Opportunities from
the INTEGRATION of
SIMULATION SCIENCE
and DATA SCIENCE

PROCEEDINGS OF A WORKSHOP

Committee on Future Directions for NSF
Advanced Computing Infrastructure to Support U.S. Science in 2017-2020

Computer Science and Telecommunications Board

Division on Engineering and Physical Sciences

THE NATIONAL ACADEMIES PRESS
Washington, DC
www.nap.edu

THE NATIONAL ACADEMIES PRESS 500 Fifth Street, NW Washington, DC 20001

This activity was supported by contracts between the National Academy of Sciences and the National Science Foundation under award number OCI-1344417. Any opinions, findings, conclusions, or recommendations expressed in this publication do not necessarily reflect the views of any organization or agency that provided support for the project.

International Standard Book Number-13: 978-0-309-48186-1
International Standard Book Number-10: 0-309-48186-4
Digital Object Identifier: https://doi.org/10.17226/25199

Copyright 2018 by the National Academy of Sciences. All rights reserved.

Printed in the United States of America

Suggested citation: National Academies of Sciences, Engineering, and Medicine. 2018. Opportunities from the Integration of Simulation Science and Data Science: Proceedings of a Workshop. Washington, DC: The National Academies Press. doi: https://doi.org/10.17226/25199.

COMMITTEE ON FUTURE DIRECTIONS FOR NSF ADVANCED COMPUTING INFRASTRUCTURE TO SUPPORT U.S. SCIENCE IN 2017-2020

WILLIAM GROPP, NAE,¹ University of Illinois at Urbana-Champaign, Co-Chair

ROBERT J. HARRISON, Stony Brook University, Co-Chair

MARK ABBOTT, Woods Hole Oceanographic Institution

ROBERT GROSSMAN, University of Chicago

PETER M. KOGGE, EMU Solutions, Inc.

PADMA RAGHAVAN, Vanderbilt University

DANIEL A. REED, University of Utah

VALERIE E. TAYLOR, Argonne National Laboratory

KATHERINE A. YELICK, NAE, University of California, Berkeley

Staff

JON EISENBERG, Senior Director

KATIRIA ORTIZ, Associate Program Officer

SHENAE BRADLEY, Administrative Assistant

JANKI PATEL, Senior Program Assistant

___________________

¹ Member, National Academy of Engineering.

COMPUTER SCIENCE AND TELECOMMUNICATIONS BOARD

FARNAM JAHANIAN, Carnegie Mellon University, Chair

LUIZ ANDRÉ BARROSO, Google, Inc.

STEVEN M. BELLOVIN, NAE, Columbia University

ROBERT F. BRAMMER, Brammer Technology, LLC

DAVID CULLER, NAE, University of California, Berkeley

EDWARD FRANK, Cloud Parity, Inc.

LAURA HAAS, NAE, University of Massachusetts, Amherst

MARK HOROWITZ, NAE, Stanford University

ERIC HORVITZ, NAE, Microsoft Corporation

VIJAY KUMAR, NAE, University of Pennsylvania

BETH MYNATT, Georgia Institute of Technology

CRAIG PARTRIDGE, Raytheon BBN Technologies

DANIELA RUS, NAE, Massachusetts Institute of Technology

FRED B. SCHNEIDER, NAE, Cornell University

MARGO SELTZER, Harvard University

MOSHE VARDI, NAS¹/NAE, Rice University

Staff

JON EISENBERG, Senior Director

LYNETTE I. MILLETT, Associate Director

SHENAE BRADLEY, Administrative Assistant

EMILY GRUMBLING, Program Officer

RENEE HAWKINS, Financial and Administrative Manager

KATIRIA ORTIZ, Associate Program Officer

JANKI PATEL, Senior Program Assistant

For more information on CSTB, see its website at http://www.cstb.org, write to CSTB,
National Research Council, 500 Fifth Street, NW, Washington, DC 20001,
call (202) 334-2605, or email the CSTB at cstb@nas.edu.

___________________

¹ Member, National Academy of Sciences.

Preface

In 2016, the Committee on Future Directions for NSF Advanced Computing Infrastructure to Support U.S. Science in 2017-2020 issued a report making recommendations aimed at achieving four broad goals: (1) positioning the United States for continued leadership in science and engineering, (2) ensuring that resources meet community needs, (3) aiding the scientific community in keeping up with the revolution in computing, and (4) sustaining the infrastructure for advanced computing. In 2018, as the culmination of its work, the committee organized a workshop, which is summarized in this report, to explore opportunities for the integration of simulation and data-driven science.

