• What
    is this?
    You've landed on the AMD Portal on AnandTech. This section is sponsored by AMD. It features a collection of all of our independent AMD content, as well as Tweets & News from AMD directly. AMD will also be running a couple of huge giveaways here so check back for those.


Jumping into pure compute performance, we’re going to have several new factors influencing the 290X as compared to the 280X. On the front end 290X/Hawaii has those 8 ACEs versus 280X/Tahiti’s 2 ACEs, potentially allowing 290X to queue up a lot more work and to keep itself better fed as a result; though in practice we don’t expect most workloads to be able to put the additional ACEs to good use at the moment. Meanwhile on the back end 290X has that 11% memory bandwidth boost and the 33% increase in L2 cache, which in compute workloads can be largely dedicated to said computational work. On the other hand 290X takes a hit to its double precision floating point (FP64) rate versus 280X, so in double precision scenarios it’s certainly going to enter with a larger handicap.

As always we'll start with our DirectCompute game example, 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. While DirectCompute is used in many games, this is one of the only games with a benchmark that can isolate the use of DirectCompute and its resulting performance.

Unfortunately Civ V can’t tell us much of value, due to the fact that we’re running into CPU bottlenecks, not to mention increasingly absurd frame rates. In the 3 years since this game was released high-end CPUs are around 20% faster per core, whereas GPUs are easily 150% faster (if not more). As such the GPU portion of texture decoding has apparently started outpacing the CPU portion, though this is still an enlightening benchmark for anything less than a high-end video card.

For what it is worth, the 290X can edge out the GTX 780 here, only to fall to GTX Titan. But in these CPU limited scenarios the behavior at the very top can be increasingly inconsistent.

Our next benchmark is LuxMark2.0, the official benchmark of SmallLuxGPU 2.0. SmallLuxGPU is an OpenCL accelerated ray tracer that is part of the larger LuxRender suite. Ray tracing has become a stronghold for GPUs in recent years as ray tracing maps well to GPU pipelines, allowing artists to render scenes much more quickly than with CPUs alone.

LuxMark by comparison is very simple and very scalable. 290X packs with it a significant increase in computational resources, so 290X picks up from where 280X left off and tops the chart for AMD once more. Titan is barely half as fast here, and GTX 780 falls back even further. Though the fact that scaling from the 280X to 290X is only 16% – a bit less than half of the increase in CUs – is surprising at first glance. Even with the relatively simplistic nature of the benchmark, it has shown signs in the past of craving memory bandwidth and certainly this seems to be one of those times. Feeding those CUs with new rays takes everything the 320GB/sec memory bus of the 290X can deliver, putting a cap on performance gains versus the 280X.

Our 3rd compute benchmark is Sony Vegas Pro 12, an OpenGL and OpenCL video editing and authoring package. Vegas can use GPUs in a few different ways, the primary uses being to accelerate the video effects and compositing process itself, and in the video encoding step. With video encoding being increasingly offloaded to dedicated DSPs these days we’re focusing on the editing and compositing process, rendering to a low CPU overhead format (XDCAM EX). This specific test comes from Sony, and measures how long it takes to render a video.

Vegas is another title where GPU performance gains are outpacing CPU performance gains, and as such earlier GPU offloading work has reached its limits and led to the program once again being CPU limited. It’s a shame GPUs have historically underdelivered on video encoding (as opposed to video rendering), as wringing significantly more out of Vegas will require getting rid of the next great CPU bottleneck.

Our 4th benchmark set comes from CLBenchmark 1.1. CLBenchmark contains a number of subtests; we’re focusing on the most practical of them, the computer vision test and the fluid simulation test. The former being a useful proxy for computer imaging tasks where systems are required to parse images and identify features (e.g. humans), while fluid simulations are common in professional graphics work and games alike.

Curiously, the 290X’s performance advantage over 280X is unusual dependent on the specific sub-test. The fluid simulation scales decently enough with the additional CUs, but the computer vision benchmark is stuck in the mud as compared to the 280X. The fluid simulation is certainly closer than the vision benchmark towards being the type of stupidly parallel workload GPUs excel at, though that doesn’t fully explain the lack of scaling in computer vision. If nothing else it’s a good reminder of why professional compute workloads are typically profiled and optimized against specific target hardware, as it reduces these kinds of outcomes in complex, interconnected workloads.

Moving on, our 5th compute benchmark is FAHBench, the official Folding @ Home benchmark. Folding @ Home is the popular Stanford-backed research and distributed computing initiative that has work distributed to millions of volunteer computers over the internet, each of which is responsible for a tiny slice of a protein folding simulation. FAHBench can test both single precision and double precision floating point performance, with single precision being the most useful metric for most consumer cards due to their low double precision performance. Each precision has two modes, explicit and implicit, the difference being whether water atoms are included in the simulation, which adds quite a bit of work and overhead. This is another OpenCL test, as Folding @ Home has moved exclusively to OpenCL this year with FAHCore 17.

With FAHBench we’re not fully convinced that it knows how to best handle 290X/Hawaii as opposed to 280X/Tahiti. The scaling in single precision explicit is fairly good, but the performance regression in the water-free (and generally more GPU-limited) implicit simulation is unexpected. Consequently while the results are accurate for FAHCore 17, it’s hopefully something AMD and/or the FAH project can work out now that 290X has been released.

Meanwhile double precision performance also regresses, though here we have a good idea why. With DP performance on 290X being 1/8 FP32 as opposed to ¼ on 280X, this is a benchmark 290X can’t win. Though given the theoretical performance differences we should be expecting between the two video cards – 290X should have about 70% of the FP 64 performance of 280X – the fact that 290X is at 82% bodes well for AMD’s newest GPU. However there’s no getting around the fact that the 290X loses to GTX 780 here even though the GTX 780 is even more harshly capped, which given AMD’s traditional strength in OpenCL compute performance is going to be a let-down.

Wrapping things up, our final compute benchmark is an in-house project developed by our very own Dr. Ian Cutress. SystemCompute is our first C++ AMP benchmark, utilizing Microsoft’s simple C++ extensions to allow the easy use of GPU computing in C++ programs. SystemCompute in turn is a collection of benchmarks for several different fundamental compute algorithms, as described in this previous article, with the final score represented in points. DirectCompute is the compute backend for C++ AMP on Windows, so this forms our other DirectCompute test.

SystemCompute and the underlying C++ AMP environment scales relatively well with the additional CUs offered by 290X. Not only does the 290X easily surpass the GTX Titan and GTX 780 here, but it does so while also beating the 280X by 18%. Or to use AMD’s older GPUs as a point of comparison, we’re up to a 3.4x improvement over 5870, well above the improvement in CU density alone and another reminder of how AMD has really turned things around on the GPU compute side with GCN.

Synthetics Power, Temperature, & Noise


View All Comments

  • 46andtool - Thursday, October 24, 2013 - link

    I dont know where your getting your information but your obviously nvidia biased because its all wrong. AMD is known for using poor reference coolers, once manufactures like sapphire and HIS roll out there cards in a couple weeks Im sure the noise and heat wont be a problem. and the 780ti is poised to be between a 780gtx and a titan, it will not be faster than a 290x, sorry. We already have the 780ti's specs..what Nvidia needs to focus on is dropping its insane pricing. Reply
  • SolMiester - Monday, October 28, 2013 - link

    Sorry bud, but the Ti will be much faster than Titan, otherwise there is no point, hell even the 780OC is enough to edge the Titan. Why are people going on about Titan, its a once in a blue moon product to fill a void that AMD left open with CUDA dev for prosumers...Full monty with perhaps 7ghz memory, wahey! Reply
  • Samus - Friday, October 25, 2013 - link

    What in the world makes you think the 780Ti will be faster than Titan? That's ridiculous. What's next, a statement that the 760Ti will be faster than the 770? Reply
  • TheJian - Friday, October 25, 2013 - link

    Another shader and more mhz.
    If the specs are true quite a few sites think it will be faster than titan.
    Check the table. 780TI would win in gflops if leak is true. The extra 80mhz+1SMX mean it should either tie or barely beat it in nearly everything.

    Even a tie at $650 would be quite awesome at less watts/heat/noise possibly. Of course it will be beat a week later buy a fully unlocked titan ultra or more mhz, or mhz+fully unlocked. NV won't just drop titan. They will make a better one easily. It's not like NV just sat on their butts for the last 8 months. It's comic anyone thinks AMD has won. OK, for a few weeks tops (and not really even now other than price looking at 1080p and the games I mentioned previously).
  • ShieTar - Thursday, October 24, 2013 - link

    It doesn't cost less than a GTX780, it only has a lower MSRP. The actual price for which you can buy a GTX780 is already below 549$ today, so as usual you pay the same price for the same performance with both companies.

    And testing 4K gaming is important right now, but it should be another 3-5 years before 4K performance actually impacts sales figures in any relevant way.

    And about Titan? Keep in mind that it is 8 months old, still has one SMX disabled (unlike the Quadro K6000), and still uses less power in games than the 290X. So I wouldn't be surprised to see a Titan+ come out soon, with 15 SMX and higher base clocks, and as Ryan puts it in this article "building a refined GPU against a much more mature 28nm process". That should be enough to gain 10%-15% performance in anything restricted by computing power, thus showing a much more clear lead over the 290X.

    The only games that the 290X will clearly win are those that are restricted by memory bandwidth. But nVidia have proven with the 770 that they can operate memory at 7GHz as well, so they can increase Titans bandwidth by 16% through clocks alone.

    Don't get me wrong, the 290X looks like a very nice card, with a very good price to it. I just don't think nVidia has any reason to worry, this is just competition as usual, AMD have made their move, nVidia will follow.
  • Drumsticks - Thursday, October 24, 2013 - link


    Searched on Newegg, sorted by lowest price, lowest one was surprise! $650. I don't think Newegg is over $100 off in their pricing with competitors.
  • 46andtool - Thursday, October 24, 2013 - link


    your clearly horrible at searching
  • TheJian - Friday, October 25, 2013 - link

    $580 isn't $550 though right? And out of stock. I wonder how many of these they can actually make seeing how hot it is already in every review pegged 94c. Nobody was able to OC it past 1125. They're clearly pushing this thing a lot already. Reply
  • ShieTar - Friday, October 25, 2013 - link

    Well, color me surprised. I admittedly didn't check the US market, because for more than a decade now, electronics used to be sold in the Euro-Region with a price conversion assumption of 1€=1$, so everything was about 35% more expensive over here (but including 19% VAT of course).

    So for this discussion I used our German comparison engines. Both the GTX780 and the R290X are sold for the same price of just over 500€ over here, which is basically 560$+19%VAT. I figured the same price policies would apply in the US, it basically always does.

    Well, as international shipping is rarely more that 15$, it would seem like your cheapest way to get a 780 right now is to actually import it from Germany. Its always been the other way around with electronics, interesting to see it the other way around for once.
  • 46andtool - Thursday, October 24, 2013 - link

    the price of a 780gtx is not below $649 unless you are talking about a refurbished or open box card. Reply

Log in

Don't have an account? Sign up now