Visualizing large 3D geodesic grid data with massively distributed GPUs

Jinrong Xie; Hongfeng Yu; Kwan Liu Maz

doi:10.1109/LDAV.2014.7013198

Visualizing large 3D geodesic grid data with massively distributed GPUs

Jinrong Xie, Hongfeng Yu, Kwan Liu Maz

Computer Science and Engineering

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

5 Scopus citations

Abstract

Geodesic grids become increasingly prevalent in large weather and climate applications. The deluge amount of simulation data demands efficient and scalable visualization capabilities for scientific exploration and understanding. Given the unique characteristics of geodesic grids, no current techniques can scalably visualize scalar fields defined on a geodesic grid. In this paper, we present a new parallel ray-casting algorithm for large geodesic grids using massively distributed GPUs. We construct a spherical quadtree to adaptively partition and distribute the data according to the grid resolution of simulation, and ensure a balanced workload assignment over a large number of processors from different view angles. We have designed and implemented the entire rendering pipeline based on the MPI and CUDA architecture, and demonstrated the effectiveness and scalability of our approach using an example of large application on a supercomputer with thousands of GPUs.

Original language	English (US)
Title of host publication	IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings
Editors	Hank Childs, Hank Childs, Renato Pajarola, Venkatram Vishwanath
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3-10
Number of pages	8
ISBN (Electronic)	9781479952151
DOIs	https://doi.org/10.1109/LDAV.2014.7013198
State	Published - Jan 16 2014
Event	4th IEEE Symposium on Large Data Analysis and Visualization, LDAV 2014 - Paris, France Duration: Oct 9 2014 → Oct 10 2014

Publication series

Name	IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings

Other

Other	4th IEEE Symposium on Large Data Analysis and Visualization, LDAV 2014
Country	France
City	Paris
Period	10/9/14 → 10/10/14

ASJC Scopus subject areas

Information Systems
Computer Vision and Pattern Recognition

Access to Document

10.1109/LDAV.2014.7013198

Fingerprint Dive into the research topics of 'Visualizing large 3D geodesic grid data with massively distributed GPUs'. Together they form a unique fingerprint.

Cite this

Xie, J., Yu, H., & Maz, K. L. (2014). Visualizing large 3D geodesic grid data with massively distributed GPUs. In H. Childs, H. Childs, R. Pajarola, & V. Vishwanath (Eds.), IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings (pp. 3-10). [7013198] (IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/LDAV.2014.7013198

Visualizing large 3D geodesic grid data with massively distributed GPUs. / Xie, Jinrong; Yu, Hongfeng; Maz, Kwan Liu.

IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings. ed. / Hank Childs; Hank Childs; Renato Pajarola; Venkatram Vishwanath. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3-10 7013198 (IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings).

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

Xie, J, Yu, H & Maz, KL 2014, Visualizing large 3D geodesic grid data with massively distributed GPUs. in H Childs, H Childs, R Pajarola & V Vishwanath (eds), IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings., 7013198, IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 3-10, 4th IEEE Symposium on Large Data Analysis and Visualization, LDAV 2014, Paris, France, 10/9/14. https://doi.org/10.1109/LDAV.2014.7013198

Xie J, Yu H, Maz KL. Visualizing large 3D geodesic grid data with massively distributed GPUs. In Childs H, Childs H, Pajarola R, Vishwanath V, editors, IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3-10. 7013198. (IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings). https://doi.org/10.1109/LDAV.2014.7013198

Xie, Jinrong ; Yu, Hongfeng ; Maz, Kwan Liu. / Visualizing large 3D geodesic grid data with massively distributed GPUs. IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings. editor / Hank Childs ; Hank Childs ; Renato Pajarola ; Venkatram Vishwanath. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3-10 (IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings).

@inproceedings{0f80ceadff89493ba5fb3fe240ef124d,

title = "Visualizing large 3D geodesic grid data with massively distributed GPUs",

abstract = "Geodesic grids become increasingly prevalent in large weather and climate applications. The deluge amount of simulation data demands efficient and scalable visualization capabilities for scientific exploration and understanding. Given the unique characteristics of geodesic grids, no current techniques can scalably visualize scalar fields defined on a geodesic grid. In this paper, we present a new parallel ray-casting algorithm for large geodesic grids using massively distributed GPUs. We construct a spherical quadtree to adaptively partition and distribute the data according to the grid resolution of simulation, and ensure a balanced workload assignment over a large number of processors from different view angles. We have designed and implemented the entire rendering pipeline based on the MPI and CUDA architecture, and demonstrated the effectiveness and scalability of our approach using an example of large application on a supercomputer with thousands of GPUs.",

author = "Jinrong Xie and Hongfeng Yu and Maz, {Kwan Liu}",

year = "2014",

month = jan,

day = "16",

doi = "10.1109/LDAV.2014.7013198",

language = "English (US)",

series = "IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings",

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

pages = "3--10",

editor = "Hank Childs and Hank Childs and Renato Pajarola and Venkatram Vishwanath",

booktitle = "IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings",

note = "4th IEEE Symposium on Large Data Analysis and Visualization, LDAV 2014 ; Conference date: 09-10-2014 Through 10-10-2014",

}

TY - GEN

T1 - Visualizing large 3D geodesic grid data with massively distributed GPUs

AU - Xie, Jinrong

AU - Yu, Hongfeng

AU - Maz, Kwan Liu

PY - 2014/1/16

Y1 - 2014/1/16

N2 - Geodesic grids become increasingly prevalent in large weather and climate applications. The deluge amount of simulation data demands efficient and scalable visualization capabilities for scientific exploration and understanding. Given the unique characteristics of geodesic grids, no current techniques can scalably visualize scalar fields defined on a geodesic grid. In this paper, we present a new parallel ray-casting algorithm for large geodesic grids using massively distributed GPUs. We construct a spherical quadtree to adaptively partition and distribute the data according to the grid resolution of simulation, and ensure a balanced workload assignment over a large number of processors from different view angles. We have designed and implemented the entire rendering pipeline based on the MPI and CUDA architecture, and demonstrated the effectiveness and scalability of our approach using an example of large application on a supercomputer with thousands of GPUs.

AB - Geodesic grids become increasingly prevalent in large weather and climate applications. The deluge amount of simulation data demands efficient and scalable visualization capabilities for scientific exploration and understanding. Given the unique characteristics of geodesic grids, no current techniques can scalably visualize scalar fields defined on a geodesic grid. In this paper, we present a new parallel ray-casting algorithm for large geodesic grids using massively distributed GPUs. We construct a spherical quadtree to adaptively partition and distribute the data according to the grid resolution of simulation, and ensure a balanced workload assignment over a large number of processors from different view angles. We have designed and implemented the entire rendering pipeline based on the MPI and CUDA architecture, and demonstrated the effectiveness and scalability of our approach using an example of large application on a supercomputer with thousands of GPUs.

UR - http://www.scopus.com/inward/record.url?scp=84946685182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946685182&partnerID=8YFLogxK

U2 - 10.1109/LDAV.2014.7013198

DO - 10.1109/LDAV.2014.7013198

M3 - Conference contribution

AN - SCOPUS:84946685182

T3 - IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings

SP - 3

EP - 10

BT - IEEE Symposium on Large Data Analysis and Visualization 2014, LDAV 2014 - Proceedings

A2 - Childs, Hank

A2 - Pajarola, Renato

A2 - Vishwanath, Venkatram

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE Symposium on Large Data Analysis and Visualization, LDAV 2014

Y2 - 9 October 2014 through 10 October 2014

ER -