Optimizing AI Systems through Cross-Layer Design: A Data-Centric Approach
Monday, April 22, 2024
As artificial intelligence (AI) transforms various industries, state-of-the-art models have grown exponentially in size and capability. However, previous optimization efforts have primarily concentrated on computational aspects, often overlooking the significant bottleneck in AI system efficiency caused by the storage, retrieval, and orchestration of data. To address this challenge, we adopt a data-centric approach, performing collaborative optimization across the algorithms, systems, architecture, and circuit layers. In this presentation, we will first discuss the memory capacity and bandwidth bottleneck that has emerged with the advancement of AI models. Furthermore, we will present our optimization efforts aimed at addressing this bottleneck, which include compressing the AI model, tailoring the computation schedule, and customizing the memory hierarchy. Additionally, we explore the potential of compute-in-memory as a comprehensive solution to these challenges, presenting a holistic approach that integrates computation and memory for enhanced efficiency in AI systems. At the conclusion of our presentation, we will share our insights and vision for a data-centric approach to optimizing AI systems.
Post Talk Link: Click Here
Passcode: 6C+dvh&?
Speaker/s
Hai “Helen” Li is the Clare Boothe Luce Professor and Department Chair of the Electrical and Computer Engineering Department at Duke University. She received her B.S and M.S. from Tsinghua University and Ph.D. from Purdue University. Her research interests include neuromorphic circuit and system for brain-inspired computing, machine learning acceleration and trustworthy AI, conventional and emerging memory design and architecture, and software and hardware co-design. Dr. Li served/serves as the Associate Editor for multiple IEEE and ACM journals. She was the General Chair or Technical Program Chair of multiple IEEE/ACM conferences and the Technical Program Committee members of over 30 international conference series. Dr. Li is a Distinguished Lecturer of the IEEE CAS society (2018-2019) and a distinguished speaker of ACM (2017-2020). Dr. Li is a recipient of the NSF Career Award, DARPA Young Faculty Award, TUM-IAS Hans Fischer Fellowship from Germany, ELATE Fellowship, nine best paper awards and another nine best paper nominations. Dr. Li is a fellow of ACM and IEEE.
Related
Polygenic Score Modeling to Investigate Genotype-Phenotype Associations
Read More
Trustworthy Machine Learning: Transparency, Collaboration, and Evaluation
Read More