squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
fb335f6a5f
cutlass/docs/search/all_4.js

173 lines
56 KiB
JavaScript
Raw Normal View History

CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
var searchData=
[
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['d',['D',['../structcutlass_1_1library_1_1GemmArguments.html#a2f4c0652e6632aebe6d9159c425ecc3f',1,'cutlass::library::GemmArguments::D()'],['../structcutlass_1_1library_1_1GemmArrayArguments.html#ae6ccc3b91e9a77ad170d276f70fe2c30',1,'cutlass::library::GemmArrayArguments::D()']]],
Updating Doxygen docs
2018-10-27 05:54:58 +08:00
['d_5fa',['d_a',['../structcutlass_1_1reduction_1_1BatchedReductionTraits_1_1Params.html#af1b12ba220602692e84616b420b00f1c',1,'cutlass::reduction::BatchedReductionTraits::Params']]],
['d_5fc',['d_c',['../structcutlass_1_1reduction_1_1BatchedReductionTraits_1_1Params.html#ac79830eaf080ea0ffddd2100db6cf3e1',1,'cutlass::reduction::BatchedReductionTraits::Params']]],
['d_5fd',['d_d',['../structcutlass_1_1reduction_1_1BatchedReductionTraits_1_1Params.html#abf9744373a72f3819a616b5a5b3bff22',1,'cutlass::reduction::BatchedReductionTraits::Params']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['data',['data',['../structcutlass_1_1AlignedBuffer.html#a8ed8b9d3469621fc82d0041846c59da2',1,'cutlass::AlignedBuffer::data()'],['../structcutlass_1_1AlignedBuffer.html#acbfc684b16c9c717df5712bcb729acf3',1,'cutlass::AlignedBuffer::data() const '],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#af47ab51582aa1e4c811a9e111b594556',1,'cutlass::Array< T, N, true >::data()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a3d3d2637b7051145a2048cff1b55c0bf',1,'cutlass::Array< T, N, true >::data() const '],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#a1949c8a8c81dc2743328a56ff19fc933',1,'cutlass::Array< T, N, false >::data()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#ab617ed6c9cc6336baf1030713d6dfbbb',1,'cutlass::Array< T, N, false >::data() const '],['../structcutlass_1_1epilogue_1_1threadblock_1_1EpilogueBase_1_1SharedStorage.html#a2d57be4f0bdad670c7eb67e64dd1a9f5',1,'cutlass::epilogue::threadblock::EpilogueBase::SharedStorage::data()'],['../classcutlass_1_1TensorRef.html#ac7db3ca62ab1dfe0d3ea08bcadbc9352',1,'cutlass::TensorRef::data() const '],['../classcutlass_1_1TensorRef.html#a965e8b3b7f92dc51d4d3821ea6a25012',1,'cutlass::TensorRef::data(LongIndex idx) const ']]],
['debug_5fprint',['debug_print',['../structcutlass_1_1epilogue_1_1threadblock_1_1EpilogueBase_1_1SharedStorage.html#afd521c2dc754bb30024e8767bfc51e49',1,'cutlass::epilogue::threadblock::EpilogueBase::SharedStorage']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['debugtype',['DebugType',['../structDebugType.html',1,'']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['debugtypefunc',['DebugTypeFunc',['../tools_2util_2include_2cutlass_2util_2debug_8h.html#ab7e23b523490567225b20e2c72649f20',1,'debug.h']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['debugvalue',['DebugValue',['../structDebugValue.html',1,'']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['default',['Default',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemmSplitKParallel.html#a839689cbd754a38f8b5e2bb41465069e',1,'cutlass::gemm::kernel::DefaultGemmSplitKParallel']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['default_5fdelete',['default_delete',['../structcutlass_1_1platform_1_1default__delete.html',1,'cutlass::platform']]],
['default_5fdelete_3c_20t_5b_5d_3e',['default_delete< T[]>',['../structcutlass_1_1platform_1_1default__delete_3_01T[]_4.html',1,'cutlass::platform']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['default_5fepilogue_5fcomplex_5ftensor_5fop_2eh',['default_epilogue_complex_tensor_op.h',['../default__epilogue__complex__tensor__op_8h.html',1,'']]],
['default_5fepilogue_5fsimt_2eh',['default_epilogue_simt.h',['../default__epilogue__simt_8h.html',1,'']]],
['default_5fepilogue_5ftensor_5fop_2eh',['default_epilogue_tensor_op.h',['../default__epilogue__tensor__op_8h.html',1,'']]],
['default_5fepilogue_5fvolta_5ftensor_5fop_2eh',['default_epilogue_volta_tensor_op.h',['../default__epilogue__volta__tensor__op_8h.html',1,'']]],
['default_5fepilogue_5fwmma_5ftensor_5fop_2eh',['default_epilogue_wmma_tensor_op.h',['../default__epilogue__wmma__tensor__op_8h.html',1,'']]],
['default_5fgemm_2eh',['default_gemm.h',['../default__gemm_8h.html',1,'']]],
['default_5fgemm_5fconfiguration_2eh',['default_gemm_configuration.h',['../default__gemm__configuration_8h.html',1,'']]],
['default_5fgemm_5fsplitk_5fparallel_2eh',['default_gemm_splitk_parallel.h',['../default__gemm__splitk__parallel_8h.html',1,'']]],
['default_5fgemv_2eh',['default_gemv.h',['../default__gemv_8h.html',1,'']]],
['default_5fgemv_5fcore_2eh',['default_gemv_core.h',['../default__gemv__core_8h.html',1,'']]],
['default_5fmma_2eh',['default_mma.h',['../default__mma_8h.html',1,'']]],
['default_5fmma_5fcore_2eh',['default_mma_core.h',['../default__mma__core_8h.html',1,'']]],
['default_5fmma_5fcore_5fsimt_2eh',['default_mma_core_simt.h',['../default__mma__core__simt_8h.html',1,'']]],
['default_5fmma_5fcore_5fsm50_2eh',['default_mma_core_sm50.h',['../default__mma__core__sm50_8h.html',1,'']]],
['default_5fmma_5fcore_5fsm70_2eh',['default_mma_core_sm70.h',['../default__mma__core__sm70_8h.html',1,'']]],
['default_5fmma_5fcore_5fsm75_2eh',['default_mma_core_sm75.h',['../default__mma__core__sm75_8h.html',1,'']]],
['default_5fmma_5fcore_5fwmma_2eh',['default_mma_core_wmma.h',['../default__mma__core__wmma_8h.html',1,'']]],
['default_5fmma_5ftensor_5fop_2eh',['default_mma_tensor_op.h',['../default__mma__tensor__op_8h.html',1,'']]],
