arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.07346cs.LGcs.CE
收藏

INSIGHT:利用自回归Transformer的模拟电路通用神经仿真器

INSIGHT: Universal Neural Simulator for Analog Circuits Harnessing Autoregressive Transformers

The University of Texas at Austin(德克萨斯大学奥斯汀分校);Samsung Advanced Institute of Technology(三星先进技术研究院)

Souradip Poddar, Youngmin Oh, Yao Lai, Hanqing Zhu, Bosun Hwang, David Z. Pan

AI总结:

本文提出INSIGHT,一个基于自回归Transformer的GPU通用神经仿真器,能以微秒级推理准确预测模拟电路性能,并作为代理模型将尺寸调整所需实时仿真降至20次以下,成本降低100-1000倍。

摘要:

模拟前端设计高度依赖专业人工经验和昂贵的试错仿真,这促使了许多先前关于模拟设计自动化的工作。然而,由于SPICE仿真耗时较长,对庞大而复杂的设计空间进行高效且有效的探索仍然受到限制,这使得有效的设计自动化成为一项具有挑战性的工作。在本文中,我们提出了INSIGHT,这是一个GPU驱动、技术无关且高效的通用神经仿真器,用于模拟前端设计自动化回路。INSIGHT能够以仅几微秒的推理时间准确预测跨多种工艺的模拟电路性能指标。值得注意的是,其自回归能力使INSIGHT能够利用成本较低的性能指标信息,准确预测仿真成本高昂的关键瞬态规格。低成本和低保真度特性使INSIGHT成为模拟前端优化框架中标准仿真器的良好替代品。INSIGHT与任何优化框架兼容,通过复杂的离线学习和自适应技术,促进增强的设计空间探索,以提高样本效率。我们的实验表明,INSIGHT-M是一个基于模型的批量强化学习尺寸调整框架,以INSIGHT作为精确代理,仅需少于20次实时仿真,仿真成本降低100-1000倍,并且相比现有尺寸调整方法具有显著加速。

英文摘要:

Analog front-end design heavily relies on specialized human expertise and costly trial-and-error simulations, which motivated many prior works on analog design automation. However, efficient and effective exploration of the vast and complex design space remains constrained by the time-consuming nature of SPICE simulations, making effective design automation a challenging endeavor. In this paper, we introduce INSIGHT, a GPU-powered, technology-agnostic, effective universal neural simulator in the analog front-end design automation loop. INSIGHT accurately predicts the performance metrics of analog circuits across various technologies with just a few microseconds of inference time. Notably, its autoregressive capabilities enable INSIGHT to accurately predict simulation-costly critical transient specifications leveraging less expensive performance metric information. The low cost and high fidelity feature make INSIGHT a good substitute for standard simulators in analog front-end optimization frameworks. INSIGHT is compatible with any optimization framework, facilitating enhanced design space exploration for sample efficiency through sophisticated offline learning and adaptation techniques. Our experiments demonstrate that INSIGHT-M, a model-based batch reinforcement learning sizing framework with INSIGHT as the accurate surrogate, only requires < 20 real-time simulations with 100-1000x lower simulation costs and significant speedup over existing sizing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