Scope and Aim:
Recent years have witnessed the successful applications of artificial intelligence (AI) in a variety of disciplines, due to the recent developments in the domain of neural networks and cloud computing. e.g., autonomous driving, personal assistants, etc. AI has received a tremendous amount of attention, but at the same time it has also brought huge challenges to the IT industry. Owing to the depth of the neural network layers, complex structure, large number of nodes, and big training data sets, the time required for the training process is particularly long. As the demand for artificial intelligence increases sharply, existing computing architectures encounter many challenges such as power walls, performance walls, memory walls, and the slowing down of Moore's Law, urgently require innovation in computing system architecture.
Recently, computing system architectures, aiming to accelerate the processing speed of artificial intelligence have received significant attention, since the intelligent computing system architectures proposes a possible solution to meet the high computation requirements for the training and inference of AI algorithms. However, there are many challenges existing for novel designs of intelligent computing system architectures for AI applications, and their co-optimization. Moreover, designing an AI application with a relatively low amount of communication and calculation is the direction of effort, such as using dynamic algorithms, model pruning, and weight quantization, etc.
On the other hand, some explorations have been made for system architecture using AI, such as the design of branch predictors, memory controllers, task schedulers and chip layouts. Although current AI-based methods for computing system architecture have already exceeded their respective state-of-the-art heuristic and human expert designs, it will likely continue to provide breakthroughs as promising applications are explored.
The topics of interest include, but are not limited to:
All original manuscripts that fit within the scope are welcome.
Submission Details:
General information for submitting papers to JSA can be found at https://www.journals.elsevier.com/journal-of-systems-architecture. Submissions should be made online at https://www.editorialmanager.com/jsa/. Please select the “VSI:AI-CSA” option as the type of the paper during the submission process.
JSA has adopted the Virtual Special Issue model to speed up the publication process, where Special Issue papers are published in regular issues, but marked as SI papers. Acceptance decisions are made on a rolling basis. Therefore, authors are encouraged to submit papers early, and need not wait until the submission deadline.
Important Dates
Paper submission due: October 1st, 2021
Final decision: July 1st, 2022
Guest Editors:
Prof. Zeng Zeng
Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)
Singapore
Email: [email protected]
Prof. Bharadwaj Veeravalli
Department of ECE,
Faculty of Engineering, National University of Singapore, Singapore
Email: [email protected]
Prof. Xu Zhou
College of Information Science and Engineering, Hunan University, China
Email: [email protected]
Prof. Keqin Li
IEEE Fellow Department of Computer ScienceState University of New York, USA
Email: [email protected]