This event is a part of the "Best Practices for HPC Software Developers" webinar series, produced by the IDEAS Productivity family of projects. The HPC Best Practices webinars address issues faced by developers of computational science and engineering (CSE) software on high-performance computers (HPC) and occur approximately monthly.
| Resource Information | Details |
|---|---|
| Webinar Title | High-Performance Computing and Software Sustainability: Toward Green Software Development |
| Date and Time | 2025-01-15 1:00 pm - 2:00 pm EST |
| Presenter | Antigoni Georgiadou (Oak Ridge National Laboratory) |
| Registration, Information, and Archives | https://ideas-productivity.org/events/hpcbp-089-green-software |
| Presentation Language | English |
Webinars are free and open to the public, but advance registration is required through the Event website. Archives (recording, slides, Q&A) will be posted at the same link soon after the event, and all registrants will be notified.
Abstract
The power consumption of data centers is becoming a hot topic. With the growth of AI and exascale, systems are requiring 30+ MW, enough to power sizable towns. There is widespread interest in green software development, with academia, government, and industry spearheading the discussion of how software developers can produce better software in terms of more energy-efficient approaches. This presentation will discuss topics concerning Leadership Computing Facilities with respect to energy consumption, awareness of the costs of running on the systems, and potential green software practices. This talk aims to spark further discussion on specific software practices related to energy-efficient software. The goals include raising awareness of good software practices, improving scientific productivity, and informing ongoing efforts for sustainability planning.
Presenter
- Antigoni Georgiadou (Oak Ridge National Laboratory)
Presenter Bio
Antigoni Georgiadou is a Computational Scientist in Mathematics at the Oak Ridge National Laboratory in the Science Engagement Section, Algorithms & Performance Analysis (APA) Group. Dr. Georgiadou obtained her Ph.D. in Computational Mathematics from Florida State University, where she worked on optimization in stellar evolution applications. Before joining the APA Group, Antigoni Georgiadou was a postdoctoral research associate in OLCF’s Advanced Computing for Nuclear, Particles, & Astrophysics Group. Astrophysics applications and simulations motivate some of her research; collaborates with scientists across domains to optimize performance and requirements of applications on OLCF supercomputers. Dr. Georgiadou is the task lead of the Uncertainty Quantification Working Group in the Science Engagement section and has been supporting INCITE, ECP, and CAAR projects for current and emerging GPU-accelerated systems at the OLCF. Dr. Georgiadou has served as chair of the SC workshop on “Enabling Predictive Science with Optimization and Uncertainty Quantification in HPC” taking place at SC’23 and SC’24. Since July 2023, she also serves as a member of the Fortran standards committee.
