Slashdot Mirror


NVidia Cripples PhysX "Open" API

An anonymous reader writes "In a foot-meet-bullet type move, NVidia is going to disable PhysX engine if you are using a display adapter other than one that came from their company. This despite the fact that you may have an NVidia card on your system specifically to do this type of processing. 'For a variety of reasons some development expense, some quality assurance and some business reasons Nvidia will not support GPU accelerated PhysX with Nvidia GPUs while GPU rendering is happening on non-Nvidia GPUs.' Time to say hello to Microsoft dx physics or Intel's Havok engine."

47 of 393 comments (clear)

  1. Havok by sopssa · · Score: 4, Insightful

    Havok is a better engine anyway.

    But that's the problem with corporate buyings anyway. Even if its kinda wrong to stop supporting the other platforms, they have every right to do so.

    1. Re:Havok by negRo_slim · · Score: 3, Insightful

      Havok is a better engine anyway.

      That may be the case but in the end we'll more than likely see corporate drama surrounding that effort as well.
      I hate to say it but I think a DirectX option is the lesser of three evils.

      --
      On the Oregon Cost born and raised, On the beach is where I spent most of my days
    2. Re:Havok by Kratisto · · Score: 5, Funny

      That's a new record for a Microsoft product. Lesser of two evils? Okay, occasionally. But a lesser of three!? There's hope for them yet!

      --
      Conscience is the inner voice which warns us that someone may be looking.
    3. Re:Havok by Sinan+H · · Score: 3, Insightful

      No. Bullet Physics and OpenCL is the answer to this problem. Not a closed standard like DirectCompute that you can only use on Windows. Havok will use Larrabee, PhysX uses CUDA, however they will all eventually use OpenCL eventually. Although Bullet Physics can be ported to Larrabee, CUDA (already demos exists), support for OpenCL is the right way to go.

    4. Re:Havok by interval1066 · · Score: 3, Insightful

      @sopssa: "Havok is a better engine anyway."

      By saying that in the context of this article you're implying that Havoc is a more open, less ip/license/business relationship-constrained option, and I don't think that's true. If Intel wants to exert its rights over the technology in the same way we're right back to the same situation with PhysX; Havoc may be better technically but its worthless if no one can get their hands on it.

      --
      Python: 'And then suddenly you have a language which says "we're all stuck with whatever the whiniest coder wants".'
    5. Re:Havok by DJRumpy · · Score: 4, Insightful

      Doesn't one normally wait until they have a good market for a product before they try to lock people in? This will only drive people to an engine that is more widely supported, or to an open standard that does the same thing. I understand the business reason, but it seems silly to show all your cards this early in the game.

    6. Re:Havok by hairyfeet · · Score: 4, Insightful

      Well I can say that Nvidia acting like dicks is what switched me to go full AMD on my newest PCs, along with Intel acting like asses over virtualization on only certain CPUs got me to switch over to AMD for my customers as well. The new quads are more than powerful enough for the average Joe, and after being burnt on the 5xxx series, followed by a couple of my customers getting burnt on the bad solder BS (and Nvidia acting like dicks instead of manning up to their mistakes) made it not very hard to just switch.

      I've found the new AMD boards have great graphics out of the box, and for those that need more the 4xxx series are affordable and don't need an AC unit to cool the thing. This burning everyone with PhysiX just is the icing on the stupidity cake. I just wonder how much of Nvidia acting like dicks comes back to getting burnt on the solder? Plus with Intel and AMD having their own GPU solutions Nvidia is looking more and more like the odd man odd. It may be just me but this smells like a desperate move to try and get some lock in going. Considering how nice and affordable the new ATI cards are I wonder how much luck they are gonna have in this climate. Only time will tell I suppose. Oh well, as long as stuff blows up real good I don't care if every piece of debris lands in the correct spot anyway.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    7. Re:Havok by V!NCENT · · Score: 4, Interesting

      Yeah it really sucks that some major vendors work together to deliver you a platform inde-fscking-pendant solution that speeds up your computer at no extra freaking costs, patents and other crap. What hidden agenda are you pushing?

      --
      Here be signatures
    8. Re:Havok by jpmorgan · · Score: 3, Insightful

      25%? Really? There are two possible usage scenarios they've killed:

      1. An onboard NVIDIA device with a discrete ATI graphics card. From what I've heard, PhysX running on integrated devices isn't any faster than running on the CPU in software mode, so nothing has been lost. So no target market has been lost there.

      2. Having both a discrete ATI graphics card, and an unused GeForce 8000+ or Tesla. That is a pretty fucking weird configuration. I can't see that being more than a tenth of a percent of gamers. I've personally never encountered someone who runs both.

