Dax toolkit

A proposed framework for data analysis and visualization at extreme scale

Kenneth Moreland, Utkarsh Ayachit, Berk Geveci, Kwan-Liu Ma

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

34 Citations (Scopus)

Abstract

Experts agree that the exascale machine will comprise processors that contain many cores, which in turn will necessitate a much higher degree of concurrency. Software will require a minimum of a 1,000 times more concurrency. Most parallel analysis and visualization algorithms today work by partitioning data and running mostly serial algorithms concurrently on each data partition. Although this approach lends itself well to the concurrency of current high-performance computing, it does not exhibit the appropriate pervasive parallelism required for exascale computing. The data partitions are too small and the overhead of the threads is too large to make effective use of all the cores in an extreme-scale machine. This paper introduces a new visualization framework designed to exhibit the pervasive parallelism necessary for extreme scale machines. We demonstrate the use of this system on a GPU processor, which we feel is the best analog to an exascale node that we have available today.

Original languageEnglish (US)
Title of host publication1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings
Pages97-104
Number of pages8
DOIs
StatePublished - Dec 26 2011
Event1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Providence, RI, United States
Duration: Oct 23 2011Oct 24 2011

Other

Other1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011
CountryUnited States
CityProvidence, RI
Period10/23/1110/24/11

Fingerprint

Data visualization
Visualization
Graphics processing unit

Keywords

  • D.1.3 [Software]: Programming Techniques - Concurrent Programming

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Moreland, K., Ayachit, U., Geveci, B., & Ma, K-L. (2011). Dax toolkit: A proposed framework for data analysis and visualization at extreme scale. In 1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings (pp. 97-104). [6092323] https://doi.org/10.1109/LDAV.2011.6092323

Dax toolkit : A proposed framework for data analysis and visualization at extreme scale. / Moreland, Kenneth; Ayachit, Utkarsh; Geveci, Berk; Ma, Kwan-Liu.

1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings. 2011. p. 97-104 6092323.

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

Moreland, K, Ayachit, U, Geveci, B & Ma, K-L 2011, Dax toolkit: A proposed framework for data analysis and visualization at extreme scale. in 1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings., 6092323, pp. 97-104, 1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011, Providence, RI, United States, 10/23/11. https://doi.org/10.1109/LDAV.2011.6092323
Moreland K, Ayachit U, Geveci B, Ma K-L. Dax toolkit: A proposed framework for data analysis and visualization at extreme scale. In 1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings. 2011. p. 97-104. 6092323 https://doi.org/10.1109/LDAV.2011.6092323
Moreland, Kenneth ; Ayachit, Utkarsh ; Geveci, Berk ; Ma, Kwan-Liu. / Dax toolkit : A proposed framework for data analysis and visualization at extreme scale. 1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings. 2011. pp. 97-104
@inproceedings{d5c6a075864c407283dafec8bca89d61,
title = "Dax toolkit: A proposed framework for data analysis and visualization at extreme scale",
abstract = "Experts agree that the exascale machine will comprise processors that contain many cores, which in turn will necessitate a much higher degree of concurrency. Software will require a minimum of a 1,000 times more concurrency. Most parallel analysis and visualization algorithms today work by partitioning data and running mostly serial algorithms concurrently on each data partition. Although this approach lends itself well to the concurrency of current high-performance computing, it does not exhibit the appropriate pervasive parallelism required for exascale computing. The data partitions are too small and the overhead of the threads is too large to make effective use of all the cores in an extreme-scale machine. This paper introduces a new visualization framework designed to exhibit the pervasive parallelism necessary for extreme scale machines. We demonstrate the use of this system on a GPU processor, which we feel is the best analog to an exascale node that we have available today.",
keywords = "D.1.3 [Software]: Programming Techniques - Concurrent Programming",
author = "Kenneth Moreland and Utkarsh Ayachit and Berk Geveci and Kwan-Liu Ma",
year = "2011",
month = "12",
day = "26",
doi = "10.1109/LDAV.2011.6092323",
language = "English (US)",
isbn = "9781467301541",
pages = "97--104",
booktitle = "1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings",

}

TY - GEN

T1 - Dax toolkit

T2 - A proposed framework for data analysis and visualization at extreme scale

AU - Moreland, Kenneth

AU - Ayachit, Utkarsh

AU - Geveci, Berk

AU - Ma, Kwan-Liu

PY - 2011/12/26

Y1 - 2011/12/26

N2 - Experts agree that the exascale machine will comprise processors that contain many cores, which in turn will necessitate a much higher degree of concurrency. Software will require a minimum of a 1,000 times more concurrency. Most parallel analysis and visualization algorithms today work by partitioning data and running mostly serial algorithms concurrently on each data partition. Although this approach lends itself well to the concurrency of current high-performance computing, it does not exhibit the appropriate pervasive parallelism required for exascale computing. The data partitions are too small and the overhead of the threads is too large to make effective use of all the cores in an extreme-scale machine. This paper introduces a new visualization framework designed to exhibit the pervasive parallelism necessary for extreme scale machines. We demonstrate the use of this system on a GPU processor, which we feel is the best analog to an exascale node that we have available today.

AB - Experts agree that the exascale machine will comprise processors that contain many cores, which in turn will necessitate a much higher degree of concurrency. Software will require a minimum of a 1,000 times more concurrency. Most parallel analysis and visualization algorithms today work by partitioning data and running mostly serial algorithms concurrently on each data partition. Although this approach lends itself well to the concurrency of current high-performance computing, it does not exhibit the appropriate pervasive parallelism required for exascale computing. The data partitions are too small and the overhead of the threads is too large to make effective use of all the cores in an extreme-scale machine. This paper introduces a new visualization framework designed to exhibit the pervasive parallelism necessary for extreme scale machines. We demonstrate the use of this system on a GPU processor, which we feel is the best analog to an exascale node that we have available today.

KW - D.1.3 [Software]: Programming Techniques - Concurrent Programming

UR - http://www.scopus.com/inward/record.url?scp=84055189992&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84055189992&partnerID=8YFLogxK

U2 - 10.1109/LDAV.2011.6092323

DO - 10.1109/LDAV.2011.6092323

M3 - Conference contribution

SN - 9781467301541

SP - 97

EP - 104

BT - 1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings

ER -