Ara es mostren els items 127-146 de 326

    • Feature discriminativity estimation in CNNs for transfer learning 

      Giménez Ábalos, Víctor; Vilalta Arias, Armand; Garcia Gasulla, Dario; Labarta Mancho, Jesús José; Ayguadé Parra, Eduard (IOS Press, 2019)
      Text en actes de congrés
      Accés obert
      The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. However, raw feature extraction from all ...
    • Fine-grain parallel megabase sequence comparison with multiple heterogeneous GPUs 

      De Sandes, Edans; Miranda Álamo, Guillermo; Melo, Alba; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (Association for Computing Machinery (ACM), 2014)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper proposes and evaluates a parallel strategy to execute the exact Smith-Waterman (SW) algorithm for megabase DNA sequences in heterogeneous multi-GPU platforms. In our strategy, the computation of a single huge ...
    • Fine-grain parallel megabase sequence comparison with multiple heterogeneous GPUs 

      De Sandes, Edans; Miranda Álamo, Guillermo; De Melo, Alba Cristina Magalhaes Alves; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (2014-08-01)
      Article
      Accés restringit per política de l'editorial
      This paper proposes and evaluates a parallel strategy to execute the exact Smith-Waterman (SW) algorithm for megabase DNA sequences in heterogeneous multi-GPU platforms. In our strategy, the computation of a single huge ...
    • Fluid communities: a competitive, scalable and diverse community detection algorithm 

      Parés Sabatés, Ferran; García Gasulla, Darío; Vilalta Arias, Armand; Moreno, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Springer, 2017)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      We introduce a community detection algorithm (Fluid Communities) based on the idea of fluids interacting in an environment, expanding and contracting as a result of that interaction. Fluid Communities is based on the ...
    • Formalization of block pruning: reducing the number of cells computed in exact biological sequence comparison algorithms 

      De Sandes, Edans; Teodoro, George; Walter, Maria Emilia; Martorell Bofill, Xavier; Ayguadé Parra, Eduard; Melo, Alba (Wiley Heyden, 2018-05-01)
      Article
      Accés obert
      Biological sequence comparison algorithms that compute the optimal local and global alignments calculate a dynamic programming (DP) matrix with quadratic time complexity. The DP matrix H is calculated with a recurrence ...
    • Full-network embedding in a multimodal embedding pipeline 

      Vilalta Arias, Armand; Garcia Gasulla, Dario; Parés Pont, Ferran; Moreno Vázquez, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Association for Computational Linguistics, 2017)
      Comunicació de congrés
      Accés obert
      The current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representation into a shared embedding space. In this ...
    • Gaining asynchronity by using Hybrid UPC/SMPSS 

      Farreras Esclusa, Montserrat; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (2009)
      Text en actes de congrés
      Accés obert
      Partitioned Global Address Space (PGAS) languages provide a unique programming model that can span shared-memory multiprocessor (SMP) architectures, distributed memory machines, or cluster of SMPs. Users can program large ...
    • General purpose task-dependence management hardware for task-based dataflow programming models 

      Tan, Xubin; Bosch, Jaume; Vidal, Miquel; Alvarez, Carlos; Jimenez-Gonzalez, Daniel; Ayguadé Parra, Eduard; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2017)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      Task-based programming models such as OpenMP, IntelTBB and OmpSs offer the possibility of expressing dependences among tasks to drive their execution at runtime. Managing these dependences introduces noticeable overheads ...
    • Generating a periodic pattern for VLIW 

      Barrado Muxí, Cristina; Labarta Mancho, Jesús José; Ayguadé Parra, Eduard; Valero Cortés, Mateo (Universidad de Málaga, 1995)
      Text en actes de congrés
      Accés obert
      Fine-grain parallelism available in VLIW and superscalar processors can be mainly exploited in computational intensive loops. Aggressive scheduling techniques are required to fully exploit this parallelism. In this paper ...
    • GOPHER, an HPC framework for large scale graph exploration and inference 

      Josep Fabregó, Marc; Teruel García, Xavier; Giménez Ábalos, Víctor; Cirilo, Davide; Garcia Gasulla, Dario; Álvarez Napagao, Sergio; Garcia Gasulla, Marta; Ayguadé Parra, Eduard; Valencia, Alfonso (Springer, 2020)
      Text en actes de congrés
      Accés obert
      Biological ontologies, such as the Human Phenotype Ontology (HPO) and the Gene Ontology (GO), are extensively used in biomedical research to investigate the complex relationship that exists between the phenome and the ...
    • Graph partitioning applied to DAG scheduling to reduce NUMA effects 

      Sánchez Barrera, Isaac; Casas, Marc; Moretó Planas, Miquel; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Valero Cortés, Mateo (Association for Computing Machinery (ACM), 2018)
      Comunicació de congrés
      Accés obert
      The complexity of shared memory systems is becoming more relevant as the number of memory domains increases, with different access latencies and bandwidth rates depending on the proximity between the cores and the devices ...
    • Guest editors introduction: special issue on OpenMP 

      Gao, G R; Sato, M; Ayguadé Parra, Eduard (2008-06)
      Article
      Accés restringit per política de l'editorial
      The article discusses various reports published within the issue, including one on OpenMP software and another on supporting OpenMP on cell.
    • Hardware-software coherence protocol for the coexistence of caches and local memories 

      Álvarez Martí, Lluc; Vilanova, Lluís; González Tallada, Marc; Martorell Bofill, Xavier; Navarro, Nacho; Ayguadé Parra, Eduard (2015-01-01)
      Article
      Accés obert
      Cache coherence protocols limit the scalability of multicore and manycore architectures and are responsible for an important amount of the power consumed in the chip. A good way to alleviate these problems is to introduce ...
    • Heuristics for register-constrained software pipelining 

      Llosa Espuny, José Francisco; Valero Cortés, Mateo; Ayguadé Parra, Eduard (Institute of Electrical and Electronics Engineers (IEEE), 1996)
      Text en actes de congrés
      Accés obert
      Software Pipelining is a loop scheduling technique that extracts parallelism from loops by overlapping the execution of several consecutive iterations. There has been a significant effort to produce throughput-optimal ...
    • Hierarchical clustered register file organization for VLIW processors 

      Zalamea León, Francisco Javier; Llosa Espuny, José Francisco; Ayguadé Parra, Eduard; Valero Cortés, Mateo (IEEE Computer Society, 2003)
      Text en actes de congrés
      Accés obert
      Technology projections indicate that wire delays will become one of the biggest constraints in future microprocessor designs. To avoid long wire delays and therefore long cycle times, processor cores must be partitioned ...
    • Hierarchical task-based programming with StarSs 

      Planas Carbonell, Judit; Badia Sala, Rosa Maria; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (2009-08)
      Article
      Accés restringit per política de l'editorial
      Programming models for multicore and many-core systems are listed as one of the main challenges in the near future for computing research. These programming models should be able to exploit the underlying platform, but ...
    • How data volume affects spark based data analytics on a scale-up server 

      Awan, Ahsan; Brorsson, Mats; Vlassov, Vladimir; Ayguadé Parra, Eduard (Springer, 2015)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      Sheer increase in volume of data over the last decade has triggered research in cluster computing frameworks that enable web enterprises to extract big insights from big data. While Apache Spark is gaining popularity for ...
    • HPC benchmarking: scaling right and looking beyond the average 

      Radulović, Milan; Asifuzzaman, Kazi; Carpenter, Paul Matthew; Radojković, Petar; Ayguadé Parra, Eduard (Springer, 2018)
      Text en actes de congrés
      Accés obert
      Designing a balanced HPC system requires an understanding of the dominant performance bottlenecks. There is as yet no well established methodology for a unified evaluation of HPC systems and workloads that quantifies the ...
    • Hybrid access-specific software cache techniques for the cell BE architecture 

      O’Brien, Kathryn; O'Brien, Kevin; González Tallada, Marc; Vujic, Nikola; Martorell Bofill, Xavier; Ayguadé Parra, Eduard; Eichenberger, Alexandre E.; Chen, Tong; Sura, Zehra; Zhang, Tao (Association for Computing Machinery, 2008)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      Ease of programming is one of the main impediments for the broad acceptance of multi-core systems with no hardware support for transparent data transfer between local and global memories. Software cache is a robust approach ...
    • Hypernode reduction modulo scheduling 

      Llosa Espuny, José Francisco; Valero Cortés, Mateo; Ayguadé Parra, Eduard; González Colás, Antonio María (Institute of Electrical and Electronics Engineers (IEEE), 1995)
      Text en actes de congrés
      Accés obert
      Software pipelining is a loop scheduling technique that extracts parallelism from loops by overlapping the execution of several consecutive iterations. Most prior scheduling research has focused on achieving minimum execution ...