[PATCH] D62969: [x86] narrow extract subvector of vector select

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: llvm/test/CodeGen/X86/horizontal-reduce-smax.ll:541
-; X64-AVX1-NEXT:    vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
+; X64-AVX1-NEXT:    vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
 ; X64-AVX1-NEXT:    vmovq %xmm0, %rax
 ; X64-AVX1-NEXT:    vzeroupper
----------------
This case probably has a extract_element(extract_subvector(vselect())) pattern - should the existing DAGCombine code catch it?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D62969/new/

https://reviews.llvm.org/D62969