2026-07-21T12:18:23Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:2081 2024-03-06T11:08:34Z ddc:004 open_access

Combinatorial Problems in High-Performance Computing: Partitioning Bisseling, Rob van Leeuwen, Tristan Catalyurek, Umit V. Partitioning sparse matrix hypergraph parallel HPC This extended abstract presents a survey of combinatorial problems encountered in scientific computations on today's high-performance architectures, with sophisticated memory hierarchies, multiple levels of cache, and multiple processors on chip as well as off-chip. For parallelism, the most important problem is to partition sparse matrices, graph, or hypergraphs into nearly equal-sized parts while trying to reduce inter-processor communication. Common approaches to such problems involve multilevel methods based on coarsening and uncoarsening (hyper)graphs, matching of similar vertices, searching for good separator sets and good splittings, dynamical adjustment of load imbalance, and two-dimensional matrix splitting methods. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Rob Bisseling and Tristan van Leeuwen and Umit V. Catalyurek 2009 Is Part Of Dagstuhl Seminar Proceedings, Volume 9061, Combinatorial Scientific Computing (2009) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagSemProc.09061.6 urn:nbn:de:0030-drops-20818 https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.09061.6 eng https://creativecommons.org/licenses/by/4.0/legalcode