A Hadoop-based Principle Component Analysis on embedded heterogeneous platform

Sheng Yen Chen, Chia I. Wei, Yu Chen Chiu, Bo-Cheng Lai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Hadoop is a widely adopted distributed processing framework which assumes each computing node a CPU-based system with local memory. This design scheme cannot effectively take full advantage of an embedded heterogeneous many-core platform due the mismatch of data collection and management paradigms between the Hadoop environment and embedded heterogeneous systems. This paper proposes a Hadoop-based design of Principle Component Analysis (PCA) to efficiently leverage the distributed embedded heterogeneous many-core systems. By taking the same data layout of conventional Hadoop applications, the proposed design introduces efficient manners to collect and manage the fine-grained data chunks. The experiments on a Tegra K1 has achieved 5.9× performance enhancement.

Original languageEnglish
Title of host publication2017 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509039692
DOIs
StatePublished - 5 Jun 2017
Event2017 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2017 - Hsinchu, Taiwan
Duration: 24 Apr 201727 Apr 2017

Publication series

Name2017 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2017

Conference

Conference2017 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2017
Country/TerritoryTaiwan
CityHsinchu
Period24/04/1727/04/17

Fingerprint

Dive into the research topics of 'A Hadoop-based Principle Component Analysis on embedded heterogeneous platform'. Together they form a unique fingerprint.

Cite this