Dependencia de los algoritmos con el consumo de energía en sistemas HPC

El consumo energético es un aspecto cada vez más importante en el diseño de microprocesadores. Este trabajo experimenta con una técnica de control del consumo, el escalado dinámico de tensión y frecuencia (DVFS, siglas en inglés), para determinar cuan efectiva es la misma en la ejecución de programas con diferentes cargas de trabajo, intensivas en cómputo o memoria. Además, se ha extendido la experimentación a varios núcleos de ejecución, permitiendo comprobar en que medida las características de la ejecución en una arquitectura multicore afecta al desempeño de dicha técnica.

Optimització d'una aplicació bioinformàtica d'aliniament de seqüències executada en processadors many-core (GPUs)

Las herramientas de análisis de secuencias genómicas permiten a los biólogos identificar y entender regiones fundamentales que tienen implicación en enfermedades genéticas. Actualmente existe una necesidad de dotar al ámbito científico de herramientas de análisis eficientes. Este proyecto lleva a cabo una caracterización y análisis del rendimiento de algoritmos utilizados en la comparación de secuencias genómicas completas, y ejecutadas en arquitecturas MultiCore y ManyCore. A partir del análisis se evalúa la idoneidad de este tipo de arquitecturas para resolver el problema de comparar secuencias genómicas. Finalmente se propone una serie de modificaciones en las implementaciones de estos algoritmos con el objetivo de mejorar el rendimiento.

Multicast extension of unicast charging for QoS Services

In order to successfully deploy multicast services in QoS-aware networks, pricing architectures must take into account the particular characteristics of multicast sessions. With this objective, we propose a charging scheme for QoS multicast services, assuming that the unicast cost of each interconnecting link is determined and that such cost is expressed in terms of quality of service (QoS) parameters. Our scheme allows determining the cost distribution of a multicast session along a cost distribution tree (CDT), and basing such distribution in those pre-existing unicast cost functions. The paper discusses in detail the main characteristics of the problem in a realistic interdomain scenario and how the proposed scheme would contribute to its solution

Hybrid coordination of reinforcement learning-based behaviors for AUV control

This paper proposes a hybrid coordination method for behavior-based control architectures. The hybrid method takes advantages of the robustness and modularity in competitive approaches as well as optimized trajectories in cooperative ones. This paper shows the feasibility of applying this hybrid method with a 3D-navigation to an autonomous underwater vehicle (AUV). The behaviors are learnt online by means of reinforcement learning. A continuous Q-learning implemented with a feed-forward neural network is employed. Realistic simulations were carried out. The results obtained show the good performance of the hybrid method on behavior coordination as well as the convergence of the behaviors

Proposal of a parallel architecture for a motion detection algorithm

This paper proposes a parallel architecture for estimation of the motion of an underwater robot. It is well known that image processing requires a huge amount of computation, mainly at low-level processing where the algorithms are dealing with a great number of data. In a motion estimation algorithm, correspondences between two images have to be solved at the low level. In the underwater imaging, normalised correlation can be a solution in the presence of non-uniform illumination. Due to its regular processing scheme, parallel implementation of the correspondence problem can be an adequate approach to reduce the computation time. Taking into consideration the complexity of the normalised correlation criteria, a new approach using parallel organisation of every processor from the architecture is proposed

A new approach to real time traffic sign recognition based on colour information

The automatic interpretation of conventional traffic signs is very complex and time consuming. The paper concerns an automatic warning system for driving assistance. It does not interpret the standard traffic signs on the roadside; the proposal is to incorporate into the existing signs another type of traffic sign whose information will be more easily interpreted by a processor. The type of information to be added is profuse and therefore the most important object is the robustness of the system. The basic proposal of this new philosophy is that the co-pilot system for automatic warning and driving assistance can interpret with greater ease the information contained in the new sign, whilst the human driver only has to interpret the "classic" sign. One of the codings that has been tested with good results and which seems to us easy to implement is that which has a rectangular shape and 4 vertical bars of different colours. The size of these signs is equivalent to the size of the conventional signs (approximately 0.4 m2). The colour information from the sign can be easily interpreted by the proposed processor and the interpretation is much easier and quicker than the information shown by the pictographs of the classic signs

