What are Qualcomm QNN HTP/DSP Delegates?

[Dwayne Duane]

For Snapdragon 888 based devices like Sony Xperia 1 III, and One Plus 9 Pro, the ranking table states that benchmark data were collected using the Qualcomm QNN HTP or DSP delegate. Is this different from the NNAPI delegate or Hexagon delegate? Where can I find documentation for the QNN delegate? How do I enable the QNN delegate in Tensorflow Lite?

Googling "tensorflow lite QNN delegate" yields nothing.


Thank you.

 

[Hachimaki]

I am also interested in the topic. Is the QNN delegate a custom delegate developed around the SNPE SDK?

 

[Andrey Ignatov]

Hi @Dwayne Duane and @Hachimaki,

Is the QNN delegate a custom delegate developed around the SNPE SDK?

QNN is a new delegate developed by Qualcomm, it is targeted at the TFLite Hexagon replacement. There obviously exists some connection between the QNN and SNPE, but we cannot say much more than that now.

Where can I find documentation for the QNN delegate?

Unfortunately, there is still no public information or documentation for it. Nevertheless, we expect that it will become public at some point, but don't know the exact dates.

For now, you can use AI Benchmark's PRO mode to check its performance for custom NN architectures.

 

[Dwayne Duane]

@Andrey Ignatov that is exciting news! Earlier this year, we had to abandon SNPE in favor of TFLite+NNAPI when we found out that having SNPE leverage the Hexagon DSP from an Android App with targetSDK > 28 is an intractable problem due to issues like:

library libqape.qti.so needed or dlopened by libSNPE.so is not accessible

developer.qualcomm.com

DSP Fail (SElinux problem)

developer.qualcomm.com

Android 10, ADSP, and .so permissions failures

developer.qualcomm.com

Hopefully the QNN delegate manages to address these shortcomings of SNPE.