Sergio Barrachina

Universitat Jaume I, Castellón, Valencia, Spain

Are you Sergio Barrachina?

Claim your profile

Publications (28)2.89 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: We present a concurrent algorithm for mapping short and long RNA sequences on multicore processors. Our solution processes the data, initially stored on disk, in batches of reads which are passed between the consecutive stages of a pipeline. A major operational reorganization of the original static pipeline, combined with a complete reimplementation based on POSIX threads, renders a dissociated execution between threads and stages/task types, so that threads can compute any type of pending task resulting in a dynamic pipeline. The experiments on a multicore platform reveal that this reorganization yields significantly higher performance, specially for architectures equipped with a small to moderate number of cores. As an additional contribution, our experiments also reveal that the use of 16-nucleotide (nt) seeds during the one of the stages of the pipeline, instead of the 15-nt length that was proposed originally, yields a remarkable reduction in the execution time of the global alignment process while maintaining the sensitivity of the algorithm.
    Proceedings of the 20th European MPI Users' Group Meeting; 09/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we introduce a novel parallel pipeline for fast and accurate mapping of RNA sequences on servers equipped with multicore processors. Our software, named HPG-Aligner, leverages the speed of the Burrows-Wheeler Transform to map a large number of RNA fragments (reads) rapidly, as well as the accuracy of the Smith-Waterman algorithm, that is employed to deal with conflictive reads. The aligner is complemented with a careful strategy to detect splice junctions based on the division of RNA reads into short segments (or seeds), which are then mapped onto a number of candidate alignment locations, providing useful information for the successful alignment of the complete reads. Experimental results on platforms with AMD and Intel multicore processors report the remarkable parallel performance of HPG-Aligner, on short and long RNA reads, which excels in both execution time and sensitivity to an state-of-the-art aligner such as TopHat 2 built on top of Bowtie and Bowtie 2.
    04/2013;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Current machine translation (MT) systems are still not perfect. In practice, the output from these systems needs to be edited to correct errors. A way of increasing the productivity of the whole translation process (MT plus human work) is to incorporate the human correction activities within the translation process itself, thereby shifting the MT paradigm to that of computer-assisted translation. This model entails an iterative process in which the human translator activity is included in the loop: In each iteration, a prefix of the translation is validated (accepted or amended) by the human and the system computes its best (or n-best) translation suffix hypothesis to complete this prefix. A successful framework for MT is the so-called statistical (or pattern recognition) framework. Interestingly, within this framework, the adaptation of MT systems to the interactive scenario affects mainly the search process, allowing a great reuse of successful techniques and models. In this article, alignment templates, phrase-based models, and stochastic finite-state transducers are used to develop computer-assisted translation systems. These systems were assessed in a European project (TransType2) in two real tasks: The translation of printer manuals; manuals and the translation of the Bulletin of the European Union. In each task, the following three pairs of languages were involved (in both translation directions): English-Spanish, English-German, and English-French.
    Computational Linguistics. 01/2009; 35:3-28.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present several algorithms to compute the solution of a linear system of equations on a graphics processor (GPU), as well as general techniques to improve their performance, such as padding and hybrid GPU-CPU computation. We compare single and double precision performance of a modern GPU with unified architecture, and show how iterative refinement with mixed precision can be used to regain full accuracy in the solution of linear systems, exploiting the potential of the processor for single precision arithmetic. Experimental results on a GTX280 using CUBLAS 2.0, the implementation of BLAS for NVIDIA® GPUs with unified architecture, illustrate the performance of the different algorithms and techniques proposed. Copyright © 2009 John Wiley & Sons, Ltd.
    Concurrency and Computation Practice and Experience 01/2009; 21:2457-2477. · 0.85 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present our joint efforts to design and develop parallel implementations of the GNU Scientific Library for a wide variety of parallel platforms. The multilevel software architecture proposed provides several interfaces: asequential interface that hides the parallel nature of the library to sequential users, a parallel interface for parallel programmers, and a web services based interface to provide remote access to the routines of the library. The physical level of the architecture includes platforms ranging from distributed and shared-memory multiprocessors to hybrid systems and heterogeneous clusters. Several well-known operations arising in discrete mathematics and sparse linear algebra are used to illustrate the challenges, benefits, and performance of different parallelization approaches.
    The Journal of Supercomputing 01/2009; 48:88-114. · 0.92 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present several algorithms to compute the solution of a linear system of equations on a GPU, as well as general techniques to improve their performance, such as padding and hybrid GPU-CPU computation. We also show how iterative refinement with mixed-precision can be used to regain full accuracy in the solution of linear systems. Experimental results on a G80 using CUBLAS 1.0, the implementation of BLAS for NVIDIA® GPUs with unified architecture, illustrate the performance of the different algorithms and techniques proposed.
    08/2008: pages 739-748;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The increase in performance of the last generations of graphics processors (GPUs) has made this class of platform a coprocessing tool with remarkable success in certain types of operations. In this paper we evaluate the performance of the Level 3 operations in CUBLAS, the implementation of BIAS for NVIDIAreg GPUs with unified architecture. From this study, we gain insights on the quality of the kernels in the library and we propose several alternative implementations that are competitive with those in CUBLAS. Experimental results on a GeForce 8800 Ultra compare the performance of CUBLAS and the new variants.
    22nd IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2008, Miami, Florida USA, April 14-18, 2008; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The availability of large amounts of data is a fundamental prerequisite for building handwriting recognition systems. Any system needs a test set of labelled samples for measuring its performance along its development and guiding it. Moreover, there are systems that need additional samples for learning the recognition task they have to cope with later, i.e. a training set. Thus, the acquisition and distribution of standard databases has become an important issue in the handwriting recognition research community. Examples of widely used databases in the online domain are UNIPEN, IRONOFF, and Pendigits. This paper describes the current state of our own database, UJIpenchars, whose first version contains online representations of 1 364 isolated handwritten characters produced by 11 writers and is freely available at the UCI Machine Learning Repository. Moreover, we have recently concluded a second acquisition phase, totalling more than 11 000 samples from 60 writers to be made available in short as UJIpenchars2.
    Proceedings of the International Conference on Language Resources and Evaluation, LREC 2008, 26 May - 1 June 2008, Marrakech, Morocco; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the solution of large-scale generalized algebraic Bernoulli equations as those arising in control and systems theory. Here, we discuss algorithms based on a generalization of the Newton iteration for the matrix sign function. The algorithms are easy to parallelize and provide an efficient numerical tool to solve large-scale problems. Both the accuracy and the parallel performance of our implementations on a cluster of Intel Xeon processors are reported.
    Numerical Algorithms 01/2007; 46:351-368. · 1.13 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the parallel solution of large-scale discrete-time alge-braic Riccati equations, as those arising in control and systems theory, on a cluster of symmetric multiprocessors. The structure-preserving doubling algorithms considered in this paper are composed of matrix operations im-plemented in existing parallel dense linear algebra libraries. We suggest a parallel implementation that employs a new and efficient update strategy for the doubling iteration and a suitable stopping criterion. Numerical experiments on a cluster of multiprocessor nodes confirm the parallel per-formance and scalability of the doubling algorithms, which are comparable to those of other parallel DARE solvers based on the matrix sign and disk functions.
    09/2006;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We discuss and compare two approaches for model reduction of large-scale unstable systems on parallel computers. The first method proceeds by computing the additive decomposition of the transfer function via a block diagonalization, followed by a reduction of the stable part of the system using techniques based on state-space truncation. The second method employs a representation of the controllability and observability Gramians of an unstable systems in terms of the Gramians of the stabilized system where the particular stabilization is obtained via the solution of dual algebraic Bernoulli equations. Based on these Gramians, balanced truncation is then applied in the usual manner. All core computational steps in these methods can be efficiently solved on parallel computers by means of diverse variants of the Newton iteration for the sign function. Numerical experiments on a cluster of Intel Xeon processors show the numerical and parallel performances of these methods.
    Decision and Control, 2005 and 2005 European Control Conference. CDC-ECC '05. 44th IEEE Conference on; 01/2006
  • [Show abstract] [Hide abstract]
    ABSTRACT: We present our joint effort to develop a web based interface for the GNU Scientific library and its parallelization. The interface has been developed using standard web services technology to enable the use of non local resources to execute parallel programs. The final result is a computing service where sequential and parallel routines demanding high performace computing are supplied. The design allows to incorporate new servers and platforms with a small number of software requirements. We also introduce an open source development environment to allow developers to cooperate in the parallelization of the GNU Scientific library codes. These codes also will be available trough the web based interface to end users. Performance results are shown for some GSL codes in two cluster heterogeneous systems using the interface enabled with web services technology.
