PMP: performance-driven multilevel partitioning by aggregating the preferred signal directions of I/O conduits

In this paper, we present a new performance-driven multilevel partitioning algorithm, which calculates the timing gain of a move in the move-based partitioning strategies based on the aggregation of preferred signal directions. In addition, we propose a new timing-aware multilevel clustering algorithm that uses the connection strength of an edge as the primary objective, and the maximum depth or the maximum hop-count of any path containing the edge as a tiebreaker for the clustering step. These ideas are integrated into a general multilevel partitioning framework, which consists of three phases: uncoarsening, initial partitioning, and coarsening and refinement phases. The benchmarks show that, on average, we can reduce delay by 14.6%, while increasing the cutsize by 1.2% when compared to hMetis (Karygpis et al., 1997).