In order to measure the performance of a parallel machine, a set of application kernels as benchmarks have often been used. However, it is not always possible to characterize the performance using only benchmarks, given the fact that each one usually reﬂects a narrow set of kernel applications at best. Computers show different performance indices for different applications as they run them. Accurate prediction of parallel applications’ performance is becoming increasingly complex and the time required to run it thoroughly is an onerous requirement; especially if we want to predict for different systems. In production clusters, where throughput and efﬁciency...
Bertogna, Mario Leandro
The work carried out in the thesis describes efficient virtual environments management. One of the main contributions is a middleware scheduling optimization based on Grid environments. Being the overall goal to get an optimal resource selection plus a coordinate task execution optimization. In particular, the research was related with the interaction between non trivial quality service and tasks distribution issues in meta-organizations. While linking allocation and policies belonging to virtual and local organizations.
Vasant, Pandian M.
In this Ph. D thesis, the main significant contributions are: formulation of a new non-linear membership function using fuzzy approach to capture and describe vagueness in the technological coefficients of constraints in the industrial production planning problems. This non-linear membership function is flexible and convenience to the decision makers in their decision making process. Secondly, a nonlinear objective function in the form of cubic function for fuzzy optimization problems is successfully solved by 15 hybrid and non-hybrid optimization techniques from the area of soft computing and classical approaches. Among the 15 techniques, three outstanding techniques are selected based on the...
Tinetti, Fernando Gustavo
The book Using OpenMP: Portable Shared Memory Parallel Programming, presents OpenMP more than appropriately, from the perspective of high performance computing, which traditionally has provided most (if not all) the parallel software development strategies.
Almudi Neto, Dario; Martins, Luiz Eduardo Galvão
This paper presents the results of studies that made possible to propose a particular contribution to improve the quality on developing automotive embedded systems through a requirements specification template of a communication network based on CAN protocol. The whole template structure is composed by sections that specify the controlling units, the subnetworks, the data dictionary and the general aspects of the communication network. A study case was performed to test the proposed template and a study of the requirements of an embedded automotive environment was specified. The conclusions of this study and the evaluation are presented and further studies are...
Khalil, M. I.
This paper outlines and deals with the problem of fault detection, isolation and identification of the four-elements detector system attached to the Cairo Fourier diffractometer facility (CFDF) used for neutron time-of-flight (TOF) spectrum measurements. A feed forward neural network and error back propagation training algorithm are employed to diagnose four commonly occurring faults of the detector system: preamplifier, amplifier, discriminator and the high voltage. The diagnostic system processes the acquired data to determine whether the detector system state is normal or not. The experimental results showed that the trained network has the capability to detect and identify various faults which...
Ekpenyong, Moses E.; Robinson, Samuel; Isabona, Joseph
In this paper, the signal propagation characteristics of urban environments are predicted by modeling important propagation parameters of the Code Division Multiple Access (CDMA) network for macrocells. The MOPEM propagation model has been selected as a model of choice due to its robustness in handling urban parameters. The model is simulated with some modifications using empirical data from the Visafone CDMA gathered from the Nigerian Telecommunications Limited (NITEL), Uyo, Nigeria and data from the field.
From the simulation, we observe that propagation model parameters such as orientation angel, street width, building height, among others, has great influence on the system performance...
Rodríguez, Guillermo L.; San Martín, Patricia S.
The following research proposes a first approximation to the Dynamic Hypermedial Device modeling based on the analysis of interactions. In addition, the DEVS (Discrete EVents dynamic Systems) formalism is employed, which is particularly suitable for the modeling of discrete event systems with continuous time. In this sense, the descriptive model of the denominated "Hypermedial Package" is presented as a basic conceptual component of the DHD. Then, a functional example of basic analysis of the interactions implemented in the PowerDEVS environment is shown. The ultimate goal of this proposal is to provide a tool to assist in the quality analysis and...
Cagnina, Leticia; Esquivel, Susana Cecilia
This paper presents a hybrid method to solve hard multiobjective problems. The proposed approach adopts an epsilon-constraint method which uses a Particle Swarm Optimizer to get points near of the true Pareto front. In this approach, only few points will be generated and then, new intermediate points will be calculated using an interpolation method, to increase the among of points in the output Pareto front. The proposed approach is validated using two difficult multiobjective test problems and the results are compared with those obtained by a multiobjective evolutionary algorithm representative of the state of the art: NSGA-II.
Rexachs del Rosario, Dolores; Luque Fadón, Emilio
Fault tolerance has become an important issue for parallel applications in the last few years. The parallel systems' users want them to be reliable considering two main dimensions, availability and data consistency. Availability can be provided with solutions such as RADIC, a fault tolerant architecture with different protection levels, offering high availability with transparency, decentralization, flexibility and scalability for message-passing systems. Transient faults may cause an application running in a computer system to be removed from execution, however the biggest risk of transient faults is to provoke undetected data corruption that changes the final result of the application without anyone...