Path: utzoo!dciem!nrcaer!scs!spl1!laidbak!att!pacbell!ames!husc6!ukma!david From: david@ms.uky.edu (David Herron -- One of the vertebrae) Newsgroups: comp.sys.amiga Subject: Re: AT Bridgeboard, '020 Status? Message-ID: <9552@g.ms.uky.edu> Date: 5 Jun 88 02:40:54 GMT Article-I.D.: g.9552 References: <2300009@hpsadla.HP> <4336@killer.UUCP> Reply-To: david@ms.uky.edu (David Herron -- One of the vertebrae) Organization: U of Kentucky, Mathematical Sciences Lines: 31 In article <4336@killer.UUCP> elg@killer.UUCP (Eric Green) writes: >in article <2300009@hpsadla.HP>, jimh@hpsadla.HP (Jim Horn) says: ^^^^^^^^^^ This isn't a valid domain name -- how would I be able to respone to this address if I wanted to? >As for that slower'n molasses bit, the IBM AT people are solving that with >high-powered array processors and other custom hardware that currently isn't >available for the Amiga. The 80286-based machines have no trouble moving 256K >of graphics data in under a second... just so long as they don't have to >actually process it. It'd be quite handy if we could access some of that AT >hardware, since we need to do real-time processing of 16 frames/minute... um, I read recently somewhere (I read too many magazines so I have no idea where I saw this) that Transputer boards were going to be available for Amiga's (I suppose in a Zorro II form) along with the Helios OS. This will match similar availability for IBM PC, Atari ST, Sun, probably Mac II, and so forth. Transputers (especially the T800 with the floating pt chips) have lots of cpu power by themselves and can be easily networked to provide lots more cpu. This is especially important for graphics because graphics algorithms lend themselves so well to parallel processing. Now, if only I could convince myself to be able to spend many thousands of dollars building a small network of transputers :-). -- <---- David Herron -- The E-Mail guy <---- s.k.a.: David le casse\*' {rutgers,uunet}!ukma!david, david@UKMA.BITNET <---- <---- Goodbye RAH.