CMakeLists.txt
LICENSE
MANIFEST.in
Makefile
README.md
pyproject.toml
setup.py
bin/CMakeLists.txt
bin/RegisterTritonDialects.h
bin/triton-llvm-opt.cpp
bin/triton-lsp.cpp
bin/triton-opt.cpp
bin/triton-reduce.cpp
bin/triton-tensor-layout.cpp
cmake/AddTritonUnitTest.cmake
cmake/FindLLVM.cmake
cmake/json-version.txt
cmake/llvm-hash.txt
cmake/nvidia-toolchain-version.json
docs/Makefile
docs/conf.py
docs/index.rst
docs/requirements.txt
docs/_templates/versions.html
docs/backend/ldmatrixOperand0.svg
docs/backend/ldmatrixOperand1.svg
docs/getting-started/installation.rst
docs/getting-started/tutorials/grouped_vs_row_major_ordering.png
docs/getting-started/tutorials/parallel_reduction.png
docs/getting-started/tutorials/random_bits.png
docs/meetups/dev-meetup-2023.md
docs/meetups/dev_conference_2024.md
docs/meetups/01-06-2026/notes.md
docs/meetups/01-24-2024/notes.md
docs/meetups/02-20-2024/Proton.pdf
docs/meetups/02-20-2024/notes.md
docs/meetups/03-04-2026/notes.md
docs/meetups/03-12-2025/notes.md
docs/meetups/04-02-2024/notes.md
docs/meetups/05-01-2025/notes.md
docs/meetups/05-07-2024/notes.md
docs/meetups/07-09-2025/notes.md
docs/meetups/07-18-2023/notes.md
docs/meetups/08-06-2024/notes.md
docs/meetups/08-22-2023/amd-update.pdf
docs/meetups/08-22-2023/intel-xpu-update.pptx
docs/meetups/08-22-2023/notes.md
docs/meetups/09-03-2025/notes.md
docs/meetups/10-25-2023/intel-xpu-update.pdf
docs/meetups/10-25-2023/notes.md
docs/meetups/10-25-2023/triton-shared.pptx
docs/meetups/11-05-2025/notes.md
docs/meetups/12-13-2023/notes.md
docs/meetups/for_moderators/README.md
docs/programming-guide/chapter-1/cuda-parallel-matmul.png
docs/programming-guide/chapter-1/introduction.rst
docs/programming-guide/chapter-1/triton-parallel-matmul.png
docs/programming-guide/chapter-2/halide-iteration.png
docs/programming-guide/chapter-2/polyhedral-iteration.png
docs/programming-guide/chapter-2/related-work.rst
docs/programming-guide/chapter-3/debugging.rst
docs/python-api/triton-semantics.rst
docs/python-api/triton.language.extra.cuda.rst
docs/python-api/triton.language.rst
docs/python-api/triton.rst
docs/python-api/triton.testing.rst
include/CMakeLists.txt
include/triton/CMakeLists.txt
include/triton/Analysis/Alias.h
include/triton/Analysis/Allocation.h
include/triton/Analysis/AxisInfo.h
include/triton/Analysis/BufferRegion.h
include/triton/Analysis/Membar.h
include/triton/Analysis/Utility.h
include/triton/Conversion/CMakeLists.txt
include/triton/Conversion/MLIRTypes.h
include/triton/Conversion/TritonGPUToLLVM/AllocateSharedMemoryUtility.h
include/triton/Conversion/TritonGPUToLLVM/AsmFormat.h
include/triton/Conversion/TritonGPUToLLVM/CMakeLists.txt
include/triton/Conversion/TritonGPUToLLVM/ElementwiseOpToLLVMBase.h
include/triton/Conversion/TritonGPUToLLVM/FMADotUtility.h
include/triton/Conversion/TritonGPUToLLVM/Passes.h
include/triton/Conversion/TritonGPUToLLVM/Passes.td
include/triton/Conversion/TritonGPUToLLVM/PatternTritonGPUOpToLLVM.h
include/triton/Conversion/TritonGPUToLLVM/TargetInfoBase.h
include/triton/Conversion/TritonGPUToLLVM/TypeConverter.h
include/triton/Conversion/TritonGPUToLLVM/Utility.h
include/triton/Conversion/TritonGPUToLLVM/WarpSpecializeUtility.h
include/triton/Conversion/TritonToTritonGPU/CMakeLists.txt
include/triton/Conversion/TritonToTritonGPU/Passes.h
include/triton/Conversion/TritonToTritonGPU/Passes.td
include/triton/Dialect/CMakeLists.txt
include/triton/Dialect/Gluon/CMakeCache.txt
include/triton/Dialect/Gluon/CMakeLists.txt
include/triton/Dialect/Gluon/IR/CMakeLists.txt
include/triton/Dialect/Gluon/IR/Dialect.h
include/triton/Dialect/Gluon/IR/GluonAttrDefs.td
include/triton/Dialect/Gluon/IR/GluonDialect.td
include/triton/Dialect/Gluon/IR/GluonOps.td
include/triton/Dialect/Gluon/Transforms/CMakeLists.txt
include/triton/Dialect/Gluon/Transforms/InferLayoutUtils.h
include/triton/Dialect/Gluon/Transforms/Passes.h
include/triton/Dialect/Gluon/Transforms/Passes.td
include/triton/Dialect/Triton/CMakeLists.txt
include/triton/Dialect/Triton/IR/CMakeLists.txt
include/triton/Dialect/Triton/IR/Dialect.h
include/triton/Dialect/Triton/IR/DiscardableAttributes.h
include/triton/Dialect/Triton/IR/Interfaces.h
include/triton/Dialect/Triton/IR/OpInterfaces.h
include/triton/Dialect/Triton/IR/Traits.h
include/triton/Dialect/Triton/IR/TritonAttrDefs.td
include/triton/Dialect/Triton/IR/TritonDialect.td
include/triton/Dialect/Triton/IR/TritonInterfaces.td
include/triton/Dialect/Triton/IR/TritonOpInterfaces.td
include/triton/Dialect/Triton/IR/TritonOps.td
include/triton/Dialect/Triton/IR/TritonTypeInterfaces.td
include/triton/Dialect/Triton/IR/TritonTypes.td
include/triton/Dialect/Triton/IR/Types.h
include/triton/Dialect/Triton/IR/Utility.h
include/triton/Dialect/Triton/Transforms/ArithTypeConversion.h
include/triton/Dialect/Triton/Transforms/CMakeLists.txt
include/triton/Dialect/Triton/Transforms/FunctionTypeConversion.h
include/triton/Dialect/Triton/Transforms/LoopPeeling.h
include/triton/Dialect/Triton/Transforms/Passes.h
include/triton/Dialect/Triton/Transforms/Passes.td
include/triton/Dialect/TritonGPU/CMakeLists.txt
include/triton/Dialect/TritonGPU/IR/Attributes.h
include/triton/Dialect/TritonGPU/IR/CGAEncodingAttr.h
include/triton/Dialect/TritonGPU/IR/CGAEncodingAttr.td
include/triton/Dialect/TritonGPU/IR/CMakeLists.txt
include/triton/Dialect/TritonGPU/IR/Dialect.h
include/triton/Dialect/TritonGPU/IR/LinearLayoutConversions.h
include/triton/Dialect/TritonGPU/IR/Traits.h
include/triton/Dialect/TritonGPU/IR/TritonGPUAttrBase.td
include/triton/Dialect/TritonGPU/IR/TritonGPUAttrDefs.td
include/triton/Dialect/TritonGPU/IR/TritonGPUAttrImpls.td
include/triton/Dialect/TritonGPU/IR/TritonGPUAttrInterfaces.td
include/triton/Dialect/TritonGPU/IR/TritonGPUDialect.td
include/triton/Dialect/TritonGPU/IR/TritonGPUEnums.td
include/triton/Dialect/TritonGPU/IR/TritonGPUInterfaces.h
include/triton/Dialect/TritonGPU/IR/TritonGPUOpInterfaces.td
include/triton/Dialect/TritonGPU/IR/TritonGPUOps.td
include/triton/Dialect/TritonGPU/IR/TritonGPUTypeInterfaces.td
include/triton/Dialect/TritonGPU/IR/TritonGPUTypes.td
include/triton/Dialect/TritonGPU/IR/Types.h
include/triton/Dialect/TritonGPU/Transforms/CMakeLists.txt
include/triton/Dialect/TritonGPU/Transforms/CoalesceUtils.h
include/triton/Dialect/TritonGPU/Transforms/DecomposeScaledBlocked.h
include/triton/Dialect/TritonGPU/Transforms/DescriptorMemoryLayouts.h
include/triton/Dialect/TritonGPU/Transforms/LayoutPropagationUtility.h
include/triton/Dialect/TritonGPU/Transforms/MMAv5PipelineUtility.h
include/triton/Dialect/TritonGPU/Transforms/Partition.h
include/triton/Dialect/TritonGPU/Transforms/PartitionBuilder.h
include/triton/Dialect/TritonGPU/Transforms/PartitionSchedulingUtility.h
include/triton/Dialect/TritonGPU/Transforms/Passes.h
include/triton/Dialect/TritonGPU/Transforms/Passes.td
include/triton/Dialect/TritonGPU/Transforms/PipelineExpander.h
include/triton/Dialect/TritonGPU/Transforms/PipeliningUtility.h
include/triton/Dialect/TritonGPU/Transforms/Schedule.h
include/triton/Dialect/TritonGPU/Transforms/TritonGPUConversion.h
include/triton/Dialect/TritonGPU/Transforms/Utility.h
include/triton/Dialect/TritonGPU/Transforms/WarpSpecialization.h
include/triton/Dialect/TritonInstrument/CMakeLists.txt
include/triton/Dialect/TritonInstrument/IR/CMakeLists.txt
include/triton/Dialect/TritonInstrument/IR/Dialect.h
include/triton/Dialect/TritonInstrument/IR/FunctionBuilder.h
include/triton/Dialect/TritonInstrument/IR/TritonInstrument.md
include/triton/Dialect/TritonInstrument/IR/TritonInstrumentAttrDefs.td
include/triton/Dialect/TritonInstrument/IR/TritonInstrumentDialect.td
include/triton/Dialect/TritonInstrument/IR/TritonInstrumentOps.td
include/triton/Dialect/TritonInstrument/IR/Utility.h
include/triton/Dialect/TritonInstrument/Transforms/CMakeLists.txt
include/triton/Dialect/TritonInstrument/Transforms/ConSanTargetHooks.h
include/triton/Dialect/TritonInstrument/Transforms/Passes.h
include/triton/Dialect/TritonInstrument/Transforms/Passes.td
include/triton/Dialect/TritonNvidiaGPU/CMakeLists.txt
include/triton/Dialect/TritonNvidiaGPU/IR/CMakeLists.txt
include/triton/Dialect/TritonNvidiaGPU/IR/Dialect.h
include/triton/Dialect/TritonNvidiaGPU/IR/TensorMemoryUtils.h
include/triton/Dialect/TritonNvidiaGPU/IR/TritonNvidiaGPUAttrDefs.td
include/triton/Dialect/TritonNvidiaGPU/IR/TritonNvidiaGPUDialect.td
include/triton/Dialect/TritonNvidiaGPU/IR/TritonNvidiaGPUOpInterfaces.td
include/triton/Dialect/TritonNvidiaGPU/IR/TritonNvidiaGPUOps.td
include/triton/Dialect/TritonNvidiaGPU/IR/TritonNvidiaGPUTypes.td
include/triton/Dialect/TritonNvidiaGPU/Transforms/CMakeLists.txt
include/triton/Dialect/TritonNvidiaGPU/Transforms/ClusterBarrierInsertion.h
include/triton/Dialect/TritonNvidiaGPU/Transforms/Passes.h
