Fixing AMD's Poor AA Performance

Now that we have a new architecture from AMD with improved AA performance, it's time again to look at a comparison of all the different AA modes these cards offer. No new modes have been introduced since the R600 and G80 reviews, but AMD has completely rebuilt their ROPs with special attention to hardware based AA resolve. In R600, hardware resolve wasn't much faster than shader based resolve, but this time around, AA runs blazingly fast whether its on the dedicated resolve hardware or on the shader hardware (since their is so much more shader hardware now even shader based resolve gets a giant boost).

The first thing we will want to look at are the MSAA modes. These are the modes we absolutely recommend for use with AMD hardware as all their other filters essentially low-pass filter the entire image by blending in neighboring subpixels. In any case, the results are very impressive for RV770.


Click to Enlarge

The RV670 at 19x12 was limited in some way other than AA (it really couldn't keep up), but at 16x10 we can get a better idea of relative impact of AA. And clearly the RV770 quite improves fall off with increasing AA levels over the previous generation. One special thing to note is that the RV770 does fall off very gracefully to 8xAA. Since the RV670, G80 and GT200 all have sharp drops in performance when moving up from 4xAA to 8xAA, the RV770 really shines here. In fact, the few tests we did with 8xAA paints the 4870 in a much better light relative to the GTX 280. Remember from our earlier architecture discussion that Oblivion is the game where the GT200 had the largest performance advantage over RV770.

While 8xAA performance is all well and good, the image quality difference is just not enough for us to recommend enabling it over increasing resolution (or better yet, pixel density on LCD panels -- hello display makers). For those with panels that don't go over 1280x1024, it would be better to spend the extra money on a large panel than a $300 graphics card. The application where we see 8xAA making the most sense is on 50+ HDTVs used as computer monitors where the pixels are just plain huge. For the majority of desktop users though 4xAA is where it's at.

We did test the performance of all the other modes as well. NVIDIA's CSAA modes are quite good (they actually improve image quality rather than degrade it), but again, stay away from anything but AMD's "box" filtered AA.


Click to Enlarge

The RV770 actually shows a bigger performance hit from enabling their tent filters than RV670. This is likely because the filters are run on shader hardware in both cases while RV770 has faster hardware resolve that can be used for normal AA resolve. If RV670 resolves "box" filtered AA on the shader as well this would explain the flatter performance in that case. Even more so than the image quality question, the fact that they perform lower really should be the nail in the coffin for AMD's tent filter garbage.
One, er, Hub to Rule them All? AA Image Quality Comparison
Comments Locked

215 Comments

View All Comments

  • Final Destination II - Wednesday, June 25, 2008 - link

    Dear girls and guys,

    does anyone know of a manufacturer, who offers a HD4850 with a better cooler? I'm desperately searching for one...


    Please reply!
  • Graven Image - Wednesday, June 25, 2008 - link

    Asus recently announced a 4850 with a non-stock cooler, though their version still doesn't expel the air out the back like a dual slot design. (http://www.asus.com/news_show.aspx?id=11871)">http://www.asus.com/news_show.aspx?id=11871). Its not available yet thought. My guess is mid-July we'll probably start seeing a couple different fan and heatsink designs.
  • strikeback03 - Thursday, June 26, 2008 - link

    Only dual-slot card I've ever used was an EVGA 8800GTS 640, it sucked air in the back and blew it into the case.
  • Final Destination II - Wednesday, June 25, 2008 - link

    Nice! 7°C cooler, that's a start! I guess I'll wait a bit more, then.
  • Spacecomber - Wednesday, June 25, 2008 - link

    Although I'm somewhat dubious about dual card solutions, I keep looking at the benchmarks and then at the prices for a couple of 8800 GTs.

    Perhaps, if the 4870 forces Nvidia to reduce their prices for the GTX 260 and the GTX 280, they will likewise bring down the price for the 9800 GX2. This is already the fastest single card solution, and it sells for less than the GTX 280. If this card starts selling for under $400 (maybe around $350), will this become Nvidia's best answer to the 4870?

    Given the performance and the prices for the 4870 and the 9800 GX2 will Nvidia be able to price the GTX 280 competitively, or will it simply be vanity product - ridiculously priced and produced only in very small numbers?

    It should be interesting to see where the prices for video cards end up over the course of the next few weeks.
  • kelmerp - Wednesday, June 25, 2008 - link

    Better HD knickknacks? Better offloading/upscaling?
  • chizow - Wednesday, June 25, 2008 - link

    The HD4000 series have better HDMI sound support with 8ch LPCM over HDMI, but still can't pass uncompressed bistreams. Image quality hasn't changed as there isn't really any room to improve.
  • kelmerp - Wednesday, June 25, 2008 - link

    It would be nice to have a video card, where it doesn't matter how weak the current-gen processor is (say the lowliest celeron available), the card can still output 1080p HDTV without dropping any frames.
  • Chaser - Wednesday, June 25, 2008 - link

    Good to have back at the FRONT of the finish line.
  • JPForums - Wednesday, June 25, 2008 - link

    Ragarding the SLI scaling in Witcher:
    The GTX 280 SLI setup may be running into a bottleneck or driver issues, rather than seeing inherent scaling issues. Consider, the 9800 GTX+ SLI setup scales from 22.9 to 44.5. So the scaling isn't an inherent SLI scaling problem. Though it may point to scaling issues specific to the GTX 280, it is more likely that the problem lies elsewhere. I do, however, agree with your general statement that when CF is working properly, it tends to scale better. In my systems, it seems to require less CPU overhead.

Log in

Don't have an account? Sign up now