Reliability-Aware Quantization for Anti-Aging NPUs
Sami Salamin1,a, Georgios Zervakis1,b, Ourania Spantidi2,a, Iraklis Anagnostopoulos2,b, Jörg Henkel1,c and Hussam Amrouch3,1
1Chair for Embedded Systems (CES), Karlsruhe Institute of Technology, Karlsruhe, Germany
asami.salamin@kit.edu
bgeorgios.zervakis@kit.edu
chenkel@kit.edu
2Department of Electrical and Computer Engineering, Southern Illinois University, Carbondale, U.S.A
aourania.spantidi@siu.edu
biraklis.anagno@siu.edu
3Chair of Semiconductor Test and Reliability (STAR), University of Stuttgart, Stuttgart, Germany
amrouch@iti.uni-stuttgart.de
ABSTRACT
Transistor aging is one of the major concerns that challenges designers in advanced technologies. It profoundly degrades the reliability of circuits during its lifetime as it slows down transistors resulting in errors due to timing violations unless large guardbands are included, which leads to considerable performance losses. When it comes to Neural Processing Units (NPUs), where increasing the inference speed is the primary goal, such performance losses cannot be tolerated. In this work, we are the first to propose a reliability-aware quantization to eliminate aging effects in NPUs while completely removing guardbands. Our technique delivers a graceful inference accuracy degradation over time while compensating for the aging-induced delay increase of the NPU. Our evaluation, over ten state-of-the-art neural network architectures trained on the ImageNet dataset, demonstrates that for an entire lifetime of 10 years, the average accuracy loss is merely 3%. In the meantime, our technique achieves 23% higher performance due to the elimination of the aging guardband.
Keywords: Approximate Computing, Adaptive Approximation, Aging, Neural Networks, Quantization, Reliability.
