A Parallel Solver for Graph Laplacians

被引:2
作者
Konolige, Tristan [1 ]
Brown, Jed [1 ]
机构
[1] Univ Colorado, Boulder, CO 80309 USA
来源
PROCEEDINGS OF THE PLATFORM FOR ADVANCED SCIENTIFIC COMPUTING CONFERENCE (PASC '18) | 2017年
关键词
Graph Laplacian; Unsmoothed Aggregation multigrid; Distributed Memory; Iterative Solver;
D O I
10.1145/3218176.3218227
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Problems from graph drawing, spectral clustering, network flow and graph partitioning can all be expressed in terms of graph Laplacian matrices. There are a variety of practical approaches to solving these problems in serial. However, as problem sizes increase and single core speeds stagnate, parallelism is essential to solve such problems quickly. We present an unsmoothed aggregation multigrid method for solving graph Laplacians in a distributed memory setting. We introduce new parallel aggregation and low degree elimination algorithms targeted specifically at irregular degree graphs. These algorithms are expressed in terms of sparse matrix-vector products using generalized sum and product operations. This formulation is amenable to linear algebra using arbitrary distributions and allows us to operate on a 2D sparse matrix distribution, which is necessary for parallel scalability. Our solver outperforms the natural parallel extension of the current state of the art in an algorithmic comparison. We demonstrate scalability to 576 processes and graphs with up to 1.7 billion edges.
引用
收藏
页数:11
相关论文
共 32 条
[1]   Parallel multigrid smoothing: polynomial versus Gauss-Seidel [J].
Adams, M ;
Brezina, M ;
Hu, J ;
Tuminaro, R .
JOURNAL OF COMPUTATIONAL PHYSICS, 2003, 188 (02) :593-610
[2]   A fully asynchronous multifrontal solver using distributed dynamic scheduling [J].
Amestoy, PR ;
Duff, IS ;
L'Excellent, JY ;
Koster, J .
SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2001, 23 (01) :15-41
[3]  
[Anonymous], 2004, P 36 ANN ACM S THEOR, DOI [DOI 10.1145/1007352, DOI 10.1145/1007352.1007372]
[4]  
Backstrom L, 2012, PROCEEDINGS OF THE 3RD ANNUAL ACM WEB SCIENCE CONFERENCE, 2012, P33
[5]  
Balay S, 1997, MODERN SOFTWARE TOOLS FOR SCIENTIFIC COMPUTING, P163
[6]  
Balay S., 2019, PETSc Users Manual
[7]   EXPOSING FINE-GRAINED PARALLELISM IN ALGEBRAIC MULTIGRID METHODS [J].
Bell, Nathan ;
Dalton, Steven ;
Olson, Luke N. .
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2012, 34 (04) :C123-C152
[8]   Four Degrees of Separation, Really [J].
Boldi, Paolo ;
Vigna, Sebastiano .
2012 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM), 2012, :1222-1227
[9]  
Boman EG, 2016, INFORM-J COMPUT INFO, V40, P95
[10]   Scalable Matrix Computations on Large Scale-Free Graphs Using 2D Graph Partitioning [J].
Boman, Erik G. ;
Devine, Karen D. ;
Rajamanickam, Sivasankaran .
2013 INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS (SC), 2013,