检索结果-内蒙古大学图书馆

GPU Acceleration of Finding Maximum Eigenvalue of Positive Matrices 1

14th International Conference on Algorithms and Architectures for parallel Processing (ICA3PP)

作者： Tian, Ning Guo, Longjiang Ai, Chunyu Ren, Meirui Li, Jinbao Heilongjiang Univ Sch Comp Sci & Technol Harbin Peoples R China Key Lab Database & Parallel Comp Heilongjiang Peoples R China Univ S Carolina Upstate Div Math & Comp Sci Upstate Peoples R China

ISBN: (数字)9783319111940

ISBN: (纸本)9783319111940;9783319111933

Matrix eigenvalue theory has become an important analysis tool in scientific computing. Sometimes, people do not need to find all eigenvalues but only the maximum eigenvalue. Existing algorithms of finding the maximum eigenvalue of matrices are implemented sequentially. With the increasing of the orders of matrices, the workload of calculation is getting heavier. Therefore, traditional sequential methods are unable to meet the need of fast calculation for large matrices. This paper proposes a parallel algorithm named PA-ST to find the maximum eigenvalue of positive matrices by using similarity transformation which is implemented by CUDA (computer Unified Device Architecture) on GPU (Graphic Process Unit). To the best of our knowledge, this is the first CUDA based parallel algorithm of calculating maximum eigenvalue of matrices. In order to improve the performance, optimization techniques are applied in this paper such as using the shared memory rather than the global memory to improve the speed of computation, avoiding bank conflicts by setting the span index, satisfying the principle of coalesced memory access, and by using single-precision floating-point arithmetic and the pinned memory to reduce the copy operation and obtain higher data transfer bandwidth between the host and the GPU device. The experimental results show that the similarity transformation technique can significantly shorten the running time compared to the sequential algorithm and the speedup ratio is nearly stable when the number of iterations increases. As the matrix order increases, the running time of the sequential algorithm and PA-ST increases correspondingly. Experiments also show that the speedup ratio of the PA-ST is between 2.85 and 35.028.

关键词： Maximum Eigenvalue Positive Matrix Similarity Transformation GPU CUDA

来源：评论

学校读者我要写书评

暂无评论

Motif Recognition parallel Algorithm based on GPU 6

Motif Recognition Parallel Algorithm based on GPU

引用

6th International Conference on Cyber-Enabled Distributed computing and Knowledge Discovery (CyberC)

作者： Zheng, Jinliang Lu, Jun Shi, Xinyi Shi, Yan Jing, Ruiqing Heilongjiang Univ Coll Comp Sci & Technol Harbin Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Key Lab Database & Parallel Comp Heilongjiang Pro Harbin Peoples R China

ISBN: (纸本)9781479962365

In this paper, a GPU-based parallel algorithm is proposed to improve the processing efficiency of motif recognition algorithm. The work includes a serial motif recognition algorithm and a parallel algorithm based on GPU. Our GPU parallel algorithm is compared with the serial algorithm by using of 1 KB promoter data of five kinds of plant genes upstream regions. The experimental results show that a factor of 20 speeds can be achieved. It means that there are a lot of advantages by GPU parallel technology on gene motif recognition algorithm. It is significant to the great amount of data analysis work of genetic sequence.

关键词： GPU parallel Promoter Motif Recognition

来源：评论

学校读者我要写书评

暂无评论

The key Algorithms of Promoter Data parallel Processing based on OpenMP 6

The Key Algorithms of Promoter Data Parallel Processing base...

引用

6th International Conference on Cyber-Enabled Distributed computing and Knowledge Discovery (CyberC)

作者： Shi, Yan Lu, Jun Shi, Xinyi Zheng, Jinliang Li, Jun Heilongjiang Univ Coll Comp Sci & Technol Harbin Peoples R China Univ Chinese Acad Sci Harbin Peoples R China Key Lab Database & Parallel Comp Heilongjiang Pro Harbin Peoples R China

ISBN: (纸本)9781479962365

The key algorithm of parallel technology based on OpenMP is advanced to dispose the promoter data. The promoter data are intercepted from the upstream area of five plants sequences. The five plants contain Arabidopsis Thaliana, Soybean, Alfalfa, Rice and Beans. The processing includes disturbing the sequences in random, calculating the P value, selecting the significant motifs from the frequent motifs, labeling the sequence number and so on. The serial algorithm and the parallel algorithm are compared in the implementation procedure. The experimental result shows that the OpenMP parallel technology can effectively improve the efficiency of the promoter data analysis and processing. It is a realistic significance to the vast amounts of biological information data processing.

关键词： gene openmp biological information promoter

来源：评论

学校读者我要写书评

暂无评论

GPU Acceleration of Finding LPRs in DNA Sequence Based on SUA Index

GPU Acceleration of Finding LPRs in DNA Sequence Based on SU...

