├── .clang-format ├── .editorconfig ├── .git-blame-ignore-revs ├── .github ├── CODEOWNERS ├── ISSUE_TEMPLATE │ ├── bug.yml │ ├── config.yml │ ├── feature-request.yml │ └── performance.yml ├── PULL_REQUEST_TEMPLATE.md ├── README.md ├── WINDOWS.md ├── actions │ ├── get-commit-id │ │ └── action.yml │ ├── install-dependency │ │ └── action.yml │ ├── install-wheels │ │ └── action.yml │ ├── load │ │ └── action.yml │ ├── save │ │ └── action.yml │ ├── setup-pyenv-python │ │ └── action.yml │ ├── setup-python │ │ └── action.yml │ ├── setup-pytorch │ │ └── action.yml │ └── setup-triton │ │ └── action.yml ├── dependabot.yml ├── models │ ├── accuracy │ │ ├── huggingface.txt │ │ ├── timm_models.txt │ │ └── torchbench.txt │ └── performance │ │ ├── huggingface.txt │ │ ├── timm_models.txt │ │ └── torchbench.txt ├── pins │ ├── e2e_reference_torch-xpu-ops.txt │ ├── pti.txt │ └── pytorch.txt └── workflows │ ├── auto-update-translator-cid.yml │ ├── bandit-check.yml │ ├── build-macos.yml │ ├── build-test-gpu.yml │ ├── build-test-python.yml │ ├── build-test-reusable.yml │ ├── build-test-spirv.yml │ ├── build-test-windows.yml │ ├── build-test.yml │ ├── build-windows.yml │ ├── ci.yml │ ├── coverity.yml │ ├── create_release.yml │ ├── documentation.yml │ ├── e2e-accuracy.yml │ ├── e2e-performance.yml │ ├── e2e-reusable.yml │ ├── e2e-windows.yml │ ├── inductor-tests-reusable.yml │ ├── inductor-tests-windows.yml │ ├── inductor-tests.yml │ ├── integration-tests-amd.yml │ ├── integration-tests-nvidia.yml │ ├── llvm-build.yml │ ├── llvm-build │ └── almalinux.Dockerfile │ ├── nightly-wheels.yml │ ├── pip-test-windows.yml │ ├── pip-test.yml │ ├── pre-commit.yml │ ├── runner-preparation.yml │ ├── spirvrunner-test.yml │ ├── third-party-benchmarks.yml │ ├── third-party-tests.yml │ ├── triton-benchmarks-bmg.yml │ ├── triton-benchmarks-pvc.yml │ ├── triton-benchmarks.yml │ ├── try-latest-pytorch.yml │ ├── wheels-pytorch.yml │ ├── wheels-triton.yml │ └── wheels.yml ├── .gitignore ├── .pre-commit-config.yaml ├── CMakeLists.txt ├── CONTRIBUTING.md ├── DEVELOPMENT.md ├── LICENSE ├── MANIFEST.in ├── Makefile ├── README.md ├── RELEASE.md ├── SECURITY.md ├── bandit.yaml ├── benchmarks ├── CMakeLists.txt ├── cmake │ ├── FindCUTLASSLibrary.cmake │ ├── FindXeTLALibrary.cmake │ └── FindoneDNNLibrary.cmake ├── cutlass_kernel │ ├── CMakeLists.txt │ ├── attention │ │ ├── CMakeLists.txt │ │ └── attention.hpp │ ├── config-tool.py │ ├── cutlass-library.conf │ ├── gemm │ │ ├── CMakeLists.txt │ │ ├── gemm.hpp │ │ └── input_gemm.in │ └── python_main.cpp ├── gpu_info.json ├── micro_benchmarks │ ├── conversion │ │ ├── __init__.py │ │ └── float_conversion │ │ │ ├── __init__.py │ │ │ └── float_conversion.py │ ├── core_ops │ │ ├── __init__.py │ │ └── dot_scaled.py │ └── run_benchmarks.py ├── onednn_kernel │ ├── CMakeLists.txt │ ├── onednn-library.conf │ ├── python_main.cpp │ └── softmax │ │ ├── CMakeLists.txt │ │ └── softmax.h ├── setup.py ├── tests │ ├── test_entry_point.py │ ├── test_mocks.py │ └── test_shape_pattern_parser.py ├── third_party │ ├── e2e-flex_attention │ │ ├── prompt.json │ │ ├── run_llm_inductor_greedy.py │ │ ├── transform_results.py │ │ ├── transformers-commit.txt │ │ └── transformers-patch-for-timing.diff │ ├── liger │ │ ├── README.md │ │ ├── run_benchmarks.sh │ │ └── transform.py │ ├── sglang │ │ ├── scaled_mm_benchmark.py │ │ ├── sglang-bench-fix.patch │ │ ├── sglang-pin.txt │ │ └── sglang-test-fix.patch │ └── vllm │ │ ├── batched_moe_benchmark.py │ │ ├── transform_results.py │ │ ├── unified_attention_benchmark.py │ │ ├── vllm-fix.patch │ │ ├── vllm-kernels-pin.txt │ │ └── vllm-pin.txt ├── triton_kernels_benchmark │ ├── __init__.py │ ├── benchmark_shapes_parser.py │ ├── benchmark_testing.py │ ├── benchmark_utils.py │ ├── build_report.py │ ├── configs │ │ ├── __init__.py │ │ └── benchmark_config_templates.py │ ├── flash_attention_benchmark.py │ ├── flash_attention_tensor_desc_benchmark.py │ ├── flex_attention_benchmark_causal_mask.py │ ├── flex_attention_benchmark_custom_masks.py │ ├── fused_softmax.py │ ├── gemm_benchmark.py │ ├── gemm_postop_addmatrix_benchmark.py │ ├── gemm_postop_gelu_benchmark.py │ ├── gemm_preop_exp_benchmark.py │ ├── gemm_splitk_benchmark.py │ ├── gemm_streamk_benchmark.py │ ├── gemm_tensor_desc_benchmark.py │ ├── gemm_tensor_of_ptr_benchmark.py │ └── prefix_sums.py └── xetla_kernel │ ├── CMakeLists.txt │ ├── flash_attention │ ├── CMakeLists.txt │ ├── fmha_backward.h │ ├── fmha_backward_policy.h │ ├── fmha_forward_v5.h │ ├── fmha_policy_v2.h │ └── fmha_utils.h │ ├── gemm │ ├── CMakeLists.txt │ ├── gemm.h │ ├── gemm_config.hpp │ └── kernel_func.hpp │ ├── python_main.cpp │ ├── softmax │ ├── CMakeLists.txt │ ├── kernel_func.hpp │ ├── softmax.h │ └── softmax_config.hpp │ ├── split_k_gemm │ ├── CMakeLists.txt │ └── split_k_gemm.h │ ├── stream_k_gemm │ ├── CMakeLists.txt │ └── stream_k_gemm.h │ └── xetla-library.conf ├── bin ├── CMakeLists.txt ├── RegisterTritonDialects.h ├── triton-llvm-opt.cpp ├── triton-lsp.cpp ├── triton-opt.cpp ├── triton-reduce.cpp └── triton-tensor-layout.cpp ├── cmake ├── AddTritonUnitTest.cmake ├── FindLLVM.cmake ├── json-version.txt ├── llvm-hash.txt └── nvidia-toolchain-version.json ├── docs ├── ARCHITECTURE.md ├── BLOCK_LOADS_LAYOUT.md ├── Makefile ├── _static │ └── .gitkeep ├── _templates │ └── versions.html ├── backend │ ├── ldmatrixOperand0.svg │ └── ldmatrixOperand1.svg ├── conf.py ├── getting-started │ ├── architecture.rst │ ├── installation.rst │ ├── start.rst │ └── tutorials │ │ ├── grouped_vs_row_major_ordering.png │ │ ├── parallel_reduction.png │ │ └── random_bits.png ├── index.rst ├── meetups │ ├── 01-24-2024 │ │ └── notes.md │ ├── 02-20-2024 │ │ ├── Proton.pdf │ │ └── notes.md │ ├── 03-12-2025 │ │ └── notes.md │ ├── 04-02-2024 │ │ └── notes.md │ ├── 05-01-2025 │ │ └── notes.md │ ├── 05-07-2024 │ │ └── notes.md │ ├── 07-09-2025 │ │ └── notes.md │ ├── 07-18-2023 │ │ └── notes.md │ ├── 08-06-2024 │ │ └── notes.md │ ├── 08-22-2023 │ │ ├── amd-update.pdf │ │ ├── intel-xpu-update.pptx │ │ └── notes.md │ ├── 09-03-2025 │ │ └── notes.md │ ├── 10-25-2023 │ │ ├── intel-xpu-update.pdf │ │ ├── notes.md │ │ └── triton-shared.pptx │ ├── 11-05-2025 │ │ └── notes.md │ ├── 12-13-2023 │ │ └── notes.md │ ├── dev-meetup-2023.md │ ├── dev_conference_2024.md │ └── for_moderators │ │ └── README.md ├── pics │ ├── encoding.png │ ├── execution_model.png │ ├── load_store.png │ ├── memory-hierarchy.png │ ├── perf-benchmark.png │ ├── prog-model.png │ ├── pt2.png │ ├── shared1.png │ ├── shared2.png │ └── triton.png ├── programming-guide │ ├── chapter-1 │ │ ├── cuda-parallel-matmul.png │ │ ├── introduction.rst │ │ └── triton-parallel-matmul.png │ ├── chapter-2 │ │ ├── halide-iteration.png │ │ ├── polyhedral-iteration.png │ │ └── related-work.rst │ └── chapter-3 │ │ ├── debugging.rst │ │ └── profiling.rst ├── python-api │ ├── triton-semantics.rst │ ├── triton.language.extra.cuda.rst │ ├── triton.language.rst │ ├── triton.rst │ └── triton.testing.rst ├── requirements.txt └── update_sycl_libdevice.md ├── include ├── CMakeLists.txt └── triton │ ├── Analysis │ ├── Alias.h │ ├── Allocation.h │ ├── AxisInfo.h │ ├── Membar.h │ └── Utility.h │ ├── CMakeLists.txt │ ├── Conversion │ ├── CMakeLists.txt │ ├── MLIRTypes.h │ ├── TritonGPUToLLVM │ │ ├── AllocateSharedMemoryUtility.h │ │ ├── AsmFormat.h │ │ ├── CMakeLists.txt │ │ ├── ElementwiseOpToLLVMBase.h │ │ ├── FMADotUtility.h │ │ ├── Passes.h │ │ ├── Passes.td │ │ ├── PatternTritonGPUOpToLLVM.h │ │ ├── TargetInfoBase.h │ │ ├── TypeConverter.h │ │ └── Utility.h │ └── TritonToTritonGPU │ │ ├── CMakeLists.txt │ │ ├── Passes.h │ │ └── Passes.td │ ├── Dialect │ ├── CMakeLists.txt │ ├── Gluon │ │ ├── CMakeCache.txt │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Dialect.h │ │ │ ├── GluonAttrDefs.td │ │ │ ├── GluonDialect.td │ │ │ └── GluonOps.td │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ ├── InferLayoutUtils.h │ │ │ ├── Passes.h │ │ │ └── Passes.td │ ├── Triton │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Dialect.h │ │ │ ├── DiscardableAttributes.h │ │ │ ├── Interfaces.h │ │ │ ├── OpInterfaces.h │ │ │ ├── Traits.h │ │ │ ├── TritonAttrDefs.td │ │ │ ├── TritonDialect.td │ │ │ ├── TritonInterfaces.td │ │ │ ├── TritonOpInterfaces.td │ │ │ ├── TritonOps.td │ │ │ ├── TritonTypes.td │ │ │ ├── Types.h │ │ │ └── Utility.h │ │ └── Transforms │ │ │ ├── ArithTypeConversion.h │ │ │ ├── CMakeLists.txt │ │ │ ├── FunctionTypeConversion.h │ │ │ ├── LoopPeeling.h │ │ │ ├── Passes.h │ │ │ └── Passes.td │ ├── TritonGPU │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── Attributes.h │ │ │ ├── CMakeLists.txt │ │ │ ├── CTAEncodingAttr.h │ │ │ ├── CTAEncodingAttr.td │ │ │ ├── Dialect.h │ │ │ ├── LinearLayoutConversions.h │ │ │ ├── Traits.h │ │ │ ├── TritonGPUAttrBase.td │ │ │ ├── TritonGPUAttrDefs.td │ │ │ ├── TritonGPUAttrImpls.td │ │ │ ├── TritonGPUDialect.td │ │ │ ├── TritonGPUInterfaces.h │ │ │ ├── TritonGPUOpInterfaces.td │ │ │ ├── TritonGPUOps.td │ │ │ ├── TritonGPUTypeInterfaces.td │ │ │ ├── TritonGPUTypes.td │ │ │ └── Types.h │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ ├── CoalesceUtils.h │ │ │ ├── DecomposeScaledBlocked.h │ │ │ ├── LayoutPropagationUtility.h │ │ │ ├── MMAv5PipelineUtility.h │ │ │ ├── Partition.h │ │ │ ├── PartitionBuilder.h │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ ├── PipelineExpander.h │ │ │ ├── PipeliningUtility.h │ │ │ ├── Schedule.h │ │ │ ├── TritonGPUConversion.h │ │ │ ├── Utility.h │ │ │ └── WarpSpecialization.h │ ├── TritonInstrument │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Dialect.h │ │ │ ├── FunctionBuilder.h │ │ │ ├── TritonInstrument.md │ │ │ ├── TritonInstrumentAttrDefs.td │ │ │ ├── TritonInstrumentDialect.td │ │ │ ├── TritonInstrumentOps.td │ │ │ └── Utility.h │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ ├── Passes.h │ │ │ └── Passes.td │ └── TritonNvidiaGPU │ │ ├── CMakeLists.txt │ │ ├── IR │ │ ├── CMakeLists.txt │ │ ├── Dialect.h │ │ ├── TensorMemoryUtils.h │ │ ├── TritonNvidiaGPUAttrDefs.td │ │ ├── TritonNvidiaGPUDialect.td │ │ ├── TritonNvidiaGPUOpInterfaces.td │ │ └── TritonNvidiaGPUOps.td │ │ └── Transforms │ │ ├── CMakeLists.txt │ │ ├── Passes.h │ │ ├── Passes.td │ │ └── TMAUtilities.h │ ├── Target │ ├── CMakeLists.txt │ └── LLVMIR │ │ ├── CMakeLists.txt │ │ ├── Passes.h │ │ └── Passes.td │ └── Tools │ ├── GenericSwizzling.h │ ├── LayoutUtils.h │ ├── LinearLayout.h │ ├── PluginUtils.h │ ├── StrUtil.h │ └── Sys │ └── GetEnv.hpp ├── lib ├── Analysis │ ├── Alias.cpp │ ├── Allocation.cpp │ ├── AxisInfo.cpp │ ├── CMakeLists.txt │ ├── Membar.cpp │ └── Utility.cpp ├── CMakeLists.txt ├── Conversion │ ├── CMakeLists.txt │ ├── TritonGPUToLLVM │ │ ├── AllocateSharedMemory.cpp │ │ ├── AllocateSharedMemoryUtility.cpp │ │ ├── AllocateWarpGroups.cpp │ │ ├── AssertOpToLLVM.cpp │ │ ├── CMakeLists.txt │ │ ├── ControlFlowOpToLLVM.cpp │ │ ├── ConvertLayoutOpToLLVM.cpp │ │ ├── DotOpToLLVM │ │ │ ├── FMA.cpp │ │ │ └── FMADotUtility.cpp │ │ ├── ElementwiseOpToLLVM.cpp │ │ ├── FuncOpToLLVM.cpp │ │ ├── GatherOpToLLVM.cpp │ │ ├── GlobalScratchMemoryAllocation.cpp │ │ ├── HistogramOpToLLVM.cpp │ │ ├── MakeRangeOpToLLVM.cpp │ │ ├── MemoryOpToLLVM.cpp │ │ ├── PrintOpToLLVM.cpp │ │ ├── ReduceOpToLLVM.cpp │ │ ├── ReduceScanCommon.h │ │ ├── SPMDOpToLLVM.cpp │ │ ├── ScanOpToLLVM.cpp │ │ ├── TypeConverter.cpp │ │ ├── Utility.cpp │ │ └── ViewOpToLLVM.cpp │ ├── TritonInstrumentToLLVM │ │ ├── CMakeLists.txt │ │ └── InstrumentationToLLVM.cpp │ └── TritonToTritonGPU │ │ ├── CMakeLists.txt │ │ ├── RelayoutTritonGPU.cpp │ │ ├── TritonGPUConversion.cpp │ │ └── TritonToTritonGPUPass.cpp ├── Dialect │ ├── CMakeLists.txt │ ├── Gluon │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ └── Dialect.cpp │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ ├── Canonicalize.cpp │ │ │ ├── InferCoalescedEncodings.cpp │ │ │ ├── InferLayoutUtils.cpp │ │ │ ├── Inline.cpp │ │ │ ├── ResolveAutoEncodings.cpp │ │ │ └── SimplifyControlFlow.cpp │ ├── Triton │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Canonicalize.td │ │ │ ├── Dialect.cpp │ │ │ ├── DiscardableAttributes.cpp │ │ │ ├── OpInterfaces.cpp │ │ │ ├── Ops.cpp │ │ │ ├── Traits.cpp │ │ │ ├── Types.cpp │ │ │ └── Utility.cpp │ │ └── Transforms │ │ │ ├── ArithTypeConversion.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── Combine.cpp │ │ │ ├── Combine.td │ │ │ ├── FunctionTypeConversion.cpp │ │ │ ├── LoopAwareCSE.cpp │ │ │ ├── LoopInvariantCodeMotion.cpp │ │ │ ├── LoopPeeling.cpp │ │ │ ├── LoopUnroll.cpp │ │ │ ├── ReorderBroadcast.cpp │ │ │ ├── RewriteTensorDescriptorToPointer.cpp │ │ │ └── RewriteTensorPointer.cpp │ ├── TritonGPU │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Dialect.cpp │ │ │ ├── LinearLayoutConversions.cpp │ │ │ ├── Ops.cpp │ │ │ └── Types.cpp │ │ └── Transforms │ │ │ ├── AccelerateMatmul.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── Coalesce.cpp │ │ │ ├── CoalesceAsyncCopy.cpp │ │ │ ├── CoalesceUtils.cpp │ │ │ ├── CombineTensorSelectAndIf.cpp │ │ │ ├── DecomposeScaledBlocked.cpp │ │ │ ├── F32DotTC.cpp │ │ │ ├── FuseNestedLoops.cpp │ │ │ ├── HoistTMEMAlloc.cpp │ │ │ ├── LayoutPropagationUtility.cpp │ │ │ ├── OptimizeAccumulatorInit.cpp │ │ │ ├── OptimizeDotOperands.cpp │ │ │ ├── OptimizeThreadLocality.cpp │ │ │ ├── Pipeliner │ │ │ ├── AssignLatencies.cpp │ │ │ ├── LowerLoops.cpp │ │ │ ├── MMAv5PipelineUtility.cpp │ │ │ ├── PipelineExpander.cpp │ │ │ ├── PipeliningUtility.cpp │ │ │ ├── Schedule.cpp │ │ │ ├── ScheduleLoops.cpp │ │ │ ├── SoftwarePipeliner.cpp │ │ │ ├── TMAStoresPipeline.cpp │ │ │ ├── TestPipelineLowerLoop.cpp │ │ │ └── WGMMAPipeline.cpp │ │ │ ├── Prefetch.cpp │ │ │ ├── ReduceDataDuplication.cpp │ │ │ ├── RemoveLayoutConversions.cpp │ │ │ ├── ReorderInstructions.cpp │ │ │ ├── Utility.cpp │ │ │ └── WarpSpecialization │ │ │ ├── AutomaticWarpSpecialization.cpp │ │ │ ├── OptimizePartitionWarps.cpp │ │ │ ├── Partition.cpp │ │ │ ├── PartitionBuilder.cpp │ │ │ ├── PartitionLoops.cpp │ │ │ └── PartitionScheduling.cpp │ ├── TritonInstrument │ │ ├── CMakeLists.txt │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Dialect.cpp │ │ │ ├── FunctionBuilder.cpp │ │ │ ├── Ops.cpp │ │ │ └── Utility.cpp │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ └── ConcurrencySanitizer.cpp │ └── TritonNvidiaGPU │ │ ├── CMakeLists.txt │ │ ├── IR │ │ ├── CMakeLists.txt │ │ ├── Dialect.cpp │ │ ├── Ops.cpp │ │ └── TensorMemoryUtils.cpp │ │ └── Transforms │ │ ├── CMakeLists.txt │ │ ├── CheckMatmulTwoCTAs.cpp │ │ ├── FenceInsertion.cpp │ │ ├── InterleaveTMem.cpp │ │ ├── MMALowering.cpp │ │ ├── OptimizeDescriptorEncoding.cpp │ │ ├── OptimizeTMemLayouts.cpp │ │ ├── PlanCTA.cpp │ │ ├── PromoteLHSToTMem.cpp │ │ ├── ProxFenceInsertion.cpp │ │ ├── RemoveTMEMTokens.cpp │ │ ├── TMALowering.cpp │ │ ├── TMAUtilities.cpp │ │ └── TensorMemoryAllocation.cpp ├── Plugins │ ├── CMakeLists.txt │ ├── Passes.td │ ├── README.md │ └── TritonPlugin.cpp ├── Target │ ├── CMakeLists.txt │ └── LLVMIR │ │ ├── CMakeLists.txt │ │ ├── LLVMDILocalVariable.cpp │ │ ├── LLVMDIScope.cpp │ │ ├── LLVMIRBreakPhiStruct.cpp │ │ └── LLVMPasses.h └── Tools │ ├── CMakeLists.txt │ ├── GenericSwizzling.cpp │ ├── LayoutUtils.cpp │ ├── LinearLayout.cpp │ └── PluginUtils.cpp ├── pyproject.toml ├── python ├── build_helpers.py ├── examples │ └── gluon │ │ └── 01-attention-forward.py ├── requirements.txt ├── src │ ├── gluon_ir.cc │ ├── interpreter.cc │ ├── ir.cc │ ├── ir.h │ ├── linear_layout.cc │ ├── llvm.cc │ ├── main.cc │ ├── passes.cc │ ├── passes.h │ └── specialize.cc ├── test-requirements.txt ├── test │ ├── backend │ │ ├── extension_backend.c │ │ ├── test_device_backend.py │ │ ├── test_mir_stage.py │ │ └── test_stages_inspection.py │ ├── conftest.py │ ├── gluon │ │ ├── test_consan.py │ │ ├── test_core.py │ │ ├── test_frontend.py │ │ └── test_lowerings.py │ ├── kernel_comparison │ │ └── kernels.yml │ ├── microbenchmark │ │ └── launch_overhead.py │ ├── regression │ │ ├── test_cast_matmul.py │ │ └── test_functional_regressions.py │ └── unit │ │ ├── cuda │ │ ├── __init__.py │ │ ├── test_libdevice.py │ │ ├── test_mixed_io.py │ │ ├── test_tensor_descriptor.py │ │ ├── test_tma_descriptor.py │ │ └── test_tma_store_gemm.py │ │ ├── instrumentation │ │ └── test_gpuhello.py │ │ ├── intel │ │ ├── __init__.py │ │ ├── block_load_helper.py │ │ ├── helion795.py │ │ ├── test_block_io.py │ │ ├── test_block_load.py │ │ ├── test_conversions.py │ │ ├── test_core.py │ │ ├── test_driver.py │ │ ├── test_mxfp_matmul.py │ │ ├── test_native_code_generation.py │ │ └── test_regressions.py │ │ ├── language │ │ ├── print_helper.py │ │ ├── test_annotations.py │ │ ├── test_block_pointer.py │ │ ├── test_compile_errors.py │ │ ├── test_compile_only.py │ │ ├── test_conversions.py │ │ ├── test_core.py │ │ ├── test_decorator.py │ │ ├── test_frontend.py │ │ ├── test_libdevice.py │ │ ├── test_line_info.py │ │ ├── test_matmul.py │ │ ├── test_module.py │ │ ├── test_mxfp.py │ │ ├── test_pipeliner.py │ │ ├── test_random.py │ │ ├── test_reproducer.py │ │ ├── test_standard.py │ │ ├── test_subprocess.py │ │ ├── test_tensor_descriptor.py │ │ ├── test_tuple.py │ │ └── test_warp_specialization.py │ │ ├── plugins │ │ ├── custom_stages.py │ │ └── test_plugin.py │ │ ├── runtime │ │ ├── test_autotuner.py │ │ ├── test_bindings.py │ │ ├── test_blaslt.py │ │ ├── test_build.py │ │ ├── test_cache.py │ │ ├── test_compilation_listener.py │ │ ├── test_driver.py │ │ ├── test_launch.py │ │ ├── test_specialize.py │ │ └── test_subproc.py │ │ ├── test_debug.py │ │ ├── test_debug_dump.py │ │ ├── test_debug_kernels.py │ │ ├── test_debuginfo.py │ │ ├── test_filecheck.py │ │ ├── test_knobs.py │ │ ├── test_link.py │ │ ├── test_perf_warning.py │ │ └── tools │ │ ├── test_aot.py │ │ ├── test_disasm.py │ │ ├── test_irsource.py │ │ ├── test_linear_layout.py │ │ └── test_triton_to_gluon.py ├── triton │ ├── _C │ │ └── libtriton │ │ │ └── linear_layout.pyi │ ├── __init__.py │ ├── _filecheck.py │ ├── _internal_testing.py │ ├── _utils.py │ ├── backends │ │ ├── __init__.py │ │ ├── compiler.py │ │ └── driver.py │ ├── compiler │ │ ├── __init__.py │ │ ├── code_generator.py │ │ ├── compiler.py │ │ ├── errors.py │ │ └── make_launcher.py │ ├── errors.py │ ├── experimental │ │ ├── __init__.py │ │ └── gluon │ │ │ ├── __init__.py │ │ │ ├── _compiler.py │ │ │ ├── _runtime.py │ │ │ ├── amd │ │ │ ├── __init__.py │ │ │ └── gfx1250.py │ │ │ ├── language │ │ │ ├── __init__.py │ │ │ ├── _core.py │ │ │ ├── _layouts.py │ │ │ ├── _math.py │ │ │ ├── _semantic.py │ │ │ ├── _standard.py │ │ │ ├── amd │ │ │ │ ├── __init__.py │ │ │ │ ├── _layouts.py │ │ │ │ ├── _ops.py │ │ │ │ ├── cdna3 │ │ │ │ │ └── __init__.py │ │ │ │ ├── cdna4 │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── async_copy.py │ │ │ │ ├── gfx1250 │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── async_copy.py │ │ │ │ │ ├── mbarrier.py │ │ │ │ │ └── tdm.py │ │ │ │ ├── rdna3 │ │ │ │ │ └── __init__.py │ │ │ │ └── rdna4 │ │ │ │ │ └── __init__.py │ │ │ ├── extra │ │ │ │ └── __init__.py │ │ │ ├── intel │ │ │ │ ├── __init__.py │ │ │ │ └── _layouts.py │ │ │ └── nvidia │ │ │ │ ├── __init__.py │ │ │ │ ├── ampere │ │ │ │ ├── __init__.py │ │ │ │ ├── async_copy.py │ │ │ │ └── mbarrier.py │ │ │ │ ├── blackwell │ │ │ │ ├── __init__.py │ │ │ │ ├── float2.py │ │ │ │ └── tma.py │ │ │ │ └── hopper │ │ │ │ ├── __init__.py │ │ │ │ ├── mbarrier.py │ │ │ │ └── tma.py │ │ │ └── nvidia │ │ │ ├── __init__.py │ │ │ ├── blackwell.py │ │ │ └── hopper.py │ ├── knobs.py │ ├── language │ │ ├── __init__.py │ │ ├── core.py │ │ ├── extra │ │ │ ├── __init__.py │ │ │ └── libdevice.py │ │ ├── math.py │ │ ├── random.py │ │ ├── semantic.py │ │ ├── standard.py │ │ └── target_info.py │ ├── runtime │ │ ├── __init__.py │ │ ├── _allocation.py │ │ ├── _async_compile.py │ │ ├── autotuner.py │ │ ├── build.py │ │ ├── cache.py │ │ ├── driver.py │ │ ├── errors.py │ │ ├── interpreter.py │ │ └── jit.py │ ├── testing.py │ └── tools │ │ ├── __init__.py │ │ ├── build_extern.py │ │ ├── compile.py │ │ ├── disasm.py │ │ ├── link.py │ │ ├── mxfp.py │ │ ├── ragged_tma.py │ │ ├── tensor_descriptor.py │ │ └── triton_to_gluon_translater │ │ ├── translator.py │ │ └── translator_helpers.py ├── triton_kernels │ ├── .gitignore │ ├── bench │ │ ├── bench_mlp.py │ │ ├── bench_utils.py │ │ └── distributed.py │ ├── pyproject.toml │ ├── tests │ │ ├── __init__.py │ │ ├── conftest.py │ │ ├── test_compaction.py │ │ ├── test_distributed.py │ │ ├── test_matmul.py │ │ ├── test_matmul_details │ │ │ └── test_opt_flags_split_k.py │ │ ├── test_mxfp.py │ │ ├── test_reduce.py │ │ ├── test_specialize.py │ │ ├── test_swiglu.py │ │ ├── test_tensor.py │ │ ├── test_tensor_details │ │ │ ├── test_layout_blackwell.py │ │ │ ├── test_layout_cdna4.py │ │ │ └── test_layout_hopper.py │ │ └── test_topk.py │ └── triton_kernels │ │ ├── __init__.py │ │ ├── compaction.py │ │ ├── compaction_details │ │ └── _masked_compaction.py │ │ ├── distributed.py │ │ ├── matmul.py │ │ ├── matmul_details │ │ ├── _common.py │ │ ├── _matmul.py │ │ ├── _p_matmul.py │ │ ├── opt_flags.py │ │ └── opt_flags_details │ │ │ ├── opt_flags_amd.py │ │ │ ├── opt_flags_intel.py │ │ │ └── opt_flags_nvidia.py │ │ ├── numerics.py │ │ ├── numerics_details │ │ ├── __init__.py │ │ ├── flexpoint.py │ │ ├── mxfp.py │ │ └── mxfp_details │ │ │ ├── _downcast_to_mxfp.py │ │ │ └── _upcast_from_mxfp.py │ │ ├── proton_opts.py │ │ ├── reduce.py │ │ ├── roofline.py │ │ ├── specialize.py │ │ ├── swiglu.py │ │ ├── swiglu_details │ │ └── _swiglu.py │ │ ├── target_info.py │ │ ├── tensor.py │ │ ├── tensor_details │ │ ├── bitmatrix.py │ │ ├── bitmatrix_details │ │ │ └── sum_bitmatrix_rows.py │ │ ├── layout.py │ │ ├── layout_details │ │ │ ├── base.py │ │ │ ├── blackwell_scale.py │ │ │ ├── blackwell_value.py │ │ │ ├── cdna4_scale.py │ │ │ ├── hopper_scale.py │ │ │ ├── hopper_value.py │ │ │ └── strided.py │ │ └── ragged_tensor.py │ │ ├── testing.py │ │ ├── topk.py │ │ └── topk_details │ │ ├── __init__.py │ │ ├── _topk_backward.py │ │ └── _topk_forward.py └── tutorials │ ├── 01-vector-add.py │ ├── 02-fused-softmax.py │ ├── 03-matrix-multiplication.py │ ├── 04-low-memory-dropout.py │ ├── 05-layer-norm.py │ ├── 06-fused-attention.py │ ├── 07-extern-functions.py │ ├── 08-grouped-gemm.py │ ├── 09-persistent-matmul.py │ ├── 10-block-scaled-matmul.py │ ├── 10-experimental-block-pointer.py │ ├── 11-programmatic-dependent-launch.py │ ├── README.rst │ └── gluon │ ├── 01-intro.py │ ├── 02-layouts.py │ ├── 03-async-copy.py │ ├── 04-tma.py │ ├── 05-wgmma.py │ ├── 06-tcgen05.py │ ├── 07-persistence.py │ └── 08-warp-specialization.py ├── scripts ├── automate_skiplist.sh ├── basekit.yml ├── build-llvm-project.sh ├── build_pti_data │ ├── CMakeLists.txt │ ├── README.md │ └── pyproject.toml ├── capture-hw-details.sh ├── check-update-translator-cid.sh ├── check_inductor_report.py ├── compare-ci-runs │ ├── README.md │ ├── compare_runs.py │ └── requirements.txt ├── compile-triton.sh ├── docs-triton.sh ├── e2e_checks │ ├── aggregate_e2e_results.py │ └── compare_reference.sh ├── flash_attention.py ├── get_failed_cases.py ├── inductor_xpu_test.sh ├── install-pti.sh ├── install-pytorch.sh ├── llvm_igc_debug.sh ├── pass_rate.py ├── patch-pytorch.sh ├── pti_lib.py ├── pytest-utils.sh ├── requirements-test.txt ├── run_tutorial.py ├── skiplist │ ├── .gitignore │ ├── a770 │ │ ├── .gitkeep │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── intel.txt │ │ ├── interpreter.txt │ │ ├── language.txt │ │ ├── mxfp.txt │ │ ├── scaled_dot.txt │ │ ├── subprocess.txt │ │ ├── tools.txt │ │ ├── triton_kernels.txt │ │ └── tutorials.txt │ ├── arl-h │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── intel.txt │ │ ├── interpreter.txt │ │ ├── language.txt │ │ ├── mxfp.txt │ │ ├── scaled_dot.txt │ │ ├── subprocess.txt │ │ ├── triton_kernels.txt │ │ └── tutorials.txt │ ├── arl-s │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── intel.txt │ │ ├── interpreter.txt │ │ ├── language.txt │ │ ├── mxfp.txt │ │ ├── scaled_dot.txt │ │ ├── subprocess.txt │ │ ├── triton_kernels.txt │ │ └── tutorials.txt │ ├── default │ │ ├── .gitkeep │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── language.txt │ │ └── triton_kernels.txt │ ├── lts │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── language.txt │ │ └── triton_kernels.txt │ ├── mtl │ │ ├── .gitkeep │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── language.txt │ │ ├── scaled_dot.txt │ │ ├── triton_kernels.txt │ │ └── tutorials.txt │ └── xe2 │ │ ├── .gitkeep │ │ ├── debug.txt │ │ ├── gluon.txt │ │ ├── language.txt │ │ ├── tools.txt │ │ ├── triton_kernels.txt │ │ └── tutorials.txt ├── sycl_rt_lib.py ├── test-pytorch.sh ├── test-triton.sh ├── test_pass_rate.py ├── torch_cmake.py ├── triton-opt.sh ├── triton-version.sh └── triton.yml ├── setup.py ├── test ├── Analysis │ ├── amd │ │ └── test-alignment.mlir │ ├── intel │ │ └── test-axis-info.mlir │ ├── test-alias.mlir │ ├── test-alignment.mlir │ ├── test-allocation.mlir │ ├── test-liveness.mlir │ ├── test-membar-ttng.mlir │ └── test-membar.mlir ├── CMakeLists.txt ├── Conversion │ ├── allocate_shared_memory.mlir │ ├── allocate_warp_groups.mlir │ ├── amd │ │ ├── allocate_shared_memory.mlir │ │ ├── amdgpu_membar.mlir │ │ ├── async-ops-alias-scopes.mlir │ │ ├── async_ops_to_llvm.mlir │ │ ├── async_ops_to_llvm_gfx1250.mlir │ │ ├── async_ops_to_llvm_invalid.mlir │ │ ├── buffer_atomic_cas.mlir │ │ ├── buffer_load_store.mlir │ │ ├── buffer_load_to_local_to_llvm.mlir │ │ ├── builtin_func_to_llvm.mlir │ │ ├── cluster_load.mlir │ │ ├── compute-base-ptr.mlir │ │ ├── convert_layout.mlir │ │ ├── dedup-by-constancy.mlir │ │ ├── ds_transpose.mlir │ │ ├── ds_transpose_gfx1250.mlir │ │ ├── fp_to_fp.mlir │ │ ├── in_thread_transpose.mlir │ │ ├── invalid_concat_op.mlir │ │ ├── invalid_extractslice_to_llvm.mlir │ │ ├── load_store.mlir │ │ ├── math-denorm-handling.mlir │ │ ├── mbarrier_ops_to_llvm_gfx1250.mlir │ │ ├── mfma-shortcut.mlir │ │ ├── minmax.mlir │ │ ├── tritongpu_tdm_to_llvm.mlir │ │ ├── tritongpu_to_llvm.mlir │ │ ├── tritongpu_to_llvm_rdna.mlir │ │ ├── tritongpu_wmma_dot_scaled_to_llvm.mlir │ │ ├── tritongpu_wmma_dot_to_llvm.mlir │ │ ├── upcast_mxfp.mlir │ │ ├── wmma-v1-shortcut.mlir │ │ └── wmma-v2-shortcut.mlir │ ├── atomic_ldst.mlir │ ├── cvt_to_llvm.mlir │ ├── dedup-by-constancy.mlir │ ├── divide-by-0.mlir │ ├── intel │ │ ├── arith_to_llvm.mlir │ │ ├── dot_layout_offset.mlir │ │ ├── dpas_to_block_layout_convert.mlir │ │ ├── intel-allocate-shared-memory.mlir │ │ ├── load_store_to_llvm.mlir │ │ ├── shared_to_dot_layout_convert.mlir │ │ ├── sub-group-shuffle.mlir │ │ ├── sub-group-transpose.mlir │ │ ├── tritongpu_to_gen.mlir │ │ ├── tritongpu_to_gen_dot.mlir │ │ └── tritonintelgpu_to_llvm.mlir │ ├── nvgpu_to_llvm.mlir │ ├── reduce_to_llvm.mlir │ ├── relayout_tritongpu.mlir │ ├── scan_to_llvm.mlir │ ├── tma_to_llvm.mlir │ ├── triton_to_tritongpu.mlir │ ├── tritongpu_to_llvm.mlir │ ├── tritongpu_to_llvm_blackwell.mlir │ ├── tritongpu_to_llvm_block_dot_shortcut.mlir │ ├── tritongpu_to_llvm_debug.mlir │ ├── tritongpu_to_llvm_hopper.mlir │ ├── tritongpu_to_llvm_hopper_ptx80.mlir │ ├── tritongpu_to_llvm_sm120.mlir │ ├── tritongpu_to_llvm_volta.mlir │ ├── tritongpu_to_ptx.mlir │ ├── tritongpu_to_ptx_mmav3.mlir │ ├── tritoninstrument_to_llvm.mlir │ ├── tritonnvidiagpu_to_llvm.mlir │ └── warp_specialize_to_llvm.mlir ├── Gluon │ ├── auto_encoding.mlir │ ├── infer_coalesced_encoding.mlir │ ├── inlining.mlir │ ├── invalid_auto_encoding.mlir │ └── invalid_infer_coalesced_encoding.mlir ├── Hopper │ ├── CMakeLists.txt │ └── WarpSpecialization │ │ ├── ws_code_partition.mlir │ │ ├── ws_data_partition.mlir │ │ ├── ws_task_id_propagation.mlir │ │ └── ws_task_partition.mlir ├── LLVMIR │ ├── break-phi-struct.ll │ ├── convert-to-llvmir-with-dbg-info.mlir │ ├── freeze-masked-div-rem.ll │ └── insert-dbg-intrinsic.mlir ├── NVWS │ ├── aref-tmem-insertion.mlir │ ├── assign_stage_phase.mlir │ ├── insert_aref.mlir │ ├── invalid.mlir │ ├── lower_aref.mlir │ ├── lower_warp_group.mlir │ └── ops.mlir ├── Plugins │ └── test-plugin.mlir ├── Proton │ ├── allocate_global_scratch_buffer.mlir │ ├── allocate_shared_memory.mlir │ ├── amd │ │ ├── add_sched_barriers.mlir │ │ └── protongpu_to_llvm.mlir │ ├── nvidia │ │ └── protongpu_to_llvm.mlir │ ├── ops.mlir │ ├── proton_to_protongpu.mlir │ ├── protongpu_transforms.mlir │ └── scope_id.mlir ├── Target │ └── LLVMIR │ │ └── triton-gen.mlir ├── Tools │ └── tensor_layout_print.mlir ├── Triton │ ├── Intel │ │ ├── FuseReshape │ │ │ └── fuse-reshape.mlir │ │ ├── RemoveBoundaryChecks │ │ │ └── remove-boundary-checks.mlir │ │ ├── RemoveMasks │ │ │ ├── loop-canonical-masks.mlir │ │ │ ├── loop-invariant-masks.mlir │ │ │ ├── regressions.mlir │ │ │ └── unnecessary-masks.mlir │ │ ├── StrideVersioning │ │ │ └── stride-versioning.mlir │ │ └── TensorDescToBlockPointer │ │ │ ├── basic.mlir │ │ │ ├── invalid.mlir │ │ │ └── loop.mlir │ ├── canonicalize.mlir │ ├── combine.mlir │ ├── invalid.mlir │ ├── loop-invariant-code-motion.mlir │ ├── loop-peeling.mlir │ ├── loop-unroll.mlir │ ├── loop_cse.mlir │ ├── ops.mlir │ ├── reorder-broadcast.mlir │ ├── reproducer.mlir │ ├── rewrite-tensor-descriptor-to-pointer.mlir │ ├── rewrite-tensor-pointer.mlir │ ├── vecadd.mlir │ └── verify-make-range.mlir ├── TritonGEN │ ├── tritongen-2Dblockload-to-llvm-asserts.mlir │ ├── tritongen-2Dblockload-to-llvm.mlir │ ├── tritongen-2Dblockprefetch-to-llvm.mlir │ ├── tritongen-2Dblockstore-to-llvm.mlir │ ├── tritongen-invalid.mlir │ ├── tritongen-to-llvm.mlir │ ├── tritongen-to-spirv.mlir │ └── tritongen.mlir ├── TritonGPU │ ├── accelerate-matmul.mlir │ ├── accumulator-init.mlir │ ├── amd │ │ ├── accelerate-amd-matmul-chain-dot.mlir │ │ ├── accelerate-amd-matmul-fma.mlir │ │ ├── accelerate-amd-matmul-mfma-decompose-scaled-dot.mlir │ │ ├── accelerate-amd-matmul-mfma-gfx950.mlir │ │ ├── accelerate-amd-matmul-mfma.mlir │ │ ├── accelerate-amd-matmul-wmma-gen1.mlir │ │ ├── accelerate-amd-matmul-wmma-gen2.mlir │ │ ├── accelerate-amd-matmul-wmma-gfx1250.mlir │ │ ├── amd-block-pingpong-chained-dots.mlir │ │ ├── amd-block-pingpong.mlir │ │ ├── amd-canonicalize-extract-slice.mlir │ │ ├── amd-canonicalize-pointers-dont-run-mlir-canonicalizer.mlir │ │ ├── amd-canonicalize-pointers-no-large-tensor.mlir │ │ ├── amd-canonicalize-pointers.mlir │ │ ├── amd-coalesce-async-copy.mlir │ │ ├── amd-concat-op.mlir │ │ ├── amd-conditional-barrier.mlir │ │ ├── amd-convert-buffer-ops-range-analysis.mlir │ │ ├── amd-convert-buffer-ops-small-tensor.mlir │ │ ├── amd-convert-buffer-ops.mlir │ │ ├── amd-extractslice-op.mlir │ │ ├── amd-fold-true-cmpi.mlir │ │ ├── amd-hoist-cvtToDotOp.mlir │ │ ├── amd-optimize-dot-operands.mlir │ │ ├── amd-optimize-epilogue.mlir │ │ ├── amd-pipeline-chained-dots.mlir │ │ ├── amd-range-analysis.mlir │ │ ├── amd-reorder-instructions.mlir │ │ ├── amd-schedule-hint.mlir │ │ ├── amd-stream-lds-layout-selection.mlir │ │ ├── amd-stream-loop-assume.mlir │ │ ├── amd-update-async-wait-count-without-token.mlir │ │ ├── amd-update-async-wait-count.mlir │ │ ├── in-thread-transpose.mlir │ │ ├── invalid.mlir │ │ ├── mfma-double-rate.mlir │ │ ├── mfma-xf32.mlir │ │ ├── optimize-lds-usage.mlir │ │ └── sink-setprio-mfma.mlir │ ├── atomic-cas.mlir │ ├── automatic-warp-specialization.mlir │ ├── bf16x3-matmul.mlir │ ├── canonicalize.mlir │ ├── coalesce-async-copy.mlir │ ├── coalesce.mlir │ ├── combine-select-if.mlir │ ├── combine.mlir │ ├── consan-negative.mlir │ ├── consan.mlir │ ├── dot-operands.mlir │ ├── fence-inserstion.mlir │ ├── fuse-nested-loops.mlir │ ├── global_scratch_alloc.mlir │ ├── global_scratch_to_llvm.mlir │ ├── hoist-tmem-alloc.mlir │ ├── inline.mlir │ ├── invalid-attributes.mlir │ ├── invalid.mlir │ ├── loop-pipeline-async-latencies.mlir │ ├── loop-pipeline-blackwell.mlir │ ├── loop-pipeline-combine-waits.mlir │ ├── loop-pipeline-cuda.mlir │ ├── loop-pipeline-expand.mlir │ ├── loop-pipeline-hip.mlir │ ├── loop-pipeline-hopper-remove-wait.mlir │ ├── loop-pipeline-hopper.mlir │ ├── loop-pipeline-indirect-load.mlir │ ├── loop-pipeline.mlir │ ├── loop-schedule.mlir │ ├── matmul-loop-pipeline.mlir │ ├── matmul.mlir │ ├── memdesc-subview-split.mlir │ ├── ops.mlir │ ├── optimize-locality.mlir │ ├── optimize-partition-warps.mlir │ ├── optimize_epilogue.mlir │ ├── partition-loops.mlir │ ├── partition-scheduling.mlir │ ├── pipeline-assign-latencies.mlir │ ├── pipeline-loop-nest.mlir │ ├── pipeline-lower-loop.mlir │ ├── pipeline-schedule-loop.mlir │ ├── prefetch.mlir │ ├── promote-lhs-to-tmem.mlir │ ├── prox_fence_insertion.mlir │ ├── reduce-data-duplication.mlir │ ├── reorder-instructions.mlir │ ├── samples │ │ ├── descriptor-matmul-pipeline.mlir │ │ ├── descriptor-matmul-pipeline.mlir.in │ │ ├── simulated-grouped-gemm.mlir │ │ └── simulated-grouped-gemm.mlir.in │ ├── tf32x3-matmul.mlir │ └── verify-blocked-layout.mlir ├── TritonIntelGPU │ ├── accelerate-matmul-ats.mlir │ ├── accelerate-matmul-pvc.mlir │ ├── atomic_cas.mlir │ ├── backward_combine_dpas_dot_layout.mlir │ ├── blockptr_load.mlir │ ├── blockptr_store.mlir │ ├── coalesce.mlir │ ├── combine.mlir │ ├── dot-operands.mlir │ ├── fp4tofp.mlir │ ├── loop-pipeline.mlir │ ├── materialize-block-pointer.mlir │ ├── optimize-reduction.mlir │ ├── pipeline-assign-latencies.mlir │ ├── prefetch-to-llvm.mlir │ ├── reduce-variable-liveness.mlir │ ├── remove_layout_conversions_5124.mlir │ ├── split-barrier.mlir │ ├── subgroup-2d-block-io.mlir │ ├── tensor-pointer-load-block-2d.mlir │ ├── tensor-pointer-store-block-2d.mlir │ ├── triton_annotate_module.mlir │ ├── tritongpu_reduce_op_lowering.mlir │ ├── tritonintelgpu-canonicalize.mlir │ ├── tritonintelgpu-convert-layout-shortcut.mlir │ ├── tritonintelgpu-invalid.mlir │ ├── tritonintelgpu-rewrite-stack-ptr.mlir │ ├── tritonintelgpu.mlir │ ├── tritonintlgpu-nested-layout.mlir │ └── tritonintlgpu-reduce-data-duplication.mlir ├── TritonNvidiaGPU │ ├── bf16-atomics.mlir │ ├── canonicalize.mlir │ ├── inline.mlir │ ├── interleave_tmem.mlir │ ├── invalid.mlir │ ├── membar.mlir │ ├── mma_lowering.mlir │ ├── ops.mlir │ ├── optimize_descriptor_encoding.mlir │ ├── test_promotion_to_tensor_memory.mlir │ ├── test_tensor_memory_allocation.mlir │ ├── tma_lowering.mlir │ └── tmem_layouts.mlir ├── include │ └── Analysis │ │ └── TestAxisInfo.h ├── lib │ ├── Analysis │ │ ├── CMakeLists.txt │ │ ├── TestAlias.cpp │ │ ├── TestAllocation.cpp │ │ ├── TestAxisInfo.cpp │ │ ├── TestLivenessAnalysis.cpp │ │ ├── TestMembar.cpp │ │ └── intel │ │ │ └── TestAxisInfo.cpp │ ├── CMakeLists.txt │ ├── Dialect │ │ ├── CMakeLists.txt │ │ └── TestLoopPeeling.cpp │ ├── Instrumentation │ │ ├── CMakeLists.txt │ │ └── GPUHello.cpp │ └── Proton │ │ ├── CMakeLists.txt │ │ └── TestScopeIdAllocation.cpp ├── lit.cfg.py └── lit.site.cfg.py.in ├── third-party-programs.txt ├── third_party ├── amd │ ├── CMakeLists.txt │ ├── backend │ │ ├── __init__.py │ │ ├── compiler.py │ │ ├── driver.c │ │ ├── driver.py │ │ ├── include │ │ │ ├── hip │ │ │ │ ├── amd_detail │ │ │ │ │ ├── amd_channel_descriptor.h │ │ │ │ │ ├── amd_device_functions.h │ │ │ │ │ ├── amd_hip_atomic.h │ │ │ │ │ ├── amd_hip_common.h │ │ │ │ │ ├── amd_hip_gl_interop.h │ │ │ │ │ ├── amd_hip_runtime.h │ │ │ │ │ ├── amd_hip_runtime_pt_api.h │ │ │ │ │ ├── amd_hip_unsafe_atomics.h │ │ │ │ │ ├── amd_hip_vector_types.h │ │ │ │ │ ├── amd_math_functions.h │ │ │ │ │ ├── amd_surface_functions.h │ │ │ │ │ ├── amd_warp_functions.h │ │ │ │ │ ├── amd_warp_sync_functions.h │ │ │ │ │ ├── device_library_decls.h │ │ │ │ │ ├── hip_assert.h │ │ │ │ │ ├── hip_fp16_math_fwd.h │ │ │ │ │ ├── hip_ldg.h │ │ │ │ │ ├── hip_prof_str.h │ │ │ │ │ ├── hip_runtime_prof.h │ │ │ │ │ ├── host_defines.h │ │ │ │ │ ├── math_fwd.h │ │ │ │ │ ├── ockl_image.h │ │ │ │ │ ├── texture_fetch_functions.h │ │ │ │ │ └── texture_indirect_functions.h │ │ │ │ ├── channel_descriptor.h │ │ │ │ ├── driver_types.h │ │ │ │ ├── hip_common.h │ │ │ │ ├── hip_deprecated.h │ │ │ │ ├── hip_runtime.h │ │ │ │ ├── hip_runtime_api.h │ │ │ │ ├── hip_texture_types.h │ │ │ │ ├── hip_vector_types.h │ │ │ │ ├── hip_version.h │ │ │ │ ├── library_types.h │ │ │ │ ├── linker_types.h │ │ │ │ ├── surface_types.h │ │ │ │ └── texture_types.h │ │ │ ├── hipblas-common │ │ │ │ └── hipblas-common.h │ │ │ ├── hsa │ │ │ │ ├── amd_hsa_kernel_code.h │ │ │ │ ├── hsa.h │ │ │ │ ├── hsa_ext_amd.h │ │ │ │ ├── hsa_ext_image.h │ │ │ │ ├── hsa_ven_amd_loader.h │ │ │ │ └── hsa_ven_amd_pc_sampling.h │ │ │ └── roctracer │ │ │ │ ├── ext │ │ │ │ └── prof_protocol.h │ │ │ │ ├── roctracer.h │ │ │ │ ├── roctracer_ext.h │ │ │ │ ├── roctracer_hip.h │ │ │ │ ├── roctracer_roctx.h │ │ │ │ └── roctx.h │ │ └── lib │ │ │ ├── asanrtl.bc │ │ │ ├── ockl.bc │ │ │ └── ocml.bc │ ├── include │ │ ├── Analysis │ │ │ ├── AMDGPUAllocation.h │ │ │ ├── AxisInfoExt.h │ │ │ └── RangeAnalysis.h │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ └── TritonAMDGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.h │ │ │ │ ├── TritonAMDGPUAttrDefs.td │ │ │ │ ├── TritonAMDGPUDialect.td │ │ │ │ ├── TritonAMDGPUOpInterfaces.td │ │ │ │ └── TritonAMDGPUOps.td │ │ │ │ └── Utility │ │ │ │ └── CommonUtils.h │ │ ├── TritonAMDGPUToLLVM │ │ │ ├── CMakeLists.txt │ │ │ ├── GCNAsmFormat.h │ │ │ ├── MembarUtility.h │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ ├── PatternTritonAMDGPUToLLVM.h │ │ │ └── TargetUtils.h │ │ ├── TritonAMDGPUTransforms │ │ │ ├── CMakeLists.txt │ │ │ ├── MfmaGroup.h │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ ├── TritonGPUConversion.h │ │ │ └── WmmaGroup.h │ │ ├── Utils │ │ │ └── Utility.h │ │ ├── hipblas_instance.h │ │ └── hipblas_types.h │ ├── language │ │ └── hip │ │ │ ├── __init__.py │ │ │ ├── libdevice.py │ │ │ └── utils.py │ ├── lib │ │ ├── Analysis │ │ │ ├── AMDGPUAllocation.cpp │ │ │ ├── AxisInfoExt.cpp │ │ │ ├── CMakeLists.txt │ │ │ └── RangeAnalysis.cpp │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ └── TritonAMDGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── Dialect.cpp │ │ │ │ └── Utility │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── CommonUtils.cpp │ │ ├── TritonAMDGPUDialectToLLVM │ │ │ ├── CMakeLists.txt │ │ │ ├── ConcatOpToLLVM.cpp │ │ │ ├── ExtractSliceOpToLLVM.cpp │ │ │ ├── InThreadTransposeOpToTTG.cpp │ │ │ ├── ScaledUpcastToLLVM.cpp │ │ │ ├── TritonAMDGPUToLLVMPatterns.cpp │ │ │ ├── Utility.cpp │ │ │ └── Utility.h │ │ ├── TritonAMDGPUToLLVM │ │ │ ├── AllocateSharedMemory.cpp │ │ │ ├── AsyncUtility.cpp │ │ │ ├── AsyncUtility.h │ │ │ ├── AtomicRMWOpsEmitter.cpp │ │ │ ├── AtomicRMWOpsEmitter.h │ │ │ ├── BarrierOpToLLVM.cpp │ │ │ ├── BufferOpsEmitter.cpp │ │ │ ├── BufferOpsEmitter.h │ │ │ ├── BuiltinFuncToLLVM.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── ConvertLayoutOpToLLVM.cpp │ │ │ ├── DotOpToLLVM.cpp │ │ │ ├── DotOpToLLVM │ │ │ │ ├── FMA.cpp │ │ │ │ ├── MFMA.cpp │ │ │ │ └── WMMA.cpp │ │ │ ├── ElementwiseOpToLLVM.cpp │ │ │ ├── Fp4ToFpOpToLLVM.cpp │ │ │ ├── GCNAsmFormat.cpp │ │ │ ├── LoadStoreOpToLLVM.cpp │ │ │ ├── MaskedOpsToLLVM.cpp │ │ │ ├── MembarUtility.cpp │ │ │ ├── MemoryOpToLLVM.cpp │ │ │ ├── OptimizeLDSUsage.cpp │ │ │ ├── OptimizeLDSUtility.cpp │ │ │ ├── OptimizeLDSUtility.h │ │ │ ├── PatternTritonGPUOpToLLVM.h │ │ │ ├── SPMDOpToLLVM.cpp │ │ │ ├── ScalarizePackedFOps.cpp │ │ │ ├── SchedInstructions.cpp │ │ │ ├── TDMUtility.cpp │ │ │ ├── TDMUtility.h │ │ │ ├── TargetInfo.cpp │ │ │ ├── TargetInfo.h │ │ │ ├── TargetUtils.cpp │ │ │ ├── TensorPtrOpsToLLVM.cpp │ │ │ ├── TritonGPUToLLVM.cpp │ │ │ ├── UpcastMXFPToLLVM.cpp │ │ │ ├── Utility.cpp │ │ │ └── Utility.h │ │ └── TritonAMDGPUTransforms │ │ │ ├── AccelerateAMDMatmul.cpp │ │ │ ├── BlockPingpong.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── CanonicalizePointers.cpp │ │ │ ├── CoalesceAsyncCopy.cpp │ │ │ ├── ConvertToBufferOps.cpp │ │ │ ├── FoldTrueCmpIOp.cpp │ │ │ ├── HoistLayoutConversions.cpp │ │ │ ├── InThreadTranspose.cpp │ │ │ ├── LowerLoops.cpp │ │ │ ├── MfmaGroup.cpp │ │ │ ├── OptimizeDotOperands.cpp │ │ │ ├── OptimizeEpilogue.cpp │ │ │ ├── Pipeline.cpp │ │ │ ├── PipelineUtility.h │ │ │ ├── ReorderInstructions.cpp │ │ │ ├── ScheduleLoops.cpp │ │ │ ├── UpdateAsyncWaitCount.cpp │ │ │ ├── Utility.cpp │ │ │ ├── Utility.h │ │ │ └── WmmaGroup.cpp │ ├── python │ │ ├── examples │ │ │ └── gluon │ │ │ │ ├── f16_fa_gfx1250.py │ │ │ │ ├── f16_gemm_gfx1250.py │ │ │ │ ├── mxfp_fa_gfx1250.py │ │ │ │ └── mxfp_gemm_gfx1250.py │ │ ├── test │ │ │ ├── address_sanitizer_helper.py │ │ │ ├── attn_fwd.ttir │ │ │ ├── conftest.py │ │ │ ├── test_address_sanitizer.py │ │ │ ├── test_convert_op_permlane_swap.py │ │ │ ├── test_extract_slice_concat_op.py │ │ │ ├── test_gluon_gfx1250.py │ │ │ ├── test_scalarize_packed_fops.py │ │ │ └── test_scheduler_hints.py │ │ └── triton_amd.cc │ ├── test │ │ ├── CMakeLists.txt │ │ └── lib │ │ │ ├── Analysis │ │ │ ├── CMakeLists.txt │ │ │ ├── TestAMDGPUMembar.cpp │ │ │ ├── TestAMDRangeAnalysis.cpp │ │ │ └── TestAxisInfo.cpp │ │ │ └── CMakeLists.txt │ ├── tools │ │ └── hip │ │ │ ├── compile.cpp │ │ │ └── compile.h │ └── unittest │ │ ├── CMakeLists.txt │ │ └── Conversion │ │ ├── CMakeLists.txt │ │ └── OptimizeLDSTest.cpp ├── f2reduce │ ├── CMakeLists.txt │ ├── LICENCE.txt │ ├── README.md │ ├── VERSION │ ├── f2reduce.cpp │ └── f2reduce.h ├── intel │ ├── CMakeLists.txt │ ├── backend │ │ ├── __init__.py │ │ ├── arch_parser.c │ │ ├── compiler.py │ │ ├── driver.c │ │ ├── driver.py │ │ ├── include │ │ │ └── sycl_functions.h │ │ ├── lib │ │ │ └── libsycl-spir64-unknown-unknown.bc │ │ ├── proton │ │ │ └── include │ │ │ │ └── pti │ │ │ │ ├── pti.h │ │ │ │ ├── pti_callback.h │ │ │ │ ├── pti_driver_levelzero_api_ids.h │ │ │ │ ├── pti_export.h │ │ │ │ ├── pti_metrics.h │ │ │ │ ├── pti_runtime_sycl_api_ids.h │ │ │ │ ├── pti_version.h │ │ │ │ └── pti_view.h │ │ ├── proton_utils.cpp │ │ └── track.py │ ├── bin │ │ ├── CMakeLists.txt │ │ └── triton-translate.cpp │ ├── cmake │ │ ├── 3122.patch │ │ ├── 3388.patch │ │ ├── 3462.patch │ │ └── FindSPIRVToLLVMTranslator.cmake │ ├── include │ │ ├── Analysis │ │ │ ├── Allocation.h │ │ │ ├── AxisInfo.h │ │ │ ├── DPAS.h │ │ │ ├── Liveness.h │ │ │ ├── Membar.h │ │ │ └── Utility.h │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ ├── Triton │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── Transforms │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── Passes.h │ │ │ │ │ └── Passes.td │ │ │ ├── TritonGEN │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── IR │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── TritonGENAttrDefs.td │ │ │ │ │ ├── TritonGENDialect.h │ │ │ │ │ ├── TritonGENDialect.td │ │ │ │ │ └── TritonGENOps.td │ │ │ └── TritonIntelGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── IR │ │ │ │ ├── Attributes.h │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.h │ │ │ │ ├── LinearLayoutConversions.h │ │ │ │ ├── TritonIntelGPUAttrDefs.td │ │ │ │ ├── TritonIntelGPUDialect.td │ │ │ │ ├── TritonIntelGPUOps.td │ │ │ │ └── Utils.h │ │ │ │ └── Transforms │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── DecomposeScaledBlocked.h │ │ │ │ ├── Passes.h │ │ │ │ ├── Passes.td │ │ │ │ └── Utility.h │ │ ├── GPUToTritonGEN │ │ │ ├── CMakeLists.txt │ │ │ ├── GPUToTritonGENPass.h │ │ │ ├── Passes.h │ │ │ └── Passes.td │ │ ├── Target │ │ │ ├── LLVMIR │ │ │ │ ├── Dialect │ │ │ │ │ └── TritonGEN │ │ │ │ │ │ └── TritonGENToLLVMIRTranslation.h │ │ │ │ └── PostProcess.h │ │ │ └── SPIRV │ │ │ │ └── SPIRVTranslation.h │ │ ├── TritonAnnotateModule │ │ │ ├── CMakeLists.txt │ │ │ ├── Passes.h │ │ │ └── Passes.td │ │ ├── TritonGENToLLVM │ │ │ ├── CMakeLists.txt │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ └── TritonGENToLLVMPass.h │ │ ├── TritonGENToSPIRV │ │ │ ├── CMakeLists.txt │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ └── TritonGENToSPIRVPass.h │ │ ├── TritonIntelGPUToLLVM │ │ │ ├── CMakeLists.txt │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ ├── TypeConverter.h │ │ │ └── XeAsmFormat.h │ │ └── Utils │ │ │ ├── DefUseChain.h │ │ │ └── Utility.h │ ├── language │ │ └── intel │ │ │ ├── __init__.py │ │ │ ├── libdevice.py │ │ │ └── utils.py │ ├── lib │ │ ├── Analysis │ │ │ ├── Allocation.cpp │ │ │ ├── AxisInfo.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── DPAS.cpp │ │ │ ├── Liveness.cpp │ │ │ ├── Membar.cpp │ │ │ └── Utility.cpp │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ ├── Triton │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── Transforms │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── FuseReshape.cpp │ │ │ │ │ ├── RemoveBoundaryChecks.cpp │ │ │ │ │ ├── RemoveMasks.cpp │ │ │ │ │ ├── StrideVersioning.cpp │ │ │ │ │ └── TensorDescToBlockPointer.cpp │ │ │ ├── TritonGEN │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── IR │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── TritonGENAttrs.cpp │ │ │ │ │ ├── TritonGENDialect.cpp │ │ │ │ │ └── TritonGENOps.cpp │ │ │ └── TritonIntelGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.cpp │ │ │ │ ├── LinearLayoutConversions.cpp │ │ │ │ └── Ops.cpp │ │ ├── GPUToTritonGEN │ │ │ ├── CMakeLists.txt │ │ │ ├── GPUOpsLowering.h │ │ │ ├── GPUToTritonGEN.td │ │ │ ├── GPUToTritonGENPass.cpp │ │ │ └── OpToFuncCallLowering.h │ │ ├── Target │ │ │ ├── CMakeLists.txt │ │ │ ├── LLVMIR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ └── TritonGEN │ │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ │ └── TritonGENToLLVMIRTranslation.cpp │ │ │ │ ├── LLVMIRFreezeMaskedDivRem.cpp │ │ │ │ ├── LLVMPasses.h │ │ │ │ └── PostProcess.cpp │ │ │ └── SPIRV │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── SPIRVTranslation.cpp │ │ │ │ └── spirv-llvm-translator.conf │ │ ├── TritonAnnotateModule │ │ │ ├── CMakeLists.txt │ │ │ └── TritonAnnotateModule.cpp │ │ ├── TritonGENToLLVM │ │ │ ├── Attributes.cpp │ │ │ ├── Attributes.h │ │ │ ├── CMakeLists.txt │ │ │ └── TritonGENToLLVMPass.cpp │ │ ├── TritonGENToSPIRV │ │ │ ├── CMakeLists.txt │ │ │ └── TritonGENToSPIRVPass.cpp │ │ ├── TritonIntelGPUToLLVM │ │ │ ├── AllocateSharedMemory.cpp │ │ │ ├── BF16Casts.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── ControlFlowOpToLLVM.cpp │ │ │ ├── ConvertLayoutOpToLLVM.cpp │ │ │ ├── DotOpToLLVM.cpp │ │ │ ├── DotOpToLLVM │ │ │ │ └── DPAS.cpp │ │ │ ├── ElementwiseOpToLLVM.cpp │ │ │ ├── Fp4ToFpOpToLLVM.cpp │ │ │ ├── HistogramOpToLLVM.cpp │ │ │ ├── LoadStoreOpToLLVM.cpp │ │ │ ├── PatternTritonGPUOpToLLVM.h │ │ │ ├── PipelineManager.h │ │ │ ├── PrintOpToLLVM.cpp │ │ │ ├── ReduceOpToLLVM.cpp │ │ │ ├── SPIRVSubgroupOps.h │ │ │ ├── SPIRVTargetInfo.cpp │ │ │ ├── SPIRVTargetInfo.h │ │ │ ├── SPMDOpToLLVM.cpp │ │ │ ├── TargetInfo.cpp │ │ │ ├── TargetInfo.h │ │ │ ├── TensorPtrOpsToLLVM.cpp │ │ │ ├── TritonGPUToLLVM.cpp │ │ │ ├── TritonGPUToLLVMBase.h │ │ │ ├── TypeConverter.cpp │ │ │ ├── Utility.cpp │ │ │ ├── Utility.h │ │ │ └── XeAsmFormat.cpp │ │ ├── TritonIntelGPUTransforms │ │ │ ├── AccelerateMatmul.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── Coalesce.cpp │ │ │ ├── DecomposeScaledBlocked.cpp │ │ │ ├── MaterializeBlockPointer.cpp │ │ │ ├── OptimizeDotOperands.cpp │ │ │ ├── OptimizeReductionLocality.cpp │ │ │ ├── Pipeliner │ │ │ │ ├── MatmulLoopPipeline.cpp │ │ │ │ ├── Schedule.h │ │ │ │ └── SoftwarePipeliner.cpp │ │ │ ├── ReduceDataDuplication.cpp │ │ │ ├── ReduceVariableLiveness.cpp │ │ │ ├── RemoveLayoutConversions.cpp │ │ │ ├── RewriteStackPtr.cpp │ │ │ └── Utility.cpp │ │ └── Utils │ │ │ ├── CMakeLists.txt │ │ │ ├── DefUseChain.cpp │ │ │ ├── LLVMIntr.cpp │ │ │ ├── LLVMIntr.h │ │ │ ├── LibCallEmitter.cpp │ │ │ ├── LibCallEmitter.h │ │ │ ├── Mangling.cpp │ │ │ ├── Mangling.h │ │ │ └── Utility.cpp │ ├── python │ │ └── test │ │ │ ├── conftest.py │ │ │ └── test_divide.py │ ├── tools │ │ └── intel │ │ │ ├── compile.cpp │ │ │ └── compile.h │ ├── triton_xpu.cc │ └── unittest │ │ ├── CMakeLists.txt │ │ ├── Conversion │ │ ├── CMakeLists.txt │ │ └── TritonIntelGPUToLLVM │ │ │ ├── CMakeLists.txt │ │ │ └── XeAsmFormatTest.cpp │ │ └── Dialect │ │ ├── CMakeLists.txt │ │ └── TritonIntelGPU │ │ ├── CMakeLists.txt │ │ ├── DPAStoLinearLayoutTest.cpp │ │ └── LinearLayoutConversionsTest.cpp ├── nvidia │ ├── CMakeLists.txt │ ├── backend │ │ ├── __init__.py │ │ ├── compiler.py │ │ ├── driver.c │ │ ├── driver.py │ │ └── lib │ │ │ └── libdevice.10.bc │ ├── hopper │ │ ├── CMakeLists.txt │ │ ├── include │ │ │ ├── CMakeLists.txt │ │ │ └── Transforms │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Passes.h │ │ │ │ └── Passes.td │ │ └── lib │ │ │ ├── CMakeLists.txt │ │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ ├── WarpSpecialization.cpp │ │ │ └── WarpSpecialization │ │ │ ├── CodePartitionUtility.cpp │ │ │ ├── CodePartitionUtility.h │ │ │ ├── TaskIdPropagation.cpp │ │ │ ├── TaskIdPropagation.h │ │ │ ├── Utility.cpp │ │ │ ├── Utility.h │ │ │ ├── WSBuffer.cpp │ │ │ ├── WSCodePartition.cpp │ │ │ ├── WSDataPartition.cpp │ │ │ ├── WSLowerMem.cpp │ │ │ ├── WSLowerToken.cpp │ │ │ ├── WSSpecialize.cpp │ │ │ ├── WSTaskIdPropagate.cpp │ │ │ └── WSTaskPartition.cpp │ ├── include │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ ├── NVGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── IR │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── Dialect.h │ │ │ │ │ ├── NVGPUAttrDefs.td │ │ │ │ │ ├── NVGPUDialect.td │ │ │ │ │ └── NVGPUOps.td │ │ │ └── NVWS │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.h │ │ │ │ ├── NVWSAttrDefs.td │ │ │ │ ├── NVWSDialect.td │ │ │ │ ├── NVWSOpInterfaces.td │ │ │ │ ├── NVWSOps.td │ │ │ │ └── NVWSTypes.td │ │ │ │ └── Transforms │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Passes.h │ │ │ │ └── Passes.td │ │ ├── NVGPUToLLVM │ │ │ ├── CMakeLists.txt │ │ │ ├── NVGPUToLLVMPass.h │ │ │ ├── Passes.h │ │ │ └── Passes.td │ │ ├── TritonNVIDIAGPUToLLVM │ │ │ ├── CMakeLists.txt │ │ │ ├── PTXAsmFormat.h │ │ │ ├── Passes.h │ │ │ ├── Passes.td │ │ │ └── Utility.h │ │ ├── cublas_instance.h │ │ └── cublas_types.h │ ├── language │ │ └── cuda │ │ │ ├── __init__.py │ │ │ ├── gdc.py │ │ │ ├── libdevice.py │ │ │ └── utils.py │ ├── lib │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ ├── NVGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── IR │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ └── Dialect.cpp │ │ │ └── NVWS │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.cpp │ │ │ │ └── Ops.cpp │ │ │ │ └── Transforms │ │ │ │ ├── AssignStagePhase.cpp │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── InsertAref.cpp │ │ │ │ ├── InsertTmemAref.cpp │ │ │ │ ├── LowerAref.cpp │ │ │ │ ├── LowerWarpGroup.cpp │ │ │ │ ├── Utilities.cpp │ │ │ │ └── Utilities.h │ │ ├── NVGPUToLLVM │ │ │ ├── CMakeLists.txt │ │ │ └── NVGPUToLLVMPass.cpp │ │ └── TritonNVIDIAGPUToLLVM │ │ │ ├── Allocation.cpp │ │ │ ├── Allocation.h │ │ │ ├── BarrierOpToLLVM.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── ClusterOpsToLLVM.cpp │ │ │ ├── ConvertLayoutOpToLLVM.cpp │ │ │ ├── ConvertWarpSpecializeToLLVM.cpp │ │ │ ├── DotOpToLLVM.cpp │ │ │ ├── DotOpToLLVM │ │ │ ├── MMAHelpers.h │ │ │ ├── MMAv2.cpp │ │ │ ├── MMAv5.cpp │ │ │ └── WGMMA.cpp │ │ │ ├── ElementwiseOpToLLVM.cpp │ │ │ ├── Fp4ToFpOpToLLVM.cpp │ │ │ ├── LoadStoreOpToLLVM.cpp │ │ │ ├── MemoryOpToLLVM.cpp │ │ │ ├── PTXAsmFormat.cpp │ │ │ ├── PatternTritonGPUOpToLLVM.h │ │ │ ├── SPMDOpToLLVM.cpp │ │ │ ├── TMAToLLVM.cpp │ │ │ ├── TargetInfo.cpp │ │ │ ├── TargetInfo.h │ │ │ ├── TensorMemoryToLLVM.cpp │ │ │ ├── TensorPtrOpsToLLVM.cpp │ │ │ ├── TritonGPUToLLVM.cpp │ │ │ ├── Utility.cpp │ │ │ └── Utility.h │ ├── tools │ │ └── cuda │ │ │ ├── compile.c │ │ │ └── compile.h │ ├── triton_nvidia.cc │ └── unittest │ │ ├── CMakeLists.txt │ │ └── Conversion │ │ ├── CMakeLists.txt │ │ └── TritonGPUToLLVM │ │ ├── CMakeLists.txt │ │ └── PTXAsmFormatTest.cpp └── proton │ ├── .gitignore │ ├── CMakeLists.txt │ ├── Dialect │ ├── CMakeLists.txt │ ├── include │ │ ├── Analysis │ │ │ └── ScopeIdAllocation.h │ │ ├── CMakeLists.txt │ │ ├── Conversion │ │ │ ├── CMakeLists.txt │ │ │ ├── ProtonGPUToLLVM │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Passes.h │ │ │ │ ├── Passes.td │ │ │ │ ├── PatternProtonGPUOpToLLVM.h │ │ │ │ ├── ProtonAMDGPUToLLVM │ │ │ │ │ ├── AMDPatternProtonGPUOpToLLVM.h │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── Passes.h │ │ │ │ │ ├── Passes.td │ │ │ │ │ └── TargetInfo.h │ │ │ │ ├── ProtonNvidiaGPUToLLVM │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── NvidiaPatternProtonGPUOpToLLVM.h │ │ │ │ │ ├── Passes.h │ │ │ │ │ ├── Passes.td │ │ │ │ │ └── TargetInfo.h │ │ │ │ ├── TargetInfoBase.h │ │ │ │ └── Utility.h │ │ │ └── ProtonToProtonGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Passes.h │ │ │ │ └── Passes.td │ │ └── Dialect │ │ │ ├── CMakeLists.txt │ │ │ ├── Proton │ │ │ ├── CMakeLists.txt │ │ │ └── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.h │ │ │ │ ├── ProtonAttrDefs.td │ │ │ │ ├── ProtonDialect.td │ │ │ │ └── ProtonOps.td │ │ │ └── ProtonGPU │ │ │ ├── CMakeLists.txt │ │ │ ├── IR │ │ │ ├── CMakeLists.txt │ │ │ ├── Dialect.h │ │ │ ├── ProtonGPUAttrDefs.td │ │ │ ├── ProtonGPUDialect.td │ │ │ ├── ProtonGPUOps.td │ │ │ ├── ProtonGPUTypes.td │ │ │ └── Types.h │ │ │ └── Transforms │ │ │ ├── CMakeLists.txt │ │ │ ├── Passes.h │ │ │ └── Passes.td │ ├── lib │ │ ├── Analysis │ │ │ ├── CMakeLists.txt │ │ │ └── ScopeIdAllocation.cpp │ │ ├── CMakeLists.txt │ │ ├── Dialect │ │ │ ├── CMakeLists.txt │ │ │ ├── Proton │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── IR │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ ├── Dialect.cpp │ │ │ │ │ └── Ops.cpp │ │ │ └── ProtonGPU │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── IR │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── Dialect.cpp │ │ │ │ ├── Ops.cpp │ │ │ │ └── Types.cpp │ │ │ │ └── Transforms │ │ │ │ ├── CMakeLists.txt │ │ │ │ └── ProtonGPUTransformsPass.cpp │ │ ├── ProtonGPUToLLVM │ │ │ ├── AllocateProtonGlobalScratchBuffer.cpp │ │ │ ├── AllocateProtonSharedMemory.cpp │ │ │ ├── CMakeLists.txt │ │ │ ├── PatternProtonGPUOpToLLVM.cpp │ │ │ ├── ProtonAMDGPUToLLVM │ │ │ │ ├── AMDPatternProtonGPUOpToLLVM.cpp │ │ │ │ ├── AddSchedBarriers.cpp │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── ConvertProtonGPUToLLVM.cpp │ │ │ │ └── TargetInfo.cpp │ │ │ ├── ProtonNvidiaGPUToLLVM │ │ │ │ ├── CMakeLists.txt │ │ │ │ ├── ConvertProtonGPUToLLVM.cpp │ │ │ │ ├── NvidiaPatternProtonGPUOpToLLVM.cpp │ │ │ │ └── TargetInfo.cpp │ │ │ └── Utility.cpp │ │ └── ProtonToProtonGPU │ │ │ ├── CMakeLists.txt │ │ │ └── ProtonToProtonGPUPass.cpp │ └── triton_proton.cc │ ├── README.md │ ├── common │ ├── CMakeLists.txt │ ├── include │ │ ├── Device.h │ │ └── TraceDataIO │ │ │ ├── ByteSpan.h │ │ │ ├── CircularLayoutParser.h │ │ │ ├── EntryDecoder.h │ │ │ ├── Parser.h │ │ │ └── TraceWriter.h │ └── lib │ │ ├── CMakeLists.txt │ │ └── TraceDataIO │ │ ├── ByteSpan.cpp │ │ ├── CMakeLists.txt │ │ ├── CircularLayoutParser.cpp │ │ ├── EntryDecoder.cpp │ │ ├── Parser.cpp │ │ └── TraceWriter.cpp │ ├── csrc │ ├── CMakeLists.txt │ ├── Proton.cpp │ ├── include │ │ ├── Context │ │ │ ├── Context.h │ │ │ ├── Python.h │ │ │ └── Shadow.h │ │ ├── Data │ │ │ ├── Data.h │ │ │ ├── Metric.h │ │ │ ├── TraceData.h │ │ │ └── TreeData.h │ │ ├── Driver │ │ │ ├── Dispatch.h │ │ │ └── GPU │ │ │ │ ├── CudaApi.h │ │ │ │ ├── CuptiApi.h │ │ │ │ ├── HipApi.h │ │ │ │ ├── HsaApi.h │ │ │ │ ├── NvtxApi.h │ │ │ │ ├── RoctracerApi.h │ │ │ │ ├── XpuApi.h │ │ │ │ └── XpuptiApi.h │ │ ├── Profiler │ │ │ ├── Cupti │ │ │ │ ├── CuptiPCSampling.h │ │ │ │ └── CuptiProfiler.h │ │ │ ├── GPUProfiler.h │ │ │ ├── Instrumentation │ │ │ │ ├── CudaRuntime.h │ │ │ │ ├── HipRuntime.h │ │ │ │ ├── InstrumentationProfiler.h │ │ │ │ ├── Metadata.h │ │ │ │ └── Runtime.h │ │ │ ├── Profiler.h │ │ │ ├── Roctracer │ │ │ │ └── RoctracerProfiler.h │ │ │ └── Xpupti │ │ │ │ └── XpuptiProfiler.h │ │ ├── Proton.h │ │ ├── Session │ │ │ └── Session.h │ │ └── Utility │ │ │ ├── Atomic.h │ │ │ ├── Env.h │ │ │ ├── Errors.h │ │ │ ├── Map.h │ │ │ ├── Numeric.h │ │ │ ├── Set.h │ │ │ ├── Singleton.h │ │ │ ├── String.h │ │ │ └── Traits.h │ └── lib │ │ ├── CMakeLists.txt │ │ ├── Context │ │ ├── CMakeLists.txt │ │ ├── Context.cpp │ │ ├── Python.cpp │ │ └── Shadow.cpp │ │ ├── Data │ │ ├── CMakeLists.txt │ │ ├── Data.cpp │ │ ├── TraceData.cpp │ │ └── TreeData.cpp │ │ ├── Driver │ │ ├── CMakeLists.txt │ │ ├── Device.cpp │ │ └── GPU │ │ │ ├── CudaApi.cpp │ │ │ ├── CuptiApi.cpp │ │ │ ├── HipApi.cpp │ │ │ ├── HsaApi.cpp │ │ │ ├── NvtxApi.cpp │ │ │ ├── RoctracerApi.cpp │ │ │ ├── XpuApi.cpp │ │ │ └── XpuptiApi.cpp │ │ ├── Profiler │ │ ├── CMakeLists.txt │ │ ├── Cupti │ │ │ ├── CuptiPCSampling.cpp │ │ │ └── CuptiProfiler.cpp │ │ ├── Instrumentation │ │ │ ├── CudaRuntime.cpp │ │ │ ├── HipRuntime.cpp │ │ │ ├── InstrumentationProfiler.cpp │ │ │ └── Metadata.cpp │ │ ├── RocTracer │ │ │ └── RoctracerProfiler.cpp │ │ └── Xpupti │ │ │ └── XpuptiProfiler.cpp │ │ └── Session │ │ ├── CMakeLists.txt │ │ └── Session.cpp │ ├── proton │ ├── __init__.py │ ├── context.py │ ├── flags.py │ ├── hooks │ │ ├── __init__.py │ │ ├── hook.py │ │ ├── instrumentation.py │ │ └── launch.py │ ├── language.py │ ├── mode.py │ ├── profile.py │ ├── proton.py │ ├── scope.py │ ├── specs.py │ ├── state.py │ └── viewer.py │ ├── scripts │ └── dump_ttgir.sh │ ├── test │ ├── CMakeLists.txt │ ├── conftest.py │ ├── examples │ │ ├── cuda.json │ │ ├── frame.json │ │ ├── hip.json │ │ ├── leaf_nodes.json │ │ └── triton.json │ ├── helper.py │ ├── helper_kernels.py │ ├── instrument.py │ ├── override_helper.py │ ├── test_api.py │ ├── test_cmd.py │ ├── test_instrumentation.py │ ├── test_lib.py │ ├── test_override.py │ ├── test_profile.py │ ├── test_viewer.py │ └── unittest │ │ ├── CMakeLists.txt │ │ ├── TraceDataIO │ │ ├── ByteSpanTest.cpp │ │ ├── CMakeLists.txt │ │ ├── ChromeTraceWriterTest.cpp │ │ ├── CircularLayoutParserTest.cpp │ │ └── DecoderTest.cpp │ │ └── util │ │ ├── loop.bin │ │ ├── seq.bin │ │ └── trace_gen.py │ └── tutorials │ ├── dynamic-net.py │ ├── intra_kernel │ ├── README.md │ ├── example_dsl.py │ ├── example_override.py │ └── insert_proton_records │ └── matmul.py ├── unittest ├── Analysis │ ├── CMakeLists.txt │ └── UtilityTest.cpp ├── CMakeLists.txt ├── Dialect │ ├── CMakeLists.txt │ └── TritonGPU │ │ ├── CMakeLists.txt │ │ ├── DialectTest.cpp │ │ ├── DumpLayoutTest.cpp │ │ ├── LinearLayoutConversionsTest.cpp │ │ └── SwizzleTest.cpp ├── Tools │ ├── CMakeLists.txt │ ├── LayoutUtilsTest.cpp │ └── LinearLayoutTest.cpp └── googletest.cmake └── utils ├── SPIRVRunner ├── CMakeLists.txt ├── README.md ├── SPIRVRunner.cpp ├── llvm_parser.cpp ├── llvm_parser.h └── tests │ ├── add_kernel │ ├── 01-vector-add.py │ ├── add_kernel.spv │ └── expected_output.pt │ ├── dot │ ├── args_data.json │ ├── expected_output.pt │ ├── kernel.spv │ ├── tensor_0.pt │ ├── tensor_1.pt │ ├── tensor_2.pt │ └── tensor_3.pt │ └── test_spirv_runner.py ├── generate-test-checks.py └── nightly.pypirc /.clang-format: -------------------------------------------------------------------------------- 1 | BasedOnStyle: LLVM 2 | -------------------------------------------------------------------------------- /.editorconfig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.editorconfig -------------------------------------------------------------------------------- /.git-blame-ignore-revs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.git-blame-ignore-revs -------------------------------------------------------------------------------- /.github/CODEOWNERS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/CODEOWNERS -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/ISSUE_TEMPLATE/bug.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/ISSUE_TEMPLATE/config.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature-request.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/ISSUE_TEMPLATE/feature-request.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/performance.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/ISSUE_TEMPLATE/performance.yml -------------------------------------------------------------------------------- /.github/PULL_REQUEST_TEMPLATE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/PULL_REQUEST_TEMPLATE.md -------------------------------------------------------------------------------- /.github/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/README.md -------------------------------------------------------------------------------- /.github/WINDOWS.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/WINDOWS.md -------------------------------------------------------------------------------- /.github/actions/get-commit-id/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/get-commit-id/action.yml -------------------------------------------------------------------------------- /.github/actions/install-wheels/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/install-wheels/action.yml -------------------------------------------------------------------------------- /.github/actions/load/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/load/action.yml -------------------------------------------------------------------------------- /.github/actions/save/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/save/action.yml -------------------------------------------------------------------------------- /.github/actions/setup-python/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/setup-python/action.yml -------------------------------------------------------------------------------- /.github/actions/setup-pytorch/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/setup-pytorch/action.yml -------------------------------------------------------------------------------- /.github/actions/setup-triton/action.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/actions/setup-triton/action.yml -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/dependabot.yml -------------------------------------------------------------------------------- /.github/models/accuracy/huggingface.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/models/accuracy/huggingface.txt -------------------------------------------------------------------------------- /.github/models/accuracy/timm_models.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/models/accuracy/timm_models.txt -------------------------------------------------------------------------------- /.github/models/accuracy/torchbench.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/models/accuracy/torchbench.txt -------------------------------------------------------------------------------- /.github/models/performance/huggingface.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/models/performance/huggingface.txt -------------------------------------------------------------------------------- /.github/models/performance/timm_models.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/models/performance/timm_models.txt -------------------------------------------------------------------------------- /.github/models/performance/torchbench.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/models/performance/torchbench.txt -------------------------------------------------------------------------------- /.github/pins/e2e_reference_torch-xpu-ops.txt: -------------------------------------------------------------------------------- 1 | 1e69f40b3c03492eb3dd7e03462a5566f29674d3 2 | -------------------------------------------------------------------------------- /.github/pins/pti.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/pins/pti.txt -------------------------------------------------------------------------------- /.github/pins/pytorch.txt: -------------------------------------------------------------------------------- 1 | 01f94d4096060597e2815efe385255ac19c9c787 2 | -------------------------------------------------------------------------------- /.github/workflows/bandit-check.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/bandit-check.yml -------------------------------------------------------------------------------- /.github/workflows/build-macos.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-macos.yml -------------------------------------------------------------------------------- /.github/workflows/build-test-gpu.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-test-gpu.yml -------------------------------------------------------------------------------- /.github/workflows/build-test-python.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-test-python.yml -------------------------------------------------------------------------------- /.github/workflows/build-test-reusable.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-test-reusable.yml -------------------------------------------------------------------------------- /.github/workflows/build-test-spirv.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-test-spirv.yml -------------------------------------------------------------------------------- /.github/workflows/build-test-windows.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-test-windows.yml -------------------------------------------------------------------------------- /.github/workflows/build-test.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-test.yml -------------------------------------------------------------------------------- /.github/workflows/build-windows.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/build-windows.yml -------------------------------------------------------------------------------- /.github/workflows/ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/ci.yml -------------------------------------------------------------------------------- /.github/workflows/coverity.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/coverity.yml -------------------------------------------------------------------------------- /.github/workflows/create_release.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/create_release.yml -------------------------------------------------------------------------------- /.github/workflows/documentation.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/documentation.yml -------------------------------------------------------------------------------- /.github/workflows/e2e-accuracy.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/e2e-accuracy.yml -------------------------------------------------------------------------------- /.github/workflows/e2e-performance.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/e2e-performance.yml -------------------------------------------------------------------------------- /.github/workflows/e2e-reusable.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/e2e-reusable.yml -------------------------------------------------------------------------------- /.github/workflows/e2e-windows.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/e2e-windows.yml -------------------------------------------------------------------------------- /.github/workflows/inductor-tests-windows.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/inductor-tests-windows.yml -------------------------------------------------------------------------------- /.github/workflows/inductor-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/inductor-tests.yml -------------------------------------------------------------------------------- /.github/workflows/integration-tests-amd.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/integration-tests-amd.yml -------------------------------------------------------------------------------- /.github/workflows/llvm-build.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/llvm-build.yml -------------------------------------------------------------------------------- /.github/workflows/nightly-wheels.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/nightly-wheels.yml -------------------------------------------------------------------------------- /.github/workflows/pip-test-windows.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/pip-test-windows.yml -------------------------------------------------------------------------------- /.github/workflows/pip-test.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/pip-test.yml -------------------------------------------------------------------------------- /.github/workflows/pre-commit.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/pre-commit.yml -------------------------------------------------------------------------------- /.github/workflows/runner-preparation.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/runner-preparation.yml -------------------------------------------------------------------------------- /.github/workflows/spirvrunner-test.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/spirvrunner-test.yml -------------------------------------------------------------------------------- /.github/workflows/third-party-benchmarks.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/third-party-benchmarks.yml -------------------------------------------------------------------------------- /.github/workflows/third-party-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/third-party-tests.yml -------------------------------------------------------------------------------- /.github/workflows/triton-benchmarks-bmg.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/triton-benchmarks-bmg.yml -------------------------------------------------------------------------------- /.github/workflows/triton-benchmarks-pvc.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/triton-benchmarks-pvc.yml -------------------------------------------------------------------------------- /.github/workflows/triton-benchmarks.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/triton-benchmarks.yml -------------------------------------------------------------------------------- /.github/workflows/try-latest-pytorch.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/try-latest-pytorch.yml -------------------------------------------------------------------------------- /.github/workflows/wheels-pytorch.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/wheels-pytorch.yml -------------------------------------------------------------------------------- /.github/workflows/wheels-triton.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/wheels-triton.yml -------------------------------------------------------------------------------- /.github/workflows/wheels.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.github/workflows/wheels.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/CMakeLists.txt -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /DEVELOPMENT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/DEVELOPMENT.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/MANIFEST.in -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/README.md -------------------------------------------------------------------------------- /RELEASE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/RELEASE.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/SECURITY.md -------------------------------------------------------------------------------- /bandit.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bandit.yaml -------------------------------------------------------------------------------- /benchmarks/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/CMakeLists.txt -------------------------------------------------------------------------------- /benchmarks/cmake/FindCUTLASSLibrary.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cmake/FindCUTLASSLibrary.cmake -------------------------------------------------------------------------------- /benchmarks/cmake/FindXeTLALibrary.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cmake/FindXeTLALibrary.cmake -------------------------------------------------------------------------------- /benchmarks/cmake/FindoneDNNLibrary.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cmake/FindoneDNNLibrary.cmake -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cutlass_kernel/CMakeLists.txt -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/attention/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(cutlass_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/config-tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cutlass_kernel/config-tool.py -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/cutlass-library.conf: -------------------------------------------------------------------------------- 1 | b0cb10e655d8f9b1d0474e9538a82d218f74c694 2 | -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/gemm/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(cutlass_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/gemm/gemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cutlass_kernel/gemm/gemm.hpp -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/gemm/input_gemm.