Non-preemptive and SRP-based fullypreemptive scheduling of real-time Software Transactional Memory

Recent embedded processor architectures containing multiple heterogeneous cores and non-coherent caches renewed attention to the use of Software Transactional Memory (STM) as a building block for developing parallel applications. STM promises to ease concurrent and parallel software development, but relies on the possibility of abort conflicting transactions to maintain data consistency, which in turns affects the execution time of tasks carrying transactions. Because of this fact the timing behaviour of the task set may not be predictable, thus it is crucial to limit the execution time overheads resulting from aborts. In this paper we formalise a FIFO-based algorithm to order the sequence of commits of concurrent transactions. Then, we propose and evaluate two non-preemptive and one SRP-based fully-preemptive scheduling strategies, in order to avoid transaction starvation.

RADIC II: a fault tolerant architecture with flexible dynamic redundancy

The demand for computational power has been leading the improvement of the High Performance Computing (HPC) area, generally represented by the use of distributed systems like clusters of computers running parallel applications. In this area, fault tolerance plays an important role in order to provide high availability isolating the application from the faults effects. Performance and availability form an undissociable binomial for some kind of applications. Therefore, the fault tolerant solutions must take into consideration these two constraints when it has been designed. In this dissertation, we present a few side-effects that some fault tolerant solutions may presents when recovering a failed process. These effects may causes degradation of the system, affecting mainly the overall performance and availability. We introduce RADIC-II, a fault tolerant architecture for message passing based on RADIC (Redundant Array of Distributed Independent Fault Tolerance Controllers) architecture. RADIC-II keeps as maximum as possible the RADIC features of transparency, decentralization, flexibility and scalability, incorporating a flexible dynamic redundancy feature, allowing to mitigate or to avoid some recovery side-effects.

Entorno de desarrollo para clusters

El presente trabajo expone los entornos de desarrollo de aplicaciones paralelas en sistemas distribuidos. Se ha dedicado especial atención a los entornos gráficos, como plataforma de acceso al cluster. Dada la cantidad de alternativas a seleccionar en este tipo de entornos, como puede ser la parametrización de las aplicaciones, especificación de la arquitectura a utilizar de los nodos, caracterización de la carga, políticas de planificación, etc, hace que este trabajo pueda servir de punto inicial de partida a usuarios que deseen iniciarse en este tipo de entornos.

Análisis de rendimiento de aplicaciones paralelas de memoria compartida: problema N-body

Este trabajo analiza el rendimiento de cuatro nodos de cómputo multiprocesador de memoria compartida para resolver el problema N-body. Se paraleliza el algoritmo serie, y se codifica usando el lenguaje C extendido con OpenMP. El resultado son dos variantes que obedecen a dos criterios de optimización diferentes: minimizar los requisitos de memoria y minimizar el volumen de cómputo. Posteriormente, se realiza un proceso de análisis de las prestaciones del programa sobre los nodos de cómputo. Se modela el rendimiento de las variantes secuenciales y paralelas de la aplicación, y de los nodos de cómputo; se instrumentan y ejecutan los programas para obtener resultados en forma de varias métricas; finalmente se muestran e interpretan los resultados, proporcionando claves que explican ineficiencias y cuellos de botella en el rendimiento y posibles líneas de mejora. La experiencia de este estudio concreto ha permitido esbozar una incipiente metodología de análisis de rendimiento, identificación de problemas y sintonización de algoritmos a nodos de cómputo multiprocesador de memoria compartida.

Análisis y sintonización de aplicaciones paralelas/distribuidas de bioinformática: caso de estudio mpiBLAST

