Guiming Wu
Research Subjects
Guiming Wu has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Changzheng Wei
Ant Group
6 shared publications - Ying Yan
Ant Group
6 shared publications - Pengcheng Qiu
Ant Group
4 shared publications - Zhenxiang Zhang
Alibaba Group, Hangzhou, China
3 shared publications - Hui Zhang
Ant Group, Hangzhou, Zhejiang, China
2 shared publications - Jiali Jiang
Alibaba Group, China
2 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (10) , 3323-3336
WestLake: Accelerating Fully Homomorphic Encryption With Less On-Chip Memory
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (10) , 3323-3336
WestLake: Accelerating Fully Homomorphic Encryption With Less On-Chip Memory
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (1) , 1-25
ALOHA: Accelerating Leveled Fully Homomorphic Encryption with Cryptography-Specific Architectures
Fully homomorphic encryption (FHE) enables privacy-preserving computation on encrypted data but incurs prohibitive computational overhead. To reduce this overhead, leveled FHE (LFHE) limits the multiplicative depth of supported computations. However, this restriction compromises its generality, making it necessary to integrate LFHE with federated learning (FL) and secure multiparty computation (MPC). Yet these hybrid FL/MPC workflows introduce new challenges, as they require dynamic cryptographic adaptation and flexible scheduling for efficient execution. We propose ALOHA, an FPGA-based LFHE acceleration framework designed to eliminate performance and scheduling bottlenecks in hybrid workflows. ALOHA’s hardware engine efficiently directs ciphertext operations to cryptographic modular arithmetic lanes, enabling parallel computational throughput while eliminating data contention. A reconfigurable Benes network dynamically interconnects these lanes, enabling native support for FHE-specific automorphism and adaptive memory access. To bridge algorithmic flexibility with hardware efficiency, ALOHA further integrates a domain-specific compiler that automates ciphertext packing and generates latency-optimized instruction schedules. In the ablation study, the hardware and the compiler contribute 177.8× and 145.5× speedup compared to state-of-the-art solutions, respectively. In end-to-end evaluations, ALOHA accelerates complex privacy-preserving services hybrid with FL and MPC, resulting in a speedup of 2.5× and 3.3× compared to state-of-the-art accelerators.
- 22 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (1) , 1-25
Open AccessALOHA: Accelerating Leveled Fully Homomorphic Encryption with Cryptography-Specific Architectures
Fully homomorphic encryption (FHE) enables privacy-preserving computation on encrypted data but incurs prohibitive computational overhead. To reduce this overhead, leveled FHE (LFHE) limits the multiplicative depth of supported computations. However, this restriction compromises its generality, making it necessary to integrate LFHE with federated learning (FL) and secure multiparty computation (MPC). Yet these hybrid FL/MPC workflows introduce new challenges, as they require dynamic cryptographic adaptation and flexible scheduling for efficient execution. We propose ALOHA, an FPGA-based LFHE acceleration framework designed to eliminate performance and scheduling bottlenecks in hybrid workflows. ALOHA’s hardware engine efficiently directs ciphertext operations to cryptographic modular arithmetic lanes, enabling parallel computational throughput while eliminating data contention. A reconfigurable Benes network dynamically interconnects these lanes, enabling native support for FHE-specific automorphism and adaptive memory access. To bridge algorithmic flexibility with hardware efficiency, ALOHA further integrates a domain-specific compiler that automates ciphertext packing and generates latency-optimized instruction schedules. In the ablation study, the hardware and the compiler contribute 177.8× and 145.5× speedup compared to state-of-the-art solutions, respectively. In end-to-end evaluations, ALOHA accelerates complex privacy-preserving services hybrid with FL and MPC, resulting in a speedup of 2.5× and 3.3× compared to state-of-the-art accelerators.
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (2) , 593-605
Exa: A Unified Architecture for Multi-Scalar Multiplication and Polynomial Computation in Zero-Knowledge Proof
Zero-knowledge proof (ZKP) is a cryptographic protocol that allows a prover to convince verifiers that a computation is correctly executed without disclosing the prover’s secret. ZKP has been deployed in various privacy-preserving applications. However, the proof generation is notably inefficient on general-purpose processors. Multi-scalar multiplication (MSM) and polynomial computation (POLY), including number theoretic transform (NTT), are two of the most computation-intensive parts in proof generation. Recently, separate accelerators for MSM and POLY (mostly NTT) have been proposed. Unfortunately, separate accelerators may have poor resource utilization since MSM and POLY cannot be performed concurrently. To address this challenge, we propose Exa, a unified hardware architecture for MSM and POLY. It enables MSM and POLY to share computational resources and memory resources through decoupling dataflow control, computation, and memory. We design a novel unified functional unit (FU) array that can support both POLY operation and point addition (PADD) for MSM. In addition, we propose a 3-D NTT implementation and an adaptive MSM implementation on the FU array using a domain-specific instruction set architecture (ISA). Exa is scalable and can be efficiently orchestrated by our proposed runtime system. Compared with the separate accelerators for MSM and NTT, Exa occupies 47% less chip area. Compared to state-of-the-art accelerator PipeZK, Exa achieves up to$20.68 \times $ and$4.58 \times $ improvement for NTT and MSM, respectively, while occupying a chip area that is$2.6 \times $ smaller. For end-to-end applications, Exa can achieve a speedup of$6.5 \times $ on average than software implementation.- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (2) , 593-605
Exa: A Unified Architecture for Multi-Scalar Multiplication and Polynomial Computation in Zero-Knowledge Proof
Zero-knowledge proof (ZKP) is a cryptographic protocol that allows a prover to convince verifiers that a computation is correctly executed without disclosing the prover’s secret. ZKP has been deployed in various privacy-preserving applications. However, the proof generation is notably inefficient on general-purpose processors. Multi-scalar multiplication (MSM) and polynomial computation (POLY), including number theoretic transform (NTT), are two of the most computation-intensive parts in proof generation. Recently, separate accelerators for MSM and POLY (mostly NTT) have been proposed. Unfortunately, separate accelerators may have poor resource utilization since MSM and POLY cannot be performed concurrently. To address this challenge, we propose Exa, a unified hardware architecture for MSM and POLY. It enables MSM and POLY to share computational resources and memory resources through decoupling dataflow control, computation, and memory. We design a novel unified functional unit (FU) array that can support both POLY operation and point addition (PADD) for MSM. In addition, we propose a 3-D NTT implementation and an adaptive MSM implementation on the FU array using a domain-specific instruction set architecture (ISA). Exa is scalable and can be efficiently orchestrated by our proposed runtime system. Compared with the separate accelerators for MSM and NTT, Exa occupies 47% less chip area. Compared to state-of-the-art accelerator PipeZK, Exa achieves up to$20.68 \times $ and$4.58 \times $ improvement for NTT and MSM, respectively, while occupying a chip area that is$2.6 \times $ smaller. For end-to-end applications, Exa can achieve a speedup of$6.5 \times $ on average than software implementation.- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 35 (12) , 2297-2314
Acceleration of Multi-Body Molecular Dynamics With Customized Parallel Dataflow
FPGAs are drawing increasing attention in resolving molecular dynamics (MD) problems, and have already been applied in problems such as two-body potentials, force fields composed of these potentials, etc. Competitive performance is obtained compared with traditional counterparts such as CPUs and GPUs. However, as far as we know, FPGA solutions for more complex and real-world MD problems, such as multi-body potentials, are seldom to be seen. This work explores the prospects of state-of-the-art FPGAs in accelerating multi-body potential. An FPGA-based accelerator with customized parallel dataflow that features multi-body potential computation, motion update, and internode communication is designed. Major contributions include: (1) parallelization applied at different levels of the accelerator; (2) an optimized dataflow mixing atom-level pipeline and cell-level pipeline to achieve high throughput; (3) a mixed-precision method using different precision at different stages of simulations; and (4) a communication-efficient method for internode communication. Experiments show that, our single-node accelerator is over 2.7× faster than an 8-core CPU design, performing 20.501 ns/day on a 55,296-atom system for the Tersoff simulation. Regarding power efficiency, our accelerator is 28.9× higher than I7-11700 and 4.8× higher than RTX 3090 when running the same test case.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 35 (12) , 2297-2314
