Flexible analysis software for emerging architectures

Kenneth Moreland, Brad King, Robert Maynard, Kwan-Liu Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We are on the threshold of a transformative change in the basic architecture of high-performance computing. The use of accelerator processors, characterized by large core counts, shared but asymmetrical memory, and heavy thread loading, is quickly becoming the norm in high performance computing. These accelerators represent significant challenges in updating our existing base of software. An intrinsic problem with this transition is a fundamental programming shift from message passing processes to much more fine thread scheduling with memory sharing. Another problem is the lack of stability in accelerator implementation; processor and compiler technology is currently changing rapidly. In this paper we describe our approach to address these two immediate problems with respect to scientific analysis and visualization algorithms. Our approach to accelerator programming forms the basis of the Dax toolkit, a framework to build data analysis and visualization algorithms applicable to exascale computing.

Original languageEnglish (US)
Title of host publicationProceedings - 2012 SC Companion
Subtitle of host publicationHigh Performance Computing, Networking Storage and Analysis, SCC 2012
Pages821-826
Number of pages6
DOIs
StatePublished - Dec 1 2012
Event2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012 - Salt Lake City, UT, United States
Duration: Nov 10 2012Nov 16 2012

Other

Other2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012
CountryUnited States
CitySalt Lake City, UT
Period11/10/1211/16/12

Fingerprint

Particle accelerators
Data storage equipment
Data visualization
Message passing
Visualization
Scheduling

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Cite this

Moreland, K., King, B., Maynard, R., & Ma, K-L. (2012). Flexible analysis software for emerging architectures. In Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012 (pp. 821-826). [6495897] https://doi.org/10.1109/SC.Companion.2012.115

Flexible analysis software for emerging architectures. / Moreland, Kenneth; King, Brad; Maynard, Robert; Ma, Kwan-Liu.

Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012. 2012. p. 821-826 6495897.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Moreland, K, King, B, Maynard, R & Ma, K-L 2012, Flexible analysis software for emerging architectures. in Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012., 6495897, pp. 821-826, 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012, Salt Lake City, UT, United States, 11/10/12. https://doi.org/10.1109/SC.Companion.2012.115
Moreland K, King B, Maynard R, Ma K-L. Flexible analysis software for emerging architectures. In Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012. 2012. p. 821-826. 6495897 https://doi.org/10.1109/SC.Companion.2012.115
Moreland, Kenneth ; King, Brad ; Maynard, Robert ; Ma, Kwan-Liu. / Flexible analysis software for emerging architectures. Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012. 2012. pp. 821-826
@inproceedings{022f6d5fd7ad4f5da5422138033cd54d,
title = "Flexible analysis software for emerging architectures",
abstract = "We are on the threshold of a transformative change in the basic architecture of high-performance computing. The use of accelerator processors, characterized by large core counts, shared but asymmetrical memory, and heavy thread loading, is quickly becoming the norm in high performance computing. These accelerators represent significant challenges in updating our existing base of software. An intrinsic problem with this transition is a fundamental programming shift from message passing processes to much more fine thread scheduling with memory sharing. Another problem is the lack of stability in accelerator implementation; processor and compiler technology is currently changing rapidly. In this paper we describe our approach to address these two immediate problems with respect to scientific analysis and visualization algorithms. Our approach to accelerator programming forms the basis of the Dax toolkit, a framework to build data analysis and visualization algorithms applicable to exascale computing.",
author = "Kenneth Moreland and Brad King and Robert Maynard and Kwan-Liu Ma",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/SC.Companion.2012.115",
language = "English (US)",
isbn = "9780769549569",
pages = "821--826",
booktitle = "Proceedings - 2012 SC Companion",

}

TY - GEN

T1 - Flexible analysis software for emerging architectures

AU - Moreland, Kenneth

AU - King, Brad

AU - Maynard, Robert

AU - Ma, Kwan-Liu

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We are on the threshold of a transformative change in the basic architecture of high-performance computing. The use of accelerator processors, characterized by large core counts, shared but asymmetrical memory, and heavy thread loading, is quickly becoming the norm in high performance computing. These accelerators represent significant challenges in updating our existing base of software. An intrinsic problem with this transition is a fundamental programming shift from message passing processes to much more fine thread scheduling with memory sharing. Another problem is the lack of stability in accelerator implementation; processor and compiler technology is currently changing rapidly. In this paper we describe our approach to address these two immediate problems with respect to scientific analysis and visualization algorithms. Our approach to accelerator programming forms the basis of the Dax toolkit, a framework to build data analysis and visualization algorithms applicable to exascale computing.

AB - We are on the threshold of a transformative change in the basic architecture of high-performance computing. The use of accelerator processors, characterized by large core counts, shared but asymmetrical memory, and heavy thread loading, is quickly becoming the norm in high performance computing. These accelerators represent significant challenges in updating our existing base of software. An intrinsic problem with this transition is a fundamental programming shift from message passing processes to much more fine thread scheduling with memory sharing. Another problem is the lack of stability in accelerator implementation; processor and compiler technology is currently changing rapidly. In this paper we describe our approach to address these two immediate problems with respect to scientific analysis and visualization algorithms. Our approach to accelerator programming forms the basis of the Dax toolkit, a framework to build data analysis and visualization algorithms applicable to exascale computing.

UR - http://www.scopus.com/inward/record.url?scp=84876549359&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876549359&partnerID=8YFLogxK

U2 - 10.1109/SC.Companion.2012.115

DO - 10.1109/SC.Companion.2012.115

M3 - Conference contribution

SN - 9780769549569

SP - 821

EP - 826

BT - Proceedings - 2012 SC Companion

ER -