En termes de temps d'execució i ús de dades, les aplicacions paral·leles/distribuïdes poden tenir execucions variables, fins i tot quan s'empra el mateix conjunt de dades d'entrada. Existeixen certs aspectes de rendiment relacionats amb l'entorn que poden afectar dinàmicament el comportament de l'aplicació, tals com: la capacitat de la memòria, latència de la xarxa, el nombre de nodes, l'heterogeneïtat dels nodes, entre d'altres. És important considerar que l'aplicació pot executar-se en diferents configuracions de maquinari i el desenvolupador d'aplicacions no port garantir que els ajustaments de rendiment per a un sistema en particular continuïn essent vàlids per a d'altres configuracions. L'anàlisi dinàmica de les aplicacions ha demostrat ser el millor enfocament per a l'anàlisi del rendiment per dues raons principals. En primer lloc, ofereix una solució molt còmoda des del punt de vista dels desenvolupadors mentre que aquests dissenyen i evaluen les seves aplicacions paral·leles. En segon lloc, perquè s'adapta millor a l'aplicació durant l'execució. Aquest enfocament no requereix la intervenció de desenvolupadors o fins i tot l'accés al codi font de l'aplicació. S'analitza l'aplicació en temps real d'execució i es considra i analitza la recerca dels possibles colls d'ampolla i optimitzacions. Per a optimitzar l'execució de l'aplicació bioinformàtica mpiBLAST, vam analitzar el seu comportament per a identificar els paràmetres que intervenen en el rendiment d'ella, com ara: l'ús de la memòria, l'ús de la xarxa, patrons d'E/S, el sistema de fitxers emprat, l'arquitectura del processador, la grandària de la base de dades biològica, la grandària de la seqüència de consulta, la distribució de les seqüències dintre d'elles, el nombre de fragments de la base de dades i/o la granularitat dels treballs assignats a cada procés. El nostre objectiu és determinar quins d'aquests paràmetres tenen major impacte en el rendiment de les aplicacions i com ajustar-los dinàmicament per a millorar el rendiment de l'aplicació. Analitzant el rendiment de l'aplicació mpiBLAST hem trobat un conjunt de dades que identifiquen cert nivell de serial·lització dintre l'execució. Reconeixent l'impacte de la caracterització de les seqüències dintre de les diferents bases de dades i una relació entre la capacitat dels workers i la granularitat de la càrrega de treball actual, aquestes podrien ser sintonitzades dinàmicament. Altres millores també inclouen optimitzacions relacionades amb el sistema de fitxers paral·lel i la possibilitat d'execució en múltiples multinucli. La grandària de gra de treball està influenciat per factors com el tipus de base de dades, la grandària de la base de dades, i la relació entre grandària de la càrrega de treball i la capacitat dels treballadors.

Predictive and distributed routing balancing (PR-DRB): high speed interconnection networks

Current parallel applications running on clusters require the use of an interconnection network to perform communications among all computing nodes available. Imbalance of communications can produce network congestion, reducing throughput and increasing latency, degrading the overall system performance. On the other hand, parallel applications running on these networks posses representative stages which allow their characterization, as well as repetitive behavior that can be identified on the basis of this characterization. This work presents the Predictive and Distributed Routing Balancing (PR-DRB), a new method developed to gradually control network congestion, based on paths expansion, traffic distribution and effective traffic load, in order to maintain low latency values. PR-DRB monitors messages latencies on intermediate routers, makes decisions about alternative paths and record communication pattern information encountered during congestion situation. Based on the concept of applications repetitiveness, best solution recorded are reapplied when saved communication pattern re-appears. Traffic congestion experiments were conducted in order to evaluate the performance of the method, and improvements were observed.

Phylogenetic Code in the Cloud - Can it Meet the Expectations?

Cloud computing has recently become very popular, and several bioinformatics applications exist already in that domain. The aim of this article is to analyse a current cloud system with respect to usability, benchmark its performance and compare its user friendliness with a conventional cluster job submission system. Given the current hype on the theme, user expectations are rather high, but current results show that neither the price/performance ratio nor the usage model is very satisfactory for large-scale embarrassingly parallel applications. However, for small to medium scale applications that require CPU time at certain peak times the cloud is a suitable alternative.

Aplicación de la ingeniería del software sobre la herramienta MATE: Common y DMLib

Aquest projecte intenta implantar una metodologia de treball sobre MATE. MATE es una eina de sintonització d'aplicacions paral·leles sorgida de la tesis doctoral d'Anna Sikora a 2003. Vistos els resultats obtinguts, es va decidir donar un pas endavant i convertir-la en un producte software Open Source. Per fer-ho ha sigut necessari aplicar una serie d'estàndards i fer un proces de tests. En aquest treball s'ha creat part de la metodologia i s'han modificat dos dels mòduls principals.

Aplicación de la ingeniería software sobre la herramienta MATE Analyzer

MATE (Monitoring, Analysis and Tuning Environment) es un proyecto que surge en 2004 como tesis doctoral de Anna Sikora con el propósito de investigar la mejora de rendimiento de aplicaciones paralelas a través de la modificación dinámica. Nuestro proyecto supone un paso adelante en cuestiones de calidad de software y pretende dotar al proyecto MATE de una base de desarrollo sólida de cara a futuras lineas de trabajo. Para ello se hace frente a la problemática desde tres perspectivas: la creación de una metodología de desarrollo (y su aplicación sobre el proyecto existente), la implantación de un entorno de desarrollo de soporte y el desarrollo de nuevas características para favorecer la portabilidad y la usabilidad, entre otros aspectos.

