Instruction-aware learning-based timing error models through significance-driven approximations

S Tompazi, I Tsiokanos, JM del-Rincon… - 2022 IEEE 40th …, 2022 - ieeexplore.ieee.org
The adoption of aggressively down-scaled voltages along with worsening process
variations, render nanometer devices prone to timing errors that threaten system …

Microarchitecture-aware timing error prediction via deep neural networks

S Tompazi, G Karakonstantis - … on On-Line Testing and Robust …, 2023 - ieeexplore.ieee.org
Nanometer circuits are becoming increasingly prone to timing errors due to worsening
parametric variations and operation close to voltage and frequency limits. Such errors …

ePredictNet: Low Cost Error Prediction Neural Network

G Chatzitsompanis, G Karakonstantis - Proceedings of the 29th ACM …, 2024 - dl.acm.org
The pursuit of miniature energy-efficient chips, and push for scaled voltages leads to
increased timing errors that threaten the correct system functionality. Conventional error …

Guest Editors' Introduction: Special Issue on Machine Learning for CAD/EDA

U Schlichtmann, B Li, B Yu, R Gal - IEEE Design & Test, 2023 - ieeexplore.ieee.org
Moore's Law is still alive and well, as far as increasing the complexity of integrated circuits
(ICs) is concerned. Logic ICs with about 20 billion transistors or even more are being …

AVATAR: An Aging-and Variation-Aware Dynamic Timing Analyzer for Error-Efficient Computing

Z Zhang, Z Guo, Y Lin, M Li, R Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
As the timing guardband consumes more and more design margin with the technology
scaling, better-than-worst-case (BTWC) techniques have gained more attention as a …

A Compressed and Accurate Sparse Deep Learning-based Workload-Aware Timing Error Model

S Tompazi, G Karakonstantis - 2023 IEEE 41st International …, 2023 - ieeexplore.ieee.org
This paper showcases the novel application of Deep-Learning (DL) in the development of
accurate microarchitecture and workload-aware timing error models and investigates …

[PDF][PDF] Microarchitecture and Workload-Aware Error Prediction

S Tompazi - 2024 - pure.qub.ac.uk
In 1975, Moore observed that the complexity of integrated circuits would double every two
years towards the end of the decade, instead of every year [83]. He predicted that this would …

PoC Self-Generation Technology Based on Vulnerability Verification Program

F Long, F Gao, Z Zha, J Chen, M Yu… - 2023 IEEE 4th …, 2023 - ieeexplore.ieee.org
With the continuous development of the computer field, the network application is more and
more extensive, and various security problems also appear. In this environment, a self …