Ara es mostren els items 1-20 de 24

  • Characterizing the resource-sharing levels of the UltraSparc T2 processor 

    Cakarevic, Vladimir; Radojkovic, Petar; Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro; Cazorla Almeida, Francisco Javier; Nemirovsky, Mario; Valero Cortés, Mateo (Association for Computing Machinery (ACM), 2009)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Thread level parallelism (TLP) has become a popular trend to improve processor performance, overcoming the limitations of extracting instruction level parallelism. Each TLP paradigm, such as Simultaneous Multithreading or ...
  • Code semantic-aware runahead threads 

    Ramírez García, Tanausu; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Valero Cortés, Mateo (2009-09)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Memory-intensive threads can hoard shared re- sources without making progress on a multithreading processor (SMT), thereby hindering the overall system performance. A recent promising solution to overcome this important ...
  • Control-flow independence reuse via dynamic vectorization 

    Pajuelo González, Manuel Alejandro; González Colás, Antonio María; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2005)
    Text en actes de congrés
    Accés obert
    Current processors exploit out-of-order execution and branch prediction to improve instruction level parallelism. When a branch prediction is wrong, processors flush the pipeline and squash all the speculative work. However, ...
  • Dynamic web worker pool management for highly parallel javascript web applications 

    Verdú Mulà, Javier; Costa Prats, Juan José; Pajuelo González, Manuel Alejandro (2016-09-10)
    Article
    Accés obert
    JavaScript web applications are improving performance mainly thanks to the inclusion of new standards by HTML5. Among others, web workers API allows multithreaded JavaScript web apps to exploit parallel processors. However, ...
  • FAME: FAirly MEasuring multithreaded architectures 

    Vera, Javier; Cazorla, Francisco; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Fernandez Garcia, Enrique; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2007)
    Text en actes de congrés
    Accés obert
    Nowadays, multithreaded architectures are becoming more and more popular. In order to evaluate their behavior, several methodologies and metrics have been proposed. A methodology defines when the measurements of a given ...
  • Introducing runahead threads 

    Ramírez García, Tanausu; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Valero Cortés, Mateo (2007-07)
    Report de recerca
    Accés obert
    Simultaneous Multithreading processors share their resources among multiple threads in order to improve performance. However, a resource control policy is needed to avoid resource conflicts and prevent some threads from ...
  • Mapa conceptual global como herramienta para la visión de conjunto de un sistema operativo 

    Verdú Mulà, Javier; López Álvarez, David; Pajuelo González, Manuel Alejandro (2009-06-15T12:03:04Z)
    Text en actes de congrés
    Accés obert
    Numerosas asignaturas están formadas por un temario que está totalmente interrelacionado. Al final del curso los estudiantes deberían haber adquirido los conocimientos de cada tema pero, más importante aún, deberían saber ...
  • Measuring operating system overhead on CMT processors 

    Radojkovic, Petar; Cakarevic, Vladimir; Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro; Gioiosa, Roberto; Cazorla Almeida, Francisco Javier; Nemirovsky, Mario; Valero Cortés, Mateo (IEEE Computer Society Publications, 2008)
    Text en actes de congrés
    Accés obert
    Numerous studies have shown that Operating System (OS) noise is one of the reasons for significant performance degradation in clustered architectures. Although many studies examine the OS noise for High Performance Computing ...
  • Measuring operating system overhead on Sun UltraSparc T1 processor 

    Radojkovic, Petar; Cakarevic, Vladimir; Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro; Gioiosa, Roberto; Cazorla Almeida, Francisco Javier; Nemirovsky, Mario; Valero Cortés, Mateo (2009-06)
    Text en actes de congrés
    Accés obert
    Numerous studies have shown that Operating System (OS) noise is one of the reasons for significant performance degradation in clustered architectures. Although many studies examine the OS noise for High Performance Computing, ...
  • On the problem of evaluating the performance of multiprogrammed workloads 

    Cazorla, Francisco; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Fernández Rodríguez, José Enrique; Valero Cortés, Mateo (2010-12)
    Article
    Accés obert
    Multithreaded architectures are becoming more and more popular. In order to evaluate their behavior, several methodologies and metrics have been proposed. A methodology defines when the measurements for a given workload ...
  • Overhead of the spin-lock loop in UltraSPARC T2 

