EE HPC SOP 2022 Workshop
Sustainably supporting science through committed community action
Sustainably supporting science through committed community action
The 4th Energy Efficient HPC State of the Practice Workshop (EE HPC SOP) was held on October 24th from 8-11AM PT as part of the International Green and Sustainable Computing Conference (IGSCC).
INTRODUCTION 8AM Pacific TIme
Keynote Presentation: The Evolution of High Performance Computing (HPC) and the Path to Exascale at Lawrence Livermore National Laboratory (LLNL) by Anna Maria Bailey, Lawrence Livermore National Laboratory.
Electrical Commissioning Owner’s Project Requirements: A Template, Authors Brandon Hong, Lawrence Livermore National Laboratory; Aditya Deshpande, Microsoft and Ethan Thomason, Bureauveritas
-- Presentation: Electrical Commissioning Owner's Project Requirements: A Template
- Energy Aware Scheduler of Single/Multi-node Jobs Considering CPU Node Heterogeneity, Authors Keiichiro Fukazawa, Kyoto University; Jiacheng Zhou, Kyoto University; and Hiroshi Nakashima, Kyoto University
-- Presentation: Energy Aware Scheduler of Single/Multi-node Jobs Considering CPU Node Heterogeneity
BREAK 9:50-10:00 AM Pacific Time
Guiding Hardware-Driven Turbo with Application Performance Awareness, Authors Daniel C. Wilson, Boston University; Asma H. Al-Rawi, Intel; Lowren H. Lawson, Intel; Siddhartha Jana, Intel; Federico Ardanaz, Intel; Jonathan M. Eastep, Intel; and Ayse K. Coskun, Boston University
-- Presentation: Guiding Hardware Driven Turbo with Application Performance Awareness
- Soft Cluster powercap at SuperMUC-NG with EAR, Authors Julita Corbalan, Barcelona Supercomputing Center; Lluis Alonso, Barcelona Supercomputing Center; Carmen Navarrete, LRZ; and Carla Guillem, LRZ
-- Presentation: Soft Cluster powercap at SuperMUC-NG with EAR
CLOSURE 11:00AM Pacific Time
Speakers
Anna Maria Bailey is Lawrence Livermore National Laboratory’s (LLNL) HPC Chief Engineer. She holds a B.S. in Electrical Engineering from Cal Poly, San Luis Obispo and is registered with the California Board for Professional Engineers and Land Surveyors. She has 30+ years of experience in multiple engineering roles at LLNL, notably serving as the design/construction manager for LLNL’s HPC Center, which houses some of the world’s most powerful supercomputers. In addition, she led the effort to earn LEED certification for two HPC facilities and is currently overseeing the planning of an Exascale facility modernization project to prepare for unprecedented Exascale facility infrastructure challenges. She also serves as the co-chair of the Energy Efficient HPC Working Group (EE HPC WG).
Brandon Hong is the Lead Engineer of Strategic Initiatives and Planning for High Performance Computing at Lawrence Livermore National Laboratory. He has a B.S. in Electrical Engineering from University of California, Santa Barbara and is a registered Electrical Professional Engineer in California. Brandon manages the execution of the Livermore Computing HPC Facility Master Plan to enable the data centers to operate some of the world’s top supercomputers. He recently designed the electrical distribution for the exascale computer, El Capitan coming to LLNL in 2023. Brandon is currently the chair of the Electrical Commissioning team in the EE HPC WG.
Daniel Wilson received BS degrees in Computer Science and Computer Engineering from NC State University in Raleigh, North Carolina. He is working toward a PhD degree in Computer Engineering at Boston University. Prior to his current studies, Daniel worked at NetApp and Itron. He works as an intern at Intel while pursuing his PhD. His current research interests include energy-aware computing and systemwide optimization.
Lluis Alonso studied computer science in Universitat de Barcelona and graduated in 2018. He started working at BSC in that same year where he joined the EAR team in the computer science department. He started working in energy optimisation in HPC clusters which brought him to working on power capping solutions. Besides that, he is part of the REGALE project which also focuses on power and energy management in HPC.
