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

MethodDescriptorIterator operator+

3rd/cutlass/include/cute/atom/mma_traits_sm90_gmma.hpp:322

MethodDescriptorIterator operator+

3rd/cutlass/include/cute/atom/mma_traits_sm100.hpp:333

MethodDirectConvolution

Constructs Implicit GEMM

3rd/cutlass/include/cutlass/conv/device/direct_convolution.h:101

MethodDirectConvolution

3rd/cutlass/include/cutlass/conv/kernel/direct_convolution.h:371

3rd/cutlass/include/cute/container/tuple.hpp:92

3rd/cutlass/include/cute/container/tuple.hpp:102

3rd/cutlass/include/cute/container/tuple.hpp:114

3rd/cutlass/include/cute/container/tuple.hpp:126

FunctionElectOneLaneIdReturnType elect_one_leader_sync

3rd/cutlass/include/cute/arch/cluster_sm90.hpp:208

MethodElementCompute reduction

3rd/cutlass/include/cutlass/epilogue/threadblock/fusion/visitor_store.hpp:552

MethodElementwiseOpDispatcher

3rd/cutlass/include/cutlass/epilogue/thread/linear_combination_bias_elementwise.h:66

MethodElementwiseOpDispatcher

3rd/cutlass/include/cutlass/epilogue/thread/linear_combination_bias_elementwise.h:83

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/ell_gemm.h:374

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/ell_gemm.h:716

3rd/cutlass/include/cutlass/gemm/kernel/ell_gemm.h:155

3rd/cutlass/include/cutlass/gemm/kernel/ell_gemm.h:537

MethodEllPredicatedTileAccessIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_access_iterator.h:644

MethodEllPredicatedTileAccessIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_access_iterator.h:836

MethodEllPredicatedTileAccessIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_access_iterator.h:1032

MethodEllPredicatedTileAccessIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_access_iterator.h:1228

FunctionEllPredicatedTileAccessIterator operator++

Increment and return an instance to self.

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_access_iterator.h:452

MethodEllPredicatedTileIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_iterator.h:226

MethodEllPredicatedTileIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_iterator.h:554

MethodEllPredicatedTileIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_iterator.h:782

MethodEllPredicatedTileIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_iterator.h:1003

MethodEllPredicatedTileIterator

Constructs a TileIterator from its precomputed state, threadblock offset, and thread ID

3rd/cutlass/include/cutlass/transform/threadblock/ell_predicated_tile_iterator.h:1202

3rd/cutlass/include/cutlass/epilogue/collective/sm70_epilogue_vectorized_array.hpp:163

MethodEpilogueBaseStreamK

3rd/cutlass/include/cutlass/epilogue/threadblock/epilogue_base_streamk.h:109

MethodEpilogueFusedVisitorConcept

3rd/cutlass/include/cutlass/epilogue/threadblock/epilogue_with_visitor.h:77

MethodEpilogueGemmKReduction

3rd/cutlass/include/cutlass/epilogue/threadblock/epilogue_gemm_k_reduction.h:110

MethodEpilogueSmemAccumulator

3rd/cutlass/include/cutlass/epilogue/threadblock/epilogue_smem_accumulator.h:92

MethodEpilogueStreamkWithBroadcastOpBase

Constructor from Params

3rd/cutlass/include/cutlass/epilogue/threadblock/epilogue_streamk_with_broadcast.h:112

MethodEpilogueWithBroadcastOpBase

Constructor from Params

3rd/cutlass/include/cutlass/epilogue/threadblock/epilogue_with_broadcast.h:119

FunctionF16F32Format to_F16F32Format

3rd/cutlass/include/cute/arch/mma_sm100_desc.hpp:141

MethodFastDivmod

3rd/cutlass/include/cutlass/fast_math.h:365

MethodFastLinearCombinationClamp

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

3rd/cutlass/include/cutlass/epilogue/thread/linear_combination_clamp.h:564

FunctionFp16BitCast

src/allreduce/fuse_allreduce_rmsnorm_low_latency.h:89

MethodFragmentShuffler

3rd/cutlass/include/cutlass/gemm/warp/mma_mixed_input_tensor_op.h:150

MethodFragmentShuffler

3rd/cutlass/include/cutlass/gemm/warp/mma_mixed_input_tensor_op.h:234

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm.h:357

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm.h:697

3rd/cutlass/include/cutlass/gemm/kernel/gemm.h:148

MethodGemmArray

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_array.h:341

MethodGemmArray

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_array.h:654

MethodGemmArray

3rd/cutlass/include/cutlass/gemm/kernel/gemm_array.h:135

MethodGemmBatched

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_batched.h:336

MethodGemmBatched

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_batched.h:627

MethodGemmBatched

3rd/cutlass/include/cutlass/gemm/kernel/gemm_batched.h:136

MethodGemmBlockwise

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_blockwise.h:358

MethodGemmBlockwise

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_blockwise.h:694

MethodGemmComplex

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_complex.h:330

MethodGemmComplex

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_complex.h:646

MethodGemmCoord

3rd/cutlass/include/cutlass/gemm_coord.h:108

MethodGemmCoord implicit_gemm_problem_size

Determine the problem size of the implicit GEMM operation

3rd/cutlass/include/cutlass/conv/conv3d_problem_size.h:340

MethodGemmCoord implicit_gemm_problem_size

Determine the problem size of the implicit GEMM operation

3rd/cutlass/include/cutlass/conv/conv2d_problem_size.h:327

MethodGemmGrouped

3rd/cutlass/include/cutlass/gemm/kernel/gemm_grouped.h:283

MethodGemmGroupedProblemVisitor

3rd/cutlass/include/cutlass/gemm/kernel/gemm_grouped_problem_visitor.h:106

MethodGemmGroupedSoftmaxMainloopFusion

3rd/cutlass/include/cutlass/gemm/kernel/gemm_grouped_softmax_mainloop_fusion.h:297

