[Openmp-commits] [PATCH] D129344: [libomptarget] compile DeviceRTL bc files with -O3

[Ye Luo via Phabricator via Openmp-commits]

ye-luo added a comment.

When I compared miniQMC kernel performance w/ w/o LTO, the difference comes from bc files (slower) being compiled with O1 <https://reviews.llvm.org/owners/package/1/> and the LTO used static library (faster) being compiled with O3 <https://reviews.llvm.org/owners/package/3/>. About 30% difference on a kernel I was monitoring.
To reduce the variants among compilation options, it is better to just use O3 <https://reviews.llvm.org/owners/package/3/>.
For a long time, we cannot change to O3 <https://reviews.llvm.org/owners/package/3/> because of the backend rejects the kernel compiled with O3 <https://reviews.llvm.org/owners/package/3/>. This issue has been resolved and I changed the bc compilation to O3 <https://reviews.llvm.org/owners/package/3/>.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D129344/new/

https://reviews.llvm.org/D129344