Title of article :
Energy-Aware GPU Programming at Source-Code Levels
Author/Authors :
Zhang, Changyou Peking University - School of Electronics Engineering and Computer Science - Key Laboratory of High Confidence Software Technologies, China , Huang, Kun Peking University - School of Electronics Engineering and Computer Science - Key Laboratory of High Confidence Software Technologies, China , Cui, Xiang Peking University - School of Electronics Engineering and Computer Science - Key Laboratory of High Confidence Software Technologies, China , Chen, Yifeng Peking University - School of Electronics Engineering and Computer Science - Key Laboratory of High Confidence Software Technologies, China
Abstract :
To enhance the energy efficiency and performance of algorithms with Graphics Processing Unit (GPU) accelerators in source-code development, we consider the power efficiency based on data transfer bandwidth and power consumption in key situations. First, a set of primitives is abstracted from program statements. Then, data transfer bandwidth and power consumption in different granularity sizes are considered and mapped into proper primitives. With these mappings, a programmer can intuitively determine the power efficiency and performance in different running states of a thread. Finally, this intuition enables the programmer to tune the algorithm in order to achieve the best energy efficiency and performance. Using these power-aware principles, two Fast Fourier Transform (FFT) methods are compared. The mapping between power consumption and primitives is helpful for algorithm tuning in source-code levels.
Keywords :
GPU , power , aware , source , code , primitive
Journal title :
Tsinghua Science and Technology
Journal title :
Tsinghua Science and Technology
