[llvm] [AMDGPU] Invalidate uniformity info after intrinsic combine (PR #222357)

[Shilei Tian via llvm-commits]

================
@@ -0,0 +1,77 @@
+; REQUIRES: asserts
+; RUN: opt -mtriple=amdgpu10.10-amd-amdhsa \
+; RUN:   -passes=amdgpu-uniform-intrinsic-combine -S < %s | FileCheck %s
+; RUN: opt -mtriple=amdgpu10.10-amd-amdhsa \
+; RUN:   -passes='amdgpu-uniform-intrinsic-combine,reassociate' \
+; RUN:   -verify-analysis-invalidation -disable-output < %s
+
+; Reassociate must not use uniformity information that refers to invalidated
+; cycle information after the combine changes the IR.
+
+declare i64 @llvm.amdgcn.ballot.i64(i1)
----------------
shiltian wrote:

no need for declaration 

https://github.com/llvm/llvm-project/pull/222357