An experimental study across GPU DBMSes toward cost-effective analytical processing

Young Kyoon Suh; Seounghyeon Kim; Joo Young Lee; Hawon Chu; Junyoung An; Kyong Ha Lee

doi:10.1587/transinf.2020DAL0001

An experimental study across GPU DBMSes toward cost-effective analytical processing

Young Kyoon Suh, Seounghyeon Kim, Joo Young Lee, Hawon Chu, Junyoung An, Kyong Ha Lee

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

SUMMARY In this letter we analyze the economic worth of GPU on analytical processing of GPU-accelerated database management systems (DBMSes). To this end, we conducted rigorous experiments with TPC-H across three popular GPU DBMSes. Consequently, we show that co-processing with CPU and GPU in the GPU DBMSes was cost-effective despite exposed concerns.

Original language	English
Pages (from-to)	551-555
Number of pages	5
Journal	IEICE Transactions on Information and Systems
Volume	E104.D
Issue number	5
DOIs	https://doi.org/10.1587/transinf.2020DAL0001
State	Published - 2021

Keywords

Analytical processing
Cost-effectiveness
Database management systems (DBMS)
Economic perspectives
GPU

Access to Document

10.1587/transinf.2020DAL0001

Cite this

@article{deb2ea9779264d94a6c06e34a100a991,

title = "An experimental study across GPU DBMSes toward cost-effective analytical processing",

abstract = "SUMMARY In this letter we analyze the economic worth of GPU on analytical processing of GPU-accelerated database management systems (DBMSes). To this end, we conducted rigorous experiments with TPC-H across three popular GPU DBMSes. Consequently, we show that co-processing with CPU and GPU in the GPU DBMSes was cost-effective despite exposed concerns.",

keywords = "Analytical processing, Cost-effectiveness, Database management systems (DBMS), Economic perspectives, GPU",

author = "Suh, {Young Kyoon} and Seounghyeon Kim and Lee, {Joo Young} and Hawon Chu and Junyoung An and Lee, {Kyong Ha}",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 The Institute of Electronics, Information and Communication Engineers",

year = "2021",

doi = "10.1587/transinf.2020DAL0001",

language = "English",

volume = "E104.D",

pages = "551--555",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "5",

}

TY - JOUR

T1 - An experimental study across GPU DBMSes toward cost-effective analytical processing

AU - Suh, Young Kyoon

AU - Kim, Seounghyeon

AU - Lee, Joo Young

AU - Chu, Hawon

AU - An, Junyoung

AU - Lee, Kyong Ha

PY - 2021

Y1 - 2021

N2 - SUMMARY In this letter we analyze the economic worth of GPU on analytical processing of GPU-accelerated database management systems (DBMSes). To this end, we conducted rigorous experiments with TPC-H across three popular GPU DBMSes. Consequently, we show that co-processing with CPU and GPU in the GPU DBMSes was cost-effective despite exposed concerns.

AB - SUMMARY In this letter we analyze the economic worth of GPU on analytical processing of GPU-accelerated database management systems (DBMSes). To this end, we conducted rigorous experiments with TPC-H across three popular GPU DBMSes. Consequently, we show that co-processing with CPU and GPU in the GPU DBMSes was cost-effective despite exposed concerns.

KW - Analytical processing

KW - Cost-effectiveness

KW - Database management systems (DBMS)

KW - Economic perspectives

KW - GPU

UR - http://www.scopus.com/inward/record.url?scp=85106694814&partnerID=8YFLogxK

U2 - 10.1587/transinf.2020DAL0001

DO - 10.1587/transinf.2020DAL0001

M3 - Article

AN - SCOPUS:85106694814

SN - 0916-8532

VL - E104.D

SP - 551

EP - 555

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

IS - 5

ER -

An experimental study across GPU DBMSes toward cost-effective analytical processing

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this