MPPM, Viewed as a co-design effort

Paul R. Woodward; Jagan Jayaraj; Richard Barrett

doi:10.1109/Co-HPC.2014.13

MPPM, Viewed as a co-design effort

Paul R. Woodward, Jagan Jayaraj, Richard Barrett

Physics and Astronomy (Twin Cities)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

The Piecewise Parabolic Method (PPM) was designed as a means of exploring compressible gas dynam-ics problems of interest in astrophysics, including super-sonic jets, compressible turbulence, stellar convection, and turbulent mixing and burning of gases in stellar interiors. Over time, the capabilities encapsulated in PPM have co-evolved with the availability of a series of high performance computing platforms. Implementation of the algorithm has adapted to and advanced with the architectural capabilities and characteristics of these machines. This adaptability of our PPM codes has enabled targeted astrophysical applica-tions of PPM to exploit these scarce resources to explore complex physical phenomena. Here we describe the means by which this was accomplished, and set a path forward, with a new miniapp, mPPM, for continuing this process in a diverse and dynamic architecture design environment. Adaptations in mPPM for the latest high performance machines are discussed that address the important issue of limited bandwidth from locally attached main memory to the microprocessor chip.

Original language	English (US)
Title of host publication	Proceedings of Co-HPC 2014
Subtitle of host publication	1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	33-40
Number of pages	8
ISBN (Electronic)	9781479975648
DOIs	https://doi.org/10.1109/Co-HPC.2014.13
State	Published - Jan 21 2014
Event	1st International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2014 - Held in Conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014 - New Orleans, United States Duration: Nov 17 2014 → …

Publication series

Name	Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis

Other

Other	1st International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2014 - Held in Conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014
Country/Territory	United States
City	New Orleans
Period	11/17/14 → …

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

Co-design
memory bandwidth
miniapp

Access

10.1109/Co-HPC.2014.13

OpenUrl availability

Full text

Cite this

Woodward, P. R., Jayaraj, J., & Barrett, R. (2014). MPPM, Viewed as a co-design effort. In Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 33-40). Article 7017961 (Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/Co-HPC.2014.13

MPPM, Viewed as a co-design effort. / Woodward, Paul R.; Jayaraj, Jagan; Barrett, Richard.
Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2014. p. 33-40 7017961 (Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Woodward, PR, Jayaraj, J & Barrett, R 2014, MPPM, Viewed as a co-design effort. in Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis., 7017961, Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 33-40, 1st International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2014 - Held in Conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, New Orleans, United States, 11/17/14. https://doi.org/10.1109/Co-HPC.2014.13

Woodward PR, Jayaraj J, Barrett R. MPPM, Viewed as a co-design effort. In Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2014. p. 33-40. 7017961. (Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/Co-HPC.2014.13

Woodward, Paul R. ; Jayaraj, Jagan ; Barrett, Richard. / MPPM, Viewed as a co-design effort. Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 33-40 (Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{e4d7cc24a64a49bdb62d6879cc99758c,

title = "MPPM, Viewed as a co-design effort",

abstract = "The Piecewise Parabolic Method (PPM) was designed as a means of exploring compressible gas dynam-ics problems of interest in astrophysics, including super-sonic jets, compressible turbulence, stellar convection, and turbulent mixing and burning of gases in stellar interiors. Over time, the capabilities encapsulated in PPM have co-evolved with the availability of a series of high performance computing platforms. Implementation of the algorithm has adapted to and advanced with the architectural capabilities and characteristics of these machines. This adaptability of our PPM codes has enabled targeted astrophysical applica-tions of PPM to exploit these scarce resources to explore complex physical phenomena. Here we describe the means by which this was accomplished, and set a path forward, with a new miniapp, mPPM, for continuing this process in a diverse and dynamic architecture design environment. Adaptations in mPPM for the latest high performance machines are discussed that address the important issue of limited bandwidth from locally attached main memory to the microprocessor chip.",

keywords = "Co-design, memory bandwidth, miniapp",

author = "Woodward, {Paul R.} and Jagan Jayaraj and Richard Barrett",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 1st International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2014 - Held in Conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014 ; Conference date: 17-11-2014",

year = "2014",

month = jan,

day = "21",

doi = "10.1109/Co-HPC.2014.13",

language = "English (US)",

series = "Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "33--40",

booktitle = "Proceedings of Co-HPC 2014",

}

TY - GEN

T1 - MPPM, Viewed as a co-design effort

AU - Woodward, Paul R.

AU - Jayaraj, Jagan

AU - Barrett, Richard

PY - 2014/1/21

Y1 - 2014/1/21

N2 - The Piecewise Parabolic Method (PPM) was designed as a means of exploring compressible gas dynam-ics problems of interest in astrophysics, including super-sonic jets, compressible turbulence, stellar convection, and turbulent mixing and burning of gases in stellar interiors. Over time, the capabilities encapsulated in PPM have co-evolved with the availability of a series of high performance computing platforms. Implementation of the algorithm has adapted to and advanced with the architectural capabilities and characteristics of these machines. This adaptability of our PPM codes has enabled targeted astrophysical applica-tions of PPM to exploit these scarce resources to explore complex physical phenomena. Here we describe the means by which this was accomplished, and set a path forward, with a new miniapp, mPPM, for continuing this process in a diverse and dynamic architecture design environment. Adaptations in mPPM for the latest high performance machines are discussed that address the important issue of limited bandwidth from locally attached main memory to the microprocessor chip.

AB - The Piecewise Parabolic Method (PPM) was designed as a means of exploring compressible gas dynam-ics problems of interest in astrophysics, including super-sonic jets, compressible turbulence, stellar convection, and turbulent mixing and burning of gases in stellar interiors. Over time, the capabilities encapsulated in PPM have co-evolved with the availability of a series of high performance computing platforms. Implementation of the algorithm has adapted to and advanced with the architectural capabilities and characteristics of these machines. This adaptability of our PPM codes has enabled targeted astrophysical applica-tions of PPM to exploit these scarce resources to explore complex physical phenomena. Here we describe the means by which this was accomplished, and set a path forward, with a new miniapp, mPPM, for continuing this process in a diverse and dynamic architecture design environment. Adaptations in mPPM for the latest high performance machines are discussed that address the important issue of limited bandwidth from locally attached main memory to the microprocessor chip.

KW - Co-design

KW - memory bandwidth

KW - miniapp

UR - http://www.scopus.com/inward/record.url?scp=84946687237&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946687237&partnerID=8YFLogxK

U2 - 10.1109/Co-HPC.2014.13

DO - 10.1109/Co-HPC.2014.13

M3 - Conference contribution

AN - SCOPUS:84946687237

T3 - Proceedings of Co-HPC 2014: 1st International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 33

EP - 40

BT - Proceedings of Co-HPC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2014 - Held in Conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014

Y2 - 17 November 2014

ER -

MPPM, Viewed as a co-design effort

Abstract

Publication series

Other

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this