From: lindahl@pbm.com (Greg Lindahl) Newsgroups: comp.parallel Subject: Re: What Ever Became of the "Transputer" ??? Date: 9 May 1999 04:48:13 GMT Organization: a guest of Shadow Island Games Approved: bigrigg@cs.cmu.edu Message-Id: <7h342d$j4a$1@goldenapple.srv.cs.cmu.edu> Originator: bigrigg@ux6.sp.cs.cmu.edu Xref: ukc comp.parallel:15575 Milind Bhandarkar writes: > > >several ultra-highspeed "serial" links through which > > >data could be exchanged between processors. If anything, > > "ultra-high" is your term. > It was hardly "ultra-high". There were 4 links that could communicate > at 10 Mbps bidirectional b/w. The only advantage was that they were > within the processor, so it saved some space for additional > communication hardware. Um, at the time, that was pretty good bandwdith, especially given that it was both cheap (4 included with the cpu), fairly low latency, and (most importantly) low overhead. It just goes to show that slow serial speed can kill any architecture. However, the Alpha 21364 is supposed to get transputer-like serial links on the CPU. It's the marriage of a conventional core with the transputer idea... -- g -- Articles to bigrigg+parallel@cs.cmu.edu (Admin: bigrigg@cs.cmu.edu) Archive: http://www.hensa.ac.uk/parallel/internet/usenet/comp.parallel