L'étude de la lecture s'intéresse, entre autres, aux facteurs déterminant la visibilité de lettres et les mouvements oculaires. Néanmoins, l'approche de ces mécanismes reste différente selon qu'elle concerne la vision centrale ou périphérique. Cette thèse proposait, au contraire, une approche conjointe dans le but (1) de mettre en évidence les effets des facteurs visuels limitant la reconnaissance de mots, (2) de mieux comprendre le comportement oculomoteur lors de la lecture en vision centrale et (3) d'étudier le rôle des facteurs oculomoteurs spécifiques à la lecture en vision périphérique. Trois expériences ont été menées. La première axée sur l'étude des facteurs visuels, a mis en évidence que l'effet OVP était moins important pour des mots présentés dans le champ visuel inférieur. Ce résultat pouvant s'expliquer par la géométrie de l'acuité visuelle et de l'encombrement, suggère que la lecture en périphérie est limitée par les mêmes facteurs qu'en vision centrale. La deuxième étude, concernant la stabilité de fixation durant la lecture en présence d'un scotome artificiel, a révélé que la vitesse de lecture pouvait être améliorée en présence d'une stimulation fovéale stable. Enfin, nous avons montré que les mouvements oculaires variaient selon la taille des lettres, et ce, différemment selon la position du regard par rapport au centre des mots. Ce résultat, nouveau, est vraisemblablement attribuable à l'effet de processus visuomoteurs précoces. En conclusion, l'étude conjointe de la lecture en vision centrale et périphérique est prometteuse, non seulement d'un point de vue fondamental, mais aussi pour l'aide aux patients atteints de DMLA. / Reading is a large research field, which investigates for a great part the variables influencing letter visibility and eye movements. However, its study in central and peripheral vision has been conducted in parallel and with different approaches. Our work relied, on the contrary, on a joint approach in order (1) to uncover the visual factors limiting word recognition, (2) to better determine how the eyes move during reading in central vision, and (3) to study the role of oculomotor factors that might affect reading in peripheral vision. Three experiments were conducted. The first study focused on the role of visual factors in word identification. It showed that the OVP effect is reduced for words displayed in the lower visual field. This result, which can be explained by the geometry of visual acuity andl crowding, suggests that reading in peripheral vision is limited by the same visual factors as in central vision. Then we investigated the influence of fixation stability on sentence reading using an artificial scotoma. It revealed that reading speed could be improved with a stable foveal stimulation. The third experiment re-examined the possible influence of character size on eye movements in central vision. It revealed that eye movements varied depending on letter size, and differently as a function of the location of the eye relative to the center of words. This novel finding was very likely the effect of early visuomotor processes. In conclusion, the joint study of reading in central and peripheral vision is promising, not only at a fundamental level, but also for a better understanding of retinal visual deficits, such as AMD.

Thesis (M. Soc. Sc.)--University of Hong Kong, 1997. / Includes bibliographical references (leaf 81-84).

Thesis (M. Soc. Sc.)--University of Hong Kong, 1997. / Includes bibliographical references (leaf 81-84). Also available in print.

In the recent years, there has been a rapid development of miniature sensor based wearable devices with broad functionality. Some of these devices are designed to function continuously for weeks with a single battery charge, which requires their power usage to be as low as possible. This can be achieved either through circuit optimization, a more powerful battery, or through optimization of the software controlling the device. This thesis presents an approach to the latter option by the means of a power and energy simulator based on the Open Virtual Platform (OVP). Such a tool can simulate the embedded software and predict the power and energy usage of the system. The result of the simulator could be used in combination with other tools to optimize the software implementation of the system and to lower its overall power and energy consumption.

