Rongliang Fu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Rongliang Fu has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
- Tsung-Yi Ho
The Chinese University of Hong Kong
23 shared publications - Junying Huang
SKLP, Institute of Computing Technology, CAS, Beijing, China
8 shared publications - Bei Yu
The Chinese University of Hong Kong
6 shared publications - Xiaochun Ye
Institute of Computing Technology Chinese Academy of Sciences
6 shared publications - Ran Zhang
SKLP, Institute of Computing Technology, CAS, Beijing, China and School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China
4 shared publications - Robert Wille
Technical University of Munich
4 shared publications
Latest Publications
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
JSPlace: A Shape-Controllable and Length-Matching Placement for Rapid Single-Flux-Quantum Circuits
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessJSPlace: A Shape-Controllable and Length-Matching Placement for Rapid Single-Flux-Quantum Circuits
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
ModuPlace: LLM-Assisted Modular PCB Placement via Preference-Optimized Constraint Graph Generation
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessModuPlace: LLM-Assisted Modular PCB Placement via Preference-Optimized Constraint Graph Generation
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Late Breaking Results: A Multi-Agent System for Adaptive Optimization of Large-Scale Conjunctive Normal Form
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessLate Breaking Results: A Multi-Agent System for Adaptive Optimization of Large-Scale Conjunctive Normal Form
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
MappingEvolve: LLM-Driven Code Evolution for Technology Mapping
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessMappingEvolve: LLM-Driven Code Evolution for Technology Mapping
- Open Access
- 21 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Quantum Computing
FlatDD: Parallel Quantum Circuit Simulation using Decision Diagram and Flat Array
Quantum circuit simulator (QCS) is essential for designing quantum algorithms because it assists researchers in understanding how quantum operations work without access to expensive quantum computers. Traditional array-based QCSs suffer from exponential time and memory complexities. To address this problem, Decision Diagram (DD) was introduced to compress simulation data by exploring the circuit regularity. However, for irregular circuit structures, DD-based simulation incurs significant runtime and memory overhead. To overcome this challenge, we present FlatDD, a parallel QCS that capitalizes on the strength of both DD- and array-based approaches. FlatDD parallelizes the simulation workload at multiple levels and leverages caching to reuse historical results. To further enhance the simulation performance for deep circuits, FlatDD introduces a gate-fusion algorithm to reduce the computational cost. Compared to state-of-the-art QCSs on commonly used quantum circuits, FlatDD achieves 54.35 × speed-up and 1.91 × memory reduction.
- 21 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Quantum Computing
Open AccessFlatDD: Parallel Quantum Circuit Simulation using Decision Diagram and Flat Array
Quantum circuit simulator (QCS) is essential for designing quantum algorithms because it assists researchers in understanding how quantum operations work without access to expensive quantum computers. Traditional array-based QCSs suffer from exponential time and memory complexities. To address this problem, Decision Diagram (DD) was introduced to compress simulation data by exploring the circuit regularity. However, for irregular circuit structures, DD-based simulation incurs significant runtime and memory overhead. To overcome this challenge, we present FlatDD, a parallel QCS that capitalizes on the strength of both DD- and array-based approaches. FlatDD parallelizes the simulation workload at multiple levels and leverages caching to reuse historical results. To further enhance the simulation performance for deep circuits, FlatDD introduces a gate-fusion algorithm to reduce the computational cost. Compared to state-of-the-art QCSs on commonly used quantum circuits, FlatDD achieves 54.35 × speed-up and 1.91 × memory reduction.
- Open Access
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 31-37
THLR: A Top-down Hierarchical Logic Rewrite Framework for Xor-Majority-Inverter Graphs
With the increasing complexity of integrated circuits, multiple Boolean network types have been developed to support efficient logic rewriting methods. Although the Xor-Majority-Inverter Graphs (XMG) have a relatively compact expressive power, due to the characteristics of the rewriting itself and the inherent properties of XMG, the rewriting does not always perform optimally in terms of optimization performance on XMG. In this paper, we propose a novel top-down hierarchical logic rewriting framework for XMG that exploits the complementary expressive capabilities of multiple Boolean network types. To more effectively leverage the rewriting potential of hierarchical Boolean network types, we propose a type-aware partitioning strategy that decomposes the network into structurally meaningful sub-circuits. This enables targeted optimizations tailored to the structural characteristics of each sub-circuit, effectively balancing rewriting quality with computational efficiency. Experimental results demonstrate that our framework significantly improves circuit quality, achieving an approximate 4.31% reduction in node-depth product (NDP) compared to state-of-the-art rewriting methods, while also reducing the runtime by about 13.62%. Moreover, after ASIC mapping, THLR delivers a 3.10% improvement in area-delay product (ADP) over the state-of-the-art approaches.
