Energy Efficient HPC State of the Practice Workshop  Presentations

Event: Call for Papers (Energy Efficient HPC State of the Practice Workshop (EE HPC SOP 2019) )

Subject: The 48th International Conference on Parallel Processing (ICPP 2019)

Date/Time: August 5 – August 8, 2019

Location: Kyoto, Japan

Submission Deadline: May 1st, 2019

Website: https://www.hpcs.cs.tsukuba.ac.jp/icpp2019/

 

Key Dates

 

Submissions Open:  February 15, 2019

Submission Deadline:  May 01, 2019

Author Notification:  May 30, 2019

Camera Ready Paper:  June 07, 2019

All dates are Anywhere on Earth

 

Scope And Objectives

 

The facility demands for supercomputing centers (SCs) are characterized by electrical power demands for computing systems that scale to tens of megawatts (MW) and millisecond voltage fluctuations approaching 10MW for the largest systems. The demand for primary electrical distribution capabilities to current large-scale facilities can exceed 60MW, comprising multiple, redundant, and diverse medium-voltage feeders.   Despite significant pressure on both Moore’s Law and Dennard scaling, the appetite for ever-larger systems and the subsequent demand for both agile power and effective cooling for these systems continues to grow. Computing trends, in terms of highly optimized hardware platforms that may leverage accelerators or other non-traditional components, scalable and high performing applications, and the requirements to manage exponentially larger data sets are driving facility demands not envisioned just a few years ago.

 

SC facilities must consider multiple elements, including the cost to extend or fit existing primary distribution capabilities; the cost and consequence of both trapped and stranded capacity, ever-increasing heat densities for new systems that may render existing cooling mechanisms obsolete or ineffective, increased mandatory use of liquid cooling for portions of the heat load, and wet weights that exceed the carrying capacities of existing raised floor systems.

 

Additionally, the operational costs of these facilities must be balanced versus the demand from the systems owners and users for high availability, high utilization, and low-impact facility maintenance and service demands. To achieve this balance, many SCs continue to innovate their operational design practices and technologies. Solutions seek improved management of both the electrical and mechanical systems, and minimizing long-term facility costs through best practices associated with their design.

 

Some SCs 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 buildings and building infrastructure.

 

The purpose of this workshop is to allow for publication of practices, policies, procedures, and technologies in formal peer-reviewed papers so the broader community can benefit from these experiences.  The nature of these papers is generally descriptive with hard experiential data generally gathered through surveys, case studies and research for practice.

 

Workshop Topics of Interest Include (but are not limited to)

 

Reports on experience gained with grid integration

  •  Impact of large HPC power loads and rapid voltage swings on electrical distribution systems
  •  Demand response and other ‘sustainability’ programs
  •  Negotiations on contracts with electricity service providers

 

Use cases, lessons learned and best practices from large-scale, production deployment of:

  •  integrated operational data collection and analytics
  •  Energy and power-aware job scheduling and resource management
  •  Liquid cooling control systems for HPC facilities, systems or both
  • Standards and open interfaces for power management and energy efficiency (e.g., Power API, Redfish, GEOPM, READEX, PowerStack)

 

Experiences from extending the L2/L3 power measurement methodology to other benchmarks (beyond HPL)

Use cases, lessons learned and best practices from:

  • Energy and power considerations during procurement of HPC systems
  • Liquid cooling commissioning
  • HPC facility preventative maintenance and management practices for RAS-M (reliability, availability, serviceability, and maintainability)
  • Energy and power considerations during facility construction or improvement that supports HPC systems
  • Measuring and evaluating the value of ITUE (IT power usage effectiveness), similar to PUE but “inside” the system and TUE (total power usage effectiveness)

 

 

Paper Submission

 

Abstracts and papers to be submitted via Easy Chair - https://easychair.org/conferences/?conf=eehpcsop2019

Accepted papers must be presented at the workshop.

Long papers should not exceed **8** pages and short papers should not exceed **4** pages in the ACM format

For reproducibility, authors are expected to provide an appendix describing the methods used to gather, test and archive the data described in the paper.  This appendix is not included in the page limit, but cannot exceed **2** pages.

 

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 ACM as part of the ICPP2019 Proceedings in a companion volume for workshops.

 

 

Organizing Committee

 

Natalie Bates, Energy Efficient HPC Working Group

Fumiyoshi Shoji, RIKEN

Jim Rogers, Oak Ridge National Laboratory

Greg. Koenig, KPMG

Siddhartha Jana, Intel

Torsten Wilde, HPE

 

 

Program Committee

 

Steve Martin, Cray Inc.

Todd Rosedahl, IBM

Anders Clausen, University Southern Denmark

Grant Stewart, Los Alamos National Laboratory

Ryan Grant, Sandia National Laboratory

Thomas Scogland, Lawrence Livermore National Laboratory

Ladina Gilly, Swiss National Supercomputing Center

Jason Hick, Los Alamos National Laboratory

James H. Laros, Sandia National Laboratory

Gert Svensson, Royal Institute of Technology (KTH)

Anna Maria Bailey, Lawrence Livermore National Laboratory

David Grant, Oak Ridge National Laboratory

David Martinez, Sandia National Laboratory

Jeff Broughton, Lawrence Berkeley National Laboratory

Norman Bourassa, Lawrence Berkeley National Laboratory

Herbert Huber, Leibniz Supercomputing Center (LRZ)

Daniel Hackenberg, Technical University of Dresden

Ted Kubaska, Independent Technical Writer & Software Engineer

Tapasya Patki, Lawrence Livermore National Laboratory

Matthias Maiterth, LMU Munich and Intel

Barry Rountree, Lawrence Livermore National Laboratory

Barbara Macchioni, Lawrence Livermore National Laboratory

John Gutman, Oak Ridge National Laboratory

Francis Belot, Alternative Energies and Atomic Energy Commission (CEA)

François Robin, Alternative Energies and Atomic Energy Commission (CEA)

Andrea Bartolini, University of Bologna

Bilel Hadri, King Abdullah University of Science and Technology

 

Lawrence Livermore National Laboratory

7000 East Avenue • Livermore, CA 94550

Operated by Lawrence Livermore National Security, LLC, for the Department of Energy's National Nuclear Security Administration

LLNL-WEB-670983  |  Privacy & Legal Notice | Site Search

Energy Efficient HPC Working Group

Energy Efficient HPC State of the Practice Workshop

Energy Efficient HPC State of the Practice Workshop  Presentations