Exploració per autor "Mateo Bellido, Sergi"

Ara es mostren els items 1-8 de 8

    • Auto-tuned OpenCL kernel co-execution in OmpSs for heterogeneous systems 

      Pérez, Borja; Stafford, Esteban; Bosque Orero, José Luis; Beivide Palacio, Ramon; Mateo Bellido, Sergi; Teruel García, Xavier; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (2019-03-01)
      Article
      Accés obert
      The emergence of heterogeneous systems has been very notable recently. The nodes of the most powerful computers integrate several compute accelerators, like GPUs. Profiting from such node configurations is not a trivial ...

    • Extending the OpenCHK Model with advanced checkpoint features 

      Maroñas Bravo, Marcos; Mateo Bellido, Sergi; Keller, Kai Rasmus; Bautista Gomez, Leonardo; Ayguadé Parra, Eduard; Beltran Querol, Vicenç (Elsevier, 2020-11)
      Article
      Accés obert
      One of the major challenges in using extreme scale systems efficiently is to mitigate the impact of faults. Application-level checkpoint/restart (CR) methods provide the best trade-off between productivity, robustness, and ...

    • Introducing the Task-Aware Storage I/O (TASIO) Library 

      Roca Nonell, Aleix; Beltran Querol, Vicenç; Mateo Bellido, Sergi (Springer, 2019-08-09)
      Capítol de llibre
      Accés obert
      Task-based programming models are excellent tools to parallelize and seamlessly load balance an application workload. However, the integration of I/O intensive applications and task-based programming models is lacking. ...

    • Leveraging OmpSs to exploit hardware accelerators 

      Sainz, Florentino; Mateo Bellido, Sergi; Beltran Querol, Vicenç; Bosque, José L.; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (Institute of Electrical and Electronics Engineers (IEEE), 2014)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      CUDA and OpenCL are the most widely used programming models to exploit hardware accelerators. Both programming models provide a C-based programming language to write accelerator kernels and a host API used to glue the host ...

    • Resolución del problema Minimum Rooted Arborescence mediante Ant Colony Optimization 

      Mateo Bellido, Sergi (Universitat Politècnica de Catalunya, 2012-01-25)
      Projecte/Treball Final de Carrera
      Accés obert
      En este projecto se aborda el problema de hallar la arborescencia de peso mínimo enraizada en un cierto vértice. Se presenta un algoritmo Híbrido (entre otros) de Ant Colony Optimization y Programación Dinámica que genera ...

    • Scaling irregular array-type reductions in OmpSs 

      Ciesko, Jan; Mateo Bellido, Sergi; Teruel, Xavier; Beltran Querol, Vicenç; Martorell Bofill, Xavier; Badia Sala, Rosa Maria; Labarta Mancho, Jesús José (Barcelona Supercomputing Center, 2015-05-05)
      Text en actes de congrés
      Accés obert
      Array-type reductions represent a frequently occurring algorithmic pattern in many scientific applications. A special case occurs if array elements are accessed in a non-linear, often random manner, which makes their ...

    • The cooperative parallel: A discussion about run-time schedulers for nested parallelism 

      Royuela, Sara; Serrano, Maria A.; García Gasulla, Marta; Mateo Bellido, Sergi; Labarta Mancho, Jesús José; Quiñones Moreno, Eduardo (Springer, 2019)
      Text en actes de congrés
      Accés obert
      Nested parallelism is a well-known parallelization strategy to exploit irregular parallelism in HPC applications. This strategy also fits in critical real-time embedded systems, composed of a set of concurrent functionalities. ...

    • The OmpSs reductions model and how to deal with scatter-updates 

      Ciesko, Jan; Mateo Bellido, Sergi; Teruel, Xavier; Beltran Querol, Vicenç; Martorell Bofill, Xavier; Badia Sala, Rosa Maria; Labarta Mancho, Jesús José (Barcelona Supercomputing Center, 2015-05-05)
      Text en actes de congrés
      Accés obert
      Scatter-updates represent a reoccurring algorithmic pattern in many scientific applications. Their scalable execution on modern systems is difficult due to performance limitations introduced by their irregular memory access ...