Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2604.15768

A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection with Neural Network Quantum States

Daran Sun, Bowen Kan, Haoquan Long, Hairui Zhao, Haoxu Li, Yicheng Liu, Pengyu Zhou, Ankang Feng, Wenjing Huang, Yida Gu, Zhenyu Li, Honghui Shang, Yunquan Zhang, Dingwen Tao, Ninghui Sun, Guangming Tan

Published Apr 17, 2026• 0 citations
arXivHTMLPDF

Abstract

AI-driven methods have demonstrated considerable success in tackling the central challenge of accurately solving the Schrödinger equation for complex many-body systems. Among neural network quantum state (NNQS) approaches, the NNQS-SCI (Selected Configuration Interaction) method stands out as a state-of-the-art technique, recognized for its high accuracy and scalability. However, its application to larger systems is severely constrained by a hybrid CPU-GPU architecture. Specifically, centralized CPU-based global de-duplication creates a severe scalability barrier due to communication bottlenecks, while host-resident coupled-configuration generation induces prohibitive computational overheads. We introduce QiankunNet-cuSCI, a fully GPU-accelerated SCI framework designed to overcome these bottlenecks. It first integrates a distributed, load-balanced global de-duplication algorithm to minimize redundancy and communication overhead at scale. To address compute limitations, it employs specialized, fine-grained CUDA kernels for exact coupled configuration generation. Finally, to break the single-GPU memory barrier exposed by this full acceleration, it incorporates a GPU memory-centric runtime featuring GPU-side pooling, streaming mini-batches, and overlapped offloading. This design enables much larger configuration spaces and shifts the bottleneck from host-side limitations back to on-device inference. Our evaluation demonstrates that our work fundamentally expands the scale of solvable problems. On an NVIDIA A100 cluster with 64 GPUs, our work achieves up to 2.32X end-to-end speedup over the highly-optimized NNQS-SCI baseline while preserving the same chemical accuracy. Furthermore, it demonstrates excellent distributed performance, maintaining over 90% parallel efficiency in strong scaling tests.

DOI
10.48550/arxiv.2604.15768

Related papers

A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection with Neural Network Quantum States

Daran Sun, Bowen Kan, Haoquan Long +13 more

AI-driven methods have demonstrated considerable success in tackling the central challenge of accurately solving the Schrödinger equation for complex many-body systems. Among neural network quantum state (NNQS) approaches, the NNQS-SCI (Selected Configuration Interaction) method stands out as a state-of-the-art technique, recognized for its high accuracy and scalability. However, its application to larger systems is severely constrained by a hybrid CPU-GPU architecture. Specifically, centralized CPU-based global de-duplication creates a severe scalability barrier due to communication bottlenecks, while host-resident coupled-configuration generation induces prohibitive computational overheads. We introduce QiankunNet-cuSCI, a fully GPU-accelerated SCI framework designed to overcome these bottlenecks. It first integrates a distributed, load-balanced global de-duplication algorithm to minimize redundancy and communication overhead at scale. To address compute limitations, it employs specialized, fine-grained CUDA kernels for exact coupled configuration generation. Finally, to break the single-GPU memory barrier exposed by this full acceleration, it incorporates a GPU memory-centric runtime featuring GPU-side pooling, streaming mini-batches, and overlapped offloading. This design enables much larger configuration spaces and shifts the bottleneck from host-side limitations back to on-device inference. Our evaluation demonstrates that our work fundamentally expands the scale of solvable problems. On an NVIDIA A100 cluster with 64 GPUs, our work achieves up to 2.32 × end-to-end speedup over the highly-optimized NNQS-SCI baseline while preserving the same chemical accuracy. Furthermore, it demonstrates excellent distributed performance, maintaining over 90% parallel efficiency in strong scaling tests.

ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC)•Jul 11, 2026•0 citations

NNQS-SCI: Tackling Trillion-Dimensional Hilbert Space with Adaptive Neural Network Quantum States

Bowen Kan, Yumeng Zhou, Daiyou Xie +3 more

Neural Network Quantum States (NNQS) offer a powerful variational Monte Carlo (VMC) approach for quantum many-body problems, balancing polynomial scaling with high expressive power. However, scaling NNQS to large chemical systems faces challenges in preserving accuracy with exact energy and managing vast configurations efficiently. In this work, we introduce NNQS-SCI, a high-performance Selected Configuration Interaction (SCI) based NNQS method designed to overcome these limitations. NNQS-SCI employs highly parallelized Slater-Condon rules for fast local energy evaluations, avoiding accuracy loss, while its adaptive SCI engine dynamically manages billions of configurations without space explosion or arbitrary cutoffs that plague other NNQS-CI approaches. Optimized for extreme scalability via multi-level parallelism and memory compression, NNQS-SCI successfully simulates systems up to 152 spin orbitals, tackling Hilbert space dimensions exceeding 1014 and demonstrating significant advances in scale and efficiency. NNQS-SCI thus provides a robust and scalable path towards high-accuracy quantum chemistry on high-performance computing platforms.

International Conference for High Performance Computing, Networking, Storage and Analysis (SC)•Nov 12, 2025•5 citations

Accelerating Many-Body Quantum Chemistry via Generative Transformer-Enhanced Configuration Interaction

Bowen Kan, Honghui Shang

Quantum many-body calculations are fundamentally limited by the exponential growth of the configuration space, making accurate treatment of strongly correlated systems computationally prohibitive. Here we present the Generative Transformer Neural Network Selected Configuration Interaction (GTNN-SCI), a Transformer-based machine learning approach that generatively samples important configurations to accelerate many-body quantum chemistry calculations. By leveraging the Transformer architecture’s self-attention mechanism to capture long-range electron correlations, GTNN-SCI achieves up to 10× speedup compared to state-of-the-art neural network methods while maintaining high accuracy. We demonstrate the efficacy of GTNN-SCI by calculating correlation and binding energies for representative molecules including N 2, H 2 O, and C 2 using both Gaussian (cc-pVDZ) and plane-wave basis sets, achieving faster convergence and lower energies than previously reported neural network-based selected CI techniques. Most significantly, our generative approach identifies higher-order excitations missed by conventional coupling schemes, yielding lower variational energies than established methods including heat-bath CI. This capability enables GTNN-SCI to accurately treat the strongly correlated [Fe 2 S 2 (SCH 3 ) 4 ] 2– ([2Fe–2S]) cluster system, achieving ground-state energies within chemical accuracy of DMRG benchmarks, whereas conventional selected CI methods have failed on this system. The GTNN-SCI method thus combines modern deep learning with high-performance electronic structure computation, providing an efficient and precise avenue for solving the electronic Schrödinger equation in challenging molecular systems.

Journal of Chemical Theory and Computation•Nov 24, 2025•2 citations

An Iterative Dual-Channel Neural Quantum State Algorithm for Selected Configuration Interaction

Jen-Yu Chang, Yi-Chun Chang, Yu-Jui Lin +6 more

Accurately solving the electronic Schrödinger equation for strongly correlated systems remains a central challenge in quantum chemistry, where the exponential growth of configuration space limits the applicability of exact methods. Selected Configuration Interaction (SCI) algorithms address this challenge by adaptively constructing compact determinantal expansions, yet their efficiency depends critically on the quality of the sampling strategy used to identify chemically important configurations. Here we introduce the Handover Iterative Neural Quantum State (HI-NQS) algorithm, which embeds a classically trained autoregressive Transformer neural quantum state within the iterative sample--diagonalize--update framework of Sample-Based Quantum Diagonalization. A dual-channel Transformer architecture with explicit spin-up/spin-down cross-attention encodes fermionic spin structure as an architectural inductive bias, enabling expressive and physically informed wavefunction representations. After each subspace diagonalization, the resulting eigenvector is distilled back into the network through a factorized spin-marginal teacher signal, establishing a closed feedback loop between generative sampling and exact diagonalization. Benchmarks across a range of small molecules and a systematic nitrogen active-space series demonstrate that HI-NQS achieves chemical accuracy on all systems tested, with determinant-count scaling substantially more favorable than conventional CIPSI-based SCI for all but the smallest active spaces. All calculations are performed on GPU hardware without quantum computing resources, establishing HI-NQS as an efficient and scalable purely classical approach to the selected configuration interaction problem.

