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.