Slashdot Mirror


All GeForce 8 Graphics Cards to Gain PhysX Support

J. Dzhugashvili writes "Nvidia completed its acquisition of Ageia yesterday, and it has revealed exactly what it plans to do with the company's PhysX physics processing engine. Nvidia CEO Jen-Hsun Huang says Nvidia is working to add PhysX support to its GeForce 8 series graphics processors using its CUDA general-purpose GPU (GPGPU) application programming interface. PhysX support will be available to all GeForce 8 owners via a simple software download, allowing those users to accelerate games that use the PhysX API without the need for any extra hardware. (Older cards aren't CUDA-compatible and therefore won't gain PhysX support.) With Havok FX shelved, the move may finally popularize hardware-accelerated physics processing in games."

114 comments

  1. It's the "Ray" experience. by Anonymous Coward · · Score: 0

    Aw crap! I was going to buy an ATI.

    1. Re:It's the "Ray" experience. by IBBoard · · Score: 1

      Because they don't get developers to plaster things like that "en-veeee-diar" voice over the start of games?

      Having said that, I use Linux so my next card probably will be an nVidia because of the better drivers. Unless ATI get better in the one/two/three years until I buy a new card.

      It'll be interesting to see what they can do to really exploit this PhysX and make it worth its while, though.

    2. Re:It's the "Ray" experience. by tolomea · · Score: 5, Interesting

      Better is very subjective. We have both nVidia and ATI based thinkpad laptops running Ubuntu at work. And what I've noticed is that the ATI ones can do a kernel update with out screwing up the gfx drivers and they can switch between single and dual monitors (necessary when going on and off dock) without restarting X. On the other hand the nVidia ones have a pretty lil graphical config tool, while the ATI ones use a somewhat arcane and unreliable command line program. Personally I wouldn't trade my ATI one for an nVidia one any day, I very much like being able to unplug from the dock and switch down to single screen without closing and restarting all my apps.

    3. Re:It's the "Ray" experience. by pla · · Score: 1

      Having said that, I use Linux so my next card probably will be an nVidia because of the better drivers. Unless ATI get better in the one/two/three years until I buy a new card.

      AMD has open sourced their Radeon drivers. What more could you ask for than that?

    4. Re:It's the "Ray" experience. by Datamonstar · · Score: 2, Insightful

      Exactly. I support ATI now primarily for that fact. After using them I realized that they are just more capable all around cards. Who cares which one is minutely faster? In the end it doesn't matter what card I play my games on, so why should they be shoving ads for nVidia down my throat?

      --
      The eternal struggle of good vs. evil begins within one's self.
    5. Re:It's the "Ray" experience. by IBBoard · · Score: 1

      Graphics drivers that run Compiz-Fusion and let my play DirectX games through Wine without having to do a force redirect with a key combo? Graphics drivers on a 256MB X800 that rotate the cube as smoothly as the low-end nVidia in my machine at work? Graphics drivers that run video at full-screen with Compiz-Fusion running without all the tweaking and tinkering?

      Yes, the open sourcing might be useful, but nVidia works more smoothly with DirectX, Compiz-Fusion and media played through anything other than VLC (where I can easily set the output mode, although it still seems a tad sluggish at times).

    6. Re:It's the "Ray" experience. by IBBoard · · Score: 1

      "nVidia - the way it is meant to be" (or whatever it is).

      No, the way it is meant to be is a game that I play on my computer, not an advert for a specific card manufacturer!

    7. Re:It's the "Ray" experience. by IBBoard · · Score: 2, Interesting

      See my other post for what doesn't work quite right with my ATI card. I guess there might be a difference between desktop and laptop, but most of those things aren't an issue for me. Can't say a kernel update has ever screwed up the graphics drivers on my work machine with an nVidia card, but then I use the Livna repositories for Fedora to download the RPMs for the graphics along with the kernel update.

    8. Re:It's the "Ray" experience. by BiggerIsBetter · · Score: 4, Informative

      Whereas for me, ATI hasn't had usable XV support since 8.35.5 (or thereabouts), and the 3D rendering is buggy as hell... which kinda defeats the purpose of using a dedicated GPU. Go look at the known issues in the release notes - it reads like an alpha dev-snapshot. I regret fitting ATI to my laptop for the sake of a supposed performance advantage over the Nvidia option, and my next machines will absolutely be NVidia Quadro (Sun workstation, yes Nvidia even provides drivers for Solaris x86) or Intel integrated (ultraportable notebook).

      --
      Forget thrust, drag, lift and weight. Airplanes fly because of money.
    9. Re:It's the "Ray" experience. by KDR_11k · · Score: 1

      Really? I've abandoned the idea of buying an Ati long ago when I found out how crappy their OpenGL support is.

      --
      Justice is the sheep getting arrested while an impartial judge declares the vote void.
    10. Re:It's the "Ray" experience. by Andy+Dodd · · Score: 3, Insightful

      Have they? Where's the big news announcement?

      The last big news I saw was not that they OSed the drivers, but that they had given partial card specs and promised more.

      Please note that Matrox did the same thing in 1999 - They gave partial card specs (insufficient for implementing any 3D) and promised more, but never delivered. Lots of Linux users got suckered into buying paperweight G200s (including myself) back then. I will buy a card that performs as advertised NOW (whether or not it is with an open source driver or not), not a card that the manufacturer promises will eventually perform as advertised but can't at the moment.

