Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs
The study presents a comparison of computing systems based on IBM POWER8, IBM POWER9, and Intel Xeon Platinum 8160 processors running parallel applications. Memory subsystem bandwidth was studied, parallel programming technologies were compared, and the operating modes and capabilities of simultaneo...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-06-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/9/6/1035 |
_version_ | 1797564399223832576 |
---|---|
author | Aleksei Sorokin Sergey Malkovsky Georgiy Tsoy Alexander Zatsarinnyy Konstantin Volovich |
author_facet | Aleksei Sorokin Sergey Malkovsky Georgiy Tsoy Alexander Zatsarinnyy Konstantin Volovich |
author_sort | Aleksei Sorokin |
collection | DOAJ |
description | The study presents a comparison of computing systems based on IBM POWER8, IBM POWER9, and Intel Xeon Platinum 8160 processors running parallel applications. Memory subsystem bandwidth was studied, parallel programming technologies were compared, and the operating modes and capabilities of simultaneous multithreading technology were analyzed. Performance analysis for the studied computing systems running parallel applications based on the OpenMP and MPI technologies was carried out by using the NAS Parallel Benchmarks. An assessment of the results obtained during experimental calculations led to the conclusion that IBM POWER8 and Intel Xeon Platinum 8160 systems have almost the same maximum memory bandwidth, but require a different number of threads for efficient utilization. The IBM POWER9 system has the highest maximum bandwidth, which can be attributed to the large number of memory channels per socket. Based on the results of numerical experiments, recommendations are given on how the hardware of a similar grade can be utilized to solve various scientific problems, including recommendations on optimal processor architecture choice for leveraging the operation of high-performance hybrid computing platforms. |
first_indexed | 2024-03-10T18:56:48Z |
format | Article |
id | doaj.art-df29c7ccbd464d12a098e28bc165e562 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T18:56:48Z |
publishDate | 2020-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-df29c7ccbd464d12a098e28bc165e5622023-11-20T04:42:49ZengMDPI AGElectronics2079-92922020-06-0196103510.3390/electronics9061035Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUsAleksei Sorokin0Sergey Malkovsky1Georgiy Tsoy2Alexander Zatsarinnyy3Konstantin Volovich4Computing Center of the Far Eastern Branch of the Russian Academy of Sciences, 680000 Khabarovsk, RussiaComputing Center of the Far Eastern Branch of the Russian Academy of Sciences, 680000 Khabarovsk, RussiaComputing Center of the Far Eastern Branch of the Russian Academy of Sciences, 680000 Khabarovsk, RussiaFederal Research Center “Computer Science and Control” of the Russian Academy of Sciences, 119333 Moscow, RussiaFederal Research Center “Computer Science and Control” of the Russian Academy of Sciences, 119333 Moscow, RussiaThe study presents a comparison of computing systems based on IBM POWER8, IBM POWER9, and Intel Xeon Platinum 8160 processors running parallel applications. Memory subsystem bandwidth was studied, parallel programming technologies were compared, and the operating modes and capabilities of simultaneous multithreading technology were analyzed. Performance analysis for the studied computing systems running parallel applications based on the OpenMP and MPI technologies was carried out by using the NAS Parallel Benchmarks. An assessment of the results obtained during experimental calculations led to the conclusion that IBM POWER8 and Intel Xeon Platinum 8160 systems have almost the same maximum memory bandwidth, but require a different number of threads for efficient utilization. The IBM POWER9 system has the highest maximum bandwidth, which can be attributed to the large number of memory channels per socket. Based on the results of numerical experiments, recommendations are given on how the hardware of a similar grade can be utilized to solve various scientific problems, including recommendations on optimal processor architecture choice for leveraging the operation of high-performance hybrid computing platforms.https://www.mdpi.com/2079-9292/9/6/1035high-performance computingcomputer architectureheterogeneous computingsimultaneous multithreadingmemory bandwidthSTREAM |
spellingShingle | Aleksei Sorokin Sergey Malkovsky Georgiy Tsoy Alexander Zatsarinnyy Konstantin Volovich Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs Electronics high-performance computing computer architecture heterogeneous computing simultaneous multithreading memory bandwidth STREAM |
title | Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs |
title_full | Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs |
title_fullStr | Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs |
title_full_unstemmed | Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs |
title_short | Comparative Performance Evaluation of Modern Heterogeneous High-Performance Computing Systems CPUs |
title_sort | comparative performance evaluation of modern heterogeneous high performance computing systems cpus |
topic | high-performance computing computer architecture heterogeneous computing simultaneous multithreading memory bandwidth STREAM |
url | https://www.mdpi.com/2079-9292/9/6/1035 |
work_keys_str_mv | AT alekseisorokin comparativeperformanceevaluationofmodernheterogeneoushighperformancecomputingsystemscpus AT sergeymalkovsky comparativeperformanceevaluationofmodernheterogeneoushighperformancecomputingsystemscpus AT georgiytsoy comparativeperformanceevaluationofmodernheterogeneoushighperformancecomputingsystemscpus AT alexanderzatsarinnyy comparativeperformanceevaluationofmodernheterogeneoushighperformancecomputingsystemscpus AT konstantinvolovich comparativeperformanceevaluationofmodernheterogeneoushighperformancecomputingsystemscpus |