Architecture driven partitioning

In this paper, we present a new algorithm to partition netlists for logic emulation under consideration of the targeted emulator architecture. The proposed algorithm allows the flexible use for a wide variety of applications because the description of the architecture is part of the input data. It combines a new approach of finding and improving an initial solution with existing algorithms to cluster the netlist and optimize the number of cut nets between blocks. As a result, the algorithm ensures that the cut nets between the created blocks can be connected within the emulation system, even without a full interconnect structure. Experiments on a number of designs and architectures demonstrate that the algorithm is competitive for architectures with full interconnect and that it is unique for architectures with limited interconnect resources