MR-Search - Massively Parallel Heuristic Search with MapReduce

Heuristic search can be applied to a wide range of optimization problems, e.g. to multiple sequence alignment or shortest path problems. In the MR-Search project, we are developing scalable search algorithms for massively parallel supercomputers.

MR-Search is a framework for massively parallel breadth-first and heuristic search based on the MapReduce paradigm. It can run on shared-memory machines using OpenMP and on distributed memory machines using MPI.

Publikationen

2013 2012 2011 2010 2009

2013
Alexander Reinefeld, Thorsten Schütt, Robert Döbbelin	Analyzing the performance of SMP memory allocators with iterative MapReduce applications	Parallel Computing, 39(12), pp. 879-889, 2013	BibTeX DOI
Robert Döbbelin, Thorsten Schütt, Alexander Reinefeld	Building Large Compressed PDBs for the Sliding Tile Puzzle	Workshop on Computer Games, 2013 (preprint available as ZIB-Report 13-21)	PDF (ZIB-Report) BibTeX
Thorsten Schütt, Robert Döbbelin, Alexander Reinefeld	Forward Perimeter Search with Controlled Use of Memory	International Joint Conference on Artificial Intelligence, IJCAI-13, Beijing, 2013	PDF BibTeX
2012
Robert Döbbelin, Thorsten Schütt, Alexander Reinefeld	An Analysis of SMP Memory Allocators	Proceedings of the 41st International Conference on Parallel Processing Workshops (Fifth International Workshop on Parallel Programming Models and Systems Software for High-End Computing (P2S2)), pp. 48-54, 2012	BibTeX DOI
2011
Bert Münnich	Kürzeste-Wege-Suche mit Grafikkarten	Master's thesis, Humboldt-Universität zu Berlin, 2011	BibTeX
Thorsten Schütt, Alexander Reinefeld, Robert Döbbelin	MR-search: massively parallel heuristic search	Concurrency and Computation: Practice and Experience, 25(1), pp. 40-54, 2011	BibTeX DOI
Robert Maier	Massiv-parallele Suche und effiziente Heuristiken	Master's thesis, Humboldt-Universität zu Berlin, Alexander Reinefeld (Advisor), 2011	PDF BibTeX URN
2010
Joos-Hendrik Böse, Artur Andrzejak, Mikael Högqvist	Beyond online aggregation: Parallel and incremental data mining with online Map-Reduce	Proceedings of the 2010 Workshop on Massive Data Analytics on the Cloud, pp. 3:1-3:6, MDAC ’10, 2010	BibTeX DOI
Alexander Reinefeld, Thorsten Schütt, Robert Döbbelin	Very large pattern databases for heuristic search	HPDC, Salim Hariri, Kate Keahey (Eds.), pp. 803-809, 2010	BibTeX DOI
2009
Alexander Reinefeld	Heuristic Search	Encyclopedia of Optimization, pp. 1506-1508, Christodoulos Floudas, Panos Pardalos (Eds.), Springer, 2009	BibTeX DOI
Alexander Reinefeld, Thorsten Schütt	Out-of-Core Parallel Frontier Search with MapReduce	HPCS, pp. 323-336, Vol.5976, Lecture Notes in Computer Science, 2009	BibTeX DOI
Alexander Reinefeld	Parallel Heuristic Search	Encyclopedia of Optimization, Christodoulos Floudas, Panos Pardalos (Eds.), Springer, pp. 2908-2912, 2009	BibTeX DOI