diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-10-13 16:11:15 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-10-13 16:11:15 +0000 |
| commit | c5d7c6e5f68476fae3144fb2500bbf6d807555b3 (patch) | |
| tree | a317237ec8367ca93550704485cc31ed9ba44ccd /llvm/test/Transforms/InstCombine/stack-overalign.ll | |
| parent | 3d22fbd785eb934d94133020195bd9f268f654f4 (diff) | |
| download | bcm5719-llvm-c5d7c6e5f68476fae3144fb2500bbf6d807555b3.tar.gz bcm5719-llvm-c5d7c6e5f68476fae3144fb2500bbf6d807555b3.zip | |
[X86][SSE] Remove most of vector CTTZ custom lowering and use LegalizeDAG instead.
There is one remnant - AVX1 custom splitting of 256-bit vectors - which is due to a regression where the X86ISD::ANDNP is still performed as a YMM.
I've also tightened the CTLZ or CTPOP lowering in SelectionDAGLegalize::ExpandBitCount to require a legal CTLZ - it doesn't affect existing users and fixes an issue with AVX512 codegen.
llvm-svn: 344457
Diffstat (limited to 'llvm/test/Transforms/InstCombine/stack-overalign.ll')
0 files changed, 0 insertions, 0 deletions
