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.

TMS320F28335: TMS320F28335 fixed vs floating

Part Number: TMS320F28335

Hello All,

I have to solve a fairly complex model of a system online for my control application( MPC).  The model is taking too much time to compute 4.2 us. I have optimized the additions, multiplications etc as much as possible to reduce it ,but I am able to reduce it to only 3.8us. I need further reduction about 2.2us etc. Can coding in fixed point reduce it further or is the processor optimized already for floating point operations and both will take same time? Is there any other method to reduce the timing given same no of math operations?

Regards

  • Hi Debanjan,

    This controller already has FPU enabled. You can check Project -> Properties and relevant section if "-fpu" is selected or not. You can also try using IQMath library but I won't be able to give you the direct benefit in clock cycles or time.

    Regards,
    Gautam