Pipelined data parallel algorithms-II: design
For pt.I see ibid., p.470-85. A methodology for designing pipelined data-parallel algorithms on multicomputers is studied. The design procedure starts with a sequential algorithm which can be expressed as a nested loop with constant loop-carried dependencies. The procedure's main focus is on pa...
Uloženo v:
| Vydáno v: | IEEE transactions on parallel and distributed systems Ročník 1; číslo 4; s. 486 - 499 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.10.1990
|
| Témata: | |
| ISSN: | 1045-9219 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | For pt.I see ibid., p.470-85. A methodology for designing pipelined data-parallel algorithms on multicomputers is studied. The design procedure starts with a sequential algorithm which can be expressed as a nested loop with constant loop-carried dependencies. The procedure's main focus is on partitioning the loop by grouping related iterations together. Grouping is necessary to balance the communication overhead with the available parallelism and to produce pipelined execution patterns, which result in pipelined data-parallel computations. The grouping should satisfy dependence relationships among the iterations and also allow the granularity to be controlled. Various properties of grouping are studied, and methods for generating communication-efficient grouping are given. Given a grouping and an assignment of the groups to the processors, an analytic model is combined with the grouping results to describe the behavior and to estimate the performance of the resultant parallel program. Expressions characterizing the performance are derived.< > |
|---|---|
| Bibliografie: | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| ISSN: | 1045-9219 |
| DOI: | 10.1109/71.80176 |