Title :
A robust parallel programming model for dynamic non-uniform scientific computations
Author :
Kohn, Scott R. ; Baden, Scott B.
Author_Institution :
Dept. of Comput. Sci. & Eng., California Univ., San Diego, La Jolla, CA, USA
Abstract :
LPARX provides efficient run-time support for dynamic, non-uniform scientific calculations running on MIMD distributed memory architectures. It extends HPF´s data decomposition model to provide support for dynamic, block irregular data structures. LPARX represents data decompositions as first-class objects and expresses data dependencies in a manner which is logically independent of data decomposition and problem dimension. LPARX applications are portable across a diversity of MIMD machines. We have implemented a number of applications in LPARX-including a 3D particle calculation and 2D and 3D adaptive multigrid solvers-which could not have been efficiently implemented in HPF
Keywords :
data structures; distributed memory systems; parallel algorithms; parallel programming; physics computing; 2D adaptive multigrid solvers; 3D adaptive multigrid solvers; 3D particle calculation; HPF; LPARX; MIMD; MIMD machines; data decomposition; data decomposition model; data decompositions; data dependencies; distributed memory architecture; dynamic block irregular data structures; dynamic nonuniform scientific computations; first-class objects; problem dimension; robust parallel programming model; run-time support; three dimensional adaptive multigrid solvers; three dimensional particle calculation; Application software; Computer science; Concurrent computing; Data structures; Dynamic programming; High performance computing; Parallel programming; Robustness; Runtime; Workstations;
Conference_Titel :
Scalable High-Performance Computing Conference, 1994., Proceedings of the
Conference_Location :
Knoxville, TN
Print_ISBN :
0-8186-5680-8
DOI :
10.1109/SHPCC.1994.296685
