[llvm-dev] Reversion of rL292621 caused about 7% performance regressions on Cortex-M
Evgeny Astigeevich via llvm-dev
llvm-dev at lists.llvm.org
Mon Jan 30 02:54:38 PST 2017
I checked the patch. It works. The regressions are fixed. I will have results of other benchmarks tomorrow.
Thank you very much for the quick resolution.
Senior Compiler Engineer
> -----Original Message-----
> From: Wei Mi [mailto:wmi at google.com]
> Sent: Saturday, January 28, 2017 1:34 AM
> To: Evgeny Astigeevich
> Cc: llvm-dev; nd
> Subject: Re: Reversion of rL292621 caused about 7% performance
> regressions on Cortex-M
> Quentin recommited the patch with the fix at rL293353.
> On Fri, Jan 27, 2017 at 1:31 PM, Wei Mi <wmi at google.com> wrote:
> > Hi Evgeny,
> > Quentin and Matthias found it was a problem about subreg live range
> > update and will push a fix soon
> > (http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-
> > Thanks,
> > Wei.
More information about the llvm-dev