Armaster launches Star 100e edge-AI prototype with Cortex-M42
Armaster and Arm launched the Star 100e AIoT prototype platform, combining the Cortex-M42 CPU with the Arm Ethos-U55 NPU for low-power edge-AI workloads. Armaster says the FPGA-based system has run keyword detection, object recognition and automatic speech recognition, with vendor testing showing large inference gains over using Cortex-M42 alone. Cortex-M42 is based on Armv8.1-M and includes Helium vector processing, Arm Custom Instructions support and a compact AHB-based design.
The platform gives embedded-chip partners a reference architecture for combining CPU vector processing with dedicated NPU acceleration in cost- and area-sensitive devices, although the reported performance figures come from vendor testing.
11月18日,安谋科技(中国)有限公司(以下简称“安谋科技”)举办Arm® Cortex®-M CPU新品说明会,深度解析Arm Cortex-M42 CPU,并正式推出基于该产品的“星辰100e”AIoT原型平台。

Cortex-M42处理器面向对成本和面积敏感的智能端点设备打造,基于Armv8.1-M架构,兼具三大核心能力:
• Arm Helium™技术:加速向量处理,带来更强的机器学习(ML)和数字信号处理(DSP)性能。• Arm自定义指令(ACI):支持芯片合作伙伴实现专用指令,针对特定工作负载优化处理性能。• 基于AHB的紧凑设计:沿用成熟的微控制器(MCU)系统架构,无需复杂的内存子系统,可高效集成至现有设计中。
这些能力共同为芯片合作伙伴提供了一条更简便的演进路径:使他们能够在现有Arm Cortex-M4和Arm Cortex-M33产品基础上轻松升级,同时保留在成熟MCU设计中的大部分既有投入。
#Armaster#Arm#Cortex-M42#Arm Ethos-U55#Arm Helium#Arm Custom Instructions