Análisis de rendimiento de aplicaciones paralelas de memoria compartida: problema N-body

Este trabajo analiza el rendimiento de cuatro nodos de cómputo multiprocesador de memoria compartida para resolver el problema N-body. Se paraleliza el algoritmo serie, y se codifica usando el lenguaje C extendido con OpenMP. El resultado son dos variantes que obedecen a dos criterios de optimización diferentes: minimizar los requisitos de memoria y minimizar el volumen de cómputo. Posteriormente, se realiza un proceso de análisis de las prestaciones del programa sobre los nodos de cómputo. Se modela el rendimiento de las variantes secuenciales y paralelas de la aplicación, y de los nodos de cómputo; se instrumentan y ejecutan los programas para obtener resultados en forma de varias métricas; finalmente se muestran e interpretan los resultados, proporcionando claves que explican ineficiencias y cuellos de botella en el rendimiento y posibles líneas de mejora. La experiencia de este estudio concreto ha permitido esbozar una incipiente metodología de análisis de rendimiento, identificación de problemas y sintonización de algoritmos a nodos de cómputo multiprocesador de memoria compartida.

Alineamiento múltiple de secuencias con T-Coffee: una aproximación paralela

Las aplicaciones de alineamiento múltiple de secuencias son prototipos de aplicaciones que requieren elevada potencia de cómputo y memoria. Se destacan por la relevancia científica que tienen los resultados que brindan a investigaciones científicas en el campo de la biomedicina, genética y farmacología. Las aplicaciones de alineamiento múltiple tienen la limitante de que no son capaces de procesar miles de secuencias, por lo que se hace necesario crear un modelo para resolver la problemática. Analizando el volumen de datos que se manipulan en el área de las ciencias biológica y la complejidad de los algoritmos de alineamiento de secuencias, la única vía de solución del problema es a través de la utilización de entornos de cómputo paralelos y la computación de altas prestaciones. La investigación realizada por nosotros tiene como objetivo la creación de un modelo paralelo que le permita a los algoritmos de alineamiento múltiple aumentar el número de secuencias a procesar, tratando de mantener la calidad en los resultados para garantizar la precisión científica. El modelo que proponemos emplea como base la clusterización de las secuencias de entrada utilizando criterios biológicos que permiten mantener la calidad de los resultados. Además, el modelo se enfoca en la disminución del tiempo de cómputo y consumo de memoria. Para presentar y validar el modelo utilizamos T-Coffee, como plataforma de desarrollo e investigación. El modelo propuesto pudiera ser aplicado a cualquier otro algoritmo de alineamiento múltiple de secuencias.

An objective anisotropic elastic plastic model and Algorithm applicable to bone mechanics

The implicit projection algorithm of isotropic plasticity is extended to an objective anisotropic elastic perfectly plastic model. The recursion formula developed to project the trial stress on the yield surface, is applicable to any non linear elastic law and any plastic yield function.A curvilinear transverse isotropic model based on a quadratic elastic potential and on Hill's quadratic yield criterion is then developed and implemented in a computer program for bone mechanics perspectives. The paper concludes with a numerical study of a schematic bone-prosthesis system to illustrate the potential of the model.

Parallel spinors on pseudo-riemannian spin(q) manifolds

We study simply-connected irreducible non-locally symmetric pseudo-Riemannian Spin(q) manifolds admitting parallel quaternionic spinors.

A numerical algorithm for finding solutions of a generalized Nash equilibrium problem

A family of nonempty closed convex sets is built by using the data of the Generalized Nash equilibrium problem (GNEP). The sets are selected iteratively such that the intersection of the selected sets contains solutions of the GNEP. The algorithm introduced by Iusem-Sosa (2003) is adapted to obtain solutions of the GNEP. Finally some numerical experiments are given to illustrate the numerical behavior of the algorithm.

An algorithm for semi-infinite polynomial optimization

"Vegeu el resum a l'inici del document del fitxer adjunt."

