Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!dali.cs.montana.edu!caen!uwm.edu!cs.utexas.edu!uunet!mcsun!ukc!canon!laukee
From: laukee@canon.co.uk (David Lau-Kee)
Newsgroups: comp.graphics
Subject: Re: Rendering performance
Message-ID: <1991May7.090203.18257@canon.co.uk>
Date: 7 May 91 09:02:03 GMT
References: <1991Apr29.162712.1905@canon.co.uk> <1991May3.190648.13574@ucunix.san.uc.edu> <1991May3.224900.12807@dsd.es.com> <1991May6.114747.12681@canon.co.uk> <1991May6.234927.17724@dsd.es.com>
Reply-To: laukee@canon.co.uk
Organization: Canon Research Europe, Guildford, UK
Lines: 43

rthomson@mesa.dsd.es.com (Rich Thomson) writes:

>In article <1991May6.114747.12681@canon.co.uk>
>	laukee@canon.co.uk writes:
>>The VGX does 1.1 million *GOURAUD* shaded, *PHONG* lighted, Z-buffered,
>>100 pixel, 3-sided polgons (triangle meshes) per second.

>The quotations I've all seen refer to flat shaded polygons and not
>Gouraud shaded polygons with regards to the 1.1 Mp/s.  Here are the
>numbers posted by Kurt Akeley of SGI to comp.benchmarks a while back:

...benchmarks deleted...

>The 1.1 number is for flat shaded triangle meshes and not Gouraud
>shaded triangle meshes (which come in at 770K p/s).  I don't believe
>they are phong lighted, either; I believe a simple lighting model was
>used (the code that generated these numbers was also posted, but I
>omit it here).

>I noticed also that you edited out my question asking for information
>on your claim of 3 Mp/s for the IBM RS6K/730.

I edited it out because it wasn't my claim and it isn't relevent.

Yes I remember seeing the benchmarks, posted after someone 
disputed the numbers in the SGI promotional literature (I believe
SGI were redeemed), shall I bore you by quoting verbatim from that
technical report? Yes, I think I shall:
"Specifically the 4D/380VGX system delivers ... 1,000,000 Z-buffered
3-sided, Gouraud shaded, Phong lighted polygons per second" (Well,
ok then, 1 not 1.1, but the shading is there, as is the lighting and
Z-buffering)

I don't dispute your sources, or your sums.  My point is that these
sorts of numbers are in some circumstances nearly meaningless.  I don't
intend to repeat my argument here, take a look at the rest of
<1991May6.114747.12681@canon.co.uk> if you're interested.

-------------
David Lau-Kee, Canon Research Centre Europe,
17/20 Frederick Sanger Rd, Surrey Research Park, Guildford, Surrey, GU25YD, UK.
laukee@canon.co.uk, laukee@canon.uucp, ..!mcsun!ukc!uos-ee!canon!laukee
Tel: +44 (0) 483 574325 Fax: +44 (0) 483 574360