Accelerating Scientific Computing in the Post-Moore's Era

Kathleen E. Hamilton; Catherine D. Schuman; Steven R. Young; Ryan S. Bennink; Neena Imam; Travis S. Humble

doi:10.1145/3380940

Accelerating Scientific Computing in the Post-Moore's Era

Kathleen E. Hamilton, Catherine D. Schuman, Steven R. Young, Ryan S. Bennink, Neena Imam, Travis S. Humble

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

Novel uses of graphical processing units for accelerated computation revolutionized the field of high-performance scientific computing by providing specialized workflows tailored to algorithmic requirements. As the era of Moore's law draws to a close, many new non-von Neumann processors are emerging as potential computational accelerators, including those based on the principles of neuromorphic computing, tensor algebra, and quantum information. While development of these new processors is continuing to mature, the potential impact on accelerated computing is anticipated to be profound. We discuss how different processing models can advance computing in key scientific paradigms: machine learning and constraint satisfaction. Significantly, each of these new processor types utilizes a fundamentally different model of computation, and this raises questions about how to best use such processors in the design and implementation of applications. While many processors are being developed with a specific domain target, the ubiquity of spin-glass models and neural networks provides an avenue for multi-functional applications. This also hints at the infrastructure needed to integrate next-generation processing units into future high-performance computing systems.

Original language	English
Article number	6
Journal	ACM Transactions on Parallel Computing
Volume	7
Issue number	1
DOIs	https://doi.org/10.1145/3380940
State	Published - Mar 2020

Funding

This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC0500OR22725 with the U.S. Department of Energy. The publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for the United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan. This work was supported in part by the United States Department of Defense and used resources of the Computational Research and Development Programs at Oak Ridge National Laboratory. Research sponsored in part by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the U. S. Department of Energy. The work was supported in part by the Department of Energy, Office of Science, Early Career Research Program. This work was partially supported as part of the ASCR Testbed Pathfinder Program at Oak Ridge National Laboratory under FWP #ERKJ332. This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, under contract number DE-AC05-00OR22725. Authors’ addresses: K. E. Hamilton (corresponding author), C. D. Schuman, S. R. Young, R. S. Bennink, N. Imam, T. S. Humble, Computing and Computational Sciences Directorate, Oak Ridge National Laboratory, One Bethel Valley Road, Oak Ridge, TN, 37831; emails: {hamiltonke, schumancd, youngsr, benninkrs, imamn, humblets}@ornl.gov. Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of the United States government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only. © 2020 Copyright held by the owner/author(s). Publication rights licensed to ACM. 2329-4949/2020/03-ART6 $15.00 https://doi.org/10.1145/3380940

Funders	Funder number
U.S. Department of Defense
U.S. Department of Energy
Office of Science
Advanced Scientific Computing Research	FWP #ERKJ332, DE-AC05-00OR22725
Oak Ridge National Laboratory

Keywords

Graph algorithms
constraint satisfaction problems
machine learning
neuromorphic computing
optical Ising machines
quantum computing

Access to Document

10.1145/3380940

Cite this

@article{f79c8172deaf4277b8457c55dd293fc7,

title = "Accelerating Scientific Computing in the Post-Moore's Era",

abstract = "Novel uses of graphical processing units for accelerated computation revolutionized the field of high-performance scientific computing by providing specialized workflows tailored to algorithmic requirements. As the era of Moore's law draws to a close, many new non-von Neumann processors are emerging as potential computational accelerators, including those based on the principles of neuromorphic computing, tensor algebra, and quantum information. While development of these new processors is continuing to mature, the potential impact on accelerated computing is anticipated to be profound. We discuss how different processing models can advance computing in key scientific paradigms: machine learning and constraint satisfaction. Significantly, each of these new processor types utilizes a fundamentally different model of computation, and this raises questions about how to best use such processors in the design and implementation of applications. While many processors are being developed with a specific domain target, the ubiquity of spin-glass models and neural networks provides an avenue for multi-functional applications. This also hints at the infrastructure needed to integrate next-generation processing units into future high-performance computing systems.",

keywords = "Graph algorithms, constraint satisfaction problems, machine learning, neuromorphic computing, optical Ising machines, quantum computing",

author = "Hamilton, {Kathleen E.} and Schuman, {Catherine D.} and Young, {Steven R.} and Bennink, {Ryan S.} and Neena Imam and Humble, {Travis S.}",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.",

year = "2020",

month = mar,

doi = "10.1145/3380940",

language = "English",

volume = "7",

journal = "ACM Transactions on Parallel Computing",

issn = "2329-4949",

publisher = "Association for Computing Machinery (ACM)",

number = "1",

}

TY - JOUR

T1 - Accelerating Scientific Computing in the Post-Moore's Era

AU - Hamilton, Kathleen E.

AU - Schuman, Catherine D.

AU - Young, Steven R.

AU - Bennink, Ryan S.

AU - Imam, Neena

AU - Humble, Travis S.

PY - 2020/3

Y1 - 2020/3

N2 - Novel uses of graphical processing units for accelerated computation revolutionized the field of high-performance scientific computing by providing specialized workflows tailored to algorithmic requirements. As the era of Moore's law draws to a close, many new non-von Neumann processors are emerging as potential computational accelerators, including those based on the principles of neuromorphic computing, tensor algebra, and quantum information. While development of these new processors is continuing to mature, the potential impact on accelerated computing is anticipated to be profound. We discuss how different processing models can advance computing in key scientific paradigms: machine learning and constraint satisfaction. Significantly, each of these new processor types utilizes a fundamentally different model of computation, and this raises questions about how to best use such processors in the design and implementation of applications. While many processors are being developed with a specific domain target, the ubiquity of spin-glass models and neural networks provides an avenue for multi-functional applications. This also hints at the infrastructure needed to integrate next-generation processing units into future high-performance computing systems.

AB - Novel uses of graphical processing units for accelerated computation revolutionized the field of high-performance scientific computing by providing specialized workflows tailored to algorithmic requirements. As the era of Moore's law draws to a close, many new non-von Neumann processors are emerging as potential computational accelerators, including those based on the principles of neuromorphic computing, tensor algebra, and quantum information. While development of these new processors is continuing to mature, the potential impact on accelerated computing is anticipated to be profound. We discuss how different processing models can advance computing in key scientific paradigms: machine learning and constraint satisfaction. Significantly, each of these new processor types utilizes a fundamentally different model of computation, and this raises questions about how to best use such processors in the design and implementation of applications. While many processors are being developed with a specific domain target, the ubiquity of spin-glass models and neural networks provides an avenue for multi-functional applications. This also hints at the infrastructure needed to integrate next-generation processing units into future high-performance computing systems.

KW - Graph algorithms

KW - constraint satisfaction problems

KW - machine learning

KW - neuromorphic computing

KW - optical Ising machines

KW - quantum computing

UR - http://www.scopus.com/inward/record.url?scp=85083233363&partnerID=8YFLogxK

U2 - 10.1145/3380940

DO - 10.1145/3380940

M3 - Article

AN - SCOPUS:85083233363

SN - 2329-4949

VL - 7

JO - ACM Transactions on Parallel Computing

JF - ACM Transactions on Parallel Computing

IS - 1

M1 - 6

ER -

Accelerating Scientific Computing in the Post-Moore's Era

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this