[llvm] [AMDGPU] Look through bitcast when skipping musttail returns in UnifyDivergentExitNodes (PR #201021)

[Krzysztof Drewniak via llvm-commits]

================
@@ -102,3 +103,29 @@ bb.0:
 bb.1:
   ret i32 %load
 }
+
+define ptr @musttail_call_with_bitcast(ptr %p) {
----------------
krzysz00 wrote:

Is it intentional that the pass output is the same as the pass input?

(or, would it make sense to pre-commit this?)

https://github.com/llvm/llvm-project/pull/201021