Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!usc!zaphod.mps.ohio-state.edu!math.lsa.umich.edu!emv
From: emv@math.lsa.umich.edu (Edward Vielmetti)
Newsgroups: comp.windows.x
Subject: Re: DECstation 3100 vs. SPARCstation 1
Message-ID: <EMV.90Jan6163836@stag.math.lsa.umich.edu>
Date: 6 Jan 90 21:38:36 GMT
References: <55888@csvax1.cs.tcd.ie> <9001061951.AA09883@expo.lcs.mit.edu>
Sender: news@math.lsa.umich.edu
Organization: University of Michigan Math Dept., Ann Arbor MI.
Lines: 25
In-reply-to: rws@EXPO.LCS.MIT.EDU's message of 6 Jan 90 19:51:09 GMT

In article <9001061951.AA09883@expo.lcs.mit.edu> rws@EXPO.LCS.MIT.EDU (Bob Scheifler) writes:

   Here are x11perf version 1.2 numbers for the MIT R4 server on a
   DECstation 3100 and a SPARCstation 1.  The DECstation has 16Mb of
   memory, and is running Ultrix 3.1.  The SPARCstation has 16Mb of
   memory, a CG3 framebuffer, and is running SunOS 4.0.3.  The server
   was compiled with the standard compiler on both systems.  As usual,
   your mileage will certainly vary, depending on which server (MIT's or
   the product ones), configuration, and applications you actually use.

   The numbers in parentheses are the ratio of column 2 to column 1.

   1: MIT R4 on SPARCstation 1 with CG3
   2: MIT R4 on DECstation 3100

"Standard compiler" could be ambiguous here, since R4 recommends
to use GCC for Vax and 68020.  In the future I'd find it useful to
be a bit more explicit with which compiler is used (since that seems
to be as important as anything else in determining performance).

That said, these comparisons are great!  Is there anyone collecting
them for the purpose of a periodic comparison ala xfroot ?  I
realize that there are a lot more numbers to this one.

--Ed