apeforest commented on a change in pull request #17882:
URL: https://github.com/apache/incubator-mxnet/pull/17882#discussion_r445866782
##########
File path: src/operator/tensor/broadcast_reduce_op.h
##########
@@ -1147,16 +1249,26 @@ inline void BroadcastComputeImpl(const nnvm::NodeAttrs&
attrs,
outputs[0].get_with_shape<xpu, 2, OType>(dst_shape.get<2>(), s);
Tensor<xpu, 2, IType> data =
inputs[0].get_with_shape<xpu, 2, IType>(src_shape.get<2>(), s);
- Kernel<broadcast_kernel<mshadow_op::identity>, xpu>::Launch(
- s, out.shape_.Size(), data.dptr_, out.dptr_, aux_data, req[0], 2);
+ if (isCPU) {
+ Kernel<broadcast_kernel_cpu<mshadow_op::identity>, xpu>::Launch(
+ s, data.shape_.Size(), data.dptr_, out.dptr_, aux_data, req[0], 2);
+ } else {
+ Kernel<broadcast_kernel<mshadow_op::identity>, xpu>::Launch(
+ s, out.shape_.Size(), data.dptr_, out.dptr_, aux_data, req[0], 2);
+ }
} else {
const int ndim = MXNET_SPECIAL_MAX_NDIM;
Tensor<xpu, ndim, OType> out =
outputs[0].get_with_shape<xpu, ndim, OType>(dst_shape.get<ndim>(),
s);
Tensor<xpu, ndim, IType> data =
inputs[0].get_with_shape<xpu, ndim, IType>(src_shape.get<ndim>(), s);
- Kernel<broadcast_kernel<mshadow_op::identity>, xpu>::Launch(
- s, out.shape_.Size(), data.dptr_, out.dptr_, aux_data, req[0], ndim);
+ if (isCPU) {
+ Kernel<broadcast_kernel_cpu<mshadow_op::identity>, xpu>::Launch(
Review comment:
If it's only CPU you don't need to use the generic kernel, right? You
can just use the Kernel<OP, cpu> template.
----------------------------------------------------------------
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:
us...@infra.apache.org
