(11월 29일) Approximate Computing for Machine Learning and Artificial Intelligence
Approximate Computing for Machine Learning and Artificial Intelligence
2016년 11월 29일(화) 오후 4시
최정욱 박사님 (IBM)
정보전자동 E3-2 2층 우리별세미나실
Machine learning (ML) and artificial intelligence (AI) technologies have revolutionized the ways in which we interact with large-scale, imperfect, real-world data. While traditional workloads including transactional and database processing continue to grow modestly, there is an explosion in the computational footprint of a range of ML and AI applications that aim to extract deep insight from vast quantities of structured and unstructured data. There is an exactness implied by traditional computing that is not needed in the processing of most types of these data. Approximate computing aims to relax these exactness constraints with the goal of obtaining significant gains in computational throughput and energy savings – while still maintaining an acceptable quality of results.
In this talk, we demonstrate that multiple approximation techniques can be applied to applications in these domains and can be further combined together to compound their benefits. In assessing the potential of approximation in these applications, we take the liberty of changing multiple layers of the system stack: architecture, programming model, and algorithms. Across a set of AI and ML applications spanning the domains of DSP, robotics, and deep learning, we show that hot loops in the applications can be perforated by an average of 50% with proportional reduction in execution time, while still producing acceptable quality of results. In addition, the width of the data used in the computation can be reduced to 10-16 bits from the currently common 32/64 bits with potential for significant performance and energy benefits. For parallel applications we reduce execution time by 50% using relaxed synchronization mechanisms. Finally, our results also demonstrate that benefits are compounded when these techniques are applied concurrently.
Jungwook Choi is a Research Staff Member at the IBM T.J. Watson Research Center, where he has worked on accelerator architecture and machine learning. He received the B.S. and M.S. degree in Electrical and Computer Engineering from Seoul National University, Seoul, South Korea, in 2008 and 2010, respectively, and his Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 2015.
His research interests include high performance, energy efficient, and reliable implementation of machine learning and deep learning algorithms. He won 2013 IEEE Workshop on Signal Processing Systems (SiPS) Bob Owens Best Student Paper Award, and he was one of the design contest winners of 2013 ACM/IEEE International Conference on Formal Methods and Models for Codesign (MEMOCODE).