Compute

Update 3/30/2010: After hearing word after the launch that NVIDIA has artificially capped the GTX 400 series' double precision (FP64) performance, we asked NVIDIA for confirmation. NVIDIA has confirmed it - the GTX 400 series' FP64 performance is capped at 1/8th (12.5%) of its FP32 performance, as opposed to what the hardware natively can do of 1/2 (50%) FP32. This is a market segmentation choice - Tesla of course will not be handicapped in this manner. All of our compute benchmarks are FP32 based, so they remain unaffected by this cap.

Continuing at our look at compute performance, we’re moving on to more generalized compute tasks. GPGPU has long been heralded as the next big thing for GPUs, as in the right hands at the right task they will be much faster than a CPU would be. Fermi in turn is a serious bet on GPGPU/HPC use of the GPU, as a number of architectural tweaks went in to Fermi to get the most out of it as a compute platform. The GTX 480 in turn may be targeted as a gaming product, but it has the capability to be a GPGPU powerhouse when given the right task.

The downside to GPGPU use however is that a great deal of GPGPU applications are specialized number-crunching programs for business use. The consumer side of GPGPU continues to be underrepresented, both due to a lack of obvious, high-profile tasks that would be well-suited for GPGPU use, and due to fragmentation in the marketplace due to competing APIs. OpenCL and DirectCompute will slowly solve the API issue, but there is still the matter of getting consumer orientated GPGPU applications out in the first place.

With the introduction of OpenCL last year, we were hoping by the time Fermi was launched that we would see some suitable consumer applications that would help us evaluate the compute capabilities of both AMD and NVIDIA’s cards. That has yet to come to pass, so at this point we’re basically left with synthetic benchmarks for doing cross-GPU comparisons. With that in mind we’ve run a couple of different things, but the results should be taken with a grain of salt as they don’t represent any single truth about compute performance on NVIDIA or AMD’s cards.

Out of our two OpenCL benchmarks, we’ll start with an OpenCL implementation of an N-Queens solver from PCChen of Beyond3D. This benchmark uses OpenCL to find the number of solutions for the N-Queens problem for a board of a given size, with a time measured in seconds. For this test we use a 17x17 board, and measure the time it takes to generate all of the solutions.

This benchmark offers a distinct advantage to NVIDIA GPUs, with the GTX cards not only beating their AMD counterparts, but the GTX 285 also beating the Radeon 5870. Due to the significant underlying differences of AMD and NVIDIA’s shaders, even with a common API like OpenCL the nature of the algorithm still plays a big part in the performance of the resulting code, so that may be what we’re seeing here. In any case, the GTX 480 is the fastest of the GPUs by far, beating out the GTX 285 by over half the time, and coming in nearly 5 times faster than the Radeon 5870.

Our second OpenCL benchmark is a post-processing benchmark from the GPU Caps Viewer utility. Here a torus is drawn using OpenGL, and then an OpenCL shader is used to apply post-processing to the image. Here we measure the framerate of the process.

Once again the NVIDIA cards do exceptionally well here. The GTX 480 is the clear winner, while even the GTX 285 beats out both Radeon cards. This could once again be the nature of the algorithm, or it could be that the GeForce cards really are that much better at OpenCL processing. These results are going to be worth keeping in mind as real OpenCL applications eventually start arriving.

Moving on from cross-GPU benchmarks, we turn our attention to CUDA benchmarks. Better established than OpenCL, CUDA has several real GPGPU applications, with the limit being that we can’t bring the Radeons in to the fold here. So we can see how much faster the GTX 480 is over the GTX 285, but not how this compares to AMD’s cards.

We’ll start with Badaboom, Elemental Technologies’ GPU-accelerated video encoder for CUDA. Here we are encoding a 2 minute 1080i clip and measuring the framerate of the encoding process.

The performance difference with Badaboom is rather straightforward. We have twice the shaders running at similar clockspeeds, and as a result we get twice the performance. The GTX 480 encodes our test clip in a little over half the time it took the GTX 280.

Up next is a special benchmark version of Folding@Home that has added Fermi compatibility. Folding@Home is a Standford research project that simulates protein folding in order to better understand how misfolded proteins lead to diseases. It has been a poster child of GPGPU use, having been made available on GPUs as early as 2006 as a Close-To-Metal application for AMD’s X1K series of GPUs. Here we’re measuring the time it takes to fully process a sample work unit so that we can project how many nodes (units of work) a GPU could complete per day when running Folding@Home.

Folding@Home is the first benchmark we’ve seen that really showcases the compute potential for Fermi. Unlike everything else which has the GTX 480 running twice as fast as the GTX 285, the GTX 480 is a fewtimes faster than the GTX 285 when it comes to folding. Here a GTX 480 would get roughly 3.5x as much work done per day as a GTX 285. And while this is admittedly more of a business/science application than it is a home user application (even if it’s home users running it), it gives us a glance at what Fermi is capable when it comes to compuete.

