| CalculateGridSize(const CGridDesc_M_N &c_grid_desc_m_n) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| CalculateHasMainK0BlockLoop(index_t K0) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| CheckValidity(const AGridDesc_K0_M_K1 &a_grid_desc_k0_m_k1, const BGridDesc_K0_N_K1 &b_grid_desc_k0_n_k1, const CGridDesc_M_N &c_grid_desc_m_n, index_t M01, index_t N01) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| DefaultBlock2CTileMap typedef | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | |
| GetABlockDescriptor_K0PerBlock_MPerBlock_K1() | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| GetSharedMemoryNumberOfByte() | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| GetWaveIdx() | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| GetWaveKNIdx(const index_t thread_id) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| I0 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I1 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I2 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I3 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I4 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I5 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I6 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| I7 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| IsValidCompilationParameter() | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| K0PerThread | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| K1 | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| MakeBGridDescriptor_K0_K1_K2_N0_N1_N2_N3_K3(const BGridDesc_K0_N_K1 &b_grid_desc_k0_n_k1) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| MakeCGridDescriptor_M0_N0_M1_N1_M2_M3_M4_N2(const CGridDesc_M_N &c_grid_desc_m_n) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| MakeDefaultBlock2CTileMap(const CGridDesc_M_N &c_grid_desc_m_n, index_t M01, index_t N01) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| MWaves | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| NWaves | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| Run(const FloatAB *__restrict__ p_a_grid, const FloatAB *__restrict__ p_b_grid, FloatC *__restrict__ p_c_grid, void *__restrict__ p_shared, const AGridDesc_K0_M_K1 &a_grid_desc_k0_m_k1, const BGridDesc_K0_K1_K2_N0_N1_N2_N3_K3 &b_grid_desc_k0_k1_k2_n0_n1_n2_n3_k3, const CGridDesc_M0_N0_M1_N1_M2_M3_M4_N2 &c_grid_desc_m0_n0_m1_n1_m2_m3_m4_n2, const AElementwiseOperation &a_element_op, const BElementwiseOperation &b_element_op, const CElementwiseOperation &c_element_op, const Block2CTileMap &block_2_ctile_map) | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | inlinestatic |
| ThisThreadBlock typedef | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | |
| WaveSize | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |
| xdlops_gemm | ck::GridwiseGemm_k0mk1_k0nk1_mn_xdlops_skip_b_lds_v1< BlockSize, FloatAB, FloatAcc, FloatC, CGlobalMemoryDataOperation, AGridDesc_K0_M_K1, BGridDesc_K0_N_K1, CGridDesc_M_N, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, MPerBlock, NPerBlock, K0PerBlock, MPerXdl, NPerXdl, K1Value, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, AThreadTransferSrcResetCoordinateAfterRun, ABlockLdsExtraM, BBlockTransferSrcScalarPerVector, BThreadTransferSrcResetCoordinateAfterRun, BBlockBufferSize, CThreadTransferSrcDstAccessOrder, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector > | static |