/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/device/impl/split_k_utils.hpp File Reference

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/device/impl/split_k_utils.hpp File Reference#

Composable Kernel: /home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/device/impl/split_k_utils.hpp File Reference
split_k_utils.hpp File Reference
#include <numeric>
#include <hip/hip_runtime.h>
#include "ck/utility/env.hpp"
#include "ck/utility/number.hpp"
#include "ck/host_utility/hip_check_error.hpp"
#include "ck/ck.hpp"

Go to the source code of this file.

Classes

struct  ck::tensor_operation::device::DeviceProperties
 

Namespaces

 ck
 
 ck::tensor_operation
 
 ck::tensor_operation::device
 

Functions

ck::index_t ck::tensor_operation::device::get_best_occupancy_k_batch_value (int max_occupancy, ck::index_t grid_size)
 
template<ck::index_t NDimSpatial>
auto ck::tensor_operation::device::get_bwd_weight_gemm_sizes (const std::array< index_t, NDimSpatial+3 > &a_g_n_k_wos_lengths, const std::array< index_t, NDimSpatial+3 > &e_g_k_c_xs_lengths)
 
template<ck::index_t MPerBlock, ck::index_t NPerBlock>
ck::index_t ck::tensor_operation::device::calculate_mn_grid_size (ck::index_t gemmM, ck::index_t gemmN)