Jia Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jia Wang has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Fan Yang
School of Microelectronics, Fudan University
5 shared publications - Xuan Zeng
Fudan University
4 shared publications - Yiting Liu
School of Computer Science, Fudan University, Shanghai, China
4 shared publications - Hai Zhou
Northwestern University
3 shared publications Hai Zhou
Department of ECE, Northwestern University, Evanston, IL, USA
2 shared publications- Li Shang
Computer Science, Fudan University
2 shared publications
Latest Publications
- Open Access
- 10 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31 (5) , 1-23
Graph Neural Network based Initialization for Timing Driven Placement
Timing-driven placement is very important to achieve timing closure especially as designs become increasingly complex. This article presents a novel Timing-Driven Placement (TDP) framework that integrates a graph convolutional network (GCN), Dirichlet boundary conditions, and a nonlinear placement engine to optimize placement quality with timing awareness throughout the flow. The proposed methodology begins by clustering components based on their interconnection topology, while Dirichlet boundary conditions are applied to handle fixed components such as IOs and macros. This yields a reduced graph with minimized inter-cluster connectivity, simplifying timing optimization. A GCN is then trained to learn a generalized and optimized mapping from circuit connectivity to physical wirelength. To improve early-stage timing estimation, virtual buffers are inserted prior to Static Timing Analysis (STA) to eliminate maximum capacitance violations. With this improved timing fidelity, STA provides pin-level slack, which is then used to dynamically adjust interconnection weights, guiding the placement of timing-critical components toward improved timing closure. Experimental results on ICCAD2015 contest benchmarks demonstrate that our algorithm can improve worse negative slack and total negative slack by 6% compared to the state-of-the-art method.
- 10 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31 (5) , 1-23
Open AccessGraph Neural Network based Initialization for Timing Driven Placement
Timing-driven placement is very important to achieve timing closure especially as designs become increasingly complex. This article presents a novel Timing-Driven Placement (TDP) framework that integrates a graph convolutional network (GCN), Dirichlet boundary conditions, and a nonlinear placement engine to optimize placement quality with timing awareness throughout the flow. The proposed methodology begins by clustering components based on their interconnection topology, while Dirichlet boundary conditions are applied to handle fixed components such as IOs and macros. This yields a reduced graph with minimized inter-cluster connectivity, simplifying timing optimization. A GCN is then trained to learn a generalized and optimized mapping from circuit connectivity to physical wirelength. To improve early-stage timing estimation, virtual buffers are inserted prior to Static Timing Analysis (STA) to eliminate maximum capacitance violations. With this improved timing fidelity, STA provides pin-level slack, which is then used to dynamically adjust interconnection weights, guiding the placement of timing-critical components toward improved timing closure. Experimental results on ICCAD2015 contest benchmarks demonstrate that our algorithm can improve worse negative slack and total negative slack by 6% compared to the state-of-the-art method.
- Open Access
- 29 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 886-892
Enhancing Modern SAT Solver With Machine Learning Method
- 29 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 886-892
Open AccessEnhancing Modern SAT Solver With Machine Learning Method
- 1 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (10) , 3924-3937
An Efficient Placement Speedup Technique Based on Graph Signal Processing
Placement is a critical task with high computation complexity in VLSI physical design. Modern analytical placers formulate the placement objective as a nonlinear optimization task, which suffers a long iteration time. To accelerate and enhance the placement process, recent studies have turned to deep learning-based approaches, particularly leveraging graph convolution networks (GCNs). However, learning-based placers require time-and data-consuming model training due to the complexity of circuit placement that involves large-scale cells and design-specific graph statistics. This paper proposes GiFt, a parameter-free initialization technique for accelerating placement, rooted in graph signal processing. GiFt excels at capturing multi-resolution smooth signals of circuit graphs to generate optimized initial placement solutions without the need for time-consuming model training, and meanwhile significantly reduces the number of iterations required by analytical placers. Moreover, we present GiFtPlus, an enhanced version of GiFt, which is more efficient in handling large-scale circuit placement and can accommodate location constraints. Experimental results on public benchmarks show that GiFt and GiFtPlus significantly improve placement efficiency, while achieving competitive or superior performance compared to state-of-the-art placers. In particular, the recently proposed GPU-accelerated analytical placer DREAMPlace uses up to 50% more total runtime than GiFtPlus-DREAMPlace.
