Nikita Popov 24e9fbc1a3 Revert "[InstCombine] Fold multiuse shr eq zero" ...

This reverts commit 9423f78240.

A performance regression with this patch has been reported at
https://reviews.llvm.org/rG9423f78240a2#990953. Reverting for now.

2021-04-21 21:40:52 +02:00

..

addsub-inseltpoison.ll

…

addsub.ll

…

ctlz-loop.ll

Revert "[InstCombine] Fold multiuse shr eq zero"

2021-04-21 21:40:52 +02:00

horiz-math-inseltpoison.ll

…

horiz-math.ll

…

lit.local.cfg

…

loop-idiom-vs-indvars.ll

…

masked-memory-ops.ll

…

nancvt.ll

…

peel-before-lv-to-enable-vectorization.ll

…

pixel-splat.ll

[Reassociate] allow or->add with shl operands

2021-02-07 09:45:19 -05:00

pr48844-br-to-switch-vectorization.ll

…

scalarization-inseltpoison.ll

…

scalarization.ll

Update InstCombine to use undef matcher instead

2021-04-18 11:05:36 +09:00

shuffle-inseltpoison.ll

…

shuffle.ll

…

spurious-peeling.ll

[PassManager] Run additional LICM before LoopRotate

2021-04-02 11:11:42 +03:00

SROA-after-loop-unrolling.ll

…

vdiv-nounroll.ll

[PhaseOrdering] add test for loop-invariant fdiv; NFC

2021-04-16 10:51:43 -04:00

vdiv.ll

[PassManager] Run additional LICM before LoopRotate

2021-04-02 11:11:42 +03:00

vector-reductions-expanded.ll

[PhaseOrdering] add AVX attribute to make test less fragile; NFC

2021-03-23 11:34:33 -04:00

vector-reductions.ll

…