Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!watmath!clyde!rutgers!sri-spam!ames!pioneer!lamaster
From: lamaster@pioneer.UUCP
Newsgroups: comp.arch
Subject: Weitek 8000/8032/8064
Message-ID: <256@ames.UUCP>
Date: Fri, 30-Jan-87 19:08:01 EST
Article-I.D.: ames.256
Posted: Fri Jan 30 19:08:01 1987
Date-Received: Sat, 31-Jan-87 08:38:05 EST
Sender: usenet@ames.UUCP
Reply-To: lamaster@ames.UUCP (Hugh LaMaster)
Organization: NASA Ames Research Center, Moffett Field, Calif.
Lines: 29
Keywords: floating point, microprocessor, vector instructions
Summary: Fast microprocessor floating point


I call to your attention that Weitek has announced a new chip 
set which includes several versions of a basic microprocessor,
and two floating point units.  The processors are described in the
Feb. 87 UNIX World magazine in the Inside Edge column.  Time
will tell, but a 5 MIPS basic processor, with a 64 bit bus
option, and 2 MFLOPS scalar floating point performance on the
LINPACK benchmark (full precision) (with the 8064), tell me that
Weitek deserves a very careful look.  

The floating point processors (IEEE compatible) also have vector
instructions which run at 12.5MFLOPS.  Very nice.  In fact, very
much what a lot of people around here need.

The article summary says:

"Weitek is going to make it ridiculously easy and inexpensive to
build desktop and midrange machines with high speed arithmetic
and vector capabilities."

I hope so.

  Hugh LaMaster, m/s 233-9,  UUCP {seismo,topaz,lll-crg}!ames!pioneer!lamaster 
  NASA Ames Research Center  ARPA lamaster@ames-pioneer.arpa
  Moffett Field, CA 94035    ARPA lamaster@pioneer.arc.nasa.gov
  Phone:  (415)694-6117      ARPA lamaster@ames.arc.nasa.gov

("Any opinions expressed herein are solely the responsibility of the
author and do not represent the opinions of NASA or the U.S. Government")