[llvm] [NFC][AMDGPU] Pre-commit a test case that shows wrong reverse operation is used for V_CMPX_LE_U32 (PR #146527)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Shilei Tian (shiltian)

<details>
<summary>Changes</summary>



---
Full diff: https://github.com/llvm/llvm-project/pull/146527.diff


1 Files Affected:

- (modified) llvm/test/CodeGen/AMDGPU/cmp_shrink.mir (+13) 


``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/cmp_shrink.mir b/llvm/test/CodeGen/AMDGPU/cmp_shrink.mir
index ae3fa153f381a..296903043bceb 100644
--- a/llvm/test/CodeGen/AMDGPU/cmp_shrink.mir
+++ b/llvm/test/CodeGen/AMDGPU/cmp_shrink.mir
@@ -10,3 +10,16 @@ body:             |
     ; GCN: S_CMP_LT_I32 65, 1, implicit-def $scc
     S_CMP_GT_I32 1, 65, implicit-def $scc
 ...
+
+---
+name:             shrink_icmp
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: shrink_icmp
+    ; GCN: %op0:sgpr_32 = COPY $sgpr0
+    ; GCN-NEXT: %cond:sreg_64 = V_CMPX_LE_U32_e64 5, %op0, implicit-def $exec, implicit $exec
+    ; GCN-NEXT: S_NOP 0
+    %op0:sgpr_32 = COPY $sgpr0
+    %cond:sreg_64 = V_CMPX_LE_U32_e64 %op0, 5, implicit-def $exec, implicit $exec
+    S_NOP 0
+...

``````````

</details>


https://github.com/llvm/llvm-project/pull/146527