NVIDIA's GeForce 8800 (G80): GPUs Re-architected for DirectX 10
by Anand Lal Shimpi & Derek Wilson on November 8, 2006 6:01 PM EST- Posted in
- GPUs
Our DX9FSAAViewer won't show us the exact sample patterns for CSAA, but we can take a look at where ATI and NVIDIA are getting their color sample points:
| ATI |  |
 |
 |
| G70 |  |
 |
 |
| G80 |  |
 |
 |
| G80* |  |
 |
 |
*Gamma AA disabled
As we can see, NVIDIA's 8x color sample AA modes use a much better pseudo random sample pattern rather than a combination of two rotated grid 4xAA patterns as in G70's 8xSAA.
While it is interesting to talk about the internal differences between MSAA and CSAA, the real test is pitting NVIDIA's new highest quality mode against ATI's highest quality.
G70 4X G80 16XQ ATI 6X
Hold mouse over links to see Image Quality
G70 4X G80 16XQ ATI 6X
Hold mouse over links to see Image Quality
Stacking up the best shows the power of NVIDIA's CSAA with 16 sample points and 8 color/z values looking much smoother than ATI's 6xAA. Compared to G70, both ATI and G80 look much better. Now let's take a look at the performance impact of CSAA. This graph may require a little explanation to understand, but it is quite interesting and worth looking at.
As we move from lower to higher quality AA modes, performance generally goes down. The exception is with G80's 16x mode. Its performance is only slightly lower than 8x. This is due to the fact that both modes use 4 color samples alongside more coverage samples. We can see the performance impact of having more coverage samples than color samples by looking at the performance drop from 4x to 8x on G80. There is another slight drop in performance when increasing the number of coverage samples from 8x to 16x, but it is almost nil. With the higher number of multisamples in 8xQ, algorithms that require z/stencil data per sub-pixel may look better, but 16x definitely does great job with the common edge case with much less performance impact. Enabling 16xQ shows us the performance impact of enabling more coverage samples with 8x multisamples.
It is conceivable that a CSAA mode using 32 sample points and 8 color points could be enabled to further improve coverage data at nearly the same performance impact of 16xQ (similar to the performance difference we see with 8x and 16x). Whatever the reason this wasn't done in G80, the potential is there for future revisions of the hardware to offer a 32x mode with the performance impact of 8x. Whether the quality improvement is there or not is another issue entirely.
Facebook
Twitter
RSS
111 Comments
View All Comments
Nightmare225 - Sunday, November 26, 2006 - link
Are the FPS posted in this article, Minimum FPS, Average FPS, or Maximum? Thanks!multiblitz - Monday, November 20, 2006 - link
I enjoyed your reviews always a lot as they inclueded the video-capbilities for a HTPC on previous cards. Unfortunately this was this time not the case. Hopefully there will be a 2. Part covering this as well ? If so, it would be nice to make a compariosn on picture quality as well against the filters of ffdshow, as nvidia is now as well supporting postprocessing filters...DerekWilson - Tuesday, November 21, 2006 - link
What we know right now is that 8800 gets a 128 out of 130 on HQV tests.We haven't quite put together an HTPC look at 8800, but this is a possibility for the future.
epsil0n - Sunday, November 19, 2006 - link
I am not agree with this:"It isn't surprising to see that NVIDIA's implementation of a unified shader is based on taking a pixel shader quad pipeline, and breaking up the vector units into 4 scalar units. Now, rather than 4 pixel quads, we see 16 SPs per "quad" or block of stream processors. Each block of 16 SPs shares 4 texture address units, 8 texture filter units, and an L1 cache."
If i understood well this sentence tells that given 4 pixels the numbers of SPs involved in the computation are 16. Then, this assumes that each component of the pixel shader is computed horizontally over 16 SP (4pixel x 4rgba = 16SP). But, are you sure??
I didn't found others articles over the web that speculate about this. Reading others articles the main idea that i realized is that a shader is computed by one and only one SP. Each vector instruction (inside the shader) is "mapped" as a sequence of scalar operations (a dot product beetwen two vectors is mapped as 4 MUD/ADD operations). As a consequence, in this scenario 4 pixels are computed only by 4 SPs.
DerekWilson - Tuesday, November 21, 2006 - link
Honestly, NVIDIA wouldn't give us this level of detail. We certainly pressed them about how vertices and pixels map to SPs, but the answer we got was always something about how dynamic the hardware is able to dynamically schedule the SPs optimally according to what needs to be done.They can get away with being obscure about how they actually process the data because it could happen either way and provide the same effect to the developer and gamer alike.
Scheduling the simultaneous processing one vec4 MAD operation on 4 quads (16 pixels) over 4 groups of 4 SPs will take 4 clock cycles (in terms of throughput). Processing the same 16 pixels on 16 SPs will also take 4 clock cycles.
But there are reasons to believe that things happen the way we described. Loading components of 16 different "threads" (verts, pixels or whatever) would likely be harder on the cache than loading all 4 components of 4 different threads. We could see them schedule multiple ops from 4 threads to fill up each block of shaders -- like computing 4 consecutive scalar operations for 4 threads on 16 SPs.
At the same time, it might be easier to maximize SP utilization if 16 threads were processed on one block of SPs every clock.
I think the answer to this question is that NVIDIA knows, they didn't tell us, and all we can do is give it our best guess.
xtknight - Thursday, November 16, 2006 - link
This has been AT's best article in awhile. Tons of great, concise info.I have a question about the gamma corrected AA. This would be detrimental if you've already calibrated your display, correct (assuming the game heeds to the calibration)? Do you know what gamma correction factor the cards use for 'gamma corrected AA'?
DerekWilson - Monday, November 20, 2006 - link
I don't know if they dynamically adjust gamma correction based on monitor (that would be nice though) ...if they don't they likely adjusted for a gamma of either (or between) 2.2 or 2.5.
Also, thanks :-) There was a lot more we wanted to pack in, but I'm glad to see that we did a good job with what we were able to include.
Thanks,
Derek Wilson
bjacobson - Sunday, November 12, 2006 - link
This comment is unrelated, but could you implement some system where after rating a comment, on reload the page goes back to the comment I was just at? Otherwise I rate something halfway down and then have to spend several seconds finding where I just was. Just a little nuissance.Thanks for the great article, fun read.
neo229 - Friday, November 10, 2006 - link
This is a very suspect quote. A card that requires two PCIe power connectors is going to dissipate a lot of heat. More heat means there must be a faster, louder fan or more substantial and costly heat sink. The extra costs associated with providing a truly quiet card mean that the bulk of manufacturers go with the loud fan option.
DerekWilson - Friday, November 10, 2006 - link
If manufacturers go with the NVIDIA reference design, then we will see a nice large heatsink with a huge quiet fan.Really, it does move a lot of air without making a lot of noise ... Are there any devices we can get to measure the airflow of a cooling solution?
We are also seeing some designs using water cooling and theres even one with a thermo-electric (peltier) cooler on it. Manufacturers are going to great lengths to keep this thing running cool without generating much noise.
None of the 8 retail cards we are testing right now generate nearly the noise of the X1950 XTX ... We are working on a retail roundup right now, and we'll absolutely have noise numbers for all of these cards at load.