['default_5fmma_5fwmma_5ftensor_5fop_2eh',['default_mma_wmma_tensor_op.h',['../default__mma__wmma__tensor__op_8h.html',1,'']]],
['default_5fthread_5fmap_5fsimt_2eh',['default_thread_map_simt.h',['../default__thread__map__simt_8h.html',1,'']]],
['default_5fthread_5fmap_5ftensor_5fop_2eh',['default_thread_map_tensor_op.h',['../default__thread__map__tensor__op_8h.html',1,'']]],
['default_5fthread_5fmap_5fvolta_5ftensor_5fop_2eh',['default_thread_map_volta_tensor_op.h',['../default__thread__map__volta__tensor__op_8h.html',1,'']]],
['default_5fthread_5fmap_5fwmma_5ftensor_5fop_2eh',['default_thread_map_wmma_tensor_op.h',['../default__thread__map__wmma__tensor__op_8h.html',1,'']]],
['defaultblockswizzle',['DefaultBlockSwizzle',['../structcutlass_1_1reduction_1_1DefaultBlockSwizzle.html#a1ad8edda7b73d23fb5592a531f5736cc',1,'cutlass::reduction::DefaultBlockSwizzle']]],
['defaultblockswizzle',['DefaultBlockSwizzle',['../structcutlass_1_1reduction_1_1DefaultBlockSwizzle.html',1,'cutlass::reduction']]],
['defaultepiloguecomplextensorop',['DefaultEpilogueComplexTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueComplexTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultepiloguesimt',['DefaultEpilogueSimt',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueSimt.html',1,'cutlass::epilogue::threadblock']]],
['defaultepiloguetensorop',['DefaultEpilogueTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultepiloguevoltatensorop',['DefaultEpilogueVoltaTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueVoltaTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultepiloguewmmatensorop',['DefaultEpilogueWmmaTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultEpilogueWmmaTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultgemm',['DefaultGemm',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm.html',1,'cutlass::gemm::kernel']]],
['defaultgemm_3c_20elementa_2c_20layout_3a_3acolumnmajorinterleaved_3c_20interleavedk_20_3e_2c_20kalignmenta_2c_20elementb_2c_20layout_3a_3arowmajorinterleaved_3c_20interleavedk_20_3e_2c_20kalignmentb_2c_20elementc_2c_20layout_3a_3acolumnmajorinterleaved_3c_20interleavedk_20_3e_2c_20int32_5ft_2c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20threadblockshape_2c_20warpshape_2c_20instructionshape_2c_20epilogueoutputop_2c_20threadblockswizzle_2c_202_2c_20splitkserial_2c_20operator_2c_20isbetazero_20_3e',['DefaultGemm< ElementA, layout::ColumnMajorInterleaved< InterleavedK >, kAlignmentA, ElementB, layout::RowMajorInterleaved< InterleavedK >, kAlignmentB, ElementC, layout::ColumnMajorInterleaved< InterleavedK >, int32_t, arch::OpClassTensorOp, arch::Sm75, ThreadblockShape, WarpShape, InstructionShape, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator, IsBetaZero >',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01layout_1_1ColumnMajorInterleave661fe54d13cc2c9153dcdf31e4beaa30.html',1,'cutlass::gemm::kernel']]],
['defaultgemm_3c_20elementa_2c_20layouta_2c_20kalignmenta_2c_20elementb_2c_20layoutb_2c_20kalignmentb_2c_20elementc_2c_20layout_3a_3arowmajor_2c_20elementaccumulator_2c_20arch_3a_3aopclasssimt_2c_20archtag_2c_20threadblockshape_2c_20warpshape_2c_20gemmshape_3c_201_2c_201_2c_201_20_3e_2c_20epilogueoutputop_2c_20threadblockswizzle_2c_202_2c_20splitkserial_2c_20operator_20_3e',['DefaultGemm< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementC, layout::RowMajor, ElementAccumulator, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 1 >, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator >',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01Edd80343e6570718ed237122e4ebf7fb5.html',1,'cutlass::gemm::kernel']]],
['defaultgemm_3c_20elementa_2c_20layouta_2c_20kalignmenta_2c_20elementb_2c_20layoutb_2c_20kalignmentb_2c_20elementc_2c_20layout_3a_3arowmajor_2c_20elementaccumulator_2c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm70_2c_20threadblockshape_2c_20warpshape_2c_20gemmshape_3c_208_2c_208_2c_204_20_3e_2c_20epilogueoutputop_2c_20threadblockswizzle_2c_202_2c_20splitkserial_2c_20operator_20_3e',['DefaultGemm< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementC, layout::RowMajor, ElementAccumulator, arch::OpClassTensorOp, arch::Sm70, ThreadblockShape, WarpShape, GemmShape< 8, 8, 4 >, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator >',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01E044b039b2fe402f29b04a9f5feee5342.html',1,'cutlass::gemm::kernel']]],
['defaultgemm_3c_20elementa_2c_20layouta_2c_20kalignmenta_2c_20elementb_2c_20layoutb_2c_20kalignmentb_2c_20elementc_2c_20layout_3a_3arowmajor_2c_20elementaccumulator_2c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20threadblockshape_2c_20warpshape_2c_20instructionshape_2c_20epilogueoutputop_2c_20threadblockswizzle_2c_202_2c_20splitkserial_2c_20operator_20_3e',['DefaultGemm< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementC, layout::RowMajor, ElementAccumulator, arch::OpClassTensorOp, arch::Sm75, ThreadblockShape, WarpShape, InstructionShape, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator >',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01E5d78d37a9ae2ec08d7d477d571df036e.html',1,'cutlass::gemm::kernel']]],
['defaultgemm_3c_20int8_5ft_2c_20layouta_2c_20kalignmenta_2c_20int8_5ft_2c_20layoutb_2c_20kalignmentb_2c_20elementc_2c_20layoutc_2c_20elementaccumulator_2c_20arch_3a_3aopclasssimt_2c_20archtag_2c_20threadblockshape_2c_20warpshape_2c_20gemmshape_3c_201_2c_201_2c_204_20_3e_2c_20epilogueoutputop_2c_20threadblockswizzle_2c_202_2c_20splitkserial_2c_20operator_2c_20false_20_3e',['DefaultGemm< int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementC, LayoutC, ElementAccumulator, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 4 >, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator, false >',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01int8__t_00_01LayoutA_00_01kAlignmentA_00_01inf48440732c1c5f42ddbfaba179861815.html',1,'cutlass::gemm::kernel']]],
['defaultgemmconfiguration',['DefaultGemmConfiguration',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasssimt_2c_20archtag_2c_20elementa_2c_20elementb_2c_20elementc_2c_20elementaccumulator_20_3e',['DefaultGemmConfiguration< arch::OpClassSimt, ArchTag, ElementA, ElementB, ElementC, ElementAccumulator >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassSimt_00_01ArchTag286687c5e6abe22d241f789fe344a465.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasssimt_2c_20archtag_2c_20int8_5ft_2c_20int8_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassSimt, ArchTag, int8_t, int8_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassSimt_00_01ArchTag3026e48abb8c905d1cc6d13d669700e4.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm70_2c_20elementa_2c_20elementb_2c_20elementc_2c_20elementaccumulator_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm70, ElementA, ElementB, ElementC, ElementAccumulator >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arc567cad318a31d04b70ea615d6321decd.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20elementa_2c_20elementb_2c_20elementc_2c_20elementaccumulator_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, ElementA, ElementB, ElementC, ElementAccumulator >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arcde61af9be1337dac1fdb210e7e7a6e01.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20int4b_5ft_2c_20int4b_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int4b_t, int4b_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arc485a4f0b5a7d2d4ab2c1a24da6328048.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20int4b_5ft_2c_20uint4b_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int4b_t, uint4b_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arc8e2604a56dff3a7595da9ee0604ae55e.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20int8_5ft_2c_20int8_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int8_t, int8_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arc4fada4957d463c80a2831e47f28157c4.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20int8_5ft_2c_20uint8_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, int8_t, uint8_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arc8ab5fd2693c6a6ec43e447acb07f784c.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20uint4b_5ft_2c_20int4b_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint4b_t, int4b_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arcffcf31256aed23d4d8d0eab627bc0cad.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20uint4b_5ft_2c_20uint4b_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint4b_t, uint4b_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arcb2e258b7bd321c633dd65d3ebcf6414a.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20uint8_5ft_2c_20int8_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint8_t, int8_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arcb27bf218007928652d5b803193eab473.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasstensorop_2c_20arch_3a_3asm75_2c_20uint8_5ft_2c_20uint8_5ft_2c_20elementc_2c_20int32_5ft_20_3e',['DefaultGemmConfiguration< arch::OpClassTensorOp, arch::Sm75, uint8_t, uint8_t, ElementC, int32_t >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassTensorOp_00_01arcfea0f3503156e8e3fba6456f0cedafdd.html',1,'cutlass::gemm::device']]],
['defaultgemmconfiguration_3c_20arch_3a_3aopclasswmmatensorop_2c_20archtag_2c_20elementa_2c_20elementb_2c_20elementc_2c_20elementaccumulator_20_3e',['DefaultGemmConfiguration< arch::OpClassWmmaTensorOp, ArchTag, ElementA, ElementB, ElementC, ElementAccumulator >',['../structcutlass_1_1gemm_1_1device_1_1DefaultGemmConfiguration_3_01arch_1_1OpClassWmmaTensorOp_00_0884059ecad03bea3e86c4cf722226097.html',1,'cutlass::gemm::device']]],
['defaultgemmkernel',['DefaultGemmKernel',['../classcutlass_1_1gemm_1_1device_1_1GemmBatched.html#a6acd50cfc477e95dbcf0d4fbba5df65c',1,'cutlass::gemm::device::GemmBatched']]],
['defaultgemmsplitkparallel',['DefaultGemmSplitKParallel',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemmSplitKParallel.html',1,'cutlass::gemm::kernel']]],
['defaultgemv',['DefaultGemv',['../structcutlass_1_1gemm_1_1kernel_1_1DefaultGemv.html',1,'cutlass::gemm::kernel']]],
['defaultgemvcore',['DefaultGemvCore',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultGemvCore.html',1,'cutlass::gemm::threadblock']]],
['defaultinterleavedepiloguetensorop',['DefaultInterleavedEpilogueTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultInterleavedEpilogueTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultinterleavedthreadmaptensorop',['DefaultInterleavedThreadMapTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultInterleavedThreadMapTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultmma',['DefaultMma',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMma.html',1,'cutlass::gemm::threadblock']]],
