DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB > Struct Template Reference

• ck
• tensor_operation
• device
• DeviceMoeGemmBlockScale

Classes | Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | List of all members

ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB > Struct Template Reference

#include <device_moe_gemm_blockscale.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >:

Classes
struct	Invoker

Public Types
template<index_t NXdlPerWave_>
using	GridwiseGemmBase
using	GridwiseGemm64 = GridwiseGemmBase<math::max(NXdlPerWave64, 1)>
using	GridwiseGemm32 = GridwiseGemmBase<NXdlPerWave32>
using	Argument = typename GridwiseGemm64::Argument

Public Member Functions
int	GetPreShuffleParameters () override
bool	IsSupportedArgument (const BaseArgument *p_arg) override
std::unique_ptr< BaseArgument >	MakeArgumentPointer (const void *p_a, const void *p_b, std::array< const void *, NumDTensor > p_ds, void *p_c, index_t M, index_t N, index_t K, index_t StrideA, index_t StrideB, std::array< ck::index_t, NumDTensor > StrideDs, index_t StrideC, const void *p_a_scale, const void *p_b_scale, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CElementwiseOperation c_element_op) override
std::unique_ptr< BaseInvoker >	MakeInvokerPointer () override
std::string	GetTypeString () const override
Public Member Functions inherited from ck::tensor_operation::device::BaseOperator
	BaseOperator ()=default
	BaseOperator (const BaseOperator &)=default
BaseOperator &	operator= (const BaseOperator &)=default
virtual std::string	GetInstanceString () const
virtual std::string	GetTypeIdName () const
virtual std::optional< std::string >	GetObjectName () const
virtual std::optional< std::string >	GetTemplateInfo () const
virtual std::string	GetTypeIdHashCode () const
virtual size_t	GetWorkSpaceSize (const BaseArgument *) const
virtual void	SetWorkSpacePointer (BaseArgument *p_arg, void *p_workspace, const StreamConfig &=StreamConfig{}) const
virtual	~BaseOperator ()

Static Public Member Functions
static constexpr bool	IsValidCompilationParameter ()
static bool	IsSupportedArgument (const Argument &arg)
static auto	MakeArgument (const void *p_sorted_token_ids, const void *p_sorted_expert_ids, const void *p_max_token_id, const void *p_a, const void *p_b, std::array< const void *, NumDTensor > p_ds, void *p_c, index_t NumTokens, index_t TopK, index_t M, index_t N, index_t K, index_t StrideA, index_t StrideB, std::array< index_t, NumDTensor > StrideDs, index_t StrideC, const void *p_a_scale, const void *p_b_scale, index_t KBatch, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CElementwiseOperation c_element_op)
static auto	MakeInvoker ()

Static Public Attributes
static GET_NXDL_PER_WAVE_IMPL constexpr auto	NXdlPerWave64 = GetNXdlPerWave<true>()
static constexpr auto	NXdlPerWave32 = GetNXdlPerWave<false>()
static constexpr index_t	NumDTensor = DsDataType::Size()
static constexpr index_t	APackedSize
static constexpr index_t	BPackedSize
Static Public Attributes inherited from ck::tensor_operation::device::DeviceGemmMultipleD_BlockScale_BPreshuffle< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, ScaleBlockM, ScaleBlockN, ScaleBlockK, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >
static constexpr index_t	NumDTensor

Member Typedef Documentation

◆ Argument

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

using ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::Argument = typename GridwiseGemm64::Argument

◆ GridwiseGemm32

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

using ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::GridwiseGemm32 = GridwiseGemmBase<NXdlPerWave32>

◆ GridwiseGemm64

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

using ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::GridwiseGemm64 = GridwiseGemmBase<math::max(NXdlPerWave64, 1)>

◆ GridwiseGemmBase

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

template<index_t NXdlPerWave_>

using ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::GridwiseGemmBase

Member Function Documentation

◆ GetPreShuffleParameters()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

int ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::GetPreShuffleParameters ( )

inlineoverridevirtual

Implements ck::tensor_operation::device::DeviceGemmMultipleD_BlockScale_BPreshuffle< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, ScaleBlockM, ScaleBlockN, ScaleBlockK, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >.

◆ GetTypeString()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

std::string ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::GetTypeString ( ) const

inlineoverridevirtual

Reimplemented from ck::tensor_operation::device::BaseOperator.

