W00T! It looks like a great feature

Quote: Originally Posted by Anandtech WeÂ’ll start things off with a shocker then: NVIDIA is going to putting integrated GPUs on all of their motherboards. Yes, youÂ’re reading that right, soon every NVIDIA motherboard will ship with an integrated GPU, from the highest end enthusiast board to the lowest end budget board. Why? Hybrid SLI. ItÂ’s no secret that enthusiast-class GPUs have poor power performance, even when idling they eat a lot of power. ItÂ’s just not possible right now to make a G80 or G92 based video card power down enough that itÂ’s not sucking at least some non-trivial amount of power. NVIDIA sees this as a problem, particularly with the most powerful setups (2 8800GTXs for example) and wants to avoid this problem in the future. Their solution to this is the first part of Hybrid SLI and the reasoning for moving to adding integrated GPUs in every board, what NVIDIA is calling HybridPower. If youÂ’ve read our article on AMDÂ’s Hybrid Crossfire technology then you already have a good idea of where this is leading. NVIDIA wants to achieve better power reductions by switching to an integrated GPU when doing non-GPU intensive tasks and shutting off the discrete GPU entirely. The integrated GPU eats a fraction of the power of even an idle discrete GPU, with the savings increasing as we move up the list of discrete GPUs towards the most powerful ones. To do this, NVIDIA needs to get integrated GPUs in more than just their low-end boards, which is why they are going to begin putting integrated GPUs in all of their boards. NVIDIA seems rather excited about what this is going to do for power consumption . To illustrate the point they gave us some power consumption numbers from their own testing, which while we canÂ’t confirm at this point and are certainly the worst (best) case situation, we know from our own testing that NVIDIAÂ’s numbers canÂ’t be too far off. Currently NVIDIA is throwing around savings of up to 400W, this assumes a pair of high-end video cards in SLI, where they eat 300W each at load and 200W at idle. NVIDIA doesnÂ’t currently have any cards with this kind of power consumption, but they might with future cards. Even if this isnÂ’t the case, we saw a live demo where NVIDIA showed us using this technology saving around 120W on a rig they brought, so 100W looks like a practical target right now. The returns will diminish as we work our way towards less powerful cards, but NVIDIA is arguing that the savings are still worth it. The electricity to idle a enthusiast GPU is not trivial, so even cutting 60W is approaching a level on-par with getting rid of an incandescent lightbulb.

Article Link

This'll be very handy for everyone. Means you don't have to buy a graphics card when you buy a high-end mobo. CPU-based benching will be easier because you won't need to fit a GPU. But I'll stick with my HD3870 for now....uses next to nothing idling compared to an Nvidia card.

This is great. As somebody who feels pretty guilty about the amount of energy my computer consumes, it's really good to see some effort being put into decreasing it. I think I know what my next motherboard will be

Power saving is cool, its just a shame that nVidia chipset boards for Intel platforms are cr@p.

This is great and all, but what does it really mean? I mean if my computer uses 100W less power, what is the long term impact? How may kilowats per year will that save me? What is the drawback?

I just read some of the article and while it sounds good, I'm not so sure it is going to be good, at least not for the highest end of the GPU spectrum. If the integeated GPU uses system memory for the frame buffer and you have say, 2 8800GTX cards in SLI, that would require 1.5gb (768mb x 2) of system ram just to move the data from the card to the mobo so it can be displayed.

Quote: Originally Posted by DickNervous This is great and all, but what does it really mean? I mean if my computer uses 100W less power, what is the long term impact? How may kilowats per year will that save me? What is the drawback? I just read some of the article and while it sounds good, I'm not so sure it is going to be good, at least not for the highest end of the GPU spectrum. If the integeated GPU uses system memory for the frame buffer and you have say, 2 8800GTX cards in SLI, that would require 1.5gb (768mb x 2) of system ram just to move the data from the card to the mobo so it can be displayed.

I don't think it would need that much memory at all since the only time the frame buffer would be full would be if you were gaming and you wouldn't be switching to integrated graphics to game. Plus it should only be for a few seconds while it gets transfered and then it just acts like a normal integrated graphics card taking up 128mb (or whatever you set it too).

After reading about the ATi Hybrid, I got really sad cause I cant use my 2900PRO with it.

Nuts, shoulda got an nVidia.

Quote: Originally Posted by eascarface I don't think it would need that much memory at all since the only time the frame buffer would be full would be if you were gaming and you wouldn't be switching to integrated graphics to game. Plus it should only be for a few seconds while it gets transfered and then it just acts like a normal integrated graphics card taking up 128mb (or whatever you set it too).

If you read the article the way it is setup is that ALL video would go through the integrated GPU (and it's frame buffer) so that when it switches from one to the other it is seamless. Otherwise you would have to switch the cable on the back, and that would be stupid. Here is the diagram...



So what happens is there is a video connector on the mobo that the monitor would be connected to. When you do regular desktop stuff the integrated GPU would be used. THen you switch (manually at the moment) to the discrete GPU. At that point what happens is that the discrete GPU does it's thing and then sends the frame to the integrated GPU which sends it to the monitor.

This raises two concerns for me, from a gaming perspective. The fist is the amount of SYSTEM RAM that would be required for the frame buffer of the integrated GPU to be able to hold that frame as it moves it along. The second is the additional time added to each frame to be rendered.

Ah ok. I probably shoulda read the full article too. But if I'm reading it correctly than Anandtech says that Nvidia is saying that it won't be a problem; but since they arn't saying how it won't be a problem I'm assuming it is. That being said I can't see Nvidia releasing something that would be that unfinished/bad performer.

Quote: Originally Posted by eascarface Ah ok. I probably shoulda read the full article too. But if I'm reading it correctly than Anandtech says that Nvidia is saying that it won't be a problem; but since they arn't saying how it won't be a problem I'm assuming it is. That being said I can't see Nvidia releasing something that would be that unfinished/bad performer.

Neither can I, so I assume they have some type of plan to deal with it, but I will wait and see.

Yeah, I trust that nVidia wouldn't go out of their way to cripple their own products' performance