Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!water!watnot!watmath!clyde!rutgers!ames!ucbcad!ucbvax!decvax!decwrl!labrea!navajo!billw
From: billw@navajo.UUCP
Newsgroups: comp.lang.lisp
Subject: Re: LISP floating point performance
Message-ID: <1432@navajo.STANFORD.EDU>
Date: Tue, 3-Mar-87 15:25:31 EST
Article-I.D.: navajo.1432
Posted: Tue Mar  3 15:25:31 1987
Date-Received: Fri, 6-Mar-87 03:57:13 EST
References: <16921@glacier.STANFORD.EDU> <441@spar.SPAR.SLB.COM>
Organization: Stanford University
Lines: 9
Summary: C code <> Native...


I'd be VERY careful about considering the speed of an FFT coded
in C as equivilent to the "native" speed of the machine - after
all, C isn't a numeric language either.  I'd feel a lot better
if the "native" times came from an optimizing fortran compiler
like VMS fortran, and better still if they were from carefully
hand coded assembler...

BillW, dinosaur keeper.