000 01764naa a2200181 a 4500
003 AR-LpUFIB
005 20250311170419.0
008 230201s2011 ag r 000 0 spa d
024 8 _aDIF-M6656
_b6795
_zDIF006019
040 _aAR-LpUFIB
_bspa
_cAR-LpUFIB
100 1 _aRucci, Enzo
245 1 0 _aDNA sequence alignment :
_bhybrid parallel programming on a multicore cluster
300 _a1 archivo (484,8 KB)
500 _aFormato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
520 _aDNA sequence alignment is one of the most important operations of computational biology. In 1981, Smith and Waterman developed a method for sequences local alignment. Due to its computational power and memory requirements, various heuristics have been developed to reduce execution time at the expense of a loss of accuracy in the result. This is why heuristics do not ensure that the best alignment is found. For this reason, it is interesting to study how to apply the computer power of different parallel platforms to speed up the sequence alignment process without losing result accuracy. In this article, a new parallelization strategy (HI-M) of Smith-Waterman algorithm on a multi-core cluster is presented, configuring a pipeline with a hybrid communication model. Additionally, a performance analysis is carried out and compared with two previously presented parallel solutions. Finally, experimental results are presented, as well as future research lines.
534 _aRecent advances in computers, communications, applied social science and mathematics : Proceedings of the International Conference on Applied, Numerical and Computational Mathematics (ICANCM
942 _cCP
999 _c55801
_d55801