[llvm] [AMDGPU] Move attributes to the bottom of a test file (NFC) (PR #219470)

[via llvm-commits]

llvmorg-github-actions[bot] wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Frederik Harwath (frederik-h)

<details>
<summary>Changes</summary>

This was requested in post merge review of #<!-- -->219172.

---
Full diff: https://github.com/llvm/llvm-project/pull/219470.diff


1 Files Affected:

- (modified) llvm/test/CodeGen/AMDGPU/promote-alloca-lds-granularity-limit.ll (+2-1) 


``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/promote-alloca-lds-granularity-limit.ll b/llvm/test/CodeGen/AMDGPU/promote-alloca-lds-granularity-limit.ll
index 5e1bd118ab504..00aa7ed524ead 100644
--- a/llvm/test/CodeGen/AMDGPU/promote-alloca-lds-granularity-limit.ll
+++ b/llvm/test/CodeGen/AMDGPU/promote-alloca-lds-granularity-limit.ll
@@ -1,7 +1,6 @@
 ; RUN: opt -S -mtriple=amdgpu9.50-amd-amdhsa -passes=amdgpu-promote-alloca -disable-promote-alloca-to-vector < %s | FileCheck %s
 
 @lds_12800 = internal addrspace(3) global [12800 x i8] poison, align 16
-attributes #0 = { "amdgpu-flat-work-group-size"="64,64" }
 
 ; This is a regression test for a bug in getMaxLocalMemSizeWithWaveCount
 ; which did not round to the LDS allocation block size, leading
@@ -35,3 +34,5 @@ define amdgpu_kernel void @test(ptr addrspace(1) %out, i32 %idx) #0 {
   store i8 %load, ptr addrspace(1) %out, align 1
   ret void
 }
+
+attributes #0 = { "amdgpu-flat-work-group-size"="64,64" }

``````````

</details>


https://github.com/llvm/llvm-project/pull/219470