diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-10-14 15:56:28 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-10-14 15:56:28 +0000 |
| commit | a0590a4f7a661388f4924a88c0fff9ccf3683cf1 (patch) | |
| tree | b6100f7e93f3ad887587d1a724d1c9843f5c0f00 /llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | |
| parent | 7181146c6c45e14614b4eef8a8b5d1e91d0b2ad7 (diff) | |
| download | bcm5719-llvm-a0590a4f7a661388f4924a88c0fff9ccf3683cf1.tar.gz bcm5719-llvm-a0590a4f7a661388f4924a88c0fff9ccf3683cf1.zip | |
[LegalizeDAG] Don't bother with final MUL+SRL stage for byte CTPOP.
The final stage of CTPOP expansion (v = (v * 0x01010101...) >> (Len - 8)) is completely pointless for the byte (Len = 8) case as it reduces to (v = (v * 0x01...) >> 0), but annoyingly this doesn't always get optimized away.
Found while investigating generic vector CTPOP expansion (PR32655).
llvm-svn: 344477
Diffstat (limited to 'llvm/lib/Transforms/Vectorize/LoopVectorize.cpp')
0 files changed, 0 insertions, 0 deletions
