GridwiseGemmPipeline_v2 Struct Reference

GridwiseGemmPipeline_v2 Struct Reference#

Composable Kernel: ck::GridwiseGemmPipeline_v2 Struct Reference

#include <gridwise_gemm_pipeline_v2.hpp>

Static Public Member Functions
__host__ static constexpr __device__ bool	IsSupported (const index_t num_loop)

__host__ static constexpr __device__ bool	CalculateHasMainLoop (const index_t num_loop)

template<bool HasMainLoop, typename AGridDesc , typename ABlockDesc , typename ABlockTransfer , typename AGridBuffer , typename ABlockBuffer , typename ABlockTransferStep , typename BGridDesc , typename BBlockDesc , typename BBlockTransfer , typename BGridBuffer , typename BBlockBuffer , typename BBlockTransferStep , typename BlockwiseGemm , typename CThreadBuffer >
static __device__ void	Run (const AGridDesc &a_grid_desc, const ABlockDesc &a_block_desc, ABlockTransfer &a_blockwise_copy, const AGridBuffer &a_grid_buf, ABlockBuffer &a_block_buf, const ABlockTransferStep &a_block_copy_step, const BGridDesc &b_grid_desc, const BBlockDesc &b_block_desc, BBlockTransfer &b_blockwise_copy, const BGridBuffer &b_grid_buf, BBlockBuffer &b_block_buf, const BBlockTransferStep &b_block_copy_step, const BlockwiseGemm &blockwise_gemm, CThreadBuffer &c_thread_buf, index_t num_loop)

Member Function Documentation

◆ CalculateHasMainLoop()

__host__ static constexpr __device__ bool ck::GridwiseGemmPipeline_v2::CalculateHasMainLoop ( const index_t num_loop )

inlinestaticconstexpr

◆ IsSupported()

__host__ static constexpr __device__ bool ck::GridwiseGemmPipeline_v2::IsSupported ( const index_t num_loop )

inlinestaticconstexpr

◆ Run()

template<bool HasMainLoop, typename AGridDesc , typename ABlockDesc , typename ABlockTransfer , typename AGridBuffer , typename ABlockBuffer , typename ABlockTransferStep , typename BGridDesc , typename BBlockDesc , typename BBlockTransfer , typename BGridBuffer , typename BBlockBuffer , typename BBlockTransferStep , typename BlockwiseGemm , typename CThreadBuffer >

static __device__ void ck::GridwiseGemmPipeline_v2::Run	(	const AGridDesc &	a_grid_desc,
		const ABlockDesc &	a_block_desc,
		ABlockTransfer &	a_blockwise_copy,
		const AGridBuffer &	a_grid_buf,
		ABlockBuffer &	a_block_buf,
		const ABlockTransferStep &	a_block_copy_step,
		const BGridDesc &	b_grid_desc,
		const BBlockDesc &	b_block_desc,
		BBlockTransfer &	b_blockwise_copy,
		const BGridBuffer &	b_grid_buf,
		BBlockBuffer &	b_block_buf,
		const BBlockTransferStep &	b_block_copy_step,
		const BlockwiseGemm &	blockwise_gemm,
		CThreadBuffer &	c_thread_buf,
		index_t	num_loop
	)

inlinestatic

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

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/docs-6.4.3/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp