{"title":"ML for Analog Design: Good Progress, but More to Do","authors":"B. Nikolić","doi":"10.1145/3551901.3557042","DOIUrl":null,"url":null,"abstract":"Analog and mixed-signal (AMS) blocks are often critical and time-consuming part of System-on-Chip (SoC) design, due to the largely manual process of circuit design, simulation and SoC integration iterations. There have been numerous efforts to realize AMS blocks from specification by using a process analogous to digital synthesis, with automated place and route techniques [1], [2], but although very effective within their application domains, they have been limited in scope. AMS block design process, outlined in Figure 1, starts with the derivation of its target performance specifications (gain, bandwidth, phase margin, settling time, etc.) from system requirements, and establishes a simulation testbench. Then, a designer relies on their expertise to choose the topology that is most likely to achieve the desired performance with minimum power consumption. Circuit sizing is a process of determining schematic-level transistor widths and lengths to attain the specifications, with minimum power consumption. Many of the commonly used analog circuits can be sized by using well-established heuristics to achieve near-optimal performance [3]-[5]. The performance is verified by running simulations, and there has been a notable progress in enriching the commercial simulators to automate the testbench design. Machine learning (ML) based techniques have recently been deployed in circuit sizing to achieve optimality without relying on design heuristics [6]-[8]. Many of the commonly employed ML techniques require a rich training dataset; reinforcement learning (RL) sidesteps this issue by using agent that interacts with its simulation environment through a trial-and-error process that mimics learning in humans. In each step, the RL agent, which contains a neural network, observes the state of the environment and takes a sizing action. The most time-consuming step in a traditional design procedure is layout, which is typically a manual iterative process. Layout parasitics degrade the schematic-level performance, requiring circuit resizing. However, the use of circuit generators, such as the Berkeley Analog Generator (BAG) [9] automates the layout iterations. RL agents have been coupled with BAG to automate the complete design process for a fixed circuit topology [7]. Simulations with post-layout parasitics are much slower than schematic-level simulations, which calls for deployment of RL techniques that limit the sampled space. Finally, the process of integrating an AMS block into an SoC and verifying its system-level performance can be very time consuming.","PeriodicalId":349548,"journal":{"name":"Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3551901.3557042","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Analog and mixed-signal (AMS) blocks are often critical and time-consuming part of System-on-Chip (SoC) design, due to the largely manual process of circuit design, simulation and SoC integration iterations. There have been numerous efforts to realize AMS blocks from specification by using a process analogous to digital synthesis, with automated place and route techniques [1], [2], but although very effective within their application domains, they have been limited in scope. AMS block design process, outlined in Figure 1, starts with the derivation of its target performance specifications (gain, bandwidth, phase margin, settling time, etc.) from system requirements, and establishes a simulation testbench. Then, a designer relies on their expertise to choose the topology that is most likely to achieve the desired performance with minimum power consumption. Circuit sizing is a process of determining schematic-level transistor widths and lengths to attain the specifications, with minimum power consumption. Many of the commonly used analog circuits can be sized by using well-established heuristics to achieve near-optimal performance [3]-[5]. The performance is verified by running simulations, and there has been a notable progress in enriching the commercial simulators to automate the testbench design. Machine learning (ML) based techniques have recently been deployed in circuit sizing to achieve optimality without relying on design heuristics [6]-[8]. Many of the commonly employed ML techniques require a rich training dataset; reinforcement learning (RL) sidesteps this issue by using agent that interacts with its simulation environment through a trial-and-error process that mimics learning in humans. In each step, the RL agent, which contains a neural network, observes the state of the environment and takes a sizing action. The most time-consuming step in a traditional design procedure is layout, which is typically a manual iterative process. Layout parasitics degrade the schematic-level performance, requiring circuit resizing. However, the use of circuit generators, such as the Berkeley Analog Generator (BAG) [9] automates the layout iterations. RL agents have been coupled with BAG to automate the complete design process for a fixed circuit topology [7]. Simulations with post-layout parasitics are much slower than schematic-level simulations, which calls for deployment of RL techniques that limit the sampled space. Finally, the process of integrating an AMS block into an SoC and verifying its system-level performance can be very time consuming.
由于电路设计、仿真和SoC集成迭代的大量手工过程,模拟和混合信号(AMS)模块通常是片上系统(SoC)设计中关键且耗时的部分。通过使用类似于数字合成的过程,使用自动放置和路由技术[1],[2],已经有许多努力来实现AMS块规范,但是尽管在其应用领域内非常有效,但它们的范围有限。AMS模块设计过程如图1所示,首先从系统需求推导出其目标性能规格(增益、带宽、相位裕度、稳定时间等),并建立仿真试验台。然后,设计人员依靠他们的专业知识来选择最可能以最小功耗实现所需性能的拓扑。电路尺寸是确定原理图级晶体管宽度和长度的过程,以达到规格,最小的功耗。许多常用的模拟电路可以通过使用完善的启发式来确定尺寸,以达到接近最佳的性能[3]-[5]。通过运行仿真验证了其性能,并且在丰富商用仿真器以实现试验台设计自动化方面取得了显著进展。基于机器学习(ML)的技术最近已被部署在电路尺寸中,以实现最优性,而不依赖于设计启发式[6]-[8]。许多常用的机器学习技术需要丰富的训练数据集;强化学习(RL)通过使用代理,通过模仿人类学习的试错过程与模拟环境进行交互,从而避免了这个问题。在每一步中,RL代理(包含一个神经网络)观察环境的状态并采取调整动作。传统设计过程中最耗时的步骤是布局,这通常是一个手动迭代的过程。布局寄生降低了原理级性能,需要调整电路尺寸。然而,电路生成器的使用,如Berkeley Analog Generator (BAG)[9]使布局迭代自动化。RL代理已与BAG相结合,以自动完成固定电路拓扑的整个设计过程[7]。具有布局后寄生的模拟比原理图级模拟慢得多,这需要部署限制采样空间的RL技术。最后,将AMS块集成到SoC中并验证其系统级性能的过程可能非常耗时。