A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection with Neural Network Quantum States
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910168275484672 |
|---|---|
| author | Sun, Daran Kan, Bowen Long, Haoquan Zhao, Hairui Li, Haoxu Liu, Yicheng Zhou, Pengyu Feng, Ankang Huang, Wenjing Gu, Yida Li, Zhenyu Shang, Honghui Zhang, Yunquan Tao, Dingwen Sun, Ninghui Tan, Guangming |
| author_facet | Sun, Daran Kan, Bowen Long, Haoquan Zhao, Hairui Li, Haoxu Liu, Yicheng Zhou, Pengyu Feng, Ankang Huang, Wenjing Gu, Yida Li, Zhenyu Shang, Honghui Zhang, Yunquan Tao, Dingwen Sun, Ninghui Tan, Guangming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15768 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection with Neural Network Quantum States Sun, Daran Kan, Bowen Long, Haoquan Zhao, Hairui Li, Haoxu Liu, Yicheng Zhou, Pengyu Feng, Ankang Huang, Wenjing Gu, Yida Li, Zhenyu Shang, Honghui Zhang, Yunquan Tao, Dingwen Sun, Ninghui Tan, Guangming Distributed, Parallel, and Cluster Computing Artificial Intelligence Computational Engineering, Finance, and Science 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. |
| title | A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection with Neural Network Quantum States |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2604.15768 |