Title
Fine-grain parallel megabase sequence comparison with multiple heterogeneous GPUs
Abstract
This paper proposes and evaluates a parallel strategy to execute the exact Smith-Waterman (SW) algorithm for megabase DNA sequences in heterogeneous multi-GPU platforms. In our strategy, the computation of a single huge SW matrix is spread over multiple GPUs, which communicate border elements to the neighbour, using a circular buffer mechanism that hides the communication overhead. We compared 4 pairs of human-chimpanzee homologous chromosomes using 2 different GPU environments, obtaining a performance of up to 140.36 GCUPS (Billion of cells processed per second) with 3 heterogeneous GPUS.
Year
DOI
Venue
2014
10.1145/2555243.2555280
PPOPP
Keywords
Field
DocType
parallel strategy,border element,different gpu environment,megabase dna sequence,circular buffer mechanism,communication overhead,single huge sw matrix,fine-grain parallel megabase sequence,heterogeneous multi-gpu platform,exact smith-waterman,multiple heterogeneous gpus,heterogeneous gpus,smith waterman
Computer science,Matrix (mathematics),Parallel computing,Circular buffer,Theoretical computer science,Smith–Waterman algorithm,Computation
Conference
Volume
Issue
ISSN
49
8
0362-1340
Citations 
PageRank 
References 
5
0.44
3
Authors
5
Name
Order
Citations
PageRank
weigang1222.61
Guillermo Miranda2261.62
Alba Cristina Magalhaes Alves De Melo325333.90
Xavier Martorell41470125.40
Eduard Ayguade574149.83