include/triton/Dialect/TritonNvidiaGPU/Transforms/Passes.td
include/triton/Dialect/TritonNvidiaGPU/Transforms/TMAUtilities.h
include/triton/Target/CMakeLists.txt
include/triton/Target/LLVMIR/CMakeLists.txt
include/triton/Target/LLVMIR/Passes.h
include/triton/Target/LLVMIR/Passes.td
include/triton/Tools/GenericSwizzling.h
include/triton/Tools/LayoutUtils.h
include/triton/Tools/LinearLayout.h
include/triton/Tools/PluginUtils.h
include/triton/Tools/StrUtil.h
include/triton/Tools/Sys/Dump.hpp
include/triton/Tools/Sys/GetEnv.hpp
lib/CMakeLists.txt
lib/Analysis/Alias.cpp
lib/Analysis/Allocation.cpp
lib/Analysis/AxisInfo.cpp
lib/Analysis/BufferRegion.cpp
lib/Analysis/CMakeLists.txt
lib/Analysis/Membar.cpp
lib/Analysis/Utility.cpp
lib/Conversion/CMakeLists.txt
lib/Conversion/TritonGPUToLLVM/AllocateSharedMemory.cpp
lib/Conversion/TritonGPUToLLVM/AllocateSharedMemoryUtility.cpp
lib/Conversion/TritonGPUToLLVM/AllocateWarpGroups.cpp
lib/Conversion/TritonGPUToLLVM/AssertOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/CMakeLists.txt
lib/Conversion/TritonGPUToLLVM/CanonicalizeLLVMIR.cpp
lib/Conversion/TritonGPUToLLVM/ControlFlowOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/ConvertLayoutOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/ElementwiseOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/FuncOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/GatherOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/GlobalScratchMemoryAllocation.cpp
lib/Conversion/TritonGPUToLLVM/HistogramOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/MakeRangeOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/MemoryOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/PrintOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/ReduceOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/ReduceScanCommon.h
lib/Conversion/TritonGPUToLLVM/SPMDOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/ScanOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/TypeConverter.cpp
lib/Conversion/TritonGPUToLLVM/Utility.cpp
lib/Conversion/TritonGPUToLLVM/ViewOpToLLVM.cpp
lib/Conversion/TritonGPUToLLVM/WarpSpecializeUtility.cpp
lib/Conversion/TritonGPUToLLVM/DotOpToLLVM/FMA.cpp
lib/Conversion/TritonGPUToLLVM/DotOpToLLVM/FMADotUtility.cpp
lib/Conversion/TritonInstrumentToLLVM/CMakeLists.txt
lib/Conversion/TritonInstrumentToLLVM/GSanToLLVM.cpp
lib/Conversion/TritonInstrumentToLLVM/InstrumentationToLLVM.cpp
lib/Conversion/TritonToTritonGPU/CMakeLists.txt
lib/Conversion/TritonToTritonGPU/RelayoutTritonGPU.cpp
lib/Conversion/TritonToTritonGPU/TritonGPUConversion.cpp
lib/Conversion/TritonToTritonGPU/TritonToTritonGPUPass.cpp
lib/Dialect/CMakeLists.txt
lib/Dialect/Gluon/CMakeLists.txt
lib/Dialect/Gluon/IR/CMakeLists.txt
lib/Dialect/Gluon/IR/Dialect.cpp
lib/Dialect/Gluon/Transforms/CMakeLists.txt
lib/Dialect/Gluon/Transforms/Canonicalize.cpp
lib/Dialect/Gluon/Transforms/InferCoalescedEncodings.cpp
lib/Dialect/Gluon/Transforms/InferLayoutUtils.cpp
lib/Dialect/Gluon/Transforms/Inline.cpp
lib/Dialect/Gluon/Transforms/ResolveAutoEncodings.cpp
lib/Dialect/Gluon/Transforms/SimplifyControlFlow.cpp
lib/Dialect/Triton/CMakeLists.txt
lib/Dialect/Triton/IR/CMakeLists.txt
lib/Dialect/Triton/IR/Canonicalize.td
lib/Dialect/Triton/IR/Dialect.cpp
lib/Dialect/Triton/IR/DiscardableAttributes.cpp
lib/Dialect/Triton/IR/OpInterfaces.cpp
lib/Dialect/Triton/IR/Ops.cpp
lib/Dialect/Triton/IR/Traits.cpp
lib/Dialect/Triton/IR/Types.cpp
lib/Dialect/Triton/IR/Utility.cpp
lib/Dialect/Triton/Transforms/ArithTypeConversion.cpp
lib/Dialect/Triton/Transforms/CMakeLists.txt
lib/Dialect/Triton/Transforms/Combine.cpp
lib/Dialect/Triton/Transforms/Combine.td
lib/Dialect/Triton/Transforms/FunctionTypeConversion.cpp
lib/Dialect/Triton/Transforms/LoopAwareCSE.cpp
lib/Dialect/Triton/Transforms/LoopInvariantCodeMotion.cpp
lib/Dialect/Triton/Transforms/LoopPeeling.cpp
lib/Dialect/Triton/Transforms/LoopUnroll.cpp
lib/Dialect/Triton/Transforms/ReorderBroadcast.cpp
lib/Dialect/Triton/Transforms/RewriteTensorDescriptorToPointer.cpp
lib/Dialect/TritonGPU/CMakeLists.txt
lib/Dialect/TritonGPU/IR/CMakeLists.txt
lib/Dialect/TritonGPU/IR/Dialect.cpp
lib/Dialect/TritonGPU/IR/LinearLayoutConversions.cpp
lib/Dialect/TritonGPU/IR/Ops.cpp
lib/Dialect/TritonGPU/IR/Traits.cpp
lib/Dialect/TritonGPU/IR/Types.cpp
lib/Dialect/TritonGPU/Transforms/AccelerateMatmul.cpp
lib/Dialect/TritonGPU/Transforms/CMakeLists.txt
lib/Dialect/TritonGPU/Transforms/Coalesce.cpp
lib/Dialect/TritonGPU/Transforms/CoalesceAsyncCopy.cpp
lib/Dialect/TritonGPU/Transforms/CoalesceUtils.cpp
lib/Dialect/TritonGPU/Transforms/CombineTensorSelectAndIf.cpp
lib/Dialect/TritonGPU/Transforms/DecomposeScaledBlocked.cpp
lib/Dialect/TritonGPU/Transforms/DescriptorMemoryLayouts.cpp
lib/Dialect/TritonGPU/Transforms/F32DotTC.cpp
lib/Dialect/TritonGPU/Transforms/FuseNestedLoops.cpp
lib/Dialect/TritonGPU/Transforms/HoistTMEMAlloc.cpp
lib/Dialect/TritonGPU/Transforms/LayoutPropagationUtility.cpp
lib/Dialect/TritonGPU/Transforms/OptimizeAccumulatorInit.cpp
lib/Dialect/TritonGPU/Transforms/OptimizeDotOperands.cpp
lib/Dialect/TritonGPU/Transforms/OptimizeThreadLocality.cpp
lib/Dialect/TritonGPU/Transforms/Prefetch.cpp
lib/Dialect/TritonGPU/Transforms/ReduceDataDuplication.cpp
lib/Dialect/TritonGPU/Transforms/RemoveLayoutConversions.cpp
lib/Dialect/TritonGPU/Transforms/ReorderInstructions.cpp
lib/Dialect/TritonGPU/Transforms/Utility.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/AssignLatencies.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/LowerLoops.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/MMAv5PipelineUtility.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/PipelineExpander.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/PipeliningUtility.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/Schedule.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/ScheduleLoops.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/SoftwarePipeliner.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/TMAStoresPipeline.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/TestPipelineLowerLoop.cpp
lib/Dialect/TritonGPU/Transforms/Pipeliner/WGMMAPipeline.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/AutomaticWarpSpecialization.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/OptimizePartitionWarps.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/Partition.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/PartitionBuilder.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/PartitionLoops.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/PartitionScheduling.cpp
lib/Dialect/TritonGPU/Transforms/WarpSpecialization/PartitionSchedulingUtility.cpp
lib/Dialect/TritonInstrument/CMakeLists.txt
lib/Dialect/TritonInstrument/IR/CMakeLists.txt
lib/Dialect/TritonInstrument/IR/Dialect.cpp
lib/Dialect/TritonInstrument/IR/FunctionBuilder.cpp
lib/Dialect/TritonInstrument/IR/Ops.cpp
lib/Dialect/TritonInstrument/IR/Utility.cpp
lib/Dialect/TritonInstrument/Transforms/CMakeLists.txt
lib/Dialect/TritonInstrument/Transforms/ConcurrencySanitizer.cpp
lib/Dialect/TritonInstrument/Transforms/FpSanitizer.cpp
lib/Dialect/TritonInstrument/Transforms/GlobalSanitizer.cpp
lib/Dialect/TritonNvidiaGPU/CMakeLists.txt
lib/Dialect/TritonNvidiaGPU/IR/CMakeLists.txt
lib/Dialect/TritonNvidiaGPU/IR/Dialect.cpp
lib/Dialect/TritonNvidiaGPU/IR/Ops.cpp
lib/Dialect/TritonNvidiaGPU/IR/TensorMemoryUtils.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/CMakeLists.txt
lib/Dialect/TritonNvidiaGPU/Transforms/CheckMatmulTwoCTAs.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/ClusterBarrierInsertion.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/ConSanNVIDIA.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/FenceInsertion.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/InterleaveTMem.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/MMALowering.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/OptimizeDescriptorEncoding.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/OptimizeTMemLayouts.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/PlanCTA.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/PromoteLHSToTMem.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/ProxyFenceInsertion.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/RemoveTMEMTokens.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/TMALowering.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/TMAUtilities.cpp
lib/Dialect/TritonNvidiaGPU/Transforms/TensorMemoryAllocation.cpp
lib/Target/CMakeLists.txt
lib/Target/LLVMIR/CMakeLists.txt
lib/Target/LLVMIR/LLVMDILocalVariable.cpp
lib/Target/LLVMIR/LLVMDIScope.cpp
lib/Target/LLVMIR/LLVMDIUtils.cpp
lib/Target/LLVMIR/LLVMDIUtils.h