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 31-37
Open AccessTHLR: A Top-down Hierarchical Logic Rewrite Framework for Xor-Majority-Inverter Graphs
With the increasing complexity of integrated circuits, multiple Boolean network types have been developed to support efficient logic rewriting methods. Although the Xor-Majority-Inverter Graphs (XMG) have a relatively compact expressive power, due to the characteristics of the rewriting itself and the inherent properties of XMG, the rewriting does not always perform optimally in terms of optimization performance on XMG. In this paper, we propose a novel top-down hierarchical logic rewriting framework for XMG that exploits the complementary expressive capabilities of multiple Boolean network types. To more effectively leverage the rewriting potential of hierarchical Boolean network types, we propose a type-aware partitioning strategy that decomposes the network into structurally meaningful sub-circuits. This enables targeted optimizations tailored to the structural characteristics of each sub-circuit, effectively balancing rewriting quality with computational efficiency. Experimental results demonstrate that our framework significantly improves circuit quality, achieving an approximate 4.31% reduction in node-depth product (NDP) compared to state-of-the-art rewriting methods, while also reducing the runtime by about 13.62%. Moreover, after ASIC mapping, THLR delivers a 3.10% improvement in area-delay product (ADP) over the state-of-the-art approaches.
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
Towards Secure and Efficient DNN Accelerators via Hardware-Software Co-Design
The rapid deployment of deep neural network (DNN) accelerators in safety-critical domains such as autonomous vehicles, healthcare systems, and financial infrastructure necessitates robust mechanisms to safeguard data confidentiality and computational integrity. Existing security solutions for DNN accelerators, however, suffer from excessive hardware resource demands and frequent off-chip memory access overheads, which degrade performance and scalability. To address these challenges, this paper presents a secure and efficient memory protection framework for DNN accelerators with minimal overhead. First, we propose a bandwidth-aware cryptographic scheme that adapts encryption granularity based on memory traffic patterns, striking a balance between security and resource efficiency. Second, we observe that both the overlapping regions in the intra-layer tiling’s sliding window pattern and those resulting from inter-layer tiling strategy discrepancies introduce substantial redundant memory accesses and repeated computational overhead in cryptography. Third, we introduce a multi-level authentication mechanism that effectively eliminates unnecessary off-chip memory accesses, enhancing performance and energy efficiency. Experimental results show that this work decreases performance overhead by over 12% and achieves 87% energy efficiency improvement for both server and edge neural processing units (NPUs), while ensuring robust scalability.
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
Towards Secure and Efficient DNN Accelerators via Hardware-Software Co-Design
The rapid deployment of deep neural network (DNN) accelerators in safety-critical domains such as autonomous vehicles, healthcare systems, and financial infrastructure necessitates robust mechanisms to safeguard data confidentiality and computational integrity. Existing security solutions for DNN accelerators, however, suffer from excessive hardware resource demands and frequent off-chip memory access overheads, which degrade performance and scalability. To address these challenges, this paper presents a secure and efficient memory protection framework for DNN accelerators with minimal overhead. First, we propose a bandwidth-aware cryptographic scheme that adapts encryption granularity based on memory traffic patterns, striking a balance between security and resource efficiency. Second, we observe that both the overlapping regions in the intra-layer tiling’s sliding window pattern and those resulting from inter-layer tiling strategy discrepancies introduce substantial redundant memory accesses and repeated computational overhead in cryptography. Third, we introduce a multi-level authentication mechanism that effectively eliminates unnecessary off-chip memory accesses, enhancing performance and energy efficiency. Experimental results show that this work decreases performance overhead by over 12% and achieves 87% energy efficiency improvement for both server and edge neural processing units (NPUs), while ensuring robust scalability.
