Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms

Dhinakaran Pandiyan, Carole-Jean Wu

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

21 Citations (Scopus)

Abstract

In portable computing systems like smartphones, energy is generally a key but limited resource where application cores have been proven to consume a significant part of it. To understand the characteristics of the energy consumption, in this paper, we focus our attention on the portion of energy that is spent to move data to the application core's internal registers from the memory system. The primary motivation for this focus comes from the relatively higher energy cost associated with a data movement instruction compared to that of an arithmetic instruction. Another important factor is the distributive computing nature among different units in a SoC which leads to a higher data movement to/from the application cores. We perform a detailed investigation to quantify the impact of data movement on overall energy consumption of a popular, commercially-available smart phone device. To aid this study, we design micro-benchmarks that generate desired data movement patterns between different levels of the memory hierarchy and measure the instantaneous power consumed by the device when running these micro-benchmarks. We extensively make use of hardware performance counters to validate the micro-benchmarks and to characterize the energy consumed in moving data. We take a step further to utilize this calculated energy cost of data movement to characterize the portion of energy that an application spends in moving data for a wide range of popular smart phone workloads. We find that a considerable amount of total device energy is spent in data movement (an average of 35% of the total device energy). Our results also indicate a relatively high stalled cycle energy consumption (an average of 23.5%) for current smart phones. To our knowledge, this is the first study that quantifies the amount of data movement energy for emerging smart phone applications running on a recent, commercial smart phone device. We hope this characterization study and the insights developed in the paper can inspire innovative designs in smart phone architectures with improved performance and energy efficiency.

Original languageEnglish (US)
Title of host publicationIISWC 2014 - IEEE International Symposium on Workload Characterization
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages171-180
Number of pages10
ISBN (Print)9781479964536
DOIs
StatePublished - Dec 11 2014
Event2014 IEEE International Symposium on Workload Characterization, IISWC 2014 - Raleigh, United States
Duration: Oct 26 2014Oct 28 2014

Other

Other2014 IEEE International Symposium on Workload Characterization, IISWC 2014
CountryUnited States
CityRaleigh
Period10/26/1410/28/14

Fingerprint

Energy utilization
Costs
Data storage equipment
Smartphones
Energy efficiency
Hardware
System-on-chip

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Pandiyan, D., & Wu, C-J. (2014). Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms. In IISWC 2014 - IEEE International Symposium on Workload Characterization (pp. 171-180). [6983056] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IISWC.2014.6983056

Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms. / Pandiyan, Dhinakaran; Wu, Carole-Jean.

IISWC 2014 - IEEE International Symposium on Workload Characterization. Institute of Electrical and Electronics Engineers Inc., 2014. p. 171-180 6983056.

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

Pandiyan, D & Wu, C-J 2014, Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms. in IISWC 2014 - IEEE International Symposium on Workload Characterization., 6983056, Institute of Electrical and Electronics Engineers Inc., pp. 171-180, 2014 IEEE International Symposium on Workload Characterization, IISWC 2014, Raleigh, United States, 10/26/14. https://doi.org/10.1109/IISWC.2014.6983056
Pandiyan D, Wu C-J. Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms. In IISWC 2014 - IEEE International Symposium on Workload Characterization. Institute of Electrical and Electronics Engineers Inc. 2014. p. 171-180. 6983056 https://doi.org/10.1109/IISWC.2014.6983056
Pandiyan, Dhinakaran ; Wu, Carole-Jean. / Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms. IISWC 2014 - IEEE International Symposium on Workload Characterization. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 171-180
@inproceedings{d5b2c01aa5cc43229c3b6307c2fe4784,
title = "Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms",
abstract = "In portable computing systems like smartphones, energy is generally a key but limited resource where application cores have been proven to consume a significant part of it. To understand the characteristics of the energy consumption, in this paper, we focus our attention on the portion of energy that is spent to move data to the application core's internal registers from the memory system. The primary motivation for this focus comes from the relatively higher energy cost associated with a data movement instruction compared to that of an arithmetic instruction. Another important factor is the distributive computing nature among different units in a SoC which leads to a higher data movement to/from the application cores. We perform a detailed investigation to quantify the impact of data movement on overall energy consumption of a popular, commercially-available smart phone device. To aid this study, we design micro-benchmarks that generate desired data movement patterns between different levels of the memory hierarchy and measure the instantaneous power consumed by the device when running these micro-benchmarks. We extensively make use of hardware performance counters to validate the micro-benchmarks and to characterize the energy consumed in moving data. We take a step further to utilize this calculated energy cost of data movement to characterize the portion of energy that an application spends in moving data for a wide range of popular smart phone workloads. We find that a considerable amount of total device energy is spent in data movement (an average of 35{\%} of the total device energy). Our results also indicate a relatively high stalled cycle energy consumption (an average of 23.5{\%}) for current smart phones. To our knowledge, this is the first study that quantifies the amount of data movement energy for emerging smart phone applications running on a recent, commercial smart phone device. We hope this characterization study and the insights developed in the paper can inspire innovative designs in smart phone architectures with improved performance and energy efficiency.",
author = "Dhinakaran Pandiyan and Carole-Jean Wu",
year = "2014",
month = "12",
day = "11",
doi = "10.1109/IISWC.2014.6983056",
language = "English (US)",
isbn = "9781479964536",
pages = "171--180",
booktitle = "IISWC 2014 - IEEE International Symposium on Workload Characterization",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Quantifying the energy cost of data movement for emerging smart phone workloads on mobile platforms

