- Jun 21, 2005
- 11,864
- 2,066
- 126
So basically they're saying they'll never support GPU-accelerated physics except in cases with extremely low/undemanding resolutions and games.FUD blurb
Sources close to AMD's Physics department have told us that AMD plans to introduce Havok on GPU only when this ends up being faster than Physics on a GPU.
ExtremeTech Interview
So what is AMD/ATI's take on all this? I spoke with Senior PR manager Rob Keosheyan at AMD, and he had plenty to say about the situation. Open industry standards are extremely important to AMD as a company, and they feel that GP-GPU work should be no different. It's working hard only on its own StreamSDK and Brook+, but with the Kronos group on OpenCL, where it sees the real future.
If open standards are so important, why partner with Havok for physics work? That technology is far from open; it's owned by Intel, the other chief competitor of AMD/ATI. Of course, there are no truly open physics middleware solutions on the market with any traction, so that point might be kind of moot.
Keosheyan says, "We chose Havok for a couple of reasons. One, we feel Havok's technology is superior. Two, they have demonstrated that they'll be very open and collaborative with us, working together with us to provide great solutions. It really is a case of a company acting very indepently from their parent company. Three, today on PCs physics almost always runs on the CPU, and we need to make sure that's an optimal solution first." Nvidia, he says, has not shown that they would be an open and truly collaborative partner when it comes to PhsyX. The same goes for CUDA, for that matter.
Though he admits and agrees that they haven't called up Nvidia on the phone to talk about supporting PhysX and CUDA, he says there are lots of opportunities for the companies to interact in this industry and Nvidia hasn't exactly been very welcoming.
To sum up, Keosheyan assures us that he's very much aware that the GP-GPU market is moving fast, and he thinks that's great. AMD/ATI is moving fast, too. He knows that gamers want GPU physics and GP-GPU apps, but "we're devoted to doing it the right way, not just the fast way."
So it sounds like support for CUDA or PhysX on ATI graphics cards just isn't going to happen unless Nvidia picks up the phone first and offers an olive branch, or there is an overwhelming demand from ATI's customers.
ExtremeTech Interview
Many have thought that CUDA is proprietary, and will only ever work on Nvidia's GPUs. This is not entirely true.
Though it has been submitted to no outside standards body, it is in fact completely free to download the specs and write CUDA apps, and even completely free to write a CUDA driver to allow your company's hardware (CPU, GPU, whatever) to run apps written in the CUDA environment.
Nvidia "owns" and controls the future of CUDA, so it's not open in the "open source" definition, but it's certainly free. Nvidia tells us it would be thrilled for ATI to develop a CUDA driver for their GPUs.
But what about PhysX? Nvidia claims they would be happy for ATI to adopt PhysX support on Radeons. To do so would require ATI to build a CUDA driver, with the benefit that of course other CUDA apps would run on Radeons as well. ATI would also be required to license PhysX in order to hardware accelerate it, of course, but Nvidia maintains that the licensing terms are extremely reasonable?it would work out to less than pennies per GPU shipped.
I spoke with Roy Taylor, Nvidia's VP of Content Business Development, and he says his phone hasn't even rung to discuss the issue. "If Richard Huddy wants to call me up, that's a call I'd love to take," he said.
Originally posted by: apoppin
AMD evidently was working on their own proprietary version of physics to run on their GPUs since '05. That is what the CrossfireX was supposed to have brought; a more "two-way" communication between CPU and GPU for Physics. However, it appears that it may not have worked out so well [evidently], so they went to Intel's company - Havok - to develop Physics for both CPU and GPU.
It is very clear AMD wants to do Physics on their GPUs [and CPUs] using Havok and would rather die - go to intel and beg - then use 'Nvidia Anything' for PhysX or CUDA. I think that is just their corporate philosophy and now we are left with two *competing* solutions:
1. Intel and AMD supporting Havok for CPU and later GPU
and
2. Nvidia supporting PhysX
So the question remains ... who will win?
i say we wait and see .. it is impossible to predict right now, imo
- frankly i am looking forward to D/Ling the Nvidia pack and trying out Warmonger and the extra maps and demos. Then i want to see what AMD can do.
i think it will be at least a couple of years before either solution becomes a fixture in most games.
I don't think there's any doubt it would be in consumer's best interests to have 100% of discrete GPU makers behind a single standard to increase adoption rate of GPU-accelerated PhysX, but at the same time I think NV has the market share and dollars to make it work regardless whether AMD participates. Again, with a claimed 70 million GF 8 and 9 series parts and a dominant 2:1 market share in discrete GPUs, NV already has a greater installed user-base relative to other popular check-box features like EAX and DX10. AMD clearly has more to lose here if they choose to do nothing, as they're doing now.Originally posted by: nitromullet
From Chizow's posts, it sounds to me like AMD and NV both sort of need each other on this one and they would both benefit from being able to run PhysX/CUDA on NV and ATI GPUs, but neither wants to pick of the phone...
Originally posted by: apoppin
It is very clear AMD wants to do Physics on their GPUs [and CPUs] using Havok and would rather die - go to intel and beg - then use 'Nvidia Anything' for PhysX or CUDA. I think that is just their corporate philosophy and now we are left with two *competing* solutions:
1. Intel and AMD supporting Havok for CPU and later GPU
and
2. Nvidia supporting PhysX
So the question remains ... who will win?
i say we wait and see .. it is impossible to predict right now, imo
- frankly i am looking forward to D/Ling the Nvidia pack and trying out Warmonger and the extra maps and demos. Then i want to see what AMD can do.
i think it will be at least a couple of years before either solution becomes a fixture in most games.
Originally posted by: nitromullet
edit: honestly, based on how game development works these days where you have most studios developing games for the Xbox 360, PS2, and PC simultaneously, I don't think ATI, NV, Intel, or anyone on the PC side of things are going to decide who wins the physics wars. I think it's going to be a console company like Sony or Microsoft who nudges game devs in a certain direction by implementing a physics solution based on whatever API they choose in their next gen console.