RIKEN Center for Computational Science


The 177th R-CCS Cafe

The 177th R-CCS Cafe
Date and Time: Wed. July 31, 2019, 14:00 - 15:30
Place: Seminar Room (1st floor) at R-CCS

Title: Global Collaboration to Improve HPC Energy Efficiency
Speaker: Natalie Bates (Energy Efficient HPC Working Group)

Presentation Language: English
Presentation Material: English


The purpose of the Energy Efficient HPC Working Group (EE HPC WG) is to promote energy efficiency in HPC. The EE HPC WG develops best practices for maximizing energy efficiency in HPC facilities and systems. It provides a venue for sharing of information (peer-to-peer exchange) and collective action. The EE HPC WG is cross-disciplinary and encourages interaction between facilities, operations and computational science organizations.
The EE HPC WG has a strong presence in the United States and Europe, with a growing presence in Japan. The Japanese HPC centers have a lot of innovative technologies and approaches that work towards improving HPC energy efficiency. The United States and European HPC centers would like to learn more about their Japanese counterparts.
The purpose of this seminar is to promote further collaboration between the United States, Europe and Japan within the EE HPC WG. This seminar will describe the EE HPC WG. It will describe areas where Japanese HPC centers have already contributed to the EE HPC WG. The seminar will be informational, but will also allow for discussion and exploration of further collaborative opportunities.
Below are some of the EE HPC WG Teams that will be discussed in this seminar. Some of the Teams focus more on HPC systems and others more on HPC facilities, but none of them are exclusively one or the other..
• _Energy and Power Aware Job Scheduling and Resource Management:_ This team did a global survey of sites deploying the emerging EPA JSRM technologies to evaluate what they are doing and trying to accomplish. Three papers were published. The team is currently investigating site policies for EPAJSRM with a view towards optimization techniques.
• _Operational Data Analytics:_ This team has published 3 case studies and is doing a global survey to evaluate the benefits and challenges of instrumentation, data collection and analytics for facility operations, including data from HPC systems.
• _System Power Measurement Methodology:_ The Green500 and Top500 power measurement methodology has been made more rigorous, consistent and higher quality as a result of this Team. The team is still working on promoting the use of the highest quality measurements.
• _Grid Integration:_ Demand Response for the electric grid was the initial focus of this team and two papers were published describing how sites were reacting to demand response opportunities from their electricity service providers. The Team is now focused on rapid and extreme voltage fluctuations from HPC systems and the impact that might have on the electric grid. It has done a limited site survey and published a short paper on this topic. Further investigation is underway.