Abstract The performance of three implementations of the restarted GMRES algorithm with randomized-SVD-based preconditioning has been analyzed. They have been tested with a wide population of matrices of varying properties and compared to the standard ILU(0) preconditioning. The implementations comprise two variants of the preconditioner, one of them implemented for CPU-only and hybrid GPU–CPU executions to better assess the benefits and pitfalls in both contexts. The trade-off between iteration-to-solution and time-to-solution metrics is discussed and it is shown that a competitive convergence rate is attained. In addition, the CPU off-loading to the GPU leads to a significant improvement of the second metric for the largest matrices analyzed. Such an in efficiency is promising considering the various codes and tools that employ the restarted GMRES algorithm.

Abstract Every computation presents a small chance that an unexpected phenomenon ruins or modifies its output. Computers are prone to errors that, although may be very unlikely, are hard, expensive or simply impossible to avoid. In the exascale, with thousands of processors involved in a single computation, those errors are especially harmful because they can corrupt or distort the results, wasting human and material resources. In the present work, we study the effect of ionizing radiation on several pieces of commercial hardware, very common in modern supercomputers. Aiming to reproduce the natural radiation that could arise, CPUs (Xeon, EPYC) and GPUs (A100, V100, T4) are subject to a known flux of neutrons coming from two radioactive sources, namely $$^{252}$$ 252 Cf and $$^{241}$$ 241 Am-Be, in a special irradiation facility. The working hardware is irradiated under supervision to quantify any appearing error. Once the hardware response is characterised, we are able to scale down the radiation intensity and to estimate the effects on standard data centres. This can help administrators and researchers to develop their contingency plans and protocols.

In this work the strategy of the Latin American Giant Observatory (LAGO) to build a Latin American collaboration is presented. Installing Cosmic Rays detectors settled all around the Continent, from Mexico to the Antarctica, this collaboration is forming a community that embraces both high energy physicist and computer scientists. This is so because the data that are measured must be analytical processed and due to the fact that a priori and a posteriori simulations representing the effects of the radiation must be performed. To perform the calculi, customized codes have been implemented by the collaboration. With regard to the huge amount of data emerging from this network of sensors and from the computational simulations performed in a diversity of computing architectures and e-infrastructures, an effort is being carried out to catalog and preserve a vast amount of data produced by the water-Cherenkov Detector network and the complete LAGO simulation workflow that characterize each site. Metadata, Permanent Identifiers and the facilities from the LAGO Data Repository are described in this work jointly with the simulation codes used. These initiatives allow researchers to produce and find data and to directly use them in a code running by means of a Science Gateway that provides access to different clusters, Grid and Cloud infrastructures worldwide.

During the last years, High Performance Computing (HPC) resources have undergone a dramatic transformation, with an explosion on the available parallelism and the use of special purpose processors. There are international initiatives focusing on redesigning hardware and software in order to achieve the Exaflop capability. With this aim, the HPC4E project is applying the new exascale HPC techniques to energy industry simulations, customizing them if necessary, and going beyond the state-of-the-art in the required HPC exascale simulations for different energy sources that are the present and the future of energy: wind energy production and design, efficient combustion systems for biomass-derived fuels (biogas), and exploration geophysics for hydrocarbon reservoirs. HPC4E joins efforts of several institutions settled in Brazil and Europe.

Summary There are many applications in every scientific and engineering fields that have high computational requirements. They have to be adapted to either high‐performance computing or high‐throughput computing platforms, depending on their characteristics. For the latter case, the high volume of resources available in grid infrastructures should allow for a reduction of their calculation times and an increase of the accuracy of the results. Nevertheless, the low performance achieved by early‐binding methods is noticeable, and the current systems based on pilot jobs are not suitable for running legacy applications. Therefore, running a wide range of codes quickly and easily can be infeasible for many users and developers. For this reason, it would be of great advantage to count on pilot job techniques that truly exploit grid resources in an efficient way while maintaining compatibility with legacy applications. In this work, GWpilot is presented as a complete pilot job framework that overcomes the adaptability limitations of other pilot job systems to tackle the challenge of efficiently accomplishing high‐throughput calculations. To test the GWpilot system, two applications widely used for studying the properties of collisional transport in fusion plasmas (drift kinetic equation solver code and integrator of stochastic differential equations in plasmas) have been chosen as a proof of concept. Real calculations were performed with them to illustrate the adaptation process to the new framework and its performance. Additionally, the physics results obtained were analysed for completeness and further reading. Both applications also represent two different approaches further extended in the scientific community, that is, parameter sweep and Monte Carlo codes. Therefore, the general suitability of GWpilot for scientific and industrial applications belonging to other fields is demonstrated in this work. Copyright © 2014 John Wiley & Sons, Ltd.

