/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp File Reference#
gridwise_2d_multiple_reduction_multiblock.hpp File Reference
#include "ck/utility/reduction_common.hpp"
#include "ck/utility/reduction_operator.hpp"
#include "ck/utility/reduction_functions_accumulate.hpp"
#include "ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp"
#include "ck/tensor_operation/gpu/thread/reduction_functions_threadwise.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.
Namespaces | |
ck | |
Functions | |
template<typename GridwiseMultipleReduction , index_t NumReduction, typename InDataType , typename OutDataTypePointerTuple , typename AccDataType , typename InGridDesc_M_K , typename OutGridDesc_M_Tuple , typename InElementwiseOperationTuple , typename AccElementwiseOperationTuple > | |
__global__ void | ck::kernel_multiple_reduce_multiblock (const InGridDesc_M_K in_grid_desc_m_k, const OutGridDesc_M_Tuple out_grid_desc_m_tuple, const InElementwiseOperationTuple in_elementwise_op_tuple, const AccElementwiseOperationTuple acc_elementwise_op_tuple, index_t block_group_size, index_t num_k_block_tile_iteration, Array< AccDataType, NumReduction > alpha_values, const InDataType *const __restrict__ p_in_value_global, Array< AccDataType, NumReduction > beta_values, OutDataTypePointerTuple p_out_value_global_tuple) |