['defaultmma_3c_20elementa_2c_20layouta_2c_20kalignmenta_2c_20elementb_2c_20layoutb_2c_20kalignmentb_2c_20elementaccumulator_2c_20layout_3a_3acolumnmajorinterleaved_3c_20interleavedk_20_3e_2c_20operatorclass_2c_20archtag_2c_20threadblockshape_2c_20warpshape_2c_20instructionshape_2c_202_2c_20operator_2c_20true_20_3e',['DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::ColumnMajorInterleaved< InterleavedK >, OperatorClass, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, true >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMma_3_01ElementA_00_01LayoutA_00_01kAlignmentA_0010764e1fd5a3251a57eddafbd83eab8e.html',1,'cutlass::gemm::threadblock']]],
['defaultmma_3c_20elementa_2c_20layouta_2c_20kalignmenta_2c_20elementb_2c_20layoutb_2c_20kalignmentb_2c_20elementaccumulator_2c_20layout_3a_3arowmajor_2c_20arch_3a_3aopclasssimt_2c_20archtag_2c_20threadblockshape_2c_20warpshape_2c_20instructionshape_2c_202_2c_20operator_2c_20false_20_3e',['DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMma_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00c67c16f9881e4f2fda76d8ed83ebabd6.html',1,'cutlass::gemm::threadblock']]],
['defaultmma_3c_20elementa_2c_20layouta_2c_20kalignmenta_2c_20elementb_2c_20layoutb_2c_20kalignmentb_2c_20elementaccumulator_2c_20layout_3a_3arowmajor_2c_20arch_3a_3aopclasstensorop_2c_20archtag_2c_20threadblockshape_2c_20warpshape_2c_20instructionshape_2c_202_2c_20operator_2c_20false_20_3e',['DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassTensorOp, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMma_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00ce36642cae579bce6605ff8edde3c6ab.html',1,'cutlass::gemm::threadblock']]],
['defaultmma_3c_20int8_5ft_2c_20layouta_2c_20kalignmenta_2c_20int8_5ft_2c_20layoutb_2c_20kalignmentb_2c_20elementaccumulator_2c_20layout_3a_3arowmajor_2c_20arch_3a_3aopclasssimt_2c_20archtag_2c_20threadblockshape_2c_20warpshape_2c_20gemmshape_3c_201_2c_201_2c_204_20_3e_2c_202_2c_20operator_2c_20false_20_3e',['DefaultMma< int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 4 >, 2, Operator, false >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMma_3_01int8__t_00_01LayoutA_00_01kAlignmentA_00_07e7230d4011ada5e22cfcb29103b696.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore',['DefaultMmaCore',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_201_20_3e_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmShab94a11a77dd0565102710907089acee0.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_201_20_3e_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmShafafd5c61db86cbfe90863578ddd11092.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_201_20_3e_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_2c_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_, >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha46446d1e3871e31d2e728f710d78c8c1.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_201_20_3e_2c_20elementa_5f_2c_20layout_3a_3arowmajor_2c_20elementb_5f_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha8da7a0cfbbe859b701fdd9f2b8566aa7.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_201_20_3e_2c_20elementa_5f_2c_20layout_3a_3arowmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha84e9f8afb6a4ca9f5dcd219b182d16e7.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_204_20_3e_2c_20int8_5ft_2c_20layout_3a_3acolumnmajor_2c_20int8_5ft_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha2c0d0b7cdb5c4bcb11e83c058eb65345.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_204_20_3e_2c_20int8_5ft_2c_20layout_3a_3acolumnmajor_2c_20int8_5ft_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha34a52cc7b2942e8c290f0032b6779b52.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_204_20_3e_2c_20int8_5ft_2c_20layout_3a_3arowmajor_2c_20int8_5ft_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmShaaf312aafe9da92ea9d417bcc12a8e7dc.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_201_2c_201_2c_204_20_3e_2c_20int8_5ft_2c_20layout_3a_3arowmajor_2c_20int8_5ft_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasssimt_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha863d4139ccaa713bc4bde32c425f4067.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_208_2c_208_2c_204_20_3e_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmShaf03a122202ad10acdc96f280106d678b.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_208_2c_208_2c_204_20_3e_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha69bef08ea63dd930f99d9788105873dd.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_208_2c_208_2c_204_20_3e_2c_20elementa_5f_2c_20layout_3a_3arowmajor_2c_20elementb_5f_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmSha3adf608332a8c9ee7014fced0da8a9ca.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20gemmshape_3c_208_2c_208_2c_204_20_3e_2c_20elementa_5f_2c_20layout_3a_3arowmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01GemmShab7edfba3cdf43a07e3c4d719d87565a4.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20instructionshape_5f_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01Instruc803d38bc1e4618c07c47f54c87ae2678.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20instructionshape_5f_2c_20elementa_5f_2c_20layout_3a_3acolumnmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01Instrucf60fe02fcdd80d28b7fd419133465dcc.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20instructionshape_5f_2c_20elementa_5f_2c_20layout_3a_3acolumnmajorinterleaved_3c_20interleavedk_20_3e_2c_20elementb_5f_2c_20layout_3a_3arowmajorinterleaved_3c_20interleavedk_20_3e_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_2c_20accumulatorsinrowmajor_20_3e',['DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01Instruc2bf00737f4ad0a9da9a8be6d3e66c152.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20instructionshape_5f_2c_20elementa_5f_2c_20layout_3a_3arowmajor_2c_20elementb_5f_2c_20layout_3a_3acolumnmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01Instruc24092ddc01fc83dabb7db4c14880fe60.html',1,'cutlass::gemm::threadblock']]],
