Abstract
In order to be able to minimise the energy consumption of an application program, information about the specific energy consumption is required. Modern Nvidia graphics processing units (GPUs) measure their current power consumption and the driver makes the value available to the application every 20 ms. However, for evaluating the energy consumption of GPU kernel functions, such a sampling interval might not be sufficient since the kernels may have a shorter execution time.
This article proposes a method for generating high-resolution power profiles, which is the power consumption of a specific function depending on the progress of its execution. The method uses low-resolution measuring instruments offered by GPUs. Power measurements obtained during several executions of the function are combined into a single power profile. The resulting power profile contains power values in intervals which are much shorter than the sampling interval of the hardware driver so that even short-term power changes can be considered, e.g. for calculating the energy consumption of a single function. The article also shows how to extend the approach to an online generation of power profiles. Furthermore, an overview on the power profiles of some important functions, such as BLAS routines, is given.
Chapter PDF
References
Powermizer 8.0: Intelligent power management technology. Tech. rep., Nvidia (June 2008), tB-04051-001_v01
AMD PowerTune technology. Whitepaper, AMD (December 2010), http://www.amd.com/uk/Documents/PowerTune_Technology_Whitepaper.pdf
Abe, Y., Sasaki, H., Peres, M., Inoue, K., Murakami, K., Kato, S.: Power and performance analysis of GPU-accelerated systems. In: Workshop on Power Aware Computing and Systems, HotPower 2012 (2012)
Advanced Micro Devices: BIOS and Kernel Developer‘s Guide (BKDG) for AMD Family 15h Models 00h-0Fh Processors, rev. 3.12 (October 2012)
Chen, D., Singh, D.: Using OpenCL to evaluate the efficiency of CPUs, GPUs and FPGAs for information filtering. In: 22nd Int. Conf. on Field Programmable Logic and Applications (FPL), pp. 5–12 (2012)
Chen, J., Li, B., Zhang, Y., Peng, L., Peir, J.K.: Statistical GPU power analysis using tree-based methods. In: Int. Green Computing Conf. and Workshops (IGCC), pp. 1–6 (2011)
Collange, S., Defour, D., Tisserand, A.: Power consumption of GPUs from a software perspective. In: 9th Int. Conf. on Computational Science (2009)
Hong, S., Kim, H.: An integrated GPU power and performance model. SIGARCH Comput. Archit. News 38(3), 280–289 (2010)
Huang, S., Xiao, S., Feng, W.: On the energy efficiency of graphics processing units for scientific computing. In: IEEE Int. Symp. on Parallel Distributed Processing (IPDPS 2009), pp. 1–8 (2009)
Hähnel, M., Döbel, B., Völp, M., Härtig, H.: Measuring energy consumption for short code paths using RAPL. In: GREENMETRICS 2012 (2012)
Intel Corporation: Intel 64 and IA-32 Architectures Software Developer‘s Manual (May 2012)
Isci, C., Martonosi, M.: Runtime power monitoring in high-end processors: Methodology and empirical data. In: 36th IEEE/ACM Int. Symp. on Microarchitecture (2003)
Kasichayanula, K., Terpstra, D., Luszczek, P., Tomov, S., Moore, S., Peterson, G.: Power aware computing on GPUs. In: 2012 Symp. on Application Accelerators in High-Performance Computing (2012)
Li, D., Byna, S., Chakradhar, S.: Energy-aware workload consolidation on GPU. In: 40th Int. Conf. on Parallel Processing Workshops, pp. 389–398 (2011)
McCullough, J.C., Agarwal, Y., Chandrashekar, J., Kuppuswamy, S., Snoeren, A.C., Gupta, R.K.: Evaluating the effectiveness of model-based power characterization. In: 2011 USENIX Conf. (2011)
Nagasaka, H., Maruyama, N., Nukada, A., Endo, T., Matsuoka, S.: Statistical power modeling of GPU kernels using performance counters. In: Int. Green Computing Conf. (IGCC), pp. 115–122 (2010)
Nvidia: Tesla C2075 Computing Processor Board. Board Specification (2011), http://www.nvidia.com/docs/IO/43395/BD-05880-001_v02.pdf , bD-05880-001_v02
Nvidia: CUBLAS Library – User Guide, version 5.0 (October 2012), http://docs.nvidia.com/cuda/pdf/CUDA_CUBLAS_Users_Guide.pdf
Nvidia: NVML API Reference Manual, ver. 3.295.45 (2012), http://developer.download.nvidia.com/assets/cuda/files/CUDADownloads/NVML/nvml.pdf
Rauber, T., Rünger, G.: Towards an energy model for modular parallel scientific applications. In: Green Computing and Communications (GreenCom), pp. 523–532 (2012)
Rofouei, M., Stathopoulos, T., Ryffel, S., Kaiser, W., Sarrafzadeh, M.: Energy-aware high performance computing with graphic processing units. In: Workshop on Power Aware Computing and Systems, HotPower 2008 (2008)
Weaver, V., Johnson, M., Kasichayanula, K., Ralph, J., Luszczek, P., Terpstra, D., Moore, S.: Measuring energy and power with PAPI. In: Int. Workshop on Power-Aware Systems and Architectures, PASA 2012 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lang, J., Rünger, G. (2013). High-Resolution Power Profiling of GPU Functions Using Low-Resolution Measurement. In: Wolf, F., Mohr, B., an Mey, D. (eds) Euro-Par 2013 Parallel Processing. Euro-Par 2013. Lecture Notes in Computer Science, vol 8097. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40047-6_80
Download citation
DOI: https://doi.org/10.1007/978-3-642-40047-6_80
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40046-9
Online ISBN: 978-3-642-40047-6
eBook Packages: Computer ScienceComputer Science (R0)