引用

33rd IEEE International Performance, computing, and Communications Conference (IPCCC)

作者： Du, Shufang Guo, Longjiang Ai, Chunyu Ren, Meirui Qu, Hao Li, Jinbao Heilongjiang Univ Sch Comp Sci & Technol Harbin 150080 Heilongjiang Peoples R China Key Lab Database & Parallel Comp Harbin 150080 Heilongjiang Peoples R China Univ South Carolina Upstate Div Math & Comp Sci Spartanburg SC 29303 USA

ISBN: (纸本)9781479975754

The repetitions in biological sequence analysis are of great biological significance. Finding the repetitions has been a hot topic in gene projects naturally. In recent years, graphics processing unit (GPU) has been far exceeded the CPU in terms of computing capability and memory bandwidth, especially CUDA dramatically increases in computing performance by harnessing the power of the GPUs. This paper proposes efficient parallel algorithms on CUDA to accelerate finding PTRs which is redefined as LPRs based on the SUA Index. The proposed parallel algorithms have been utilized with the parallel primitives offered by Thrust library and the effective parallel bit compression technology based on division to achieve better acceleration. Optimization techniques include CUDA streams technology are also realized to reduce transmission latency. Experimental results show that the proposed parallel algorithms are faster than the benchmark with 1.6 similar to 5.4 speedup.

关键词： Biological Sequence PTR Largest Pattern Repetition CUDA Acceleration

来源：评论

学校读者我要写书评

暂无评论

GPU Acceleration of Finding Frequent Patterns over Large Biological Sequence 20

GPU Acceleration of Finding Frequent Patterns over Large Bio...

引用

20th IEEE International Conference on parallel and Distributed Systems (ICPADS)

作者： Du, Shufang Guo, Longjiang Ai, Chunyu Li, Jinbao Ren, Meirui Guo, Yahong Heilongjiang Univ Sch Comp Sci & Technol Harbin 150080 Heilongjiang Peoples R China Key Lab Database & Parallel Comp Harbin 150080 Heilongjiang Peoples R China Univ South Carolina Upstate Div Math & Comp Sci Spartanburg SC 29303 USA Heilongjiang Univ Sch Informat Sci & Technol Harbin 150080 Heilongjiang Peoples R China

ISBN: (纸本)9781479976157

Biological frequent patterns usually correspond to the important function (or structure) in biological sequences. Along with the rapid growth of biological sequences, it is significant to find frequent patterns over a large bio-sequence efficiently. However, most of existing algorithms need to produce lots of short patterns or projected databases, which influence the efficiency badly and also increase the cost of space. Graphics processing units (GPUs) embracing many core computing devices, have been extensively applied to accelerate computation performance in many areas. In order to meet the demand of biologists, we redefine the frequent pattern problem with length constraints for finding frequent patterns. We present pruning optimization method for the serial algorithm (POSA), and based on this technique, we propose a parallel algorithm (POPA) which not only reduces the time complexity with a low space cost but also obtains better performance on CUDA. To validate the presented algorithms, we implemented the algorithms on multiple-core CPU and various GPU devices. Also, CUDA optimization techniques are applied to speed up calculation in the paper. Finally, experimental results show that compared with the serial algorithm on CPU with six cores, POSA achieves 1.2 similar to 4.5 speedup, and POPA gains 3 similar to 20 speedup.

关键词： Frequent Pattern CUDA Acceleration Large Biological Sequence

来源：评论

学校读者我要写书评

暂无评论

Research on Universal Combinatorial Coding

引用

SCIENTIFIC WORLD JOURNAL 2014年第1期2014卷 414613-414613页

作者： Lu, Jun Zhang, Zhuo Mo, Juan Heilongjiang Univ Coll Comp Sci & Technol Harbin 150080 Peoples R China Key Lab Database & Parallel Comp Heilongjiang Pro Harbin 150080 Peoples R China

The conception of universal combinatorial coding is proposed. Relations exist more or less in many coding methods. It means that a kind of universal coding method is objectively existent. It can be a bridge connecting many coding methods. Universal combinatorial coding is lossless and it is based on the combinatorics theory. The combinational and exhaustive property make it closely related with the existing code methods. Universal combinatorial coding does not depend on the probability statistic characteristic of information source, and it has the characteristics across three coding branches. It has analyzed the relationship between the universal combinatorial coding and the variety of coding method and has researched many applications technologies of this coding method. In addition, the efficiency of universal combinatorial coding is analyzed theoretically. The multicharacteristic and multiapplication of universal combinatorial coding are unique in the existing coding methods. Universal combinatorial coding has theoretical research and practical application value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quick-MergeSort Algorithm Based on Multi-coreLinux

Quick-MergeSort Algorithm Based on Multi-coreLinux

引用

International Conference on Mechatronic Sciences, Electric Engineering and computer (MEC)

作者： Liu, Yang Yang, Yan Heilongjiang Univ Sch Comp Sci & Technol Key Lab Database & Parallel Comp Heilongjiang Pro Harbin Peoples R China