lib/Target/LLVMIR/LLVMIRBreakPhiStruct.cpp
lib/Target/LLVMIR/LLVMPasses.h
lib/Tools/CMakeLists.txt
lib/Tools/GenericSwizzling.cpp
lib/Tools/LayoutUtils.cpp
lib/Tools/LinearLayout.cpp
lib/Tools/PluginUtils.cpp
python/build_helpers.py
python/requirements.txt
python/test-requirements.txt
python/src/gluon_ir.cc
python/src/interpreter.cc
python/src/ir.cc
python/src/ir.h
python/src/linear_layout.cc
python/src/llvm.cc
python/src/main.cc
python/src/passes.cc
python/src/passes.h
python/src/specialize.cc
python/test/conftest.py
python/test/backend/extension_backend.c
python/test/backend/test_device_backend.py
python/test/backend/test_mir_stage.py
python/test/gluon/test_consan.py
python/test/gluon/test_core.py
python/test/gluon/test_fpsan.py
python/test/gluon/test_frontend.py
python/test/gluon/test_layout_format_view.py
python/test/gluon/test_lowerings.py
python/test/gsan/test_allocator.py
python/test/gsan/test_gsan.py
python/test/gsan/test_gsan_failures.py
python/test/gsan/test_utils.py
python/test/kernel_comparison/kernels.yml
python/test/microbenchmark/launch_overhead.py
python/test/regression/test_cast_matmul.py
python/test/regression/test_functional_regressions.py
python/test/unit/test_debug.py
python/test/unit/test_debug_dump.py
python/test/unit/test_debuginfo.py
python/test/unit/test_filecheck.py
python/test/unit/test_knobs.py
python/test/unit/test_link.py
python/test/unit/test_perf_warning.py
python/test/unit/test_stages_inspection.py
python/test/unit/cuda/test_libdevice_cuda.py
python/test/unit/cuda/test_mixed_io.py
python/test/unit/cuda/test_tensor_descriptor_cuda.py
python/test/unit/cuda/test_tma_descriptor.py
python/test/unit/cuda/test_tma_store_gemm.py
python/test/unit/instrumentation/test_gpuhello.py
python/test/unit/language/print_helper.py
python/test/unit/language/test_annotations.py
python/test/unit/language/test_block_pointer.py
python/test/unit/language/test_compile_errors.py
python/test/unit/language/test_compile_only.py
python/test/unit/language/test_conversions.py
python/test/unit/language/test_core.py
python/test/unit/language/test_decorator.py
python/test/unit/language/test_frontend.py
python/test/unit/language/test_libdevice.py
python/test/unit/language/test_line_info.py
python/test/unit/language/test_matmul.py
python/test/unit/language/test_module.py
python/test/unit/language/test_mxfp.py
python/test/unit/language/test_pipeliner.py
python/test/unit/language/test_random.py
python/test/unit/language/test_reproducer.py
python/test/unit/language/test_standard.py
python/test/unit/language/test_subprocess.py
python/test/unit/language/test_tensor_descriptor.py
python/test/unit/language/test_tuple.py
python/test/unit/language/test_warp_specialization.py
python/test/unit/plugins/custom_ops.py
python/test/unit/plugins/custom_stages.py
python/test/unit/plugins/override_helper.py
python/test/unit/plugins/test_dialect_plugin.py
python/test/unit/plugins/test_plugin.py
python/test/unit/runtime/no_torch_dispatch_example.py
python/test/unit/runtime/test_autotuner.py
python/test/unit/runtime/test_bindings.py
python/test/unit/runtime/test_blaslt.py
python/test/unit/runtime/test_build.py
python/test/unit/runtime/test_cache.py
python/test/unit/runtime/test_compilation_listener.py
python/test/unit/runtime/test_driver.py
python/test/unit/runtime/test_launch.py
python/test/unit/runtime/test_no_torch_dispatch.py
python/test/unit/runtime/test_specialize.py
python/test/unit/runtime/test_subproc.py
python/test/unit/tools/test_aot.py
python/test/unit/tools/test_disasm.py
python/test/unit/tools/test_irsource.py
python/test/unit/tools/test_linear_layout.py
python/test/unit/tools/test_slice_kernel.py
python/test/unit/tools/test_stable_toposort.py
python/test/unit/tools/test_triton_to_gluon.py
python/triton/__init__.py
python/triton/_filecheck.py
python/triton/_internal_testing.py
python/triton/_utils.py
python/triton/errors.py
python/triton/knobs.py
python/triton/testing.py
python/triton.egg-info/PKG-INFO
python/triton.egg-info/SOURCES.txt
python/triton.egg-info/dependency_links.txt
python/triton.egg-info/entry_points.txt
python/triton.egg-info/not-zip-safe
python/triton.egg-info/requires.txt
python/triton.egg-info/top_level.txt
python/triton/_C/libtriton/linear_layout.pyi
python/triton/backends/__init__.py
python/triton/backends/compiler.py
python/triton/backends/driver.py
python/triton/compiler/__init__.py
python/triton/compiler/code_generator.py
python/triton/compiler/compiler.py
python/triton/compiler/errors.py
python/triton/compiler/make_launcher.py
python/triton/experimental/__init__.py
python/triton/experimental/gluon/__init__.py
python/triton/experimental/gluon/_compiler.py
python/triton/experimental/gluon/_runtime.py
python/triton/experimental/gluon/amd/__init__.py
python/triton/experimental/gluon/amd/gfx1250.py
python/triton/experimental/gluon/language/__init__.py
python/triton/experimental/gluon/language/_core.py
python/triton/experimental/gluon/language/_layouts.py
python/triton/experimental/gluon/language/_math.py
python/triton/experimental/gluon/language/_semantic.py
python/triton/experimental/gluon/language/_standard.py
python/triton/experimental/gluon/language/amd/__init__.py
python/triton/experimental/gluon/language/amd/_layouts.py
python/triton/experimental/gluon/language/amd/_ops.py
python/triton/experimental/gluon/language/amd/warp_pipeline.py
python/triton/experimental/gluon/language/amd/cdna3/__init__.py
python/triton/experimental/gluon/language/amd/cdna4/__init__.py
python/triton/experimental/gluon/language/amd/cdna4/async_copy.py
python/triton/experimental/gluon/language/amd/gfx1250/__init__.py
python/triton/experimental/gluon/language/amd/gfx1250/_layouts.py
python/triton/experimental/gluon/language/amd/gfx1250/async_copy.py
python/triton/experimental/gluon/language/amd/gfx1250/cluster.py
python/triton/experimental/gluon/language/amd/gfx1250/mbarrier.py
python/triton/experimental/gluon/language/amd/gfx1250/tdm.py
python/triton/experimental/gluon/language/amd/rdna3/__init__.py
python/triton/experimental/gluon/language/amd/rdna4/__init__.py
python/triton/experimental/gluon/language/extra/__init__.py
python/triton/experimental/gluon/language/nvidia/__init__.py
python/triton/experimental/gluon/language/nvidia/ampere/__init__.py
python/triton/experimental/gluon/language/nvidia/ampere/async_copy.py
python/triton/experimental/gluon/language/nvidia/ampere/mbarrier.py
python/triton/experimental/gluon/language/nvidia/blackwell/__init__.py
python/triton/experimental/gluon/language/nvidia/blackwell/clc.py
python/triton/experimental/gluon/language/nvidia/blackwell/float2.py
python/triton/experimental/gluon/language/nvidia/blackwell/tma.py
python/triton/experimental/gluon/language/nvidia/hopper/__init__.py
python/triton/experimental/gluon/language/nvidia/hopper/cluster.py
python/triton/experimental/gluon/language/nvidia/hopper/mbarrier.py
python/triton/experimental/gluon/language/nvidia/hopper/tma.py
python/triton/experimental/gluon/nvidia/__init__.py
python/triton/experimental/gluon/nvidia/blackwell.py
python/triton/experimental/gluon/nvidia/hopper.py
python/triton/experimental/gsan/README.md
python/triton/experimental/gsan/__init__.py
python/triton/experimental/gsan/_allocator.py
python/triton/experimental/gsan/_stream_sync.py
python/triton/experimental/gsan/_testing.py
python/triton/experimental/gsan/_testing_utils.py
python/triton/experimental/gsan/_utils.py
python/triton/experimental/gsan/src/GSan.h
python/triton/experimental/gsan/src/GSanAllocator.cc
python/triton/experimental/gsan/src/GSanLibrary.cu
python/triton/experimental/gsan/src/Hash.cuh
python/triton/experimental/gsan/src/gsan_testing.cc
python/triton/language/__init__.py
python/triton/language/core.py
python/triton/language/math.py
python/triton/language/random.py
python/triton/language/semantic.py
python/triton/language/standard.py
python/triton/language/target_info.py
python/triton/language/extra/__init__.py
python/triton/language/extra/libdevice.py
python/triton/runtime/__init__.py
python/triton/runtime/_allocation.py
python/triton/runtime/_async_compile.py
python/triton/runtime/autotuner.py
python/triton/runtime/build.py
python/triton/runtime/cache.py
python/triton/runtime/driver.py
python/triton/runtime/errors.py
python/triton/runtime/interpreter.py
python/triton/runtime/jit.py
python/triton/tools/__init__.py
python/triton/tools/build_extern.py
python/triton/tools/compile.py
python/triton/tools/disasm.py
python/triton/tools/gsan.py
python/triton/tools/link.py
python/triton/tools/mxfp.py
python/triton/tools/ragged_tma.py
python/triton/tools/tensor_descriptor.py
python/triton/tools/triton_to_gluon_translator/__init__.py
python/triton/tools/triton_to_gluon_translator/inline_helpers.py
