Next Generation IoT Architectures_Hans Salomonsson
Download as PPTX, PDF0 likes7 views
The document discusses the Vedliot project focused on developing efficient deep learning architectures for IoT, running from November 2020 to October 2023 with 12 partners across Europe. It highlights the use of scalable, heterogeneous hardware and a toolchain optimized for various IoT use cases such as industrial IoT and smart homes. Additionally, it invites participation in the project’s open call for early use and evaluation of Vedliot technology.
Next Generation IoT Architectures_Hans Salomonsson
- 1. Hans Salomonsson CEO @ EmbeDL EU-IoT Training Workshops Series: Next Generation IoT Architectures 8. Nov 2021 VEDLIoT - Toolchain for Efficient Deep Learning on heterogenous hardware
- 2. 2 Research Hardware: Scalable, heterogeneous, distributed Accelerators: Efficiency boost by FPGA and ASIC technology Toolchain: Optimizing Deep Learning for IoT Use cases Industrial IoT Automotive Smart Home Open call At project mid-term Early use and evaluation of VEDLIoT technology Very Efficient Deep Learning IoT – VEDLIoT Call: H2020-ICT2020-1 Topic: ICT-56-2020 Next Generation Internet of Things Duration: 1. November 2020 – 31. Oktober 2023 Coordinator: Bielefeld University (Germany) Consortium: 12 partners from 4 EU countries (Germany, Poland, Portugal and Sweden) and one associated country (Switzerland). More info: https://www.vedliot.eu/ https://twitter.com/VEDLIoT https://www.linkedin.com/company/vedliot/
- 3. 3 Deep Learning IoT Architecture t.RECS u.RECS Edge RECS|Box Optimized Deep Learning Model (inference) Cloud Embedded
- 4. 4 VEDLIoT Hardware Platform Heterogeneous, modular, scalable microserver system Supporting the full spectrum of IoT from embedded over the edge towards the cloud Different technology concepts for improving x86 GPU ML-ASIC ARM v8 GPU SoC FPGA SoC RISC-V FPGA VEDLIOT Cognitive IoT Platform Performance Cost-effectiveness Maintainability Reliability Energy-Efficiency Safety
- 6. 6 VEDLIoT‘s Deep Learning Toolchain • Image Classification • Object Detection • Semantic Segmentation • Instance Segmentation • Extractive Question Answering Model Zoo Optimization Engine Compilers & Runtime APIs Heterogeneous Hardware Platforms
- 7. 7 Model ZOO
- 8. 8 Model ZOO
- 9. 9 Model ZOO
- 10. 10 Efficent deep learning for IoT
- 14. 14 1&3 Flexible and adaptable Accelerators for Deep Learning DL Model DL Model CPU, GPU- SoC, ML-SoC FPGA-SoC End of Moore’s law & dark silicon – Domain Specific Architectures (DSA) Efficient, flexible, scalable accelerators for the compute continuum Algotecture Optimized DL algorithms Optimized toolchain Optimized computer architecture Heterogeneous DL Accelerator Algotecture/ Co-Designed DL Accelerator Optimizer & Compiler Co-Design
- 15. 15 The fun has just started! Follow our work! https://twitter.com/VEDLIoT https://www.linkedin.com/company/vedliot/ https://vedliot.eu Be part of it Open call at project mid-term Allow early use and evaluation of VEDLIoT technology
- 16. 16 Thank you for your attention. Me Hans Salomonsson EmbeDL, Sweden hans@embedl.ai Contact Jens Hagemeyer, Carola Haumann Bielefeld University, Germany chaumann@cor-lab.uni-bielefeld.de jhagemey@cit-ec.uni-bielefeld.de