Impact of Thread and Frequency Scaling on Performance and Energy Efficiency: An Evaluation of Core i7-8700K Using SPEC CPU2017

This paper describes the results of measurement based studies focusing on performance and energy efficiency of SPEC CPU2017 speed and rate benchmark runs on the Intel’s Core i7-S700K processor. We measure execution time and the total energy consumed during individual benchmark runs with 1 thread/copy (IT/IC) and 6 threads/copies (6T/6C) when the processor clock is set to its nominal frequency of 3.7 GHz. Next, we evaluate how changes in the processor clock frequency impact performance, energy efficiency, as well as a composite metric called PE that captures both performance and energy efficiency. We find that IT/IC benchmark runs at the nominal frequency achieve an optimal PE, whereas 6T/6C benchmark runs achieve optimal PE when running at 2.7 GHz.

[1]  Thomas Ilsche,et al.  An Energy Efficiency Feature Survey of the Intel Haswell Processor , 2015, 2015 IEEE International Parallel and Distributed Processing Symposium Workshop.

[2]  Michael L. Scott,et al.  Energy-efficient processor design using multiple clock domains with dynamic voltage and frequency scaling , 2002, Proceedings Eighth International Symposium on High Performance Computer Architecture.

[3]  Xi Yang,et al.  Looking back on the language and hardware revolutions: measured power, performance, and scaling , 2011, ASPLOS XVI.

[4]  Aleksandar Milenkovic,et al.  SPEC CPU2017: Performance, Event, and Energy Characterization on the Core i7-8700K , 2019, ICPE.

[5]  Gernot Heiser,et al.  Dynamic voltage and frequency scaling: the laws of diminishing returns , 2010 .

[6]  Aleksandar Milenkovic,et al.  Impact of thread and frequency scaling on performance and energy in modern multicores: a measurement-based study , 2014, ACM Southeast Regional Conference.

[7]  Huazhe Zhang,et al.  A Quantitative Evaluation of the RAPL Power Control System , 2014 .

[8]  Shirley Moore,et al.  Measuring Energy and Power with PAPI , 2012, 2012 41st International Conference on Parallel Processing Workshops.

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

[10]  Jóakim von Kistowski,et al.  SPEC CPU2017: Next-Generation Compute Benchmark , 2018, ICPE Companion.