mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
* fix relu
* clean up
* clean up
* adding 1x1 conv
* adding 1x1 conv
* added 1x1 conv
* refactor
* refactor
* refactor
* added profiler for conv+bias+relu+add
* clean up
* adding conv+bias+relu
* adding conv+bias+relu
* added conv+bias+relu
* Update README.md
* update cpu verification
* adding c shuffle
* update static_tensor for dealing with invalid element
* adding c shuffle
* debugging
* fix bug
* convert to fp16 before shuffle
* shuffle more than one M/NRepeat
* clean up
* remove coordinate step hack from GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r1
* clean up
* remove coordinate step hack from all gridwise gemm xdl
* clean up coordinate step hack
* clean up coordinate step hack
* ThreadwiseTensorSliceTransfer_v3r2 support pointwise op on both src and dst
* adding output shuffle in conv+bias+relu+add
* update
* added conv+bias+relu+add with c shuffle
* added conv+bias+relu+add with c shuffle
* fix forward_sweep bugs in threadwise copy
* clean up
* refactor
* clean up
* clean up
* added conv_c_shuffle+bias_relu
* clean up
* added conv+bias+relu+atomic_add
* clean up
* clean up
* clean up
* clean up
* clean up
* clean up
* misc fixes; add 1x1 specialization
* clean up
* delete unused device op
* clean up
* add support for odd C value
[ROCm/composable_kernel commit: acbd7bd7c5]
27 lines
785 B
C++
27 lines
785 B
C++
#ifndef CK_DEVICE_OPERATION_INSTANCE_HPP
|
|
#define CK_DEVICE_OPERATION_INSTANCE_HPP
|
|
|
|
#include <stdlib.h>
|
|
|
|
namespace ck {
|
|
namespace tensor_operation {
|
|
namespace device {
|
|
|
|
template <typename OpInstance, typename NewOpInstances>
|
|
void add_device_operation_instances(std::vector<std::unique_ptr<OpInstance>>& op_instances,
|
|
const NewOpInstances& new_op_instances)
|
|
{
|
|
ck::static_for<0, std::tuple_size_v<NewOpInstances>, 1>{}([&](auto i) {
|
|
const auto new_op_instance = std::get<i>(new_op_instances);
|
|
|
|
using NewOpInstance = remove_cvref_t<decltype(new_op_instance)>;
|
|
|
|
op_instances.push_back(std::make_unique<NewOpInstance>(new_op_instance));
|
|
});
|
|
}
|
|
|
|
} // namespace device
|
|
} // namespace tensor_operation
|
|
} // namespace ck
|
|
#endif
|