[PATCH] D133972: [AMDGPU] Fix size of SOPK instructions to 4 bytes

[Anshil Gandhi via Phabricator via llvm-commits]

gandhi21299 added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/sopk-no-literal.ll:12
+; Function Attrs: convergent noinline nounwind
+define void @foo(i32 %a, i32 %b, float %c, float %d) unnamed_addr #8 {
+; CHECK-NEXT: bb.0:
----------------
arsenm wrote:
> I'm not seeing where there's a sopk instruction in this function
s_waitcnt_* are all SOPK instructions


================
Comment at: llvm/test/CodeGen/AMDGPU/sopk-no-literal.ll:89-90
+; CHECK-NEXT: s_setpc_b64 s[30:31]
+  %18 = fadd reassoc nnan ninf nsz contract float %c, %d
+  %19 = fadd reassoc nnan ninf nsz contract float %18, %c
+  ret void
----------------
arsenm wrote:
> Don't need all the instruction flags. Should also use named values
I will remove them since they are eliminated and do not generate any SOPK anyways.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D133972/new/

https://reviews.llvm.org/D133972