alu design

Discussion in 'The Projects Forum' started by neenu, Sep 27, 2010.

  1. neenu

    Thread Starter New Member

    Aug 11, 2010
    6
    0
    hi.. i want to design a 32 bit floating point addition subtraction multiplication and division unit. kindly help me..
     
  2. Papabravo

    Expert

    Feb 24, 2006
    10,136
    1,786
    What do you know about ALU design so far. A floating point unit is all well and fine, but do you know how to do a fixed point ALU? It is a really excellent place to start. This is based on the idea that you have to learn to crawl and walk before you try to run a marathon.
     
  3. neenu

    Thread Starter New Member

    Aug 11, 2010
    6
    0
    hi.. thanks for your reply.. i didnt do fixed point operations yet.. is it possible to do floating point operations without doing fixed point operations.. and i need to design this using vhdl.
     
  4. Papabravo

    Expert

    Feb 24, 2006
    10,136
    1,786
    I suppose it is possible, but surely inadvisable. If you don't know anything about how fixed point arithmetic works, it seems unlikely that you could get your head around floating point operations with any expectation of getting it right and being able to debug your design if things go wrong.

    You're a smart guy so if you've got the stones, go for it.
     
  5. tom66

    Senior Member

    May 9, 2009
    2,613
    213
    Have a look at how software floating point math works. I recommend you have a look at the code for PIC micros which implement IEEE-794 32-bit addition, subtraction, multiplication, division etc. It may be possible to convert it to VHDL. You did not specify whether you were doing IEEE-794 32-bit, 64-bit or any other format.
     
  6. Papabravo

    Expert

    Feb 24, 2006
    10,136
    1,786
    Without knowing anything about fixed point arithmetic he's going to understand the PIC library without any difficulty whatsoever. Sure, and pigs may grow wings and fly.
     
Loading...