Seems like we've been waiting for these new GeForce GTX 400's for an long time now. And NVIDIA gave us a first glimpse at its latest GPU architecture about half a year ago, right around the time that AMD was introducing its Radeon HD 5870. In the intervening six months, AMD has fleshed out its Radeon HD 5000 series with an full suite of DirectX 11 class GPU chips and graphics cards. Meanwhile, NVIDIA's own GF100 chip is just later than a stoner to study hall. Fortunately, our wait is coming to an end. These GeForce GTX 470 and GeForce GTX 480 are expected to be available soon, and we have wrangled several for testing. We can say with confidence that the GF100 is nothing if not fascinating. - TechReport

NVIDIA GeForce GTX 480 (GF100) Video Card Review

This GeForce GTX 480 graphics board is a straightforward near doubling of peak shader arithmetic and raster operation throughput rates versus the GeForce GTX 285 card, but memory bandwidth is only marginally higher. In theory the GeForce GTX 480 is, amazingly, slower at texturing than the GeForce GTX 285 version, but NVIDIA expects the GF100 to deliver higher real world texturing performance thanks to some texture cache optimizations that should reduce conflicts during sampling. Clearly, the GF100 missed its targets on a number of fronts. And even when dialed back, the GF100 is in running for the performance title.

These two new GeForce's draw more power, generate more heat and noise, and have higher price tags than the closest competing Radeon's, but they are not substantially faster at running current games. For many, that will be the brutal bottom line on the GeForce GTX 400 series. Given the complexity and the rich feature sets of modern graphics processors, that hardly seems fair, but these GF100 is facing formidable competition that made it to market first and is clearly more efficient in pretty much every way that matters. In fact, the GF100's major contribution to real-time graphics is an increased geometry processing facility.

Then again, AMD seems to be making inroads with game developers, which is what happens when you are first to market with a whole family of DirectX 11 chipsets. For what it's worth, these GF100 may not be a disappointment in all markets. With its geometry processing throughput, it should make an fantastic Quadro workstation graphics card. The GF100 based Tesla cards could still succeed in the realm of dedicated GPU computing too. The Fermi architecture really is ahead of any of its competitors there for a number of reasons that can't be ignored, and the question now is whether it can build a business around it.

The firm seemed to be expecting a huge progress in this regard when it revealed the first details of this architecture to us. We're curious to see how good a graphics chip this generation of NVIDIA's technology could make when it is stripped of all the extra fat needed to serve other markets. You don't need any of those things to play games or even to transcode video. As such a leaner, meaner mid-range variant of the Fermi architecture might make a much more attractive graphics card, especially if NVIDIA can get some of the apparent chip issues worked out and reach some higher clock speeds.