python/triton/tools/triton_to_gluon_translator/ordered_set.py
python/triton/tools/triton_to_gluon_translator/scoped_dict.py
python/triton/tools/triton_to_gluon_translator/slice_kernel.py
python/triton/tools/triton_to_gluon_translator/stable_toposort.py
python/triton/tools/triton_to_gluon_translator/translator.py
python/triton/tools/triton_to_gluon_translator/translator_helpers.py
test/CMakeLists.txt
test/lit.cfg.py
test/lit.site.cfg.py.in
test/Analysis/test-alias.mlir
test/Analysis/test-alignment.mlir
test/Analysis/test-allocation-partitioned.mlir
test/Analysis/test-allocation.mlir
test/Analysis/test-buffer-region.mlir
test/Analysis/test-membar-ttng.mlir
test/Analysis/test-membar.mlir
test/Analysis/amd/test-alignment.mlir
test/Conversion/allocate_shared_memory.mlir
test/Conversion/allocate_warp_groups.mlir
test/Conversion/atomic_ldst.mlir
test/Conversion/cat_broadcast_regs_to_llvm.mlir
test/Conversion/clc_to_llvm.mlir
test/Conversion/cvt_to_llvm.mlir
test/Conversion/dedup-by-constancy.mlir
test/Conversion/divide-by-0.mlir
test/Conversion/lower_tensor_memory_to_llvm.mlir
test/Conversion/nvgpu_invalid.mlir
test/Conversion/nvgpu_to_llvm.mlir
test/Conversion/reduce_to_llvm.mlir
test/Conversion/relayout_tritongpu.mlir
test/Conversion/scan_to_llvm.mlir
test/Conversion/tma_to_llvm.mlir
test/Conversion/triton_to_tritongpu.mlir
test/Conversion/tritongpu_to_llvm.mlir
test/Conversion/tritongpu_to_llvm_blackwell.mlir
test/Conversion/tritongpu_to_llvm_block_dot_shortcut.mlir
test/Conversion/tritongpu_to_llvm_debug.mlir
test/Conversion/tritongpu_to_llvm_gsan.mlir
test/Conversion/tritongpu_to_llvm_hopper.mlir
test/Conversion/tritongpu_to_llvm_hopper_ptx80.mlir
test/Conversion/tritongpu_to_llvm_sm120.mlir
test/Conversion/tritongpu_to_llvm_volta.mlir
test/Conversion/tritongpu_to_ptx.mlir
test/Conversion/tritongpu_to_ptx_mmav3.mlir
test/Conversion/tritoninstrument_to_llvm.mlir
test/Conversion/tritonnvidiagpu_to_llvm.mlir
test/Conversion/warp_specialize_to_llvm.mlir
test/Conversion/amd/allocate_shared_memory.mlir
test/Conversion/amd/amdgpu_membar.mlir
test/Conversion/amd/async-ops-alias-scopes.mlir
test/Conversion/amd/async_ops_to_llvm.mlir
test/Conversion/amd/async_ops_to_llvm_gfx1250.mlir
test/Conversion/amd/async_ops_to_llvm_invalid.mlir
test/Conversion/amd/atomic_cas.mlir
test/Conversion/amd/buffer_atomic_cas.mlir
test/Conversion/amd/buffer_atomic_rmw_barrier.mlir
test/Conversion/amd/buffer_load_store.mlir
test/Conversion/amd/buffer_load_to_local_to_llvm.mlir
test/Conversion/amd/buffer_ops_gfx1250.mlir
test/Conversion/amd/builtin_func_to_llvm.mlir
test/Conversion/amd/cluster_barrier_to_llvm.mlir
test/Conversion/amd/cluster_load.mlir
test/Conversion/amd/compute-base-ptr.mlir
test/Conversion/amd/convert_layout.mlir
test/Conversion/amd/dedup-by-constancy.mlir
test/Conversion/amd/ds_transpose.mlir
test/Conversion/amd/ds_transpose_gfx1250.mlir
test/Conversion/amd/fp_to_fp.mlir
test/Conversion/amd/in_thread_transpose.mlir
test/Conversion/amd/invalid_async_ops_to_lllvm.mlir
test/Conversion/amd/invalid_concat_op.mlir
test/Conversion/amd/invalid_extractslice_to_llvm.mlir
test/Conversion/amd/load_store.mlir
test/Conversion/amd/math-denorm-handling.mlir
test/Conversion/amd/mbarrier_ops_to_llvm_gfx1250.mlir
test/Conversion/amd/mfma-shortcut.mlir
test/Conversion/amd/minmax.mlir
test/Conversion/amd/reduce_tree_vectorize.mlir
test/Conversion/amd/tritongpu_tdm_stride_order.mlir
test/Conversion/amd/tritongpu_tdm_to_llvm.mlir
test/Conversion/amd/tritongpu_to_llvm.mlir
test/Conversion/amd/tritongpu_to_llvm_gfx1250.mlir
test/Conversion/amd/tritongpu_to_llvm_rdna.mlir
test/Conversion/amd/tritongpu_wmma_dot_scaled_to_llvm.mlir
test/Conversion/amd/tritongpu_wmma_dot_to_llvm.mlir
test/Conversion/amd/warp_id_to_llvm.mlir
test/Conversion/amd/wmma-v1-shortcut.mlir
test/Conversion/amd/wmma-v2-shortcut.mlir
test/Gluon/auto_encoding.mlir
test/Gluon/infer_coalesced_encoding.mlir
test/Gluon/inlining.mlir
test/Gluon/invalid_auto_encoding.mlir
test/Gluon/invalid_infer_coalesced_encoding.mlir
test/Hopper/CMakeLists.txt
test/Hopper/WarpSpecialization/ws_code_partition.mlir
test/Hopper/WarpSpecialization/ws_data_partition.mlir
test/Hopper/WarpSpecialization/ws_task_id_propagation.mlir
test/Hopper/WarpSpecialization/ws_task_partition.mlir
test/LLVMIR/break-phi-struct.ll
test/LLVMIR/convert-to-llvmir-with-dbg-info.mlir
test/LLVMIR/insert-dbg-intrinsic.mlir
test/NVWS/aref-tmem-insertion.mlir
test/NVWS/assign_stage_phase.mlir
test/NVWS/hoist_tmem_store.mlir
test/NVWS/insert_aref.mlir
test/NVWS/invalid.mlir
test/NVWS/lower_aref.mlir
test/NVWS/lower_warp_group.mlir
test/NVWS/ops.mlir
test/Plugins/test-dialect-plugin.mlir
test/Plugins/test-plugin.mlir
test/Proton/allocate_global_scratch_buffer.mlir
test/Proton/allocate_shared_memory.mlir
test/Proton/ops.mlir
test/Proton/proton_to_protongpu.mlir
test/Proton/protongpu_transforms.mlir
test/Proton/scope_id.mlir
test/Proton/amd/add_sched_barriers.mlir
test/Proton/amd/protongpu_to_llvm.mlir
test/Proton/nvidia/protongpu_to_llvm.mlir
test/Tools/tensor_layout_print.mlir
test/Triton/canonicalize.mlir
test/Triton/combine.mlir
test/Triton/invalid.mlir
test/Triton/loop-invariant-code-motion.mlir
test/Triton/loop-peeling.mlir
test/Triton/loop-unroll.mlir
test/Triton/loop_cse.mlir
test/Triton/ops.mlir
test/Triton/reorder-broadcast.mlir
test/Triton/reproducer.mlir
test/Triton/rewrite-tensor-descriptor-to-pointer.mlir
test/Triton/vecadd.mlir
test/Triton/verify-make-range.mlir
test/TritonGPU/accelerate-matmul.mlir
test/TritonGPU/accelerate-matmul.mlir.nyi
test/TritonGPU/accumulator-init.mlir
test/TritonGPU/atomic-cas.mlir
test/TritonGPU/automatic-warp-specialization.mlir
test/TritonGPU/bf16x3-matmul.mlir
test/TritonGPU/canonicalize.mlir
test/TritonGPU/coalesce-async-copy.mlir
test/TritonGPU/coalesce.mlir
test/TritonGPU/combine-select-if.mlir
test/TritonGPU/combine.mlir
test/TritonGPU/consan.mlir
test/TritonGPU/dot-operands.mlir
test/TritonGPU/fence-inserstion.mlir
test/TritonGPU/fpsan.mlir
test/TritonGPU/fuse-nested-loops.mlir
test/TritonGPU/global_scratch_alloc.mlir
test/TritonGPU/global_scratch_to_llvm.mlir
test/TritonGPU/gsan.mlir
test/TritonGPU/hoist-tmem-alloc.mlir
test/TritonGPU/inline.mlir
test/TritonGPU/invalid-attributes.mlir
test/TritonGPU/invalid.mlir
test/TritonGPU/loop-pipeline-async-latencies.mlir
test/TritonGPU/loop-pipeline-blackwell.mlir
test/TritonGPU/loop-pipeline-combine-waits.mlir
test/TritonGPU/loop-pipeline-cuda.mlir
test/TritonGPU/loop-pipeline-expand.mlir
test/TritonGPU/loop-pipeline-hip.mlir
test/TritonGPU/loop-pipeline-hopper-remove-wait.mlir
test/TritonGPU/loop-pipeline-hopper.mlir
test/TritonGPU/loop-pipeline-indirect-load.mlir
test/TritonGPU/loop-pipeline.mlir
test/TritonGPU/loop-schedule.mlir
test/TritonGPU/matmul-loop-pipeline.mlir
test/TritonGPU/matmul.mlir
test/TritonGPU/memdesc-subview-split.mlir
test/TritonGPU/nvidia-fpsan.mlir
test/TritonGPU/ops.mlir
test/TritonGPU/optimize-locality.mlir
test/TritonGPU/optimize-partition-warps.mlir
test/TritonGPU/optimize_epilogue.mlir
test/TritonGPU/partition-loops.mlir
test/TritonGPU/partition-scheduling.mlir
test/TritonGPU/pipeline-assign-latencies.mlir
test/TritonGPU/pipeline-loop-nest.mlir
test/TritonGPU/pipeline-lower-loop.mlir
test/TritonGPU/pipeline-schedule-loop.mlir
test/TritonGPU/prefetch.mlir
test/TritonGPU/promote-lhs-to-tmem.mlir
test/TritonGPU/proxy_fence_insertion.mlir
test/TritonGPU/reduce-data-duplication.mlir
test/TritonGPU/reorder-instructions.mlir
test/TritonGPU/tf32x3-matmul.mlir
test/TritonGPU/verify-blocked-layout.mlir
test/TritonGPU/verify-padded-layouts.mlir
test/TritonGPU/amd/accelerate-amd-matmul-chain-dot.mlir
test/TritonGPU/amd/accelerate-amd-matmul-fma.mlir
test/TritonGPU/amd/accelerate-amd-matmul-mfma-decompose-scaled-dot.mlir
test/TritonGPU/amd/accelerate-amd-matmul-mfma-gfx950.mlir
test/TritonGPU/amd/accelerate-amd-matmul-mfma.mlir
test/TritonGPU/amd/accelerate-amd-matmul-wmma-gen1.mlir
test/TritonGPU/amd/accelerate-amd-matmul-wmma-gen2.mlir
test/TritonGPU/amd/accelerate-amd-matmul-wmma-gfx1250.mlir
test/TritonGPU/amd/amd-block-pingpong-chained-dots.mlir
test/TritonGPU/amd/amd-block-pingpong.mlir
test/TritonGPU/amd/amd-buffer-cache-modifiers-rdna3.mlir
test/TritonGPU/amd/amd-canonicalize-extract-slice.mlir
test/TritonGPU/amd/amd-canonicalize-pointers-different-bases.mlir
test/TritonGPU/amd/amd-canonicalize-pointers-dont-run-mlir-canonicalizer.mlir
test/TritonGPU/amd/amd-canonicalize-pointers-empty-uniformsum.mlir
test/TritonGPU/amd/amd-canonicalize-pointers-no-large-tensor.mlir
test/TritonGPU/amd/amd-canonicalize-pointers.mlir
test/TritonGPU/amd/amd-coalesce-async-copy.mlir
test/TritonGPU/amd/amd-concat-op.mlir
test/TritonGPU/amd/amd-conditional-barrier.mlir
test/TritonGPU/amd/amd-consan.mlir
