RT Generic
T1 Analysis and implementation of a BLAST-Like algorithm for MIC architectures
T2 Análisis e implementación de algoritmo BLAST-Like para arquitecturas MIC
A1 Sulser-Larraz, Felipe
K1 Tecnología SIMD
K1 Bioinformática
K1 Algoritmos
K1 Multiprocesadores
K1 Informática - Trabajos Fin de Grado
K1 Grado en Ingeniería Informática - Trabajos Fin de Grado
AB Sequence alignment is becoming increasingly important in our current day and age,and with the rise of coprocessors, it is important to adapt sequence alignment algorithms to the new architecture. Parallelization using SIMD technology has previously been achieved that implement alignment algorithms e efficiently such as SWIPE, described by Rognes in 2011.The Intel Xeon Phi provides a solid architecture which can be used and exploitedto maximize the speed in sequence alignment. It is therefore important, to develop algorithms that are able to use efficiently the coprocessor to maximize throughput.A diferent approach and implementation is described and benchmarked. The new program, called BLPhi, aims to reduce execution time by using a filtering method.BLPhi takes advantage of the architecture of the Intel Xeon Phi and provides aparallel solution to sequence alignment using SIMD technology.While exact alignment methods such as the Smith-Waterman are too sensitive fordatabase searching, BLPhi uses a filtering technique that can be adapted to anylength given. This gives the user the ability to adapt the search for his needs and may, perhaps, make the search more restrictive.An analysis with current state of the art alignment methods is also presented. Weperform speed and accuracy analysis to see the potential that BLPhi has among itscompetitors.
YR 2017
FD 2017-01-25
LK http://hdl.handle.net/10630/12794
UL http://hdl.handle.net/10630/12794
LA spa
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 21 ene 2026