include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp File Reference

• include
• ck
• tensor_operation
• gpu
• grid

Classes | Namespaces | Functions

gridwise_tensor_rearrange.hpp File Reference

#include "ck/utility/common_header.hpp"
#include "ck/tensor_description/multi_index_transform_helper.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp"
#include "ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp"
#include "ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp"
#include "ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp"
#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"

Go to the source code of this file.

Classes
struct	ck::GridwiseTensorRearrange< InputGridDesc, InputDataType, OutputGridDesc, OutputDataType, BlockSize, MPerBlock, KPerBlock, ThreadClusterLengths, ScalarPerVector, DstInMemOp, Block2ETileMap, ComputePtrOffsetOfStridedBatch >

Namespaces
	ck

Functions
template<typename InputGridDesc , typename InputDataType , typename OutputGridDesc , typename OutputDataType , typename Block2ETileMap , typename ComputePtrOffsetOfStridedBatch , typename GridwiseTensorRearrangeKernel >
__global__ void	ck::kernel_tensor_rearrange (const InputGridDesc in_grid_desc, const InputDataType *__restrict__ p_in_global, const OutputGridDesc out_grid_desc, OutputDataType *__restrict__ p_out_global, const index_t batch_count, const Block2ETileMap block_2_tile_map, const ComputePtrOffsetOfStridedBatch compute_ptr_offset_of_batch)