Power draw is a complex physical response to the workload of a given application on the hardware, which is difficult to model, in part, due to its variability. The empirical mode decomposition and Hilbert–Huang transform (EMD/HHT) is a method commonly applied to physical systems varying with time to analyze their complex behavior. In authors’ work, the EMD/HHT is considered for the first time to study power usage of high-performance applications. Here, this method is applied to the power measurement sequences (called here power traces) collected on three different computing platforms featuring two generations of Intel Xeon Phi, which are an attractive solution under the power budget constraints. The high-performance applications explored in this work are codesign molecular synamics and general atomic and molecular electronic structure system—which exhibit different power draw characteristics—to showcase strengths and limitations of the EMD/HHT analysis. Specifically, EMD/HHT measures intensity of an execution, which shows the concentration of power draw with respect to execution time and provides insights into performance bottlenecks. This article compares intensity among executions, noting on a relationship between intensity and execution characteristics, such as computation amount and data movement. In general, this article concludes that the EMD/HHT method is a viable tool to compare application power usage and performance over the entire execution and that it has much potential in selecting most appropriate execution configurations.
AbdurachmanovDBockelmanBElmerP, et al. (2014) Heterogeneous high throughput scientific computing with APM X-Gene and Intel Xeon Phi. CoRR abs/1410.3441 (2014). Available at:http://arxiv.org/abs/1410.3441 (accessed 7 August 2016).
2.
ApràEKlemmMKowalskiK (2014) Efficient implementation of many-body quantum chemical methods on the intel® Xeon Phi™ coprocessor. In: Proceedings of the international conference for high performance computing, networking, storage and analysis (SC ‘14), New Orleans, LA, USA, 16–21 November 2014, pp. 674–684. IEEE Press, Piscataway, NJ, USA. DOI: 10.1109/SC.2014.60.
3.
BernaschiMSalvadoreF (2014) Multi-Kepler GPU vs. multi-intel MIC: a two test case performance study. In: 2014 International conference on high performance computing simulation (HPCS), Bologna, Italy, pp. 1–8. IEEEDOI: 10.1109/HPCSim. 2014.6903662.
4.
BernaschiMBissonMSalvadoreF (2014) Multi-Kepler GPU vs. multi-Intel MIC for spin systems simulations. Computer Physics Communications185(10): 2495–2503. DOI: 10.1016/j.cpc.2014.05.026
5.
BrownWCarrilloJGavhaneN, et al. (2015) Optimizing legacy molecular dynamics software with directive-based offload. Computer Physics Communications195: 95–101. DOI: 10.1016/j.cpc.2015.05.004
6.
ChoiJMukhanMLiuX, et al. (2014) Algorithmic time, energy, and power on candidate HPC compute building blocks. In: 2014 IEEE 28th international symposium on parallel distributed processing (IPDPS). Phoenix, Arizona, USA. IEEE.
EzerTCorlettW (2012) Is sea level rise accelerating in the Chesapeake Bay? A demonstration of a novel new approach for analyzing sea level data. Geophysical Research Letters39(19). DOI: 10.1029/2012GL053435.
11.
EzerTAtkinsonLPCorlettWB, et al. (2013) Gulf Stream’s induced sea level rise and variability along the U.S. mid-Atlantic coast. Journal of Geophysical Research: Oceans118(2): 685–697. DOI: 10.1002/jgrc.20091
12.
GordonMSSchmidtMW (2005) Advances in Electronic Structure Theory: GAMESS a Decade Later. In: DykstraCEFrenkingGKimKSScuseriaGE (ed) Theory and Applications of Computational Chemistry:the first forty years, pp. 1167–1189.
13.
HeineckeAVaidyanathanKSmelyanskiyM, et al. (2013) Design and implementation of the linpack benchmark for single and multi-node systems based on intel xeon phi coprocessor. In: 2013 IEEE 27th international symposium on parallel distributed processing (IPDPS), Boston, MA, USA, pp. 126–137. IEEE.
14.
