Game Devs Only Use PhysX For the Money, Says AMD

arcticstoat writes "AMD has just aimed a shot at Nvidia's PhysX technology, saying that most game developers only implement GPU-accelerated PhysX for the money. AMD's Richard Huddy explained that 'Nvidia creates a marketing deal with a title, and then as part of that marketing deal, they have the right to go in and implement PhysX in the game.' However, he adds that 'the problem with that is obviously that the game developer doesn't actually want it. They're not doing it because they want it; they're doing it because they're paid to do it. So we have a rather artificial situation at the moment where you see PhysX in games, but it isn't because the game developer wants it in there.' AMD is pushing open standards such as OpenCL and DirectCompute as alternatives to PhysX, as these APIs can run on both AMD and Nvidia GPUs. AMD also announced today that it will be giving away free versions of Pixelux's DMM2 physics engine, which now includes Bullet Physics, to some game developers."

Comments

They wish they'd thought of it first

[EvolutionsPeak]

Sounds to me like AMD just wishes they'd thought of it first. There's no reason AMD couldn't offer similar deals.

Re:They wish they'd thought of it first

[hedwards]

But, should they? If a developer doesn't want to use PhysX, they shouldn't. If they're doing it purely for money, then chances are that it's damaging to the industry. Sure physics acceleration is cool for certain types of games, racing games and FPS, but the problem is that developers shouldn't be paid to use technology that isn 't helpful for creating quality games.

Especially if it causes games to be less enjoyable on other hardware platforms. I could see a real problem with this in terms of anti-trust actions.

Re:They wish they'd thought of it first

[jpmorgan]

Suggesting that OpenCL and DirectCompute are alternatives to PhysX is analgous to saying that OpenGL is an alternative to Unreal Engine.

The basic reality here is that four years ago NVIDIA decided invest a lot of money in making GPUs more general purpose, to apply them to more problems than just 3D rendering. ATI didn't care and just focused on making the fastest 3D card possible. Today there are alternatives to NVIDIA's technology, most notably OpenCL... but it's worth remembering that OpenCL is very strongly derived from CUDA. In fact, most of the OpenCL spec looks like they ripped it out of the CUDA spec and changed the function calls from cudaSomething to clSomething.

So yes, open standards are good. But in this case it does smell strongly of sour grapes. ATI made several bad business decisions and have been left playing catchup.

Re:They wish they'd thought of it first

[DragonWriter]

But, should they? If a developer doesn't want to use PhysX, they shouldn't. If they're doing it purely for money, then chances are that it's damaging to the industry. Sure physics acceleration is cool for certain types of games, racing games and FPS, but the problem is that developers shouldn't be paid to use technology that isn't helpful for creating quality games.

The payment could just mitigate the risk associated with bearing the extra cost of adding PhysX to a game when not all of the market can utilize it and there is limited experience with it in the developer community. That doesn't mean its bad for the industry, or bad for the quality of the game.

Especially if it causes games to be less enjoyable on other hardware platforms. I could see a real problem with this in terms of anti-trust actions.

Really? Can you point to any provision of anti-trust law that this would violate?

Re:They wish they'd thought of it first

[Z34107]

It's a difference in scale over Havok. I haven't had much time to play video games lately, but I saw a particularly nifty shot from Arkham Asylum. Shoot a bookshelf without PhysX and it falls over. Shoot it with PhysX and suddenly every individual page from every book flies through the air, each tracing its own path down from the sky.

So, you can do physics in Havok. But not on that scale.

I'd suspect that it's not being used for anything other than "ground clutter" is because you can't design your game around PhysX - not everyone has an NVIDIA card. So, PhysX has to be optional and can't change gameplay - which pretty much relegates it to ground clutter.

Re:They wish they'd thought of it first

[hughJ]

Using a game like Arkham Asylum as a comparison between physx and havok is silly. You've got one physics path that's been specially developed to showcase the strengths of a particular brand of hardware, while the other is left as a compatibility fallback for everything else. That's not an apples to apples comparison. With that same reasoning one could say that ATI has worse anti aliasing than nvidia, simply because the game shipped without support for it for ATI.

Re:They wish they'd thought of it first

[Xrikcus]

Unfortunately from the physics simulations I've been working with I'm pretty sure that what they've done there is simply removed physics activity from the non-accelerated version rather than adding it to the accelerated one. A sneaky way of making GPU-accelerated PhysX look better. I'd be shocked if those book effects wouldn't be just as easy at the same framerate on the CPU unless there are truly ridiculous numbers of books.

