Application-Specific Autonomic Cache Tuning for General Purpose GPUs

Sam Gianelli, Edward Richter, DIego Jimenez, Hugo Valdez, Tosiron Adegbija, Ali Akoglu

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

2 Citations (Scopus)

Abstract

Cache tuning has been widely studied in CPUs, and shown to achieve substantial energy savings, with minimal performance degradations. However, cache tuning has yet to be explored in General Purpose Graphics Processing Units (GPGPU), which have emerged as efficient alternatives for general purpose high-performance computing. In this paper, we explore autonomic cache tuning for GPGPUs, where the cache configurations (cache size, line size, and associativity) can be dynamically specialized/tuned to the executing applications' resource requirements. We investigate cache tuning for both the level one (L1) and level two (L2) caches to derive insights into which cache level offers maximum optimization benefits. To illustrate the optimization potentials of autonomic cache tuning in GPGPUs, we implement a tuning heuristic that can dynamically determine each application's best L1 data cache configurations during runtime. Our results show that application-specific autonomic L1 data cache tuning can reduce the average energy delay product (EDP) and improve the performance by 16.5% and 18.8%, respectively, as compared to a static cache.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages104-113
Number of pages10
ISBN (Electronic)9781538619391
DOIs
StatePublished - Oct 9 2017
Event4th IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017 - Tucson, United States
Duration: Sep 18 2017Sep 22 2017

Other

Other4th IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017
CountryUnited States
CityTucson
Period9/18/179/22/17

Fingerprint

Cache
Tuning
GPGPU
Graphics processing unit
Program processors
Energy conservation
Configuration
Associativity
Optimization
Degradation
Graphics Processing Unit
Energy Saving
High Performance
Heuristics
Resources
Computing
Line
Alternatives

Keywords

  • adaptable hardware
  • cache memories
  • cache tuning
  • configurable caches
  • GPGPU
  • GPU cache management
  • Graphics processing unit
  • high performance computing
  • low-power design
  • low-power embedded systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Control and Optimization

Cite this

Gianelli, S., Richter, E., Jimenez, DI., Valdez, H., Adegbija, T., & Akoglu, A. (2017). Application-Specific Autonomic Cache Tuning for General Purpose GPUs. In Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017 (pp. 104-113). [8064058] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCAC.2017.17

Application-Specific Autonomic Cache Tuning for General Purpose GPUs. / Gianelli, Sam; Richter, Edward; Jimenez, DIego; Valdez, Hugo; Adegbija, Tosiron; Akoglu, Ali.

Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 104-113 8064058.

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

Gianelli, S, Richter, E, Jimenez, DI, Valdez, H, Adegbija, T & Akoglu, A 2017, Application-Specific Autonomic Cache Tuning for General Purpose GPUs. in Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017., 8064058, Institute of Electrical and Electronics Engineers Inc., pp. 104-113, 4th IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017, Tucson, United States, 9/18/17. https://doi.org/10.1109/ICCAC.2017.17
Gianelli S, Richter E, Jimenez DI, Valdez H, Adegbija T, Akoglu A. Application-Specific Autonomic Cache Tuning for General Purpose GPUs. In Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 104-113. 8064058 https://doi.org/10.1109/ICCAC.2017.17
Gianelli, Sam ; Richter, Edward ; Jimenez, DIego ; Valdez, Hugo ; Adegbija, Tosiron ; Akoglu, Ali. / Application-Specific Autonomic Cache Tuning for General Purpose GPUs. Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 104-113
@inproceedings{ac74c45c061148f2af374aba382411ba,
title = "Application-Specific Autonomic Cache Tuning for General Purpose GPUs",
abstract = "Cache tuning has been widely studied in CPUs, and shown to achieve substantial energy savings, with minimal performance degradations. However, cache tuning has yet to be explored in General Purpose Graphics Processing Units (GPGPU), which have emerged as efficient alternatives for general purpose high-performance computing. In this paper, we explore autonomic cache tuning for GPGPUs, where the cache configurations (cache size, line size, and associativity) can be dynamically specialized/tuned to the executing applications' resource requirements. We investigate cache tuning for both the level one (L1) and level two (L2) caches to derive insights into which cache level offers maximum optimization benefits. To illustrate the optimization potentials of autonomic cache tuning in GPGPUs, we implement a tuning heuristic that can dynamically determine each application's best L1 data cache configurations during runtime. Our results show that application-specific autonomic L1 data cache tuning can reduce the average energy delay product (EDP) and improve the performance by 16.5{\%} and 18.8{\%}, respectively, as compared to a static cache.",
keywords = "adaptable hardware, cache memories, cache tuning, configurable caches, GPGPU, GPU cache management, Graphics processing unit, high performance computing, low-power design, low-power embedded systems",
author = "Sam Gianelli and Edward Richter and DIego Jimenez and Hugo Valdez and Tosiron Adegbija and Ali Akoglu",
year = "2017",
month = "10",
day = "9",
doi = "10.1109/ICCAC.2017.17",
language = "English (US)",
pages = "104--113",
booktitle = "Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Application-Specific Autonomic Cache Tuning for General Purpose GPUs

