Arm, the British chip and software design firm, recently staged its Arm Everywhere China showcase in Shanghai, unveiling a suite of fresh AI‑computing solutions aimed at the mobile market. Central to the announcement is the AI‑native compute platform CSS for Mobile 2 and the new Mali G2‑Ultra NX GPU, a processor built around neural‑accelerated graphics that promises higher visual fidelity while keeping heat and power draw low. Arm positions its on‑device AI graphics pipeline as a more transparent alternative to Nvidia’s controversial DLSS 5, aligning more closely with developers’ original creative intent.
While Arm did not name specific products that will ship with the Mali G2‑Ultra NX, its predecessor, the Mali G1‑Ultra, already powers devices from Xiaomi, Vivo and OnePlus, suggesting a similar rollout path for the new silicon. Deyan Lazarov, a member of Arm’s GPU team within the Edge AI division, explained that the G2‑Ultra NX has been in development for roughly two and a half years. Its primary goal is to give mobile developers access to compute‑heavy techniques such as ray tracing, which have traditionally been confined to high‑end PCs and consoles.
"We’ve seen a steady rise in mobile titles experimenting with ray tracing," Lazarov noted. "It was a slow start, but now more games are actively looking to add that level of realism." The chip’s capabilities have already been demonstrated in a partnership with Sumo Digital, which produced the demo game Neural Dawn to showcase the Mali G2‑Ultra NX’s performance. The GPU also supports Unreal Engine features like MegaLights, enabling developers to integrate sophisticated lighting without sacrificing battery life.
Lazarov described the target audience as "mobile‑first games that want desktop‑grade visuals" as well as cross‑platform titles that need to deliver a consistent experience whether played on a console at home or on a train in London. He highlighted upcoming games that will leverage the new hardware, including Tencent’s Arena Breakout Infinite, NetEase’s Where Winds Meet, and Infold Games’ Infinity Nikki. One of the core challenges for smartphones is their limited thermal envelope and power budget compared with consoles or PCs. "A phone can’t dump heat the way a console can, and it runs on a battery," Lazarov explained.
Arm’s answer is to blend neural processing with the traditional rendering pipeline, offloading part of the GPU’s workload to dedicated neuro‑accelerators. This reduces the amount of work the GPU must perform, cuts power consumption, and ultimately improves overall system efficiency. The result, according to Lazarov, is "new efficiency that removes many of the trade‑offs developers usually face." With that headroom, developers can choose to reinvest saved resources into higher visual fidelity, smoother frame rates, longer battery life, or any combination thereof.
To make this possible, Arm is taking an open‑software stance, releasing a suite of tools and publishing its neural networks on public repositories such as GitHub and Hugging Face. Key components of Arm’s AI graphics stack include Neural Super Sampling (NSS), Neural Super Sampling and Denoising (NSSD), and Neural Frame Rate Upscaling (NFRU). These technologies can upscale lower‑resolution images, add extra rays for better lighting, and generate additional frames using AI‑driven reconstruction.
Lazarov illustrated the process with a two‑frame example: in the first frame the GPU renders only 25 % of the image while the neuro‑accelerators reconstruct the remaining three‑quarters via NSS; in the second frame the entire image is produced by the neuro‑accelerators, with the GPU doing virtually no traditional rendering. Nvidia’s DLSS 5 also uses AI to enhance images, but Arm argues its approach is fundamentally different. "Our networks are not generative; they’re convolutional, so they don’t imagine new content—they simply know how existing content should look," Lazarov said.
Arm trains its models on real‑world data and makes the trained weights publicly available, allowing developers to fine‑tune the networks with their own art styles. This openness prevents the loss of intellectual‑property control that can occur with proprietary, black‑box solutions like DLSS, where developers cannot see the training data or modify the model.
Another distinction is the mobile‑first design philosophy. Arm’s networks are built to respect the strict power, bandwidth, and memory constraints of smartphones.
"If you tried to run DLSS on a phone, you’d instantly blow past the power budget," Lazarov warned. By contrast, Arm reports up to four‑fold improvements in performance and efficiency, alongside a 70 % reduction in DRAM traffic—a major source of power draw on mobile devices. Performance numbers reinforce the claim.
When pushed to its limits, the previous‑generation Mali GPU could only run Neural Dawn at about 40 fps under ideal conditions and dropped to 15 fps in typical use. The G2‑Ultra NX comfortably reaches 60 fps, delivering a smoother experience without overheating. From a developer tooling perspective, Arm currently offers Unreal Engine plug‑ins and plans to expand support to Unity and other engines. The company recently announced a partnership with Unity China, signaling a broader strategy.
For studios using custom engines, Arm provides an SDK that streamlines integration, allowing teams to add AI‑native graphics to existing titles in as little as three months. Lazarov emphasized that Neural Dawn was built by a small team—fewer than 20 people—in under 18 months, illustrating how Arm’s technology can accelerate development cycles. By providing open, efficient, and mobile‑centric AI reconstruction, Arm aims to empower developers to quickly elevate the visual quality of both new and legacy games while staying within the tight power envelopes of modern smartphones.