[llvm-dev] LLVM LNT floating point performance tests on X86 - using the llvm-test-suite benchmarks

[Blower, Melanie I via llvm-dev]

Thanks. I created https://reviews.llvm.org/D102861 to modify test-suite and suppress FP_CONTRACT in certain source files, this test-suite patch allows testing to pass with the patch for https://reviews.llvm.org/D74436 in place

> -----Original Message-----
> From: Johannes Doerfert <johannesdoerfert at gmail.com>
> Sent: Wednesday, May 19, 2021 3:53 PM
> To: Blower, Melanie I <melanie.blower at intel.com>; Florian Hahn
> <florian_hahn at apple.com>; llvm-dev <llvm-dev at lists.llvm.org>
> Cc: spatel+llvm at rotateright.com; hal.finkel.llvm at gmail.com
> Subject: Re: LLVM LNT floating point performance tests on X86 - using the llvm-
> test-suite benchmarks
> 
> 
> On 5/19/21 1:54 PM, Blower, Melanie I wrote:
> > Using march=native as suggested by @Florian
> Hahn<mailto:florian_hahn at apple.com> I can see 20 failing tests, thanks!
> >
> > I looked at the source for SingleSource/Benchmarks/Polybench/linear-
> algebra/kernels/trmm which is one of the failing tests and noticed that there is
> #pragma STDC FP_CONTRACT OFF in many places, but not in the function
> kernel_trmm
> >
> > Perhaps this function was overlooked for that pragma because the FMA is
> syntactically not obvious due to the += operation?  So I added the pragma and
> reran that test, and now that test is passing.
> >
> > Would it be acceptable to modify trmm with this change?
> 
> Yes.
> 
> 
> >
> > From: Florian Hahn <florian_hahn at apple.com>
> > Sent: Wednesday, May 19, 2021 12:25 PM
> > To: Blower, Melanie I <melanie.blower at intel.com>; llvm-dev <llvm-
> dev at lists.llvm.org>
> > Cc: Johannes Doerfert <johannesdoerfert at gmail.com>;
> spatel+llvm at rotateright.com; hal.finkel.llvm at gmail.com
> > Subject: Re: LLVM LNT floating point performance tests on X86 - using the
> llvm-test-suite benchmarks
> >
> >
> >
> >
> > On May 19, 2021, at 17:08, Blower, Melanie I
> <melanie.blower at intel.com<mailto:melanie.blower at intel.com>> wrote:
> >
> > What I'm trying to do is to determine whether the patch I'm submitting is
> going to cause benchmarking problems that force the patch to be reverted--
> since that happened the last time I committed the patch (several months ago).
> >
> >
> > IIUC the problem with the patch was not runtime performance, but
> unexpected results causing some tests/benchmarks to fail.
> >
> > I think you might need to select a CPU on X86 to cause the mis-compares.
> Below the commands I used to reproduce the failure of
> MultiSource/Applications/oggenc/oggenc. Note `-march=native`. Without that,
> the test passes. There are a couple of other failures as well.
> >
> >
> >> cmake -G Ninja \
> >      -DCMAKE_C_COMPILER=/path/to/bin/clang \
> >      -DCMAKE_C_FLAGS="-O3 -march=native" -DCMAKE_CXX_FLAGS="-O3 -
> march=native" \
> >      Path/to/llvm-test-suite
> >
> >> ninja MultiSource/Applications/oggenc/oggenc
> >> llvm-lit MultiSource/Applications/oggenc/
> > -- Testing: 1 tests, 1 workers --
> > FAIL: test-suite :: MultiSource/Applications/oggenc/oggenc.test (1 of 1)
> > ********************
> > Failed Tests (1):
> >    test-suite :: MultiSource/Applications/oggenc/oggenc.test
> >