基于多态并行处理器的生物计算并行实现  

Implementation of Parallel Biological Computing Based on Polymorphous Parallel Processor

作　　者：刘玉荣[1] 李涛[1] 

机构地区：[1]西安邮电大学电子工程学院,陕西西安710061

出　　处：《计算机技术与发展》2014年第8期55-58,62,共5页Computer Technology and Development

基　　金：国家自然科学基金重点资助项目(61136002);陕西省科学技术研究发展计划资助项目(2011K06-47)

摘　　要：针对传统的生物计算中DNA序列保守序列的识别(模体识别)和最长公共子序列计算需要较大的数据量、计算量,以及功耗大等问题,文中提出了两种基于PAAG多态并行处理器的并行算法,该并行处理器能够支持数据、线程、指令多种并行。通过编程在PAAG多态并行处理的处理单元(PE)上开发了相应的串行和并行程序,将计算的不同过程分派到不同的处理单元(PE)上进行处理,实现了不同粒度算法的并行。实验结果表明,文中提出的并行算法使模体识别和最长公共子序列的计算效率得到明显提高。Aiming at the problems of large amount of data and computing,and power consumption for the conserved sequence identifying and the longest common sub-sequence in DNA of traditional biological computing,propose two parallel computing algorithms of based on PAAG polymorphic parallel processor. This parallel processor can support the multiple parallelism of data, thread and instruction. Through programming,develop the corresponding serial and parallel procedure in PE,realizing the parallel of different granularity algorithm. Experimental results demonstrate that the proposed method is very effective in identifying the optimal motif and computing the longest common sub-sequence.

关 键 词：PAAG多态并行处理器 并行算法 模体识别 最长公共子序列 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]