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 | Size | Format | |
---|---|---|---|---|
doi.org_10.32010_26166127.2019.2.2.122.140.pdf | 1.21 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.