Multithreading RTOS processor design

Tese de Doutoramento Plano Doutoral em Engenharia Eletrónica e de Computadores.

As cores de Braga: levantamento cromático da rua do Souto e da rua D. Diogo de Sousa

Dissertação de mestrado integrado em Arquitectura (área de especialização em Cultura Arquitectónica)

Implementation of Multi-Core Processor Based on PLASMA (Most MIPS I) IP Core

Multi-core processors is a design philosophy that has become mainstream in scientific and engineering applications. Increasing performance and gate capacity of recent FPGA devices has permitted complex logic systems to be implemented on a single programmable device. By using VHDL here we present an implementation of one multi-core processor by using the PLASMA IP core based on the (most) MIPS I ISA and give an overview of the processor architecture and share theexecution results.

Software for Explicitly Parallel Memory-Centric Processor Architecture

Advances in computer memory technology justify research towards new and different views on computer organization. This paper proposes a novel memory-centric computing architecture with the goal to merge memory and processing elements in order to provide better conditions for parallelization and performance. The paper introduces the architectural concepts and afterwards shows the design and implementation of a corresponding assembler and simulator.

Efficient query processing in co-processor-accelerated databases

...Diese Dissertation zeigt, wie wir Datenbankmanagementsysteme bauen können, die heterogene Prozessoren effizient und zuverlässig zur Beschleunigung der Anfrageverarbeitung nutzen können. Daher untersuchen wir typische Entwurfsentscheidungen von coprozessorbeschleunigten Datenbankmanagementsystemen und leiten darauf aufbauend eine generische Architektur für solche Systeme ab. Unsere Untersuchungen zeigen, dass eines der wichtigsten Probleme für solche Datenbankmanagementsysteme die Entscheidung ist, welche Operatoren einer Anfrage auf welchem Prozessor ausgeführt werden sollen...

Payoff-dependent balancedness and cores (revised version)

We prove the non-emptiness of the core of an NTU game satisfying a condition of payoff-dependent balancedness, based on transfer rate mappings. We also define a new equilibrium condition on transfer rates and we prove the existence of core payoff vectors satisfying this condition. The additional requirement of transfer rate equilibrium refines the core concept and allows the selection of specific core payoff vectors. Lastly, the class of parametrized cooperative games is introduced. This new setting and its associated equilibrium-core solution extend the usual cooperative game framework and core solution to situations depending on an exogenous environment. A non-emptiness result for the equilibrium-core is also provided in the context of a parametrized cooperative game. Our proofs borrow mathematical tools and geometric constructions from general equilibrium theory with non convexities. Applications to extant results taken from game theory and economic theory are given.

Creació d'IP Cores en una plataforma NIOS: metodologia de disseny

NIOS és el processador que Altera empra en els seus dissenys SOC (System On Chip). Per tal de facilitar-ne el seu ús, Altera també proporciona una plataforma de desenvolupament SOPC (System On Programable Chip) que agilitza enormement el disseny d’aquests sistemes. Així doncs, aquest projecte està centrat en la definició metodològica per a la creació d'IP Cores en una plataforma NIOS.

Addressing Sea Surface Salinity retrieval at different spatial resolution. Feasibility study using OCCAM data within SEPS simulator and L2 processor tools

Projecte de recerca elaborat a partir d’una estada a la National Oceanography Centre of Southampton (NOCS), Gran Bretanya, entre maig i juliol del 2006. La possibilitat d’obtenir una estimació precissa de la salinitat marina (SSS) és important per a investigar i predir l’extensió del fenòmen del canvi climàtic. La missió Soil Moisture and Ocean Salinity (SMOS) va ser seleccionada per l’Agència Espacial Europea (ESA) per a obtenir mapes de salinitat de la superfície marina a escala global i amb un temps de revisita petit. Abans del llençament de SMOS es preveu l’anàlisi de la variabilitat horitzontal de la SSS i del potencial de les dades recuperades a partir de mesures de SMOS per a reproduir comportaments oceanogràfics coneguts. L’objectiu de tot plegat és emplenar el buit existent entre les fonts de dades d’entrada/auxiliars fiables i les eines desenvolupades per a simular i processar les dades adquirides segons la configuració de SMOS. El SMOS End-to-end Performance Simulator (SEPS) és un simulador adhoc desenvolupat per la Universitat Politècnica de Catalunya (UPC) per a generar dades segons la configuració de SMOS. Es va utilitzar dades d’entrada a SEPS procedents del projecte Ocean Circulation and Climate Advanced Modeling (OCCAM), utilitzat al NOCS, a diferents resolucions espacials. Modificant SEPS per a poder fer servir com a entrada les dades OCCAM es van obtenir dades de temperatura de brillantor simulades durant un mes amb diferents observacions ascendents que cobrien la zona seleccionada. Les tasques realitzades durant l’estada a NOCS tenien la finalitat de proporcionar una tècnica fiable per a realitzar la calibració externa i per tant cancel•lar el bias, una metodologia per a promitjar temporalment les diferents adquisicions durant les observacions ascendents, i determinar la millor configuració de la funció de cost abans d’explotar i investigar les posibiltats de les dades SEPS/OCCAM per a derivar la SSS recuperada amb patrons d’alta resolució.

Disseny d'un adaptador d'IPs per a NoCs tolerants a falles

L’aparició d’un nou paradigma per al disseny de sistemes multiprocessador, les NoC; requereixen una manera d’adaptar els IP cores ja existents i permetre la seva connexió en xarxa. Aquest projecte presenta un disseny d’una interfície que aconsegueix adaptar un IP core existent, el LEON3; del protocol del bus AMBA al protocol de la xarxa. D’aquesta manera i basant-nos en idees d’interfícies discutides en l’estat de l’art, aconseguim desacoblar el processador del disseny i topologia de la xarxa.

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.

Microfluidic processor allows rapid HER2 immunohistochemistry of breast carcinomas and significantly reduces ambiguous (2+) read-outs.

Biomarker analysis is playing an essential role in cancer diagnosis, prognosis, and prediction. Quantitative assessment of immunohistochemical biomarker expression on tumor tissues is of clinical relevance when deciding targeted treatments for cancer patients. Here, we report a microfluidic tissue processor that permits accurate quantification of the expression of biomarkers on tissue sections, enabled by the ultra-rapid and uniform fluidic exchange of the device. An important clinical biomarker for invasive breast cancer is human epidermal growth factor receptor 2 [(HER2), also known as neu], a transmembrane tyrosine kinase that connotes adverse prognostic information for the patients concerned and serves as a target for personalized treatment using the humanized antibody trastuzumab. Unfortunately, when using state-of-the-art methods, the intensity of an immunohistochemical signal is not proportional to the extent of biomarker expression, causing ambiguous outcomes. Using our device, we performed tests on 76 invasive breast carcinoma cases expressing various levels of HER2. We eliminated more than 90% of the ambiguous results (n = 27), correctly assigning cases to the amplification status as assessed by in situ hybridization controls, whereas the concordance for HER2-negative (n = 31) and -positive (n = 18) cases was 100%. Our results demonstrate the clinical potential of microfluidics for accurate biomarker expression analysis. We anticipate our technique will be a diagnostic tool that will provide better and more reliable data, onto which future treatment regimes can be based.

Characterization of fecal indicator bacteria in sediments cores from the largest freshwater lake of Western Europe (Lake Geneva, Switzerland)

This study characterized the fecal indicator bacteria (FIB), including Escherichia coli (E. coli) and Enteroccocus (ENT), disseminated over time in the Bay of Vidy, which is the most contaminated area of Lake Geneva. Sediments were collected from a site located at similar to 500 m from the present waste water treatment plant (WWTP) outlet pipe, in front of the former WWTP outlet pipe, which was located at only 300 m from the coastal recreational area (before 2001). E. coil and ENT were enumerated in sediment suspension using the membrane filter method. The FIB characterization was performed for human Enterococcus faecalis (E. faecalis) and Enterococcus faecium (E. faecium) and human specific bacteroides by PCR using specific primers and a matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS). Bacterial cultures revealed that maximum values of 35.2 x 10(8) and 6.6 x 10(6) CFU g(-1) dry sediment for E. coil and ENT, respectively, were found in the sediments deposited following eutrophication of Lake Geneva in the 1970s. whereas the WWTP started operating in 1964. The same tendency was observed for the presence of human fecal pollution: the percentage of PCR amplification with primers ESP-1/ESP-2 for E. faecalis and E. faecium indicated that more than 90% of these bacteria were from human origin. Interestingly, the PCR assays for specific-human bacteroides HF183/HF134 were positive for DNA extracted from all isolated strains of sediment surrounding WWPT outlet pipe discharge. The MALDI-TOF MS confirmed the presence of general E. coli and predominance E. faecium in isolated strains. Our results demonstrated that human fecal bacteria highly increased in the sediments contaminated with WWTP effluent following the eutrophication of Lake Geneva. Additionally, other FIB cultivable strains from animals or adapted environmental strains were detected in the sediment of the bay. The approaches used in this research are valuable to assess the temporal distribution and the source of the human fecal pollution in aquatic environments. (C) 2011 Elsevier Inc. All rights reserved.

As cores no ambiente de terapia intensiva: percepções de pacientes e profissionais

A utilização das cores no ambiente da Unidade de Terapia Intensiva - UTI pode interferir no bem-estar dos profissionais e clientes. Este estudo teve como objetivo analisar percepções de profissionais e pacientes quanto às cores utilizadas no ambiente de terapia intensiva, identificando aquelas consideradas agradáveis e desagradáveis. Trata-se de pesquisa descritivo-exploratória, com enfoque quanti-qualitativo. A amostra foi constituída de clientes internados e profissionais que trabalham em três UTIs de hospitais públicos localizados em Goiânia. As cores consideradas mais agradáveis para serem utilizadas em UTI foram o azul-claro e o verde-claro. Além dessas, apontaram o amarelo-claro, palha, cinza, rosa e goiaba. O vermelho e o preto foram consideradas as cores mais desagradáveis para um ambiente de UTI. Os profis-sionais e clientes referem preferência por cores variadas, as quais podem ser utilizadas no sentido de melhorar o clima da UTI.

Os outros olhares com que nos viram.... a natureza : entre a paleta das cores e o ramo de flores

Livro de homenagem à professora Maria Emília Ricardo Marques

Optical nebulosities associated with IRAS sources in dense cloud cores

I, H¿ and [SII] CCD images of the regions around 4 young IRAS sources embedded in the dense molecular cloud cores CB 6, CB 39, AFGL 5142, and L 1251 are presented. Reflection nebulosities are found in all 4 regions. Herbig-Haro objects are detected in AFGL 5142 and L 1251. In both cases, the HH objects are new discoveries.