      --
      retrorocket.o not found, launch anyway?
    11. Re:It's the "Ray" experience. by RupW · · Score: 1

      In the end it doesn't matter what card I play my games on, so why should they be shoving ads for nVidia down my throat? Because nvidia bought the ad by supplying hardware and technical assistance to the dev team. ATI do it too.

    12. Re:It's the "Ray" experience. by mdarksbane · · Score: 4, Interesting

      As an OpenGL developer, I can say that I will never touch an ATI product when I have a choice.

      Their driver support lags behind nVidia by years, and when they "support" a feature, it will often be in software with no warning that it is - so instead of failing with a useful error message, all you know is that *something* you did causes your system to render at 1 frame per minute and be completely unusable.

      I have spent weeks bending over backwards and through hoops to get our ATI test card to agree with me, just because it is so darn unresponsive when anything goes wrong. Non power of two texture in one of your models because the modeller apparently ignored your instructions? No warning, no error - just a hung machine that will take 5 minutes to kill the process.

      Give me nVidia any day.

    13. Re:It's the "Ray" experience. by MostAwesomeDude · · Score: 1

      The ATI/AMD guys responsible for releasing docs are also FOSS devs working on X.org. The next data dump will be tcore code, which is used to program 3D shaders on R500 and R600 GPUs, and will probably be relevant to the R400 engine, which is similar to the engine in certain R500 cards. This is not a bait and switch; ATI needs the market share too badly.

      --
      ~ C.
    14. Re:It's the "Ray" experience. by Andy+Dodd · · Score: 3, Insightful

      "ATI needs the market share too badly."
      So did Matrox...

      --
      retrorocket.o not found, launch anyway?
    15. Re:It's the "Ray" experience. by ildon · · Score: 1

      So I take it you've never played HL2 or TF2 or anything else using the HL2 engine?

    16. Re:It's the "Ray" experience. by Anonymous Coward · · Score: 0

      I very much like being able to unplug from the dock and switch down to single screen without closing and restarting all my apps. ok some stuff might be different but on my nvidia card (not used it for a while) i could switch screens without restarting aps fine (i just had to use twinview). Not sure if twinview is usable i n your situation but in MY experience nvidia cards have always been easier to use in dual mon setups under both windows and linux due solely to better tools.
    17. Re:It's the "Ray" experience. by mandolin · · Score: 1
      Please note that Matrox did the same thing in 1999 - They gave partial card specs (insufficient for implementing any 3D) and promised more, but never delivered

      Bull! I used to routinely play Quake3, as well as TuxRacer (full version) with a matrox g200 card in my Linux box. See this site for instance, the documentation may not have been the best, but it was enough.

      I know they had problems getting an OpenGL driver out for Windows, I'm not sure they ever got it right, and a lot of people were pissed, but that's completely different.

    18. Re:It's the "Ray" experience. by mandolin · · Score: 1

      Just to follow up, the g400 series was out in '99, and it had one of the best open-source 3d drivers for linux for quite awhile.

    19. Re:It's the "Ray" experience. by Creepy · · Score: 1

      I agree - especially in the extensions realm, nVidia has MUCH better OpenGL support. In fact, the last ATI card I bought was well after fragment [pixel] shaders were approved by the ARB (an EXT in 1.3), but the card spec claiming both vertex and fragment shaders was misleading - the fragment shaders were ATI's (then long dead) proprietary fragment shader GL_ATI_fragment_shader.
          They came out with OGL 2.0 and 2.1 cards well before ATI, as well (but ATI tends to outperform them when they finally do show).

    20. Re:It's the "Ray" experience. by Anonymous Coward · · Score: 2, Interesting

      Having said that, I use Linux so my next card probably will be an nVidia because of the better drivers.
      You might like to hold off for a while, then. NVidia Linux support is very poor at the moment; the current drivers work fine for 7-series cards and some older 8-series cards, but they are hopeless for anything from the 8800GT onwards.

      Since I upgraded to an 8800GT from an old 7-series card, performance in Windows has rocketed but graphics in Linux have gotten slower, and the display is full of glitches too. They actually had a bug in the drivers where the fan ran at 100% constantly, making the computer sound like a leaf blower whenever I was booted into Linux, and it took them over a month to fix this.

      Unless they get their act together soon, this shall be my last NVidia card.
    21. Re:It's the "Ray" experience. by The+Analog+Kid · · Score: 1

      it reads like an alpha dev-snapshot.

      Not to mention it functions like one too. A few releases ago, the driver had broken the ability to display 1650x1050 and up until recently it couldn't suspend with any kernel using the SLUB allocator which debuted as the default in 2.6.23 but was in 2.6.22. What a joke.

    22. Re:It's the "Ray" experience. by Andy+Dodd · · Score: 1

      Hmm. Must've been very late 1999 (Quake3 was released nearly a year after I ditched my G200 in favor of a Riva TNT, which was probably around Jan-Feb '99.) I bought the G200 in August '98 because Matrox was promising all sorts of support, and all I know is by the time I stopped checking to see if anything had happened (4-5 months after purchasing the TNT), nothing significant had yet been delivered and the only 3D available on the Gx00 series was based on the earlier generation Mystique cards (and was EXTREMELY limited - no texture mapping for example.)

      --
      retrorocket.o not found, launch anyway?
  2. Think of the Earth! by bartmanus · · Score: 1

    This gives much more sense to buying all those dual GPU cards out there. However, they do consume quite a bit of power and therefore contribute to global warming by taxing the power stations more.