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cutlass_kernel/gemm/input_gemm.in -------------------------------------------------------------------------------- /benchmarks/cutlass_kernel/python_main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/cutlass_kernel/python_main.cpp -------------------------------------------------------------------------------- /benchmarks/gpu_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/gpu_info.json -------------------------------------------------------------------------------- /benchmarks/micro_benchmarks/conversion/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/micro_benchmarks/core_ops/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/onednn_kernel/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/onednn_kernel/CMakeLists.txt -------------------------------------------------------------------------------- /benchmarks/onednn_kernel/onednn-library.conf: -------------------------------------------------------------------------------- 1 | df786faad216a0024da083786a5047af6014fe59 2 | -------------------------------------------------------------------------------- /benchmarks/onednn_kernel/python_main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/onednn_kernel/python_main.cpp -------------------------------------------------------------------------------- /benchmarks/onednn_kernel/softmax/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(onednn_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/onednn_kernel/softmax/softmax.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/onednn_kernel/softmax/softmax.h -------------------------------------------------------------------------------- /benchmarks/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/setup.py -------------------------------------------------------------------------------- /benchmarks/tests/test_entry_point.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/tests/test_entry_point.py -------------------------------------------------------------------------------- /benchmarks/tests/test_mocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/tests/test_mocks.py -------------------------------------------------------------------------------- /benchmarks/third_party/e2e-flex_attention/transformers-commit.txt: -------------------------------------------------------------------------------- 1 | 6e9972962fbc80d218234bfbd8c9b2843ef02b2b 2 | -------------------------------------------------------------------------------- /benchmarks/third_party/liger/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/third_party/liger/README.md -------------------------------------------------------------------------------- /benchmarks/third_party/liger/transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/third_party/liger/transform.py -------------------------------------------------------------------------------- /benchmarks/third_party/sglang/sglang-pin.txt: -------------------------------------------------------------------------------- 1 | d6fee73d1f593bd6754cd2550775fd2e54aeae60 2 | -------------------------------------------------------------------------------- /benchmarks/third_party/vllm/vllm-fix.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/third_party/vllm/vllm-fix.patch -------------------------------------------------------------------------------- /benchmarks/third_party/vllm/vllm-kernels-pin.txt: -------------------------------------------------------------------------------- 1 | 2ad9a6e2adabddd5b51e0e4777d2ab5a358ef2c6 2 | -------------------------------------------------------------------------------- /benchmarks/third_party/vllm/vllm-pin.txt: -------------------------------------------------------------------------------- 1 | 2b856970313e80a649a573879d94e9d3430ba018 2 | -------------------------------------------------------------------------------- /benchmarks/triton_kernels_benchmark/configs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/xetla_kernel/CMakeLists.txt -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/flash_attention/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(xetla_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/gemm/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(xetla_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/gemm/gemm.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/xetla_kernel/gemm/gemm.h -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/gemm/gemm_config.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/xetla_kernel/gemm/gemm_config.hpp -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/gemm/kernel_func.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/xetla_kernel/gemm/kernel_func.hpp -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/python_main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/xetla_kernel/python_main.cpp -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/softmax/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(xetla_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/softmax/softmax.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/benchmarks/xetla_kernel/softmax/softmax.h -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/split_k_gemm/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(xetla_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/stream_k_gemm/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | target_include_directories(xetla_kernel PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}) 2 | -------------------------------------------------------------------------------- /benchmarks/xetla_kernel/xetla-library.conf: -------------------------------------------------------------------------------- 1 | bde127ffebf502d32ef8ac2748e12d7839597fab 2 | -------------------------------------------------------------------------------- /bin/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/CMakeLists.txt -------------------------------------------------------------------------------- /bin/RegisterTritonDialects.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/RegisterTritonDialects.h -------------------------------------------------------------------------------- /bin/triton-llvm-opt.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/triton-llvm-opt.cpp -------------------------------------------------------------------------------- /bin/triton-lsp.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/triton-lsp.cpp -------------------------------------------------------------------------------- /bin/triton-opt.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/triton-opt.cpp -------------------------------------------------------------------------------- /bin/triton-reduce.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/triton-reduce.cpp -------------------------------------------------------------------------------- /bin/triton-tensor-layout.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/bin/triton-tensor-layout.cpp -------------------------------------------------------------------------------- /cmake/AddTritonUnitTest.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/cmake/AddTritonUnitTest.cmake -------------------------------------------------------------------------------- /cmake/FindLLVM.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/cmake/FindLLVM.cmake -------------------------------------------------------------------------------- /cmake/json-version.txt: -------------------------------------------------------------------------------- 1 | v3.11.3 2 | -------------------------------------------------------------------------------- /cmake/llvm-hash.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/cmake/llvm-hash.txt -------------------------------------------------------------------------------- /cmake/nvidia-toolchain-version.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/cmake/nvidia-toolchain-version.json -------------------------------------------------------------------------------- /docs/ARCHITECTURE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/ARCHITECTURE.md -------------------------------------------------------------------------------- /docs/BLOCK_LOADS_LAYOUT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/BLOCK_LOADS_LAYOUT.md -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/_static/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /docs/_templates/versions.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/_templates/versions.html -------------------------------------------------------------------------------- /docs/backend/ldmatrixOperand0.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/backend/ldmatrixOperand0.svg -------------------------------------------------------------------------------- /docs/backend/ldmatrixOperand1.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/backend/ldmatrixOperand1.svg -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/getting-started/architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/getting-started/architecture.rst -------------------------------------------------------------------------------- /docs/getting-started/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/getting-started/installation.rst -------------------------------------------------------------------------------- /docs/getting-started/start.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/getting-started/start.rst -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/meetups/01-24-2024/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/01-24-2024/notes.md -------------------------------------------------------------------------------- /docs/meetups/02-20-2024/Proton.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/02-20-2024/Proton.pdf -------------------------------------------------------------------------------- /docs/meetups/02-20-2024/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/02-20-2024/notes.md -------------------------------------------------------------------------------- /docs/meetups/03-12-2025/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/03-12-2025/notes.md -------------------------------------------------------------------------------- /docs/meetups/04-02-2024/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/04-02-2024/notes.md -------------------------------------------------------------------------------- /docs/meetups/05-01-2025/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/05-01-2025/notes.md -------------------------------------------------------------------------------- /docs/meetups/05-07-2024/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/05-07-2024/notes.md -------------------------------------------------------------------------------- /docs/meetups/07-09-2025/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/07-09-2025/notes.md -------------------------------------------------------------------------------- /docs/meetups/07-18-2023/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/07-18-2023/notes.md -------------------------------------------------------------------------------- /docs/meetups/08-06-2024/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/08-06-2024/notes.md -------------------------------------------------------------------------------- /docs/meetups/08-22-2023/amd-update.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/08-22-2023/amd-update.pdf -------------------------------------------------------------------------------- /docs/meetups/08-22-2023/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/08-22-2023/notes.md -------------------------------------------------------------------------------- /docs/meetups/09-03-2025/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/09-03-2025/notes.md -------------------------------------------------------------------------------- /docs/meetups/10-25-2023/intel-xpu-update.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/10-25-2023/intel-xpu-update.pdf -------------------------------------------------------------------------------- /docs/meetups/10-25-2023/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/10-25-2023/notes.md -------------------------------------------------------------------------------- /docs/meetups/10-25-2023/triton-shared.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/10-25-2023/triton-shared.pptx -------------------------------------------------------------------------------- /docs/meetups/11-05-2025/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/11-05-2025/notes.md -------------------------------------------------------------------------------- /docs/meetups/12-13-2023/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/12-13-2023/notes.md -------------------------------------------------------------------------------- /docs/meetups/dev-meetup-2023.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/dev-meetup-2023.md -------------------------------------------------------------------------------- /docs/meetups/dev_conference_2024.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/dev_conference_2024.md -------------------------------------------------------------------------------- /docs/meetups/for_moderators/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/meetups/for_moderators/README.md -------------------------------------------------------------------------------- /docs/pics/encoding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/encoding.png -------------------------------------------------------------------------------- /docs/pics/execution_model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/execution_model.png -------------------------------------------------------------------------------- /docs/pics/load_store.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/load_store.png -------------------------------------------------------------------------------- /docs/pics/memory-hierarchy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/memory-hierarchy.png -------------------------------------------------------------------------------- /docs/pics/perf-benchmark.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/perf-benchmark.png -------------------------------------------------------------------------------- /docs/pics/prog-model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/prog-model.png -------------------------------------------------------------------------------- /docs/pics/pt2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/pt2.png -------------------------------------------------------------------------------- /docs/pics/shared1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/shared1.png -------------------------------------------------------------------------------- /docs/pics/shared2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/shared2.png -------------------------------------------------------------------------------- /docs/pics/triton.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/pics/triton.png -------------------------------------------------------------------------------- /docs/python-api/triton-semantics.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/python-api/triton-semantics.rst -------------------------------------------------------------------------------- /docs/python-api/triton.language.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/python-api/triton.language.rst -------------------------------------------------------------------------------- /docs/python-api/triton.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/python-api/triton.rst -------------------------------------------------------------------------------- /docs/python-api/triton.testing.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/python-api/triton.testing.rst -------------------------------------------------------------------------------- /docs/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/requirements.txt -------------------------------------------------------------------------------- /docs/update_sycl_libdevice.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/docs/update_sycl_libdevice.md -------------------------------------------------------------------------------- /include/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(triton) 2 | -------------------------------------------------------------------------------- /include/triton/Analysis/Alias.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Analysis/Alias.h -------------------------------------------------------------------------------- /include/triton/Analysis/Allocation.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Analysis/Allocation.h -------------------------------------------------------------------------------- /include/triton/Analysis/AxisInfo.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Analysis/AxisInfo.h -------------------------------------------------------------------------------- /include/triton/Analysis/Membar.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Analysis/Membar.h -------------------------------------------------------------------------------- /include/triton/Analysis/Utility.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Analysis/Utility.h -------------------------------------------------------------------------------- /include/triton/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/CMakeLists.txt -------------------------------------------------------------------------------- /include/triton/Conversion/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Conversion/CMakeLists.txt -------------------------------------------------------------------------------- /include/triton/Conversion/MLIRTypes.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Conversion/MLIRTypes.h -------------------------------------------------------------------------------- /include/triton/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/CMakeLists.txt -------------------------------------------------------------------------------- /include/triton/Dialect/Gluon/CMakeCache.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Gluon/CMakeCache.txt -------------------------------------------------------------------------------- /include/triton/Dialect/Gluon/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Gluon/CMakeLists.txt -------------------------------------------------------------------------------- /include/triton/Dialect/Gluon/IR/Dialect.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Gluon/IR/Dialect.h -------------------------------------------------------------------------------- /include/triton/Dialect/Gluon/IR/GluonOps.td: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Gluon/IR/GluonOps.td -------------------------------------------------------------------------------- /include/triton/Dialect/Triton/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Triton/CMakeLists.txt -------------------------------------------------------------------------------- /include/triton/Dialect/Triton/IR/Dialect.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Triton/IR/Dialect.h -------------------------------------------------------------------------------- /include/triton/Dialect/Triton/IR/Traits.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Triton/IR/Traits.h -------------------------------------------------------------------------------- /include/triton/Dialect/Triton/IR/Types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Triton/IR/Types.h -------------------------------------------------------------------------------- /include/triton/Dialect/Triton/IR/Utility.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/Triton/IR/Utility.h -------------------------------------------------------------------------------- /include/triton/Dialect/TritonGPU/IR/Traits.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/TritonGPU/IR/Traits.h -------------------------------------------------------------------------------- /include/triton/Dialect/TritonGPU/IR/Types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Dialect/TritonGPU/IR/Types.h -------------------------------------------------------------------------------- /include/triton/Target/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(LLVMIR) 2 | -------------------------------------------------------------------------------- /include/triton/Target/LLVMIR/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Target/LLVMIR/CMakeLists.txt -------------------------------------------------------------------------------- /include/triton/Target/LLVMIR/Passes.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Target/LLVMIR/Passes.h -------------------------------------------------------------------------------- /include/triton/Target/LLVMIR/Passes.td: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Target/LLVMIR/Passes.td -------------------------------------------------------------------------------- /include/triton/Tools/GenericSwizzling.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Tools/GenericSwizzling.h -------------------------------------------------------------------------------- /include/triton/Tools/LayoutUtils.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Tools/LayoutUtils.h -------------------------------------------------------------------------------- /include/triton/Tools/LinearLayout.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Tools/LinearLayout.h -------------------------------------------------------------------------------- /include/triton/Tools/PluginUtils.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Tools/PluginUtils.h -------------------------------------------------------------------------------- /include/triton/Tools/StrUtil.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Tools/StrUtil.h -------------------------------------------------------------------------------- /include/triton/Tools/Sys/GetEnv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/include/triton/Tools/Sys/GetEnv.hpp -------------------------------------------------------------------------------- /lib/Analysis/Alias.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Analysis/Alias.cpp -------------------------------------------------------------------------------- /lib/Analysis/Allocation.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Analysis/Allocation.cpp -------------------------------------------------------------------------------- /lib/Analysis/AxisInfo.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Analysis/AxisInfo.cpp -------------------------------------------------------------------------------- /lib/Analysis/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Analysis/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Analysis/Membar.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Analysis/Membar.cpp -------------------------------------------------------------------------------- /lib/Analysis/Utility.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Analysis/Utility.cpp -------------------------------------------------------------------------------- /lib/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Conversion/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Conversion/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Conversion/TritonGPUToLLVM/Utility.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Conversion/TritonGPUToLLVM/Utility.cpp -------------------------------------------------------------------------------- /lib/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Gluon/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Gluon/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Gluon/IR/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Gluon/IR/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Gluon/IR/Dialect.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Gluon/IR/Dialect.cpp -------------------------------------------------------------------------------- /lib/Dialect/Gluon/Transforms/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Gluon/Transforms/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Gluon/Transforms/Inline.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Gluon/Transforms/Inline.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/Canonicalize.td: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/Canonicalize.td -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/Dialect.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/Dialect.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/OpInterfaces.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/OpInterfaces.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/Ops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/Ops.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/Traits.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/Traits.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/Types.