/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp File Reference#
device_grouped_gemm_xdl_splitk_cshuffle.hpp File Reference
#include <iostream>
#include <sstream>
#include "ck/ck.hpp"
#include "ck/utility/env.hpp"
#include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp"
#include "ck/host_utility/hip_check_error.hpp"
#include "ck/utility/common_header.hpp"
#include "ck/utility/tuple.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp"
Go to the source code of this file.
Namespaces | |
ck | |
ck::tensor_operation | |
ck::tensor_operation::device | |
Functions | |
template<typename GridwiseGemm , typename GemmDesc , bool HasMainKBlockLoop, InMemoryDataOperationEnum CGlobalMemoryDataOperation, typename AElementwiseOperation = ck::tensor_operation::element_wise::PassThrough, typename BElementwiseOperation = ck::tensor_operation::element_wise::PassThrough, typename CElementwiseOperation = ck::tensor_operation::element_wise::PassThrough> | |
__global__ void | ck::tensor_operation::device::kernel_grouped_gemm_xdl_splitk (const void CK_CONSTANT_ADDRESS_SPACE *gemm_descs_const, const index_t group_count, const AElementwiseOperation a_element_op, const BElementwiseOperation b_element_op, const CElementwiseOperation c_element_op) |