Abstract
The proper evaluation of System–on–Chip architectures and Single Board Computers, requires from scientists and developers to acquire reliable data from their performance and energy consumption. The performance analysis becomes a hard task due to the high variations in the systems that change dynamically even during the execution, caused by limited power budgets or temperature constraints among others, and producing very different results from one execution to the other. An extra added obstacle in energy analysis arises with the difficulty to obtain the measurements due to the lack of both a unified measurement standard and appropriate sensors to gather them. Attaining a benchmarking process to produce reliable and reproducible data results constitutes a difficult problem to solve and an extremely necessary task. As a consequence, unified solutions that simplify the process and reduce the number of issues to tackle during the computational experiements are of great beneficial to the scientific community. We enumerate several factors that hinder proper metric gathering and propose the use of a unified benchmarking framework to simplify energy measurements to address and hide the toughest aspects. Finally, to validate our proposal, we present a performance and energy evaluation to illustrate the enhance of the quality of measurements obtained where the reliability and reproducibility are improved. A mini-cluster collecting a set of heterogeneous devices running computer fluid dynamics kernels have been used as the testbed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Afonso, S., Almeida, F.: Rancid: reliable benchmarking on android platforms. IEEE Access 8, 143342–143358 (2020)
Almeida, F., Arteaga, J., Blanco, V., Cabrera, A.: Energy measurement tools for ultrascale computing: a survey. Supercomput. Front. Innov. 2(2), 64–76 (2015)
Andrae, A.S., Edler, T.: On global electricity usage of communication technology: trends to 2030. Challenges 6(1), 117–157 (2015)
Bailey, D., Harris, T., Saphir, W., Van Der Wijngaart, R., Woo, A., Yarrow, M.: The NAS parallel benchmarks 2.0. Technical Report, Technical Report NAS-95-020, NASA Ames Research Center (1995)
Barrachina, S., Barreda, M., Catalán, S., Dolz, M.F., Fabregat, G., Mayo, R., Quintana-Ortí, E.: An integrated framework for power-performance analysis of parallel scientific workloads. In: Energy pp. 114–119 (2013)
Bergman, K., Borkar, S., Campbell, D., Carlson, W., et al.: ExaScale computing study: technology challenges in achieving exascale systems peter Kogge, Editor & Study Lead (2008)
Bez, J.L., Bernart, E.E., dos Santos, F.F., Schnorr, L.M., Navaux, P.O.A.: Performance and energy efficiency analysis of HPC physics simulation applications in a cluster of ARM processors. Concurrency Comput. Pract. Experience 29(22), e4014 (2017)
Borkar, S., Chien, A.A.: The future of microprocessors. Commun. ACM 54(5), 67–77 (2011)
Cabrera, A., Almeida, F., Arteaga, J., Blanco, V.: Measuring energy consumption using EML (energy measurement library). Comput. Sci.-Res. Dev. 30(2), 135–143 (2015)
Dzhagaryan, A., Milenkovic, A., Milosevic, M., Jovanov, E.: An environment for automated measuring of energy consumed by android mobile devices. In: Ahrens, A., Benavente-Peces, C. (eds.) Proceedings of the 6th International Joint Conference on Pervasive and Embedded Computing and Communication Systems (PECCS 2016), Lisbon, Portugal, 25–27 July 2016, pp. 28–39. SciTePress (2016)
Göddeke, D., et al.: Energy efficiency vs. performance of the numerical solution of PDEs: an application study on a low-power arm-based cluster. J. Comput. Phys. 237, 132–150 (2013)
González Rincón, J.D.: Sistema basado en open source hardware para la monitorización del consumo de un computador (2015)
Group of architecture and technology of computing systems (ArTeCS) of the Complutense University of Madrid: AccelPowerCape reference Page. https://artecs.dacya.ucm.es/tools/accelpowercape/ Accessed 17 Feb 2021
Hunold, S., Träff, J.L.: On the state and importance of reproducible experimental research in parallel computing (2013)
Kim, J.M., Kim, Y.G., Chung, S.W.: Stabilizing CPU frequency and voltage for temperature-aware DVFS in mobile devices. IEEE Trans. Comput. 64(1), 286–292 (2015)
Milosevic, M., Dzhagaryan, A., Jovanov, E., Milenkovic, A.: An environment for automated power measurements on mobile computing platforms. In: Saad, A. (ed.) ACM Southeast Regional Conference 2013, ACM SE’13, Savannah, GA, USA, 4–6 April 2013. pp. 19:1–19:6. ACM (2013)
Nikov, K., Núñez-Yáñez, J.L.: Intra and inter-core power modelling for single-ISA heterogeneous processors. Int. J. Embed. Syst. 12(3), 324–340 (2020)
Núñez-Yáñez, J.L., Lore, G.: Enabling accurate modeling of power and energy consumption in an arm-based system-on-chip. Microprocess. Microsyst. 37(3), 319–332 (2013)
Schürmans, S., Onnebrink, G., Leupers, R., Ascheid, G., Chen, X.: Frequency-aware ESL power estimation for ARM cortex-a9 using a black box processor model. ACM Trans. Embed. Comput. Syst. 16(1), 26:1–26:26 (2016)
Venkatesh, G., et al.: Conservation cores: reducing the energy of mature computations. ACM Sigplan Not. 45(3), 205–218 (2010)
Vitek, J., Kalibera, T.: R3: repeatability, reproducibility and rigor. SIGPLAN Not. 47(4a), 30–36 (2012)
Yokoyama, D., Schulze, B., Borges, F., Mc Evoy, G.: The survey on ARM processors for HPC. J. Supercomput. 75(10), 7003–7036 (2019). https://doi.org/10.1007/s11227-019-02911-9
Acknowledgments
This work has been supported by the Spanish Ministry of Science and Innovation with the PID2019-107228RB-I00 project, and Contract FPU16/00942; by the Government of the Canary Islands, with the project ProID2021010012 and the grant TESIS2017010134, which is co-financed by the Ministry of Economy, Industry, Commerce and Knowledge of Canary Islands and the European Social Funds (ESF), operative program integrated of Canary Islands 2014–2020 Strategy Aim 3, Priority Topic 74(85%); and the Spanish network CAPAP-H.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cabrera, A., Nichita, P., Afonso, S., Almeida, F., Blanco, V. (2023). Reliable Energy Measurement on Heterogeneous Systems–on–Chip Based Environments. In: Wyrzykowski, R., Dongarra, J., Deelman, E., Karczewski, K. (eds) Parallel Processing and Applied Mathematics. PPAM 2022. Lecture Notes in Computer Science, vol 13826. Springer, Cham. https://doi.org/10.1007/978-3-031-30442-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-30442-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30441-5
Online ISBN: 978-3-031-30442-2
eBook Packages: Computer ScienceComputer Science (R0)