Multiple keyword matching is an important problem in text processing that involves the location of all the positions of an input string where one or more keywords from a finite set occur. Modern multiple keyword match...
详细信息
In this paper we present the integration of state of the art, open source, production level tools into a parallel programming environment, used for teaching parallel programming in MPI and OpenMP. Based on experiences...
详细信息
With the remarkable increase in the number of DNA and proteins sequences, it is very important to study the performance of multiple pattern matching algorithms when querying sequence patterns in biological sequence da...
详细信息
ISBN:
(纸本)9789898425362
With the remarkable increase in the number of DNA and proteins sequences, it is very important to study the performance of multiple pattern matching algorithms when querying sequence patterns in biological sequence databases. In this paper, we present a performance study of the running time of well known multiple pattern matching algorithms on widely used biological sequence databases containing the building blocks of nucleotides (in the case of nucleic acid sequence databases) and amino acids (in the case of protein sequence databases).
Multiple keyword matching is an important problem in text processing that involves the location of all the positions of an input string where one or more keywords from a finite set occur. Modern multiple keyword match...
详细信息
Multiple keyword matching is an important problem in text processing that involves the location of all the positions of an input string where one or more keywords from a finite set occur. Modern multiple keyword matching algorithms can scan the input string in a single pass by preprocessing the keyword set, an essential phase that affects the overall performance of each algorithm. This paper presents a performance evaluation in terms of preprocessing of the well known Commentz-Walter, Wu-Manber, Set Backward Oracle Matching and Salmela-Tarhio-Kyt\"{o}joki multiple keyword matching algorithms for different types of keywords and for several problem parameters.
In this paper we present the integration of state of the art, open source, production level tools into a parallel programming environment, used for teaching parallel programming in MPI and OpenMP. Based on experiences...
详细信息
In this paper we present the integration of state of the art, open source, production level tools into a parallel programming environment, used for teaching parallel programming in MPI and OpenMP. Based on experiences introduced during this case study, and opinions gathered by an online questionnaire, a refined set of missing features that would strengthen the environment's educational role is defined.
parallel programming is the future of computer science. Now days shift to parallelprocessing makes it even more useful. This research effort aims at helping parallelism education on real life target systems, using pr...
详细信息
Multiple keyword matching is a basic problem in computer science and is used to locate all the appearances of a finite set of keywords (the so called "patterns") inside an input string (the so called "t...
parallel programming is the future of computer science. Now days shift to parallelprocessing makes it even more useful. This research effort aims at helping parallelism education on real life target systems, using pr...
详细信息
parallel programming is the future of computer science. Now days shift to parallelprocessing makes it even more useful. This research effort aims at helping parallelism education on real life target systems, using production oriented software tools. On its beginning, a survey of software environments for parallel programming is presented. The surveyed software environments are categorized according to their main function. An identity is synthesized for each environment by software and project attributes. Based on it and a set of proper criteria there are selected two groups of tools, those of primary and those of secondary interest for this research. An analysis of functional characteristics is performed for both groups. From the first group an open source software environment is chosen as the basis platform that will be enriched with education oriented enhancements. The characteristics analysis is exploited for the proposal of a research and development framework. Its target is the support of parallel programming, on real life target systems, using production oriented software environments.
Graphics processing units (GPUs) have evolved over the past few years from dedicated graphics rendering devices to powerful parallel processors, outperforming traditional central processing units (CPUs) in many areas ...
详细信息
Graphics processing units (GPUs) have evolved over the past few years from dedicated graphics rendering devices to powerful parallel processors, outperforming traditional central processing units (CPUs) in many areas of scientific computing. The use of GPUs as processing elements was very limited until recently, when the concept of general-purpose computing on graphics processing units (GPGPU) was introduced. GPGPU made possible to exploit the processing power and the memory bandwidth of the GPUs with the use of APIs that hide the GPU hardware from programmers. This paper presents experimental results on the parallelprocessing for some well known on-line string matching algorithms using one such GPU abstraction API, the Compute Unified Device Architecture (CUDA).
In the last decade an unprecedented development in bioinformatics has been observed. An extremely high number of organisms have been sequenced and included in genomic databases. The huge amount of data produced needs ...
详细信息
In the last decade an unprecedented development in bioinformatics has been observed. An extremely high number of organisms have been sequenced and included in genomic databases. The huge amount of data produced needs to be stored and processed for further analysis. Scientists, have researched algorithms for finding complicated patterns in DNA sequences, but there is a need for computational power and large storage systems, in order to implement specific algorithms in as many as possible DNA sequences stored in large Databases and save the results produced for future use. Recently, a number of pattern matching algorithms that allowing gaps have been introduced and Grid is an emerging technology that seems to be helpful in this kind of biomedical research. In this paper, we present our effort towards the construction of a user friendly Interface for accessing the Grid EGEE platform. The Interface is a specific one and was built to perform Pattern-Matching with Bounded Gaps in Genomic and Proteomic Sequences. The algorithm and the Interface is tested with small and large DNA and protein sequences as an input, downloaded from a gene and protein repository, NCBI (National Center for Biotechnology Information) and the gathered results produced are presented.
暂无评论