ISDEP (Integrator of Stochastic Differential Equations for Plasmas) is a Monte Carlo code that solves the plasma dynamics in a fusion device and perfectly scales on distributed computing platforms. Montera is a recent framework developed for achieving Grid efficient executions of Monte Carlo applications, as ISDEP is. In this work, the improvement of performing the calculations of ISDEP with Montera, which rise up to 34.9%, is shown as well as an analysis on the implications it could have, which aim to show to the fusion research community the benefits of using Montera.

FAFNER is code developed by Lister which simulates by Monte Carlo methods the Neutral Beam Injection (NBI) technology, one of the most extended heating methods for fusion devices. To the date, FAFNER has been usually run at CIEMAT adapted to the TJ-II helical axis stellarator on shared memory Cray architecture machines. From this version, FAFNER has been ported to the Grid in the framework of the EGEE Project. At the same time, this work is the first step of a more ambitious target since the code can be now coupled to many others such as ion transport tools. In this paper, all these preliminary advances are described as well as the performance and portability gains obtained.

The gyrofluid electromagnetic (GEM) model studies the phenomena in the context of edge turbulence, a matter of adding collisions and electromagnetic induction to the parallel dynamics of the standard six-moment toroidal model, the use of which was done in core turbulence works. Currently, the code describes the fluctuation free-energy conservation in a gyrofluid model by means of the polarization equation which relates ExB flow and eddy energy to combinations of the potential and the density and perpendicular temperature. To the date, GEM has usually been run on high performance computers. In this work we demonstrate its feasibility as a cluster application in a production environment based on any kind of distributed memory. The scalability and correctness of our solution has been evaluated in a local cluster. Fault tolerance and Grid suitability has been demonstrated by executing our application in the EUFORIA (EUrope Fusion fOR ITER Applications) Grid infrastructure. With this work, the fusion community is provided with a new tool to simulate plasma phenomena on the Grid. It can be employed on its own or belonging to workflows, in order to perform wider, more complex analysis of fusion reactors

Calculating neoclassical (NC) transport is a fundamental part of the complete simulation cycle of the behavior of plasmas inside all tokamaks and stellerators. Also, due to NC transport is mainly determined by the magnetic properties of the device, its study is mandatory to ensure the efficiency of a certain coil configuration before it is implemented in a Fusion reactor. Thus, improvements to already constructed devices and certain design decisions for newer ones such as W7-X, NCSX or QPS will be made based on estimations of NC transport. In this work, we present the porting process to the Grid of the Drift Kinetic Equation solver code, widely accepted by the Fusion Community, devoted to obtain the monoenergetic diffusion coefficients of NC transport. The advantage of this code over the Monte Carlo applications already in production on Grid, is that it allows the estimation of all the transport coefficients, not only the diagonal ones. The tests and results obtained have been applied to the TJ-II Flexible Heliac at National Fusion Laboratory (Spain) by using the EELA-2 infrastructure.

The EELA Project (E-Infrastructure shared between Europe and Latin America) is a collaboration between Latin American and European institutions that has developed a potent e-Infrastructure for e-Science applications. Nowadays, several groups have ported their applications to the EELA Grid framework and are obtaining their first results thanks to the e-Infrastructure that has been created. This paper describes the applications already ported and the progress achieved so far. The EELA project is funded by the European Commission under the contract number IST-2006-026409.