[llvm] [AMDGPU][InstCombine] Fold unused m0 operand to poison for sendmsg intrinsics (PR #183755)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,234 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -passes=instcombine -S | FileCheck %s --check-prefixes=CHECK,GFX9
+; RUN: opt < %s -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -passes=instcombine -S | FileCheck %s --check-prefixes=CHECK,GFX10
+; RUN: opt < %s -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -passes=instcombine -S | FileCheck %s --check-prefixes=CHECK,GFX11
+
----------------
arsenm wrote:

Can you check this is a no-op for the default target? In particular the cases with conflicting encodings should nop 

https://github.com/llvm/llvm-project/pull/183755