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.

Sun Blackbox

Sun Microsystems has created a computing center inside of a 20 foot shipping container. This product is meant to be a portable IT center for oil companies, DHS/FEMA, commercial disaster recovery, portable on-demand computing. The container is completely sealed from the outside and connects to external power and cooling pumps (which could be contained in a second 20 foot shipping container). This could potentially provide all of the computing power for a training base in Kuwait or for a mobile Live/Virtual/Constructive training package.

The product incorporates standard computing capabilities. Its unique features are in the design for shock absorbency, separation from the elements, air flow, and power consumption.

• Fast Company Article
  
• Sun Blackbox Web Site
  
• Sun CEO Blog on BB
  

Server-side Rendering - Sun and Nvidia

Sun has been working with Nvidia to create a capability to do both the computation and any associated rendering on the server side. Then they stream the screen image to the client device. This is significant switch from what we do with the DIS and HLA federations now. But Sun’s goal is to make it possible to experience rich 3D scenes on lightweight client devices because all of the rendering is done on the server. They are also working on a capability to use new graphic chips to render “Pixar quality” images in real-time for display in CAVE environments.

If Sun is successful then it is an indication that network bandwidth is becoming plentiful enough that we can change the model we have used for decades of creating very small data packets and doing all of the scene generation on the client side. This is valuable for customers who do not want to have to hold a powerful graphic machine in their hand (like a cellphone). Instead, customers will be able to see rich 3D worlds on very minimal computing clients, e.g. something that is capable of playing MP3 movies today. This brings down a significant commercial barrier. Even the cheapest cellphones and pocket PCs would be able to play a rich 3D game because the game would really be running and rendering on the server. It is hard to imagine a world in which bandwidth is that plentiful for the consumer. Probably it would be rolled out to industrial customers for limited applications and private bandwidth first. Their product name for this is TurboVNC.

On the military side, we would be able to tap into any scene that anyone in the training event is seeing. We could see it on a regular cellphone (if/when it becomes available through a cellular network) or a wireless pocket PC.

The World Needs Only 5 Computers

Greg Papadopolous, the CTO of Sun Microsystems, has been getting a lot of play from the statement that the world only needs 5 computers. This plays against a (purported) famous statement by Thomas Watson Jr. of IBM, when he truly believed that there were only a few customers for big computers. Greg P. has an entirely different meaning. He sees the networking of the world as a force that will concentrate computational power into a few major centers that will serve up most of the services that people will need from computers. As examples he identifies the 5 providers of these services as Google, eBay, Amazon.com, Microsoft, and Salesforce.com.

Militarizing this idea, we could say that the Army only needs 3 computers. These would be networked “hyperscale machines” (Papadopolous’ term) that serve up: (1) Business IT, (2) Mission Operations, and (3) Training Events. As with Papadopolous’ list of 5, further digging will reveal that these 3 computers only cover 80-90% of what the Army needs to do. Perhaps there will be smaller machines for R&D and other functions. Yes, smaller. The amount of R&D computation is probably very small compared to the pooled operations in the top three categories of business, mission, and training.

Papadopolous’ original article