Cover Image

Performance pattern of unified parallel C on multi-core clusters

The Partitioned Global Address Space (PGAS) model has been widely used in multi-core clusters as an alternative to MPI. Among the widespread use is Unified Parallel C (UPC). Previous research has shown that UPC performance is comparable with MPI, however in certain cases UPC require hand-tuning tech...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdul Hamid, Nor Asilah Wati, Serres, Olivier, Anbar, Ahmad, Hassan, Sazlinah
Format: Conference or Workshop Item
Published: IEEE (IEEE Xplore) 2013
Online Access:http://psasir.upm.edu.my/id/eprint/41309/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.41309
record_format eprints
spelling my.upm.eprints.413092015-11-03T04:00:30Z http://psasir.upm.edu.my/id/eprint/41309/ Performance pattern of unified parallel C on multi-core clusters Abdul Hamid, Nor Asilah Wati Serres, Olivier Anbar, Ahmad Hassan, Sazlinah The Partitioned Global Address Space (PGAS) model has been widely used in multi-core clusters as an alternative to MPI. Among the widespread use is Unified Parallel C (UPC). Previous research has shown that UPC performance is comparable with MPI, however in certain cases UPC require hand-tuning techniques such as prefetching and privatized pointers-to-shared to improve the performance. In this paper we reviews, evaluate and analyze the performance pattern between UPC Naïve, UPC optimize and MPI on two different multi-core clusters architecture. We focus our study using matrix multiplication as the benchmark and perform our experimental on two distributed memory machine, Cray XE6 with Gemini interconnects and Sun Cluster with Infiniband interconnects. We provide analysis on each core execution time to understand the pattern of communication for both machines. We also demonstrate the gaps between naïve and optimized are depends on the compiler with its associate distributed memory machine. We also observed unnecessary optimization for certain programs related to HPC architecture and compiler. IEEE (IEEE Xplore) 2013 Conference or Workshop Item NonPeerReviewed Abdul Hamid, Nor Asilah Wati and Serres, Olivier and Anbar, Ahmad and Hassan, Sazlinah (2013) Performance pattern of unified parallel C on multi-core clusters. In: 2013 IEEE International Conference on High Performance Computing and Communications & 2013 IEEE International Conference on Embedded and Ubiquitous Computing, 13-15 Nov. 2013, Zhangzijie, China. (pp. 1751-1757). 10.1109/HPCC.and.EUC.2013.250
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
description The Partitioned Global Address Space (PGAS) model has been widely used in multi-core clusters as an alternative to MPI. Among the widespread use is Unified Parallel C (UPC). Previous research has shown that UPC performance is comparable with MPI, however in certain cases UPC require hand-tuning techniques such as prefetching and privatized pointers-to-shared to improve the performance. In this paper we reviews, evaluate and analyze the performance pattern between UPC Naïve, UPC optimize and MPI on two different multi-core clusters architecture. We focus our study using matrix multiplication as the benchmark and perform our experimental on two distributed memory machine, Cray XE6 with Gemini interconnects and Sun Cluster with Infiniband interconnects. We provide analysis on each core execution time to understand the pattern of communication for both machines. We also demonstrate the gaps between naïve and optimized are depends on the compiler with its associate distributed memory machine. We also observed unnecessary optimization for certain programs related to HPC architecture and compiler.
format Conference or Workshop Item
author Abdul Hamid, Nor Asilah Wati
Serres, Olivier
Anbar, Ahmad
Hassan, Sazlinah
spellingShingle Abdul Hamid, Nor Asilah Wati
Serres, Olivier
Anbar, Ahmad
Hassan, Sazlinah
Performance pattern of unified parallel C on multi-core clusters
author_facet Abdul Hamid, Nor Asilah Wati
Serres, Olivier
Anbar, Ahmad
Hassan, Sazlinah
author_sort Abdul Hamid, Nor Asilah Wati
title Performance pattern of unified parallel C on multi-core clusters
title_short Performance pattern of unified parallel C on multi-core clusters
title_full Performance pattern of unified parallel C on multi-core clusters
title_fullStr Performance pattern of unified parallel C on multi-core clusters
title_full_unstemmed Performance pattern of unified parallel C on multi-core clusters
title_sort performance pattern of unified parallel c on multi-core clusters
publisher IEEE (IEEE Xplore)
publishDate 2013
url http://psasir.upm.edu.my/id/eprint/41309/
_version_ 1643832960666828800
score 13.211869

Similar Items