Last, but not least for our look at compute, we have another tech demo from NVIDIA. This one is called Design Garage, and it’s a ray tracing tech demo that we first saw at CES. Ray tracing has come in to popularity as of late thanks in large part to Intel, who has been pushing the concept both as part of their CPU showcases and as part of their Larrabee project.

In turn, Design Garage is a GPU-powered ray tracing demo, which uses ray tracing to draw and illuminate a variety of cars. If you’ve never seen ray tracing before it looks quite good, but it’s also quite resource intensive. Even with a GTX 480, with the high quality rendering mode we only get a couple of frames per second.

On a competitive note, it’s interesting to see NVIDIA try to go after ray tracing since that has been Intel’s thing. Certainly they don’t want to let Intel run around unchecked in case ray tracing and Larrabee do take off, but at the same time it’s rasterization and not ray tracing that is Intel’s weak spot. At this point in time it wouldn’t necessarily be a good thing for NVIDIA if ray tracing suddenly took off.

Much like the Folding@Home demo, this is one of the best compute demos for Fermi. Compared to our GTX 285, the GTX 480 is eight times faster at the task. A lot of this comes down to Fermi’s redesigned cache, as ray tracing as a high rate of cache hits which help to avoid hitting up the GPU’s main memory any more than necessary. Programs that benefit from Fermi’s optimizations to cache, concurrency, and fast task switching apparently stand to gain the most in the move from GT200 to Fermi.

Tessellation & PhysX Image Quality & AA
POST A COMMENT

197 Comments

View All Comments

  • Headfoot - Monday, March 29, 2010 - link

    Great review, great depth but not too long. Concise but still enough information.

    THANK YOU SO MUCH FOR INCLUDING MINIMUM FRAME RATES!!! IMO they contribute the most to a game feeling "smooth"
    Reply
  • niceboy60 - Friday, August 20, 2010 - link

    This review is not accurate , Badaboom GTX 400 series cards , are not compatible with GTX 400 series yet .However they already post the test resaults
    I have a GTX 480 and does not work with badaboom , Badaboom official site confirms that
    Reply
  • slickr - Sunday, March 28, 2010 - link

    I thought that after the line-up of games thread, you would really start testing games from all genres, so we can actually see how each graphic cards performs in different scenarios.

    Now you have 80% first person shooters, 10% racing/Action-adventure and 10%RPG and RTS.
    Where are the RTS games, isometric RPG's, simulation games, etc?

    I would really like Battleforge thrown out and replaced by Starcraft 2, DOW 2: Chaos Rising, Napoleon Total War. All these RTS games play differently and will give different results, and thus better knowledge of how graphic cards perform.
    How about also testing The Sims 3, NFS:Shift, Dragon Age Origins.
    Reply
  • Ryan Smith - Monday, March 29, 2010 - link

    Actually DAO was in the original test suite I wanted to use. At the high end it's not GPU limited, not in the slightest. Just about everything was getting over 100fps, at which point it isn't telling us anything useful.

    The Sims 3 and Starcraft are much the same way.
    Reply
  • Hsuku - Sunday, March 28, 2010 - link

    On Page 9 of Crysis, your final sentence indicates that SLI scales better than CF at lower resolutions, which is incorrect from your own graphs. CF clearly scales better at lower resolutions when video RAM is not filled:

    @ 1680x1050
    480 SLI -- 60.2:40.7 --> 1.48
    5870 CF -- 53.8:30.5 --> 1.76 (higher is better)

    @ 1920x1200
    480 SLI -- 54.5:33.4 --> 1.63
    5870 CF -- 46.8:25.0 --> 1.87 (higher is better)

    This indicates the CF technology scales better than SLI, even if the brute performance of the nVidia solution comes out on top. This opposes diametrically your conclusion to page 9 ("Even at lower resolutions SLI seems to be scaling better than CF").

    (Scaling ability is a comparison of ratios, not a comparison of FPS)
    Reply
  • Ryan Smith - Monday, March 29, 2010 - link

    You're looking at the minimums, not the averages. Reply
  • Hsuku - Tuesday, March 30, 2010 - link

    My apologies, I was looking at the wrong graphs.

    However, even so, your assertion is still incorrect: at at the lowest listed resolution, CF and SLI scaling are tied.
    Reply
  • Ryan Smith - Wednesday, March 31, 2010 - link

    Correct. The only thing I really have to say about that is that while we include 1680 for reference's sake, for any review of a high-end video card I'm looking nearly exclusively at 1920 and 2560. Reply
  • Hrel - Thursday, September 02, 2010 - link

    I get that, to test the card. But if you don't have a monitor that goes that high, it really doesn't matter. I'd really like to see 1080p thrown in there. 1920x1080; as that's the only resolution that matters to me and most everyone else in the US. Reply
  • Vinas - Sunday, March 28, 2010 - link

    It's pretty obvious that anantech was spanked by nVIDIA the last time they did a review. No mention of 5970 being superior to the 480 is a little disturbing. I guess the days of "trusting anandtech" are over. Come on guys, not even a mention of how easily the 5870 overclocks? The choice is still clear, dual 5870's with full cover blocks FTW! Reply

Log in

Don't have an account? Sign up now