Title
Adaptive decomposition and remapping algorithms for object-space-parallel direct volume rendering of unstructured grids
Abstract
Object space (OS) parallelization of an efficient direct volume rendering algorithm for unstructured grids on distributed-memory architectures is investigated. The adaptive OS decomposition problem is modeled as a graph partitioning (GP) problem using an efficient and highly accurate estimation scheme for view-dependent node and edge weighting. In the proposed model, minimizing the cutsize corresponds to minimizing the parallelization overhead due to the data communication and redundant computation/storage while maintaining the GP balance constraint corresponds to maintaining the computational load balance in parallel rendering. A GP-based, view-independent cell clustering scheme is introduced to induce more tractable view-dependent computational graphs for successive visualizations. As another contribution, a graph-theoretical remapping model is proposed as a solution to the general remapping problem and is used in minimization of the cell-data migration overhead. The remapping tool RM-MeTiS is developed by modifying the GP tool MeTiS and is used in partitioning the remapping graphs. Experiments are conducted using benchmark datasets on a 28-node PC cluster to evaluate the performance of the proposed models.
Year
DOI
Venue
2007
10.1016/j.jpdc.2006.05.005
J. Parallel Distrib. Comput.
Keywords
Field
DocType
accurate estimation scheme,gp tool,unstructured grids,graph-theoretical remapping model,adaptive decomposition,gp balance constraint corresponds,cell-data migration overhead,general remapping problem,remapping graph,unstructured grid,remapping algorithm,remapping tool,object-space-parallel direct volume rendering,object space parallelization,remapping,graph partitioning,direct volume rendering,adaptive os decomposition problem,load balance,parallel rendering,data migration
Graph theory,Parallel rendering,Parallel algorithm,Computer science,Parallel computing,Algorithm,Adaptive algorithm,Graph partition,Cluster analysis,Grid,Domain decomposition methods
Journal
Volume
Issue
ISSN
67
1
Journal of Parallel and Distributed Computing
Citations 
PageRank 
References 
13
0.82
33
Authors
4
Name
Order
Citations
PageRank
Cevdet Aykanat199684.08
B. Barla Cambazoglu273538.87
Ferit Findik3130.82
Tahsin M. Kurç41423149.77