Path: utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!samsung!brutus.cs.uiuc.edu!apple!fox!portal!cup.portal.com!mslater
From: mslater@cup.portal.com (Michael Z Slater)
Newsgroups: comp.arch
Subject: Re: Sun/Sparc FPUs
Message-ID: <25669@cup.portal.com>
Date: 6 Jan 90 18:01:46 GMT
References: <158@csinc.UUCP> <787@stat.fsu.edu>
  <42701@lll-winken.LLNL.GOV> <4411@crdgw1.crd.ge.com> <47516@sgi.sgi.com>
Organization: The Portal System (TM)
Lines: 24

>> There are several different FPU units around. Weitek and TI I believe.
>> I remember something about early SparcStations being shipped with different
>> FPU's.
>> 
>> Not all SparcStations are created equal?
>
>I thought every SparcStation 1 went out with exactly one Weitek WTL 3170 chip.
>LSI Logic was running an ad a few months ago with a photo of the processor
>board which showed it (along with several of their parts).  And I've heard
>it reported that Weitek sold Sun 40,000 of those devices last year.

The Weitek 3170 became available just as the SPARCstation 1 was announced.
Some early SPARCstations had a piggy-back board in the 3170 socket, which
had a TI 8847 FPU and LSI Logic's gate-array FP controller chip.  I don't
know if Sun shipped these to customers, or used them only in-house.  The
two FPUs definitely differ in their pipeline structure and performance.

There will soon be (or maybe already are?) more FPUs that are pin-compatible
with the 3170, but have different performance characteristics.  Compiler
writers need to pick one to optimize for, and presumably it will be
Weitek's 3170, since it's in the SPARCstation 1.

Michael Slater, Microprocessor Report    mslater@cup.portal.com
550 California Ave., Suite 320, Palo Alto, CA 94306 415/494-2677