Unordered Task-Parallel Augmented Merge Tree Construction
Pages 3585 - 3596
Abstract
Contemporary scientific data sets require fast and scalable topological analysis to enable visualization, simplification and interaction. Within this field, parallel merge tree construction has seen abundant recent contributions, with a trend of decentralized, task-parallel or SMP-oriented algorithms dominating in terms of total runtime. However, none of these recent approaches computed complete merge trees on distributed systems, leaving this field to traditional divide & conquer approaches. This article introduces a scalable, parallel and distributed algorithm for merge tree construction outperforming the previously fastest distributed solution by a factor of around three. This is achieved by a task-parallel identification of individual merge tree arcs by growing regions around critical points in the data, without any need for ordered progression or global data structures, based on a novel insight introducing a sufficient local boundary for region growth.
References
[1]
H. Edelsbrunner and J. Harer, Computational Topology: An Introduction.Providence, RI, USA: Amer. Math. Soc., 2009.
[2]
V. Pascucci, X. Tricoche, H. Hagen, and J. Tierny, Topological Methods in Data Analysis and Visualization: Theory, Algorithms, and Applications, 1st ed. Berlin, Germany: Springer, 2011.
[3]
C. Heine, et al., “A survey of topology-based methods in visualization,” Comput. Graph. Forum, vol. 35, no. 3, pp. 643–667, Jun. 2016.
[4]
P. Rosen, et al., “Using contour trees in the analysis and visualization of radio astronomy data cubes,” 2017,.
[5]
W. Widanagamaachchi, C. Christensen, V. Pascucci, and P.-T. Bremer, “Interactive exploration of large-scale time-varying data using dynamic tracking graphs,” in Proc. IEEE Symp. Large Data Anal. Visual., 2012, pp. 9–17.
[6]
H. Saikia, H.-P. Seidel, and T. Weinkauf, “Extended branch decomposition graphs: Structural comparison of scalar data,” Comput. Graph. Forum, vol. 33, no. 3, pp. 41–50, 2014.
[7]
E. Zhang, K. Mischaikow, and G. Turk, “Feature-based surface parameterization and texture mapping,” ACM Trans. Graph., vol. 24, no. 1, pp. 1–27, Jan. 2005.
[8]
Z. Wood, H. Hoppe, M. Desbrun, and P. Schröder, “Removing excess topology from isosurfaces,” ACM Trans. Graph., vol. 23, no. 2, pp. 190–208, Apr. 2004.
[9]
J. Tierny, J.-P. Vandeborre, and M. Daoudi, “3D mesh skeleton extraction using topological and geometrical analyses,” in Proc. 14th Pacific Conf. Comput. Graph. Appl., 2006, pp. 85–94.
[10]
G. Weber, P.-T. Bremer, and V. Pascucci, “Topological landscapes: A terrain metaphor for scientific data,” IEEE Trans. Visual. Comput. Graph., vol. 13, no. 6, pp. 1416–1423, Nov. 2007.
[11]
G. H. Weber, S. E. Dillard, H. A. Carr, V. Pascucci, and B. Hamann, “Topology-controlled volume rendering,” IEEE Trans. Visual. Comput. Graph., vol. 13, no. 2, pp. 330–341, Mar./Apr. 2007.
[12]
H. Carr, J. Snoeyink, and M. van de Panne, “Simplifying flexible isosurfaces using local geometric measures,” in Proc. Visual., 2004, pp. 497–504.
[13]
H. Carr, J. Snoeyink, and U. Axen, “Computing contour trees in all dimensions,” Comput. Geometry, vol. 24, no. 2, pp. 75–94, 2003.
[14]
C. Gueunet, P. Fortin, J. Jomier, and J. Tierny, “Task-based augmented merge trees with Fibonacci heaps,” IEEE Trans. Parallel Distrib. Syst., vol. 30, no. 8, pp. 1889–1905, Aug. 2019.
[15]
H. Carr, G. H. Weber, C. Sewell, O. Rubel, P. Fasel, and J. Ahrens, “Scalable contour tree computation by data parallel peak pruning,” IEEE Trans. Visual. Comput. Graph., vol. 27, no. 4, pp. 2437–2454, Apr. 2021.
[16]
K. C.-M. V. Pascucci, “Parallel computation of the topology of level sets,” Algorithmica, vol. 38, no. 1, pp. 249–268, 2003.
[17]
B. Raichel and C. Seshadhri, “A mountaintop view requires minimal sorting: A faster contour tree algorithm,” 2014,.
[18]
S. Maadasamy, H. Doraiswamy, and V. Natarajan, “A hybrid parallel algorithm for computing and tracking level set topology,” in Proc. 19th Int. Conf. High Perform. Comput., 2012, pp. 1–10.
[19]
Y.-J. Chiang, T. Lenz, X. Lu, and G. Rote, “Simple and optimal output-sensitive construction of contour trees using monotone paths,” Comput. Geometry, vol. 30, pp. 165–195, 2005.
[20]
A. G. Landge, et al., “In-situ feature extraction of large scale combustion simulations using segmented merge trees,” in Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal., 2014, pp. 1020–1031.
[21]
H. Carr, C. Sewell, L.-T. Lo, and J. Ahrens, “Hybrid data-parallel contour tree computation,” in Proc. Conf. Comput. Graph. Vis. Comput., 2016, pp. 73–80.
[22]
D. Morozov and G. Weber, “Distributed contour trees,” in Topological Methods in Data Analysis and Visualization III. Berlin, Germany: Springer, 2014, pp. 89–102.
[23]
D. Morozov and G. Weber, “Distributed merge trees,” SIGPLAN Notices, vol. 48, no. 8, pp. 93–102, Feb. 2013.
[24]
H. Edelsbrunner and E. P. Mücke, “Simulation of simplicity: A technique to cope with degenerate cases in geometric algorithms,” ACM Trans. Graph., vol. 9, no. 1, pp. 66–104, Jan. 1990.
