Výsledky vyhledávání - "Hill, David R. A."

Report

Reproducibility, Replicability, and Repeatability: A survey of reproducible research with a focus on high performance computing

Autor: Antunes, Benjamin A., Hill, David R. C.

Publikováno v: Computer Science Review, 2024, 53, pp.100655

Reproducibility is widely acknowledged as a fundamental principle in scientific research. Currently, the scientific community grapples with numerous challenges associated with reproducibility, often referred to as the ''reproducibility crisis.'' This

Externí odkaz: http://arxiv.org/abs/2402.07530

Zobrazit plný text záznamu

Report

Reproducibility, energy efficiency and performance of pseudorandom number generators in machine learning: a comparative study of python, numpy, tensorflow, and pytorch implementations

Autor: Antunes, Benjamin, Hill, David R. C

Pseudo-Random Number Generators (PRNGs) have become ubiquitous in machine learning technologies because they are interesting for numerous methods. The field of machine learning holds the potential for substantial advancements across various domains,

Externí odkaz: http://arxiv.org/abs/2401.17345

Zobrazit plný text záznamu

Report

Identifying Quality Mersenne Twister Streams For Parallel Stochastic Simulations

Autor: Antunes, Benjamin, Mazel, Claude, Hill, David R. C

The Mersenne Twister (MT) is a pseudo-random number generator (PRNG) widely used in High Performance Computing for parallel stochastic simulations. We aim to assess the quality of common parallelization techniques used to generate large streams of MT

Externí odkaz: http://arxiv.org/abs/2401.17115

Zobrazit plný text záznamu

Report

A Subset of the CERN Virtual Machine File System: Fast Delivering of Complex Software Stacks for Supercomputing Resources

Autor: Boyer, Alexandre F, Haen, Christophe, Stagni, Federico, Hill, David R C

Publikováno v: ISC High Performance 2022, May 2022, Hamburg, Germany. pp.354-371

Delivering a reproducible environment along with complex and up-to-date software stacks on thousands of distributed and heterogeneous worker nodes is a critical task. The CernVM-File System (CVMFS) has been designed to help various communities to dep

Externí odkaz: http://arxiv.org/abs/2303.16675

Zobrazit plný text záznamu