/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_welford_first_half.hpp File Reference#
gridwise_multiblock_welford_first_half.hpp File Reference
#include "ck/utility/data_type.hpp"
#include "ck/utility/math.hpp"
#include "ck/tensor_operation/gpu/block/blockwise_welford.hpp"
#include "ck/tensor_operation/gpu/thread/threadwise_welford.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 GridwiseMultiblockWelfordFirstHalf_ , typename XDataType , typename MeanVarDataType , typename XGridDesc_M_K , typename MeanVarCountGridDesc_M_G , typename GetReduceCountPerThreadFunctor > | |
__global__ void | ck::kernel_multiblock_welford_first_half (const XGridDesc_M_K x_grid_desc_m_k, const MeanVarCountGridDesc_M_G mean_var_count_grid_desc_m_g, const GetReduceCountPerThreadFunctor get_reduce_count_per_thread, index_t num_k_block_tile_iteration, const XDataType *const __restrict__ p_x, MeanVarDataType *const p_welford_mean, MeanVarDataType *const p_welford_variance, int32_t *const p_welford_count) |