[Mlir-commits] [mlir] [mlir][xevm] Remove unnecessary attach target pass. (PR #184432)

[llvmlistbot at llvm.org]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-mlir-gpu

Author: Charitha Saumya (charithaintc)

<details>
<summary>Changes</summary>



---
Full diff: https://github.com/llvm/llvm-project/pull/184432.diff


1 Files Affected:

- (modified) mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp (-1) 


``````````diff
diff --git a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
index d6a4dae4c5c32..ba2601038acb0 100644
--- a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
+++ b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
@@ -64,7 +64,6 @@ void buildGPUPassPipeline(OpPassManager &pm,
   xegpu::XeGPUPropagateLayoutOptions laneLayoutOptions;
   laneLayoutOptions.layoutKind = "lane";
   pm.addNestedPass<ModuleOp>(createCSEPass());
-  pm.addNestedPass<ModuleOp>(createGpuXeVMAttachTarget());
   if (options.xegpuOpLevel == "workgroup") {
     xegpu::XeGPUPropagateLayoutOptions sgLayoutOptions;
     sgLayoutOptions.layoutKind = "subgroup";

``````````

</details>


https://github.com/llvm/llvm-project/pull/184432