    So Ageia's stocks go up, nVidia's down. I hope I didn't plant any ideas into the heads of the green peacemakers. :P

    1. Re:Think of the Earth! by Some_Llama · · Score: 1

      "However, they do consume quite a bit of power and therefore contribute to global warming by taxing the power stations more. "

      I replaced all of my house's lighting with CFLs so the impact will be negligible. in fact after the switch i am using less power overall.

      (i'm pretty sure you were jesting but thought i'd throw that idea out there for any green conscientious gamers.)

  3. PhysX by Leonard+Fedorov · · Score: 1

    I knew buying a PhysX was a waste of time. Now they're effectivly useless - I already have an 8800.

    1. Re:PhysX by SuperDre · · Score: 2, Interesting

      No it wasn't a waste of time.. the PhysX-card is much better at calculating physics than the 8800 which is already busy enough doing 3D.. So the combo of 8800 with Physx-card is much better than using a dual 8800..

    2. Re:PhysX by masticina · · Score: 2, Insightful

      They are not as they did put in the market a product that has a place. Okay they did fail to sell succesfull a product but the first graphic accelerators we'rent the most lucky either! What matters is that the idea sticks and that now we might see Physics being offloaded more. So it has a place but the one putting it first on the market well, they didn't fare well!

      --
      Codefile Defected to another Hexadimal Range refresh your CHAOSTACK.NLM file with a new copy
  4. Nice! But... by johannesg · · Score: 4, Insightful

    ...what will be calculating my 3D images, if the GPU is already working on the physics? It is not like there is so much spare capacity left over in modern games anyway...

    1. Re:Nice! But... by Silverlancer · · Score: 1

      The GeForce 8800GTX, for example, has 16 stream processors, each of which can run up to 8 identical commands per clock (SIMD). They're not the same as the main graphics processors; they're a separate part of the chip AFAIK.

    2. Re:Nice! But... by qbwiz · · Score: 2, Interesting

      The 8800GTX has 8 groups of 16 stream processors, and they are the main graphics processors.

      --
      Ewige Blumenkraft.
    3. Re:Nice! But... by pwroberts · · Score: 1

      Dude, they /are/ the main graphics processor(s).

    4. Re:Nice! But... by eggnoglatte · · Score: 4, Informative

      They're not the same as the main graphics processors; they're a separate part of the chip AFAIK. You know wrong. OpenGL, Direct 3D and CUDA all share the same stream processors on the chip.

      (Think! Why would NVIDIA waste expensive chip real estate for stream processors if they weren't useful for 99.9% of the applications running on these chips?)

    5. Re:Nice! But... by Anonymous Coward · · Score: 3, Informative

      ...what will be calculating my 3D images, if the GPU is already working on the physics? It is not like there is so much spare capacity left over in modern games anyway... FTFA

      Our expectation is that this is gonna encourage people to buy even better GPUs. It might--and probably will--encourage people to buy a second GPU for their SLI slot. And for the highest-end gamer, it will encourage them to buy three GPUs. Potentially two for graphics and one for physics, or one for graphics and two for physics.


    6. Re:Nice! But... by Leonard+Fedorov · · Score: 1

      So SLi just became useful for those of us not running rediculously high resolutions?

    7. Re:Nice! But... by volsung · · Score: 5, Informative

      On the CUDA forums, we've gone back and forth about this, and the diagrams that people base this statement on are backwards. There are 16 multiprocessors (to use the NVIDIA terminology), each with 8 stream processors per multiprocessor. The 8 stream processors on each multiprocessor run the same instruction at once, but on separate register files. Multiprocessors, however, are completely independent, so in principle, one could imagine partitioning the resources between physics simulation and 3D rendering. This sort of partitioning has not been made available through CUDA yet, but hopefully this means we will see it soon.

      You are correct that these 128 stream processors (however you slice them) are the main compute engine. There is additional circuitry to do hardware accelerated video decoding, but NVIDIA has not exposed that functionality to 3rd party programmers, and it isn't used during 3D rendering.

    8. Re:Nice! But... by poot_rootbeer · · Score: 1

      Why would NVIDIA waste expensive chip real estate for stream processors if they weren't useful for 99.9% of the applications running on these chips?)

      3D acceleration itself is not useful for 99.9% of the applications running on these chips, if we include computing activities that are not gaming.

    9. Re:Nice! But... by ichigo+2.0 · · Score: 1

      "3D acceleration" is no longer a meaningful concept, as the majority of the "acceleration" happens on general purpose stream processors. A modern GPU is a parallel processor which just happens to have a rasterisation engine built-in. I'm guessing we'll eventually move the stream processors closer to the CPU, and integrate the graphics handling parts in the motherboard.

    10. Re:Nice! But... by eggnoglatte · · Score: 1

      3D acceleration itself is not useful for 99.9% of the applications running on these chips, if we include computing activities that are not gaming. That may certainly be true, howver there clearly are people who buy these cards to do stuff with them. As you correclty point out, "stuff" is mostly gaming, so it makes no sense to add features to these cards that are not useful for gaming but add significant costs. That was what my remark was about.
    11. Re:Nice! But... by Anonymous Coward · · Score: 0

      Think! Next time, figure out ways to sound more condescending in your reply.

  5. Hopefully, now PhysX adoption will become better.. by bomanbot · · Score: 2, Insightful

    I hope the NVIDIA acquisition and now this news will drive the adoption of the PhysX Engine. Right now, if you look at the list of titles, the PhysX Engine is not used by many games (namely, mostly Unreal3-Engine titles).

    If the adoption picks up, maybe Havok (which is now Intel property) will not remain the only physics engine in town, but right now, this news will not affect a whole lot of games...

