Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!caen!math.lsa.umich.edu!sharkey!msuinfo!news
From: chouw@galaxy.cps.msu.edu (Wen Hwa Chou)
Newsgroups: comp.sys.next
Subject: Re: NeXTStation Benchmark
Message-ID: <1990Nov19.235421.23596@msuinfo.cl.msu.edu>
Date: 19 Nov 90 23:54:21 GMT
References: <743@kaos.MATH.UCLA.EDU> <1990Nov16.192938.17923@Neon.Stanford.EDU> <obFjTbS00Vp50k61pn@andrew.cmu.edu>
Sender: news@msuinfo.cl.msu.edu
Reply-To: chouw@galaxy.cps.msu.edu (Wen Hwa Chou)
Distribution: na
Organization: Dept. of Computer Science, Michigan State University
Lines: 14

In article <obFjTbS00Vp50k61pn@andrew.cmu.edu> ea08+@andrew.cmu.edu (Eric A. Anderson) writes:
>Float Version :
>cvt float to double
>mult double
>cvt double to float.
>
>And in the Double version just
>mult double.
>
>It doesn't seem to make sense that the float version would be faster. 
>

The multiplication of double precision is not of constant time.  It
changes, based on the data you throwed in.