubs" and "www-releases" SVN modules. Previously they were hidden in a + largely inaccessible old CVS server.
    • + +
  • llvm.org is now hosted on a new (and much + faster) server. It is still graciously hosted at the University of Illinois + of Urbana Champaign.
    • +
+
+ + +
+Major New Features +
+ +
+ +

LLVM 2.7 includes several major new capabilities:

+ +
    +
  • 2.7 includes initial support for the MicroBlaze target. + MicroBlaze is a soft processor core designed for Xilinx FPGAs.
    • + +
  • 2.7 includes a new LLVM IR "extensible metadata" feature. This feature + supports many different use cases, including allowing front-end authors to + encode source level information into LLVM IR, which is consumed by later + language-specific passes. This is a great way to do high-level optimizations + like devirtualization, type-based alias analysis, etc. See the + Extensible Metadata Blog Post for more information.
    • + +
  • 2.7 encodes debug information +in a completely new way, built on extensible metadata. The new implementation +is much more memory efficient and paves the way for improvements to optimized +code debugging experience.
    • + +
  • 2.7 now directly supports taking the address of a label and doing an + indirect branch through a pointer. This is particularly useful for + interpreter loops, and is used to implement the GCC "address of label" + extension. For more information, see the +Address of Label and Indirect Branches in LLVM IR Blog Post. + +
  • 2.7 is the first release to start supporting APIs for assembling and + disassembling target machine code. These APIs are useful for a variety of + low level clients, and are surfaced in the new "enhanced disassembly" API. + For more information see the The X86 + Disassembler Blog Post for more information.
    • + +
  • 2.7 includes major parts of the work required by the new MC Project, + see the MC update above for more information.
    • + +
+ +
+ + +
+LLVM IR and Core Improvements +
+ +
+

LLVM IR has several new features for better support of new targets and that +expose new optimization opportunities:

+ +
    +
  • LLVM IR now supports a 16-bit "half float" data type through two new intrinsics and APFloat support.
    • +
  • LLVM IR supports two new function + attributes: inlinehint and alignstack(n). The former is a hint to the + optimizer that a function was declared 'inline' and thus the inliner should + weight it higher when considering inlining it. The later + indicates to the code generator that the function diverges from the platform + ABI on stack alignment.
    • +
  • The new llvm.objectsize intrinsic + allows the optimizer to infer the sizes of memory objects in some cases. + This intrinsic is used to implement the GCC __builtin_object_size + extension.
    • +
  • LLVM IR now supports marking load and store instructions with "non-temporal" hints (building on the new + metadata feature). This hint encourages the code + generator to generate non-temporal accesses when possible, which are useful + for code that is carefully managing cache behavior. Currently, only the + X86 backend provides target support for this feature.
    • + +
  • LLVM 2.7 has pre-alpha support for unions in LLVM IR. + Unfortunately, this support is not really usable in 2.7, so if you're + interested in pushing it forward, please help contribute to LLVM mainline.
    • + +
+ +
+ + +
+Optimizer Improvements +
+ +
+ +

In addition to a large array of minor performance tweaks and bug fixes, this +release includes a few major enhancements and additions to the optimizers:

+ +
    + +
  • The inliner reuses now merges arrays stack objects in different callees when + inlining multiple call sites into one function. This reduces the stack size + of the resultant function.
    • +
  • The -basicaa alias analysis pass (which is the default) has been improved to + be less dependent on "type safe" pointers. It can now look through bitcasts + and other constructs more aggressively, allowing better load/store + optimization.
    • +
  • The load elimination optimization in the GVN Pass [intro + blog post] has been substantially improved to be more aggressive about + partial redundancy elimination and do more aggressive phi translation. Please + see the + Advanced Topics in Redundant Load Elimination with a Focus on PHI Translation + Blog Post for more details.
    • +
  • The module target data string now + includes a notion of 'native' integer data types for the target. This + helps mid-level optimizations avoid promoting complex sequences of + operations to data types that are not natively supported (e.g. converting + i32 operations to i64 on 32-bit chips).
    • +
  • The mid-level optimizer is now conservative when operating on a module with + no target data. Previously, it would default to SparcV9 settings, which is + not what most people expected.
    • +
  • Jump threading is now much more aggressive at simplifying correlated + conditionals and threading blocks with otherwise complex logic. It has + subsumed the old "Conditional Propagation" pass, and -condprop has been + removed from LLVM 2.7.
    • +
  • The -instcombine pass has been refactored from being one huge file to being + a library of its own. Internally, it uses a customized IRBuilder to clean + it up and simplify it.
    • + +
  • The optimal edge profiling pass is reliable and much more complete than in + 2.6. It can be used with the llvm-prof tool but isn't wired up to the + llvm-gcc and clang command line options yet.
    • + +
  • A new experimental alias analysis implementation, -scev-aa, has been added. + It uses LLVM's Scalar Evolution implementation to do symbolic analysis of + pointer offset expressions to disambiguate pointers. It can catch a few + cases that basicaa cannot, particularly in complex loop nests.
    • + +
  • The default pass ordering has been tweaked for improved optimization + effectiveness.
    • + +
+ +
+ + + +
+Interpreter and JIT Improvements +
+ +
+ +
    +
  • The JIT now supports generating debug information and is compatible with +the new GDB 7.0 (and later) interfaces for registering dynamically generated +debug info.
    • + +
  • The JIT now defaults +to compiling eagerly to avoid a race condition in the lazy JIT. +Clients that still want the lazy JIT can switch it on by calling +ExecutionEngine::DisableLazyCompilation(false).
    • + +
  • It is now possible to create more than one JIT instance in the same process. +These JITs can generate machine code in parallel, +although you +still have to obey the other threading restrictions.
    • + +
+ +
+ + +
+Target Independent Code Generator Improvements +
+ +
+ +

We have put a significant amount of work into the code generator +infrastructure, which allows us to implement more aggressive algorithms and make +it run faster:

+ +
    +
  • The 'llc -asm-verbose' option (which is now the default) has been enhanced + to emit many useful comments to .s files indicating information about spill + slots and loop nest structure. This should make it much easier to read and + understand assembly files. This is wired up in llvm-gcc and clang to + the -fverbose-asm option.
    • + +
  • New LSR with "full strength reduction" mode, which can reduce address + register pressure in loops where address generation is important.
    • + +
  • A new codegen level Common Subexpression Elimination pass (MachineCSE) + is available and enabled by default. It catches redundancies exposed by + lowering.
    • +
  • A new pre-register-allocation tail duplication pass is available and enabled + by default, it can substantially improve branch prediction quality in some + cases.
    • +
  • A new sign and zero extension optimization pass (OptimizeExtsPass) + is available and enabled by default. This pass can takes advantage + architecture features like x86-64 implicit zero extension behavior and + sub-registers.
    • +
  • The code generator now supports a mode where it attempts to preserve the + order of instructions in the input code. This is important for source that + is hand scheduled and extremely sensitive to scheduling. It is compatible + with the GCC -fno-schedule-insns option.
    • +
  • The target-independent code generator now supports generating code with + arbitrary numbers of result values. Returning more values than was + previously supported is handled by returning through a hidden pointer. In + 2.7, only the X86 and XCore targets have adopted support for this + though.
    • +
  • The code generator now supports generating code that follows the + Glasgow Haskell Compiler Calling + Convention and ABI.
    • +
  • The "DAG instruction + selection" phase of the code generator has been largely rewritten for + 2.7. Previously, tblgen spit out tons of C++ code which was compiled and + linked into the target to do the pattern matching, now it emits a much + smaller table which is read by the target-independent code. The primary + advantages of this approach is that the size and compile time of various + targets is much improved. The X86 code generator shrunk by 1.5MB of code, + for example.
    • +
  • Almost the entire code generator has switched to emitting code through the + MC interfaces instead of printing textually to the .s file. This led to a + number of cleanups and speedups. In 2.7, debug an exception handling + information does not go through MC yet.
    • +
+
+ + +
+X86-32 and X86-64 Target Improvements +
+ +
+

New features of the X86 target include: +

+ +
    +
  • The X86 backend now optimizes tails calls much more aggressively for + functions that use the standard C calling convention.
    • +
  • The X86 backend now models scalar SSE registers as subregs of the SSE vector + registers, making the code generator more aggressive in cases where scalars + and vector types are mixed.
    • + +
+ +
+ + +
+ARM Target Improvements +
+ +
+

New features of the ARM target include: +

+ +
    + +
  • The ARM backend now generates instructions in unified assembly syntax.
    • + +
  • llvm-gcc now has complete support for the ARM v7 NEON instruction set. This + support differs slightly from the GCC implementation. Please see the + + ARM Advanced SIMD (NEON) Intrinsics and Types in LLVM Blog Post for + helpful information if migrating code from GCC to LLVM-GCC.
    • + +
  • The ARM and Thumb code generators now use register scavenging for stack + object address materialization. This allows the use of R3 as a general + purpose register in Thumb1 code, as it was previous reserved for use in + stack address materialization. Secondly, sequential uses of the same + value will now re-use the materialized constant.
    • + +
  • The ARM backend now has good support for ARMv4 targets and has been tested + on StrongARM hardware. Previously, LLVM only supported ARMv4T and + newer chips.
    • + +
  • Atomic builtins are now supported for ARMv6 and ARMv7 (__sync_synchronize, + __sync_fetch_and_add, etc.).
    • + +
+ + +
+ + +
+New Useful APIs +
+ +
+ +

This release includes a number of new APIs that are used internally, which + may also be useful for external clients. +

+ +
    +
  • The optimizer uses the new CodeMetrics class to measure the size of code. + Various passes (like the inliner, loop unswitcher, etc) all use this to make + more accurate estimates of the code size impact of various + optimizations.
    • +
  • A new + llvm/Analysis/InstructionSimplify.h interface is available for doing + symbolic simplification of instructions (e.g. a+0 -> a) + without requiring the instruction to exist. This centralizes a lot of + ad-hoc symbolic manipulation code scattered in various passes.
    • +
  • The optimizer now uses a new SSAUpdater + class which efficiently supports + doing unstructured SSA update operations. This centralized a bunch of code + scattered throughout various passes (e.g. jump threading, lcssa, + loop rotate, etc) for doing this sort of thing. The code generator has a + similar + MachineSSAUpdater class.
    • +
  • The + llvm/Support/Regex.h header exposes a platform independent regular + expression API. Building on this, the FileCheck utility now supports + regular exressions.
    • +
  • raw_ostream now supports a circular "debug stream" accessed with "dbgs()". + By default, this stream works the same way as "errs()", but if you pass + -debug-buffer-size=1000 to opt, the debug stream is capped to a + fixed sized circular buffer and the output is printed at the end of the + program's execution. This is helpful if you have a long lived compiler + process and you're interested in seeing snapshots in time.
    • +
+ + +
+ + +
+Other Improvements and New Features +
+ +
+

Other miscellaneous features include:

+ +
    +
  • You can now build LLVM as a big dynamic library (e.g. "libllvm2.7.so"). To + get this, configure LLVM with the --enable-shared option.
    • + +
  • LLVM command line tools now overwrite their output by default. Previously, + they would only do this with -f. This makes them more convenient to use, and + behave more like standard unix tools.
    • + +
  • The opt and llc tools now autodetect whether their input is a .ll or .bc + file, and automatically do the right thing. This means you don't need to + explicitly use the llvm-as tool for most things.
    • +
+ +
+ + + +
+Major Changes and Removed Features +
+ +
+ +

If you're already an LLVM user or developer with out-of-tree changes based +on LLVM 2.6, this section lists some "gotchas" that you may run into upgrading +from the previous release.

+ +
    + +
  • +The Andersen's alias analysis ("anders-aa") pass, the Predicate Simplifier +("predsimplify") pass, the LoopVR pass, the GVNPRE pass, and the random sampling +profiling ("rsprofiling") passes have all been removed. They were not being +actively maintained and had substantial problems. If you are interested in +these components, you are welcome to ressurect them from SVN, fix the +correctness problems, and resubmit them to mainline.
    • + +
  • LLVM now defaults to building most libraries with RTTI turned off, providing +a code size reduction. Packagers who are interested in building LLVM to support +plugins that require RTTI information should build with "make REQUIRE_RTTI=1" +and should read the new Advice on Packaging LLVM +document.
    • + +
  • The LLVM interpreter now defaults to not using libffi even +if you have it installed. This makes it more likely that an LLVM built on one +system will work when copied to a similar system. To use libffi, +configure with --enable-libffi.
    • + +
  • Debug information uses a completely different representation, an LLVM 2.6 +.bc file should work with LLVM 2.7, but debug info won't come forward.
    • + +
  • The LLVM 2.6 (and earlier) "malloc" and "free" instructions got removed, + along with LowerAllocations pass. Now you should just use a call to the + malloc and free functions in libc. These calls are optimized as well as + the old instructions were.
    • +
+ +

In addition, many APIs have changed in this release. Some of the major LLVM +API changes are:

+ +
    +
  • Just about everything has been converted to use raw_ostream instead of + std::ostream.
    • +
  • llvm/ADT/iterator.h has been removed, just use <iterator> + instead.
    • +
  • The Streams.h file and DOUT got removed, use DEBUG(errs() << ...); + instead.
    • +
  • The TargetAsmInfo interface was renamed to MCAsmInfo.
    • +
  • ModuleProvider has been removed +and its methods moved to Module and GlobalValue. +Most clients can remove uses of ExistingModuleProvider, +replace getBitcodeModuleProvider with +getLazyBitcodeModule, and pass their Module to +functions that used to accept ModuleProvider. Clients who +wrote their own ModuleProviders will need to derive from +GVMaterializer instead and use +Module::setMaterializer to attach it to a +Module.
    • + +
  • GhostLinkage has given up the ghost. +GlobalValues that have not yet been read from their backing +storage have the same linkage they will have after being read in. +Clients must replace calls to +GlobalValue::hasNotBeenReadFromBitcode with +GlobalValue::isMaterializable.
    • + +
  • The isInteger, isIntOrIntVector, isFloatingPoint, +isFPOrFPVector and isFPOrFPVector methods have been renamed +isIntegerTy, isIntOrIntVectorTy, isFloatingPointTy, +isFPOrFPVectorTy and isFPOrFPVectorTy respectively.
    • + +
  • llvm::Instruction::clone() no longer takes argument.
    • +
  • raw_fd_ostream's constructor now takes a flag argument, not individual + booleans (see include/llvm/Support/raw_ostream.h for details).
    • +
  • Some header files have been renamed: +
      +
    • llvm/Support/AIXDataTypesFix.h to + llvm/System/AIXDataTypesFix.h
      • +
    • llvm/Support/DataTypes.h to llvm/System/DataTypes.h
      • +
    • llvm/Transforms/Utils/InlineCost.h to + llvm/Analysis/InlineCost.h
      • +
    • llvm/Support/Mangler.h to llvm/Target/Mangler.h
      • +
    • llvm/Analysis/Passes.h to llvm/CodeGen/Passes.h
      • +
    • +
+ +
+ + + + +
+ Portability and Supported Platforms +
+ + +
+ +

LLVM is known to work on the following platforms:

+ +
    +
  • Intel and AMD machines (IA32, X86-64, AMD64, EMT-64) running Red Hat + Linux, Fedora Core, FreeBSD and AuroraUX (and probably other unix-like + systems).
    • +
  • PowerPC and X86-based Mac OS X systems, running 10.4 and above in 32-bit + and 64-bit modes.
    • +
  • Intel and AMD machines running on Win32 using MinGW libraries (native).
    • +
  • Intel and AMD machines running on Win32 with the Cygwin libraries (limited + support is available for native builds with Visual C++).
    • +
  • Sun x86 and AMD64 machines running Solaris 10, OpenSolaris 0906.
    • +
  • Alpha-based machines running Debian GNU/Linux.
    • +
+ +

The core LLVM infrastructure uses GNU autoconf to adapt itself +to the machine and operating system on which it is built. However, minor +porting may be required to get LLVM to work on new platforms. We welcome your +portability patches and reports of successful builds or error messages.

+ +
+ + +
+ Known Problems +
+ + +
+ +

This section contains significant known problems with the LLVM system, +listed by component. If you run into a problem, please check the LLVM bug database and submit a bug if +there isn't already one.

+ +
    +
  • LLVM will not correctly compile on Solaris and/or OpenSolaris +using the stock GCC 3.x.x series 'out the box', +See: Broken versions of GCC and other tools. +However, A Modern GCC Build +for x86/x86-64 has been made available from the third party AuroraUX Project +that has been meticulously tested for bootstrapping LLVM & Clang.
    • +
+ +
+ + +
+ Experimental features included with this release +
+ +
+ +

The following components of this LLVM release are either untested, known to +be broken or unreliable, or are in early development. These components should +not be relied on, and bugs should not be filed against them, but they may be +useful to some people. In particular, if you would like to work on one of these +components, please contact us on the LLVMdev list.

+ +
    +
  • The MSIL, Alpha, SPU, MIPS, PIC16, Blackfin, MSP430, SystemZ and MicroBlaze + backends are experimental.
    • +
  • llc "-filetype=asm" (the default) is the only + supported value for this option. The MachO writer is experimental, and + works much better in mainline SVN.
    • +
+ +
+ + +
+ Known problems with the X86 back-end +
+ +
+ +
    +
  • The X86 backend does not yet support + all inline assembly that uses the X86 + floating point stack. It supports the 'f' and 't' constraints, but not + 'u'.
    • +
  • The X86 backend generates inefficient floating point code when configured + to generate code for systems that don't have SSE2.
    • +
  • Win64 code generation wasn't widely tested. Everything should work, but we + expect small issues to happen. Also, llvm-gcc cannot build the mingw64 + runtime currently due to lack of support for the 'u' inline assembly + constraint and for X87 floating point inline assembly.
    • +
  • The X86-64 backend does not yet support the LLVM IR instruction + va_arg. Currently, front-ends support variadic + argument constructs on X86-64 by lowering them manually.
    • +
+ +
+ + +
+ Known problems with the PowerPC back-end +
+ +
+ +
    +
  • The Linux PPC32/ABI support needs testing for the interpreter and static +compilation, and lacks support for debug information.
    • +
+ +
+ + +
+ Known problems with the ARM back-end +
+ +
+ +
    +
  • Thumb mode works only on ARMv6 or higher processors. On sub-ARMv6 +processors, thumb programs can crash or produce wrong +results (PR1388).
    • +
  • Compilation for ARM Linux OABI (old ABI) is supported but not fully tested. +
    • +
+ +
+ + +
+ Known problems with the SPARC back-end +
+ +
+ +
    +
  • The SPARC backend only supports the 32-bit SPARC ABI (-m32); it does not + support the 64-bit SPARC ABI (-m64).
    • +
+ +
+ + +
+ Known problems with the MIPS back-end +
+ +
+ +
    +
  • 64-bit MIPS targets are not supported yet.
    • +
+ +
+ + +
+ Known problems with the Alpha back-end +
+ +
+ +
    + +
  • On 21164s, some rare FP arithmetic sequences which may trap do not have the +appropriate nops inserted to ensure restartability.
    • + +
+
+ + +
+ Known problems with the C back-end +
+ +
+ + + +
+ + + +
+ Known problems with the llvm-gcc C and C++ front-end +
+ +
+ +

The only major language feature of GCC not supported by llvm-gcc is + the __builtin_apply family of builtins. However, some extensions + are only supported on some targets. For example, trampolines are only + supported on some targets (these are used when you take the address of a + nested function).

+ +
+ + +
+ Known problems with the llvm-gcc Fortran front-end +
+ +
+
    +
  • Fortran support generally works, but there are still several unresolved bugs + in Bugzilla. Please see the + tools/gfortran component for details.
    • +
+
+ + +
+ Known problems with the llvm-gcc Ada front-end +
+ +
+The llvm-gcc 4.2 Ada compiler works fairly well; however, this is not a mature +technology, and problems should be expected. +
    +
  • The Ada front-end currently only builds on X86-32. This is mainly due +to lack of trampoline support (pointers to nested functions) on other platforms. +However, it also fails to build on X86-64 +which does support trampolines.
    • +
  • The Ada front-end fails to bootstrap. +This is due to lack of LLVM support for setjmp/longjmp style +exception handling, which is used internally by the compiler. +Workaround: configure with --disable-bootstrap.
    • +
  • The c380004, c393010 +and cxg2021 ACATS tests fail +(c380004 also fails with gcc-4.2 mainline). +If the compiler is built with checks disabled then c393010 +causes the compiler to go into an infinite loop, using up all system memory.
    • +
  • Some GCC specific Ada tests continue to crash the compiler.
    • +
  • The -E binder option (exception backtraces) +does not work and will result in programs +crashing if an exception is raised. Workaround: do not use -E.
    • +
  • Only discrete types are allowed to start +or finish at a non-byte offset in a record. Workaround: do not pack records +or use representation clauses that result in a field of a non-discrete type +starting or finishing in the middle of a byte.
    • +
  • The lli interpreter considers +'main' as generated by the Ada binder to be invalid. +Workaround: hand edit the file to use pointers for argv and +envp rather than integers.
    • +
  • The -fstack-check option is +ignored.
    • +
+
+ + +
+ Additional Information +
+ + +
+ +

A wide variety of additional information is available on the LLVM web page, in particular in the documentation section. The web page also +contains versions of the API documentation which is up-to-date with the +Subversion version of the source code. +You can access versions of these documents specific to this release by going +into the "llvm/doc/" directory in the LLVM tree.

+ +

If you have any questions or comments about LLVM, please feel free to contact +us via the mailing +lists.

+ +
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-04-27 01:53:59 -0500 (Tue, 27 Apr 2010) $ +
+ + + Added: www-releases/trunk/2.7/docs/SourceLevelDebugging.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/SourceLevelDebugging.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/SourceLevelDebugging.html (added) +++ www-releases/trunk/2.7/docs/SourceLevelDebugging.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,1741 @@ + + + + + Source Level Debugging with LLVM + + + + +
Source Level Debugging with LLVM
+ + + + + +
+ + +A leafy and green bug eater +
+ +
+

Written by Chris Lattner + and Jim Laskey

+
+ + + +
Introduction
+ + +
+ +

This document is the central repository for all information pertaining to + debug information in LLVM. It describes the actual format + that the LLVM debug information takes, which is useful for those + interested in creating front-ends or dealing directly with the information. + Further, this document provides specific examples of what debug information + for C/C++.

+ +
+ + +
+ Philosophy behind LLVM debugging information +
+ +
+ +

The idea of the LLVM debugging information is to capture how the important + pieces of the source-language's Abstract Syntax Tree map onto LLVM code. + Several design aspects have shaped the solution that appears here. The + important ones are:

+ +
    +
  • Debugging information should have very little impact on the rest of the + compiler. No transformations, analyses, or code generators should need to + be modified because of debugging information.
    • + +
  • LLVM optimizations should interact in well-defined and + easily described ways with the debugging information.
    • + +
  • Because LLVM is designed to support arbitrary programming languages, + LLVM-to-LLVM tools should not need to know anything about the semantics of + the source-level-language.
    • + +
  • Source-level languages are often widely different from one another. + LLVM should not put any restrictions of the flavor of the source-language, + and the debugging information should work with any language.
    • + +
  • With code generator support, it should be possible to use an LLVM compiler + to compile a program to native machine code and standard debugging + formats. This allows compatibility with traditional machine-code level + debuggers, like GDB or DBX.
    • +
+ +

The approach used by the LLVM implementation is to use a small set + of intrinsic functions to define a + mapping between LLVM program objects and the source-level objects. The + description of the source-level program is maintained in LLVM metadata + in an implementation-defined format + (the C/C++ front-end currently uses working draft 7 of + the DWARF 3 + standard).

+ +

When a program is being debugged, a debugger interacts with the user and + turns the stored debug information into source-language specific information. + As such, a debugger must be aware of the source-language, and is thus tied to + a specific language or family of languages.

+ +
+ + +
+ Debug information consumers +
+ +
+ +

The role of debug information is to provide meta information normally + stripped away during the compilation process. This meta information provides + an LLVM user a relationship between generated code and the original program + source code.

+ +

Currently, debug information is consumed by the DwarfWriter to produce dwarf + information used by the gdb debugger. Other targets could use the same + information to produce stabs or other debug forms.

+ +

It would also be reasonable to use debug information to feed profiling tools + for analysis of generated code, or, tools for reconstructing the original + source from generated code.

+ +

TODO - expound a bit more.

+ +
+ + +
+ Debugging optimized code +
+ +
+ +

An extremely high priority of LLVM debugging information is to make it + interact well with optimizations and analysis. In particular, the LLVM debug + information provides the following guarantees:

+ +
    +
  • LLVM debug information always provides information to accurately read + the source-level state of the program, regardless of which LLVM + optimizations have been run, and without any modification to the + optimizations themselves. However, some optimizations may impact the + ability to modify the current state of the program with a debugger, such + as setting program variables, or calling functions that have been + deleted.
    • + +
  • LLVM optimizations gracefully interact with debugging information. If + they are not aware of debug information, they are automatically disabled + as necessary in the cases that would invalidate the debug info. This + retains the LLVM features, making it easy to write new + transformations.
    • + +
  • As desired, LLVM optimizations can be upgraded to be aware of the LLVM + debugging information, allowing them to update the debugging information + as they perform aggressive optimizations. This means that, with effort, + the LLVM optimizers could optimize debug code just as well as non-debug + code.
    • + +
  • LLVM debug information does not prevent many important optimizations from + happening (for example inlining, basic block reordering/merging/cleanup, + tail duplication, etc), further reducing the amount of the compiler that + eventually is "aware" of debugging information.
    • + +
  • LLVM debug information is automatically optimized along with the rest of + the program, using existing facilities. For example, duplicate + information is automatically merged by the linker, and unused information + is automatically removed.
    • +
+ +

Basically, the debug information allows you to compile a program with + "-O0 -g" and get full debug information, allowing you to arbitrarily + modify the program as it executes from a debugger. Compiling a program with + "-O3 -g" gives you full debug information that is always available + and accurate for reading (e.g., you get accurate stack traces despite tail + call elimination and inlining), but you might lose the ability to modify the + program and call functions where were optimized out of the program, or + inlined away completely.

+ +

LLVM test suite provides a + framework to test optimizer's handling of debugging information. It can be + run like this:

+ +
+
+% cd llvm/projects/test-suite/MultiSource/Benchmarks  # or some other level
+% make TEST=dbgopt
+
+
+ +

This will test impact of debugging information on optimization passes. If + debugging information influences optimization passes then it will be reported + as a failure. See TestingGuide for more + information on LLVM test infrastructure and how to run various tests.

+ +
+ + +
+ Debugging information format +
+ + +
+ +

LLVM debugging information has been carefully designed to make it possible + for the optimizer to optimize the program and debugging information without + necessarily having to know anything about debugging information. In + particular, te use of metadadta avoids duplicated dubgging information from + the beginning, and the global dead code elimination pass automatically + deletes debugging information for a function if it decides to delete the + function.

+ +

To do this, most of the debugging information (descriptors for types, + variables, functions, source files, etc) is inserted by the language + front-end in the form of LLVM metadata.

+ +

Debug information is designed to be agnostic about the target debugger and + debugging information representation (e.g. DWARF/Stabs/etc). It uses a + generic pass to decode the information that represents variables, types, + functions, namespaces, etc: this allows for arbitrary source-language + semantics and type-systems to be used, as long as there is a module + written for the target debugger to interpret the information.

+ +

To provide basic functionality, the LLVM debugger does have to make some + assumptions about the source-level language being debugged, though it keeps + these to a minimum. The only common features that the LLVM debugger assumes + exist are source files, + and program objects. These abstract + objects are used by a debugger to form stack traces, show information about + local variables, etc.

+ +

This section of the documentation first describes the representation aspects + common to any source-language. The next section + describes the data layout conventions used by the C and C++ front-ends.

+ +
+ + +
+ Debug information descriptors +
+ +
+ +

In consideration of the complexity and volume of debug information, LLVM + provides a specification for well formed debug descriptors.

+ +

Consumers of LLVM debug information expect the descriptors for program + objects to start in a canonical format, but the descriptors can include + additional information appended at the end that is source-language + specific. All LLVM debugging information is versioned, allowing backwards + compatibility in the case that the core structures need to change in some + way. Also, all debugging information objects start with a tag to indicate + what type of object it is. The source-language is allowed to define its own + objects, by using unreserved tag numbers. We recommend using with tags in + the range 0x1000 through 0x2000 (there is a defined enum DW_TAG_user_base = + 0x1000.)

+ +

The fields of debug descriptors used internally by LLVM + are restricted to only the simple data types int, uint, + bool, float, double, mdstring and + mdnode.

+ +
+
+!1 = metadata !{
+  uint,   ;; A tag
+  ...
+}
+
+
+ +

The first field of a descriptor is always an + uint containing a tag value identifying the content of the + descriptor. The remaining fields are specific to the descriptor. The values + of tags are loosely bound to the tag values of DWARF information entries. + However, that does not restrict the use of the information supplied to DWARF + targets. To facilitate versioning of debug information, the tag is augmented + with the current debug version (LLVMDebugVersion = 7 << 16 or 0x70000 or + 458752.)

+ +

The details of the various descriptors follow.

+ +
+ + +
+ Compile unit descriptors +
+ +
+ +
+
+!0 = metadata !{
+  i32,       ;; Tag = 17 + LLVMDebugVersion 
+             ;; (DW_TAG_compile_unit)
+  i32,       ;; Unused field. 
+  i32,       ;; DWARF language identifier (ex. DW_LANG_C89) 
+  metadata,  ;; Source file name
+  metadata,  ;; Source file directory (includes trailing slash)
+  metadata   ;; Producer (ex. "4.0.1 LLVM (LLVM research group)")
+  i1,        ;; True if this is a main compile unit. 
+  i1,        ;; True if this is optimized.
+  metadata,  ;; Flags
+  i32        ;; Runtime version
+}
+
+
+ +

These descriptors contain a source language ID for the file (we use the DWARF + 3.0 ID numbers, such as DW_LANG_C89, DW_LANG_C_plus_plus, + DW_LANG_Cobol74, etc), three strings describing the filename, + working directory of the compiler, and an identifier string for the compiler + that produced it.

+ +

Compile unit descriptors provide the root context for objects declared in a + specific source file. Global variables and top level functions would be + defined using this context. Compile unit descriptors also provide context + for source line correspondence.

+ +

Each input file is encoded as a separate compile unit in LLVM debugging + information output. However the code generator emits only one compile unit, + marked as main compile unit, in an object file's debugging information section. + Most of the, if not all, target specific tool chains expect only one compile + unit entry per object file.

+
+ + +
+ Global variable descriptors +
+ +
+ +
+
+!1 = metadata !{
+  i32,      ;; Tag = 52 + LLVMDebugVersion 
+            ;; (DW_TAG_variable)
+  i32,      ;; Unused field.
+  metadata, ;; Reference to context descriptor
+  metadata, ;; Name
+  metadata, ;; Display name (fully qualified C++ name)
+  metadata, ;; MIPS linkage name (for C++)
+  metadata, ;; Reference to compile unit where defined
+  i32,      ;; Line number where defined
+  metadata, ;; Reference to type descriptor
+  i1,       ;; True if the global is local to compile unit (static)
+  i1,       ;; True if the global is defined in the compile unit (not extern)
+  {  }*     ;; Reference to the global variable
+}
+
+
+ +

These descriptors provide debug information about globals variables. The +provide details such as name, type and where the variable is defined.

+ +
+ + +
+ Subprogram descriptors +
+ +
+ +
+
+!2 = metadata !{
+  i32,      ;; Tag = 46 + LLVMDebugVersion
+            ;; (DW_TAG_subprogram)
+  i32,      ;; Unused field.
+  metadata, ;; Reference to context descriptor
+  metadata, ;; Name
+  metadata, ;; Display name (fully qualified C++ name)
+  metadata, ;; MIPS linkage name (for C++)
+  metadata, ;; Reference to compile unit where defined
+  i32,      ;; Line number where defined
+  metadata, ;; Reference to type descriptor
+  i1,       ;; True if the global is local to compile unit (static)
+  i1        ;; True if the global is defined in the compile unit (not extern)
+}
+
+
+ +

These descriptors provide debug information about functions, methods and + subprograms. They provide details such as name, return types and the source + location where the subprogram is defined.

+ +
+ + +
+ Block descriptors +
+ +
+ +
+
+!3 = metadata !{
+  i32,     ;; Tag = 13 + LLVMDebugVersion (DW_TAG_lexical_block)
+  metadata ;; Reference to context descriptor
+}
+
+
+ +

These descriptors provide debug information about nested blocks within a + subprogram. The array of member descriptors is used to define local + variables and deeper nested blocks.

+ +
+ + +
+ Basic type descriptors +
+ +
+ +
+
+!4 = metadata !{
+  i32,      ;; Tag = 36 + LLVMDebugVersion 
+            ;; (DW_TAG_base_type)
+  metadata, ;; Reference to context (typically a compile unit)
+  metadata, ;; Name (may be "" for anonymous types)
+  metadata, ;; Reference to compile unit where defined (may be NULL)
+  i32,      ;; Line number where defined (may be 0)
+  i64,      ;; Size in bits
+  i64,      ;; Alignment in bits
+  i64,      ;; Offset in bits
+  i32,      ;; Flags
+  i32       ;; DWARF type encoding
+}
+
+
+ +

These descriptors define primitive types used in the code. Example int, bool + and float. The context provides the scope of the type, which is usually the + top level. Since basic types are not usually user defined the compile unit + and line number can be left as NULL and 0. The size, alignment and offset + are expressed in bits and can be 64 bit values. The alignment is used to + round the offset when embedded in a + composite type (example to keep float + doubles on 64 bit boundaries.) The offset is the bit offset if embedded in + a composite type.

+ +

The type encoding provides the details of the type. The values are typically + one of the following:

+ +
+
+DW_ATE_address       = 1
+DW_ATE_boolean       = 2
+DW_ATE_float         = 4
+DW_ATE_signed        = 5
+DW_ATE_signed_char   = 6
+DW_ATE_unsigned      = 7
+DW_ATE_unsigned_char = 8
+
+
+ +
+ + +
+ Derived type descriptors +
+ +
+ +
+
+!5 = metadata !{
+  i32,      ;; Tag (see below)
+  metadata, ;; Reference to context
+  metadata, ;; Name (may be "" for anonymous types)
+  metadata, ;; Reference to compile unit where defined (may be NULL)
+  i32,      ;; Line number where defined (may be 0)
+  i32,      ;; Size in bits
+  i32,      ;; Alignment in bits
+  i32,      ;; Offset in bits
+  metadata  ;; Reference to type derived from
+}
+
+
+ +

These descriptors are used to define types derived from other types. The +value of the tag varies depending on the meaning. The following are possible +tag values:

+ +
+
+DW_TAG_formal_parameter = 5
+DW_TAG_member           = 13
+DW_TAG_pointer_type     = 15
+DW_TAG_reference_type   = 16
+DW_TAG_typedef          = 22
+DW_TAG_const_type       = 38
+DW_TAG_volatile_type    = 53
+DW_TAG_restrict_type    = 55
+
+
+ +

DW_TAG_member is used to define a member of + a composite type + or subprogram. The type of the member is + the derived + type. DW_TAG_formal_parameter is used to define a member which + is a formal argument of a subprogram.

+ +

DW_TAG_typedef is used to provide a name for the derived type.

+ +

DW_TAG_pointer_type,DW_TAG_reference_type, + DW_TAG_const_type, DW_TAG_volatile_type + and DW_TAG_restrict_type are used to qualify + the derived type.

+ +

Derived type location can be determined + from the compile unit and line number. The size, alignment and offset are + expressed in bits and can be 64 bit values. The alignment is used to round + the offset when embedded in a composite + type (example to keep float doubles on 64 bit boundaries.) The offset is + the bit offset if embedded in a composite + type.

+ +

Note that the void * type is expressed as a + llvm.dbg.derivedtype.type with tag of DW_TAG_pointer_type + and NULL derived type.

+ +
+ + +
+ Composite type descriptors +
+ +
+ +
+
+!6 = metadata !{
+  i32,      ;; Tag (see below)
+  metadata, ;; Reference to context
+  metadata, ;; Name (may be "" for anonymous types)
+  metadata, ;; Reference to compile unit where defined (may be NULL)
+  i32,      ;; Line number where defined (may be 0)
+  i64,      ;; Size in bits
+  i64,      ;; Alignment in bits
+  i64,      ;; Offset in bits
+  i32,      ;; Flags
+  metadata, ;; Reference to type derived from
+  metadata, ;; Reference to array of member descriptors
+  i32       ;; Runtime languages
+}
+
+
+ +

These descriptors are used to define types that are composed of 0 or more +elements. The value of the tag varies depending on the meaning. The following +are possible tag values:

+ +
+
+DW_TAG_array_type       = 1
+DW_TAG_enumeration_type = 4
+DW_TAG_structure_type   = 19
+DW_TAG_union_type       = 23
+DW_TAG_vector_type      = 259
+DW_TAG_subroutine_type  = 21
+DW_TAG_inheritance      = 28
+
+
+ +

The vector flag indicates that an array type is a native packed vector.

+ +

The members of array types (tag = DW_TAG_array_type) or vector types + (tag = DW_TAG_vector_type) are subrange + descriptors, each representing the range of subscripts at that level of + indexing.

+ +

The members of enumeration types (tag = DW_TAG_enumeration_type) are + enumerator descriptors, each representing + the definition of enumeration value for the set.

+ +

The members of structure (tag = DW_TAG_structure_type) or union (tag + = DW_TAG_union_type) types are any one of + the basic, + derived + or composite type descriptors, each + representing a field member of the structure or union.

+ +

For C++ classes (tag = DW_TAG_structure_type), member descriptors + provide information about base classes, static members and member + functions. If a member is a derived type + descriptor and has a tag of DW_TAG_inheritance, then the type + represents a base class. If the member of is + a global variable descriptor then it + represents a static member. And, if the member is + a subprogram descriptor then it represents + a member function. For static members and member + functions, getName() returns the members link or the C++ mangled + name. getDisplayName() the simplied version of the name.

+ +

The first member of subroutine (tag = DW_TAG_subroutine_type) type + elements is the return type for the subroutine. The remaining elements are + the formal arguments to the subroutine.

+ +

Composite type location can be + determined from the compile unit and line number. The size, alignment and + offset are expressed in bits and can be 64 bit values. The alignment is used + to round the offset when embedded in + a composite type (as an example, to keep + float doubles on 64 bit boundaries.) The offset is the bit offset if embedded + in a composite type.

+ +
+ + +
+ Subrange descriptors +
+ +
+ +
+
+%llvm.dbg.subrange.type = type {
+  i32,    ;; Tag = 33 + LLVMDebugVersion (DW_TAG_subrange_type)
+  i64,    ;; Low value
+  i64     ;; High value
+}
+
+
+ +

These descriptors are used to define ranges of array subscripts for an array + composite type. The low value defines + the lower bounds typically zero for C/C++. The high value is the upper + bounds. Values are 64 bit. High - low + 1 is the size of the array. If low + == high the array will be unbounded.

+ +
+ + +
+ Enumerator descriptors +
+ +
+ +
+
+!6 = metadata !{
+  i32,      ;; Tag = 40 + LLVMDebugVersion 
+            ;; (DW_TAG_enumerator)
+  metadata, ;; Name
+  i64       ;; Value
+}
+
+
+ +

These descriptors are used to define members of an + enumeration composite type, it + associates the name to the value.

+ +
+ + +
+ Local variables +
+ +
+ +
+
+!7 = metadata !{
+  i32,      ;; Tag (see below)
+  metadata, ;; Context
+  metadata, ;; Name
+  metadata, ;; Reference to compile unit where defined
+  i32,      ;; Line number where defined
+  metadata  ;; Type descriptor
+}
+
+
+ +

These descriptors are used to define variables local to a sub program. The + value of the tag depends on the usage of the variable:

+ +
+
+DW_TAG_auto_variable   = 256
+DW_TAG_arg_variable    = 257
+DW_TAG_return_variable = 258
+
+
+ +

An auto variable is any variable declared in the body of the function. An + argument variable is any variable that appears as a formal argument to the + function. A return variable is used to track the result of a function and + has no source correspondent.

+ +

The context is either the subprogram or block where the variable is defined. + Name the source variable name. Compile unit and line indicate where the + variable was defined. Type descriptor defines the declared type of the + variable.

+ +
+ + +
+ Debugger intrinsic functions +
+ +
+ +

LLVM uses several intrinsic functions (name prefixed with "llvm.dbg") to + provide debug information at various points in generated code.

+ +
+ + +
+ llvm.dbg.declare +
+ +
+
+  void %llvm.dbg.declare( { } *, metadata )
+
+ +

This intrinsic provides information about a local element (ex. variable.) The + first argument is the alloca for the variable, cast to a { }*. The + second argument is + the %llvm.dbg.variable containing + the description of the variable.

+ +
+ + +
+ llvm.dbg.value +
+ +
+
+  void %llvm.dbg.value( metadata, i64, metadata )
+
+ +

This intrinsic provides information when a user source variable is set to a + new value. The first argument is the new value (wrapped as metadata). The + second argument is the offset in the user source variable where the new value + is written. The third argument is + the %llvm.dbg.variable containing + the description of the user source variable.

+ +
+ + +
+ Object lifetimes and scoping +
+ +
+

In many languages, the local variables in functions can have their lifetimes + or scopes limited to a subset of a function. In the C family of languages, + for example, variables are only live (readable and writable) within the + source block that they are defined in. In functional languages, values are + only readable after they have been defined. Though this is a very obvious + concept, it is non-trivial to model in LLVM, because it has no notion of + scoping in this sense, and does not want to be tied to a language's scoping + rules.

+ +

In order to handle this, the LLVM debug format uses the metadata attached to + llvm instructions to encode line nuber and scoping information. Consider the + following C fragment, for example:

+ +
+
+1.  void foo() {
+2.    int X = 21;
+3.    int Y = 22;
+4.    {
+5.      int Z = 23;
+6.      Z = X;
+7.    }
+8.    X = Y;
+9.  }
+
+
+ +

Compiled to LLVM, this function would be represented like this:

+ +
+
+define void @foo() nounwind ssp {
+entry:
+  %X = alloca i32, align 4                        ; <i32*> [#uses=4]
+  %Y = alloca i32, align 4                        ; <i32*> [#uses=4]
+  %Z = alloca i32, align 4                        ; <i32*> [#uses=3]
+  %0 = bitcast i32* %X to { }*                    ; <{ }*> [#uses=1]
+  call void @llvm.dbg.declare({ }* %0, metadata !0), !dbg !7
+  store i32 21, i32* %X, !dbg !8
+  %1 = bitcast i32* %Y to { }*                    ; <{ }*> [#uses=1]
+  call void @llvm.dbg.declare({ }* %1, metadata !9), !dbg !10
+  store i32 22, i32* %Y, !dbg !11
+  %2 = bitcast i32* %Z to { }*                    ; <{ }*> [#uses=1]
+  call void @llvm.dbg.declare({ }* %2, metadata !12), !dbg !14
+  store i32 23, i32* %Z, !dbg !15
+  %tmp = load i32* %X, !dbg !16                   ; <i32> [#uses=1]
+  %tmp1 = load i32* %Y, !dbg !16                  ; <i32> [#uses=1]
+  %add = add nsw i32 %tmp, %tmp1, !dbg !16        ; <i32> [#uses=1]
+  store i32 %add, i32* %Z, !dbg !16
+  %tmp2 = load i32* %Y, !dbg !17                  ; <i32> [#uses=1]
+  store i32 %tmp2, i32* %X, !dbg !17
+  ret void, !dbg !18
+}
+
+declare void @llvm.dbg.declare({ }*, metadata) nounwind readnone
+
+!0 = metadata !{i32 459008, metadata !1, metadata !"X", 
+                metadata !3, i32 2, metadata !6}; [ DW_TAG_auto_variable ]
+!1 = metadata !{i32 458763, metadata !2}; [DW_TAG_lexical_block ]
+!2 = metadata !{i32 458798, i32 0, metadata !3, metadata !"foo", metadata !"foo", 
+               metadata !"foo", metadata !3, i32 1, metadata !4, 
+               i1 false, i1 true}; [DW_TAG_subprogram ]
+!3 = metadata !{i32 458769, i32 0, i32 12, metadata !"foo.c", 
+                metadata !"/private/tmp", metadata !"clang 1.1", i1 true, 
+                i1 false, metadata !"", i32 0}; [DW_TAG_compile_unit ]
+!4 = metadata !{i32 458773, metadata !3, metadata !"", null, i32 0, i64 0, i64 0, 
+                i64 0, i32 0, null, metadata !5, i32 0}; [DW_TAG_subroutine_type ]
+!5 = metadata !{null}
+!6 = metadata !{i32 458788, metadata !3, metadata !"int", metadata !3, i32 0, 
+                i64 32, i64 32, i64 0, i32 0, i32 5}; [DW_TAG_base_type ]
+!7 = metadata !{i32 2, i32 7, metadata !1, null}
+!8 = metadata !{i32 2, i32 3, metadata !1, null}
+!9 = metadata !{i32 459008, metadata !1, metadata !"Y", metadata !3, i32 3, 
+                metadata !6}; [ DW_TAG_auto_variable ]
+!10 = metadata !{i32 3, i32 7, metadata !1, null}
+!11 = metadata !{i32 3, i32 3, metadata !1, null}
+!12 = metadata !{i32 459008, metadata !13, metadata !"Z", metadata !3, i32 5, 
+                 metadata !6}; [ DW_TAG_auto_variable ]
+!13 = metadata !{i32 458763, metadata !1}; [DW_TAG_lexical_block ]
+!14 = metadata !{i32 5, i32 9, metadata !13, null}
+!15 = metadata !{i32 5, i32 5, metadata !13, null}
+!16 = metadata !{i32 6, i32 5, metadata !13, null}
+!17 = metadata !{i32 8, i32 3, metadata !1, null}
+!18 = metadata !{i32 9, i32 1, metadata !2, null}
+
+
+ +

This example illustrates a few important details about LLVM debugging + information. In particular, it shows how the llvm.dbg.declare + intrinsic and location information, which are attached to an instruction, + are applied together to allow a debugger to analyze the relationship between + statements, variable definitions, and the code used to implement the + function.

+ +
+
+call void @llvm.dbg.declare({ }* %0, metadata !0), !dbg !7   
+
+
+ +

The first intrinsic + %llvm.dbg.declare + encodes debugging information for the variable X. The metadata + !dbg !7 attached to the intrinsic provides scope information for the + variable X.

+ +
+
+!7 = metadata !{i32 2, i32 7, metadata !1, null}
+!1 = metadata !{i32 458763, metadata !2}; [DW_TAG_lexical_block ]
+!2 = metadata !{i32 458798, i32 0, metadata !3, metadata !"foo", 
+                metadata !"foo", metadata !"foo", metadata !3, i32 1, 
+                metadata !4, i1 false, i1 true}; [DW_TAG_subprogram ]   
+
+
+ +

Here !7 is metadata providing location information. It has four + fields: line number, column number, scope, and original scope. The original + scope represents inline location if this instruction is inlined inside a + caller, and is null otherwise. In this example, scope is encoded by + !1. !1 represents a lexical block inside the scope + !2, where !2 is a + subprogram descriptor. This way the + location information attached to the intrinsics indicates that the + variable X is declared at line number 2 at a function level scope in + function foo.

+ +

Now lets take another example.

+ +
+
+call void @llvm.dbg.declare({ }* %2, metadata !12), !dbg !14
+
+
+ +

The second intrinsic + %llvm.dbg.declare + encodes debugging information for variable Z. The metadata + !dbg !14 attached to the intrinsic provides scope information for + the variable Z.

+ +
+
+!13 = metadata !{i32 458763, metadata !1}; [DW_TAG_lexical_block ]
+!14 = metadata !{i32 5, i32 9, metadata !13, null}
+
+
+ +

Here !14 indicates that Z is declaread at line number 5 and + column number 9 inside of lexical scope !13. The lexical scope + itself resides inside of lexical scope !1 described above.

+ +

The scope information attached with each instruction provides a + straightforward way to find instructions covered by a scope.

+ +
+ + +
+ C/C++ front-end specific debug information +
+ + +
+ +

The C and C++ front-ends represent information about the program in a format + that is effectively identical + to DWARF 3.0 in + terms of information content. This allows code generators to trivially + support native debuggers by generating standard dwarf information, and + contains enough information for non-dwarf targets to translate it as + needed.

+ +

This section describes the forms used to represent C and C++ programs. Other + languages could pattern themselves after this (which itself is tuned to + representing programs in the same way that DWARF 3 does), or they could + choose to provide completely different forms if they don't fit into the DWARF + model. As support for debugging information gets added to the various LLVM + source-language front-ends, the information used should be documented + here.

+ +

The following sections provide examples of various C/C++ constructs and the + debug information that would best describe those constructs.

+ +
+ + +
+ C/C++ source file information +
+ +
+ +

Given the source files MySource.cpp and MyHeader.h located + in the directory /Users/mine/sources, the following code:

+ +
+
+#include "MyHeader.h"
+
+int main(int argc, char *argv[]) {
+  return 0;
+}
+
+
+ +

a C/C++ front-end would generate the following descriptors:

+ +
+
+...
+;;
+;; Define the compile unit for the source file "/Users/mine/sources/MySource.cpp".
+;;
+!3 = metadata !{
+  i32 458769,    ;; Tag
+  i32 0,         ;; Unused
+  i32 4,         ;; Language Id
+  metadata !"MySource.cpp", 
+  metadata !"/Users/mine/sources", 
+  metadata !"4.2.1 (Based on Apple Inc. build 5649) (LLVM build 00)", 
+  i1 true,       ;; Main Compile Unit
+  i1 false,      ;; Optimized compile unit
+  metadata !"",  ;; Compiler flags
+  i32 0}         ;; Runtime version
+
+;;
+;; Define the compile unit for the header file "/Users/mine/sources/MyHeader.h".
+;;
+!1 = metadata !{
+  i32 458769,    ;; Tag
+  i32 0,         ;; Unused
+  i32 4,         ;; Language Id
+  metadata !"MyHeader.h", 
+  metadata !"/Users/mine/sources", 
+  metadata !"4.2.1 (Based on Apple Inc. build 5649) (LLVM build 00)", 
+  i1 false,      ;; Main Compile Unit
+  i1 false,      ;; Optimized compile unit
+  metadata !"",  ;; Compiler flags
+  i32 0}         ;; Runtime version
+
+...
+
+
+ +
+ + +
+ C/C++ global variable information +
+ +
+ +

Given an integer global variable declared as follows:

+ +
+
+int MyGlobal = 100;
+
+
+ +

a C/C++ front-end would generate the following descriptors:

+ +
+
+;;
+;; Define the global itself.
+;;
+%MyGlobal = global int 100
+...
+;;
+;; List of debug info of globals
+;;
+!llvm.dbg.gv = !{!0}
+
+;;
+;; Define the global variable descriptor.  Note the reference to the global
+;; variable anchor and the global variable itself.
+;;
+!0 = metadata !{
+  i32 458804,              ;; Tag
+  i32 0,                   ;; Unused
+  metadata !1,             ;; Context
+  metadata !"MyGlobal",    ;; Name
+  metadata !"MyGlobal",    ;; Display Name
+  metadata !"MyGlobal",    ;; Linkage Name
+  metadata !1,             ;; Compile Unit
+  i32 1,                   ;; Line Number
+  metadata !2,             ;; Type
+  i1 false,                ;; Is a local variable
+  i1 true,                 ;; Is this a definition
+  i32* @MyGlobal           ;; The global variable
+}
+
+;;
+;; Define the basic type of 32 bit signed integer.  Note that since int is an
+;; intrinsic type the source file is NULL and line 0.
+;;    
+!2 = metadata !{
+  i32 458788,              ;; Tag
+  metadata !1,             ;; Context
+  metadata !"int",         ;; Name
+  metadata !1,             ;; Compile Unit
+  i32 0,                   ;; Line number
+  i64 32,                  ;; Size in Bits
+  i64 32,                  ;; Align in Bits
+  i64 0,                   ;; Offset in Bits
+  i32 0,                   ;; Flags
+  i32 5                    ;; Encoding
+}
+
+
+
+ +
+ + +
+ C/C++ function information +
+ +
+ +

