Abstract:

Owing to its high performance and high power efficiency, GPU (Graphics Processing Units) has become the one of the most popular accelerators in heterogeneous high performance computing systems. Although GPU has relatively high peak power efficiency, the absolute power consumption is much higher than generalpurpose CPUs. As GPUs being adopted by more high performance computing systems, the lowpower optimization method specific to GPU will become one of the most hot topics in this field. Accurate power predication is an important basis for power optimization. This paper proposes a Hardware Performance Counter (HPC) based power predication method targeted for the GPU architecture. The method coordinates HPC and partial sample power consumption under specific running frequencies and makes use of the linear regression method to predicate the power consumption for other running frequencies. The experimental results validate the effectiveness of the proposed method.

Key words: CPU-GPU heterogeneous system;GPU power model;dynamic voltage and frequency scaling