['defaultmmacore_3c_20shape_5f_2c_20warpshape_5f_2c_20instructionshape_5f_2c_20elementa_5f_2c_20layout_3a_3arowmajor_2c_20elementb_5f_2c_20layout_3a_3arowmajor_2c_20elementc_5f_2c_20layoutc_5f_2c_20arch_3a_3aopclasstensorop_2c_202_2c_20operator_5f_20_3e',['DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >',['../structcutlass_1_1gemm_1_1threadblock_1_1DefaultMmaCore_3_01Shape___00_01WarpShape___00_01Instruc4fee9f2965b8468bfb42b94a74527d22.html',1,'cutlass::gemm::threadblock']]],
['defaultmmatensorop',['DefaultMmaTensorOp',['../structcutlass_1_1gemm_1_1warp_1_1DefaultMmaTensorOp.html',1,'cutlass::gemm::warp']]],
['defaultthreadmapsimt',['DefaultThreadMapSimt',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapSimt.html',1,'cutlass::epilogue::threadblock']]],
['defaultthreadmaptensorop',['DefaultThreadMapTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultthreadmapvoltatensorop',['DefaultThreadMapVoltaTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['defaultthreadmapvoltatensorop_3c_20threadblockshape_5f_2c_20warpshape_5f_2c_20partitionsk_2c_20elementoutput_5f_2c_20elementsperaccess_2c_20float_20_3e',['DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, float >',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp_3_01ThreadblockShape__95db04b7b72e34283958bd7fbf851d16.html',1,'cutlass::epilogue::threadblock']]],
['defaultthreadmapvoltatensorop_3c_20threadblockshape_5f_2c_20warpshape_5f_2c_20partitionsk_2c_20elementoutput_5f_2c_20elementsperaccess_2c_20half_5ft_20_3e',['DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, half_t >',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp_3_01ThreadblockShape__d58c94abc36b7c5c109b55202c6992e7.html',1,'cutlass::epilogue::threadblock']]],
['defaultthreadmapwmmatensorop',['DefaultThreadMapWmmaTensorOp',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapWmmaTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['deleter',['deleter',['../structcutlass_1_1device__memory_1_1allocation_1_1deleter.html',1,'cutlass::device_memory::allocation']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['deleter_5ftype',['deleter_type',['../classcutlass_1_1platform_1_1unique__ptr.html#a85cab9945c36dc56bd7d6adf30c0d252',1,'cutlass::platform::unique_ptr']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['delta',['delta',['../structcutlass_1_1Distribution.html#a77613df810c3f8f68b595599802cedb4',1,'cutlass::Distribution::delta()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileThreadMap.html#ae083ea17a4ed1c6b8032a46b2344b4af',1,'cutlass::epilogue::threadblock::OutputTileThreadMap::Delta()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileOptimalThreadMap.html#a76da5585b34f64eb22432a1f04a95548',1,'cutlass::epilogue::threadblock::OutputTileOptimalThreadMap::Delta()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileOptimalThreadMap_1_1CompactedThreadMap.html#ab50601383eae7a10595aba985bb83d58',1,'cutlass::epilogue::threadblock::OutputTileOptimalThreadMap::CompactedThreadMap::Delta()'],['../structcutlass_1_1epilogue_1_1threadblock_1_1InterleavedOutputTileThreadMap.html#a78a41e1ae9167d0746815de4ac9a3f9c',1,'cutlass::epilogue::threadblock::InterleavedOutputTileThreadMap::Delta()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kC_00_01Element_4ccafbc821b3a55cd532602442a74031.html#a67ed49d8344f29e7c85e2248020d80af',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::ColumnMajor, Policy_ >::Delta()'],['../classcutlass_1_1gemm_1_1warp_1_1MmaSimtTileIterator_3_01Shape___00_01Operand_1_1kC_00_01Element_8f92ea79e85febb67169c4b2d94b1b20.html#a4cf7081daf014063f4a8a652ee0d47b4',1,'cutlass::gemm::warp::MmaSimtTileIterator< Shape_, Operand::kC, Element_, layout::RowMajor, Policy_ >::Delta()'],['../structcutlass_1_1transform_1_1PitchLinearStripminedThreadMap.html#aed1e512ae8dde49bdbba25a966026e27',1,'cutlass::transform::PitchLinearStripminedThreadMap::Delta()'],['../structcutlass_1_1transform_1_1PitchLinearTilePolicyStripminedThreadContiguous.html#a7a67bb78b04e55c44fbd9a2255171c53',1,'cutlass::transform::PitchLinearTilePolicyStripminedThreadContiguous::Delta()'],['../structcutlass_1_1transform_1_1PitchLinearTilePolicyStripminedThreadStrided.html#a2019db51b4d5aed441fe31f6c7ec3707',1,'cutlass::transform::PitchLinearTilePolicyStripminedThreadStrided::Delta()'],['../structcutlass_1_1transform_1_1PitchLinearWarpRakedThreadMap.html#a2b34c242897c93f99d1bf402ab53cf11',1,'cutlass::transform::PitchLinearWarpRakedThreadMap::Delta()'],['../structcutlass_1_1transform_1_1TransposePitchLinearThreadMap.html#adfa87c73e85a088159450b488e0311d6',1,'cutlass::transform::TransposePitchLinearThreadMap::Delta()'],['../structcutlass_1_1transform_1_1TransposePitchLinearThreadMapSimt.html#a97a631b10803b78d757d8dffce39b54d',1,'cutlass::transform::TransposePitchLinearThreadMapSimt::Delta()'],['../structcutlass_1_1transform_1_1PitchLinearWarpStripedThreadMap.html#a8c898ce4cdfff0eb223534c0607eb9e3',1,'cutlass::transform::PitchLinearWarpStripedThreadMap::Delta()'],['../structcutlass_1_1transform_1_1PitchLinear2DThreadTileStripminedThreadMap_3_01Shape___00_01Thread0082c3467229b12cc9dd996283ee7160.html#abc06fa8bfb735fee7e8d89eee42842d7',1,'cutlass::transform::PitchLinear2DThreadTileStripminedThreadMap< Shape_, Threads, cutlass::layout::PitchLinearShape< 4, 4 > >::Delta()'],['../structcutlass_1_1transform_1_1TransposePitchLinearThreadMap2DThreadTile.html#a674092700284a0aec2665e7ea118a024',1,'cutlass::transform::TransposePitchLinearThreadMap2DThreadTile::Delta()']]],
