A High-Performance Collective Communication Library on Parallell and Distributed Systems

碩士 === 國立清華大學 === 資訊科學學系 === 83 === Massively parallel and distributed memory machine can provide enormous computation power. However, the communication latency has limited the performance. This thesis describes an implementation...

Full description

Bibliographic Details
Main Authors: Chou, Chi-Nan, 周吉男
Other Authors: Jenq-Kuen Lee
Format: Others
Language:zh-TW
Published: 1995
Online Access:http://ndltd.ncl.edu.tw/handle/92192385639865667375
id ndltd-TW-083NTHU0394024
record_format oai_dc
spelling ndltd-TW-083NTHU03940242015-10-13T12:26:20Z http://ndltd.ncl.edu.tw/handle/92192385639865667375 A High-Performance Collective Communication Library on Parallell and Distributed Systems 一個平行及分散式系統上的高速集體通訊程式庫 Chou, Chi-Nan 周吉男 碩士 國立清華大學 資訊科學學系 83 Massively parallel and distributed memory machine can provide enormous computation power. However, the communication latency has limited the performance. This thesis describes an implementation of the high-performance communication library. The library is based on the theoretical rationale of C. Koelbel "Compiler-Time Generation of Regular Communication Patterns". This library is machine independent, and it can run on nCUBE/2, DEC Alpha farm workstations, and SUN workstations. It uses the nCUBE message passing library to passing the data in the nCUBE/2 machine, and it is based on the PVM environment in the workstations. This library supports the general users, FORTRAN compiler, and Parallel C++ compiler. It can reduce the complexity of compiler and enhance the performance. The current version has been incorporated into a Parallel C++ environment to support parallel I/O. There are some other functions in the library. They are the general functions like gather, scalar, shift, and the special functions like processor remapping, data moving in the arrays of the different dimensions, and out of the current configuration. Our collective communication work involving in processor remapping and out of current configuration issues an innovation in this area. It makes the system can work with an open environment where workstations are dynamically incorporated into the execution environment. Jenq-Kuen Lee 李政崑 1995 學位論文 ; thesis 67 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立清華大學 === 資訊科學學系 === 83 === Massively parallel and distributed memory machine can provide enormous computation power. However, the communication latency has limited the performance. This thesis describes an implementation of the high-performance communication library. The library is based on the theoretical rationale of C. Koelbel "Compiler-Time Generation of Regular Communication Patterns". This library is machine independent, and it can run on nCUBE/2, DEC Alpha farm workstations, and SUN workstations. It uses the nCUBE message passing library to passing the data in the nCUBE/2 machine, and it is based on the PVM environment in the workstations. This library supports the general users, FORTRAN compiler, and Parallel C++ compiler. It can reduce the complexity of compiler and enhance the performance. The current version has been incorporated into a Parallel C++ environment to support parallel I/O. There are some other functions in the library. They are the general functions like gather, scalar, shift, and the special functions like processor remapping, data moving in the arrays of the different dimensions, and out of the current configuration. Our collective communication work involving in processor remapping and out of current configuration issues an innovation in this area. It makes the system can work with an open environment where workstations are dynamically incorporated into the execution environment.
author2 Jenq-Kuen Lee
author_facet Jenq-Kuen Lee
Chou, Chi-Nan
周吉男
author Chou, Chi-Nan
周吉男
spellingShingle Chou, Chi-Nan
周吉男
A High-Performance Collective Communication Library on Parallell and Distributed Systems
author_sort Chou, Chi-Nan
title A High-Performance Collective Communication Library on Parallell and Distributed Systems
title_short A High-Performance Collective Communication Library on Parallell and Distributed Systems
title_full A High-Performance Collective Communication Library on Parallell and Distributed Systems
title_fullStr A High-Performance Collective Communication Library on Parallell and Distributed Systems
title_full_unstemmed A High-Performance Collective Communication Library on Parallell and Distributed Systems
title_sort high-performance collective communication library on parallell and distributed systems
publishDate 1995
url http://ndltd.ncl.edu.tw/handle/92192385639865667375
work_keys_str_mv AT chouchinan ahighperformancecollectivecommunicationlibraryonparallellanddistributedsystems
AT zhōujínán ahighperformancecollectivecommunicationlibraryonparallellanddistributedsystems
AT chouchinan yīgèpíngxíngjífēnsànshìxìtǒngshàngdegāosùjítǐtōngxùnchéngshìkù
AT zhōujínán yīgèpíngxíngjífēnsànshìxìtǒngshàngdegāosùjítǐtōngxùnchéngshìkù
AT chouchinan highperformancecollectivecommunicationlibraryonparallellanddistributedsystems
AT zhōujínán highperformancecollectivecommunicationlibraryonparallellanddistributedsystems
_version_ 1716858208056770560