- Arm’s Luex chips promise huge improvements to AI on the device
- Its CPUs offer up to 5x better AI performance
- CPUs are seen as the power center for AI
Arm has lifted the wrapping of its next generation of Luex chip design, optimized to run some local AI workloads on mobile devices.
Its architecture allows for four different design types ranging from energy -efficient cores to laptop to high performance cores to flagship smartphones.
The slats accelerated product cycles that result in tighter time scales and reduced margin for errors, arm says its integrated platforms combine CPU, GPU and software stacks to speed up time to the market.
Arm’s Lumex could be used in your next smartphone
Arm described LUMEX as its “new custom-built compute subsystem (CSS) platform to meet the growing requirements of AI experiences on device.”
Armv9.3 C1 CPU cluster includes built-in SME2 devices for accelerated AI, promising 5x better AI performance and 3x more efficiency compared to the previous generation.
Standard Benchmarks sees performance increases by 30% by a 15% speed in apps and 12% lower power use in daily workloads compared to the previous generation.
The four CPUs offered are C1-ULTRA for the Great Model Inferencing, C1-Premium for Multitasking, C1-Pro for video playback and C1-Nano for Wearables.
Mali G1-ULTRA GPU also enables 20% faster AI/ML inference than Immortalis-G295, as well as improvements across games such as 2x better beaming performance.
LUMEX also offers G1-Premium and G1-Pro settings-but no G1-NANO.
Interestingly, the arm CPUs positions like the universal AI engine, considering the lack of standardization in NPUs, although NPUs are starting to earn their place in PC chips.
Launch with LUMEX is a complete Android 16-ready software stack, SME2-enabled Kleidiai Libraries and Telemetry to analyze the performance and identify bottlenecks, allowing developers to tailor LUMEX for each model.
“Mobile Computing is going into a new era defined by how intelligence is built, scaled and delivered,” explained senior director Kinjal Dave.
When we look ahead, Arm notes that many popular Google apps are already SME2 enabled, which means they are ready to take advantage of improved AI features on device when the next generation hardware becomes available.
