论文信息 - Cost minimization of partitioning circuits with complex resource constraints in FPGAs

Cost minimization of partitioning circuits with complex resource constraints in FPGAs

In this paper, we formulated a new cost minimization partition problem with complex resource constraints in large FPGAs and proposed a maximum matching and ILP based algorithm to solve it. The ILP solver, LINGO, is employed to find the number of the FPGA chips of each type to minimize the total cost. In order to get a smaller cut-size partition, we proposed a new vertex ordering matching algorithm to partition the given circuit. Experimental results on the MCNC LGSynth91 benchmark show that circuit partition with multiple resource types obtained by our algorithm has 21% lower cost on average than that using simple resource type FPGA. The proposed vertex ordering method reduces the cost by 19% compared with the method without vertex ordering considerations.

[1] Martin D. F. Wong,et al. Network-flow-based multiway partitioning with area and pin constraints , 1998, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[2] Krzysztof Kozminski,et al. Cost Minimization of Partitions into Multiple Devices , 1993, 30th ACM/IEEE Design Automation Conference.

[3] Martin D. F. Wong,et al. Circuit partitioning with complex resource constraints in FPGAs , 1998, FPGA '98.

[4] Andrew B. Kahng,et al. A General Framework For Vertex Orderings, With Applications To Netlist Clustering , 1994, IEEE/ACM International Conference on Computer-Aided Design.

[5] J. Cong,et al. Multiway partitioning with pairwise movement , 1998, ICCAD '98.

[6] Martin D. F. Wong,et al. Network flow based multi-way partitioning with area and pin constraints , 1997, ISPD '97.

[7] Baldomir Zajc,et al. Multi-way Netlist Partitioning into Heterogeneous FPGAs and Minimization of Total Device Cost and Interconnect , 1994, 31st Design Automation Conference.