NVIDIA Acquires AGEIA: Enlightenment and the Death of the PPU
by Derek Wilson on February 12, 2008 11:00 AM EST- Posted in
- GPUs
The Face of the Competition
The Enemy of My Enemy Is What Now?
Who is NVIDIA's competition when it comes to their burgeoning physics business? It's certainly not AMD now that Havok is owned by Intel, and with the removal of AGEIA, we've got one option left: Intel itself.
Sure, maybe a developer could write his/her own physics engine directly for AMD GPUs, but that isn't going to go very far very quickly. That kind of project takes time. The bottom line is that without the support of a physics engine, AMD's GPUs can't be realistically thought of as a viable alternative to CPU based physics. While their CPUs will certainly benefit from whatever agenda Intel has with Havok, AMD doesn't have the same luxury Intel does of ignoring (directing?) the impact of its actions on the graphics market.
With Intel's march down the multi-threaded path towards their proposed many core architectures, NVIDIA has to be feeling at least a little heat. They need to expand their own relevance to push out of the graphics box into the grey area between many single threaded cores and true parallel computing. There are plenty of ways to do this, and if they establish themselves now it will be easier to fight the battles they may be presented with when CPU and GPU eventually meet again somewhere in between many cores that handle single threaded dependent code well and true massively parallel computing.
A Cold Front Moving Through Hell
While not stating that anything is in the works and even noting that it would be hard to logistically organize, NVIDIA's Tony Tamasi stated that they are committed to working with any of their competitors in the GPU market to get PhysX running on their hardware. The major concern is to put more powerful physics options in the hands of developers, and having PhysX enable hardware accelerated physics on any GPU would set the stage for a physics revolution. We would see developers actually start to push the limits of the hardware because everyone would have access to it.
And, more importantly from NVIDIA's perspective, it would put advanced physics out of reach of current CPU architectures. Even though a GPU may not be as well suited to physics as dedicated hardware, a modern CPU is vastly inferior to both. Getting more developers to implement PhysX, selling them on the pervasiveness of hardware support, and bringing a more impactful user experience to gamers could help push PhysX past Havok in the physics market.
Facebook
Twitter
RSS
32 Comments
View All Comments
Soubriquet - Monday, February 18, 2008 - link
Ageia was always a dog without a home. They were simply looking for an exit strategy and they must have made nVidia a tempting offer.IMHO nVidia didn't need Ageia, but thought it might come in handy for reasons mentioned hereabouts. Not nearly as expensive as some speculative acquisitions which spring to mind (AMD+ATI) but not likely to be particularly revolutionary either, IMHO.
Physics processing for the mainstream has to be API lead. So we can expect that to come from MS so Intel, AMD and nVidia will all need to get in touch with them and develope their own hardware to suit.
I get the sense that virtualisation may assist here, since physics on a GPU is not like physics on a CPU unless you have that layer in between software and hardware that can make the distinction insignificant to the software. In which case AMD have a decision to make, do they add their own version to the GPU (& compete with nVidia) or the CPU (and compete with Intel) or both ?
In any case virtualisation is just jargon for the time being and we are heading down the multicore CPU route so the CPU seems the obvious place for physics. But nVidia dont make CPUs and I wonder if not a little of their motivation in getting Ageia was to prevent anyone else getting it. A dog in the manger, as it were!
goku - Saturday, February 16, 2008 - link
Thanks for destroying the best thing that could've happened to gaming, now I'll be waiting 10 years for a feature to be added to a game while I could've had that feature in 2 years had there been dedicated physics cards.I don't want to have to buy an nvidia GPU just to get add on physics. At least with the PPU card, it didn't matter what video card I had, and if I don't want or need to improve the visual effects of the game I'm playing but would like more interactivity, all I have to do is buy a new PPU and not a whole new video card.
perzy - Thursday, February 14, 2008 - link
Everyone knows that the CPU is dead, it's not developing beacuse of the frequency-/heat-wall.So the foreseeable future is the discret processors, gpu, fpu and maybe spu. Whatever x-pu you can imagine or come up with.
The gpumakers whant the fpumarket also for sure but the want to do it on their product in the channel they know and trust.
This is like when GM and Ford bought the bus-companies in the USA and closed them down.
