Arm CSS for Client is intended to provide leading AI-based experiences and make it easier and faster for the company’s silicon partners to build Arm-based solutions and get to market quickly.
CSS for Client provides the foundational computing elements for SoCs and features the latest Armv9.2 CPUs and Immortalis GPUs, as well as production ready physical implementations for CPU and GPU on 3nm processes and the latest Corelink System Interconnect and System Memory Management Units (SMMUs).
“We are co-designing and delivering CPU and GPU physical implementations, which includes tape-out ready Cortex-X925 CPU and Immortalis-G925 physical implementations for 3nm,” explained Arm. “This helps our partners to access the full PPA benefits on the 3nm process, while shortening silicon development and deployment timelines through the production-ready silicon solutions.”
According to Arm, the new Arm Cortex-X925 delivers the highest year-on-year performance uplift in the history of Cortex-X.
By taking advantage of the leading edge 3nm process nodes, assuming a 3.8GHz clock rate and maximum cache size, the result is a 36 percent increase in single-thread performance when comparing to 2023 smartphone flagship 4nm SoCs, according to Arm, while for AI, the Cortex-X925 provides a 41 percent performance uplift to dramatically improve the responsiveness of on-device generative AI, like large language models (LLMs).
While Immortalis-G925 is for the flagship smartphone market, the highly scalable new GPU family, including Arm Mali-G725 and Mali-G625 GPUs, targets a broad range of consumer device markets, from premium mobile handsets to smartwatches and XR wearables.
To enable developers to land these innovations quickly at the highest performance, Arm is also introducing Arm Kleidi, which includes KleidiAI for AI workloads and KleidiCV for computer vision applications.
KleidiAI is a set of compute kernels for developers of AI frameworks, providing them with access to the best performance possible on Arm CPUs, across a wide range of devices, with support for key Arm architectural features such as NEON, SVE2 and SME2.
KleidiAI integrates with AI frameworks, such as PyTorch, Tensorflow and MediaPipe, accelerating the performance of key models including Meta Llama 3 and Phi-3. It is also backwards and forwards compatible to ensure Arm is future fit as we bring additional technologies to market.
