[llvm] [AMDGPU] Fix miscompile folding math calls with poison/undef vector lanes (PR #216971)

[Arseniy Obolenskiy via llvm-commits]

================
@@ -0,0 +1,97 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-simplifylib %s | FileCheck %s
----------------
aobolensk wrote:

Done

https://github.com/llvm/llvm-project/pull/216971