Maybe

[Hatta]

I wouldn't be surprised if most game devs wouldn't implement PhysX if not for a subsidy. Only half the market is going to be able to take advantage of it after all. It may not be that they don't want it, just that it's not an economical use of their time otherwise.

Re:Maybe

[hedwards]

If you noticed in the summary, AMD is advocating for a similar technology that works on their hardware as well as on nVidia's, seems like developers would prefer that for practical reasons.

Re:Maybe

[blahplusplus]

"Flying boxes and wood splinters do not make a better game."

But dead guys laying 180 perpendicular off a cliff makes them awesome? Does no one here remember the good old days of early FPS where if you died on the edge of a ledge your body would lay flat over the edge? Does no one remember the time when you hit dead bodies with shots and they didn't move or flail around? What about mass effect 1 the anti-gravity at the end with the geth/dead bodies floating and flailing around, not cool at all?

All that is physics and yes the do make a better game WHEN they are applied to things that need them and not over-used, especially not using physics as a gimmick.

Re:Maybe

[EvilMonkeySlayer]

No, you're thinking of the Furry engine. It offers ultra realistic fur simulation, I hear it's quite popular with the Second Life crowd.

Re:Maybe

[MobyDisk]

Open standards always win out over closed standards. Like OpenGL -vs- DirectX.... oh... wait... :-P

Re:Maybe

[H0p313ss]

Does no one remember the time when you hit dead bodies with shots and they didn't move or flail around?

Not everyone includes "pretty" in their "good game" equation. Doom can still hold it's own against modern games in terms of actual fun.

Clearly you don't get a kick out of shooting dead bodies and seeing them twitch.

What the hell's wrong with you?

Re:Maybe

[ASBands]

I've done some work with both PhysX and the things that AMD is pushing for. I try to keep with the Physics Abstraction Layer, which lets me plug in whatever physics engine as the backend, which gives a pretty damn good apples-to-apples performance metric. Personally, my ultimate choice of physics engine is the one which exhibits the best performance. My experience may differ from others, but I generally get the best performance from PhysX on with an nVidia GPU and BulletPhysics with an AMD GPU. Sometimes, the software version of PhysX outstrips the competition, but I have never seen anything beat PhysX in performance with GPU acceleration turned on. And with PAL, it is easy to check if there is GPU support on the machine and swap in the physics engine with the best performance (PAL is awesome).

Here's the thing: GPU-accelerated physics are just plain faster. Why? Because collision detection is a highly parallelizable problem. Guess what hardware we have that can help? The GPU. Another great part of using the GPU is that it frees the CPU to do more random crap (like AI or parsing the horribly slow scripting language).

AMD is working on both BulletPhysics and Havok so they can do GPU acceleration. But I have a feeling that PhysX performance will remain faster for a while: PhysX was designed to natively run on the GPU (technically, a GPU-like device), while these other libraries are not. Furthermore, nVidia has quite a head start in performance tuning, optimization and simple experience. In five years, that shouldn't matter, but I'm just saying that it will take a while.

So here is my message to AMD: If you want people to use your stuff, make something that works and let me test it out in my applications. You've released a demo of Havok with GPU acceleration. PhysX has been and continues to work with GPU acceleration on nVidia GPUs and will frequently outperform the software implementation. I'm all for open alternatives, but in this case, the open alternatives aren't good enough.

Re:What does PhysX do anyways?

[binarylarry]

duh, it's got what gamers crave!

clutching at straws

[obarthelemy]

GPU makers are in a bind:
- IGP are now enough for 90% of users: office work (even w/ Aero), video, light gaming, dual-screen... all work fine with IGPs
- the remaining 10% (gamers, graphic artists) are dwindling for lack or outstanding games: game publishers are turned off by rampant piracy, mainly online games bring in big money nowadays
- GPGPU is useless except in scientific computing: we already have more x86 cores than the devs know how to use, let alone use a different computing paradigm
- devs have to target the lowest common denominator, which means no GPGPU for games

I'm actually think of moving my home PC to one of the upcoming ARM-based smarttops. They look good enough for torrenting + video watching + web browsing, consume 10 watts instead of 150...

Re:clutching at straws

[Ironhandx]

Tell that to AMD who have sold 2 million directx11 GPUs since release. (http://www.dailytech.com/ATI+Sells+Over+2+Million+DirectX+11+GPUs+Celebrates+With+Radeon+Cake/article17349.htm)

IGP are sufficient for 90% of users... but that hasn't changed since back in the Pentium 1 days. Many PCs were equipped with IGP or something that amounted to the same thing but in card form even then.

