NVIDIA’s DirectX 11 Architecture: GF100 (Fermi) In Detail
Anti-Aliasing Image Quality
To improve anti-aliasing image quality, the GF100 introduces a new anti-aliasing mode: 32xCSAA. nVidia’s previous strongest edge AA mode was 16xQ, but this is now bested by 32xAA. Here’s the sample pattern for it, courtesy of nVidia:
32xAA = 8xMSAA + 24xCSAA.
Thus 32xCSAA is a natural extension of 16xQ, and offers even stronger edge (polygon) anti-aliasing, courtesy of providing a total of 32 unique samples
But that’s not all that has improved. The GF100 has a new ability to use coverage samples to affect the quality of alpha textures, as implemented through transparency anti-aliasing. With previous nVidia hardware such as the GT200, coverage samples had no effect on transparency anti-aliasing quality, as the result was derived solely from the base multi-sampling pattern in effect.
Also in the specific case of transparency multi-sampling, image quality has improved there too. Any titles using the older alpha test method to render transparent textures have their shader code automatically converted to use the alpha-to-cover technique, which should greatly improve image quality, especially in heavily aliased areas.
The upshot of this is higher quality edges, and higher quality alpha textures.
Anti-Aliasing Performance
In addition to improving image quality, anti-aliasing performance has also increased. When it comes to AA, the most obvious area to target is the ROPs, and that’s exactly what nVidia has done. The GF100 has 48 ROPs, up from 32 ROPs on the GTX285, which is especially helpful for portions of the scene that cannot be compressed.
Each ROP is also faster and more efficient than on previous generations, so it can do more work per cycle. This includes improvements made to the compression technology.
Aside from better AA performance in general, nVidia’s old Achilles heel with 8xMSAA performance should also be addressed by the improvements. Historically, prior nVidia architectures have exhibited much higher relative performance hit when going from 4xMSAA to 8xMSAA, compared to competing ATi architectures.
Also by moving to 384 bit GDDR5, nVidia should have access to plenty of memory bandwidth to keep all of those ROPs fed with data.
ati status
[told] x
benchmarks? none?
Benchmarks in a review of brand new GPU architecture!?!
– when have you seen that before?
We expect to have benchmarks vs. GTX 285 and vs. Radeon when we get the actual cards.
I noticed that you mentioned “time check”. These comments must be approved manually; sorry for any delay.
I thought you guys guys were gonna post something substantial, not this rehash. NDA my ass…
This is what they gave us TTimmy. It is not like other sites got anything different and we got garbage.
However, I do understand that this is not what you all wanted to see. We also wanted to see some more definitive information such as benchmark numbers, clock speeds, release date and pricing but…ABT isn’t releasing a video card (yet), they are.
I wouldn’t call what we posted, a “rehash”. What has happened with this progressive revelation, always happens with new architecture – no matter who releases it, AMD, NVIDIA or Intel. First you get the general information about upcoming architecture, then more and more information is released until it goes into production.
Much of the information about Fermi’s GeForce in our article is brand new information about Fermi’s gaming capabilities. Much of what we wrote about was not disclosed anywhere previously. There is a lot more to add since we wrote about Fermi’s computing architecture last year.
As I understand it, only the devs would have engineering samples of GF100. That means NVIDIA’s partners would not have them nor would any tech review site. There are no fixed clocks, nothing about power consumption nor thermals – and certainly no solid performance benchmarks other than what NVIDIA did internally. Not yet.
I hope Nvidia release a decent mid range $300 Fermi GPU.