Saturday, April 27, 2024

New Intel Core Ultra Processor-Based COM Express Compact Modules For AI At The Edge

- Advertisement -

With features like multiple P-cores, energy-efficient E-cores, and a powerful Intel Arc GPU, coupled with an integrated Neural Processing Unit (NPU) for advanced AI processing, these modules are set to revolutionise industries like healthcare and industrial automation. 

Congatec has unveiled its most recent series of COM Express Compact modules featuring the Intel Core Ultra processors. These modules offer an exceptional blend of diverse compute engines, encompassing CPU, GPU, and NPU, making them an excellent choice for efficiently handling demanding AI workloads at the edge.

In addition to the robust P-cores and energy-efficient E-cores designed for general computing tasks and the high-performance Intel Arc GPU tailored for graphics-intensive work, the integrated Neural Processing Unit (NPU) known as Intel AI Boost brings advanced neural processing capabilities to the overall computational framework. This integrated NPU streamlines the integration of advanced artificial intelligence workloads with reduced system complexity and costs compared to separate accelerators. 

- Advertisement -

Key features

  • The capacity for up to 6 P-Cores and up to 8 E-Cores, supporting up to 20 threads
  • Integrate the Intel Arc GPU with up to 8 Xe Cores and up to 128 EUs
  • Capable of handling stunning graphics at up to 2x 8K resolutions, along with rapid GPGPU-based vision data (pre)processing. 
  • Support for 96 GB DDR SO-DIMM with in-band ECC at 5600 MT/s enhances power-efficient high data throughput and minimises latency.

The new Intel Core Ultra processor-based Computer-on-Modules offer significant advantages, particularly in surgical robotics, medical imaging, and diagnostic systems, where AI-driven insights can aid healthcare professionals. Furthermore, these modules find application in enhancing situational awareness in industrial settings, including inspection systems, stationary robotic arms, autonomous mobile robots (AMRs), and autonomous guided vehicles (AGVs).

These modules benefit from the company’s comprehensive, performance-driven OEM ecosystem, which encompasses efficient active and passive cooling solutions and readily available evaluation carrier boards. Customers can procure modules with pre-evaluated real-time hypervisor technology provided by Real-Time Systems, enabling virtual machine deployments and workload consolidation in edge computing scenarios. A range of service offerings is available, such as shock and vibration testing for custom system designs, temperature screening, and high-speed signal compliance testing.

Akanksha Gaur
Akanksha Gaur
Akanksha Sondhi Gaur is a journalist at EFY. She has a German patent and brings a robust blend of 7 years of industrial & academic prowess to the table. Passionate about electronics, she has penned numerous research papers showcasing her expertise and keen insight.

SHARE YOUR THOUGHTS & COMMENTS

Unique DIY Projects

Electronics News

Truly Innovative Tech

MOst Popular Videos

Electronics Components

Calculators