  6. My suspicions about PhysX by Anonymous Coward · · Score: 0


    1. CPUs and GPUs today are extremely powerful and have a lot of design thrown into them. To design a physics processor that markedly supplements these costs lots of money.

    2. Even if you design such a physics processor it needs to have custom support in every game to sell well, but to sell well it needs to have custom support in every game. This means few people will buy it.

    3. See 2 - just to get food on the table you have to sell it hideously expensive, and just to get people to stock it you need to give them very generous wholesale prices. So it's expensive but you don't make much from it.

    4. See 3 - if you are selling a small number of units very expensively and are still struggling to stay afloat, it's likely that actual design and R&D struggles.

    5. Your product sucks and doesn't do anything useful, but it has probably had a lot poured into marketing. The perfect target to buy for a dime and have people feel good more cheaply.

    1. Re:My suspicions about PhysX by Anonymous Coward · · Score: 0
      Hasn't the NVidia acquisition basically nullified *all* of your points?

      2. Even if you design such a physics processor it needs to have custom support in every game to sell well, but to sell well it needs to have custom support in every game. This means few people will buy it. You could have said the exact same thing about 3D acceleration in games in the mid 90's. Look how well that failed.

  7. now that the gpu is doing 2 things lets do 3 !!! by sirmonkey · · Score: 3, Funny

    so now that my vid card is processing the 3d graphics and the physics (which is really only eye candy) how about we make it -the gpu- run the O/S tooo!!!! ooo ooo my next summer project! have linux run on just the video card! (openmosix is still around right :-D?) :-p what?!?!?! it runs on everything else. right now i'm typeing this on my old 700mhz laptop running the latest debian :-p

    --
    bored? try this http://jadmadi.net/blog/2005/01/27/linux-wine-how-to-running-windows-viruses-with-wine/
  8. Open Source != Holy Grail by Project2501a · · Score: 1

    > AMD has open sourced their Radeon drivers. What more could you ask for than that?

    GPL Licence? better support for linux from AMD themselves?

    --
    ----
    1. Re:Open Source != Holy Grail by jx100 · · Score: 3, Informative

      The RadeonHD driver *is* GPL'd, and all the specifications necessary for writing your own drivers from scratch are in the process of being released. Significant amounts have already been released after being checked out by AMD's lawyers.

      And the closed-source, binary module is still making progress while all that other stuff happens.

    2. Re:Open Source != Holy Grail by pinkocommie · · Score: 4, Informative

      Not quite true. They said they'd release the specs so said driver could be created but they only released partial specs for the 2D aspects of their chips. They still haven't released updated doc's for 3D/Video rendering etc

    3. Re:Open Source != Holy Grail by Jah-Wren+Ryel · · Score: 1

      They still haven't released updated doc's for 3D/Video rendering etc The reason they have not released docs for video rendering, and won't for the current generation of cards, is microsoft.

      The video rendering hardware is intertwined with their DRM enforcement hardware. On MS Windows that's all fine and dandy because MS loves DRM and MS drivers are closed source. But ATI is afraid that if they release the specs for the current video/drm combo hardware that will compromise their DRM on Windows. Security through obscruity, blah, blah, blah.

      Their solution is for their next generation of cards to separate the DRM hardware from the video rendering hardware. Then they can give out the specs for just the video rendering half and preserve their DRM secrecy on Windows. But that means they will never release those specs for any of their current cards.

      So, yet another away that people who don't need DRM and don't want DRM still have to pay the price for DRM.
      --
      When information is power, privacy is freedom.
  9. So, what's actually accelerated here? by 91degrees · · Score: 4, Informative

    Physics covers a lot, from gravity, inertia, particles, collisions, IK and various other bits and pieces. Not everything lends itself to acceleration. So what will be accelerated by this?

    1. Re:So, what's actually accelerated here? by TeknoHog · · Score: 5, Funny

      Obviously, gravity and other kinds of non-steady motion are good targets for acceleration. And because of NVidia's evil closed source drivers, the best way to accelerate your GeForce is at 9.81 m/s**2.

      --
      Escher was the first MC and Giger invented the HR department.
    2. Re:So, what's actually accelerated here? by vux984 · · Score: 5, Interesting

      From what I understand of this (and I could be wrong), the physx accelerator is primarily used to add eye-candy -- so things like showers of sparks, sprays of blood, geysers and clouds of dirt or water or snow on an impact (whether a footfall or a weapon strike...), leaves falling when you shoot trees, better hair and clothing, clouds, rain drop impacts, etc, etc.

      All the physics processing for all those particles can be offloaded to the physx engine, allowing more particle effects to be going on at higher level of detail and realism (e.g. incorporating 'wind' etc..) without dragging down the cpu.

      Its cool... but not earthshattering. And its a logical step to incorporate it into a video card.

      I don't honestly know if it it can really be used to assist with the trajectory calculations of the interactive players tank or fighter plane or whatever, etc... but I doubt it. And it probably doesn't matter either. That is a minor part of the scene...each shower of sparks by itself probably requires more physics calculations than an entire squadron of planes... more independant particles in the shower.

    3. Re:So, what's actually accelerated here? by LingNoi · · Score: 1

      I don't honestly know if it it can really be used to assist with the trajectory calculations of the interactive players tank or fighter plane or whatever, etc...
      It won't unless you can get the data back from the card. It's useless for some calculations and I much prefer the way a dedicated card works that feeds the data back to a program.