physics.chem-phCross-listedarXiv:2606.26760•Jun 26, 2026•0 citations

Fully GPU-Accelerated Full Configuration Interaction for Exact Molecular Ground-state Energy Calculation

Hong Gao, Yasuaki Ito, Koji Nakano +3 more

Full configuration interaction (FCI) serves as a benchmark tool for evaluating the accuracy of approximate quantum chemical methods. However, its exponential computational cost limits its practical use. The inherently parallel and compute-intensive nature of matrix and vector operations in FCI is well-suited for acceleration on modern GPU architectures. Despite this potential, prior research has only focused on accelerating the matrix and vector multiplication, thus failing to fully exploit the power of GPUs. In this paper, we present a fully GPU-accelerated FCI implementation that uses a CUDA-enabled GPU for the entire computational workflow, achieving end-to-end acceleration. Our implementation incorporates and refines advanced optimization strategies from previous studies, while crucially eliminating redundant computational steps and minimizing CPU-GPU data transfers. To facilitate broad usability and integration, we offer both Python- and C-based implementations. Our C implementation achieves up to a 35.4× speedup over a multithreaded CPU implementation and up to a 15.9× speedup over the current leading GPU-based implementation, respectively. Our Python implementation also delivers substantial acceleration, reaching up to 18.9× and 8.7× speedups over CPU and prior GPU implementations, respectively.

International Symposium on Computing and Networking•Nov 25, 2025•0 citations

NNQS-Transformer: an Efficient and Scalable Neural Network Quantum States Approach for Ab initio Quantum Chemistry

Yangjun Wu, Chu Guo, Yi Fan +2 more

Neural network quantum state (NNQS) has emerged as a promising candidate for quantum many-body problems, but its practical applications are often hindered by the high cost of sampling and local energy calculation. We develop a high-performance NNQS method for ab initio electronic structure calculations. The major innovations include: (1) A transformer based architecture as the quantum wave function ansatz; (2) A data-centric parallelization scheme for the variational Monte Carlo (VMC) algorithm which preserves data locality and well adapts for different computing architectures; (3) A parallel batch sampling strategy which reduces the sampling cost and achieves good load balance; (4) A parallel local energy evaluation scheme which is both memory and computationally efficient; (5) Study of real chemical systems demonstrates both the superior accuracy of our method compared to state-of-the-art and the strong and weak scalability for large molecular systems with up to 120 spin orbitals.

