Theoreticals & Tessellation

From a rendering perspective one of the most interesting things AMD did with Tahiti was what they didn’t do: they didn’t add more ROPs, they didn’t add more geometry engines. And yet based on our game performance they’ve clearly improved on their performance in those situations by making more efficient use of the hardware they do have.

So we wanted to take a quick look at synthetic performance to see what these tools had to say about AMD’s changes. We’ve included the numbers for every other GPU in our lineup as a reference point, but we would strongly suggest against reading into them too much. AMD versus AMD is sometimes relevant to real world performance; AMD versus NVIDIA rarely is.

Theoretical: 3DMark Vantage Pixel Fill

We’ll start with 3DMark Vantage and its color fill test. This is basically a ROP test that attempts to have a GPU’s ROPs blend as many pixels as it can. Theoretically AMD can do 32 color operations per clock on Tahiti, which at 925MHz for 7970 means the theoretical limit is 29.6Gpix/sec; not that any architecture is ever that efficient. In practice 7970 hits 13.33Gpix/sec, which is still well short of the theoretical maximum, but pay close attention to 7970’s performance relative to 6970. Even with the same number of ROPs and a similar theoretical performance limit (29.6 vs 28.16), 7970 is pushing 51% more pixels than 6970 is.

In designing Tahiti AMD said that they didn’t need more ROPs they just needed more efficient ROPs, and it looks like they’ve delivered on this. It’s not clear whether this is the limit for efficiency or if AMD can squeeze more out of their ROPs in future designs, but this definitely helps to prove that there’s more to graphics rendering than a large number of functional units.

Theoretical: 3DMark Vantage Texture Fill

Our other 3DMark synthetic benchmark is the 3DMark Vantage Texture Blend test, which measures how quickly a GPU can blend multiple FP16 textures. This is more synthetic than most tests because FP16 textures aren’t widely used, but it’s a consistent benchmark.

The theoretical performance improvement from 6970 to 7970 is 40% - 33% more texture units operating at a 5% higher clockspeed. In practice the 7970 exceeds that improvement by increasing texture performance by 46%, meaning the 7970 has benefitted from more than the increase in texture units. Most likely the new cache architecture has further improved the efficiency of the texture units, although the 3DMark texture set is not particularly large.

Moving on, we also wanted to take a look at tessellation. AMD did not increase the theoretical geometry performance of Tahiti as compared to Cayman – both top out at 2 triangles per clock – but AMD has put a lot of effort into improving the efficiency of Tahiti’s geometry units as we’ve seen reflected in our game benchmarks.

Tessellation: DirectX11 Detail Tessellation Sample

Our first tessellation benchmark is the traditional Detail Tessellation sample program from the DirectX SDK. Here we’re looking at tessellation performance as a product of the framerate, testing at tessellation factors 7 (normal) and 15 (max). Traditionally this is a test that has been rather balanced at normal tessellation levels, while NVIDIA cards with their superior geometry throughput have been the top performers at maximum tessellation levels. So it’s all the more interesting when we’ve seen the tables turned; the 7970 is merely competitive with the GTX 580 at normal tessellation levels, but now it’s ahead of the GTX 580 by 24%. More significantly however the 7970 is ahead of the 6970 by 57%.

Tessellation: Unigine Heaven

Our second tessellation benchmark is Unigine Heaven, a benchmark that straddles the line between a synthetic benchmark and a real-world benchmark, as the engine is licensed but no notable DX11 games have been produced using it yet. In any case the Heaven benchmark is notable for its heavy use of tessellation, which means it’s largely a proxy test for tessellation performance.

As with the Detail Tessellation sample program, Heaven shows significant gains for the 7970 versus the 6970, with the 7970 leading by 56%. Meanwhile it leads the GTX 580 by 27%, which is actually slightly better than what we saw under the more “pure” Detail Tessellation sample. Between these two benchmarks it’s clear that AMD’s tessellation efficiency improvements are quite real, and that with Tahiti AMD can deliver much better tessellation performance than Cayman even at virtually the same theoretical triangle throughput rate.

Of course one has to wonder what NVIDIA will have in store for Kepler next year. Their current Fermi design seems to scale well with additional geometry units, but if Tahiti is anything to go by, there’s a great deal to be gained just by focusing on efficiency. NVIDIA has prided themselves on their geometry performance since before GF100 even shipped, so it will be interesting if they have anything in store to hold on to that distinction.

Compute: The Real Reason for GCN Power, Temperature, & Noise
POST A COMMENT

291 Comments

View All Comments

  • Wreckage - Thursday, December 22, 2011 - link

    That's kind of disappointing. Reply
  • atticus14 - Thursday, December 22, 2011 - link

    oh look its that guy that was banned from the forums for being an overboard nvidia zealot. Reply
  • medi01 - Tuesday, January 03, 2012 - link

    Maybe he meant "somebody @ anandtech is again pissing on AMDs cookies"?

    I mean "oh, it's fastest and coolest single GPU card on the market, it is slightly more expensive than competitor's, but it kinda sucks since AMD didn't go "significantly cheaper than nVidia" route" is hard to call unbiased, eh?

    Kind of disappointing conclusion, indeed.
    Reply
  • ddarko - Thursday, December 22, 2011 - link

    To each their own but I think this is undeniable impressive:

    "Even with the same number of ROPs and a similar theoretical performance limit (29.6 vs 28.16), 7970 is pushing 51% more pixels than 6970 is" and

    "it’s clear that AMD’s tessellation efficiency improvements are quite real, and that with Tahiti AMD can deliver much better tessellation performance than Cayman even at virtually the same theoretical triangle throughput rate."
    Reply
  • Samus - Thursday, December 22, 2011 - link

    I prefer nVidia products, mostly because the games I play (EA/DICE Battlefield-series) are heavily sponsered by nVidia, giving them a developement-edge.

    That out of the way, nVidia has had their problems just like this card is going to experience. Remember when Fermi came out, it was a performance joke, not because it was slow, but because it used a ridiculous amount of power to do the same thing as an ATI card while costing substantially more.

    Fermi wasn't successful until second-generation products were released, most obviously the GTX460 and GT430, reasonably priced cards with quality drivers and low power consumption. But it took over a year for nVidia to release those, and it will take over a year for ATI to make this architecture shine.
    Reply
  • kyuu - Thursday, December 22, 2011 - link

    Wat? The only thing there might be an issue with is drivers. As far as power consumption goes, this should be better than Cayman. Reply
  • CeriseCogburn - Sunday, March 11, 2012 - link

    He's saying the 28mn node will have further power improvements. Take it as an amd compliment - rather you should have. Reply
  • StriderTR - Thursday, December 22, 2011 - link

    EA/Dice are just as heavily sponsored by AMD, more in fact. Not sure where your getting your information, but its .. well ... wrong. Nvidia bought the rights to advertize the game with their hardware, AMD is heavily sponsoring BF3 and related material. Example, The Controller.

    Also, the GTX 580 and HD 6970 perform within a few FPS of each other on BF3. I run dual 6970's, by buddy runs dual 580's, we are almost always within 2 FPS of one and other at any given time.

    AMD will have the new architecture "shining" in far under a year. They have been focused on it for a long time already.

    Simple bottom line, both Nvidia and AMD make world class cards these days. No matter your preference, you have cards to choose from that will rock any games on the planet for a long time to come.
    Reply
  • deaner - Thursday, December 22, 2011 - link

    Umm, yea no. Not so much with nvidia and EA/DICE Batttlefield series giving nvidia a development edge. (if it does, the results are yet to be seen)
    Facts are facts, the 5 series to our current review today, the 7970, do and again continue to edge the Nvidia lines. The AMD Catalyst performance of particular note, BF3, has been far superior.

    Reply
  • RussianSensation - Thursday, December 22, 2011 - link

    ."..most obviously the GTX460 and GT430, reasonably priced cards with quality drivers and low power consumption. But it took over a year for nVidia to release those"

    GTX470/480 launched March 26, 2010
    GTX460 launched July 12, 2010
    GT430 launched October 11, 2010

    Also, Fermi's performance at launch was not a joke. GTX470 delivered performance between HD5850 and HD5870, priced in the middle. Looking now, GTX480 ~ HD6970. So again, both of those cards did relatively well at the time. Once you consider overclocking of the 470/480, they did extremely well, both easily surprassing the 5870 in performance in overclocked states.

    Sure power consumption was high, but that's the nature of the game for highest-end GPUs.
    Reply

Log in

Don't have an account? Sign up now