Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Towards high performance data analytic on heterogeneous many-core systems: A study on Bayesian Sequential Partitioning
Ist Teil von
Journal of parallel and distributed computing, 2018-12, Vol.122, p.36-50
Ort / Verlag
United States: Elsevier Inc
Erscheinungsjahr
2018
Link zum Volltext
Quelle
ScienceDirect Journals (5 years ago - present)
Beschreibungen/Notizen
Bayesian Sequential Partitioning (BSP) is a statistically effective density estimation method to comprehend the characteristics of a high dimensional data space. The intensive computation of the statistical model and the counting of enormous data have caused serious design challenges for BSP to handle the growing volume of the data. This paper proposes a high performance design of BSP by leveraging a heterogeneous CPU/GPGPU system that consists of a host CPU and a K80 GPGPU. A series of techniques, on both data structures and execution management policies, is implemented to extensively exploit the computation capability of the heterogeneous many-core system and alleviate system bottlenecks. When compared with a parallel design on a high-end CPU, the proposed techniques achieve 48x average runtime enhancement while the maximum speedup can reach 78.76x.
•Techniques to speedup Bayesian Sequential Partitioning by 48x on a heterogeneous many-core system.•Proposes a series of techniques, for both data structures and execution management policies.•Achieve 106x average runtime enhancement while the maximum speedup can reach 197.96x.