['denorm_5fmin',['denorm_min',['../structstd_1_1numeric__limits_3_01cutlass_1_1half__t_01_4.html#a2c05c19022c183e8734ada65c8970af5',1,'std::numeric_limits< cutlass::half_t >']]],
['description',['description',['../classcutlass_1_1library_1_1Operation.html#a62b9fbee4b72857214ca6c01874a27ce',1,'cutlass::library::Operation']]],
['destination',['destination',['../structcutlass_1_1reduction_1_1kernel_1_1ReduceSplitK_1_1Params.html#a08089218798599f5f47184f8c94723cb',1,'cutlass::reduction::kernel::ReduceSplitK::Params']]],
['destination_5fref',['destination_ref',['../structcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp_1_1Params.html#a89d406e705b7817243e3aa9d4253bb14',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp::Params']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapWmmaTensorOp_1_1Detail.html',1,'cutlass::epilogue::threadblock::DefaultThreadMapWmmaTensorOp']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1detail_1_1RowArrangement_3_01Shape_00_01WarpsRemainief28e98b3f284469f271d28aba73de2e.html',1,'cutlass::epilogue::threadblock::detail::RowArrangement< Shape, WarpsRemaining, ElementsPerAccess, ElementSize, true >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape___00_01Element___00_032f88d1be8b209e44a4815c707ba35bb.html',1,'cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::VoltaTensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1Gemm770cbca45441d295d5d7433e8222a700.html',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, float, layout::RowMajor >']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1warp_1_1TileIteratorTensorOp_3_01WarpShape___00_01OperatorShape___05f11e023c9e6ee5f7a888fa4c5bbf6d1.html',1,'cutlass::epilogue::warp::TileIteratorTensorOp< WarpShape_, OperatorShape_, Element_, layout::RowMajor >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1TransposePitchLinearThreadMap_1_1Detail.html',1,'cutlass::transform::TransposePitchLinearThreadMap']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1PitchLinearWarpStripedThreadMap_1_1Detail.html',1,'cutlass::transform::PitchLinearWarpStripedThreadMap']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1PitchLinear2DThreadTileStripminedThreadMap_3_01Shape___00_01Thread896c01a3c466da1bf392e0cdfced4d53.html',1,'cutlass::transform::PitchLinear2DThreadTileStripminedThreadMap< Shape_, Threads, cutlass::layout::PitchLinearShape< 4, 4 > >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileAccessIterator_3_01Shape___00_01Element_3be8b96d170d886f39b6b30acab65e7a.html',1,'cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::TensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape___00_01Element___00_052caec9d5bceeb59b9a13cb3338ce64d.html',1,'cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::TensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape___00_01Element___00_039093927f4b1ee61538c569bf1ae4efd.html',1,'cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::TensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Crosswise >, AdvanceRank, ThreadMap_, Alignment >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape___00_01Element___00_02d305cfb0b55c6fb236a52cf2240651e.html',1,'cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::VoltaTensorOpMultiplicandBCongruous< sizeof_bits< Element_ >::value >, AdvanceRank, ThreadMap_, Alignment >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileIterator_3_01Shape___00_01Element___00_0390833403016f5d817416e20828845df.html',1,'cutlass::transform::threadblock::RegularTileIterator< Shape_, Element_, layout::VoltaTensorOpMultiplicandCrosswise< sizeof_bits< Element_ >::value, Shape_::kContiguous >, AdvanceRank, ThreadMap_, Alignment >']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapSimt_1_1Detail.html',1,'cutlass::epilogue::threadblock::DefaultThreadMapSimt']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultInterleavedThreadMapTensorOp_1_1Detail.html',1,'cutlass::epilogue::threadblock::DefaultInterleavedThreadMapTensorOp']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp_3_01ThreadblockShape__4433cc988100e98097a748d2670fb0fc.html',1,'cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, half_t >']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapVoltaTensorOp_3_01ThreadblockShape__52116c60c62f0fd520071558e42b814f.html',1,'cutlass::epilogue::threadblock::DefaultThreadMapVoltaTensorOp< ThreadblockShape_, WarpShape_, PartitionsK, ElementOutput_, ElementsPerAccess, float >']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1PitchLinearWarpRakedThreadMap_1_1Detail.html',1,'cutlass::transform::PitchLinearWarpRakedThreadMap']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1PitchLinearStripminedThreadMap_1_1Detail.html',1,'cutlass::transform::PitchLinearStripminedThreadMap']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1DefaultThreadMapTensorOp_1_1Detail.html',1,'cutlass::epilogue::threadblock::DefaultThreadMapTensorOp']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1InterleavedOutputTileThreadMap_1_1Detail.html',1,'cutlass::epilogue::threadblock::InterleavedOutputTileThreadMap']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1warp_1_1TileIteratorVoltaTensorOp_3_01WarpShape___00_01gemm_1_1Gemmffcab2297c8de8d0013602a39c525b78.html',1,'cutlass::epilogue::warp::TileIteratorVoltaTensorOp< WarpShape_, gemm::GemmShape< 32, 32, 4 >, half_t, layout::RowMajor >']]],
['detail',['Detail',['../structcutlass_1_1epilogue_1_1threadblock_1_1OutputTileOptimalThreadMap_1_1Detail.html',1,'cutlass::epilogue::threadblock::OutputTileOptimalThreadMap']]],
