VQCSim:何时编译一次的态矢量模拟优于通用量子框架?
VQCSim: When Does Compile-Once Statevector Simulation Beat Generic Quantum Frameworks?
浏览论文内容
中文总结 AI 辅助
研究混合量子-经典机器学习工作流中编译一次的态矢量模拟何时优于通用量子框架,通过VQCSim实现,它有原生自动求导,在MQT Bench研究及多GPU评估中有加速效果,推导硬件感知图并发布开源选择器,助力QML设计循环选模拟器。
中文摘要 AI 辅助
混合量子-经典机器学习工作流程在训练和模型探索期间会反复评估许多小型参数化电路。在这种情况下,框架调度和编排开销通常主导运行时。先前的模拟器加速了执行,但对于静态变分电路,何时进行一次编译专门化是正确选择的问题仍然存在。我们使用VQCSim回答了这个问题,它是一个具有原生自动求导的一次编译、PyTorch原生的态矢量执行路径。在系统的MQT Bench研究中,VQCSim编译了所有测试的静态电路并提供了87.7%的端到端语义验证。在一个五GPU评估集上,VQCSim在原生推理中实现了4.49倍的合并中位数加速,在原生训练中实现了26.78倍的加速,同时在匹配的有限差分训练下保持3.31倍的优势。消融实验确定原生自动求导是加速的主要来源(27.6倍),一次编译缓存和批量矢量化带来了额外的收益。加速是以更高的GPU内存(VQCSim在高端受内存限制)换取更低的运行时。我们推导了一个硬件感知状态图,并发布了vqcsim-oracle,这是一个开源后端选择器,具有91.1%-97.7%的top-1一致性(包括跨GPU传输),能够在QML设计循环中自动选择模拟器。
英文摘要
Hybrid quantum-classical machine learning workflows repeatedly evaluate many small parametrized circuits during training and model exploration. In this regime, framework dispatch and orchestration overhead often dominate runtime. Prior simulators accelerate execution but leave open the question of when compile-once specialization is the right choice for static variational circuits. We answer this question with VQCSim, a compile-once, PyTorch-native statevector execution path with native autograd. In a systematic MQT Bench study, VQCSim compiles all tested static circuits and provides 87.7% end-to-end semantic validation. Across a five-GPU evaluation set, VQCSim delivers pooled median speedups of 4.49x for native inference and 26.78x for native training, while retaining a 3.31x advantage under matched finite-difference training. Ablation identifies native autograd as the dominant source of acceleration (27.6x), with compile-once caching and batch vectorization contributing additional gains. The speedup trades higher GPU memory (VQCSim is memory-limited at the high end) for lower runtime. We derive a hardware-aware regime map and release vqcsim-oracle, an open-source backend selector with 91.1%-97.7% top-1 agreement (including cross-GPU transfers), enabling automatic simulator selection in QML design loops.
发表机构
- Brno University of Technology(布拉格技术大学)
- New York University Abu Dhabi(纽约大学阿布扎克分校)
机构由 AI 辅助整理,请以论文原文为准。