Distributed allocation and scheduling of applications on HPC platforms

High Performance Computing e una tecnologia usata dai cluster computazionali per creare sistemi di elaborazione che sono in grado di fornire servizi molto piu potenti rispetto ai computer tradizionali. Di conseguenza la tecnologia HPC e diventata un fattore determinante nella competizione industriale e nella ricerca. I sistemi HPC continuano a crescere in termini di nodi e core. Le previsioni indicano che il numero dei nodi arrivera a un milione a breve. Questo tipo di architettura presenta anche dei costi molto alti in termini del consumo delle risorse, che diventano insostenibili per il mercato industriale. Un scheduler centralizzato non e in grado di gestire un numero di risorse cosi alto, mantenendo un tempo di risposta ragionevole. In questa tesi viene presentato un modello di scheduling distribuito che si basa sulla programmazione a vincoli e che modella il problema dello scheduling grazie a una serie di vincoli temporali e vincoli sulle risorse che devono essere soddisfatti. Lo scheduler cerca di ottimizzare le performance delle risorse e tende ad avvicinarsi a un profilo di consumo desiderato, considerato ottimale. Vengono analizzati vari modelli diversi e ognuno di questi viene testato in vari ambienti.

Collision Detection: Broad Phase Adaptation from Multi-Core to Multi-GPU Architecture

We present in this paper several contributions on the collision detection optimization centered on hardware performance. We focus on the broad phase which is the first step of the collision detection process and propose three new ways of parallelization of the well-known Sweep and Prune algorithm. We first developed a multi-core model takes into account the number of available cores. Multi-core architecture enables us to distribute geometric computations with use of multi-threading. Critical writing section and threads idling have been minimized by introducing new data structures for each thread. Programming with directives, like OpenMP, appears to be a good compromise for code portability. We then proposed a new GPU-based algorithm also based on the "Sweep and Prune" that has been adapted to multi-GPU architectures. Our technique is based on a spatial subdivision method used to distribute computations among GPUs. Results show that significant speed-up can be obtained by passing from 1 to 4 GPUs in a large-scale environment.

Semantic scheduling of virtualized infrastructures for scientific workflows

Virtualized Infrastructures are a promising way for providing flexible and dynamic computing solutions for resourceconsuming tasks. Scientific Workflows are one of these kind of tasks, as they need a large amount of computational resources during certain periods of time. To provide the best infrastructure configuration for a workflow it is necessary to explore as many providers as possible taking into account different criteria like Quality of Service, pricing, response time, network latency, etc. Moreover, each one of these new resources must be tuned to provide the tools and dependencies required by each of the steps of the workflow. Working with different infrastructure providers, either public or private using their own concepts and terms, and with a set of heterogeneous applications requires a framework for integrating all the information about these elements. This work proposes semantic technologies for describing and integrating all the information about the different components of the overall system and a set of policies created by the user. Based on this information a scheduling process will be performed to generate an infrastructure configuration defining the set of virtual machines that must be run and the tools that must be deployed on them.

Improving probabilistic flood forecasting through a data assimilation scheme based on genetic programming

Opportunities offered by high performance computing provide a significant degree of promise in the enhancement of the performance of real-time flood forecasting systems. In this paper, a real-time framework for probabilistic flood forecasting through data assimilation is presented. The distributed rainfall-runoff real-time interactive basin simulator (RIBS) model is selected to simulate the hydrological process in the basin. Although the RIBS model is deterministic, it is run in a probabilistic way through the results of calibration developed in a previous work performed by the authors that identifies the probability distribution functions that best characterise the most relevant model parameters. Adaptive techniques improve the result of flood forecasts because the model can be adapted to observations in real time as new information is available. The new adaptive forecast model based on genetic programming as a data assimilation technique is compared with the previously developed flood forecast model based on the calibration results. Both models are probabilistic as they generate an ensemble of hydrographs, taking the different uncertainties inherent in any forecast process into account. The Manzanares River basin was selected as a case study, with the process being computationally intensive as it requires simulation of many replicas of the ensemble in real time.

