en.Wedoany.com Reported - Axiomtek has introduced the CEM570 COM Express Type 6 Basic module, powered by the Intel Core Ultra processor series, designed for edge AI applications in medical, transportation, defense, robotics, heavy industry, and energy sectors.
The CEM570 module features up to a 14-core, 20-thread Intel Core Ultra processor, integrating Intel Graphics and a dedicated NPU to enhance AI inference throughput and multitasking efficiency within power envelopes of 15W, 28W, and 45W. This architecture aims to reduce reliance on discrete graphics cards, simplifying system design and lowering power consumption.
In terms of I/O expansion, the CEM570 offers up to 20 PCIe lanes (including PCIe Gen 4 interfaces), onboard NVMe storage (up to 512GB), up to four USB 3.2 Gen 2 ports, eight USB 2.0 interfaces, dual SATA 3.0, and 2.5GbE Ethernet based on the Intel I226. The platform supports simultaneous transmission from multiple high-definition cameras and sensors, ensuring low latency and deterministic system response, making it suitable for machine vision, automated optical inspection (AOI), robotics, and medical imaging deployments.
The CEM570 supports dual-channel DDR5-5600 SO-DIMM memory with a maximum capacity of 96GB, providing higher memory bandwidth compared to DDR4 platforms. The module adopts the industry-standard COM Express Type 6 Basic form factor (125×95 mm), allowing customers to upgrade existing carrier boards without significant redesign. Axiomtek states that this plug-and-play approach can reduce development cycles by over 60% and lower engineering costs.
The module offers an optional wide temperature operating range (-40°C to +85°C), vibration resistance up to 3.5 Grms, and supports TPM 2.0 security features, making it suitable for harsh industrial environments. Axiomtek provides a long-term support commitment of 7 to 10 years for this platform.
Kevin Lin, Product Manager of Axiomtek's EDS Division, stated that the CEM570 is designed to help customers accelerate the transition from traditional embedded platforms to AI edge systems, reducing deployment complexity by combining processors, AI acceleration, high-speed connectivity, and COM Express compatibility.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
