[PATCH] D159303: [AMDGPU] Precommit test for i8 vector CopyToReg handling patch

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll:3173
+; GFX10-SCRATCH-NEXT:    s_setpc_b64 s[30:31]
+  %val = load <2 x i8>, ptr addrspace(1) undef
+  call amdgpu_gfx void @external_void_func_v2i8(<2 x i8> %val)
----------------
use load null instead of load undef 


================
Comment at: llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll:3174
+  %val = load <2 x i8>, ptr addrspace(1) undef
+  call amdgpu_gfx void @external_void_func_v2i8(<2 x i8> %val)
+  ret void
----------------
not sure if call returns are covered


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D159303/new/

https://reviews.llvm.org/D159303