home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.transputer
- Path: sparky!uunet!haven.umd.edu!darwin.sura.net!mips!sdd.hp.com!ux1.cso.uiuc.edu!news.cso.uiuc.edu!usenet
- From: heller@lisboa (Helmut Heller)
- Subject: Re: How many Transputers are enough?
- References: <1992Aug13.102814.12544@aiware.in-berlin.de>
- Message-ID: <BsxLLo.KA5@news.cso.uiuc.edu>
- Sender: usenet@news.cso.uiuc.edu (Net Noise owner)
- Reply-To: heller@lisboa.ks.uiuc.edu
- Organization: University of Illinois at Urbana
- Date: Thu, 13 Aug 1992 16:53:47 GMT
- Lines: 33
-
- In article <1992Aug13.102814.12544@aiware.in-berlin.de> scm@aiware.in-berlin.de
- (Harald Schmidt) writes:
- > Hallihallo,
- >
- > does anybody know the max. number of transputers I can connect,
- > and the resulting MIPS/MFLOPS.
- > What is the best price/power-ratio?
- >
- > Thanks for any infomation,
- >
- > Harald
- > --
- There is no maximal number, only your financial funds will limit the size of your
- machine :-).
- The theoretical MIPS/MFLOPS performance increases linear with the number of your
- Transputers, but the actual MIPS/MFLOPS value will be less than that, strongly
- depending on your application.
- Therefore, with 1 Transputer you will get the best price/power-ratio, but this is
- probably not what you want :-)
-
- 64 or 128 T800 make quite a nice machine. If you want to test your application
- first, before you spend DM 100000s, I could offer you a guest login on our
- Transputer guest account tguest. There you could experiment with up to 5 T800 for
- free. Send me e-mail if you are interested.
-
- Viele Gruesse nach Deutschland,
- --
- Servus, Helmut (W9/DH0MAD) ______________NeXT-mail preferred________________
- heller@lisboa.ks.uiuc.edu "Knowledge must be gathered and cannot be given"
- FAX: (217)244-8371 ZEN, one of BLAKES7
- Phone: (217)244-6914 -------------------------------------------------
- Helmut Heller, University of Illinois at Urbana-Champaign, Beckman Institute
- Theoretical Biophysics Group, Room 3143, MC 251
-