Giorgis Georgakoudis

prof_pic.jpg

Hello! My name is Giorgis Georgakoudis and I work as a Computer Scientist in the Center for Advanced Scientific Computing (CASC) at Lawrence Livermore National Laboratory (LLNL), USA.

I obtained my PhD in Computer Engineering from the University of Thessaly, Greece in 2017. From 2013 until 2018, I was working at Queen’s University of Belfast, United Kingdom concurrently with my doctoral studies. Since 2018, I work at the Lawrence Livermore National Laboratory.

My research interests are on High Performance Computing (HPC) and include parallel programming models, performance analysis/optimization, compilers, and fault tolerance. Among other work, I am a contributor to the LLVM project, enabling parallelism-aware compiler optimizations for parallel programs in OpenMP. Also, I am the main developer and maintainer of Apollo, which is a programmable, machine-learning-based autotuning library.

selected publications

2022

  1. IPDPS’22
    Co-Designing an OpenMP GPU Runtime and Optimizations for Near-Zero Overhead Execution
    Johannes Doerfert, Atemn Patel, Joseph Huber, Shilei Tian, Jose M Monsalve Diaz, Barbara Chapman, and Giorgis Georgakoudis
    In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2022
    (acceptance 26% 123/474)

2021

  1. SC21
    HPAC: Evaluating Approximate Computing Techniques on HPC OpenMP Applications
    Konstantinos Parasyris, Giorgis Georgakoudis, Harshitha Menon, James Diffenderfer, Ignacio Laguna, Daniel Osei-Kuffuor, and Markus Schordan
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2021
    Best reproducibility award (acceptance 25.8% 98/379)
  2. ISC’21
    Artemis: Automatic Runtime Tuning Of Parallel Execution Parameters Using Machine Learning
    Chad Wood, Giorgis Georgakoudis, David Beckingsale, David Poliakoff, Alfredo Gimenez, Kevin Huck, Allen Malony, and Todd Gamblin
    In High Performance Computing: 36th International Conference, ISC High Performance 2021, Virtual Event, June 24 – July 2, 2021, Proceedings, 2021
    (acceptance 32.4% 24/74)

2020

  1. IWOMP 2020
    FAROS: A Framework to Analyze OpenMP Compilation Through Benchmarking and Compiler Optimization Analysis
    Giorgis Georgakoudis, Johannes Doerfert, Ignacio Laguna, and Thomas R. W. Scogland
    In OpenMP: Portable Multi-Level Parallelism on Modern Systems, 2020
    Best paper award
  2. ISC’20
    Reinit++: Evaluating the Performance of Global-Restart Recovery Methods for MPI Fault Tolerance
    Giorgis Georgakoudis, Luanzheng Guo, and Ignacio Laguna
    In High Performance Computing, 2020
    (acceptance 31% 27/87)

2019

  1. IPDPS’19
    SAFIRE: Scalable and Accurate Fault Injection for Parallel Multithreaded Applications
    Giorgis Georgakoudis, Ignacio Laguna, Hans Vandierendonck, Dimitrios S. Nikolopoulos, and Martin Schulz
    In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS), May 2019
    (acceptance 28% 103/372)

2017

  1. SC17
    REFINE: Realistic Fault Injection via Compiler-based Instrumentation for Accuracy, Portability and Speed
    Giorgis Georgakoudis, Ignacio Laguna, Dimitrios S. Nikolopoulos, and Martin Schulz
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, May 2017
    (acceptance 19% 61/327)