ORGANIZING COMMITTEE
Torsten Wilde, Hewlett Packard Enterprise
Siddhartha Jana, Intel
Anna Maria Bailey, Lawrence Livermore National Laboratory
Natalie Bates, Energy Efficient HPC Working Group
PROGRAM COMMITTEE
Xingfu Wu, Argonne National Laboratory
Jim Rogers, Oak Ridge National Laboratory
Shirley Moore, University of Texas
Woong Shin, Oak Ridge National Laboratory
Rong Ge, Clemson University
Steven Martin, Hewlett Packard Enterprise
Melissa Romanus, Lawrence Berkeley National Laboratory
Vadim Elisseev, IBM
Toshio Endo, Tokyo Technical Institute of Technology
Jorji Nonaka, RIKEN
Gregory Koenig, Arkestro
Fumiyoshi Shoji, RIKEN
Yuetsu Kodama, RIKEN
Gregg Barrett, Cirrus AI
Matthias Maiterth, Technical University of Munich
Grant Stewart, Los Alamos National Laboratory
Masaaki Terai, RIKEN
Daniel Ellsworth, Colorado College
Thomas Durbin, Durbin Engineering
Bilel Hadri, KAUST
Aditya Deshpande, Microsoft
Marie-Christine Sawley, ICES FOUNDATION
Hayk Shoukourian, Bosch
Norman Bourassa, Lawrence Berkeley National Laboratory
Andy Gundry, European Center for Mid-range Weather Forecasts (ECMWF)
Francois Robin, CEA Retired
Michael Ott, Leibniz Supercomputing Center (LRZ)
ABSTRACT: Power and energy are recognized as first-order constraints in high-performance computing. Optimizing for various factors such as cost, efficiency and performance under power and energy constraints requires coordination across the infrastructure (e.g., mechanical and electrical systems), the HPC system (hardware and software), and end-user applications. There are early adopters and innovators in operational practices and technologies that are geared towards improving energy and power management capabilities. This workshop will explore these operational and technological innovations that span HPC computational systems as well as building infrastructure. The purpose of this workshop is to allow for the publication of practices, policies, procedures, and technologies in formal peer-reviewed papers so the broader community can benefit from these experiences. It will expose use cases, lessons learned, and best practices in design, commissioning, and operations. The nature of these papers is generally descriptive with hard experiential data gathered through surveys, case studies, and research for practice.
## Workshop Topics of interest include (but are not limited to):
## Workshop Topics of interest include (but are not limited to) the following areas, specifically related to HPC power and energy:
** Instrumentation, measurement, monitoring
** Management and control
** Operational data analytics
** Liquid cooling
** Electrical power distribution
** Procurement considerations
** APIs, standards, specifications, open solutions
** Reliability, availability, serviceability, and maintainability
** Efficiency and operational insights gained from working with emergency remote and/or limited on-site operations (e.g., due to COVID)
** Sustainability
==================================
This workshop will be held in conjunction with the International Green and Sustainable Computing Conference 2022.
KEY DATES: All dates are Anywhere on Earth
Call for Participation- June 17th
Submission Deadline- August 3rd August 10th
Author Notification- August 31st
Camera Ready Version- September 7th September 9th
Workshop Presentation- October 24th
==================================
The submission Web page for EE HPC SOP 2022 is https://easychair.org/conferences/?conf=eehpcsop2022
Accepted papers must be represented by at least one author and presented at the workshop, in alignment with the decision of the main conference series. There will be a registration fee for the Conference (specific fee amount TBD).
Any paper must:
not exceed 8 pages, including references. Any paper may be shorter than 8 pages.
be in PDF format.
be compliant with the IEEE template: https://www.ieee.org/conferences/publishing/templates.html
include author names and affiliations.
include appropriate citations of prior work.
The review committee will have ~35 people primarily selected for their expertise and willingness to review at least one paper. Each paper will have at least 3 reviewers. Reviewers are required to submit conflicts of interest information.
Submissions will be judged on correctness, novel or innovative approaches to a problem, technical and/or operational strength, written quality, and interest and relevance to the workshop scope. The workshop organizers will provide written reviews for all timely submissions. Editorial review and recommendations may be provided as well.
Accepted papers will be published by IEEE as part of the IGSC2022 Proceedings.