      Mountain. Molehill.

    9. Re:Havok by electrosoccertux · · Score: 4, Insightful

      Havok and the DX Physics are completely open and either party can use them, no proprietary api or licensing or anything silly. No hardware vendor controls what happens.

      PhysX is not. It is controlled by Nvidia. Gosh, they wouldn't have financial motives to abuse this power would they? No of course not...

      Nvidia lately seems to have been getting around the whole market segmentation issue by ... paying off forum members in all the hot PC Hardware forums? Lately my favorite has been inundated with troll and fanboy posts proclaiming the wonders of PhysX (still waiting for a game where it actually adds anything) and the death of AMD/ATi.

    10. Re:Havok by azior · · Score: 5, Funny

      That's a new record for a Microsoft product. Lesser of two evils? Okay, occasionally. But a lesser of three!? There's hope for them yet!

      Microsoft <3

      you mean like this?

    11. Re:Havok by Fantom42 · · Score: 4, Funny

      That's a new record for a Microsoft product. Lesser of two evils? Okay, occasionally. But a lesser of three!? There's hope for them yet!

      .

      Microsoft <3

      you mean like this?

      .

      Close, but more like this: Microsoft <3 Evil. *

  2. Anti-trust? by headkase · · Score: 5, Interesting

    Why is this not anti-trust? When you paid for the nVidia card to put into your machine why should its functions depend on whether or not a competitors hardware is present? What if Windows said uh-oh you have Linux installed on another partition, disabling Windows...

    --
    Shh.
    1. Re:Anti-trust? by MozeeToby · · Score: 3, Insightful

      Worse than that even, this is using your strength in one industry segment (physics acceleration) to support sales of an arguably different segment (graphics acceleration).

    2. Re:Anti-trust? by mcrbids · · Score: 4, Informative

      Worse than that even, this is using your strength in one industry segment (physics acceleration) to support sales of an arguably different segment (graphics acceleration).

      Which is nasty and unethical to be sure, but it's not illegal unless it can be legally shown that Nvidia is a monopoly. It's amazing to me how many slashbots don't understand this distinction.

      I'm pissed at ATI for dropping binary support for FGLRX for Linux kernels later than 2.6.29, and was considering getting an Nvidia GPU in my next laptop, but now it looks an awful lot like Intel is getting my $50....

      --
      I have no problem with your religion until you decide it's reason to deprive others of the truth.
    3. Re:Anti-trust? by Joce640k · · Score: 4, Insightful

      This phrase "anti-trust", I don't think it means what you think it means.

      How are they leveraging a monopoly to gain unfair advantage in a marketplace?

      To me it seems more like NVIDIA has finally realized that they *can't* use it to gain unfair advantage so they're dumping it.

      --
      No sig today...
    4. Re:Anti-trust? by Moryath · · Score: 3, Interesting

      I gave up on Nvidia when they screwed over my 3D glasses setup; I'd gone through all the trouble of maintaining my rig with an NVidia graphics card, because their occasional driver updates for the stereoscopic driver still made my old VRStandard rig (coupled with a 120Hz-capable CRT) run well.

      Lo and behold, their latest set "only" works either with the Nvidia-branded "Geforce 3D Vision" glasses and a short-list of extra-expensive "approved" 120-Hz LCD's, or else red/blue anaglyph setups. No reason for them to cut off older shutter glasses setups except to force people to buy their new setup if they wanted to continue to have stereoscopic 3D.

      So add the PhysX thing in and we can chalk up two strikes for Nvidia. My new card when I updated my computer this summer was an ATi (no point wasting the $$$ on a Nvidia). One more strike and I won't bother going back to them ever. Boy am I glad I didn't buy that second-hand PCI PhysX board the other day...

    5. Re:Anti-trust? by Lonewolf666 · · Score: 3, Informative

      Getting a bit off topic, but I like the direction ATI is taking recently with Open Source. Long term, I think they will be the better choice for Linux.
      In a recent test at Phoronix (http://www.phoronix.com/scan.php?page=article&item=amd_r600_r700_2d&num=1) the OS driver already offered better 2D performance over the binary one :-)

      --
      C - the footgun of programming languages
    6. Re:Anti-trust? by PitaBred · · Score: 3, Informative

      fglrx has always sucked. Why not look at an ATI card because their open-source driver is really maturing? It's OpenGL 1.4, and all recent cards should be supported in Ubuntu 10.04. My Radeon 4670 is already supported in the Fedora Core 12 betas (or are they alphas? I can never remember). ATI's open-source drivers are currently supporting Doom3, OpenArena, Nexuiz... lots of stuff. And they're playing the game with Intel, doing the acceleration the right way, instead of replacing most of the graphics stack with their own binary module like Nvidia does.

