Hi.
I'm trying to run my neural network with different runtimes on SD870, but I found that the performance for gpu is faster than AIP runtime (76709us vs 186290us). I have quantized my network and enable_hta.I think the benchmark result is not correct, but I don't know why(No errors were reported when I run benchmark).
What can i do with this?
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.
