Arm Holdings has announced the release of new chip blueprints and software tools designed to enhance smartphones’ ability to handle artificial intelligence (AI) tasks. The company also introduced changes in the delivery method of these blueprints, potentially accelerating their adoption in the industry.
Arm’s technology, which has been instrumental in the rise of smartphones, is also increasingly used in PCs and data centers due to its energy efficiency, Reuters news report said.
HIGHLIGHTS
Arm Compute Subsystems (CSS) for Client, brings together Armv9 benefits with validated and verified production ready implementations of new Arm CPUs and GPUs on 3nm process nodes to enable silicon partners to rapidly innovate and speed time to market.
AI-optimized Arm CSS for Client with next generation Cortex-X CPU, delivering highest year-on-year IPC uplift resulting in a 36 percent increase in performance; new Immortalis GPU brings a 37 percent uplift in graphics performance.
New KleidiAI software integrates with popular AI frameworks for seamless developer experiences; KleidiAI with Arm CSS improves performance of computing applications by leveraging a range of Arm’s acceleration technologies (NEON, SVE2 and SME2).
BENEFITS
For AI, Cortex-X925 provides 41 percent performance uplift to improve the responsiveness of on-device generative AI, like large language models (LLMs).
CSS for Client is the fastest Arm compute platform addressing demanding real-life Android workloads with greater than 30 percent increase on compute and graphics performance and 59 percent faster AI inference for broader AI/ML and computer vision (CV) workloads.
Arm Cortex-A725 CPU delivers 35 percent improvement in performance efficiency to target AI and mobile gaming use cases.
Arm Immortalis-G925 GPU delivers 37 percent more performance across a range of mobile gaming applications, as well as 34 percent more performance when measured over multiple AI and ML networks.
Smartphones remain Arm’s largest market, with the company providing intellectual property to major competitors like Apple and Android chip suppliers Qualcomm and MediaTek. The designs include central processing units (CPUs) optimized for AI tasks and new graphics processing units (GPUs). Arm is also offering software tools to facilitate the implementation of AI applications, such as chatbots, on its chips.
The significant shift comes in the delivery of these products. Traditionally, Arm provided specifications or abstract designs, leaving chip companies to create physical blueprints—an intricate process involving the arrangement of billions of transistors. For the new products, Arm collaborated with Samsung Electronics and Taiwan Semiconductor Manufacturing (TSMC) to produce ready-for-manufacture physical designs.
Chris Bergey, senior vice president and general manager of Arm’s client line of business, emphasized that Arm’s goal is not to compete with its customers but to expedite their time-to-market. This allows them to focus on other critical components of chips for PCs and phones, such as neural processing units (NPUs) that deliver superior AI performance. Microsoft’s latest AI features, for instance, require NPUs to function.
Currently, Arm does not supply NPU technology for phones and PCs. However, Chris Bergey stated that the company plans to offer more comprehensive designs, enabling chip firms to integrate their NPUs seamlessly. This strategy aims to support customers in achieving faster and more efficient development of AI-capable devices.
