mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +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]
27 lines
531 B
C++
27 lines
531 B
C++
#include <iostream>
|
|
#include <numeric>
|
|
#include <initializer_list>
|
|
#include <cstdlib>
|
|
#include <stdlib.h>
|
|
#include <half.hpp>
|
|
|
|
int gemm_profiler(int, char*[]);
|
|
int conv_profiler(int, char*[]);
|
|
|
|
int main(int argc, char* argv[])
|
|
{
|
|
if(strcmp(argv[1], "gemm") == 0)
|
|
{
|
|
return gemm_profiler(argc, argv);
|
|
}
|
|
else if(strcmp(argv[1], "conv") == 0)
|
|
{
|
|
return conv_profiler(argc, argv);
|
|
}
|
|
else
|
|
{
|
|
printf("arg1: tensor operation (gemm=GEMM, conv=Convolution)\n");
|
|
return 0;
|
|
}
|
|
}
|