An approach to synchronization for parallel computing

1 January 1988

conference paper
Published by Association for Computing Machinery (ACM)

p. 573-581
https://doi.org/10.1145/55364.55420

Abstract

This paper proposes an approach to minimally constrained synchronization for the parallel execution of imperative programs in a shared-memory environment. Anti-dependencies and output-dependencies arising from array references within loops are completely removed, using run-time analysis if necessary. A parallel reference-pattern generation scheme based on one proposed in [13] is used in conjunction with dynamic allocation and binding of storage, to completely remove non-intrinsic data dependencies during execution.

Keywords

PARALLEL REFERENCE-PATTERN GENERATION SCHEME
ARRAY REFERENCE
PARALLEL EXECUTION
IMPERATIVE PROGRAM
RUN-TIME ANALYSIS
PARALLEL COMPUTING
DYNAMIC ALLOCATION
NON-INTRINSIC DATA DEPENDENCY
SHARED-MEMORY ENVIRONMENT
PARALLEL COMPUTER
SHARED MEMORY
TIMING ANALYSIS

This publication has 0 references indexed in Scilit: