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.

TMS320C6678: how does FFTLIB support multi-core processing?

Part Number: TMS320C6678
Other Parts Discussed in Thread: FFTLIB

Hi All,

I have just started testing fftlib on a TMDSEVM6678LE. it the intro page http://www.ti.com/tool/FFTLIB it says it supports multi-core processing. I am curious to know how it takes care of that because I checked the code and I don't see any OpenMP pragma sth like that.

Please let me know it multi-core processing is realized by fftlib.

Any clue and comment is much appreciate it.

  • Mike,

    Please check for #pragma omp parallel usage in the code example for fft_omp_*_* and ifft_omp_*_* functions in the library. Those pragmas are inserted for parallel processing,

    As we have indicated few times earlier to your E2E posts, we are not currently supporting this library as it is not being actively maintained and we don`t have access to the developers. If this library is important for your project then we recommend that you refer to existing documentation and source "as is". 

    Regards,

    Rahul

  • Hi Rahul,

    Thank you for the valuable input you provided. My requirement is to be able to calculate fast FFT (and inverse fft) for complex input signals (sequence of numbers representing a signal). 

    Please let me if DSPLIB full fills such requirements and if so how it facilitates the calculation speed and if there is any timing and accuracy performance benchmark published regarding fft calcuations.

    Many thanks,

    Mike