Functions — github.com/Tencent/hpc-ops

CodeHub MCPcopy Create free account

hub / github.com/Tencent/hpc-ops / functions

Functions10,542 in github.com/Tencent/hpc-ops

⨍ Functions 10,542◇ Types & classes 8,025↳ Endpoints 13

FunctionCollectiveMma

3rd/cutlass/include/cutlass/gemm/collective/sm103_blockscaled_mma_warpspecialized.hpp:390

MethodCollectiveMma

3rd/cutlass/include/cutlass/gemm/collective/sm80_mma_multistage.hpp:144

MethodCollectiveMma

3rd/cutlass/include/cutlass/gemm/collective/sm80_mma_multistage.hpp:447

MethodCollectiveMma

3rd/cutlass/include/cutlass/gemm/collective/sm70_mma_twostage.hpp:139

MethodCollectiveMma

3rd/cutlass/include/cutlass/gemm/collective/sm70_mma_twostage.hpp:384

MethodCollectiveMma

3rd/cutlass/include/cutlass/gemm/collective/sm80_mma_array_multistage.hpp:153

MethodColumnMajor

3rd/cutlass/include/cutlass/layout/matrix.h:184

MethodColumnMajor, 1>

3rd/cutlass/include/cutlass/arch/memory_sm75.h:151

MethodColumnMajor, 2>

3rd/cutlass/include/cutlass/arch/memory_sm75.h:175

MethodColumnMajor, 4>

3rd/cutlass/include/cutlass/arch/memory_sm75.h:199

MethodColumnMajorBlockLinear

3rd/cutlass/include/cutlass/layout/matrix.h:1033

MethodColumnMajorInterleaved

3rd/cutlass/include/cutlass/layout/matrix.h:388

MethodColumnMajorTensorOpMultiplicand64bCrosswise

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm80.h:469

MethodColumnMajorTensorOpMultiplicandCongruous

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm75.h:497

MethodColumnMajorTensorOpMultiplicandCongruous128b

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm80.h:736

MethodColumnMajorTensorOpMultiplicandCongruous64b

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm80.h:191

MethodColumnMajorTensorOpMultiplicandCrosswise

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm75.h:809

MethodColumnMajorTensorOpMultiplicandCrosswise128x4

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm80.h:1012

MethodColumnMajorVoltaTensorOpMultiplicandBCongruous

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm70.h:589

MethodColumnMajorVoltaTensorOpMultiplicandCongruous

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm70.h:252

MethodColumnMajorVoltaTensorOpMultiplicandCrosswise

3rd/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm70.h:903

MethodCommunicator

src/communicator/communicator.cc:17

MethodComposedLayout

3rd/cutlass/include/cute/layout_composed.hpp:56

src/communicator/connector.cc:86

MethodConnector

src/communicator/connector.cc:27

FunctionConstSubbyteReference operator+

Returns a reference to an element with a given offset from the current reference

3rd/cutlass/include/cutlass/subbyte_reference.h:259

FunctionConstSubbyteReference operator-

Returns a reference to an element with a given offset from the current reference

3rd/cutlass/include/cutlass/subbyte_reference.h:279

FunctionConstSubbyteReference operator-=

Returns a reference to an element with a given offset from the current reference

3rd/cutlass/include/cutlass/subbyte_reference.h:289

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_compute_tma_warpspecialized.hpp:165

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_tma_warpspecialized.hpp:590

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_tma_warpspecialized.hpp:639

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_tma_warpspecialized.hpp:690

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_load_tma_warpspecialized.hpp:112

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_load_tma_warpspecialized.hpp:144

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_load_tma_warpspecialized.hpp:719

MethodConsumerStoreCallbacks

3rd/cutlass/include/cutlass/epilogue/fusion/sm90_visitor_load_tma_warpspecialized.hpp:884

FunctionConsumerToken consumer_test_wait

3rd/cutlass/include/cutlass/pipeline/sm90_pipeline.hpp:599

FunctionConsumerToken consumer_test_wait

3rd/cutlass/include/cutlass/pipeline/sm100_pipeline.hpp:491

FunctionConsumerToken consumer_try_wait

3rd/cutlass/include/cutlass/pipeline/sm90_pipeline.hpp:589

FunctionConsumerToken consumer_try_wait

/////////////// Consumer APIs ///////////////

3rd/cutlass/include/cutlass/pipeline/sm100_pipeline.hpp:231

MethodConv2dAnalyticParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:72

MethodConv2dDgradFilterIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:654

MethodConv2dDgradOutputGradientIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:531

MethodConv2dDgradOutputGradientTileAccessIteratorAnalyticParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:140

MethodConv2dFewChannelsParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:106

MethodConv2dFpropActivationIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:237

MethodConv2dFpropActivationIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:330

MethodConv2dFpropFilterIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:396

MethodConv2dFpropFilterIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:469

FunctionConv2dProblemSize reset_mode

3rd/cutlass/include/cutlass/conv/conv2d_problem_size.h:198

FunctionConv2dProblemSize reset_split_k_slices

Reset covolution mode in the problem

3rd/cutlass/include/cutlass/conv/conv2d_problem_size.h:206

MethodConv2dStridedDgradFilterIteratorOptimizedParams

offset in units of bytes to move back the pointer Methods

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:710

MethodConv2dStridedDgradOutputGradientIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:598

MethodConv2dWgradActivationIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:830

