EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture

Qiang Wang; Pengfei Xu; Yatao Zhang; Xiaowen Chu

doi:10.1145/3077839.3077858

EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture

Qiang Wang, Pengfei Xu, Yatao Zhang, Xiaowen Chu

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

11 Citations (Scopus)

Abstract

To address the ever-increasing demand for computing capacities, more and more heterogeneous systems have been designed to use both general-purpose and special-purpose processors. On the other hand, the huge energy consumption of these heterogeneous systems raises new environmental concerns and challenges. Besides performance, energy efficiency is now another key factor to be considered by system designers and also consumers. In this paper, we present a benchmark suite EPPMiner for evaluating the performance, power, and energy of different heterogeneous systems. EPPMiner consists of 16 benchmark programs that cover a broad range of application domains, and it shows a great variety in the intensity of utilizing the processors. We have implemented a prototype of EPPMiner that supports OpenMP, CUDA, and OpenCL, and demonstrated its usage by three showcases. Firstly, we use EPPMiner to compare the power efficiency of a set of processors, including two Intel x86 CPUs, two Nvidia GPUs, and one AMD GPU. Secondly, we investigate the impact of multi-threading on the power efficiency of multi-core CPUs. At last, we use EPPMiner to illustrate the effectiveness of GPU Dynamic Voltage and Frequency Scaling (DVFS) on the power efficiency of GPGPU applications. We show that DVFS can improve the energy efficiency by 86% over the default setting on an AMD GPU.

Original language	English
Title of host publication	e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems
Publisher	Association for Computing Machinery, Inc
Pages	23-33
Number of pages	11
ISBN (Electronic)	9781450350365
DOIs	https://doi.org/10.1145/3077839.3077858
Publication status	Published - 16 May 2017
Externally published	Yes
Event	8th ACM International Conference on Future Energy Systems, e-Energy 2017 - Shatin, Hong Kong Duration: 16 May 2017 → 19 May 2017

Publication series

Name	e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems

Conference

Conference	8th ACM International Conference on Future Energy Systems, e-Energy 2017
Country/Territory	Hong Kong
City	Shatin
Period	16/05/17 → 19/05/17

Bibliographical note

Publisher Copyright:
© 2017 Association for Computing Machinery.

Keywords

Benchmarks
Dynamic Voltage and Frequency Scaling
Graphics Processing Units
Performance Evaluation

UN SDGs

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

Access to Document

10.1145/3077839.3077858

Cite this

Wang, Q., Xu, P., Zhang, Y., & Chu, X. (2017). EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture. In e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems (pp. 23-33). (e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3077839.3077858

Wang, Qiang ; Xu, Pengfei ; Zhang, Yatao et al. / EPPMiner : An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture. e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems. Association for Computing Machinery, Inc, 2017. pp. 23-33 (e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems).

@inproceedings{099cebdc58ad42b8bb94dfe0b5f1d6d8,

title = "EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture",

abstract = "To address the ever-increasing demand for computing capacities, more and more heterogeneous systems have been designed to use both general-purpose and special-purpose processors. On the other hand, the huge energy consumption of these heterogeneous systems raises new environmental concerns and challenges. Besides performance, energy efficiency is now another key factor to be considered by system designers and also consumers. In this paper, we present a benchmark suite EPPMiner for evaluating the performance, power, and energy of different heterogeneous systems. EPPMiner consists of 16 benchmark programs that cover a broad range of application domains, and it shows a great variety in the intensity of utilizing the processors. We have implemented a prototype of EPPMiner that supports OpenMP, CUDA, and OpenCL, and demonstrated its usage by three showcases. Firstly, we use EPPMiner to compare the power efficiency of a set of processors, including two Intel x86 CPUs, two Nvidia GPUs, and one AMD GPU. Secondly, we investigate the impact of multi-threading on the power efficiency of multi-core CPUs. At last, we use EPPMiner to illustrate the effectiveness of GPU Dynamic Voltage and Frequency Scaling (DVFS) on the power efficiency of GPGPU applications. We show that DVFS can improve the energy efficiency by 86\% over the default setting on an AMD GPU.",

keywords = "Benchmarks, Dynamic Voltage and Frequency Scaling, Graphics Processing Units, Performance Evaluation",

author = "Qiang Wang and Pengfei Xu and Yatao Zhang and Xiaowen Chu",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 8th ACM International Conference on Future Energy Systems, e-Energy 2017 ; Conference date: 16-05-2017 Through 19-05-2017",

