- This event has passed.
Utah Arch Virtual Talk Series – Hadi Esmaeilzadeh
February 19 @ 10:00 am - 11:00 am
Utah Arch Virtual Talk Series
Halicioğlu Chair in Computer Architecture
Department of Computer Science and Engineering
University of California, San Diego
Friday, February 19, 2021
Join Zoom Meeting
https://utah.zoom.us/j/8244189779 (Passcode: m5Sd3j$7f)
Host: Mahdi Bojnordi
AI for Accelerated AI Execution
Abstract: This talk, first, presents our cutting-edge comprehensive efforts to utilize the foundational mathematics of Artificial Intelligence (AI) to develop AI-assisted open-source compilation and deep quantization technologies for deep learning. Among these technologies, our upcoming ICLR 2020 paper devises the first Reinforcement-Learning-based optimizing compiler for deep learning and our MLSys 2020 paper delves into compilation of randomly-wired DNN that are mainly the result of automated Network Architecture Search (NAS). One ICML 2020 paper deals with using knowledge distillation to speed up and improve the accuracy of deep quantization training algorithms. The follow-on quantization work shows how to use stochastic gradient descent to discover quantization levels below 8 bits that preserve the accuracy while quantizing them. Then, the talk delves into a new challenge arising from the narrow focus of the community on intelligent workloads through domain-specific accelerators. These platforms obtain performance benefits by restricting the algorithmic domain. Such accelerators require specialized language interfaces and are often constrained to specific hardware, thus trading off expressiveness for high performance. The pendulum has swung from one hardware (general-purpose processors) for all domains to the opposite end, i.e., one hardware per individual domain. The middle-ground on this spectrum–which provides a unified computational stack across multiple, but not all, domains–is an emerging and open research challenge. As such, the last part of the talk This paper sets out to explore this region and its associated tradeoff between expressiveness and performance by defining a cross- domain stack, dubbed PolyMath. This stack defines a high-level cross-domain language, a multi-granular intermediate representation, and a compilation infrastructure that enables expressing multi-domain applications comprising the Robotics, Digital Signal Processing, Deep Learning, and Data Analytics domains as a single program, while targeting a variety of accelerators. These frameworks have and will be made open-source and publicly available at our portal https://bitbucket.org/act-lab/.
Bio: Dr. Esmaeilzadeh was awarded early tenure at the University of California, San Diego (UCSD), where he is the inaugural holder of Halicioglu Chair in Computer Architecture with the rank of associate professor in Computer Science and Engineering. Prior to UCSD, he was an assistant professor in the School of Computer Science at the Georgia Institute of Technology from 2013 to 2017. There, he was the inaugural holder of the Catherine M. and James E. Allchin Early Career Professorship. Hadi is the founding director of the Alternative Computing Technologies (ACT) Lab, where his team is developing new technologies and cross-stack solutions to build the next generation computer systems. He is also the associate director of Center for Machine Integrated Compu=ng and Security (MICS) at UCSD. Dr. Esmaeilzadeh obtained his Ph.D. from the Department of Computer Science and Engineering at the University of Washington in 2013 where his Ph.D. work received the 2013 William Chan Memorial Best Dissertation Award. Prof. Esmaeilzadeh received the IEEE Technical Committee on Computer Architecture (TCCA) “Young Architect” Award in 2018 and was inducted to the ISCA Hall of Fame in the same year. He has received the Air Force Office of Scientific Research Young Investigator Award (2017), College of Computing Outstanding Junior Faculty Research Award (2017), Qualcomm Research Award (2020, 2017, and 2016), Google Research Faculty Award (2018, 2016 and 2014), Microsoft Research Award (2017 and 2016), and Lockheed Inspirational Young Faculty Award (2016). His teams were awarded the Qualcomm Innovation Fellowship in 2014 and 2018, one of his students was a Microsoft Research Fellow, and two of his students won the National Center for Women & IT (NCWIT) Collegiate Award in 2017 and 2020. Four of his undergraduate students have been awarded the Georgia Tech President’s Undergraduate Research Award (PURA). His research has been recognized by four Communications of the ACM Research Highlights, four IEEE Micro Top Picks, a nomination for Communications of the ACM Research Highlights, an honorable mention in IEEE Micro Top Picks, and a Distinguished Paper Award in HPCA 2016. Hadi’s work on dark silicon has also been profiled in New York Times. More information is available on his webpage, http://cseweb.ucsd.edu/~hadi/.