[PATCH] D135782: [AMDGPU] Add GFX11 tests for fcmp and ballot. NFC

[Jay Foad via Phabricator via llvm-commits]

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

Seems obviously fine.



================
Comment at: llvm/test/CodeGen/AMDGPU/v_cmp_gfx11.ll:16
 entry:
   %0 = tail call i64 @llvm.amdgcn.icmp.i64.i16(i16 0, i16 0, i32 32)
   %cmp0 = icmp eq i64 %0, 0
----------------
It's a bit nicer to use named values instead of numbered.


================
Comment at: llvm/test/CodeGen/AMDGPU/v_cmp_gfx11.ll:39
+entry:
+  %0 = tail call i64 @llvm.amdgcn.fcmp.i64.f16(half %x, half %y, i32 5)
+  %cmp0 = icmp eq i64 %0, 0
----------------
Same.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D135782/new/

https://reviews.llvm.org/D135782