DMP: Deterministic Shared-Memory Multiprocessing

Authors:
Joseph Devietti;Brandon Lucia;Luis Ceze;Mark Oskin
Affiliations:
University of Washington;University of Washington;University of Washington;University of Washington
Venue:
IEEE Micro
Year:
2010

Citing 0
Cited 3

Concurrent programming with revisions and isolation types

Proceedings of the ACM international conference on Object oriented programming systems languages and applications
Two for the price of one: a model for parallel and incremental computation

Proceedings of the 2011 ACM international conference on Object oriented programming systems languages and applications
An Extended SystemC Framework for Efficient HW/SW Co-Simulation

ACM Transactions on Design Automation of Electronic Systems (TODAES)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shared-memory multicore and multiprocessor systems are nondeterministic, which frustrates debugging and complicates testing of multithreaded code, impeding parallel programming's widespread adoption. The authors propose fully deterministic shared-memory multiprocessing that not only enhances debugging by offering repeatability by default, but also improves the quality of testing and the deployment of production code. They show that determinism can be provided with little performance cost on future hardware.