Is there any way to enhance pdnn performance on GPU machine? the run time for the same algorithm on cpu is almost identical to the gpu one? any ideas?

yajiemiao / pdnn

PDNN: A Python Toolkit for Deep Learning. http://www.cs.cmu.edu/~ymiao/pdnntk.html

Apache License 2.0

224 stars 105 forks source link

Open nouramoubayed opened 8 years ago

nouramoubayed commented 8 years ago

I use a big partition value and i enable Stream, but nothing seems to make it work better.

ghost commented 8 years ago

This is most likely because your GPUs are not properly. What functionality are you using from PDNN?