Online Panel Discussion

Sustainable Hybrid Approaches for HPC (Rebroadcast)

Series: Strategies for Working Remotely

This panel discussion was held during SC21 and is being rebroadcast with live chat Q&A. The panel explored strategies for working remotely, with emphasis on how teams in high-performance computing (HPC) can be effective and efficient in long-term hybrid settings, where some staff work remotely and others on site, or collaborate while geographically dispersed.

In spring 2020 many of us abruptly transitioned from a primarily on-site to a primarily remote work experience. Unplanned and imposed remote work created a sea change that has altered the way we work now and will likely impact the way we work in the future. This panel will explore strategies for working remotely, with emphasis on how teams in high-performance computing (HPC) can be effective and efficient in long-term hybrid settings, where some staff work remotely and others on site, or collaborate while geographically dispersed. This shift provides an opportunity to be more inclusive and compassionate, opening doors for technological innovation to support how we work and communicate as teams of scientists. By exploring how hybrid settings can help with hiring and retaining a diverse set of employees, this panel session will offer an opportunity for dialog to help shape and influence the future of HPC work (see



Panelist Bios

Christian Bischof is professor for scientific computing and head of the university computing center at Technical University (TU) Darmstadt. He studied Mathematics at the University of Würzburg, then continued his studies at Cornell University under a Fulbright fellowship, and completed a Ph.D. in computer science in 1988. Thereafter, he joined the Mathematics and Computer Science Division at Argonne National Laboratory as the first Wilkinson Fellow in Computational Mathematics, and continued as staff member until 1998. Then he was professor for high-performance computing and head of the Center for Computing and Communication at RWTH Aachen University until 2011. His research interests include performance engineering, performance measurement and modeling, algorithms for cryptanalysis, source transformations and automatic differentiation as well as software engineering practices for reliability and reproducibility. He is a head of the National High-Performance Computing Center for Computational Engineering Sciences (NHR4CES), a joint effort of TU Darmstadt with RWTH Aachen University.

Helen Cademartori is the Deputy of Operations for the Computing Sciences Area, and the Computational Research Division. She has held similar positions in Biosciences and the IT Division during her 13 year tenure at the Lawrence Berkeley National Lab (Berkeley Labs). In her current role she oversees all business and operational aspects of operations including Human Resources, finance, travel, conferences and procurement, proposal development, space management and environmental health and safety. She is also responsible for strategic planning for new initiatives and infrastructure upgrades.

Devin Hodge is the Chief Operations Officer for Argonne National Laboratory’s Computing, Environment, and Life Sciences (CELS) directorate. He leads both long- and short-range strategic and tactical operations for CELS and is responsible for the development, implementation, and management of efficient, cost- effective, and high-quality operational and administrative support activities for the directorate. He has more than two decades of leadership experience. Prior to his current appointment, Devin was the Deputy Director of Operations for Argonne’s Joint Center for Energy Storage Research, and he has held positions in sustainability, waste management, environmental compliance, nuclear operations, and project management. Recently, Devin led a team that collected feedback on employee perspectives on long-term full- and part-time remote work (after the disruption of COVID-19) as part of Argonne’s Next Generation Workplace initiative.

Kengo Nakajima is a Professor in the Supercomputing Research Division, Information Technology Center at the University of Tokyo. Prior to joining the University of Tokyo in 2004, he spent 19 years in industry. He also has been a Deputy Director of RIKEN R-CCS (Center for Computational Science) since 2018. His research interests include computational mechanics, computational fluid dynamics, numerical linear algebra, parallel iterative algorithms, parallel preconditioning methods, multigrid methods, parallel programming models, adaptive mesh refinement, and parallel visualization. His degrees are B. Eng (1985, Aeronautics, University of Tokyo), M.S. (1993, Aerospace Engineering, University of Texas at Austin), and Ph.D. (2003, Engineering Mechanics, University of Tokyo).

Pat Quillen is a software engineering manager at MathWorks; his group is responsible for the mathematics in MATLABTM as well as the PDE Toolbox. His team of computational scientists and software engineers focuses on building high-quality, mathematically-sound technical computing software to help accelerate the pace of engineering and science. Like many, Pat and his whole team have been working remotely only since March 2020.

Moderator Bio

Elaine Raybourn is a social scientist in the Statistics and Human Systems Group (Applied Cognitive Science) at Sandia National Laboratories. Her research focuses on virtual teams, software developer productivity, virtual environments, visualization, and transmedia learning. She is the SC21 Scientific Visualization & Data Analytics Showcase Chair. Elaine has worked remotely for a combined total of 14 years while at Sandia National Laboratories: from the UK as a guest researcher at British Telecom; Germany (Fraunhofer FIT) and France (INRIA) as a Fellow of the European Research Consortium in Informatics and Mathematics (ERCIM), and most recently from Orlando, Florida as Sandia’s Institutional PI for the IDEAS-ECP productivity project. Elaine leads PSIP and the panel series Strategies for Working Remotely.