Compute

Moving on from our look at gaming performance, we have our customary look at compute performance.

Our first compute benchmark comes from Civilization V, which uses DirectCompute to decompress textures on the fly. Civ5 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.

In the game world Civ5 benefits significantly from SLI and CrossFire. For our texture compression test however AFR is more a liability than a benefit. This doesn’t impact the game in any meaningful manner, but it’s an example of how SLI/CF aren’t always the right tool for the job. Unfortunately for both parties, with as few compute applications as there are today, almost none of them benefit from SLI/CF.

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 only currently supports ray tracing with one GPU, so all of our results are effectively proxies for what would be if the GTX 590 only had one GPU. Not surprisingly overclocks do wonders here, and NVIDIA’s strong compute architecture gives them an easy win. SLI/CF performance will become more important here when we upgrade to LuxMark for our next iteration of our benchmark suite, as LuxMark can handle multiple OpenCL drivers.

Our final compute benchmark is a Folding @ Home benchmark. Given NVIDIA’s focus on compute for Fermi, cards such as the GTX 590 can be particularly interesting for distributed computing enthusiasts, as two GPUs should be able to quickly retire work units.

Folding@Home doesn’t directly benefit from CF/SLI at all. However by dispatching one WU to each GPU it’s possible to double effective performance. With that taken into account the GTX 590 is quite an effective cruncher, particularly when we start looking at overclocking.

Wolfenstein Power, Temperature, & Noise
Comments Locked

123 Comments

View All Comments

  • Ryan Smith - Thursday, March 24, 2011 - link

    There are only 2 reasons this card isn't reference.

    1) Factory overclock, which we can and will nullify for testing

    2) The EVGA backplate. Admittedly I don't have the reference backplate, but the NV backplates shouldn't cause any of our results to differ - the difference is mostly cosmetic.

    For this reason, it's "more-or-less" reference. Technically it's not reference, but once we change the clocks it's quite identical in performance.
  • mariush - Friday, March 25, 2011 - link

    Can you explain how can you nullify the modified / improved cooling system of the eVGA compared to reference cards?

    A reference card with stock voltages/frequencies may still run worse than this eVGA when downclocked, for example because on the reference card the voltage regulators may heat more and throttle the card more often.

    Otherwise.... not an ATI fan but it's painfully obvious you're not focusing on this review on things that make this card look bad, like playing on 2 x 1920x1080 monitors or something like that.
  • Ryan Smith - Friday, March 25, 2011 - link

    The cooling on the EVGA isn't any different. With such a mild overclock, they're basically just clocking it up a bit; the voltage and the cooling is no difference from reference.
  • etamin - Thursday, March 24, 2011 - link

    Where do you get the MSRPs for all the cards on the first page? I'm never able to find any of them at those prices.
  • etamin - Thursday, March 24, 2011 - link

    btw I'm looking at the 6850, 6870, and 6970. They start at $170, $210, and $340 on newegg.
  • Ryan Smith - Thursday, March 24, 2011 - link

    I factor in Mail In Rebates. if you don't, that's probably why you see prices differently.
  • Ramon Zarat - Thursday, March 24, 2011 - link

    Review title:

    ''NVIDIA’s GeForce GTX 590: Duking It Out For The Single Card King''

    Comments in conclusion:

    ''...and as a result there is no one card that can be crowned king.''

    LMAO... How to pretend to say someting and actually mean the complete oppsite!

    Now, performance, cost and power ratio is STILL best with the 6990. And that's without even considering multi screen gaming setup. At 1.5Gb Vram, the 590 WILL come up short at 5760 X 1200.

    Ramon
  • Silent_Scone - Thursday, March 24, 2011 - link

    But none the less, I think I'll stick with my 580GTX SLi thanks ;)
  • krumme - Thursday, March 24, 2011 - link

    REALLY FAST AT 1080 ON HAWX

    NO NOISE

    OVERCLOCK YOURS NOW !!!
  • freedomsbeat212 - Thursday, March 24, 2011 - link

    I hate coming to anandtech sometimes because so many of the comments are from wannabe editors. It's annoying and takes away from the excellent content..

    Why not have an "email correction" button vs taking it out in the comment section? It's weird, I don't see this anywhere else - you guys must be a particularly anal group...

    To go back O/T, I miss the days of powerful sub-$250 graphics cards. There's a market for it but all the action's on the high-end. Remember when the affordable TNT2 would play every recent game at playable framerates?

Log in

Don't have an account? Sign up now