Acceleration of Multi-Body Molecular Dynamics With Customized Parallel Dataflow
FPGAs are drawing increasing attention in resolving molecular dynamics (MD) problems, and have already been applied in problems such as two-body potentials, force fields composed of these potentials, etc. Competitive performance is obtained compared with traditional counterparts such as CPUs and GPUs. However, as far as we know, FPGA solutions for more complex and real-world MD problems, such as multi-body potentials, are seldom to be seen. This work explores the prospects of state-of-the-art FPGAs in accelerating multi-body potential. An FPGA-based accelerator with customized parallel dataflow that features multi-body potential computation, motion update, and internode communication is designed. Major contributions include: (1) parallelization applied at different levels of the accelerator; (2) an optimized dataflow mixing atom-level pipeline and cell-level pipeline to achieve high throughput; (3) a mixed-precision method using different precision at different stages of simulations; and (4) a communication-efficient method for internode communication. Experiments show that, our single-node accelerator is over 2.7× faster than an 8-core CPU design, performing 20.501 ns/day on a 55,296-atom system for the Tersoff simulation. Regarding power efficiency, our accelerator is 28.9× higher than I7-11700 and 4.8× higher than RTX 3090 when running the same test case.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
MSMAC: Accelerating Multi-Scalar Multiplication for Zero-Knowledge Proof
Multi-scalar multiplication (MSM) is the most computation-intensive part in proof generation of Zero-knowledge proof (ZKP). In this paper, we propose MSMAC, an FPGA accelerator for large-scale MSM. MSMAC adopts a specially designed Instruction Set Architecture (ISA) for MSM and optimizes pipelined Point Addition Unit (PAU) with hybrid Karatsuba multiplier. Moreover, a runtime system is proposed to split MSM tasks with the optimal sub-task size and orchestrate execution of Processing Elements (PEs). Experimental results show that MSMAC achieves up to 328X and 1.96X speedups compared to the state-of-the-art implementation on CPU (one core) and GPU, respectively, outperforming the state-of-the-art ASIC accelerator by 1.79X. On 4 FPGAs, MSMAC performs 1,261X faster than a single CPU core.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessMSMAC: Accelerating Multi-Scalar Multiplication for Zero-Knowledge Proof
Multi-scalar multiplication (MSM) is the most computation-intensive part in proof generation of Zero-knowledge proof (ZKP). In this paper, we propose MSMAC, an FPGA accelerator for large-scale MSM. MSMAC adopts a specially designed Instruction Set Architecture (ISA) for MSM and optimizes pipelined Point Addition Unit (PAU) with hybrid Karatsuba multiplier. Moreover, a runtime system is proposed to split MSM tasks with the optimal sub-task size and orchestrate execution of Processing Elements (PEs). Experimental results show that MSMAC achieves up to 328X and 1.96X speedups compared to the state-of-the-art implementation on CPU (one core) and GPU, respectively, outperforming the state-of-the-art ASIC accelerator by 1.79X. On 4 FPGAs, MSMAC performs 1,261X faster than a single CPU core.
- Open Access
- 1 September 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 16 (4) , 1-30
Topgun: An ECC Accelerator for Private Set Intersection
Elliptic Curve Cryptography (ECC), one of the most widely used asymmetric cryptographic algorithms, has been deployed in Transport Layer Security (TLS) protocol, blockchain, secure multiparty computation, and so on. As one of the most secure ECC curves, Curve25519 is employed by some secure protocols, such as TLS 1.3 and Diffie-Hellman Private Set Intersection (DH-PSI) protocol. High-performance implementation of ECC is required, especially for the DH-PSI protocol used in privacy-preserving platform. Point multiplication, the chief cryptographic primitive in ECC, is computationally expensive. To improve the performance of DH-PSI protocol, we propose Topgun, a novel and high-performance hardware architecture for point multiplication over Curve25519. The proposed architecture features a pipelined Finite-field Arithmetic Unit and a simple and highly efficient instruction set architecture. Compared to the best existing work on Xilinx Zynq 7000 series FPGA, our implementation with one Processing Element can achieve 3.14× speedup on the same device. To the best of our knowledge, our implementation appears to be the fastest among the state-of-the-art works. We also have implemented our architecture consisting of 4 Compute Groups, each with 16 PEs, on an Intel Agilex AGF027 FPGA. The measured performance of 4.48 Mops/s is achieved at the cost of 86 Watts power, which is the record-setting performance for point multiplication over Curve25519 on FPGAs.