International Conference for High Performance Computing, Networking, Storage and Analysis (SC)•Oct 30, 2023•34 citations
AI-driven methods have demonstrated considerable success in tackling the central challenge of accurately solving the Schrödinger equation for complex many-body systems. Among neural network quantum state (NNQS) approaches, the NNQS-SCI (Selected Configuration Interaction) method stands out as a state-of-the-art technique, recognized for its high accuracy and scalability. However, its application to larger systems is severely constrained by a hybrid CPU-GPU architecture. Specifically, centralized CPU-based global de-duplication creates a severe scalability barrier due to communication bottlenecks, while host-resident coupled-configuration generation induces prohibitive computational overheads. We introduce QiankunNet-cuSCI, a fully GPU-accelerated SCI framework designed to overcome these bottlenecks. It first integrates a distributed, load-balanced global de-duplication algorithm to minimize redundancy and communication overhead at scale. To address compute limitations, it employs specialized, fine-grained CUDA kernels for exact coupled configuration generation. Finally, to break the single-GPU memory barrier exposed by this full acceleration, it incorporates a GPU memory-centric runtime featuring GPU-side pooling, streaming mini-batches, and overlapped offloading. This design enables much larger configuration spaces and shifts the bottleneck from host-side limitations back to on-device inference. Our evaluation demonstrates that our work fundamentally expands the scale of solvable problems. On an NVIDIA A100 cluster with 64 GPUs, our work achieves up to 2.32X end-to-end speedup over the highly-optimized NNQS-SCI baseline while preserving the same chemical accuracy. Furthermore, it demonstrates excellent distributed performance, maintaining over 90% parallel efficiency in strong scaling tests.
AI-driven methods have demonstrated considerable success in tackling the central challenge of accurately solving the Schrödinger equation for complex many-body systems. Among neural network quantum state (NNQS) approaches, the NNQS-SCI (Selected Configuration Interaction) method stands out as a state-of-the-art technique, recognized for its high accuracy and scalability. However, its application to larger systems is severely constrained by a hybrid CPU-GPU architecture. Specifically, centralized CPU-based global de-duplication creates a severe scalability barrier due to communication bottlenecks, while host-resident coupled-configuration generation induces prohibitive computational overheads. We introduce QiankunNet-cuSCI, a fully GPU-accelerated SCI framework designed to overcome these bottlenecks. It first integrates a distributed, load-balanced global de-duplication algorithm to minimize redundancy and communication overhead at scale. To address compute limitations, it employs specialized, fine-grained CUDA kernels for exact coupled configuration generation. Finally, to break the single-GPU memory barrier exposed by this full acceleration, it incorporates a GPU memory-centric runtime featuring GPU-side pooling, streaming mini-batches, and overlapped offloading. This design enables much larger configuration spaces and shifts the bottleneck from host-side limitations back to on-device inference. Our evaluation demonstrates that our work fundamentally expands the scale of solvable problems. On an NVIDIA A100 cluster with 64 GPUs, our work achieves up to 2.32 × end-to-end speedup over the highly-optimized NNQS-SCI baseline while preserving the same chemical accuracy. Furthermore, it demonstrates excellent distributed performance, maintaining over 90% parallel efficiency in strong scaling tests.
Neural Network Quantum States (NNQS) offer a powerful variational Monte Carlo (VMC) approach for quantum many-body problems, balancing polynomial scaling with high expressive power. However, scaling NNQS to large chemical systems faces challenges in preserving accuracy with exact energy and managing vast configurations efficiently. In this work, we introduce NNQS-SCI, a high-performance Selected Configuration Interaction (SCI) based NNQS method designed to overcome these limitations. NNQS-SCI employs highly parallelized Slater-Condon rules for fast local energy evaluations, avoiding accuracy loss, while its adaptive SCI engine dynamically manages billions of configurations without space explosion or arbitrary cutoffs that plague other NNQS-CI approaches. Optimized for extreme scalability via multi-level parallelism and memory compression, NNQS-SCI successfully simulates systems up to 152 spin orbitals, tackling Hilbert space dimensions exceeding 1014 and demonstrating significant advances in scale and efficiency. NNQS-SCI thus provides a robust and scalable path towards high-accuracy quantum chemistry on high-performance computing platforms.
