Compute & Normalized Numbers

Moving on from our look at gaming performance, we have our customary look at compute performance, bundled with a look at theoretical tessellation performance. Unlike our gaming benchmarks where NVIDIA’s architectural enhancements could have an impact, everything here should be dictated by the core clock and SMs, with the GTX 570’s slight core clock advantage over the GTX 480 defining most of these tests.

Our first compute benchmark comes from Civilization V, which uses DirectCompute to decompress textures on the fly. Civ V includes a sub-benchmark that exclusively tests the speed of their texture decompression algorithm by repeatedly decompressing the textures required for one of the game’s leader scenes.

The core clock advantage for the GTX 570 here is 4.5%; in practice it leads to a difference of less than 2% for Civilization V’s texture decompression test. Even the lead over the GTX 470 is a bit less than usual, at 23%. Nor should the lack of a competitive placement from an AMD product be a surprise, as NVIDIA’s cards consistently do well at this test, lending credit to the idea that it’s a compute application better suited for NVIDIA’s scalar processor design.

Our second GPU compute benchmark is SmallLuxGPU, the GPU ray tracing branch of the open source LuxRender renderer. While it’s still in beta, SmallLuxGPU recently hit a milestone by implementing a complete ray tracing engine in OpenCL, allowing them to fully offload the process to the GPU. It’s this ray tracing engine we’re testing.

SmallLuxGPU is rather straightforward in its requirements: compute and lots of it. The GTX 570’s core clock advantage over the GTX 480 drives a fairly straightforward 4% performance improvement, roughly in line with the theoretical maximum. The reduction in memory bandwidth and L2 cache does not seem to impact SmallLuxGPU. Meanwhile the advantage over the GTX 470 doesn’t quite reach its theoretical maximum, but the GTX 570 is still 27% faster.

However as was the case with the GTX 580, all of the NVIDIA cards fall to AMD’s faster cards here; the GTX 570 is only between the 6850 and 6870 in performance, thanks to AMD’s compute-heavy VLIW5 design that SmallLuxGPU excels at. The situation is quite bad for the GTX 570 as a result, with the top card being the Radeon 5870, which the GTX 570 underperforms by 27%.

Our final compute benchmark is a Folding @ Home benchmark. Given NVIDIA’s focus on compute for Fermi and in particular GF110 and GF100, cards such as the GTX 580 can be particularly interesting for distributed computing enthusiasts, who are usually looking for the fastest card in the coolest package.

Once more the performance advantage for the GTX 570 matches its core clock advantage. If not for the fact that a DC project like F@H is trivial to scale to multi-GPU configurations, the GTX 570 would likely be the sweet spot for price, performance, and power/noise.

Finally, to take another look at GTX 570’s performance, we have the return of our normalized data view that we first saw with our look at the GTX 580. Unlike the GTX 580 which had similar memory/ROP abilities as the GTX 480 but more SMs, the GTX 570 contains the same number of SMs with fewer ROPs and a narrower memory bus. As such while a normalized dataset for the GTX 580 shows the advantage of the GF110’s architectural enhancements and the highter SM count, the normalized dataset for the GTX 570 shows the architectural enhancements alongside the impact of lost memory bandwidth, ROPs, and L2 cache.

The results certainly paint an interesting picture. Just about everything is ultimately affected by the lack of memory bandwidth, L2 cache, and ROPs; if the GTX 570 didn’t normally have its core clock advantage, it would generally lose to the GTX 480 by small amounts. The standouts here include STALKER, Mass Effect 2, and BattleForge which are all clearly among the most memory-hobbled titles.

On the other hand we have DIRT 2 and HAWX, both of which show a 4% improvement even though our normalized GTX 570 is worse compared to a GTX 480 in every way except architectural advantages. Clearly these were some of the games NVIDIA had in mind when they were tweaking GF110.

Wolfenstein Power, Temperature, & Noise
POST A COMMENT

54 Comments

View All Comments

  • ilkhan - Tuesday, December 07, 2010 - link

    I love my HDMI connection. It falls out of my monitor about once a month and I have to flip the screen around to plug it back in. Thanks TV industry! Reply
  • Mr Perfect - Tuesday, December 07, 2010 - link

    It is somewhat disappointing. People with existing screens probably don't care, and the cheap TN screens still pimp the DVI interface, but all of the high end IPS panel displays include either HDMI, DP or both. Why wouldn't a high end video card have the matching outputs? Reply
  • EnzoFX - Tuesday, December 07, 2010 - link

    High-End gaming card is probably for serious gamers, which should probably go with TN as they are the best against input lag =P. Reply
  • Mr Perfect - Tuesday, December 07, 2010 - link

    Input lag depends on the screen's controller, you're thinking pixel response time. Yes, TN is certainly faster then IPS for that. I still wouldn't get a TN though, the IPS isn't far enough behind in response time to negate the picture quality improvement. Reply
  • MrSpadge - Tuesday, December 07, 2010 - link

    Agreed. The pixel response time of my eIPS is certainly good enough to be of absolutely no factor. The image quality, on the other hand, is worth every cent.

    MrS
    Reply
  • DanNeely - Tuesday, December 07, 2010 - link

    Due to the rarity of HDMI 1.4 devices (needed to go above 1920x1200) replacing a DVI port with an HDMI port would result in a loss of capability. This is aggravated by the fact that due to their stickerprice 30" monitors have a much longer lifetime than 1080p displays and owners who would get even more outraged as being told they had to replace their screens to use a new GPU. MiniDVI isn't an option either because it's singlelink and has the same 1920x1200 cap as HDMI 1.3.

    Unfortunately there isn't room for anything except a single miniHDMI/miniDP port to the side of 2 DVI's, installing it on the top half of a double height card like ATI has done cuts into the cards exhaust airflow and hurts cooling. With the 5xx series still limited to 2 outputs that's not a good tradeoff, and HDMI is much more ubiquitous.

    The fiasco with DP-DVI adapters and the 5xxx series cards doesn't exactly make them an appealing option either to consumers.
    Reply
  • Mr Perfect - Wednesday, December 08, 2010 - link

    That makes good sense too, you certainty wouldn't want to drop an existing port to add DP. I guess it really comes down to that cooling vs port selection problem.

    I wonder why ATI stacked the DVI ports? Those are the largest ports out of the three and so block the most ventilation. If you could stack a mini-DP over the mini HDMI, it would be a pretty small penalty. It might even be possible to mount the mini ports on edge instead of horizontally to keep them all on one slot.
    Reply
  • BathroomFeeling - Tuesday, December 07, 2010 - link

    "...Whereas the GTX 580 took a two-tiered approach on raising the bar on GPU performance while simultaneously reducing power consumption, the GeForce GTX 470 takes a much more single-tracked approach. It is for all intents and purposes the new GTX 480, offering gaming performance..." Reply
  • Lonyo - Tuesday, December 07, 2010 - link

    Any comments on how many will be available? In the UK sites are expecting cards on the 9th~11th December, so not a hard launch there.
    Newegg seems to only have limited stock.

    Not to mention an almost complete lack of UK availability of GTX580s, and minimal models and quantities on offer from US sites (Newegg).
    Reply
  • Kef71 - Tuesday, December 07, 2010 - link

    Or maybe they are a nvidia "feature" only? Reply

Log in

Don't have an account? Sign up now