A direct parallel implementation of the Hoshen–Kopelman algorithm for distributed memory architectures

We present a direct (i.e. non iterative) method for identifying the clusters of a cubic lattice on a distributed memory parallel machine. We describe the various cluster properties which we were able to compute with this method. Finally, we give some performance measurements.

Uloženo v:

Podrobná bibliografie
Vydáno v:	Computer physics communications Ročník 130; číslo 1; s. 118 - 129
Hlavní autoři:	Teuler, J.M., Gimel, J.C.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Amsterdam Elsevier B.V 01.07.2000 Elsevier Science Elsevier
Témata:	Atomic and molecular physics Calculations and mathematical techniques in atomic and molecular physics (excluding electron correlation calculations) Computational techniques Computer Science Coupled cluster theory Data Structures and Algorithms Electronic structure of atoms, molecules and their ions: theory Exact sciences and technology Mathematical methods in physics Parallel computing Percolation Physics Statistical model calculations (including Thomas-Fermi and Thomas-Fermi-Dirac models) Percolation Parallel computing Performance evaluation Distributed memory Cubic lattices Percolation clusters Algorithms Theoretical study Percolation theory Parallel computation Calculation methods
ISSN:	0010-4655, 1879-2944
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	We present a direct (i.e. non iterative) method for identifying the clusters of a cubic lattice on a distributed memory parallel machine. We describe the various cluster properties which we were able to compute with this method. Finally, we give some performance measurements.
ISSN:	0010-4655 1879-2944
DOI:	10.1016/S0010-4655(00)00046-1