• Locked Locked
  • Replies 5 replies
  • Subscribers 119 subscribers
  • Views 3693 views
  • Users 0 members are here
2025 survey

We are running a survey to help us improve the experience for all of our members. If you see the survey appear, please take the time to tell us about your experience if you can.

Options
Related
How was your experience today?
This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Unable to count event in Cortex R4 using PMC

sandesh mukartihal
Note: This was originally posted on 22nd July 2011 at http://forums.arm.com

Hi,

I am trying to set the event counter register to count particular event using ARM Cortex R4's performance monitor register.

I followed the steps as in this link..
http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4237.html

But it is not counting the events which I set. Only the cycle count is working. I am using RVDS 4.1 prof.

Does RVDS support event counting or is there any configuration error that needs to be corrected?
Parents
  • Note: This was originally posted on 28th July 2011 at http://forums.arm.com

    Thank you very much.

    I actually want to measure the branch prediction related events accurately for my code and I don't want any background application/process to be running when I run my code. So thereby I'll be getting accurate branch related counter info. Is it possible to use beagle board in this configuration and debug target using RVDS?

    I have a panda board with dual cortex A9 in it, but it has to be loaded with boot loader and linux OS. Doing so I cant measure PMC's accurately for my program if I run it on OS. Am I right regarding this or is there a way to go about it? Considering this, and the fact that ARM workbench supports beagle board target I am thinking of switching to beagle board.

    Any suggestions will be of great help to me. Thank you for your time.

    If you use real hardware (a board), then yes you will have the PMU present.  Remember that by default the PMU is only accessible in privileged modes.  User mode access must be manually set if you required.
Reply
  • Note: This was originally posted on 28th July 2011 at http://forums.arm.com

    Thank you very much.

    I actually want to measure the branch prediction related events accurately for my code and I don't want any background application/process to be running when I run my code. So thereby I'll be getting accurate branch related counter info. Is it possible to use beagle board in this configuration and debug target using RVDS?

    I have a panda board with dual cortex A9 in it, but it has to be loaded with boot loader and linux OS. Doing so I cant measure PMC's accurately for my program if I run it on OS. Am I right regarding this or is there a way to go about it? Considering this, and the fact that ARM workbench supports beagle board target I am thinking of switching to beagle board.

    Any suggestions will be of great help to me. Thank you for your time.

    If you use real hardware (a board), then yes you will have the PMU present.  Remember that by default the PMU is only accessible in privileged modes.  User mode access must be manually set if you required.
Children
No data