Arm, the British leader in semiconductor and software design, staged its Arm Everywhere China showcase in Shanghai to announce a suite of fresh AI‑computing innovations aimed at the mobile market. The centerpiece of the announcement is a comprehensive AI‑native ecosystem that includes the new AI‑centric compute platform CSS for Mobile 2 and the Mali G2‑Ultra NX graphics processor. This GPU is built around dedicated neural‑compute blocks, promising higher graphical fidelity while dramatically cutting heat output and power draw compared with traditional mobile GPUs.
Arm positions its on‑device AI solution as an open alternative to Nvidia’s controversial DLSS 5, arguing that its method stays truer to developers’ original artistic intent. While the company did not name specific products that will ship with the Mali G2‑Ultra NX, the predecessor Mali G1‑Ultra is already deployed in smartphones from Xiaomi, Vivo and OnePlus, suggesting a similar rollout path. Deyan Lazarov, a senior member of Arm’s GPU team within the Edge AI division, explained that the Mali G2‑Ultra NX has been under development for roughly two and a half years. Its primary goal is to give mobile developers access to compute‑intensive features such as real‑time ray tracing, a capability that has historically been limited to high‑end PCs and consoles.
“There was actually growing adoption of ray tracing in mobile titles,” Lazarov said. “The technology has been a bit slow to get going, but now we’re seeing more and more titles actually interested in enabling ray tracing.” The new chip integrates tightly with Unreal Engine, allowing developers to leverage advanced features like MegaLights.
Arm collaborated with Sumo Digital to produce a demo game, Neural Dawn, which showcases the Mali G2‑Ultra NX’s ability to render complex scenes with high visual quality at modest power budgets. Other upcoming titles that will exploit the chip include Tencent’s Arena Breakout Infinite, NetEase’s Where Winds Meet, and Infold Games’ Infinity Nikki. Lazarov emphasized that mobile devices face unique constraints: they cannot dissipate heat like a console or a desktop PC and must operate continuously on battery power.
“The thing that’s different about mobile phones is that they have different thermals and different power budgets from a console,” he noted. “They cannot just dissipate heat as much as a console can, as much as a PC can, and they are operating off of a battery all the time.” Arm’s answer is to fuse neural processing with the traditional graphics pipeline. By offloading portions of the rendering workload to dedicated neural accelerators, the GPU can render fewer native pixels and let the AI reconstruct the remainder.
This reduces both GPU compute cycles and memory traffic, leading to lower overall power consumption and higher system‑level efficiency. “So what that basically means is that you get this new efficiency, which helps remove some of the limitations that developers face. And it also helps them not have to worry about making trade‑offs as much as they would normally do,” Lazarov explained. To make the technology attractive to developers, Arm is adopting an open‑source software strategy.
All of its AI models—including Neural Super Sampling (NSS), Neural Super Sampling and Denoising (NSSD), and Neural Frame Rate Upscaling (NFRU)—are published on GitHub and Hugging Face. The models are convolution‑based rather than generative, meaning they do not hallucinate new content but instead learn how real images should look. “Our networks are not generative, so they’re not from the same nature as the latest DLSS model,” Lazarov said. “They’re convolution type networks, which means that they don’t imagine anything, they don’t create anything, they just kind of know what things need to look like.” Because the models are open, developers can fine‑tune them on their own art assets.
If a studio has a distinctive visual style, it can capture a dataset from its game, retrain Arm’s network, and ensure that upscaling and frame‑generation respect that style. This approach safeguards intellectual‑property control and eliminates the “black‑box” concerns associated with Nvidia’s proprietary DLSS, which cannot be retrained or inspected.
“DLSS is not open. It’s proprietary, it’s closed, it’s a black box, you don’t know what’s happening, you don’t know what it’s trained on,” Lazarov contrasted. “Our network is open, you can take it and make it work the way you want.” Arm also highlights that its solution was engineered from the ground up for mobile constraints such as power, bandwidth, and thermal limits. A DLSS‑style algorithm would quickly exceed those budgets on a smartphone, whereas Arm’s networks are deliberately lightweight.
In practice, Arm reports up to four‑fold gains in performance and efficiency, alongside a 70 % reduction in DRAM traffic—a major source of power draw on handheld devices. “The less you have to go out to external memory, the less power you burn,” Lazarov added. Performance figures illustrate the advantage. Running Neural Dawn on the previous‑generation Mali GPU capped at roughly 40 fps under ideal conditions and dropped to 15 fps in real‑world use.
The Mali G2‑Ultra NX, by contrast, sustains a smooth 60 fps experience with the same visual settings, thanks to AI‑assisted reconstruction that fills in three‑quarters of each frame from neural inference alone. On the tooling side, Arm currently offers plug‑ins for Unreal Engine and plans to extend support to Unity and other engines. An SDK provides a streamlined integration path for custom engines, enabling developers to adopt the technology without waiting for official plug‑ins. Lazarov noted that integrating Arm’s AI graphics into an existing shipped title can be accomplished in as little as three months, allowing studios to refresh older games with modern visual fidelity, better battery life, or higher frame rates.
In summary, Arm’s mobile‑first AI reconstruction strategy diverges sharply from Nvidia’s DLSS 5 model. By delivering open, convolution‑based networks that can be retrained on a developer’s own data, and by embedding neural accelerators directly into the GPU pipeline, Arm promises to give mobile game creators a powerful, flexible, and energy‑efficient toolset to bring console‑level graphics to handheld devices without sacrificing battery life or thermal headroom.