Given a function declared as follows:

+ +
+
+int main(int argc, char *argv[]) {
+  return 0;
+}
+
+
+ +

a C/C++ front-end would generate the following descriptors:

+ +
+
+;;
+;; Define the anchor for subprograms.  Note that the second field of the
+;; anchor is 46, which is the same as the tag for subprograms
+;; (46 = DW_TAG_subprogram.)
+;;
+!0 = metadata !{
+  i32 458798,        ;; Tag
+  i32 0,             ;; Unused
+  metadata !1,       ;; Context
+  metadata !"main",  ;; Name
+  metadata !"main",  ;; Display name
+  metadata !"main",  ;; Linkage name
+  metadata !1,       ;; Compile unit
+  i32 1,             ;; Line number
+  metadata !2,       ;; Type
+  i1 false,          ;; Is local 
+  i1 true            ;; Is definition
+}
+;;
+;; Define the subprogram itself.
+;;
+define i32 @main(i32 %argc, i8** %argv) {
+...
+}
+
+
+ +
+ + +
+ C/C++ basic types +
+ +
+ +

The following are the basic type descriptors for C/C++ core types:

+ +
+ + +
+ bool +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"bool",  ;; Name
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 8,             ;; Size in Bits
+  i64 8,             ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 2              ;; Encoding
+}
+
+
+ +
+ + +
+ char +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"char",  ;; Name
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 8,             ;; Size in Bits
+  i64 8,             ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 6              ;; Encoding
+}
+
+
+ +
+ + +
+ unsigned char +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"unsigned char", 
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 8,             ;; Size in Bits
+  i64 8,             ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 8              ;; Encoding
+}
+
+
+ +
+ + +
+ short +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"short int",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 16,            ;; Size in Bits
+  i64 16,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 5              ;; Encoding
+}
+
+
+ +
+ + +
+ unsigned short +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"short unsigned int",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 16,            ;; Size in Bits
+  i64 16,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 7              ;; Encoding
+}
+
+
+ +
+ + +
+ int +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"int",   ;; Name
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 32,            ;; Size in Bits
+  i64 32,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 5              ;; Encoding
+}
+
+ +
+ + +
+ unsigned int +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"unsigned int",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 32,            ;; Size in Bits
+  i64 32,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 7              ;; Encoding
+}
+
+
+ +
+ + +
+ long long +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"long long int",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 64,            ;; Size in Bits
+  i64 64,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 5              ;; Encoding
+}
+
+
+ +
+ + +
+ unsigned long long +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"long long unsigned int",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 64,            ;; Size in Bits
+  i64 64,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 7              ;; Encoding
+}
+
+
+ +
+ + +
+ float +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"float",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 32,            ;; Size in Bits
+  i64 32,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 4              ;; Encoding
+}
+
+
+ +
+ + +
+ double +
+ +
+ +
+
+!2 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"double",;; Name
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 64,            ;; Size in Bits
+  i64 64,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 4              ;; Encoding
+}
+
+
+ +
+ + +
+ C/C++ derived types +
+ +
+ +

Given the following as an example of C/C++ derived type:

+ +
+
+typedef const int *IntPtr;
+
+
+ +

a C/C++ front-end would generate the following descriptors:

+ +
+
+;;
+;; Define the typedef "IntPtr".
+;;
+!2 = metadata !{
+  i32 458774,          ;; Tag
+  metadata !1,         ;; Context
+  metadata !"IntPtr",  ;; Name
+  metadata !3,         ;; Compile unit
+  i32 0,               ;; Line number
+  i64 0,               ;; Size in bits
+  i64 0,               ;; Align in bits
+  i64 0,               ;; Offset in bits
+  i32 0,               ;; Flags
+  metadata !4          ;; Derived From type
+}
+
+;;
+;; Define the pointer type.
+;;
+!4 = metadata !{
+  i32 458767,          ;; Tag
+  metadata !1,         ;; Context
+  metadata !"",        ;; Name
+  metadata !1,         ;; Compile unit
+  i32 0,               ;; Line number
+  i64 64,              ;; Size in bits
+  i64 64,              ;; Align in bits
+  i64 0,               ;; Offset in bits
+  i32 0,               ;; Flags
+  metadata !5          ;; Derived From type
+}
+;;
+;; Define the const type.
+;;
+!5 = metadata !{
+  i32 458790,          ;; Tag
+  metadata !1,         ;; Context
+  metadata !"",        ;; Name
+  metadata !1,         ;; Compile unit
+  i32 0,               ;; Line number
+  i64 32,              ;; Size in bits
+  i64 32,              ;; Align in bits
+  i64 0,               ;; Offset in bits
+  i32 0,               ;; Flags
+  metadata !6          ;; Derived From type
+}
+;;
+;; Define the int type.
+;;
+!6 = metadata !{
+  i32 458788,          ;; Tag
+  metadata !1,         ;; Context
+  metadata !"int",     ;; Name
+  metadata !1,         ;; Compile unit
+  i32 0,               ;; Line number
+  i64 32,              ;; Size in bits
+  i64 32,              ;; Align in bits
+  i64 0,               ;; Offset in bits
+  i32 0,               ;; Flags
+  5                    ;; Encoding
+}
+
+
+ +
+ + +
+ C/C++ struct/union types +
+ +
+ +

Given the following as an example of C/C++ struct type:

+ +
+
+struct Color {
+  unsigned Red;
+  unsigned Green;
+  unsigned Blue;
+};
+
+
+ +

a C/C++ front-end would generate the following descriptors:

+ +
+
+;;
+;; Define basic type for unsigned int.
+;;
+!5 = metadata !{
+  i32 458788,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"unsigned int",
+  metadata !1,       ;; Compile Unit
+  i32 0,             ;; Line number
+  i64 32,            ;; Size in Bits
+  i64 32,            ;; Align in Bits
+  i64 0,             ;; Offset in Bits
+  i32 0,             ;; Flags
+  i32 7              ;; Encoding
+}
+;;
+;; Define composite type for struct Color.
+;;
+!2 = metadata !{
+  i32 458771,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"Color", ;; Name
+  metadata !1,       ;; Compile unit
+  i32 1,             ;; Line number
+  i64 96,            ;; Size in bits
+  i64 32,            ;; Align in bits
+  i64 0,             ;; Offset in bits
+  i32 0,             ;; Flags
+  null,              ;; Derived From
+  metadata !3,       ;; Elements
+  i32 0              ;; Runtime Language
+}
+
+;;
+;; Define the Red field.
+;;
+!4 = metadata !{
+  i32 458765,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"Red",   ;; Name
+  metadata !1,       ;; Compile Unit
+  i32 2,             ;; Line number
+  i64 32,            ;; Size in bits
+  i64 32,            ;; Align in bits
+  i64 0,             ;; Offset in bits
+  i32 0,             ;; Flags
+  metadata !5        ;; Derived From type
+}
+
+;;
+;; Define the Green field.
+;;
+!6 = metadata !{
+  i32 458765,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"Green", ;; Name
+  metadata !1,       ;; Compile Unit
+  i32 3,             ;; Line number
+  i64 32,            ;; Size in bits
+  i64 32,            ;; Align in bits
+  i64 32,             ;; Offset in bits
+  i32 0,             ;; Flags
+  metadata !5        ;; Derived From type
+}
+
+;;
+;; Define the Blue field.
+;;
+!7 = metadata !{
+  i32 458765,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"Blue",  ;; Name
+  metadata !1,       ;; Compile Unit
+  i32 4,             ;; Line number
+  i64 32,            ;; Size in bits
+  i64 32,            ;; Align in bits
+  i64 64,             ;; Offset in bits
+  i32 0,             ;; Flags
+  metadata !5        ;; Derived From type
+}
+
+;;
+;; Define the array of fields used by the composite type Color.
+;;
+!3 = metadata !{metadata !4, metadata !6, metadata !7}
+
+
+ +
+ + +
+ C/C++ enumeration types +
+ +
+ +

Given the following as an example of C/C++ enumeration type:

+ +
+
+enum Trees {
+  Spruce = 100,
+  Oak = 200,
+  Maple = 300
+};
+
+
+ +

a C/C++ front-end would generate the following descriptors:

+ +
+
+;;
+;; Define composite type for enum Trees
+;;
+!2 = metadata !{
+  i32 458756,        ;; Tag
+  metadata !1,       ;; Context
+  metadata !"Trees", ;; Name
+  metadata !1,       ;; Compile unit
+  i32 1,             ;; Line number
+  i64 32,            ;; Size in bits
+  i64 32,            ;; Align in bits
+  i64 0,             ;; Offset in bits
+  i32 0,             ;; Flags
+  null,              ;; Derived From type
+  metadata !3,       ;; Elements
+  i32 0              ;; Runtime language
+}
+
+;;
+;; Define the array of enumerators used by composite type Trees.
+;;
+!3 = metadata !{metadata !4, metadata !5, metadata !6}
+
+;;
+;; Define Spruce enumerator.
+;;
+!4 = metadata !{i32 458792, metadata !"Spruce", i64 100}
+
+;;
+;; Define Oak enumerator.
+;;
+!5 = metadata !{i32 458792, metadata !"Oak", i64 200}
+
+;;
+;; Define Maple enumerator.
+;;
+!6 = metadata !{i32 458792, metadata !"Maple", i64 300}
+
+
+
+ +
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + Chris Lattner
+ LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-03-11 18:16:00 -0600 (Thu, 11 Mar 2010) $ +
+ + + Added: www-releases/trunk/2.7/docs/SystemLibrary.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/SystemLibrary.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/SystemLibrary.html (added) +++ www-releases/trunk/2.7/docs/SystemLibrary.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,319 @@ + + + + System Library + + + + +
System Library
+ + +
+

Written by Reid Spencer

+
+ + + +
Abstract
+
+

This document provides some details on LLVM's System Library, located in + the source at lib/System and include/llvm/System. The + library's purpose is to shield LLVM from the differences between operating + systems for the few services LLVM needs from the operating system. Much of + LLVM is written using portability features of standard C++. However, in a few + areas, system dependent facilities are needed and the System Library is the + wrapper around those system calls.

+

By centralizing LLVM's use of operating system interfaces, we make it + possible for the LLVM tool chain and runtime libraries to be more easily + ported to new platforms since (theoretically) only lib/System needs + to be ported. This library also unclutters the rest of LLVM from #ifdef use + and special cases for specific operating systems. Such uses are replaced + with simple calls to the interfaces provided in include/llvm/System. +

+

Note that the System Library is not intended to be a complete operating + system wrapper (such as the Adaptive Communications Environment (ACE) or + Apache Portable Runtime (APR)), but only provides the functionality necessary + to support LLVM. +

The System Library was written by Reid Spencer who formulated the + design based on similar work originating from the eXtensible Programming + System (XPS). Several people helped with the effort; especially, + Jeff Cohen and Henrik Bach on the Win32 port.

+
+ + +
+ Keeping LLVM Portable +
+
+

In order to keep LLVM portable, LLVM developers should adhere to a set of + portability rules associated with the System Library. Adherence to these rules + should help the System Library achieve its goal of shielding LLVM from the + variations in operating system interfaces and doing so efficiently. The + following sections define the rules needed to fulfill this objective.

+
+ + +
Don't Include System Headers +
+
+

Except in lib/System, no LLVM source code should directly + #include a system header. Care has been taken to remove all such + #includes from LLVM while lib/System was being + developed. Specifically this means that header files like "unistd.h", + "windows.h", "stdio.h", and "string.h" are forbidden to be included by LLVM + source code outside the implementation of lib/System.

+

To obtain system-dependent functionality, existing interfaces to the system + found in include/llvm/System should be used. If an appropriate + interface is not available, it should be added to include/llvm/System + and implemented in lib/System for all supported platforms.

+
+ + +
Don't Expose System Headers +
+
+

The System Library must shield LLVM from all system headers. To + obtain system level functionality, LLVM source must + #include "llvm/System/Thing.h" and nothing else. This means that + Thing.h cannot expose any system header files. This protects LLVM + from accidentally using system specific functionality and only allows it + via the lib/System interface.

+
+ + +
Use Standard C Headers
+
+

The standard C headers (the ones beginning with "c") are allowed + to be exposed through the lib/System interface. These headers and + the things they declare are considered to be platform agnostic. LLVM source + files may include them directly or obtain their inclusion through + lib/System interfaces.

+
+ + +
Use Standard C++ Headers +
+
+

The standard C++ headers from the standard C++ library and + standard template library may be exposed through the lib/System + interface. These headers and the things they declare are considered to be + platform agnostic. LLVM source files may include them or obtain their + inclusion through lib/System interfaces.

+
+ + +
High Level Interface
+
+

The entry points specified in the interface of lib/System must be aimed at + completing some reasonably high level task needed by LLVM. We do not want to + simply wrap each operating system call. It would be preferable to wrap several + operating system calls that are always used in conjunction with one another by + LLVM.

+

For example, consider what is needed to execute a program, wait for it to + complete, and return its result code. On Unix, this involves the following + operating system calls: getenv, fork, execve, and wait. The + correct thing for lib/System to provide is a function, say + ExecuteProgramAndWait, that implements the functionality completely. + what we don't want is wrappers for the operating system calls involved.

+

There must not be a one-to-one relationship between operating + system calls and the System library's interface. Any such interface function + will be suspicious.

+
+ + +
No Unused Functionality
+
+

There must be no functionality specified in the interface of lib/System + that isn't actually used by LLVM. We're not writing a general purpose + operating system wrapper here, just enough to satisfy LLVM's needs. And, LLVM + doesn't need much. This design goal aims to keep the lib/System interface + small and understandable which should foster its actual use and adoption.

+
+ + +
No Duplicate Implementations +
+
+

The implementation of a function for a given platform must be written + exactly once. This implies that it must be possible to apply a function's + implementation to multiple operating systems if those operating systems can + share the same implementation. This rule applies to the set of operating + systems supported for a given class of operating system (e.g. Unix, Win32). +

+
+ + +
No Virtual Methods
+
+

The System Library interfaces can be called quite frequently by LLVM. In + order to make those calls as efficient as possible, we discourage the use of + virtual methods. There is no need to use inheritance for implementation + differences, it just adds complexity. The #include mechanism works + just fine.

+
+ + +
No Exposed Functions
+
+

Any functions defined by system libraries (i.e. not defined by lib/System) + must not be exposed through the lib/System interface, even if the header file + for that function is not exposed. This prevents inadvertent use of system + specific functionality.

+

For example, the stat system call is notorious for having + variations in the data it provides. lib/System must not declare + stat nor allow it to be declared. Instead it should provide its own + interface to discovering information about files and directories. Those + interfaces may be implemented in terms of stat but that is strictly + an implementation detail. The interface provided by the System Library must + be implemented on all platforms (even those without stat).

+
+ + +
No Exposed Data
+
+

Any data defined by system libraries (i.e. not defined by lib/System) must + not be exposed through the lib/System interface, even if the header file for + that function is not exposed. As with functions, this prevents inadvertent use + of data that might not exist on all platforms.

+
+ + +
Minimize Soft Errors
+
+

Operating system interfaces will generally provide error results for every + little thing that could go wrong. In almost all cases, you can divide these + error results into two groups: normal/good/soft and abnormal/bad/hard. That + is, some of the errors are simply information like "file not found", + "insufficient privileges", etc. while other errors are much harder like + "out of space", "bad disk sector", or "system call interrupted". We'll call + the first group "soft" errors and the second group "hard" + errors.

+

lib/System must always attempt to minimize soft errors. + This is a design requirement because the + minimization of soft errors can affect the granularity and the nature of the + interface. In general, if you find that you're wanting to throw soft errors, + you must review the granularity of the interface because it is likely you're + trying to implement something that is too low level. The rule of thumb is to + provide interface functions that can't fail, except when faced with + hard errors.

+

For a trivial example, suppose we wanted to add an "OpenFileForWriting" + function. For many operating systems, if the file doesn't exist, attempting + to open the file will produce an error. However, lib/System should not + simply throw that error if it occurs because its a soft error. The problem + is that the interface function, OpenFileForWriting is too low level. It should + be OpenOrCreateFileForWriting. In the case of the soft "doesn't exist" error, + this function would just create it and then open it for writing.

+

This design principle needs to be maintained in lib/System because it + avoids the propagation of soft error handling throughout the rest of LLVM. + Hard errors will generally just cause a termination for an LLVM tool so don't + be bashful about throwing them.

+

Rules of thumb:

+
    +
  1. Don't throw soft errors, only hard errors.
    2. +
  2. If you're tempted to throw a soft error, re-think the interface.
    3. +
  3. Handle internally the most common normal/good/soft error conditions + so the rest of LLVM doesn't have to.
    4. +
+
+ + +
No throw Specifications +
+
+

None of the lib/System interface functions may be declared with C++ + throw() specifications on them. This requirement makes sure that the + compiler does not insert additional exception handling code into the interface + functions. This is a performance consideration: lib/System functions are at + the bottom of many call chains and as such can be frequently called. We + need them to be as efficient as possible. However, no routines in the + system library should actually throw exceptions.