      Why? Well say you're running an MMOG server (or any server for that matter), you could have all sorts of crazy physics running on the server through a dedicated chip, or even an array of dedicated chips on some kind of physics server you could offload all the physics on to. You can't do that with physics on a graphics card because it's a one way pipeline, from your program to your monitor. So what we have to do today is run all the physics through the CPU and then send those calculations over to the players, slowing down the servers and limiting us to simple physics simulations.

      Not only that, if physics on the graphics card is going to be Nvidia only it means you'd have code them twice. The Nvidia way and another way for everyone else. I think a chip on the motherboard would be much better option as a game programmer it leaves a lot more possibilities open in the future when everyone has them as standard then on the gfx card would.
    4. Re:So, what's actually accelerated here? by CarpetShark · · Score: 2, Interesting

      You can't do that with physics on a graphics card because it's a one way pipeline, from your program to your monitor.


      I don't think that's the case. Graphics cards work on the same PCI-X buses that acceleration cards probably use lately. They use DMA to communicate with main memory without involving the processor. The VRAM might be optimised for writing, but it should be very possible to do calculations on the card, and get the results back. That's the whole point of the generalised GPGPU techniques.

      On physics being done in the CPU as well, and on physics engines not being used for much beyond extra eye-candy... well, it's the natural consequence of having machines without that feature as standard. You can't rely on it for the core gameplay, therefore it's only used for bonus features.
    5. Re:So, what's actually accelerated here? by teslar · · Score: 4, Funny
      Naw, it's much easier than you think. All of Physics can be expressed by just one equation, the Grand Unified Theory, the computation of which is accelerated by PhysX. The Grand Unified Theory was first discovered when programmers at Valve tried to optimise the physics engine of HL2. From the link:

      Game Engine Software Engineer at Valve, Jose Garcia discovered the theory. "The game engine ran too slowly. I was assigned the job of speeding it up," he said. "I started out by combining some of the gravity equations with some of the other force equations and found it all started to fit together. After a day, I had fine-tuned the entire physics-animation functions down to four lines of code, which ran a bit faster," he added.


      ;)
    6. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      PCIe, not PCI-X, go look them up and understand why.

    7. Re:So, what's actually accelerated here? by cnettel · · Score: 4, Informative

      I don't think that's the case. Graphics cards work on the same PCI-X buses that acceleration cards probably use lately. They use DMA to communicate with main memory without involving the processor. The VRAM might be optimised for writing, but it should be very possible to do calculations on the card, and get the results back. That's the whole point of the generalised GPGPU techniques.
      Nitpicking: PCI Express is not PCI-X. PCI-X was a derivative of the parallel PCI bus and never found in mainstream machines.
    8. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      NVidia already sell their Tesla GPGPU which is GPU-derived general computing hardware.

    9. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      If graphics cards are a "one way street" then Folding@Home couln't use them to accelerate their calculations (granted it is only for ATI cards), but they do.

    10. Re:So, what's actually accelerated here? by Robotech_Master · · Score: 1

      Yeah, that's what City of Heroes uses it for. When a villain smashes a mailbox, a cloud of letters goes flying everywhere. Things like that. It really is eye-candy, doesn't improve the game in any majorly meaningful way. Certainly not worth the $150-$200 extra that an Ageia PhysX standalone card would run you.

      Of course, you don't have to have the sepaate card even now to get some of the benefits; the Ageia engine will run in software, too, just not as well. It will be interesting to see what happens when nVidia slaps it into CUDA.

      --
      Editor Emeritus and Senior Writer, TeleRead.org
    11. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      Nitpicking the nitpick: PCI-X was used in one mainstream system: The PowerMac G5.

      The Mac Pro has PCI-E despite the similar-looking case, though.

    12. Re:So, what's actually accelerated here? by LingNoi · · Score: 1

      I confused you with an MMO example. What I am looking at here is consumer grade hardware that allows physics computation but not only for graphics, I want to use physics for much more then just what you can see on the screen.

    13. Re:So, what's actually accelerated here? by Lally+Singh · · Score: 1

      Nope, the eye candy was done b/c it's harder to re-architect games to use more extensive physics in primary gameplay. You have to shove all the physics models into the application code for all that advanced simulation. It's a lot easier to run 10,000 copies of a simple parabolic arc.

      Rigid body physics, constrained motion, etc all take up some decent CPU. As does collision detection. So far, game developers have had to do with simplified collision geometries, simplified models, etc. As a first stab at what you could see with this, consider what they do in Uncharted: Drake's fortune. There's a dedicated SPU for making sure that the hand and foot movements are correct. Consider how much more realistic a game would be if the people moved more like people. If their feet actually touched each step as they went up stairs. If when they run and stop, you see their body shift a bit.

      That sort of stuff could use real physics simulation (for the body's own internal physics). Right now it's basically a single point mass instead of a skeleton with joints, muscles, and mass.

      --
      Care about electronic freedom? Consider donating to the EFF!
    14. Re:So, what's actually accelerated here? by tonywong · · Score: 1

      Bah I just woke up so this may come across clearly.

      The reason why it's only for eye candy at the moment is because developers do not want to fork the gaming experience. Since accelerated physics would create a have and have not situation for gamers, where the non accelerated experience would be too slow to be acceptable, developers choose to only fluff up the eye candy portions because you could not make the game play experience identical between the two.

      This means that you could fork development and have two versions of the game, where the first non accelerated version is significantly less physics rich and has less eye candy than an accelerated one. The big caveat to that is that we live in a networked world, and multiplayer games are big too. This would also create a fundamental incompatibility between the different gaming experiences which means the two versions could not interact.

