mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 06:01:23 +00:00
Add host API (#220)
* Add host API * manually rebase on develop * clean * manually rebase on develop * exclude tests from all target * address review comments * update client app name * fix missing lib name * clang-format update * refactor * refactor * refactor * refactor * refactor * fix test issue * refactor * refactor * refactor * upate cmake and readme Co-authored-by: Chao Liu <chao.liu2@amd.com>
This commit is contained in:
@@ -269,7 +269,7 @@ template <int NDimSpatial,
|
||||
bool profile_convnd_bwd_data_impl(int do_verification,
|
||||
int init_method,
|
||||
bool do_log,
|
||||
int nrepeat,
|
||||
bool time_kernel,
|
||||
ck::index_t N,
|
||||
ck::index_t K,
|
||||
ck::index_t C,
|
||||
@@ -410,7 +410,8 @@ bool profile_convnd_bwd_data_impl(int do_verification,
|
||||
{
|
||||
std::string conv_name = conv_ptr->GetTypeString();
|
||||
|
||||
float ave_time = invoker_ptr->Run(argument_ptr.get(), nrepeat);
|
||||
float ave_time =
|
||||
invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, time_kernel});
|
||||
|
||||
std::size_t flop =
|
||||
ck::utils::conv::get_flops(N, C, K, filter_spatial_lengths, output_spatial_lengths);
|
||||
|
||||
Reference in New Issue
Block a user