mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-16 10:59:55 +00:00
Batched gemm and reduction (#156)
* adding batched_gemm_and_reduction
* batched_gemm_reduce works with bactch_count=1
* fix a bug in grid_size; batched_gemm_reduce works for batch_count > 1
* adding profiler for batched_gemm_fp16
* fixed a bug in declaration of d1 and d0; both example and profiler work
* clang-format
* cleanup
* batched_gemm_reduce: add test
* minor change
* fixed some typo in function names
[ROCm/composable_kernel commit: 34c661e71c]
This commit is contained in:
@@ -17,6 +17,7 @@ int profile_conv_fwd_bias_relu_add(int, char*[]);
|
||||
int profile_conv_fwd_bias_relu_atomic_add(int, char*[]);
|
||||
int profile_convnd_bwd_data(int, char*[], int);
|
||||
int profile_reduce(int, char*[]);
|
||||
int profile_batched_gemm_reduce(int, char*[]);
|
||||
|
||||
int main(int argc, char* argv[])
|
||||
{
|
||||
@@ -44,6 +45,10 @@ int main(int argc, char* argv[])
|
||||
{
|
||||
return profile_batched_gemm(argc, argv);
|
||||
}
|
||||
else if(strcmp(argv[1], "batched_gemm_reduce") == 0)
|
||||
{
|
||||
return profile_batched_gemm_reduce(argc, argv);
|
||||
}
|
||||
else if(strcmp(argv[1], "grouped_gemm") == 0)
|
||||
{
|
||||
profile_grouped_gemm(argc, argv);
|
||||
|
||||
Reference in New Issue
Block a user