Synopses & Reviews
Variation-Aware Analog Structural Synthesis describes computational intelligence-based tools for robust design of analog circuits. It starts with global variation-aware sizing and knowledge extraction, and progressively extends to variation-aware topology design. The computational intelligence techniques developed in this book generalize beyond analog CAD, to domains such as robotics, financial engineering, automotive design, and more. The tools are for: Globally-reliable variation-aware automated sizing via SANGRIA, leveraging structural homotopy and response surface modeling. Template-free symbolic models via CAFFEINE canonical form functions, for greater insight into the relationship between design/process variables and circuit performance/robustness. Topology selection and topology synthesis via MOJITO. 30 well-known analog building blocks are hierarchically combined, leading to >100,000 different possible topologies which are all trustworthy by construction. MOJITO does multi-objective genetic programming-based search across these topologies with SPICE accuracy, to return a set of sized topologies on the optimal performance/yield tradeoff curve. Nonlinear sensitivity analysis, topology decision trees, and analytical tradeoffs. With a data-mining perspective on Pareto-optimal topologies, this book shows how to do global nonlinear sensitivity analysis on topology and sizing variables, automatically extract a specs-to-topology decision tree, and determine analytical expressions of performance tradeoffs. Novel topology design. The MOJITO-N and ISCLEs tools generate novel yet trustworthy topologies; including boosting digitally-sized circuits for analog functionality.
Review
From the reviews: "This book is squarely aimed at analog circuit designers who are searching for new approaches to analog structural design and optimization. ... Those most likely to benefit from this book ... are experts in the field of industrial circuit design seeking insight into new design tools. ... for the non-expert, with only a cursory understanding of the background material, the processes and results described in this book are an inspiring example of real-world applications of evolutionary design." (John Rieffel, Genetic Programming and Evolvable Machines, Vol. 12, 2011)
Synopsis
Variation-Aware Analog Structural Synthesis describes computational intelligence-based tools for robust design of analog circuits. It starts with global variation-aware sizing and knowledge extraction, and progressively extends to variation-aware topology design. The computational intelligence techniques developed in this book generalize beyond analog CAD, to domains such as robotics, financial engineering, automotive design, and more.
Synopsis
This book describes new tools for front end analog designers, starting with global variation-aware sizing, and extending to novel variation-aware topology design. The tools aid design through automation, but more importantly, they also aid designer insight through automation. We now describe four design tasks, each more general than the previous, and how this book contributes design aids and insight aids to each. The ?rst designer task targeted is global robust sizing. This task is supported by a design tool that does automated, globally reliable, variation-aware s- ing (SANGRIA), and an insight-aiding tool that extracts designer-interpretable whitebox models that relate sizings to circuit performance (CAFFEINE). SANGRIA searches on several levels of problem dif?culty simultaneously, from lower cheap-to-evaluate exploration layers to higher full-evaluation exploitation layers (structural homotopy). SANGRIAmakes maximal use of circuit simulations by performing scalable data mining on simulation results to choose new candidate designs. CAFFEINE accomplishes its task by tre- ing function induction as a tree-search problem. It constrains its tree search space via a canonical-functional-form grammar, and searches the space with grammatically constrained genetic programming. The second designer task is topology selection/topology design. Topology selection tools must consider a broad variety of topologies such that an app- priate topology is selected, must easily adapt to new semiconductor process nodes, and readily incorporate new topologies. Topology design tools must allow designers to creatively explore new topology ideas as rapidly as possible."
Synopsis
This book describes computational intelligence-based tools for robust design of analog circuits. It starts with global variation-aware sizing and knowledge extraction and progressively extends to variation-aware topology design.
