[PATCH] D59041: [SDAG][X86] Expand pow2 mulo using shifts

[Nikita Popov via Phabricator via llvm-commits]

nikic marked 2 inline comments as done.
nikic added inline comments.


================
Comment at: llvm/test/CodeGen/X86/mulo-pow2.ll:30
-; AVX-NEXT:    vpcmpeqd %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vblendvps %xmm2, %xmm0, %xmm1, %xmm0
 ; AVX-NEXT:    retq
----------------
This being optimized is a nice side-effect, but we really should have a fold for `mulo(x, 1)`.


================
Comment at: llvm/test/CodeGen/X86/mulo-pow2.ll:109
 ; AVX-NEXT:    vpcmpeqd %xmm2, %xmm3, %xmm2
 ; AVX-NEXT:    vblendvps %xmm2, %xmm0, %xmm1, %xmm0
 ; AVX-NEXT:    retq
----------------
This code is generated by the `mulo(x, 2) -> addo(x, x)` fold and seems worse than what we'd get from the shift expansion. Not sure what to do about it.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59041/new/

https://reviews.llvm.org/D59041