Document Detail


Exploiting graphics processing units for computational biology and bioinformatics.
MedLine Citation:
PMID:  20658333     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
Advances in the video gaming industry have led to the production of low-cost, high-performance graphics processing units (GPUs) that possess more memory bandwidth and computational capability than central processing units (CPUs), the standard workhorses of scientific computing. With the recent release of generalpurpose GPUs and NVIDIA's GPU programming language, CUDA, graphics engines are being adopted widely in scientific computing applications, particularly in the fields of computational biology and bioinformatics. The goal of this article is to concisely present an introduction to GPU hardware and programming, aimed at the computational biologist or bioinformaticist. To this end, we discuss the primary differences between GPU and CPU architecture, introduce the basics of the CUDA programming language, and discuss important CUDA programming practices, such as the proper use of coalesced reads, data types, and memory hierarchies. We highlight each of these topics in the context of computing the all-pairs distance between instances in a dataset, a common procedure in numerous disciplines of scientific computing. We conclude with a runtime analysis of the GPU and CPU implementations of the all-pairs distance calculation. We show our final GPU implementation to outperform the CPU implementation by a factor of 1700.
Authors:
Joshua L Payne; Nicholas A Sinnott-Armstrong; Jason H Moore
Related Documents :
3840093 - A simple, low-cost computer program for scatchard plot analysis of binding data in ster...
3962973 - Epidemiologic programs for computers and calculators. simple algorithms for the represe...
15957563 - Evaluation of a high school peer group intervention for at-risk youth.
Publication Detail:
Type:  Journal Article     Date:  2010-07-25
Journal Detail:
Title:  Interdisciplinary sciences, computational life sciences     Volume:  2     ISSN:  1913-2751     ISO Abbreviation:  Interdiscip Sci     Publication Date:  2010 Sep 
Date Detail:
Created Date:  2010-07-26     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101515919     Medline TA:  Interdiscip Sci     Country:  Germany    
Other Details:
Languages:  eng     Pagination:  213-20     Citation Subset:  IM    
Affiliation:
Computational Genetics Laboratory, Department of Genetics, Dartmouth Medical School, Lebanon, NH, 03756, USA, Joshua.Payne@Dartmouth.edu.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Grant Support
ID/Acronym/Agency:
R01 AI059694-06/AI/NIAID NIH HHS; R01 LM009012-04/LM/NLM NIH HHS; R01 LM010098-01/LM/NLM NIH HHS

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Mesenteric ischemia and altered splanchnic hemodynamics: MDCT demonstration.
Next Document:  Chemometrics-based approach to modeling quantitative composition-activity relationships for Radix Ti...