Not logged in, Join Here! or Log In Below:  
News Articles Search    

Submitted by Jacco Bikker, posted on April 29, 2005

Image Description, by Jacco Bikker

A while back I sent in an ray tracing IOTD showing the Stanford bunny, rendered at high speed. I've been busy since I made that demo, and these shots show the current state of the art. The top shot represents the maximum image quality: There are textures, adaptive super sampling (for edge anti aliasing), a bloom filter causing a subtle glow and of course the reflections. Sadly all this eye candy comes at a cost. The lower shot shows a very good performing model: The number of rays per second is no less than 3 million on a 1.7 Pentium-M - on a P4 @ 3.2Ghz this would be about 6 million rays per second, which is better than the SaarCOR FPGA ray tracing chip.

Over the past months, many things have improved: The overall speed of the ray tracer has been improved considerably due to some stiff competition from tbp (the odd french dude), there's a complete tool chain now to get from downloaded content to ray traced images (via the .obj file format), and the functionality has been extended considerably (textures, reflections, HDRI, networked rendering etc.).

There will be more good stuff, I'll keep you all informed. Greets - Jacco.

Image of the Day Gallery


Message Center / Reader Comments: ( To Participate in the Discussion, Join the Community )
Archive Notice: This thread is old and no longer active. It is here for reference purposes. This thread was created on an older version of the flipcode forums, before the site closed in 2005. Please keep that in mind as you view this thread, as many of the topics and opinions may be outdated.

May 04, 2005, 10:46 AM

Well, Scali and Dummy could write a raytracer with the BrainFucker language, and then the guy with the fastest result, for a given platform, is the winner... And, *maybe*, a fun programming site will still be fun ! And take care before any answer, remenber that my father is the strongest father of the world.


May 04, 2005, 11:15 AM

It's just the standard kind of figures you see on tech sites like this:,1558,1777120,00.asp

May not be entirely accurate, but it should be obvious that there are orders of magnitude of difference between the PhysX accelerator and a system with one or two high-end x86 processors.

You can test your CPU's physics performance with NovodeX Rocket anyway.


May 04, 2005, 02:09 PM

ash the blunt man...

(aside: i tend to agree with scali more than dummy, who was, in fact, patently rude and dismissive. then again, scali should have been equally dismissive and not chosen to go down that dreaded "arguing about arguing" route, from which no sense can be derived... oh well...)


May 04, 2005, 02:22 PM

when i say o(n), i mean wrt to resolution: double the res, half the speed.

doing 3 box filters is a pretty good approximation to a gaussian (see, and if you're smart about caching etc you can make it seriously fast. alex evans at lionhead (ahhh, don't i love that place ;) wrote a cool article on fast blurring on gamasutra (iirc), definitely check that out.

Jacco Bikker

May 04, 2005, 03:15 PM

Found the article here:
Reading it now. Thanks for the pointer!


May 04, 2005, 04:33 PM

Hey, about my post above, I somehow highly doubt my school would purcahse p4s 3.2ghz pcs. First of all, no one needs machines that strong there, and second it would kill the whole school system's budget purchasing pcs like that, in such amounts.

I would say it something more like P4 2.2, or 2.4 ghz machines. If not less, we just had _old_ compaque machines with win 95 there last year, so the school finally raised funds and bought some better tech.

Nothing special really, yet i am quite surprised to have such performance there, in contrast to your (almost everyone's) posts. At first i didn't even expect the demo to run ;)

- Tim


May 04, 2005, 04:34 PM

however, i'm getting the impression that scali just doesn't know what he's talking about wrt to sampling etc. good job trying to clear it up jacco, but your words fell on deaf ears unfortunately...

and that is the end of my partiality.


May 04, 2005, 05:04 PM

Dave, It looks like you accidentally posted this message in the IOTD forum while I think it should have been in the 'dear mary' forum :^D

p.s. Anyhow, any advice on women is always welcome.. Darned if I understand these enigmous critters. I think I'd be better of trying to decipher Jacco's sourcecode anyday ;^D


May 04, 2005, 05:32 PM

lycium wrote: however, i'm getting the impression that scali just doesn't know what he's talking about wrt to sampling etc. good job trying to clear it up jacco, but your words fell on deaf ears unfortunately...

In actuality, it is the opposite. I think Jacco Bikker mistook me for saying that I wanted texture filtering to replace AA. He even gave an example of an untextured model.
What I meant was to not rely on AA alone to solve all texture sampling problems, but use more advanced texture filtering... I think nobody understood what I meant, except for davepermen.

Sadly Jacco didn't respond to my post where I tried to correct him, and explain what I actually meant.


May 05, 2005, 04:18 AM

Schools tend to buy stuff irrationally when they get a buget. ;)

Btw: I think you wouldn't get anything below a 2,8GHz proc nowadays. (except a celeron perhaps)

(and please don't nail me on that.. i know that my A64 just has 2GHz :P i just meant that as a performance-measure-scale to p4's)

This thread contains 160 messages.
First Previous ( To view more messages, select a page: 1 2 3 4 5 ... out of 5) Next Last
Hosting by Solid Eight Studios, maker of PhotoTangler Collage Maker.