Forums - How PerformanceProfile impacts SNPE Performance on 820 Platform

1 post / 0 new
How PerformanceProfile impacts SNPE Performance on 820 Platform
tao.yao
Join Date: 25 Jun 17
Posts: 5
Posted: Fri, 2017-08-11 02:57

Hi, I experimented SNPE SDK 1.2.2.0 on a S820 platform where Linux AGL is running.

The network model I used is inception_v3.

I tried two PerformanceProfile options while building the network with GPU Runtime.

The time cost is listed below.

the left column is for HIGH_PERFORMANCE, while the right is for POWER_SAVE mode.

From the data, there seems no noticable performance improvement while PerformanceProfile=HIGH_PERFORMANCE.

In general, how much perf improvement can be achieved for HIGH_PERFORMANCE mode?

Thanks.

Snpe library build network model GPU RunTime 

HIGH_PERFORMANCE 

POWER_SAVE 

 

 

368.393 ms 
371.305 ms 
367.644 ms 
369.606 ms 
368.653 ms 

 

363.47 ms 
369.301 ms 
369.353 ms 
368.327 ms 
368.223 ms 

 

  • Up0
  • Down0

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.