Ultra96 is an Arm-based, Xilinx Zynq UltraScale+ MPSoC development board based on the Linaro 96Boards specification. The 96Boards’ specifications are open and define a standard board layout for development platforms that can be used by software application, hardware device, kernel, and other system software developers. Ultra96 represents a unique position in the 96Boards community with a wide range of potential peripherals and acceleration engines in the programmable logic that is not available from other offerings.
Ultra96 boots from the provided Delkin 16 GB MicroSD card, pre-loaded with PetaLinux. Engineers have options of connecting to Ultra96 through a Webserver using integrated wireless access point capability or to use the provided PetaLinux desktop environment which can be viewed on the integrated Mini DisplayPort video output. Multiple application examples and on-board development options are provided as examples.
Ultra96 provides four user-controllable LEDs. Engineers may also interact with the board through the 96Boards-compatible low-speed and high-speed expansion connectors by adding peripheral accessories such as those included in Seeed Studio’s Grove Starter Kit for 96Boards.
Micron LPDDR4 memory provides 2 GB of RAM in a 512M x 32 configuration. Wireless options include 802.11b/g/n Wi-Fi and Bluetooth 4.2 (provides both Bluetooth Classic and Low Energy (BLE)). UARTs are accessible on a header as well as through the expansion connector. JTAG is available through a header (external USB-JTAG required). I2C is available through the expansion connector.
Ultra96 provides one upstream (device) and two downstream (host) USB 3.0 connections. A USB 2.0 downstream (host) interface is provided on the high speed expansion bus. Two Microchip USB3320 USB 2.0 ULPI Transceivers and one Microchip USB5744 4-Port SS/HS USB Controller Hub are specified.
The integrated power supply generates all on-board voltages from an external 12V supply (available as an accessory).
Raj Pawate, Niranjan Yadla and Sachin Ghanekar presented a low cost SDK for Cadence HiFi 3 DSP. This Hikey960 development board enables software developers to leverage the power of the HiFi 3 DSP and introduce new algorithms for audio and speech processing. With HiFi 3 DSP running at 533 MHz and access to a large shared system memory of 13MB, software developers are no longer constrained to showcase their advanced algorithms. In addition, the HiFi 3 DSP works closely with an App processor hosting Android allowing software developers to integrate DSP functionality within the context of Android Applications.
OPEN AI Lab aims to promote the industry development of Arm embedded smart machines, build an embedded SoC basic computing framework for smart machine application scenarios, and integrate application scenario service interfaces. Committed to promoting the in-depth collaboration of the entire industry chain of chips, hardware, and algorithm software, artificial intelligence will be available where there is computation. You can also watch Mingfei Huang's keynote about Open AI Lab here.
HiSilicon and Hoperun introduces their new HiKey 970 development board, 10nm HiSilicon Kirin 970 based (same chipset that is in the recent Huawei Mate 10) quad ARM Cortex-A73 at 2.36GHz with quad ARM Cortex-A53 at 1.8GHz with Mali-G72MP12 and their new Dedicated Neural-network Processing Unit (NPU) with 256MAC/cycle @ 960MHz performance. To be available next month for $299 on Amazon and at http://hihope.org this is their Super Edge AI Computing Platform with Huawei HiAI SDK that can provide up to 25X Performance and 50X better Power Efficiency compared with doing the AI tasks by CPU or GPU. This enables the Heterogeneous multi processing Resource Management for use in applications such as Deep Learning, Robots, Automobile, Smart City. The NPU provides frequently used artificial intelligence function APIs, model management APIs and basic operator computing APIs, so developers can focus on developing new AI applications instead of focusing on performance tuning. The HiKey970’s dedicated AI processor has a rich set of imaging and I/Os that enables developers to build highly integrated flexible products for AI-based intelligent cameras in smart cities.
UEFI + ARM Trusted Firmware
Video Codec enable
PCIe enable for storage and LTE connect
4 lanes CSI + 2 lanes CSI
CAN V2.0B up to 1Mbps
Video Dec up to H.265 3840x2160@60fps
6GB 1866MHz, 4 Channel LPDDR4x
GPS, GLONASS, and BeiDou