[PATCH] D130059: [X86] Promote v32f16's fadd into v32f32's fadd when it is avx512 without avx512fp16

[Phoebe Wang via Phabricator via llvm-commits]

pengfei accepted this revision.
pengfei added a comment.
This revision is now accepted and ready to land.

LGTM, thanks for the fix!



================
Comment at: llvm/test/CodeGen/X86/avx512-f16c-v16f16-fadd.ll:4
+
+define <16 x half> @foo(<16 x half> %a, <16 x half> %b) {
+; CHECK-LABEL: foo:
----------------
Add `nounwind` to supress the .cfi*


================
Comment at: llvm/test/CodeGen/X86/avx512-skx-v32f16-fadd.ll:4
+
+define <32 x half> @foo(<32 x half> %a, <32 x half> %b) {
+; CHECK-LABEL: foo:
----------------
ditto.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130059/new/

https://reviews.llvm.org/D130059