29 July 2024 in IEEE Access
This paper studies the problem of designing analog circuits to achieve target specifications, which can be formulated as a multi-objective combinatorial optimization (MOCO) under uncertainty. We address this challenging problem using the gm / ID methodology and a reinforcement learning (RL) framework. The proposed fast RL-based analog circuit designer (fRL-AD) maintains circuits’ DC bias conditions while determining their sizing parameters associated with AC characteristics. This ensures robust convergence to optimal sizing parameters across target specifications and proficiently captures layout effects. Specifically, by decomposing the problem into a sequence of feasible problems, our pre-trained RL agent can efficiently seek a solution for each feasible problem by generating states (i.e., candidate solutions) following a learned policy. Since the sequence of feasible regions is designed to approach an optimal solution to our main problem, the RL agent can find a near-optimal solution by sequentially tackling the feasible problems. Remarkably, using better initial points (or states), our approach is more efficient than directly solving the last feasible problem. Furthermore, we introduce an adaptive action space in our RL framework, which can dynamically modulate the size of the action space elements. The proposed method can provide an effective and stable design of various analog circuits, overcoming their traditionally low productivity due to reliance on human expertise and time-consuming simulations to handle uncertainties. We verify the effectiveness of our algorithm via experiments with various analog circuit topologies.
28 December 2022 in IEEE Access
This paper presents a design automation methodology for ring voltage-controlled oscillators (RVCOs) with their realistic and physical characteristics captured. With multiple sets of input constraints such as target frequency, phase noise, and control voltage range, the proposed algorithm automatically finds the design candidates that satisfy the target constraints, by running iterative post-layout simulations with auto-generated layouts and testbenches. The number of post-layout simulations is significantly reduced by the backtracking algorithm that observes the simulation results and determines the search direction. The proposed algorithm is applied to generate RVCOs in 40-nm planar and 7-nm FinFET technologies for DDR5 applications, and it turns out the proposed methodology produces sets of design parameters that meet the target specification in multiple technologies.
23 April 2024 in IEEE Transactions on Circuits and Systems II: Express Briefs
This brief solves the challenge of loop latency in the digital filter of conventional digital phase-locked loops (DPLLs), which hinders timely updates of phase frequency detector error information. To address this latency problem, we introduce a direct path for jitter correction, utilizing a pulse generator with an adaptive pulse width controller (PWC). The impact of PWC-based phase correction is analyzed to optimize the proportional gain in DPLLs. The DPLL, designed with adaptive gain control and realized in 40-nm CMOS technology, significantly enhances its performance metrics. Operating from a 100-MHz reference clock to produce a 3.2-GHz output, the prototype achieves a power consumption of 6.36 mW. Remarkably, the measurements indicate a 25% improvement in integrated jitter, reduced from 1231 to 942 fs, while maintaining comparable reference spur performance relative to conventional DPLL designs.