Performance Improvement of Processor Through Configurable Approximate Arithmetic Units in Multicore Systems

SAK Gharavi, S Safari - IEEE Access, 2024 - ieeexplore.ieee.org
Multicore systems are utilized in a wide range of applications, from embedded systems to
high-performance applications. Controlling power consumption while maximizing …

LCT-TL: Learning Classifier Table (LCT) with Transfer Learning for runtime SoC performance-power optimization

A Surhonne, F Maurer, T Wild… - 2023 IEEE 16th …, 2023 - ieeexplore.ieee.org
Learning classifier tables (LCTs) are lightweight and classifier-based reinforcement learning
building blocks in hardware that inherit the concepts of learning classifier systems. LCTs are …

EPIC-Q: E quivalent-P olicy I nvariant C omparison Enhanced Transfer Q-learning for Run-Time SoC Performance-Power Optimization

A Surhonne, HS Fawzi, F Maurer, O Lenke… - … on Embedded Computer …, 2024 - Springer
As power density becomes the main constraint of multicore systems, managing power
consumption using DVFS while providing the desired performance becomes increasingly …