基于多态并行处理器的生物计算并行实现

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。

Implementation of Parallel Biological Computing Based on Polymorphous Parallel Processor

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.