ISBN: (纸本)9781479925650

Sorting a list of input numbers is one of the most fundamental problems in the field of computer science. This paper presents an efficient implementation and detailed analysis of quick sort algorithm called QM-sort on Multi-core CPU architectures. Our QM-sort has two stages. The first stage is making blocks sorted, and the second stage is merging the sorted blocks. At the first stage, we propose a parallel quick sort algorithm named BPQsort. The run time of BPQsort achieves 40%-50% better than Qsort (STL), so we make blocks sorted more efficient. On the other hand, our algorithm can read file in parallel, thus reduce the time of reading file from disk. At the second stage, our parallel merge algorithm can operate the data on consecutive memory. Thus we avoid the expensive unaligned load/store operations, thus make our merge algorithm faster. At last, the run time of QM-sort is 10%-15% better than quick sort based on OpenMP.

关键词： QuickSort Sort Multi-core CPU Linux Multi-thread

来源：评论

学校读者我要写书评

暂无评论

Time Constraint-based Team Formation in Social Networks

Time Constraint-based Team Formation in Social Networks

引用

International Conference on Mechatronic Sciences, Electric Engineering and computer (MEC)

作者： Han, Xue Liu, Yong Guo, Xingkai Wu, Xianyi Song, Xiaolong Heilongjang Univ Sch Comp Sci & Technol Harbin Peoples R China Heilongjang Univ Key Lab Database & Parallel Comp Heilongjiang Pro Harbin Peoples R China

ISBN: (纸本)9781479925650

We investigate the problem of discovering a team of experts from a social network. Given a task with the skill set and the time span length, our goal is to obtain a team that covers all the skills, and have a low communication cost. Furthermore, each member of the team must have common free time whose length is no less than the span length required by the task. Previous works only attempt to cover the required skills and minimize the communication cost without taking the common free time of the individuals into account. We are the first to consider time factor in team formation and thus propose a novel team formation formulation with time constraint. We show that the problem is NP-hard. We first extend the RarestFirst algorithm to deal with our new problem, then propose two novel pruning strategies, called time pruning and skill pruning respectively, and an efficient algorithm called TSP-TF, to efficiently obtain an effective team for a given task. Experimental results show that TSP-TF outperforms the generalized RarestFirst algorithm by more than an order of magnitude.

关键词： social network team formation time constrait

来源：评论

学校读者我要写书评

暂无评论

Team Formation with Time Limit in Social Networks

Team Formation with Time Limit in Social Networks

引用

International Conference on Mechatronic Sciences, Electric Engineering and computer (MEC)

作者： Yang, Yan Hu, Haiyue Heilongjiang Univ Sch Comp Sci & Technol Key Lab Database & Parallel Comp Heilongjiang Pro Harbin Peoples R China Heilongjiang Univ Sch Comp Sci & Technol Harbin Peoples R China

ISBN: (纸本)9781479925650

Team formation is finding a team of experts in a social network to complete a given task. In many tasks, there is a deadline to complete them. Previous research work doesnt consider this point. In this paper, an attribute time is considered in team formation problem. For an expert completing a skill will cost some time. To complete a task, experts should communicate with each other, which will cost some time too. This paper is the first to consider these two elements and define a new cost model TotalCost. Based on the new cost model, we propose two approximation algorithms. The objective is to find a team not only covers the skills that the task requires as well as completes every skill in the specified time and minimize TotalCost. Experimental results show that the team built by our methods satisfies the given task and with a low TotalCost.

关键词： social network team formation time limit TotalCost

来源：评论

学校读者我要写书评

暂无评论

Bipartite Graph-based keyword Query Results Recommendation

Bipartite Graph-based Keyword Query Results Recommendation

引用

International Conference on Mechatronic Sciences, Electric Engineering and computer (MEC)

作者： Feng, Limin Yang, Yan Heilongjiang Univ Sch Comp Sci & Technol Harbin Peoples R China Heilongjiang Univ Sch Comp Sci & Technol Key Lab Database & Parallel Comp Heilongjiang Pro Harbin Peoples R China

ISBN: (纸本)9781479925650

Relational database is widely used in people's daily life and productions. keyword search in relational database makes people search structured information from database as using search engine. So it has become a research hotspot. In recent years, there are a lot of research works about how to use historical query information to improve query efficiency. The existing works can be divided into two main aspects: query expansion and query recommendation. These two aspects have common feature, that is, they both use the historical words to improve query efficiency. If the results of historical query can be directly recommended to the current query, the query efficiency will be improved. But there are not any works using recommended model of recommended system to help keyword search. We have found that recommended model can be used to improve efficiency. We are the first one to use bipartite graph model, and propose query result recommendation algorithm, namely, Query_base algorithm and Distance_base algorithm. Finally this paper analyzes the factors which affect the efficiency of the algorithms, and verified the performance and higher accuracy of the recommendation algorithms by experiments.

关键词： database bipartite graph result recommend

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：