论文信息 - First results of performance comparisons on many-core processors in solving QAP with ACO: kepler GPU versus xeon PHI

First results of performance comparisons on many-core processors in solving QAP with ACO: kepler GPU versus xeon PHI

This paper compares the performance of parallel computation on two types of many-core processors, Tesla K20c GPU and Xeon Phi 5110P, in solving the quadratic assignment problem (QAP) with ant colony optimization (ACO). The results show that the performance on Xeon Phi 5110P is not so promising compared to the Tesla K20c GPU on these problems. Further efficient implementation methods must be investigated for Xeon Phi.

[1] Pierre Collet,et al. Massively Parallel Evolutionary Computation on GPGPUs , 2013, Natural Computing Series.

[2] Shigeyoshi Tsutsui,et al. ACO with tabu search on a GPU for solving QAPs using move-cost adjusted thread assignment , 2011, GECCO '11.

[3] Franz Rendl,et al. QAPLIB – A Quadratic Assignment Problem Library , 1997, J. Glob. Optim..