• State
  • Locked Locked
  • Replies 2 replies
  • Subscribers 98 subscribers
  • Views 1612 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

Loop buffer exception and Missed Stall

Guillermo Fernandez
Intellectual 385 points

Hi experts,

We are using a DM648 DSP. We obtain the following exception after running 3hours:

EXC_exceptionHandler : EFR = 0x2

            NRP=0xe30e686c
            mode=supervisor

Internal exception: IERR=0x180

           Loop buffer exception
           Missed stall

System abort called with message 'Run-time exception detected, aborting..."

 We are sure that nobody is writing at external program memory at this moment, because we have saved the content of external program memory and we have compared it before and after the exception.

Could you explain what does it mean?

Thanks in advance.

Best regards.

 

 

  • 0
    TI__Guru**** 171094 points

    Guillermo,

    As you probably know, this is a hardware exception from the controller and the message is spawned by DSP/BIOS EXC controller.

    This exception is generated from a SPLOOP or SPKERNEL and happens when a loop skips a required stall during its execution (check chapter 6 of SPRU732). Therefore it is not an invalid memory access.

    The reasons for this error are listed in section 7.15.2 of the book referred previously and are usually caused by a hardware misstep of some sort, but the exact reason is very difficult to predict, especially after 3+ hours of continuous execution in the target board.

    I would then try to create a very reproducible scenario and take note of anything unusual during the execution, especially regarding power fluctuations - if any peripherals or other systems on the board are powered on or off around the same time the exception occurs or if there is any spike in temperature or a sudden increase in system activity.

    Unfortunately it is very difficult to do a precise assessment of the root cause for this error, but I will forward this thread to the device forum so they may have additional ideas about it, ok?

    Hope this helps,

    Rafael

  • 0 in reply to desouza
    Intellectual 385 points

    Thank you for your fast reply Rafael. I would appreciate any kind of help in this issue, please send this question to your colleagues. I understand the main reason of these kind of problems is a hardware misstep. We are going to try to detect any power fluctuation.

    Thank you very much.

    Best Regards.