[PATCH] D96793: [AMDGPU] Add implicit vcc_lo on S_CBRANCH_VCCNZ in wave32

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/skip-if-dead.ll:33
+; GFX10-WAVE64-NEXT:    exp null off, off, off, off done vm
+; GFX10-WAVE64-NEXT:    s_endpgm
+;
----------------
You could add a WAVE64 prefix, to common up the SI and GFX10-WAVE64 checks here.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D96793/new/

https://reviews.llvm.org/D96793