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/Types.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/IR/Utility.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/IR/Utility.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/Transforms/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/Transforms/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/Triton/Transforms/Combine.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/Transforms/Combine.cpp -------------------------------------------------------------------------------- /lib/Dialect/Triton/Transforms/Combine.td: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/Transforms/Combine.td -------------------------------------------------------------------------------- /lib/Dialect/Triton/Transforms/LoopUnroll.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/Triton/Transforms/LoopUnroll.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonGPU/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonGPU/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/TritonGPU/IR/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonGPU/IR/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/TritonGPU/IR/Dialect.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonGPU/IR/Dialect.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonGPU/IR/Ops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonGPU/IR/Ops.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonGPU/IR/Types.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonGPU/IR/Types.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonGPU/Transforms/Utility.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonGPU/Transforms/Utility.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonInstrument/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonInstrument/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/TritonInstrument/IR/Dialect.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonInstrument/IR/Dialect.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonInstrument/IR/Ops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonInstrument/IR/Ops.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonInstrument/IR/Utility.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonInstrument/IR/Utility.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonNvidiaGPU/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonNvidiaGPU/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Dialect/TritonNvidiaGPU/IR/Dialect.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonNvidiaGPU/IR/Dialect.cpp -------------------------------------------------------------------------------- /lib/Dialect/TritonNvidiaGPU/IR/Ops.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Dialect/TritonNvidiaGPU/IR/Ops.cpp -------------------------------------------------------------------------------- /lib/Plugins/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Plugins/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Plugins/Passes.td: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Plugins/Passes.td -------------------------------------------------------------------------------- /lib/Plugins/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Plugins/README.md -------------------------------------------------------------------------------- /lib/Plugins/TritonPlugin.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Plugins/TritonPlugin.cpp -------------------------------------------------------------------------------- /lib/Target/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(LLVMIR) 2 | -------------------------------------------------------------------------------- /lib/Target/LLVMIR/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Target/LLVMIR/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Target/LLVMIR/LLVMDILocalVariable.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Target/LLVMIR/LLVMDILocalVariable.cpp -------------------------------------------------------------------------------- /lib/Target/LLVMIR/LLVMDIScope.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Target/LLVMIR/LLVMDIScope.cpp -------------------------------------------------------------------------------- /lib/Target/LLVMIR/LLVMIRBreakPhiStruct.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Target/LLVMIR/LLVMIRBreakPhiStruct.cpp -------------------------------------------------------------------------------- /lib/Target/LLVMIR/LLVMPasses.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Target/LLVMIR/LLVMPasses.h -------------------------------------------------------------------------------- /lib/Tools/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Tools/CMakeLists.txt -------------------------------------------------------------------------------- /lib/Tools/GenericSwizzling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Tools/GenericSwizzling.cpp -------------------------------------------------------------------------------- /lib/Tools/LayoutUtils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Tools/LayoutUtils.cpp -------------------------------------------------------------------------------- /lib/Tools/LinearLayout.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Tools/LinearLayout.cpp -------------------------------------------------------------------------------- /lib/Tools/PluginUtils.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/lib/Tools/PluginUtils.cpp -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/pyproject.toml -------------------------------------------------------------------------------- /python/build_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/build_helpers.py -------------------------------------------------------------------------------- /python/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/requirements.txt -------------------------------------------------------------------------------- /python/src/gluon_ir.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/gluon_ir.cc -------------------------------------------------------------------------------- /python/src/interpreter.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/interpreter.cc -------------------------------------------------------------------------------- /python/src/ir.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/ir.cc -------------------------------------------------------------------------------- /python/src/ir.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/ir.h -------------------------------------------------------------------------------- /python/src/linear_layout.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/linear_layout.cc -------------------------------------------------------------------------------- /python/src/llvm.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/llvm.cc -------------------------------------------------------------------------------- /python/src/main.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/main.cc -------------------------------------------------------------------------------- /python/src/passes.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/passes.cc -------------------------------------------------------------------------------- /python/src/passes.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/passes.h -------------------------------------------------------------------------------- /python/src/specialize.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/src/specialize.cc -------------------------------------------------------------------------------- /python/test-requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test-requirements.txt -------------------------------------------------------------------------------- /python/test/backend/extension_backend.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/backend/extension_backend.c -------------------------------------------------------------------------------- /python/test/backend/test_device_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/backend/test_device_backend.py -------------------------------------------------------------------------------- /python/test/backend/test_mir_stage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/backend/test_mir_stage.py -------------------------------------------------------------------------------- /python/test/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/conftest.py -------------------------------------------------------------------------------- /python/test/gluon/test_consan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/gluon/test_consan.py -------------------------------------------------------------------------------- /python/test/gluon/test_core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/gluon/test_core.py -------------------------------------------------------------------------------- /python/test/gluon/test_frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/gluon/test_frontend.py -------------------------------------------------------------------------------- /python/test/gluon/test_lowerings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/gluon/test_lowerings.py -------------------------------------------------------------------------------- /python/test/kernel_comparison/kernels.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/kernel_comparison/kernels.yml -------------------------------------------------------------------------------- /python/test/regression/test_cast_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/regression/test_cast_matmul.py -------------------------------------------------------------------------------- /python/test/unit/cuda/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/test/unit/cuda/test_libdevice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/cuda/test_libdevice.py -------------------------------------------------------------------------------- /python/test/unit/cuda/test_mixed_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/cuda/test_mixed_io.py -------------------------------------------------------------------------------- /python/test/unit/cuda/test_tma_descriptor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/cuda/test_tma_descriptor.py -------------------------------------------------------------------------------- /python/test/unit/cuda/test_tma_store_gemm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/cuda/test_tma_store_gemm.py -------------------------------------------------------------------------------- /python/test/unit/intel/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/test/unit/intel/block_load_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/block_load_helper.py -------------------------------------------------------------------------------- /python/test/unit/intel/helion795.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/helion795.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_block_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_block_io.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_block_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_block_load.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_conversions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_conversions.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_core.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_driver.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_mxfp_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_mxfp_matmul.py -------------------------------------------------------------------------------- /python/test/unit/intel/test_regressions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/intel/test_regressions.py -------------------------------------------------------------------------------- /python/test/unit/language/print_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/print_helper.py -------------------------------------------------------------------------------- /python/test/unit/language/test_core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_core.py -------------------------------------------------------------------------------- /python/test/unit/language/test_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_decorator.py -------------------------------------------------------------------------------- /python/test/unit/language/test_frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_frontend.py -------------------------------------------------------------------------------- /python/test/unit/language/test_libdevice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_libdevice.py -------------------------------------------------------------------------------- /python/test/unit/language/test_line_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_line_info.py -------------------------------------------------------------------------------- /python/test/unit/language/test_matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_matmul.py -------------------------------------------------------------------------------- /python/test/unit/language/test_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_module.py -------------------------------------------------------------------------------- /python/test/unit/language/test_mxfp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_mxfp.py -------------------------------------------------------------------------------- /python/test/unit/language/test_pipeliner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_pipeliner.py -------------------------------------------------------------------------------- /python/test/unit/language/test_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_random.py -------------------------------------------------------------------------------- /python/test/unit/language/test_reproducer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_reproducer.py -------------------------------------------------------------------------------- /python/test/unit/language/test_standard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_standard.py -------------------------------------------------------------------------------- /python/test/unit/language/test_subprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_subprocess.py -------------------------------------------------------------------------------- /python/test/unit/language/test_tuple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/language/test_tuple.py -------------------------------------------------------------------------------- /python/test/unit/plugins/custom_stages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/plugins/custom_stages.py -------------------------------------------------------------------------------- /python/test/unit/plugins/test_plugin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/plugins/test_plugin.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_autotuner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_autotuner.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_bindings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_bindings.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_blaslt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_blaslt.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_build.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_cache.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_driver.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_launch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_launch.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_specialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_specialize.py -------------------------------------------------------------------------------- /python/test/unit/runtime/test_subproc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/runtime/test_subproc.py -------------------------------------------------------------------------------- /python/test/unit/test_debug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_debug.py -------------------------------------------------------------------------------- /python/test/unit/test_debug_dump.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_debug_dump.py -------------------------------------------------------------------------------- /python/test/unit/test_debug_kernels.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_debug_kernels.py -------------------------------------------------------------------------------- /python/test/unit/test_debuginfo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_debuginfo.py -------------------------------------------------------------------------------- /python/test/unit/test_filecheck.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_filecheck.py -------------------------------------------------------------------------------- /python/test/unit/test_knobs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_knobs.py -------------------------------------------------------------------------------- /python/test/unit/test_link.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_link.py -------------------------------------------------------------------------------- /python/test/unit/test_perf_warning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/test_perf_warning.py -------------------------------------------------------------------------------- /python/test/unit/tools/test_aot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/tools/test_aot.py -------------------------------------------------------------------------------- /python/test/unit/tools/test_disasm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/tools/test_disasm.py -------------------------------------------------------------------------------- /python/test/unit/tools/test_irsource.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/tools/test_irsource.py -------------------------------------------------------------------------------- /python/test/unit/tools/test_linear_layout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/test/unit/tools/test_linear_layout.py -------------------------------------------------------------------------------- /python/triton/_C/libtriton/linear_layout.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/_C/libtriton/linear_layout.pyi -------------------------------------------------------------------------------- /python/triton/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/__init__.py -------------------------------------------------------------------------------- /python/triton/_filecheck.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/_filecheck.py -------------------------------------------------------------------------------- /python/triton/_internal_testing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/_internal_testing.py -------------------------------------------------------------------------------- /python/triton/_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/_utils.py -------------------------------------------------------------------------------- /python/triton/backends/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/backends/__init__.py -------------------------------------------------------------------------------- /python/triton/backends/compiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/backends/compiler.py -------------------------------------------------------------------------------- /python/triton/backends/driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/backends/driver.py -------------------------------------------------------------------------------- /python/triton/compiler/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/compiler/__init__.py -------------------------------------------------------------------------------- /python/triton/compiler/code_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/compiler/code_generator.py -------------------------------------------------------------------------------- /python/triton/compiler/compiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/compiler/compiler.py -------------------------------------------------------------------------------- /python/triton/compiler/errors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/compiler/errors.py -------------------------------------------------------------------------------- /python/triton/compiler/make_launcher.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/triton/errors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/errors.py -------------------------------------------------------------------------------- /python/triton/experimental/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/triton/experimental/gluon/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/experimental/gluon/__init__.py -------------------------------------------------------------------------------- /python/triton/experimental/gluon/_compiler.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/triton/experimental/gluon/_runtime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/experimental/gluon/_runtime.py -------------------------------------------------------------------------------- /python/triton/knobs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/knobs.py -------------------------------------------------------------------------------- /python/triton/language/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/__init__.py -------------------------------------------------------------------------------- /python/triton/language/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/core.py -------------------------------------------------------------------------------- /python/triton/language/extra/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/extra/__init__.py -------------------------------------------------------------------------------- /python/triton/language/extra/libdevice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/extra/libdevice.py -------------------------------------------------------------------------------- /python/triton/language/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/math.py -------------------------------------------------------------------------------- /python/triton/language/random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/random.py -------------------------------------------------------------------------------- /python/triton/language/semantic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/semantic.py -------------------------------------------------------------------------------- /python/triton/language/standard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/standard.py -------------------------------------------------------------------------------- /python/triton/language/target_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/language/target_info.py -------------------------------------------------------------------------------- /python/triton/runtime/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/__init__.py -------------------------------------------------------------------------------- /python/triton/runtime/_allocation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/_allocation.py -------------------------------------------------------------------------------- /python/triton/runtime/_async_compile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/_async_compile.py -------------------------------------------------------------------------------- /python/triton/runtime/autotuner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/autotuner.py -------------------------------------------------------------------------------- /python/triton/runtime/build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/build.py -------------------------------------------------------------------------------- /python/triton/runtime/cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/cache.py -------------------------------------------------------------------------------- /python/triton/runtime/driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/driver.py -------------------------------------------------------------------------------- /python/triton/runtime/errors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/errors.py -------------------------------------------------------------------------------- /python/triton/runtime/interpreter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/interpreter.py -------------------------------------------------------------------------------- /python/triton/runtime/jit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/runtime/jit.py -------------------------------------------------------------------------------- /python/triton/testing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/testing.py -------------------------------------------------------------------------------- /python/triton/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/__init__.py -------------------------------------------------------------------------------- /python/triton/tools/build_extern.