◆ IsSupportedArgument() [1/2]

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

bool ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::IsSupportedArgument ( const Argument & arg )

inlinestatic

◆ IsSupportedArgument() [2/2]

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

bool ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::IsSupportedArgument ( const BaseArgument * p_arg )

inlineoverridevirtual

Reimplemented from ck::tensor_operation::device::BaseOperator.

◆ IsValidCompilationParameter()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

constexpr bool ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::IsValidCompilationParameter ( )

inlinestaticconstexpr

◆ MakeArgument()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

auto ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::MakeArgument ( const void * p_sorted_token_ids, const void * p_sorted_expert_ids, const void * p_max_token_id, const void * p_a, const void * p_b, std::array< const void *, NumDTensor > p_ds, void * p_c, index_t NumTokens, index_t TopK, index_t M, index_t N, index_t K, index_t StrideA, index_t StrideB, std::array< index_t, NumDTensor > StrideDs, index_t StrideC, const void * p_a_scale, const void * p_b_scale, index_t KBatch, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CElementwiseOperation c_element_op )

inlinestatic

◆ MakeArgumentPointer()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

std::unique_ptr< BaseArgument > ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::MakeArgumentPointer ( const void * p_a, const void * p_b, std::array< const void *, NumDTensor > p_ds, void * p_c, index_t M, index_t N, index_t K, index_t StrideA, index_t StrideB, std::array< ck::index_t, NumDTensor > StrideDs, index_t StrideC, const void * p_a_scale, const void * p_b_scale, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CElementwiseOperation c_element_op )

inlineoverridevirtual

Implements ck::tensor_operation::device::DeviceGemmMultipleD_BlockScale_BPreshuffle< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, ScaleBlockM, ScaleBlockN, ScaleBlockK, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >.

◆ MakeInvoker()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

auto ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::MakeInvoker ( )

inlinestatic

◆ MakeInvokerPointer()

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

std::unique_ptr< BaseInvoker > ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::MakeInvokerPointer ( )

inlineoverridevirtual

Implements ck::tensor_operation::device::DeviceGemmMultipleD_BlockScale_BPreshuffle< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, ScaleBlockM, ScaleBlockN, ScaleBlockK, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >.

Member Data Documentation

◆ APackedSize

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

index_t ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::APackedSize

staticconstexpr

Initial value:

= []() {

if constexpr(is_same_v<remove_cvref_t<ADataType>, pk_i4_t>)

return 2;

else

return 1;

}()

ck::is_same_v

constexpr bool is_same_v

Definition type.hpp:283

ck::pk_i4_t

Definition data_type.hpp:187

◆ BPackedSize

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

index_t ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::BPackedSize

staticconstexpr

Initial value:

= []() {

if constexpr(is_same_v<remove_cvref_t<BDataType>, pk_i4_t>)

return 2;

else

return 1;

}()

◆ NumDTensor

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

index_t ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::NumDTensor = DsDataType::Size()

staticconstexpr

◆ NXdlPerWave32

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

auto ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::NXdlPerWave32 = GetNXdlPerWave<false>()

staticconstexpr

◆ NXdlPerWave64

template<typename ALayout, typename BLayout, typename DsLayout, typename CLayout, typename ADataType, typename AScaleDataType, typename BDataType, typename BScaleDataType, typename DsDataType, typename CDataType, typename GemmAccDataType, typename CShuffleDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation, GemmSpecialization GemmSpec, index_t BlockSize, index_t ScaleBlockM, index_t ScaleBlockN, index_t ScaleBlockK, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEShuffleBlockTransferScalarPerVectors, BlockGemmPipelineScheduler BlkGemmPipeSched = BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion BlkGemmPipelineVer = BlockGemmPipelineVersion::v1, index_t ActivationOP = 0, bool NSwizzle = false, bool IsInputGemm = true, bool MulRoutedWeight = false, typename IndexType = index_t, typename ComputeTypeA = CDataType, typename ComputeTypeB = ComputeTypeA, typename LDSTypeA = ComputeTypeA, typename LDSTypeB = ComputeTypeB>

GET_NXDL_PER_WAVE_IMPL constexpr auto ck::tensor_operation::device::DeviceMoeGemmBlockScale< ALayout, BLayout, DsLayout, CLayout, ADataType, AScaleDataType, BDataType, BScaleDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, ScaleBlockM, ScaleBlockN, ScaleBlockK, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ActivationOP, NSwizzle, IsInputGemm, MulRoutedWeight, IndexType, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >::NXdlPerWave64 = GetNXdlPerWave<true>()

staticconstexpr

---

The documentation for this struct was generated from the following file:

• device_moe_gemm_blockscale.hpp