Please use this identifier to cite or link to this item:
Main Title: An integrated hardware-software approach to task graph management
Author(s): Engelhardt, Nina
Dallou, Tamer
Elhossini, Ahmed
Juurlink, Ben
Type: Conference Object
Language Code: en
Abstract: Task-based parallel programming models with explicit data dependencies, such as OmpSs, are gaining popularity, due to the ease of describing parallel algorithms with complex and irregular dependency patterns. These advantages, however, come at a steep cost of runtime overhead incurred by dynamic dependency resolution. Hardware support for task management has been proposed in previous work as a possible solution. We present VSs, a runtime library for the OmpSs programming model that integrates the Nexus++ hardware task manager, and evaluate the performance of the VSs-Nexus++ system. Experimental results show that applications with fine-grain tasks can achieve speedups of up to 3.4×, while applications optimized for current runtimes attain 1.3×. Providing support for hardware task managers in runtime libraries is therefore a viable approach to improve the performance of OmpSs applications.
Issue Date: 2014
Date Available: 9-Mar-2017
DDC Class: 004 Datenverarbeitung; Informatik
Subject(s): OmpSs
hardware task scheduler
parallel programming models
runtime library
task dataflow
Proceedings Title: 2014 IEEE Intl Conf on High Performance Computing and Communications, 2014 IEEE 6th Intl Symp on Cyberspace Safety and Security, 2014 IEEE 11th Intl Conf on Embedded Software and Syst (HPCC,CSS,ICESS)
Publisher: IEEE
Publisher Place: New York, NY [u.a.]
Publisher DOI: 10.1109/HPCC.2014.66
Page Start: 392
Page End: 399
ISBN: 978-1-4799-6124-5
Appears in Collections:FG Architektur eingebetteter Systeme » Publications

Files in This Item:
File Description SizeFormat 
2014_Engelhardt_et-al.pdf2.27 MBAdobe PDFThumbnail

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.