[25]
T. Banchoff, “Critical points and curvature for embedded polyhedra,” J. Differ. Geometry, vol. 1, no. 3–4, pp. 245–256, 1967.
[26]
C. Gueunet, P. Fortin, J. Jomier, and J. Tierny, “Task-based Augmented Reeb Graphs with Dynamic ST-Trees,” in Proc. Eurograph. Symp. Parallel Graph. Visual., Porto, Portugal, Jun. 2019, pp. 27–37.
[27]
C. Gueunet, P. Fortin, J. Jomier, and J. Tierny, “Task-based augmented merge trees with fibonacci heaps,” in Proc. IEEE 7th Symp. Large Data Anal. Visual., 2017, pp. 6–15.
[28]
C. Gueunet, P. Fortin, J. Jomier, and Vijay, “Contour forests: Fast multi-threaded augmented contour trees,” in Proc. IEEE Symp. Large Data Anal. Visualization, 2016, pp. 85–92.
[29]
A. Acharya and V. Natarajan, “A parallel and memory efficient algorithm for constructing the contour tree,” in Proc. IEEE Pacific Visual. Symp., 2015, pp. 271–278.
[30]
A. Nath, K. Fox, P. K. Agarwal, and K. Munagala, “Massively parallel algorithms for computing tin dems and contour trees for large terrains,” in Proc. 24th ACM SIGSPATIAL Int. Conf. Adv. Geogr. Inf. Syst., 2016, pp. 1–10.
[31]
M. Hajij and P. Rosen, “An efficient data retrieval parallel reeb graph algorithm,” Alogrithms, vol. 13, 2020, Art. no.
[32]
H. A. Carr, G. H. Weber, C. M. Sewell, and J. P. Ahrens, “Parallel peak pruning for scalable SMP contour tree computation,” in Proc. IEEE Symp. Large Data Anal. Visual., 2016, pp. 75–84.
[33]
P. Rosen, J. Tu, and L. Piegl, “A hybrid solution to parallel calculation of augmented join trees of scalar fields in any dimension,” Comput.-Aided Des. Appl., vol. 15, no. 1, pp. 610–618, 2018.
[34]
R. Sarkar, X. Zhu, J. Gao, L. J. Guibas, and J. Mitchell, “Iso-contour queries and gradient descent with guaranteed delivery in sensor networks,” in IEEE INFOCOM 27th Conf. Comput. Commun., 2008, pp. 960–967.
[35]
W. Pugh, “Concurrent maintenance of skip lists,” Dept. Comput. Sci., Inst. Adv. Comput. Stud., Univ. Maryland, College Park, MD, USA, Tech. Rep. CS-TR-2222.1, 1989.
[36]
H. Kaiser, M. Brodowicz, and T. Sterling, “Parallex an advanced parallel execution model for scaling-impaired applications,” in Proc. Int. Conf. Parallel Process. Workshops, 2009, pp. 394–401.
[37]
J. Patchett, B. Nouanesengesy, J. Pouderoux, J. Ahrens, and H. Hagen, “Parallel multi-level ghost cell generation for distributed unstructured grids,” in Proc. IEEE 7th Symp. Large Data Anal. Visual., 2017, pp. 84–91.
[38]
J. Patchett and G. Gisler, “Deep water impact ensemble data set,” U.S. Dept. Energy, Washington, D.C., USA, Tech. Rep.TR-LA-UR-17–21595, Apr. 27, 2017. [Online]. Available: https://datascience.dsscale.org/wp-content/uploads/2017/03/DeepWaterImpactEnsembleDataSet.pdf
[39]
C. Garth, “Simulation of a jet flow,” 2020. [Online]. Available: https://doi.org/10.21227/qjxp-kc31
[40]
K. Werner, “Reproducible source code for unordered task-parallel augmented merge tree construction,” 2020. [Online]. Available: https://codeocean.com/capsule/0498480/tree/v1
[41]
K. Werner and C. Garth, “Alternative parameters for on-the-fly simplification of MergeTrees,” in Proc. Eurograph. Symp. Parallel Graph. Visual., 2020, pp. 75–79.
Index Terms
- Unordered Task-Parallel Augmented Merge Tree Construction
Index terms have been assigned to the content through auto-classification.
Recommendations
Obstacle-avoiding rectilinear Steiner tree construction
ICCAD '08: Proceedings of the 2008 IEEE/ACM International Conference on Computer-Aided DesignIn today's VLSI designs, there can be many blockages in a routing region. The obstacle-avoiding rectilinear Steiner minimum tree (OARSMT) problem has become an important problem in the physical design stage of VLSI circuits. This problem has attracted a ...
Obstacle-avoiding rectilinear Steiner tree construction in sequential and parallel approach
The Rectilinear Steiner Minimum Tree (RSMT) problem is a fundamental one in VLSI physical design. In this paper, we present a maze routing based heuristics to solve the obstacle-avoiding RSMT (OARSMT) problem. Our approach can handle multi-pin nets in ...
Efficient obstacle-avoiding rectilinear steiner tree construction
ISPD '07: Proceedings of the 2007 international symposium on Physical designGiven a set of pins and a set of obstacles on a plane, an obstacle-avoiding rectilinear Steiner minimal tree (OARSMT) connects these pins, possibly through some additional points (called Steiner points), and avoids running through any obstacle to ...
Comments
Information & Contributors
Information
Published In
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
Publisher
IEEE Educational Activities Department
United States
Publication History
Published: 01 August 2021
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 30 Aug 2024
Other Metrics
Citations
Cited By
View allView Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in