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.

CCS code execution speed is slower than standalone mode

Hello,

 

We have a project built for DM648.Now we are evaluating the code execution time.

 

We found that the program on DM648 runs slower when connected to CCS 3.3 through 

JTAG emulator(XDS560 USB). 

It is around 30 milisec slow when compared to standalone mode (i.e. when JTAG is not connected).

 

I have contacted Blackhawk about XDS560 speed and I was told the

delay may be cuased by CCS 3.3 itself.

 

We are just loading and running the program from CCS(through Run button) 

and not using breakpoints or any other Real time debug etc on CCS.

Also tried "Debug->Run Free" and Release (Non-Debug) mode and there was no change. 

note:CGT version 6.1.12

 

In an another post I read about hardware initialization through CCS may consume time but in our case 

.tcf files are used for target configuration and I dont think that could cause the delay.

We are calculating the time throug a source code(inbuilt in the project) which outputs the 

clock cycles used by the CPU.

 

We appreciate any inputs on this issue.

 

Regards.

  • Hello,

    mudigere said:
    Also tried "Debug->Run Free" and Release (Non-Debug) mode and there was no change. 

    Run Free should effectively disconnects CCS from the target. When you did this, did you remove the JTAG cable from the target and still noticed no change?

    mudigere said:
    In an another post I read about hardware initialization through CCS may consume time but in our case 

    Are you using any startup GEL file with CCS?

    mudigere said:

    We are calculating the time throug a source code(inbuilt in the project) which outputs the 

    clock cycles used by the CPU.

    How do you output the data? CIO?

    Thanks

    ki