Proceedings IEEE International Conference on Application-Specific Systems, Architectures and Processors
DOI: 10.1109/asap.1997.606829
|View full text |Cite
|
Sign up to set email alerts
|

Tiling with limited resources

Abstract: In the framework of perfect loop nests with uniform dependences, tiling has been extensively studied as a source-to-source program transformation. Little work has been devoted to the mapping and scheduling of the tiles on to physical processors. We present several new results in the context of limited computational resources, and assuming communication-computation overlap. In particular, under some reasonable assumptions, we derive the optimal mapping and scheduling of tiles to physical processors.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
19
0

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 19 publications
(19 citation statements)
references
References 9 publications
0
19
0
Order By: Relevance
“…7 This small example shows that our target problem is intrinsically more complex than the instance with same-speed processors: as shown in Ref. [8], a columnwise allocation would be optimal for our two-column iteration space with two processors of equal speed.…”
Section: Optimality and Columnwise Allocationsmentioning
confidence: 85%
See 2 more Smart Citations
“…7 This small example shows that our target problem is intrinsically more complex than the instance with same-speed processors: as shown in Ref. [8], a columnwise allocation would be optimal for our two-column iteration space with two processors of equal speed.…”
Section: Optimality and Columnwise Allocationsmentioning
confidence: 85%
“…Rather than providing a detailed motivation for tiling, we refer the reader to the papers by Calland, Dongarra and Robert [8] and by H ogsted, Carter and Ferrante [16], which provide a review of the existing literature. Brie¯y, most of the work amounts to partitioning the iteration space of a uniform loop nest into tiles whose shape and size are optimized according to some criterion (such as the communication-to-computation ratio).…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Tilling can be taken as both an important transformation and a code generation technique, which is concerned by a large amount of literature [28,30]. The classical definition of the "tile" should include three points [28]: 1) it is constrained by bounds; 2) it is identical by translation; and 3) it is an atomic unit.…”
Section: Code Generationmentioning
confidence: 99%
“…The classical definition of the "tile" should include three points [28]: 1) it is constrained by bounds; 2) it is identical by translation; and 3) it is an atomic unit. The bound constraints are obvious.…”
Section: Code Generationmentioning
confidence: 99%