test/TritonGPU/amd/amd-convert-buffer-ops-i64-offset.mlir
test/TritonGPU/amd/amd-convert-buffer-ops-range-analysis.mlir
test/TritonGPU/amd/amd-convert-buffer-ops-small-tensor.mlir
test/TritonGPU/amd/amd-convert-buffer-ops.mlir
test/TritonGPU/amd/amd-convert-tensor-ops.mlir
test/TritonGPU/amd/amd-convert-warp-pipeline.mlir
test/TritonGPU/amd/amd-extractslice-op.mlir
test/TritonGPU/amd/amd-fold-true-cmpi.mlir
test/TritonGPU/amd/amd-fpsan.mlir
test/TritonGPU/amd/amd-hoist-cvtToDotOp.mlir
test/TritonGPU/amd/amd-move-up-prologue-loads.mlir
test/TritonGPU/amd/amd-optimize-buffer-ops-base-ptr-increment.mlir
test/TritonGPU/amd/amd-optimize-descriptor-encoding.mlir
test/TritonGPU/amd/amd-optimize-dot-operands.mlir
test/TritonGPU/amd/amd-optimize-epilogue.mlir
test/TritonGPU/amd/amd-pid-bounds.mlir
test/TritonGPU/amd/amd-pipeline-chained-dots.mlir
test/TritonGPU/amd/amd-pipeline-padded-layout-gfx1250.mlir
test/TritonGPU/amd/amd-pipeline-padded-layout-small-tile-gfx950.mlir
test/TritonGPU/amd/amd-pipeline-shared-layout-async-copy-gfx9.mlir
test/TritonGPU/amd/amd-pipeline-tdm.mlir
test/TritonGPU/amd/amd-prepare-if-combining.mlir
test/TritonGPU/amd/amd-range-analysis.mlir
test/TritonGPU/amd/amd-scaled-upcast-gfx1250.mlir
test/TritonGPU/amd/amd-schedule-hint.mlir
test/TritonGPU/amd/amd-sink-layout-conversions.mlir
test/TritonGPU/amd/amd-stream-lds-layout-selection.mlir
test/TritonGPU/amd/amd-stream-loop-assume.mlir
test/TritonGPU/amd/amd-update-async-wait-count-without-token.mlir
test/TritonGPU/amd/amd-update-async-wait-count.mlir
test/TritonGPU/amd/amd-warp-pipeline.mlir
test/TritonGPU/amd/in-thread-transpose.mlir
test/TritonGPU/amd/invalid.mlir
test/TritonGPU/amd/mfma-double-rate.mlir
test/TritonGPU/amd/mfma-mixed-f8-types.mlir
test/TritonGPU/amd/mfma-xf32.mlir
test/TritonGPU/amd/sink-setprio-mfma.mlir
test/TritonGPU/samples/descriptor-matmul-pipeline.mlir
test/TritonGPU/samples/descriptor-matmul-pipeline.mlir.in
test/TritonGPU/samples/simulated-grouped-gemm.mlir
test/TritonGPU/samples/simulated-grouped-gemm.mlir.in
test/TritonNvidiaGPU/bf16-atomics.mlir
test/TritonNvidiaGPU/canonicalize.mlir
test/TritonNvidiaGPU/inline.mlir
test/TritonNvidiaGPU/interleave_tmem.mlir
test/TritonNvidiaGPU/invalid.mlir
test/TritonNvidiaGPU/membar-cluster.mlir
test/TritonNvidiaGPU/membar.mlir
test/TritonNvidiaGPU/mma_lowering.mlir
test/TritonNvidiaGPU/ops.mlir
test/TritonNvidiaGPU/optimize_descriptor_encoding.mlir
test/TritonNvidiaGPU/plan_cta.mlir
test/TritonNvidiaGPU/test_promotion_to_tensor_memory.mlir
test/TritonNvidiaGPU/test_tensor_memory_allocation.mlir
test/TritonNvidiaGPU/tma_lowering.mlir
test/TritonNvidiaGPU/tmem_layouts.mlir
test/include/Analysis/TestAxisInfo.h
test/lib/CMakeLists.txt
test/lib/Analysis/CMakeLists.txt
test/lib/Analysis/TestAlias.cpp
test/lib/Analysis/TestAllocation.cpp
test/lib/Analysis/TestAxisInfo.cpp
test/lib/Analysis/TestBufferRegion.cpp
test/lib/Analysis/TestMembar.cpp
test/lib/Dialect/CMakeLists.txt
test/lib/Dialect/TestLoopPeeling.cpp
test/lib/Instrumentation/CMakeLists.txt
test/lib/Instrumentation/GPUHello.cpp
test/lib/Proton/CMakeLists.txt
test/lib/Proton/TestScopeIdAllocation.cpp
third_party/amd/CMakeLists.txt
third_party/amd/backend/__init__.py
third_party/amd/backend/compiler.py
third_party/amd/backend/driver.c
third_party/amd/backend/driver.py
third_party/amd/backend/include/TDMCommon.h
third_party/amd/backend/include/hip/channel_descriptor.h
third_party/amd/backend/include/hip/driver_types.h
third_party/amd/backend/include/hip/hip_common.h
third_party/amd/backend/include/hip/hip_deprecated.h
third_party/amd/backend/include/hip/hip_runtime.h
third_party/amd/backend/include/hip/hip_runtime_api.h
third_party/amd/backend/include/hip/hip_texture_types.h
third_party/amd/backend/include/hip/hip_vector_types.h
third_party/amd/backend/include/hip/hip_version.h
third_party/amd/backend/include/hip/library_types.h
third_party/amd/backend/include/hip/linker_types.h
third_party/amd/backend/include/hip/surface_types.h
third_party/amd/backend/include/hip/texture_types.h
third_party/amd/backend/include/hip/amd_detail/amd_channel_descriptor.h
third_party/amd/backend/include/hip/amd_detail/amd_device_functions.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_atomic.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_common.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_gl_interop.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_runtime.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_runtime_pt_api.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_unsafe_atomics.h
third_party/amd/backend/include/hip/amd_detail/amd_hip_vector_types.h
third_party/amd/backend/include/hip/amd_detail/amd_math_functions.h
third_party/amd/backend/include/hip/amd_detail/amd_surface_functions.h
third_party/amd/backend/include/hip/amd_detail/amd_warp_functions.h
third_party/amd/backend/include/hip/amd_detail/amd_warp_sync_functions.h
third_party/amd/backend/include/hip/amd_detail/device_library_decls.h
third_party/amd/backend/include/hip/amd_detail/hip_assert.h
third_party/amd/backend/include/hip/amd_detail/hip_fp16_math_fwd.h
third_party/amd/backend/include/hip/amd_detail/hip_ldg.h
third_party/amd/backend/include/hip/amd_detail/hip_prof_str.h
third_party/amd/backend/include/hip/amd_detail/hip_runtime_prof.h
third_party/amd/backend/include/hip/amd_detail/host_defines.h
third_party/amd/backend/include/hip/amd_detail/math_fwd.h
third_party/amd/backend/include/hip/amd_detail/ockl_image.h
third_party/amd/backend/include/hip/amd_detail/texture_fetch_functions.h
third_party/amd/backend/include/hip/amd_detail/texture_indirect_functions.h
third_party/amd/backend/include/hipblas-common/hipblas-common.h
third_party/amd/backend/include/hsa/amd_hsa_kernel_code.h
third_party/amd/backend/include/hsa/hsa.h
third_party/amd/backend/include/hsa/hsa_ext_amd.h
third_party/amd/backend/include/hsa/hsa_ext_image.h
third_party/amd/backend/include/hsa/hsa_ven_amd_loader.h
third_party/amd/backend/include/hsa/hsa_ven_amd_pc_sampling.h
third_party/amd/backend/include/roctracer/roctracer.h
third_party/amd/backend/include/roctracer/roctracer_ext.h
third_party/amd/backend/include/roctracer/roctracer_hip.h
third_party/amd/backend/include/roctracer/roctracer_roctx.h
third_party/amd/backend/include/roctracer/roctx.h
third_party/amd/backend/include/roctracer/ext/prof_protocol.h
third_party/amd/backend/lib/asanrtl.bc
third_party/amd/backend/lib/ockl.bc
third_party/amd/backend/lib/ocml.bc
third_party/amd/include/CMakeLists.txt
third_party/amd/include/hipblas_instance.h
third_party/amd/include/hipblas_types.h
third_party/amd/include/Analysis/AMDGPUAllocation.h
third_party/amd/include/Analysis/AxisInfoExt.h
third_party/amd/include/Analysis/RangeAnalysis.h
third_party/amd/include/Dialect/CMakeLists.txt
third_party/amd/include/Dialect/TritonAMDGPU/CMakeLists.txt
third_party/amd/include/Dialect/TritonAMDGPU/IR/CMakeLists.txt
third_party/amd/include/Dialect/TritonAMDGPU/IR/Dialect.h
third_party/amd/include/Dialect/TritonAMDGPU/IR/TritonAMDGPUAttrDefs.td
third_party/amd/include/Dialect/TritonAMDGPU/IR/TritonAMDGPUDialect.td
third_party/amd/include/Dialect/TritonAMDGPU/IR/TritonAMDGPUOpInterfaces.td
third_party/amd/include/Dialect/TritonAMDGPU/IR/TritonAMDGPUOps.td
third_party/amd/include/Dialect/TritonAMDGPU/Utility/CommonUtils.h
third_party/amd/include/TritonAMDGPUToLLVM/CMakeLists.txt
third_party/amd/include/TritonAMDGPUToLLVM/GCNAsmFormat.h
third_party/amd/include/TritonAMDGPUToLLVM/MembarUtility.h
third_party/amd/include/TritonAMDGPUToLLVM/Passes.h
third_party/amd/include/TritonAMDGPUToLLVM/Passes.td
third_party/amd/include/TritonAMDGPUToLLVM/PatternTritonAMDGPUToLLVM.h
third_party/amd/include/TritonAMDGPUToLLVM/TargetUtils.h
third_party/amd/include/TritonAMDGPUToLLVM/TypeConverter.h
third_party/amd/include/TritonAMDGPUTransforms/CMakeLists.txt
third_party/amd/include/TritonAMDGPUTransforms/MfmaGroup.h
third_party/amd/include/TritonAMDGPUTransforms/Passes.h
third_party/amd/include/TritonAMDGPUTransforms/Passes.td
third_party/amd/include/TritonAMDGPUTransforms/TritonGPUConversion.h
third_party/amd/include/TritonAMDGPUTransforms/WmmaGroup.h
third_party/amd/include/Utils/Utility.h
third_party/amd/language/hip/__init__.py
third_party/amd/language/hip/libdevice.py
third_party/amd/language/hip/utils.py
third_party/amd/lib/CMakeLists.txt
third_party/amd/lib/Analysis/AMDGPUAllocation.cpp
third_party/amd/lib/Analysis/AxisInfoExt.cpp
third_party/amd/lib/Analysis/CMakeLists.txt
third_party/amd/lib/Analysis/RangeAnalysis.cpp
third_party/amd/lib/Dialect/CMakeLists.txt
third_party/amd/lib/Dialect/TritonAMDGPU/CMakeLists.txt
third_party/amd/lib/Dialect/TritonAMDGPU/IR/CMakeLists.txt
third_party/amd/lib/Dialect/TritonAMDGPU/IR/Dialect.cpp
