Optimizing atomic functions using compile-time information

Authors:
T. Ruhl;H. E. Bal
Affiliations:
-;-
Venue:
PMMP '95 Proceedings of the conference on Programming Models for Massively Parallel Computers
Year:
1995

Citing 0
Cited 1

Performance evaluation of the Orca shared-object system

ACM Transactions on Computer Systems (TOCS)

Quantified Score

Hi-index	0.01

Visualization

Abstract

Functions that invoke operations on multiple objects atomically are a useful extension of object-based parallel languages, such as Orca. This paper introduces atomic functions and shows how compile-time information can drive run-time optimizations of such functions.