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.

Compiler/TMS320F280049: CLA compiler doubts

Part Number: TMS320F280049

Tool/software: TI C/C++ Compiler

Hi,

Just one doubt about CLA. As we know, CLA has several restrictions, which are described in the compiler manual. Besides these restrictions, CLA's performance is not as good as C28x, like the execution on data type (int, short), if/else, >>/<<, bit operation and others.

Is there any plan to improve, from compiler side?

Thanks a lot.

Br, Jordan

  • Hi Jordan,

    Limitations like this are restricted by the CLA architecture. Sometimes the compiler can do a better job at compiling more efficient code. But the CLA is a floating point engine. And it is not very efficient working on integers.

    One thing you can do is to make sure your integer math is being performed on 32-bits and not 16-bits.

    Finally, the CLAs performance is not necessarily not as good as the CLA. Often times, the performance on floating point math can be just as good or better than the C28x and FPU.

    Hope this helps,
    sal