4850/70 vs PhysX Support

geoffry

Senior member
Sep 3, 2007
599
0
76
So I'm thinking of selling my 8800 and crossfiring some 4850s or 4870s given the nice reviews, BUT with NVDA owning Ageia and supposedly lots of devs supporting PhysX and games using the CUDA based PhysX coming out as soon as late this year, wouldn't the lack of CUDA support hurt the ATI cards in this scenario?

Are the devs going to have to choose PhysX vs Havok? And an INTC / AMD friendly dev will use Havok and an NVDA friendly dev will use PhysX, leaving ATI card holders in the cold for realistic physics...

Maybe some of you know more about this than me, I know nothing is for certain because nothing using GPU based physics processing is out yet but perhaps some rumours/dev talk is out there that I'm not aware of.
 

Nathelion

Senior member
Jan 30, 2006
697
1
0
AMD is going to be supporting Havoc on their cards. But yeah, I'm guessing that developers are going to have to choose between the two, to the detriment of hardware physics...
 

tuteja1986

Diamond Member
Jun 1, 2005
3,676
0
0
I think Microsoft just need release a Physic API to end the war. Then Both Nvidia and ATI will support it :! PX 1.0 any one.
 

geoffry

Senior member
Sep 3, 2007
599
0
76
Originally posted by: tuteja1986
I think Microsoft just need release a Physic API to end the war. Then Both Nvidia and ATI will support it :! PX 1.0 any one.

Agreed, an industry standard would definitely be beneficial.
 

thilanliyan

Lifer
Jun 21, 2005
11,868
2,075
126
Originally posted by: geoffry
So I'm thinking of selling my 8800 and crossfiring some 4850s or 4870s given the nice reviews, BUT with NVDA owning Ageia and supposedly lots of devs supporting PhysX and games using the CUDA based PhysX coming out as soon as late this year, wouldn't the lack of CUDA support hurt the ATI cards in this scenario?

Are the devs going to have to choose PhysX vs Havok? And an INTC / AMD friendly dev will use Havok and an NVDA friendly dev will use PhysX, leaving ATI card holders in the cold for realistic physics...

Maybe some of you know more about this than me, I know nothing is for certain because nothing using GPU based physics processing is out yet but perhaps some rumours/dev talk is out there that I'm not aware of.

I would put more emphasis on performance/price than PhysX support. There were supposed to be lots of games that used it by now but there weren't that many popular titles I think. Plus, when there was support it degraded performance which will still be the case since instead of dedicating all resources to graphics rendering the video card will now have to do physics as well.

Hopefully there will be a separate Cuda PhysX driver from nVidia because then my plan will be to use my current 8800GT as the Physics card and I'll use a 4850/4870 as the GPU.
 

Wreckem

Diamond Member
Sep 23, 2006
9,458
987
126
Originally posted by: thilan29
Originally posted by: geoffry
So I'm thinking of selling my 8800 and crossfiring some 4850s or 4870s given the nice reviews, BUT with NVDA owning Ageia and supposedly lots of devs supporting PhysX and games using the CUDA based PhysX coming out as soon as late this year, wouldn't the lack of CUDA support hurt the ATI cards in this scenario?

Are the devs going to have to choose PhysX vs Havok? And an INTC / AMD friendly dev will use Havok and an NVDA friendly dev will use PhysX, leaving ATI card holders in the cold for realistic physics...

Maybe some of you know more about this than me, I know nothing is for certain because nothing using GPU based physics processing is out yet but perhaps some rumours/dev talk is out there that I'm not aware of.

I would put more emphasis on performance/price than PhysX support. There were supposed to be lots of games that used it by now but there weren't that many popular titles I think. Plus, when there was support it degraded performance which will still be the case since instead of dedicating all resources to graphics rendering the video card will now have to do physics as well.

Hopefully there will be a separate Cuda PhysX driver from nVidia because then my plan will be to use my current 8800GT as the Physics card and I'll use a 4850/4870 as the GPU.

There havent been many games because there hasnt been people with that capability to run it until the large install base Nvidia has created as of late.

 

Piuc2020

Golden Member
Nov 4, 2005
1,716
0
0
ATI adopted Havok but NV offered PhysX so if in the future Havok dies and PhysX becomes the standard, ATI can go along with it, NV doesn't have a deadlock on PhysX.

I may be on something here but didn't ATI adopt CUDA?
 

Sylvanas

Diamond Member
Jan 20, 2004
3,752
0
0
With PhysX enabled games we saw little to no improvement over no Physx- it's not something you should be holding out for. DX11 is expected to bring a new Physics standard which everyone will support (remember Intel will be entering soon aswell) in which case Physx will be tossed to the wayside once again. I don't see the big song and dance over CUDA, it's Nvidia marketing all the way AMD has it's own proprietary API it's just they don't make a big song and dance about it.
 

ViRGE

Elite Member, Moderator Emeritus
Oct 9, 1999
31,516
167
106
Originally posted by: Nathelion
AMD is going to be supporting Havoc on their cards. But yeah, I'm guessing that developers are going to have to choose between the two, to the detriment of hardware physics...
Just so we're clear, no such thing has been annouced. There was a nebulous press release about Havok and AMD working together but it was focused on the CPU side, the GPU side only got a single sentence. Nothing has even been rumored yet, never mind confirmed, nor would I honestly expect something.

As for the matter at hand, PhysX is a license/royalty free standard, AMD could support it any time they wanted to if they wanted to write a driver for it in Brook+ (or if they're sadistic, CAL) for their GPUs. Not that they'll do it, but either way they're going to have to write a physics driver, either for PhysX or for the mythical DirectPhysics.
 

ViRGE

Elite Member, Moderator Emeritus
Oct 9, 1999
31,516
167
106
Originally posted by: Sylvanas
With PhysX enabled games we saw little to no improvement over no Physx- it's not something you should be holding out for. DX11 is expected to bring a new Physics standard which everyone will support (remember Intel will be entering soon aswell) in which case Physx will be tossed to the wayside once again. I don't see the big song and dance over CUDA, it's Nvidia marketing all the way AMD has it's own proprietary API it's just they don't make a big song and dance about it.
To be frank, AMD's initiative is rather poor at the moment. They don't really have a strong stream computing initiative, it mostly comes off as opposing NVIDIA for the sake of it.

Hardware: NVIDIA has a whole line of Tesla products raging from cards to rackmounts, and numerous vendors to work with. AMD has just single cards, and I haven't seen any of their vendors put together more exotic setups beyond stuffing a few cards in a desktop. The rackmount thing is a really big deal, it's what the big (read: high paying) shops are using since they're doing everything in bulk.

High level language: CUDA and Brook+ are fairly similar, but it's been slowly diverging for some time now. Since CUDA is all in house, NVIDIA has thrown a ton of resources at developing and continuing to develop CUDA, adding things that their users keep asking for such as atomic operations. Brook+ has been rather stagnant; AMD needed a high-level language to compete with CUDA, but they didn't want or have the resources to build something, so they took Brook and made it work with what they have. It's not bad by any means, but it's not as refined as it could be and CUDA is continuing to pull ahead.

Low level language: Here's where the two parties are on equal footing. CUDA's low level language, PTX, and AMD's Computer Abstraction Layer (CAL) are both equally capable. In fact this is where AMD has put the majority of the resources it has dedicated for Stream Computing. You won't find NVIDIA talking about PTX too much since they want everyone working at a higher level, but both PTX and CAL are equally capable of making good use of the underlying hardware.

Ultimately it's a matter of strategy and support. NVIDIA wanted to create an entire GPGPU environment; tools for every level, a variety of hardware, and lots of developer support; a very Intel strategy. AMD is far more low-key, they only intended to have a low-level language, and let others build from there with very little support beyond that. It worked with CTM since NVIDIA had nothing, but now that NVIDIA has CUDA it leaves AMD's offering underwhelming. The lack of high-powered hardware hasn't helped things either.