GPU Accelerated Implementation for Sunday String Pattern Matching Algorithm

Abstract

In recent days, Graphics Processing Units (GPU's) have some specialized optimizations that have led to outperform traditional CPU's. General Purpose computing on Graphics Processor Units (GPGPU) brings massively parallel computing (hundreds of compute cores) to the desktop at a reasonable cost, but requires that algorithms be carefully designed to take advantage of this power. The present work explores the possibilities of using GPU's along with CUDA Streams to improve the performance of a string matching algorithm. String matching plays an important role in today's computer applications. Strings are an integral part of almost every data structure we manage. Boyer-Moore and Knuth-Morris-Pratt algorithms are the most famous string matching algorithms that have been proved efficient to some extent using CPU's and GPU's. Sunday string matching algorithm is another version of Boyer-Moore algorithm. In this paper, we have used GPU's to accelerate the performance of the Sunday string matching algorithm. We have conducted experiments to measure the performance of the GPU implementation with respect to the serial CPU implementation. Our results show a speedup of up to 20 times compared to the sequential implementation on the CPU.