[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/avx512-shuffles/shuffle-blend.ll:243
+  ret <4 x i32> %t4
+}
----------------
RKSimon wrote:
> pre-commit these additional tests
Sure. I'll do it.


================
Comment at: llvm/test/CodeGen/X86/avx512-shuffles/shuffle-blend.ll:94
+; X86-AVX512BW-NEXT:    vmovdqa64 %zmm2, %zmm0
+; X86-AVX512BW-NEXT:    retl
+;
----------------
RKSimon wrote:
> LuoYuanke wrote:
> > `retl` can be merged to `retq` by `ret{{[l|q]}}`. Not sure why utils/update_llc_test_checks.py doesn't merge.
> "kmovd %eax" vs "kmovq %rax"
Got it. :)


Repository:
  rG LLVM Github Monorepo

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

https://reviews.llvm.org/D129537