A measurement study of GPU DVFS on energy conservation

Nowadays, GPUs are widely used to accelerate many high performance computing applications. Energy conservation of such computing systems has become an important research topic. Dynamic voltage/frequency scaling (DVFS) is proved to be an appealing method for saving energy for traditional computing centers. However, there is still a lack of firsthand study on the effectiveness of GPU DVFS. This paper presents a thorough measurement study that aims to explore how GPU DVFS affects the system energy consumption. We conduct experiments on a real GPU platform with 37 benchmark applications. Our results show that GPU voltage/frequency scaling is an effective approach to conserving energy. For example, by scaling down the GPU core voltage and frequency, we have achieved an average of 19.28% energy reduction compared with the default setting, while giving up no more than 4% of performance. For all tested GPU applications, core voltage scaling is significantly effective to reduce system energy consumption. Meanwhile the effects of scaling core frequency and memory frequency depend on the characteristics of GPU applications.

[1]  Satoshi Matsuoka,et al.  Statistical power modeling of GPU kernels using performance counters , 2010, International Conference on Green Computing.

[2]  Jiming Liu,et al.  Speeding up K-Means Algorithm by GPUs , 2010, 2010 10th IEEE International Conference on Computer and Information Technology.

[3]  Mateo Valero,et al.  Understanding the future of energy-performance trade-off via DVFS in HPC environments , 2012, J. Parallel Distributed Comput..

[4]  Chris Fallin,et al.  Memory power management via dynamic voltage/frequency scaling , 2011, ICAC '11.

[5]  Min Yeol Lim,et al.  Determining the Minimum Energy Consumption using Dynamic Voltage and Frequency Scaling , 2007, 2007 IEEE International Parallel and Distributed Processing Symposium.

[6]  Nam Sung Kim,et al.  GPUWattch: enabling energy optimizations in GPGPUs , 2013, ISCA.

[7]  Xiaowen Chu,et al.  Practical Random Linear Network Coding on GPUs , 2009, Networking.

[8]  Nam Sung Kim,et al.  Improving Throughput of Power-Constrained GPUs Using Dynamic Voltage/Frequency and Core Scaling , 2011, 2011 International Conference on Parallel Architectures and Compilation Techniques.

[9]  Hiroshi Sasaki,et al.  Power and Performance Analysis of GPU-Accelerated Systems , 2012, HotPower.

[10]  Nam Sung Kim,et al.  Optimizing total power of many-core processors considering voltage scaling limit and process variations , 2009, ISLPED.

[11]  Rong Ge,et al.  Effects of Dynamic Voltage and Frequency Scaling on a K20 GPU , 2013, 2013 42nd International Conference on Parallel Processing.

[12]  Wu-chun Feng,et al.  Power and Performance Characterization of Computational Kernels on the GPU , 2010, 2010 IEEE/ACM Int'l Conference on Green Computing and Communications & Int'l Conference on Cyber, Physical and Social Computing.

[13]  Sunpyo Hong.  Modeling performance and power for energy-efficient GPGPU computing , 2012 .

[14]  Hyesoon Kim,et al.  An integrated GPU power and performance model , 2010, ISCA.

[15]  Hyesoon Kim,et al.  An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness , 2009, ISCA '09.

[16]  Xiaowen Chu,et al.  Massively Parallel Network Coding on GPUs , 2008, 2008 IEEE International Performance, Computing and Communications Conference.

[17]  Henry Wong,et al.  Analyzing CUDA workloads using a detailed GPU simulator , 2009, 2009 IEEE International Symposium on Performance Analysis of Systems and Software.

[18]  Kevin Skadron,et al.  Rodinia: A benchmark suite for heterogeneous computing , 2009, 2009 IEEE International Symposium on Workload Characterization (IISWC).