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

Mon Sep 23 07:10:46 PDT 2024

llvm-ci wrote:

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

Full details are available at: https://lab.llvm.org/buildbot/#/builders/80/builds/4006

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

```
Step 5 (build-unified-tree) failure: build (failure)
...
63.820 [2649/28/4729] Building ShapeInferenceOpInterfaces.h.inc...
63.820 [2649/27/4730] Building MyExtension.h.inc...
63.821 [2649/26/4731] Building MyExtensionTypes.h.inc...
63.824 [2649/25/4732] Building MyExtension.cpp.inc...
63.826 [2649/24/4733] Creating library symlink lib/libMLIRArithTestPasses.so
63.844 [2649/23/4734] Linking CXX shared library lib/libMLIRMathTestPasses.so.20.0git
63.845 [2649/22/4735] Linking CXX shared library lib/libMLIRCAPIExecutionEngine.so.20.0git
63.868 [2649/21/4736] Building CXX object tools/mlir/examples/minimal-opt/CMakeFiles/mlir-minimal-opt-canonicalize.dir/mlir-minimal-opt-canonicalize.cpp.o
63.872 [2649/20/4737] Linking CXX shared library lib/libMLIRAffineToStandard.so.20.0git
63.942 [2649/19/4738] 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-sharedlibs/build/tools/mlir/lib/Conversion/VectorToXeGPU -I/home/tcwg-buildbot/worker/flang-aarch64-sharedlibs/llvm-project/mlir/lib/Conversion/VectorToXeGPU -I/home/tcwg-buildbot/worker/flang-aarch64-sharedlibs/build/include -I/home/tcwg-buildbot/worker/flang-aarch64-sharedlibs/llvm-project/llvm/include -I/home/tcwg-buildbot/worker/flang-aarch64-sharedlibs/llvm-project/mlir/include -I/home/tcwg-buildbot/worker/flang-aarch64-sharedlibs/build/tools/mlir/include -fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror=date-time -Werror=unguarded-availability-new -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wmissing-field-initializers -pedantic -Wno-long-long -Wc++98-compat-extra-semi -Wimplicit-fallthrough -Wcovered-switch-default -Wno-noexcept-type -Wnon-virtual-dtor -Wdelete-non-virtual-dtor -Wsuggest-override -Wstring-conversion -Wmisleading-indentation -Wctad-maybe-unsupported -fdiagnostics-color -ffunction-sections -fdata-sections -Wundef -Werror=mismatched-tags -Werror=global-constructors -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-sharedlibs/llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp:172:16: error: no member named 'MemoryScope' in namespace 'mlir::xegpu'
  172 |         xegpu::MemoryScope::Global,
      |         ~~~~~~~^
../llvm-project/mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp:217:57: error: no member named 'MemoryScope' in namespace 'mlir::xegpu'
  217 |         /*scattered=*/false, /*array_length=*/1, xegpu::MemoryScope::Global,
      |                                                  ~~~~~~~^
2 errors generated.
63.975 [2649/18/4739] Linking CXX shared library lib/libMLIRTosaToLinalg.so.20.0git
63.978 [2649/17/4740] Linking CXX shared library lib/libMLIRMeshTest.so.20.0git
63.982 [2649/16/4741] Linking CXX shared library lib/libMLIRSPIRVTranslateRegistration.so.20.0git
64.002 [2649/15/4742] Linking CXX shared library lib/libMLIRTensorTilingInterfaceImpl.so.20.0git
64.005 [2649/14/4743] Linking CXX shared library lib/libMLIRMemRefTransforms.so.20.0git
64.011 [2649/13/4744] Linking CXX shared library lib/libMLIRTensorTransforms.so.20.0git
64.056 [2649/12/4745] Linking CXX shared library lib/libMLIRGPUToVulkanTransforms.so.20.0git
64.084 [2649/11/4746] Linking CXX shared library lib/libMLIRVectorToSCF.so.20.0git
64.121 [2649/10/4747] Linking CXX shared library lib/libMLIRSPIRVTarget.so.20.0git
64.124 [2649/9/4748] Linking CXX shared library lib/libMLIRSPIRVConversion.so.20.0git
64.124 [2649/8/4749] Linking CXX shared library lib/libMLIRVectorToGPU.so.20.0git
64.147 [2649/7/4750] Linking CXX shared library lib/libMLIRToLLVMIRTranslationRegistration.so.20.0git
64.149 [2649/6/4751] Linking CXX shared library lib/libMLIRVectorToLLVM.so.20.0git
64.292 [2649/5/4752] Linking CXX shared library lib/libMLIRAffineTransformOps.so.20.0git
65.017 [2649/4/4753] Building CXX object tools/mlir/examples/transform-opt/CMakeFiles/mlir-transform-opt.dir/mlir-transform-opt.cpp.o
103.530 [2649/3/4754] Building CXX object tools/mlir/examples/toy/Ch5/CMakeFiles/toyc-ch5.dir/toyc.cpp.o
109.190 [2649/2/4755] Building CXX object tools/mlir/tools/mlir-opt/CMakeFiles/MLIRMlirOptMain.dir/mlir-opt.cpp.o
111.031 [2649/1/4756] Building CXX object tools/mlir/examples/toy/Ch6/CMakeFiles/toyc-ch6.dir/toyc.cpp.o
ninja: build stopped: subcommand failed.

```

</details>

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