Automatic placement of communications in mesh-partitioning parallelization

Authors:
Laurent Hascoët
Affiliations:
INRIA Sophia-Antipolis, B.P. 93, 06902 Sophia-Antipolis, France
Venue:
PPOPP '97 Proceedings of the sixth ACM SIGPLAN symposium on Principles and practice of parallel programming
Year:
1997

Citing 5
Cited 0

Communication and concurrency

Communication and concurrency
Compiling programs for nonshared memory machines

Compiling programs for nonshared memory machines
Supporting irregular distributions in FORTRAN 90D/HPF compilers

Supporting irregular distributions in FORTRAN 90D/HPF compilers
Automatic Parallelization of the AVL FIRE Benchmark for a Distributed-Memory System

PARA '95 Proceedings of the Second International Workshop on Applied Parallel Computing, Computations in Physics, Chemistry and Engineering Science
MPI: A Message-Passing Interface Standard

MPI: A Message-Passing Interface Standard

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a tool for mesh-partitioning parallelization of numerical programs working iteratively on an unstructured mesh. This conventional method splits a mesh into sub-meshes, adding some overlap on the boundaries of the sub-meshes. The program is then run in SPMD mode on a parallel architecture with distributed memory. It is necessary to add calls to communication routines at a few carefully selected locations in the code. The tool presented here uses the data-dependence information to mechanize the placement of these synchronizations. Additionally, we see that there is not a unique solution for placing these synchronizations, and performance depends on this choice.