Address review comments.

mshahneo · mshahneo · commit 14487e39092b · 2025-10-17T17:56:38.000Z
Remove the explicit use of `convert-xevm-to-llvm` pass.
`convert-to-llvm` already uses this pattern.
diff --git a/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp b/mlir/lib/Dialect/GPU/Pipelines/GPUToXeVMPipeline.cpp
@@ -83,7 +83,6 @@ void buildGpuPassPipeline(OpPassManager &pm,
     pm.addNestedPass<gpu::GPUModuleOp>(
         createConvertGpuOpsToLLVMSPVOps(gpuToLLVMSPVOptions));
   }
-  pm.addNestedPass<gpu::GPUModuleOp>(createConvertXeVMToLLVMPass());
   pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());
 }
 

Original file line number	Diff line number	Diff line change
`@@ -83,7 +83,6 @@ void buildGpuPassPipeline(OpPassManager &pm,`
`83`	`83`	`pm.addNestedPass<gpu::GPUModuleOp>(`
`84`	`84`	`createConvertGpuOpsToLLVMSPVOps(gpuToLLVMSPVOptions));`
`85`	`85`	`}`
`86`		`- pm.addNestedPass<gpu::GPUModuleOp>(createConvertXeVMToLLVMPass());`
`87`	`86`	`pm.addNestedPass<gpu::GPUModuleOp>(createCSEPass());`
`88`	`87`	`}`
`89`	`88`