OpenPARF: An Open-Source Placement and Routing Framework for Large-Scale Heterogeneous FPGAs with Deep Learning Toolkit
- Resource Type
- Conference
- Authors
- Mai, Jing; Wang, Jiarui; Di, Zhixiong; Luo, Guojie; Liang, Yun; Lin, Yibo
- Source
- 2023 IEEE 15th International Conference on ASIC (ASICON) ASIC (ASICON), 2023 IEEE 15th International Conference on. :1-4 Oct, 2023
- Subject
- Components, Circuits, Devices and Systems
Deep learning
Roads
Graphics processing units
Benchmark testing
Routing
Field programmable gate arrays
Physical design
- Language
- ISSN
- 2162-755X
This paper proposes OpenPARF, an open-source placement and routing framework for large-scale FPGA designs 1 . OpenPARF is implemented with the deep learning toolkit PyTorch and supports massive parallelization on GPU. The framework proposes a novel asymmetric multi-electrostatic field system to solve FPGA placement. It considers fine-grained routing resources inside configurable logic blocks (CLBs) for FPGA routing and supports large-scale irregular routing resource graphs. Experimental results on ISPD 2016 and ISPD 2017 FPGA contest benchmarks and industrial benchmarks demonstrate that OpenPARF can achieve 0.4-12.7% improvement in routed wirelength and more than 2× speedup in placement. We believe that OpenPARF can pave the road for developing FPGA physical design engines and stimulate further research on related topics.