Multicore Scheduling of Real-Time Irregular Parallel Algorithms in Linux

Face à estagnação da tecnologia uniprocessador registada na passada década, aos principais fabricantes de microprocessadores encontraram na tecnologia multi-core a resposta `as crescentes necessidades de processamento do mercado. Durante anos, os desenvolvedores de software viram as suas aplicações acompanhar os ganhos de performance conferidos por cada nova geração de processadores sequenciais, mas `a medida que a capacidade de processamento escala em função do número de processadores, a computação sequencial tem de ser decomposta em várias partes concorrentes que possam executar em paralelo, para que possam utilizar as unidades de processamento adicionais e completar mais rapidamente. A programação paralela implica um paradigma completamente distinto da programação sequencial. Ao contrário dos computadores sequenciais tipificados no modelo de Von Neumann, a heterogeneidade de arquiteturas paralelas requer modelos de programação paralela que abstraiam os programadores dos detalhes da arquitectura e simplifiquem o desenvolvimento de aplicações concorrentes. Os modelos de programação paralela mais populares incitam os programadores a identificar instruções concorrentes na sua lógica de programação, e a especificá-las sob a forma de tarefas que possam ser atribuídas a processadores distintos para executarem em simultâneo. Estas tarefas são tipicamente lançadas durante a execução, e atribuídas aos processadores pelo motor de execução subjacente. Como os requisitos de processamento costumam ser variáveis, e não são conhecidos a priori, o mapeamento de tarefas para processadores tem de ser determinado dinamicamente, em resposta a alterações imprevisíveis dos requisitos de execução. `A medida que o volume da computação cresce, torna-se cada vez menos viável garantir as suas restrições temporais em plataformas uniprocessador. Enquanto os sistemas de tempo real se começam a adaptar ao paradigma de computação paralela, há uma crescente aposta em integrar execuções de tempo real com aplicações interativas no mesmo hardware, num mundo em que a tecnologia se torna cada vez mais pequena, leve, ubíqua, e portável. Esta integração requer soluções de escalonamento que simultaneamente garantam os requisitos temporais das tarefas de tempo real e mantenham um nível aceitável de QoS para as restantes execuções. Para tal, torna-se imperativo que as aplicações de tempo real paralelizem, de forma a minimizar os seus tempos de resposta e maximizar a utilização dos recursos de processamento. Isto introduz uma nova dimensão ao problema do escalonamento, que tem de responder de forma correcta a novos requisitos de execução imprevisíveis e rapidamente conjeturar o mapeamento de tarefas que melhor beneficie os critérios de performance do sistema. A técnica de escalonamento baseado em servidores permite reservar uma fração da capacidade de processamento para a execução de tarefas de tempo real, e assegurar que os efeitos de latência na sua execução não afectam as reservas estipuladas para outras execuções. No caso de tarefas escalonadas pelo tempo de execução máximo, ou tarefas com tempos de execução variáveis, torna-se provável que a largura de banda estipulada não seja consumida por completo. Para melhorar a utilização do sistema, os algoritmos de partilha de largura de banda (capacity-sharing) doam a capacidade não utilizada para a execução de outras tarefas, mantendo as garantias de isolamento entre servidores. Com eficiência comprovada em termos de espaço, tempo, e comunicação, o mecanismo de work-stealing tem vindo a ganhar popularidade como metodologia para o escalonamento de tarefas com paralelismo dinâmico e irregular. O algoritmo p-CSWS combina escalonamento baseado em servidores com capacity-sharing e work-stealing para cobrir as necessidades de escalonamento dos sistemas abertos de tempo real. Enquanto o escalonamento em servidores permite partilhar os recursos de processamento sem interferências a nível dos atrasos, uma nova política de work-stealing que opera sobre o mecanismo de capacity-sharing aplica uma exploração de paralelismo que melhora os tempos de resposta das aplicações e melhora a utilização do sistema. Esta tese propõe uma implementação do algoritmo p-CSWS para o Linux. Em concordância com a estrutura modular do escalonador do Linux, ´e definida uma nova classe de escalonamento que visa avaliar a aplicabilidade da heurística p-CSWS em circunstâncias reais. Ultrapassados os obstáculos intrínsecos `a programação da kernel do Linux, os extensos testes experimentais provam que o p-CSWS ´e mais do que um conceito teórico atrativo, e que a exploração heurística de paralelismo proposta pelo algoritmo beneficia os tempos de resposta das aplicações de tempo real, bem como a performance e eficiência da plataforma multiprocessador.

