Path: utzoo!mnetor!tmsoft!torsqnt!news-server.csri.toronto.edu!clyde.concordia.ca!thunder.mcrcim.mcgill.edu!snorkelwacker.mit.edu!apple!usc!zaphod.mps.ohio-state.edu!van-bc!rsoft!mindlink!a447
From: a447@mindlink.UUCP (Colin Fox)
Newsgroups: comp.sys.amiga.tech
Subject: Re: Speeding up fractals in assembly
Message-ID: <4217@mindlink.UUCP>
Date: 22 Dec 90 09:54:12 GMT
Organization: MIND LINK! - British Columbia, Canada
Lines: 16

I know a bit about MandFXP (been told by one of the authors, Bruce Dawson).
First off, they draw into a separate buffer and then use DrawImage() to blit
the image to the screen. Much faster than using WritePixel(). Next, they spent
WEEKS on tiny loops to squeeze every cycle out of it. This is where they became
68000 experts. :)

And it's also fixed point, not floating point. I don't know if a floating point
processor (at roughly equivalent speeds) can duplicate that of a CPU doing
fixed point.

Also, apparently they do their math to 300 bits. (not decimal places). So it
sounds fairly accurate.

All in all, you've got your hands full with that speed demon. :)

   --- Colin ---