Cortex-A320 CPU and Ethos-U85 NPU Set New Industry Standards
Summary
The platform’s Armv9.2 architecture supports security features like Pointer Authentication (PAC), Branch Target Identification (BTI) and Memory Tagging Extension (MTE) to even the smallest Cortex-A devices while operating in rough environments managing sensitive data. Delivering AI capabilities and tools for developers, the Cortex-A320 extends the Armv9 architecture to IoT, optimizing power efficiency and ensuring software compatibility. It is designed to enhance AI and ML workloads on Arm-based CPUs with no additional developer work required. KleidiAI is integrated into general IoT AI frameworks such as Llama.cpp and ExecuTorch or LiteRT via XNNPACK, increasing the efficiency of key models, including Meta Llama 3 and Phi-3. This seamless integration between the two technologies provides an optimized solution for developers to build modern edge AI applications like anomaly detection in precision agriculture, smart manufacturing, and autonomous vehicles,” commented Yasser Alsaied, Vice President of loT, AWS