Interconnect complexity-aware FPGA placement using Rent's rule
Authors:
Open Access
- 1 March 2001
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 115-121
Abstract
Field Programmable Gate Arrays (FPGAs) have gained in commercial acceptance because they offer instant manufacturing turnaround and low costs. However, FPGAs are constantly hard pressed to keep up with the requirements of the more complex and larger scale circuits which are being targeted for them. Routability of a circuit depends on the FPGA architecture, the placement, and the interconnection complexity of the circuit to be placed and routed. This paper explores the use of Rent's rule as a complexity metric for improving the placement of circuits on a target FPGA architecture, such that routing resource utilization is improved. A new simulated annealing based placement algorithm is presented and experimental results are presented to illustrate the validity of the approach for certain example circuits and the ISCAS benchmarks.Keywords
This publication has 10 references indexed in Scilit:
- Optimal layout via Boolean satisfiability2003
- Generating synthetic benchmark circuits for evaluating CAD toolsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2000
- Balancing interconnect and computation in a reconfigurable computing array (or, why you don't really want 100% LUT utilization)1999
- FPGA routing and routability estimation via Boolean satisfiability1997
- Graph based analysis of 2-D FPGA routingIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1996
- On routability prediction for field-programmable gate arrays1993
- Optimization by Simulated AnnealingScience, 1983
- Two-dimensional stochastic model for interconnections in master slice integrated circuitsIEEE Transactions on Circuits and Systems, 1981
- Placement and average interconnection lengths of computer logicIEEE Transactions on Circuits and Systems, 1979
- On a Pin Versus Block Relationship For Partitions of Logic GraphsIEEE Transactions on Computers, 1971