- 1 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (10) , 3924-3937
An Efficient Placement Speedup Technique Based on Graph Signal Processing
Placement is a critical task with high computation complexity in VLSI physical design. Modern analytical placers formulate the placement objective as a nonlinear optimization task, which suffers a long iteration time. To accelerate and enhance the placement process, recent studies have turned to deep learning-based approaches, particularly leveraging graph convolution networks (GCNs). However, learning-based placers require time-and data-consuming model training due to the complexity of circuit placement that involves large-scale cells and design-specific graph statistics. This paper proposes GiFt, a parameter-free initialization technique for accelerating placement, rooted in graph signal processing. GiFt excels at capturing multi-resolution smooth signals of circuit graphs to generate optimized initial placement solutions without the need for time-consuming model training, and meanwhile significantly reduces the number of iterations required by analytical placers. Moreover, we present GiFtPlus, an enhanced version of GiFt, which is more efficient in handling large-scale circuit placement and can accommodate location constraints. Experimental results on public benchmarks show that GiFt and GiFtPlus significantly improve placement efficiency, while achieving competitive or superior performance compared to state-of-the-art placers. In particular, the recently proposed GPU-accelerated analytical placer DREAMPlace uses up to 50% more total runtime than GiFtPlus-DREAMPlace.
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
The Power of Graph Signal Processing for Chip Placement Acceleration
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessThe Power of Graph Signal Processing for Chip Placement Acceleration
- 8 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 32 (5) , 810-822
Hierarchical Graph Learning-Based Floorplanning With Dirichlet Boundary Conditions
Floorplanning is a complex physical design problem that produces initial locations of movable objects, the quality of which has a great impact on downstream tasks such as placement and routing. To improve the efficacy of floorplanning, machine learning techniques have recently been recruited for help. However, the application-specific location constraints (IOs and cells with fixed locations) pose a huge challenge for machine learning. This article presents a novel uniformization approach by Dirichlet boundary conditions, which decomposes floorplanning into two easier-to-solve subproblems, namely a convex quadratic wirelength optimization problem with location constraints and an NP-hard combinatorial problem with homogeneous Dirichlet boundary conditions. The former problem is efficiently solved using quadratic optimization, and the latter is addressed by efficient graph inference using the proposed hierarchical GNN-based model. The proposed floorplanner called DPlanner has been integrated with state-of-the-art mixed-size placers to generate high-quality placement solutions with up to 56% and 41% improvement in placement iterations and runtime. In addition, compared to the state-of-the-art integrated floorplanning-placement flow, DPlanner achieves over a 20% improvement in placement iteration and more than a 21% reduction in total runtime, along with a 2% average reduction in wirelength.
- 8 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 32 (5) , 810-822
Hierarchical Graph Learning-Based Floorplanning With Dirichlet Boundary Conditions
Floorplanning is a complex physical design problem that produces initial locations of movable objects, the quality of which has a great impact on downstream tasks such as placement and routing. To improve the efficacy of floorplanning, machine learning techniques have recently been recruited for help. However, the application-specific location constraints (IOs and cells with fixed locations) pose a huge challenge for machine learning. This article presents a novel uniformization approach by Dirichlet boundary conditions, which decomposes floorplanning into two easier-to-solve subproblems, namely a convex quadratic wirelength optimization problem with location constraints and an NP-hard combinatorial problem with homogeneous Dirichlet boundary conditions. The former problem is efficiently solved using quadratic optimization, and the latter is addressed by efficient graph inference using the proposed hierarchical GNN-based model. The proposed floorplanner called DPlanner has been integrated with state-of-the-art mixed-size placers to generate high-quality placement solutions with up to 56% and 41% improvement in placement iterations and runtime. In addition, compared to the state-of-the-art integrated floorplanning-placement flow, DPlanner achieves over a 20% improvement in placement iteration and more than a 21% reduction in total runtime, along with a 2% average reduction in wirelength.