Enhanced Failure Detection Mechanism in MapReduce

The popularity of MapReduce programming model has increased interest in the research community for its improvement. Among the other directions, the point of fault tolerance, concretely the failure detection issue seems to be a crucial one, but that until now has not reached its satisfying level. Motivated by this, I decided to devote my main research during this period into having a prototype system architecture of MapReduce framework with a new failure detection service, containing both analytical (theoretical) and implementation part. I am confident that this work should lead the way for further contributions in detecting failures to any NoSQL App frameworks, and cloud storage systems in general.

On a meaningful integration of web services in data-intensive biomedical environments: The DICODE approach

This paper reports on an innovative approach that aims to reduce information management costs in data-intensive and cognitively-complex biomedical environments. Recognizing the importance of prominent high-performance computing paradigms and large data processing technologies as well as collaboration support systems to remedy data-intensive issues, it adopts a hybrid approach by building on the synergy of these technologies. The proposed approach provides innovative Web-based workbenches that integrate and orchestrate a set of interoperable services that reduce the data-intensiveness and complexity overload at critical decision points to a manageable level, thus permitting stakeholders to be more productive and concentrate on creative activities.

On a mathematical model arising in MHD perturbed equilibrium for Stellarator devices. A numerical approach.

Abstract?We consider a mathematical model related to the stationary regime of a plasma of fusion nuclear, magnetically confined in a Stellarator device. Using the geometric properties of the fusion device, a suitable system of coordinates and averaging methods, the mathematical problem may be reduced to a two dimensional free boundary problem of nonlocal type, where the corresponding differential equation is of the Grad?Shafranov type. The current balance within each flux magnetic gives us the possibility to define the third covariant magnetic field component with respect to the averaged poloidal flux function. We present here some numerical experiences and we give some numerical approach for the averaged poloidal flux and for the third covariant magnetic field component.

Parallel Algorithms for FE-BE Coupling

When non linear physical systems of infinite extent are modelled, such as tunnels and perforations, it is necessary to simulate suitably the solution in the infinite as well as the non linearity. The finite element method (FEM) is a well known procedure for simulating the non linear behavior. However, the treatment of the infinite field with domain truncations is often questionable. On the other hand, the boundary element method (BEM) is suitable to simulate the infinite behavior without truncations. Because of this, by the combination of both methods, suitable use of the advantages of each one may be obtained. Several possibilities of FEM-BEM coupling and their performance in some practical cases are discussed in this paper. Parallelizable coupling algorithms based on domain decomposition are developed and compared with the most traditional coupling methods.

Mesh traversal and sorting for efficient memory usage in scientific codes

Applications that operate on meshes are very popular in High Performance Computing (HPC) environments. In the past, many techniques have been developed in order to optimize the memory accesses for these datasets. Different loop transformations and domain decompositions are com- monly used for structured meshes. However, unstructured grids are more challenging. The memory accesses, based on the mesh connectivity, do not map well to the usual lin- ear memory model. This work presents a method to improve the memory performance which is suitable for HPC codes that operate on meshes. We develop a method to adjust the sequence in which the data are used inside the algorithm, by means of traversing and sorting the mesh. This sorted mesh can be transferred sequentially to the lower memory levels and allows for minimum data transfer requirements. The method also reduces the lower memory requirements dra- matically: up to 63% of the L1 cache misses are removed in a traditional cache system. We have obtained speedups of up to 2.58 on memory operations as measured in a general- purpose CPU. An improvement is also observed with se- quential access memories, where we have observed reduc- tions of up to 99% in the required low-level memory size.

