ICP Germany Unveils Mustang-M2BM-MX2 AI Accelerator Card

January 31, 2020 Alix Paultre

ICP Germany recently released the Mustang-M2BM-MX2 card AI accelerator cards, adding to their portfolio of Mini PCIe and PCIe based solutions with an M.2 PCIe plug-in card variant. The 22x80mm cards have two Intel Movidius Myriad X MA2485 Vision Processing Units (VPUs) to provide AI functionality through 16 SHAVES cores each. Each Myriad VPU delivers up to one trillion calculations per second. 

With a maximum power of 8 watts, the Mustang-M2BM-MX2 is particularly suitable for low-power AI applications. Additionally, the multi-channel capability allows each VPU to be assigned a different DL topology. Its compatibility with the Open Visual Inference Neural Network Optimization (OpenVINOTM) Toolkit from Intel ensures a simple and rapid integration of various AI training models. 

The Mustang-M2BM-MX2 is compatible with common Linux operating systems, CentOS, and Windows 10, and supports numerous architectures and topologies of neural networks, such as AlexNet, GoogleNet, SqueezeNet and Yolo. In addition to other AI accelerator cards, ICP also offers ready-to-use embedded systems, which are also equipped with AI functionality.

The card and other products can be seen live at the Embedded World in Nuremberg in Hall 1 Stand 201.

www.icp-deutschland.de

 
Previous Article
Radiflow and Fraunhofer Launch Joint Research to Apply AI in Industrial Cybersecurity
Radiflow and Fraunhofer Launch Joint Research to Apply AI in Industrial Cybersecurity

Radiflow and the Fraunhofer Institute of Optronics, System Technologies, and Image Exploitation (IOSB) laun...

Next Article
WIN Enterprises Announces 2U HPC with Intel Skylake-SP/Cascade Lake-SP processor, DDR4, 8 PCIe X8 slot and Redundant PSU
WIN Enterprises Announces 2U HPC with Intel Skylake-SP/Cascade Lake-SP processor, DDR4, 8 PCIe X8 slot and Redundant PSU

The PL-82020 HPC server can support hybrid configurations in the Cloud, IoT, and Call Center applications.