Variation-Aware Analog Structural Synthesis
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.
A roadmap for analog CAD and its implementation algorithm-by-algorithm, presented by notable figures in analog CAD and analog design field who have experience in both the academia and industry
A compelling demonstration of how to overcome a key problem in computational intelligence (genetic programming): trustworthy synthesis of complex structures
A renewed emphasis for analog CAD tools to give insight to analog designers, with many creative examples of new insights provided
Each of the tools described show the first-ever approach to solving their respective problem in a fashion that is industrially palatable. Specifically: SANGRIA is the first approach that simultaneously does global and variation-aware analog sizing. CAFFEINE is the first approach for template-free symbolic modeling. MOJITO is the first approach that does trustworthy analog topology synthesis without the need for unreasonable user inputs, and MOJITO-R is the first approach which does it with variation-awareness. The specs-to-topology decision trees are the first which are automatically-constructed. The nonlinear sensitivity analysis is the first-ever approach which includes both structural and sizing parameters. MOJITO-N and ISCLEs are the first approaches to novel topology design which do not have issues with designer trust