VEDLIoT - Next generation accelerated AIoT systems and applications

The VEDLIoT project aims to develop energy-efficient Deep Learning methodologies for distributed Artificial Intelligence of Things (AIoT) applications. During our project, we propose a holistic approach that focuses on optimizing algorithms while addressing safety and security challenges inherent to AIoT systems. The foundation of this approach lies in a modular and scalable cognitive IoT hardware platform, which leverages microserver technology to enable users to configure the hardware to meet the requirements of a diverse array of applications. Heterogeneous computing is used to boost performance and energy efficiency. In addition, the full spectrum of hardware accelerators is integrated, providing specialized ASICs as well as FPGAs for reconfigurable computing. The project's contributions span across trusted computing, remote attestation, and secure execution environments, with the ultimate goal of facilitating the design and deployment of robust and efficient AIoT systems. The overall architecture is validated on use-cases ranging from Smart Home to Automotive and Industrial IoT appliances. Ten additional use cases are integrated via an open call, broadening the range of application areas.

[1]  Mario Porrmann,et al.  Evaluation of heterogeneous AIoT Accelerators within VEDLIoT , 2023, 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[2]  E. Knauss,et al.  An investigation of challenges encountered when specifying training data and runtime monitors for safety critical ML applications , 2023, REFSQ.

[3]  E. Knauss,et al.  A Compositional Approach to Creating Architecture Frameworks with an Application to Distributed AI Systems , 2022, J. Syst. Softw..

[4]  M. Azhar,et al.  FiBHA: Fixed Budget Hybrid CNN Accelerator , 2022, 2022 IEEE 34th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD).

[5]  Mario Porrmann,et al.  FAQ: A Flexible Accelerator for Q-Learning with Configurable Environment , 2022, 2022 IEEE 33rd International Conference on Application-specific Systems, Architectures and Processors (ASAP).

[6]  P. Felber,et al.  WebAssembly as a Common Layer for the Cloud-edge Continuum , 2022, FRAME@HPDC.

[7]  P. Felber,et al.  WaTZ: A Trusted WebAssembly Runtime Environment with Remote Attestation for TrustZone , 2022, 2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS).

[8]  P. Felber,et al.  Attestation Mechanisms for Trusted Execution Environments Demystified , 2022, DAIS.

[9]  A. Bessani,et al.  VEDLIoT: Very Efficient Deep Learning in IoT , 2022, 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[10]  Onur Mutlu,et al.  Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks , 2021, 2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT).

[11]  Valerio Schiavoni,et al.  Twine: An Embedded Trusted Runtime for WebAssembly , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[12]  Sheng Ma,et al.  HeSA: Heterogeneous Systolic Array Architecture for Compact CNNs Hardware Accelerators , 2021, 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[13]  Valerio Schiavoni,et al.  LEGaTO: Low-Energy, Secure, and Resilient Toolset for Heterogeneous Computing , 2019, 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[14]  Deming Chen,et al.  Deep Neural Network Model and FPGA Accelerator Co-Design: Opportunities and Challenges , 2018, 2018 14th IEEE International Conference on Solid-State and Integrated Circuit Technology (ICSICT).

[15]  Kenneth O'Brien,et al.  FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks , 2018 .

[16]  Giovanni Agosta,et al.  M2DC - Modular Microserver DataCentre with heterogeneous hardware , 2017, Microprocess. Microsystems.

[17]  Eric Knauss,et al.  Automotive Architecture Framework: The experience of Volvo Cars , 2017, J. Syst. Archit..

[18]  Timo Aila,et al.  Pruning Convolutional Neural Networks for Resource Efficient Inference , 2016, ICLR.

[19]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[20]  Mario Porrmann,et al.  A Scalable Server Architecture for Next-Generation Heterogeneous Compute Clusters , 2014, 2014 12th IEEE International Conference on Embedded and Ubiquitous Computing.

[21]  Robert S. Hanmer,et al.  The Twin Peaks of Requirements and Architecture , 2013 .