pengzhao-intel commented on a change in pull request #14819: [MKLDNN] Enable 
more convolution + activation fusion
URL: https://github.com/apache/incubator-mxnet/pull/14819#discussion_r279192785
 
 

 ##########
 File path: src/operator/nn/mkldnn/mkldnn_act.cc
 ##########
 @@ -57,6 +57,10 @@ bool SupportMKLDNNAct(const ActivationParam& param, const 
NDArray &input) {
   return SupportMKLDNNAct(param);
 }
 
+bool SupportQuantizedMKLDNNAct(const ActivationParam &param) {
+  return param.act_type == activation::kReLU;
 
 Review comment:
   Add `TODO` for other FP32 fusion in the future

----------------------------------------------------------------
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:
[email protected]


With regards,
Apache Git Services

Reply via email to