baidu-research / DeepBench

Benchmarking Deep Learning operations on different hardware
Apache License 2.0
1.07k stars 239 forks source link

Make cudnn_helper.h compile independently. #78

Closed galv closed 6 years ago

galv commented 6 years ago

Previously, it would depend on having already been #included, in order to access std::shared_ptr.

sharannarang commented 6 years ago

LGTM, merging.