Browsing by Autor "Harold Castro"

Now showing 1 - 7 of 7

18 GFOG: Green and Flexible Opportunistic Grids
(University of Luxembourg, 2014) Harold Castro; Mario Villamizar; Germán Sotelo; César O. Díaz; Johnatan E. Pecero; Pascal Bouvry; Samee U. Khan
Large-scale computing platforms and current networking technologies enable sharing, selection, and aggregation of highly heterogeneous resources for solving complex real problems. Opportunistic grids are distributed platforms built out of the available resources (volunteers or donors) of an existing hardware platform that
A Location Routing Protocol based on Smart Antennas for Wireless Sensor Networks
(Indian Society for Education and Environment, 2015) Luis Cobo; Harold Castro; Alejandro Quintero
The task of finding and maintaining routes in a Wireless Sensor Networks is a nontrivial task since energy restrictions and sudden changes in node status (e.g. failure) cause frequent and unpredictable topological changes. This work introduces a novel location routing protocol that uses smart antennas to estimate nodes positions into the network and to deliver information basing routing decisions on neighbor’s status connection and relative position, named LBRA. The main purpose of LBRA is to eliminate network control overhead as much as possible. To achieve this goal, the algorithm employs local position for route decision, implements a novel mechanism to collect the location information and involves only route participants in the synchronization of location information. In addition, the protocol uses node battery information to make power aware routing decisions. In order to asses LBRA a series of simulations were designed with the help of the Network Simulator 2 (ns2). The experiment results showed that LBRA succeed in reducing the control overhead and the routing load, improving the packet delivery rate. Additionally, network power depletion is more balanced, since routing decisions are made depending on nodes’ battery level Keywords: Local Positioning, Routing Protocol, Smart Antennas, Wireless Sensor Networks
Analysis of Gromacs MPI Using the Opportunistic Cloud Infrastructure UnaCloud
(2012) Nathalia Garcés; Harold Castro; Paula Delgado; Andres Gonz'lez; Carlos A. Jaramillo; Natalia Peñaranda; María del Pilar Delgado
This paper shows and analyzes the execution of a molecular dynamic application that uses Message Passing Interface (MPI) mechanism-Gromacs MPI-over a cloud infrastructure (UnaCloud) supported by desktop computers. The main objective is to find a solution to support Gromacs-MPI on UnaCloud. This coupling was carried out in order to predict and to redefine the Helicobacter pylori Cag A protein 3D structure. Although the structure of eight indigenous sequences was obtained, the handle of resource discovery and failure recovery on the opportunistic infrastructure was achieved manually, restricting the application scope of the solution. To eliminate these restrictions, a mechanism to automate the process execution on UnaCloud was identified and proposed.
Boosting Advanced Computational Applications and Resources in Latin America through Collaboration and Sharing
(AIP Publishing, 2018) Esteban Mocskos; Carlos Barrios-Hernandez; Harold Castro; Dennis Cazar; Sergio Nesmachnow; Rafael Mayo-García
Although computing research and facilities in Latin America have been developing steadily, a remarkable gap nevertheless remains in the availability of resources and specialized human resources compared to other regions. RICAP (Red Iberoamericana de Computación de Altas Prestaciones, or Ibero-American Network for High-Performance Computing) aims to fill this gap by means of a strategic and advanced computational infrastructure that includes both high-performance and high-throughput computing platforms. This network will also develop software tools to facilitate this infrastructures accessibility and computational efficiency to encourage use by the Latin American computing community as well as focus on strengthening and training human resources in both parallel programming techniques and large-scale computing platform operations.
Ejecutando y Pausando Aplicaciones Distribuidas Corriendo sobre Desktop Clouds Mediante Snapshots Globales
(Costa Rica Institute of Technology, 2020) Carlos E. Gómez; Jaime Chavarriaga; David C. Bonilla; Harold Castro
Los desktop clods dependen de recursos computacionales volátiles. Por ejemplo, plataformas como cuCloud y UnaCloud ejecutan aplicaciones científicas en máquinas virtuales que aprovechan recursos ociosos en salas de cómputo y laboratorios. Lamentablemente, estos recursos pueden ser reclamados por los usuarios, apagados o presentar fallas en cualquier momento. La aplicación que se ejecuta en estas plataformas sufre interferencias e interrupciones que no ocurren en plataformas dedicadas. Nosotros hemos estado investigando cómo enfrentar estas interrupciones para aumentar la confiabilidad de la plataforma y soportar aplicaciones que se ejecutan durante largos períodos de tiempo. Este artículo describe una aplicación de nuestro Protocolo de Snapshot Global, el cual puede emplearse para ejecutar y pausar aplicaciones distribuidas que se ejecutan en desktop clouds. Nosotros encontramos que, en estos entornos, la cantidad de fallas causadas por los usuarios de los computadores de escritorio es mayor que la causada por el hardware y las comunicaciones. Allí, cuando se detiene un sistema distribuido que se ejecuta en las máquinas virtuales de un desktop cloud, nosotros podemos reanudar la ejecución usando los mismos computadores y finalizar exitosamente la ejecución de las aplicaciones.
Expanding Horizons: Advancing HPC Education in Colombia through CyberColombia's Summer Schools
(2024) Aurelio Vivas; C. E. Álvarez; Jose M. Monsalve Diaz; Esteban Ordiano Hernández; Juan Guillermo Lalinde Pulido; Harold Castro
High-performance computing (HPC) is an important tool for research, development, and the industry.Moreover, with the recent expansion of machine learning applications, the need for HPC is increasing even further.However, in developing countries with limited access to the HPC ecosystem, the lack of infrastructure, expertise, and access to knowledge represents a major obstacle to the expansion of HPC.Under these constraints, the adoption of HPC by communities presents several challenges.The HPC Summer Schools are an initiative of CyberColombia that has taken place over the past 5 years.It aims to develop the critical skills, strategic planning, and networking required to make available, disseminate, and maintain the knowledge of high-performance computing and its applications in Colombia.Here we report the results of this series of Summer Schools.The events have proven to be successful, with over 200 participants from more than 20 institutions.Participants span different levels of expertise, including undergraduate and graduate students as well as professionals.We also describe successful use cases for HPC cloud solutions, namely Chameleon Cloud. INTRODUCTIONSupercomputers are of paramount importance in solving critical challenges in many fields.Some of these are atmospheric simulation, genome sequencing, and cybersecurity, to name a few [15].In Colombia, this area is developing at a slower pace in comparison to leading countries such as the USA, Japan, and European countries.Colombia only spent 0.29% of its Gross domestic product (GDP) on Research and Development according to the UNESCO statistics [23].This level of investment is 0.92% behind South American countries such as Brazil, which is one of the leading Latin American countries in supercomputing technology.Differences in investment levels on the development of supercomputers [10] and adoption of HPC are some of the factors that heavily influence this gap.
Perspectives of UnaCloud: An Opportunistic Cloud Computing Solution for Facilitating Research
(2012) Juan David Abella Osorio; Harold Castro; Francisco Brasileiro
This paper presents UnaCloud, an opportunistic Infraestructure as a Service implementation oriented to academic and research institutions, where the IaaS model is supported through the opportunistic use of idle computing resources available in the institution campus, providing researchers with significant and low cost computing capabilities. Also presented are the existing perspectives for current and future work on this project, related work about different concepts of opportunistic or volunteer cloud computing, and the significance and potential impact of this project in the regional research community.