mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 08:50:17 +00:00
41cdd3801a
* gemm+activation * move C pointwise operation into threadwise copy * add pointwise operation to A/B matrix * update ckProfiler * adding bias add * adding bias add * adding bias add * added bias add; worked around compiler issues * clean up * clean up * Update README.md * Update README.md * Update README.md * clean up * add conv_xdl example * adding conv_xdl_bias_relu_add example * add conv+bias+relu+add, but has register spill issue * tweak * tweak * refactor * Update README.md update readme for example/2_gemm_xdl_bias_relu_add * clean up * Update README.md update readme for example/3_conv_xdl * Update README.md
28 lines
794 B
C++
28 lines
794 B
C++
#ifndef DEVICE_GEMM_INSTANTCE_HPP
|
|
#define DEVICE_GEMM_INSTANTCE_HPP
|
|
|
|
#include "device_gemm.hpp"
|
|
#include "element_wise_operation.hpp"
|
|
|
|
namespace ck {
|
|
namespace tensor_operation {
|
|
namespace device {
|
|
namespace device_gemm_instance {
|
|
|
|
template <typename ADataType,
|
|
typename BDataType,
|
|
typename CDataType,
|
|
typename ALayout,
|
|
typename BLayout,
|
|
typename CLayout>
|
|
void add_device_gemm_instance(
|
|
std::vector<DeviceGemmPtr<ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough>>&);
|
|
|
|
} // namespace device_gemm_instance
|
|
} // namespace device
|
|
} // namespace tensor_operation
|
|
} // namespace ck
|
|
#endif
|