GPU-Based Memory Optimization Method for Multiple Sequence Alignment

被引：0

作者：

Jin, Lizhong ^{[1
]}

机构：

[1] Northeast Dianli Univ, Sch Chem Engn, Changchun 130012, Jilin, Peoples R China

来源：

ISBE 2011: 2011 INTERNATIONAL CONFERENCE ON BIOMEDICINE AND ENGINEERING, VOL 4 | 2011年

关键词：

Multiple Sequence Alignment; GPU; Memory Optimization; ClustalW; CLUSTALW; HARDWARE; PARALLEL;

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

In this paper, we present a few memory optimization strategies to accelerate the ClustalW program based on GPUs. The non-coalesced global memory accesses, the global memory accesses and the control expenses are eliminated or reduced by using global memory optimization, the share memory optimization and by loop unrolling strategies respectively. This results in a high-speed implementation with more than 12x speedup on a commodity graphics card over the optimized ClustalW program on the Intel Quad Q9400 platform.

引用

页码：36 / 39

页数：4

共 10 条

[1] Multiple sequence alignment in parallel on a workstation cluster
Ebedes, J
Datta, A
[J]. BIOINFORMATICS, 2004, 20 (07) : 1193 - 1195
[2] ClustalW-MPI: ClustalW analysis using distributed and parallel computing
Li, KB
[J]. BIOINFORMATICS, 2003, 19 (12) : 1585 - 1586
[3] Ligowski L., 2010, P ACM SIGPLAN S PRIN, P137
[4] Liu WG, 2006, LECT NOTES COMPUT SC, V4297, P363
[5] CUDASW++: Optimizing Smith-Waterman sequence database searches for CUDA-enabled graphics processing units
Liu Y.
Maskell D.L.
Schmidt B.
[J]. BMC Research Notes, 2 (1)
[6] CUDA compatible GPU cards as efficient hardware accelerators for Smith-Waterman sequence alignment
Manavski, Svetlin A.
Valle, Giorgio
[J]. BMC BIOINFORMATICS, 2008, 9 (Suppl 2)
[7] Mikhailov D., 2001, WHITE PAPERS SILICON
[8] *NVIDIA CORP, CUDA PROGR GUID VERS
[9] Using reconfigurable hardware to accelerate multiple sequence alignment with ClustalW
Oliver, T
Schmidt, B
Nathan, D
Clemens, R
Maskell, D
[J]. BIOINFORMATICS, 2005, 21 (16) : 3431 - 3432
[10] Wang Yifei, 2006, BIOINFORMATICS

← 1 →