Abstract
GPUs are of increasing interests in the multi-core era due to their high computing power. However, the power consumption caused by the rising performance of GPUs has been a general concern. As a consequence, it is becoming an imperative demand to optimize the GPU power consumption, among which the power consumption estimation is one of the important and useful solutions. In this work, we present a novel statistical model that is capable of dynamically estimating the power consumption of the AMD’s integrated GPU (iGPU). Precisely, we adopt the linear regression for power consumption modeling and propose a mechanism called kernel extension to lengthen the kernel execution time so that we can sample system data for model evaluation. The results show that the median absolute error of our model is less than 3%. Furthermore, to reduce the latency of power consumption estimation, we conduct a study to explore the possibility to simplify our statistical model. The results suggest that the accuracy and stability is still acceptable in the simplified model. This provides a desirable option to reduce our model latency when it is applied to the iGPU power consumption optimization in the real world.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nvidia Corparation, What is CUDA (2016). http://www.nvidia.com/object/what_is_cuda_new.html
Stone, J.E., Gohara, N., Shi, G.: OpenCL: a parallel programming standard for heterogeneous computing systems. Comput. Sci. Eng. 12(3), 66–72 (2010)
Nvidia Corparation. Geforce GTX 280 (2016). http://www.nvidia.com/object/product_geforce_gtx_280_us.html
Intel Corparation. Intel Core i7–920 Processor (2016). http://ark.intel.com/product.aspx?id=37147
Branover, A., Foley, D., Steinman, M.: AMD fusion APU: Llano. IEEE Micro. 32(2), 28–37 (2012)
AMD, Amd CodeXL (2016). http://developer.amd.com/tools-and-sdks/opencl-zone/codexl/
Zhang, Y., Owens, J.D.: A quantitative performance analysis model for GPU architectures. In: Proceedings of International Symposium on High-Performance Computer Architecture, pp. 382–393 (2011)
Luo, C., Suda, J.: A performance and energy consumption analytical model for GPU. In: 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing, pp. 658–665 (2011)
Baghsorkhi, S.S., Delahaye, M., Patel, S.J., Gropp, W.D., Hwu, W.W.: An adaptive performance modeling tool for GPU architectures. ACM SIGPLAN Not. 45(5), 105 (2010)
Hong, S., Kim, H.: An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness. ACM SIGGARCH Comput. Archit. News 37(3), 152 (2009)
Wu, G., Greathouse, J.L., Lyashevsky, A., Jaysasena, N., Chiou, D.: GPGPU performance and power estimation using machine learning. In: 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), pp. 564–576 (2015)
Diop, T., Jerger, N.E., Anderson, J.: Power modeling for heterogeneous processors. In: Proceedings of Workshop on General Purpose Processing Using GPUs, pp. 90–98 (2014)
Zhang, Y., Hu, Y., Li, B., Peng, L.: Performance and power analysis of ATI GPU: a statistical approach. In: Proceedings of 6th IEEE International Conference on Networking, Architecture, and Storage, NAS 2011, pp. 149–158 (2011)
Karami, A., Khunjush, F., Anderson, S.A.: A statistic performance analyzer framework for OpenCL kernels on Nvidia GPUs. J. Supercomput. 71(8), 2900–2921 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Q., Li, N., Shen, L., Wang, Z. (2017). A Novel Statistical Power Model for Integrated GPU with Optimization. In: Zou, B., Han, Q., Sun, G., Jing, W., Peng, X., Lu, Z. (eds) Data Science. ICPCSEE 2017. Communications in Computer and Information Science, vol 728. Springer, Singapore. https://doi.org/10.1007/978-981-10-6388-6_26
Download citation
DOI: https://doi.org/10.1007/978-981-10-6388-6_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6387-9
Online ISBN: 978-981-10-6388-6
eBook Packages: Computer ScienceComputer Science (R0)