NVIDIA Acquires RayScale Software

Edison

http://www.pcper.com/comments.php?nid=5674

Sitting here at an NVIDIA meeting in San Jose, word just got passed to the world that NVIDIA will be announcing the acquisition of a ray tracing software company called RayScale.  

This is an incredibly interesting move and clarifies more of NVIDIA's stance on merging traditional rasterization and ray tracing techniques, as we saw in our interview with David Kirk, NVIDIA's CTO.  

RayScale was a startup based out of the University of Utah and has built a hybrid renderer that merges the two techniques - all of the reflections in the image they showed were indeed done with ray tracing alone.  The engine was not up to real-time frame rates on the images but they said they have spent the last two weeks working on adding features, not performance, and that it should be "no problem" to get his running in real-time.

We are obviously very early into the news cycle and will be trying to get more information on what NVIDIA plans to do with this new acquisition.  I can tell you that you won't see these techniques in games for some time - both the software and hardware need time to mature and be optimized; but it is coming.  

The RayScale group purchase is brand new, and in fact the press release for this announcement won't hit until later today or tomorrow at the best.

Edison

Company Information
RayScale is a product of the decade-long interactive ray tracing research at the University of Utah.  For more information, send mail to: info@rayscale.com

RayScale Team:

• James Bigler, has B.S. and M.S. degrees in Computer Science from the University of Utah.  He is the author of several refereed technical papers and has worked on several large-scale graphics and scientific computing systems.
  

• Solomon Boulos, has B.S. and M.S. degrees in Computer Science from the University of Utah and is currently in the Ph.D. program in Computer Science at Stanford University.  He is the author of several refereed technical papers and has worked on several large-scale software engineering projects including Google Earth (TM).

• Mike Fahnert, Chairman, was founder, President and CEO of KeyLabs as well as founder and CEO of Micro Access. He has worked in a variety of roles including business developments, technology management, professional services, and software quality assurance. He has an MBA with an emphasis in Technology Management, a BS degree in Computer Information Systems with a minor in Electronic Engineering Technology and an Associates degree in Computer Science.

• Alan Mendel, Chief of Business Development, is the founder and managing partner of Focus 20.  He has worked as an engineer and business consultant in a variety of industries mainly associated  with computer-aided design.  He is also a co-founder and Chairman of the Children's Biomedical center of Utah, a non-profit corporation dedicated to the treatment and care of children with Autism Spectrum Disorder (ASD) located in Salt Lake City.

• R. Keith Morley, Chief Software Engineer, has a B.S. in Computer Science from the University of Utah, and also studied at Princeton University. He served as team leader in the *RAY interactive ray tracer project. This project was performed in conjunction with Silicon Graphics and was demoed at SIGGRAPH 2002. He worked as a Senior Software Engineer at Walt Disney Feature Animation on 3D rendering and lighting tools. He is the author of a book on ray tracing.

• Steven Parker, Chief Architect, has a B.S. in Electrical Engineering from the University of Oklahoma and a Ph.D. in Computer Science from the University of Utah. He was the designer and principle author of the first highly interactive ray tracer "rtrt" presented at the Visualization 98 and I3D 99 conferences. He was a general chair of the IEEE Symposium on Interactive Ray Tracing in 2006. He teaches the graduate course on ray tracing at the University of Utah and is the author of over 60 refereed technical articles on computer graphics, visualization, scientific computing, and software engineering. He was the main architect for the technology underlying RayScale's products.

• Austin Robison, Chief Developer of Technology, has a B.S. in Computer Science from the University of Chicago and an M.S. in Computer Science from the University of Utah.  He has worked on several large-scale software engineering projects including the game The World Series of Poker (TM).

• Peter Shirley, Chief Technology Officer, has a B.S. in Physics from Reed College and a Ph.D. in Computer Science from the University of Illinois. He wrote several of the lighting and material codes for the "rtrt" ray tracer. He was a papers chair of the IEEE Symposium on Interactive Ray Tracing in 2006. He teaches the realistic rendering course at the University of Utah and is the author of two graphics books and over 70 refereed papers on computer graphics and visualization.

Edison

Pete Shirley's Graphics Blog：

Hybrid algorithms

Some movies are made with a "hybrid" algorithm where rasterization is used for the visibility pass and ray tracing is used for some or all of the shading. This raises two questions:

   1. Why is this done rather than using just one algorithm?
   2. Would this technique be good for games?

First question 1: the reason it makes sense to use both is that rasterization is fantastic at dealing with procedural images. It is the basic Reyes look that is still going strong after almost 25 years: for each patch, dice in micropolygons while applying displacements. If you do a billion micropolygons, no problem as they are never stored. The frame buffer is where the action is. Now suppose you want to do ambient occlusion; the best way to do that is ray tracing. But ray tracing on procedural geometry is slow. Using Pharr et al's caching technique is probably the best known method. But an alternative is just not to apply the displacements and use less geometry as PDI did for the Shrek 2 movie (see their siggraph paper for details). That idea goes back to at least Cohen's 85 paper where detailed geometry is illuminated by a coarse model.

Now question 2: would this be good for games. Nobody knows. I will give two arguments, one for, and one against. The reason this will happen is again procedural geometry. But there will not be so much that it wont fit in core. Still doing it with rasterization will help locality and something like a DX10 geometry shader can be used, and efficient use of caches is where the action is and will continue to be. Now an argument against: Whitted-style ray tracing has good locality and thus such complexity is not needed. Once games use ray tracing they may as well use it for visibility for software simplicity. My bet is on the latter, but I sure wouldn't give odds. If graphics teaches us anything, it is that predicting the future is difficult!


Ray Tracing Shading Language

Steve Parker and friends at Utah have developed a ray tracing shading language (RTSL) described in this pdf file. I am very excited about this work for entirely selfish reasons. I like ray tracing partially because of the elegant code. Now add ray packets and SSE and voila-- it makes DirectX code look lovely in comparison. The initial results are that ray packets and SSE can be relegated to a compiler with little or no loss of performance. and the code is pretty sweet looking. I have been looking over the shoulder of this project writing some RTSL code and it really seems to work as well as reported in the paper. A surprise to me is that it is much nicer to write than C++ for me because you avoid the blasted C++ header files.