Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!think.com!spool.mu.edu!uunet!microsoft!gideony
From: gideony@microsoft.UUCP (Gideon YUVAL)
Newsgroups: comp.arch
Subject: Re: new instructions
Keywords: fixed, fractional
Message-ID: <72561@microsoft.UUCP>
Date: 26 May 91 20:02:55 GMT
Article-I.D.: microsof.72561
References: <9105200213.AA05095@ucbvax.Berkeley.EDU> <1991May20.121708.5023@dartvax.dartmouth.edu> <49278@ut-emx.uucp>
Reply-To: gideony@microsoft.UUCP (Gideon Yuval)
Organization: Microsoft Corp., Redmond WA
Lines: 12

In article <49278@ut-emx.uucp> nather@ut-emx.uucp (Ed Nather) writes:
>For people who use computers for real-time data acquisition and control,
>and there are a lot of them, floating point operations are very seldom
>used, if at all.  ...

Obvious question: is FP avoided because it is the wrong thing, or is it
avoided due to its cost (a 387 is a few hundred $) and slowness
(memory-to-memory floating-add can be 100 cycles)?

If anyone has data on this, I would be grateful
-- 
Gideon Yuval, gideony@microsof.UUCP, 206-882-8080 (fax:206-883-8101;TWX:160520)