HöhnerbachMIsmailAEBientinesiP (2016) The Vectorization of the Tersoff Multi-Body Potential: An Exercise in Performance Portability. ArXiv e-prints (July2016). abs/1607.02904.
15.
HuangNShenZLongS, et al. (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc A: Math Phy Eng Sci454(1971): 903–995. DOI: 10.1098/rspa.1998.0193
JundtATiwariAWardWJr, et al. (2015) Optimizing Codes on the Xeon Phi: A Case-study with LAMMPS. In: Proceedings of the 2015 XSEDE conference: scientific advancements enabled by enhanced cyberinfrastructure (XSEDE ‘15). ACM, New York, NY, USA, Article 28, p. 2. DOI: 10.1145/2792745.2792773.
19.
KrishnaiyerRKultursayEChawlaP, et al. (2013) Compiler-based data prefetching and streaming non-temporal store generation for the Intel Xeon Phi coprocessor. In: 2013 IEEE 27th International Symposium on Parallel Distributed Processing (IPDPS), Boston, MA, USA, pp. 1575–1586. IEEE.
LaiCHaoZHuangM, et al. (2014) Comparison of parallel programming models on intel mic computer cluster. In: 2014 IEEE international parallel distributed processing symposium workshops (IPDPSW), Phoenix, AZ, USA, pp. 925–932. DOI: 10.1109/IPDPSW.2014.105. IEEE.
22.
LaKomskiDZongZJinT, et al. (2015) Optimal balance between energy and performance in hybrid computing applications. In: 2015 Sixth international green computing conference and sustainable computing conference (IGSC), Las Vegas, NV, USA, p. 1–8. DOI: 10.1109/IGCC.2015.7393697.
23.
LarosJ (2016) Sandia national laboratories high performance computing power application programming interface (API) specification. (2016). Available at:http://powerapi.sandia.gov/. (accessed 7 August 2016).
24.
LawsonGSosonkinaMShenY (2014) Performance and energy evaluation of CoMD on Intel Xeon Phi co-processors. In: Proceedings of the 1st international workshop on hardware-software co-design for high performance computing (Co-HPC ‘14), New Orleans, LA, USA, Piscataway, NJ, USA: pp. 49–54. DOI: 10.1109/Co-HPC.2014.12.
25.
LawsonGSosonkinaMEzerT, et al. (2017) Empirical mode decomposition for modeling of parallel applications on intel xeon phi processors. In: 2nd International Workshop on Theoretical Approaches to Performance Evaluation, Modeling and Simulation (TAPEMS). Madrid, Spain, 18 September 2017, pp. 1000–1008. IEEE.
26.
LawsonGSundriyalVSosonkinaM, et al. (2015) Modeling performance and energy for applications offloaded to Intel Xeon Phi. In: Proceedings of the 2nd international workshop on hardware-software co-design for high performance computing (Co-HPC ‘15). Austin, TX, USA, ACM, New York, NY, USA, Article 7, 7:1–7:8. DOI: 10.1145/28348 99.2834903.
27.
LawsonGSundriyalVSosonkinaM, et al. (2016) Runtime power limiting of parallel applications on Intel Xeon Phi processors. In: Proceedings of the 4th International Workshop on Energy Efficient Supercomputing (E2SC ‘16), Salt Lake City, UT, USA, pp. 39–45. IEEE Press, Piscataway, NJ, USA. DOI: 10.1109/E2SC. 2016.9.
28.
LiBChangHCSongS, et al. (2014) The power-performance tradeoffs of the Intel Xeon Phi on HPC applications. In: 2014 IEEE international parallel distributed processing symposium workshops (IPDPSW), Phoenix, AZ, USA, pp. 1448–1456. DOI: 10.1109/IPDPSW. 2014.162. ACM.
LiuXPengSYangC, et al. (2015) mAMBER: Accelerating Explicit Solvent Molecular Dynamic with Intel Xeon Phi Many-Integrated Core Coprocessors. In: 2015 15th IEEE/ACM international symposium on cluster, cloud and grid computing (CCGrid), Shenzhen, China, pp. 729–732. DOI: 10.1109/CCGrid.2015.66. IEEE.