- Open Access
- 24 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 28 (2) , 1-24
GraphPlanner: Floorplanning with Graph Neural Network
Chip floorplanning has long been a critical task with high computation complexity in the physical implementation of VLSI chips. Its key objective is to determine the initial locations of large chip modules with minimized wirelength while adhering to the density constraint, which in essence is a process of constructing an optimized mapping from circuit connectivity to physical locations. Proven to be an NP-hard problem, chip floorplanning is difficult to be solved efficiently using algorithmic approaches. This article presents GraphPlanner, a variational graph-convolutional-network-based deep learning technique for chip floorplanning. GraphPlanner is able to learn an optimized and generalized mapping between circuit connectivity and physical wirelength and produce a chip floorplan using efficient model inference. GraphPlanner is further equipped with an efficient clustering method, a unification of hyperedge coarsening with graph spectral clustering, to partition a large-scale netlist into high-quality clusters with minimized inter-cluster weighted connectivity. GraphPlanner has been integrated with two state-of-the-art mixed-size placers. Experimental studies using both academic benchmarks and industrial designs demonstrate that compared to state-of-the-art mixed-size placers alone, GraphPlanner improves placement runtime by 25% with 4% wirelength reduction on average.
- 24 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 28 (2) , 1-24
Open AccessGraphPlanner: Floorplanning with Graph Neural Network
Chip floorplanning has long been a critical task with high computation complexity in the physical implementation of VLSI chips. Its key objective is to determine the initial locations of large chip modules with minimized wirelength while adhering to the density constraint, which in essence is a process of constructing an optimized mapping from circuit connectivity to physical locations. Proven to be an NP-hard problem, chip floorplanning is difficult to be solved efficiently using algorithmic approaches. This article presents GraphPlanner, a variational graph-convolutional-network-based deep learning technique for chip floorplanning. GraphPlanner is able to learn an optimized and generalized mapping between circuit connectivity and physical wirelength and produce a chip floorplan using efficient model inference. GraphPlanner is further equipped with an efficient clustering method, a unification of hyperedge coarsening with graph spectral clustering, to partition a large-scale netlist into high-quality clusters with minimized inter-cluster weighted connectivity. GraphPlanner has been integrated with two state-of-the-art mixed-size placers. Experimental studies using both academic benchmarks and industrial designs demonstrate that compared to state-of-the-art mixed-size placers alone, GraphPlanner improves placement runtime by 25% with 4% wirelength reduction on average.
- Open Access
Reconstruction of microbial haplotypes by integration of statistical and physical linkage in scaffolding
DNA sequencing technologies provide unprecedented opportunities to analyze within-host evolution of microorganism populations. Often, within-host populations are analyzed via pooled sequencing of the population, which contains multiple individuals or ‘haplotypes’. However, current next-generation sequencing instruments, in conjunction with single-molecule barcoded linked-reads, cannot distinguish long haplotypes directly. Computational reconstruction of haplotypes from pooled sequencing has been attempted in virology, bacterial genomics, metagenomics and human genetics, using algorithms based on either cross-host genetic sharing or within-host genomic reads. Here we describe PoolHapX, a flexible computational approach that integrates information from both genetic sharing and genomic sequencing. We demonstrated that PoolHapX outperforms state-of-the-art tools tailored to specific organismal systems, and is robust to within-host evolution. Importantly, together with barcoded linked-reads, PoolHapX can infer whole-chromosome-scale haplotypes from 50 pools each containing 12 different haplotypes. By analyzing real data, we uncovered dynamic variations in the evolutionary processes of within-patient HIV populations previously unobserved in single position-based analysis.
