NVIDIA Purchased AGEIA Technologies

“I was merely stating what happened when NV bought out 3dfx, raising the possibility that something similar may happen again.”
It’s not the same. NV didn’t buy 3DFX they bought some of 3DFX’s assists. NV didn’t and don’t own 3DFX the company. It was 3DFX that chose to stop driver support not NV.
With Ageia NV did buy the company and do own them.

How can NV buying some of 3DFX's assists and not the company be classed as similar to NV buying Ageia the company? NV have to honer the Ageia warrantees e.c.t They didnt with 3DFX as they dont own them.


They can dissolve Agea the day after they close the deal, at that point Agea no longer exists, and Nv does not have to honor warranties or continue driver support of Agea's products. Not saying that they necessarily will. If it does, the best you could hope for is a class action that would not be settled for 5+ years, that made a few lawyers rich and not much more.
Also, as I already stated, I never thought they should have to honor 3dfx's warranties or continue driver support. Twice that has been brought up, when I never said that they should have. Comment on what I wrote, not what you imagine I think.

Edit: NV owned the IP, nobody could legally write drivers for 3dfx hardware without Nv's permission, not even the "corporate entity formerly known as 3dfx". ;)
 
Saw almost an identical post over Here. I am interested in seeing this take off (Hey more people that get into physics the better). However, I am more interested to see how a $400 video card physics acceleration is going to compare to the $100-$150 Physx card.
 
Saw almost an identical post over Here. I am interested in seeing this take off (Hey more people that get into physics the better). However, I am more interested to see how a $400 video card physics acceleration is going to compare to the $100-$150 Physx card.

Same here, because that will shed light over the previous claims about GPU-physics ;)
 
I don't think you need to compare a "$100-$150" PhysX card to a "$400" G80 card. Ageia was claiming 58 GFLOPS performance for the PhysX card. Let's start from there.

It's not clear if that 58 GFLOPS figure peak theoretical or actual throughput. To give the PhysX card the benefit here, say that 58 GFLOPS was actual throughput.

Observed throughput per SP in GPGPU loads is about 1.6 FLOPS per SP per shader clock on G8x cards. Applying that to a 8400GS, you get about 23 GFLOPS throughput, which clearly isn't a match and kind of rules out expectations for an integrated video chip matching a PhysX card in this generation. However, a vanilla 8600GT would have over 70 GFLOPS measured throughput in real GPGPU loads. That brings a performance competitive part down to under $90. IMO, the 8500GT is probably the most comparable card for throughput to the PhysX card and is even cheaper.

Why am I treating the PhysX card like a general purpose SIMD engine and not some super-optimized physics engine? See here: http://arstechnica.com/articles/paedia/hardware/physx-hpc.ars

Of course we won't know how it compares until nvidia released the CUDA PhysX driver.
 
I don't think you need to compare a "$100-$150" PhysX card to a "$400" G80 card. Ageia was claiming 58 GFLOPS performance for the PhysX card. Let's start from there.

It's not clear if that 58 GFLOPS figure peak theoretical or actual throughput. To give the PhysX card the benefit here, say that 58 GFLOPS was actual throughput.

Observed throughput per SP in GPGPU loads is about 1.6 FLOPS per SP per shader clock on G8x cards. Applying that to a 8400GS, you get about 23 GFLOPS throughput, which clearly isn't a match and kind of rules out expectations for an integrated video chip matching a PhysX card in this generation. However, a vanilla 8600GT would have over 70 GFLOPS measured throughput in real GPGPU loads. That brings a performance competitive part down to under $90. IMO, the 8500GT is probably the most comparable card for throughput to the PhysX card and is even cheaper.

Why am I treating the PhysX card like a general purpose SIMD engine and not some super-optimized physics engine? See here: http://arstechnica.com/articles/paedia/hardware/physx-hpc.ars

Of course we won't know how it compares until nvidia released the CUDA PhysX driver.

FLOPS are useless here, it's the efficiency and the implemetation in real world usage that counts.
And once again, in the time of GPU limited games, adding burdens to the GPU makes no sense...and for the record:
No one has a clue to the preformance of any 8x00 GPU in physics..despite "Quantum".

And as for the architechture og the PhysX here is some usefull information:
http://www.blachford.info/computer/articles/PhysX2.html
This is not a GPU...no matter how much PR is spun.

And I'll bet that NVIDIA could make a comparison test of the PPU vs G80 in no time...question is...do they really want to?
 
FLOPS are useless here, it's the efficiency and the implemetation in real world usage that counts.
I'm not talking about LINPACK GFLOPS, but actual workload measured performance. The theoretical performance for the G8x SPs is almost double the 1.6 figure I used above. If you read what you quoted, I gave the PPU full credit for the 58 GFLOPS Ageia performance claim even though actual throughput is probably significantly lower.

No one has a clue to the preformance of any 8x00 GPU in physics..despite "Quantum".
LOL, because it does have some physics performance data. You only exclude it because it's inconvenient.