Programació d'aplicacions bioinformàtiques

Avui en dia la biologia aporta grans quantitats de dades que només la informàtica pot tractar. Les aplicacions bioinformàtiques són la més important eina d’anàlisi i comparació que tenim per entendre la vida i aconseguir desxifrar aquestes dades. Aquest projecte centra el seu esforç en l’estudi de les aplicacions dedicades a l’alineament de seqüències genètiques, i més concretament a dos algoritmes, basats en programació dinàmica i òptims: el Needleman&Wunsch i el Smith&Waterman. Amb l’objectiu de millorar el rendiment d’aquests algoritmes per a alineaments de seqüències grans, proposem diferents versions d’implementació. Busquem millorar rendiments en temps i espai. Per a aconseguir millorar els resultats aprofitem el paral·lelisme. Els resultats dels anàlisis de les versions els comparem per obtenir les dades necessàries per valorar cost, guany i rendiment.

An approximation algorithm for #k-SAT

"Vegeu el resum a l'inici del document del fitxer adjunt"

Parallelization of whole genome alignment

With the advent of High performance computing, it is now possible to achieve orders of magnitude performance and computation e ciency gains over conventional computer architectures. This thesis explores the potential of using high performance computing to accelerate whole genome alignment. A parallel technique is applied to an algorithm for whole genome alignment, this technique is explained and some experiments were carried out to test it. This technique is based in a fair usage of the available resource to execute genome alignment and how this can be used in HPC clusters. This work is a rst approximation to whole genome alignment and it shows the advantages of parallelism and some of the drawbacks that our technique has. This work describes the resource limitations of current WGA applications when dealing with large quantities of sequences. It proposes a parallel heuristic to distribute the load and to assure that alignment quality is mantained.

Including the workload effect in the parallel program signature

Performance prediction and application behavior modeling have been the subject of exten- sive research that aim to estimate applications performance with an acceptable precision. A novel approach to predict the performance of parallel applications is based in the con- cept of Parallel Application Signatures that consists in extract an application most relevant parts (phases) and the number of times they repeat (weights). Executing these phases in a target machine and multiplying its exeuction time by its weight an estimation of the application total execution time can be made. One of the problems is that the performance of an application depends on the program workload. Every type of workload affects differently how an application performs in a given system and so affects the signature execution time. Since the workloads used in most scientific parallel applications have dimensions and data ranges well known and the behavior of these applications are mostly deterministic, a model of how the programs workload affect its performance can be obtained. We create a new methodology to model how a program’s workload affect the parallel application signature. Using regression analysis we are able to generalize each phase time execution and weight function to predict an application performance in a target system for any type of workload within predefined range. We validate our methodology using a synthetic program, benchmarks applications and well known real scientific applications.

Gemcitabine, oxaliplatin and 5-FU in advanced bile duct and gallbladder carcinoma: two parallel, multicentre phase-II trials.

BACKGROUND: Gemcitabine, oxaliplatin and 5-fluorouracil (5-FU) are active in biliary tract cancer and have a potentially synergistic mode of action and non-overlapping toxicity. The objective of these trials was to determine response, survival and toxicity separately in patients with bile duct cancer (BDC) and gallbladder cancer (GBC) treated with gemcitabine/oxaliplatin/5-FU chemotherapy. METHODS: Eligible patients with histologically proven, advanced or metastatic BDC (n=37) or GBC (n=35) were treated with gemcitabine (900 mg m(-2) over 30 min), oxaliplatin (65 mg m(-2)) and 5-FU (1500 mg m(-2) over 24 h) on days 1 and 8 of a 21-day cycle. Tumour response was the primary outcome measure. RESULTS: Response rates were 19% (95% CI: 6-32%) and 23% (95% CI: 9-37%) for BDC and GBC, respectively. Median survivals were 10.0 months (95% CI: 8.6-12.4) and 9.9 months (95% CI: 7.5-12.2) for BDC and GBC, respectively, and 1- and 2-year survival rates were 40 and 23% in BDC and 34 and 6% in GBC (intention-to-treat analysis). Major grade III and IV adverse events were neutropenia, thrombocytopenia, elevated bilirubin and anorexia. CONCLUSION: Triple-drug chemotherapy achieves comparable results for response and survival to previously reported regimens, but with more toxicity.

