bcorrie@uvicctr.UVic.ca.UUCP (Brian Corrie) (10/13/89)
Howdy folks....
Its survey time again, and I would appreciate your participation
in this version of twenty questions.
I am interested in parallel algorithms for ray tracing, and I am
curious about a couple of things. Please note that I have most of
the ``standard references'' that get cited in the literature, but
I am interested in some of the OTHER stuff that is out there.
The papers that I have:
Cleary et al. ``Multiprocessor Ray Tracing'', Internal Report,
83/128/17, Department of Computer Science, University of Calgary,
Calgary, Alberta, Canada.
Dippe et al ``An Adaptive Subdivision Algorithm and Parallel
Architecture for Realistic Image Synthesis'', Computer Graphics,
Volume 18, Number 3.
Gaudet et al ``Multiprocessor Experiments for High Speed Ray Tracing'',
ACM TOG, Volume 7, Number 3.
etc.....
What I am interested in are references to some of the goodies that are
out there in the real world. Are there any papers on the hardware Pixar
uses. How about the AT&T pixel machine, the Connection Machine (there is
a piece on it in Scientific American, Volume 256, Number 6 that I
already have), and other bizarre architectures. Dave Jevans from the
University of Calgary (Hi Dave, remember me? I met you at SIGGRAPH this
year) mentioned at one point he implemented some stuff on a BBN
Butterfly (I think). Any more info on that Dave? Did you write it up?
Anybody else doing anything similar?
Here is the info I want....
1) What architecture do you run on?
2) Parallel, vectorized etc?
For parallel systems:
3) How many processors do you use?
4) How tightly coupled are they?
5) Do you perform any load balancing, and if so how?
6) Architectural requirements (memory/node, communications etc)?
7) Anything else you can think of that might be useful.
Thanks in advance for any help you can give me. Replies by email
are of course the best route to take, but I read comp.graphics
every morning, so a reply here will be seen. I will
post a summary to the net if I get enough information.
For those of you in the RT News mailing list and don't read
the net like I do, I will send a copy of both this and the summary
to Eric.
Thanks,
Brian
--
...!uw-beaver!uvicctr!bcorrie bcorrie@uvicctr.UVic.ca
Under the most rigourously controlled conditions of pressure,
temperature, volume, humidity and other variables, the organism
will do as it damn well pleases.
Sounds like some of the code I have written!!!!! 8^)turk@Apple.COM (Ken "Turk" Turkowski) (10/17/89)
Joe Cychosz addresses vectorized ray-tracing in his thesis at Purdue. You might ask him to finish it and send you a copy: sun!decwrl!decvax!pur-ee!cychosz -- Ken Turkowski @ Apple Computer, Inc., Cupertino, CA Internet: turk@apple.com Applelink: TURKOWSKI1 UUCP: sun!apple!turk