NVIDIA DLSS is a new ray tracing technology that promises to make the process of rendering 3D games and movies faster and more accurate. The technology is based on the company’s Tegra processor, which is used in many of today’s top-selling devices like the iPhone and Android devices. DLSS uses multiple streams of data to create a three-dimensional image, which can be processed much faster than traditional ray tracing methods. This means that you can create images that are more accurate and realistic, making them easier to produce for games and movies. The Tegra processor also makes it possible to use less memory, so you can render larger images with less impact on your device’s performance. This means that you can use DLSS in even more demanding games and movies, making them run smoother and faster. DLSS is already being used by some of the world’s most popular gaming platforms like Unreal Engine 4 and Unity3D. It’s likely that it will become even more popular as time goes on, as it offers a much faster and more accurate way to create 3D graphics.
At NVIDIA’s CES 2019 presentation, the company showed off a new technology called DLSS. In demonstrations, it all but eliminates the performance hit taken in games that enable fancy new ray-tracing graphics on RTX cards. But how does it work?
What Is DLSS?
DLSS stands for “deep learning super-sampling.” There are two parts to this idea, but let’s focus on the second one first: super-sampling.
Super-sampling is something you can do on your machine right now with a lot of games. It essentially renders the game at a resolution beyond what your monitor can support. That sounds strange, but it can help smooth out some of the harsh edges in polygonal graphics. NVIDIA and AMD cards already support this technology, as do some PC games all on their own. To learn more about super-sampling, check out this article.
Now, on to the “deep learning” part. Deep learning is something of a nebulous term: it basically means tons and tons of computations run on high-powered hardware in a process that improves over time. Some applications call this “artificial intelligence” (AI), but that’s a misnomer; the system isn’t “learning” in any human sense, it’s just getting better at a repetitive process.
NVIDIA’s DLSS system runs super-sampling on one specific game, over and over again, on the graphics cards in its massive data centers. It computes the best ways to apply the super-sampling technique to a game with repetitive processing on that game’s visuals—the polygons and textures that make up what you see on your screen. The “deep learning” part of the process comes into play here; the system learns as much as it possibly can about the way that the game looks, and how to make it look better.
Combine super-sampling for smoother polygon lines and textures with deep learning for applying general improvements to a game, and you get DLSS. Picture-improving techniques, already calculated at NVIDIA’s data centers, are applied on the fly via the Tensor processing cores in the RTX card.
NVIDIA engineers explained and demonstrated the process to us, running on a graphics benchmark at CES. The improvements over a non-DLSS setup were impressive, with smoother, more even textures and polygons evident. This was true even when the DLSS machine was rendering its graphics at a lower output (1080p) than the non-DLSS machine (1440p).
How Does It Make A Game Run Faster?
The DLSS system applies generalized improvements to a game’s visuals, especially if you’re running the game with NVIDIA’s ray-tracing enhancements enabled. Ray tracing, first introduced with RTX-series cards, allows for more accurate reflections, shadows, and diffusion of light with some amazing results. We’ve already covered the ways ray tracing can improve in-game visuals.
Unfortunately, ray tracing also increases the load on the GPU. The load is so high that many games fall below that desirable 60 frames-per-second mark, even when using the latest NVIDIA cards and high-end components in the rest of the PC.
Using the pre-calculated improvements of DLSS, which the RTX GPUs in NVIDIA’s data centers have already number crunched, can smooth out the performance of RTX-enabled games. In its CES demonstration, a game with ray tracing and DLSS both enabled played within a frame or two of the game running without any ray tracing enabled at all. To put it as simply as possible: DLSS enables games to run much faster with more fancy lighting effects.
NVIDIA tells us the process isn’t perfect: enabling DLSS might wash out textures or geometry in some rare cases. But overall, the improvement is dramatic and well worth enabling if it’s an option.
Can My Card Use DLSS?
DLSS is a feature of NVIDIA’s proprietary Tensor processing core, present on the Turing GPU architecture in the new RTX cards. If you have a GeForce RTX graphics card, you can use DLSS. If you don’t, then you can’t. So, the still-popular GeForce GTX 900 and 1000 series cards cannot take advantage of DLSS.
Do I Need A Web Connection To Use It?
No. While the DLSS process makes use of vast amounts of cloud computing hardware—huge NVIDIA server farms packed to the gills with industrial versions of RTX graphics cards—the process runs on your local PC once the system is set up and enabled. Just make sure you’re running the latest drivers.
Is My Game Compatible With DLSS?
Here’s the rub: the deep learning part of DLSS requires months of processing in NVIDIA’s data centers before it can be applied to PC games. So for every new game that comes out, NVIDIA needs to run its gigantic GPU arrays for a long time in order to get DLSS ready.
Once the heavy lifting is done, NVIDIA will update its GPU drivers and enable DLSS on the new games, at which point the developer can enable it by default or allow it as a graphics option in the settings menu. Because the deep learning system has to look at the geometry and textures of each game individually to improve the performance of that specific game, there’s no way around this “one game at a time” approach. It will get faster as NVIDIA improves it—possibly shaving the time down to weeks or days for one game—but at the moment it takes a while.
Play Video
At the time of writing (January 2019), only one game has DLSS that you can enable on a gaming PC at home: Final Fantasy XV. Even that is in a beta form and only works on the highest resolutions. Early testing shows that, indeed, it boosts framerates by 10-15 FPS—about the same amount you lose by enabling RTX ray tracing in other games. (Right now FFXV doesn’t support ray tracing, so the DLSS boost isn’t being applied where it’s really needed.)
NVIDIA has announced a list of other existing and upcoming games that will support DLSS eventually—presumably the company is running its data centers at capacity to get it ready. At present, NVIDIA has confirmed upcoming DLSS support for twenty-five games, with notable titles including Hellblade: Senua’s Sacrifice, ARK: Survival Evolved, Atomic Heart, Hitman 2, Mechwarrior V, Playerunknown’s Battlegrounds, Shadow of the Tomb Raider, and We Happy Few. At CES the company also announced that Battlefield V and the upcoming Anthem will support DLSS—the latter might even have the processing done by the time it’s ready for release.
Play Video
Games that will support both RTX-exclusive ray tracing effects, and the performance-boosting DLSS system, are a short list:
Anthem Atomic Heart Battlefield V MechWarrior V Shadow of the Tomb Raider Justice Online JX3
Naturally, this list will grow as developers become more comfortable with ray tracing, NVIDIA smooths and speeds up its DLSS computation process, and PC gamers demand access to the full features of their RTX-branded graphics cards.
