A Grid Supercomputing Enviroment for High Demand Computational Applications

Despite the huge increase in processor and interprocessor network performace, many computational problems remain unsolved due to lack of some critical resources such as floating point sustained performance, memory bandwidth, etc... Examples of these problems are found in areas of climate research, biology, astrophysics, high energy physics (montecarlo simulations) and artificial intelligence, among others. For some of these problems, computing resources of a single supercomputing facility can be 1 or 2 orders of magnitude apart from the resources needed to solve some them. Supercomputer centers have to face an increasing demand on processing performance, with the direct consequence of an increasing number of processors and systems, resulting in a more difficult administration of HPC resources and the need for more physical space, higher electrical power consumption and improved air conditioning, among other problems. Some of the previous problems can´t be easily solved, so grid computing, intended as a technology enabling the addition and consolidation of computing power, can help in solving large scale supercomputing problems. In this document, we describe how 2 supercomputing facilities in Spain joined their resources to solve a problem of this kind. The objectives of this experience were, among others, to demonstrate that such a cooperation can enable the solution of bigger dimension problems and to measure the efficiency that could be achieved. In this document we show some preliminary results of this experience and to what extend these objectives were achieved.

A lightweight supercomputing web portal for inferring phylogenetic trees

In this paper we describe a lightweight Web portal developed for running computational jobs on a IBM JS21 Bladecenter cluster, ThamesBlue, for inferring and analyzing evolutionary histories. We first discuss the need for leveraging HPC as a enabler for molecular phylogenetics research. We go on to describe how the portal is designed to interface with existing open-source software that is typical of a HPC resource configuration, and how by design this portal is generic enough to be portable to other similarly configured compute clusters, and for other applications.

A STUDY OF PENALTY FORMULATIONS USED IN THE NUMERICAL APPROXIMATION OF A RADIALLY SYMMETRIC ELASTICITY PROBLEM

We consider a class of two-dimensional problems in classical linear elasticity for which material overlapping occurs in the absence of singularities. Of course, material overlapping is not physically realistic, and one possible way to prevent it uses a constrained minimization theory. In this theory, a minimization problem consists of minimizing the total potential energy of a linear elastic body subject to the constraint that the deformation field must be locally invertible. Here, we use an interior and an exterior penalty formulation of the minimization problem together with both a standard finite element method and classical nonlinear programming techniques to compute the minimizers. We compare both formulations by solving a plane problem numerically in the context of the constrained minimization theory. The problem has a closed-form solution, which is used to validate the numerical results. This solution is regular everywhere, including the boundary. In particular, we show numerical results which indicate that, for a fixed finite element mesh, the sequences of numerical solutions obtained with both the interior and the exterior penalty formulations converge to the same limit function as the penalization is enforced. This limit function yields an approximate deformation field to the plane problem that is locally invertible at all points in the domain. As the mesh is refined, this field converges to the exact solution of the plane problem.

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.

Probabilistically analysable real-time systems (PROARTIS)

Critical real-time ebedded (CRTE) Systems require safe and tight worst-case execution time (WCET) estimations to provide required safety levels and keep costs low. However, CRTE Systems require increasing performance to satisfy performance needs of existing and new features. Such performance can be only achieved by means of more agressive hardware architectures, which are much harder to analyze from a WCET perspective. The main features considered include cache memòries and multi-core processors.Thus, althoug such features provide higher performance, corrent WCET analysis methods are unable to provide tight WCET estimations. In fact, WCET estimations become worse than for simple rand less powerful hardware. The main reason is the fact that hardware behavior is deterministic but unknown and, therefore, the worst-case behavior must be assumed most of the time, leading to large WCET estimations. The purpose of this project is developing new hardware designs together with WCET analysis tools able to provide tight and safe WCET estimations. In order to do so, those pieces of hardware whose behavior is not easily analyzable due to lack of accurate information during WCET analysis will be enhanced to produce a probabilistically analyzable behavior. Thus, even if the worst-case behavior cannot be removed, its probabilty can be bounded, and hence, a safe and tight WCET can be provided for a particular safety level in line with the safety levels of the remaining components of the system. During the first year the project we have developed molt of the evaluation infraestructure as well as the techniques hardware techniques to analyze cache memories. During the second year those techniques have been evaluated, and new purely-softwar techniques have been developed.

Memory-based scheduling of scientific computing clusters

This study looks at how increased memory utilisation affects throughput and energy consumption in scientific computing, especially in high-energy physics. Our aim is to minimise energy consumed by a set of jobs without increasing the processing time. The earlier tests indicated that, especially in data analysis, throughput can increase over 100% and energy consumption decrease 50% by processing multiple jobs in parallel per CPU core. Since jobs are heterogeneous, it is not possible to find an optimum value for the number of parallel jobs. A better solution is based on memory utilisation, but finding an optimum memory threshold is not straightforward. Therefore, a fuzzy logic-based algorithm was developed that can dynamically adapt the memory threshold based on the overall load. In this way, it is possible to keep memory consumption stable with different workloads while achieving significantly higher throughput and energy-efficiency than using a traditional fixed number of jobs or fixed memory threshold approaches.

Let's do data research work: the creation of a portal with research information from Catalan Universities

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

Learning-Based Approach to Estimation of Morphable Model Parameters

We describe the key role played by partial evaluation in the Supercomputing Toolkit, a parallel computing system for scientific applications that effectively exploits the vast amount of parallelism exposed by partial evaluation. The Supercomputing Toolkit parallel processor and its associated partial evaluation-based compiler have been used extensively by scientists at MIT, and have made possible recent results in astrophysics showing that the motion of the planets in our solar system is chaotically unstable.

Exploiting the Parallelism Exposed by Partial Evaluation

We describe the key role played by partial evaluation in the Supercomputing Toolkit, a parallel computing system for scientific applications that effectively exploits the vast amount of parallelism exposed by partial evaluation. The Supercomputing Toolkit parallel processor and its associated partial evaluation-based compiler have been used extensively by scientists at MIT, and have made possible recent results in astrophysics showing that the motion of the planets in our solar system is chaotically unstable.

Managing groups of files in a rule oriented data management system (iRODS)

The iRODS system, created by the San Diego Supercomputing Centre, is a rule oriented data management system that allows the user to create sets of rules to define how the data is to be managed. Each rule corresponds to a particular action or operation (such as checksumming a file) and the system is flexible enough to allow the user to create new rules for new types of operations. The iRODS system can interface to any storage system (provided an iRODS driver is built for that system) and relies on its’ metadata catalogue to provide a virtual file-system that can handle files of any size and type. However, some storage systems (such as tape systems) do not handle small files efficiently and prefer small files to be packaged up (or “bundled”) into larger units. We have developed a system that can bundle small data files of any type into larger units - mounted collections. The system can create collection families and contains its’ own extensible metadata, including metadata on which family the collection belongs to. The mounted collection system can work standalone and is being incorporated into the iRODS system to enhance the systems flexibility to handle small files. In this paper we describe the motivation for creating a mounted collection system, its’ architecture and how it has been incorporated into the iRODS system. We describe different technologies used to create the mounted collection system and provide some performance numbers.