- 1 September 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 16 (4) , 1-30
Open AccessTopgun: An ECC Accelerator for Private Set Intersection
Elliptic Curve Cryptography (ECC), one of the most widely used asymmetric cryptographic algorithms, has been deployed in Transport Layer Security (TLS) protocol, blockchain, secure multiparty computation, and so on. As one of the most secure ECC curves, Curve25519 is employed by some secure protocols, such as TLS 1.3 and Diffie-Hellman Private Set Intersection (DH-PSI) protocol. High-performance implementation of ECC is required, especially for the DH-PSI protocol used in privacy-preserving platform. Point multiplication, the chief cryptographic primitive in ECC, is computationally expensive. To improve the performance of DH-PSI protocol, we propose Topgun, a novel and high-performance hardware architecture for point multiplication over Curve25519. The proposed architecture features a pipelined Finite-field Arithmetic Unit and a simple and highly efficient instruction set architecture. Compared to the best existing work on Xilinx Zynq 7000 series FPGA, our implementation with one Processing Element can achieve 3.14× speedup on the same device. To the best of our knowledge, our implementation appears to be the fastest among the state-of-the-art works. We also have implemented our architecture consisting of 4 Compute Groups, each with 16 PEs, on an Intel Agilex AGF027 FPGA. The measured performance of 4.48 Mops/s is achieved at the cost of 86 Watts power, which is the record-setting performance for point multiplication over Curve25519 on FPGAs.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 43 (5) , 88-96
E-Booster: A Field-Programmable Gate Array-Based Accelerator for Secure Tree Boosting Using Additively Homomorphic Encryption
Tree boosting is a widely used machine learning model in many financial fields. Additively homomorphic encryption is an important cryptographic tool used for secure tree boosting in the setting of federated learning. However, homomorphic encryption includes computationally expensive operations. Current frameworks for secure tree boosting are extremely slow. In this article, we propose E-Booster, a novel accelerator for the training of secure tree boosting. E-Booster can fully exploit algorithmic superiority and architectural optimization to achieve unprecedented performance and to address the obstacle in deploying additively homomorphic encryption in industrial applications. E-Booster has been implemented on an Intel Agilex FPGA and evaluated on four public datasets. It achieves 5.1-7.8× speedup over a CPU with 32 threads for secure tree boosting. To the best of our knowledge, E-Booster is the first additively homomorphic encryption accelerator that can be applied to industrial secure tree boosting.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 43 (5) , 88-96
E-Booster: A Field-Programmable Gate Array-Based Accelerator for Secure Tree Boosting Using Additively Homomorphic Encryption
Tree boosting is a widely used machine learning model in many financial fields. Additively homomorphic encryption is an important cryptographic tool used for secure tree boosting in the setting of federated learning. However, homomorphic encryption includes computationally expensive operations. Current frameworks for secure tree boosting are extremely slow. In this article, we propose E-Booster, a novel accelerator for the training of secure tree boosting. E-Booster can fully exploit algorithmic superiority and architectural optimization to achieve unprecedented performance and to address the obstacle in deploying additively homomorphic encryption in industrial applications. E-Booster has been implemented on an Intel Agilex FPGA and evaluated on four public datasets. It achieves 5.1-7.8× speedup over a CPU with 32 threads for secure tree boosting. To the best of our knowledge, E-Booster is the first additively homomorphic encryption accelerator that can be applied to industrial secure tree boosting.