31.
LopezMGYoungJMeredithJS, et al. (2015) Examining recent many-core architectures and programming models using SHOC. In: Proceedings of the 6th international workshop on performance modeling, benchmarking, and simulation of high performance computing systems (PMBS ‘15). Austin, TX, USA, ACM, New York, NY, USA, Article 3, p. 12. DOI: 10.1145/2832087.2832090.
32.
LuoMLiMVenkateshA, et al. (2013) UPC on MIC: Early experiences with native and symmetric modes. In: Proceedings of the 7th international conference on PGAS programming models (2013). Ohio State University.
33.
MathewBRaiNGuptaA, et al. (2015) Exploiting computing power of xeon and intel xeon phi for a molecular dynamics application. In: Proceedings of the symposium on high performance computing (HPC ‘15) society for computer simulation international, Alexandria, VA, USA, pp. 9–16. San Diego, CA, USA. http://dl.acm.org/citation.cfm?id=2872599.2872601.
34.
MisraGKurkureNDasA, et al. (2013) Evaluation of rodinia codes on Intel Xeon Phi. In: 2013 4th international conference on intelligent systems, modelling and simulation, Bangkok, Thailand, 7 August 2016, pp. 415–419. DOI: 10.1109/ISMS.2013.118. IEEE.
35.
NewburnCJDmitrievSNarayanaswamyR, et al. (2013) Offload compiler runtime for the Intel Xeon Phi™ Coprocessor. In: Proceedings of the 2013 IEEE 27th international symposium on parallel and distributed processing workshops and PhD forum (IPDPSW ‘13), pp. 1213–1225. IEEE Computer Society, Washington, DC, USA. DOI: 10.1109/IPDPSW.2013.251.
ParkJBikshandiGVaidyanathanK, et al. (2013) Tera-scale 1D FFT with Low-communication algorithm and intel xeon phi coprocessors. In: Proceedings of the international conference on high performance computing, networking, storage and analysis (SC ‘13), Denver, CO, USA, ACM, New York, NY, USA, Article 34, p. 12. DOI: 10.1145/2503210.2503242.
38.
SainiSJinHJespersenD, et al. (2015) Early multi-node performance evaluation of a knights corner (KNC) based NASA supercomputer. In: 2015 IEEE international parallel and distributed processing symposium workshop (IPDPSW), Hyderabad, India, pp. 57–67. DOI: 10.1109/IPDPSW.2015.140.
39.
SainzFBellnJBeltranV, et al. (2015) Collective offload for heterogeneous clusters. In: 2015 IEEE 22nd international conference on high performance computing (HiPC), Bangalore, India, pp. 376–385. DOI: 10.1109/HiPC.2015.20.
40.
SauleEKayaKÇatalyürekÜ (2014) Performance Evaluation of Sparse Matrix Multiplication Kernels on Intel Xeon Phi. Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 559–570. DOI: 10.1007/978–3–642–55224–3_52
41.
SchmidtMWBaldridgeKKBoatzJA, et al. (1993) General atomic and molecular electronic structure system. Journal of Computational Chemistry14(11): 1347–1363. DOI: 10.1002/jcc.540141112
TeodoroGKurcTKongJ, et al. (2014) Comparative performance analysis of Intel (R) Xeon Phi (TM), GPU, and CPU: a case study from microscopy image analysis. In: 2014 IEEE 28th international parallel and distributed processing symposium, Phoenix, AZ, USA, pp. 1063–1072. DOI: 10.1109/IPDPS.2014.111.
WoodJZongZGuQ, et al. (2014) Energy and power characterization of parallel programs running on Intel Xeon Phi. In: 2014 43rd international conference on parallel processing workshops, Minneapolis, MN, USA. pp. 265–272. DOI: 10.1109/ICPPW.2014.43.
46.
WuZHuangN (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis1(1): 1–41. DOI: 10.1142/S1793536909000047
