Havok to compete with AGEIA for physics

by Tuan Nguyen on 11/2/2005 9:31 AM EST
Comments Locked

33 Comments

Back to Article

  • realphysics - Thursday, November 10, 2005 - link

    It is easy to jump to the bandwagon, but don't be hasty - those who create games develop and publish them have two issues related to physics. One: how much they have to pay companies such as Havok to get that physics toolkit..It isn't free folks.. Havok gets paid for every game for using their physics toolkit. Ageia has an SDK for physics which is FREE. There goes the economics for the game developers. Argument number two: Physics can never be AS REAL,VIVID OR IMMERSIVE or as envisioned or fancied by the game developers, or those who enjoy a gaming experience when the game itself is limited by the hardware that executes it (remember CPU and GPU were designed and developed more than a decade ago at least - with a completely different purpose and still serve those purposes). Don't confuse the issues. If you want mediocre physics - go for what you have in the market, if you want real physics and experience go for Ageia. You get what you pay for. Remember, in the future those who create, develop and publish games are going to realize they have even greater potential to express their creativity with the physics offloaded to hardware than can really perform and the SDK they use for it is FREE - not something that Havok offers - Go figure
  • Nighteye2 - Thursday, November 3, 2005 - link

    Havok FX vs AGEIA is like integrated graphics vs a video card. I expect developers will use Havok FX as a substitute for gamers that do not have an AGEIA card.

    I find it hard to believe that a GPU already stressed by dozens of other things to calculate could outperform a dedicated PPU. Keep in mind that scenes with lots of physics have lots of moving components in them and those cast lots of shadows, so the scenes with the most physics calculations are likely to also be the ones that tax the GPU the most - even without cramming some of those physics calculations unto the GPU.

    You'll probably see that the highest physics level in games will start to require an AGEIA PPU, just as some detail modes once required a 3DFX chip.
  • SynthDude2001 - Wednesday, November 2, 2005 - link

    I like the idea in general, but I worry about performance. First of all, how would this perform compared to the discrete PPU (=how well would the GPU perform these types of calculations and how fast); and how will this affect 3D rendering? We don't know much about how this works right now, but you'd think that the computing cycles for these sorts of heavy calculations have to come from somewhere...the fact that they even admit that this would be better on dual GPU systems worries me. Unless you can use your old video card as a 'dedicated GPU-PPU', I'm definitely worried about performance. And since they say SM3 is required, only those upgrading from 6600/6800 cards will be able to do that anyway. I'm wondering if I'll be able to keep my AGP 6800GT and use it just for physics with this...but at that point, it would seem to make more sense to sell it and get a real PPU for about the same price.

    In any case, like someone else said, I'm glad that another company (and not just a tiny one nobody has ever heard of) is starting to get serious and push physics processing.
  • KristopherKubicki - Wednesday, November 2, 2005 - link

    quote:

    AGP 6800GT and use it just for physics with this


    Unfortunately, AGP + any sort of physics computation doesn't seem very likely due to the asynchronous bandwidth.

    Kristopher
  • SynthDude2001 - Thursday, November 3, 2005 - link

    aha, thanks for the clarification. I suppose it doesn't make too much of a difference since I'll be upgrading the video card by next summer, and I doubt any of this physics processing stuff will surface at retail before then anyway.

    Still not sure how I feel about this, I guess it's really too early to know much of anything. I was looking forward to the stand-alone PPU, but if this idea catches on and provides similar physics performance without having to spend extra on a dedicated card...I'm all for it. I guess we'll have to wait and see.
  • tfranzese - Wednesday, November 2, 2005 - link

    quote:

    Havok explains that its engine is able to offload such physics operations as collision detection, which on today's general purpose GPUs are very slow to compute. We spoke to Havok and they said:


    I do believe you meant CPUs.
  • KristopherKubicki - Wednesday, November 2, 2005 - link

    Unfortunately, GPU is correct. Collision detection on a GPU is very poor because branch prediction on a chip that essentially only calculates scalar math is not very good.

    Kristopher
  • tfranzese - Wednesday, November 2, 2005 - link

    Within the context of the article then, that doesn't make a whole lot of sense considering Havocs position on a GPU vs. a PPU.

