People

Charbel Sakr

Charbel Received his PhD (2021) from the Coordinated Science Laboratory at the University of Illinois at Urbana-Champaign. His research interests are in resource-constrained machine learning, with a particular focus on analysis and implementation of reduced precision models and algorithms and their co-design with machine learning accelerator hardware.

Research Area(s)
Artificial Intelligence and Machine Learning
Circuits and VLSI Design
Main Field of Interest
Artificial Intelligence and Machine Learning
Google Scholar
https://scholar.google.com/citations?user=Ks1WOEUAAAAJ&hl=en&oi=ao

Publications

2023

VaPr: Variable-Precision Tensors to Accelerate Robot Motion Planning
Yu-Shun Hsiao, Siva Hari, Balakumar Sundaralingam, Jason Yik, Thierry Tambe, Charbel Sakr, Steve Keckler, Vijay Janapa Reddi
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023)
A 95.6-TOPS/W Deep Learning Inference Accelerator With Per-Vector Scaled 4-bit Quantization in 5 nm
Ben Keller, Rangharajan Venkatesan, Steve Dai, Stephen Tell, Brian Zimmer, Charbel Sakr, William Dally, Tom Gray, Brucek Khailany
Journal of Solid-State Circuits

2022

Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
Charbel Sakr, Steve Dai, Rangharajan Venkatesan, Brian Zimmer, Brucek Khailany, William Dally
2022 International Conference on Machine Learning (ICML)

2021

Optimizing Selective Protection for CNN Resilience
Abdulrahman Mahmoud, Siva Hari, Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, Pavlo Molchanov, Michael B. Sullivan, Timothy Tsai, Steve Keckler
International Symposium on Software Reliability Engineering (ISSRE)

2020

HarDNN: Feature Map Vulnerability Evaluation in CNNs
Abdulrahman Mahmoud, Siva Hari, Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, Pavlo Molchanov, Michael B. Sullivan, Timothy Tsai, Steve Keckler
arXiv