mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 18:42:06 +00:00
Grouped GEMM for fp16 (#126)
* init of grouped_gemm
* 2 gemm test
* perf test
* clean
* wrap desc into a struct
* test cast static_arr to pointer
* add ptr to GemmDesc
* add grouped gemm profiler
* fixed mem issue with unique_ptr
* clean
* clean
* finished ckprofiler
* Update README.md
* readme
* fixed readme
* add example
* improve code
* fixed comments: reserve, seperate ptr and gemm_shapes
* merge group and non-group
* fixed comments: replace push_back with emplace_back to avoid copy constructor
* fixed comments: unified blk2ctile; add test
* ci fix
* fixed ci
* fixed ci
* fixed ci
[ROCm/composable_kernel commit: 716f1c7fb1]
This commit is contained in:
@@ -15,9 +15,11 @@ int profile_conv_fwd_bias_relu_add(int, char*[]);
|
||||
int profile_conv_fwd_bias_relu_atomic_add(int, char*[]);
|
||||
int profile_conv_bwd_data(int, char*[]);
|
||||
int profile_reduce(int, char*[]);
|
||||
int profile_grouped_gemm(int, char*[]);
|
||||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
#if 0
|
||||
if(strcmp(argv[1], "gemm") == 0)
|
||||
{
|
||||
return profile_gemm(argc, argv);
|
||||
@@ -62,6 +64,10 @@ int main(int argc, char* argv[])
|
||||
{
|
||||
return profile_reduce(argc, argv);
|
||||
}
|
||||
else if(strcmp(argv[1], "grouped_gemm") == 0)
|
||||
{
|
||||
return profile_grouped_gemm(argc, argv);
|
||||
}
|
||||
else
|
||||
{
|
||||
// clang-format off
|
||||
@@ -74,9 +80,13 @@ int main(int argc, char* argv[])
|
||||
" conv_fwd_bias_relu_add: ForwardConvolution+Bias+ReLU+Add\n"
|
||||
" conv_fwd_bias_relu_atomic_add: ForwardConvolution+Bias+ReLU+AtomicAdd\n"
|
||||
" conv_bwd: BackwardConvolution\n"
|
||||
" grouped_gemm: Grouped Gemm\n"
|
||||
" reduce: REDUCE\n");
|
||||
// clang-format on
|
||||
|
||||
return 0;
|
||||
}
|
||||
#else
|
||||
profile_grouped_gemm(argc, argv);
|
||||
#endif
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user