Nvidia DLSS 3 predicts frames to deliver next-level gaming performance – Digital Trends

Digital Trends may earn a commission when you buy through links on our site. Why trust us?Nvidia has just announced DLSS 3 at its GeForce Beyond event, a new generation of its deep learning super sampling technology that will be available on next-gen Nvidia RTX 40-Series graphics cards.DLSS 3 is a new AI that predicts entire frames instead of just pixels. This time around, it will even boost CPU-reliant games, and Nvidia showed off that capability in Microsoft Flight Simulator.Nvidia introduced DLSS 3 as part of its GTC 2022 keynote, announcing the tech as part of the perks delivered by the new RTX 40-Series graphics cards. The tech has four components, including a new optical flow accelerator and game engine motion vectors. DLSS 3 processes the previous frame and the new frame and then predicts how the scene is changing. As a result, DLSS 3 generates new frames all of its own, boosting gaming performance and visuals.Nvidia promises that DLSS 3 will be up to four times faster thanks to its ability to multiply frame rates with its new optical flow accelerator. The new tech actually bundles three different technologies into one, including the DLSS Super Resolution, DLSS Frame Generation, and Nvidia Reflex, which improves responsiveness and brings the latency down considerably. This is done by synchronizing the GPU and the CPU, and as Nvidia claims, it can reduce the latency by up to 2 times.The company’s CEO, Jensen Huang, talked about the capabilities of DLSS 3 and described the whole process, including how the technology is able to capture pixel-level information while also utilizing game engine motion vectors in order to follow the movement and geometry in each scene. In Nvidia’s example, shown in its blog post, DLSS 3 was able to reconstruct seven-eights of the total displayed pixels, resulting in a huge performance leap.DLSS 3 is able to boost the performance of games that traditionally rely more on the CPU than on the GPU, such as Microsoft Flight Simulator, because it allows the RTX 40-Series GPU to render the game at a much higher frame rate. Nvidia proved this by showing little clips from the game; with DLSS off, the frames per second (fps) hovered around the 65 mark, but with DLSS 3 on, the game was able to reach as high as 135 fps. The tech was also seen pushing new heights in Cyberpunk 2077.When all is said and done, DLSS 3 will “boost game performance by up to four times over brute-force rendering,” said Jensen Huang. Nvidia will release DLSS 3 in October, and more than 35 games and applications will be supporting it at that time. There’s also a fun new thing coming out: Portal RTX, a reimagined version of the iconic game, now with DLSS 3 and ray tracing.In addition to DLSS 3, Nvidia has also announced the new Shader Execution Reordering (SER) technology that will dynamically reorganize shader workloads in order to make them more efficient. This tech is said to boost shader performance by up to 2x, and as a result, offers a 25% in-game frame rate boost.Nvidia is launching three RTX 40-Series GPUs: the RTX 4090, available on October 12, and two versions of the RTX 4080 to follow in November.Apple Intelligence’s long-awaited rollout in China is getting closer to covering the company’s wider ecosystem. After securing regulatory approval for iPhones earlier this year, Apple has now completed another important registration process that could finally bring its AI features to iPads and MacBooks in the country.According to a Reuters report, Shanghai’s cyberspace regulator confirmed on November 9 that Apple Intelligence has completed registration for use on tablets and notebook computers. This is a major development for Apple, which has spent nearly two years navigating China’s regulatory requirements for generative AI services. It basically removes a previously outstanding hurdle for expanding Apple Intelligence beyond the iPhone.Meta has launched Muse Ember, its smallest and cheapest AI model yet. It isn’t trying to solve the world’s hardest problems. Instead, Meta designed it for the small, repetitive tasks AI agents keep doing, like using tools, fixing small bits of code, sorting requests, grabbing data from files, and reading lengthy documents.https://twitter.com/finkd/status/2119851180948152590I just gently tilted my head up, and the book I was reading on my Mac scrolled up. Last night, I was experimenting with a fusion Thai curry recipe and had nearly 20 tabs open on my laptop, which sat at a safe distance from the chopping board. To switch back and forth between the tabs, I didn’t have to touch the trackpad and get it messy. Looking to my left or right let me switch between tabs, and tilting my head toward either shoulder took me back and forth on the website pages I was reading. I interacted with my Mac without ever touching it. All of it was controlled by the AirPods in my ears.Upgrade your lifestyleDigital Trends helps readers keep tabs on the fast-paced world of tech with all the latest news, fun product reviews, insightful editorials, and one-of-a-kind sneak peeks.source