Deep learning inference accelerating M.2 BM key card

ICP Australia introduces iEi’s Mustang-M2BM-MX2 deep learning inference accelerating M.2 BM key card with 2 x Intel Movidius Myriad X MA2485 VPU, M.2 interface 22 mm x 80mm.

The Mustang-M2BM-MX2 is a deep learning convolutional neural network acceleration card for speeding up AI inference, in a flexible and scalable way. Equipped with Intel Movidius Myriad X Vision Processing Unit (VPU), the Mustang-M2BM-MX2 M.2 card can be used with the existing system, enabling high-performance computing without costing a fortune.

VPUs can run AI faster, and is well suited for low power consumption applications such as surveillance, retail and transportation. With the advantage of power efficiency and high performance to dedicate DNN topologies, it is perfect to be implemented in AI edge computing device to reduce total power usage, providing longer duty time for the rechargeable edge computing equipment.

Open Visual Inference & Neural Network Optimisation (OpenVINO) toolkit is based on convolutional neural networks (CNN). The toolkit extends workloads across Intel hardware and maximises performance. It can optimise pre-trained deep learning model such as Caffe, MXNET, Tensorflow into IR binary file then execute the inference engine across Intel-hardware heterogeneously such as CPU, GPU, Intel Movidius Myriad X VPU, and FPGA.

Key features include:

  • 2 BM key form factor (22mm x 80mm).
  • 2 x Intel Movidius Myriad X VPU MA2485.
  • Power efficiency, approximate 7.5W.
  • Operating temperature -20°C-60°C.
  • Powered by Intel’s OpenVINO Toolkit.