[Mlir-commits] [mlir] [MLIR][AMDGPU] Add amdgpu.global_transpose_load op for RDNA4 global memory transpose loads (PR #195287)

[llvmlistbot at llvm.org]

github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {clang-format}-->


:warning: C/C++ code formatter, clang-format found issues in your code. :warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
git-clang-format --diff origin/main HEAD --extensions cpp -- mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp mlir/lib/Dialect/AMDGPU/IR/AMDGPUOps.cpp --diff_from_common_commit
``````````

:warning:
The reproduction instructions above might return results for more than one PR
in a stack if you are using a stacked PR workflow. You can limit the results by
changing `origin/main` to the base branch/commit you want to compare against.
:warning:

</details>

<details>
<summary>
View the diff from clang-format here.
</summary>

``````````diff
diff --git a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
index 5844a845b..ef7dfa54c 100644
--- a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
+++ b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
@@ -4468,8 +4468,8 @@ void mlir::populateAMDGPUToROCDLConversionPatterns(LLVMTypeConverter &converter,
            PackedScaledTruncOpLowering, PackedTrunc2xFp8OpLowering,
            PackedStochRoundFp8OpLowering, GatherToLDSOpLowering,
            GlobalLoadAsyncToLDSOpLowering, TransposeLoadOpLowering,
-           GlobalTransposeLoadOpLowering,
-           AMDGPUPermlaneLowering, AMDGPUMakeDmaBaseLowering<MakeDmaBaseOp>,
+           GlobalTransposeLoadOpLowering, AMDGPUPermlaneLowering,
+           AMDGPUMakeDmaBaseLowering<MakeDmaBaseOp>,
            AMDGPUMakeDmaBaseLowering<MakeGatherDmaBaseOp>,
            AMDGPULowerDescriptor<MakeDmaDescriptorOp>,
            AMDGPULowerDescriptor<MakeGatherDmaDescriptorOp>,
diff --git a/mlir/lib/Dialect/AMDGPU/IR/AMDGPUOps.cpp b/mlir/lib/Dialect/AMDGPU/IR/AMDGPUOps.cpp
index 7d9bccd89..d50448a6d 100644
--- a/mlir/lib/Dialect/AMDGPU/IR/AMDGPUOps.cpp
+++ b/mlir/lib/Dialect/AMDGPU/IR/AMDGPUOps.cpp
@@ -1091,13 +1091,12 @@ LogicalResult GlobalTransposeLoadOp::verify() {
 
   auto resultType = cast<VectorType>(getType());
   size_t numElements = resultType.getNumElements();
-  size_t elementTypeSize =
-      resultType.getElementType().getIntOrFloatBitWidth();
+  size_t elementTypeSize = resultType.getElementType().getIntOrFloatBitWidth();
 
   // ElementSize -> NumElements (matches ISA-documented global_load_tr variants)
   const llvm::SmallDenseMap<size_t, size_t> kValidLoadSizeMap = {
-      {8, 8},   // global_load_tr_b64
-      {16, 8},  // global_load_tr_b128
+      {8, 8},  // global_load_tr_b64
+      {16, 8}, // global_load_tr_b128
   };
 
   auto validNumElems = kValidLoadSizeMap.find(elementTypeSize);

``````````

</details>


https://github.com/llvm/llvm-project/pull/195287