MethodConv2dWgradActivationIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:848

MethodConv2dWgradOutputGradientIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv2d_params.h:780

MethodConv3dAnalyticParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:73

MethodConv3dDgradFilterIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:327

MethodConv3dDgradOutputGradientIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:254

MethodConv3dFpropActivationIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:113

MethodConv3dFpropFilterIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:195

FunctionConv3dProblemSize reset_mode

Reset covolution mode in the problem

3rd/cutlass/include/cutlass/conv/conv3d_problem_size.h:247

FunctionConv3dProblemSize reset_split_k_slices

Reset covolution mode in the problem

3rd/cutlass/include/cutlass/conv/conv3d_problem_size.h:255

MethodConv3dWgradActivationIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:465

MethodConv3dWgradOutputGradientIteratorOptimizedParams

3rd/cutlass/include/cutlass/conv/threadblock/conv3d_params.h:392

MethodConvFilterFormatTransformer

3rd/cutlass/include/cutlass/transform/kernel/filter_format_transformer.hpp:88

MethodConvProblemShape

3rd/cutlass/include/cutlass/conv/convnd_problem_shape.hpp:99

Constructs the function object, possibly loading from pointers in host memory

3rd/cutlass/include/cutlass/epilogue/thread/conversion_op.h:91

Default ctor initializes uniformly

3rd/cutlass/include/cutlass/coord.h:86

FunctionCoord<1, T> make_Coord

3rd/cutlass/include/cutlass/coord.h:422

FunctionCoord<2, T> make_Coord

3rd/cutlass/include/cutlass/coord.h:430

FunctionCoord<3, T> make_Coord

3rd/cutlass/include/cutlass/coord.h:438

FunctionCoord<4, T> make_Coord

3rd/cutlass/include/cutlass/coord.h:446

FunctionCoord<5, T> make_Coord

3rd/cutlass/include/cutlass/coord.h:454

FunctionCoord<N, T>make_Coord_with_padding

3rd/cutlass/include/cutlass/coord.h:462

FunctionCoord<Rank, Index> operator*

3rd/cutlass/include/cutlass/coord.h:372

FunctionCoord<Rank, Index> operator/

3rd/cutlass/include/cutlass/coord.h:394

FunctionCoord<Rank> CoordinateDecomposition

3rd/cutlass/include/cutlass/fast_math.h:624

FunctionCoord<Rank> CoordinateDecompositionLittleEndian

3rd/cutlass/include/cutlass/fast_math.h:667

MethodCoord<Slice, Index, LongIndex> slice

3rd/cutlass/include/cutlass/coord.h:114

FunctionCoord<Ts...> make_coord

3rd/cutlass/include/cute/layout.hpp:81

MethodCopy_Traits

3rd/cutlass/include/cute/atom/copy_traits_sm90_im2col.hpp:208

MethodCopy_Traits

3rd/cutlass/include/cute/atom/copy_traits_sm90_tma.hpp:192

MethodCopy_Traits

3rd/cutlass/include/cute/atom/copy_traits_sm90_tma.hpp:342

MethodCopy_Traits

3rd/cutlass/include/cute/atom/copy_traits_sm90_tma.hpp:594

3rd/cutlass/include/cutlass/half.h:126

MethodCreateTensorSync

src/communicator/entry.cc:27

FunctionCudaHostAdapter

3rd/cutlass/include/cutlass/cuda_host_adapter.hpp:227

MethodCudaHostLaunchAttributes

3rd/cutlass/include/cutlass/cuda_host_adapter.hpp:177

MethodDefaultBlockSwizzle

3rd/cutlass/include/cutlass/reduction/threadblock_swizzle.h:41

MethodDefaultEpilogueArray

3rd/cutlass/include/cutlass/epilogue/collective/default_epilogue_array.hpp:146

MethodDepthwise2dFpropDirectConvActivationIteratorFixedStrideDilationParams

3rd/cutlass/include/cutlass/conv/threadblock/depthwise_direct_conv_params.h:172

MethodDepthwise2dFpropDirectConvFilterIteratorParams

3rd/cutlass/include/cutlass/conv/threadblock/depthwise_direct_conv_params.h:212

MethodDepthwise2dFpropDirectConvParams

3rd/cutlass/include/cutlass/conv/threadblock/depthwise_direct_conv_params.h:101

MethodDepthwiseDirect2dConvIdentityThreadblockSwizzle

3rd/cutlass/include/cutlass/conv/threadblock/threadblock_swizzle.h:172

MethodDepthwiseDirect2dConvSimtTileIterator

Default ctor constructs null iterator

3rd/cutlass/include/cutlass/conv/warp/mma_depthwise_simt_tile_iterator.h:416

MethodDepthwiseDirect2dConvSimtTileIterator

Default ctor constructs null iterator

3rd/cutlass/include/cutlass/conv/warp/mma_depthwise_simt_tile_iterator.h:719

MethodDepthwiseMmaSimtTileIterator

Default ctor constructs null iterator

3rd/cutlass/include/cutlass/conv/warp/mma_depthwise_simt_tile_iterator.h:171

MethodDerivedType operator+

3rd/cutlass/include/cute/pointer_base.hpp:154

FunctionDescriptorIterator recast_ptr

3rd/cutlass/include/cute/atom/mma_traits_sm90_gmma.hpp:342

← previous next →1,701–1,800 of 10,542, ranked by callers