In article <40686cfe$1@news.povray.org> , "Chambers" 
<bdc### [at] yahoocom> wrote:

> Well, it's been a few years, but I used to do quite a bit of graphics
> programming in assembly.  Did you know that, for instance, the FPU registers
> load so fast that games used them to load bitmaps from regular memory to
> video memory?  It worked about 30% faster than a standard transfer.  In
> fact, this was the reason MMX used the FPU registers, and so you can't use
> FPU and MMX at the same time.

That is nonsense.  They are faster for copies because you execute fewer
instructions per copy and on a 64 bit bus (since the Pentium, and even with
burst transfers on a 486 bus) the maximum bandwidth is used.  Further, MMX
used FPU registers simply as a kludge so operating systems and many ancient
programs would not have to be modified to save additional data when
switching contexts.  This is why certain versions of Windows needed patching
later on when SSE with its additional registers was added.

    Thorsten

____________________________________________________
Thorsten Froehlich, Duisburg, Germany
e-mail: tho### [at] trfde

Visit POV-Ray on the web: http://mac.povray.org

Post a reply to this message