[llvm-branch-commits] [llvm] [AMDGPU][UnifyDivergentExitNodes][StructurizeCFG] Add support for callbr instruction with inline-asm (PR #152161)

[Sameer Sahasrabuddhe via llvm-branch-commits]

================
@@ -0,0 +1,54 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck %s
+
+define void @callbr_inline_asm(ptr %src, ptr %dst1, ptr %dst2, i32 %c) {
----------------
ssahasra wrote:

Need to add a test where the targets of a `callbr` create an unstructured region due to some branch "between" them before they reach the post-dominator.

https://github.com/llvm/llvm-project/pull/152161