Towards high performance data analytic on heterogeneous many-core systems: A study on Bayesian Sequential Partitioning

Bo-Cheng Lai*, Tung Yu Wu, Tsou Han Chiu, Kun Chun Li, Chia Ying Lee, Wei Chen Chien, Wing Hung Wong

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)36-50
Number of pages15
JournalJournal of Parallel and Distributed Computing
Volume122
DOIs
StatePublished - 1 Dec 2018

Keywords

  • Data processing
  • Design and optimization
  • Heterogeneous system
  • Many-core system
  • Performance analysis

Fingerprint Dive into the research topics of 'Towards high performance data analytic on heterogeneous many-core systems: A study on Bayesian Sequential Partitioning'. Together they form a unique fingerprint.

Cite this