東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Profiling and optimizing K-means alg...

Thibodeau, Eric.

FindBook

Google Book

Amazon

博客來

Profiling and optimizing K-means algorithms in a Beowulf cluster environment.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Profiling and optimizing K-means algorithms in a Beowulf cluster environment./
作者:	Thibodeau, Eric.
面頁冊數:	169 p.
附註:	Source: Masters Abstracts International, Volume: 48-04, page: 2328.
Contained By:	Masters Abstracts International48-04.
標題:	Engineering, System Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR57317
ISBN:	9780494573174

Profiling and optimizing K-means algorithms in a Beowulf cluster environment.
Thibodeau, Eric.

Profiling and optimizing K-means algorithms in a Beowulf cluster environment. - 169 p.

Source: Masters Abstracts International, Volume: 48-04, page: 2328.

Thesis (M.Eng.)--Ecole de Technologie Superieure (Canada), 2009.

The K-means algorithm is a well known statistical agglomeration algorithm used to sort a database of unlabeled items into K groups. As pan of the fitness function of an Evolutionary Algorithm (EA), the optimization of the K-means algorithm has become a point of great interest. Although many approaches have been proposed for its parallelization and optimization, very few address the question of scalability and efficiency. In most cases, the description of the execution environment remains opaque and precise profiles of the program are mostly absent. Performance and efficiency issues are quickly relegated to communication issues.

ISBN: 9780494573174Subjects--Topical Terms:

1018128
Engineering, System Science.

Profiling and optimizing K-means algorithms in a Beowulf cluster environment.
LDR:02946nam 2200289 4500 001 1401679
005 20111017084427.5
008 130515s2009 ||||||||||||||||| ||eng d
020 $a 9780494573174
035 $a (UMI)AAIMR57317
035 $a AAIMR57317
040 $a UMI $c UMI
100 1 $a Thibodeau, Eric. $3 1680828
245 1 0 $a Profiling and optimizing K-means algorithms in a Beowulf cluster environment.
300 $a 169 p.
500 $a Source: Masters Abstracts International, Volume: 48-04, page: 2328.
502 $a Thesis (M.Eng.)--Ecole de Technologie Superieure (Canada), 2009.
520 $a The K-means algorithm is a well known statistical agglomeration algorithm used to sort a database of unlabeled items into K groups. As pan of the fitness function of an Evolutionary Algorithm (EA), the optimization of the K-means algorithm has become a point of great interest. Although many approaches have been proposed for its parallelization and optimization, very few address the question of scalability and efficiency. In most cases, the description of the execution environment remains opaque and precise profiles of the program are mostly absent. Performance and efficiency issues are quickly relegated to communication issues.
520 $a We address these deficiencies by presenting a detailed description of two parallel environments, the Beowulf style clusters and the Symmetric Multi-Processors (SMP) parallel machines. A mixture of theoretical and empirical models were used to characterize these environments and set baseline expectations pertaining to the K-means algorithm. Due to the necessity of a multidisciplinary expertise, a detailed use of Tuning and Analysis Utilities (TAU) is provided to ease the parallel performance profiling task. Coupled with the high precision counter interface provided by Performance Application Programming Interface (PAPI), we present a grey box method by which a parallel master-slave implementation of the K-means is evolved into a highly efficient island version of itself. Communications and computational optimization were guided by prior theoretical and empirical models of the parallel execution environment.
520 $a Our work has revealed that there is much more to parallel processing than the simple balance between computation and communications. We have brought forth the negative impact of using mathematical libraries for specific problems and identified performance issues specific to some versions of the same series of Message Passing Inerface (MPI) libraries. High precision profiling has shown that data representation and processing can be a more significant source of scalability bottleneck than computation and communications put together.
590 $a School code: 1246.
650 4 $a Engineering, System Science. $3 1018128
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
690 $a 0790
690 $a 0800
690 $a 0984
710 2 $a Ecole de Technologie Superieure (Canada). $3 1057894
773 0 $t Masters Abstracts International $g 48-04.
790 $a 1246
791 $a M.Eng.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR57317