    Parallel and Distributed Processing and Applications, 4th International Symposium, ISPA 2006, Sorrento, Italy, December 4-6, 2006, Proceedings; 01/2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present our joint effort to develop a Web based interface for the GNU Scientific library and its parallelization. The interface has been developed using standard Web services technology to enable the use of non local resources to execute parallel programs. The final result is a computing service where sequential and parallel routines demanding high performance computing are supplied. The design allows to incorporate new servers and platforms with a small number of software requirements.
    14th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP 2006), 15-17 February 2006, Montbeliard-Sochaux, France; 01/2006
  • Source
    S. Barrachina, P. Benner, E.S. Quintana-Orti
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the numerical solution of algebraic Bernoulli equations via the Newton iteration for the matrix sign function. Bernoulli equations are nonlinear matrix equations arising in control and systems theory in the context of stabilization of linear systems, coprime factorization of rational matrix-valued functions, as well as model reduction. The algorithm proposed here is easily parallelizable and thus provides an efficient tool to solve large-scale problems. We report the parallel performance and scalability of our parallel implementations on an IBM Regatta system. Efficiencies around 80% and higher are obtained for using a reduced number of nodes.
    Parallel Processing, 2005. ICPP 2005 Workshops. International Conference Workshops on; 07/2005
  • [Show abstract] [Hide abstract]
    ABSTRACT: Computer-Assisted Translation (CAT) is an alternative approach to Machine Translation, that integrates human expertise into the automatic translation process. In this framework, a human translator interacts with a translation system that dynamically offers a list of translations that best completes the part of the sentence already translated. Stochastic finite-state transducer technology is proposed to support this CAT system. The system was assessed on two real tasks of different complexity in several languages.
    Finite-State Methods and Natural Language Processing, 5th International Workshop, FSMNLP 2005, Helsinki, Finland, September 1-2, 2005. Revised Papers; 01/2005
  • Source
    Parallel Computing: Current & Future Issues of High-End Computing, Proceedings of the International Conference ParCo 2005, 13-16 September 2005, Department of Computer Architecture, University of Malaga, Spain; 01/2005
  • Sergio Barrachina, Juan Miguel Vilar
    Proceedings of the 16th Eureopean Conference on Artificial Intelligence, ECAI'2004, including Prestigious Applicants of Intelligent Systems, PAIS 2004, Valencia, Spain, August 22-27, 2004; 01/2004
  • [Show abstract] [Hide abstract]
    ABSTRACT: It is a fact that current methodologies for automatic translation cannot be expected to produce high quality translations. An alternative approach is to use them as an aid to manual translation. We focus on a possible way to help human translators: to interactively provide completions for the parts of the sentences already translated. We explain how finite state transducers can be used for this task and show experiments in which the keystrokes needed to translate printer manuals were reduced to nearly 25% of the original.
    Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshops, SSPR 2004 and SPR 2004, Lisbon, Portugal, August 18-20, 2004 Proceedings; 01/2004
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we explore the parallelization of the scientific library from GNU both on shared-memory and distributed-memory architectures. A pair of classical operations, arising in sparse linear algebra and discrete mathematics, allow us to identify the major challenges involved in this task, and to analyze the performance, benefits, and drawbacks of two different possible parallelization approaches.
    Applied Parallel Computing, State of the Art in Scientific Computing, 7th International Workshop, PARA 2004, Lyngby, Denmark, June 20-23, 2004, Revised Selected Papers; 01/2004
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: State-of-the-art machine translation techniques are still far from producing high quality translations. This drawback leads us to introduce an alterna- tive approach to the translation problem that brings human expertise into the machine translation sce- nario. In this framework, namely Computer As- sisted Translation (CAT), human translators inter- act with a translation system, as an assistance tool, that dinamically offers, a list of translations that best completes the part of the sentence already trans- lated. In this paper, finite state transducers are presented as a candidate technology in the CAT paradigm. The appropriateness of this technique is evaluated on a printer manual corpus and re- sults from preliminary experiments confirm that hu- man translators would reduce to less than 25% the amount of work to be done for the same task.
    Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing , EMNLP 2004, A meeting of SIGDAT, a Special Interest Group of the ACL, held in conjunction with ACL 2004, 25-26 July 2004, Barcelona, Spain; 01/2004