NVIDIA Responds To GPU PhysX Cheating Allegation

What I do have a problem with is the fact that the graphics card can't do both rendering and physics at the same time, hence future mark should really bring out a combined test with both intensive rendering and intensive physics.

Don't they have that already though? The physics test in the CPU test section is obviously a synthetic test that stresses only physics.
But there are also various physics in the first graphics test, most notably the water and cloth effects. As far as I know, these will be accelerated by PhysX aswell.
 
I'm a tad confused how its cheating, aren't they just enabled hardware support for a particular feature? Isn't this a GOOD thing??

Because the other side doesn't have the PhysX technology. It's cheating..


Like nVidia has an AWP, and ATI got only a DE because they didn't want to spend the money, so someone claims h4x.
 
It's already working in UT3 too. The special PhysX levels (I know, yawn) get almost 3x speedups. It should also work in the regular game, but those gains are modest even with a PPU installed, and might disappear with GPU PhysX.

Yes, but it also works with ANY game that was designed around a Physx PPU as well, opening up those few games to more people to get Physx acceleration effects.

I see this as a non-issue, as it has immediate real game benefits for those titles utilizing Physx as stated above.

Sensationalist journalism at its worst (not the [H]).
 
I read the initial "Charlie rant", when the Inq's link was posted in the video card sub-forum, and as someone already mentioned Charlie is nothing short of a moron. He's been doing nothing but a sort of NVIDIA smearing campaign for a while now, going as far as writing articles like these, that basically show how limited his knowledge on the subject is.

But it also comes with no surprise, since the Inq, and especially when it comes to possible NVIDIA news, usually just spreads FUD.
I am surprised though, to see readers/posters of this forum, actually considering this cheating. Since when is having a new feature enabled, that actually improves (or can improve) the gaming experience, cheating ?
Should ATI be accused of cheating in Assassin's Creed, because they have DX10.1 support in their hardware ?

Really don't understand the issue here. Now our graphics cards can process physics (among other non-graphical things), as was mentioned/advertised a couple of years ago, but it was never actually done. Now that it is done, it's cheating...:rolleyes:...go figure...
 
Yes, but it also works with ANY game that was designed around a Physx PPU as well
Not yet. Hopefully most games will be supported when the driver is updated for official G80/G92 support next month.
 
Not yet. Hopefully most games will be supported when the driver is updated for official G80/G92 support next month.

Is that so? As far as I know, it just installs the complete PhysX libraries for the GPU, so any game that supported the PhysX PPU previously, will automatically use the GPU now (just as 3DMark Vantage).
I don't think there are any 'levels of compatibility' or ;exceptions' or anything. It's either PhysX or it isn't.
 
It's either PhysX or it isn't.
Right now only UT3 and Vantage are accelerated using the beta driver. Everything else either crashes or does not recognize the GPU driver. I don't expect 100% compatibility initially, just hoping for close to it.
 
I suppose that's why it's a beta. If it crashes, you know it at least *tries* to use the GPU driver :)
If it isn't recognized, then the software probably has a rather shady way of determining PPU support (perhaps they expect an exact match on device name or version number or something).
 
I think it's more than that. ATI and nvidia have per game profiles and I think nvidia will have to make per game tweaks in those cases to make GPU PhysX acceleration run smoothly (i.e. balance out graphics and PhysX loads).
 
I think it's more than that. ATI and nvidia have per game profiles and I think nvidia will have to make per game tweaks in those cases to make GPU PhysX acceleration run smoothly (i.e. balance out graphics and PhysX loads).

They will probably do that dynamically. They have to balance between vertex/geometry/pixelshaders anyway, and in some cases even video acceleration. Now they'll just add 'physics shaders' to the mix of threads that run on the GPU concurrently.
The profiles are mostly for invoking special workarounds or replacement shaders etc. Things like that will probably not apply to PhysX, because PhysX is far more straightforward than the super complex statemachines that OpenGL and Direct3D are.
 
Hrm, well I think this is a great feature. Enable hardware acceleration for physics on hardware thats already on the market-- fantastic idea! Anyone whos upset by this must not have a card capable of doing so. For those users, keep in mind that it wont be long till something similar gets developed for the 3000 or 4000 series of video cards in the near future. So chill.
 
Did you read what i wrote ? I'm talking about noobs, who use 3DMark as system comparison tool. And with this PhysX enabled driver, they will think that their 8800GT on E6400 is better than HD4870 with Q9450. Which is simply not true, who will higher framerates in all games ? The second one. Who will have higher ratings ? The first one.

Why is it Nvidia's responsibility to protect idiots and tell them to buy a competitor's product? They're not out flaunting FM scores. The issue rests with Futuremark and the reviewers who continue to show FM ratings.
 
As for the physics + graphics argument...
I suppose people don't realize that there actually ARE graphics in the physics test in 3dmark Vantage?
Sure, they're relatively simple, but already the GPU has to do both graphics and physics, and apparently it still gets over 120 fps, so it can balance well between physics and graphics workloads.

This is a LOT faster than what any CPU can get (apparently nearly 10 times as fast), because the physics in their test are way heavier than in any game (it seems that a lot of people think that physics are physics, but CPUs are incredibly poor at physics).
So we can say that if the GPU would spend roughly 10% of its resources on physics, it could offload the CPU completely, and still have 90% of its resources left for graphics.
Additionally, when doing graphics, the efficiency is not 100%, so there will be some unused resources. It could well be that there are already 10% unused resources in most games... So that would mean that there's a whole CPU's worth of physics power going idle currently.

What this comes down to is that offloading the CPU physics to the GPU may have little or no impact on the framerate... And when you were previously CPU-limited, you would actually get a higher framerate by offloading the physics.

Ofcourse an alternative is to use much more complex physics at a slightly reduced framerate or simpler graphics, for games that were previously not possible on a CPU.
So this could be a big step in gaming. It will use your GPU more efficiently, it will free up resources on your CPU, and it allows for new levels of realism in physics.

+1 great post

In the physics tests the gpu is being used as a cpu, that's why it's in the cpu section. What do you think CUDA does? If a game was to come out with physics requirements like the futuremark cpu test then it would go that much faster with gpu accelerated physics, no problem there.

What I do have a problem with is the fact that the graphics card can't do both rendering and physics at the same time, hence future mark should really bring out a combined test with both intensive rendering and intensive physics. This is not nvidia's fault however, and I suspect by the time they do you'll be able to run a second graphics card solely for physics - i.e. I buy a next gen card to do graphics, and then stick my old 8800GT in my second * 16 slot and use it as an uber physics accelerator.

rendering and physics is already designed to work on a single cuda-enabled gpu with physx ->

http://hardforum.com/showthread.php?p=1032674131#post1032674131

physx is apparently running on radeon cards already ->

http://www.tgdaily.com/content/view/38137/135/

from fudzilla, but who knows, might turn out to be true ->

http://www.overclock3d.net/news.php?/gpu_displays/ati_falls_for_physx/1
 
imo, the faster physx can be supported on both sides, the better off everyone will be. devs will have a larger market to take advantage of physx in their games, publishers will have an additional marketing avenue, gpu makers will have a great feature to tout to prospective consumers giving them more of a reason to upgrade, and consumers will be able to enjoy more immersion, realism, eye candy, and hopefully more gameplay-affected physics in their games.
 
I think overall its a good thing.

This will entice Game developers to use PhysX, and since NVIDIA already helps 85% of Game devs with their development. This means better gameplay in the end.

3d mark hasent ever really meant much to me, real games are where its at. so "cheating" doesnt bother me.
 
Back
Top