Re: Computational power AVR vs. MSP430?

From: Casey (cclremovethispart_at_cox.net)
Date: 12/24/03 

Date: Wed, 24 Dec 2003 11:23:04 -0600

John R. Strohm said...
> "Thomas W. Carley" <tcarley@eng.umd.edu> wrote in message
> >
> > Think fixed point math rather than floating point. It is MUCH more
> > efficient.
>
> It isn't that simple. Doing fixed point math, you have to worry a lot more
> about scale factors and where your binary point is at any given instant. You
> MAY have to worry about which way an operation will truncate.

True... but we get paid to worry about such things.

Casey

Relevant Pages

  • Re: A new math usenet group
    ... But I think you have no worry here. ... large percentage of nonsense, troll postings, and spam. ... Most of my enjoyment of sci.math is learning about math ... but it's real sin is that it's just dull and boring. ...
    (sci.math)
  • Re: Computational power AVR vs. MSP430?
    ... "Thomas W. Carley" wrote in message ... > Think fixed point math rather than floating point. ... MAY have to worry about which way an operation will truncate. ...
    (comp.arch.embedded)
  • Re: Computational power AVR vs. MSP430?
    ... > John R. Strohm said... ... Doing fixed point math, you have to worry a lot more ... >> MAY have to worry about which way an operation will truncate. ...
    (comp.arch.embedded)
  • Re: This must be "New" Math
    ... Major Misunderstanding wrote: ... We would never say New Math. ... Don't worry yourself in the least...our expectations ...
    (soc.culture.scottish)
  • Re: Which free software could acquire 48 bits color depth pictures from a scanner ?
    ... floating point math on it and expect to keep the level of precision ... You're stuck on the data representation and completely ignoring ... only machine and compare the result to make sure it's doing the same ...
    (rec.photo.digital)