🚀 COMX C710 AI Module for Next-Gen Robotics from ARBOR Technology! 🤖

[Elif Özaksu]

ARBOR Technology Transforms the World of Robotics and Automation!​

ARBOR Technology has introduced the COMX-C710 computer module, powered by AMD Ryzen AI Embedded X100 processors. This module offers high-performance heterogeneous computing for industrial automation, medical systems, and autonomous devices.

Architecture and Hardware Features​

• The COMX-C710 conforms to the COM-HPC Client Size C form factor, measuring 120 mm x 160 mm.
  
• It provides up to 126 TOPS of total computing performance for AI workloads.
  
• It includes a dedicated neural processing unit (NPU) based on the XDNA 2 architecture, with a capacity of 50 TOPS.
  
• High-density LPDDR5x memory maximizes data transfer speeds while minimizing latency.
  
• It offers wide voltage range and extended operating temperature support for demanding operating environments.
  

Task Distribution in Heterogeneous Computing​

The platform distributes computing workloads across specialized hardware components to optimize energy efficiency and processing speed:

• Central Processing Unit (CPU): Manages deterministic operational logic, system control, and high-level decision algorithms.
  
• Graphics Processing Unit (GPU): Accelerates multi-camera visual processing pipelines, real-time spatial mapping, and simultaneous localization and mapping (SLAM) computations.
  
• Neural Processing Unit (NPU): Processes object detection, classification, and scene segmentation models, including YOLO neural network architectures.
  

Sumit Shah from AMD states that the integration of CPU, GPU, and NPU on a single chip provides low-latency processing for edge automation platforms. Vincent Liao from ARBOR Technology emphasizes that combining heterogeneous computing units in standardized module form factors reduces system design complexity in medical and robotic equipment.

Target Applications and Industrial Deployment Options​

This hardware design integrates real-time motion control, image capture, and neural inference into a single computing module. Target deployment environments include autonomous mobile robots, collaborative robotic arms, industrial automation gateways, high-resolution medical imaging devices, endoscopes, and patient monitoring systems. By combining multiple computing subsystems in a standardized module interface, deployment complexity in multi-sensor edge setups is reduced.

Additional Information​

The COM-HPC Client Size C form factor defines high-speed interconnect pinouts that support high-lane-count PCIe channels and high-bandwidth memory buses compared to older standards like COM Express Type 6. In physical AI applications, integrated neural processing units compete with discrete PCIe accelerator cards. Embedded platforms with integrated NPU architectures achieve lower power consumption metrics per TOPS by avoiding external bus transfer overheads and utilizing low-power memory interfaces like LPDDR5x. Standard benchmarking criteria for embedded modules in this class focus on inference efficiency (frames per second/watt) on standardized models like YOLOv8, memory bandwidth utilization, and thermal dissipation stability in fanless enclosures.