光学学报, 2018, 38 (4): 0411004, 网络出版: 2018-07-10
基于总变分最小化模型的异步并行GPU加速算法 下载: 757次
Asynchronous Parallel GPU Acceleration Method Based on Total Variation Minimization Model
成像系统 优化类重建算法 异步并行迭代 总变分最小化模型 多图形处理器加速 imaging systems optimization-based reconstruction method asynchronous parallel iteration total variation minimization model multi-graphics processing unit acceleration
摘要
相比于传统同步并行计算策略,在异步并行计算框架下,针对最常用的总变分(TV)最小化重建模型,通过将其转化为不动点迭代问题,并利用异步交替方向法(ADM)进行求解,推导出基于TV最小化模型的异步ADM迭代重建算法,即异步交替方向总变分最小化算法(Async-ADTVM)。利用消息传递接口技术将该算法在图形处理器(GPU)集群上进行测试,进一步提高了原始基于TV最小化模型的迭代重建算法的计算效率。实验表明,该算法在计算求解精度上略优于ADTVM算法,同时在GPU性能存在差异的条件下相比传统多GPU加速策略可获得更高的加速比。
Abstract
Compared to the traditional synchronous parallel computing, an asynchronous parallel alternating direction method (ADM) for total variation (TV) minimization reconstruction, namely asynchronous alternating direction total variation minimization method (Async-ADTVM), is proposed in this paper. Under the asynchronous parallel computing framework, Async-ADTVM transforms TV minimization reconstruction model to the problem of fixed-point iteration, which is solved by asynchronous parallel ADM. It is implemented on the graphics processing unit (GPU) cluster based on message passing interface technology. Experimental results show that the proposed Async-ADTVM can provide a little higher calculation accuracy than ADTVM. Meanwhile, it can provide a higher speed-up ratio than the traditional multi-GPU acceleration strategy when the performance of each GPU is different.
路万里, 蔡爱龙, 郑治中, 王林元, 李磊, 闫镔. 基于总变分最小化模型的异步并行GPU加速算法[J]. 光学学报, 2018, 38(4): 0411004. Wanli Lu, Ailong Cai, Zhizhong Zheng, Linyuan Wang, Lei Li, Bin Yan. Asynchronous Parallel GPU Acceleration Method Based on Total Variation Minimization Model[J]. Acta Optica Sinica, 2018, 38(4): 0411004.