A Survey of Neural Network Variational Monte Carlo from a Computing Workload Characterization Perspective

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Zhengze, Ding, Xuanzhe, Lou, Yuyang, Cheng, Lixue, Li, Chaojian
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912977259593728
author Xiao, Zhengze
Ding, Xuanzhe
Lou, Yuyang
Cheng, Lixue
Li, Chaojian
author_facet Xiao, Zhengze
Ding, Xuanzhe
Lou, Yuyang
Cheng, Lixue
Li, Chaojian
contents Neural Network Variational Monte Carlo (NNVMC) has emerged as a promising paradigm for solving quantum many-body problems by combining variational Monte Carlo with expressive neural-network wave-function ansätze. Although NNVMC can achieve competitive accuracy with favorable asymptotic scaling, practical deployment remains limited by high runtime and memory cost on modern graphics processing units (GPUs). Compared with language and vision workloads, NNVMC execution is shaped by physics-specific stages, including Markov-Chain Monte Carlo sampling, wave-function construction, and derivative/Laplacian evaluation, which produce heterogeneous kernel behavior and nontrivial bottlenecks. This paper provides a workload-oriented survey and empirical GPU characterization of four representative ansätze: PauliNet, FermiNet, Psiformer, and Orbformer. Using a unified profiling protocol, we analyze model-level runtime and memory trends and kernel-level behavior through family breakdown, arithmetic intensity, roofline positioning, and hardware utilization counters. The results show that end-to-end performance is often constrained by low-intensity elementwise and data-movement kernels, while the compute/memory balance varies substantially across ansätze and stages. Based on these findings, we discuss algorithm--hardware co-design implications for scalable NNVMC systems, including phase-aware scheduling, memory-centric optimization, and heterogeneous acceleration.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18126
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Survey of Neural Network Variational Monte Carlo from a Computing Workload Characterization Perspective
Xiao, Zhengze
Ding, Xuanzhe
Lou, Yuyang
Cheng, Lixue
Li, Chaojian
Hardware Architecture
Chemical Physics
Neural Network Variational Monte Carlo (NNVMC) has emerged as a promising paradigm for solving quantum many-body problems by combining variational Monte Carlo with expressive neural-network wave-function ansätze. Although NNVMC can achieve competitive accuracy with favorable asymptotic scaling, practical deployment remains limited by high runtime and memory cost on modern graphics processing units (GPUs). Compared with language and vision workloads, NNVMC execution is shaped by physics-specific stages, including Markov-Chain Monte Carlo sampling, wave-function construction, and derivative/Laplacian evaluation, which produce heterogeneous kernel behavior and nontrivial bottlenecks. This paper provides a workload-oriented survey and empirical GPU characterization of four representative ansätze: PauliNet, FermiNet, Psiformer, and Orbformer. Using a unified profiling protocol, we analyze model-level runtime and memory trends and kernel-level behavior through family breakdown, arithmetic intensity, roofline positioning, and hardware utilization counters. The results show that end-to-end performance is often constrained by low-intensity elementwise and data-movement kernels, while the compute/memory balance varies substantially across ansätze and stages. Based on these findings, we discuss algorithm--hardware co-design implications for scalable NNVMC systems, including phase-aware scheduling, memory-centric optimization, and heterogeneous acceleration.
title A Survey of Neural Network Variational Monte Carlo from a Computing Workload Characterization Perspective
topic Hardware Architecture
Chemical Physics
url https://arxiv.org/abs/2603.18126