1 results listed
Fast developing GPU technology
increases the performance of search algorithms
used to solve NP-hard problems. Travelling
Salesman Problem (TSP) is a well-known NP-hard
problem. In this paper, we parallelize a popular
swarm algorithm, Artificial Bee Colony, to solve
TSP. Proposed algorithm is tested on small scale
benchmarks obtained by modifying Mandl’s Swiss
Road Network. Proposed implementation is tested
by three experiments performed on a host PC and
a GPU card. The results are compared against the
results generated by the serial implementatio n,
which is executed on the host PC. Test results for
the fully connected benchmark show that the
proposed parallel implementation has increased
the performance of the computation up to 150
times compared to the serial implementation.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Fouad Asil
Mustafa Gök