+
+ + +
Code Organization
+
+

Implementations of the System Library interface are separated by their + general class of operating system. Currently only Unix and Win32 classes are + defined but more could be added for other operating system classifications. + To distinguish which implementation to compile, the code in lib/System uses + the LLVM_ON_UNIX and LLVM_ON_WIN32 #defines provided via configure through the + llvm/Config/config.h file. Each source file in lib/System, after implementing + the generic (operating system independent) functionality needs to include the + correct implementation using a set of #if defined(LLVM_ON_XYZ) + directives. For example, if we had lib/System/File.cpp, we'd expect to see in + that file:

+ 

+  #if defined(LLVM_ON_UNIX)
+  #include "Unix/File.cpp"
+  #endif
+  #if defined(LLVM_ON_WIN32)
+  #include "Win32/File.cpp"
+  #endif
+
+

The implementation in lib/System/Unix/File.cpp should handle all Unix + variants. The implementation in lib/System/Win32/File.cpp should handle all + Win32 variants. What this does is quickly differentiate the basic class of + operating system that will provide the implementation. The specific details + for a given platform must still be determined through the use of + #ifdef.

+
+ + +
Consistent Semantics
+
+

The implementation of a lib/System interface can vary drastically between + platforms. That's okay as long as the end result of the interface function + is the same. For example, a function to create a directory is pretty straight + forward on all operating system. System V IPC on the other hand isn't even + supported on all platforms. Instead of "supporting" System V IPC, lib/System + should provide an interface to the basic concept of inter-process + communications. The implementations might use System V IPC if that was + available or named pipes, or whatever gets the job done effectively for a + given operating system. In all cases, the interface and the implementation + must be semantically consistent.

+
+ + +
Bug 351
+
+

See bug 351 + for further details on the progress of this work

+
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + Reid Spencer
+ LLVM Compiler Infrastructure
+ Last modified: $Date: 2009-07-17 16:11:24 -0500 (Fri, 17 Jul 2009) $ +
+ + Added: www-releases/trunk/2.7/docs/TableGenFundamentals.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/TableGenFundamentals.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/TableGenFundamentals.html (added) +++ www-releases/trunk/2.7/docs/TableGenFundamentals.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,804 @@ + + + + TableGen Fundamentals + + + + +
TableGen Fundamentals
+ +
+ +
+ +
+

Written by Chris Lattner

+
+ + +
Introduction
+ + +
+ +

TableGen's purpose is to help a human develop and maintain records of +domain-specific information. Because there may be a large number of these +records, it is specifically designed to allow writing flexible descriptions and +for common features of these records to be factored out. This reduces the +amount of duplication in the description, reduces the chance of error, and +makes it easier to structure domain specific information.

+ +

The core part of TableGen parses a file, instantiates +the declarations, and hands the result off to a domain-specific "TableGen backend" for processing. The current major user +of TableGen is the LLVM code generator.

+ +

Note that if you work on TableGen much, and use emacs or vim, that you can +find an emacs "TableGen mode" and a vim language file in the +llvm/utils/emacs and llvm/utils/vim directories of your LLVM +distribution, respectively.

+ +
+ + +
Basic concepts
+ +
+ +

TableGen files consist of two key parts: 'classes' and 'definitions', both +of which are considered 'records'.

+ +

TableGen records have a unique name, a list of values, and a list of +superclasses. The list of values is the main data that TableGen builds for each +record; it is this that holds the domain specific information for the +application. The interpretation of this data is left to a specific TableGen backend, but the structure and format rules are +taken care of and are fixed by TableGen.

+ +

TableGen definitions are the concrete form of 'records'. These +generally do not have any undefined values, and are marked with the +'def' keyword.

+ +

TableGen classes are abstract records that are used to build and +describe other records. These 'classes' allow the end-user to build +abstractions for either the domain they are targeting (such as "Register", +"RegisterClass", and "Instruction" in the LLVM code generator) or for the +implementor to help factor out common properties of records (such as "FPInst", +which is used to represent floating point instructions in the X86 backend). +TableGen keeps track of all of the classes that are used to build up a +definition, so the backend can find all definitions of a particular class, such +as "Instruction".

+ +

TableGen multiclasses are groups of abstract records that are +instantiated all at once. Each instantiation can result in multiple +TableGen definitions. If a multiclass inherits from another multiclass, +the definitions in the sub-multiclass become part of the current +multiclass, as if they were declared in the current multiclass.

+ +
+ + +
An example record
+ +
+ +

With no other arguments, TableGen parses the specified file and prints out +all of the classes, then all of the definitions. This is a good way to see what +the various definitions expand to fully. Running this on the X86.td +file prints this (at the time of this writing):

+ +
+
+...
+def ADD32rr {   // Instruction X86Inst I
+  string Namespace = "X86";
+  dag OutOperandList = (outs GR32:$dst);
+  dag InOperandList = (ins GR32:$src1, GR32:$src2);
+  string AsmString = "add{l}\t{$src2, $dst|$dst, $src2}";
+  list<dag> Pattern = [(set GR32:$dst, (add GR32:$src1, GR32:$src2))];
+  list<Register> Uses = [];
+  list<Register> Defs = [EFLAGS];
+  list<Predicate> Predicates = [];
+  int CodeSize = 3;
+  int AddedComplexity = 0;
+  bit isReturn = 0;
+  bit isBranch = 0;
+  bit isIndirectBranch = 0;
+  bit isBarrier = 0;
+  bit isCall = 0;
+  bit canFoldAsLoad = 0;
+  bit mayLoad = 0;
+  bit mayStore = 0;
+  bit isImplicitDef = 0;
+  bit isTwoAddress = 1;
+  bit isConvertibleToThreeAddress = 1;
+  bit isCommutable = 1;
+  bit isTerminator = 0;
+  bit isReMaterializable = 0;
+  bit isPredicable = 0;
+  bit hasDelaySlot = 0;
+  bit usesCustomInserter = 0;
+  bit hasCtrlDep = 0;
+  bit isNotDuplicable = 0;
+  bit hasSideEffects = 0;
+  bit neverHasSideEffects = 0;
+  InstrItinClass Itinerary = NoItinerary;
+  string Constraints = "";
+  string DisableEncoding = "";
+  bits<8> Opcode = { 0, 0, 0, 0, 0, 0, 0, 1 };
+  Format Form = MRMDestReg;
+  bits<6> FormBits = { 0, 0, 0, 0, 1, 1 };
+  ImmType ImmT = NoImm;
+  bits<3> ImmTypeBits = { 0, 0, 0 };
+  bit hasOpSizePrefix = 0;
+  bit hasAdSizePrefix = 0;
+  bits<4> Prefix = { 0, 0, 0, 0 };
+  bit hasREX_WPrefix = 0;
+  FPFormat FPForm = ?;
+  bits<3> FPFormBits = { 0, 0, 0 };
+}
+...
+
+
+ +

This definition corresponds to a 32-bit register-register add instruction in +the X86. The string after the 'def' string indicates the name of the +record—"ADD32rr" in this case—and the comment at the end of +the line indicates the superclasses of the definition. The body of the record +contains all of the data that TableGen assembled for the record, indicating that +the instruction is part of the "X86" namespace, the pattern indicating how the +the instruction should be emitted into the assembly file, that it is a +two-address instruction, has a particular encoding, etc. The contents and +semantics of the information in the record is specific to the needs of the X86 +backend, and is only shown as an example.

+ +

As you can see, a lot of information is needed for every instruction +supported by the code generator, and specifying it all manually would be +unmaintainable, prone to bugs, and tiring to do in the first place. Because we +are using TableGen, all of the information was derived from the following +definition:

+ +
+
+let Defs = [EFLAGS],
+    isCommutable = 1,                  // X = ADD Y,Z --> X = ADD Z,Y
+    isConvertibleToThreeAddress = 1 in // Can transform into LEA.
+def ADD32rr  : I<0x01, MRMDestReg, (outs GR32:$dst),
+                                   (ins GR32:$src1, GR32:$src2),
+                 "add{l}\t{$src2, $dst|$dst, $src2}",
+                 [(set GR32:$dst, (add GR32:$src1, GR32:$src2))]>;
+
+
+ +

This definition makes use of the custom class I (extended from the +custom class X86Inst), which is defined in the X86-specific TableGen +file, to factor out the common features that instructions of its class share. A +key feature of TableGen is that it allows the end-user to define the +abstractions they prefer to use when describing their information.

+ +
+ + +
Running TableGen
+ +
+ +

TableGen runs just like any other LLVM tool. The first (optional) argument +specifies the file to read. If a filename is not specified, tblgen +reads from standard input.

+ +

To be useful, one of the TableGen backends must be +used. These backends are selectable on the command line (type 'tblgen +-help' for a list). For example, to get a list of all of the definitions +that subclass a particular type (which can be useful for building up an enum +list of these records), use the -print-enums option:

+ +
+
+$ tblgen X86.td -print-enums -class=Register
+AH, AL, AX, BH, BL, BP, BPL, BX, CH, CL, CX, DH, DI, DIL, DL, DX, EAX, EBP, EBX,
+ECX, EDI, EDX, EFLAGS, EIP, ESI, ESP, FP0, FP1, FP2, FP3, FP4, FP5, FP6, IP,
+MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7, R10, R10B, R10D, R10W, R11, R11B, R11D,
+R11W, R12, R12B, R12D, R12W, R13, R13B, R13D, R13W, R14, R14B, R14D, R14W, R15,
+R15B, R15D, R15W, R8, R8B, R8D, R8W, R9, R9B, R9D, R9W, RAX, RBP, RBX, RCX, RDI,
+RDX, RIP, RSI, RSP, SI, SIL, SP, SPL, ST0, ST1, ST2, ST3, ST4, ST5, ST6, ST7,
+XMM0, XMM1, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, XMM2, XMM3, XMM4, XMM5,
+XMM6, XMM7, XMM8, XMM9,
+
+$ tblgen X86.td -print-enums -class=Instruction 
+ABS_F, ABS_Fp32, ABS_Fp64, ABS_Fp80, ADC32mi, ADC32mi8, ADC32mr, ADC32ri,
+ADC32ri8, ADC32rm, ADC32rr, ADC64mi32, ADC64mi8, ADC64mr, ADC64ri32, ADC64ri8,
+ADC64rm, ADC64rr, ADD16mi, ADD16mi8, ADD16mr, ADD16ri, ADD16ri8, ADD16rm,
+ADD16rr, ADD32mi, ADD32mi8, ADD32mr, ADD32ri, ADD32ri8, ADD32rm, ADD32rr,
+ADD64mi32, ADD64mi8, ADD64mr, ADD64ri32, ...
+
+
+ +

The default backend prints out all of the records, as described above.

+ +

If you plan to use TableGen, you will most likely have to write a backend that extracts the information specific to +what you need and formats it in the appropriate way.

+ +
+ + + +
TableGen syntax
+ + +
+ +

TableGen doesn't care about the meaning of data (that is up to the backend to +define), but it does care about syntax, and it enforces a simple type system. +This section describes the syntax and the constructs allowed in a TableGen file. +

+ +
+ + +
TableGen primitives
+ + +
TableGen comments
+ +
+ +

TableGen supports BCPL style "//" comments, which run to the end of +the line, and it also supports nestable "/* */" comments.

+ +
+ + +
+ The TableGen type system +
+ +
+ +

TableGen files are strongly typed, in a simple (but complete) type-system. +These types are used to perform automatic conversions, check for errors, and to +help interface designers constrain the input that they allow. Every value definition is required to have an associated type. +

+ +

TableGen supports a mixture of very low-level types (such as bit) +and very high-level types (such as dag). This flexibility is what +allows it to describe a wide range of information conveniently and compactly. +The TableGen types are:

+ +
+
bit
+
A 'bit' is a boolean value that can hold either 0 or 1.
+ +
int
+
The 'int' type represents a simple 32-bit integer value, such as 5.
+ +
string
+
The 'string' type represents an ordered sequence of characters of + arbitrary length.
+ +
bits<n>
+
A 'bits' type is an arbitrary, but fixed, size integer that is broken up + into individual bits. This type is useful because it can handle some bits + being defined while others are undefined.
+ +
list<ty>
+
This type represents a list whose elements are some other type. The + contained type is arbitrary: it can even be another list type.
+ +
Class type
+
Specifying a class name in a type context means that the defined value + must be a subclass of the specified class. This is useful in conjunction with + the list type, for example, to constrain the elements of the + list to a common base class (e.g., a list<Register> can + only contain definitions derived from the "Register" class).
+ +
dag
+
This type represents a nestable directed graph of elements.
+ +
code
+
This represents a big hunk of text. NOTE: I don't remember why this is + distinct from string!
+
+ +

To date, these types have been sufficient for describing things that +TableGen has been used for, but it is straight-forward to extend this list if +needed.

+ +
+ + +
+ TableGen values and expressions +
+ +
+ +

TableGen allows for a pretty reasonable number of different expression forms +when building up values. These forms allow the TableGen file to be written in a +natural syntax and flavor for the application. The current expression forms +supported include:

+ +
+
?
+
uninitialized field
+
0b1001011
+
binary integer value
+
07654321
+
octal integer value (indicated by a leading 0)
+
7
+
decimal integer value
+
0x7F
+
hexadecimal integer value
+
"foo"
+
string value
+
[{ ... }]
+
code fragment
+
[ X, Y, Z ]<type>
+
list value. <type> is the type of the list +element and is usually optional. In rare cases, +TableGen is unable to deduce the element type in +which case the user must specify it explicitly.
+
{ a, b, c }
+
initializer for a "bits<3>" value
+
value
+
value reference
+
value{17}
+
access to one bit of a value
+
value{15-17}
+
access to multiple bits of a value
+
DEF
+
reference to a record definition
+
CLASS<val list>
+
reference to a new anonymous definition of CLASS with the specified + template arguments.
+
X.Y
+
reference to the subfield of a value
+
list[4-7,17,2-3]
+
A slice of the 'list' list, including elements 4,5,6,7,17,2, and 3 from + it. Elements may be included multiple times.
+
(DEF a, b)
+
a dag value. The first element is required to be a record definition, the + remaining elements in the list may be arbitrary other values, including nested + `dag' values.
+
!strconcat(a, b)
+
A string value that is the result of concatenating the 'a' and 'b' + strings.
+
!cast<type>(a)
+
A symbol of type type obtained by looking up the string 'a' in +the symbol table. If the type of 'a' does not match type, TableGen +aborts with an error. !cast<string> is a special case in that the argument must +be an object defined by a 'def' construct.
+
!nameconcat<type>(a, b)
+
Shorthand for !cast<type>(!strconcat(a, b))
+
!subst(a, b, c)
+
If 'a' and 'b' are of string type or are symbol references, substitute +'b' for 'a' in 'c.' This operation is analogous to $(subst) in GNU make.
+
!foreach(a, b, c)
+
For each member 'b' of dag or list 'a' apply operator 'c.' 'b' is a +dummy variable that should be declared as a member variable of an instantiated +class. This operation is analogous to $(foreach) in GNU make.
+
!car(a)
+
The first element of list 'a.'
+
!cdr(a)
+
The 2nd-N elements of list 'a.'
+
!null(a)
+
An integer {0,1} indicating whether list 'a' is empty.
+
!if(a,b,c)
+
'b' if the result of integer operator 'a' is nonzero, 'c' otherwise.
+
!eq(a,b)
+
Integer one if string a is equal to string b, zero otherwise. This + only operates on string objects. Use !cast to compare other + types of objects.
+
+ +

Note that all of the values have rules specifying how they convert to values +for different types. These rules allow you to assign a value like "7" +to a "bits<4>" value, for example.

+ +
+ + +
+ Classes and definitions +
+ +
+ +

As mentioned in the intro, classes and definitions +(collectively known as 'records') in TableGen are the main high-level unit of +information that TableGen collects. Records are defined with a def or +class keyword, the record name, and an optional list of "template arguments". If the record has superclasses, +they are specified as a comma separated list that starts with a colon character +(":"). If value definitions or let expressions are needed for the class, they are +enclosed in curly braces ("{}"); otherwise, the record ends with a +semicolon.

+ +

Here is a simple TableGen file:

+ +
+
+class C { bit V = 1; }
+def X : C;
+def Y : C {
+  string Greeting = "hello";
+}
+
+
+ +

This example defines two definitions, X and Y, both of +which derive from the C class. Because of this, they both get the +V bit value. The Y definition also gets the Greeting member +as well.

+ +

In general, classes are useful for collecting together the commonality +between a group of records and isolating it in a single place. Also, classes +permit the specification of default values for their subclasses, allowing the +subclasses to override them as they wish.

+ +
+ + +
+ Value definitions +
+ +
+ +

Value definitions define named entries in records. A value must be defined +before it can be referred to as the operand for another value definition or +before the value is reset with a let expression. A +value is defined by specifying a TableGen type and a name. +If an initial value is available, it may be specified after the type with an +equal sign. Value definitions require terminating semicolons.

+ +
+ + +
+ 'let' expressions +
+ +
+ +

A record-level let expression is used to change the value of a value +definition in a record. This is primarily useful when a superclass defines a +value that a derived class or definition wants to override. Let expressions +consist of the 'let' keyword followed by a value name, an equal sign +("="), and a new value. For example, a new class could be added to the +example above, redefining the V field for all of its subclasses:

+ +
+
+class D : C { let V = 0; }
+def Z : D;
+
+
+ +

In this case, the Z definition will have a zero value for its "V" +value, despite the fact that it derives (indirectly) from the C class, +because the D class overrode its value.

