http://sedici.unlp.edu.ar:80/handle/10915/57263 2026-09-16T00:33:14Z 2026-09-16T00:33:14Z Rucci, Enzo http://sedici.unlp.edu.ar:80/handle/10915/57275 2019-06-24T04:03:04Z 2016-11-01T00:00:00Z

Revision Journal of Computer Science & Technology; vol. 16, no. 2 Bioinformatics is one of the areas affected by current HPC problems due to the exponential growth of biological data in the last years and the increasing number of bioinformatics applications demanding HPC to meet performance requirements. One of these applications is sequence alignment, which is considered to be fundamental procedure in biological sciences. The alignment process compares two or more biological sequences and its purpose is to identify regions of similarity among them. The Smith-Waterman (SW) algorithm is a popular method for local sequence alignment that has been used as the basis for many subsequent algorithms, and is often employed as a benchmark when comparing different alignment techniques. However, due to the quadratic computational complexity of Smith-Waterman algorithm, several heuristics are used in practice that reduce the execution time but at the expense of not guaranteeing to discover the optimal local alignments. In order to process the ever increasing quantity of biological data with acceptable response times, it is necessary to develop new computational tools that are capable of accelerating key primitives and fundamental algorithms in an efficient manner from performance and energy consumption points of view. For that reason, this thesis considered, as general objective, evaluating performance and energy efficiency of HPC systems for accelerating Smith-Waterman biological sequence alignment. Es revisión de: http://sedici.unlp.edu.ar/handle/10915/53045; Resumen de la tesis doctoral presentada por el autor en la Universidad de La Plata en marzo de 2016.

2016-11-01T00:00:00Z Bioinformatics is one of the areas affected by current HPC problems due to the exponential growth of biological data in the last years and the increasing number of bioinformatics applications demanding HPC to meet performance requirements. One of these applications is sequence alignment, which is considered to be fundamental procedure in biological sciences. The alignment process compares two or more biological sequences and its purpose is to identify regions of similarity among them. The Smith-Waterman (SW) algorithm is a popular method for local sequence alignment that has been used as the basis for many subsequent algorithms, and is often employed as a benchmark when comparing different alignment techniques. However, due to the quadratic computational complexity of Smith-Waterman algorithm, several heuristics are used in practice that reduce the execution time but at the expense of not guaranteeing to discover the optimal local alignments. In order to process the ever increasing quantity of biological data with acceptable response times, it is necessary to develop new computational tools that are capable of accelerating key primitives and fundamental algorithms in an efficient manner from performance and energy consumption points of view. For that reason, this thesis considered, as general objective, evaluating performance and energy efficiency of HPC systems for accelerating Smith-Waterman biological sequence alignment. Méndez, Mariano http://sedici.unlp.edu.ar:80/handle/10915/57273 2019-06-24T04:02:58Z 2016-11-01T00:00:00Z

Revision Journal of Computer Science & Technology; vol. 16, no. 2 Software production and maintenance is one of the most widely studied topics in computer science. Taking into account that scientists were the first ones to perform this task, even before the Computer Science discipline obtained its name, scientific software production still remains a challenge. This phenomenon may stem from the fact that some authors realized that there is a "gap" between scientific production techniques and industry software techniques [1]. This research work is founded on two relevant contributions to this subject. The first one, the Aristotelian analysis performed by Frederick Brooks on software essence that has been beautifully described in [2]. The second one was proposed by Ralph Johnson in his article "Software development is program transformation." Based on these two great contributions, Change- Driven Development is proposed as a new agile methodology born as a new approach to maintain and develop Scientific Software. Resumen de la tesis doctoral presentada por el autor en la Universidad de La Plata en abril de 2016.

2016-11-01T00:00:00Z Software production and maintenance is one of the most widely studied topics in computer science. Taking into account that scientists were the first ones to perform this task, even before the Computer Science discipline obtained its name, scientific software production still remains a challenge. This phenomenon may stem from the fact that some authors realized that there is a "gap" between scientific production techniques and industry software techniques [1]. This research work is founded on two relevant contributions to this subject. The first one, the Aristotelian analysis performed by Frederick Brooks on software essence that has been beautifully described in [2]. The second one was proposed by Ralph Johnson in his article "Software development is program transformation." Based on these two great contributions, Change- Driven Development is proposed as a new agile methodology born as a new approach to maintain and develop Scientific Software. De Giusti, Laura Cristina Leibovich, Fabiana Yael Chichizola, Franco Naiouf, Marcelo http://sedici.unlp.edu.ar:80/handle/10915/57270 2019-06-24T04:03:01Z 2016-11-01T00:00:00Z

Articulo Journal of Computer Science & Technology; vol. 16, no. 2 Possible methodologies for teaching the concepts of processor heterogeneity and its impact on speedup and efficiency in a parallel system are discussed, as well as energy efficiency of parallel algorithms based on processor power. CMRE (Concurrent Multi Robot Environment) is expanded to be able to consider different virtual clocks in each robot (processor), as well as the cost – both in relation to time and energy consumption – of the operations carried out by the robots (Move, Put Down / Pick Up / Message / Inform). In this paper, we analyze some examples to show how concepts are introduced to students.