Quantum many-body calculations are fundamentally limited by the exponential growth of the configuration space, making accurate treatment of strongly correlated systems computationally prohibitive. Here we present the Generative Transformer Neural Network Selected Configuration Interaction (GTNN-SCI), a Transformer-based machine learning approach that generatively samples important configurations to accelerate many-body quantum chemistry calculations. By leveraging the Transformer architecture’s self-attention mechanism to capture long-range electron correlations, GTNN-SCI achieves up to 10× speedup compared to state-of-the-art neural network methods while maintaining high accuracy. We demonstrate the efficacy of GTNN-SCI by calculating correlation and binding energies for representative molecules including N 2, H 2 O, and C 2 using both Gaussian (cc-pVDZ) and plane-wave basis sets, achieving faster convergence and lower energies than previously reported neural network-based selected CI techniques. Most significantly, our generative approach identifies higher-order excitations missed by conventional coupling schemes, yielding lower variational energies than established methods including heat-bath CI. This capability enables GTNN-SCI to accurately treat the strongly correlated [Fe 2 S 2 (SCH 3 ) 4 ] 2– ([2Fe–2S]) cluster system, achieving ground-state energies within chemical accuracy of DMRG benchmarks, whereas conventional selected CI methods have failed on this system. The GTNN-SCI method thus combines modern deep learning with high-performance electronic structure computation, providing an efficient and precise avenue for solving the electronic Schrödinger equation in challenging molecular systems.
Accurately solving the electronic Schrödinger equation for strongly correlated systems remains a central challenge in quantum chemistry, where the exponential growth of configuration space limits the applicability of exact methods. Selected Configuration Interaction (SCI) algorithms address this challenge by adaptively constructing compact determinantal expansions, yet their efficiency depends critically on the quality of the sampling strategy used to identify chemically important configurations. Here we introduce the Handover Iterative Neural Quantum State (HI-NQS) algorithm, which embeds a classically trained autoregressive Transformer neural quantum state within the iterative sample--diagonalize--update framework of Sample-Based Quantum Diagonalization. A dual-channel Transformer architecture with explicit spin-up/spin-down cross-attention encodes fermionic spin structure as an architectural inductive bias, enabling expressive and physically informed wavefunction representations. After each subspace diagonalization, the resulting eigenvector is distilled back into the network through a factorized spin-marginal teacher signal, establishing a closed feedback loop between generative sampling and exact diagonalization. Benchmarks across a range of small molecules and a systematic nitrogen active-space series demonstrate that HI-NQS achieves chemical accuracy on all systems tested, with determinant-count scaling substantially more favorable than conventional CIPSI-based SCI for all but the smallest active spaces. All calculations are performed on GPU hardware without quantum computing resources, establishing HI-NQS as an efficient and scalable purely classical approach to the selected configuration interaction problem.
Full configuration interaction (FCI) serves as a benchmark tool for evaluating the accuracy of approximate quantum chemical methods. However, its exponential computational cost limits its practical use. The inherently parallel and compute-intensive nature of matrix and vector operations in FCI is well-suited for acceleration on modern GPU architectures. Despite this potential, prior research has only focused on accelerating the matrix and vector multiplication, thus failing to fully exploit the power of GPUs. In this paper, we present a fully GPU-accelerated FCI implementation that uses a CUDA-enabled GPU for the entire computational workflow, achieving end-to-end acceleration. Our implementation incorporates and refines advanced optimization strategies from previous studies, while crucially eliminating redundant computational steps and minimizing CPU-GPU data transfers. To facilitate broad usability and integration, we offer both Python- and C-based implementations. Our C implementation achieves up to a 35.4× speedup over a multithreaded CPU implementation and up to a 15.9× speedup over the current leading GPU-based implementation, respectively. Our Python implementation also delivers substantial acceleration, reaching up to 18.9× and 8.7× speedups over CPU and prior GPU implementations, respectively.
Neural network quantum state (NNQS) has emerged as a promising candidate for quantum many-body problems, but its practical applications are often hindered by the high cost of sampling and local energy calculation. We develop a high-performance NNQS method for ab initio electronic structure calculations. The major innovations include: (1) A transformer based architecture as the quantum wave function ansatz; (2) A data-centric parallelization scheme for the variational Monte Carlo (VMC) algorithm which preserves data locality and well adapts for different computing architectures; (3) A parallel batch sampling strategy which reduces the sampling cost and achieves good load balance; (4) A parallel local energy evaluation scheme which is both memory and computationally efficient; (5) Study of real chemical systems demonstrates both the superior accuracy of our method compared to state-of-the-art and the strong and weak scalability for large molecular systems with up to 120 spin orbitals.