The fields of System-On-Chip (SOC) and Embedded Systems Design have received a lot of attention in the last years. As part of an effort to increase productivity and reduce the time-to-market of new products, different approaches for Electronic System-Level Design frameworks have been proposed. These different methods promise a transparent co-design of hardware and software without having to focus on the final hardware/software split. In our work, we focused on enhancing the component database, modeling and synthesis capabilities of the System-On-Chip Environment (SCE). We investigated two different virtual platform emulators (QEMU and OVP) for integration into SCE. Based on a comparative analysis, we opted on integrating the Open Virtual Platforms (OVP) models and tested the enhanced SCE simulation, design and synthesis capabilities with a JPEG encoder application, which uses both custom hardware and software as part of the system. Our approach proves not only to provide fast functional verification support for designers (10+ times faster than cycle accurate models), but also to offer a good speed/accuracy relationship when compared against integration of cycle accurate or behavioral (host-compiled) models. / text

La fovéa est la seule zone de la rétine où l’acuité visuelle est maximale. Les mécanismes qui visent à déterminer à quels endroits vont avoir lieu les prochaines fixations restent débattus. Certains auteurs suggèrent que les yeux sont principalement attirés par les zones les plus saillantes de la scène. D’autres suggèrent qu’ils sont orientés vers les objets. Les propriétés du système oculomoteur contraignent également les mouvements oculaires. L’objectif de cette thèse était de départager ces différents points de vue en examinant la contribution respective et le décours temporel des facteurs visuo-moteurs de bas niveau et des facteurs cognitifs de plus haut niveau dans la détermination des mouvements oculaires. Nous nous sommes focalisés sur trois phénomènes comportementaux clés : la tendance à bouger les yeux à proximité du centre des objets (Prefered-Viewing Location), les répercussions qu’ont ces positions d’atterrissage sur les durées initiales des fixations (Inverted Optimal-Viewing-Position) et les probabilités de refixation (Optimal-Viewing-Position). Nous avons observé que ces trois effets émergeaient, et ce, quel que soit le type de stimulus testé: des objets, des mots ou des objets sans signification. Cela suggère que ces effets reflètent les propriétés de bas niveau des systèmes visuel et oculomoteur. Par ailleurs, nous avons observé que l’endroit où les yeux atterrissaient au sein de l’objet était également influencé au fil du temps par les traitements de plus haut-niveau des propriétés du stimulus. Les saccades initiées plus tardivement atterrissaient plus proches de la zone la plus informative de l’objet. / High-quality vision is restricted to the fovea - a small region at the center of gaze. The mechanisms that determine which locations in a scene are selected for fixation remain debated. Some suggest that eye movements are mainly driven by the salient features in a scene. Others suggest that eye guidance is object based. The properties of the oculomotor system also strongly constrain eye behavior, but these have been neglected in most existing models. The purpose of this thesis was to disentangle between these different views, by investigating how low-level visuomotor factors versus higher-level cognitive factors contribute to eye movements towards and within isolated objects, and with which time course. We focused on three viewing-position effects: the tendency to move the eyes near the centers of objects (the PVL effect), and the repercussions these initial landing positions have on initial fixation durations (the I-OVP effect) and refixation probabilities (the OVP effect). We found that these three viewing-position effects emerged, and were comparable, in all stimulus types that we tested in this thesis: objects, words and even meaningless non-objects. This suggests that the effects reflect low-level properties of the visual and oculomotor systems. Furthermore, we found that where the eye moved within objects became influenced by ongoing processing of higher-level stimulus properties (e.g., object affordances) over time. Later- compared to early-triggered initial saccades, and even more so within-object refixations, were biased towards the most informative part of the objects, and away from their center of gravity.

