From: nmm1@cus.cam.ac.uk (Nick Maclaren) Newsgroups: comp.parallel Subject: Re: Future of massively parallel machines?.... Date: 12 Nov 1998 05:17:30 GMT Organization: University of Cambridge, England Approved: bigrigg@cs.cmu.edu Message-Id: <72dr1a$fue$1@encore.ece.cmu.edu> Originator: bigrigg@ece.cmu.edu In article <712l6o$h5d$1@encore.ece.cmu.edu>, hsh2@cov.ac.uk wrote: > >Just wondering what is the future for massively parallel machines (ie. >machines with over 1000 individual processors, such as CMs). > >Surely there will be a point when the chips cannot get any smaller, and >interprocessor communication cannot get any faster (speed of light?), so the >only way for these machines to get 'faster/ more performance' is to grow in >physical size (more processors/ increased parallelism?) Perhaps, but we are a very long way off that. Even at current rates, it is unlikely to happen before 2050. >Have you any ideas?, wacky or not I would like to hear. I've heard of >hypercubes... how about spheres?... if the Internet (comms) was fast enough >would it be possible to use connected computers to form a very massive parallel >machine?? Is parallelism the way home PCs are or will be heading? They already have been. The factorisation exercises are one such use. Massively parallel systems are not showing much signs of breaking into the low end, but it is likely that home computers will have small-scale (say 4- to 8-way) shared memory parellelism within a few years. >... oh and would anyone like to guess when a biologist will be working >with a computer scientist to create a bio-chip? They already are. Don't hold your breath. Regards, Nick Maclaren, University of Cambridge Computing Service, New Museums Site, Pembroke Street, Cambridge CB2 3QG, England. Email: nmm1@cam.ac.uk Tel.: +44 1223 334761 Fax: +44 1223 334679 -- Articles to bigrigg+parallel@cs.cmu.edu (Admin: bigrigg@cs.cmu.edu) Archive: http://www.hensa.ac.uk/parallel/internet/usenet/comp.parallel