szha commented on a change in pull request #12926: parallelize
NDArray::Copy<cpu, cpu> when data size is large
URL: https://github.com/apache/incubator-mxnet/pull/12926#discussion_r227914102
##########
File path: src/ndarray/ndarray_function.cc
##########
@@ -32,19 +32,34 @@
namespace mxnet {
namespace ndarray {
+template<typename DType>
+void OMPCopy(const TBlob &from, TBlob *to, const index_t size) {
+ DType* dst_dptr = to->dptr<DType>();
+ DType* src_dptr = from.dptr<DType>();
+ #pragma omp parallel for
num_threads(engine::OpenMP::Get()->GetRecommendedOMPThreadCount())
+ for (index_t i = 0; i < size; ++i) {
+ dst_dptr[i] = src_dptr[i];
+ }
+}
+
template<>
void Copy<cpu, cpu>(const TBlob &from, TBlob *to,
Context from_ctx, Context to_ctx,
RunContext ctx) {
MSHADOW_TYPE_SWITCH(to->type_flag_, DType, {
if (to->type_flag_ == from.type_flag_) {
- mshadow::Copy(to->FlatTo1D<cpu, DType>(),
- from.FlatTo1D<cpu, DType>());
+ index_t copy_block_size = dmlc::GetEnv("MXNET_CPU_PARALLEL_COPY_SIZE",
200000);
+ const index_t size = from.Size();
+ if (size >= copy_block_size) {
+ OMPCopy<DType>(from, to, size);
+ } else {
+ mshadow::Copy(to->FlatTo1D<cpu, DType>(), from.FlatTo1D<cpu, DType>());
Review comment:
We can probably get rid of the mshadow::Copy here, and merge that in OMP
copy. This way you can put the threshold check as a condition in pragma omp
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
