19 May 2022

Industrial edge Inference server launched to help optimise AI

Digitalisation

Advantech’s HPC-6240+ASMB-622 industrial edge Inference server designed for the rapid deployment, management, and scaling of AI and inference workloads in the modern hybrid cloud, has recently been launched. The HPC-6240+ASMB-622 also works with the newly announced NVIDIA A2 Tensor Core GPU, an entry-level, low-power, compact accelerator for inference and edge workloads.

The opportunity for artificial intelligence (AI) to transform every industry is greater than ever. From thousands of sensors and Auto-Optical Inspection (AOI) equipment in smart factories to enhance the safety, accuracy, and efficiency, to over one billion smart city cameras working to ensure public safety, to the 500 million calls per day to contact centres, the demand for AI to serve these needs is enormous.

Inference is key to optimising production procedures, making them more convenient, preventing revenue loss, and increasing operational efficiency as we ascend into an AI economy. However, developing inference solutions from concept to deployment is not easy. Advantech HPC-6240+ASMB-622, powered by the soon to be available NVIDIA A2, offers a complete end-to-end stack and suite of products and services to deliver the performance, efficiency, and responsiveness that is critical to powering the next generation of AI inference in embedded devices. With only 20.5” depth and multiple expansion slots, this system is especially suitable in Industrial Equipment Manufactures (IEM), robotics, retail, intelligent video analytics (IVA), and other applications of AI at the edge.
Advantech’s HPC-6240+ASMB-622 is a 2U short-depth compact edge server with dual 3rd Gen Intel Xeon scalable processors. It provides 8 expansion slots and multiple PCIe for flexible GPU, NIC, Frame Grabber Card, and motion-control card integrations. Four PCIeX16 design supports up to four NVIDIA A2 GPUs for AI and HPC.

Low power requirement, compact size, and multiple expansion capability with four A2 GPUs, this solution empowers complex AI Auto-Optical Inspection and manufacturing equipment applications.

HPC-6240+ASMB-622 leverages Advantech’s thermal management system to increase airflow and pressure. This feature enables high computing workloads at the industrial edge by cooling GPU cards and reducing noise output.

It is also able to scale out from a single-GPU node to multi-GPU nodes when needed in industrial applications, especially in the areas of AOI, voice recognition, and translation.

Company info: Advantech