['detail',['Detail',['../structcutlass_1_1transform_1_1threadblock_1_1RegularTileAccessIterator_3_01Shape___00_01Element_0a9491607d11be8e1780e79ad711aa42.html',1,'cutlass::transform::threadblock::RegularTileAccessIterator< Shape_, Element_, layout::TensorOpMultiplicandCongruous< sizeof_bits< Element_ >::value, int(128/sizeof(Element_))>, AdvanceRank, ThreadMap_, Alignment >']]],
['device_5fbacked',['device_backed',['../classcutlass_1_1HostTensor.html#a73430856f79bedb64f9cf6b2044f38e3',1,'cutlass::HostTensor']]],
['device_5fdata',['device_data',['../classcutlass_1_1HostTensor.html#aca2b28a16fc92d29102d00f154a1dfd1',1,'cutlass::HostTensor::device_data()'],['../classcutlass_1_1HostTensor.html#abecb0dce978ea2c542d7d87a35f7997a',1,'cutlass::HostTensor::device_data() const ']]],
['device_5fdata_5fptr_5foffset',['device_data_ptr_offset',['../classcutlass_1_1HostTensor.html#a81043b0539c8d18c40957411dd149e28',1,'cutlass::HostTensor']]],
['device_5fdump_2eh',['device_dump.h',['../device__dump_8h.html',1,'']]],
['device_5fkernel_2eh',['device_kernel.h',['../device__kernel_8h.html',1,'']]],
['device_5fmemory_2eh',['device_memory.h',['../device__memory_8h.html',1,'']]],
['device_5fref',['device_ref',['../classcutlass_1_1HostTensor.html#a55a73e5ff7c7404c0bdee5f2b578b876',1,'cutlass::HostTensor::device_ref(LongIndex ptr_element_offset=0)'],['../classcutlass_1_1HostTensor.html#a4bf91f711ef17492809c09d53364cb35',1,'cutlass::HostTensor::device_ref(LongIndex ptr_element_offset=0) const ']]],
['device_5ftype',['device_type',['../structcutlass_1_1TypeTraits.html#a0fff5d43bdc223aab64e32dd045e6c4c',1,'cutlass::TypeTraits::device_type()'],['../structcutlass_1_1TypeTraits_3_01int8__t_01_4.html#a3569c760289b932f6acebffe42a1ff92',1,'cutlass::TypeTraits< int8_t >::device_type()'],['../structcutlass_1_1TypeTraits_3_01uint8__t_01_4.html#a582965751efd761e874611a3282dbe34',1,'cutlass::TypeTraits< uint8_t >::device_type()'],['../structcutlass_1_1TypeTraits_3_01int_01_4.html#a03dd152e9eff97c5b378fbdd7fc6abb5',1,'cutlass::TypeTraits< int >::device_type()'],['../structcutlass_1_1TypeTraits_3_01unsigned_01_4.html#aa303609d2c6f1618d9360190f3e450a8',1,'cutlass::TypeTraits< unsigned >::device_type()'],['../structcutlass_1_1TypeTraits_3_01int64__t_01_4.html#ad67f4b5261dd7d128c97c74b86a55cc8',1,'cutlass::TypeTraits< int64_t >::device_type()'],['../structcutlass_1_1TypeTraits_3_01uint64__t_01_4.html#a9bc248b7cd871ca79a73e3321ef5c1d0',1,'cutlass::TypeTraits< uint64_t >::device_type()'],['../structcutlass_1_1TypeTraits_3_01half__t_01_4.html#abdd84ca5cd2fe5209602fa730561a85c',1,'cutlass::TypeTraits< half_t >::device_type()'],['../structcutlass_1_1TypeTraits_3_01float_01_4.html#aa4d3935a9d7fe380f6177020c9ef45be',1,'cutlass::TypeTraits< float >::device_type()'],['../structcutlass_1_1TypeTraits_3_01double_01_4.html#abcb11e62d2ccc2fce7577ef63b2c1cf0',1,'cutlass::TypeTraits< double >::device_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01half_01_4_01_4.html#a01f6604dff64aedba173c1ceae9fd773',1,'cutlass::TypeTraits< complex< half > >::device_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01half__t_01_4_01_4.html#a7213cece86548037bcf7ad229633629d',1,'cutlass::TypeTraits< complex< half_t > >::device_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01float_01_4_01_4.html#a226f54f55c3a2154e89632ca81a99789',1,'cutlass::TypeTraits< complex< float > >::device_type()'],['../structcutlass_1_1TypeTraits_3_01complex_3_01double_01_4_01_4.html#a9aeac5291f73780ee4fd7c33966f56a3',1,'cutlass::TypeTraits< complex< double > >::device_type()']]],
['device_5fview',['device_view',['../classcutlass_1_1HostTensor.html#a075b666917a43c9bc168bfff6db27203',1,'cutlass::HostTensor::device_view(LongIndex ptr_element_offset=0)'],['../classcutlass_1_1HostTensor.html#a6d1c49888cf678d3d5469eba4e911337',1,'cutlass::HostTensor::device_view(LongIndex ptr_element_offset=0) const ']]],
['diag',['diag',['../structcutlass_1_1reference_1_1device_1_1detail_1_1TensorFillDiagonalFunc_1_1Params.html#abcbca40684cd478a53c0cc80c8e418e1',1,'cutlass::reference::device::detail::TensorFillDiagonalFunc::Params::diag()'],['../structcutlass_1_1reference_1_1device_1_1detail_1_1TensorUpdateDiagonalFunc_1_1Params.html#adc562519d503d235a49b11a8f2fc2bf6',1,'cutlass::reference::device::detail::TensorUpdateDiagonalFunc::Params::diag()'],['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorFillDiagonalFunc.html#a027d9ae77e068454e8df798018276c18',1,'cutlass::reference::host::detail::TensorFillDiagonalFunc::diag()']]],
['diagonal',['Diagonal',['../classcutlass_1_1thread_1_1Matrix.html#a7f68cf22835050f9c77df48750e278f2',1,'cutlass::thread::Matrix']]],
['difference_5ftype',['difference_type',['../structcutlass_1_1AlignedBuffer.html#a68527eff431854311f0221aa61e1c94d',1,'cutlass::AlignedBuffer::difference_type()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01true_01_4.html#a7ffe7541c2cadd34bc6e65ad351772ce',1,'cutlass::Array< T, N, true >::difference_type()'],['../classcutlass_1_1Array_3_01T_00_01N_00_01false_01_4.html#af8dd11bf19216707ab3340b66833c9c9',1,'cutlass::Array< T, N, false >::difference_type()']]],
['digits',['digits',['../structstd_1_1numeric__limits_3_01cutlass_1_1half__t_01_4.html#a92152311525685a53c6a0db4cb74f193',1,'std::numeric_limits< cutlass::half_t >']]],
['direct_5fepilogue_5ftensor_5fop_2eh',['direct_epilogue_tensor_op.h',['../direct__epilogue__tensor__op_8h.html',1,'']]],
['directepiloguetensorop',['DirectEpilogueTensorOp',['../classcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp.html#a7a64b4523780869f4b7dde2225572b2f',1,'cutlass::epilogue::threadblock::DirectEpilogueTensorOp']]],