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/build_extern.py -------------------------------------------------------------------------------- /python/triton/tools/compile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/compile.py -------------------------------------------------------------------------------- /python/triton/tools/disasm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/disasm.py -------------------------------------------------------------------------------- /python/triton/tools/link.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/link.py -------------------------------------------------------------------------------- /python/triton/tools/mxfp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/mxfp.py -------------------------------------------------------------------------------- /python/triton/tools/ragged_tma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/ragged_tma.py -------------------------------------------------------------------------------- /python/triton/tools/tensor_descriptor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton/tools/tensor_descriptor.py -------------------------------------------------------------------------------- /python/triton_kernels/.gitignore: -------------------------------------------------------------------------------- 1 | triton_bench.egg-info/ 2 | -------------------------------------------------------------------------------- /python/triton_kernels/bench/bench_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton_kernels/bench/bench_mlp.py -------------------------------------------------------------------------------- /python/triton_kernels/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton_kernels/pyproject.toml -------------------------------------------------------------------------------- /python/triton_kernels/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/triton_kernels/tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton_kernels/tests/conftest.py -------------------------------------------------------------------------------- /python/triton_kernels/tests/test_mxfp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton_kernels/tests/test_mxfp.py -------------------------------------------------------------------------------- /python/triton_kernels/tests/test_topk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/triton_kernels/tests/test_topk.py -------------------------------------------------------------------------------- /python/triton_kernels/triton_kernels/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/triton_kernels/triton_kernels/numerics_details/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/triton_kernels/triton_kernels/topk_details/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /python/tutorials/01-vector-add.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/01-vector-add.py -------------------------------------------------------------------------------- /python/tutorials/02-fused-softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/02-fused-softmax.py -------------------------------------------------------------------------------- /python/tutorials/04-low-memory-dropout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/04-low-memory-dropout.py -------------------------------------------------------------------------------- /python/tutorials/05-layer-norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/05-layer-norm.py -------------------------------------------------------------------------------- /python/tutorials/06-fused-attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/06-fused-attention.py -------------------------------------------------------------------------------- /python/tutorials/07-extern-functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/07-extern-functions.py -------------------------------------------------------------------------------- /python/tutorials/08-grouped-gemm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/08-grouped-gemm.py -------------------------------------------------------------------------------- /python/tutorials/09-persistent-matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/09-persistent-matmul.py -------------------------------------------------------------------------------- /python/tutorials/README.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/README.rst -------------------------------------------------------------------------------- /python/tutorials/gluon/01-intro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/01-intro.py -------------------------------------------------------------------------------- /python/tutorials/gluon/02-layouts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/02-layouts.py -------------------------------------------------------------------------------- /python/tutorials/gluon/03-async-copy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/03-async-copy.py -------------------------------------------------------------------------------- /python/tutorials/gluon/04-tma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/04-tma.py -------------------------------------------------------------------------------- /python/tutorials/gluon/05-wgmma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/05-wgmma.py -------------------------------------------------------------------------------- /python/tutorials/gluon/06-tcgen05.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/06-tcgen05.py -------------------------------------------------------------------------------- /python/tutorials/gluon/07-persistence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/python/tutorials/gluon/07-persistence.py -------------------------------------------------------------------------------- /scripts/automate_skiplist.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/automate_skiplist.sh -------------------------------------------------------------------------------- /scripts/basekit.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/basekit.yml -------------------------------------------------------------------------------- /scripts/build-llvm-project.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/build-llvm-project.sh -------------------------------------------------------------------------------- /scripts/build_pti_data/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/build_pti_data/CMakeLists.txt -------------------------------------------------------------------------------- /scripts/build_pti_data/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/build_pti_data/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/build_pti_data/pyproject.toml -------------------------------------------------------------------------------- /scripts/capture-hw-details.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/capture-hw-details.sh -------------------------------------------------------------------------------- /scripts/check-update-translator-cid.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/check-update-translator-cid.sh -------------------------------------------------------------------------------- /scripts/check_inductor_report.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/check_inductor_report.py -------------------------------------------------------------------------------- /scripts/compare-ci-runs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/compare-ci-runs/README.md -------------------------------------------------------------------------------- /scripts/compare-ci-runs/compare_runs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/compare-ci-runs/compare_runs.py -------------------------------------------------------------------------------- /scripts/compare-ci-runs/requirements.txt: -------------------------------------------------------------------------------- 1 | matplotlib 2 | pandas 3 | seaborn 4 | -------------------------------------------------------------------------------- /scripts/compile-triton.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/compile-triton.sh -------------------------------------------------------------------------------- /scripts/docs-triton.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/docs-triton.sh -------------------------------------------------------------------------------- /scripts/e2e_checks/compare_reference.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/e2e_checks/compare_reference.sh -------------------------------------------------------------------------------- /scripts/flash_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/flash_attention.py -------------------------------------------------------------------------------- /scripts/get_failed_cases.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/get_failed_cases.py -------------------------------------------------------------------------------- /scripts/inductor_xpu_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/inductor_xpu_test.sh -------------------------------------------------------------------------------- /scripts/install-pti.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/install-pti.sh -------------------------------------------------------------------------------- /scripts/install-pytorch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/install-pytorch.sh -------------------------------------------------------------------------------- /scripts/llvm_igc_debug.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/llvm_igc_debug.sh -------------------------------------------------------------------------------- /scripts/pass_rate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/pass_rate.py -------------------------------------------------------------------------------- /scripts/patch-pytorch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/patch-pytorch.sh -------------------------------------------------------------------------------- /scripts/pti_lib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/pti_lib.py -------------------------------------------------------------------------------- /scripts/pytest-utils.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/pytest-utils.sh -------------------------------------------------------------------------------- /scripts/requirements-test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/requirements-test.txt -------------------------------------------------------------------------------- /scripts/run_tutorial.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/run_tutorial.py -------------------------------------------------------------------------------- /scripts/skiplist/.gitignore: -------------------------------------------------------------------------------- 1 | current/ 2 | -------------------------------------------------------------------------------- /scripts/skiplist/a770/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/a770/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/intel.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/intel.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/interpreter.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/a770/language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/language.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/mxfp.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/mxfp.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/scaled_dot.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/scaled_dot.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/subprocess.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/subprocess.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/tools.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/a770/triton_kernels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/triton_kernels.txt -------------------------------------------------------------------------------- /scripts/skiplist/a770/tutorials.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/a770/tutorials.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/intel.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/intel.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/interpreter.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/language.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/mxfp.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/mxfp.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/scaled_dot.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/scaled_dot.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/subprocess.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/subprocess.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/triton_kernels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/triton_kernels.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-h/tutorials.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-h/tutorials.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/intel.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/intel.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/interpreter.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/language.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/mxfp.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/mxfp.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/scaled_dot.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/scaled_dot.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/subprocess.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/subprocess.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/triton_kernels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/triton_kernels.txt -------------------------------------------------------------------------------- /scripts/skiplist/arl-s/tutorials.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/arl-s/tutorials.txt -------------------------------------------------------------------------------- /scripts/skiplist/default/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/default/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/default/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/default/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/default/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/default/language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/default/language.txt -------------------------------------------------------------------------------- /scripts/skiplist/default/triton_kernels.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/lts/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/lts/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/lts/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/lts/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/lts/language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/lts/language.txt -------------------------------------------------------------------------------- /scripts/skiplist/lts/triton_kernels.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/mtl/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/mtl/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/mtl/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/mtl/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/mtl/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/mtl/language.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/mtl/language.txt -------------------------------------------------------------------------------- /scripts/skiplist/mtl/scaled_dot.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/mtl/scaled_dot.txt -------------------------------------------------------------------------------- /scripts/skiplist/mtl/triton_kernels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/mtl/triton_kernels.txt -------------------------------------------------------------------------------- /scripts/skiplist/mtl/tutorials.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/mtl/tutorials.txt -------------------------------------------------------------------------------- /scripts/skiplist/xe2/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/xe2/debug.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/xe2/debug.txt -------------------------------------------------------------------------------- /scripts/skiplist/xe2/gluon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/skiplist/xe2/gluon.txt -------------------------------------------------------------------------------- /scripts/skiplist/xe2/language.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/xe2/tools.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/xe2/triton_kernels.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/skiplist/xe2/tutorials.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/sycl_rt_lib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/sycl_rt_lib.py -------------------------------------------------------------------------------- /scripts/test-pytorch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/test-pytorch.sh -------------------------------------------------------------------------------- /scripts/test-triton.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/test-triton.sh -------------------------------------------------------------------------------- /scripts/test_pass_rate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/test_pass_rate.py -------------------------------------------------------------------------------- /scripts/torch_cmake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/torch_cmake.py -------------------------------------------------------------------------------- /scripts/triton-opt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/triton-opt.sh -------------------------------------------------------------------------------- /scripts/triton-version.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/triton-version.sh -------------------------------------------------------------------------------- /scripts/triton.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/scripts/triton.yml -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/setup.py -------------------------------------------------------------------------------- /test/Analysis/amd/test-alignment.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/amd/test-alignment.mlir -------------------------------------------------------------------------------- /test/Analysis/intel/test-axis-info.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/intel/test-axis-info.mlir -------------------------------------------------------------------------------- /test/Analysis/test-alias.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/test-alias.mlir -------------------------------------------------------------------------------- /test/Analysis/test-alignment.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/test-alignment.mlir -------------------------------------------------------------------------------- /test/Analysis/test-allocation.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/test-allocation.mlir -------------------------------------------------------------------------------- /test/Analysis/test-liveness.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/test-liveness.mlir -------------------------------------------------------------------------------- /test/Analysis/test-membar-ttng.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/test-membar-ttng.mlir -------------------------------------------------------------------------------- /test/Analysis/test-membar.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Analysis/test-membar.mlir -------------------------------------------------------------------------------- /test/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/CMakeLists.txt -------------------------------------------------------------------------------- /test/Conversion/allocate_warp_groups.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/allocate_warp_groups.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/amdgpu_membar.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/amdgpu_membar.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/cluster_load.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/cluster_load.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/compute-base-ptr.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/compute-base-ptr.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/convert_layout.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/convert_layout.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/ds_transpose.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/ds_transpose.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/fp_to_fp.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/fp_to_fp.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/load_store.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/load_store.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/mfma-shortcut.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/mfma-shortcut.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/minmax.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/minmax.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/upcast_mxfp.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/upcast_mxfp.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/wmma-v1-shortcut.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/wmma-v1-shortcut.mlir -------------------------------------------------------------------------------- /test/Conversion/amd/wmma-v2-shortcut.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/amd/wmma-v2-shortcut.mlir -------------------------------------------------------------------------------- /test/Conversion/atomic_ldst.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/atomic_ldst.mlir -------------------------------------------------------------------------------- /test/Conversion/cvt_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/cvt_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/dedup-by-constancy.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/dedup-by-constancy.mlir -------------------------------------------------------------------------------- /test/Conversion/divide-by-0.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/divide-by-0.mlir -------------------------------------------------------------------------------- /test/Conversion/intel/arith_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/intel/arith_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/nvgpu_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/nvgpu_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/reduce_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/reduce_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/relayout_tritongpu.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/relayout_tritongpu.mlir -------------------------------------------------------------------------------- /test/Conversion/scan_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/scan_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/tma_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/tma_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/triton_to_tritongpu.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/triton_to_tritongpu.mlir -------------------------------------------------------------------------------- /test/Conversion/tritongpu_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/tritongpu_to_llvm.mlir -------------------------------------------------------------------------------- /test/Conversion/tritongpu_to_ptx.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Conversion/tritongpu_to_ptx.mlir -------------------------------------------------------------------------------- /test/Gluon/auto_encoding.