Dear Team,
As per my usecase, we have multiple DL model Application to be optimized to run parallely on DSP , GPU and CPU core.
Please let me know, which option is better to go with w.r.t to Application optimization for real time output.
Thanks and Regards,
Vyom Mishra
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.
Dear developer,
You could request multiple SNPE instance for you application models.
BR.
Wei
Dear Weihuan,
Thanks for the reply!
With reference to your reply, I should assume that QNN is not capable of handling multiple Deep Learning models as compared to SNPE.
Please correct me , If I my understanding is wrong.
Could you please suggest APIs in SNPE to run multiple model parallely and also can you please confirm if we run multiple instances of SNPE or QNN of the Deep Learning model simultaneously, the Qualcomm DSP(HTP) will handle the scheduling of the DL models parallely.
Thanks and Regards,
Vyom Mishra