ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-13 09:45:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Groupnorm + swish external api (#668)

Browse Source 
* Rename to proper naming

* Add example of groupnorm + swish

* Extract duplicate code in example

* Add groupnorm + swish instances

* Ractor instance generation, split into multiple cpp file

* Add external api and client example

* Refine profiler message

* Use ck math version of exp

* Refine problem size in example

* Add host version of exp
This commit is contained in:
rocking5566
2023-04-10 21:02:17 +08:00
committed by GitHub
parent 3248387bbb
commit ed3a2e5226
23 changed files with 626 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
profiler/include/profiler/profile_groupnorm_impl.hpp
View File

@@ -190,9 +190,9 @@ bool profile_groupnorm_impl(int do_verification,
if(time_kernel)
{
LogRange(std::cout << "length = ", length, ",") << ", ";
std::cout << "num_kernel = " << num_kernel << ", best perf = " << best_avg_time << " ms, "
<< best_gb_per_sec << " GB/s, " << best_instance_name << std::endl;
LogRange(std::cout << "length = ", length, ",") << std::endl;
std::cout << "best perf = " << best_avg_time << " ms, " << best_gb_per_sec << " GB/s, "
<< best_instance_name << std::endl;
}
if(num_kernel == 0)