Open AccessReconstruction of microbial haplotypes by integration of statistical and physical linkage in scaffolding
DNA sequencing technologies provide unprecedented opportunities to analyze within-host evolution of microorganism populations. Often, within-host populations are analyzed via pooled sequencing of the population, which contains multiple individuals or ‘haplotypes’. However, current next-generation sequencing instruments, in conjunction with single-molecule barcoded linked-reads, cannot distinguish long haplotypes directly. Computational reconstruction of haplotypes from pooled sequencing has been attempted in virology, bacterial genomics, metagenomics and human genetics, using algorithms based on either cross-host genetic sharing or within-host genomic reads. Here we describe PoolHapX, a flexible computational approach that integrates information from both genetic sharing and genomic sequencing. We demonstrated that PoolHapX outperforms state-of-the-art tools tailored to specific organismal systems, and is robust to within-host evolution. Importantly, together with barcoded linked-reads, PoolHapX can infer whole-chromosome-scale haplotypes from 50 pools each containing 12 different haplotypes. By analyzing real data, we uncovered dynamic variations in the evolutionary processes of within-patient HIV populations previously unobserved in single position-based analysis.
- Open Access
- 19 May 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 58 (6) , 1372-1381
In-Place FPGA Retiming for Mitigation of Variational Single-Event Transient Faults
For anti-fuse or flash-memory-based field-programmable gate arrays (FPGAs), single-event transient (SET)-induced faults are significantly more pronounced than single-event upsets (SEUs). While most existing work studies SEU, this paper proposes a retiming algorithm for mitigating variational SETs (i.e., SETs with different durations and strengths). Considering the reshaping effect of an SET pulse caused by broadening and attenuation during its propagation, SET-aware retiming (SaR) redistributes combinational paths via post layout retiming and minimizes the possibility that an SET pulse is latched. The SaR problem is formulated as an integer linear programming (ILP) problem and solved efficiently by a progressive ILP approach. In contrast to existing SET-mitigation techniques, the proposed SaR does not change the FPGA architecture or the layout of an FPGA application. Instead, it reconfigures the connection between a flip-flop and an LUT within a programmable logic block. Experimental results show that SaR increases mean-time-to-failure (MTTF) by 78% for variational SETs with a 10-min runtime limit while preserving the clock frequency on ISCAS89 benchmark circuits. To the best of our knowledge, this paper is the first in-depth study on FPGA retiming for SET mitigation.
- 19 May 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 58 (6) , 1372-1381
Open AccessIn-Place FPGA Retiming for Mitigation of Variational Single-Event Transient Faults
For anti-fuse or flash-memory-based field-programmable gate arrays (FPGAs), single-event transient (SET)-induced faults are significantly more pronounced than single-event upsets (SEUs). While most existing work studies SEU, this paper proposes a retiming algorithm for mitigating variational SETs (i.e., SETs with different durations and strengths). Considering the reshaping effect of an SET pulse caused by broadening and attenuation during its propagation, SET-aware retiming (SaR) redistributes combinational paths via post layout retiming and minimizes the possibility that an SET pulse is latched. The SaR problem is formulated as an integer linear programming (ILP) problem and solved efficiently by a progressive ILP approach. In contrast to existing SET-mitigation techniques, the proposed SaR does not change the FPGA architecture or the layout of an FPGA application. Instead, it reconfigures the connection between a flip-flop and an LUT within a programmable logic block. Experimental results show that SaR increases mean-time-to-failure (MTTF) by 78% for variational SETs with a 10-min runtime limit while preserving the clock frequency on ISCAS89 benchmark circuits. To the best of our knowledge, this paper is the first in-depth study on FPGA retiming for SET mitigation.