MethodGemmHorizontalThreadblockSwizzle

3rd/cutlass/include/cutlass/gemm/threadblock/threadblock_swizzle.h:166

MethodGemmIdentityThreadblockSwizzle

3rd/cutlass/include/cutlass/gemm/threadblock/threadblock_swizzle.h:59

MethodGemmLayernormMainloopFusion

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_layernorm_mainloop_fusion.h:311

MethodGemmParams

3rd/cutlass/include/cutlass/gemm/kernel/gemm_params.h:102

FunctionGemmPipelined

3rd/cutlass/include/cutlass/gemm/kernel/gemm_pipelined.h:56

MethodGemmSplitKParallel

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_splitk_parallel.h:249

MethodGemmSplitKParallel

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_splitk_parallel.h:562

MethodGemmSplitKParallel

3rd/cutlass/include/cutlass/gemm/kernel/gemm_splitk_parallel.h:129

MethodGemmUniversal

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_universal.h:368

MethodGemmUniversalAdapter

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_universal_adapter.h:708

MethodGemmUniversalBlockwise

3rd/cutlass/include/cutlass/gemm/kernel/gemm_universal_blockwise.h:148

MethodGemmUniversalStreamkWithBroadcast

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_universal_streamk_with_broadcast.h:312

MethodGemmUniversalWithAbsMax

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_universal_with_absmax.h:330

MethodGemmUniversalWithBroadcast

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_universal_with_broadcast.h:312

MethodGemmWithKReduction

Constructs the GEMM.

3rd/cutlass/include/cutlass/gemm/device/gemm_with_k_reduction.h:341

Constructs the Gemv.

3rd/cutlass/include/cutlass/gemm/device/gemv.h:90

3rd/cutlass/include/cutlass/gemm/threadblock/gemv.h:86

3rd/cutlass/include/cutlass/gemm/kernel/gemv.h:272

3rd/cutlass/include/cutlass/gemm/kernel/gemv.h:509

FunctionGemvBatchedStrided

3rd/cutlass/include/cutlass/gemm/kernel/gemv_batched_strided.h:189

FunctionGemvBatchedStridedDevice

3rd/cutlass/include/cutlass/gemm/kernel/gemv_batched_strided.h:94

MethodGemvBlockScaled

Constructs the GemvBlockScaled.

3rd/cutlass/include/cutlass/gemm/device/gemv_blockscaled.h:93

src/communicator/entry.cc:66

MethodGetWorldSize

src/communicator/entry.cc:68

FunctionGmmaDescriptor

3rd/cutlass/include/cute/arch/mma_sm90_desc.hpp:82

FunctionGmmaDescriptor make_gmma_desc

3rd/cutlass/include/cute/atom/mma_traits_sm90_gmma.hpp:197

FunctionGmmaDescriptor raw_pointer_cast

3rd/cutlass/include/cute/atom/mma_traits_sm90_gmma.hpp:334

MethodIMulticastCommunicator

src/communicator/entry.cc:20

MethodIdentityTensorLayout

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

MethodImplicitGemmConvolution

Constructs Implicit GEMM

3rd/cutlass/include/cutlass/conv/device/implicit_gemm_convolution.h:102

MethodImplicitGemmConvolution

3rd/cutlass/include/cutlass/conv/kernel/implicit_gemm_convolution.h:276

MethodImplicitGemmConvolutionFusion

Constructs Implicit GEMM

3rd/cutlass/include/cutlass/conv/device/implicit_gemm_convolution_fusion.h:101

MethodImplicitGemmConvolutionFusion

3rd/cutlass/include/cutlass/conv/kernel/implicit_gemm_convolution_fusion.h:276

MethodImplicitGemmConvolutionStridedDgrad

3rd/cutlass/include/cutlass/conv/kernel/implicit_gemm_convolution_strided_dgrad.h:275

MethodImplicitGemmConvolutionWithAbsMax

3rd/cutlass/include/cutlass/conv/kernel/implicit_gemm_convolution_with_absmax.h:296

MethodImplicitGemmConvolutionWithFusedEpilogue

3rd/cutlass/include/cutlass/conv/kernel/implicit_gemm_convolution_with_fused_epilogue.h:296

MethodInputTensors tensors_perform_update

3rd/cutlass/include/cutlass/gemm/collective/sm90_mma_array_tma_gmma_ss_warpspecialized_fp8_blockwise_scaling.hpp:1186

MethodInputTensors tensors_perform_update

3rd/cutlass/include/cutlass/gemm/collective/sm120_mma_array_tma_blockwise_scaling.hpp:970

MethodInputTensors tensors_perform_update

3rd/cutlass/include/cutlass/gemm/collective/sm120_blockscaled_mma_array_tma.hpp:1147

MethodInputTensors tensors_perform_update

3rd/cutlass/include/cutlass/gemm/collective/sm90_mma_array_tma_gmma_rs_warpspecialized_mixed_input.hpp:1364

MethodInputTensors tensors_perform_update

3rd/cutlass/include/cutlass/gemm/collective/sm90_mma_array_tma_gmma_ss_warpspecialized.hpp:759

MethodInputTensors tensors_perform_update

3rd/cutlass/include/cutlass/gemm/collective/sm90_mma_array_tma_gmma_ss_warpspecialized_fp8.hpp:768

← previous next →1,801–1,900 of 10,542, ranked by callers