Forums - Optimized Ops/kernel and intra/inter layer multithreading

1 post / 0 new
or Register
Optimized Ops/kernel and intra/inter layer multithreading
kumaramar1031
Join Date: 20 Mar 18
Posts: 2
Posted: Mon, 2019-01-14 01:27
Top

Hi,

I benchmarked mobilenet network using Qualcomm SNPE , ARM-NN , and TF-Lite . Results of Arm-NN and TF-lite is comparable but SNPE results are so bad (approx 7x more than Arm-NN/TF-Lite in terms of Latency).

So, I have some questions:

1. Is SNPE supports inter/intra layer multithreading.

2. If yes then Is't tunable and  how to enable it ?

3. Is SNPE supports Optimized Ops/kernels (Neon) for operator implementations.

4. One document shared by Qualcomm , says that using SNPE, we can able to achieve 27x  gain , so on what metrices , they are comparing. (https://www.qualcomm.com/media/documents/files/achieving-ai-at-scale-pre...)

 

Thanks and Regards

Amar kumar

 

  • 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.