A performance-oriented circuit partitioning algorithm with logic-block replication for multi-FPGA systems

Abstract

This paper proposes a circuit partitioning algorithm in which the delay of each critical signal path is within a specified upper bound. Its core is recursive bipartitioning of a circuit which consists of three stages: (0) detection of critical paths; (1) bipartitioning of a set of primary inputs and outputs; and (2) bipartitioning of a set of logic-blocks. In (0), the algorithm detects the critical paths based on their lower bounds of delays. The delays of the critical paths are reduced with higher priority. In (1), the algorithm attempts to assign the primary input and output on each critical path to one chip. In (2), the algorithm not only decreases the number of crossings between chips but also assigns the logic blocks on each critical path to one chip by exploiting a network flow technique with logic-block replication. The experimental results demonstrate that it resolves almost all path delay constraints with the maximum number of required I/O blocks per chip small compared with conventional algorithms.