A Dynamically Adaptive Parallelizat ion Model Based on Speculative Multithreading

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" A Dynamically Adaptive Parallelizat ion Model Based on Speculative Multithreading "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151583
Doc. No	:	ET23375
Main Entry	:	Iffat Hoque Kazi
Title Proper	:	A Dynamically Adaptive Parallelizat ion Model Based on Speculative Multithreading
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	A wide variety of application programs have inherent looplevel pardlelism that can be exploitedon shared-memory multiprocessor systems for pedomance improvement. Pardelizing compilers areavailable that can automatically identify and extract some of the loop-level parallelism in sequentialprograms. Traditional parallelizing compilers, however, often cannot extract much of the availableparallelism due to the inherent limitations of compite-time information. Loops with potentid datadependences that are caused by run-time values, or loops with sequential constructs (e.g. do-whileloops), in particular are impossible to parallelize using these compilers. The parallelism in such loopscan be exploited only by using run- time parallelization techniques since the information requiredto parallelize these loops is available only at run-time. Once a program has been parallelized, it isnecessary to efficiently execute it in parallel to improve its performance. Compiler parailelized codecannot predetermine the number of processors a parallel code region can most efficiently use, however,.....-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL46614.pdf
Title and statement of responsibility and	:	A Dynamically Adaptive Parallelizat ion Model Based on Speculative Multithreading [Thesis]