INSIGHT: A Universal Neural Simulator Framework for Analog Circuits with Autoregressive Transformers

The compute-intensive nature of SPICE simulations hinders effective analog design automation. This paper introduces INSIGHT, a data-efficient, adaptive, high-fidelity, technologyagnostic universal neural simulator framework that formulates analog performance prediction as an autoregressive sequence...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autori:	Poddar, Souradip, Oh, Youngmin, Lai, Yao, Zhu, Hanqing, Hwang, Bosun, Pan, David Z.
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 22.06.2025
Predmet:	Adaptation models Computational modeling Computer architecture Design automation Performance metrics SPICE Training Training data Transfer learning Transformers
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	The compute-intensive nature of SPICE simulations hinders effective analog design automation. This paper introduces INSIGHT, a data-efficient, adaptive, high-fidelity, technologyagnostic universal neural simulator framework that formulates analog performance prediction as an autoregressive sequence generation task to accurately predict performance across diverse circuits. INSIGHT achieves test \mathbf{R}^{\mathbf{2}} scores \geq \mathbf{0. 9 5}, outperforming existing neural surrogates. Cross-technology transfer learning experiments show that INSIGHT can preserve model performance with \sim \mathbf{6 0 \%} less training data. Low-Rank Adaptation (LoRA) integration further reduces memory footprint by \sim 42 \% and training time by \sim 25 \%, maintaining high performance. Our experiments show that INSIGHT-based RL sizing framework achieves 100-1000 \times lower simulation costs over existing sizing methods for identical benchmarks and target specifications.
DOI:	10.1109/DAC63849.2025.11133292