Swarm processor system: Hardware process scheduler based energy efficient multi-core system

Won Seob Jeong, Seung Hun Kim, Sang Min Lee, Won Woo Ro

Research output: Contribution to journalLetter

Abstract

Single-ISA heterogeneous multi-core processors can provide energy efficient performance by properly assigning workloads on two types of cores in a processor: high performance large cores and low power small cores. However, traditional process scheduling mechanism is hard to support an proper workload distribution due to an overhead of fine-grained state monitoring and scheduling. To overcome this problem, we propose Swarm Processor System which supports hardware implemented workload scheduling mechanism. In the proposed system, each core chooses a proper workload by using special hardware modules in the core instead of the scheduler of operating systems. We compare Swarm Processor System against the traditional mechanisms, and found that the proposed method shows the closest energy efficiency to the oracle case with providing stable performance.

Original languageEnglish
JournalIEICE Electronics Express
Volume11
Issue number14
DOIs
Publication statusPublished - 2014 Jul 4

Fingerprint

central processing units
hardware
Scheduling
Hardware
scheduling
Energy efficiency
energy
support systems
Monitoring
modules

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Cite this

@article{1d254f161a62484e850e31502be5f8b6,
title = "Swarm processor system: Hardware process scheduler based energy efficient multi-core system",
abstract = "Single-ISA heterogeneous multi-core processors can provide energy efficient performance by properly assigning workloads on two types of cores in a processor: high performance large cores and low power small cores. However, traditional process scheduling mechanism is hard to support an proper workload distribution due to an overhead of fine-grained state monitoring and scheduling. To overcome this problem, we propose Swarm Processor System which supports hardware implemented workload scheduling mechanism. In the proposed system, each core chooses a proper workload by using special hardware modules in the core instead of the scheduler of operating systems. We compare Swarm Processor System against the traditional mechanisms, and found that the proposed method shows the closest energy efficiency to the oracle case with providing stable performance.",
author = "Jeong, {Won Seob} and Kim, {Seung Hun} and Lee, {Sang Min} and Ro, {Won Woo}",
year = "2014",
month = "7",
day = "4",
doi = "10.1587/elex.11.20140424",
language = "English",
volume = "11",
journal = "IEICE Electronics Express",
issn = "1349-2543",
publisher = "The Institute of Electronics, Information and Communication Engineers (IEICE)",
number = "14",

}

Swarm processor system : Hardware process scheduler based energy efficient multi-core system. / Jeong, Won Seob; Kim, Seung Hun; Lee, Sang Min; Ro, Won Woo.

In: IEICE Electronics Express, Vol. 11, No. 14, 04.07.2014.

Research output: Contribution to journalLetter

TY - JOUR

T1 - Swarm processor system

T2 - Hardware process scheduler based energy efficient multi-core system

AU - Jeong, Won Seob

AU - Kim, Seung Hun

AU - Lee, Sang Min

AU - Ro, Won Woo

PY - 2014/7/4

Y1 - 2014/7/4

N2 - Single-ISA heterogeneous multi-core processors can provide energy efficient performance by properly assigning workloads on two types of cores in a processor: high performance large cores and low power small cores. However, traditional process scheduling mechanism is hard to support an proper workload distribution due to an overhead of fine-grained state monitoring and scheduling. To overcome this problem, we propose Swarm Processor System which supports hardware implemented workload scheduling mechanism. In the proposed system, each core chooses a proper workload by using special hardware modules in the core instead of the scheduler of operating systems. We compare Swarm Processor System against the traditional mechanisms, and found that the proposed method shows the closest energy efficiency to the oracle case with providing stable performance.

AB - Single-ISA heterogeneous multi-core processors can provide energy efficient performance by properly assigning workloads on two types of cores in a processor: high performance large cores and low power small cores. However, traditional process scheduling mechanism is hard to support an proper workload distribution due to an overhead of fine-grained state monitoring and scheduling. To overcome this problem, we propose Swarm Processor System which supports hardware implemented workload scheduling mechanism. In the proposed system, each core chooses a proper workload by using special hardware modules in the core instead of the scheduler of operating systems. We compare Swarm Processor System against the traditional mechanisms, and found that the proposed method shows the closest energy efficiency to the oracle case with providing stable performance.

UR - http://www.scopus.com/inward/record.url?scp=84904977985&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904977985&partnerID=8YFLogxK

U2 - 10.1587/elex.11.20140424

DO - 10.1587/elex.11.20140424

M3 - Letter

AN - SCOPUS:84904977985

VL - 11

JO - IEICE Electronics Express

JF - IEICE Electronics Express

SN - 1349-2543

IS - 14

ER -