iEi Integration Mustang-MPCIE-MX2 computing accelerator card

Click2Contact

iEi’s Mustang-MPCIE-MX2 computing accelerator miniPCIe card features two Intel Movidius Myriad X vision processing units (VPUs). It provides a flexible AI inference solution for space-limited and embedded systems and is designed to execute two topologies simultaneously.

The flexible product supports Intel’s OpenVINO toolkit for the optimisation of pre-trained deep-learning models such as Caffe, MXNT, ONNX and Tensorflow. The VPUs can run AI fast and are suitable for low power consumption applications such as surveillance, retail and transportation, as their power consumption is 7.5 W.

With the advantage of power efficiency and high performance to dedicate to DNN topologies, the card can be implemented in AI edge computing devices to reduce total power usage, providing longer duty time for rechargeable edge computing equipment.