[GitHub] [incubator-mxnet] gxkevin opened a new issue #15450: the recall_model->exec->Forward cost most time, how can I reduce the cost time?

[GitBox <gi...@apache.org>]

gxkevin opened a new issue #15450: the recall_model->exec->Forward cost most time, how can I reduce the cost time?
URL: https://github.com/apache/incubator-mxnet/issues/15450
 
 
   I have a problem is that when I do the dnn predict, where I will use the  SyncCopyFromCPU and the Forward， the batch_size and fea_num is 40，default blas is openblas（I have also tried the Intel mkl，but it doesn't work），the cpu is broadwell，58 logical core total。
   
   I have 32-58 worker thread，each thead only have 1 openmp thread，I worry that open too many openmp thread will decrease the performance。
   
   After the test, I found that , the predict totally cost 13.9ms, SyncCopyFromCPU cost 275us, but the Forward cost 11ms， have can i reduce the forward cost time ?
   
           dnn_model->model_data["data"].SyncCopyFromCPU(batch_data.data(), batch_size * fea_num);
           mxnet::cpp::NDArray::WaitAll();
           dnn_model->exec->Forward(false);
           mxnet::cpp::NDArray::WaitAll();
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services