Path: utzoo!attcan!uunet!maverick.ksu.ksu.edu!ux1.cso.uiuc.edu!ux1.cso.uiuc.edu!m.cs.uiuc.edu!gillies
From: gillies@m.cs.uiuc.edu
Newsgroups: comp.arch
Subject: Re: Optimal Computer Architectures
Message-ID: <3300209@m.cs.uiuc.edu>
Date: 9 Nov 90 04:03:00 GMT
References: <212412@<1990Nov8>
Lines: 13
Nf-ID: #R:<1990Nov8:212412:m.cs.uiuc.edu:3300209:000:678
Nf-From: m.cs.uiuc.edu!gillies    Nov  8 22:03:00 1990


> I have a recursive algorithm that I would like to run as fast as
> possible.  I am running a part of it on a SPARCstation SLC.  But at
> this rate, it might finnish in a couple of years!!  I was wondering if
> someone could suggest a couple of architectures that may suit this
> recursive algorithm better than others.  

Oh that's easy.  Any RISC BESIDES the SPARC should probably run much
faster.  In a recent benchmark, I found that, on deeply recursive code
the SPARCstation 1 was 2.8 times faster than 16Mhz 68020/Mac II, but 6
times faster on non-recursive code.  SPARC seems to suck the big wazoo
on deep recursion, presumably because of its register-windowing
design.