Hi, I'm using snpe on sa8295p, I found that AIP runtime is not working, how can I use NPU for inference?
Hi, I'm using snpe on sa8295p, I found that AIP runtime is not working, how can I use NPU for inference?
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.
Hi
Did you intialized with all ADSP library path? If not please do it .
Please check below points for refernce
thank you for your reply, I have intialized with all ADSP library path, DSP runtime is available, error code is as follow:
and for your suggestions 1. how to install AI Processing runtime? 2. No such file or directory in my device
As I reply in another case, SNPE is not used in 8295, from Gen4, we use QNN to replace 8295. Actually, QNN is widely used in Auto IVI(Gen4)/ADAS/Mobile/IOT.
Hi, I am trying to use QNN on 8295 right now, I found that the backend shared libraries provided by QNN include cpu/gpu/htp, I found a picture in the QNN document, I want to know how to run my network in hta hardware, there is no hta shared library in qnn. thank you.
you can ask this issue via case. No hta hardware in SA8295, you can ask your bsp team to check SA8295 hardware design.
You can think HTP is a new hardware which integreate HTA + DSP into one hardware core. This way, no memory gap b/w HTA and DSP. HTP support int8/int16/fp16 with high Tops, I believe it is powerful than SA8155P in all cases .
In all, in 8295, use HTP backend.
Thank you. Now I have a clearer understanding of 8295.
Have a nice day!
Hi, I'm running QNN demo on 8295, cpu and gpu backend is normal, when I switch to htp backend, it's running but output is empty (cpu and gpu do have output)
For SA8295 AI, we have dedicated support team. You can raise case via creatpoint and get support.
you can download the KBA from creatpoint, it has basic debug tips.
KBA-220726022834: How_to_run_model_in_different_HTP_on_SA8540_QNN1.x
Regarding the issue, it is most like load wrong libs. For example, you may load wrong libQnnHtpV68Skel.so into HTP. In all, it is a simple environment issue and can get better support via case system.