An adaptive neighborhood taboo search on GPU for Hardware/Software Co-design
Neng Hou, Fazhi He, Yilin Chen, Yi Zhou · 2016
Hardware/software partitioning is an essential step in Hardware/Software Co-design. This paper presents a GPU-accelerated adaptive neighborhood taboo search algorithm(GPU-accelerated ANTS) to solve the problem. Firstly, a pre-GPU version of ANTS is presented to test our idea, in which both the number of feasible candidates in neighborhood and the length of taboo list can be adaptively adjusted. Secondly, a GPU-accelerated version combined with the two merits from pre-GPU version is presented. Furthermore, in order to fully leverage the power of GPU, the special consideration for the optimization strategies and implementation details on GPU are explored for our GPU- accelerated ANTS algorithm. Finally, enough number of experiments show that our GPU-accelerated ANTS method outperforms state-of-the-art work of taboo search for the HW/SW partitioning in both quality and speed under mid/low range GPU platform.