[PATCH] D129537: [X86][DAGISel] Don't widen shuffle element with AVX512

[LuoYuanke via Phabricator via llvm-commits]

LuoYuanke added inline comments.


================
Comment at: llvm/test/CodeGen/X86/haddsub-undef.ll:1053
+; AVX512-SLOW:       # %bb.0:
+; AVX512-SLOW-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX512-SLOW-NEXT:    vaddps %xmm0, %xmm2, %xmm0
----------------
This looks a regression, I'll take a look at it.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D129537/new/

https://reviews.llvm.org/D129537