On AUV control architecture

This paper surveys control architectures proposed in the literature and describes a control architecture that is being developed for a semi-autonomous underwater vehicle for intervention missions (SAUVIM) at the University of Hawaii. Conceived as hybrid, this architecture has been organized in three layers: planning, control and execution. The mission is planned with a sequence of subgoals. Each subgoal has a related task supervisor responsible for arranging a set of pre-programmed task modules in order to achieve the subgoal. Task modules are the key concept of the architecture. They are the main building blocks and can be dynamically re-arranged by the task supervisor. In our architecture, deliberation takes place at the planning layer while reaction is dealt through the parallel execution of the task modules. Hence, the system presents both a hierarchical and an heterarchical decomposition, being able to show a predictable response while keeping rapid reactivity to the dynamic environment

Label Space Reduction in MPLS Networks: How Much Can A Single Stacked Label Do?

Most network operators have considered reducing LSR label spaces (number of labels used) as a way of simplifying management of underlaying virtual private networks (VPNs) and therefore reducing operational expenditure (OPEX). The IETF outlined the label merging feature in MPLS-allowing the configuration of multipoint-to-point connections (MP2P)-as a means of reducing label space in LSRs. We found two main drawbacks in this label space reduction a)it should be separately applied to a set of LSPs with the same egress LSR-which decreases the options for better reductions, and b)LSRs close to the edge of the network experience a greater label space reduction than those close to the core. The later implies that MP2P connections reduce the number of labels asymmetrically

Exploring Cross-layer power management for PGAS applications on the SCC platform

Technological limitations and power constraints are resulting in high-performance parallel computing architectures that are based on large numbers of high-core-count processors. Commercially available processors are now at 8 and 16 cores and experimental platforms, such as the many-core Intel Single-chip Cloud Computer (SCC) platform, provide much higher core counts. These trends are presenting new sets of challenges to HPC applications including programming complexity and the need for extreme energy efficiency.In this work, we first investigate the power behavior of scientific PGAS application kernels on the SCC platform, and explore opportunities and challenges for power management within the PGAS framework. Results obtained via empirical evaluation of Unified Parallel C (UPC) applications on the SCC platform under different constraints, show that, for specific operations, the potential for energy savings in PGAS is large; and power/performance trade-offs can be effectively managed using a cross-layerapproach. We investigate cross-layer power management using PGAS language extensions and runtime mechanisms that manipulate power/performance tradeoffs. Specifically, we present the design, implementation and evaluation of such a middleware for application-aware cross-layer power management of UPC applications on the SCC platform. Finally, based on our observations, we provide a set of recommendations and insights that can be used to support similar power management for PGAS applications on other many-core platforms.

Análisis de rendimiento de aplicaciones en sistemas multicore

El rápido crecimiento del los sistemas multicore y los diversos enfoques que estos han tomado, permiten que procesos complejos que antes solo eran posibles de ejecutar en supercomputadores, hoy puedan ser ejecutados en soluciones de bajo coste también denominadas "hardware de comodidad". Dichas soluciones pueden ser implementadas usando los procesadores de mayor demanda en el mercado de consumo masivo (Intel y AMD). Al escalar dichas soluciones a requerimientos de cálculo científico se hace indispensable contar con métodos para medir el rendimiento que los mismos ofrecen y la manera como los mismos se comportan ante diferentes cargas de trabajo. Debido a la gran cantidad de tipos de cargas existentes en el mercado, e incluso dentro de la computación científica, se hace necesario establecer medidas "típicas" que puedan servir como soporte en los procesos de evaluación y adquisición de soluciones, teniendo un alto grado de certeza de funcionamiento. En la presente investigación se propone un enfoque práctico para dicha evaluación y se presentan los resultados de las pruebas ejecutadas sobre equipos de arquitecturas multicore AMD e Intel.

Porting and performance analysis of EC-Earth System on the BSC-MareNostrum Supercomputer

Earth System Models (ESM) have been successfuly developed over past few years, and are currently beeing used for simulating present day-climate, seasonal to interanual predictions of climate change. The supercomputer performance plays an important role in climate modeling since one of the challenging issues for climate modellers is to efficiently and accurately couple earth System components on present day computers architectures. At the Barcelona Supercomputing Center (BSC), we work with the EC- Earth System Model. The EC- Earth is an ESM, which currently consists of an atmosphere (IFS) and an ocean (NEMO) model that communicate with each other through the OASIS coupler. Additional modules (e.g. for chemistry and vegetation ) are under development. The EC-Earth ESM has been ported successfully over diferent high performance computin platforms (e.g, IBM P6 AIX, CRAY XT-5, Intelbased Linux Clusters, SGI Altix) at diferent sites in Europ (e.g., KNMI, ICHEC, ECMWF). The objective of the first phase of the project was to identify and document the issues related with the portability and performance of EC-Earth on the MareNostrum supercomputer, a System based on IBM PowerPC 970MP processors and run under a Linux Suse Distribution. EC-Earth was successfully ported to MareNostrum, and a compilation incompatibilty was solved by a two step compilation approach using XLF version 10.1 and 12.1 compilers. In addition, the EC-Earth performance was analyzed with respect to escalability and trace analysis with the Paravear software. This analysis showed that EC-Earth with a larger number of IFS CPUs (<128) is not feasible at the moment since some issues exists with the IFS-NEMO balance and MPI Communications.

Parallelizing remote sensing image geometric correction

Remote sensing spatial, spectral, and temporal resolutions of images, acquired over a reasonably sized image extent, result in imagery that can be processed to represent land cover over large areas with an amount of spatial detail that is very attractive for monitoring, management, and scienti c activities. With Moore's Law alive and well, more and more parallelism is introduced into all computing platforms, at all levels of integration and programming to achieve higher performance and energy e ciency. Being the geometric calibration process one of the most time consuming processes when using remote sensing images, the aim of this work is to accelerate this process by taking advantage of new computing architectures and technologies, specially focusing in exploiting computation over shared memory multi-threading hardware. A parallel implementation of the most time consuming process in the remote sensing geometric correction has been implemented using OpenMP directives. This work compares the performance of the original serial binary versus the parallelized implementation, using several multi-threaded modern CPU architectures, discussing about the approach to nd the optimum hardware for a cost-e ective execution.

Contribución al diseño de GNSS-SDR, un receptor GNSS de código abierto

[ANGLÈS] This project introduces GNSS-SDR, an open source Global Navigation Satellite System software-defined receiver. The lack of reconfigurability of current commercial-of-the-shelf receivers and the advent of new radionavigation signals and systems make software receivers an appealing approach to design new architectures and signal processing algorithms. With the aim of exploring the full potential of this forthcoming scenario with a plurality of new signal structures and frequency bands available for positioning, this paper describes the software architecture design and provides details about its implementation, targeting a multiband, multisystem GNSS receiver. The result is a testbed for GNSS signal processing that allows any kind of customization, including interchangeability of signal sources, signal processing algorithms, interoperability with other systems, output formats, and the offering of interfaces to all the intermediate signals, parameters and variables. The source code release under the GNU General Public License (GPL) secures practical usability, inspection, and continuous improvement by the research community, allowing the discussion based on tangible code and the analysis of results obtained with real signals. The source code is complemented by a development ecosystem, consisting of a website (http://gnss-sdr.org), as well as a revision control system, instructions for users and developers, and communication tools. The project shows in detail the design of the initial blocks of the Signal Processing Plane of the receiver: signal conditioner, the acquisition block and the receiver channel, the project also extends the functionality of the acquisition and tracking modules of the GNSS-SDR receiver to track the new Galileo E1 signals available. Each section provides a theoretical analysis, implementation details of each block and subsequent testing to confirm the calculations with both synthetically generated signals and with real signals from satellites in space.

Exchange bias between magnetoelectric YMnO3 and ferromagnetic SrRuO3 epitaxial films

Orthorhombic YMnO3 (YMO) epitaxial thin films were deposited on SrTiO3 (STO) single-crystal substrates. We show that the out-of-plane texture of the YMO films can be tailored using STO substrates having (001), (110), or (111) orientations. We report on the magnetic properties of the YMO(010) films grown on STO(001) substrates. The dependence of the susceptibility on the temperature indicates that the films are antiferromagnetic below the Néel temperature (around 35 K). Orthorhombic YMO(010) films were also deposited on an epitaxial buffer layer of ferromagnetic and metallic SrRuO3 (SRO). The magnetic hysteresis loops of SRO show exchange bias at temperatures below the Néel temperature of YMO. These results confirm that the YMO films are antiferromagnetic and demonstrate that magnetoelectric YMO can be integrated in functional epitaxial architectures.