Kill the competition, and a cheap low-selling...no brainer.
I'm just waiting for Intel to release their high-performance GPU's and later FPU's.
They are in desperate need to branch out.
mlambert890 - Thursday, February 14, 2008 - link
Everyone knows that the CPU is dead? Really? Have you sent a note off to Intel and AMD? I dont think they got the memo.A GPU, FPU or PPU are all processing units. Any efficiency implemented in those parts can be implemented in a CPU. Any physical challenges in terms of die size, heat, and signaling noise faced by the CPU are also faced by those other, transistor based, parts. What are you getting on about?
All of these parts are a collection of a ton of transistors arranged on a die and coupled with some defined microcode. How they are arranged is a shell game where various sides basically bet on the most commercially viable packaging for any given market segment.
There is no such thing as "dead" or "alive". With transistor based electronic ICs, there are simply various ways of solving various problems and an ever moving landscape target based on what end users want to do. Semiconductor firms can adapt pretty easily and the semantics dont matter at all.
I remember similarly ridiculous comments with the advent of digital media when people were saying the "CPU is dead" and the future would be "all DSPs". Back then I was equally amazed at just how far some can be from "getting it"
forsunny - Wednesday, February 13, 2008 - link
So basically from the article it appears that Intel wants PPU hardware to fail so that the CPU is needed for processing Physics and they can continue to push (sell) for newer CPUs for higher performance.Therefor it appears that Nvidia may want to compete in the CPU market or even in the PPU market so that extra performance can be gained out of the existing CPU power. Nvidia is already in competition with intel in the general chipset market. Then they could claim better performance than intel by adding the PPU technology; unless intel starts to do the same.
I don't see where AMD fits into the picture?
FXi - Wednesday, February 13, 2008 - link
I'm thinking there might be some near term benefit from adding a few secondary chips to the gpu card. There is bandwidth enough in pci-e 2.0 to handle some additional calculations.I'm thinking:
phyics ppu
sound apu
Nvidia has experience (some a bit dated) in both, but they now own the harder of the two to provide. Now they may run into power and heat budgets that constrain them from pursuing this route, but there is plenty of pci-e bandwidth to handle all these things on a single or even dual (sli) style card(s).
With even Asus going into the sound route that sounds like an easy one to cover (and one that has benefits in the home theater arena as well). Now that they have the physics I'd think the trio would work well. And when the gpu advances enough to cover one or both of the secondary chips you just remove them, let the gpu take over the calculations, lower the transistor count and move along. You continue to keep the same set of calculations all based on same card and all under the same roof.
And with their experience in OpenGL acceleration, I'd take a reasonable bet they could do OpenAL acceleration as well. Who knows, will we see eventually OpenPL? :)
haplo602 - Wednesday, February 13, 2008 - link
I think that the whole PPU market missed it's target. Instead of targeting the single-player FPS/RPG etc market, they should have targeted the MMO developers market.Any advanced physics needed for a single-player FPS can be handled by a multicore CPU or alternatively on the GPU shaders with a bit of work.
However imagine a large non-instanced MMORPG with tens of thousands of players and NPCs interating in combat and other tasks. All the collision handling, hit calculations etc HAVE to be done on the server side to prevent cheating. This puts a large strain on the server hardware.
Now imagine a server farm basicaly a multinode cluster handling a large world with each server hosting an area of the game. It has to handle all the interaction and in addition network traffic, backend database handling. A single or dual PPU setup with proper software could make worlds (if not universes) of difference to the player experience, offloading the server CPUs from a bulk of operations.
Huge improvements to player experience here. Maybe I just miss information on these, but I have yet to hear about an MMO that actualy uses this kind of technology.
DigitalFreak - Tuesday, February 12, 2008 - link
HA HA HA HA HA HA HA! Chumps!Zan Lynx - Tuesday, February 12, 2008 - link
Nvidia should start calling their next-gen cards with PhysX support "VRPU"s instead of GPUs. Call it a Virtual Reality Processing Unit.The CPU feeds it objects. The VRPU can use the vertex and texture data for both graphics and physics. Add some new data to the textures for physics and off it goes. The CPU can sit back and feed in user and network inputs to update the virtual world state.
cheburashka - Tuesday, February 12, 2008 - link
Larrabee