Code Optimization in the Polyhedron Model - Improving the Efficiency of Parallel Loop Nests
Code-Optimierung im Polyedermodell - Effizienzsteigerung von parallelen Schleifensätzen
- A safe basis for automatic loop parallelization is the polyhedron model which represents the iteration domain of a loop nest as a polyhedron in $\mathbb{Z}^n$. However, turning the parallel loop program in the model to efficient code meets with several obstacles, due to which performance may deteriorate seriously -- especially on distributed memory architectures. We introduce a fine-grained model of the computation performed and show how this model can be applied to create efficient code.
Author: | Peter Faber |
---|---|
URN: | urn:nbn:de:bvb:739-opus-12512 |
Advisor: | Martin Griebl |
Document Type: | Doctoral Thesis |
Language: | English |
Year of Completion: | 2007 |
Date of Publication (online): | 2008/10/21 |
Publishing Institution: | Universität Passau |
Granting Institution: | Universität Passau, Fakultät für Informatik und Mathematik |
Date of final exam: | 2008/06/25 |
Release Date: | 2008/10/21 |
Tag: | OpenMP; Polyedermodell; Schleifenparallelisierung; automatische Parallelisierung; optimierende Compiler OpenMP; automatic parallelization; loop parallelization; optimizing compilers; polyhedron model |
GND Keyword: | Polyeder; High Performance Fortran; Codegenerierung; Compiler; Nebenläufigkeit |
Institutes: | Fakultät für Informatik und Mathematik / Sonstiger Autor der Fakultät für Informatik und Mathematik |
Dewey Decimal Classification: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
open_access (DINI-Set): | open_access |
Licence (German): | Standardbedingung laut Einverständniserklärung |