[PATCH] D106675: [X86] Freeze shl(x,1) -> add(x,x) vector fold (PR50468)

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: llvm/test/CodeGen/X86/oddsubvector.ll:232
 ; AVX1-NEXT:    addl c+128(%rip), %eax
-; AVX1-NEXT:    vmovd %eax, %xmm0
+; AVX1-NEXT:    vpinsrd $0, %eax, %xmm0, %xmm0
 ; AVX1-NEXT:    vmovdqa c+128(%rip), %xmm1
----------------
We've lost a INSERT_VECTOR_ELT -> (dependency breaking) SCALAR_TO_VECTOR optimization - still investigating this.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D106675/new/

https://reviews.llvm.org/D106675