German embedded computing company Congatec has introduced a module for compute-intensive physical AI applications.

The application-ready aReady.Com Conga-HPC/cRX1 has been designed for physical AI applications that consolidate perception, intelligence and actuation to executecomplex tasks in dynamic operating environments. Typical applications include robotics, autonomous commercial vehicles for smart farming, logistics and forestry, as well as medical technology and industrial automation.

The Com-HPC Client Size C module has up to 16 AMD Zen 5 CPU cores, up to 40 compute units of the integrated AMD Radeon RDNA 3.5 GPU, and a dedicated NPU. Its integrated AI and FP32 compute performance eliminates the need for discrete AI accelerator cards in many target applications. It supports industrial temperatures from -40 to +85˚C.

The module, part of the AMD Kria AI SoM portfolio, leverages the AMD Ryzen AI Embedded X100 series with up to 16 Zen 5 CPU cores for time-critical, sequential workloads such as real-time control, sensor fusion, planning and decision-making. The integrated GPU delivers up to 59Tops of INT8 AI inference performance and up to 29.7Tflops of FP32 compute performance, accelerating highly parallel workloads such as perception and object detection in collaborative robots and autonomous vehicles.

It also enables the local execution of large language models (LLMs). The dedicated NPU additionally provides up to 50Tops of AI performance for always-on AI workloads such as object detection and recognition, speech recognition, and image processing.

“Physical AI applications are placing ever-increasing demands on embedded systems,” said Florian Drittenthaler, product line manager at Congatec (www.congatec.com). “Our Conga-HPC/cRX1, powered by AMD Ryzen AI Embedded X100 series processors, delivers the highest performance currently available in a Com-HPC client module. This enables OEMs to eliminate the need for discrete AI accelerator cards in many applications, allowing them to develop more compact, energy-efficient, reliable and cost-effective embedded edge systems with a lower total cost of ownership.”

Sumit Shah from AMD (www.amd.com) added: “The next wave of embedded innovation will be defined by delivering more intelligence in smaller, more power-efficient designs. AMD Ryzen AI Embedded X100 series processors integrate CPU, GPU and NPU capabilities into a single platform, reducing system complexity while delivering deterministic performance and the efficiency required for real-world AI at the edge.”

Further information on the Conga-HPC/cRX1 computers-on-module can be found at: www.congatec.com/en/products/com-hpc/conga-hpccrx1/.