    It'd be great to see an actual analysis on this stuff rather than all this endless speculation about how useful it could be.
  • JarredWalton - Wednesday, November 2, 2005 - link

    I think the point is that SM3.0 makes such computations more feasible (i.e. it wouldn't have been worth pursuing in the DX8 days).
  • shabby - Wednesday, November 2, 2005 - link

    Those poor poor ati users with sm2 cards...
  • linuxOwnzIfUrLeet - Wednesday, November 2, 2005 - link

    What if creative labs used all the supercomputing power of their new sound card to do physics?
  • JarredWalton - Wednesday, November 2, 2005 - link

    Maybe Sony should sell a PS2-powered super-computer expansion card as well? Just think, Sony AND Creative working together on proprietary technology - who could stand against them!? :)
  • ncage - Wednesday, November 2, 2005 - link

    If i had to guess nvidia/ati might be puting physic functions in their GPU as we get die shrinks. I think this is the best place to put it to. I can imagine some of the newer video cards will tought ppu functions. Ive heard some state that as amd/intel add more cores then they think that amd/intel would add specialized cores that would take care of the physics part of games. This makes no sense at all. How many people don't game? They would be adding features to a CPU that everyone would have to pay for yet only gamers could use. Oh wow i just got a new operteron 10 core cpu with 2 cores used for PPU for my Database server. They could add specialized cores that would help in more pipelined parallel operations (pretty much now a gpu is designed) but i dought they add specialized functions like this to the cpu. It makes much more sense to put it in the gpu and i don't think aegis can really compete with nvidia/ati.
  • OrSin - Wednesday, November 2, 2005 - link

    The ATI video card in the new Xbox already off loads some physcial to a daughter GPU.
    Sorry but I doubt the CPU is the Cause of slow downs in most games. What they really need to do is off load the physics to the second Core. All new console and most CPU are going to dual core and most games are just not setup for it. If they write for PPU then maybse some software can Translate that PPU to the other CPU in the system.
    Makes the most since when trying to program.
  • adamfarden - Wednesday, November 2, 2005 - link

    Hmmm if it does work out on PC's then maybe we could see in systems a high end GPU used for graphics, and a low end GPU used for physics... a great way to recycle your old graphics card!
  • huges84 - Wednesday, November 2, 2005 - link

    That is exactly what I was thinking. However, that would only work for in the future when people's old cards are SM 3.0 capable. It wouldn't work for most ppl right now.

    But then again, in the near future more people will have Dual Core CPUs. That would be the best way to go in my opinion, becuase you can use that second core for multitasking everyday, not just when playing games.

    Also, if physics is such a big deal and has high demand, why don't AMD and Intel introduce new instructions into their next generation CPUs to help accelerate physics calculations. They did similar with SSE* to accelerate multimedia calculations. I think it would be better if that was done because that means that again everyone will eventually have a CPU that can do that, while eveeryone will not have a PPU or 2 GPUs.
  • bersl2 - Wednesday, November 2, 2005 - link

    A CPU can't perform operations in parallel the way a GPU can.

    If graphics cards had open ISAs like CPUs do, there's no telling what kind of inventive uses people might find for them. The Wikipedia article http://en.wikipedia.org/wiki/GPGPU">lists various uses of the GPU, w/ links.
  • bersl2 - Wednesday, November 2, 2005 - link

    To add to this, from an http://www.extremetech.com/article2/0,1697,1867123...">ExtremeTech article (emphasis mine):
    quote:

    The third future project at ATI is dramatically improved support for the GPGPU scene. These are researches, mostly academic, that are tapping into the massive parallel computing power of graphics processors for general computing tasks, like fluid dynamics calculations, protein folding, or audio and signal processing. ATI's new GPU architecture should be better at GPGPU tasks than any that has come before, as it provides more registers per pipeline than either ATI's old architecture or Nvidia's new one. This is a sore spot for GPGPU developers but not really a limitation for game makers. The improved performance of dynamic branching in the new architecture should be a huge win for GPGPU applications as well. Developers working to enable general purpose non-graphics applications on GPUs have lamented the lack of more direct access to the hardware, but ATI plans to remedy that by publishing a detailed spec and even a thin "close to the metal" abstraction layer for these coders, so it can get away from using DirectX and OpenGL as an interface to the cards. Those are fine graphics APIs, but they're less than optimal for general purpose computing.


    If this means what I think it means, it's a real gift not only for the GPGPU guys, but also for the DRI and Mesa projects.
  • Shinei - Wednesday, November 2, 2005 - link

    Cg has been doing fluid dynamics simulations for at least a year by now (the demo of which you can download from nVidia's developer site (http://developer.nvidia.com))">http://developer.nvidia.com)), so an abstract layer that runs specifically on GPUs isn't new. However, I'd be curious to see if nVidia intends on releasing a physics-oriented version of their Cg instruction set that allows them to handle more general-purpose calculations to run as competition against AGEIA and Havok.
    Which, of course, brings me to my next point--even if Havok offers this GPU-enabled physics engine, it's my understanding that AGEIA's NovodeX physics engine is about ten times as fast as Havok's current engine is, even when executed solely on CPU resources. Havok would have to significantly streamline their physics calculations if they ever intend to compete with NovodeX for speed, and especially if they want to keep the GPU usage levels low enough that the GPU can actually spend some time rendering the scene...
  • Lord Zado - Wednesday, November 2, 2005 - link

    Personally, I don't really care whether Ageia's method or Havok's method is better. I'm just glad to see another company showing interest in this physics idea. I was really excited about the PPU when I first heard about it months ago, but I figured it was dead in the water since only one company was really pushing it and it didn't look too consumer friendly.

    I think independant physics processing is the logical next evolution of gaming and I'm glad to see another company in the mix.
  • rqle - Wednesday, November 2, 2005 - link

    Honestly, I RATHER have Developer use their time to offload physics to the GPU or Duel core CPU when/if possible, even IF it is at a lost of a few physics effects. To me, a little less effect is better if more can benefit. A little more physics (assuming this AGEIA PPU is GREATER then developer what DEVELOPER can offload to CPU/GPU) isnt going to make a bad game good.
  • Houdani - Wednesday, November 2, 2005 - link

    Very valid point about developer resources. Consoles are the ideal market for Havok FX since they are a closed system, therefore developers know exactly what hardware is available and can tailor their software accordingly. On PCs (an open system), the decision isn't nearly as cut and dry.
  • Houdani - Wednesday, November 2, 2005 - link

    Why would anyone want to put MORE burden on the graphics card when the graphics card is already the bottleneck (at higher resolutions or AA/AF)?

    In Havok's own quote they state the GPU may be overtaxed as it is. And giving the overtaxed GPU the additional responsibility of handling physics processing is good why?

    AGEIA may be a lame duck (mostly due to cost), but frankly I'm not really keen on Havok's idea.

    I had bad thoughts about overburdened GPU's when ATI was tooting their own horn over GPU physics processing. Havok has just rekindled those thoughts. Oye!
  • Griswold - Wednesday, November 2, 2005 - link

    quote:

    Why would anyone want to put MORE burden on the graphics card when the graphics card is already the bottleneck (at higher resolutions or AA/AF)?


    Fear is about the only game that makes a vid card the bottleneck at a reasonable resolution right now. In most cases, the CPU is the bottleneck. If you take the physics load off the CPU and put it on the GPU, there shouldnt be much of a penalty - but the GPU apparently can process physics much faster than a CPU.

    Alternatively, CryTek will support dualcores with the next version of the Farcry engine. They will let the physics engine run on a second core, if its available.

    At any rate, I dont see many people buying a PPU card if there are other viable options to use existing hardware.
  • JarredWalton - Wednesday, November 2, 2005 - link

    There are other games that tax the GPU quite a lot, like Doom 3, Quake 4, AOE3, etc. The question is how they tax the GPU. HL2 and FEAR do a lot of pixel shader stuff. Doom 3 and Quake 4 are more constrained by GPU memory bandwidth (for all the shadows among other things). So while D3/Q4 are GPU limited, there may still be unused GPU resources available.

    How this all plays out remains to be seen, naturally. I'm skeptical but at the same time hopeful.
  • Lord Zado - Wednesday, November 2, 2005 - link

    I still think the route to go is some sort of all in one "Gamer Card" with the GPU and PPU on the same card. Even Havok admits that its method would work best with two GPU's. Well what's better: 2 GPU's or 1 GPU and 1 PPU?
    The latter is probably cheaper unless you are buying really low end SLI cards.
  • Griswold - Wednesday, November 2, 2005 - link

    AGEIA is already dead before it was born.

    Nobody in their right mind would shell out 200-300 bucks for some physics engine when the same can be done by your 200-300 dollar vid card.
  • Crassus - Wednesday, November 2, 2005 - link

    Now why would spending 200-300 $ for a PPU be so different from spending the same amount for a second grafics card?
  • xtknight - Wednesday, November 2, 2005 - link

    Because there's no reasonable certainty that game devs will even use this thing we spent $300 for.
  • dwalton - Wednesday, November 2, 2005 - link

    I think this will force Ageia to introduce this type of off loading to the GPU function to their engine. I doubt many developers will want to use a physics engine that only can be take advantage of with a discrete PPU. This would be akin to offering SLI-only games.

    However, offering an engine that flexible enough to be used by a CPU, GPU or a discrete PPU (depending on setup) enables the opportunity for developers to create games based off the AGEIA engine for all gamers. This will allow games to offer different physic feature sets depending on the setup. Im a fan of this scenario because it gives more flexibility to the gamer especially under the condition that any PPU would be generally cheaper than a highend GPU. It also offer a gradual transition to a GPU/PPU setup while not requiring a PPU.

    It seems that offloading physics calcualtion to the GPU will come at cost of reducing the resources for actual graphics. It seems that under normal scenarios the most graphic intensive scenes will also be the ones that are also the most physic intensive. Its hard to believe that graphics and physics are inversely related and developers won't be forced to make graphical or physical sacrifices to enhance the other.

    Using an old GPU card to function as a PPU card is a great idea. However, it seems that SLI and Crossfire are moving towards allowing different generation card SLI/CrossFire setups to enhance graphical performance as well. A PPU will allow extreme gamers who dont want to sacrifice graphical performance for physic performance to simply add a PPU to their SLI setup. A PPU and a flexible physic engine (if available now) would give gamers a choice of:

    Extreme HighEnd
    7800GTX-GT/7800GTX-GT/PPU
    7800GTX-GT/6800Ultra-vanilla/PPU
    1800XT-XL/1800XT-XL/PPU
    1800XT-XL/850XT-Pro-800XL/PPU

    HighEnd
    7800GTX-GT/7800GTX-GT
    7800GTX-GT/6800Ultra-vanilla-6600GT-5XXX generation/PPU
    7800GTX-GT/6800Ultra-vanilla-6600GT-5XXX generation
    7800GTX-GT/PPU
    1800XT-XL/1800XT-XL
    1800XT-XL/850XT-Pro-800XL-GTO-700PRO-9XXX generation/PPU
    1800XT-XL/850XT-Pro-800XL-GTO-700PRO-9XXX generation
    1800XT-XL/PPU

    and so on and so on
  • AndreasM - Wednesday, November 2, 2005 - link

    That's a good point, and would be the best case scenario for gamers. But Havok FX and most likely a possible Ageia GPU solution is limited to SM 3.0, so using an old GPU card wouldn't really be an option, especially so with Ati cards. But I'm not entirely convinced a GPU physics solution would be able to beat a true PPU. But I guess that will remain to be seen, hopefully Ageia releases their card soon.
  • oneils - Wednesday, November 2, 2005 - link

    Hi Griswold, I agree with your post...but there are plenty of people who pay $500-$1000 for graphics cards (SLI), $300 for performance ram, $300 for a soundcard, and $200 for a 74gb raptor hard drive. These people will probably be buying a PPU if it means a performance increase of any kind for games.

    S.O.
  • oneils - Wednesday, November 2, 2005 - link

    Also, I have to admit, I'm guilty of the same excesses. I bought a 500$ vid card and a $1000 monitor. Never claimed to be sane, but that's the danger of hobbies.

    S.O.

Log in

Don't have an account? Sign up now