Also: GPGPU is NOT meant for gfx processing on the fly at all, so it has absolutely nothing to do with devs having to target the lowest common denominator. You even state that its useless except for scientific purposes in your own comment. The entire purpose of the GPGPU move is towards scientific purposes where vast quantities of repeated calcs have to be done. Something that GPUs excel at.

At least get SOME of your facts straight before spouting FUD.

Re:clutching at straws

[obarthelemy]

There are about 25 million PCs sold per month. I guess ATI is happy to have sold 8% of that monthly amount over the several months their 5xxx have been available, that's 3-4% of PC sales. Congrats to them, but still, fairly marginal.

Discrete cards have always been better than IGPs. I don't really get your point. Only recently (definitely way after the pentium 1) have IGPs become good enough to display all video files, or handle Aero.

PhysX is about making physics computations, not directly putting pixels on screen, so it's a kind of specialized GPGPU.

I think you are confuzled

[Sycraft-fu]

Intel owns Havok (since 2007) and licenses it out all over the place. There's a page that has all the titles using it (http://www.havok.com/index.php?page=available-games) and it is not a small list. Havok also runs on the CPU exclusively (and will probably continue that way since Intel wants to sell quad cores) so works no matter what your graphics card.

It's also not just physics anymore, there's Havok animation libraries and so on.

Re:Is 'Incentivizing' Anti-Competitive?

[KillShill]

Nvidia is very anti-competitive and has been for a very long time.

The recent "making physx stop working when AMD gfx card is present" is just one of the more public outings of their unethical behavior.

I wish someone would expose all of their shenanigans and anti-competitive practices so people can realize how badly these things affect the industry and consumers (ugh, hate that word).

The most recent thing I read about their practices is from the upcoming PC game, Just Cause 2. There's a trailer showing off Nvidia-only effects ...(something which is dead standard DirectX code) and artificially blocking out AMD/others from getting the benefits. The Batman Arkham Asylam scandal was one more people may recall. They claim (and their users/shills) that TWIMTBP is just "marketing"... more like bribery and blocking out the competition. They've been caught on many occasions but the public rarely sees anything negative about them.

Nvidia is the Intel/Microsoft of the video card industry but unlike them, isn't quite as dominant (thankfully for us) but they still do a hell of a lot of damage. (The Jupiter of the computer industry... too small to become a sun but still an 800 quadrillion ton gorilla).

I've stopped buying Nvidia cards since the Geforce 2. At that time for performance reasons but since then I vote with my wallet and let others know to support fair and legal competition.

Best example with the MMORPG UTOPIA

[SharpFang]

A friend told me about his experience with Utopia. It implemented GPU-accelerated physics in one of recent patches. But try hard as you wish, he failed to notice any difference for weeks of gameplay. Until he entered the central city. With flags by the entrance fluttering smoothly in the wind, instead of the old static animation.

Yep, that's it. Many megabytes of a patch, a game of hundreds of miles of terrain, hundreds of locations, battles, vehicles, all that stuff... and physics acceleration is used to flutter flags by the entrance.

Its all Hearsay

[KharmaWidow]

We don't have any proof that developers don't want PhysX. What we have is spokes person from company A saying that no one wants company B's technology. There are no scientifically obtained statistics only one guy's - a competitor - opinion.

Nor did the article state *why* it may be unwanted, or any specific why-nots for using PhysX

Re:It's a new riff on the old joke

[Rob the Bold]

That should read "Says the kid that the dog isn't playing with."With whom the dog is not playing.

Yes, that's something up with which I cannot put.

Open standards, and nothing else

[unity100]

i wouldnt even care if physx was the biggest software innovation of the century - in gaming, especially in regard to graphics, we have suffered a lot because of proprietary shit in the last 2 decades. i dont want to see that again. even if its coarse, inadequate at the start, everyone should push for open standards so that we wont get in deep trouble later.

In my experience, PhysX has only been a hindrance!

[Roger Wilcox]

I have to disable PhysX in the nVidia control panel to get HL2 or any of the Source engine games to run properly! I had no idea what was causing these games to crash. After disabling PhysX they work right every time!

Apparently it doesn't do anything crucial or even noticable as my games run just fine with it turned off. And now I'm told the game devs don't even want to use it?

This "feature" has caused me nothing but grief!