Please use this identifier to cite or link to this item: http://dspace.azjhpc.org/xmlui/handle/123456789/36
Title: THE PARSEC MACHINE: A NON-NEWTONIAN SUPRA-LINEAR SUPERCOMPUTER
Authors: Abdulkarimova, Ulviya
Leonteva, Anna Ouskova
Rolando, Christian
Jeannin-Girardon, Anne
Collet, Pierre
Keywords: Beowulf cluster;relative space-time;supra-linear acceleration;qualitative acceleration;GPGPU;loosely coupled machines;artificial evolution;transfer learning;harmonic analysis;super-resolution;non-uniform sampling;Fourier transform
Issue Date: Dec-2019
Publisher: Azerbaijan Journal of High Performance Computing
Abstract: This paper describes how transfer-learning can turn a Beowulf cluster into a full super-computer with supra-linear qualitative acceleration. Harmonic Analysis is used as a real-world example to show the kind of result that can be achieved with the proposed supercomputer architecture, that locally exploits absolute space-time parallelism on each machine (SIMD parallelism) and loosely-coupled relative space-time parallelization between different machines (loosely coupled MIMD).
URI: http://localhost:8080/xmlui/handle/123456789/36
ISSN: 2616-6127
2617-4383
DOI: https://doi.org/10.32010/26166127.2019.2.2.122.140
Journal Title: Azerbaijan Journal of High Performance Computing
Volume: 2
Issue: 2
First page number: 122
Last page number: 140
Number of pages: 19
Appears in Collections:Azerbaijan Journal of High Performance Computing

Files in This Item:
File Description SizeFormat 
doi.org_10.32010_26166127.2019.2.2.122.140.pdf1.21 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.