Paper Info
Title
Parallelization of Bayesian Network based SNPs Pattern Analysis and Performance Characterization on SMP/HT
Abstract
Single Nucleotide Polymorphisms (SNPs) is subtle variation in a genomic DNA sequence ofindividuals of the same species. It plays a key role in the pharmaceutical industry to understand variations in drug treatment responses betweenindividuals at the molecular level. Discovering patterns around SNPs loci is very important forbetter understanding the possible origin of SNPs in evolution. Bayesian network has been applied to this problem and got promising results. Since Bayesian Network based SNPs pattern analysis demonstrates high computational complexity, weparallelized this workload on Intel Xeon SMP systems. SNPs' task level parallelism is exploited. Experiment results show that memory is bottleneck: on 8-way Xeon SMP Hyper-Threading enabled system, system memory bandwidth is fullysaturated and memory load access latency is roughly 50% longer than on single processorsystem. Another interesting result is that Intel's Hyper-Threading Technology helps improve the multi-threaded workload's performance by 1.6X speedup. Workload profiling shows that parallel SNPs' data sharing nature matches Hyper-Threading'scache sharing mechanism, and thus greatly reduces cache coherency protocol traffic onshared front side bus. Scalability analysis shows that imbalance and locks are two major factors that may limit the parallel workload speedup on more processor platforms.
Year
DOI
Venue
2004
10.1109/ICPADS.2004.62
ICPADS
Keywords
Field
DocType
parallel workload speedup,8-way xeon smp hyper-threading,system memory bandwidth,bayesian network,snps pattern analysis,hyper-threading technology,memory load access latency,performance characterization,parallel snps,multi-threaded workload,snps locus,dna,multi threading,hyper threading technology,pharmaceuticals,genetics,computational complexity,memory bandwidth,sequences,bioinformatics,pattern recognition,pattern analysis,single nucleotide polymorphisms,parallel processing,genomics,bayesian methods,genomic dna,single nucleotide polymorphism,data mining
Memory bandwidth,Cache,Computer science,Parallel computing,Real-time computing,Hyper-threading,Xeon,Distributed computing,Scalability,Front-side bus,Speedup,Cache coherence
Conference
ISBN
Citations 
PageRank 
0-7695-2152-5
1
0.36
References 
Authors
3
9
Name
Order
Citations
PageRank
Justin Song162.33
Eric Li210.36
Wei Hu318214.17
Steven Ge4959.47
chunrong lai5283.83
Yimin Zhang61536130.17
Xuegong Zhang770451.44
Wenguang Chen8101470.57
Weimin Zheng91889182.48