UP AI Edge platform launched to work across Intel CPU, GPU, VPU and FPGA
UP Bridge the Gap – a brand of AAEON Europe – is bringing its latest innovation to Kicksarter. Introducing UP AI Edge: an x86 computing platform works across Intel CPU, GPU,VPU and FPGA to enable Artificial Intelligence (AI) on the Edge.
Most IT solutions 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-only models.
UP AI Edge is said to be the solution for 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.
It is the only AI on the Edge platform fully powered by Intel technology and it consists of :
- UP Core Plus: the credit-sized ( 56 x 90 mm ) board powered by Intel formerly known as Apollo Lake-I family, a 64 bit QuadCore Atom architecture with extremely high performance in only 9.5 W of TDP ( x5 – 3940). The board supports up to 8GB Dual Channel DDR4 2.400 MHz, DP up to 4K, eDP, 2 USB 2.0, 1 USB 3.0, 1 USB 3.0 OTG, Wi-Fi 802.11 AC 2T2R, 2 x CSI and it has 2 x 100 pin high speed connector which bring to the carrier board I2C, I2S, ISH, UART, PCI-Express, USB 3.0 etc.
- AI Plus: the credit-sized ( 56 x 90 mm ) companion board for UP Core Plus, powered by Intel® Cyclone® 10GX ( 105KLe-220KLe ) with 1 GB DDRIII, Display Port-IN connected to Cyclone 10gx for Video Acquisition, USB Type-C connector & GPIO connected to Intel Cyclone 10gx for data acquisition, LVDS-IN connected to Intel® Cyclone® 10GX for Camera acquisition natively compatible to Basler LVDS cameras, 1 GBit Ethernet, 1 USB 3.0 and mini-PCIe connected to UP Core Plus via the 100 pin high speed connector.
- Net Plus: the credit-sized companion board of UP Core Plus which features 4 Full Gigabit LAN powered by Intel® I211AT ( option for I210 with support of TSN), mPCIe to host either AI Core or 3G/4G modem, SATA, USB 3.0.
- Vision Plus: integrates in one ultra-compact board three Intel® Movidius™ MyriadTM 2 VPU , 1x GbLAN , 2x USB 3.0, and 1x mPCIEe for 3G/4G connectivity or other expansions.It delivers three time the performance of a single UP AI Core module.
- AI Core: the mini-PCIe module powered by Intel® Movidius™ MyriadTM 22450 with 512 MB DDR, the most advanced low-power technology for running deep learning and neural network on the Edge and processing video images.
- UP AI Core M2 is a M.2 2280 B+M key module which can be seamless integrated in most of the edge computers available on the market such the latest Intel NUC boards accelerating the path to production from lab to field installation. It is powered by two Intel® Movidius™ MyriadTM 2 VPU delivering double performance compared to single VPU solution.
- UP Squared AI Vision Development Kit: UP Squared board powered by Intel x7-3950 SoC, 4GB memory, 64 GB eMMC with Ubuntu 16.04 image, a AI Core module, a UP HD camera, a fanless chassis and a power supply.
AI Core (front)
UP AI Core, UP AI Core M2 and UP Vision Plus are fully compatibility with Intel Neural Compute Stick ( NCS ) SDK which speeds up the development cycle and they are fully supported by OpenVINO™ toolkit which permits developers to balance the load between CPU, GPU, FPGA and Myriad 2 VPU.
All the products are supported in the UP Community which also offers examples of real field deployment. UP is working in the creation of an AI software ecosystems; companies who want to join it and adopt UP solution get special discounts and early access to new products and technology.
UP AI Edge prices at Kickstarter campaign start at €49 for a M.2 2280 Intel Movidius Myraid 2 module (AI Core M2). To experience the power of Intel Apollo Lake SoC with Intel® Cyclone® 10GX FPGA, the package starts from €399. To run 3x Intel Movidius Myraid 2 together with Intel x5-E3930 and semi-industrial camera, it costs only €409. There are many different packages to fulfill your needs to build your AI Edge device. Come to support us at Kickstarter!
Comment on this article below or via Twitter @IoTGN