基于OpenCL的均值平移算法在多个众核平台的性能优化研究

摘要

As a general-purpose programming standard for multiple platforms, OpenCL has accelerated many applications. Due to the differences of different platforms in hardware and software environments,general optimization methods may not accelerate the application well for all. Taking the optimization of the mean shift algorithm on GPU and APU platforms as an example, the paper provided several insights on contributions of various optimization methods on different platforms. On one hand, we explored the architectures of different platforms. On the other hand, we compared the pros and cons of different optimization methods. Based on meticulous evaluations of the pros and cons, we looked for the optimal solution. Experimental results show that,on AMD 5850,Tesla C2050 and APU A6-3650 platforms,the optimized algorithm achieves 9. 68× ,5. 74× and 1. 27 × speedups,respectively,and 79. 73× ,93. 88× and 2. 22× speedups compared to the serial version, respectively, and 1. 27× and 1. 24× speedups compared to the CUDA version OpenCV program for the first two platforms,respectively.%OpenCL作为一种面向多种平台、通用目的的编程标准,已经对许多应用程序进行了加速.由于平台硬件和软件环境的差异,通用的优化方法不一定在所有平台都有很好的加速.通过对均值平移算法在GPU和APU平台的优化,探讨了不同平台各种优化方法的贡献力,一方面研究各个平台的计算特性,另一方面体会不同优化方法的优劣,在优劣的相互转化中寻求最优的解决方案.实验表明,算法并行优化前、后在AMD 5850、Tesla C2050和APU A63650上分别达到了9.68、5.74和1.27倍加速,并行相比串行程序达到79.73、93.88和2.22倍加速,前两个平台OpenCL版本相比,CUDA版本的OpenCV程序达到1.27和1.24倍加速.