Newshot

Arm Technology launches "Xingchen 100e" AIoT prototype platform based on Arm Cortex-M42 CPU

AI summary

Arm Technology (China) Co., Ltd. held an Arm Cortex-M CPU launch event today, detailing the Arm Cortex-M42 CPU and officially launching the "Xingchen 100e" AIoT prototype platform based on it. The Cortex-M42 processor targets cost- and area-sensitive intelligent endpoint devices, is based on the Armv8.1-M architecture, and combines three core capabilities: Arm Helium technology, Arm Custom Instructions (ACI), and a compact AHB-based design. Arm Technology says the new-generation AIoT prototype platform "Xingchen 100e" uses Cortex-M42 + Ethos-U55, and that the next-generation "Xingchen" prototype platform with higher performance will launch in 2027.

Translation(model translation, not the source's own text)

Arm China Launches "Stellar 100e" AIoT Prototype Platform Based on Arm Cortex-M42 CPU

IT之家 November 18 news: Arm China (安谋科技) today held a launch briefing for new Arm Cortex-M CPU products, detailing the Arm Cortex-M42 CPU and officially introducing the "Stellar 100e" AIoT prototype platform based on it.

The Cortex-M42 processor is built for intelligent endpoint devices sensitive to cost and area, based on the Armv8.1-M architecture, and combines three core capabilities:

  • Arm Helium technology: accelerates vector processing, delivering stronger machine learning (ML) and digital signal processing (DSP) performance.
  • Arm Custom Instructions (ACI): enables chip partners to implement dedicated instructions to optimize processing performance for specific workloads.
  • Compact AHB-based design: retains the mature microcontroller (MCU) system architecture, requires no complex memory subsystem, and can be efficiently integrated into existing designs.

According to the company, Cortex-M42 offers chip partners a solution with a smaller area and lower power consumption than Arm Cortex-M52, suitable for designs that do not require a rich memory subsystem (including optional cache and tightly coupled memory, TCM). In a configuration using the TSMC 22ULL process at 150MHz, compared with Cortex-M52, Cortex-M42 delivers similar scalar and vector performance while reducing silicon area by 10% and lowering power consumption by 15%.

IT之家 has learned that the product was developed by Arm China in collaboration with Arm, is named "Stellar" STAR-MC3 in the Chinese market, and is now officially included in Arm's global Cortex-M product roadmap.

According to the company, the new-generation AIoT prototype platform "Stellar 100e" uses Cortex-M42 + Ethos-U55. Arm China has currently built the "Stellar 100e" system on an FPGA platform, and has already run a series of AI use cases including keyword detection, object recognition, and speech recognition.

Measured data shows that, compared with using the Cortex-M42 processor alone, pairing Cortex-M42 with Ethos-U55 improves keyword detection inference performance by 95 times; object recognition inference performance by more than 132 times; and automatic speech recognition performance by more than 340 times.

According to the introduction, the first-generation platform "Stellar 300" uses Cortex-M52 ("Stellar" STAR-MC2) and Ethos-U55, and already fully supports mainstream small models; a higher-performance next-generation "Stellar" prototype platform will be launched in 2027.

Related Articles

  • Reuters: Arm chief Haas enters the field of candidates to succeed 黄仁勋, having worked at 英伟达 for 7 years
  • Arm launches Cortex-M42 processor: vector compute up to 3 times that of the previous generation, bringing local AI to more small devices
  • Arm Q2 FY2027 revenue $1.44 billion, up 27% year over year, a record high for Q2, GAAP net income $130 million, down 45% year over year
  • ECARX and Arm sign memorandum of cooperation to jointly develop next-generation high-performance AI computing platforms for the mobility sector and cross-industry scenarios
  • 英伟达 updates path tracing tool for developers: 20% performance improvement, support for Windows on Arm
  • Linux frequency scaling policy sparks discussion: Huawei suggests enabling CPU Boost by default, Arm engineer raises objections

The translation is machine-generated and individual terms may be off. Nothing is rewritten or cut; the original is authoritative.

Published by IT之家
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