mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
* add DeviceGemmXdl
* update script
* fix naming issue
* fix comment
* output HostTensorDescriptor
* rename
* padded GEMM for fwd v4r4r4 nhwc
* refactor
* refactor
* refactor
* adding ckProfiler
* adding ckProfiler
* refactor
* fix tuning parameter bug
* add more gemm instances
* add more fp16 GEMM instances
* fix profiler driver
* fix bug in tuning parameter
* add fp32 gemm instances
* small fix
* refactor
* rename
* refactor gemm profiler; adding DeviceConv and conv profiler
* refactor
* fix
* add conv profiler
* refactor
* adding more GEMM and Conv instance
* Create README.md
Add build instruction for ckProfiler
* Create README.md
Add Readme for gemm_xdl example
* Update README.md
Remove build instruction from top most folder
* Update README.md
* clean up
[ROCm/composable_kernel commit: e823d518cb]
24 lines
544 B
C++
24 lines
544 B
C++
#ifndef DEVICE_GEMM_INSTANTCE_HPP
|
|
#define DEVICE_GEMM_INSTANTCE_HPP
|
|
|
|
#include "device_gemm.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>&);
|
|
|
|
} // namespace device_gemm_instance
|
|
} // namespace device
|
|
} // namespace tensor_operation
|
|
} // namespace ck
|
|
#endif
|