Code Optimization in the Polyhedron Model - Improving the Efficiency of Parallel Loop Nests

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.

Level thesis:degree_level

thesis.doctoral

Grantor dc:publisher

Universität Passau

Year

2008

Author dc:creator

• Faber, Peter

Contributors dc:contributor

• Griebl, Martin

• Polyedermodell
• Schleifenparallelisierung
• OpenMP
• automatische Parallelisierung
• optimierende Compiler
• polyhedron model
• loop parallelization
• automatic parallelization
• optimizing compilers

Statement dc:rights

• Standardbedingung laut Einverständniserklärung

Repository record source_url

https://opus4.kobv.de/opus4-uni-passau/frontdoor/index/index/docId/100

OAI identifier oai:identifier

oai:kobv.de-opus4-uni-passau:100