    7. Re:Anti-trust? by Lonewolf666 · · Score: 4, Informative

      Read the f... Phoronix article ;-)

      Yes, it seems the binary is really crappy in this case and the OSS driver at least passable. Although I'm not familiar with those benchmarks and how they measure up against similar software on Windows.
      3D still seems to lag behind, otherwise we could officially forget the Catalyst driver and use the OSS driver exclusively for Linux. But I think we'll get there.

      --
      C - the footgun of programming languages
  3. Truth by DoofusOfDeath · · Score: 4, Funny

    'For a variety of reasons some development expense, some quality assurance and some business reasons Nvidia will not support GPU accelerated PhysX with Nvidia GPUs while GPU rendering is happening on non-Nvidia GPUs.'

    At least he was 33.3% truthful.

  4. But... by nicc777 · · Score: 5, Funny

    ...will it my $TERM faster?

    --
    Need an ISP in South Africa?
    1. Re:But... by Anonymous Coward · · Score: 5, Funny

      I think you accidentally the verb.

  5. Good luck with that by Flowstone · · Score: 5, Insightful

    First they scoop up PhysX and try to create a market for PPUs. Now the only way PhysX is ever going to get any use is out of pure coincidence. Not the smartest move for Nvidia to make when Ati/AMD is on their heels with a new line of cards.

    1. Re:Good luck with that by PhrostyMcByte · · Score: 4, Informative

      An OpenCL implementation of Bullet physics is coming. It's Open Source and is already being used in commercial games -- once it gets GPU acceleration there will probably be little demand for PhysX.

  6. Re:Can someone explain this more clearly? by cheesybagel · · Score: 4, Informative

    It is no standard. PhysX was an API made by a company (Ageia) who wanted to cell physics acceleration cards. Their cards never sold well, but the free beer software libraries were used by a number of people (the libraries supported CPU execution as well). Then NVIDIA bought them and ported the thing to run on their GPUs. So I see this ending up like the 3Dfx Glide API for 3D graphics - some historic games used it, such as Mechwarrior, but no one uses it anymore.

  7. Closing the Architecture by headkase · · Score: 3, Insightful

    Heres some thoughts on the meaning of this. The PC is an open-architecture, you are free to put whatever you want into your machine. If nVidia can dictate what their hardware works with then they are effectively creating a "nVidia-Approved" list of hardware. First step down the slippery slope of closing the PC's openness. In the software world an equivalent would be Windows refusing to connect to network shares that were based off of Samba or the other way around a Windows box refusing connections from Linux machines. Standards apply to hardware as well as software and if any manufacturer gets away with an "approved" list then the platform as a whole will eventually suffer for it.

    --
    Shh.
    1. Re:Closing the Architecture by Ant+P. · · Score: 4, Informative

      OpenGL3 is the first time that companies are breaking away from windows.

      It seems like OpenAL was the first. Creative have been visibly pushing it now that Vista's forced-software-only sound API has made their sound cards pointless.

    2. Re:Closing the Architecture by Joe+U · · Score: 4, Insightful

      MS pulled a smackdown on Creative. Creative cards (and drivers, especially drivers! [FU creative]) have been sucking for years.

      So, new OS comes out and MS removes all the hooks that 3rd parties have been putting into the Windows sound system, instantly leveling the playing field and removing a major source of Windows instability.

      One of the few times MS really did the right thing.

  8. oh well by poetmatt · · Score: 4, Informative

    physx seemed nice until they tried to close source it. Does Nvidia have anything left this round? Bad Yields, physx being stupid and abusive when disabled (it only uses 1 cpu core when on AMD for example instead of even all threads). Not to mention their crippling of batman as well.

    So what's left for Nvidia? I don't see a whole lot.

  9. Re:Can someone explain this more clearly? by Unit3 · · Score: 4, Informative

    No. The framework would only run on their GPUs. However, you could have one of their cards in the system to do purely physics calculations, and then use a competitor's card to do the actual display and 3d rendering. They've now disabled this, so if your monitors are connected to, say, and ATI card, you can no longer use the Nvidia card in your system for physics processing.

    Before you discount this as an unlikely scenario, consider motherboards with onboard NVidia chipsets. These are usually underpowered for full time duty, but are perfectly suited to being used for physics calculations while a more powerful ATI card in the PCI-E slot does the graphics rendering. This is actually a fairly likely setup these days, and NVidia has just said they're going to block it.

    Personally, I agree with others who have pointed out this must be an anti-trust issue. Intel and Microsoft have both been fined heavily recently for doing exactly this kind of anti-competitive behaviour.

    --
    -- sudo.ca
  10. Proprietary APIs by Adrian+Lopez · · Score: 3, Interesting

    I'm currently avoiding PhysX due to the fact that the license requires that credit be given to nVidia/PhysX in any advertisement that mentions the advertised product's physics capabilities. It's a real shame, because I hear that PhysX has pretty robust physics implementation.

    The current state of physics acceleration reminds me of the days when hardware-accelerated 3D graphics (except for high-end OpenGL stuff) were only supported through manufacturer-specific APIs. Hopefully, DirectX physics will be good enough that PhysX will ultimately become mostly irrelevant to game developers -- I'm just not convinced that Microsoft can pull it off.

    --
    "In prison you just have to shut your eyes and take it. Here you have to shut your eyes and give it."
  11. Soon irrelevant anyway by perrin · · Score: 4, Insightful

    Once the big game engines and physics libraries get generic support for GPU programming through OpenCL, this will all be pretty moot anyway. From what I can tell, the bullet physics library is already developing this, and I am sure closed source competitors are doing that as well. Relying on anything that will only run on a single vendor's hardware is just a losing business proposition (unless that vendor pays you for it, which I guess is how PhysX got going).

  12. Bullet Physics for the Win! by BitZtream · · Score: 4, Informative

    http://www.bulletphysics.com/

    I don't have any affiliation with the project other than I've used it in my homegrown game engine that has never left my hard drive. It is however rather easy to use. When I was looking for a physics engine, Bullet turned out to be the best license, code base, and documentation set out there for no cost.

    --
    Persistent Volume manager for Kubernetes - https://github.com/dwimsey/openshift-pvmanager
  13. Re:Key word: "reportedly" by The+Moof · · Score: 5, Informative

    From the NVIDIA PhysX FAQ:

    Can I use an NVIDIA GPU as a PhysX processor and a non-NVIDIA GPU for regular display graphics?
    No. There are multiple technical connections between PhysX processing and graphics that require tight collaboration between the two technologies. To deliver a good experience for users, NVIDIA PhysX technology has been fully verified and enabled using only NVIDIA GPUs for graphics.

  14. THIS JUST IN! by Tanman · · Score: 3, Funny

    Nvidia releases announcement that they will no longer provide free driver support to ATI for interaction between Nvidia hardware and ATI competing hardware. Notes that software APIs are available for ATI to pay for and release their own damn drivers.

    NEWS AT 11!!!

  15. Re:Can someone explain this more clearly? by BitZtream · · Score: 5, Insightful

    Its anti-consumer, but that doesn't trigger an anti-trust charge, they don't have a monopoly.

    Why does everyone scream like its illegal when a company does something they don't like? Unless they are king of the hill and using their powers to force others into capitulating with them, its not an issue for the courts. You don't have to buy nVidia. You don't have to use PhysX. You don't have to buy a Voodoo 3 card. Sure a game may only support one of the above, but thats not something that justifies going after nVidia unless they owned the market.

    --
    Persistent Volume manager for Kubernetes - https://github.com/dwimsey/openshift-pvmanager
  16. Re:Can someone explain this more clearly? by Old97 · · Score: 3, Informative

    Microsoft and Intel are monopolies. Nvidia is not. You also can't designate a company as a monopoly by narrowly defining some market niche either. Barriers to entry for the market in question are also a consideration. It's not an issue here. If you are not a monopoly than you can engage in a broader set of behaviors. What got Microsoft in trouble is that they continued their anti-competitive behavior after they gained their monopoly and attempted to leverage their existing monopoly to gain unfair advantages in other markets, i.e. web browsers. If Apple had done that it would have been perfectly legal because they don't have a monopoly. If Microsoft had not had a monopoly what they did to Netscape would have been legal.

    --
    Very often, people confuse simple with simplistic. The nuance is lost on most. - Clement Mok
  17. Re:Can someone explain this more clearly? by smoker2 · · Score: 4, Insightful

    How can it be anti-trust if (a) they aren't a monopoly, and (b) they are disabling their own hardware ?

    If they caused the ATI card to not function then I could understand it, but a secondary function on their own card ?

  18. You recommend against proprietary APIs and yet.. by Junta · · Score: 3, Insightful

    You express a desire for an API from Microsoft to become dominant?

    --
    XML is like violence. If it doesn't solve the problem, use more.
  19. Re:CRT? Are you from the past? by HeronBlademaster · · Score: 3, Insightful

    No, but you can't blame a company for not wanting to support outdated technology.

