Predicting Efficient Execution with Source Code Analysis in a Heterogeneous Environment
| dc.contributor.author | Hellwig, Markus | |
| dc.contributor.author | Becker, Thomas | |
| dc.date.accessioned | 2020-03-11T00:06:24Z | |
| dc.date.available | 2020-03-11T00:06:24Z | |
| dc.date.issued | 2017 | |
| dc.description.abstract | Finding a good schedule for the tasks of an application is a critical step for the efficient usage of heterogeneous systems. A good schedule can only be found with information about the tasks to be scheduled. In a dynamic system, this information is normally only available after each task is at least executed once, thereby creating an initial overhead until a good schedule can be created. Therefore, we introduce a method based on static code analysis and machine learning algorithms to predict the fastest processor of a given OpenCL task before runtime by classification which helps to reduce this initial overhead. We show how we used a static code analysis implementation based on Clang to generate training data on a set of 10 different heterogeneous processors including Intel, AMD and Nvidia GPUs, a Intel Xeon Phi and Intel CPUs. This training data was used to generate prediction models via several different machine learning algorithms including Random Forest and k-Nearest Neighbour and then evaluate the models by predicting the fastest processor out of two and more processors via classification. | en |
| dc.identifier.pissn | 0177-0454 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/31944 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V., Fachgruppe PARS | |
| dc.relation.ispartof | PARS-Mitteilungen: Vol. 34, Nr. 1 | |
| dc.title | Predicting Efficient Execution with Source Code Analysis in a Heterogeneous Environment | en |
| dc.type | Text/Journal Article | |
| gi.citation.endPage | 90 | |
| gi.citation.publisherPlace | Berlin | |
| gi.citation.startPage | 78 |
Dateien
Originalbündel
1 - 1 von 1