QAMEM

Query aware memory energy management

Srinivasan Chandrasekharan, Christopher Gniady

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

As memory becomes cheaper, use of it has become more prominent in computer systems. This increase in number of memory modules increases the ratio of energy consumption by memory to the overall energy consumption of a computer system. As Database Systems become more memory centric and put more pressure on the memory subsystem, managing energy consumption of main memory is becoming critical. Therefore, it is important to take advantage of all memory idle times and lower power states provided by newer memory architectures by placing memory in low power modes using application level cues. While there have been studies on CPU power consumption in Database Systems, only limited research has been done on the role of memory in Database Systems with respect to energy management. We propose Query Aware Memory Energy Management (QAMEM) where the Database System provides application level cues to the memory controller to switch to lower power states using query information and performance counters. Our results show that by using QAMEM on TPC-H workloads one can save 25% of total system energy in comparison to the state of the art memory energy management mechanisms.

Original languageEnglish (US)
Title of host publicationProceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages412-421
Number of pages10
ISBN (Electronic)9781538658154
DOIs
StatePublished - Jul 13 2018
Event18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018 - Washington, United States
Duration: May 1 2018May 4 2018

Other

Other18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018
CountryUnited States
CityWashington
Period5/1/185/4/18

Fingerprint

Energy management
Data storage equipment
Energy utilization
Computer systems
Memory architecture
Program processors
Electric power utilization
Switches

Keywords

  • Database
  • Memory
  • Memory energy management
  • Postgresql
  • SQL queries
  • TPCH

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Chandrasekharan, S., & Gniady, C. (2018). QAMEM: Query aware memory energy management. In Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018 (pp. 412-421). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCGRID.2018.00068

QAMEM : Query aware memory energy management. / Chandrasekharan, Srinivasan; Gniady, Christopher.

Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 412-421.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chandrasekharan, S & Gniady, C 2018, QAMEM: Query aware memory energy management. in Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc., pp. 412-421, 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018, Washington, United States, 5/1/18. https://doi.org/10.1109/CCGRID.2018.00068
Chandrasekharan S, Gniady C. QAMEM: Query aware memory energy management. In Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 412-421 https://doi.org/10.1109/CCGRID.2018.00068
Chandrasekharan, Srinivasan ; Gniady, Christopher. / QAMEM : Query aware memory energy management. Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 412-421
@inproceedings{ffeac1885e584e75bff759a3b13320d3,
title = "QAMEM: Query aware memory energy management",
abstract = "As memory becomes cheaper, use of it has become more prominent in computer systems. This increase in number of memory modules increases the ratio of energy consumption by memory to the overall energy consumption of a computer system. As Database Systems become more memory centric and put more pressure on the memory subsystem, managing energy consumption of main memory is becoming critical. Therefore, it is important to take advantage of all memory idle times and lower power states provided by newer memory architectures by placing memory in low power modes using application level cues. While there have been studies on CPU power consumption in Database Systems, only limited research has been done on the role of memory in Database Systems with respect to energy management. We propose Query Aware Memory Energy Management (QAMEM) where the Database System provides application level cues to the memory controller to switch to lower power states using query information and performance counters. Our results show that by using QAMEM on TPC-H workloads one can save 25{\%} of total system energy in comparison to the state of the art memory energy management mechanisms.",
keywords = "Database, Memory, Memory energy management, Postgresql, SQL queries, TPCH",
author = "Srinivasan Chandrasekharan and Christopher Gniady",
year = "2018",
month = "7",
day = "13",
doi = "10.1109/CCGRID.2018.00068",
language = "English (US)",
pages = "412--421",
booktitle = "Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - QAMEM

T2 - Query aware memory energy management

AU - Chandrasekharan, Srinivasan

AU - Gniady, Christopher

PY - 2018/7/13

Y1 - 2018/7/13

N2 - As memory becomes cheaper, use of it has become more prominent in computer systems. This increase in number of memory modules increases the ratio of energy consumption by memory to the overall energy consumption of a computer system. As Database Systems become more memory centric and put more pressure on the memory subsystem, managing energy consumption of main memory is becoming critical. Therefore, it is important to take advantage of all memory idle times and lower power states provided by newer memory architectures by placing memory in low power modes using application level cues. While there have been studies on CPU power consumption in Database Systems, only limited research has been done on the role of memory in Database Systems with respect to energy management. We propose Query Aware Memory Energy Management (QAMEM) where the Database System provides application level cues to the memory controller to switch to lower power states using query information and performance counters. Our results show that by using QAMEM on TPC-H workloads one can save 25% of total system energy in comparison to the state of the art memory energy management mechanisms.

AB - As memory becomes cheaper, use of it has become more prominent in computer systems. This increase in number of memory modules increases the ratio of energy consumption by memory to the overall energy consumption of a computer system. As Database Systems become more memory centric and put more pressure on the memory subsystem, managing energy consumption of main memory is becoming critical. Therefore, it is important to take advantage of all memory idle times and lower power states provided by newer memory architectures by placing memory in low power modes using application level cues. While there have been studies on CPU power consumption in Database Systems, only limited research has been done on the role of memory in Database Systems with respect to energy management. We propose Query Aware Memory Energy Management (QAMEM) where the Database System provides application level cues to the memory controller to switch to lower power states using query information and performance counters. Our results show that by using QAMEM on TPC-H workloads one can save 25% of total system energy in comparison to the state of the art memory energy management mechanisms.

KW - Database

KW - Memory

KW - Memory energy management

KW - Postgresql

KW - SQL queries

KW - TPCH

UR - http://www.scopus.com/inward/record.url?scp=85050979193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050979193&partnerID=8YFLogxK

U2 - 10.1109/CCGRID.2018.00068

DO - 10.1109/CCGRID.2018.00068

M3 - Conference contribution

SP - 412

EP - 421

BT - Proceedings - 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -