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.

TMS570LS3137: About the problem of moving programs into RAM to run

Part Number: TMS570LS3137

Hello

Team

 when I write DSP2812 programs, I see that other people's code is to moved the program into RAM to run. Some people say that it runs fast, but I dont  tested it and don't understand its original. Is it the same with tms570 series chips? Is it really slow to run in flash? Aren't they all standard clock cycles?

  thank you

  • Hi Whong,

    The TMS570L3137 internal TCM Flash can support zero address and data wait states up to a CPU speed of 50 MHz in nonpipelined mode. The flash supports a maximum CPU clock speed of 160 MHz in pipelined mode for the PGE Package and 180 MHz for the ZWT package, with one address wait state and three data wait states.

    The TMS570LS3137 internal TCM RAM can support program and data fetches at full CPU speed without any address or data wait states required.

    It is true that running code from SRAM is faster than running from flash.

  • Hi wang

    Is our structure much better than 28335, much faster, there is no need to run the program in ram?

  • Is our structure much better than 28335, much faster,

    I don't have the comparison between TMS570 and F28335. I think execution from flash is good enough.