[Mlir-commits] [mlir] [MLIR][XeGPU] Updates XeGPU TensorDescAttr and Refine Gather/Scatter definition. (PR #109144)

LLVM Continuous Integration llvmlistbot at llvm.org
Mon Sep 23 07:09:57 PDT 2024 

llvm-ci wrote:

LLVM Buildbot has detected a new failure on builder `flang-aarch64-latest-gcc` running on `linaro-flang-aarch64-latest-gcc` while building `mlir` at step 5 "build-unified-tree".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/130/builds/3964

<details>
<summary>Here is the relevant piece of the build log for the reference</summary>

```
Step 5 (build-unified-tree) failure: build (failure)
...
57.820 [2890/10/4310] Creating library symlink lib/libMLIRPDLToPDLInterp.so
57.823 [2890/9/4311] Building CXX object tools/mlir/lib/Target/LLVMIR/Dialect/NVVM/CMakeFiles/obj.MLIRNVVMToLLVMIRTranslation.dir/NVVMToLLVMIRTranslation.cpp.o
57.826 [2890/8/4312] Creating library symlink lib/libMLIRSubsetOpInterface.so
57.839 [2888/9/4313] Building CXX object tools/mlir/lib/Target/LLVM/CMakeFiles/obj.MLIRTargetLLVM.dir/ModuleToObject.cpp.o
57.986 [2888/8/4314] Linking CXX shared library lib/libMLIRArithUtils.so.20.0git
58.040 [2872/23/4315] Creating library symlink lib/libMLIRArithUtils.so
58.046 [2872/22/4316] Linking CXX shared library lib/libMLIRRewritePDL.so.20.0git
58.145 [2872/21/4317] Linking CXX shared library lib/libMLIRTargetLLVMIRImport.so.20.0git
58.177 [2872/20/4318] Linking CXX shared library lib/libMLIRSparseTensorDialect.so.20.0git
58.223 [2872/19/4319] Building CXX object tools/mlir/lib/Conversion/VectorToXeGPU/CMakeFiles/obj.MLIRVectorToXeGPU.dir/VectorToXeGPU.cpp.o
FAILED: tools/mlir/lib/Conversion/VectorToXeGPU/CMakeFiles/obj.MLIRVectorToXeGPU.dir/VectorToXeGPU.cpp.o 
/usr/local/bin/c++ -DGTEST_HAS_RTTI=0 -D_DEBUG -D_GLIBCXX_ASSERTIONS -D_GNU_SOURCE -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS -D__STDC_LIMIT_MACROS -I/home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/build/tools/mlir/lib/Conversion/VectorToXeGPU -I/home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/llvm-project/mlir/lib/Conversion/VectorToXeGPU -I/home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/build/include -I/home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/llvm-project/llvm/include -I/home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/llvm-project/mlir/include -I/home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/build/tools/mlir/include -fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror=date-time -fno-lifetime-dse -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wno-missing-field-initializers -pedantic -
Wno-long-long -Wimplicit-fallthrough -Wno-maybe-uninitialized -Wno-nonnull -Wno-class-memaccess -Wno-redundant-move -Wno-pessimizing-move -Wno-noexcept-type -Wdelete-non-virtual-dtor -Wsuggest-override -Wno-comment -Wno-misleading-indentation -Wctad-maybe-unsupported -fdiagnostics-color -ffunction-sections -fdata-sections -Wundef -O3 -DNDEBUG -std=c++17  -fno-exceptions -funwind-tables -fno-rtti -UNDEBUG -MD -MT tools/mlir/lib/Conversion/VectorToXeGPU/CMakeFiles/obj.MLIRVectorToXeGPU.dir/VectorToXeGPU.cpp.o -MF tools/mlir/lib/Conversion/VectorToXeGPU/CMakeFiles/obj.MLIRVectorToXeGPU.dir/VectorToXeGPU.cpp.o.d -o tools/mlir/lib/Conversion/VectorToXeGPU/CMakeFiles/obj.MLIRVectorToXeGPU.dir/VectorToXeGPU.cpp.o -c /home/tcwg-buildbot/worker/flang-aarch64-latest-gcc/llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp: In member function ‘virtual llvm::LogicalResult {anonymous}::TransferReadLowering::matchAndRewrite(mlir::vector::TransferReadOp, mlir::PatternRewriter&) const’:
