home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.benchmarks:1674 comp.arch:10666
- Path: sparky!uunet!ogicse!das-news.harvard.edu!cantaloupe.srv.cs.cmu.edu!lindsay
- From: lindsay+@cs.cmu.edu (Donald Lindsay)
- Newsgroups: comp.benchmarks,comp.arch
- Subject: Re: DEC ALPHA Performance Claims
- Message-ID: <BxM9nn.156.2@cs.cmu.edu>
- Date: 12 Nov 92 18:50:10 GMT
- Article-I.D.: cs.BxM9nn.156.2
- References: <1992Nov10.150330.26923@ryn.mro4.dec.com> <BxInrJ.Lr@metaflow.com> <1992Nov12.134927.13843@linus.mitre.org>
- Sender: news@cs.cmu.edu (Usenet News System)
- Organization: School of Computer Science, Carnegie Mellon
- Lines: 23
- Nntp-Posting-Host: gandalf.cs.cmu.edu
-
-
- bs@gauss.mitre.org (Robert D. Silverman) writes:
- >Why is having a *micro*-processor so important? What really matters
- >is price/performance, although for really large problems (e.g. Cray
- >YMP-C90 needed) price isn't so important.
-
- It's important to me because that allows me to put a derated version
- of the $300,000 product on my very own desk. The problems I work
- on are smaller than yours, I know, but that doesn't mean that my
- current workstation is as fast as I'd like.
-
- It's important to many others because they can consider designing the
- latest *micro*-processor into a wide variety of products, including
- high-volume products. Even if the chip is the absolutely latest
- wonder-widget, its cost may be a mere fraction of a proposed system
- list cost.
-
- Crays are wonderful, but when I look at the low-level hardware
- details of a new Cray, it is unclear to me how this technology can be
- migrated in these ways. Hence my enthusiasm for the progress of the
- chip biz.
- --
- Don D.C.Lindsay Carnegie Mellon Computer Science
-