Virtualizing CUDA Enabled GPGPUs on ARM Clusters
| Autor: | Valentina Pelliccia, Giulio Giunta, Carlo Palmieri, Raffaele Montella, Carmine Ferraro, Marco Lapegna, Giuliano Laccetti |
|---|---|
| Přispěvatelé: | R. Wyrzykowsky, E. Deelman, J. Dongarra, K. Karczewski, J. Kitowski, K. Wiatr, Raffaele, Montella, Giulio, Giunta, Laccetti, Giuliano, Lapegna, Marco, Valentina, Pelliccia, Carmine, Ferraro, Carlo, Palmieri |
| Rok vydání: | 2016 |
| Předmět: |
Service (systems architecture)
Computer science CUDA Cloud computing 02 engineering and technology computer.software_genre Virtualisation Theoretical Computer Science Remoting GPGPU · Virtualisation · Remoting · Cloud computing · ARM · CUDA · HPC NET Remoting 0202 electrical engineering electronic engineering information engineering ARM GPGPU HPC Computer Science (all) business.industry 020206 networking & telecommunications Workload Virtualization Computer architecture Operating system x86 020201 artificial intelligence & image processing General-purpose computing on graphics processing units business computer |
| Zdroj: | Parallel Processing and Applied Mathematics ISBN: 9783319321516 PPAM (2) |
| DOI: | 10.1007/978-3-319-32152-3_1 |
| Popis: | Tiny ARM based devices are the backbone of the Internet of Things technologies, nevertheless the availability of high performance multicore lightweight CPUs pushed the High Performance Computing to hybrid architectures leveraging on diverse levels parallelism. In this paper we describe how to accelerate inexpensive ARM-based computing nodes with high-end CUDA enabled GPGPUs hosted on x86 64 machines using the GVirtuS general-purpose virtualization service. We draw the vision of a possible hierarchical remote workload distribution among different devices. Preliminary, but promising, performance evaluation data suggests that the developed technology is suitable for real world applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|