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.

TM4C129XNCZAD: SRAM App

Part Number: TM4C129XNCZAD


1. Does the TivaWare DK incudes a small IAR EWARM sample application that is copy and run from SRAM instead of FLASH?

2. What will be the reduction in running performance as fetch data and code are done on same BUS?

Thanks

  • Amir Yungman1 said:
    1. Does the TivaWare DK incudes a small IAR EWARM sample application that is copy and run from SRAM instead of FLASH?

    Don't know - but I would not see the point. Just place "__ramfunc" at the declaration of the function you want to run from RAM, and the toolchain takes care of the rest.

    Amir Yungman1 said:
    2. What will be the reduction in running performance as fetch data and code are done on same BUS?

    I never measured this on a TM4C, and performance is not the usual use case. Rather, execution from RAM is mostly used when the Flash is inaccessible (erase/program).

    I would not expect a significant reduction. Usage of DMA are much more of a problem - especially because of their asynchronous nature.

    BTW, I know examples of RAM code placement for performance reasons, but for other MCUs (different vendors). But they tend to rely on RAM on different buses for that purpose (inaccessible for DMA).

  • Hello Amir

    When running code from SRAM, the performance number are lower than execution from Flash. The reduction depends on what system frequency the application is planned to be executed at.