A complexidade dos sistemas integrados em chips bem como a arquitetura de processadores comerciais vem crescendo dramaticamente nos últimos anos. Com isto, a dificuldade de avaliarmos a suscetibilidade às falhas em decorrência da incidência de partículas espaciais carregadas nestes dispositivos cresce com a mesma taxa. Este trabalho apresenta uma análise comparativa da susceptibilidade à erros de software em um microprocessador embarcado ARM Cortex-A9 single core de larga escala comercial, amplamente utilizado em aplicações críticas, executando um conjunto de 11 aplicações desenvolvidas para um ambiente bare metal e para o sistema operacional Linux. A análise de soft errors é executada por injeção de falhas na plataforma de simulação OVPSim juntamente com o injetor OVPSim-FIM, capaz de sortear o momento e local de injeção de uma falha. A campanha de injeção de falhas reproduz milhares de bit-flips no banco de registradores do microprocessador durante a execução do conjunto de benchmarks que possuem um comportamento de código diverso, desde dependência de fluxo de controle até aplicações intensivas em dados. O método de análise consiste em comparar execuções da aplicação onde falhas foram injetadas com uma execução livre de falhas. Os resultados apresentam a taxa de falhas que são classificadas em: mascaradas (UNACE), travamento ou perda de controle de fluxo (HANG) e erro nos resultados (SDC). Adicionalmente, os erros são classificados por registradores, separando erros latentes por sua localização nos resultados e por exceções detectadas pelo sistema operacional, provendo novas possibilidades de análise para um processador desta escala. O método proposto e os resultados obtidos podem ajudar a orientar desenvolvedores de software na escolha de diferentes arquiteturas de código, a fim de aprimorar a tolerância à falhas do sistema embarcado como um todo. / The complexity of integrated system on-chips as well as commercial processor’s architecture has increased dramatically in recent years. Thus, the effort for assessing the susceptibility to faults due to the incidence of spatial charged particles in these devices has growth at the same rate. This work presents a comparative analysis of soft errors susceptibility in the commercial large-scale embedded microprocessor ARM Cortex-A9 single core, widely used in critical applications, performing a set of 11 applications developed for a bare metal environment and the Linux operating system. The soft errors analysis is performed by fault injection in OVPSim simulation platform along with the OVPSim-FIM fault injector, able to randomly select the time and place to inject the fault. The fault injection campaign reproduces thousands of bit-flips in the microprocessor register file during the execution of the benchmarks set, with a diverse code behavior ranging from control flow dependency to data intensive applications. The analysis method is based on comparing applications executions where faults were injected with a fault-free implementation. The results show the error rate classified by their effect as: masked (UNACE), crash or loss of control flow (HANG) and silent data corruption (SDC); and by register locations. By separating latent errors by its location in the results and exceptions detected by the operating system, one can provide new better observability for a large-scale processor. The proposed method and the results can guide software developers in choosing different code architectures in order to improve the fault tolerance of the embedded system as a whole.

A complexidade dos sistemas integrados em chips bem como a arquitetura de processadores comerciais vem crescendo dramaticamente nos últimos anos. Com isto, a dificuldade de avaliarmos a suscetibilidade às falhas em decorrência da incidência de partículas espaciais carregadas nestes dispositivos cresce com a mesma taxa. Este trabalho apresenta uma análise comparativa da susceptibilidade à erros de software em um microprocessador embarcado ARM Cortex-A9 single core de larga escala comercial, amplamente utilizado em aplicações críticas, executando um conjunto de 11 aplicações desenvolvidas para um ambiente bare metal e para o sistema operacional Linux. A análise de soft errors é executada por injeção de falhas na plataforma de simulação OVPSim juntamente com o injetor OVPSim-FIM, capaz de sortear o momento e local de injeção de uma falha. A campanha de injeção de falhas reproduz milhares de bit-flips no banco de registradores do microprocessador durante a execução do conjunto de benchmarks que possuem um comportamento de código diverso, desde dependência de fluxo de controle até aplicações intensivas em dados. O método de análise consiste em comparar execuções da aplicação onde falhas foram injetadas com uma execução livre de falhas. Os resultados apresentam a taxa de falhas que são classificadas em: mascaradas (UNACE), travamento ou perda de controle de fluxo (HANG) e erro nos resultados (SDC). Adicionalmente, os erros são classificados por registradores, separando erros latentes por sua localização nos resultados e por exceções detectadas pelo sistema operacional, provendo novas possibilidades de análise para um processador desta escala. O método proposto e os resultados obtidos podem ajudar a orientar desenvolvedores de software na escolha de diferentes arquiteturas de código, a fim de aprimorar a tolerância à falhas do sistema embarcado como um todo. / The complexity of integrated system on-chips as well as commercial processor’s architecture has increased dramatically in recent years. Thus, the effort for assessing the susceptibility to faults due to the incidence of spatial charged particles in these devices has growth at the same rate. This work presents a comparative analysis of soft errors susceptibility in the commercial large-scale embedded microprocessor ARM Cortex-A9 single core, widely used in critical applications, performing a set of 11 applications developed for a bare metal environment and the Linux operating system. The soft errors analysis is performed by fault injection in OVPSim simulation platform along with the OVPSim-FIM fault injector, able to randomly select the time and place to inject the fault. The fault injection campaign reproduces thousands of bit-flips in the microprocessor register file during the execution of the benchmarks set, with a diverse code behavior ranging from control flow dependency to data intensive applications. The analysis method is based on comparing applications executions where faults were injected with a fault-free implementation. The results show the error rate classified by their effect as: masked (UNACE), crash or loss of control flow (HANG) and silent data corruption (SDC); and by register locations. By separating latent errors by its location in the results and exceptions detected by the operating system, one can provide new better observability for a large-scale processor. The proposed method and the results can guide software developers in choosing different code architectures in order to improve the fault tolerance of the embedded system as a whole.

