Performance and energy metrics for multi-threaded applications on DVFS processors

Abstract Due to their internal execution characteristics, application programs exploit the hardware very differently, which leads to a quite diverse behavior concerning their performance or the energy consumed for their execution. A change of the operational frequency of DVFS processors leads to further variations in performance and energy consumption, as does the exploitation of thread parallelism on multicores. This article combines frequency scaling and thread-parallelism and considers several new metrics for the evaluation of an application's performance and energy consumption. As application programs, the PARSEC benchmark suite and the SPLASH-2 benchmark suite are investigated. The PARSEC benchmark suite provides an up-to-date collection of applications with different workloads on chip-multiprocessors. The SPLASH-2 is a common suite for scientific studies on parallel shared memory machines. Intel Core i7 processors are used as hardware platforms for the evaluation.

[1]  Dong Li,et al.  PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications , 2010, IEEE Transactions on Parallel and Distributed Systems.

[2]  Rong Ge,et al.  Power-Aware Speedup , 2007, 2007 IEEE International Parallel and Distributed Processing Symposium.

[3]  Anoop Gupta,et al.  The SPLASH-2 programs: characterization and methodological considerations , 1995, ISCA.

[4]  Karthikeyan Sankaralingam,et al.  Power challenges may end the multicore era , 2013, CACM.

[5]  Eric Saxe,et al.  Power-efficient software , 2010, Commun. ACM.

[6]  Efraim Rotem,et al.  Power-Management Architecture of the Intel Microarchitecture Code-Named Sandy Bridge , 2012, IEEE Micro.

[7]  Alan D. George,et al.  RapidIO for radar processing in advanced space systems , 2007, TECS.

[8]  Simon W. Moore,et al.  A communication characterisation of Splash-2 and Parsec , 2009, 2009 IEEE International Symposium on Workload Characterization (IISWC).

[9]  Leon Atkins,et al.  Algorithms for power savings , 2014 .

[10]  Gerhard Wellein,et al.  LIKWID: A Lightweight Performance-Oriented Tool Suite for x86 Multicore Environments , 2010, 2010 39th International Conference on Parallel Processing Workshops.

[11]  Wu-chun Feng,et al.  Towards efficient supercomputing: a quest for the right metric , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[12]  Rajesh K. Gupta,et al.  Leakage aware dynamic voltage scaling for real-time embedded systems , 2004, Proceedings. 41st Design Automation Conference, 2004..

[13]  Keqin Li,et al.  Performance Analysis of Power-Aware Task Scheduling Algorithms on Multiprocessor Computers with Dynamic Voltage and Speed , 2008, IEEE Transactions on Parallel and Distributed Systems.

[14]  G. Sohi,et al.  A static power model for architects , 2000, Proceedings 33rd Annual IEEE/ACM International Symposium on Microarchitecture. MICRO-33 2000.

[15]  Manuel Prieto,et al.  Maximizing Power Efficiency with Asymmetric Multicore Systems , 2009, ACM Queue.

[16]  Gurindar S. Sohi,et al.  Adaptive, efficient, parallel execution of parallel programs , 2014, PLDI.

[17]  Thomas Rauber,et al.  Parallel Programming: for Multicore and Cluster Systems , 2010, Parallel Programming, 3rd Ed..

[18]  Mark Horowitz,et al.  Energy dissipation in general purpose microprocessors , 1996, IEEE J. Solid State Circuits.

[19]  Kai Li,et al.  PARSEC vs. SPLASH-2: A quantitative comparison of two multithreaded benchmark suites on Chip-Multiprocessors , 2008, 2008 IEEE International Symposium on Workload Characterization.

[20]  Cacm Staff,et al.  A conversation with David E. Shaw , 2009 .

[21]  Lasse Natvig,et al.  Performance and energy impact of parallelization and vectorization techniques in modern microprocessors , 2013, Computing.

[22]  Marek Chrobak,et al.  Algorithmic Aspects of Energy-Efficient Computing , 2012, Handbook of Energy-Aware and Green Computing.

[23]  Qijun Gu,et al.  Using the Greenup, Powerup, and Speedup metrics to evaluate software energy efficiency , 2015, 2015 Sixth International Green and Sustainable Computing Conference (IGSC).

[24]  Michael Schwind,et al.  Energy measurement and prediction for multi-threaded programs , 2014, SpringSim.

[25]  Richard W. Vuduc,et al.  Algorithmic Time, Energy, and Power on Candidate HPC Compute Building Blocks , 2014, 2014 IEEE 28th International Parallel and Distributed Processing Symposium.

[26]  Michael Schwind,et al.  Energy measurement, modeling, and prediction for processors with frequency scaling , 2014, The Journal of Supercomputing.

[27]  Jose Renau,et al.  Analysis of PARSEC workload scalability , 2016, 2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).

[28]  Z. Huang,et al.  Metrics and task scheduling policies for energy saving in multicore computers , 2010, 2010 11th IEEE/ACM International Conference on Grid Computing.

[29]  Chaitali Chakrabarti,et al.  Energy-efficient dynamic task scheduling algorithms for DVS systems , 2008, TECS.

[30]  Thomas Rauber,et al.  Modeling and analyzing the energy consumption of fork‐join‐based task parallel programs , 2015, Concurr. Comput. Pract. Exp..

[31]  Magnus Jahre,et al.  Optimized hardware for suboptimal software: The case for SIMD-aware benchmarks , 2014, 2014 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).

[32]  Kai Li,et al.  The PARSEC benchmark suite: Characterization and architectural implications , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).