Exploració per autor "Beltran Querol, Vicenç"

Ara es mostren els items 40-51 de 51

    • Saiph, a domain specific language for computational fluid dynamics simulations 

      Macià, Sandra; Beltran Querol, Vicenç; Mira Martínez, Daniel; Mateo, Sergi (Barcelona Supercomputing Center, 2017-05-04)
      Accés obert
      Nowadays, High-Performance Computing (HPC) is assuming an increasingly central role in scientific research while computer architectures are becoming more and more hetero-geneous and using different parallel programming ...

    • Saiph: towards a DSL for high-performance computational fluid dynamics 

      Macià, Sandra; Mateo, Sergi; Martínez-Ferrer, Pedro J.; Beltran Querol, Vicenç; Mira Martínez, Daniel; Ayguadé Parra, Eduard (Association for Computing Machinery (ACM), 2018)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      Nowadays high-performance computing is taking an increasingly central role in scientific research while computer architectures are becoming more heterogeneous and complex with different parallel programming models and ...

    • 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 ...

    • Seamless optimization of the GEMM kernel for task-based programming models 

      Lorenzon, Arthur F.; Marques, Sandro M. V. N.; Navarro Muñoz, Antoni; Beltran Querol, Vicenç (Association for Computing Machinery (ACM), 2022)
      Text en actes de congrés
      Accés obert
      The general matrix-matrix multiplication (GEMM) kernel is a fundamental building block of many scientific applications. Many libraries such as Intel MKL and BLIS provide highly optimized sequential and parallel versions ...

    • Simulating complex systems with a low-detail model 

      Nou Castell, Ramon; Guitart Fernández, Jordi; Beltran Querol, Vicenç; Carrera Pérez, David; Montero Mercadé, Lídia; Torres Viñals, Jordi; Ayguadé Parra, Eduard (2005-09)
      Text en actes de congrés
      Accés obert
      In this paper we show how modeling and simulating a complex system such as a web-server can help to evaluate di erent metrics and proposals to improve the performance without necessity of using a real system. Many times ...

    • Speeding up distributed MapReduce applications using hardware accelerators 

      Becerra Fontal, Yolanda; Beltran Querol, Vicenç; Carrera Pérez, David; González Tallada, Marc; Torres Viñals, Jordi; Ayguadé Parra, Eduard (2009-09)
      Text en actes de congrés
      Accés obert
      In an attempt to increase the performance/cost ratio, large compute clusters are becoming heterogeneous at multiple levels: from asymmetric processors, to different system architectures, operating systems and networks. ...

    • Supporting automatic recovery in offloaded distributed programming models through MPI-3 techniques 

      Peña, Antonio J.; Beltran Querol, Vicenç; Clauss, Carsten; Moschny, Thomas (ACM Digital Library, 2017-06-15)
      Comunicació de congrés
      Accés obert
      In this paper we describe the design of fault tolerance capabilities for general-purpose offload semantics, based on the OmpSs programming model. Using ParaStation MPI, a production MPI-3.1 implementation, we explore the ...

    • Task-based programming with OmpSs and its application 

      Fernandez, Alejandro; Beltran Querol, Vicenç; Martorell Bofill, Xavier; Badia,, R.M.; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (Springer, 2014)
      Text en actes de congrés
      Accés obert
      OmpSs is a task-based programming model that aims to provide portability and flexibility for sequential codes while the performance is achieved by the dynamic exploitation of the parallelism at task level. OmpSs targets ...

    • Task-parallel reductions in OpenMP and OmpSs 

      Ciesko, Jan; Mateo, Sergi; Teruel, Xavier; Beltran Querol, Vicenç; Martorell Bofill, Xavier; Badia,, R.M.; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (Springer, 2014)
      Text en actes de congrés
      Accés obert
      The wide adoption of parallel processing hardware in mainstream computing as well as the raising interest for efficient parallel programming in the developer community increase the demand for parallel programming model ...

    • 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 ...

    • Towards data-flow parallelization for adaptive mesh refinement applications 

      Sala Penadés, Kevin; Rico Carro, Alejandro; Beltran Querol, Vicenç (Institute of Electrical and Electronics Engineers (IEEE), 2020)
      Text en actes de congrés
      Accés obert
      Adaptive Mesh Refinement (AMR) is a prevalent method used by distributed-memory simulation applications to adapt the accuracy of their solutions depending on the turbulent conditions in each of their domain regions. These ...

    • Variable batched DGEMM 

      Valero-Lara, Pedro; Martinez-Perez, Ivan; Mateo, Sergio; Sirvent Pardell, Raül; Beltran Querol, Vicenç; Martorell Bofill, Xavier; Labarta Mancho, Jesús José (Institute of Electrical and Electronics Engineers (IEEE), 2018)
      Text en actes de congrés
      Accés obert
      Many scientific applications are in need to solve a high number of small-size independent problems. These individual problems do not provide enough parallelism and then, these must be computed as a batch. Today, vendors ...