About the Author
Trent McConaghy is co-founder and Chief Scientific Officer of Solido Design Automation Inc. He was a co-founder and Chief Scientist of Analog Design Automation Inc., which was acquired by Synopsys Inc. in 2004. Prior to that, he did research for the Canadian Department of National Defense. He received his PhD degree in Electrical Engineering from the Katholieke Universiteit Leuven, Belgium, in 2008. He received a Bachelor's in Engineering (with great distinction), and a Bachelor's in Computer Science (with great distinction), both from the University of Saskatchewan, Canada, in 1999. He has about 40 peer-reviewed technical papers and patents granted / pending. He has given invited talks / tutorials at many labs, universities, and conferences such as JPL, MIT, ICCAD, and DAC. He is regularly a technical program committee member and reviewer in both the CAD and intelligent systems fields, such as IEEE Trans CAD, ACM TODAES, Electronics Letters, to IEEE Trans Evolutionary Computation, the Journal of Genetic Programming and Evolvable Machines, GPTP, GECCO, ICES, etc. His research interest is in statistical machine learning and intelligent systems, with transistor-level CAD applications such as variation-aware design, analog topology design, automated sizing, knowledge extraction, and symbolic modeling. Michiel Steyaert was born in Aalst, Belgium, in 1959. He received the masters degree in electrical-mechanical engineering and the Ph.D. degree in electronics from the Katholieke Universiteit Leuven (K.U.Leuven), Heverlee, Belgium in 1983 and 1987, respectively. From 1983 to 1986 he obtained an IWNOL fellowship (Belgian National Fundation for Industrial Research) which allowed him to work as a Research Assistant
Table of Contents
Preface. Acronyms and Notation. 1. INTRODUCTION. 1.1 Motivation. 1.2 Background and Contributions to Analog CAD. 1.3 Background and Contributions to AI. 1.4 Analog CAD Is a Fruitfly for AI. 1.5 Conclusion. 2. VARIATION-AWARE SIZING: BACKGROUND. 2.1 Introduction and Problem Formulation. 2.2 Review of Yield Optimization Approaches. 2.3 Conclusion. 3. GLOBALLY RELIABLE, VARIATION-AWARE SIZING: SANGRIA. 3.1 Introduction. 3.2 Foundations: Model-Building Optimization (MBO). 3.3 Foundations: Stochastic Gradient Boosting. 3.4 Foundations: Homotopy. 3.5 SANGRIA Algorithm. 3.6 SANGRIA Experimental Results. 3.7 On Scaling to Larger Circuits. 3.8 Conclusion. 4. KNOWLEDGE EXTRACTION IN SIZING: CAFFEINE. 4.1 Introduction and Problem Formulation. 4.2 Background: GP and Symbolic Regression. 4.3 CAFFEINE Canonical Form Functions. 4.4 CAFFEINE Search Algorithm. 4.5 CAFFEINE Results. 4.6 Scaling Up CAFFEINE: Algorithm. 4.7 Scaling Up CAFFEINE: Results. 4.8 Application: Behaviorial Modeling. 4.9 Application: Process-Variable Robustness Modeling. 4.10 Application: Design-Variable Robustness Modeling. 4.11 Application: Automated Sizing. 4.12 Application: Analytical Performance Tradeoffs. 4.13 Sensitivity To Search Algorithm. 4.14 Conclusion. 5. CIRCUIT TOPOLOGY SYNTHESIS: BACKGROUND. 5.1 Introduction. 5.2 Topology-Centric Flows. 5.3 Reconciling System-Level Design. 5.4 Requirements for a Topology Selection / Design Tool. 5.5 Open-Ended Synthesis and the Analog Problem Domain. 5.6 Conclusion. 6. TRUSTWORTHY TOPOLOGY SYNTHESIS: MOJITO SEARCH SPACE. 6.1 Introduction. 6.2 Search Space Framework. 6.3 A Highly Searchable Op Amp Library. 6.4 Operating-Point Driven Formulation. 6.5 Worked Example. 6.6 Size of Search Space. 6.7 Conclusion. 7. TRUSTWORTHY TOPOLOGY SYNTHESIS: MOJITO ALGORITHM. 7.1 Introduction. 7.2 High-Level Algorithm. 7.3 Search Operators. 7.4 Handling Multiple Objectives. 7.5 Generation of Initial Individuals. 7.6 Experimental Setup. 7.7 Experiment: Hit Target Topologies? 7.8 Experiment: Diversity? 7.9 Experiment: Human-Competitive Results? 7.10 Discussion: Comparison to Open-Ended Structural Synthesis. 7.11 Conclusion. 8. KNOWLEDGE EXTRACTION IN TOPOLOGY SYNTHESIS. 8.1 Introduction. 8.2 Generation of Database. 8.3 Extraction of Specs-To-Topology Decision Tree. 8.4 Global Nonlinear Sensitivity Analysis. 8.5 Extraction of Analytical Performance Tradeoffs. 8.6 Conclusion. 9. VARIATION-AWARE TOPOLOGY SYNTHESIS & KNOWLEDGE EXTRACTION. 9.1 Introduction. 9.2 Problem Specification. 9.3 Background. 9.4 Towards a Solution. 9.5 Proposed Approach: MOJITO-R. 9.6 MOJITO-R Experimental Validation. 9.7 Conclusion. 10. NOVEL VARIATION-AWARE TOPOLOGY SYNTHESIS. 10.1 Introduction. 10.2 Background. 10.3 MOJITO-N Algorithm and Results. 10.4 ISCLEs Algorithm And Results. 10.5 Conclusion. 11. CONCLUSION. 11.1 General Contributions. 11.2 Specific Contributions. 11.3 Future Work. 11.4 Final Remarks. References. Index.