year = "2017",

month = may,

day = "16",

doi = "10.1145/3077839.3077858",

language = "English",

series = "e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems",

publisher = "Association for Computing Machinery, Inc",

pages = "23--33",

booktitle = "e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems",

}

Wang, Q, Xu, P, Zhang, Y & Chu, X 2017, EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture. in e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems. e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems, Association for Computing Machinery, Inc, pp. 23-33, 8th ACM International Conference on Future Energy Systems, e-Energy 2017, Shatin, Hong Kong, 16/05/17. https://doi.org/10.1145/3077839.3077858

EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture. / Wang, Qiang; Xu, Pengfei; Zhang, Yatao et al.
e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems. Association for Computing Machinery, Inc, 2017. p. 23-33 (e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - EPPMiner

T2 - 8th ACM International Conference on Future Energy Systems, e-Energy 2017

AU - Wang, Qiang

AU - Xu, Pengfei

AU - Zhang, Yatao

AU - Chu, Xiaowen

PY - 2017/5/16

Y1 - 2017/5/16

N2 - To address the ever-increasing demand for computing capacities, more and more heterogeneous systems have been designed to use both general-purpose and special-purpose processors. On the other hand, the huge energy consumption of these heterogeneous systems raises new environmental concerns and challenges. Besides performance, energy efficiency is now another key factor to be considered by system designers and also consumers. In this paper, we present a benchmark suite EPPMiner for evaluating the performance, power, and energy of different heterogeneous systems. EPPMiner consists of 16 benchmark programs that cover a broad range of application domains, and it shows a great variety in the intensity of utilizing the processors. We have implemented a prototype of EPPMiner that supports OpenMP, CUDA, and OpenCL, and demonstrated its usage by three showcases. Firstly, we use EPPMiner to compare the power efficiency of a set of processors, including two Intel x86 CPUs, two Nvidia GPUs, and one AMD GPU. Secondly, we investigate the impact of multi-threading on the power efficiency of multi-core CPUs. At last, we use EPPMiner to illustrate the effectiveness of GPU Dynamic Voltage and Frequency Scaling (DVFS) on the power efficiency of GPGPU applications. We show that DVFS can improve the energy efficiency by 86% over the default setting on an AMD GPU.

AB - To address the ever-increasing demand for computing capacities, more and more heterogeneous systems have been designed to use both general-purpose and special-purpose processors. On the other hand, the huge energy consumption of these heterogeneous systems raises new environmental concerns and challenges. Besides performance, energy efficiency is now another key factor to be considered by system designers and also consumers. In this paper, we present a benchmark suite EPPMiner for evaluating the performance, power, and energy of different heterogeneous systems. EPPMiner consists of 16 benchmark programs that cover a broad range of application domains, and it shows a great variety in the intensity of utilizing the processors. We have implemented a prototype of EPPMiner that supports OpenMP, CUDA, and OpenCL, and demonstrated its usage by three showcases. Firstly, we use EPPMiner to compare the power efficiency of a set of processors, including two Intel x86 CPUs, two Nvidia GPUs, and one AMD GPU. Secondly, we investigate the impact of multi-threading on the power efficiency of multi-core CPUs. At last, we use EPPMiner to illustrate the effectiveness of GPU Dynamic Voltage and Frequency Scaling (DVFS) on the power efficiency of GPGPU applications. We show that DVFS can improve the energy efficiency by 86% over the default setting on an AMD GPU.

KW - Benchmarks

KW - Dynamic Voltage and Frequency Scaling

KW - Graphics Processing Units

KW - Performance Evaluation

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000610411700003

U2 - 10.1145/3077839.3077858

DO - 10.1145/3077839.3077858

M3 - Conference Paper published in a book

T3 - e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems

SP - 23

EP - 33

BT - e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems

PB - Association for Computing Machinery, Inc

Y2 - 16 May 2017 through 19 May 2017

ER -

Wang Q, Xu P, Zhang Y, Chu X. EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture. In e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems. Association for Computing Machinery, Inc. 2017. p. 23-33. (e-Energy 2017 - Proceedings of the 8th International Conference on Future Energy Systems). doi: 10.1145/3077839.3077858

EPPMiner: An extended benchmark suite for energy, power and performance characterization of heterogeneous architecture

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this