SGI: Computer Graphics

at the moment i am reading the new issue of "Digital Production" http://www.digitalproduction.com

take a look at page 74 + 75

VRED Photo 3.2, VRED Professional 3.2

*COOL*

Hello Thomas,

thanks for the compliments, we really work hard for it.

Regards

Matthias

Since a few months have passed since my last post I would like to give an update.

We are about 2 weeks away from our 4.0 release with the major feature of global illumination which adds quite a lot of realism to interior sceneries. Other than that lots of preparing functionality (selection modi etc etc) so model preparation only takes few days. We have tested our software with big models and found out that 550 million polygons do not slow down raytracing. They consume somewhere around 55GB of main memory so there is quite a lot of room on todays workstations. Nehalem/icore 7 gave us approx 50% more performance.

@Squeen you have been somewhat silent about your project ... hope that you are still improving ... I would like to hear more facts about scaling on your ubercluster. Biggest we tried in the meantime was somewhere around 130 cores ... still way too slow to drive the Sony 4K projector @15hz

Matthias

PS: Images can been seen on our website at http://www.pi-vr.de

I just wanted to post a new picture that was produced today, I hope you like it. Click on Image for full HD resolution

I know this is an international board and it's dangerous to use idomatic expressions - but that is simply sick, sick, sick. What you guys are doing is nothing short of amazing.

Amazing!

Awesome image. I've not even touched on motion blur except as a post processing step!
How in the world is everything so clean at only 256 samples per pixel? Do you use photon mapping for some other irradiance caching or is it just magic beans?

I also don't have any sort of HDR evironment map capability yet, so I don't know what to expect in terms of lighting difficulty level for a path tracer, but I seriously doubt I could produced as clean an image in 2 hours on 4 cores, let alone 20 minutes
I'm starting to get the impression from ompf.org that VRED is a real leader in the RTRT community. (One of these days you need to PM me your handle over there).

Nice work!

Thanx for the kind words.

no photon map and no irradiance caching yet ... everything brute force with some gehirnschmalz as we germans say (my way of saying that even I do not understand everything myself) .... acording to my collegue we would really need some time to fire up vtune and friends and do some serious tuning session ... there should be some room for improvements.

I really love 3d motion blur ... this changes the look soo much ... and you never want to go back to 2d hacks again.

I dunno how often everything got refined during the last 2 years of development of the tracer, but also a whole lot of time was invested into the material system, the best tracer is worth nothing if you make it too powerful and complicated for your users to use it (that's the reason I would never achieve anything out of a regular dcc tool)

Regarding leadership we really don't care a fuss about, there's so many new selfdeclared leaders these days. I don't post on ompf anymore (even forgot my login) and after those useless bashing wars during the last weeks I am not unhappy about it.

In the end its all about having fun about what you do and having people that appreciate your work ... and best if you can make a living out of it

Have to add a small correction. The rendering uses 512 adaptive samples per pixel, but the computation time is correct. When using 256 samples you'll get some noise on the headlights and rims while rendering time goes down to 15 minutes.

We try to make some more benchmarks in the near future on various platforms (1way up to 8way systems) to see how it scales. Last test on 32core system in 2008 showed ~85% efficiency per core.

Matthias

Again an update what the current version can do on maxed out workstation hardware. Click on Image for full HD resolution



Forecast to version 4.2 (end Q1/2010)

- much better quality with motion blur
- polygons ... who needs polygons anymore ....

Less than 4 minutes at that resolution with only 4 cores! That's incredible. I honestly don't know how you control the noise so well with so few samples. The motion blur looks great too.

Sorry to bother you, but its 2x QuadCore = 8 cores + Hyperthreading. Hyperthreading adds another 22% speed increase which is very good according to intel. The mentioned time is of course with activated hyperthreading

About the noise I don't know myself (sampling is beyond my programming knowledge) but as long as its working I don't need to

I really would like to run our software on your cluster though ...

Oh my mistake. 8 cores++.


Linux?

Following recommendations:

Master running on any kind of 64bit Windows OS.
Slaves running on 64bit Windows or 64bit Linux
fast and reliable tcp/ip based network between master and slaves. To be able to use multicast for initial spreading of the data the network topology should be very flat (one hop, maybe two ?)

Possible ?

If they're on the same subnet; zero hops...

The HPC cluster is 64bit Linux and the network is Infiniband and a shared filesystem. I'm not sure if they have the multicast set up, but for our render when we request work-cores from the queue, we get an environment variable that points to a file that lists the IP of all the node we are authorized to use for the next 12 hours. I'm usually able to check-out 1000-2000 cores without any conflicts since I think they have grown the cluster to well over 10,000 by now.

None of us use Windows boxes, but maybe we could borrow one.

Let talk more about it this summer after I've finished my project's design review.

We are going mainstream now:

http://www.cgchannel.com/2010/02/vred-e ... aytracing/

http://www.pi-vr.de/en/products/vred-essentials-10.html

@Squeen

No Problem, just le me know when you are done.

Regards

Matthias

Are you motivated to show the world your artistic skills ?

Then you should participate in our competition and maybe win some prices:

http://competition.pi-vr.de/

Good luck to all participating

Matthias

I'd like to remind that the last day of registration (8th march 2010) is getting near, so everybody interested please register as soon as possible.

http://competition.pi-vr.de/

Regards

Matthias

Is there a door prize for "Saddest Atempt at Computer Graphics on an Overpriced Workstation" ?

If so, maybe I have a chance