Forums - Crash log when executing Sample app. on DSP

7 posts / 0 new
Last post
Crash log when executing Sample app. on DSP
lunarcake
Join Date: 26 Jul 17
Posts: 10
Posted: Mon, 2017-12-18 00:35

Hi,

I got such crash log when I executed image classification using DSP in sample android app eventhough it worked well.

com.qualcomm.qti.snpe.imageclassifiers: vendor/qcom/proprietary/adsprpc/src/fastrpc_apps_user.c:836::Error 4b: hlist[domain].domainsupport

com.qualcomm.qti.snpe.imageclassifiers: vendor/qcom/proprietary/adsprpc/src/fastrpc_apps_user.c:845::Error 4b: adsp current process handle failed. domain 0

Could you let me know the reason of crash log and it was really fine?

  • Up0
  • Down0
jesliger
Join Date: 6 Aug 13
Posts: 75
Posted: Mon, 2017-12-18 04:23

Thanks for trying out SNPE.  

Could you let us know which device are you running this on?  

  • Up0
  • Down0
lunarcake
Join Date: 26 Jul 17
Posts: 10
Posted: Mon, 2017-12-18 19:54

Hi, jesliger

I run it on Galaxy S8(SM-G9500). Hope it is helpful information.

  • Up0
  • Down0
jesliger
Join Date: 6 Aug 13
Posts: 75
Posted: Tue, 2017-12-19 06:01

We do see errors in the log even when things are working fine.  We'll double check on an S8 as well, when we get a chance.  If it's working, you don't need to worry about the errors.  It might be related to our DSP discovery mechanism trying things.. getting errors.. then trying something else (we do this to discover which target/DSP we are running on.)

 

 

  • Up0
  • Down0
lunarcake
Join Date: 26 Jul 17
Posts: 10
Posted: Wed, 2017-12-20 03:08

Thank you for answer.

I experienced DSP performance was fluctuated according to CPU frequency.

Thus, I wonder there are some possibility of DSP latency due to discovery mechanism error.

 

  • Up0
  • Down0
jesliger
Join Date: 6 Aug 13
Posts: 75
Posted: Wed, 2017-12-20 04:35

We only do discovery during initialization/loading time, we don't do it once SNPE is up and running and executing networks.  

Inference time fluctuations can occur due to CPU performance when using the DSP runtime as the CPU has to quantize the input tensor from float to 8bit fixed point before sending it to the DSP.  We've seen this take anywhere from 8ms to 25ms for a 299x299x3 input size (for inception V3)

There are features in newer releases that help mitigate this quantization overhead.  Which release are you using?

 

  • Up0
  • Down0
lunarcake
Join Date: 26 Jul 17
Posts: 10
Posted: Wed, 2017-12-20 18:23

Thank you, jesliger. Your answer is very helpful to understand phenomenon.

I used SNPE v1.8.0 with quantized resnet-50.

Additionally, I discovered DSP performance increasing when CPU frequency was increase for file write simultaneously.

I could not found a way to increase CPU frequency with DSP performance in SNPE v1.8.0 eventhough I set HIGH_PERFORMANCE as performance profile.

  • Up0
  • Down0
or Register

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.