2020
DOI: 10.25209/2079-3316-2021-12-1-21-113
|View full text |Cite
|
Sign up to set email alerts
|

Program transformations as the base for optimizing parallelizing compilers

Abstract: В работе рассматриваются преобразования программ, приводящие к ускорению. Приводятся публикации о различных параллельных вычислительных архитектурах и инструментах разработки эффективных программ для них. Рассматривается сочетание распараллеливания и оптимизации доступа к модулям памяти разного уровня. Отмечается, что отставание автоматической оптимизации программ от потребностей новых архитектур сдерживает развитие новых перспективных вычислительных систем. Формулируются задачи развития теории преобразования … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
1

Relationship

1
4

Authors

Journals

citations
Cited by 7 publications
(1 citation statement)
references
References 101 publications
0
1
0
Order By: Relevance
“…• automatic or semi-automatic parallelization of sequential programs with their subsequent transformation to the target architecture [1]; • development of programs or algorithms that has unlimited parallelism, determined by the problem being solved, with the subsequent "compression" of this parallelism in accordance with the restrictions determined by the target architecture [2]. There is a semantic gap between the written program and the real parallel computing system (PCS) with using any of these approaches.…”
Section: Introductionmentioning
confidence: 99%
“…• automatic or semi-automatic parallelization of sequential programs with their subsequent transformation to the target architecture [1]; • development of programs or algorithms that has unlimited parallelism, determined by the problem being solved, with the subsequent "compression" of this parallelism in accordance with the restrictions determined by the target architecture [2]. There is a semantic gap between the written program and the real parallel computing system (PCS) with using any of these approaches.…”
Section: Introductionmentioning
confidence: 99%