MedVir: 3D visual interface applied to gene profile analysis

The use of data mining techniques for the gene profile discovery of diseases, such as cancer, is becoming usual in many researches. These techniques do not usually analyze the relationships between genes in depth, depending on the different variety of manifestations of the disease (related to patients). This kind of analysis takes a considerable amount of time and is not always the focus of the research. However, it is crucial in order to generate personalized treatments to fight the disease. Thus, this research focuses on finding a mechanism for gene profile analysis to be used by the medical and biologist experts. Results: In this research, the MedVir framework is proposed. It is an intuitive mechanism based on the visualization of medical data such as gene profiles, patients, clinical data, etc. MedVir, which is based on an Evolutionary Optimization technique, is a Dimensionality Reduction (DR) approach that presents the data in a three dimensional space. Furthermore, thanks to Virtual Reality technology, MedVir allows the expert to interact with the data in order to tailor it to the experience and knowledge of the expert.

A cyber-physical approach to combined HW-SW monitoring for improving energy efficiency in data centers

High-Performance Computing, Cloud computing and next-generation applications such e-Health or Smart Cities have dramatically increased the computational demand of Data Centers. The huge energy consumption, increasing levels of CO2 and the economic costs of these facilities represent a challenge for industry and researchers alike. Recent research trends propose the usage of holistic optimization techniques to jointly minimize Data Center computational and cooling costs from a multilevel perspective. This paper presents an analysis on the parameters needed to integrate the Data Center in a holistic optimization framework and leverages the usage of Cyber-Physical systems to gather workload, server and environmental data via software techniques and by deploying a non-intrusive Wireless Sensor Net- work (WSN). This solution tackles data sampling, retrieval and storage from a reconfigurable perspective, reducing the amount of data generated for optimization by a 68% without information loss, doubling the lifetime of the WSN nodes and allowing runtime energy minimization techniques in a real scenario.

Implementing fully homomorphic encryption schemes in FPGA-based systems

LLas nuevas tecnologías orientadas a la nube, el internet de las cosas o las tendencias "as a service" se basan en el almacenamiento y procesamiento de datos en servidores remotos. Para garantizar la seguridad en la comunicación de dichos datos al servidor remoto, y en el manejo de los mismos en dicho servidor, se hace uso de diferentes esquemas criptográficos. Tradicionalmente, dichos sistemas criptográficos se centran en encriptar los datos mientras no sea necesario procesarlos (es decir, durante la comunicación y almacenamiento de los mismos). Sin embargo, una vez es necesario procesar dichos datos encriptados (en el servidor remoto), es necesario desencriptarlos, momento en el cual un intruso en dicho servidor podría a acceder a datos sensibles de usuarios del mismo. Es más, este enfoque tradicional necesita que el servidor sea capaz de desencriptar dichos datos, teniendo que confiar en la integridad de dicho servidor de no comprometer los datos. Como posible solución a estos problemas, surgen los esquemas de encriptación homomórficos completos. Un esquema homomórfico completo no requiere desencriptar los datos para operar con ellos, sino que es capaz de realizar las operaciones sobre los datos encriptados, manteniendo un homomorfismo entre el mensaje cifrado y el mensaje plano. De esta manera, cualquier intruso en el sistema no podría robar más que textos cifrados, siendo imposible un robo de los datos sensibles sin un robo de las claves de cifrado. Sin embargo, los esquemas de encriptación homomórfica son, actualmente, drás-ticamente lentos comparados con otros esquemas de encriptación clásicos. Una op¬eración en el anillo del texto plano puede conllevar numerosas operaciones en el anillo del texto encriptado. Por esta razón, están surgiendo distintos planteamientos sobre como acelerar estos esquemas para un uso práctico. Una de las propuestas para acelerar los esquemas homomórficos consiste en el uso de High-Performance Computing (HPC) usando FPGAs (Field Programmable Gate Arrays). Una FPGA es un dispositivo semiconductor que contiene bloques de lógica cuya interconexión y funcionalidad puede ser reprogramada. Al compilar para FPGAs, se genera un circuito hardware específico para el algorithmo proporcionado, en lugar de hacer uso de instrucciones en una máquina universal, lo que supone una gran ventaja con respecto a CPUs. Las FPGAs tienen, por tanto, claras difrencias con respecto a CPUs: -Arquitectura en pipeline: permite la obtención de outputs sucesivos en tiempo constante -Posibilidad de tener multiples pipes para computación concurrente/paralela. Así, en este proyecto: -Se realizan diferentes implementaciones de esquemas homomórficos en sistemas basados en FPGAs. -Se analizan y estudian las ventajas y desventajas de los esquemas criptográficos en sistemas basados en FPGAs, comparando con proyectos relacionados. -Se comparan las implementaciones con trabajos relacionados New cloud-based technologies, the internet of things or "as a service" trends are based in data storage and processing in a remote server. In order to guarantee a secure communication and handling of data, cryptographic schemes are used. Tradi¬tionally, these cryptographic schemes focus on guaranteeing the security of data while storing and transferring it, not while operating with it. Therefore, once the server has to operate with that encrypted data, it first decrypts it, exposing unencrypted data to intruders in the server. Moreover, the whole traditional scheme is based on the assumption the server is reliable, giving it enough credentials to decipher data to process it. As a possible solution for this issues, fully homomorphic encryption(FHE) schemes is introduced. A fully homomorphic scheme does not require data decryption to operate, but rather operates over the cyphertext ring, keeping an homomorphism between the cyphertext ring and the plaintext ring. As a result, an outsider could only obtain encrypted data, making it impossible to retrieve the actual sensitive data without its associated cypher keys. However, using homomorphic encryption(HE) schemes impacts performance dras-tically, slowing it down. One operation in the plaintext space can lead to several operations in the cyphertext space. Because of this, different approaches address the problem of speeding up these schemes in order to become practical. One of these approaches consists in the use of High-Performance Computing (HPC) using FPGAs (Field Programmable Gate Array). An FPGA is an integrated circuit designed to be configured by a customer or a designer after manufacturing - hence "field-programmable". Compiling into FPGA means generating a circuit (hardware) specific for that algorithm, instead of having an universal machine and generating a set of machine instructions. FPGAs have, thus, clear differences compared to CPUs: - Pipeline architecture, which allows obtaining successive outputs in constant time. -Possibility of having multiple pipes for concurrent/parallel computation. Thereby, In this project: -We present different implementations of FHE schemes in FPGA-based systems. -We analyse and study advantages and drawbacks of the implemented FHE schemes, compared to related work.