+ +
+ + +
+ Class template arguments +
+ +
+ +

TableGen permits the definition of parameterized classes as well as normal +concrete classes. Parameterized TableGen classes specify a list of variable +bindings (which may optionally have defaults) that are bound when used. Here is +a simple example:

+ +
+
+class FPFormat<bits<3> val> {
+  bits<3> Value = val;
+}
+def NotFP      : FPFormat<0>;
+def ZeroArgFP  : FPFormat<1>;
+def OneArgFP   : FPFormat<2>;
+def OneArgFPRW : FPFormat<3>;
+def TwoArgFP   : FPFormat<4>;
+def CompareFP  : FPFormat<5>;
+def CondMovFP  : FPFormat<6>;
+def SpecialFP  : FPFormat<7>;
+
+
+ +

In this case, template arguments are used as a space efficient way to specify +a list of "enumeration values", each with a "Value" field set to the +specified integer.

+ +

The more esoteric forms of TableGen expressions are +useful in conjunction with template arguments. As an example:

+ +
+
+class ModRefVal<bits<2> val> {
+  bits<2> Value = val;
+}
+
+def None   : ModRefVal<0>;
+def Mod    : ModRefVal<1>;
+def Ref    : ModRefVal<2>;
+def ModRef : ModRefVal<3>;
+
+class Value<ModRefVal MR> {
+  // Decode some information into a more convenient format, while providing
+  // a nice interface to the user of the "Value" class.
+  bit isMod = MR.Value{0};
+  bit isRef = MR.Value{1};
+
+  // other stuff...
+}
+
+// Example uses
+def bork : Value<Mod>;
+def zork : Value<Ref>;
+def hork : Value<ModRef>;
+
+
+ +

This is obviously a contrived example, but it shows how template arguments +can be used to decouple the interface provided to the user of the class from the +actual internal data representation expected by the class. In this case, +running tblgen on the example prints the following definitions:

+ +
+
+def bork {      // Value
+  bit isMod = 1;
+  bit isRef = 0;
+}
+def hork {      // Value
+  bit isMod = 1;
+  bit isRef = 1;
+}
+def zork {      // Value
+  bit isMod = 0;
+  bit isRef = 1;
+}
+
+
+ +

This shows that TableGen was able to dig into the argument and extract a +piece of information that was requested by the designer of the "Value" class. +For more realistic examples, please see existing users of TableGen, such as the +X86 backend.

+ +
+ + +
+ Multiclass definitions and instances +
+ +
+ +

+While classes with template arguments are a good way to factor commonality +between two instances of a definition, multiclasses allow a convenient notation +for defining multiple definitions at once (instances of implicitly constructed +classes). For example, consider an 3-address instruction set whose instructions +come in two forms: "reg = reg op reg" and "reg = reg op imm" +(e.g. SPARC). In this case, you'd like to specify in one place that this +commonality exists, then in a separate place indicate what all the ops are. +

+ +

+Here is an example TableGen fragment that shows this idea: +

+ +
+
+def ops;
+def GPR;
+def Imm;
+class inst<int opc, string asmstr, dag operandlist>;
+
+multiclass ri_inst<int opc, string asmstr> {
+  def _rr : inst<opc, !strconcat(asmstr, " $dst, $src1, $src2"),
+                 (ops GPR:$dst, GPR:$src1, GPR:$src2)>;
+  def _ri : inst<opc, !strconcat(asmstr, " $dst, $src1, $src2"),
+                 (ops GPR:$dst, GPR:$src1, Imm:$src2)>;
+}
+
+// Instantiations of the ri_inst multiclass.
+defm ADD : ri_inst<0b111, "add">;
+defm SUB : ri_inst<0b101, "sub">;
+defm MUL : ri_inst<0b100, "mul">;
+...
+
+
+ +

The name of the resultant definitions has the multidef fragment names + appended to them, so this defines ADD_rr, ADD_ri, + SUB_rr, etc. A defm may inherit from multiple multiclasses, + instantiating definitions from each multiclass. Using a multiclass + this way is exactly equivalent to instantiating the classes multiple + times yourself, e.g. by writing:

+ +
+
+def ops;
+def GPR;
+def Imm;
+class inst<int opc, string asmstr, dag operandlist>;
+
+class rrinst<int opc, string asmstr>
+  : inst<opc, !strconcat(asmstr, " $dst, $src1, $src2"),
+         (ops GPR:$dst, GPR:$src1, GPR:$src2)>;
+
+class riinst<int opc, string asmstr>
+  : inst<opc, !strconcat(asmstr, " $dst, $src1, $src2"),
+         (ops GPR:$dst, GPR:$src1, Imm:$src2)>;
+
+// Instantiations of the ri_inst multiclass.
+def ADD_rr : rrinst<0b111, "add">;
+def ADD_ri : riinst<0b111, "add">;
+def SUB_rr : rrinst<0b101, "sub">;
+def SUB_ri : riinst<0b101, "sub">;
+def MUL_rr : rrinst<0b100, "mul">;
+def MUL_ri : riinst<0b100, "mul">;
+...
+
+
+ +
+ + +
+ File scope entities +
+ + +
+ File inclusion +
+ +
+

TableGen supports the 'include' token, which textually substitutes +the specified file in place of the include directive. The filename should be +specified as a double quoted string immediately after the 'include' +keyword. Example:

+ +
+
+include "foo.td"
+
+
+ +
+ + +
+ 'let' expressions +
+ +
+ +

"Let" expressions at file scope are similar to "let" +expressions within a record, except they can specify a value binding for +multiple records at a time, and may be useful in certain other cases. +File-scope let expressions are really just another way that TableGen allows the +end-user to factor out commonality from the records.

+ +

File-scope "let" expressions take a comma-separated list of bindings to +apply, and one or more records to bind the values in. Here are some +examples:

+ +
+
+let isTerminator = 1, isReturn = 1, isBarrier = 1, hasCtrlDep = 1 in
+  def RET : I<0xC3, RawFrm, (outs), (ins), "ret", [(X86retflag 0)]>;
+
+let isCall = 1 in
+  // All calls clobber the non-callee saved registers...
+  let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0,
+              MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
+              XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, EFLAGS] in {
+    def CALLpcrel32 : Ii32<0xE8, RawFrm, (outs), (ins i32imm:$dst,variable_ops),
+                           "call\t${dst:call}", []>;
+    def CALL32r     : I<0xFF, MRM2r, (outs), (ins GR32:$dst, variable_ops),
+                        "call\t{*}$dst", [(X86call GR32:$dst)]>;
+    def CALL32m     : I<0xFF, MRM2m, (outs), (ins i32mem:$dst, variable_ops),
+                        "call\t{*}$dst", []>;
+  }
+
+
+ +

File-scope "let" expressions are often useful when a couple of definitions +need to be added to several records, and the records do not otherwise need to be +opened, as in the case with the CALL* instructions above.

+ +
+ + +
Code Generator backend info
+ + +

Expressions used by code generator to describe instructions and isel +patterns:

+ +
+ +
(implicit a)
+
an implicitly defined physical register. This tells the dag instruction + selection emitter the input pattern's extra definitions matches implicit + physical register definitions.
+
(parallel (a), (b))
+
a list of dags specifying parallel operations which map to the same + instruction.
+ +
+ + +
TableGen backends
+ + +
+ +

TODO: How they work, how to write one. This section should not contain +details about any particular backend, except maybe -print-enums as an example. +This should highlight the APIs in TableGen/Record.h.

+ +
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + Chris Lattner
+ LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-02-27 17:47:46 -0600 (Sat, 27 Feb 2010) $ +
+ + + Added: www-releases/trunk/2.7/docs/TestingGuide.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/TestingGuide.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/TestingGuide.html (added) +++ www-releases/trunk/2.7/docs/TestingGuide.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,1212 @@ + + + + LLVM Testing Infrastructure Guide + + + + +
+ LLVM Testing Infrastructure Guide +
+ +
    +
  1. Overview
    2. +
  2. Requirements
    3. +
  3. LLVM testing infrastructure organization + +
    4. +
  4. Quick start + +
    5. +
  5. DejaGNU structure + +
    6. +
  6. Test suite structure
    7. +
  7. Running the test suite + +
    8. +
  8. Running the nightly tester
    9. +
+ +
+

Written by John T. Criswell, Reid Spencer, and Tanya Lattner

+
+ + +
Overview
+ + +
+ +

This document is the reference manual for the LLVM testing infrastructure. It documents +the structure of the LLVM testing infrastructure, the tools needed to use it, +and how to add and run tests.

+ +
+ + +
Requirements
+ + +
+ +

In order to use the LLVM testing infrastructure, you will need all of the software +required to build LLVM, plus the following:

+ +
+
DejaGNU
+
The Feature and Regressions tests are organized and run by DejaGNU.
+
Expect
+
Expect is required by DejaGNU.
+
tcl
+
Tcl is required by DejaGNU.
+
+ +
+ + +
LLVM testing infrastructure organization
+ + +
+ +

The LLVM testing infrastructure contains two major categories of tests: code +fragments and whole programs. Code fragments are referred to as the "DejaGNU +tests" and are in the llvm module in subversion under the +llvm/test directory. The whole programs tests are referred to as the +"Test suite" and are in the test-suite module in subversion. +

+ +
+ + +
DejaGNU tests
+ + +
+ +

Code fragments are small pieces of code that test a specific +feature of LLVM or trigger a specific bug in LLVM. They are usually +written in LLVM assembly language, but can be written in other +languages if the test targets a particular language front end (and the +appropriate --with-llvmgcc options were used +at configure time of the llvm module). These tests +are driven by the DejaGNU testing framework, which is hidden behind a +few simple makefiles.

+ +

These code fragments are not complete programs. The code generated +from them is never executed to determine correct behavior.

+ +

These code fragment tests are located in the llvm/test +directory.

+ +

Typically when a bug is found in LLVM, a regression test containing +just enough code to reproduce the problem should be written and placed +somewhere underneath this directory. In most cases, this will be a small +piece of LLVM assembly language code, often distilled from an actual +application or benchmark.

+ +
+ + +
Test suite
+ + +
+ +

The test suite contains whole programs, which are pieces of +code which can be compiled and linked into a stand-alone program that can be +executed. These programs are generally written in high level languages such as +C or C++, but sometimes they are written straight in LLVM assembly.

+ +

These programs are compiled and then executed using several different +methods (native compiler, LLVM C backend, LLVM JIT, LLVM native code generation, +etc). The output of these programs is compared to ensure that LLVM is compiling +the program correctly.

+ +

In addition to compiling and executing programs, whole program tests serve as +a way of benchmarking LLVM performance, both in terms of the efficiency of the +programs generated as well as the speed with which LLVM compiles, optimizes, and +generates code.

+ +

The test-suite is located in the test-suite Subversion module.

+ +
+ + +
Quick start
+ + +
+ +

The tests are located in two separate Subversion modules. The + DejaGNU tests are in the main "llvm" module under the directory + llvm/test (so you get these tests for free with the main llvm tree). + The more comprehensive test suite that includes whole +programs in C and C++ is in the test-suite module. This module should +be checked out to the llvm/projects directory (don't use another name +then the default "test-suite", for then the test suite will be run every time +you run make in the main llvm directory). +When you configure the llvm module, +the test-suite directory will be automatically configured. +Alternatively, you can configure the test-suite module manually.

+ + +
DejaGNU tests
+ +

To run all of the simple tests in LLVM using DejaGNU, use the master Makefile + in the llvm/test directory:

+ +
+
+% gmake -C llvm/test
+
+
+ +

or

+ +
+
+% gmake check
+
+
+ +

To run only a subdirectory of tests in llvm/test using DejaGNU (ie. +Transforms), just set the TESTSUITE variable to the path of the +subdirectory (relative to llvm/test):

+ +
+
+% gmake TESTSUITE=Transforms check
+
+
+ +

Note: If you are running the tests with objdir != subdir, you +must have run the complete testsuite before you can specify a +subdirectory.

+ +

To run only a single test, set TESTONE to its path (relative to +llvm/test) and make the check-one target:

+ +
+
+% gmake TESTONE=Feature/basictest.ll check-one
+
+
+ +

To run the tests with Valgrind (Memcheck by default), just append +VG=1 to the commands above, e.g.:

+ +
+
+% gmake check VG=1
+
+
+ + +
Test suite
+ + +

To run the comprehensive test suite (tests that compile and execute whole +programs), first checkout and setup the test-suite module:

+ +
+
+% cd llvm/projects
+% svn co http://llvm.org/svn/llvm-project/test-suite/trunk test-suite
+% cd ..
+% ./configure --with-llvmgccdir=$LLVM_GCC_DIR
+
+
+ +

where $LLVM_GCC_DIR is the directory where +you installed llvm-gcc, not it's src or obj +dir. The --with-llvmgccdir option assumes that +the llvm-gcc-4.2 module was configured with +--program-prefix=llvm-, and therefore that the C and C++ +compiler drivers are called llvm-gcc and llvm-g++ +respectively. If this is not the case, +use --with-llvmgcc/--with-llvmgxx to specify each +executable's location.

+ +

Then, run the entire test suite by running make in the test-suite +directory:

+ +
+
+% cd projects/test-suite
+% gmake
+
+
+ +

Usually, running the "nightly" set of tests is a good idea, and you can also +let it generate a report by running:

+ +
+
+% cd projects/test-suite
+% gmake TEST=nightly report report.html
+
+
+ +

Any of the above commands can also be run in a subdirectory of +projects/test-suite to run the specified test only on the programs in +that subdirectory.

+ +
+ + +
DejaGNU structure
+ +
+

The LLVM DejaGNU tests are driven by DejaGNU together with GNU Make and are + located in the llvm/test directory. + +

This directory contains a large array of small tests + that exercise various features of LLVM and to ensure that regressions do not + occur. The directory is broken into several sub-directories, each focused on + a particular area of LLVM. A few of the important ones are:

+ +
    +
  • Analysis: checks Analysis passes.
    • +
  • Archive: checks the Archive library.
    • +
  • Assembler: checks Assembly reader/writer functionality.
    • +
  • Bitcode: checks Bitcode reader/writer functionality.
    • +
  • CodeGen: checks code generation and each target.
    • +
  • Features: checks various features of the LLVM language.
    • +
  • Linker: tests bitcode linking.
    • +
  • Transforms: tests each of the scalar, IPO, and utility + transforms to ensure they make the right transformations.
    • +
  • Verifier: tests the IR verifier.
    • +
+ +
+ + +
Writing new DejaGNU tests
+ +
+

The DejaGNU structure is very simple, but does require some information to + be set. This information is gathered via configure and is written + to a file, site.exp in llvm/test. The llvm/test + Makefile does this work for you.

+ +

In order for DejaGNU to work, each directory of tests must have a + dg.exp file. DejaGNU looks for this file to determine how to run the + tests. This file is just a Tcl script and it can do anything you want, but + we've standardized it for the LLVM regression tests. If you're adding a + directory of tests, just copy dg.exp from another directory to get + running. The standard dg.exp simply loads a Tcl + library (test/lib/llvm.exp) and calls the llvm_runtests + function defined in that library with a list of file names to run. The names + are obtained by using Tcl's glob command. Any directory that contains only + directories does not need the dg.exp file.

+ +

The llvm-runtests function lookas at each file that is passed to + it and gathers any lines together that match "RUN:". This are the "RUN" lines + that specify how the test is to be run. So, each test script must contain + RUN lines if it is to do anything. If there are no RUN lines, the + llvm-runtests function will issue an error and the test will + fail.

+ +

RUN lines are specified in the comments of the test program using the + keyword RUN followed by a colon, and lastly the command (pipeline) + to execute. Together, these lines form the "script" that + llvm-runtests executes to run the test case. The syntax of the + RUN lines is similar to a shell's syntax for pipelines including I/O + redirection and variable substitution. However, even though these lines + may look like a shell script, they are not. RUN lines are interpreted + directly by the Tcl exec command. They are never executed by a + shell. Consequently the syntax differs from normal shell script syntax in a + few ways. You can specify as many RUN lines as needed.

