A Novel Memory-centric Architecture and Organization of Processors and Computers

The modern computer systems that are in use nowadays are mostly processor-dominant, which means that their memory is treated as a slave element that has one major task – to serve execution units data requirements. This organization is based on the classical Von Neumann's computer model, proposed seven decades ago in the 1950ties. This model suffers from a substantial processor-memory bottleneck, because of the huge disparity between the processor and memory working speeds. In order to solve this problem, in this paper we propose a novel architecture and organization of processors and computers that attempts to provide stronger match between the processing and memory elements in the system. The proposed model utilizes a memory-centric architecture, wherein the execution hardware is added to the memory code blocks, allowing them to perform instructions scheduling and execution, management of data requests and responses, and direct communication with the data memory blocks without using registers. This organization allows concurrent execution of all threads, processes or program segments that fit in the memory at a given time. Therefore, in this paper we describe several possibilities for organizing the proposed memory-centric system with multiple data and logicmemory merged blocks, by utilizing a high-speed interconnection switching network.

Modelo de comunicación basado en el estándar AMBA AHB

Amb aquest projecte es presenta un model de comunicacions basat en ARM AMBA AHB, escrit en SystemC i dissenyat per a utilitzar-se en qualsevol sistema que necessiti una solució per a les seves comunicacions. Amb aquest objectiu s'escriu de manera que es llancin els seus processos com a processos "threads" i així puguin ser programats des del codi utilitari per mitjà de variables compartides. Per assegurar el correcte funcionament, inicialment es prova en un bus AMBA AHB complet per, un cop comprovat el compliment de l'estàndard, provar-ho en un codi que realitzi el càlcul de la transposició de matrius.

Pathological substrates of cognitive decline in Alzheimer's disease

The progressive development of Alzheimer's disease (AD)-related lesions such as neurofibrillary tangles,amyloid deposits and synaptic loss within the cerebral cortex is a main event of brain aging.Recent neuropathologic studies strongly suggested that the clinical diagnosis of dementia depends more on the severity and topography of pathologic changes than on the presence of a qualitative marker. However, several methodological problems such as selection biases, case-control design,density-based measures, and masking effects of concomitant pathologies should be taken into account when interpreting these data. In last years, the use of stereologic counting permitted to define reliably the cognitive impact of AD lesions in the human brain. Unlike fibrillar amyloid deposits that are poorly or not related to the dementia severity, the use of this method documented that total neurofibrillary tangles and neuron numbers in the CA1 field are the best correlates of cognitive deterioration in brain aging. Loss of dendritic spines in neocortical but not hippocampal areas has a modest but independent contribution to dementia. In contrast, the importance of early dendritic and axonal tau-related pathologic changes such as neuropil threads remains doubtful. Despite these progresses, neuronal pathology and synaptic loss in cases with pure AD pathology cannot explain more than 50% of clinical severity. The present review discusses the complex structure/function relationships in brain aging and AD within the theoretical framework of the functional neuropathology of brain aging.

Gestión de recursos en nodos multi-core de memoria compartida

La gestión de recursos en los procesadores multi-core ha ganado importancia con la evolución de las aplicaciones y arquitecturas. Pero esta gestión es muy compleja. Por ejemplo, una misma aplicación paralela ejecutada múltiples veces con los mismos datos de entrada, en un único nodo multi-core, puede tener tiempos de ejecución muy variables. Hay múltiples factores hardware y software que afectan al rendimiento. La forma en que los recursos hardware (cómputo y memoria) se asignan a los procesos o threads, posiblemente de varias aplicaciones que compiten entre sí, es fundamental para determinar este rendimiento. La diferencia entre hacer la asignación de recursos sin conocer la verdadera necesidad de la aplicación, frente a asignación con una meta específica es cada vez mayor. La mejor manera de realizar esta asignación és automáticamente, con una mínima intervención del programador. Es importante destacar, que la forma en que la aplicación se ejecuta en una arquitectura no necesariamente es la más adecuada, y esta situación puede mejorarse a través de la gestión adecuada de los recursos disponibles. Una apropiada gestión de recursos puede ofrecer ventajas tanto al desarrollador de las aplicaciones, como al entorno informático donde ésta se ejecuta, permitiendo un mayor número de aplicaciones en ejecución con la misma cantidad de recursos. Así mismo, esta gestión de recursos no requeriría introducir cambios a la aplicación, o a su estrategia operativa. A fin de proponer políticas para la gestión de los recursos, se analizó el comportamiento de aplicaciones intensivas de cómputo e intensivas de memoria. Este análisis se llevó a cabo a través del estudio de los parámetros de ubicación entre los cores, la necesidad de usar la memoria compartida, el tamaño de la carga de entrada, la distribución de los datos dentro del procesador y la granularidad de trabajo. Nuestro objetivo es identificar cómo estos parámetros influyen en la eficiencia de la ejecución, identificar cuellos de botella y proponer posibles mejoras. Otra propuesta es adaptar las estrategias ya utilizadas por el Scheduler con el fin de obtener mejores resultados.

Factores de rendimiento en entornos multicore

Este documento refleja el estudio de investigación para la detección de factores que afectan al rendimiento en entornos multicore. Debido a la gran diversidad de arquitecturas multicore se ha definido un marco de trabajo, que consiste en la adopción de una arquitectura específica, un modelo de programación basado en paralelismo de datos, y aplicaciones del tipo Single Program Multiple Data. Una vez definido el marco de trabajo, se han evaluado los factores de rendimiento con especial atención al modelo de programación. Por este motivo, se ha analizado la librería de threads y la API OpenMP para detectar aquellas funciones sensibles de ser sintonizadas al permitir un comportamiento adaptativo de la aplicación al entorno, y que dependiendo de su adecuada utilización han de mejorar el rendimiento de la aplicación.

Analitzador gràfic de xarxa en entorn GNU

Treball de fi de carrera d'enginyeria tècnica en informàtica de sistemes. El treball s'estructura en introducció, anàlisi, implementació, manual d'instal·lació, joc de proves... del treball. Aquest Treball Final de Carrera s'inclou dins de l'àrea de Xarxes deComputadors. Consisteix en la realització d'una aplicació gràfica en entornGNU que faci un anàlisi del tràfic d'una xarxa informàtica; això es coneix ambel nom de Sniffer.

Defensive behavior associated with secretions from the prosternal paired glands of the larvae of Heliconius erato phyllis Fabricius (Lepidoptera, Nymphalidae)

Defensive behavior associated with secretions from the prosternal paired glands of the larvae of Heliconius erato phyllis Fabricius (Lepidoptera, Nymphalidae). Our work presents for the first time, the defensive behavior associated with the release of the product of the prosternal paired glands of the larva of Heliconius erato phyllis Fabricius, 1775 (Lepidoptera, Nymphalidae, Heliconiinae). The prosternal glands were first described for larvae of H. erato phyllis. They are formed by two types of glandular structures: the impair gland and the paired glands. The prosternal glands are located within the conical integumentary sac, which in turn is situated on the individual's prosternum. The main goal of this study is to analyze the existence of any secretion from the prosternal paired glands, and check the action mode of this secretion. The methodology used for chemical analysis of the glands included the aeration and, analysis in gas chromatography and gas chromatography-mass spectrometry. The results show that the prosternal glands do not produce volatiles. Bioassays were conducted with simulated and natural attacks and revealed that the prosternal paired glands produce secretions of defense together with silk produced by labials glands as a defense strategy, described for the first time, against ants. The strategy consists in wrapping the ant with silk threads, the entire wrapped object moved to the end of the body, with the aid of the legs and prolegs, and possibly fixed in a nearby place. Evidence for the existence of a conical integumentary sac in larvae of other species and families of Lepidoptera allows us to propose the possibility of occurrence of prosternal paired glands with defensive function in these other groups as well.

Exopolysaccharides produced by the symbiotic nitrogen-fixing bacteria of leguminosae

The process of biological nitrogen fixation (BNF), performed by symbiotic nitrogen fixing bacteria with legume species, commonly known as α and β rhizobia, provides high sustainability for the ecosystems. Its management as a biotechnology is well succeeded for improving crop yields. A remarkable example of this success is the inoculation of Brazilian soybeans with Bradyrhizobium strains. Rhizobia produce a wide diversity of chemical structures of exopolysaccharides (EPS). Although the role of EPS is relatively well studied in the process of BNF, their economic and environmental potential is not yet explored. These EPS are mostly species-specific heteropolysaccharides, which can vary according to the composition of sugars, their linkages in a single subunit, the repeating unit size and the degree of polymerization. Studies have showed that the EPS produced by rhizobia play an important role in the invasion process, infection threads formation, bacteroid and nodule development and plant defense response. These EPS also confer protection to these bacteria when exposed to environmental stresses. In general, strains of rhizobia that produce greater amounts of EPS are more tolerant to adverse conditions when compared with strains that produce less. Moreover, it is known that the EPS produced by microorganisms are widely used in various industrial activities. These compounds, also called biopolymers, provide a valid alternative for the commonly used in food industry through the development of products with identical properties or with better rheological characteristics, which can be used for new applications. The microbial EPS are also able to increase the adhesion of soil particles favoring the mechanical stability of aggregates, increasing levels of water retention and air flows in this environment. Due to the importance of EPS, in this review we discuss the role of these compounds in the process of BNF, in the adaptation of rhizobia to environmental stresses and in the process of soil aggregation. The possible applications of these biopolymers in industry are also discussed.

Alzheimer disease: curly fibers and tangles in organs other than brain.

The filamentous brain lesions that define Alzheimer disease (AD) consist of senile plaques and neurofibrillary tangles. Undulated pathological filaments--curly fibers or neuropil threads--also occur in the neuropil. Beta-amyloid precursor proteins are synthesized by many cells outside the central nervous system and recently, deposition of beta-amyloid-protein was reported to occur in non-neuronal tissues. In addition, increasing data claim the importance of chronic inflammation in the pathogenesis of AD. These observations suggest that AD may be a widespread systemic disorder. Here we report that pathological argyrophilic filaments with histochemical properties of amyloid showing striking morphological similarity to curly fibers and/or tangles accumulate not only in ependymal layer and in epithelial cells of choroid plexus, but also in several other organs (e.g. liver, pancreas, ovary, testis, thyroid) in AD. The ependyma, choroid plexus, and various organs of 39 autopsy cases were analyzed. In search of curly fiber and tangle-like changes in organs other than brain, 395 blocks from 21 different tissues of 24 AD cases, 5 cases with discrete or moderate AD-type changes, and 10 control cases were investigated. We found in non-neuronal cells "curly fibers" or "tangles" immunoreactive with antibodies to P component, Tau-protein, ubiquitin, fibronectin, and Apolipoprotein-E, but lacking immunoreactivity with antibodies to neurofilament proteins. Ultrastructurally they consist of densely packed straight and paired helical filaments and closely resemble neurofibrillary tangles and neuropil threads. These observations indicate that the formation of "curly fibers" and "tangles" is not unique to the central nervous system. The results suggest that AD might be a systemic disorder or that similar fibrillary changes to tangles and curly fibers may also be associated with other amyloidosis than beta-amyloidosis. Further investigations are necessary to understand the pathogenetic interest of these fibrillary changes outside the CNS.

Ultrastructure of adhesion and movement of the tetraspores of Gelidium Lamour (Geldiaceae; Rhodophyta)

The outer part of the tetraspora cell wall in Gelidium crinale (Turner) J.V. Lamour. and G. spathulatum (Kutz.) Bornet is morphologically described in relation to the movements and displacement of these spores when they settle on a substratum. We also describe the mechanism of adhesión and the transformations undergone by this mechanism over time. The cell wall shows a network of fibrillar threads embedded in abundant mucilage. The deformations that tetraspores undergo show that the cell wall is relatively elastic.

Modification of Ca-Montmorillonite by Low-Temperature Heat Treatment, HR-106, 1964

Objectives of this investigation were to measure the effects of moderate heat treatments (below the dehydroxylation temperature) on physical and chemical properties of a calcium-montmorillonite clay. Previous workers have noted the reduction in cation exchange capacity and swelling property after heating in the range 200 to 400°C, and have suggested several possible explanations, such as hysteresis effect, increased inter-layer attractions due to removal of inter-layer water, or changes in the disposition of inter-layer or layer surface ions. The liquid limits of Ca-montmorillonite were steadily decreased with increased temperature of treatment, levelling at about 450°C. The plastic limit decreased slightly up to 350°C, above which samples could no longer be rolled into threads. The gradual change is in contrast with sudden major changes noted for weight loss (maximum rates of change at l00°C and 500°C), glycol retention surface area (520°C), and d001 diffraction peak intensity (17.7 A spacing) and breadth after glycolation (530°C). Other properties showing more gradual reductions with heat treatment were amount of exchangeable calcium (without water soaking), cation exchange capacity by NH4AC method, and d001 intensity (21 A spacing) after storing at 100% r.h. one month and re-wetting with water. Previous water soaking allowed much greater release of fixed Ca++ up to 450°C. Similar results were obtained with cation exchange capacities when samples were treated with N CaCl2 solution. The 21.0 A peak intensity curve showed close similarity to the liquid limit and plastic index curves in the low temperature range, and an explanation is suggested.

Early olfactory involvement in Alzheimer's disease.

