Now showing items 1-5 of 5

    • Characterization and modeling of atomic memory operations in arm based architectures 

      Soria Pardos, Víctor (Universitat Politècnica de Catalunya, 2022-01-26)
      Master thesis
      Restricted access - confidentiality agreement
      Covenantee:   Barcelona Supercomputing Center / Universidad de Zaragoza
      Efficient fine-grain synchronization is a classic computer architecture challenge that has been profusely addressed in the past. Load Link and Store Conditional (LL/SC) became one of the few solutions to this problem and ...
    • Characterization of HPC applications for ARM SIMD instructions 

      Soria Pardos, Víctor (Universitat Politècnica de Catalunya, 2019-07)
      Bachelor thesis
      Open Access
      Hoy en día, la mayoría de repertorios de instrucciones (ISA) incluyen instrucciones que procesan multiples datos en una única instruccion. Éstas instrucciones se utilizan para acelerar aplicaciones de alto rendimiento ...
    • Evaluation of genome alignment workflows on HPC processors 

      Langarita Benítez, Rubén (Universitat Politècnica de Catalunya, 2021-01-22)
      Master thesis
      Open Access
      Precision medicine holds promise for improving healthcare by leveraging genomic information. Due to the steep decrease in genome sequencing costs in recent years, the amount of data to be processed is increasing dramatically, ...
    • Novel techniques to improve the performance and the energy of vector architectures 

      Barredo Ferreira, Adrián (Universitat Politècnica de Catalunya, 2021-07-19)
      Doctoral thesis
      Open Access
      The rate of annual data generation grows exponentially. At the same time, there is a high demand to analyze that information quickly. In the past, every processor generation came with a substantial frequency increase, ...
    • Towards the simulation and emulation of large-scale hardware designs 

      López Paradís, Guillem (Universitat Politècnica de Catalunya, 2020-10-29)
      Master thesis
      Open Access
      The heritage of Moore's law has converged in a heterogeneous processor with a many-core and different application- or domain-specific accelerators. Having also finished the benefits of Dennard scaling, we have ended up in ...