+ +

Each RUN line is executed on its own, distinct from other lines unless + its last character is \. This continuation character causes the RUN + line to be concatenated with the next one. In this way you can build up long + pipelines of commands without making huge line lengths. The lines ending in + \ are concatenated until a RUN line that doesn't end in \ is + found. This concatenated set of RUN lines then constitutes one execution. + Tcl will substitute variables and arrange for the pipeline to be executed. If + any process in the pipeline fails, the entire line (and test case) fails too. +

+ +

Below is an example of legal RUN lines in a .ll file:

+ +
+
+; RUN: llvm-as < %s | llvm-dis > %t1
+; RUN: llvm-dis < %s.bc-13 > %t2
+; RUN: diff %t1 %t2
+
+
+ +

As with a Unix shell, the RUN: lines permit pipelines and I/O redirection + to be used. However, the usage is slightly different than for Bash. To check + what's legal, see the documentation for the + Tcl exec + command and the + tutorial. + The major differences are:

+
    +
  • You can't do 2>&1. That will cause Tcl to write to a + file named &1. Usually this is done to get stderr to go through + a pipe. You can do that in tcl with |& so replace this idiom: + ... 2>&1 | grep with ... |& grep
    • +
  • You can only redirect to a file, not to another descriptor and not from + a here document.
    • +
  • tcl supports redirecting to open files with the @ syntax but you + shouldn't use that here.
    • +
+ +

There are some quoting rules that you must pay attention to when writing + your RUN lines. In general nothing needs to be quoted. Tcl won't strip off any + ' or " so they will get passed to the invoked program. For example:

+ +
+
+... | grep 'find this string'
+
+
+ +

This will fail because the ' characters are passed to grep. This would + instruction grep to look for 'find in the files this and + string'. To avoid this use curly braces to tell Tcl that it should + treat everything enclosed as one value. So our example would become:

+ +
+
+... | grep {find this string}
+
+
+ +

Additionally, the characters [ and ] are treated + specially by Tcl. They tell Tcl to interpret the content as a command to + execute. Since these characters are often used in regular expressions this can + have disastrous results and cause the entire test run in a directory to fail. + For example, a common idiom is to look for some basicblock number:

+ +
+
+... | grep bb[2-8]
+
+
+ +

This, however, will cause Tcl to fail because its going to try to execute + a program named "2-8". Instead, what you want is this:

+ +
+
+... | grep {bb\[2-8\]}
+
+
+ +

Finally, if you need to pass the \ character down to a program, + then it must be doubled. This is another Tcl special character. So, suppose + you had: + +

+
+... | grep 'i32\*'
+
+
+ +

This will fail to match what you want (a pointer to i32). First, the + ' do not get stripped off. Second, the \ gets stripped off + by Tcl so what grep sees is: 'i32*'. That's not likely to match + anything. To resolve this you must use \\ and the {}, like + this:

+ +
+
+... | grep {i32\\*}
+
+
+ +

If your system includes GNU grep, make sure +that GREP_OPTIONS is not set in your environment. Otherwise, +you may get invalid results (both false positives and false +negatives).

+ +
+ + +
The FileCheck utility
+ + +
+ +

A powerful feature of the RUN: lines is that it allows any arbitrary commands + to be executed as part of the test harness. While standard (portable) unix + tools like 'grep' work fine on run lines, as you see above, there are a lot + of caveats due to interaction with Tcl syntax, and we want to make sure the + run lines are portable to a wide range of systems. Another major problem is + that grep is not very good at checking to verify that the output of a tools + contains a series of different output in a specific order. The FileCheck + tool was designed to help with these problems.

+ +

FileCheck (whose basic command line arguments are described in the FileCheck man page is + designed to read a file to check from standard input, and the set of things + to verify from a file specified as a command line argument. A simple example + of using FileCheck from a RUN line looks like this:

+ +
+
+; RUN: llvm-as < %s | llc -march=x86-64 | FileCheck %s
+
+
+ +

This syntax says to pipe the current file ("%s") into llvm-as, pipe that into +llc, then pipe the output of llc into FileCheck. This means that FileCheck will +be verifying its standard input (the llc output) against the filename argument +specified (the original .ll file specified by "%s"). To see how this works, +lets look at the rest of the .ll file (after the RUN line):

+ +
+
+define void @sub1(i32* %p, i32 %v) {
+entry:
+; CHECK: sub1:
+; CHECK: subl
+        %0 = tail call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %p, i32 %v)
+        ret void
+}
+
+define void @inc4(i64* %p) {
+entry:
+; CHECK: inc4:
+; CHECK: incq
+        %0 = tail call i64 @llvm.atomic.load.add.i64.p0i64(i64* %p, i64 1)
+        ret void
+}
+
+
+ +

Here you can see some "CHECK:" lines specified in comments. Now you can see +how the file is piped into llvm-as, then llc, and the machine code output is +what we are verifying. FileCheck checks the machine code output to verify that +it matches what the "CHECK:" lines specify.

+ +

The syntax of the CHECK: lines is very simple: they are fixed strings that +must occur in order. FileCheck defaults to ignoring horizontal whitespace +differences (e.g. a space is allowed to match a tab) but otherwise, the contents +of the CHECK: line is required to match some thing in the test file exactly.

+ +

One nice thing about FileCheck (compared to grep) is that it allows merging +test cases together into logical groups. For example, because the test above +is checking for the "sub1:" and "inc4:" labels, it will not match unless there +is a "subl" in between those labels. If it existed somewhere else in the file, +that would not count: "grep subl" matches if subl exists anywhere in the +file.

+ +
+ + +
The FileCheck -check-prefix option
+ +
+ +

The FileCheck -check-prefix option allows multiple test configurations to be +driven from one .ll file. This is useful in many circumstances, for example, +testing different architectural variants with llc. Here's a simple example:

+ +
+
+; RUN: llvm-as < %s | llc -mtriple=i686-apple-darwin9 -mattr=sse41 \
+; RUN:              | FileCheck %s -check-prefix=X32
+; RUN: llvm-as < %s | llc -mtriple=x86_64-apple-darwin9 -mattr=sse41 \
+; RUN:              | FileCheck %s -check-prefix=X64
+
+define <4 x i32> @pinsrd_1(i32 %s, <4 x i32> %tmp) nounwind {
+        %tmp1 = insertelement <4 x i32> %tmp, i32 %s, i32 1
+        ret <4 x i32> %tmp1
+; X32: pinsrd_1:
+; X32:    pinsrd $1, 4(%esp), %xmm0
+
+; X64: pinsrd_1:
+; X64:    pinsrd $1, %edi, %xmm0
+}
+
+
+ +

In this case, we're testing that we get the expected code generation with +both 32-bit and 64-bit code generation.

+ +
+ + +
The "CHECK-NEXT:" directive
+ +
+ +

Sometimes you want to match lines and would like to verify that matches +happen on exactly consequtive lines with no other lines in between them. In +this case, you can use CHECK: and CHECK-NEXT: directives to specify this. If +you specified a custom check prefix, just use "<PREFIX>-NEXT:". For +example, something like this works as you'd expect:

+ +
+
+define void @t2(<2 x double>* %r, <2 x double>* %A, double %B) {
+	%tmp3 = load <2 x double>* %A, align 16
+	%tmp7 = insertelement <2 x double> undef, double %B, i32 0
+	%tmp9 = shufflevector <2 x double> %tmp3,
+                              <2 x double> %tmp7,
+                              <2 x i32> < i32 0, i32 2 >
+	store <2 x double> %tmp9, <2 x double>* %r, align 16
+	ret void
+        
+; CHECK: t2:
+; CHECK: 	movl	8(%esp), %eax
+; CHECK-NEXT: 	movapd	(%eax), %xmm0
+; CHECK-NEXT: 	movhpd	12(%esp), %xmm0
+; CHECK-NEXT: 	movl	4(%esp), %eax
+; CHECK-NEXT: 	movapd	%xmm0, (%eax)
+; CHECK-NEXT: 	ret
+}
+
+
+ +

CHECK-NEXT: directives reject the input unless there is exactly one newline +between it an the previous directive. A CHECK-NEXT cannot be the first +directive in a file.

+ +
+ + +
The "CHECK-NOT:" directive
+ +
+ +

The CHECK-NOT: directive is used to verify that a string doesn't occur +between two matches (or the first match and the beginning of the file). For +example, to verify that a load is removed by a transformation, a test like this +can be used:

+ +
+
+define i8 @coerce_offset0(i32 %V, i32* %P) {
+  store i32 %V, i32* %P
+   
+  %P2 = bitcast i32* %P to i8*
+  %P3 = getelementptr i8* %P2, i32 2
+
+  %A = load i8* %P3
+  ret i8 %A
+; CHECK: @coerce_offset0
+; CHECK-NOT: load
+; CHECK: ret i8
+}
+
+
+ +
+ + +
FileCheck Pattern Matching Syntax
+ +
+ +

The CHECK: and CHECK-NOT: directives both take a pattern to match. For most +uses of FileCheck, fixed string matching is perfectly sufficient. For some +things, a more flexible form of matching is desired. To support this, FileCheck +allows you to specify regular expressions in matching strings, surrounded by +double braces: {{yourregex}}. Because we want to use fixed string +matching for a majority of what we do, FileCheck has been designed to support +mixing and matching fixed string matching with regular expressions. This allows +you to write things like this:

+ +
+
+; CHECK: movhpd	{{[0-9]+}}(%esp), {{%xmm[0-7]}}
+
+
+ +

In this case, any offset from the ESP register will be allowed, and any xmm +register will be allowed.

+ +

Because regular expressions are enclosed with double braces, they are +visually distinct, and you don't need to use escape characters within the double +braces like you would in C. In the rare case that you want to match double +braces explicitly from the input, you can use something ugly like +{{[{][{]}} as your pattern.

+ +
+ + +
FileCheck Variables
+ +
+ +

It is often useful to match a pattern and then verify that it occurs again +later in the file. For codegen tests, this can be useful to allow any register, +but verify that that register is used consistently later. To do this, FileCheck +allows named variables to be defined and substituted into patterns. Here is a +simple example:

+ +
+
+; CHECK: test5:
+; CHECK:    notw	[[REGISTER:%[a-z]+]]
+; CHECK:    andw	{{.*}}[[REGISTER]]
+
+
+ +

The first check line matches a regex (%[a-z]+) and captures it into +the variables "REGISTER". The second line verifies that whatever is in REGISTER +occurs later in the file after an "andw". FileCheck variable references are +always contained in [[ ]] pairs, are named, and their names can be +formed with the regex "[a-zA-Z][a-zA-Z0-9]*". If a colon follows the +name, then it is a definition of the variable, if not, it is a use.

+ +

FileCheck variables can be defined multiple times, and uses always get the +latest value. Note that variables are all read at the start of a "CHECK" line +and are all defined at the end. This means that if you have something like +"CHECK: [[XYZ:.*]]x[[XYZ]]" that the check line will read the previous +value of the XYZ variable and define a new one after the match is performed. If +you need to do something like this you can probably take advantage of the fact +that FileCheck is not actually line-oriented when it matches, this allows you to +define two separate CHECK lines that match on the same line. +

+ +
+ + +
Variables and +substitutions
+ +
+

With a RUN line there are a number of substitutions that are permitted. In + general, any Tcl variable that is available in the substitute + function (in test/lib/llvm.exp) can be substituted into a RUN line. + To make a substitution just write the variable's name preceded by a $. + Additionally, for compatibility reasons with previous versions of the test + library, certain names can be accessed with an alternate syntax: a % prefix. + These alternates are deprecated and may go away in a future version. +

+

Here are the available variable names. The alternate syntax is listed in + parentheses.

+ +
+
$test (%s)
+
The full path to the test case's source. This is suitable for passing + on the command line as the input to an llvm tool.
+ +
$srcdir
+
The source directory from where the "make check" was run.
+ +
objdir
+
The object directory that corresponds to the $srcdir.
+ +
subdir
+
A partial path from the test directory that contains the + sub-directory that contains the test source being executed.
+ +
srcroot
+
The root directory of the LLVM src tree.
+ +
objroot
+
The root directory of the LLVM object tree. This could be the same + as the srcroot.
+ +
path
+
The path to the directory that contains the test case source. This is + for locating any supporting files that are not generated by the test, but + used by the test.
+ +
tmp
+
The path to a temporary file name that could be used for this test case. + The file name won't conflict with other test cases. You can append to it if + you need multiple temporaries. This is useful as the destination of some + redirected output.
+ +
llvmlibsdir (%llvmlibsdir)
+
The directory where the LLVM libraries are located.
+ +
target_triplet (%target_triplet)
+
The target triplet that corresponds to the current host machine (the one + running the test cases). This should probably be called "host".
+ +
llvmgcc (%llvmgcc)
+
The full path to the llvm-gcc executable as specified in the + configured LLVM environment
+ +
llvmgxx (%llvmgxx)
+
The full path to the llvm-gxx executable as specified in the + configured LLVM environment
+ +
gccpath
+
The full path to the C compiler used to build LLVM. Note that + this might not be gcc.
+ +
gxxpath
+
The full path to the C++ compiler used to build LLVM. Note that + this might not be g++.
+ +
compile_c (%compile_c)
+
The full command line used to compile LLVM C source code. This has all + the configured -I, -D and optimization options.
+ +
compile_cxx (%compile_cxx)
+
The full command used to compile LLVM C++ source code. This has + all the configured -I, -D and optimization options.
+ +
link (%link)
+
This full link command used to link LLVM executables. This has all the + configured -I, -L and -l options.
+ +
shlibext (%shlibext)
+
The suffix for the host platforms share library (dll) files. This + includes the period as the first character.
+
+

To add more variables, two things need to be changed. First, add a line in + the test/Makefile that creates the site.exp file. This will + "set" the variable as a global in the site.exp file. Second, in the + test/lib/llvm.exp file, in the substitute proc, add the variable name + to the list of "global" declarations at the beginning of the proc. That's it, + the variable can then be used in test scripts.

+
+ + +
Other Features
+ +
+

To make RUN line writing easier, there are several shell scripts located + in the llvm/test/Scripts directory. This directory is in the PATH + when running tests, so you can just call these scripts using their name. For + example:

+
+
ignore
+
This script runs its arguments and then always returns 0. This is useful + in cases where the test needs to cause a tool to generate an error (e.g. to + check the error output). However, any program in a pipeline that returns a + non-zero result will cause the test to fail. This script overcomes that + issue and nicely documents that the test case is purposefully ignoring the + result code of the tool
+ +
not
+
This script runs its arguments and then inverts the result code from + it. Zero result codes become 1. Non-zero result codes become 0. This is + useful to invert the result of a grep. For example "not grep X" means + succeed only if you don't find X in the input.
+
+ +

Sometimes it is necessary to mark a test case as "expected fail" or XFAIL. + You can easily mark a test as XFAIL just by including XFAIL: on a + line near the top of the file. This signals that the test case should succeed + if the test fails. Such test cases are counted separately by DejaGnu. To + specify an expected fail, use the XFAIL keyword in the comments of the test + program followed by a colon and one or more regular expressions (separated by + a comma). The regular expressions allow you to XFAIL the test conditionally by + host platform. The regular expressions following the : are matched against the + target triplet for the host machine. If there is a match, the test is expected + to fail. If not, the test is expected to succeed. To XFAIL everywhere just + specify XFAIL: *. Here is an example of an XFAIL line:

+ +
+
+; XFAIL: darwin,sun
+
+
+ +

To make the output more useful, the llvm_runtest function wil + scan the lines of the test case for ones that contain a pattern that matches + PR[0-9]+. This is the syntax for specifying a PR (Problem Report) number that + is related to the test case. The number after "PR" specifies the LLVM bugzilla + number. When a PR number is specified, it will be used in the pass/fail + reporting. This is useful to quickly get some context when a test fails.

+ +

Finally, any line that contains "END." will cause the special + interpretation of lines to terminate. This is generally done right after the + last RUN: line. This has two side effects: (a) it prevents special + interpretation of lines that are part of the test program, not the + instructions to the test case, and (b) it speeds things up for really big test + cases by avoiding interpretation of the remainder of the file.

+ +
+ + +
Test suite +Structure
+ + +
+ +

The test-suite module contains a number of programs that can be compiled +with LLVM and executed. These programs are compiled using the native compiler +and various LLVM backends. The output from the program compiled with the +native compiler is assumed correct; the results from the other programs are +compared to the native program output and pass if they match.

+ +

When executing tests, it is usually a good idea to start out with a subset of +the available tests or programs. This makes test run times smaller at first and +later on this is useful to investigate individual test failures. To run some +test only on a subset of programs, simply change directory to the programs you +want tested and run gmake there. Alternatively, you can run a different +test using the TEST variable to change what tests or run on the +selected programs (see below for more info).

+ +

In addition for testing correctness, the llvm-test directory also +performs timing tests of various LLVM optimizations. It also records +compilation times for the compilers and the JIT. This information can be +used to compare the effectiveness of LLVM's optimizations and code +generation.

+ +

llvm-test tests are divided into three types of tests: MultiSource, +SingleSource, and External.

+ +
    +
  • llvm-test/SingleSource +

    The SingleSource directory contains test programs that are only a single +source file in size. These are usually small benchmark programs or small +programs that calculate a particular value. Several such programs are grouped +together in each directory.

    • + +
  • llvm-test/MultiSource +

    The MultiSource directory contains subdirectories which contain entire +programs with multiple source files. Large benchmarks and whole applications +go here.

    • + +
  • llvm-test/External +

    The External directory contains Makefiles for building code that is external +to (i.e., not distributed with) LLVM. The most prominent members of this +directory are the SPEC 95 and SPEC 2000 benchmark suites. The External +directory does not contain these actual tests, but only the Makefiles that know +how to properly compile these programs from somewhere else. The presence and +location of these external programs is configured by the llvm-test +configure script.

    • +
+ +

Each tree is then subdivided into several categories, including applications, +benchmarks, regression tests, code that is strange grammatically, etc. These +organizations should be relatively self explanatory.

+ +

Some tests are known to fail. Some are bugs that we have not fixed yet; +others are features that we haven't added yet (or may never add). In DejaGNU, +the result for such tests will be XFAIL (eXpected FAILure). In this way, you +can tell the difference between an expected and unexpected failure.

+ +

The tests in the test suite have no such feature at this time. If the +test passes, only warnings and other miscellaneous output will be generated. If +a test fails, a large <program> FAILED message will be displayed. This +will help you separate benign warnings from actual test failures.

+ +
+ + +
Running the test suite
+ + +
+ +

First, all tests are executed within the LLVM object directory tree. They +are not executed inside of the LLVM source tree. This is because the +test suite creates temporary files during execution.

