Performance-driven circuit partitioning for prototyping by using multiple FPGA chips

A new performance-driven partitioning algorithm has been developed to implement a large circuit by using multiple FPGA chips. Partitioning for multiple FPGAs has several constraints to satisfy so that each partitioned subcircuit can be implemented in a FPGA chip. To obtain satisfactory results under the constraints, the partitioning is performed in two phases which are the initial partitioning for global optimisation and the iterative partitioning improvements for constraint satisfaction. Experimental results using the MCNC benchmark examples show that our partition method produces better results than those of other recent approaches on the average and that performance-driven partitioning is effective in reducing critical time delays.