Slashdot Mirror
More on Grid Computing and Gaming
securitas writes "Sony, IBM and Butterfly.net will announce and demonstrate a new grid computing network for PS2 online gaming at the Game Developers Conference next week. The network is based on Linux and the Open Grid Services Architecture (OGSA) and is designed to support millions of players. This is believed to be the first major consumer application of grid technology. Read the details at the NY Times, CNET and the Washington Post."
support millions of players
That's gonna be crowded on the GranTurisma race tracks...
I want my karma, and I want it now!
It's not! As far as I can discern the only difference is in the length (and quantity) of the connections. Parallel computing normal involves a local cluster of computers (LAN, eg a Beowulf type project) whilst the Grid works on the SETI type system of enlisting processing power across the internet (WAN) - ie many more processors separated by greater differences. Note these are comparative terms so you decide what's a Grid and what's an MPP
Whatis says: Grid computing requires the use of software that can divide and farm out pieces of a program to as many as several thousand computers. Grid computing can be thought of as distributed and large-scale cluster computing and as a form of network-distributed parallel processing. It can be confined to the network of computer workstations within a corporation or it can be a public collaboration (in which case it is also sometimes known as a form of peer-to-peer computing).
pbhj
It seems to me that the more technology these companies throw at games, the less I feel the desire to play them. Don't get me wrong: I love excellent graphics and sound. I just think the playability suffers when a game developer spends so much effort on the technology. I'm glad we have such a scalable platform for online gaming. I just haven't seen games that are as compelling as they used to be to take advantage of the platform. Am I getting too old for video games?
Another application would be in natural language processors. They require huge databases and computing power to process them. A grid would be a perfect way to build such a system.
Mind you, these applications are equally commercially viable. You could charge say $1000 per game against the world champion chess program, or $100 for 30 minutes of conservation with the most intelligent bot ever, and so on.
... so I looked up some simple details.
"Grid is a type of parallel and distributed system that enables the sharing, selection, and aggregation of resources distributed across "multiple" administrative domains based on their (resources) availability, capability, performance, cost, and users' quality-of-service requirements."
So, this project would essentially create one of the above distributed systems using simple, low-cost console gaming systems.
I remember reading awhile ago that Iraq wanted Playstations in order to grid them together and create supercomputers from 99 dollar American gaming devices.
Reply or e-mail; don't vaguely moderate. Ex-O'Reilly/MIT employee, now a full-time Google employee.
However no one I've spoken to has the slightest clue as to how they plan on using this Grid stuff. Does anyone know any details? All I see are people saying 'no bandwidth, latency', etc.... I still can't figure out what it's supposed to do. Which is maybe on purpose.
If you look at the chess pieces on the board, so to speak... MS with Xbox, MSN, flavours of XP with media/TV style abilities... then Sony, aligned with IBM for a new chip and a radical new network... not to mention the Cell sharing some tech with IBM's forthcoming Power derivatives for Apple...
Strange things are afoot at the Circle K...
If Jesus wants me it knows where to find me.
It isn't. Grid computing is the big buzzword of the day these days. I work with, and on, Globus, and this stuff just doesn't work yet. But beyond the fact that it isn't reliable software, what IBM is doing with Butterfly isn't really Grid computing. They're just saying that to get publicity.
Some of the original articles last year attributed features of the "grid" they're setting up to the Globus software, while anyone who has actually installed Globus knows that it can't do (things like accounting, failover services, etc).
I've seen a ton of questions asking what Grid computing is. The most common one being how does it differ from parallel/distributed computing?
First off, I highly suggest reading The anatomy of the Grid by Ian Foster et. al. It provides a pretty good overview into this whole Grid thing.
But for the lazy, here's a little bit. The Grid is more than parallel computing. Typically with parallel/distributed computing the problem or resources are static or both. Grid allows both of these to change. In a nutshell, Grid computing means not having to worry about where the compute resources are. Just start a calculation and it gets done. Just like how you don't worry where your power comes from, you just plug in.
The core of the Grid is virtual organizations. Under a VO, I could get together with a few friends and pool our resources. We could set up a registry and some factories (I'm speaking OGSA here, but whatever) and create some certificates. Then, we could submit jobs to the Grid and not have to worry about the resources that they're running on.
GSI provides some really nifty security features (based on X.509 I believe). Basically you provide a mapping that allows other authorized users to run commands on your computer. When you're on the Grid you create a proxy for your certificate that is passed to the process that you run on this other computer. Then if that computer needs more resources, it can create another proxy certificate and delegate to another server.
Also, Grid computing is more than just computing. There is data storage and instrumentation sharing also. You might want to check out PPDG, GriPhyN and TeraGrid for examples of these systems.
If you're interested in playing with the GRID, you can go download Globus Toolkit 3.0 Alpha or the Java CoG Kit which is a pure Java implementation of Globus 2.x (it's much easier to install than the regular Globus 2.2.x).
My Slashdot account is old enough to drink...
There's more to this debate than pure numbers. The PS2 and the GameCube have radically different architectures to the Xbox.
In fact, in your list, the only numbers that can actually be used as a measure of performance are those of the PC-like Xbox.
If I were to describe the PS2 as having three processors working in parallel, each with their own on board memory and two of them able to operate on vectors directly, you might start to see how it differs from a PC concept.
Similarly with vRAM. The PS2 has a 'measly' 4Mb of video ram but it also has the ability to stream textures in and out of it faster than a frame can be drawn. This gives you a much larger 'virtual' vRAM.
Your mouse has moved. Please wait while Windows restarts for the change to take effect.
Sorry but this is misleading, the CPU's for the PS2 and GC are both specifically designed for games, the xbox is still more powerful but it is a lot closer than those numbers represent.
The xbox is running a x86 intel chip, I'm sure most of us here don't need to be reminded that the current x86 chips we use today are descendants of of chips designed purely to crunch numbers for business applications. Quite a lot of CPU cycles are wasted in current computers, if you were trying to design a CPU for an interactive entertainment system you would not design it like an x86 chip.
Also the fact that the PS2 is 18 months older than the xbox explains why it's spec seems to be unimpressive.