作者: ThienLuan Ho , Seung-Rohk Oh , HyunJin Kim
DOI: 10.1371/JOURNAL.PONE.0186251
关键词:
摘要: Approximate string matching with k-differences has a number of practical applications, ranging from pattern recognition to computational biology. This paper proposes an efficient memory-access algorithm for parallel approximate on Graphics Processing Units (GPUs). In the proposed algorithm, all threads in same GPUs warp share data using warp-shuffle operation instead accessing shared memory. Moreover, we implement by exploiting memory structure optimize its performance. Experiment results real DNA packages revealed that performance and implementation archived up 122.64 1.53 times compared sequential CPU previous GPUs, respectively.