A complexidade dos sistemas integrados em chips bem como a arquitetura de processadores comerciais vem crescendo dramaticamente nos últimos anos. Com isto, a dificuldade de avaliarmos a suscetibilidade às falhas em decorrência da incidência de partículas espaciais carregadas nestes dispositivos cresce com a mesma taxa. Este trabalho apresenta uma análise comparativa da susceptibilidade à erros de software em um microprocessador embarcado ARM Cortex-A9 single core de larga escala comercial, amplamente utilizado em aplicações críticas, executando um conjunto de 11 aplicações desenvolvidas para um ambiente bare metal e para o sistema operacional Linux. A análise de soft errors é executada por injeção de falhas na plataforma de simulação OVPSim juntamente com o injetor OVPSim-FIM, capaz de sortear o momento e local de injeção de uma falha. A campanha de injeção de falhas reproduz milhares de bit-flips no banco de registradores do microprocessador durante a execução do conjunto de benchmarks que possuem um comportamento de código diverso, desde dependência de fluxo de controle até aplicações intensivas em dados. O método de análise consiste em comparar execuções da aplicação onde falhas foram injetadas com uma execução livre de falhas. Os resultados apresentam a taxa de falhas que são classificadas em: mascaradas (UNACE), travamento ou perda de controle de fluxo (HANG) e erro nos resultados (SDC). Adicionalmente, os erros são classificados por registradores, separando erros latentes por sua localização nos resultados e por exceções detectadas pelo sistema operacional, provendo novas possibilidades de análise para um processador desta escala. O método proposto e os resultados obtidos podem ajudar a orientar desenvolvedores de software na escolha de diferentes arquiteturas de código, a fim de aprimorar a tolerância à falhas do sistema embarcado como um todo. / The complexity of integrated system on-chips as well as commercial processor’s architecture has increased dramatically in recent years. Thus, the effort for assessing the susceptibility to faults due to the incidence of spatial charged particles in these devices has growth at the same rate. This work presents a comparative analysis of soft errors susceptibility in the commercial large-scale embedded microprocessor ARM Cortex-A9 single core, widely used in critical applications, performing a set of 11 applications developed for a bare metal environment and the Linux operating system. The soft errors analysis is performed by fault injection in OVPSim simulation platform along with the OVPSim-FIM fault injector, able to randomly select the time and place to inject the fault. The fault injection campaign reproduces thousands of bit-flips in the microprocessor register file during the execution of the benchmarks set, with a diverse code behavior ranging from control flow dependency to data intensive applications. The analysis method is based on comparing applications executions where faults were injected with a fault-free implementation. The results show the error rate classified by their effect as: masked (UNACE), crash or loss of control flow (HANG) and silent data corruption (SDC); and by register locations. By separating latent errors by its location in the results and exceptions detected by the operating system, one can provide new better observability for a large-scale processor. The proposed method and the results can guide software developers in choosing different code architectures in order to improve the fault tolerance of the embedded system as a whole.