2012/04/30 by Rafael Ponce, Miguel Cárdenas‐Montes, Ponce, Rafael +7 · 1 citation
Computer Science · Earth and Planetary Sciences · Physics and Astronomy · #Astronomy and Astrophysical Research #Computational Physics (physics.comp-ph) #Computational Physics and Python Applications #Cosmology and Gravitation Theories #Cosmology and Nongalactic Astrophysics (astro-ph.CO) #FOS: Physical sciences #Galaxies: Formation, Evolution, Phenomena #Geophysics and Gravity Measurements #Instrumentation and Methods for Astrophysics (astro-ph.IM) #Scientific Research and Discoveries
paper · pdf · doi:10.48550/arxiv.1204.6630
openalex publication_date 2012/04/30 · openalex created_date 2020/08/13 · openalex updated_date 2026/07/28
In this work, we have explored the advantages and drawbacks of using GPUs\ninstead of CPUs in the calculation of a standard 2-point correlation function\nalgorithm, which is useful for the analysis of Large Scale Structure of\ngalaxies. Taking into account the huge volume of data foreseen in upcoming\nsurveys, our main goal has been to accelerate significantly the analysis codes.\nWe find that GPUs offer a 100-fold increase in speed with respect to a single\nCPU without a significant deviation in the results. For comparison's sake, an\nMPI version was developed as well. Some issues, like code implementation, which\narise from using this option are discussed.\n