Efficient parallelization of a regional ocean model for the western Mediterranean Sea

This paper focuses on the parallelization of an ocean model applying current multicore processor-based cluster architectures to an irregular computational mesh. The aim is to maximize the efficiency of the computational resources used. To make the best use of the resources offered by these architectures, this parallelization has been addressed at all the hardware levels of modern supercomputers: firstly, exploiting the internal parallelism of the CPU through vectorization; secondly, taking advantage of the multiple cores of each node using OpenMP; and finally, using the cluster nodes to distribute the computational mesh, using MPI for communication within the nodes. The speedup obtained with each parallelization technique as well as the combined overall speedup have been measured for the western Mediterranean Sea for different cluster configurations, achieving a speedup factor of 73.3 using 256 processors. The results also show the efficiency achieved in the different cluster nodes and the advantages obtained by combining OpenMP and MPI versus using only OpenMP or MPI. Finally, the scalability of the model has been analysed by examining computation and communication times as well as the communication and synchronization overhead due to parallelization.

Phylogenomic analysis of natural products biosynthetic gene clusters allows discovery of arseno-organic metabolites in model streptomycetes

We are indebted with Marnix Medema, Paul Straight and Sean Rovito, for useful discussions and critical reading of the manuscript, as well as with Alicia Chagolla and Yolanda Rodriguez of the MS Service of Unidad Irapuato, Cinvestav, and Araceli Fernandez for technical support in high-performance computing. This work was funded by Conacyt Mexico (grants No. 179290 and 177568) and FINNOVA Mexico (grant No. 214716) to FBG. PCM was funded by Conacyt scholarship (No. 28830) and a Cinvestav posdoctoral fellowship. JF and JFK acknowledge funding from the College of Physical Sciences, University of Aberdeen, UK.