The workshop was organized to examine current and emerging science applications that span simulation and data-driven science, their characteristics, and future approaches for cyberinfrastructure to support them, with a focus on advanced computing needs. It was focused on building on issues and themes advanced in the committee’s report and engaged representatives of scientific communities who currently work at the simulation-data intersection or may do so in the future as well as those exploring new computing architectures for supporting this research. Some examples of the types of questions posed to attendees during this workshop include:

• How can one characterize the range of scientific research that involves simulation and data-driven science? Is there a set of particular cases that can be used to illustrate that range?
• To what extent can converged cyberinfrastructure designed to support simulation and data-driven science meet future science needs, and what applications may require more specialized approaches?
• How much of convergence can be accomplished through shared systems vs. using the same basic components and architectures but in different configurations?
• What are the implications and opportunities for science of the convergence between high-performance computing and data analytics in the commercial sector?
• What roles can cloud technologies and commerce cloud providers play in meeting the needs of future science?
• What technical barriers exist to achieving convergence, such as different software stacks for simulation and data-driven science?
• What are some next steps that the scientific community could take to better understand future applications, cyberinfrastructure requirements, and opportunities for convergence?

The first chapter provides some context, drawing on William Gropp’s overview presentation. Chapter 2 contains brief summaries of presentations made at the workshop. Chapter 3 summarizes the closing discussion session along with some observations by the committee of themes throughout the workshop. The agenda of the workshop is in Appendix A. Short biosketches of the committee members and speakers appear in Appendixes B and C, respectively.

Our sincere thanks to the committee members and National Academies staff who helped organize the workshop, as well as to the invited speakers for their thoughtful remarks and enthusiastic participation in the discussions that ensued. The workshop proved especially timely, as evidenced by the high level of interest, and the enthusiasm and attentiveness of the workshop participants.

In preparing this report, some speakers prepared initial drafts of the summaries of their presentations, and all speakers were given an opportunity to review the accuracy of the summaries. Writing support was provided by Anne Frances Johnson, Creative Science Writing. Katiria Ortiz, associate program officer at the National Academies, organized the workshop and led development of this report. Shenae Bradley, administrative assistant, handled travel arrangements and meeting logistics. Jon Eisenberg, Computer Science and Telecommunications Board director, oversaw the project. We also extend our appreciation to the National Science Foundation for their support and encouragement of this activity.

William Gropp, University of Illinois at Urbana-Champaign, Co-Chair
Robert Harrison, Stony Brook University, Co-Chair

Acknowledgment of Reviewers

This Proceedings of a Workshop was reviewed in draft form by individuals chosen for their diverse perspectives and technical expertise. The purpose of this independent review is to provide candid and critical comments that will assist the National Academies of Sciences, Engineering, and Medicine in making each published proceedings as sound as possible and to ensure that it meets the institutional standards for quality, objectivity, evidence, and responsiveness to the charge. The review comments and draft manuscript remain confidential to protect the integrity of the process.

We thank the following individuals for their review of this proceedings:

Although the reviewers listed above provided many constructive comments and suggestions, they were not asked to endorse the content of the proceedings nor did they see the final draft before its release. The review of this proceedings was overseen by Daniel Atkins III, NAE, University of Michigan. He was responsible for making certain that an independent examination of this proceedings was carried out in accordance with standards of the National Academies and that all review comments were carefully considered. Responsibility for the final content rests entirely with the rapporteurs and the National Academies.

This page intentionally left blank.

Contents

1 INTRODUCTION

Workshop Context

2 PRESENTATION SUMMARIES

Science Drivers and Needs

Numerical Laboratories on Exascale

Frontiers at the Interface of High-Performance Computing, Big Data Analytics, Deep Learning, and Multimessenger Astrophysics

Data Science for Genomics

Data-Driven Materials Science

Envisioning a Cyberinfrastructure Ecosystem for an Era of Extreme Compute and Big Data

NSF’s Role in Cyberinfrastructure

Current and Future Developments

Guiding Principles Going Forward

Architectural Landscape and Trends

Evolving Toward Convergence

Google’s Tools for Convergence

Architectures at Amazon Web Services

Service, Usage Models, and Economics

Stream Processing and Simulation at Amazon Web Services

Campus-Based Systems and the National Cyberinfrastructure Ecosystem

Cloud Computing with Microsoft Azure

Data Storage and Retention

Data and Convergence at the Department of Energy

To Keep, or Not To Keep, That Is the Question: And Whether Convergence, Clouds, or Commons Is Better

Convergence Opportunities and Limits

Convergence Lessons: Future Infrastructure

Opportunities for Overcoming Data Bottlenecks

Modeling and Simulation (ModSim) Convergence in the Exascale Computing Project

3 WORKSHOP WRAP-UP DISCUSSION

Connecting Large Data Sets

Approaches to Moving Data

Quantifying User Needs

NSF’S Trade-Offs in Supporting Specialized, Midscale Systems

Alternative Ways to Allocate Investments and Track Costs

Observations

APPENDIXES

A Workshop Agenda and Participants List

B Steering Committee Biographies

C Speaker Biographies