third_party/amd/lib/Dialect/TritonAMDGPU/Utility/CMakeLists.txt
third_party/amd/lib/Dialect/TritonAMDGPU/Utility/CommonUtils.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/CMakeLists.txt
third_party/amd/lib/TritonAMDGPUDialectToLLVM/ConcatOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/ExtractSliceOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/InThreadTransposeOpToTTG.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/ScaledUpcastToLLVM.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/TritonAMDGPUToLLVMPatterns.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/Utility.cpp
third_party/amd/lib/TritonAMDGPUDialectToLLVM/Utility.h
third_party/amd/lib/TritonAMDGPUToLLVM/AllocateSharedMemory.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/AsyncUtility.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/AsyncUtility.h
third_party/amd/lib/TritonAMDGPUToLLVM/AtomicRMWOpsEmitter.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/AtomicRMWOpsEmitter.h
third_party/amd/lib/TritonAMDGPUToLLVM/BarrierOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/BufferOpsEmitter.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/BufferOpsEmitter.h
third_party/amd/lib/TritonAMDGPUToLLVM/BuiltinFuncToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/CMakeLists.txt
third_party/amd/lib/TritonAMDGPUToLLVM/ConvertLayoutOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/ConvertWarpPipeline.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/ConvertWarpSpecializeToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/ElementwiseOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/Fp4ToFpOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/FuncOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/GCNAsmFormat.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/HistogramOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/LoadStoreOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/MaskedOpsToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/MembarUtility.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/MemoryOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/PatternTritonGPUOpToLLVM.h
third_party/amd/lib/TritonAMDGPUToLLVM/PrepareConSanCaptures.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/SPMDOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/ScalarizePackedFOps.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/SchedInstructions.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/TDMUtility.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/TDMUtility.h
third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.h
third_party/amd/lib/TritonAMDGPUToLLVM/TargetUtils.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/TensorPtrOpsToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/TritonGPUToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/Utility.h
third_party/amd/lib/TritonAMDGPUToLLVM/WarpIdOpToLLVM.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/FMA.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp
third_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/WMMA.cpp
third_party/amd/lib/TritonAMDGPUTransforms/AccelerateAMDMatmul.cpp
third_party/amd/lib/TritonAMDGPUTransforms/BlockPingpong.cpp
third_party/amd/lib/TritonAMDGPUTransforms/CMakeLists.txt
third_party/amd/lib/TritonAMDGPUTransforms/CanonicalizePointers.cpp
third_party/amd/lib/TritonAMDGPUTransforms/CoalesceAsyncCopy.cpp
third_party/amd/lib/TritonAMDGPUTransforms/ConSanAMD.cpp
third_party/amd/lib/TritonAMDGPUTransforms/ConvertToBufferOps.cpp
third_party/amd/lib/TritonAMDGPUTransforms/ConvertToTensorOps.cpp
third_party/amd/lib/TritonAMDGPUTransforms/FoldTrueCmpIOp.cpp
third_party/amd/lib/TritonAMDGPUTransforms/FpSanitizer.cpp
third_party/amd/lib/TritonAMDGPUTransforms/HoistLayoutConversions.cpp
third_party/amd/lib/TritonAMDGPUTransforms/InThreadTranspose.cpp
third_party/amd/lib/TritonAMDGPUTransforms/LowerLoops.cpp
third_party/amd/lib/TritonAMDGPUTransforms/MfmaGroup.cpp
third_party/amd/lib/TritonAMDGPUTransforms/MoveUpPrologueLoads.cpp
third_party/amd/lib/TritonAMDGPUTransforms/OptimizeBufferOpPtr.cpp
third_party/amd/lib/TritonAMDGPUTransforms/OptimizeDescriptorEncoding.cpp
third_party/amd/lib/TritonAMDGPUTransforms/OptimizeDotOperands.cpp
third_party/amd/lib/TritonAMDGPUTransforms/OptimizeEpilogue.cpp
third_party/amd/lib/TritonAMDGPUTransforms/Pipeline.cpp
third_party/amd/lib/TritonAMDGPUTransforms/PipelineUtility.h
third_party/amd/lib/TritonAMDGPUTransforms/PrepareIfCombining.cpp
third_party/amd/lib/TritonAMDGPUTransforms/ScheduleLoops.cpp
third_party/amd/lib/TritonAMDGPUTransforms/SinkLayoutConversions.cpp
third_party/amd/lib/TritonAMDGPUTransforms/UpdateAsyncWaitCount.cpp
third_party/amd/lib/TritonAMDGPUTransforms/Utility.cpp
third_party/amd/lib/TritonAMDGPUTransforms/Utility.h
third_party/amd/lib/TritonAMDGPUTransforms/WarpPipeliner.cpp
third_party/amd/lib/TritonAMDGPUTransforms/WmmaGroup.cpp
third_party/amd/python/triton_amd.cc
third_party/amd/python/examples/gluon/f16_fa_gfx1250.py
third_party/amd/python/examples/gluon/f16_gemm_common_gfx1250.py
third_party/amd/python/examples/gluon/f16_gemm_gfx1250.py
third_party/amd/python/examples/gluon/f16_gemm_streamk_gfx1250.py
third_party/amd/python/examples/gluon/f16_gemm_warp_pipeline_gfx1250.py
third_party/amd/python/examples/gluon/gfx1250_utils.py
third_party/amd/python/examples/gluon/mxfp_fa_gfx1250.py
third_party/amd/python/examples/gluon/mxfp_gemm_gfx1250.py
third_party/amd/python/test/address_sanitizer_helper.py
third_party/amd/python/test/attn_fwd.ttir
third_party/amd/python/test/conftest.py
third_party/amd/python/test/gfx1250_consan_helper.py
third_party/amd/python/test/test_address_sanitizer.py
third_party/amd/python/test/test_convert_op_permlane_swap.py
third_party/amd/python/test/test_extract_slice_concat_op.py
third_party/amd/python/test/test_f16_gemm_tdm.py
third_party/amd/python/test/test_gluon_gfx1250.py
third_party/amd/python/test/test_gluon_gfx1250_consan.py
third_party/amd/python/test/test_link_hsaco_error_message.py
third_party/amd/python/test/test_mxfp_gemm_tdm.py
third_party/amd/python/test/test_packed_f32_arith.py
third_party/amd/python/test/test_pointer_optimization.py
third_party/amd/python/test/test_scalarize_packed_fops.py
third_party/amd/python/test/test_scheduler_hints.py
third_party/amd/python/test/test_warp_pipeline_gfx9.py
third_party/amd/test/CMakeLists.txt
third_party/amd/test/lib/CMakeLists.txt
third_party/amd/test/lib/Analysis/CMakeLists.txt
third_party/amd/test/lib/Analysis/TestAMDGPUMembar.cpp
third_party/amd/test/lib/Analysis/TestAMDRangeAnalysis.cpp
third_party/amd/test/lib/Analysis/TestAxisInfo.cpp
third_party/amd/tools/hip/compile.c
third_party/amd/tools/hip/compile.h
third_party/amd/tools/hip/link.h
third_party/f2reduce/CMakeLists.txt
third_party/f2reduce/LICENCE.txt
third_party/f2reduce/README.md
third_party/f2reduce/VERSION
third_party/f2reduce/f2reduce.cpp
third_party/f2reduce/f2reduce.h
third_party/nvidia/CMakeLists.txt
third_party/nvidia/triton_nvidia.cc
third_party/nvidia/backend/__init__.py
third_party/nvidia/backend/compiler.py
third_party/nvidia/backend/driver.c
third_party/nvidia/backend/driver.py
third_party/nvidia/backend/lib/libdevice.10.bc
third_party/nvidia/clang_cuda_shims/assert.h
third_party/nvidia/clang_cuda_shims/curand_mtgp32_kernel.h
third_party/nvidia/hopper/CMakeLists.txt
third_party/nvidia/hopper/include/CMakeLists.txt
third_party/nvidia/hopper/include/Transforms/CMakeLists.txt
third_party/nvidia/hopper/include/Transforms/Passes.h
third_party/nvidia/hopper/include/Transforms/Passes.td
third_party/nvidia/hopper/lib/CMakeLists.txt
third_party/nvidia/hopper/lib/Transforms/CMakeLists.txt
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/CodePartitionUtility.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/CodePartitionUtility.h
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/TaskIdPropagation.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/TaskIdPropagation.h
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/Utility.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/Utility.h
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSCodePartition.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSDataPartition.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSLowerMem.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSLowerToken.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSSpecialize.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSTaskIdPropagate.cpp
third_party/nvidia/hopper/lib/Transforms/WarpSpecialization/WSTaskPartition.cpp
third_party/nvidia/include/CMakeLists.txt
third_party/nvidia/include/cublas_instance.h
third_party/nvidia/include/cublas_types.h
third_party/nvidia/include/Dialect/CMakeLists.txt