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp:172:16: error: ‘mlir::xegpu::MemoryScope’ has not been declared
  172 |         xegpu::MemoryScope::Global,
      |                ^~~~~~~~~~~
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp: In member function ‘virtual llvm::LogicalResult {anonymous}::TransferWriteLowering::matchAndRewrite(mlir::vector::TransferWriteOp, mlir::PatternRewriter&) const’:
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp:217:57: error: ‘mlir::xegpu::MemoryScope’ has not been declared
  217 |         /*scattered=*/false, /*array_length=*/1, xegpu::MemoryScope::Global,
      |                                                         ^~~~~~~~~~~
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp: At global scope:
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp:85:1: warning: ‘mlir::xegpu::CreateNdDescOp {anonymous}::createNdDescriptor(mlir::PatternRewriter&, mlir::Location, mlir::xegpu::TensorDescType, mlir::TypedValue<mlir::MemRefType>, mlir::Operation::operand_range)’ defined but not used [-Wunused-function]
   85 | createNdDescriptor(PatternRewriter &rewriter, Location loc,
      | ^~~~~~~~~~~~~~~~~~

58.224 [2872/18/4320] Building CXX object tools/mlir/lib/Tools/Plugins/CMakeFiles/obj.MLIRPluginsLib.dir/PassPlugin.cpp.o
58.230 [2872/17/4321] Building CXX object tools/mlir/lib/Target/LLVM/CMakeFiles/obj.MLIRROCDLTarget.dir/ROCDL/Target.cpp.o
58.232 [2872/16/4322] Building CXX object tools/mlir/lib/Target/LLVM/CMakeFiles/obj.MLIRROCDLTarget.dir/ROCDL/Utils.cpp.o
58.238 [2872/15/4323] Building CXX object tools/mlir/lib/Tools/mlir-pdll-lsp-server/CMakeFiles/MLIRPdllLspServerLib.dir/MlirPdllLspServerMain.cpp.o
58.239 [2872/14/4324] Building CXX object tools/mlir/lib/Tools/mlir-pdll-lsp-server/CMakeFiles/MLIRPdllLspServerLib.dir/LSPServer.cpp.o
58.240 [2872/13/4325] Building CXX object tools/mlir/lib/Tools/mlir-opt/CMakeFiles/obj.MLIROptLib.dir/MlirOptMain.cpp.o
58.241 [2872/12/4326] Building CXX object tools/mlir/lib/Tools/mlir-pdll-lsp-server/CMakeFiles/MLIRPdllLspServerLib.dir/PDLLServer.cpp.o
58.242 [2872/11/4327] Building CXX object tools/mlir/lib/Tools/Plugins/CMakeFiles/obj.MLIRPluginsLib.dir/DialectPlugin.cpp.o
58.245 [2872/10/4328] Building CXX object tools/mlir/lib/Transforms/CMakeFiles/obj.MLIRTransforms.dir/ControlFlowSink.cpp.o
58.251 [2872/9/4329] Building CXX object tools/mlir/lib/Transforms/CMakeFiles/obj.MLIRTransforms.dir/Canonicalizer.cpp.o
58.260 [2872/8/4330] Building CXX object tools/mlir/lib/Transforms/CMakeFiles/obj.MLIRTransforms.dir/CompositePass.cpp.o
58.261 [2872/7/4331] Building CXX object tools/mlir/test/lib/Interfaces/LoopLikeInterface/CMakeFiles/MLIRLoopLikeInterfaceTestPasses.dir/TestBlockInLoop.cpp.o
58.262 [2872/6/4332] Building CXX object tools/mlir/lib/Tools/mlir-query/CMakeFiles/obj.MLIRQueryLib.dir/MlirQueryMain.cpp.o
58.267 [2872/5/4333] Building CXX object tools/mlir/lib/Tools/PDLL/CodeGen/CMakeFiles/obj.MLIRPDLLCodeGen.dir/CPPGen.cpp.o
58.275 [2872/4/4334] Building CXX object tools/mlir/lib/Tools/PDLL/CodeGen/CMakeFiles/obj.MLIRPDLLCodeGen.dir/MLIRGen.cpp.o
63.790 [2872/3/4335] Building CXX object tools/mlir/lib/Dialect/XeGPU/Transforms/CMakeFiles/obj.MLIRXeGPUTransforms.dir/XeGPUFoldAliasOps.cpp.o
69.425 [2872/2/4336] Building CXX object tools/mlir/lib/Dialect/XeGPU/IR/CMakeFiles/obj.MLIRXeGPUDialect.dir/XeGPUDialect.cpp.o
71.537 [2872/1/4337] Building CXX object tools/mlir/lib/Dialect/XeGPU/IR/CMakeFiles/obj.MLIRXeGPUDialect.dir/XeGPUOps.cpp.o
ninja: build stopped: subcommand failed.

```

</details>

https://github.com/llvm/llvm-project/pull/109144

More information about the Mlir-commits mailing list