SHF: Medium: Integrating Human and Machine Intelligence for Next Generation Interactive Analog IC Design

SHF：媒介：集成人类和机器智能以实现下一代交互式模拟 IC 设计

• 批准号: 1704758
• 负责人: David Pan
• 金额: $ 80万
• 依托单位: University of Texas at Austin
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1704758&HistoricalAwards=false
• 关键词: SHF; Medium; Integrating; Human; Machine

At present, almost all analog integrated circuits (ICs) are designed manually, leading to low productivity and low performance. The goal of this research project is to change the way analog circuits are designed by significantly increasing design automation. If successful, it will greatly shorten the time-to-market, increase the system capability, reduce the design cost, and lower the chip failure rate. The proposed research topic bridges the circuit design community with the electronic design automation (EDA) community, initiating collaboration and co-development. On the application side, the proposed novel analog circuit design methodology will serve as the catalyst for emerging applications, such as IoT, 5G cellular communication, wearable electronics, and self-driving vehicles. On the educational side, a new and dedicated course will be developed to facilitate designers to adopt the proposed novel analog IC design methodology. The PIs will also continue their active roles in graduate student mentoring, minority outreach, local community service, and settling up close ties between UT Austin and local industry. There are two existing analog design flows in existence today. One is the classic manual design methodology. Despite wide acceptance, it has low productivity and low accuracy, which results from the hard fact that human beings are inefficient at complicated numerical computation and multi-dimensional optimization. The other is analog IC design automation (ADA), which treats circuit design as a black-box optimization problem and solves it by powerful optimization algorithms. Despite its high efficiency, ADA has received limited acceptance due to unreliability. The algorithms do not understand circuits, leading to unpractical synthesis results that only make numerical sense. Analog IC design is complex both in high-level reasoning and low-level computation, thus, neither human nor algorithm alone is adequate. To address this dilemma, a new analog IC design methodology that integrates both human and machine intelligence (HMI) is proposed. Its goal is to place the designers at the center and empower them with novel interactive tools. The specific research thrusts of this project include: 1) HMI guided interactive schematic design tools; 2) HMI guided interactive layout design tools; 3) HMI guided interactive analog design methodology and silicon validation; 4) HMI guided interactive circuit architecture selection and creation; 5) overall framework and toolkit.

目前，几乎所有模拟整合电路（IC）都是手动设计的，导致生产率低，性能低。该研究项目的目的是通过显着增加设计自动化来改变模拟电路的设计方式。如果成功，它将大大缩短上市时间，增加系统功能，降低设计成本并降低芯片故障率。拟议的研究主题将巡回设计社区与电子设计自动化（EDA）社区桥接，启动了协作和共同开发。在应用方面，提出的新型模拟电路设计方法将作为新兴应用的催化剂，例如物联网，5G细胞通信，可穿戴电子设备和自动驾驶车辆。在教育方面，将开发一项新的专门课程，以促进设计师采用拟议的新型模拟IC设计方法。 PI还将继续在研究生指导，少数民族外展，当地社区服务中继续积极角色，并在UT Austin与当地行业之间建立紧密的联系。如今存在两个现有的模拟设计流。一种是经典的手动设计方法。尽管接受广泛，但其生产率较低且准确性较低，这是由于人类在复杂的数值计算和多维优化方面效率低下而导致的。另一个是模拟IC设计自动化（ADA），它将电路设计视为黑盒优化问题，并通过强大的优化算法解决它。尽管效率很高，但由于不可靠性，ADA仍获得了有限的接受。这些算法不了解电路，从而导致仅具有数值意义的不实践的合成结果。在高级推理和低级计算中，模拟IC设计都是复杂的，因此，单独的人类和算法都不足够。为了解决这一难题，提出了一种整合人类和机器智力（HMI）的新模拟IC设计方法。它的目标是将设计师放置在中心，并通过新颖的互动工具为他们增强权力。该项目的具体研究推力包括：1）HMI引导的交互式示意图设计工具； 2）HMI引导的交互式布局设计工具； 3）HMI引导的交互式模拟设计方法和硅验证； 4）HMI引导的交互式电路体系结构的选择和创建； 5）整体框架和工具包。

项目成果

Analog Placement Constraint Extraction and Exploration with the Application to Layout Retargeting

模拟布局约束提取和探索及其在布局重定向中的应用

• DOI: 10.1145/3177540.3178245
• 发表时间: 2018
• 期刊: Proceedings of the 2018 International Symposium on Physical Design
• 作者: Xu, Biying;Basaran, Bulent;Su, Ming;Pan, David Z.
• 通讯作者: Pan, David Z.

WellGAN: Generative-Adversarial-Network-Guided Well Generation for Analog/Mixed-Signal Circuit Layout

• DOI: 10.1145/3316781.3317930
• 发表时间: 2019-06
• 期刊: 2019 56th ACM/IEEE Design Automation Conference (DAC)
• 作者: Biying Xu;Yibo Lin;Xiyuan Tang;Shaolan Li;Linxiao Shen;Nan Sun;D. Pan

OpenSAR: An Open Source Automated End-to-end SAR ADC Compiler

• DOI: 10.1109/iccad51958.2021.9643494
• 发表时间: 2021-01-01
• 期刊: 2021 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN (ICCAD)
• 作者: Liu, Mingjie;Tang, Xiyuan;Pan, David Z.
• 通讯作者: Pan, David Z.

Towards Decrypting the Art of Analog Layout: Placement Quality Prediction via Transfer Learning

• DOI: 10.23919/date48585.2020.9116330
• 发表时间: 2020-01-01
• 期刊: PROCEEDINGS OF THE 2020 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2020)
• 作者: Liu, Mingjie;Zhu, Keren;Pan, David Z.
• 通讯作者: Pan, David Z.

Tutorial and Perspectives on MAGICAL: A Silicon-Proven Open-Source Analog IC Layout System

MAGICAL 教程和观点：经过硅验证的开源模拟 IC 布局系统

• DOI: 10.1109/tcsii.2022.3172869
• 发表时间: 2022
• 期刊: IEEE Transactions on Circuits and Systems II: Express Briefs
• 作者: Zhu, Keren;Chen, Hao;Liu, Mingjie;Pan, David Z.
• 通讯作者: Pan, David Z.