      That's pretty much the big reason on why physics engine accelerators have been limited to visual eye candy only and not the fundamental games. It's purely a business decision, and one that will get reassessed once the market for physics engines becomes large enough where the developers can safely 'ditch' non accelerated physics systems.

    15. Re:So, what's actually accelerated here? by KillerBob · · Score: 1

      Nitpicking: PCI Express is not PCI-X. PCI-X was a derivative of the parallel PCI bus and never found in mainstream machines.


      Nitpicking your nitpick... it's not worth pointing out that PCI-X is different from PCI Express unless you also point out that PCI Express is usually abbreviated as PCIe or PCI-E.
      --
      If you believe everything you read, you'd better not read. - Japanese proverb
    16. Re:So, what's actually accelerated here? by Khyber · · Score: 1

      Umm, only AGP is essentially one-way. PCI and PCI-E are bidirectional.

      --
      Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
    17. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      It's all MATH and includes the interaction of solid objects (like a box hitting another box. How would that 2nd box move?). It's already all being done by software; Therefore it can ALL be accelerated.

    18. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      >> Umm, only AGP is essentially one-way. PCI and PCI-E are bidirectional.

      It doesn't matter if you're using PCI or PCI-E, he's talking about the graphics pipeline. Its one way, data goes in pixel comes out. Theres a hack that the folding people use but its NOT for real time processing, they're batch processing scientific data and it only works on a few specific GPUs anyway.

      You can get GPGPU cards used for movie special effects but the GP isn't talk about that, he's talking about real time games which has a fixed function pipeline. Any physics that are implemented are going to be part of that fixed function pipeline because that's how graphics cards for gaming works!

    19. Re:So, what's actually accelerated here? by 91degrees · · Score: 1

      Trouble is, some of it doesn't lend itself to acceleration. Two examples are the ultra trivial, and the overly general.

      Ultra trivial - accelerating a single object due to gravity? The maths is quite simple. You add a constant vector to your velocity at constant intervals and add the velocity to your position. This could be done using customer hardware. This would involve sending the acceleration vector (and possible the velocity vector) to the graphics hardware and reading the position back. Fine, but it's probably quicker to do a trivial thing like that on the CPU considering the overhead of setting registers on the hardware.

      Overly general- The reason hardware graphics acceleration gives such an improvement in performance is that you are rendering a lot of pixels in exactly the same way. You can have deep pipelines and massive a parallelism. This isn't the case for all physics operations. If you're testing collisions, you'll want to avoid testing every object against every object. You'll want to split the world into segments and test objects in the same segments against each other. This involves a lot of branching and sets of operations that really don't lend themselves to the parallel processing approach used for rasterisation. You need a general purpose processor to do that. It's illogical to add a general purpose CPU to the one that you already have. You might as well spend the money on a multi-core machine.

    20. Re:So, what's actually accelerated here? by ShotgunNinja · · Score: 1

      Wow. I always told my parents that game developers led the way in the advancement of science. Yup. But that doesn't mean that CS:Source will ever be devoid of porn sprays, campers, and microphone spammers. That's just the price of advancement, I guess.

    21. Re:So, what's actually accelerated here? by sirsnork · · Score: 1

      And just to add to the nitpicking, the PhysX cards were only PCI as far as I ever saw. Maybe they didn't need the bandwidth of anything more, but that always struck me as silly to make a PCI card when PCI-E was already available on new motherboards

      --

      Normal people worry me!
    22. Re:So, what's actually accelerated here? by Anonymous Coward · · Score: 0

      The GeForce 8 series is perfectly capable of being used to accelerate physics calculations and pass the results back to the CPU. The PCI-Express bus is bidirectional, and the scheme for getting results back from calculations done on the GPU is essentially this: encode your inputs as Texture1, set the render target of your program to Texture2, use a shader to calculate the results and "render" them (drawing them to Texture2), and pull Texture2 back to system memory or reuse it for further calculations. I suggest you look into nVidia's CUDA and, for more general information, check out GPGPU.org.

      Note that with CUDA you can avoid many of the headaches induced by "normal" GPGPU programming (ie, the OpenGL/DirectX coding involved in the scheme described above), but you limit yourself solely to the GeForce 8 series, whereas GPGPU programming using GL/DX offers access to a wider range of hardware.

    23. Re:So, what's actually accelerated here? by nomel · · Score: 1

      With multi core cpu's coming out..i still say it's best left to the cpu. I rarely see a game that uses 100% cpu...all cores included.

    24. Re:So, what's actually accelerated here? by fbjon · · Score: 1

      What? So if the world is suitably segmented, with each segment unlikely to affect another, that's a perfect situation for parallel processing! Also, accelerating one box is trivial but 3000 boxes is not, like say, a brick wall falling down.

      --
      True confidence comes not from realising you are as good as your peers, but that your peers are as bad as you are.
    25. Re:So, what's actually accelerated here? by 91degrees · · Score: 1

      What? So if the world is suitably segmented, with each segment unlikely to affect another, that's a perfect situation for parallel processing!

      It's good for a multi-CPU solution. Not so suitable for SIMD type parallelism that graphics cards use though because the datasets for each segment are too different. But this is just the way I'd do it on a normal CPU. Maybe there's a way to do things differently that exploits the hardware.

      Also, accelerating one box is trivial but 3000 boxes is not, like say, a brick wall falling down.

      Indeed. So is this the sort of thing these accelerators do? Are they limited to simple objects in 3D space? Are they just for eye candy or can they help with rigid body physics?

