Exploració per autor "Bosch Pons, Jaume"Més informació

Ara es mostren els items 1-15 de 15

    • Adding tightly-integrated task scheduling acceleration to a RISC-V multi-core processor 

      Morais, Lucas; Silva, Vitor; Goldman, Alfredo; Álvarez Martínez, Carlos; Bosch Pons, Jaume; Frank, Michael; Araujo, Guido (Association for Computing Machinery (ACM), 2019)
      Text en actes de congrés
      Accés obert
      Task Parallelism is a parallel programming model that provides code annotation constructs to outline tasks and describe how their pointer parameters are accessed so that they might be executed in parallel, and asynchronously, ...

    • Asynchronous runtime for task-based dataflow programming models 

      Bosch Pons, Jaume (Universitat Politècnica de Catalunya, 2017-07)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   Barcelona Supercomputing Center
      The importance of parallel programming is increasing year after year since the power wall popularized multi-core processors, and with them, shared memory parallel programming models. In particular, task-based programming ...

    • Asynchronous runtime with distributed manager for task-based programming models 

      Bosch Pons, Jaume; Álvarez Martínez, Carlos; Jiménez González, Daniel; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (2020-09)
      Article
      Accés obert
      Parallel task-based programming models, like OpenMP, allow application developers to easily create a parallel version of their sequential codes. The standard OpenMP 4.0 introduced the possibility of describing a set of ...

    • Breaking host-centric management of task-based parallel programming models 

      Bosch Pons, Jaume (Universitat Politècnica de Catalunya, 2021-07-21)
      Tesi
      Accés obert
      Heterogeneous platforms had become popular to increase the computational power of the systems within a constrained power budget. They are present in several systems, from embedded platforms and mobile devices to high-end ...

    • Breaking master-slave model between host and FPGAs 

      Bosch Pons, Jaume; Vidal, Miquel; Filgueras Izquierdo, Antonio; Álvarez Martínez, Carlos; Jiménez González, Daniel; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (Association for Computing Machinery (ACM), 2020)
      Comunicació de congrés
      Accés obert
      This paper proposes to enhance current task-based programming models by breaking their current master-slave approach between the main processor and its hardware accelerators. As a proof-of-concept, it presents an extension ...

    • Design and implementation of an architecture-aware hardware runtime for heterogeneous systems 

      de Haro Ruiz, Juan Miguel; Bosch Pons, Jaume; Jiménez González, Daniel (Barcelona Supercomputing Center, 2020-05)
      Text en actes de congrés
      Accés obert
      Parallel computing has become the norm to gain performance in multicore and heterogeneous systems. Many programming models allow to exploit this parallelism with easy to use tools. In this work we focus on task-based ...

    • Exploiting parallelism on GPUs and FPGAs with OmpSs 

      Bosch Pons, Jaume; Filgueras Izquierdo, Antonio; Vidal, Miquel; Jiménez González, Daniel; Álvarez Martínez, Carlos; Martorell, Xavier (Association for Computing Machinery (ACM), 2017)
      Text en actes de congrés
      Accés obert
      This paper presents the OmpSs approach to deal with heterogeneous programming on GPU and FPGA accelerators. The OmpSs programming model is based on the Mercurium compiler and the Nanos++ runtime. Applications are annotated ...

    • High performance computing PP-distance algorithms to generate X-ray spectra from 3D models 

      González Griñán, César; Balocco, Simone; Bosch Pons, Jaume; Haro Ruiz, Juan Miguel de; Paolini, Maurizio; Filgueras Izquierdo, Antonio; Álvarez Martínez, Carlos; Pons, Ramon (Multidisciplinary Digital Publishing Institute (MDPI), 2022-09-27)
      Article
      Accés obert
      X-ray crystallography is a powerful method that has significantly contributed to our understanding of the biological function of proteins and other molecules. This method relies on the production of crystals that, however, ...

