Performance Characterization of Multiprocessors and Accelerators Using Micro-Benchmarks
- In this paper, a set of micro-benchmarks is proposed to determine basic performance parameters of single-node mainstream hardware architectures for High Performance Computing. Performance parameters of recent processors, including those of accelerators, are determined. The investigated systems are Intel server processor architectures and the two accelerator lines Intel Xeon Phi and Nvidia graphic processors. Additionally, the performance impact of thread mapping on multiprocessors and Intel Xeon Phi is shown. The results show similarities for some parameters between all architectures, but significant differences for others.
Document Type: | Article |
---|---|
Language: | English |
Author: | Javed Razzaq, Rudolf Berrendorf, Jan Philipp Ecker, Simon Eric Scholl, Florian Manuss |
Parent Title (English): | SysMea (International Journal on Advances in Systems and Measurements) |
Volume: | 9 |
Issue: | 1&2 |
First Page: | 77 |
Last Page: | 90 |
ISSN: | 1942-261X |
URL: | https://www.thinkmind.org/index.php?view=article&articleid=sysmea_v9_n12_2016_8 |
Publisher: | ThinkMind |
Date of first publication: | 2016/06/30 |
Keyword: | Intel Xeon Phi; Nvidia graphic processors; Performance; micro-benchmarks; server processors; thread mapping |
Departments, institutes and facilities: | Fachbereich Informatik |
Dewey Decimal Classification (DDC): | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Entry in this database: | 2016/12/16 |