    26. Re:So, what's actually accelerated here? by fbjon · · Score: 1

      Indeed. So is this the sort of thing these accelerators do? Are they limited to simple objects in 3D space? Are they just for eye candy or can they help with rigid body physics? I would assume they're for eye candy, though I don't know for sure, because I've never heard of anyone exploiting a generic physics engine's capabilities for e.g. a flight simulator.
      --
      True confidence comes not from realising you are as good as your peers, but that your peers are as bad as you are.
    27. Re:So, what's actually accelerated here? by CarpetShark · · Score: 1

      Yes, sorry. I do understand why. I just don't always remember. Not entirely my fault, I have to say; the people who design these variations should differentiate them more, instead of trying to borrow popularity from well established technologies.

  10. Re:now that the gpu is doing 2 things lets do 3 !! by Anonymous Coward · · Score: 1, Interesting

    How old are you? Serious question.

  11. Snort! by Anonymous Coward · · Score: 0

    Snot dripping from my snort hole.
    YGBFK

  12. Re:now that the gpu is doing 2 things lets do 3 !! by krilli · · Score: 1

    Who gives a shit how old anyone is? It's an interesting question.

    --
    Jag pratar lite svenska.
  13. I dont quite get it by theskov · · Score: 3, Interesting

    If existing cards can be upgraded thrugh a software patch, NVidia should have been able to do this all along. Are the PhysX people just much better at coding physics, or is there another reason this haven't already been added?

    In other words, did NVidia just buy some clever code?

    1. Re:I dont quite get it by Ristol · · Score: 1

      Not quite. NVidia just bought the rights to use some clever code.

      --
      What wouldn't Jesus do?!
    2. Re:I dont quite get it by RupW · · Score: 1

      In other words, did NVidia just buy some clever code? They also bought existing support from the Unreal 3 engine.

  14. Think of the electric bill! by Anonymous Coward · · Score: 0

    Pfft! The global warming. The electric bill doubling or trippling will put a crimp into this "buy more hardware" plan! No wonder we need alternative lighting. Now we can plow the savings right back into buying more geek gear. Two steps forward. One back.

  15. Re:Hopefully, now PhysX adoption will become bette by montyzooooma · · Score: 3, Interesting

    Isn't the real problem that the games that DO incorporate PhysX hardware support don't really showcase the technology in any carnal desire type manner. There's no equivalent of GLQuake, that drove adoption of the original 3D cards.

  16. Compatible cards by LotsOfPhil · · Score: 2, Interesting

    http://www.nvidia.com/object/cuda_learn_products.html CUDA can run on some pretty cheap cards now.

    --
    This post climbed Mt. Washington.
    1. Re:Compatible cards by p0tat03 · · Score: 1

      The question is... if you're running a cheap card you're probably already pushing the card to its limits in new games, can you afford to give any cycles to PhysX?

  17. Sarbanes-Oxley by kaleco · · Score: 0, Flamebait

    I wonder if we'll see Sarbanes-Oxley invoked here? If not, it will be a significant dent in the legitimacy of Apple's software update charge war-cry.

    --
    Prosperity is only an instrument to be used, not a deity to be worshipped. Calvin Coolidge
    1. Re:Sarbanes-Oxley by Anonymous Coward · · Score: 0

      ... What in the name of Cthulhu are you talking about?

    2. Re:Sarbanes-Oxley by wolrahnaes · · Score: 1

      I am certainly not a lawyer, but here's how I understand the situation:

      GeForce 8 cards have had CUDA support from day one.
      nVidia bought Ageia, and with it all they need involving the PhysX API.
      This upcoming download to enable physics acceleration will be a PhysX-to-CUDA wrapper that is in no way locked down to the Geforce 8 architecture (which is the point of CUDA).

      By my understanding of SarbOx (which admittedly is not great) this falls under the same category as programs being written for an Intel processor. It certainly adds value, but since the ability to program it was in the design from the beginning it shouldn't pose any accounting problems.

      --
      I used to get high on life, but I developed a tolerance. Now I need something stronger.
    3. Re:Sarbanes-Oxley by GregPK · · Score: 2, Funny

      I think it's very forward thinking of NVidia to have incorporated the ability to do this for nearly a year. I'd say its almost game changing.

    4. Re:Sarbanes-Oxley by kaleco · · Score: 1

      Wasn't intended as flamebait. Adding PhysX capabilities to existing products could be seen as adding functionality that people would otherwise have paid for. I mentioned Apple simply because it's the only high-profile example of a company using this rationale for charging for an update. I meant nothing against Apple in general.

      --
      Prosperity is only an instrument to be used, not a deity to be worshipped. Calvin Coolidge
  18. Re:now that the gpu is doing 2 things lets do 3 !! by Anonymous Coward · · Score: 1, Interesting

    Who gives a shit how old anyone is? It's an interesting question. So we can distinguish the immature because-they're-young from the immature for other reasons.

  19. Re:now that the gpu is doing 2 things lets do 3 !! by framauro13 · · Score: 1

    so now that my vid card is processing the 3d graphics and the physics (which is really only eye candy) Switch that statement.
    --
    In an effort to conform with internet communication standards, please note that the above comment is 100% biased opinion
  20. Amen. by Anonymous Coward · · Score: 1, Informative

    I had an ATI card once. The open source drivers (no mode switching) worked better than the binary ones (black screen). And the binary ones complained that, despite buying a card in a box plastered with "RADEON" and the ATI logo, it was not an ATI card, and therefore unsupported. Fuckers.