Unpacking the cognitive map: the parallel map theory of hippocampal function

In the parallel map theory, the hippocampus encodes space with 2 mapping systems. The bearing map is constructed primarily in the dentate gyrus from directional cues such as stimulus gradients. The sketch map is constructed within the hippocampus proper from positional cues. The integrated map emerges when data from the bearing and sketch maps are combined. Because the component maps work in parallel, the impairment of one can reveal residual learning by the other. Such parallel function may explain paradoxes of spatial learning, such as learning after partial hippocampal lesions, taxonomic and sex differences in spatial learning, and the function of hippocampal neurogenesis. By integrating evidence from physiology to phylogeny, the parallel map theory offers a unified explanation for hippocampal function.

An iterative Multiscale Finite-Volume algorithm converging to the exact solution

The multiscale finite volume (MsFV) method has been developed to efficiently solve large heterogeneous problems (elliptic or parabolic); it is usually employed for pressure equations and delivers conservative flux fields to be used in transport problems. The method essentially relies on the hypothesis that the (fine-scale) problem can be reasonably described by a set of local solutions coupled by a conservative global (coarse-scale) problem. In most cases, the boundary conditions assigned for the local problems are satisfactory and the approximate conservative fluxes provided by the method are accurate. In numerically challenging cases, however, a more accurate localization is required to obtain a good approximation of the fine-scale solution. In this paper we develop a procedure to iteratively improve the boundary conditions of the local problems. The algorithm relies on the data structure of the MsFV method and employs a Krylov-subspace projection method to obtain an unconditionally stable scheme and accelerate convergence. Two variants are considered: in the first, only the MsFV operator is used; in the second, the MsFV operator is combined in a two-step method with an operator derived from the problem solved to construct the conservative flux field. The resulting iterative MsFV algorithms allow arbitrary reduction of the solution error without compromising the construction of a conservative flux field, which is guaranteed at any iteration. Since it converges to the exact solution, the method can be regarded as a linear solver. In this context, the schemes proposed here can be viewed as preconditioned versions of the Generalized Minimal Residual method (GMRES), with a very peculiar characteristic that the residual on the coarse grid is zero at any iteration (thus conservative fluxes can be obtained).

Long-term efficacy and tolerability of flutamide combined with oral contraception in moderate to severe hirsutism: A 12-month, double-blind, parallel clinical trial

OBJECTIVE Our objective was to test the efficacy and tolerability of three doses of flutamide (125, 250, and 375 mg) combined with a triphasic oral contraceptive (ethynylestradiol/levonorgestrel) during 12 months to treat moderate to severe hirsutism in patients with polycystic ovary syndrome or idiopathic hirsutism. DESIGN We conducted a randomized, double-blind, placebo-controlled, parallel clinical trial. PATIENTS A total of 131 premenopausal women, suffering from moderate to severe hirsutism, were randomized to placebo or 125, 250, or 375 mg flutamide daily associated with a triphasic oral contraceptive pill. Hirsutism (Ferriman-Gallwey), acne and seborrhea (Cremoncini), and hormone serum levels were monitored at baseline and at 3 (except hormone serum levels), 6, and 12 months. Side effects and biochemical, hematological, and hepatic parameters were assessed. METHODS We used three-way ANOVA (subject, dose, and visit) with Scheffé adjustment for multiple comparisons or nonparametrical Friedman test and least-squares mean (paired data) and Kruskall-Wallis test for unpaired data analyses. We used chi(2) or Fisher's test for categorical data. RESULTS A total of 119 patients were included in the intention-to-treat analysis. All flutamide doses induced a significant decrease in hirsutism, acne, and seborrhea scores after 12 months compared with placebo without differences among dose levels. Similar related side effects were observed with placebo and 125 mg flutamide (12.5%), and slightly higher with 250 mg (17.3%) and 375 mg (21.2%). No statistically significant differences were observed either among doses or compared with placebo. CONCLUSIONS Flutamide at 125 mg daily during 12 months was the minimum effective dose to diminish hirsutism in patients with polycystic ovary syndrome or with idiopathic hirsutism.