Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!cs.utexas.edu!samsung!brutus.cs.uiuc.edu!rpi!crdgw1!sungod!davidsen
From: davidsen@sungod.crd.ge.com (William Davidsen)
Newsgroups: comp.sys.ibm.pc
Subject: Re: FasMath Math Coprocessor ?
Message-ID: <4088@crdgw1.crd.ge.com>
Date: 4 Dec 89 15:08:27 GMT
References: <8911290805.AA05793@euler.Berkeley.EDU> <3061@cbnewsl.ATT.COM>
Sender: news@crdgw1.crd.ge.com
Reply-To: davidsen@crdos1.UUCP (bill davidsen)
Organization: General Electric Corp. R&D, Schenectady, NY
Lines: 12


  The speed increase over the 387 is not across the board, for Cyrix or
ITT. The chip which may be useful is ITT's replacement for the 287. Most
of the 386s made in 86 and 87 have only a 287 socket (Intel didn't even
have the sockey specs available). This includes all the early AMI and
Compaq systems (like mine). Replacing the 10MHz 287 with a 20MHz ITT
version would give a big kick just from clock speed. I have not seen a
benchmark on the ITT chip, but I suspect that the improvement is mostly
in transcendental functions.
	bill davidsen		(davidsen@crdos1.crd.GE.COM)
  {uunet | philabs}!crdgw1!crdos1!davidsen
"Stupidity, like virtue, is its own reward" -me