+ +

To run the test suite, you need to use the following steps:

+ +
    +
  1. cd into the llvm/projects directory in your source tree. +
    2. + +

  2. Check out the test-suite module with:

    + +
    +
    +% svn co http://llvm.org/svn/llvm-project/test-suite/trunk test-suite
+
    +
    +

    This will get the test suite into llvm/projects/test-suite.

    +
    3. +

  3. Configure and build llvm.

    4. +

  4. Configure and build llvm-gcc.

    5. +

  5. Install llvm-gcc somewhere.

    6. +

  6. Re-configure llvm from the top level of + each build tree (LLVM object directory tree) in which you want + to run the test suite, just as you do before building LLVM.

    +

    During the re-configuration, you must either: (1) + have llvm-gcc you just built in your path, or (2) + specify the directory where your just-built llvm-gcc is + installed using --with-llvmgccdir=$LLVM_GCC_DIR.

    +

    You must also tell the configure machinery that the test suite + is available so it can be configured for your build tree:

    +
    +
    +% cd $LLVM_OBJ_ROOT ; $LLVM_SRC_ROOT/configure [--with-llvmgccdir=$LLVM_GCC_DIR]
+
    +
    +

    [Remember that $LLVM_GCC_DIR is the directory where you + installed llvm-gcc, not its src or obj directory.]

    +
    7. + +

  7. You can now run the test suite from your build tree as follows:

    +
    +
    +% cd $LLVM_OBJ_ROOT/projects/test-suite
+% make
+
    +
    +
    8. +
+

Note that the second and third steps only need to be done once. After you +have the suite checked out and configured, you don't need to do it again (unless +the test code or configure script changes).

+ +
+ + +
+Configuring External Tests
+ + +
+

In order to run the External tests in the test-suite + module, you must specify --with-externals. This + must be done during the re-configuration step (see above), + and the llvm re-configuration must recognize the + previously-built llvm-gcc. If any of these is missing or + neglected, the External tests won't work.

+
+
--with-externals
+
--with-externals=<directory>
+
+ This tells LLVM where to find any external tests. They are expected to be + in specifically named subdirectories of <directory>. + If directory is left unspecified, + configure uses the default value + /home/vadve/shared/benchmarks/speccpu2000/benchspec. + Subdirectory names known to LLVM include: +
+
spec95
+
speccpu2000
+
speccpu2006
+
povray31
+
+ Others are added from time to time, and can be determined from + configure. +
+ + +
+Running different tests
+ +
+

In addition to the regular "whole program" tests, the test-suite +module also provides a mechanism for compiling the programs in different ways. +If the variable TEST is defined on the gmake command line, the test system will +include a Makefile named TEST.<value of TEST variable>.Makefile. +This Makefile can modify build rules to yield different results.

+ +

For example, the LLVM nightly tester uses TEST.nightly.Makefile to +create the nightly test reports. To run the nightly tests, run gmake +TEST=nightly.

+ +

There are several TEST Makefiles available in the tree. Some of them are +designed for internal LLVM research and will not work outside of the LLVM +research group. They may still be valuable, however, as a guide to writing your +own TEST Makefile for any optimization or analysis passes that you develop with +LLVM.

+ +
+ + +
+Generating test output
+ +
+

There are a number of ways to run the tests and generate output. The most + simple one is simply running gmake with no arguments. This will + compile and run all programs in the tree using a number of different methods + and compare results. Any failures are reported in the output, but are likely + drowned in the other output. Passes are not reported explicitely.

+ +

Somewhat better is running gmake TEST=sometest test, which runs + the specified test and usually adds per-program summaries to the output + (depending on which sometest you use). For example, the nightly test + explicitely outputs TEST-PASS or TEST-FAIL for every test after each program. + Though these lines are still drowned in the output, it's easy to grep the + output logs in the Output directories.

+ +

Even better are the report and report.format targets + (where format is one of html, csv, text or + graphs). The exact contents of the report are dependent on which + TEST you are running, but the text results are always shown at the + end of the run and the results are always stored in the + report.<type>.format file (when running with + TEST=<type>). + + The report also generate a file called + report.<type>.raw.out containing the output of the entire test + run. +

+ + +
+Writing custom tests for the test suite
+ + +
+ +

Assuming you can run the test suite, (e.g. "gmake TEST=nightly report" +should work), it is really easy to run optimizations or code generator +components against every program in the tree, collecting statistics or running +custom checks for correctness. At base, this is how the nightly tester works, +it's just one example of a general framework.

+ +

Lets say that you have an LLVM optimization pass, and you want to see how +many times it triggers. First thing you should do is add an LLVM +statistic to your pass, which +will tally counts of things you care about.

+ +

Following this, you can set up a test and a report that collects these and +formats them for easy viewing. This consists of two files, an +"test-suite/TEST.XXX.Makefile" fragment (where XXX is the name of your +test) and an "llvm-test/TEST.XXX.report" file that indicates how to +format the output into a table. There are many example reports of various +levels of sophistication included with the test suite, and the framework is very +general.

+ +

If you are interested in testing an optimization pass, check out the +"libcalls" test as an example. It can be run like this:

+ +

+
+% cd llvm/projects/test-suite/MultiSource/Benchmarks  # or some other level
+% make TEST=libcalls report
+
+
+ +

This will do a bunch of stuff, then eventually print a table like this:

+ +
+
+Name                                  | total | #exit |
+...
+FreeBench/analyzer/analyzer           | 51    | 6     | 
+FreeBench/fourinarow/fourinarow       | 1     | 1     | 
+FreeBench/neural/neural               | 19    | 9     | 
+FreeBench/pifft/pifft                 | 5     | 3     | 
+MallocBench/cfrac/cfrac               | 1     | *     | 
+MallocBench/espresso/espresso         | 52    | 12    | 
+MallocBench/gs/gs                     | 4     | *     | 
+Prolangs-C/TimberWolfMC/timberwolfmc  | 302   | *     | 
+Prolangs-C/agrep/agrep                | 33    | 12    | 
+Prolangs-C/allroots/allroots          | *     | *     | 
+Prolangs-C/assembler/assembler        | 47    | *     | 
+Prolangs-C/bison/mybison              | 74    | *     | 
+...
+
+
+ +

This basically is grepping the -stats output and displaying it in a table. +You can also use the "TEST=libcalls report.html" target to get the table in HTML +form, similarly for report.csv and report.tex.

+ +

The source for this is in test-suite/TEST.libcalls.*. The format is pretty +simple: the Makefile indicates how to run the test (in this case, +"opt -simplify-libcalls -stats"), and the report contains one line for +each column of the output. The first value is the header for the column and the +second is the regex to grep the output of the command for. There are lots of +example reports that can do fancy stuff.

+ +
+ + +
Running the nightly tester
+ + +
+ +

+The LLVM Nightly Testers +automatically check out an LLVM tree, build it, run the "nightly" +program test (described above), run all of the DejaGNU tests, +delete the checked out tree, and then submit the results to +http://llvm.org/nightlytest/. +After test results are submitted to +http://llvm.org/nightlytest/, +they are processed and displayed on the tests page. An email to + +llvm-testresults at cs.uiuc.edu summarizing the results is also generated. +This testing scheme is designed to ensure that programs don't break as well +as keep track of LLVM's progress over time.

+ +

If you'd like to set up an instance of the nightly tester to run on your +machine, take a look at the comments at the top of the +utils/NewNightlyTest.pl file. If you decide to set up a nightly tester +please choose a unique nickname and invoke utils/NewNightlyTest.pl +with the "-nickname [yournickname]" command line option. + +

You can create a shell script to encapsulate the running of the script. +The optimized x86 Linux nightly test is run from just such a script:

+ +
+
+#!/bin/bash
+BASE=/proj/work/llvm/nightlytest
+export BUILDDIR=$BASE/build 
+export WEBDIR=$BASE/testresults 
+export LLVMGCCDIR=/proj/work/llvm/cfrontend/install
+export PATH=/proj/install/bin:$LLVMGCCDIR/bin:$PATH
+export LD_LIBRARY_PATH=/proj/install/lib
+cd $BASE
+cp /proj/work/llvm/llvm/utils/NewNightlyTest.pl .
+nice ./NewNightlyTest.pl -nice -release -verbose -parallel -enable-linscan \
+   -nickname NightlyTester -noexternals > output.log 2>&1 
+
+
+ +

It is also possible to specify the the location your nightly test results +are submitted. You can do this by passing the command line option +"-submit-server [server_address]" and "-submit-script [script_on_server]" to +utils/NewNightlyTest.pl. For example, to submit to the llvm.org +nightly test results page, you would invoke the nightly test script with +"-submit-server llvm.org -submit-script /nightlytest/NightlyTestAccept.cgi". +If these options are not specified, the nightly test script sends the results +to the llvm.org nightly test results page.

+ +

Take a look at the NewNightlyTest.pl file to see what all of the +flags and strings do. If you start running the nightly tests, please let us +know. Thanks!

+ +
+ + + +
+
+ Valid CSS + Valid HTML 4.01 + + John T. Criswell, Reid Spencer, and Tanya Lattner
+ The LLVM Compiler Infrastructure
+ Last modified: $Date: 2010-02-26 15:23:59 -0600 (Fri, 26 Feb 2010) $ +
+ + Added: www-releases/trunk/2.7/docs/UsingLibraries.html URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/2.7/docs/UsingLibraries.html?rev=102419&view=auto ============================================================================== --- www-releases/trunk/2.7/docs/UsingLibraries.html (added) +++ www-releases/trunk/2.7/docs/UsingLibraries.html Tue Apr 27 02:30:52 2010 @@ -0,0 +1,439 @@ + + + + Using The LLVM Libraries + + + +
Using The LLVM Libraries
+
    +
  1. Abstract
    2. +
  2. Introduction
    3. +
  3. Library Descriptions
    4. +
  4. Library Dependencies
    5. +
  5. Linkage Rules Of Thumb +
      +
    1. Always link LLVMCore, LLVMSupport, LLVMSystem +
    2. Never link both archive and re-linked +
    +
    6. +
+ +
+

Written by Reid Spencer

+
+ +

Warning: This document is out of date, please see llvm-config for more information.

+ + +
Abstract
+
+

Amongst other things, LLVM is a toolkit for building compilers, linkers, + runtime executives, virtual machines, and other program execution related + tools. In addition to the LLVM tool set, the functionality of LLVM is + available through a set of libraries. To use LLVM as a toolkit for + constructing tools, a developer needs to understand what is contained in the + various libraries, what they depend on, and how to use them. Fortunately, + there is a tool, llvm-config to aid with this. This document + describes the contents of the libraries and how to use llvm-config + to generate command line options. +

+
+ + +
Introduction
+
+

If you're writing a compiler, virtual machine, or any other utility based + on LLVM, you'll need to figure out which of the many libraries files you will + need to link with to be successful. An understanding of the contents of these + libraries will be useful in coming up with an optimal specification for the + libraries to link with. The purpose of this document is to reduce some of + the trial and error that the author experienced in using LLVM.

+

LLVM produces two types of libraries: archives (ending in .a) and + objects (ending in .o). However, both are libraries. Libraries ending + in .o are known as re-linked libraries because they contain all the + compilation units of the library linked together as a single .o file. + Furthermore, several of the libraries have both forms of library. The + re-linked libraries are used whenever you want to include all symbols from the + library. The archive libraries are used whenever you want to only resolve + outstanding symbols at that point in the link without including everything in + the library.

+

If you're using the LLVM Makefile system to link your tools,you will use + the LLVMLIBS make variable. + (see the Makefile Guide for + details). This variable specifies which LLVM libraries to link into your tool + and the order in which they will be linked. You specify re-linked libraries by + naming the library without a suffix. You specify archive libraries by naming + the library with a .a suffix but without the lib prefix. The + order in which the libraries appear in the LLVMLIBS variable + definition is the order in which they will be linked. Getting this order + correct for your tool can sometimes be challenging. +

+ +
Library Descriptions
+
+

The table below categorizes each library + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
LibraryFormsDescription
Core Libraries
LLVMArchive.aLLVM archive reading and writing
LLVMAsmParser.aLLVM assembly parsing
LLVMBCReader.aLLVM bitcode reading
LLVMBCWriter.aLLVM bitcode writing
LLVMCore.aLLVM core intermediate representation
LLVMDebugger.aSource level debugging support
LLVMLinker.aBitcode and archive linking interface
LLVMSupport.aGeneral support utilities
LLVMSystem.aOperating system abstraction layer
LLVMbzip2.aBZip2 compression library
Analysis Libraries
LLVMAnalysis.aVarious analysis passes.
LLVMDataStructure.oData structure analysis passes.
LLVMipa.aInter-procedural analysis passes.
Transformation Libraries
LLVMInstrumentation.aInstrumentation passes.
LLVMipo.aAll inter-procedural optimization passes.
LLVMScalarOpts.aAll scalar optimization passes.
LLVMTransformUtils.aTransformation utilities used by many passes.
Code Generation Libraries
LLVMCodeGen.oNative code generation infrastructure
LLVMSelectionDAG.oAggressive instruction selector for directed acyclic graphs
Target Libraries
LLVMAlpha.oCode generation for Alpha architecture
LLVMARM.oCode generation for ARM architecture
LLVMCBackend.o'C' language code generator.
LLVMPowerPC.oCode generation for PowerPC architecture
LLVMSparc.oCode generation for Sparc architecture
LLVMTarget.aGeneric code generation utilities.
LLVMX86.oCode generation for Intel x86 architecture
Runtime Libraries
LLVMInterpreter.oBitcode Interpreter
LLVMJIT.oBitcode JIT Compiler
LLVMExecutionEngine.oVirtual machine engine
+

+ + +
Using llvm-config
+
+

The llvm-config tool is a perl script that produces on its output + various kinds of information. For example, the source or object directories + used to build LLVM can be accessed by passing options to llvm-config. + For complete details on this tool, please see the + manual page.

+

To understand the relationships between libraries, the llvm-config + can be very useful. If all you know is that you want certain libraries to + be available, you can generate the complete set of libraries to link with + using one of four options, as below:

+
    +
  1. --ldflags. This generates the command line options necessary to + be passed to the ld tool in order to link with LLVM. Most notably, + the -L option is provided to specify a library search directory + that contains the LLVM libraries.
    2. +
  2. --libs. This generates command line options suitable for + use with a gcc-style linker. That is, libraries are given with a -l option + and object files are given with a full path.
    3. +
  3. --libnames. This generates a list of just the library file + names. If you know the directory in which these files reside (see --ldflags) + then you can find the libraries there.
    4. +
  4. --libfiles. This generates the full path names of the + LLVM library files.
    5. +
+

If you wish to delve further into how llvm-config generates the + correct order (based on library dependencies), please see the tool named + GenLibDeps.pl in the utils source directory of LLVM.

+ + + + + + + +

Dependency Relationships Of Libraries

+

This graph shows the dependency of archive libraries on other archive + libraries or objects. Where a library has both archive and object forms, only + the archive form is shown.

+ Library Dependencies +

Dependency Relationships Of Object Files

+

This graph shows the dependency of object files on archive libraries or + other objects. Where a library has both object and archive forms, only the + dependency to the archive form is shown.

+ Object File Dependencies +

The following list shows the dependency relationships between libraries in + textual form. The information is the same as shown on the graphs but arranged + alphabetically.

+
+
libLLVMAnalysis.a
    +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
+
libLLVMArchive.a
    +
  • libLLVMBCReader.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMAsmParser.a
    +
  • libLLVMCore.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMBCReader.a
    +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMBCWriter.a
    +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMCodeGen.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMScalarOpts.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
  • libLLVMTransformUtils.a
    • +
+
libLLVMCore.a
    +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMDebugger.a
    +
  • libLLVMBCReader.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMInstrumentation.a
    +
  • libLLVMCore.a
    • +
  • libLLVMScalarOpts.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMTransformUtils.a
    • +
+
libLLVMLinker.a
    +
  • libLLVMArchive.a
    • +
  • libLLVMBCReader.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMScalarOpts.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
  • libLLVMTransformUtils.a
    • +
+
libLLVMSelectionDAG.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCodeGen.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
  • libLLVMTransformUtils.a
    • +
+
libLLVMSupport.a
    +
  • libLLVMSystem.a
    • +
  • libLLVMbzip2.a
    • +
+
libLLVMSystem.a
    +
+
libLLVMTarget.a
    +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMTransformUtils.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
  • libLLVMipa.a
    • +
+
libLLVMbzip2.a
    +
+
libLLVMipa.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
+
libLLVMipo.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
  • libLLVMTransformUtils.a
    • +
  • libLLVMipa.a
    • +
+
libLLVMlto.a
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMBCReader.a
    • +
  • libLLVMBCWriter.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMLinker.a
    • +
  • libLLVMScalarOpts.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
  • libLLVMipa.a
    • +
  • libLLVMipo.a
    • +
+
LLVMARM.o
    +
  • libLLVMCodeGen.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSelectionDAG.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
+
LLVMAlpha.o
    +
  • libLLVMCodeGen.a
    • +
  • libLLVMCore.a
    • +
  • libLLVMSelectionDAG.a
    • +
  • libLLVMSupport.a
    • +
  • libLLVMSystem.a
    • +
  • libLLVMTarget.a
    • +
+
LLVMCBackend.o
    +
  • libLLVMAnalysis.a
    • +
  • libLLVMCodeGen.a
    • +