Small AI accelerator card for the Edge

13 AUGUST 2019

With the Mustang-MPCIE-MX2 card, ICP Deutschland expands its portfolio of KI accelerator cards with a Mini PCIe plug-in card variant. The Mini PCIe format enables system integrators to build small embedded PC systems with KI functionality for deep learning inference systems. The KI functionality is provided by two Intel® Movidius™ Myriad™ X MA2485 Vision Processing Units (VPUs). With only 5 watts, the Mustang MPCIE-MX2 is particularly suitable for low-power AI applications without sacrificing performance. The multi-channel capability allows each VPU to be assigned a different DL topology. Thus, calculations can be performed simultaneously, and object recognition and face recognition can be performed simultaneously. With compatibility to the Open Visual Inference Neural Network Optimization (OpenVINOTM) Toolkit from Intel®, various AI training models can be integrated directly at the edge. The OpenVINOTM Toolkit optimizes the performance of the training model and scales it to the target system. Due to the fast and optimized integration, developers as well as customers benefit from lower development costs.

The Mustang MPCIE-MX2 is compatible with popular Linux operating systems such as Ubuntu, CentOS and Windows® 10. Numerous architectures and topologies of neural networks are supported, such as AlexNet, GoogleNet, SqueezeNet and Yolo. In addition to other KI accelerator cards, ICP also offers embedded systems that perfectly match the new Mustang MPCIE-MX2.

Specifications

  • KI accelerator card in Mini PCIe form factor
  • Two Intel® MovidiusTM MyriadTM X MA2485 VPUs
  • Low power consumption of 5 watts
  • Operating temperature 0~50 °C
  • Powered by Intel® Open VINO Toolkit

Applications

  • Acceleration of Deep-Learning Inference Systems
  • Object recognition
  • Face recognition
  • AIoT Edge Computer

ICP Deutschland

Leave a Reply

Your email address will not be published. Required fields are marked *

  • We use your personal data ONLY to respond to your comments/requests.
  • To receive responses that are appropriate to your requests, we may transfer your email address and your name to the author of the article.
  • For more information on our Privacy Policy and Personal Data Processing, please visit the page: Privacy Policy (GDPR) & Cookies.
  • If you have any questions or concerns regarding the way we process your personal data, you can contact our Data Protection Officer at: gdpr@esp2000.ro
  • Subscribe to our magazine newsletter