Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems

S McIntosh-Smith; T Wilson; A Ávila Ibarra; J Crisp; RB Sessions

doi:10.1093/comjnl/bxr091

Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems

S McIntosh-Smith
, T Wilson
, A Ávila Ibarra
, J Crisp
, RB Sessions

Research output: Contribution to journal › Article (Academic Journal) › peer-review

28 Citations (Scopus)

5 Downloads (Pure)

Abstract

With the advent of heterogeneous computing systems consisting of multi-core central processing units (CPUs) and many-core graphics processing units (GPUs), robust methods are needed to facilitate fair benchmark comparisons between different systems. In this paper, we present a benchmarking methodology for measuring a number of performance metrics for heterogeneous systems. Methods for comparing performance and energy efficiency are included. Consideration is given to further metrics, such as associated running costs and carbon emissions. We give a case study for these metrics applied to Bristol University Docking engine, a molecular mechanics-based docking application that has been ported to open computing language at the University of Bristol. Results are included for both AMD and NVIDIA GPUs, and for a highly optimized code on the latest x86 CPUs.

Translated title of the contribution	Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems
Original language	English
Pages (from-to)	192 - 205
Number of pages	14
Journal	The Computer Journal
Volume	55
Issue number	2
DOIs	https://doi.org/10.1093/comjnl/bxr091
Publication status	Published - Feb 2012

Bibliographical note

Other: 4*

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access to Document

10.1093/comjnl/bxr091

Handle.net

Persistent link

HPC (High Performance Computing) and HTC (High Throughput Computing) Facilities
Alam, S. R. (Manager), Williams, D. A. G. (Manager), Eccleston, P. E. (Manager) & Greene, D. (Manager)
Facility/equipment: Facility

Cite this

@article{049c47910bd741668d186e855898b3f4,

title = "Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems",

abstract = "With the advent of heterogeneous computing systems consisting of multi-core central processing units (CPUs) and many-core graphics processing units (GPUs), robust methods are needed to facilitate fair benchmark comparisons between different systems. In this paper, we present a benchmarking methodology for measuring a number of performance metrics for heterogeneous systems. Methods for comparing performance and energy efficiency are included. Consideration is given to further metrics, such as associated running costs and carbon emissions. We give a case study for these metrics applied to Bristol University Docking engine, a molecular mechanics-based docking application that has been ported to open computing language at the University of Bristol. Results are included for both AMD and NVIDIA GPUs, and for a highly optimized code on the latest x86 CPUs.",

author = "S McIntosh-Smith and T Wilson and \{{\'A}vila Ibarra\}, A and J Crisp and RB Sessions",

note = "Other: 4*",

year = "2012",

month = feb,

doi = "10.1093/comjnl/bxr091",

language = "English",

volume = "55",

pages = "192 -- 205",

journal = "The Computer Journal",

issn = "1460-2067",

publisher = "Oxford University Press",

number = "2",

}

TY - JOUR

T1 - Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems

AU - McIntosh-Smith, S

AU - Wilson, T

AU - Ávila Ibarra, A

AU - Crisp, J

AU - Sessions, RB

N1 - Other: 4*

PY - 2012/2

Y1 - 2012/2

N2 - With the advent of heterogeneous computing systems consisting of multi-core central processing units (CPUs) and many-core graphics processing units (GPUs), robust methods are needed to facilitate fair benchmark comparisons between different systems. In this paper, we present a benchmarking methodology for measuring a number of performance metrics for heterogeneous systems. Methods for comparing performance and energy efficiency are included. Consideration is given to further metrics, such as associated running costs and carbon emissions. We give a case study for these metrics applied to Bristol University Docking engine, a molecular mechanics-based docking application that has been ported to open computing language at the University of Bristol. Results are included for both AMD and NVIDIA GPUs, and for a highly optimized code on the latest x86 CPUs.

AB - With the advent of heterogeneous computing systems consisting of multi-core central processing units (CPUs) and many-core graphics processing units (GPUs), robust methods are needed to facilitate fair benchmark comparisons between different systems. In this paper, we present a benchmarking methodology for measuring a number of performance metrics for heterogeneous systems. Methods for comparing performance and energy efficiency are included. Consideration is given to further metrics, such as associated running costs and carbon emissions. We give a case study for these metrics applied to Bristol University Docking engine, a molecular mechanics-based docking application that has been ported to open computing language at the University of Bristol. Results are included for both AMD and NVIDIA GPUs, and for a highly optimized code on the latest x86 CPUs.

U2 - 10.1093/comjnl/bxr091

DO - 10.1093/comjnl/bxr091

M3 - Article (Academic Journal)

SN - 1460-2067

VL - 55

SP - 192

EP - 205

JO - The Computer Journal

JF - The Computer Journal

IS - 2

ER -

Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems

Abstract

Bibliographical note

UN SDGs

Access to Document

Handle.net

Fingerprint

Equipment

HPC (High Performance Computing) and HTC (High Throughput Computing) Facilities

Cite this