Final Words

When NVIDIA launched the first Maxwell cards earlier this year, we knew that we would be in for a treat with their latest architecture. Though just a fragment of the performance of what their eventual high-end cards would be, NVIDIA’s first Maxwell cards offered an interesting look at an architecture that would be capable of doubling NVIDIA’s performance per watt on the same 28nm TSMC manufacturing process they started with over 2 years ago. To that end I don’t think there has been any doubt that NVIDIA’s eventual second generation Maxwell cards would be equally amazing when it comes to power efficiency, but I feel NVIDIA has still impressed us when it comes to performance, features, and pricing.

In many ways it feels like this latest launch has returned us to the PC video card industry of 2012. NVIDIA’s flagship consumer card is once again powered by a smaller and more potent consumer-class x04 GPU, and once again NVIDIA is swinging the one-two punch of performance and power efficiency. When GTX 680 was launched it set a new high mark for the video card industry, and now we see GTX 980 do more of the same. The GTX 980 is faster, less power hungry, and quieter than the Radeon R9 290X, so once again NVIDIA has landed the technical trifecta. Even if we’re just looking at performance and pricing the GTX 980 is the undisputed holder of the single-GPU performance crown, besting everything else AMD and NVIDIA have to offer, and offering it at a price that while no means a steal is more than reasonable given NVIDIA’s technical and performance advantage. As such GTX 980 comes very, very close to doing to Radeon R9 290X what GTX 680 did to Radeon HD 7970 over 2 years ago.

Meanwhile from a feature perspective the GTX 900 series is going to prove to be a very captivating product. Dynamic Super Resolution is a brutish-yet-clever solution of what to do about anti-aliasing on today's deferred renderer games that cannot support traditional MSAA/SSAA, and while I’m withholding my judgment on Multi-Frame sampled Anti-Aliasing until it’s made available to users in NVIDIA’s drivers, the idea at least has merit. Otherwise I am very happy to see that NVIDIA has now fully caught up to the competition in terms of baseline API features by offering everything needed to support Direct3D 11.2 and beyond.

Along those lines, NVIDIA’s focus on voxel technology for Maxwell 2 is a very interesting route to take, and I am eagerly anticipating seeing whether it gets widely adopted and what developers do with it. VXGI is a very neat concept to generate voxel based global illumination, and building in the features necessary to do significant portions of it in hardware is a wise move by NVIDIA. The catch at this point is the same catch that faces all vendor specific technologies: just because the hardware is there doesn’t mean developers will put it to good use, especially in this age of console ports. NVIDIA for their part has made the right move by making sure VXGI will run on other hardware, but I am concerned that the performance delta means that it’s only going to be viable on Maxwell 2 GPUs for now, which could discourage developers. None the less we do need better lighting in games, and I hope this encourages developers to finally adopt these kinds of high quality global illumination systems.

As for the hardware itself, is there anything left to say other than that GTX 980 is a well-built, well-engineered card? The build quality is impeccable – raising the bar over even GTX Titan – and the power efficiency gains are truly remarkable. With a TDP lower than even GTX 680, this is the lowest power consumption has been for a chart-topping card since 9800 GTX over half a decade ago. It’s really a bit of a honeymoon period since if and when NVIDIA does Big Maxwell one has to expect power consumption will go back up, but for the time being it’s very pleasing to be able to get chart-topping performance inside of 165W. And the fact that this comes from the same company responsible for GTX 480 just 2 generations ago makes this the ultimate technical turnaround.

In conclusion, the GeForce GTX 980 represents another stellar performance from NVIDIA. Their reign at the top is not going to go unchallenged – AMD can’t match NVIDIA on performance, but they can sure drive down prices – but as was the case in 2012 the crown continues to securely reside in NVIDIA’s hands, and once again they have done the technical hard work to earn it.

Finally, as a reminder we will be following up this article next week with our look at GTX 980 SLI performance and a look at the GTX 970. Of the two cards launched today the GTX 970 is without a doubt the more interesting of the two thanks to its relatively low price compared to the performance NVIDIA is offering, but due to our aforementioned board issues we will not be able to take a look at it until next week. So until then stay tuned for the rest of our GM204 coverage.

Overclocking GTX 980
Comments Locked

274 Comments

View All Comments

  • kron123456789 - Friday, September 19, 2014 - link

    Look at "Load Power Consuption — Furmark" test. It's 80W lower with 980 than with 780Ti.
  • Carrier - Friday, September 19, 2014 - link

    Yes, but the 980's clock is significantly lowered for the FurMark test, down to 923MHz. The TDP should be fairly measured at speeds at which games actually run, 1150-1225MHz, because that is the amount of heat that we need to account for when cooling the system.
  • Ryan Smith - Friday, September 19, 2014 - link

    It doesn't really matter what the clockspeed is. The card is gated by both power and temperature. It can never draw more than its TDP.

    FurMark is a pure TDP test. All NVIDIA cards will reach 100% TDP, making it a good way to compare their various TDPs.
  • Carrier - Friday, September 19, 2014 - link

    If that is the case, then the charts are misleading. GTX 680 has a 195W TDP vs. GTX 770's 230W (going by Wikipedia), but the 680 uses 10W more in the FurMark test.

    I eagerly await your GTX 970 report. Other sites say that it barely saves 5W compared to the GTX 980, even after they correct for factory overclock. Or maybe power measurements at the wall aren't meant to be scrutinized so closely :)
  • Carrier - Friday, September 19, 2014 - link

    To follow up: in your GTX 770 review from May 2013, you measured the 680 at 332W in FurMark, and the 770 at 383W in FurMark. Those numbers seem more plausible.
  • Ryan Smith - Saturday, September 20, 2014 - link

    680 is a bit different because it's a GPU Boost 1.0 card. 2.0 included the hard TDP and did away with separate power targets. Actually what you'll see is that GTX 680 wants to draw 115% TDP with NVIDIA's current driver set under FurMark.
  • Carrier - Saturday, September 20, 2014 - link

    Thank you for the clarification.
  • wanderer27 - Friday, September 19, 2014 - link

    Power at the wall (AC) is going to be different than power at the GPU - which is coming from the DC PSU.

    There are loses and efficiency difference in converting from AC to DC (PSU), plus a little wiggle from MB and so forth.
  • solarscreen - Friday, September 19, 2014 - link

    Here you go:

    http://books.google.com/books?id=v3-1hVwHnHwC&...
  • PhilJ - Saturday, September 20, 2014 - link

    As stated in the article, the power figures are total system power draw. The GTX980 is throwing out nearly double the FPS of the GTX680, so this is causing the rest of the system (mostly the CPU) to work harder to feed the card. This in tun drives the total system power consumption up, despite the fact the GTX980 itself is drawing less power than the GTX680.

Log in

Don't have an account? Sign up now