mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-20 14:59:17 +00:00
MaxPool & AvgPool bwd instances, test, ckProfiler, client example (#861)
* Add maxpool instances * Rename index pool to max pool. * Add maxpool bwd bf16 instances * Add avg pool bwd instances * Rename avgpool and maxpool to avg_pool3d and max_pool * Add bf16 pool fwd instances * Add max pool bwd to ckProfiler * Add avg pool3d bwd to ckProfiler * Add avg pool bwd test * Fix bug of reference pool fwd (dilation) * Fix bug of max pool bwd (dilation and initZero) * Support bf16 compute data type * Force compute type be f32. Because atomicAdd only support f32 * Add max pool bwd test * Rename folder * Rename pool * Add max pool bwd client example * Add avg pool bwd client example * Add missing workspace * clang format * Rename macro * remove useless header * remove useless layout
This commit is contained in:
@@ -100,6 +100,10 @@ int main(int argc, char* argv[])
|
||||
|
||||
if(op_ptr->IsSupportedArgument(argument_ptr.get()))
|
||||
{
|
||||
size_t workspace_sz = op_ptr->GetWorkSpaceSize(argument_ptr.get());
|
||||
SimpleDeviceMem workspace(workspace_sz);
|
||||
op_ptr->SetWorkSpacePointer(argument_ptr.get(), workspace.GetDeviceBuffer());
|
||||
|
||||
float ave_time = invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, true});
|
||||
|
||||
std::size_t num_byte = sizeof(XDataType) * M * N + sizeof(GammaDataType) * N +
|
||||
@@ -153,6 +157,10 @@ int main(int argc, char* argv[])
|
||||
|
||||
if(op_ptr->IsSupportedArgument(argument_ptr.get()))
|
||||
{
|
||||
size_t workspace_sz = op_ptr->GetWorkSpaceSize(argument_ptr.get());
|
||||
SimpleDeviceMem workspace(workspace_sz);
|
||||
op_ptr->SetWorkSpacePointer(argument_ptr.get(), workspace.GetDeviceBuffer());
|
||||
|
||||
invoker_ptr->Run(argument_ptr.get(), StreamConfig{nullptr, false});
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user