Abstract | ||
---|---|---|
elfplace is a flat nonlinear placement algorithm for large-scale heterogeneous field-programmable gate arrays (FPGAs). We adopt the analogy between placement and electrostatic systems initially proposed by ePlace and extend it to tackle heterogeneous blocks in FPGA designs. To achieve satisfiable solution quality with fast and robust numerical convergence, an augmented Lagrangian formulation together with a preconditioning technique and a normalized subgradient-based multiplier updating scheme are proposed. Besides pure-wirelength minimization, we also propose a unified instance area adjustment scheme to simultaneously optimize routability, pin density, and downstream clustering compatibility. Our experiments on ISPD 2016 benchmark suite show that elfPlace outperforms four state-of-the-art FPGA placers UTPlaceF, RippleFPGA, GPlace3.0, and UTPlaceF-DL by 13.6%, 11.3%, 8.9%, and 7.1%, respectively, in routed wirelength with competitive runtime. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICCAD45719.2019.8942075 | 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) |
Keywords | Field | DocType |
elfplace,electrostatics-based placement,heterogeneous FPGA,flat nonlinear placement algorithm,electrostatic systems,augmented Lagrangian formulation,preconditioning technique,normalized subgradient-based multiplier updating scheme,unified instance area adjustment scheme,ISPD 2016 benchmark suite,heterogeneous field-programmable gate arrays | Convergence (routing),Nonlinear system,Subgradient method,Computer science,Parallel computing,Field-programmable gate array,Electronic engineering,Multiplier (economics),Augmented Lagrangian method,Minification,Cluster analysis | Conference |
ISSN | ISBN | Citations |
1933-7760 | 978-1-7281-2351-6 | 0 |
PageRank | References | Authors |
0.34 | 15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wuxi Li | 1 | 36 | 6.03 |
Yibo Lin | 2 | 119 | 20.98 |
David Z. Pan | 3 | 2653 | 237.64 |