Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!swrinde!cs.utexas.edu!uunet!bcstec!voodoo!zombie
From: zombie@voodoo.UUCP (Mike York)
Newsgroups: comp.sys.sgi
Subject: Re: SGI GL matrix performance
Message-ID: <1290@voodoo.UUCP>
Date: 28 Apr 91 01:02:20 GMT
References: <15407@helios.TAMU.EDU>
Distribution: usa
Organization: BoGART To You Buddy, Bellevue, WA
Lines: 24

In article <15407@helios.TAMU.EDU> jamie@archone.tamu.edu (James Price) writes:
>Has anyone done any benchmarking of the SGI matrix functions?  I was curious
>and wrote the program included below.  It does a number of 4x4 matrix 
>multiplies, first using software, and then using the geometry pipeline 
>functions (loadmatrix(), multmatrix(), getmatrix()).  
>
>Here are some typical results:
>
>10000 iterations on fritz, with GL version: GL4DGT-3.3
                                                 ^^
                                                 Aha, a GT!

Our application used to run on 4D/60T's.  We had one 4D/70GT.  We found out 
that anything that required the graphics pipeline to regurgitate information
(picking, getmatrix, feedback goodies, etc.), was very slow with the GT 
architecture (picking was up to 6 time slower with our application).  We got
rid of all our 60's and now have a bunch of 4D/25TG's.  I would venture a
guess that if you ran your program on a non-GT machine, you'd see better
results.  
-- 
    Mike York                     |
    Boeing Computer Services      |  Support your local nanobrewer --
    (206) 865-6577                |  No twist-off bottle caps.
    zombie@voodoo.boeing.com      |