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Gluon/auto_encoding.mlir -------------------------------------------------------------------------------- /test/Gluon/infer_coalesced_encoding.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Gluon/infer_coalesced_encoding.mlir -------------------------------------------------------------------------------- /test/Gluon/inlining.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Gluon/inlining.mlir -------------------------------------------------------------------------------- /test/Gluon/invalid_auto_encoding.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Gluon/invalid_auto_encoding.mlir -------------------------------------------------------------------------------- /test/Hopper/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(WarpSpecialization) 2 | -------------------------------------------------------------------------------- /test/LLVMIR/break-phi-struct.ll: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/LLVMIR/break-phi-struct.ll -------------------------------------------------------------------------------- /test/LLVMIR/freeze-masked-div-rem.ll: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/LLVMIR/freeze-masked-div-rem.ll -------------------------------------------------------------------------------- /test/LLVMIR/insert-dbg-intrinsic.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/LLVMIR/insert-dbg-intrinsic.mlir -------------------------------------------------------------------------------- /test/NVWS/aref-tmem-insertion.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/aref-tmem-insertion.mlir -------------------------------------------------------------------------------- /test/NVWS/assign_stage_phase.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/assign_stage_phase.mlir -------------------------------------------------------------------------------- /test/NVWS/insert_aref.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/insert_aref.mlir -------------------------------------------------------------------------------- /test/NVWS/invalid.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/invalid.mlir -------------------------------------------------------------------------------- /test/NVWS/lower_aref.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/lower_aref.mlir -------------------------------------------------------------------------------- /test/NVWS/lower_warp_group.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/lower_warp_group.mlir -------------------------------------------------------------------------------- /test/NVWS/ops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/NVWS/ops.mlir -------------------------------------------------------------------------------- /test/Plugins/test-plugin.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Plugins/test-plugin.mlir -------------------------------------------------------------------------------- /test/Proton/allocate_shared_memory.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/allocate_shared_memory.mlir -------------------------------------------------------------------------------- /test/Proton/amd/add_sched_barriers.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/amd/add_sched_barriers.mlir -------------------------------------------------------------------------------- /test/Proton/amd/protongpu_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/amd/protongpu_to_llvm.mlir -------------------------------------------------------------------------------- /test/Proton/nvidia/protongpu_to_llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/nvidia/protongpu_to_llvm.mlir -------------------------------------------------------------------------------- /test/Proton/ops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/ops.mlir -------------------------------------------------------------------------------- /test/Proton/proton_to_protongpu.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/proton_to_protongpu.mlir -------------------------------------------------------------------------------- /test/Proton/protongpu_transforms.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/protongpu_transforms.mlir -------------------------------------------------------------------------------- /test/Proton/scope_id.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Proton/scope_id.mlir -------------------------------------------------------------------------------- /test/Target/LLVMIR/triton-gen.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Target/LLVMIR/triton-gen.mlir -------------------------------------------------------------------------------- /test/Tools/tensor_layout_print.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Tools/tensor_layout_print.mlir -------------------------------------------------------------------------------- /test/Triton/canonicalize.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/canonicalize.mlir -------------------------------------------------------------------------------- /test/Triton/combine.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/combine.mlir -------------------------------------------------------------------------------- /test/Triton/invalid.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/invalid.mlir -------------------------------------------------------------------------------- /test/Triton/loop-peeling.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/loop-peeling.mlir -------------------------------------------------------------------------------- /test/Triton/loop-unroll.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/loop-unroll.mlir -------------------------------------------------------------------------------- /test/Triton/loop_cse.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/loop_cse.mlir -------------------------------------------------------------------------------- /test/Triton/ops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/ops.mlir -------------------------------------------------------------------------------- /test/Triton/reorder-broadcast.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/reorder-broadcast.mlir -------------------------------------------------------------------------------- /test/Triton/reproducer.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/reproducer.mlir -------------------------------------------------------------------------------- /test/Triton/rewrite-tensor-pointer.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/rewrite-tensor-pointer.mlir -------------------------------------------------------------------------------- /test/Triton/vecadd.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/vecadd.mlir -------------------------------------------------------------------------------- /test/Triton/verify-make-range.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/Triton/verify-make-range.mlir -------------------------------------------------------------------------------- /test/TritonGEN/tritongen-invalid.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGEN/tritongen-invalid.mlir -------------------------------------------------------------------------------- /test/TritonGEN/tritongen-to-llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGEN/tritongen-to-llvm.mlir -------------------------------------------------------------------------------- /test/TritonGEN/tritongen-to-spirv.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGEN/tritongen-to-spirv.mlir -------------------------------------------------------------------------------- /test/TritonGEN/tritongen.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGEN/tritongen.mlir -------------------------------------------------------------------------------- /test/TritonGPU/accelerate-matmul.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/accelerate-matmul.mlir -------------------------------------------------------------------------------- /test/TritonGPU/accumulator-init.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/accumulator-init.mlir -------------------------------------------------------------------------------- /test/TritonGPU/amd/amd-concat-op.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/amd/amd-concat-op.mlir -------------------------------------------------------------------------------- /test/TritonGPU/amd/amd-schedule-hint.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/amd/amd-schedule-hint.mlir -------------------------------------------------------------------------------- /test/TritonGPU/amd/invalid.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/amd/invalid.mlir -------------------------------------------------------------------------------- /test/TritonGPU/amd/mfma-double-rate.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/amd/mfma-double-rate.mlir -------------------------------------------------------------------------------- /test/TritonGPU/amd/mfma-xf32.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/amd/mfma-xf32.mlir -------------------------------------------------------------------------------- /test/TritonGPU/amd/sink-setprio-mfma.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/amd/sink-setprio-mfma.mlir -------------------------------------------------------------------------------- /test/TritonGPU/atomic-cas.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/atomic-cas.mlir -------------------------------------------------------------------------------- /test/TritonGPU/bf16x3-matmul.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/bf16x3-matmul.mlir -------------------------------------------------------------------------------- /test/TritonGPU/canonicalize.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/canonicalize.mlir -------------------------------------------------------------------------------- /test/TritonGPU/coalesce-async-copy.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/coalesce-async-copy.mlir -------------------------------------------------------------------------------- /test/TritonGPU/coalesce.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/coalesce.mlir -------------------------------------------------------------------------------- /test/TritonGPU/combine-select-if.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/combine-select-if.mlir -------------------------------------------------------------------------------- /test/TritonGPU/combine.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/combine.mlir -------------------------------------------------------------------------------- /test/TritonGPU/consan-negative.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/consan-negative.mlir -------------------------------------------------------------------------------- /test/TritonGPU/consan.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/consan.mlir -------------------------------------------------------------------------------- /test/TritonGPU/dot-operands.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/dot-operands.mlir -------------------------------------------------------------------------------- /test/TritonGPU/fence-inserstion.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/fence-inserstion.mlir -------------------------------------------------------------------------------- /test/TritonGPU/fuse-nested-loops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/fuse-nested-loops.mlir -------------------------------------------------------------------------------- /test/TritonGPU/global_scratch_alloc.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/global_scratch_alloc.mlir -------------------------------------------------------------------------------- /test/TritonGPU/hoist-tmem-alloc.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/hoist-tmem-alloc.mlir -------------------------------------------------------------------------------- /test/TritonGPU/inline.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/inline.mlir -------------------------------------------------------------------------------- /test/TritonGPU/invalid-attributes.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/invalid-attributes.mlir -------------------------------------------------------------------------------- /test/TritonGPU/invalid.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/invalid.mlir -------------------------------------------------------------------------------- /test/TritonGPU/loop-pipeline-cuda.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/loop-pipeline-cuda.mlir -------------------------------------------------------------------------------- /test/TritonGPU/loop-pipeline-expand.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/loop-pipeline-expand.mlir -------------------------------------------------------------------------------- /test/TritonGPU/loop-pipeline-hip.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/loop-pipeline-hip.mlir -------------------------------------------------------------------------------- /test/TritonGPU/loop-pipeline-hopper.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/loop-pipeline-hopper.mlir -------------------------------------------------------------------------------- /test/TritonGPU/loop-pipeline.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/loop-pipeline.mlir -------------------------------------------------------------------------------- /test/TritonGPU/loop-schedule.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/loop-schedule.mlir -------------------------------------------------------------------------------- /test/TritonGPU/matmul-loop-pipeline.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/matmul-loop-pipeline.mlir -------------------------------------------------------------------------------- /test/TritonGPU/matmul.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/matmul.mlir -------------------------------------------------------------------------------- /test/TritonGPU/memdesc-subview-split.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/memdesc-subview-split.mlir -------------------------------------------------------------------------------- /test/TritonGPU/ops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/ops.mlir -------------------------------------------------------------------------------- /test/TritonGPU/optimize-locality.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/optimize-locality.mlir -------------------------------------------------------------------------------- /test/TritonGPU/optimize_epilogue.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/optimize_epilogue.mlir -------------------------------------------------------------------------------- /test/TritonGPU/partition-loops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/partition-loops.mlir -------------------------------------------------------------------------------- /test/TritonGPU/partition-scheduling.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/partition-scheduling.mlir -------------------------------------------------------------------------------- /test/TritonGPU/pipeline-loop-nest.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/pipeline-loop-nest.mlir -------------------------------------------------------------------------------- /test/TritonGPU/pipeline-lower-loop.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/pipeline-lower-loop.mlir -------------------------------------------------------------------------------- /test/TritonGPU/prefetch.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/prefetch.mlir -------------------------------------------------------------------------------- /test/TritonGPU/promote-lhs-to-tmem.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/promote-lhs-to-tmem.mlir -------------------------------------------------------------------------------- /test/TritonGPU/prox_fence_insertion.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/prox_fence_insertion.mlir -------------------------------------------------------------------------------- /test/TritonGPU/reorder-instructions.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/reorder-instructions.mlir -------------------------------------------------------------------------------- /test/TritonGPU/tf32x3-matmul.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/tf32x3-matmul.mlir -------------------------------------------------------------------------------- /test/TritonGPU/verify-blocked-layout.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonGPU/verify-blocked-layout.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/atomic_cas.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/atomic_cas.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/blockptr_load.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/blockptr_load.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/blockptr_store.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/blockptr_store.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/coalesce.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/coalesce.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/combine.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/combine.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/dot-operands.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/dot-operands.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/fp4tofp.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/fp4tofp.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/loop-pipeline.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/loop-pipeline.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/prefetch-to-llvm.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/prefetch-to-llvm.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/split-barrier.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/split-barrier.mlir -------------------------------------------------------------------------------- /test/TritonIntelGPU/tritonintelgpu.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonIntelGPU/tritonintelgpu.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/bf16-atomics.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/bf16-atomics.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/canonicalize.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/canonicalize.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/inline.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/inline.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/interleave_tmem.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/interleave_tmem.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/invalid.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/invalid.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/membar.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/membar.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/mma_lowering.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/mma_lowering.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/ops.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/ops.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/tma_lowering.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/tma_lowering.mlir -------------------------------------------------------------------------------- /test/TritonNvidiaGPU/tmem_layouts.mlir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/TritonNvidiaGPU/tmem_layouts.mlir -------------------------------------------------------------------------------- /test/include/Analysis/TestAxisInfo.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/include/Analysis/TestAxisInfo.h -------------------------------------------------------------------------------- /test/lib/Analysis/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Analysis/CMakeLists.txt -------------------------------------------------------------------------------- /test/lib/Analysis/TestAlias.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Analysis/TestAlias.cpp -------------------------------------------------------------------------------- /test/lib/Analysis/TestAllocation.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Analysis/TestAllocation.cpp -------------------------------------------------------------------------------- /test/lib/Analysis/TestAxisInfo.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Analysis/TestAxisInfo.cpp -------------------------------------------------------------------------------- /test/lib/Analysis/TestMembar.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Analysis/TestMembar.cpp -------------------------------------------------------------------------------- /test/lib/Analysis/intel/TestAxisInfo.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Analysis/intel/TestAxisInfo.cpp -------------------------------------------------------------------------------- /test/lib/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/CMakeLists.txt -------------------------------------------------------------------------------- /test/lib/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Dialect/CMakeLists.txt -------------------------------------------------------------------------------- /test/lib/Dialect/TestLoopPeeling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Dialect/TestLoopPeeling.cpp -------------------------------------------------------------------------------- /test/lib/Instrumentation/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Instrumentation/CMakeLists.txt -------------------------------------------------------------------------------- /test/lib/Instrumentation/GPUHello.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Instrumentation/GPUHello.cpp -------------------------------------------------------------------------------- /test/lib/Proton/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Proton/CMakeLists.txt -------------------------------------------------------------------------------- /test/lib/Proton/TestScopeIdAllocation.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lib/Proton/TestScopeIdAllocation.cpp -------------------------------------------------------------------------------- /test/lit.cfg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lit.cfg.py -------------------------------------------------------------------------------- /test/lit.site.cfg.py.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/test/lit.site.cfg.py.in -------------------------------------------------------------------------------- /third-party-programs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third-party-programs.txt -------------------------------------------------------------------------------- /third_party/amd/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/amd/backend/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /third_party/amd/backend/compiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/compiler.py -------------------------------------------------------------------------------- /third_party/amd/backend/driver.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/driver.c -------------------------------------------------------------------------------- /third_party/amd/backend/driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/driver.py -------------------------------------------------------------------------------- /third_party/amd/backend/include/hsa/hsa.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/include/hsa/hsa.h -------------------------------------------------------------------------------- /third_party/amd/backend/lib/asanrtl.bc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/lib/asanrtl.bc -------------------------------------------------------------------------------- /third_party/amd/backend/lib/ockl.bc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/lib/ockl.bc -------------------------------------------------------------------------------- /third_party/amd/backend/lib/ocml.bc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/backend/lib/ocml.bc -------------------------------------------------------------------------------- /third_party/amd/include/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/include/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/amd/include/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonAMDGPU) 2 | -------------------------------------------------------------------------------- /third_party/amd/include/Dialect/TritonAMDGPU/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/amd/include/Utils/Utility.