Hello,
I would like to know how to transfer data between cores (CPU, GPU, DSP (HVX), HTA, etc.) to configure a deep learning inference pipeline in the form of data load -> pre-processing -> SNPE inference -> post-processing.
I would also like to know how to divide processes by core.
If Qualcomm provides an API for this, please let me know the name of the API or related documentation.
Thnaks.
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,
There is tow way for transfering data from one backend to another.
1 General DDR
2 ION buffer also known as cDSP buffer.