CODAI 2023

News

Overview

The goal of the CODAI’23 workshop is to bring together the emerging energy in the AI compiler communities and AI accelerator communities focusing on Edge AI in both academic and industrial research. These realms of research have the opportunity to deliver a pervasive and seamless end-to-end tooling that connects hardware and software development methodologies. This workshop mainly focuses on:

Therefore, it complements the established conferences CASES and CODES+ISSS which have a wider and more academic research-spectrum. We also welcome work-in-progress papers of ongoing research projects and case studies from industrial applications. Topics for workshop submissions include, but are not limited to:

How to Find Us

On-Site: The workshop will be held in Building H, Ground Floor, Room H0.07 of the ESWeek Conference Venue. More Infomation here

Online: Zoom

Review

CODAI 2022 was a great success with many contributions from academia, industry, and international tech leaders. We accepted five high-quality papers and were positively surprised by the quality and extensiveness of submitted papers (one paper even open sourced their code on GitHub after the notification of acceptance).

The CODAI 2022 presentations can be found here.

Program

Introduction & Keynote Title Authors Affiliation Online/On-Site
10:00 – 10:30 Welcome Coffee      
10:30 – 10:35 Opening CODAI Team    
10:35 – 11:15 Keynote: Next-generation Compilers for Emerging Systems Jeronimo Castrillon Technical University of Dresden  
         
Session 1: Deployment and Optimization Techniques        
11:15 – 11:40 Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge Yao Lu, Hiram Rayo Torres Rodriguez, Sebastian Vogel, Nick van de Waterlaat, Pavol Jancura NXP Semiconductors, Eindhoven University of Technology  
11:40 – 12:05 Invited Talk: Tiny Machine Learning: Enabling Intelligence on Constrained Devices Fouad Sakr Aptiv  
12:05 – 12:30 Invited Talk: Hardware-Aware Network Compression: From Data to Silicon Thomas Pfeil Recogni  
12:30 – 13:30 Lunch Break      
         
Session 2: Compilation Frameworks and Techniques        
13:30 – 13:55 Accelerating Edge AI with Morpher: An Integrated Design, Compilation and Simulation Framework for CGRAs Dhananjaya Wijerathne, Zhaoying Li, Tulika Mitra National University of Singapore  
13:55 – 14:20 Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM’s UMA Samira Ahmadifarsani, Rafael Stahl, Philipp van Kempen, Daniel Mueller-Gritschneder, Ulf Schlichtmann Technical University of Munich  
14:20 – 14:45 ART: An Actor transition systems RunTime for enabling efficient partitioning of neural network graphs Endri Bezati Huawei Zurich Research Center  
14:45 – 15:10 Invited Talk: SYCL – A Modern C++ Programming Model for Accelerators Lukas Sommer Codeplay  
15:10 – 15:40 Coffee Break      
         
Session 3: Applications        
15:40 – 16:05 Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing Max Sponner, Julius Ott, Lorenzo Servadei, Bernd Waschneck, Robert Wille, Akash Kumar Technical University of Munich, Infineon Dresden Technologies GmbH& Co. KG  
16:05 – 16:30 Pros and Cons of Executable Neural Networks for Deeply Embedded Systems Matheus Ferraz, Birte Friesel, Olaf Spinczyk Osnarbrück University  
16:30 – 16:55 Invited Talk: Software and Hardware for Sparse ML Fredrik Kjolstad Stanford University Video/Online Talk
16:55 – 17:00 Closing remarks CODAI Team    

Important Dates

Call For Papers

Call for papers for CODAI’23 workshop

Paper Submission

Submit

Registration

Online participation

Online participation is free of charge

Registration for online participation

On-site participation

On-site participants requires an ESWEEK registration. Workshop-only participation comes at a cost of 250 USD

Registration for on-site participation

Author Information

All accepted contributions will be presented the CODAI Workshop 2023. Please be available for a 20 minute on-site presentation at ESWeek, followed by a 10 minute Q&A session. If you can not make the trip, you have to record a video of your talk, which will be streamed during the event. Afterwards, please be availabe for the Q&A session via Zoom. All talks will be recorded and live-streamed in Zoom and on YouTube.

Important: all speaker who participate on-site, require an ESWEEK registration. There is also a workshop-only option at a reduced price.

Author Instructions

ACM accepted the proposal to publish the CODAI proceedings in the [ACM digital library]{https://dl.acm.org/}. Please prepare the paper as given by the instruction that you received via E-Mail from ACM.

The proceeddings will be published on arXiv.org. Additionally, we are currently in negotiation with IEEE/ACM to publish the proceedings additionally via IEEExplore/ACM-DL. Updates on this matter will follow soon.

Please use the IEEE Template for your manuscript. Your paper must not exceed a length of 4 pages excluding references.

Organization

Organization Committee

Chairs

For questions on specific topics, contact:

Technical Program Committee

Contact

For questions contact:

Dr. Michael J. Klaiber, EnCharge AI

E-Mail: codai2023 (a) michael-klaiber.de

Code of Conduct | Anti-Harrasment Policy

Logo by Parzival’ 1997