[Mlir-commits] [mlir] [mlir][amdgpu] implement amdgpu.sparse_mfma wrapper for smfmac instructions (PR #171968)

[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/AMDGPUDialect.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 2b5010d72..d060e6747 100644
--- a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
+++ b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
@@ -3200,28 +3200,28 @@ void mlir::populateAMDGPUToROCDLConversionPatterns(LLVMTypeConverter &converter,
                                                    RewritePatternSet &patterns,
                                                    Chipset chipset) {
   populateAMDGPUTypeAndAttributeConversions(converter);
-  patterns.add<
-      FatRawBufferCastLowering,
-      RawBufferOpLowering<RawBufferLoadOp, ROCDL::RawPtrBufferLoadOp>,
-      RawBufferOpLowering<RawBufferStoreOp, ROCDL::RawPtrBufferStoreOp>,
-      RawBufferOpLowering<RawBufferAtomicFaddOp,
-                          ROCDL::RawPtrBufferAtomicFaddOp>,
-      RawBufferOpLowering<RawBufferAtomicFmaxOp,
-                          ROCDL::RawPtrBufferAtomicFmaxOp>,
-      RawBufferOpLowering<RawBufferAtomicSmaxOp,
-                          ROCDL::RawPtrBufferAtomicSmaxOp>,
-      RawBufferOpLowering<RawBufferAtomicUminOp,
-                          ROCDL::RawPtrBufferAtomicUminOp>,
-      RawBufferOpLowering<RawBufferAtomicCmpswapOp,
-                          ROCDL::RawPtrBufferAtomicCmpSwap>,
-      AMDGPUDPPLowering, MemoryCounterWaitOpLowering, LDSBarrierOpLowering,
-      SchedBarrierOpLowering, MFMAOpLowering, ScaledMFMAOpLowering, 
-      WMMAOpLowering, SparseMFMAOpLowering, ExtPackedFp8OpLowering,
-      ScaledExtPackedMatrixOpLowering, ScaledExtPackedOpLowering,
-      PackedScaledTruncOpLowering, PackedTrunc2xFp8OpLowering,
-      PackedStochRoundFp8OpLowering, GatherToLDSOpLowering,
-      TransposeLoadOpLowering, AMDGPUPermlaneLowering,
-      AMDGPUMakeDmaBaseLowering, AMDGPUMakeDmaDescriptorLowering>(converter,
-                                                                  chipset);
+  patterns
+      .add<FatRawBufferCastLowering,
+           RawBufferOpLowering<RawBufferLoadOp, ROCDL::RawPtrBufferLoadOp>,
+           RawBufferOpLowering<RawBufferStoreOp, ROCDL::RawPtrBufferStoreOp>,
+           RawBufferOpLowering<RawBufferAtomicFaddOp,
+                               ROCDL::RawPtrBufferAtomicFaddOp>,
+           RawBufferOpLowering<RawBufferAtomicFmaxOp,
+                               ROCDL::RawPtrBufferAtomicFmaxOp>,
+           RawBufferOpLowering<RawBufferAtomicSmaxOp,
+                               ROCDL::RawPtrBufferAtomicSmaxOp>,
+           RawBufferOpLowering<RawBufferAtomicUminOp,
+                               ROCDL::RawPtrBufferAtomicUminOp>,
+           RawBufferOpLowering<RawBufferAtomicCmpswapOp,
+                               ROCDL::RawPtrBufferAtomicCmpSwap>,
+           AMDGPUDPPLowering, MemoryCounterWaitOpLowering, LDSBarrierOpLowering,
+           SchedBarrierOpLowering, MFMAOpLowering, ScaledMFMAOpLowering,
+           WMMAOpLowering, SparseMFMAOpLowering, ExtPackedFp8OpLowering,
+           ScaledExtPackedMatrixOpLowering, ScaledExtPackedOpLowering,
+           PackedScaledTruncOpLowering, PackedTrunc2xFp8OpLowering,
+           PackedStochRoundFp8OpLowering, GatherToLDSOpLowering,
+           TransposeLoadOpLowering, AMDGPUPermlaneLowering,
+           AMDGPUMakeDmaBaseLowering, AMDGPUMakeDmaDescriptorLowering>(
+          converter, chipset);
   patterns.add<AMDGPUSwizzleBitModeLowering>(converter);
 }

``````````

</details>


https://github.com/llvm/llvm-project/pull/171968