Making Intelligent Computing More Efficient: A Redundancy-Centric Approach
Speaker: Xipeng Shen – Raleigh, NC, United StatesTopic(s): Software Engineering and Programming
Abstract
Modern computing, driven by advances in machine learning and AI, is becoming increasingly intelligent, while also more computationally intensive and efficiency-critical. This talk will present a redundancy-centric approach to maximizing the efficiency of intelligent computing across Deep Neural Networks, Graph Neural Networks, and Data Analytics. The approach focuses on identifying and eliminating redundancy in computations through innovations in online clustering, compression, and binarization. These optimizations result in significant speedups, ranging from several to hundreds of times faster, with minimal or no accuracy loss, on devices ranging from microcontrollers to GPU servers and supercomputers.About this Lecture
Number of Slides: 70Duration: 75 minutes
Languages Available: Chinese (Simplified), English
Last Updated:
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.