This is not a GPU...no matter how much PR is spun.
I didn't say or imply the PhysX PPU chip was a GPU. I said it was a generic SIMD processor, which your link backs up. :p

And if you want to go on record, i'll predict that the 8500GT will be pretty close in performance to the Ageia PPU once nvidia has optimized PhysX under CUDA. What's your prediction? The branching and switching performance problems nvidia had with the G7x GPUs were fixed in the G8x series and above.
 
No one has a clue to the preformance of any 8x00 GPU in physics..despite "Quantum".
I wouldn't use these as end all examples, but I found some CUDA physics videos.

Colour Particles (8800GTX)
Colour Particles (8800GTS)
Lava Particles
N-Body (8800GTX)
Elastic

Honestly if this ‘is’ what an 8800GTX can do, I’m not expecting PPU beating physics when you add a graphics workload along side those physics. As a dedicate physics card sure, but not when it is multitasking physics and graphics.
 
I don't think you need to compare a "$100-$150" PhysX card to a "$400" G80 card.

Why not?

Until we see nVidia's tech in real applications, it's just a guessing game. The point I was trying to make was if it is going to perform 3-4 times better than the PhysX card to justify the cost difference this first time around (for 1st time buyers).

After all... if you want to compare numbers, you may have chosen the HD2900XT over the 8800GTX because it looks better on paper. However we all know better that just because something looks good on paper...it might not be all that.

To me personally it's a moot point... If it performs just a little faster, on my next video card upgrade the 8800 will be moved down to take the place of the PPU and the PhysX card will be pulled. To me this whole thing is an awesome recycling program.
 
I'm thinking that this might be really good news for the 9800GX2 (or not necessarily the 9800GX2 but future GX2's; could be for the 9800GX2 as games running CUDA physics require the gpu to do the physics processing, and then you would need to sacrifice gfx at that point but would at least be able to get the physics going if you wanted them). I think what will be most interesting is how well SLI scales while working on both graphics and physics.
 
I'm not talking about LINPACK GFLOPS, but actual workload measured performance. The theoretical performance for the G8x SPs is almost double the 1.6 figure I used above. If you read what you quoted, I gave the PPU full credit for the 58 GFLOPS Ageia performance claim even though actual throughput is probably significantly lower.

And you are still going to have to run the PhysX API ported to CUDA..so the numbers mean nothing still...

LOL, because it does have some physics performance data. You only exclude it because it's inconvenient.
Show me anything like the physcis via the PhysX API..

I am tired of the BS.
In 2006 NVIDIA said:
"Our 6x00 can do GPU-physics"
That never happend and then became:
"Our 7x00 can do GPU-physics"
That never happend (again) and now have become to:
"Our 8x00 can, sorta by a wrapper, do what the PPU does.

I don't believe them...to much PR-fluf, to little real world.

I didn't say or imply the PhysX PPU chip was a GPU. I said it was a generic SIMD processor, which your link backs up. :p
You did mention it like both the PPU and GPU are godd at SIMD and hance good at physcis.
The PPU has proven what it can...the GPU-physcis havn't.

And if you want to go on record, i'll predict that the 8500GT will be pretty close in performance to the Ageia PPU once nvidia has optimized PhysX under CUDA. What's your prediction? The branching and switching performance problems nvidia had with the G7x GPUs were fixed in the G8x series and above.
I have heard this before...my el-cheapo-ass card will be the same as the PPU.

Show me the money...we are going on year 2 now...cklsing on year 3 and still not 1 game that supports GPU-physcis...and still no GPU that can macth the PPU...it is still all PR.
 
I'm thinking that this might be really good news for the 9800GX2 (or not necessarily the 9800GX2 but future GX2's; could be for the 9800GX2 as games running CUDA physics require the gpu to do the physics processing, and then you would need to sacrifice gfx at that point but would at least be able to get the physics going if you wanted them). I think what will be most interesting is how well SLI scales while working on both graphics and physics.

In the age of GPU limited games?
You get one guess ;)
 
Wow Atech, such pessimism.
What has been said before and what has been realisable have been very different things but now Physics on a GPU is very realisable, especially now NVidia have access to use an established brand and the technology rights.
Definitely room for a good discussion on the topic, it doesnt deserve being beaten down.
 
Wow Atech, such pessimism.

That is what you get when a lot of PR leads to...nothing.


What has been said before and what has been realisable have been very different things but now Physics on a GPU is very realisable, especially now NVidia have access to use an established brand and the technology rights.
More PR, wake me when they get the shit running.

Definitely room for a good discussion on the topic, it doesnt deserve being beaten down.
There was talk in 2006 about GPU-physics...
There was talk in 2007 about GPU-physics...
Now there is talk in 2008 about GPU-physcis...enough talk already, show me..not just PR-fluf me!
 
You've said it all many times already.
fine, we know your opinion now, no need to troll.
 
Back
Top