Exploració per autor "Caballero, Diego"

Ara es mostren els items 1-3 de 3

    • An OpenMP* barrier using SIMD instructions for Intel® Xeon Phi™ coprocessor 

      Caballero, Diego; Duran González, Alejandro; Martorell Bofill, Xavier (Springer, 2013)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      Barrier synchronisation is a widely-studied topic since the supercomputer era due to its significant impact on the overall performance of parallel applications. With the current shift to many-core architectures, such as ...

    • Extending OpenMP* with vector constructs for modern multicore SIMD architectures 

      Klemm, Michael; Duran González, Alejandro; Tian, Xinmin; Saito, Hideki; Caballero, Diego; Martorell Bofill, Xavier (Springer, 2012)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      In order to obtain maximum performance, many applications require to extend parallelism from multi-threading to instruction-level (SIMD) parallelism that exists in many current (and future) multi-core architectures. While ...

    • How can we improve energy efficiency through user-directed vectorization and task-based parallelization? 

      Caminal, Helena; Caballero, Diego; Cebrián, Juan M.; Ferrer, Roger; Casas, Marc; Moretó Planas, Miquel; Martorell Bofill, Xavier; Valero Cortés, Mateo (Barcelona Supercomputing Center, 2015-05-05)
      Text en actes de congrés
      Accés obert
      Heterogeneity, parallelization and vectorization are key techniques to improve the performance and energy efficiency of modern computing systems. However, programming and maintaining code for these architectures poses a ...