PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows
By Zichen Kong 1, Minghuan Song 2, Xiyuan Tang 3, Ziming Wei 4, Yi Zhong 1, Yuan Wang 1
1 School of Integrated Circuits, Peking University
2 Yuanpei College, Peking University
3 Institute for Artificial Intelligence, Peking University
4 School of Electronics Engineering and Computer Science, Peking University

Abstract
Analog circuit design automation requires both coordinated tool execution and efficient numerical search. Large language models (LLMs) offer new ways to organize tool execution, but finding one sizing that satisfies specifications across process, voltage, and temperature (PVT) corners remains costly. PVTSizing 2.0 addresses these needs through a human-agent workflow built around an independently usable numerical optimizer. An agent carries the designer's approved task through execution and result review. The optimizer reduces unnecessary training through loss-guided updates and uses critic-guided local refinement to explore additional candidates while accounting for cross-corner conflicts. An optional LLM adviser supplies parameter relationships to focus numerical search on circuit-informed directions, while the optimizer selects adjustment amplitudes and verifies their effects through simulation. Across four circuit benchmarks, the standalone optimizer completes all 40 runs and achieves a 7.3x speedup in overall mean runtime over the original PVTSizing, with a comparable mean sample count. In a separate study, the best tested knowledge-injection configuration further reduces mean runtime by 39.9% and simulation samples by 35.4% relative to the standalone optimizer.
To read the full article, click here
Related Semiconductor IP
- PVT Controller/Sensor
- PVT Sensor on Samsung 4nm, LN04LPP
- PVT Sensor
- In-Chip Monitoring Subsystem for Process, Voltage & Temperature (PVT) Monitoring, TSMC N3E
- PVT Controller (Series 5) (Sub-system for complete PVT monitoring), TSMC N3E
Related Articles
- AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing
- MEGATRON: a 28nm Analog PCM CiM/Digital System-on-Chip for Edge GenAI at 57.5 TOPS/W and 1.52 Mparam/mm²
- Generative AI for Analog Integrated Circuit Design: Methodologies and Applications
- A new era of chip-level DRC debug: Fast, scalable and AI-driven
Latest Articles
- PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows
- An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback
- Reconfiguring System-Level Protection Through Bounded Delegation in RISC-V MCUs
- SkipLane: Write-Once, Conflict-Free Accumulation for Zero-Skipping CNN Engines on FPGAs
- Priority-Aware Deficit Round Robin for AXI4 Bandwidth Fairness in ASAP-7nm Process