KI-FLEX AI chip tapes out with flexible videantis processor platform
Hannover, Germany -- December 13, 2022 – videantis GmbH, provider of a unified platform for combined processing of algorithms as diverse as AI (Artificial Intelligence), multi-modal sensor data processing and fusion, or video coding on a single architecture, today announced the tape-out of the FlexAISIC AI chip based on its flexible v-MP6000UDX unified processing platform. The tape-out has been achieved in collaboration with the Fraunhofer Institute for Integrated Circuits IIS, and the chip development is funded by the German Federal Ministry of Education and Research (BMBF) within the KI-FLEX project.
KI-FLEX is part of a broader initiative driven by the German BMBF to push research of AI-based technologies for autonomous driving. KI-FLEX develops a powerful and highly energy-efficient hardware platform and the associated software framework for AI-based processing and merging of data from different sensors, resulting in fast and reliable perception and localization for autonomous driving.
Related |
Unified Deep Learning Processor |
The videantis v-MP6000UDX platform as the core component of the FlexAISIC is a highly scalable multi-core architecture combined with a tailored bus fabric and multi-banked shared on-chip SRAM which delivers extreme efficiency and performance for a variety of algorithm types like deep learning, computer vision, signal processing, and video coding. Within KI-FLEX, videantis’ comprehensive v‑CNNDesigner front-to-end tool flow is employed to map both camera-based image detector and lidar-based point cloud pose detector networks to distinct cores of the v-MP6000UDX architecture for simultaneous execution on the FlexAISIC chip, resulting in a highly compact and efficient solution for an autonomous vehicle perception unit.
About KI-FLEX
KI-FLEX is a research project funded by the German Federal Ministry of Education and Research with the goal to develop a powerful, energy-efficient hardware platform and the associated software framework for autonomous driving. KI-FLEX is designed to process and merge data from different sensors in cars quickly and reliably by using methods of artificial intelligence (AI; German abbreviation: KI). As a result, the vehicle always has an accurate picture of the actual traffic conditions, can locate its own position in this environment and, on the basis of this information, make the right decision in every driving situation – thus making autonomous driving safe and reliable.
The consortium to develop KI-FLEX is led by Fraunhofer Institute for Integrated Circuits IIS and includes Ibeo Automotive Systems GmbH, Infineon Technologies AG, Friedrich-Alexander-University Erlangen-Nuremberg, Technical University Munich, Fraunhofer Institute for Open Communication Systems FOKUS, Daimler Center for Automotive IT Innovations DCAITI and videantis GmbH.
For more information, please visit https://www.elektronikforschung.de/projekte/ki-flex
About videantis
Headquartered in Hannover, Germany, videantis GmbH is the originator of a unique high-performance, extreme-efficiency and fully scalable unified processing platform, which enables the implementation of leading edge algorithms for AI/deep learning, multi-modal sensor data processing and fusion as well as image and video en/decoding on the same architecture in highly efficient single-chip solutions. With its processor IP, application libraries and development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers in serial production together with customers in other high-volume embedded markets. 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.
|
videantis GmbH Hot IP
Related News
- TEMPO AI chip tapes out with videantis processor platform
- videantis AI processor platform adopted for KI-FLEX autonomous driving chip
- Dream Chip Technologies tapes out a 10-TOPS SoC in 22nm with a novel AI Accelerator and an Automotive Functional Safety Processor
- BrainChip Tapes Out AKD1500 Chip in GlobalFoundries 22nm FD SOI Process
- GUC Tapes Out AI/HPC/Networking Platform on TSMC CoWoS Technology Validating 7.2 Gbps HBM3 Controller and PHY, GLink-2.5D and 112G-LR SerDes IPs
Breaking News
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
- RaiderChip Hardware NPU adds Falcon-3 LLM to its supported AI models
Most Popular
E-mail This Article | Printer-Friendly Page |