    I've been a happy owner of NVidia cards ever since.

  21. When will I be able to use my GPU for folding? by siDDis · · Score: 1

    That is all that matters for me, increasing my folding score!

  22. PhysX support GREAT!! by tristian_was_here · · Score: 1, Funny

    Its good to see PhysX support, I know it was worth keeping my limbs rather than selling a arm or leg to make Ghost Recon Advance Warfare 2 to work good.

    1. Re:PhysX support GREAT!! by mollymoo · · Score: 1

      Its good to see PhysX support, I know it was worth keeping my limbs rather than selling a arm or leg to make Ghost Recon Advance Warfare 2 to work good.

      Pity, it looks like you already sold your grammar.

      --
      Chernobyl 'not a wildlife haven' - BBC News
    2. Re:PhysX support GREAT!! by tristian_was_here · · Score: 0

      where I am from we call it "fuck it"

  23. Re:Hopefully, now PhysX adoption will become bette by Cathoderoytube · · Score: 2, Insightful

    One might think reluctance to adopt PhysX would be knowing that a large number of your customers don't use NVIDIA cards and therefore wouldn't be able to take advantage of the technology.
    It's almost the same reason why game companies aren't making their games Vista only.

    --
    I have nothing compelling to say
  24. Re:now that the gpu is doing 2 things lets do 3 !! by Anonymous Coward · · Score: 0

    Hello fellow adult-AC.

  25. Re:Hopefully, now PhysX adoption will become bette by Leonard+Fedorov · · Score: 1

    http://www.steampowered.com/status/survey.html Steam hardware survey (which I think is a fair representation of gamers - the people who use this stuff most) gives nVidia over 50% market share. 8 series is a little over 11% of all graphics cards used. There's already a fairly sizable market - and one that is only going to get bigger.

  26. Re:now that the gpu is doing 2 things lets do 3 !! by edwdig · · Score: 1

    Any physics done on a PhysX card is only eye candy.

    The latency to get the results of the calculations back from the card is high enough that your frame rate would cut in half (or worse) if you waited for the results. So games use it for particle effects, and render the results a frame or two behind. It doesn't matter at all for pure eye candy stuff, but it's just not useful for anything affects gameplay.

  27. Re:Hopefully, now PhysX adoption will become bette by ichigo+2.0 · · Score: 1

    I agree, hardware physics needs a killer app. I was playing around with the idea of adding PhysX support to Quake 2 and modifying some maps to have real liquids instead of the fake water it normally had, but after making some tests apps I realized how incredibly slow the physics are on a CPU. I'm not holding my breath, but I hope the GPU is capable of at least playable frame rates.

  28. Re:Hopefully, now PhysX adoption will become bette by Cathoderoytube · · Score: 1

    I knew as soon as I posed that somebody was going to hit me with some statistics.

    ATI isn't in the throes of death. One assumes that if Nvidia holds 50% of the market some other video card manufacturer probably holds that other 50%. My guess is it would be ATI. Who I'm guessing would make every effort to push back against Nvidia.
    Nvidia still needs to convince more of the bigger studios like id and Valve to use their technology exclusively. Which probably won't happen. Because if they start building engines locked down to one specific card their licensing potential goes way down after that. You basically have to own a specific Nvvida card in order to play the game, as opposed to whatever card you happen to have in your system.

    --
    I have nothing compelling to say
  29. w00t! by Tarlus · · Score: 1

    Thank you, nVidia and Ageia, for saving me from spending $150 on a Physx card! I was very close to buying one, but now I won't have to!

    --
    /* No Comment */
    1. Re:w00t! by ShadowsHawk · · Score: 1

      I just installed a 8600GTS yesterday. Odd timing considering that I've always used ATI until now.

  30. Compositing window managers by tepples · · Score: 1

    3D acceleration itself is not useful for 99.9% of the applications running on these chips, if we include computing activities that are not gaming. Compositing window managers such as Compiz (X11) and Aero DWM (Windows Vista) apply 3D effects to entire windows. That's not gaming, is it?
    1. Re:Compositing window managers by poot_rootbeer · · Score: 1

      Compositing window managers such as Compiz (X11) and Aero DWM (Windows Vista) apply 3D effects to entire windows. That's not gaming, is it?

      No, it's not.

      But neither is it /useful/.

    2. Re:Compositing window managers by fbjon · · Score: 2, Funny

      Not to mention a GUI isn't useful either, since everything can be done on the command line anyway. In fact, all you need is a bank of LEDs to indicate the state of the registers!

      --
      True confidence comes not from realising you are as good as your peers, but that your peers are as bad as you are.
  31. Good thing I just bought a 8600GT :) by Doug52392 · · Score: 1

    This might sound silly, but exactly what does PhysX do? And what would I benefit from having PhysX support on my new card? I know a few games I might want to get that use PhysX (Unreal Tournament 3), would that make those games run faster?

  32. Re:Good thing I just bought a 8600GT :) by DigiShaman · · Score: 1

    If you have a single core CPU, I suspect this will speed up UT3. However, if you have a multi-core CPU, it could be different. One core runs the game, another the PhysX is software, and the video card has all free resources to rendering.

    I have a feeling that benchmarks will reveal nVidia enabled PhysX will SLOW down UT3 framerates.

    --
    Life is not for the lazy.
  33. Re:Hopefully, now PhysX adoption will become bette by Anonymous Coward · · Score: 0

    Stop lying. You haven't done anything of the sort.