The HIF1A Functional Genetic Polymorphism at Locus +1772 Associates with Progression to Metastatic Prostate Cancer and Refractoriness to Hormonal Castration

The hypoxia inducible factor 1 alpha (HIF1a) is a key regulator of tumour cell response to hypoxia, orchestrating mechanisms known to be involved in cancer aggressiveness and metastatic behaviour. In this study we sought to evaluate the association of a functional genetic polymorphism in HIF1A with overall and metastatic prostate cancer (PCa) risk and with response to androgen deprivation therapy (ADT). The HIF1A +1772 C>T (rs11549465) polymorphism was genotyped, using DNA isolated from peripheral blood, in 1490 male subjects (754 with prostate cancer and 736 controls cancer-free) through Real-Time PCR. A nested group of cancer patients who were eligible for androgen deprivation therapy was followed up. Univariate and multivariate models were used to analyse the response to hormonal treatment and the risk for developing distant metastasis. Age-adjusted odds ratios were calculated to evaluate prostate cancer risk. Our results showed that patients under ADT carrying the HIF1A +1772 T-allele have increased risk for developing distant metastasis (OR, 2.0; 95%CI, 1.1-3.9) and an independent 6-fold increased risk for resistance to ADT after multivariate analysis (OR, 6.0; 95%CI, 2.2-16.8). This polymorphism was not associated with increased risk for being diagnosed with prostate cancer (OR, 0.9; 95%CI, 0.7-1.2). The HIF1A +1772 genetic polymorphism predicts a more aggressive prostate cancer behaviour, supporting the involvement of HIF1a in prostate cancer biological progression and ADT resistance. Molecular profiles using hypoxia markers may help predict clinically relevant prostate cancer and response to ADT.

Evaluation of the use of real-time PCR for human T cell lymphotropic virus 1 and 2 as a confirmatory test in screening for blood donors

INTRODUCTION: HTLV-1/2 screening among blood donors commonly utilizes an enzyme-linked immunosorbent assay (EIA), followed by a confirmatory method such as Western blot (WB) if the EIA is positive. However, this algorithm yields a high rate of inconclusive results, and is expensive. METHODS: Two qualitative real-time PCR assays were developed to detect HTLV-1 and 2, and a total of 318 samples were tested (152 blood donors, 108 asymptomatic carriers, 26 HAM/TSP patients and 30 seronegative individuals). RESULTS: The sensitivity and specificity of PCR in comparison with WB results were 99.4% and 98.5%, respectively. PCR tests were more efficient for identifying the virus type, detecting HTLV-2 infection and defining inconclusive cases. CONCLUSIONS: Because real-time PCR is sensitive and practical and costs much less than WB, this technique can be used as a confirmatory test for HTLV in blood banks, as a replacement for WB.

Solving large 0–1 multidimensional knapsack problems by a new simplified binary artificial fish swarm algorithm

The artificial fish swarm algorithm has recently been emerged in continuous global optimization. It uses points of a population in space to identify the position of fish in the school. Many real-world optimization problems are described by 0-1 multidimensional knapsack problems that are NP-hard. In the last decades several exact as well as heuristic methods have been proposed for solving these problems. In this paper, a new simpli ed binary version of the artificial fish swarm algorithm is presented, where a point/ fish is represented by a binary string of 0/1 bits. Trial points are created by using crossover and mutation in the different fi sh behavior that are randomly selected by using two user de ned probability values. In order to make the points feasible the presented algorithm uses a random heuristic drop item procedure followed by an add item procedure aiming to increase the profit throughout the adding of more items in the knapsack. A cyclic reinitialization of 50% of the population, and a simple local search that allows the progress of a small percentage of points towards optimality and after that refines the best point in the population greatly improve the quality of the solutions. The presented method is tested on a set of benchmark instances and a comparison with other methods available in literature is shown. The comparison shows that the proposed method can be an alternative method for solving these problems.

