Parallelization of sequential programs: distribution of arrays among processors and structurization of communications

Data distribution functions are introduced. They are matched with scheduling functions. The processors and iterations are determined that use an array element at its fixed position in a statement. This makes it possible to obtain the initial data distribution and also information on the data volume...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Cybernetics and systems analysis Ročník 48; číslo 1; s. 122 - 137
Hlavní autoři: Adutskevich, E. V., Likhoded, N. A., Sikorsky, A. O.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Boston Springer US 01.01.2012
Springer
Springer Nature B.V
Témata:
Algorithms
Analysis
Arrays
Artificial Intelligence
Computer memory
Control
Cybernetics
Data exchange
Distribution functions
Expenditures
Investigations
Mathematics
Mathematics and Statistics
Optimization
Parallel processing
Processor Architectures
Processors
Scheduling
Software Engineering/Programming and Operating Systems
Software–Hardware Systems
Studies
Systems analysis
Systems Theory
parallel computer with distributed memory
optimization of communications
parallel computing
affine loop nest
parallelization of algorithms
ISSN:1060-0396, 1573-8337
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Data distribution functions are introduced. They are matched with scheduling functions. The processors and iterations are determined that use an array element at its fixed position in a statement. This makes it possible to obtain the initial data distribution and also information on the data volume for every processor and on the structure of required communications.
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:1060-0396
1573-8337
DOI:10.1007/s10559-012-9382-2