Analysis of GPU Power Consumption Using Internal Sensors

• Mariza Ferro LNCC
• André Yokoyama LNCC
• Vinicius Klôh LNCC
• Gabrieli Silva LNCC
• Rodrigo Gandra PETROBRAS
• Ricardo Bragança PETROBRAS
• Andre Bulcão PETROBRAS
• Bruno Schulze LNCC

DOI: https://doi.org/10.5753/wperformance.2017.3360

Resumo

GPUs has been widely used in scientific computing, as by offering exceptional performance as by power-efficient hardware. Its position established in high-performance and scientific computing communities has increased the urgency of understanding the power cost of GPU usage in accurate measurements. For this, the use of internal sensors are extremely important. In this work, we employ the GPU sensors to obtain high-resolution power profiles of real and benchmark applications. We wrote our own tools to query the sensors of two NVIDIA GPUs from different generations and compare the accuracy of them. Also, we compare the power profile of GPU with CPU using IPMItool.

Referências

Adhinarayanan, V., Subramaniam, B., and chun Feng, W. (2016). Online power estimation of graphics processing units. In 16th IEEE/ACM International Symposium on XXXVII Congresso da Sociedade Brasileira de Computação 1710 Cluster, Cloud and Grid Computing, CCGrid 2016, Cartagena, Colmbia, May 16-19, 2016, pages 245–254. IEEE Computer Society.

Bridges, R. A., Imam, N., and Mintz, T. M. (2016). Understanding gpu power: A survey of profiling, modeling, and simulation methods. ACM Comput. Surv., 49(3):41:1–41:27.

Burtscher, M., Zecena, I., and Zong, Z. (2014). Measuring gpu power with the k20 built-in sensor. In Proceedings of Workshop on General Purpose Processing Using GPUs, GPGPU-7, pages 28:28–28:36, New York, NY, USA. ACM.

Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J. W., Lee, S.-H., and Skadron, K. (2009). Rodinia: A benchmark suite for heterogeneous computing. In IISWC, pages 44–54. IEEE.

Coplin, J. and Burtscher, M. (2016). Energy, power, and performance characterization of GPGPU benchmark programs. In 2016 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPS Workshops 2016, Chicago, IL, USA, May 23-27, 2016, pages 1190–1199. IEEE Computer Society.

Ge, R., Vogt, R., Majumder, J., Alam, A., Burtscher, M., and Zong, Z. (2013). Effects of dynamic voltage and frequency scaling on a k20 gpu. In 2013 42nd International Conference on Parallel Processing, pages 826–833.

Karami, A., Mirsoleimani, S. A., and Khunjush, F. (2013). A statistical performance prediction model for opencl kernels on nvidia gpus. In The 17th CSI International Symposium on Computer Architecture Digital Systems (CADS 2013), pages 15–22.

Kasichayanula, K., Terpstra, D., Luszczek, P., Tomov, S., Moore, S., and Peterson, G. D. (2012). Power aware computing on gpus. Application Accelerators in High-Performance Computing, Symposium on, 00:64–73.

Lee, Y. and Kim, S. (2015). Empirical characterization of power efficiency for large scale data processing. In 2015 17th International Conference on Advanced Communication Technology (ICACT), pages 787–790.

Mei, X., Wang, Q., and Chu, X. (2016). A survey and measurement study of GPU DVFS on energy conservation. Digital Communications and Networks.

Menezes, G. S., Silva-Filho, A. G., Souza, V. L., Medeiros, V. W. C., Lima, M. E., Gandra, R., and Braganca, R. (2012). Energy estimation tool fpga-based approach for petroleum industry. In Proceedings of the 2012 41st International Conference on Parallel Processing Workshops, ICPPW ’12, pages 600–601, Washington, DC, USA. IEEE Computer Society.

Mittal, S. and Vetter, J. S. (2014). A survey of methods for analyzing and improving gpu energy efficiency. ACM Comput. Surv., 47(2):19:1–19:23.

NVIDIA (2012). NVML API Reference Manual. [link].

Wang, G. (2010). Power analysis and optimizations for gpu architecture using a power simulator. In 2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE), volume 1, pages V1–619–V1–623.