third_party/nvidia/include/Dialect/NVGPU/CMakeLists.txt
third_party/nvidia/include/Dialect/NVGPU/IR/CMakeLists.txt
third_party/nvidia/include/Dialect/NVGPU/IR/Dialect.h
third_party/nvidia/include/Dialect/NVGPU/IR/NVGPUAttrDefs.td
third_party/nvidia/include/Dialect/NVGPU/IR/NVGPUDialect.td
third_party/nvidia/include/Dialect/NVGPU/IR/NVGPUOps.td
third_party/nvidia/include/Dialect/NVWS/CMakeLists.txt
third_party/nvidia/include/Dialect/NVWS/IR/CMakeLists.txt
third_party/nvidia/include/Dialect/NVWS/IR/Dialect.h
third_party/nvidia/include/Dialect/NVWS/IR/NVWSAttrDefs.td
third_party/nvidia/include/Dialect/NVWS/IR/NVWSDialect.td
third_party/nvidia/include/Dialect/NVWS/IR/NVWSOpInterfaces.td
third_party/nvidia/include/Dialect/NVWS/IR/NVWSOps.td
third_party/nvidia/include/Dialect/NVWS/IR/NVWSTypes.td
third_party/nvidia/include/Dialect/NVWS/Transforms/CMakeLists.txt
third_party/nvidia/include/Dialect/NVWS/Transforms/Passes.h
third_party/nvidia/include/Dialect/NVWS/Transforms/Passes.td
third_party/nvidia/include/NVGPUToLLVM/CMakeLists.txt
third_party/nvidia/include/NVGPUToLLVM/NVGPUToLLVMPass.h
third_party/nvidia/include/NVGPUToLLVM/Passes.h
third_party/nvidia/include/NVGPUToLLVM/Passes.td
third_party/nvidia/include/TritonNVIDIAGPUToLLVM/CMakeLists.txt
third_party/nvidia/include/TritonNVIDIAGPUToLLVM/PTXAsmFormat.h
third_party/nvidia/include/TritonNVIDIAGPUToLLVM/Passes.h
third_party/nvidia/include/TritonNVIDIAGPUToLLVM/Passes.td
third_party/nvidia/include/TritonNVIDIAGPUToLLVM/Utility.h
third_party/nvidia/language/cuda/__init__.py
third_party/nvidia/language/cuda/gdc.py
third_party/nvidia/language/cuda/libdevice.py
third_party/nvidia/language/cuda/utils.py
third_party/nvidia/lib/CMakeLists.txt
third_party/nvidia/lib/Dialect/CMakeLists.txt
third_party/nvidia/lib/Dialect/NVGPU/CMakeLists.txt
third_party/nvidia/lib/Dialect/NVGPU/IR/CMakeLists.txt
third_party/nvidia/lib/Dialect/NVGPU/IR/Dialect.cpp
third_party/nvidia/lib/Dialect/NVWS/CMakeLists.txt
third_party/nvidia/lib/Dialect/NVWS/IR/CMakeLists.txt
third_party/nvidia/lib/Dialect/NVWS/IR/Dialect.cpp
third_party/nvidia/lib/Dialect/NVWS/IR/Ops.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/AssignStagePhase.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/CMakeLists.txt
third_party/nvidia/lib/Dialect/NVWS/Transforms/HoistTmemStore.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/InsertAref.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/InsertTmemAref.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/LowerAref.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/LowerWarpGroup.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/Utilities.cpp
third_party/nvidia/lib/Dialect/NVWS/Transforms/Utilities.h
third_party/nvidia/lib/NVGPUToLLVM/CMakeLists.txt
third_party/nvidia/lib/NVGPUToLLVM/NVGPUToLLVMPass.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/Allocation.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/Allocation.h
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/BarrierOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/CMakeLists.txt
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/ClusterOpsToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/ConvertLayoutOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/ConvertWarpSpecializeToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/DotOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/ElementwiseOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/Fp4ToFpOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/LoadStoreOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/MemoryOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/PTXAsmFormat.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/PatternTritonGPUOpToLLVM.h
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/SPMDOpToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/TMAToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/TargetInfo.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/TargetInfo.h
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/TensorMemoryToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/TritonGPUToLLVM.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/Utility.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/Utility.h
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/DotOpToLLVM/MMAHelpers.h
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/DotOpToLLVM/MMAv2.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/DotOpToLLVM/MMAv5.cpp
third_party/nvidia/lib/TritonNVIDIAGPUToLLVM/DotOpToLLVM/WGMMA.cpp
third_party/nvidia/tools/cuda/compile.c
third_party/nvidia/tools/cuda/compile.h
third_party/nvidia/tools/cuda/link.h
third_party/nvidia/unittest/CMakeLists.txt
third_party/nvidia/unittest/Conversion/CMakeLists.txt
third_party/nvidia/unittest/Conversion/TritonGPUToLLVM/CMakeLists.txt
third_party/nvidia/unittest/Conversion/TritonGPUToLLVM/PTXAsmFormatTest.cpp
third_party/proton/.gitignore
third_party/proton/CMakeLists.txt
third_party/proton/README.md
third_party/proton/Dialect/CMakeLists.txt
third_party/proton/Dialect/triton_proton.cc
third_party/proton/Dialect/include/CMakeLists.txt
third_party/proton/Dialect/include/Analysis/ScopeIdAllocation.h
third_party/proton/Dialect/include/Conversion/CMakeLists.txt
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/CMakeLists.txt
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/Passes.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/Passes.td
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/PatternProtonGPUOpToLLVM.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/TargetInfoBase.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/Utility.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/AMDPatternProtonGPUOpToLLVM.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/CMakeLists.txt
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/Passes.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/Passes.td
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/TargetInfo.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/CMakeLists.txt
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/NvidiaPatternProtonGPUOpToLLVM.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/Passes.h
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/Passes.td
third_party/proton/Dialect/include/Conversion/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/TargetInfo.h
third_party/proton/Dialect/include/Conversion/ProtonToProtonGPU/CMakeLists.txt
third_party/proton/Dialect/include/Conversion/ProtonToProtonGPU/Passes.h
third_party/proton/Dialect/include/Conversion/ProtonToProtonGPU/Passes.td
third_party/proton/Dialect/include/Dialect/CMakeLists.txt
third_party/proton/Dialect/include/Dialect/Proton/CMakeLists.txt
third_party/proton/Dialect/include/Dialect/Proton/IR/CMakeLists.txt
third_party/proton/Dialect/include/Dialect/Proton/IR/Dialect.h
third_party/proton/Dialect/include/Dialect/Proton/IR/ProtonAttrDefs.td
third_party/proton/Dialect/include/Dialect/Proton/IR/ProtonDialect.td
third_party/proton/Dialect/include/Dialect/Proton/IR/ProtonOps.td
third_party/proton/Dialect/include/Dialect/ProtonGPU/CMakeLists.txt
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/CMakeLists.txt
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/Dialect.h
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/ProtonGPUAttrDefs.td
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/ProtonGPUDialect.td
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/ProtonGPUOps.td
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/ProtonGPUTypes.td
third_party/proton/Dialect/include/Dialect/ProtonGPU/IR/Types.h
third_party/proton/Dialect/include/Dialect/ProtonGPU/Transforms/CMakeLists.txt
third_party/proton/Dialect/include/Dialect/ProtonGPU/Transforms/Passes.h
third_party/proton/Dialect/include/Dialect/ProtonGPU/Transforms/Passes.td
third_party/proton/Dialect/lib/CMakeLists.txt
third_party/proton/Dialect/lib/Analysis/CMakeLists.txt
third_party/proton/Dialect/lib/Analysis/ScopeIdAllocation.cpp
third_party/proton/Dialect/lib/Dialect/CMakeLists.txt
third_party/proton/Dialect/lib/Dialect/Proton/CMakeLists.txt
third_party/proton/Dialect/lib/Dialect/Proton/IR/CMakeLists.txt
third_party/proton/Dialect/lib/Dialect/Proton/IR/Dialect.cpp
third_party/proton/Dialect/lib/Dialect/Proton/IR/Ops.cpp
third_party/proton/Dialect/lib/Dialect/ProtonGPU/CMakeLists.txt
third_party/proton/Dialect/lib/Dialect/ProtonGPU/IR/CMakeLists.txt
third_party/proton/Dialect/lib/Dialect/ProtonGPU/IR/Dialect.cpp
third_party/proton/Dialect/lib/Dialect/ProtonGPU/IR/Ops.cpp
third_party/proton/Dialect/lib/Dialect/ProtonGPU/IR/Types.cpp
third_party/proton/Dialect/lib/Dialect/ProtonGPU/Transforms/CMakeLists.txt
third_party/proton/Dialect/lib/Dialect/ProtonGPU/Transforms/ProtonGPUTransformsPass.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/AllocateProtonSharedMemory.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/CMakeLists.txt
third_party/proton/Dialect/lib/ProtonGPUToLLVM/PatternProtonGPUOpToLLVM.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/Utility.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/AMDPatternProtonGPUOpToLLVM.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/AddSchedBarriers.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/CMakeLists.txt
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/ConvertProtonGPUToLLVM.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonAMDGPUToLLVM/TargetInfo.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/CMakeLists.txt
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/ConvertProtonGPUToLLVM.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/NvidiaPatternProtonGPUOpToLLVM.cpp
third_party/proton/Dialect/lib/ProtonGPUToLLVM/ProtonNvidiaGPUToLLVM/TargetInfo.cpp
third_party/proton/Dialect/lib/ProtonToProtonGPU/CMakeLists.txt
third_party/proton/Dialect/lib/ProtonToProtonGPU/ProtonToProtonGPUPass.cpp
third_party/proton/common/CMakeLists.txt
third_party/proton/common/include/Device.h
third_party/proton/common/include/TraceDataIO/ByteSpan.h
third_party/proton/common/include/TraceDataIO/CircularLayoutParser.h
third_party/proton/common/include/TraceDataIO/EntryDecoder.h
third_party/proton/common/include/TraceDataIO/Parser.h
third_party/proton/common/include/TraceDataIO/TraceWriter.h
third_party/proton/common/lib/CMakeLists.txt
third_party/proton/common/lib/TraceDataIO/ByteSpan.cpp
third_party/proton/common/lib/TraceDataIO/CMakeLists.txt
third_party/proton/common/lib/TraceDataIO/CircularLayoutParser.cpp
third_party/proton/common/lib/TraceDataIO/EntryDecoder.cpp
third_party/proton/common/lib/TraceDataIO/Parser.cpp
third_party/proton/common/lib/TraceDataIO/TraceWriter.cpp
third_party/proton/csrc/CMakeLists.txt
third_party/proton/csrc/Proton.cpp
third_party/proton/csrc/include/Proton.h
third_party/proton/csrc/include/Context/Context.h
third_party/proton/csrc/include/Context/Python.h
third_party/proton/csrc/include/Context/Shadow.h
third_party/proton/csrc/include/Data/Data.h
third_party/proton/csrc/include/Data/Metric.h
third_party/proton/csrc/include/Data/PhaseStore.h
third_party/proton/csrc/include/Data/TraceData.h
third_party/proton/csrc/include/Data/TreeData.h
third_party/proton/csrc/include/Driver/Dispatch.h
third_party/proton/csrc/include/Driver/GPU/CudaApi.h
third_party/proton/csrc/include/Driver/GPU/CuptiApi.h
third_party/proton/csrc/include/Driver/GPU/HipApi.h
third_party/proton/csrc/include/Driver/GPU/HsaApi.h
third_party/proton/csrc/include/Driver/GPU/NvtxApi.h
third_party/proton/csrc/include/Driver/GPU/RoctracerApi.h
third_party/proton/csrc/include/Profiler/GPUProfiler.h
third_party/proton/csrc/include/Profiler/Graph.h
third_party/proton/csrc/include/Profiler/Profiler.h
third_party/proton/csrc/include/Profiler/Cupti/CuptiPCSampling.h
third_party/proton/csrc/include/Profiler/Cupti/CuptiProfiler.h
third_party/proton/csrc/include/Profiler/Instrumentation/InstrumentationProfiler.h
third_party/proton/csrc/include/Profiler/Instrumentation/Metadata.h
third_party/proton/csrc/include/Profiler/Roctracer/RoctracerProfiler.h
third_party/proton/csrc/include/Runtime/CudaRuntime.h
third_party/proton/csrc/include/Runtime/HipRuntime.h
third_party/proton/csrc/include/Runtime/Runtime.h
third_party/proton/csrc/include/Session/Session.h
third_party/proton/csrc/include/Utility/Atomic.h
third_party/proton/csrc/include/Utility/Env.h
third_party/proton/csrc/include/Utility/Errors.h
third_party/proton/csrc/include/Utility/Map.h
third_party/proton/csrc/include/Utility/MsgPackWriter.h
third_party/proton/csrc/include/Utility/Numeric.h
third_party/proton/csrc/include/Utility/Set.h
third_party/proton/csrc/include/Utility/Singleton.h
third_party/proton/csrc/include/Utility/String.h
third_party/proton/csrc/include/Utility/Table.h
third_party/proton/csrc/include/Utility/Traits.h
third_party/proton/csrc/include/Utility/Vector.h
third_party/proton/csrc/lib/CMakeLists.txt
third_party/proton/csrc/lib/Context/CMakeLists.txt
third_party/proton/csrc/lib/Context/Context.cpp
third_party/proton/csrc/lib/Context/Python.cpp
third_party/proton/csrc/lib/Context/Shadow.cpp
third_party/proton/csrc/lib/Data/CMakeLists.txt
third_party/proton/csrc/lib/Data/Data.cpp
third_party/proton/csrc/lib/Data/Metric.cpp
third_party/proton/csrc/lib/Data/TraceData.cpp
third_party/proton/csrc/lib/Data/TreeData.cpp
third_party/proton/csrc/lib/Driver/CMakeLists.txt
third_party/proton/csrc/lib/Driver/Device.cpp
third_party/proton/csrc/lib/Driver/GPU/CudaApi.cpp
third_party/proton/csrc/lib/Driver/GPU/CuptiApi.cpp
third_party/proton/csrc/lib/Driver/GPU/HipApi.cpp
third_party/proton/csrc/lib/Driver/GPU/HsaApi.cpp
third_party/proton/csrc/lib/Driver/GPU/NvtxApi.cpp
third_party/proton/csrc/lib/Driver/GPU/RoctracerApi.cpp
third_party/proton/csrc/lib/Profiler/CMakeLists.txt
third_party/proton/csrc/lib/Profiler/GPUProfiler.cpp
third_party/proton/csrc/lib/Profiler/Graph.cpp
third_party/proton/csrc/lib/Profiler/Profiler.cpp
third_party/proton/csrc/lib/Profiler/Cupti/CuptiPCSampling.cpp
third_party/proton/csrc/lib/Profiler/Cupti/CuptiProfiler.cpp
third_party/proton/csrc/lib/Profiler/Instrumentation/InstrumentationProfiler.cpp
third_party/proton/csrc/lib/Profiler/Instrumentation/Metadata.cpp
third_party/proton/csrc/lib/Profiler/RocTracer/RoctracerProfiler.cpp
third_party/proton/csrc/lib/Runtime/CMakeLists.txt
third_party/proton/csrc/lib/Runtime/CudaRuntime.cpp
third_party/proton/csrc/lib/Runtime/HipRuntime.cpp
third_party/proton/csrc/lib/Session/CMakeLists.txt
third_party/proton/csrc/lib/Session/Session.cpp
third_party/proton/csrc/lib/Utility/CMakeLists.txt
third_party/proton/csrc/lib/Utility/MsgPackWriter.cpp
third_party/proton/proton/__init__.py
third_party/proton/proton/context.py
third_party/proton/proton/data.py
third_party/proton/proton/flags.py
third_party/proton/proton/language.py
third_party/proton/proton/metric.py
third_party/proton/proton/mode.py
third_party/proton/proton/profile.py
third_party/proton/proton/proton.py
third_party/proton/proton/scope.py
third_party/proton/proton/specs.py
third_party/proton/proton/state.py
third_party/proton/proton/viewer.py
third_party/proton/proton/hooks/__init__.py
third_party/proton/proton/hooks/hook.py
third_party/proton/proton/hooks/instrumentation.py
third_party/proton/proton/hooks/launch.py
third_party/proton/scripts/dump_ttgir.sh
third_party/proton/test/CMakeLists.txt
third_party/proton/test/conftest.py
third_party/proton/test/helper.py
third_party/proton/test/helper_kernels.py
third_party/proton/test/override_helper.py
third_party/proton/test/test_api.py
third_party/proton/test/test_cmd.py
third_party/proton/test/test_instrumentation.py
third_party/proton/test/test_lib.py
third_party/proton/test/test_override.py
third_party/proton/test/test_profile.py
third_party/proton/test/test_viewer.py
third_party/proton/test/examples/cuda.json
third_party/proton/test/examples/frame.json
third_party/proton/test/examples/hip.json
third_party/proton/test/examples/leaf_nodes.json
third_party/proton/test/examples/triton.json
third_party/proton/test/reproducers/cupti_graph_replay_heap_growth.py
third_party/proton/test/unittest/CMakeLists.txt
third_party/proton/test/unittest/TraceDataIO/ByteSpanTest.cpp
third_party/proton/test/unittest/TraceDataIO/CMakeLists.txt
third_party/proton/test/unittest/TraceDataIO/ChromeTraceWriterTest.cpp
third_party/proton/test/unittest/TraceDataIO/CircularLayoutParserTest.cpp
third_party/proton/test/unittest/TraceDataIO/DecoderTest.cpp
third_party/proton/test/unittest/util/loop.bin
third_party/proton/test/unittest/util/seq.bin
third_party/proton/test/unittest/util/trace_gen.py
third_party/proton/tutorials/dynamic-net.py
third_party/proton/tutorials/matmul.py
third_party/proton/tutorials/intra_kernel/README.md
third_party/proton/tutorials/intra_kernel/example_dsl.py
third_party/proton/tutorials/intra_kernel/example_override.py
third_party/proton/tutorials/intra_kernel/insert_proton_records
unittest/CMakeLists.txt
unittest/googletest.cmake
unittest/Analysis/CMakeLists.txt
unittest/Analysis/UtilityTest.cpp
unittest/Dialect/CMakeLists.txt
unittest/Dialect/TritonGPU/CMakeLists.txt
unittest/Dialect/TritonGPU/DialectTest.cpp
unittest/Dialect/TritonGPU/DumpLayoutTest.cpp
unittest/Dialect/TritonGPU/LinearLayoutConversionsTest.cpp
unittest/Dialect/TritonGPU/PaddedTest.cpp
unittest/Dialect/TritonGPU/SwizzleTest.cpp
unittest/Tools/CMakeLists.txt
unittest/Tools/LayoutUtilsTest.cpp
unittest/Tools/LinearLayoutTest.cpp