论文信息 - Poster: Statistical Power and Energy Modeling of Multi-GPU Kernels

Poster: Statistical Power and Energy Modeling of Multi-GPU Kernels

To improve the energy efficiency of parallel applications on GPGPUs, a better understanding of the energy behavior of various applications is mandatory. In this study we employ statistical methods to model power and energy consumption of some common optimized high performance kernels (DGEMM, FFT, PRNG and FD stencils) on a multi-GPU platform.

Sunita Chandrasekaran | Barbara M. Chapman | Sayan Ghosh

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

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

[3] Xiaohan Ma,et al. Statistical Power Consumption Analysis and Modeling for GPU-based Computing , 2011 .