A consistent generation of pipeline parallelism and distribution of operations and data among processors |
| |
Authors: | E V Adutskevich N A Likhoded |
| |
Affiliation: | (1) Institute of Mathematics, National Academy of Sciences of Belarus, ul. Surganova 11, Minsk, 220072, Belarus |
| |
Abstract: | The problem of mapping affine loop nests onto parallel computers with distributed memory is considered. A technique for algorithm scheduling and distributing operations and data over processors is proposed. This technique makes it possible to generate pipeline parallelism and minimize the amount of data exchanges between the processors. The method is adapted for automation and explicitly allows for dependence on outer variables of loops. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |