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