- 20 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (8) , 2870-2884
AgeBalance: Low-Cost Lifetime Extension for SRAM-Based PIM Accelerators
Although processing-in-memory (PIM) techniques have widely been used for deep neural networks (DNNs) acceleration, the inference performance of aged PIM-based accelerators remains to be investigated. This paper makes the first attempt to study Hot Carrier Injection (HCI) and Negative Bias Temperature Instability (NBTI) aging impacts on SRAM-based DNN accelerators, which provides a novel and unified framework, termed AgeBalance for aging detection, analysis and mitigation. First, we discuss a convenient aging detection scheme. Then, we benchmark the inference accuracy drops of DNNs running on aged SRAM-based PIM accelerators. Finally, we propose a low-cost anti-aging training method without incurring additional hardware overhead on SRAM-based DNN accelerators. Extensive experimental results on MNIST, CIFAR10 and AG News datasets show that aging can cause the inference accuracy of shallow or deep DNNs to drop to about 10%, close to random guessing. The aging mitigation scheme proposed in this paper can largely restore the accuracy to the original. Moreover, the SRAM write overhead of our method is much reduced thanks to a score-based training approach, leading to a reduction of 5× to 10× writing energy compared to the traditional training method.
- 20 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (8) , 2870-2884
AgeBalance: Low-Cost Lifetime Extension for SRAM-Based PIM Accelerators
Although processing-in-memory (PIM) techniques have widely been used for deep neural networks (DNNs) acceleration, the inference performance of aged PIM-based accelerators remains to be investigated. This paper makes the first attempt to study Hot Carrier Injection (HCI) and Negative Bias Temperature Instability (NBTI) aging impacts on SRAM-based DNN accelerators, which provides a novel and unified framework, termed AgeBalance for aging detection, analysis and mitigation. First, we discuss a convenient aging detection scheme. Then, we benchmark the inference accuracy drops of DNNs running on aged SRAM-based PIM accelerators. Finally, we propose a low-cost anti-aging training method without incurring additional hardware overhead on SRAM-based DNN accelerators. Extensive experimental results on MNIST, CIFAR10 and AG News datasets show that aging can cause the inference accuracy of shallow or deep DNNs to drop to about 10%, close to random guessing. The aging mitigation scheme proposed in this paper can largely restore the accuracy to the original. Moreover, the SRAM write overhead of our method is much reduced thanks to a score-based training approach, leading to a reduction of 5× to 10× writing energy compared to the traditional training method.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
Efficient Multi-Array Parallel Scheduling for In-Memory Computing
In-memory computing (IMC) for logic functions executes a target function via a series of logic operations supported by peripheral devices. Because these operations are performed on multiple memory rows in lockstep, this paradigm follows a single-instruction multiple-data (SIMD) style. Existing multi-array schedulers mainly focus on reducing copy instruction lines but often overlook array-level parallel scheduling. This paper presents MAPSIM, an efficient multi-array parallel SIMD-IMC scheduler that reduces both copy instructions and execution cycles. To alleviate input congestion, we model input assignment as a bipartite-graph partitioning problem to optimize input distribution across arrays. For multi-array parallel scheduling, we represent the data state of each array in a state-transition graph and assign each state a scheduling potential energy. The scheduler then greedily selects actions that maximize instantaneous energy gain. To accelerate state transitions, we further employ priority-queue filtering and maximum-weight matching to select optimal, feasible actions per cycle. Experimental results on EPFL benchmarks demonstrate the effectiveness and efficiency of our framework. MAPSIM reduces execution cycles by 23.43% and copy instructions by 19.78% over the state-of-the-art, while achieving a 15.02× speedup in runtime. Our code and data are available at https://github.com/Flians/MAPSIM.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
Efficient Multi-Array Parallel Scheduling for In-Memory Computing
In-memory computing (IMC) for logic functions executes a target function via a series of logic operations supported by peripheral devices. Because these operations are performed on multiple memory rows in lockstep, this paradigm follows a single-instruction multiple-data (SIMD) style. Existing multi-array schedulers mainly focus on reducing copy instruction lines but often overlook array-level parallel scheduling. This paper presents MAPSIM, an efficient multi-array parallel SIMD-IMC scheduler that reduces both copy instructions and execution cycles. To alleviate input congestion, we model input assignment as a bipartite-graph partitioning problem to optimize input distribution across arrays. For multi-array parallel scheduling, we represent the data state of each array in a state-transition graph and assign each state a scheduling potential energy. The scheduler then greedily selects actions that maximize instantaneous energy gain. To accelerate state transitions, we further employ priority-queue filtering and maximum-weight matching to select optimal, feasible actions per cycle. Experimental results on EPFL benchmarks demonstrate the effectiveness and efficiency of our framework. MAPSIM reduces execution cycles by 23.43% and copy instructions by 19.78% over the state-of-the-art, while achieving a 15.02× speedup in runtime. Our code and data are available at https://github.com/Flians/MAPSIM.