[llvm] [LoopUnroll] Don't runtime-unroll multi-exit loops with a divergent side exit (PR #224924)

[Harrison Hao via llvm-commits]

================
@@ -0,0 +1,246 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx950 -passes=loop-unroll \
----------------
harrisonGPU wrote:

```suggestion
; RUN: opt -mtriple=amdgpu9.50 -passes=loop-unroll \
```

https://github.com/llvm/llvm-project/pull/224924