mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-18 12:00:07 +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]
23 lines
304 B
C++
23 lines
304 B
C++
#ifndef GEMM_COMMON_HPP
|
|
#define GEMM_COMMON_HPP
|
|
|
|
enum GemmMatrixLayout
|
|
{
|
|
MK_KN_MN, // 0
|
|
MK_NK_MN, // 1
|
|
KM_KN_MN, // 2
|
|
KM_NK_MN, // 3
|
|
MK_KN_NM, // 4
|
|
MK_NK_NM, // 5
|
|
KM_KN_NM, // 6
|
|
KM_NK_NM, // 7
|
|
};
|
|
|
|
enum GemmDataType
|
|
{
|
|
F32_F32_F32, // 0
|
|
F16_F16_F16, // 1
|
|
};
|
|
|
|
#endif
|