    Cakarevic, Vladimir; Radojkovic, Petar; Cazorla Almeida, Francisco Javier; Gioiosa, Roberto; Nemirovsky, Mario; Valero Cortés, Mateo; Pajuelo González, Manuel Alejandro; Verdú Mulà, Javier (2008-06-04)
    Text en actes de congrés
    Accés obert
    Spin locks are task synchronization mechanism used to provide mutual exclusion to shared software resources. Spin locks have a good performance in several situations over other synchronization mechanisms, i.e., when on ...
  • Performance scalability analysis of JavaScript applications with web workers 

    Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro (2016-12)
    Article
    Accés obert
    Web applications are getting closer to the performance of native applications taking advantage of new standard–based technologies. The recent HTML5 standard includes, among others, the Web Workers API that allows ...
  • ROB-free architecture proposal 

    González, Isidro; Galluzzi, Marco; Cristal Kestelman, Adrián; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Valero Cortés, Mateo (2007-09)
    Report de recerca
    Accés obert
    Modern processors improve performance by taking advantage of the instruction level parallelism (ILP) by means of allowing hundreds of instructions in flight. However, they still have to face an important source of degradation ...
  • Runahead threads: reducing resource contention in SMT processors 

    Ramírez García, Tanausu; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2007)
    Comunicació de congrés
    Accés obert
    In this work, we propose Runahead threads as a valuable solution for both exploiting memory-level parallelism and reducing resource contention in simultaneous multithreaded processors.
  • Runahead threads to improve SMT performance 

    Ramirez Garcia, Tanausú; Pajuelo González, Manuel Alejandro; Santana Jaria, Oliverio J.; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2008)
    Text en actes de congrés
    Accés obert
    In this paper, we propose Runahead Threads (RaT) as a valuable solution for both reducing resource contention and exploiting memory-level parallelism in Simultaneous Multithreaded (SMT) processors. Our technique converts ...
  • Speculative dynamic vectorization 

    Pajuelo González, Manuel Alejandro; González Colás, Antonio María; Valero Cortés, Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2002)
    Text en actes de congrés
    Accés obert
    Traditional vector architectures have shown to be very effective for regular codes where the compiler can detect data-level parallelism. However, this SIMD parallelism is also present in irregular or pointer-rich codes, ...
  • Speculative Vectorization for Superscalar Processors 

    Pajuelo González, Manuel Alejandro (Universitat Politècnica de Catalunya, 2005-11-24)
    Tesi
    Accés obert
    Traditional vector architectures have been shown to be very effective in executing regular codes in which the compiler can detect data-level parallelism, i.e. repeating the same computation over different elements in the ...
  • The problem of evaluating CPU-GPU systems with 3d visualization applications 

    Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro; Valero Cortés, Mateo (2012-12)
    Article
    Accés restringit per política de l'editorial
    Complex, computationally demanding 3D visualization applications can be used as benchmarks to evaluate CPU-GPU systems. However, because those applications are time dependent, their execution is not deterministic. Thus, ...
  • Thread assignment in multicore/multithreaded processors: A statistical approach 

    Radojkovic, Petar; Carpenter, Paul M.; Moreto Planas, Miquel; Cakarevic, Vladimir; Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro; Cazorla Almeida, Francisco Javier; Nemirovsky, Mario; Valero Cortés, Mateo (2016-01-01)
    Article
    Accés obert
    The introduction of multicore/multithreaded processors, comprised of a large number of hardware contexts (virtual CPUs) that share resources at multiple levels, has made process scheduling, in particular assignment of ...
  • Thread assignment of multithreaded network applications in multicore/multithreaded processors 

    Radojkovic, Petar; Cakarevic, Vladimir; Verdú Mulà, Javier; Pajuelo González, Manuel Alejandro; Cazorla Almeida, Francisco Javier; Nemirovsky, Mario; Valero Cortés, Mateo (2013-12)
    Article
    Accés obert
    The introduction of multithreaded processors comprised of a large number of cores with many shared resources makes thread scheduling, and in particular optimal assignment of running threads to processor hardware contexts ...