Title :
Adaptive Blocks: A High Performance Data Structure
Author :
Stout, Quentin F. ; de Zeeuw, Darren L. ; Gombosi, Tamas I. ; Groth, Clinton P T ; Marshall, Hal G. ; Powell, Kenneth G.
Author_Institution :
University of Michigan
Abstract :
We examine a data structure that uses flexible "adaptivity" to obtain high performance for both serial and parallel computers. The data structure is an adaptive grid which partitions a given region into regular cells. Its closest relatives are cell-based tree decompositions, but there are several important differences which lead to significant performance advantages. Using this block data structure to support adaptive mesh refinement (AMR), we were able to sustain 17 GFLOPS in ideal magnetohydrodynamic (MHD) simulations of the solar wind emanating from the base of the solar corona, using a 512 processor Cray T3D at NASA Goddard.
Keywords :
Adaptive mesh refinement; Computational modeling; Concurrent computing; Data structures; High performance computing; Laboratories; Magnetohydrodynamics; Parallel processing; Physics computing; Tree data structures;
Conference_Titel :
Supercomputing, ACM/IEEE 1997 Conference
Print_ISBN :
0-89791-985-8
DOI :
10.1109/SC.1997.10027
