A compact computing module combines processing, graphics and AI capabilities for industrial applications.

SECO has launched the SOM-COMe-CT6-R8000, its COM Express 3.1 Type 6 Compact module based on AMD Ryzen Embedded 8000 Series processors. The module combines x86 processing, an embedded AMD XDNA Neural Processing Unit (NPU) and integrated AMD RDNA 3 graphics. It is designed for applications that require high-performance computing, local AI acceleration and advanced graphics, such as industrial edge applications.
The module offers processor options with up to 6 cores and 16 threads. Within its COM Express Type 6 Compact architecture, it has integrated AMD RDNA 3 graphics with up to 6 Work Group Processors (WGPs). The NPU is capable of delivering 16 tera operations per second (TOPS) of AI performance, reaching 39 TOPS when combined with the central processing unit (CPU) and graphics processing unit (GPU). It also comes with two Double Data Rate 5 (DDR5)-5600 Small Outline Dual In-line Memory Module (SO-DIMM) slots. It supports up to four independent displays.
System designers can combine general-purpose computing, AI processing and advanced graphics using this module. The company claims that bringing the CPU, GPU and NPU together in one module enables processing and AI inference to run locally. Hence, the module can support various applications where efficient data processing, system integration and responsiveness are key.
This combination is also suitable for applications ranging from industrial automation, intelligent control systems, robotics and Physical AI to advanced HMIs and machine vision.
“As AI becomes an integral part of more industrial applications, OEMs need computing platforms that can support increasingly demanding workloads without sacrificing the flexibility required to design around their specific use cases,” said Francesco Vaiani, Product Manager Team Leader SOM & SYS at SECO. “With the SOM-COMe-CT6-R8000, we are expanding our COM Express offering with a platform that brings together x86 computing, graphics and dedicated AI acceleration, giving customers a scalable foundation for the next generation of intelligent edge systems.”
Click here for the original announcement.