    • OmpSs@FPGA framework for high performance FPGA computing 

      Haro Ruiz, Juan Miguel de; Bosch Pons, Jaume; Filgueras Izquierdo, Antonio; Vidal, Miquel; Jiménez González, Daniel; Álvarez Martínez, Carlos; Martorell Bofill, Xavier; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (Institute of Electrical and Electronics Engineers (IEEE), 2021-12-01)
      Article
      Accés obert
      This paper presents the new features of the OmpSs@FPGA framework. OmpSs is a data-flow programming model that supports task nesting and dependencies to target asynchronous parallelism and heterogeneity. OmpSs@FPGA is the ...

    • Performance analysis of a hardware accelerator of dependence management for taskbased dataflow programming models 

      Tan, Xubin; Bosch Pons, Jaume; Jiménez González, Daniel; Álvarez Martínez, Carlos; Ayguadé Parra, Eduard; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2016)
      Text en actes de congrés
      Accés obert
      Along with the popularity of multicore and manycore, task-based dataflow programming models obtain great attention for being able to extract high parallelism from applications without exposing the complexity to programmers. ...

    • Reorganització del runtime Nanos++ 

      Bosch Pons, Jaume (Universitat Politècnica de Catalunya, 2015-06)
      Treball Final de Grau
      Accés obert
      Aquest projecte proposa una reorganització del sistema de gestió de les dependències entre tasques a Nanos++ (runtime del model de programació OmpSs) amb l'objectiu de reduir la contenció d'accés a aquestes estructures, ...

    • Supporting task creation inside FPGA devices 

      Bosch Pons, Jaume; Álvarez Martínez, Carlos; Jiménez González, Daniel (Barcelona Supercomputing Center, 2019-05-07)
      Text en actes de congrés
      Accés obert
      The most common model to use co-processors/accelerators is the master-slave model where the slaves (coprocessors/ accelerators) are driven by a general purpose cpu. This simplifies the management of the accelerators because ...

    • Task-based programming models for heterogeneous recurrent workloads 

      Bosch Pons, Jaume; Vidal, Miquel; Filgueras Izquierdo, Antonio; Jiménez González, Daniel; Álvarez Martínez, Carlos; Martorell Bofill, Xavier; Ayguadé Parra, Eduard (Springer Nature, 2021)
      Text en actes de congrés
      Accés obert
      This paper proposes the extension of task-based programming models with recurrent workloads concepts. The proposal introduces new clauses in the OmpSs task directive to efficiently model recurrent workloads. The clauses ...

    • TaskGenX: A Hardware-Software Proposal for Accelerating Task Parallelism 

      Chronaki, Kallia; Casas, Marc; Moretó Planas, Miquel; Bosch Pons, Jaume; Badia Sala, Rosa Maria (Springer, 2018-05-29)
      Comunicació de congrés
      Accés obert
      As chip multi-processors (CMPs) are becoming more and more complex, software solutions such as parallel programming models are attracting a lot of attention. Task-based parallel programming models offer an appealing approach ...

    • The AXIOM software layers 

      Álvarez, Carlos; Ayguadé Parra, Eduard; Bosch Pons, Jaume; Bueno Hedo, Javier; Cherkashin, Artem; Filgueras Izquierdo, Antonio; Jiménez González, Daniel; Martorell Bofill, Xavier; Navarro, Nacho; Vidal, Miquel; Theodoropoulos, Dimitris; Pnevmatikatos, Dionisis; Catani, Davide; Oro Garcia, David; Fernandez Prades, Carles; Segura, Carlos; Rodriguez Saeta, Javier; Hernando Pericás, Francisco Javier; Scordino, Claudio; Gai, Paolo; Passera, Pierluigi; Pomella, Alberto; Bettin, Nicola; Rizzo, Antonio; Giorgi, Roberto (2016-11-01)
      Article
      Accés obert
      AXIOM project aims at developing a heterogeneous computing board (SMP-FPGA).The Software Layers developed at the AXIOM project are explained.OmpSs provides an easy way to execute heterogeneous codes in multiple cores. ...