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/include/Utils/Utility.h -------------------------------------------------------------------------------- /third_party/amd/include/hipblas_types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/include/hipblas_types.h -------------------------------------------------------------------------------- /third_party/amd/language/hip/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/language/hip/__init__.py -------------------------------------------------------------------------------- /third_party/amd/language/hip/libdevice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/language/hip/libdevice.py -------------------------------------------------------------------------------- /third_party/amd/language/hip/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/language/hip/utils.py -------------------------------------------------------------------------------- /third_party/amd/lib/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/lib/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/amd/lib/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonAMDGPU) 2 | -------------------------------------------------------------------------------- /third_party/amd/python/test/attn_fwd.ttir: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/python/test/attn_fwd.ttir -------------------------------------------------------------------------------- /third_party/amd/python/test/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/python/test/conftest.py -------------------------------------------------------------------------------- /third_party/amd/python/triton_amd.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/python/triton_amd.cc -------------------------------------------------------------------------------- /third_party/amd/test/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(lib) 2 | -------------------------------------------------------------------------------- /third_party/amd/test/lib/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Analysis) 2 | -------------------------------------------------------------------------------- /third_party/amd/tools/hip/compile.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/tools/hip/compile.cpp -------------------------------------------------------------------------------- /third_party/amd/tools/hip/compile.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/amd/tools/hip/compile.h -------------------------------------------------------------------------------- /third_party/amd/unittest/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Conversion) 2 | -------------------------------------------------------------------------------- /third_party/f2reduce/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/f2reduce/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/f2reduce/LICENCE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/f2reduce/LICENCE.txt -------------------------------------------------------------------------------- /third_party/f2reduce/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/f2reduce/README.md -------------------------------------------------------------------------------- /third_party/f2reduce/VERSION: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/f2reduce/VERSION -------------------------------------------------------------------------------- /third_party/f2reduce/f2reduce.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/f2reduce/f2reduce.cpp -------------------------------------------------------------------------------- /third_party/f2reduce/f2reduce.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/f2reduce/f2reduce.h -------------------------------------------------------------------------------- /third_party/intel/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/intel/backend/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /third_party/intel/backend/arch_parser.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/backend/arch_parser.c -------------------------------------------------------------------------------- /third_party/intel/backend/compiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/backend/compiler.py -------------------------------------------------------------------------------- /third_party/intel/backend/driver.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/backend/driver.c -------------------------------------------------------------------------------- /third_party/intel/backend/driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/backend/driver.py -------------------------------------------------------------------------------- /third_party/intel/backend/track.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/backend/track.py -------------------------------------------------------------------------------- /third_party/intel/bin/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/bin/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/intel/cmake/3122.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/cmake/3122.patch -------------------------------------------------------------------------------- /third_party/intel/cmake/3388.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/cmake/3388.patch -------------------------------------------------------------------------------- /third_party/intel/cmake/3462.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/cmake/3462.patch -------------------------------------------------------------------------------- /third_party/intel/include/Analysis/DPAS.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/include/Analysis/DPAS.h -------------------------------------------------------------------------------- /third_party/intel/include/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/include/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/intel/include/Dialect/Triton/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Transforms) 2 | -------------------------------------------------------------------------------- /third_party/intel/include/Dialect/TritonGEN/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/intel/include/Utils/Utility.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/include/Utils/Utility.h -------------------------------------------------------------------------------- /third_party/intel/language/intel/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/language/intel/utils.py -------------------------------------------------------------------------------- /third_party/intel/lib/Analysis/DPAS.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Analysis/DPAS.cpp -------------------------------------------------------------------------------- /third_party/intel/lib/Analysis/Membar.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Analysis/Membar.cpp -------------------------------------------------------------------------------- /third_party/intel/lib/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/intel/lib/Dialect/Triton/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Transforms) 2 | -------------------------------------------------------------------------------- /third_party/intel/lib/Dialect/TritonGEN/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/intel/lib/Dialect/TritonIntelGPU/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/intel/lib/Target/LLVMIR/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonGEN) 2 | -------------------------------------------------------------------------------- /third_party/intel/lib/Target/SPIRV/spirv-llvm-translator.conf: -------------------------------------------------------------------------------- 1 | a726c62f8456c1eda0c1a689c24b95a7e7c95040 2 | -------------------------------------------------------------------------------- /third_party/intel/lib/Utils/LLVMIntr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Utils/LLVMIntr.cpp -------------------------------------------------------------------------------- /third_party/intel/lib/Utils/LLVMIntr.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Utils/LLVMIntr.h -------------------------------------------------------------------------------- /third_party/intel/lib/Utils/Mangling.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Utils/Mangling.cpp -------------------------------------------------------------------------------- /third_party/intel/lib/Utils/Mangling.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Utils/Mangling.h -------------------------------------------------------------------------------- /third_party/intel/lib/Utils/Utility.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/lib/Utils/Utility.cpp -------------------------------------------------------------------------------- /third_party/intel/python/test/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/python/test/conftest.py -------------------------------------------------------------------------------- /third_party/intel/tools/intel/compile.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/tools/intel/compile.cpp -------------------------------------------------------------------------------- /third_party/intel/tools/intel/compile.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/tools/intel/compile.h -------------------------------------------------------------------------------- /third_party/intel/triton_xpu.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/triton_xpu.cc -------------------------------------------------------------------------------- /third_party/intel/unittest/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/intel/unittest/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/intel/unittest/Conversion/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonIntelGPUToLLVM) 2 | -------------------------------------------------------------------------------- /third_party/intel/unittest/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonIntelGPU) 2 | -------------------------------------------------------------------------------- /third_party/nvidia/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/nvidia/backend/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /third_party/nvidia/backend/compiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/backend/compiler.py -------------------------------------------------------------------------------- /third_party/nvidia/backend/driver.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/backend/driver.c -------------------------------------------------------------------------------- /third_party/nvidia/backend/driver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/backend/driver.py -------------------------------------------------------------------------------- /third_party/nvidia/hopper/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/hopper/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/nvidia/hopper/include/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Transforms) 2 | -------------------------------------------------------------------------------- /third_party/nvidia/hopper/lib/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Transforms) 2 | -------------------------------------------------------------------------------- /third_party/nvidia/include/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/include/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/nvidia/include/Dialect/NVGPU/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/nvidia/include/cublas_types.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/include/cublas_types.h -------------------------------------------------------------------------------- /third_party/nvidia/language/cuda/gdc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/language/cuda/gdc.py -------------------------------------------------------------------------------- /third_party/nvidia/language/cuda/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/language/cuda/utils.py -------------------------------------------------------------------------------- /third_party/nvidia/lib/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/lib/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/nvidia/lib/Dialect/NVGPU/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/nvidia/tools/cuda/compile.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/tools/cuda/compile.c -------------------------------------------------------------------------------- /third_party/nvidia/tools/cuda/compile.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/tools/cuda/compile.h -------------------------------------------------------------------------------- /third_party/nvidia/triton_nvidia.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/nvidia/triton_nvidia.cc -------------------------------------------------------------------------------- /third_party/nvidia/unittest/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(Conversion) 2 | -------------------------------------------------------------------------------- /third_party/nvidia/unittest/Conversion/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonGPUToLLVM) 2 | -------------------------------------------------------------------------------- /third_party/proton/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/.gitignore -------------------------------------------------------------------------------- /third_party/proton/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/proton/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/Dialect/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/proton/Dialect/include/Dialect/Proton/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/proton/Dialect/lib/Dialect/Proton/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(IR) 2 | -------------------------------------------------------------------------------- /third_party/proton/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/README.md -------------------------------------------------------------------------------- /third_party/proton/common/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(lib) 2 | -------------------------------------------------------------------------------- /third_party/proton/common/lib/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TraceDataIO) 2 | -------------------------------------------------------------------------------- /third_party/proton/csrc/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/csrc/CMakeLists.txt -------------------------------------------------------------------------------- /third_party/proton/csrc/Proton.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/csrc/Proton.cpp -------------------------------------------------------------------------------- /third_party/proton/csrc/include/Proton.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/csrc/include/Proton.h -------------------------------------------------------------------------------- /third_party/proton/csrc/lib/Data/Data.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/csrc/lib/Data/Data.cpp -------------------------------------------------------------------------------- /third_party/proton/proton/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/__init__.py -------------------------------------------------------------------------------- /third_party/proton/proton/context.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/context.py -------------------------------------------------------------------------------- /third_party/proton/proton/flags.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/flags.py -------------------------------------------------------------------------------- /third_party/proton/proton/hooks/hook.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/hooks/hook.py -------------------------------------------------------------------------------- /third_party/proton/proton/hooks/launch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/hooks/launch.py -------------------------------------------------------------------------------- /third_party/proton/proton/language.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/language.py -------------------------------------------------------------------------------- /third_party/proton/proton/mode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/mode.py -------------------------------------------------------------------------------- /third_party/proton/proton/profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/profile.py -------------------------------------------------------------------------------- /third_party/proton/proton/proton.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/proton.py -------------------------------------------------------------------------------- /third_party/proton/proton/scope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/scope.py -------------------------------------------------------------------------------- /third_party/proton/proton/specs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/specs.py -------------------------------------------------------------------------------- /third_party/proton/proton/state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/state.py -------------------------------------------------------------------------------- /third_party/proton/proton/viewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/proton/viewer.py -------------------------------------------------------------------------------- /third_party/proton/scripts/dump_ttgir.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/scripts/dump_ttgir.sh -------------------------------------------------------------------------------- /third_party/proton/test/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | if(TRITON_BUILD_UT) 2 | add_subdirectory(unittest) 3 | endif() 4 | -------------------------------------------------------------------------------- /third_party/proton/test/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/conftest.py -------------------------------------------------------------------------------- /third_party/proton/test/examples/hip.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/examples/hip.json -------------------------------------------------------------------------------- /third_party/proton/test/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/helper.py -------------------------------------------------------------------------------- /third_party/proton/test/helper_kernels.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/helper_kernels.py -------------------------------------------------------------------------------- /third_party/proton/test/instrument.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/instrument.py -------------------------------------------------------------------------------- /third_party/proton/test/test_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/test_api.py -------------------------------------------------------------------------------- /third_party/proton/test/test_cmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/test_cmd.py -------------------------------------------------------------------------------- /third_party/proton/test/test_lib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/test_lib.py -------------------------------------------------------------------------------- /third_party/proton/test/test_override.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/test_override.py -------------------------------------------------------------------------------- /third_party/proton/test/test_profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/test_profile.py -------------------------------------------------------------------------------- /third_party/proton/test/test_viewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/test/test_viewer.py -------------------------------------------------------------------------------- /third_party/proton/test/unittest/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TraceDataIO) 2 | -------------------------------------------------------------------------------- /third_party/proton/tutorials/matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/third_party/proton/tutorials/matmul.py -------------------------------------------------------------------------------- /unittest/Analysis/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/Analysis/CMakeLists.txt -------------------------------------------------------------------------------- /unittest/Analysis/UtilityTest.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/Analysis/UtilityTest.cpp -------------------------------------------------------------------------------- /unittest/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/CMakeLists.txt -------------------------------------------------------------------------------- /unittest/Dialect/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | add_subdirectory(TritonGPU) 2 | -------------------------------------------------------------------------------- /unittest/Dialect/TritonGPU/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/Dialect/TritonGPU/CMakeLists.txt -------------------------------------------------------------------------------- /unittest/Tools/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/Tools/CMakeLists.txt -------------------------------------------------------------------------------- /unittest/Tools/LayoutUtilsTest.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/Tools/LayoutUtilsTest.cpp -------------------------------------------------------------------------------- /unittest/Tools/LinearLayoutTest.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/Tools/LinearLayoutTest.cpp -------------------------------------------------------------------------------- /unittest/googletest.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/unittest/googletest.cmake -------------------------------------------------------------------------------- /utils/SPIRVRunner/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/CMakeLists.txt -------------------------------------------------------------------------------- /utils/SPIRVRunner/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/README.md -------------------------------------------------------------------------------- /utils/SPIRVRunner/SPIRVRunner.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/SPIRVRunner.cpp -------------------------------------------------------------------------------- /utils/SPIRVRunner/llvm_parser.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/llvm_parser.cpp -------------------------------------------------------------------------------- /utils/SPIRVRunner/llvm_parser.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/llvm_parser.h -------------------------------------------------------------------------------- /utils/SPIRVRunner/tests/dot/kernel.spv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/tests/dot/kernel.spv -------------------------------------------------------------------------------- /utils/SPIRVRunner/tests/dot/tensor_0.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/tests/dot/tensor_0.pt -------------------------------------------------------------------------------- /utils/SPIRVRunner/tests/dot/tensor_1.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/tests/dot/tensor_1.pt -------------------------------------------------------------------------------- /utils/SPIRVRunner/tests/dot/tensor_2.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/tests/dot/tensor_2.pt -------------------------------------------------------------------------------- /utils/SPIRVRunner/tests/dot/tensor_3.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/SPIRVRunner/tests/dot/tensor_3.pt -------------------------------------------------------------------------------- /utils/generate-test-checks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/generate-test-checks.py -------------------------------------------------------------------------------- /utils/nightly.pypirc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/intel-xpu-backend-for-triton/HEAD/utils/nightly.pypirc --------------------------------------------------------------------------------