Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.2 11/03/84 (WLS Mods); site astrovax.UUCP
Path: utzoo!watmath!clyde!burl!ulysses!allegra!princeton!astrovax!wls
From: wls@astrovax.UUCP (William L. Sebok)
Newsgroups: net.lang.f77,net.unix
Subject: Re: Wanted: Ultra-fast fortran compiler for UNIX
Message-ID: <624@astrovax.UUCP>
Date: Mon, 22-Jul-85 10:23:49 EDT
Article-I.D.: astrovax.624
Posted: Mon Jul 22 10:23:49 1985
Date-Received: Wed, 24-Jul-85 23:39:11 EDT
References: <621@astrovax.UUCP> <9871@Glacier.ARPA>
Reply-To: wls@astrovax.UUCP (William L. Sebok)
Organization: Princeton Univ. Astrophysics
Lines: 17
Xref: watmath net.lang.f77:332 net.unix:5106

In article <9871@Glacier.ARPA> conor@Glacier.UUCP (Conor Rafferty) writes:

>Actually there is limited room for improvement.  The 4.2BSD compiler is
>considerably better than the original f77 in that respect.  Published
>work (by Jack Dongarra at Argonne National Laboratory
>[dongarra@anl-mcs]) shows about 25-30% slower runtimes for the 4.2BSD
>compiler over the VMS 4.1 compiler, for dense linear algebra.  I've
>also coded some sparse linear algebra (essentially Yalepack) in
>assembly and found only 30-35% speed up.  Let's give credit where
>credit is due!

Somehow 25%-35% sounds like a fair amount of room for improvement to me.
However that is better than the factor of two that VMS advocates have been
shoving in my face.
-- 
Bill Sebok			Princeton University, Astrophysics
{allegra,akgua,burl,cbosgd,decvax,ihnp4,noao,princeton,vax135}!astrovax!wls