Server-side 3D Rendering

The idea that it is more efficient to render 3D images on a server and then deliver these to clients in real time runs counter to the way distributed systems have been developed for decades. We have always lived in a world in which network bandwidth was so scarce and so slow that it was the bottleneck for distributed systems. IBM, Sun, and HP all see a future in which bandwidth is much more abundant and the delivery speeds are many times faster. They are beginning to create distributed visualization systems that allow all of the heavy visualization work to be done on a server and distributed to clients in a manner similar to MP3 movies (e.g. try watching streaming movies on your PC from Netflix). But they also believe that delivery speeds will be fast enough to allow two-way interaction so that the customer on the client end can navigate through the world and make changes to it while it is being rendered on the server side. Currently it appears that they are able to do this with 3D spaces where the client is primarily interested in moving around objects like machine parts and 3D molecules. The client may occasionally make a change and see the effect reflected back by the server in near real time. This is a necessary first step toward server-side rendering for virtual simulation and gaming environments. I do not think we are at a point where we can support real time interactive play yet and are probably very limited in the number of independent players that can be supported. But the financial benefits of this technology are so compelling that I expect many companies to push on this technology until they make it happen. Even Amazon web Services could be a provider in this space if there is enough demand It essentially turns every electronic device into the equivalent of a rendering machine. Imagine playing the hottest new computer game on your iPod, PDA, or cellphone – and not the high-end version, but a very mediocre piece of hardware. Also, imagine that you do not have to upgrade your computer when a new high-powered game comes out because all of the hardware upgrade is done on the servers. The number of potential customers for such a service is certainly in the tens of millions and perhaps handreds of millions. It seems to be on the scale of the cell phone market in size.

Serious Games Hype Cycle

In 1995 the Gartner Group created and promoted a graph that they called the Hype Cycle. It describes the boom-and-bust cycle of media coverage and popular attention to a new technology. Once the seeds of a new technology become available, companies begin working on new products that exploit it. If the technology is sexy enough, the media covers it so aggressively that expectations far exceed what can be delivered in the near-term. At some point the real products fail to meet the expectations that were generated by the media, the media and the mass audiences tag it as a failure or disappointment, and wander off to pump up some other technology. However, industry continues to work with the technology and turn it into a product. A few years later the technology delivers successful products that everyone is interested in and customers wonder why it took so long. This Hype Cycle curve has been applied to many technologies and you can see some of these in the links below.



Over the last 2 years the media and our own community have gotten very excited about the promise of serious games. During 2007, the media was particularly enamored with Second Life. There was a point at which Second Life was appearing in the mainstream business press every single week (competing for attention with Facebook). Perhaps, we have gone over the peak of attention and expectation in serious games. We may be entering a period in which many people lose interest in the subject and it is no longer seen as the next revolution in simulation. But even as the media attention wanders away, there will be developers who continue to work in this area. If the hype cycle idea holds true for serious games, then in a couple of years we should see some successful products emerge and the media recognize that the industry is finally catching up with the hype that was generated in 2005-2007.

I have discussed this idea with reps from 2 different companies that develop tools for both the gaming and the military communities. One vendor believes there is no near-term growth opportunity in serious games and are ignoring it, the other vendor believes there is a good growth curve here but the market has to get past the fractured fiefdoms and love of legacy products before it can take off (beginning in 2008 or 2009 in her opinion).

• Gartner Hype Cycle Web Site: http://www.gartner.com/DisplayDocument?doc_cd=130115
• Wikipedia Hype Cycle: http://en.wikipedia.org/wiki/Hype
  

Project Darkstar

Project Darkstar is a research project at Sun Labs aimed at making massively scalable game
server system easy for traditional game programmers to construct. As such, it presents
an event driven, apparently mono-threaded programming model to the game developer while
exploiting the inherently parallel nature of games in an underlying multi-threaded/multi-process
execution environment.