Powered by Rockchip Toybrick, Linaro launched two 96Boards SOM
Powered by Rockchip solutions, TB-96AI features the latest high-performance AI processing chip RK3399Pro while the TB-96AIoT is equipped with the RK1808 AIoT chip with ultra low power consumption. The 96Boards Compute SOM designs are available for purchase today from t.beijingcheshi.net and Beiqicloud.com.
The TB-96AI , equipped with RK3399Pro, has an integrated neural network processor NPU, computing power of up to 3.0 Tops, and offers compatibility across a variety of AI architectures. It can be combined with the backplane to form a complete industry application motherboard, and be applied to various embedded artificial intelligence fields. The SOM design has the following characteristics:
● Super Performance Processor
The architecture of Arm dual-core Cortex-A72+quad-core Cortex-A53 is adopted. The main frequency is up to 1.8 GHz and it integrates Mali-T860 MP4 quad-core graphics processor.
● Ultra-high AI power NPU
Integrating AI Neural Network Processor NPU, supporting 8Bit/16Bit operation, and with computing power of up to 3.0Tops, it can meet various AI application needs such as vision, audio and so on.
● Powerful Hard Decoding Ability
Supports DP1.2, HDMI 2.0, MIPI-DSI, eDP multiple display output interfaces, dual-screen co-display/dual-screen heterodyne, 4K VP9, 4K 10bits H265/H264 and 1080P multi-format (VC-1, MPEG-1/2/4, VP8) video decoding, 1080P (H.264, VP8 format) video coding.
● Supports multiple AI frameworks
Compatible with multiple AI frameworks, the design supports TensorFlow Lite/Android NN API, AI software tools support import, mapping and optimization of Caffe / TensorFlow models, allowing developers to easily use AI technology.
● Rich Interfaces
Will be equipped with the RK1808 AIoT chip, 22nm process, ultra low power consumption with Independent NPU and AI computing power of up to 3.0Tops, the TB-96AIoT also provides rich interfaces and strong scalability:
【96Boards SOM Carrier Board】
The 96Boards SOM Carrier Board is compatible with both the TB-96AI and TB-96AIoT. It is designed to suit different markets and demonstrates how easy it is to support multiple different SOMs.
>>> The publication of version 1.0 of 96Boards SOM specifications
Today two 96Boards SOM specifications have been launched - the Compute Module Specification and the Wireless Specification. Both specifications encourage the development of reliable and cost-effective embedded platforms for building end-products. The specifications have been proposed, created and reviewed by the current 96Boards Steering Committee Members.
● The Compute Module Specification, which defines a SOM with generic module-to-carrier board interface, independent of the specific SoC choice on the module. The Compute module addresses the application requirements of segments including industrial automation, smart devices, gateway systems, automotive, medical, robotics and retail POS systems.
● The Wireless specification designs a SOM for interchangeable wireless module applications, supporting standard and/or proprietary wireless standards such as 802.15.4, BLE, WiFi, LoRa, NB-IoT, LTE-M etc. The specification is designed to enable evolution that will support multiple products and future wireless standards.
The launch of the new 96Boards specifications means that developers now have a SOM solution which is compatible across SoCs. SOM solutions today use a variety of different connector solutions including SO-DIMM connectors used in DRAM and Mini Module Plus (MMP) connectors for certain specialist boards. Up until now, there has been no solution offering flexible IO and a robust mounting mechanism, nor a standard form factor. The new 96Boards SOM specifications aim to address this lack of choice by producing a general purpose SOM platform that will enable plug and play compatibility between a whole range of different SOM solutions.
About Rockchip Toybrick
Toybrick, Rockchip’s AI development platform, integrates software and hardware development into one platform. In terms of hardware, Toybrick provides various series of development platforms and reference designs to satisfy different user groups. For software, it offers stable system, rich development tools, and series of AI cases and open source communities.
Toybrick is aiming at providing efficient, convenient and stable services, enabling developers to quickly develop AI applications, accelerating the process of industry application development, and improving the whole industry ecology. To find out more, please visit http://t.beijingcheshi.net
Pre：RockChip Releases RK2108 Smart Dock Solution, Turing an Android Tablet into a Smart Display Next：Rockchip RK3399 has passed AI chip evaluation by the Artificial Intelligence Industry Alliance (AIIA)