diff options
| author | Tom Eccles <tom.eccles@arm.com> | 2025-05-30 17:35:41 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-30 17:35:41 +0100 |
| commit | d16ecad968244ca42ce09cb3199dea1ec994b211 (patch) | |
| tree | 6839565ad22bc1bc9757e19f45b3b352e3ffd895 /llvm/tools/llvm-objdump/llvm-objdump.cpp | |
| parent | c66dbbe385561a349ec854e545bbab395ec6dcf8 (diff) | |
| download | llvm-d16ecad968244ca42ce09cb3199dea1ec994b211.zip llvm-d16ecad968244ca42ce09cb3199dea1ec994b211.tar.gz llvm-d16ecad968244ca42ce09cb3199dea1ec994b211.tar.bz2 | |
[flang] Disable noalias by default (#142128)
With these enabled we see a 70% performance regression for exchange2_r
on neoverse-v1 (aws graviton 3) using `-mcpu=native -Ofast -flto`. There
is also a smaller regression on neoverse-v2.
This appears to be because function specialization is no longer kicking
in during LTO for digits_2. This can be seen in the output executable:
previously it contained specialized copies of the function with names
like `_QMbrute_forcePdigits_2.specialized.4`. Now there are no names
like this.
The bug is not in flang - instead in the function specialization pass -
but due to the size of the regression I would like to request that this
is disabled until function specialization has been fixed.
Diffstat (limited to 'llvm/tools/llvm-objdump/llvm-objdump.cpp')
0 files changed, 0 insertions, 0 deletions