AI Core X - UP Bridge the Gap

UP AI Core X Series

Deep Neural Networks Hardware accelators

UP AI Core X series, powered by Intel® Movidius™ Myriad™ X VPUs, drive the demanding workloads of modern computer vision and AI applications at ultra-low power.

UP AI CORE X is the most complete product family of neural network accelerators for Edge devices. The expansion boards are available in MiniCard/mPCIe, M.2 2280 and custom form factors with single and multiple chips. With just a few watts of power consumption, each chip delivers up to four trillion operations per second (TOPS) with a Neural Compute Engine capable of delivering up to one TOPS.

Overview　|　Board Details　|　Tech Spec　|　Community Support　|　Add-ons

Overview

Intel® Movidius™ Myriad X

Video Processing Unit (Hardware Neural network)
Optimized for Machine learning
Real Time Pattern Recognition

Machine learning in the Cloud

Highly Efficient (Performance / W)
High costs
1000s of Classes
Large Workloads
Varying accuracy
Server Form Factor

Machine learning on the Edge

Extreme low Power – 1W-5W
Low costs
<10 Classes
Frame Rate: 15-30fps
Varying accuracy
Custom form factor

Board Details

Hardware overview

Intel® Movidius™ Myriad™ X VPU
Intel® Vision Accelerator Design SW SDK
Supported frameworks: TensorFlow, Caffe, MXNET
Ubuntu 16.04, Windows® 10
Onboard LPDDR4 Memory up to 32GB

Why Artificial Intelligence on the Edge?

Most IT solutions which are available today are focused on connecting Edge devices to the cloud and these deployments face challenges related to latency, network bandwidth, reliability and security.

Experts in this field agree that not all the tasks and decision-making processes can be addressed in cloud-based models. UP AI Edge is the solution for those cloud limitations by bringing AI performance and hardware acceleration not ‘at’ but ‘ON’ the Edge of the Internet of Things and of the latest technology.

What can you achieve with this AI module?

The Intel® Movidius™ Myriad™ X VPU is a giant leap over the previous generation of VPUs. It can reach up to 105 FPS (80 typical), and can perform over 1 trillion floating point operations per second as a dedicated neural network accelerator. The Intel® Movidius™ Myriad™ X is capable of processing video and performing facial recognition in real-time. Best of all, the Intel® Movidius™ Myriad™ X is an ultra-low power VPU, needing very little energy to perform.

Explore its potential

AI Proof

　▶ Add UP AI Core X
　　 1x Myriad™ X VPU on UP Xtreme

　▶ Add UP AI Core XM 2280
　　 2x Myriad™ X VPU on UP Xtreme

　▶ Add UP Vision Plus X
　　 3x Myriad™ X VPU on UP Xtreme

　▶ Run up to 6x Myriad™ X VPU
　　on UP Xtreme

Tech Specifications

Movidius™ Myriad™ X

Enabling deep learning by multiple VPU

Are you trying to run more than one camera? Do you need a different network in VPU? Or do you require a whole different interface? UP AI Edge provides different options for the numbers of VPU and interface.
It goes along with most of the mainboards in the market for ease of your your development. Once the development is completed, we can also integrate the VPU into a custom single board computer.

UP AI Core X

UP AI Core XM 2280

UP Vision Plus X

UP AI Core XP4

UP AI Core XP8

UP AI Core X

UP AI Core X
SoC	Intel® Movidius™ Myriad™ X VPU 2485
Quantity of VPU	1
Form factor	Mini PCI-Express
Memory	4Gb LPDDR4 x1
Dimensions	30 x 51 mm (1.18″ x 2.00″)
Thermal	Fanless heatsink
Supported Frameworks	Caffe, TensorFlow, MXNet, Kaldi, ONNX
Minimum system requirements	x86_64 Computer running Ubuntu 16.04, 1GB memory, 4GB Free storage, vacant expansion slot
Software tool	Intel® Distribution of OpenVINO™ toolkit R4 or above rev.

UP AI Core XM 2280

UP AI Core XM 2280
SoC	2x Intel® Movidius™ Myriad™ X VPUs 2485
Quantity of VPU	2
Form factor	M.2 2280
Memory	4Gb LPDDR4 x2
Dimensions	22 x 80 mm (0.86″ x 3.14″)
Thermal	Heatsink with active fan
Supported Frameworks	Caffe, TensorFlow, MXNet, Kaldi, ONNX
Minimum system requirements	x86_64 Computer running Ubuntu 16.04, 1GB memory, 4GB Free storage, vacant expansion slot
Software tool	Intel® Distribution of OpenVINO™ toolkit R4 or above rev.

UP Vision Plus X

Vision Plus X
SoC	3x Intel® Movidius™ Myriad™ X VPUs 2485
Quantity of VPU	3
Form factor	Credit Card
Memory	4Gb LPDDR4 x3
Dimensions	56.5 mm x 90mm (2.22″ x 3.54″)
Thermal	Fanless heatsink
Supported Frameworks	Caffe, TensorFlow, MXNet, Kaldi, ONNX
Minimum system requirements	x86_64 Computer running Ubuntu 16.04, 1GB memory, 4GB Free storage, vacant expansion slot
Software tool	Intel® Distribution of OpenVINO™ toolkit R4 or above rev.
Ethernet	1x Gigabit Ethernet (Realtek 8111G) to main board,
USB	2x USB 3.0 Type A
Expansion Slot	1x Mini card (full-size) SATA-PCI-e colay
Docking	2x Docking connector 100-pin to UP Core Plus
Power	12V DC
Operating temps	0~60°C
Operating humidity	10%～90%RH non-condensing
Certification	CE/FCC Class A
Compatibility	Compatible with UP Core Plus & UP Xtreme

UP AI Core XP4

UP AI Core XP4
SoC	4x Intel® Movidius™ Myriad™ X VPUs 2485
Quantity of VPU	4
Form factor	PCIe x4
Memory	4Gb LPDDR4 x4
Dimensions	111 x 170 mm (4.37″ x 6.69″)
Thermal	Heatsink with active fan
Supported Frameworks	Caffe, TensorFlow, MXNet, Kaldi, ONNX
Minimum system requirements	x86_64 Computer running Ubuntu 16.04, 1GB memory, 4GB Free storage, vacant expansion slot
Software tool	Intel® Distribution of OpenVINO™ toolkit R4 or above rev.

UP AI Core XP8

UP AI Core XP8
SoC	8x Intel® Movidius™ Myriad™ X VPUs 2485
Quantity of VPU	8
Form factor	PCIe x4
Memory	4Gb LPDDR4 x4
Dimensions	111 x 170 mm (4.37″ x 6.69″)
Thermal	Heatsink with active fan
Supported Frameworks	Caffe, TensorFlow, MXNet, Kaldi, ONNX
Minimum system requirements	x86_64 Computer running Ubuntu 16.04, 1GB memory, 4GB Free storage, vacant expansion slot
Software tool	Intel® Distribution of OpenVINO™ toolkit R4 or above rev.

AI Development Kit

UP Squared AI Vision Development Kit –

Implement and deploy computer vision solutions and support deeplearning inference across the CPU, GPU, and VPU.

This kit includes UP Squared x7-E3950 CPU 8GB RAM, 64GB eMMC, UP HD camera, and AI Core module. Besides the hardware, it comes with a complete software package including Ubuntu 16.04.4 Desktop, OpenVINO™ toolkit, Open CL/ Movidius Driver, Arduino Create and Intel System Studio.

The UP Squared AI Vision Development Kit, with its ultra-compact form factor, brings together two powerful Intel technologies: Intel Apollo Lake SoC and Intel® Movidius™ Myriad™ VPU. It is AI (Artificial Intelligence) built by IA (Intel Architecture) and comes together with a whole set of development tools.

It is a complete development kit with everything you need for AI vision development. The kit serves the purpose of bridging the gap between prototype and mass production and provides comprehensive cloud connectors such as Microsoft Azure, Amazon AWS, Google Cloud and IBM Bluemix.