A Smith-Waterman Hardware Accelerator Design using Sliding Window for Genomic Sequence Alignment

This paper presents a hardware accelerator based on the Smith-Waterman algorithm, a well-known sequence alignment technique in bioinformatics. The proposed accelerator enhances its hardware efficiency significantly by employing a sliding window technique under a linear systolic array structure. The multiple processing element (PE) in the array allows parallel computations of the alignment, improving hardware resource utilization. When implemented in a 32-nm CMOS technology, the proposed Smith-Waterman hardware design enhances the area, delay, power, and energy by 80.6%, 52.9%, 67.4%, and 84.6%, respectively, versus the traditional counterpart without the sliding window scheme.