2016-11-01T00:00:00Z Possible methodologies for teaching the concepts of processor heterogeneity and its impact on speedup and efficiency in a parallel system are discussed, as well as energy efficiency of parallel algorithms based on processor power. CMRE (Concurrent Multi Robot Environment) is expanded to be able to consider different virtual clocks in each robot (processor), as well as the cost – both in relation to time and energy consumption – of the operations carried out by the robots (Move, Put Down / Pick Up / Message / Inform). In this paper, we analyze some examples to show how concepts are introduced to students. Riveros, Francisco Benítez, Néstor Paciello, Julio Barán, Benjamín http://sedici.unlp.edu.ar:80/handle/10915/57269 2019-06-24T04:03:00Z 2016-11-01T00:00:00Z

Articulo Journal of Computer Science & Technology; vol. 16, no. 2 Evolutionary algorithms present performance drawbacks when applied to Many-objective Optimization Problems (MaOPs). In this work, a novel approach based on Ant Colony Optimization theory (ACO), denominated ACO λ base-p algorithm, is proposed in order to handle Manyobjective instances of the well-known Traveling Salesman Problem (TSP). The proposed algorithm was applied to several Many-objective TSP instances, verifying the quality of the experimental results using the Hypervolume metric. A comparison with other state-of-the-art Multi Objective ACO algorithms as MAS, M3AS and MOACS as well as NSGA2 evolutionary algorithm was made, verifying that the best experimental results were obtained when the proposed algorithm was used, proving a good applicability to MaOPs.

2016-11-01T00:00:00Z Evolutionary algorithms present performance drawbacks when applied to Many-objective Optimization Problems (MaOPs). In this work, a novel approach based on Ant Colony Optimization theory (ACO), denominated ACO λ base-p algorithm, is proposed in order to handle Manyobjective instances of the well-known Traveling Salesman Problem (TSP). The proposed algorithm was applied to several Many-objective TSP instances, verifying the quality of the experimental results using the Hypervolume metric. A comparison with other state-of-the-art Multi Objective ACO algorithms as MAS, M3AS and MOACS as well as NSGA2 evolutionary algorithm was made, verifying that the best experimental results were obtained when the proposed algorithm was used, proving a good applicability to MaOPs. Castro Lechtaler, Antonio Cipriano, Marcelo Malvacio, Eduardo http://sedici.unlp.edu.ar:80/handle/10915/57266 2019-06-24T04:02:56Z 2016-11-01T00:00:00Z

Articulo Journal of Computer Science & Technology; vol. 16, no. 2 This article calculates the theoretical probability of finding repeated primes in a given sample of unbiased issued digital certificates. These values can be used as reference for developing a statistical procedure to audit and control the behavioral pattern of a Public Key Infrastructure (PKI), thus allowing the detection of operational anomalies and the prevention of vulnerabilities of this nature.

2016-11-01T00:00:00Z This article calculates the theoretical probability of finding repeated primes in a given sample of unbiased issued digital certificates. These values can be used as reference for developing a statistical procedure to audit and control the behavioral pattern of a Public Key Infrastructure (PKI), thus allowing the detection of operational anomalies and the prevention of vulnerabilities of this nature. Basgall, María José Hasperué, Waldo Naiouf, Marcelo http://sedici.unlp.edu.ar:80/handle/10915/57265 2019-06-24T04:02:53Z 2016-11-01T00:00:00Z

Articulo Journal of Computer Science & Technology; vol. 16, no. 2 Knowledge Discovery in Databases (KDD) techniques present limitations when the volume of data to process is very large. Any KDD algorithm needs to do several iterations on the complete set of data in order to carry out its work. For continuous data stream processing it is necessary to store part of it in a temporal window. In this paper, we present a technique that uses the size of the temporal window in a dynamic way, based on the frequency of the data arrival and the response time of the KDD task. The obtained results show that this technique reaches a great size window where each example of the stream is used in more than one iteration of the KDD task.

2016-11-01T00:00:00Z Knowledge Discovery in Databases (KDD) techniques present limitations when the volume of data to process is very large. Any KDD algorithm needs to do several iterations on the complete set of data in order to carry out its work. For continuous data stream processing it is necessary to store part of it in a temporal window. In this paper, we present a technique that uses the size of the temporal window in a dynamic way, based on the frequency of the data arrival and the response time of the KDD task. The obtained results show that this technique reaches a great size window where each example of the stream is used in more than one iteration of the KDD task. Gómez Sánchez, Pilar Encinas, Diego Panadero, Javier Bezerra, Aprigio Méndez, Sandra Naiouf, Marcelo De Giusti, Armando Eduardo Rexachs del Rosario, Dolores Luque, e http://sedici.unlp.edu.ar:80/handle/10915/57264 2019-06-24T04:02:48Z 2016-11-01T00:00:00Z

Articulo Journal of Computer Science & Technology; vol. 16, no. 2 In recent years, the use of public cloud platforms as infrastructure has been gaining popularity in many scientific areas and High Performance Computing (HPC) is no exception. These kinds of platforms can be used by system administrators as Test-Bed systems for evaluating and detecting performance inefficiencies in the I/O subsystem, and for taking decisions about the configuration parameters that have influence on the performance of an application, without compromising the performance of the production HPC system. In this paper, we propose a methodology to evaluate parallel applications by using virtual clusters as a test system. Our experimental validation indicates that virtual clusters are a quick and easy solution for system administrators, for analyzing the impact of the I/O system on the I/O kernels of the parallel applications and for taking performance decisions in a controlled environment.

2016-11-01T00:00:00Z In recent years, the use of public cloud platforms as infrastructure has been gaining popularity in many scientific areas and High Performance Computing (HPC) is no exception. These kinds of platforms can be used by system administrators as Test-Bed systems for evaluating and detecting performance inefficiencies in the I/O subsystem, and for taking decisions about the configuration parameters that have influence on the performance of an application, without compromising the performance of the production HPC system. In this paper, we propose a methodology to evaluate parallel applications by using virtual clusters as a test system. Our experimental validation indicates that virtual clusters are a quick and easy solution for system administrators, for analyzing the impact of the I/O system on the I/O kernels of the parallel applications and for taking performance decisions in a controlled environment.