home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!cs.utexas.edu!qt.cs.utexas.edu!yale.edu!nigel.msen.com!paulh
- From: paulh@msen.com (Paul Haas)
- Newsgroups: comp.arch
- Subject: Re: uniprocessor design ceiling
- Date: 29 Dec 1992 00:00:50 GMT
- Organization: Msen, Inc. -- Ann Arbor, Michigan
- Lines: 25
- Message-ID: <1ho4g1INNgac@nigel.msen.com>
- References: <2340@sousa.tay.dec.com>
- NNTP-Posting-Host: garnet.msen.com
- X-Newsreader: TIN [version 1.1 PL8]
-
- Bob Supnik (supnik@human.enet.dec.com) wrote:
-
- : The ingenuity of processor designers (and semiconductor technologists) being
- : far from exhausted, I believe this performance growth can continue for the
- : rest of this decade. There are some limiting factors:
-
- : - Process technology evolution appears to be slowing somewhat, due to
- : lengthening development time (and cost) for new generations of semiconductor
- : processing equipment.
-
- Is this a long term trend?
-
- : - Increases in performance have been accompanied by increases in power
- : consumption, in opposition to rising requirements for 'green' technology.
-
- Are you talking about the CPU chip or the whole system? The top of the line
- CPU chips are using more power, but the system requirements are going down
- dramatically. During the same period that the microprocessor went from a
- few hundred milliwatts to 30 watts, disk drives went from a few hundred watts
- to a few watts. There are usually more disks in a system than CPUs. Likewise
- almost everything else in the system uses less power.
-
- --
- Paul Haas, work: paulh@ox.com, (313) 930-1888. home: paulh@hamjudo.mi.org
-
-