[llvm] [AMDGPU] Do not fold COPY with implicit operands (PR #136003)

[Mariusz Sikora via llvm-commits]

================
@@ -0,0 +1,36 @@
+# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -run-pass=si-fold-operands -o - %s | FileCheck %s
+
+---
+liveins:
+name:            do_not_fold_copy_with_implicit_exec
+tracksRegLiveness: true
+body:             |
+  ; CHECK: bb.0:
+  ; CHECK: bb.1:
+  ; CHECK: %[[A:[0-9]*]]:sreg_32 = S_ADD_I32
+  ; CHECK: COPY %[[A]]
+  ; CHECKL SI_LOOP
----------------
mariusz-sikora-at-amd wrote:

I auto-generated this test in this commit: https://github.com/llvm/llvm-project/pull/136003/commits/c9a9f10090f1d20b31ac8d32069e2097c4bc1bf6

https://github.com/llvm/llvm-project/pull/136003