reminisce commented on a change in pull request #7226: Extending the GPU dot 
operator
URL: https://github.com/apache/incubator-mxnet/pull/7226#discussion_r132261720
 
 

 ##########
 File path: src/operator/tensor/dot-inl.h
 ##########
 @@ -187,8 +187,8 @@ inline bool DotForwardInferStorageType(const 
nnvm::NodeAttrs& attrs,
   CHECK_EQ(out_attrs->size(), 1U);
   const DotParam& param = nnvm::get<DotParam>(attrs.parsed);
   // csr has many zero columns, so the result of dot(csr.T, matrix) should be 
rsp
-  // dot(csr.T,dns)=rsp not yet implemented on gpu
-  if (param.transpose_a && kCSRStorage == (*in_attrs)[0] && ctx.dev_type != 
Context::kGPU) {
+  // TODO(stefan/haibin): don't enforce kRowSparseStorage if out_attrs has 
already been set
+  if (param.transpose_a && kCSRStorage == (*in_attrs)[0]) {
     STORAGE_TYPE_ASSIGN_CHECK(*out_attrs, 0, kRowSparseStorage);
 
 Review comment:
   I discussed this with @eric-haibin-lin . We should change all 
`STORAGE_TYPE_ASSIGN_CHECK` to `type_assign` to support fallback mechanism. In 
the long run, we should also save the `type_assign` return value to determine 
whether to fallback to `FCompute` inside `FComputeEx`.
 
----------------------------------------------------------------
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:
us...@infra.apache.org


With regards,
Apache Git Services

Reply via email to