RADIC: un middleware de tolerancia a fallos que preserva el rendimiento

La tolerancia a fallos es una línea de investigación que ha adquirido una importancia relevante con el aumento de la capacidad de cómputo de los súper-computadores actuales. Esto es debido a que con el aumento del poder de procesamiento viene un aumento en la cantidad de componentes que trae consigo una mayor cantidad de fallos. Las estrategias de tolerancia a fallos actuales en su mayoría son centralizadas y estas no escalan cuando se utiliza una gran cantidad de procesos, dado que se requiere sincronización entre todos ellos para realizar las tareas de tolerancia a fallos. Además la necesidad de mantener las prestaciones en programas paralelos es crucial, tanto en presencia como en ausencia de fallos. Teniendo en cuenta lo citado, este trabajo se ha centrado en una arquitectura tolerante a fallos descentralizada (RADIC – Redundant Array of Distributed and Independant Controllers) que busca mantener las prestaciones iniciales y garantizar la menor sobrecarga posible para reconfigurar el sistema en caso de fallos. La implementación de esta arquitectura se ha llevado a cabo en la librería de paso de mensajes denominada Open MPI, la misma es actualmente una de las más utilizadas en el mundo científico para la ejecución de programas paralelos que utilizan una plataforma de paso de mensajes. Las pruebas iniciales demuestran que el sistema introduce mínima sobrecarga para llevar a cabo las tareas correspondientes a la tolerancia a fallos. MPI es un estándar por defecto fail-stop, y en determinadas implementaciones que añaden cierto nivel de tolerancia, las estrategias más utilizadas son coordinadas. En RADIC cuando ocurre un fallo el proceso se recupera en otro nodo volviendo a un estado anterior que ha sido almacenado previamente mediante la utilización de checkpoints no coordinados y la relectura de mensajes desde el log de eventos. Durante la recuperación, las comunicaciones con el proceso en cuestión deben ser retrasadas y redirigidas hacia la nueva ubicación del proceso. Restaurar procesos en un lugar donde ya existen procesos sobrecarga la ejecución disminuyendo las prestaciones, por lo cual en este trabajo se propone la utilización de nodos spare para la recuperar en ellos a los procesos que fallan, evitando de esta forma la sobrecarga en nodos que ya tienen trabajo. En este trabajo se muestra un diseño propuesto para gestionar de un modo automático y descentralizado la recuperación en nodos spare en un entorno Open MPI y se presenta un análisis del impacto en las prestaciones que tiene este diseño. Resultados iniciales muestran una degradación significativa cuando a lo largo de la ejecución ocurren varios fallos y no se utilizan spares y sin embargo utilizándolos se restablece la configuración inicial y se mantienen las prestaciones.

What to consider for applying backfilling on non-dedicated environments

The resource utilization level in open laboratories of several universities has been shown to be very low. Our aim is to take advantage of those idle resources for parallel computation without disturbing the local load. In order to provide a system that lets us execute parallel applications in such a non-dedicated cluster, we use an integral scheduling system that considers both Space and Time sharing concerns. For dealing with the Time Sharing (TS) aspect, we use a technique based on the communication-driven coscheduling principle. This kind of TS system has some implications on the Space Sharing (SS) system, that force us to modify the way job scheduling is traditionally done. In this paper, we analyze the relation between the TS and the SS systems in a non-dedicated cluster. As a consequence of this analysis, we propose a new technique, termed 3DBackfilling. This proposal implements the well known SS technique of backfilling, but applied to an environment with a MultiProgramming Level (MPL) of the parallel applications that is greater than one. Besides, 3DBackfilling considers the requirements of the local workload running on each node. Our proposal was evaluated in a PVM/MPI Linux cluster, and it was compared with several more traditional SS policies applied to non-dedicated environments.

Suurnopeuskompressorin tekninen markkinoilletuonti

Diplomityössä tarkastellaan suurnopeuskompressorin kehityspolkua suurnopeusteknologian lähtökohdista prototyypiksi ja edelleen teolliseksi tuotteeksi. Työssä tarkastelun kohteena on sähköteholtaan 20….250 kW oleva, suurnopeussähkökoneella ja öljyttömillä magneettilaakereilla varustettu keskipainekompressori. Tyypillisesti kompressorin painesuhde on 1,2 … 2,4. Ko. kompressorin käyttökohteina on tarkasteltu mm. pienen kunnallisen jätevedenpuhdistamon käsittelyaltaiden ilmastusta, suuren kaupungin vastaavan puhdistuslaitoksen ilmastuskäyttöä ja teollista käyttöä lasivillatehtaan ns. linkokompressorina. Suurnopeuskompressori soveltuu hyvin rinnankytkentään ns. ryhmäohjaimen avulla, jolloin rinnan voi olla kytkettynä jopa 16 kompressoria, joiden päällä oloa optimoidaan säätöteknisesti niin, että koko laitos on kuin yksi kompressori. Työssä tarkastellaan myös kompressorin em. sovellutuksista yli kahdeksan vuoden ajalta kaupallista kohteista saatuja käyttökokemuksia. Pääsäätöisesti voi sanoa, että jokaisessa uudessa sovellutuksessa ilmenee uusia reunaehtoja ja järjestelmäkohtaisia vaatimuksia, jotka täytyy huomioida kompressorin säädössä ja ominaisparametreissa.

Grid job scheduling using Route with Genetic Algorithm support

In 2006 the Route load balancing algorithm was proposed and compared to other techniques aiming at optimizing the process allocation in grid environments. This algorithm schedules tasks of parallel applications considering computer neighborhoods (where the distance is defined by the network latency). Route presents good results for large environments, although there are cases where neighbors do not have an enough computational capacity nor communication system capable of serving the application. In those situations the Route migrates tasks until they stabilize in a grid area with enough resources. This migration may take long time what reduces the overall performance. In order to improve such stabilization time, this paper proposes RouteGA (Route with Genetic Algorithm support) which considers historical information on parallel application behavior and also the computer capacities and load to optimize the scheduling. This information is extracted by using monitors and summarized in a knowledge base used to quantify the occupation of tasks. Afterwards, such information is used to parameterize a genetic algorithm responsible for optimizing the task allocation. Results confirm that RouteGA outperforms the load balancing carried out by the original Route, which had previously outperformed others scheduling algorithms from literature.

Application execution management on the InteGrade opportunistic grid middleware

The InteGrade project is a multi-university effort to build a novel grid computing middleware based on the opportunistic use of resources belonging to user workstations. The InteGrade middleware currently enables the execution of sequential, bag-of-tasks, and parallel applications that follow the BSP or the MPI programming models. This article presents the lessons learned over the last five years of the InteGrade development and describes the solutions achieved concerning the support for robust application execution. The contributions cover the related fields of application scheduling, execution management, and fault tolerance. We present our solutions, describing their implementation principles and evaluation through the analysis of several experimental results. (C) 2010 Elsevier Inc. All rights reserved.

Validade e confiabilidade da versão informatizada do inventário Million de estilos de personalidade

Currently, several psychological and non-psychological tests can be found in publishes without standardization on procedures set in different psychological areas, like intelligence, emotional states, attitudes, social skills, vocation, preferences and others. The computerized psychological testing is a extension of traditional testing psychological practices. However, it has own psychometrics qualities, either by its matching in a computerized environment or by the extension that can be developed in it. The current research, developed from a necessity to study process of validity and reliability on a computerized test, drew a methodological structure to provide parallel applications in numerous kinds of operational groups, evaluating the influences of the time and approach in the computerization process. This validity refers to normative values groups, reproducibility in computerized applications process and data processing. Not every psychological test can be computerized. Therefore, our need to find a good test, with quality and plausible properties to transform in computerized application, leaded us to use The Millon Personality Inventory, created by Theodore Millon. This Inventory assesses personality according to 12 bipolarities distributed in 24 factors, distributed in categories motivational styles, cognitive targets and interpersonal relations. This instrument doesn t diagnose pathological features, but test normal and non adaptive aspects in human personality, comparing with Theodore Millon theory of personality. In oder to support this research in a Brazilian context in psychological testing, we discuss the theme, evaluating the advantages and disadvantages of such practices. Also we discuss the current forms in computerization of psychological testing and the main specific criteria in this psychometric specialized area of knowledge. The test was on-line, hosted in the site http://www.planetapsi.com, during the years of 2007 and 2008, which was available a questionnaire to describe social characteristics before test. A report was generated from the data entry of each user. An application of this test was conducted in a linear way through a national coverage in all Brazil regions, getting 1508 applications. Were organized nine groups, reaching 180 applications in test and retest subject, where three periods of time and three forms of retests for studies of on-line tests were separated. Parallel to this, we organized multi-application session offline group, 20 subjects who received tests by email. The subjects of this study were generally distributed by the five Brazilian regions, and were noticed about the test via the Internet. The performance application in traditional and on-line tested groups subsidies us to conclude that on-line application provides significantly consistency in all criteria for validity studied and justifies its use. The on-line test results were related not only among themselves but were similar to those data of tests done on pencil and paper (0,82). The retests results demonstrated correlation, between 0,92 and, 1 while multisessions had a good correlation in these comparisons. Moreover, were assessed the adequacy of operational criteria used, such as security, the performance of users, the environmental characteristics, the organization of the database, operational costs and limitations in this on-line inventory. In all these five items, there were excellent performances, concluding, also, that it s possible a self-applied psychometric test. The results of this work are a guide to question and establish of methodologies studies for computerization psychological testing software in the country