[llvm] AMDGPU: Allow operand folding between loop body and its preheader (PR #137022)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,114 @@
+; NOTE: Do not autogenerate
+; RUN: llc -mtriple=amdgcn -mcpu=gfx942 -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
----------------
arsenm wrote:

```suggestion
; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefix=GCN %s
```

https://github.com/llvm/llvm-project/pull/137022