[LLVMdev] Prevent unbounded memory consuption of long lived JIT processes
jfonseca at vmware.com
Thu Mar 24 09:23:37 CDT 2011
On 03/16/2011 03:39 PM, Jakob Stoklund Olesen wrote:
> On Mar 16, 2011, at 6:19 AM, José Fonseca wrote:
>> On Tue, 2011-03-15 at 20:29 -0700, Jakob Stoklund Olesen wrote:
>>> On Mar 15, 2011, at 4:15 PM, jfonseca at vmware.com wrote:
>>>> This series of patches address several issues causing memory usage to grow
>>>> indefinetely on a long lived process.
>>> Thanks for working on this.
>>> Did you measure the performance impact of these changes?
>> I tracked performance with this change with X86 JIT and there was no
>> measurable difference, but the performance was governed more by the
>> quality of the compiled code, and not so much the compilation time.
>> If you can point me to a good compilation time benchmark I can get some
> I normally use 403.gcc, but if you don't have SPEC sources, these tests in the nightly test suite take a while to compile:
> If you run 'make TEST=nightly', both llc and opt compile times are interesting. The runtime of opt is cryptically reported in the GCCAS column.
Thanks for the detailed instructions.
I've finally got around to build and run the nightly tests, with and
without my changes, and times on the GCCAS column vary a few percent on
both directions. That is, whatever effect my change has is lost in noise.
I'm going to re-submit my patches to llvm-commits.
More information about the LLVMdev