DagSemProc.07361.5.pdf
- Filesize: 470 kB
- 12 pages
Document
Some Experiments on Tiling Loop Programs for Shared-Memory Multicore Architectures
Author
-
Part of:
Volume:
Dagstuhl Seminar Proceedings, Volume 7361
Series: Dagstuhl Seminar Proceedings (DagSemProc) - License:
Creative Commons Attribution 4.0 International license
- Publication Date: 2008-02-06
Cite AsGet BibTex
Armin Größlinger. Some Experiments on Tiling Loop Programs for Shared-Memory Multicore Architectures. In Programming Models for Ubiquitous Parallelism. Dagstuhl Seminar Proceedings, Volume 7361, pp. 1-12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)
https://doi.org/10.4230/DagSemProc.07361.5
https://doi.org/10.4230/DagSemProc.07361.5
Abstract
The model-based transformation of loop programs is a way of
detecting fine-grained parallelism in sequential programs. One of
the challenges is to agglomerate the parallelism to a coarser grain,
in order to map the operations of the program to the available cores
in a multicore architecture. We consider shared-memory multicores as
target architecture for space-time mapped loop programs and make
some observations concerning code generation, load balancing and
cache effects.
Keywords
- Multicore
- automatic parallelization
- loop transformations
- polyhedron model
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads