Investigating power capping toward energy-efficient scientific applications: Investigating Power Capping toward Energy-Efficient Scientific Applications
Abstract
The emergence of power efficiency as a primary constraint in processor and system design poses new challenges concerning power and energy awareness for numerical libraries and scientific applications. Power consumption also plays a major role in the design of data centers, which may house petascale or exascale-level computing systems. At these extreme scales, understanding and improving the energy efficiency of numerical libraries and their related applications becomes a crucial part of the successful implementation and operation of the computing system. In this paper, we study and investigate the practice of controlling a compute system's power usage, and we explore how different power caps affect the performance of numerical algorithms with different computational intensities. Further, we determine the impact, in terms of performance and energy usage, that these caps have on a system running scientific applications. This analysis will enable us to characterize the types of algorithms that benefit most from these power management schemes. Our experiments are performed using a set of representative kernels and several popular scientific benchmarks. Lastly, we quantify a number of power and performance measurements and draw observations and conclusions that can be viewed as a roadmap to achieving energy efficiency in the design and executionmore »
- Authors:
-
- Univ. of Tennessee, Knoxville, TN (United States). Innovative Computing Lab
- Univ. of Tennessee, Knoxville, TN (United States). Innovative Computing Lab ; Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Manchester (United Kingdom)
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC)
- OSTI Identifier:
- 1435180
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Concurrency and Computation. Practice and Experience
- Additional Journal Information:
- Journal Volume: 31; Journal Issue: 6; Journal ID: ISSN 1532-0626
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; energy efficiency; high performance computing; Intel Xeon Phi; Knights landing PAPI; performance analysis; performance counters; power efficiency
Citation Formats
Haidar, Azzam, Jagode, Heike, Vaccaro, Phil, YarKhan, Asim, Tomov, Stanimire, and Dongarra, Jack. Investigating power capping toward energy-efficient scientific applications: Investigating Power Capping toward Energy-Efficient Scientific Applications. United States: N. p., 2018.
Web. doi:10.1002/cpe.4485.
Haidar, Azzam, Jagode, Heike, Vaccaro, Phil, YarKhan, Asim, Tomov, Stanimire, & Dongarra, Jack. Investigating power capping toward energy-efficient scientific applications: Investigating Power Capping toward Energy-Efficient Scientific Applications. United States. https://doi.org/10.1002/cpe.4485
Haidar, Azzam, Jagode, Heike, Vaccaro, Phil, YarKhan, Asim, Tomov, Stanimire, and Dongarra, Jack. Sun .
"Investigating power capping toward energy-efficient scientific applications: Investigating Power Capping toward Energy-Efficient Scientific Applications". United States. https://doi.org/10.1002/cpe.4485. https://www.osti.gov/servlets/purl/1435180.
@article{osti_1435180,
title = {Investigating power capping toward energy-efficient scientific applications: Investigating Power Capping toward Energy-Efficient Scientific Applications},
author = {Haidar, Azzam and Jagode, Heike and Vaccaro, Phil and YarKhan, Asim and Tomov, Stanimire and Dongarra, Jack},
abstractNote = {The emergence of power efficiency as a primary constraint in processor and system design poses new challenges concerning power and energy awareness for numerical libraries and scientific applications. Power consumption also plays a major role in the design of data centers, which may house petascale or exascale-level computing systems. At these extreme scales, understanding and improving the energy efficiency of numerical libraries and their related applications becomes a crucial part of the successful implementation and operation of the computing system. In this paper, we study and investigate the practice of controlling a compute system's power usage, and we explore how different power caps affect the performance of numerical algorithms with different computational intensities. Further, we determine the impact, in terms of performance and energy usage, that these caps have on a system running scientific applications. This analysis will enable us to characterize the types of algorithms that benefit most from these power management schemes. Our experiments are performed using a set of representative kernels and several popular scientific benchmarks. Lastly, we quantify a number of power and performance measurements and draw observations and conclusions that can be viewed as a roadmap to achieving energy efficiency in the design and execution of scientific algorithms.},
doi = {10.1002/cpe.4485},
journal = {Concurrency and Computation. Practice and Experience},
number = 6,
volume = 31,
place = {United States},
year = {2018},
month = {3}
}
Web of Science
Works referenced in this record:
PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications
journal, May 2010
- Ge, Rong; Feng, Xizhou; Song, Shuaiwen
- IEEE Transactions on Parallel and Distributed Systems, Vol. 21, Issue 5
Improving Energy Efficiency in Memory-constrained Applications Using Core-specific Power Control
conference, January 2017
- Bhalachandra, Sridutt; Porterfield, Allan; Olivier, Stephen L.
- Proceedings of the 5th International Workshop on Energy Efficient Supercomputing - E2SC'17
The Tau Parallel Performance System
journal, May 2006
- Shende, Sameer S.; Malony, Allen D.
- The International Journal of High Performance Computing Applications, Vol. 20, Issue 2
Run-Time Exploitation of Application Dynamism for Energy-Efficient Exascale Computing (READEX)
conference, October 2015
- Oleynik, Yury; Gerndt, Michael; Schuchart, Joseph
- 2015 IEEE 18th International Conference on Computational Science and Engineering (CSE)
SPEC CPU2006 benchmark descriptions
journal, September 2006
- Henning, John L.
- ACM SIGARCH Computer Architecture News, Vol. 34, Issue 4
Maximizing Performance Under a Power Cap: A Comparison of Hardware, Software, and Hybrid Techniques
journal, June 2016
- Zhang, Huazhe; Hoffmann, Henry
- ACM SIGPLAN Notices, Vol. 51, Issue 4
High-performance conjugate-gradient benchmark: A new metric for ranking high-performance computing systems
journal, August 2015
- Dongarra, Jack; Heroux, Michael A.; Luszczek, Piotr
- The International Journal of High Performance Computing Applications, Vol. 30, Issue 1
Maximizing Performance Under a Power Cap: A Comparison of Hardware, Software, and Hybrid Techniques
conference, January 2016
- Zhang, Huazhe; Hoffmann, Henry
- Proceedings of the Twenty-First International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '16
Power-Management Architecture of the Intel Microarchitecture Code-Named Sandy Bridge
journal, March 2012
- Rotem, Efraim; Naveh, Alon; Ananthakrishnan, Avinash
- IEEE Micro, Vol. 32, Issue 2
Adagio: making DVS practical for complex HPC applications
conference, January 2009
- Rountree, Barry; Lownenthal, David K.; de Supinski, Bronis R.
- Proceedings of the 23rd international conference on Conference on Supercomputing - ICS '09
Emprical study on Reducing Energy of Parallel Programs using Slack Reclamation by DVFS in a Power-scalable High Performance Cluster
conference, September 2006
- Kimura, Hideaki; Sato, Mitsuhisa; Hotta, Yoshihiko
- 2006 IEEE International Conference on Cluster Computing
Power monitoring with PAPI for extreme scale architectures and dataflow-based programming models
conference, September 2014
- McCraw, Heike; Ralph, James; Danalis, Anthony
- 2014 IEEE International Conference On Cluster Computing (CLUSTER)
The READEX formalism for automatic tuning for energy efficiency
journal, January 2017
- Schuchart, Joseph; Gerndt, Michael; Kjeldsberg, Per Gunnar
- Computing, Vol. 99, Issue 8
PerfExpert: An Easy-to-Use Performance Diagnosis Tool for HPC Applications
conference, November 2010
- Burtscher, Martin; Kim, Byoung-Do; Diamond, Jeff
- 2010 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis
Application Runtime Variability and Power Optimization for Exascale Computers
conference, January 2015
- Porterfield, Allan; Fowler, Rob; Bhalachandra, Sridutt
- Proceedings of the 5th International Workshop on Runtime and Operating Systems for Supercomputers - ROSS '15
Parallel Performance Measurement of Heterogeneous Parallel Systems with GPUs
conference, September 2011
- Malony, Allen D.; Biersdorff, Scott; Shende, Sameer
- 2011 International Conference on Parallel Processing (ICPP)
PAPI-V: Performance Monitoring for Virtual Machines
conference, September 2012
- Johnson, Matthew; McCraw, Heike; Moore, Shirley
- 2012 41st International Conference on Parallel Processing Workshops (ICPPW)
HPCTOOLKIT: tools for performance analysis of optimized parallel programs
journal, January 2009
- Adhianto, L.; Banerjee, S.; Fagan, M.
- Concurrency and Computation: Practice and Experience
The Scalasca performance toolset architecture
journal, January 2010
- Geimer, Markus; Wolf, Felix; Wylie, Brian J. N.
- Concurrency and Computation: Practice and Experience
Maximizing Performance Under a Power Cap: A Comparison of Hardware, Software, and Hybrid Techniques
journal, March 2016
- Zhang, Huazhe; Hoffmann, Henry
- ACM SIGOPS Operating Systems Review, Vol. 50, Issue 2
Works referencing / citing this record:
Power-aware computing: Power-aware computing
journal, November 2018
- Ezzatti, Pablo; Quintana-Ortí, Enrique S.; Remón, Alfredo
- Concurrency and Computation: Practice and Experience, Vol. 31, Issue 6
Energy-Aware High-Performance Computing: Survey of State-of-the-Art Tools, Techniques, and Environments
journal, April 2019
- Czarnul, Pawel; Proficz, Jerzy; Krzywaniak, Adam
- Scientific Programming, Vol. 2019
Investigating power efficiency of mergesort
journal, April 2019
- Aljabri, Naif; Al-Hashimi, Muhammad; Saleh, Mostafa
- The Journal of Supercomputing, Vol. 75, Issue 10