[GitHub] eric-haibin-lin commented on a change in pull request #10939: [MXNET-420] broadcast_mul/div between csr and 1D dense on GPU

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

eric-haibin-lin commented on a change in pull request #10939: [MXNET-420] broadcast_mul/div between csr and 1D dense on GPU
URL: https://github.com/apache/incubator-mxnet/pull/10939#discussion_r188141258
 
 

 ##########
 File path: src/operator/tensor/elemwise_binary_broadcast_op_basic.cu
 ##########
 @@ -45,14 +45,16 @@ NNVM_REGISTER_OP(_backward_broadcast_sub)
                                                                 mshadow_op::negation>);
 
 NNVM_REGISTER_OP(broadcast_mul)
-.set_attr<FCompute>("FCompute<gpu>", BinaryBroadcastCompute<gpu, op::mshadow_op::mul>);
+.set_attr<FCompute>("FCompute<gpu>", BinaryBroadcastCompute<gpu, op::mshadow_op::mul>)
+.set_attr<FComputeEx>("FComputeEx<gpu>", BinaryBroadcastComputeSparseEx<gpu, op::mshadow_op::mul>);
 
 NNVM_REGISTER_OP(_backward_broadcast_mul)
 .set_attr<FCompute>("FCompute<gpu>", BinaryBroadcastBackwardUseIn<gpu, mshadow_op::right,
                                                                 mshadow_op::left>);
 
 NNVM_REGISTER_OP(broadcast_div)
-.set_attr<FCompute>("FCompute<gpu>", BinaryBroadcastCompute<gpu, op::mshadow_op::div>);
+.set_attr<FCompute>("FCompute<gpu>", BinaryBroadcastCompute<gpu, op::mshadow_op::div>)
 
 Review comment:
   pls update doc

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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