Zhili Xiong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zhili Xiong has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- David Z. Pan
The University of Texas at Austin
2 shared publications - Haoxing Ren
NVIDIA Corporation, Austin, TX, USA
1 shared publication - Rachel Selina Rajarathnam
The University of Texas at Austin
1 shared publication - Yi-Chen Lu
NVIDIA, Santa Clara, CA, USA
1 shared publication - Yusu Wang
University of California San Diego
1 shared publication - Zhishang Luo
University of California San Diego
1 shared publication
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31 (6) , 1-22
TopoGeoNet: A Heterogeneous Model for End-to-End Congestion Prediction and Optimization in FPGA Placement
Recent approaches to congestion prediction and routability-driven placement have made progress, yet important limitations remain. Most existing models rely on heuristic-based intermediate features (e.g., RUDY, pin density) rather than fully end-to-end learning, and many capture either netlist topology or geometric placement context, but not both, limiting their performance. Moreover, when model gradients are used to guide placers, they are often propagated through such intermediate features, reducing their accuracy and effectiveness. To address these gaps, we propose TopoGeoNet , a heterogeneous neural network that unifies graph-based message passing with convolutional U-Net processing over spatial grids. Through bi-directional node–grid communication, TopoGeoNet jointly leverages netlist topology and geometric placement information for accurate congestion prediction. Trained on ISPD’2016 FPGA benchmarks, TopoGeoNet achieves an 8.3% improvement in prediction accuracy over state-of-the-art ML baselines. When integrated into a routability-driven FPGA placer, it improves congestion scores by 16% on average and reduces total place-and-route runtime by 5% without degrading routed wirelength. Compared with state-of-the-art ML prediction models that provide inference and gradients through intermediate features, TopoGeoNet delivers superior routability results, highlighting the advantages of fully end-to-end prediction and differentiability.
- 15 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31 (6) , 1-22
Open AccessTopoGeoNet: A Heterogeneous Model for End-to-End Congestion Prediction and Optimization in FPGA Placement
Recent approaches to congestion prediction and routability-driven placement have made progress, yet important limitations remain. Most existing models rely on heuristic-based intermediate features (e.g., RUDY, pin density) rather than fully end-to-end learning, and many capture either netlist topology or geometric placement context, but not both, limiting their performance. Moreover, when model gradients are used to guide placers, they are often propagated through such intermediate features, reducing their accuracy and effectiveness. To address these gaps, we propose TopoGeoNet , a heterogeneous neural network that unifies graph-based message passing with convolutional U-Net processing over spatial grids. Through bi-directional node–grid communication, TopoGeoNet jointly leverages netlist topology and geometric placement information for accurate congestion prediction. Trained on ISPD’2016 FPGA benchmarks, TopoGeoNet achieves an 8.3% improvement in prediction accuracy over state-of-the-art ML baselines. When integrated into a routability-driven FPGA placer, it improves congestion scores by 16% on average and reduces total place-and-route runtime by 5% without degrading routed wirelength. Compared with state-of-the-art ML prediction models that provide inference and gradients through intermediate features, TopoGeoNet delivers superior routability results, highlighting the advantages of fully end-to-end prediction and differentiability.
- Open Access
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 64-72
GrandPlan: Differentiable, Simultaneous Top-Level Floorplanning and Partition-Level Cell Placement for Large-Scale IP-Cores
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 64-72
Open AccessGrandPlan: Differentiable, Simultaneous Top-Level Floorplanning and Partition-Level Cell Placement for Large-Scale IP-Cores