Performance of Caffe with cuDNN on the TK1

Autonomous Machines Jetson & Embedded Systems Jetson TK1
1

I have been running Caffe on the TK1 and I have noticed that I get hardly any improvement in performance with the forward or backward pass times when linking to cuDNN v2. The improvement is around a factor 1.05x better than without cuDNN. Is this to be expected for cuDNN on the TK1 ? Has anyone seen better acceleration ?

2

Hi, rhann.

Have you maximized CPU, GPU and EMC clocks?

More about setting those can be found from the wiki:
http://elinux.org/Jetson/Performance

Thanks

3

Yes, I did. The overall effect was to reduce the latency for inference. But the cuDNN performance still was only about 1.05x better than without linking to the library.

4

Hi rhann,

I’m not sure the result whether it’s normal, but you could refer to below reference performance numbers on other HW configuration to know the gap:
NVIDIA Jetson TK1 - cuDNN install with Caffe example - JetsonHacks

Thanks