An energy-aware performance analysis of SWIMM: Smith–Waterman implementation on Intel’s Multicore and Manycore architectures

摘要

Alignment is essential in many areas such as biological, chemical and criminal forensics. The well-knownrnSmith–Waterman (SW) algorithm is able to retrieve the optimal local alignment with quadratic time andrnspace complexity. There are several implementations that take advantage of computing parallelization,rnsuch as manycores, FPGAs or GPUs, in order to reduce the alignment effort. In this research, we adapt,rndevelop and tune the SW algorithm named SWIMM on a heterogeneous platform based on Intel’s Xeonrnand Xeon Phi coprocessor. SWIMM is a free tool available in a public git repository https://github.com/rnenzorucci/SWIMM. We efficiently exploit data and thread-level parallelism, reaching up to 380 GCUPS onrnheterogeneous architecture, 350 GCUPS for the isolated Xeon and 50 GCUPS on Xeon Phi. Despite thernheterogeneous implementation obtaining the best performance, it is also the most energy-demanding. Inrnfact, we also present a trade-off analysis between performance and power consumption. The greenestrnconfiguration is based on an isolated multicore system that exploits AVX2 instruction set architecturernreaching 1.5 GCUPS/Watts.