Hybrid CPU–GPU execution support in the skeleton programming framework SkePU
| Autor: | Tomas Öhberg, Christoph Kessler, August Ernstsson |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Speedup
Computer science Computation Workload 02 engineering and technology Dynamic priority scheduling Parallel computing Heterogeneous computing Hybrid execution Skeleton programming Workload partitioning Skeleton (computer programming) Partition (database) Theoretical Computer Science Datorteknik 03 medical and health sciences CUDA 0302 clinical medicine Hardware and Architecture 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer Engineering 030217 neurology & neurosurgery Software Information Systems |
| Zdroj: | The Journal of Supercomputing |
| ISSN: | 0920-8542 |
| DOI: | 10.1007/s11227-019-02824-7 |
| Popis: | In this paper, we present a hybrid execution backend for the skeleton programming framework SkePU. The backend is capable of automatically dividing the workload and simultaneously executing the computation on a multi-core CPU and any number of accelerators, such as GPUs. We show how to efficiently partition the workload of skeletons such as Map, MapReduce, and Scan to allow hybrid execution on heterogeneous computer systems. We also show a unified way of predicting how the workload should be partitioned based on performance modeling. With experiments on typical skeleton instances, we show the speedup for all skeletons when using the new hybrid backend. We also evaluate the performance on some real-world applications. Finally, we show that the new implementation gives higher and more reliable performance compared to an old hybrid execution implementation based on dynamic scheduling. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |