Forum Discussion

Altera_Forum's avatar
Altera_Forum
Icon for Honored Contributor rankHonored Contributor
14 years ago

Floating Point with Fixed Point FPGA

Good day.

I know this has been discussed a lot, but each situation seems different.

I want to implement trigonometry functions on a Fixed Point FPGA.

Can you please assist me with some tips as to how to go about this.

I figured a lookup table may work.

Does anybody have any tips or examples.

Kind regards

3 Replies

  • Altera_Forum's avatar
    Altera_Forum
    Icon for Honored Contributor rankHonored Contributor
    14 years ago

    Look up tables are the way to go if you have few input/output bit.

    In case 8 bit input and 8 bit input you get 256 byte of memory that is more than reasonable.

    With 16/16 you get 128Kb of memory, that starts to be difficult in a low cost FPGA.
  • Altera_Forum's avatar
    Altera_Forum
    Icon for Honored Contributor rankHonored Contributor
    14 years ago

    If processing time isn't an issue, CORDIC may be an alternative for high resolution trigonometric functions. Or, even more simple, but slower, power series, the classical method used by numeric co-processors and software float libraries.

  • Altera_Forum's avatar
    Altera_Forum
    Icon for Honored Contributor rankHonored Contributor
    14 years ago

    Thank you very much.

    I have'nt worked wih CORDIC, but quick research shows this to be promising. I will research a bit and try an implementation.

    Your help is appreciated