Intel® Vision Accelerator Design With Intel® Movidius™ Vision Processing Unit (VPU)

Deep Neural Networks

Optimized for computer vision applications built using deep neural networks for low power, low cost, and small form factors

Power Efficiency

Ultra-low-power demands allow for integration on cameras and edge servers running on power- and size-constrained systems

Easy to Scale

Scalable analytics with minimal software changes for single- to multiple-chip solutions

Intel® Vision Accelerator Design

Features

With 1 Intel® Movidius™ VPU

With 2 Intel Movidius VPUs

With 8 Intel Movidius VPUs

VPU

1 - MA2485

2 - MA2485

8 - MA2485

Board dimensions

M.2 2230 Key E & A

22 mm x 30 mm

M-PCIe*

30 mm x 50 mm

Half-height, half-length, single-slot PCIe*

68.90 mm x 167.65 mm

VPU memory

4 Gb LPDDR4 POP

4 Gb LPDDR4 POP

4 Gb LPDDR4 POP

Minimum system configuration

 

Intel Atom® x7 processor E3950

8 GB LPDDR4, 64 GB eMMC

USB 3.0, M.2 2230 connector

Intel Atom x7 processor E3950

8 GB LPDDR4, 64 GB eMMC

USB 3.0, M-PCIe connector

Intel® Core™ i5 processor 6500TE

8 GB RAM, 500 GB HDD

USB 3.0

2 - PCIe x4 x8 x16 connectors

Typical operating system

 

Ubuntu* 16.04 LTS 64 bit

Ubuntu 16.04 LTS 64 bit

Ubuntu 16.04 LTS 64 bit

Tools

Intel® Distribution of OpenVINO™ toolkit

Intel Distribution of OpenVINO toolkit

Intel Distribution of OpenVINO toolkit

Intel Vision Accelerator Design

Suppliers

With 1 Intel Movidius VPU

With 2 Intel Movidius VPUs

With 8 Intel Movidius VPUs

AAEON*

UP* AI Core X

UP AI Core XM 2280

UP AI Core XP8

ADLINK*

 

EDL-mPCIe-MA2485

 

Advantech*

VEGA-320

VEGA-330

 

IEI

Mustang-M2AE-MX1

Mustang-M2BM-MX2

Mustang-MPCIE-MX2

Mustang-V100-MX8-R10

JWIPC* 

 

AI Accelerator Card

 

NEXCOM*

 

 

AIBooster-X8

Uzel*

 

UI-AL2

UI-AR8