XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms

Galen Arnold, Manisha Gajbe, Seid Koric, John Urbanic

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

Abstract

The Blue Waters system at the National Center for Supercomputing Applications (NCSA) is the largest GPU accelerated system in the NSF's portfolio with greater than (>) 4200 Nvidia K20x accelerators and greater than (>) 22500 compute nodes overall. Using the accelerator nodes e?ectively is paramount to the system's success as they represent approximately 1/7 of system peak performance. As an XSEDE level 2 service provider, the system is also available to education allocations proposed by XSEDE educators and trainers. The training sta? working at Pittsburgh Supercomputing Center (PSC) along with their XSEDE and Nvidia partners have o?ered multiple OpenACC workshops since 2012. The most recent workshop was conducted on Blue Waters hosting the hands-on sessions and it was very successful. As a direct result of working with PSC on these workshop, NCSA researchers have been able to obtain significant speedups on real-world algorithms using OpenACC in the Cray environment. In this work we will look at two key kernel codes ( 3D FFT kernel, Laplace 2D MPI benchmark) and the path to obtaining the observed performance gains.

Original languageEnglish (US)
Title of host publicationProceedings of the XSEDE 2014 Conference
Subtitle of host publicationEngaging Communities
PublisherAssociation for Computing Machinery
ISBN (Print)9781450328937
DOIs
StatePublished - Jan 1 2014
Event2014 Annual Conference on Extreme Science and Engineering Discovery Environment, XSEDE 2014 - Atlanta, GA, United States
Duration: Jul 13 2014Jul 18 2014

Publication series

NameACM International Conference Proceeding Series

Other

Other2014 Annual Conference on Extreme Science and Engineering Discovery Environment, XSEDE 2014
CountryUnited States
CityAtlanta, GA
Period7/13/147/18/14

Fingerprint

Particle accelerators
Fast Fourier transforms
Water
Education
Graphics processing unit

Keywords

  • Accelerators
  • GPU
  • GPU aware MPI
  • OpenACC
  • OpenMP

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Arnold, G., Gajbe, M., Koric, S., & Urbanic, J. (2014). XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms. In Proceedings of the XSEDE 2014 Conference: Engaging Communities [28] (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/2616498.2616530

XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms. / Arnold, Galen; Gajbe, Manisha; Koric, Seid; Urbanic, John.

Proceedings of the XSEDE 2014 Conference: Engaging Communities. Association for Computing Machinery, 2014. 28 (ACM International Conference Proceeding Series).

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

Arnold, G, Gajbe, M, Koric, S & Urbanic, J 2014, XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms. in Proceedings of the XSEDE 2014 Conference: Engaging Communities., 28, ACM International Conference Proceeding Series, Association for Computing Machinery, 2014 Annual Conference on Extreme Science and Engineering Discovery Environment, XSEDE 2014, Atlanta, GA, United States, 7/13/14. https://doi.org/10.1145/2616498.2616530
Arnold G, Gajbe M, Koric S, Urbanic J. XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms. In Proceedings of the XSEDE 2014 Conference: Engaging Communities. Association for Computing Machinery. 2014. 28. (ACM International Conference Proceeding Series). https://doi.org/10.1145/2616498.2616530
Arnold, Galen ; Gajbe, Manisha ; Koric, Seid ; Urbanic, John. / XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms. Proceedings of the XSEDE 2014 Conference: Engaging Communities. Association for Computing Machinery, 2014. (ACM International Conference Proceeding Series).
@inproceedings{f324a9bce94346ed8ca7c16c3823deda,
title = "XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms",
abstract = "The Blue Waters system at the National Center for Supercomputing Applications (NCSA) is the largest GPU accelerated system in the NSF's portfolio with greater than (>) 4200 Nvidia K20x accelerators and greater than (>) 22500 compute nodes overall. Using the accelerator nodes e?ectively is paramount to the system's success as they represent approximately 1/7 of system peak performance. As an XSEDE level 2 service provider, the system is also available to education allocations proposed by XSEDE educators and trainers. The training sta? working at Pittsburgh Supercomputing Center (PSC) along with their XSEDE and Nvidia partners have o?ered multiple OpenACC workshops since 2012. The most recent workshop was conducted on Blue Waters hosting the hands-on sessions and it was very successful. As a direct result of working with PSC on these workshop, NCSA researchers have been able to obtain significant speedups on real-world algorithms using OpenACC in the Cray environment. In this work we will look at two key kernel codes ( 3D FFT kernel, Laplace 2D MPI benchmark) and the path to obtaining the observed performance gains.",
keywords = "Accelerators, GPU, GPU aware MPI, OpenACC, OpenMP",
author = "Galen Arnold and Manisha Gajbe and Seid Koric and John Urbanic",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2616498.2616530",
language = "English (US)",
isbn = "9781450328937",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
booktitle = "Proceedings of the XSEDE 2014 Conference",

}

TY - GEN

T1 - XSEDE OpenACC workshop enables blue waters researchers to accelerate key algorithms

AU - Arnold, Galen

AU - Gajbe, Manisha

AU - Koric, Seid

AU - Urbanic, John

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The Blue Waters system at the National Center for Supercomputing Applications (NCSA) is the largest GPU accelerated system in the NSF's portfolio with greater than (>) 4200 Nvidia K20x accelerators and greater than (>) 22500 compute nodes overall. Using the accelerator nodes e?ectively is paramount to the system's success as they represent approximately 1/7 of system peak performance. As an XSEDE level 2 service provider, the system is also available to education allocations proposed by XSEDE educators and trainers. The training sta? working at Pittsburgh Supercomputing Center (PSC) along with their XSEDE and Nvidia partners have o?ered multiple OpenACC workshops since 2012. The most recent workshop was conducted on Blue Waters hosting the hands-on sessions and it was very successful. As a direct result of working with PSC on these workshop, NCSA researchers have been able to obtain significant speedups on real-world algorithms using OpenACC in the Cray environment. In this work we will look at two key kernel codes ( 3D FFT kernel, Laplace 2D MPI benchmark) and the path to obtaining the observed performance gains.

AB - The Blue Waters system at the National Center for Supercomputing Applications (NCSA) is the largest GPU accelerated system in the NSF's portfolio with greater than (>) 4200 Nvidia K20x accelerators and greater than (>) 22500 compute nodes overall. Using the accelerator nodes e?ectively is paramount to the system's success as they represent approximately 1/7 of system peak performance. As an XSEDE level 2 service provider, the system is also available to education allocations proposed by XSEDE educators and trainers. The training sta? working at Pittsburgh Supercomputing Center (PSC) along with their XSEDE and Nvidia partners have o?ered multiple OpenACC workshops since 2012. The most recent workshop was conducted on Blue Waters hosting the hands-on sessions and it was very successful. As a direct result of working with PSC on these workshop, NCSA researchers have been able to obtain significant speedups on real-world algorithms using OpenACC in the Cray environment. In this work we will look at two key kernel codes ( 3D FFT kernel, Laplace 2D MPI benchmark) and the path to obtaining the observed performance gains.

KW - Accelerators

KW - GPU

KW - GPU aware MPI

KW - OpenACC

KW - OpenMP

UR - http://www.scopus.com/inward/record.url?scp=84905445203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905445203&partnerID=8YFLogxK

U2 - 10.1145/2616498.2616530

DO - 10.1145/2616498.2616530

M3 - Conference contribution

AN - SCOPUS:84905445203

SN - 9781450328937

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the XSEDE 2014 Conference

PB - Association for Computing Machinery

ER -