AU - Pandiyan, Dhinakaran

AU - Wu, Carole-Jean

PY - 2014/12/11

Y1 - 2014/12/11

N2 - In portable computing systems like smartphones, energy is generally a key but limited resource where application cores have been proven to consume a significant part of it. To understand the characteristics of the energy consumption, in this paper, we focus our attention on the portion of energy that is spent to move data to the application core's internal registers from the memory system. The primary motivation for this focus comes from the relatively higher energy cost associated with a data movement instruction compared to that of an arithmetic instruction. Another important factor is the distributive computing nature among different units in a SoC which leads to a higher data movement to/from the application cores. We perform a detailed investigation to quantify the impact of data movement on overall energy consumption of a popular, commercially-available smart phone device. To aid this study, we design micro-benchmarks that generate desired data movement patterns between different levels of the memory hierarchy and measure the instantaneous power consumed by the device when running these micro-benchmarks. We extensively make use of hardware performance counters to validate the micro-benchmarks and to characterize the energy consumed in moving data. We take a step further to utilize this calculated energy cost of data movement to characterize the portion of energy that an application spends in moving data for a wide range of popular smart phone workloads. We find that a considerable amount of total device energy is spent in data movement (an average of 35% of the total device energy). Our results also indicate a relatively high stalled cycle energy consumption (an average of 23.5%) for current smart phones. To our knowledge, this is the first study that quantifies the amount of data movement energy for emerging smart phone applications running on a recent, commercial smart phone device. We hope this characterization study and the insights developed in the paper can inspire innovative designs in smart phone architectures with improved performance and energy efficiency.

AB - In portable computing systems like smartphones, energy is generally a key but limited resource where application cores have been proven to consume a significant part of it. To understand the characteristics of the energy consumption, in this paper, we focus our attention on the portion of energy that is spent to move data to the application core's internal registers from the memory system. The primary motivation for this focus comes from the relatively higher energy cost associated with a data movement instruction compared to that of an arithmetic instruction. Another important factor is the distributive computing nature among different units in a SoC which leads to a higher data movement to/from the application cores. We perform a detailed investigation to quantify the impact of data movement on overall energy consumption of a popular, commercially-available smart phone device. To aid this study, we design micro-benchmarks that generate desired data movement patterns between different levels of the memory hierarchy and measure the instantaneous power consumed by the device when running these micro-benchmarks. We extensively make use of hardware performance counters to validate the micro-benchmarks and to characterize the energy consumed in moving data. We take a step further to utilize this calculated energy cost of data movement to characterize the portion of energy that an application spends in moving data for a wide range of popular smart phone workloads. We find that a considerable amount of total device energy is spent in data movement (an average of 35% of the total device energy). Our results also indicate a relatively high stalled cycle energy consumption (an average of 23.5%) for current smart phones. To our knowledge, this is the first study that quantifies the amount of data movement energy for emerging smart phone applications running on a recent, commercial smart phone device. We hope this characterization study and the insights developed in the paper can inspire innovative designs in smart phone architectures with improved performance and energy efficiency.

UR - http://www.scopus.com/inward/record.url?scp=84946053198&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946053198&partnerID=8YFLogxK

U2 - 10.1109/IISWC.2014.6983056

DO - 10.1109/IISWC.2014.6983056

M3 - Conference contribution

AN - SCOPUS:84946053198

SN - 9781479964536

SP - 171

EP - 180

BT - IISWC 2014 - IEEE International Symposium on Workload Characterization

PB - Institute of Electrical and Electronics Engineers Inc.

ER -