Rafael Mayo

Universitat Jaume I

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Enrique S. Quintana–Ort́ı

Universitat Politècnica de València

115

Francisco D. Igual

Universidad Complutense de Madrid

Maribel Castillo

Universitat de València

Antonio J. Peña

Universitat Politècnica de Catalunya

Manuel F. Dolz

Universitat Jaume I

Peter Benner

Max Planck Institute for Dynamics of Complex Technical Systems

José M. Badía

Universitat Jaume I

M. Ortiz

Universidad Complutense de Madrid

Juan C. Fernández

Hospital Universitari i Politècnic La Fe

Raúl Isea

Instituto de Estudios Avanzados

Cooperative Institutions

University of California, Irvine

Geospatial Research (United Kingdom)

Universitat Jaume I

Universitat Politècnica de Catalunya

Universidad Complutense de Madrid

Barcelona Supercomputing Center

Universitat Politècnica de València

Argonne National Laboratory

Centre National de la Recherche Scientifique

The Ohio State University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Desarrollo de nuevos materiales para la docencia de comunicaciones industriales (libros y curso abierto OCW)

Norberto Alonso Vera Sempere Manuel Alonso Castro Gil Gabriel Díaz Domínguez

En este articulo se presenta el desarrollo de nuevos materiales para la imparticion de una asignatura de Comunicaciones Industriales, dentro de las carreras de Ingenieria Tecnica Industrial e Ingenieria Industrial, y con unos objetivos orientados a l

Source

Cite

Citations (0)

Dynamic reconfiguration of noniterative scientific applications: A case study with HPG aligner

The International Journal of High Performance Computing Applications (2018)

Sergio Iserte Héctor Martínez Sergio Barrachina Maribel Castillo Rafael Mayo

Several studies have proved the benefits of job malleability, that is, the capacity of an application to adapt its parallelism to a dynamically changing number of allocated processors. The most remarkable advantages of executing malleable jobs as part of a high performance computer workload are the throughput increase and the more efficient utilization of the underlying resources. Malleability has been mostly applied to iterative applications where all the processes execute the same operations over different sets of data and with a balanced per process load. Unfortunately, not all scientific applications adhere to this process-level malleable job structure. There are scientific applications which are either noniterative or present an irregular per process load distribution. Unlike many other reconfiguration tools, the Dynamic Management of Resources Application Programming Interface (DMR API) provides the necessary flexibility to make malleable these out-of-target applications. In this article, we study the particular case of using the DMR API to generate a malleable version of HPG aligner, a distributed-memory noniterative genomic sequencer featuring an irregular communication pattern among processes. Through this first conversion of an out-of-target application to a malleable job, we both illustrate how the DMR API may be used to convert this type of applications into malleable and test the benefits of this conversion in production clusters. Our experimental results reveal an important reduction of the malleable HPG aligner jobs completion time compared to the original HPG aligner version. Furthermore, HPG aligner malleable workloads achieve a greater throughput than their fixed counterparts.

Control reconfiguration

10.1177/1094342018802347

Cite

Citations (10)

Possibility of LIBS for transition probabilities determination

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (2005)

Monsterrat Ortiz José Campos Rafael Mayo K. Blagoev G. Malcheva

Laser Induced Breakdown Spectroscopy (LIBS) is a one of the successfully used technique for measuring experimental atomic and ionic transition probabilities. This is due to the excitation procedure easily provides highly ionised species and neutral atoms. Nevertheless, its range also extends to another applications such as the industry or in astrophysics. In this work, we explain a specific experimental set-up -consist of fomred by a Nd:YAG laser and grating monochromator coupled with a time-resolved optical multichannel analyser. The employment of the time and spatial spectroscopy in a laser produced plasma for obtaining transition probabilities is also described. From the laser produced plasmas it is also possible to determine some of their properties such as the temperature or the composition. Besides, due to the high emission and temperature, it can be proved the existence of Local Thermodynamic Equilibrium allows determination of absolute values for the transition probabilities and the evaluation of some characteristics such as the self-absorption. The experimental data treatment for obtaining the transition probabilities and the different plasma properties that can be derived was explained.

