Power, Heat, And Efficiency
So a single GeForce GTX 570 really puts the hurt on a single Radeon HD 6950, while better scaling leads to 6950-based CrossFire triumphs. While we could go on to say that most multi-GPU buyers will be happier with AMD, there’s the little matter of operational expense that we still haven’t considered.
Oops! It might be acceptable for Nvidia’s better-performing card to consume more power in a single-GPU configuration, but CrossFire’s superior performance scaling makes the GeForce GTX 570 a poor efficiency choice in SLI. Note that the power was measured using a game as well as FurMark. This was essential, since the middle Radeon HD 6950 was completely idle during the FurMark test.
The GTX 570s also ran hotter, but this editor would like to note that AMD’s sink design leads to extremely tight fan spacing in 3-way mode. Local banshees abandoned our neighborhood at the commencement of power testing.
With Just Cause 2 (at our maximum test settings) making up the most-important portion of our power test, we used the corresponding benchmark values to calculate full-load efficiency. Average performance and power set the full-load baseline, while average power alone (for all six configurations) set the active idle baseline.
Lower power consumption and better performance gave AMD a big efficiency lead, while excellent performance scaling at a constant cost in CPU power allowed multiple HD 6950s to score higher full-load efficiency than a single card.
Here's another article on the 68xx series in Xfire
Xfire scaling was found to be 100% on 10 or the 19 games they tested, and remaining very high on the others. Nvidia and ATi seems to trade blows at different games tested, but it is evident that Ati has stepped up their Xfire drivers int he 6xxx series.