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.

2D FFT and 2D IFFT

i tested 2d FFT and iFFT  with the below code, and the result is right on dsp c64+, with ti simulator.

but when i trans the code to c6678 multi-core dsp, i got a wrong result.

the codes are the same, expect the dsplib.lib, (the lib of  c64+ dsp is dsplib64plus.lib, and the lib for c6678 is dsplib.lib) .

please help me,  thanks,

xiaoyang

  • Welcome to the TI E2E forum. I hope you will find many good answers here and in the TI.com documents and in the TI Wiki Pages (for processor issues). Be sure to search those for helpful information and to browse for the questions others may have asked on similar topics (e2e.ti.com). Please read all the links below my signature.

    We will get back to you on the above query shortly. Thank you for your patience.

    Note: We strongly recommend you to create new e2e thread for your queries instead of following up on an old/closed e2e thread, new threads gets more attention than old threads and can provide link of old threads or information on the new post for clarity and faster response.

  • For C66xx DSP(C6678), you can use the c66x dsplib and the below release supports both COFF and ELF formats (both Little/Big Endian).

    PATH: ~\ti\dsplib_c66x_3_4_0_0\packages\ti\dsplib\lib

    Also, we recommend you to use the EVM for testing and our simulator support is de-focused. The latest version of CCS does not have simulation feature. Thank you.
  • thank you for your answer.
    my FFT test project is running on device debug mode, connecting to a c6678 board. And the dsplib is for C66XX DSP downloaded from TI website. (dsplib_c66x_3_4_0_0_Win32.exe)
    however, the result is not right when i test the 2D-fft-ifft_example on c6678 DSP (device debug), meanwhile when i test the same example on a c64XX DSP with dsplib64plus.lib using software simulator, the result is correct.
    Is there something wrong with dsplib_c66XX?
  • Here is what I suggest

    The library release has a unit test for each function. The unit test has a C model of the function. I suggest that you first try to use the C model of the functions that you use and see if you get the wrong results or the right results.

    In each directory (for example look at .......\dsplib_c66x_3_4_0_0\packages\ti\dsplib\src\DSPF_sp_fftSPxSP\c66 ) you see several functions. Functions with XXX_cn.c are the natural c model of the function. Functions with XXX_d.c are unit test.

    Use the above information to see if the problem is with your setting (or your program) or the optimized version is incorrect. (as much as it is hard to believe)

    Ran