Monochromator

Analyser

10.1117/12.618751

Cite

Citations (9)

Parallel Implementation of LQG Balanced Truncation for Large-Scale Systems

Lecture notes in computer science (2008)

José M. Badía Peter Benner Rafael Mayo Enrique S. Quintana–Ort́ı Gregorio Quintana-Ortı́

Truncation (statistics)

Truncation error

LTI system theory

Model order reduction

10.1007/978-3-540-78827-0_24

Cite

Citations (1)

Remote Model Reduction of Very Large Linear Systems

Peter Benner Rafael Mayo Enrique S. Quintana–Ort́ı Gregorio Quintana-Ortı́

We describe a prototype Web service for model reduction of very large-scale linear systems. A user-friendly interface is designed so that model reduction can be easily performed on a cluster of 32 nodes. Access via the www isolates the user of the service from the complexities of installing and using the parallel model reduction codes and the maintenance of the hardware.

Installation

Interface (matter)

Source

Cite

Citations (1)

GLTO: On the Adequacy of Lightweight Thread Approaches for OpenMP Implementations

Adrián Castelló Sangmin Seo Rafael Mayo Pavan Balaji Enrique S. Quintana–Ort́ı

OpenMP is the de facto standard application programming interface (API) for on-node parallelism. The most popular OpenMP runtimes rely on POSIX threads (pthreads) implementations that offer an excellent performance for coarse-grained parallelism and match perfectly with the current hardware. However, a recent trend in runtimes/applications points in the direction of leveraging massive on-node parallelism in conjunction with fine-grained and dynamic scheduling paradigms. It has been demonstrated that lightweight thread (LWT) solutions are more appropriate for these new parallel paradigms. We have developed GLTO, an OpenMP implementation over the recently-emerged Generic Lightweight Threads (GLT) API. GLT exports a common API for LWT libraries that offers the possibility of running the same application over different native LWT solutions. In this paper we use GLTO to analyze different scenarios where OpenMP implementations may benefit from the use of either LWT or pthreads. Our study reveals that none of the threading approaches obtains the best performance in all the scenarios, but that there are important gaps among them.

POSIX Threads

Implementation

Threading (protein sequence)

POSIX

10.1109/icpp.2017.15

Cite

Citations (9)

A New Approach to rCUDA

J. Duato Antonio J. Peña Federico Silla Juan C. Fernández Rafael Mayo

Source

Cite

Citations (0)

Time and energy modeling of an INTRA-ONLY HEVC encoder

Rafael Rodríguez‐Sánchez María Teresa Alonso José Luis Martínez Rafael Mayo Enrique S. Quintana–Ort́ı

In this paper, we present precise time and energy models for an intra-only HEVC video encoder. These models are a step forward to understand and estimate the computational complexity and energy demands of an HEVC encoder, which in turn opens the path to finely tuning the computational resources that are dedicated to this purpose. Our models estimate the complexity and energy consumed by the HEVC encoder, in a frame by frame basis, considering two factors: the quantification parameter used to encode each frame and the spatial information of that frame. Our experimental validation demonstrates the accuracy of these models, which report errors that are, on average, below 10% for full HD videos, and 5% for 832 × 480 videos.

ENCODE

Intra-frame

10.1109/vcip.2015.7457831

Cite

Citations (12)

Power-aware Dense Linear Algebra Implementations on Multi-core and Many-core Processors.

Pedro Alonso Manuel F. Dolz Francisco D. Igual Bryan Marker Rafael Mayo

Linear algebra

Implementation

Multi-core processor

Source

Cite

Citations (3)

Analysis of Strategies to Save Energy for Message-Passing Dense Linear Algebra Kernels

Maribel Castillo Juan C. Fernández Rafael Mayo Enrique S. Quintana–Ort́ı Vicente Roca

In this paper we analyze the impact that energy-saving strategies, like the application of DVFS via Linux governors and the MPI communication mode, have on the performance and energy consumption of message-passing dense linear algebra operations. In the study, we employ codes from ScaLAPACK for three matrix kernels, the matrix-matrix and matrix-vector products and the Cholesky factorization, which exhibit different levels of concurrency and CPU/memory activity. Following a recent trend, we also include an accelerated version of the matrix-matrix product that off-loads all computation to a graphics processor and study the energy gains of this hybrid solver when the general-purpose cores of the system are promoted to a low consuming mode. Experimental results on a cluster equipped with state-of-the-art computation and communication hardware illustrate the results of this study.

Linear algebra

Matrix (chemical analysis)

Solver

LU decomposition

Numerical Linear Algebra

10.1109/pdp.2012.24

Cite

Citations (6)