AU - Gianelli, Sam

AU - Richter, Edward

AU - Jimenez, DIego

AU - Valdez, Hugo

AU - Adegbija, Tosiron

AU - Akoglu, Ali

PY - 2017/10/9

Y1 - 2017/10/9

N2 - Cache tuning has been widely studied in CPUs, and shown to achieve substantial energy savings, with minimal performance degradations. However, cache tuning has yet to be explored in General Purpose Graphics Processing Units (GPGPU), which have emerged as efficient alternatives for general purpose high-performance computing. In this paper, we explore autonomic cache tuning for GPGPUs, where the cache configurations (cache size, line size, and associativity) can be dynamically specialized/tuned to the executing applications' resource requirements. We investigate cache tuning for both the level one (L1) and level two (L2) caches to derive insights into which cache level offers maximum optimization benefits. To illustrate the optimization potentials of autonomic cache tuning in GPGPUs, we implement a tuning heuristic that can dynamically determine each application's best L1 data cache configurations during runtime. Our results show that application-specific autonomic L1 data cache tuning can reduce the average energy delay product (EDP) and improve the performance by 16.5% and 18.8%, respectively, as compared to a static cache.

AB - Cache tuning has been widely studied in CPUs, and shown to achieve substantial energy savings, with minimal performance degradations. However, cache tuning has yet to be explored in General Purpose Graphics Processing Units (GPGPU), which have emerged as efficient alternatives for general purpose high-performance computing. In this paper, we explore autonomic cache tuning for GPGPUs, where the cache configurations (cache size, line size, and associativity) can be dynamically specialized/tuned to the executing applications' resource requirements. We investigate cache tuning for both the level one (L1) and level two (L2) caches to derive insights into which cache level offers maximum optimization benefits. To illustrate the optimization potentials of autonomic cache tuning in GPGPUs, we implement a tuning heuristic that can dynamically determine each application's best L1 data cache configurations during runtime. Our results show that application-specific autonomic L1 data cache tuning can reduce the average energy delay product (EDP) and improve the performance by 16.5% and 18.8%, respectively, as compared to a static cache.

KW - adaptable hardware

KW - cache memories

KW - cache tuning

KW - configurable caches

KW - GPGPU

KW - GPU cache management

KW - Graphics processing unit

KW - high performance computing

KW - low-power design

KW - low-power embedded systems

UR - http://www.scopus.com/inward/record.url?scp=85035325647&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035325647&partnerID=8YFLogxK

U2 - 10.1109/ICCAC.2017.17

DO - 10.1109/ICCAC.2017.17

M3 - Conference contribution

AN - SCOPUS:85035325647

SP - 104

EP - 113

BT - Proceedings - 2017 IEEE International Conference on Cloud and Autonomic Computing, ICCAC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -