Kostadinos Parasyris
About Kostadinos Parasyris
Kostadinos Parasyris is a Postdoctoral Researcher at Lawrence Livermore National Laboratory, focusing on reducing energy consumption in modern CPU systems through Significance Aware Computing. His research includes aggressive optimizations and applications in Approximate and Unreliable Computing to enhance performance and energy efficiency.
Work at Lawrence Livermore National Laboratory
Kostadinos Parasyris has been serving as a Postdoctoral Researcher at Lawrence Livermore National Laboratory since 2020. His work focuses on reducing energy consumption in modern CPU systems through the application of Significance Aware Computing. This role involves engaging in aggressive optimizations to enhance program output quality by exploiting computation significance. His research contributes to advancements in energy efficiency and performance in computational systems.
Education and Expertise
Kostadinos Parasyris holds a Bachelor's degree in Computer and Communication Engineering from the University of Thessaly, which he completed from 2007 to 2013. He furthered his education at the same institution, obtaining a Master's degree in Electrical and Computer Engineering from 2015 to 2018. He also earned a Doctor of Philosophy (PhD) in a related field from the University of Thessaly. His academic background provides a strong foundation for his research in Approximate and Unreliable Computing.
Background in Research
Before his current position, Kostadinos Parasyris worked as a Researcher at the Centre for Research & Technology Hellas (CERTH) from 2013 to 2016. He then continued his research career at the University of Thessaly from 2016 to 2018. His experience in these roles has contributed to his expertise in energy efficiency and performance optimization in computing systems.
Research Focus and Contributions
Kostadinos Parasyris specializes in reducing energy consumption in CPU systems through innovative research in Significance Aware Computing. His work involves exploring applications in Approximate and Unreliable Computing, aiming to improve both performance and energy efficiency. This focus on aggressive optimizations reflects his commitment to advancing computational technologies.