COMPILE-TIME SCHEDULING OF MULTITHREAD WITH DATA LOCALITIES ON MULTIPLE VECTOR PROCESSORS

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > journal & Dissertation > Item 987654321/29225

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/29225

Title:	COMPILE-TIME SCHEDULING OF MULTITHREAD WITH DATA LOCALITIES ON MULTIPLE VECTOR PROCESSORS
Authors:	CHANG,CY;SHEU,JP
Contributors:	資訊工程研究所
Date:	1995
Issue Date:	2010-06-29 20:16:50 (UTC+8)
Publisher:	中央大學
Abstract:	A large class of loop programs applied in solving differential equations, Fourier transforms, image processing and neural processing can be translated or rewritten into a vector execution form with a pi-block dependence graph, In the paper we propose a multithreading strategy to partition such vectorized loops into multithread execution form. Each partitioned thread consists of instances of statements with localities in vector registers. The multithreading scheme gives a novel combination of loop unrolling, statement instances reordering, index shifting, vector register reuse exploiting and multithreading. For some cases of loop program with pi-bloek dependence graph, experimental results show that our scheme assists vector compilers of the Convex C38 series to reduce the number of memory accesses and synchronizations among CPUs.
Relation:	CONCURRENCY-PRACTICE AND EXPERIENCE
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	460	View/Open

社群 sharing