BACKGROUND: In Alzheimer's disease (AD) the olfactory system, including the olfactory bulb, a limbic paleocortex is severely damaged. The occurrence of early olfactory deficits and the presence of senile plaques and neurofibrillary tangles in olfactory bulb were reported previously by a few authors. The goal of the present study was to analyze the occurrence of AD-type degenerative changes in the peripheral part of the olfactory system and to answer the question whether the frequency and severity of changes in the olfactory bulb and tract are associated with those of the cerebral cortex in AD. MATERIAL AND METHODS: In 110 autopsy cases several cortical areas and the olfactory bulb and tract were analyzed using histo- and immunohistochemical techniques. Based on a semiquantitative analysis of cortical senile plaques, neurofibrillary tangles and curly fibers, the 110 cases were divided into four groups: 19 cases with severe (definite AD), 14 cases with moderate, 58 cases with discrete and 19 control cases without AD-type cortical changes. RESULTS: The number of cases with olfactory involvement was very high, more than 84% in the three groups with cortical AD-type lesions. Degenerative olfactory changes were present in all 19 definite AD cases, and in two of the 19 controls. The statistical analysis showed a significant association between the peripheral olfactory and cortical degenerative changes with respect to their frequency and severity (P < 0.001). Neurofibrillary tangles and neuropil threads appear in the olfactory system as early as in entorhinal cortex. CONCLUSION: The results indicate a close relationship between the olfactory and cortical degenerative changes and indicate that the involvement of the olfactory bulb and tract is one of the earliest events in the degenerative process of the central nervous system in AD.

Towards Machine Consciousness: Grounding Abstract Models as pi-Processes

We present a two-level model of concurrent communicating systems (CCS) to serve as a basis formachine consciousness. A language implementing threads within logic programming is ¯rstintroduced. This high-level framework allows for the de¯nition of abstract processes that can beexecuted on a virtual machine. We then look for a possible grounding of these processes into thebrain. Towards this end, we map abstract de¯nitions (including logical expressions representingcompiled knowledge) into a variant of the pi-calculus. We illustrate this approach through aseries of examples extending from a purely reactive behavior to patterns of consciousness.

An Interdomain PKI Model Based on Trust Lists

The penetration of PKI technology in the market is moving slowly due to interoperability concerns. Main causes are not technical but political and social since there is no trust development model that appropriately deals with multidomain PKIs. We propose a new architecture that on one hand considers that trust is not an homogeneous property but tied to a particular relation, and on the other hand, trust management must be performed through specialized entities that can evaluate its risks and threads. The model is based on trust certificate lists that allows users to hold a personalized trust view without having to get involved in technical details. The model dynamically adapts tothe context changes thanks to a new certificate extension, we have called TrustProviderLink (TPL).

Data-parallel computation in parallel and distributed environments

The past few decades have seen a considerable increase in the number of parallel and distributed systems. With the development of more complex applications, the need for more powerful systems has emerged and various parallel and distributed environments have been designed and implemented. Each of the environments, including hardware and software, has unique strengths and weaknesses. There is no single parallel environment that can be identified as the best environment for all applications with respect to hardware and software properties. The main goal of this thesis is to provide a novel way of performing data-parallel computation in parallel and distributed environments by utilizing the best characteristics of difference aspects of parallel computing. For the purpose of this thesis, three aspects of parallel computing were identified and studied. First, three parallel environments (shared memory, distributed memory, and a network of workstations) are evaluated to quantify theirsuitability for different parallel applications. Due to the parallel and distributed nature of the environments, networks connecting the processors in these environments were investigated with respect to their performance characteristics. Second, scheduling algorithms are studied in order to make them more efficient and effective. A concept of application-specific information scheduling is introduced. The application- specific information is data about the workload extractedfrom an application, which is provided to a scheduling algorithm. Three scheduling algorithms are enhanced to utilize the application-specific information to further refine their scheduling properties. A more accurate description of the workload is especially important in cases where the workunits are heterogeneous and the parallel environment is heterogeneous and/or non-dedicated. The results obtained show that the additional information regarding the workload has a positive impact on the performance of applications. Third, a programming paradigm for networks of symmetric multiprocessor (SMP) workstations is introduced. The MPIT programming paradigm incorporates the Message Passing Interface (MPI) with threads to provide a methodology to write parallel applications that efficiently utilize the available resources and minimize the overhead. The MPIT allows for communication and computation to overlap by deploying a dedicated thread for communication. Furthermore, the programming paradigm implements an application-specific scheduling algorithm. The scheduling algorithm is executed by the communication thread. Thus, the scheduling does not affect the execution of the parallel application. Performance results achieved from the MPIT show that considerable improvements over conventional MPI applications are achieved.