[llvm-branch-commits] [llvm] AMDGPU: Replace some float undef test uses with poison (PR #131090)

[Matt Arsenault via llvm-branch-commits]

================
@@ -37,7 +37,7 @@ bb2:
 define amdgpu_kernel void @preserve_condition_undef_flag(float %arg, i32 
%arg1, float %arg2) {
 bb0:
   %tmp = icmp sgt i32 %arg1, 4
-  %undef = call i1 @llvm.amdgcn.class.f32(float undef, i32 undef)
+  %undef = call i1 @llvm.amdgcn.class.f32(float poison, i32 undef)
----------------
arsenm wrote:

This is only touching float typed uses 

https://github.com/llvm/llvm-project/pull/131090
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits