Please use this identifier to cite or link to this item:
Title: Simple Performance Bounds for Multicore and Parallel Channel Systems
Authors: Robertazzi, Thomas G.
Gamboa, Carlos
Preservation Department, Stony Brook University Libraries.
Cataloging & Metadata Department, Stony Brook University Libraries.
Keywords: Communications Systems
Divisible Load Scheduling
Scheduled Networked Computing
Multicore Systems
Issue Date: 19-Jul-2010
Publisher: Stony Brook University. College of Engineering and Applied Sciences.
Stony Brook University.
Series/Report no.: CEAS Technical Report;832
Abstract: A simple modi cation of existing divisible load scheduling algo- rithms, boosting link speed by M for M parallel channels per link, allows time optimal load scheduling and performance prediction for parallel channel systems. The situation for multicore models is more complex but can be handled by a substitution involving equivalent pro- cessor speed. These modi cations yield upper bounds on such parallel systems' performance. This concept is illustrated for ideal single level (star) tree networks under a variety of scheduling policies. Less than ideal parallelism can also be modeled though mechanisms of ine ciency require further research.
Description: leave(s) : ill; 28 cm.
Appears in Collections:Community Members' Scholarship [CEAS]

Files in This Item:
File Description SizeFormat 
CEAS-832-Gamboa-Robertazzi-July-19-2010.pdf606.03 kBAdobe PDFThumbnail

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