Tempo 计划中的神经形态边缘人工智能(Edge AI)芯片中采用德国videantis公司的处理器平台

July 7, 2020, Hannover, Germany – videantis GmbH, a leading supplier of deep learning, computer vision and video coding solutions, today announced the adoption of its next-generation digital AI multi-core processor platform and toolflow for a neuromorphic mixed-signal edge AI chip. The development is part of the European TEMPO project and targets several autonomous driving use cases. TEMPO stands for “Technology & hardware for nEuromorphic coMPuting” and is an ECSEL JU innovation project supported by the EU Horizon 2020 programme.

Together with the Fraunhofer Institute for Integrated Circuits IIS, Infineon, Valeo, InnoSenT and other leading European companies and universities, videantis will develop a neuromorphic artificial intelligence ASIC platform and software development tools specifically tailored for energy-efficient edge processing for intelligent autonomous vehicles.

To this end, videantis will integrate its highly efficient and high-performance next-generation multi-core processor solution into a neuromorphic AI chip platform that processes LiDAR and radar sensor data for multiple autonomous driving use cases using AI-based methods. The solution combines deep decompression technology with a digital deep neural network (DNN) accelerator that remains software-programmable to easily adapt to different use cases of the chip.

Videantis will also support this chip with the v-CNNDesigner tool flow that automates the distribution and mapping of AI workloads onto the parallel architecture. v-CNNDesigner allows developers to map their neural networks on the videantis processors without requiring programmer’s intervention, removing the error-prone and complex programming task of finding the best quantization and parallelization strategies, data organization, and synchronization.

The videantis technology will be integrated and demonstrated together with the latest product innovations from the other research partners.

About TEMPO

TEMPO (Technology & hardware for nEuromorphic coMPuting) is a European innovation project. This project has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826655. The JU receives support from the European Union’s Horizon 2020 research and innovation programme, and from Belgium, France, Germany, Netherlands, Switzerland. TEMPO was kicked off on the 1st of April 2019 and has a duration of three years. The consortium of this ambitious project consists of no less than nineteen members. Imec takes the lead as the sole Belgian consortium partner. The other consortium members are, for France: CEA-LETI, ST-Microelectronics Crolles, ST-Microelectronics Grenoble, Thales Alenia Space and Valeo. For Germany: Bosch, Fraunhofer EMFT, Fraunhofer IIS, Fraunhofer IPMS, Infineon, Innosent, TU Dresden and videantis. For the Netherlands: imec the Netherlands, Philips Electronics and Philips Medical Systems. For Switzerland: aiCTX and the University of Zürich.

For more information, please visit www.ecsel.eu.

About videantis
Headquartered in Hannover, Germany, videantis is a one-stop deep learning, computer vision and video processor IP provider, delivering flexible computer vision, imaging and multi-standard HW/SW video coding solutions for automotive, mobile, consumer, and embedded markets. Based on a unified processor platform approach that is licensed to chip manufacturers, videantis provides tailored solutions to meet the specific needs of its customers. With core competencies of deep camera and video application expert know-how and strong SoC design and system architecture expertise, videantis serves a worldwide customer basis with a diverse range of target applications, such as advanced driver assistance systems and autonomous driving, mobile phones, AR/VR, IoT, gesture interfacing, computational photography, in-car infotainment, and over-the-top TV. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.

For more information, please visit www.videantis.com.