TY  - JOUR
EP  - 1029
SN  - 11092750
N1  - cited By 4
SP  - 1020
TI  - Solving traveling salesman problem on cluster compute nodes
AV  - none
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-69349090796&partnerID=40&md5=d482566bc38cb46d9a7a27f251e0db92
JF  - WSEAS Transactions on Computers
A1  - Aziz, I.A.
A1  - Haron, N.
A1  - Mehat, M.
A1  - Jung, L.T.
A1  - Mustapa, A.N.
A1  - Akir, E.A.P.
VL  - 8
Y1  - 2009///
N2  - In this paper, we present a parallel implementation of a solution for the Traveling Salesman Problem (TSP). TSP is the problem of finding the shortest path from point A to point B, given a set of points and passing through each point exactly once. Initially a sequential algorithm is fabricated from scratch and written in C language. The sequential algorithm is then converted into a parallel algorithm by integrating it with the Message Passing Interface (MPI) libraries so that it can be executed on a cluster computer. Our main aim by creating the parallel algorithm is to accelerate the execution time of solving TSP. Experimental results conducted on Beowulf cluster are presented to demonstrate the viability of our work as well as the efficiency of the parallel algorithm.
IS  - 6
KW  - Beowulf Cluster; C language; Cluster computer; Execution time; High Performance Computing (HPC); Message Passing Interface (MPI); Message passing interface libraries; Parallel implementations; Sequential algorithm; Shortest path
KW  -  Cluster computing; Clustering algorithms; Interfaces (computer); Message passing; Parallel algorithms; Problem solving; Sequential switching
KW  -  Traveling salesman problem
ID  - scholars703
ER  -