    That's like complaining that Microsoft won't release security updates for Windows 98. Sure, some people are still using it, and it might work perfectly well for them, but that doesn't mean MS is evil for not patching it.

  20. Re:Can someone explain this more clearly? by afidel · · Score: 3, Informative

    No, the framework also has a software renderer and on many cards you get significantly better overall game performance by using it (I know this is true for my 9600 GSO 384, I got an ~22% FPS boost by uninstalling the driver component for PhysX and using the software renderer). The software renderer is also significantly less likely to crash your system. So unless you have a slow CPU with a monster GPU and are willing to accept more crashes there's really not a lot of reason to use the GPU tied renderer.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  21. Re:CRT? Are you from the past? by OrangeTide · · Score: 5, Insightful

    What about a CRT is outdated? It has better black levels, faster refresh, and higher brightness than an LCD. It's analog but good cabling will still result in a crystal clear image. I think the primary disadvantages of CRTs is that widescreen is so costly as to be impractical. They are heavy. And they suck a lot of power. but in terms of image quality a CRT is still extremely good.

    CRTs are "outdated" because businesses want to sell LCDs. Flat and light is sexy. And LCDs sold like crazy back when the image quality was dramatically inferior to a CRT, and it took them years to catch up.

    CRT technology is not obsolete, but the marketing of CRTs is dead. If you want to argue that we should use technology based on marketability alone, be my guest. I suspect most slashdotters will rip into you pretty brutally.

    --
    “Common sense is not so common.” — Voltaire
  22. Re:CRT? Are you from the past? by Moryath · · Score: 5, Informative

    They didn't drop support for "CRT's". They decided that their stereographics driver would only work in the following configurations:

    - anaglyph glasses with a "whatever" monitor (horrible color distortion and headache-inducing ghosting ensues).

    - *THEIR* shutter glasses, with *THEIR* overpriced "partnered" LCD monitors.

    Now, what is the difference (tech-wise) between their shutter glasses and mine? Only the fact that theirs send a specific "yes I'm nvidia" signal back to the card. What is the capability difference between their overpriced "partnered" LCD monitors and my 120Hz-capable CRT? Two things: Jack and Shit.

    This is not about "dropping support for outdated technology." Prior to what they pulled, I could plug in an industry-standard shutter glasses set made by any of a number of manufacturers, combine them with any monitor capable of 120-Hz refresh (whether CRT, LCD, certain televisions, or even a few projector models), and enjoy stereoscopic gaming. After their "update" to the drivers and subsequent "update" to the stereoscopic drivers, the Nvidia cards would only recognize *THEIR* proprietary glasses (which again, hardware-wise are no different than the old type save for sending a "hi I'm from nvidia" signal to the card) and would only interoperate with a precious few "specially chosen" 120Hz LCD's.

    This had nothing to do with "dropping support" for "obsolete equipment" (which wasn't in any way, shape, or form) and everything to do with trying to milk people for $500+ on a new rig by forcibly crippling industry-standard hardware.

  23. Re:Can someone explain this more clearly? by shutdown+-p+now · · Score: 4, Informative

    Its anti-consumer, but that doesn't trigger an anti-trust charge, they don't have a monopoly.

    The perpetrator doesn't have to have a monopoly for tying to be illegal - in U.S., for example, you only need "sufficient market power" to affect "not insubstantial amount of interstate commerce in the tied product market". I dare say that NVidia has pretty damn substantial market power in GPU niche, and it is quite likely to affect sales of all other GPUs in a significant way. In the end, of course, it's up to the courts to decide, if it comes to that, but the allegation is not without merit.

  24. Re:[Citation Needed] by maxume · · Score: 3, Insightful

    He doesn't care if they are on the up and up, he cares that they (from his point of view) arbitrarily removed functionality, that, for all he could tell, was working just fine. They don't have to be dishonest to make stupid decisions that make them worth avoiding as a supplier.

    --
    Nerd rage is the funniest rage.
  25. Re:CRT? Are you from the past? by earnest+murderer · · Score: 4, Insightful

    That was a ridiculous thing to post.

    A CRT doesn't need support, it needs to not be sabotaged.
    His glasses don't need support, they need to not be sabotaged.

    Not supporting both of them takes more effort than ignoring them.

    Competent support of all that hardware would take less space in code than this comment window is high. Going to the trouble to restrict it was much more... *after* the meetings, licenses, and money exchanges had all taken place.

    The cynic in me believes that someone with a debugger is probably a single (or two) flipped bit(s) away from a working setup.

    --
    Platform advocacy is like choosing a favorite severely developmentally disabled child.