Preservación de la información génica en bacterias; mecanismos y modulación molecular. Preservation of the genetic information in bacteria; mechanisms and molecular modulation.

El objetivo general del presente proyecto es contribuir a la caracterización genética y bioquímica molecular de mecanismos involucrados en el mantenimiento de la información génica, a través del estudio de sistemas fisiológicos involucrados en la prevención, reparación y tolerancia de mutaciones. Dichos sistemas se encuentran evolutivamente conservados y ampliamente distribuidos en los seres vivos. La importancia de los mismos se refleja en el hecho que su deficiencia genera en humanos, enfermedades genéticas, apoptosis y cáncer; y en especies procariotas, células denominadas "hipermutadoras". En los últimos años el estudio de la hipermutabilidad en bacterias ha cobrado gran interés ya que se le atribuye importancia en procesos infectivos y en aspectos básicos relacionados a evolución. Nuestro modelo de estudio son las bacterias Pseudomonas aeruginosa y Escherichia coli, siendo esta última especie no solo modelo de estudio sino también especie de referencia. P. aeruginosa es una bacteria ambiental gram negativa, e importante patógeno oportunista de humanos. Específicamente nos proponemos estudiar en P. aeruginosa algunos aspectos particulares del Sistema de Reparación de Bases Apareadas Incorrectamente (Mismatch Repair System, MRS), del Sistema de Prevención/Reparación de Lesiones Oxidativas generadas a través de 8-oxo-7,8-dihidroguanina (8-oxo-dG ó GO) y el papel de las ADN Polimerasas de baja fidelidad en la modulación de la tasa de mutación. Asimismo estamos interesados en estudiar en cepas de E. coli deficientes en el sistema Dam, la existencia de subpoblaciones de alta estabilidad genética debido a la eliminación de posibles mutantes por incremento de la expresión de los otros componentes del MRS. Metodológicamente la caracterización bioquímica de factores proteicos se llevará a cabo utilizando proteínas recombinantes purificadas, análisis de interacción proteína-proteína y proteína-ADN mediante electroforesis en geles y resonancia plasmónica de superficie (Biacore), mutagenésis dirigida in vitro, y estudios de complementación en cepas mutantes específicas. Aspectos fenotípicos y de regulación génica en cultivos de biofilm y células en suspensión serán estudiados mediante la construcción de cepas mutantes, fusiones transcripcionales, PCR en tiempo real, western blot y microscopia de fluorescencia confocal.

Impact of genetic polymorphisms in cytomegalovirus glycoprotein B on outcomes in solid-organ transplant recipients with cytomegalovirus disease.

BACKGROUND:It is unknown whether specific viral polymorphisms affect in vivo therapeutic response in patients with cytomegalovirus (CMV) disease. Polymorphisms in the CMV glycoprotein B (gB) gene allow discrimination of 4 distinct genotypes (gB1-gB4). We assessed the influence of gB genotypes on the clinical and virologic outcome of CMV disease. METHODS:Solid-organ transplant recipients enrolled in a multicenter trial of CMV disease treatment (VICTOR study) were included in this study. CMV gB genotyping was performed using quantitative real-time polymerase chain reaction at day 0 (start of antiviral therapy). RESULTS:Among 239 patients with CMV disease, the prevalence of gB strain types was 26% for gB1, 10% for gB2, 10% for gB3, and 5% for gB4, whereas mixed infections were present in 49%. Donor-seropositive/recipient-seropositive patients were more likely to have mixed gB infection than donor-seropositive/recipient-seronegative patients (40% vs. 12%; P = .001). Median baseline viral loads were higher and time to viral eradication was longer ( P = .006 and P = .026 , respectively) for mixed infection versus infection with a single genotype. In a multivariate model, mixed gB infection was a significant predictor of failure to eradicate virus by day 21 (mixed vs single genotype; odds ratio, 2.66; 95% confidence interval, 1.31-5.38; P = .007 ) after controlling for baseline viral load, CMV serostatus at baseline, ganciclovir resistance, and antiviral treatment. No effect of gB genotype was seen on virologic or clinical CMV recurrence. CONCLUSIONS:No specific gB genotype appears to confer a specific CMV virulence advantage. However, mixed gB genotype infections are associated with higher viral loads and delayed viral clearance.

Quantitative genetic modeling and inference in the presence of nonignorable missing data.

Natural selection is typically exerted at some specific life stages. If natural selection takes place before a trait can be measured, using conventional models can cause wrong inference about population parameters. When the missing data process relates to the trait of interest, a valid inference requires explicit modeling of the missing process. We propose a joint modeling approach, a shared parameter model, to account for nonrandom missing data. It consists of an animal model for the phenotypic data and a logistic model for the missing process, linked by the additive genetic effects. A Bayesian approach is taken and inference is made using integrated nested Laplace approximations. From a simulation study we find that wrongly assuming that missing data are missing at random can result in severely biased estimates of additive genetic variance. Using real data from a wild population of Swiss barn owls Tyto alba, our model indicates that the missing individuals would display large black spots; and we conclude that genes affecting this trait are already under selection before it is expressed. Our model is a tool to correctly estimate the magnitude of both natural selection and additive genetic variance.

Genetic variation near IRS1 associates with reduced adiposity and an impaired metabolic profile.

Genome-wide association studies have identified 32 loci influencing body mass index, but this measure does not distinguish lean from fat mass. To identify adiposity loci, we meta-analyzed associations between ∼2.5 million SNPs and body fat percentage from 36,626 individuals and followed up the 14 most significant (P < 10(-6)) independent loci in 39,576 individuals. We confirmed a previously established adiposity locus in FTO (P = 3 × 10(-26)) and identified two new loci associated with body fat percentage, one near IRS1 (P = 4 × 10(-11)) and one near SPRY2 (P = 3 × 10(-8)). Both loci contain genes with potential links to adipocyte physiology. Notably, the body-fat-decreasing allele near IRS1 is associated with decreased IRS1 expression and with an impaired metabolic profile, including an increased visceral to subcutaneous fat ratio, insulin resistance, dyslipidemia, risk of diabetes and coronary artery disease and decreased adiponectin levels. Our findings provide new insights into adiposity and insulin resistance.

Association study of genetic variants of pro-inflammatory chemokine and cytokine genes in systemic lupus erythematosus

BACKGROUND. Several lines of evidence suggest that chemokines and cytokines play an important role in the inflammatory development and progression of systemic lupus erythematosus. The aim of this study was to evaluate the relevance of functional genetic variations of RANTES, IL-8, IL-1alpha, and MCP-1 for systemic lupus erythematosus. METHODS. The study was conducted on 500 SLE patients and 481 ethnically matched healthy controls. Genotyping of polymorphisms in the RANTES, IL-8, IL-1alpha, and MCP-1 genes were performed using a real-time polymerase chain reaction (PCR) system with pre-developed TaqMan allelic discrimination assay. RESULTS. No significant differences between SLE patients and healthy controls were observed when comparing genotype, allele or haplotype frequencies of the RANTES, IL-8, IL-1alpha, and MCP-1 polymorphisms. In addition, no evidence for association with clinical sub-features of SLE was found. CONCLUSION. These results suggest that the tested functional variation of RANTES, IL-8, IL-1alpha, and MCP-1 genes do not confer a relevant role in the susceptibility or severity of SLE in the Spanish population.

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

Genetic analysis of caveolin-1 and eNOS genes in colorectal cancer.

Caveolae are involved in physical compartmentalization between different groups of signaling events. Its main component, CAV1, modulates different pathways in cellular physiology. The emerging evidence pointing to the role of CAV1 in cancer led us to study whether different alleles of this gene are associated with colorectal cancer (CRC). Since one of the most characterized enzymes regulated by CAV1 is eNOS, we decided to include both genes in this study. We analyzed five SNPs in 360 unrelated CRC patients and 550 controls from the general population. Two of these SNPs were located within eNOS and three within the CAV1 gene. Although haplotype distribution was not associated with CRC, haplotype TiA (CAV1) was associated with familiar forms of CRC (p<0.05). This was especially evident in CRC antecedents and nuclear forms of CRC. If both CG (eNOS) and TiA (CAV1) haplotypes were taken together, this association increased in significance. Thus, we propose that CAV1, either alone or together with eNOS alleles, might modify CRC heritability.

Using 3D surface datasets to understand landslide evolution: From analogue models to real case study

Early detection of landslide surface deformation with 3D remote sensing techniques, as TLS, has become a great challenge during last decade. To improve our understanding of landslide deformation, a series of analogue simulation have been carried out on non-rigid bodies coupled with 3D digitizer. All these experiments have been carried out under controlled conditions, as water level and slope angle inclination. We were able to follow 3D surface deformation suffered by complex landslide bodies from precursory deformation still larger failures. These experiments were the basis for the development of a new algorithm for the quantification of surface deformation using automatic tracking method on discrete points of the slope surface. To validate the algorithm, comparisons were made between manually obtained results and algorithm surface displacement results. Outputs will help in understanding 3D deformation during pre-failure stages and failure mechanisms, which are fundamental aspects for future implementation of 3D remote sensing techniques in early warning systems.

Real-time molecular epidemiology of tuberculosis by direct genotyping of smear-positive clinical specimens.

We applied MIRU-VNTR (mycobacterial interspersed repetitive-unit-variable-number tandem-repeat typing) to directly analyze the bacilli present in 61 stain-positive specimens from tuberculosis patients. A complete MIRU type (24 loci) was obtained for all but one (no amplification in one locus) of the specimens (98.4%), and the allelic values fully correlated with those obtained from the corresponding cultures. Our study is the first to demonstrate that real-time genotyping of Mycobacterium tuberculosis can be achieved, fully transforming the way in which molecular epidemiology techniques can be integrated into control programs.

Laboratory detection of respiratory viruses by automated techniques.

Advances in clinical virology for detecting respiratory viruses have been focused on nucleic acids amplification techniques, which have converted in the reference method for the diagnosis of acute respiratory infections of viral aetiology. Improvements of current commercial molecular assays to reduce hands-on-time rely on two strategies, a stepwise automation (semi-automation) and the complete automation of the whole procedure. Contributions to the former strategy have been the use of automated nucleic acids extractors, multiplex PCR, real-time PCR and/or DNA arrays for detection of amplicons. Commercial fully-automated molecular systems are now available for the detection of respiratory viruses. Some of them could convert in point-of-care methods substituting antigen tests for detection of respiratory syncytial virus and influenza A and B viruses. This article describes laboratory methods for detection of respiratory viruses. A cost-effective and rational diagnostic algorithm is proposed, considering technical aspects of the available assays, infrastructure possibilities of each laboratory and clinic-epidemiologic factors of the infection.

Detection and differentiation of Cryptosporidium by real-time polymerase chain reaction in stool samples from patients in Rio de Janeiro, Brazil

This study reports the first genetic characterisation of Cryptosporidium isolates in Brazil using real-time polymerase chain reaction (RT-PCR). A total of 1,197 faecal specimens from children and 10 specimens from human immunodeficiency virus-infected patients were collected between 1999-2010 and screened using microscopy. Forty-eight Cryptosporidium oocyst-positive isolates were identified and analysed using a generic TaqMan assay targeting the 18S rRNA to detect Cryptosporidium species and two other TaqMan assays to identify Cryptosporidium hominis and Cryptosporidium parvum. The 18S rRNA assay detected Cryptosporidium species in all 48 of the stool specimens. The C. parvum TaqMan assay correctly identified five/48 stool samples, while 37/48 stool specimens were correctly amplified in the C. hominis TaqMan assay. The results obtained in this study support previous findings showing that C. hominis infections are more prevalent than C. parvum infections in Brazil and they demonstrate that the TaqMan RT-PCR procedure is a simple, fast and valuable tool for the detection and differentiation of Cryptosporidium species.