多核CPU和GPU并行求解最短公共超串-计算机软件与理论专业论文.docxVIP

II II 模型，设计适用于求解最短公共超串问题的数据分配算法，采取每个节点 运行融合遗传蚁群算法并行求解最短公共超串的方法，设计实现多核 CPU/GPU 异构机群并行求解最短公共超串的高效算法，并在多核 CPU/GPU 异 构机群曙光 5000A 系统上进行实验测试，实验结果表明本文的多核 CPU/GPU 系统上最短公共超串并行求解算法高效，且具有良好的可扩展性。 关键词：最短公共超串；并行算法；多核并行计算；GPU 计算；遗传算法； 蚁群算法；异构机群 III III PARALLEL COMPUTING SHORTEST COMMON SUPERSTRING USING MULTI-CORE CPU AND GPU ABSTRACT The goal of human genome project is to complete DNA sequencing. It has the important significance to treatment of hereditary. Now the technology cannot sequencing fragment pass hundred basic group. Only use shot gun method to get a large number small fragment to reconstitute the goal molecule. Turning the problem into the shortest common superstring problem and use computer to sole it is a new way. So, computing the shortest common superstring on hybrid multi-core CPU/GPU systems has a great significance. According to the capacity of multi-level caches, the population individuality and ant data in CPU main memory are assigned to L3 Cache, L2 Cache and L1 Cache to reduce data transfer overhead among multiple caches during parallel computing, the asynchronous and incomplete transfer data method was performed between CPU and GPU, multiple flows are asynchronously executed by multiple GPU kernel functions, the thread number of GPU block was set to the size of 16 times and GPU public memory was divided into bank with the size of 32 times, GPU constant memory was used to store read-only parameters such as cross probability and mutate probability which were read frequently, the read-only big data structure such as string set and overlap matrix were bind to GPU texture memory, and a computation, cache and communication-efficient parallel algorithm for CPU and GPU coordinate solving shortest common superstring problem was designed and implemented. The experimental results for solving shortest common superstring problem with several sizes show the proposed CPU and GPU parallel algorithm is faster over 70 times than the sequential algorithm. The goal is that