['directepiloguetensorop',['DirectEpilogueTensorOp',['../classcutlass_1_1epilogue_1_1threadblock_1_1DirectEpilogueTensorOp.html',1,'cutlass::epilogue::threadblock']]],
['distribution',['Distribution',['../structcutlass_1_1Distribution.html',1,'cutlass']]],
['distribution',['Distribution',['../structcutlass_1_1Distribution.html#a40f0b9d0f92199f8a49c931d34dd8c8a',1,'cutlass::Distribution']]],
['distribution_2eh',['distribution.h',['../distribution_8h.html',1,'']]],
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
['divide_5fassert',['divide_assert',['../structcutlass_1_1divide__assert.html',1,'cutlass']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['divides',['divides',['../structcutlass_1_1divides.html',1,'cutlass']]],
['divides_3c_20array_3c_20half_5ft_2c_20n_20_3e_20_3e',['divides< Array< half_t, N > >',['../structcutlass_1_1divides_3_01Array_3_01half__t_00_01N_01_4_01_4.html',1,'cutlass']]],
['divides_3c_20array_3c_20t_2c_20n_20_3e_20_3e',['divides< Array< T, N > >',['../structcutlass_1_1divides_3_01Array_3_01T_00_01N_01_4_01_4.html',1,'cutlass']]],
['dot',['dot',['../structcutlass_1_1Coord.html#a057a417a4d4a6e2f69e0b55a6f7ee902',1,'cutlass::Coord::dot()'],['../namespacecutlass_1_1arch.html#aa36dc224381add086ca4e0f96a04a964',1,'cutlass::arch::dot(Array< T, N > const &a, Array< T, N > const &b, Accumulator accum)'],['../namespacecutlass_1_1arch.html#a47b07bdb36714f93b31ad14bec925274',1,'cutlass::arch::dot(Array< half_t, 2 > const &a, Array< half_t, 2 > const &b, half_t accum)'],['../namespacecutlass_1_1arch.html#acea872f9068fc5e07ce359984fe793c3',1,'cutlass::arch::dot(Array< half_t, 2 > const &a, Array< half_t, 2 > const &b, float accum)'],['../namespacecutlass_1_1arch.html#af6adcb969a1e4acfed289a7839013695',1,'cutlass::arch::dot(Array< int8_t, 4 > const &a, Array< int8_t, 4 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#a027d23864f8145417feecf3f019f9ef4',1,'cutlass::arch::dot(Array< uint8_t, 4 > const &a, Array< int8_t, 4 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#a40582b9a769301d83e532fc5215a5259',1,'cutlass::arch::dot(Array< int8_t, 4 > const &a, Array< uint8_t, 4 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#a262f27261d801dfd9a9d1cde280321ac',1,'cutlass::arch::dot(Array< uint8_t, 4 > const &a, Array< uint8_t, 4 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#a2c67269e7497315437d5ade0ab313ec8',1,'cutlass::arch::dot(Array< int16_t, 2 > const &a, Array< int8_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#a9dc4e9c5eddc624e2aecd15ef4b55f35',1,'cutlass::arch::dot(Array< uint16_t, 2 > const &a, Array< int8_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#aeedc20bfc0ea4dde354a9eee802bdea8',1,'cutlass::arch::dot(Array< int16_t, 2 > const &a, Array< uint8_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#ad4b65852d862718f9917ea2019752abb',1,'cutlass::arch::dot(Array< uint16_t, 2 > const &a, Array< uint8_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#ab3255aee11ed0bc172e248673576c37a',1,'cutlass::arch::dot(Array< int16_t, 2 > const &a, Array< int16_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#a4af405b474cc766adcaec63d46cbbc49',1,'cutlass::arch::dot(Array< uint16_t, 2 > const &a, Array< int16_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#ab42df2f28bc1b03350884df1048f060c',1,'cutlass::arch::dot(Array< int16_t, 2 > const &a, Array< uint16_t, 2 > const &b, int32_t accum)'],['../namespacecutlass_1_1arch.html#ae01862e2b75604eaca84e3b95bf110bf',1,'cutlass::arch::dot(Array< uint16_t, 2 > const &a, Array< uint16_t, 2 > const &b, int32_t accum)']]],
['doxygen_5fmainpage_2emd',['doxygen_mainpage.md',['../doxygen__mainpage_8md.html',1,'']]],
['dp4a_5ftype',['dp4a_type',['../classcutlass_1_1gemm_1_1warp_1_1MmaSimt.html#a05844d5ebdefec80551d620dd05c4d18',1,'cutlass::gemm::warp::MmaSimt']]],
['dst',['dst',['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorCopyIf.html#a0d94963e36e238233ddb550845b37004',1,'cutlass::reference::host::detail::TensorCopyIf']]],
['dsttensorview',['DstTensorView',['../structcutlass_1_1reference_1_1host_1_1detail_1_1TensorCopyIf.html#af25c3242565e3600b4ab447c2fc47f2d',1,'cutlass::reference::host::detail::TensorCopyIf']]],
Updated doxygen
2018-09-20 05:02:08 +08:00
['dummy',['dummy',['../structcutlass_1_1platform_1_1is__base__of__helper_1_1dummy.html',1,'cutlass::platform::is_base_of_helper']]],
CUTLASS 2.0 (#62) CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
2019-11-20 08:55:34 +08:00
['dump_5ffragment',['dump_fragment',['../namespacecutlass_1_1debug.html#a59e178f3c9b305571b12d80e5604b2c0',1,'cutlass::debug']]],
['dump_5fshmem',['dump_shmem',['../namespacecutlass_1_1debug.html#a6c7e23e12761423f54ccc4518b1f5fed',1,'cutlass::debug']]],
['dynamic_5fsmem',['dynamic_smem',['../structcutlass_1_1KernelLaunchConfiguration.html#a4a6ac693d4284c84301279219623e2bc',1,'cutlass::KernelLaunchConfiguration']]],
['gemm_5fbatched_2eh',['gemm_batched.h',['../device_2gemm__batched_8h.html',1,'']]],
['gemm_5fsplitk_5fparallel_2eh',['gemm_splitk_parallel.h',['../device_2gemm__splitk__parallel_8h.html',1,'']]],
['tensor_5fcompare_2eh',['tensor_compare.h',['../device_2tensor__compare_8h.html',1,'']]],
['tensor_5felementwise_2eh',['tensor_elementwise.h',['../device_2kernel_2tensor__elementwise_8h.html',1,'']]],
['tensor_5ffill_2eh',['tensor_fill.h',['../device_2tensor__fill_8h.html',1,'']]],
['tensor_5fforeach_2eh',['tensor_foreach.h',['../device_2tensor__foreach_8h.html',1,'']]],
['tensor_5fforeach_2eh',['tensor_foreach.h',['../device_2kernel_2tensor__foreach_8h.html',1,'']]]
CUTLASS v1.0 release
2018-05-17 02:44:56 +08:00
];
Reference in New Issue Copy Permalink