mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 17:00:18 +00:00
* 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
53 lines
1.8 KiB
C++
53 lines
1.8 KiB
C++
#ifndef DEVICE_CONV_INSTANTCE_HPP
|
|
#define DEVICE_CONV_INSTANTCE_HPP
|
|
|
|
#include "device_conv.hpp"
|
|
#include "element_wise_operation.hpp"
|
|
|
|
namespace ck {
|
|
namespace tensor_operation {
|
|
namespace device {
|
|
namespace device_conv_instance {
|
|
|
|
template <ck::index_t NDimSpatial,
|
|
typename InDataType,
|
|
typename WeiDataType,
|
|
typename OutDataType,
|
|
typename InLayout,
|
|
typename WeiLayout,
|
|
typename OutLayout>
|
|
void add_device_conv_fwd_instance(
|
|
std::vector<DeviceConvFwdPtr<ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough>>&);
|
|
|
|
template <ck::index_t NDimSpatial,
|
|
typename InDataType,
|
|
typename WeiDataType,
|
|
typename OutDataType,
|
|
typename InLayout,
|
|
typename WeiLayout,
|
|
typename OutLayout>
|
|
void add_device_conv_bwd_instance(
|
|
std::vector<DeviceConvBwdPtr<ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough>>&);
|
|
|
|
template <ck::index_t NDimSpatial,
|
|
typename InDataType,
|
|
typename WeiDataType,
|
|
typename OutDataType,
|
|
typename InLayout,
|
|
typename WeiLayout,
|
|
typename OutLayout>
|
|
void add_device_conv_wrw_instance(
|
|
std::vector<DeviceConvWrwPtr<ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough,
|
|
ck::tensor_operation::element_wise::PassThrough>>&);
|
|
|
|
} // namespace device_conv_instance
|
|
} // namespace device
|
|
} // namespace tensor_operation
|
|
} // namespace ck
|
|
#endif
|