Performance-driven multi-FPGA partitioning using functional clustering and replication

  • Authors:
  • Wen-Jong Fang;Allen C.-H. Wu

  • Affiliations:
  • Department of Computer Science, Tsing Hua University, Hsinchu, Taiwan, 300, Republic of China;Department of Computer Science, Tsing Hua University, Hsinchu, Taiwan, 300, Republic of China

  • Venue:
  • DAC '98 Proceedings of the 35th annual Design Automation Conference
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a new performance-driven partitioning method for multi-FPGA designs. The proposed method consists of three steps: (1) functional-cluster formation, (2) slack computation, and (3) set-covering-based partitioning with functional replication. The proposed method performs multi-FPGA partitioning by taking into account path delays and design structural information. We introduce a functional replication technique which performs circuit replications at the functional-cluster level instead of the cell level for delay and interconnect minimization. Experimental results on a number of benchmarks and industrial designs demonstrate that the proposed method achieves high-performance and high-density multi-FPGA partitions.