MemSens: Significantly Reducing Memory Overhead in Adjoint Sensitivity Analysis Using Novel Error-Bounded Lossy Compression

Adjoint sensitivity analysis is an exceptionally efficient method for computing the gradient of an objective function with respect to given parameters, playing a crucial role in modern circuit design and verification. According to the principles of the adjoint method, it is necessary to store all es...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 62nd ACM/IEEE Design Automation Conference (DAC) S. 1 - 7
Hauptverfasser: Li, Chenxi, Feng, Yihang, Deng, Fuxing, Tao, Dingwen, Liu, Weifeng, Jin, Zhou
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 22.06.2025
Schlagworte:
Accuracy
Adjoint sensitivity analysis
Circuit simulation
Compression algorithms
Lossy compression
Memory management
Prediction algorithms
Quantization (signal)
Sensitivity analysis
Smoothing methods
Spatiotemporal phenomena
Vectors
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Adjoint sensitivity analysis is an exceptionally efficient method for computing the gradient of an objective function with respect to given parameters, playing a crucial role in modern circuit design and verification. According to the principles of the adjoint method, it is necessary to store all essential system state information, such as state vectors and Jacobian matrices, at each time step during the forward integration process in order to construct the adjoint equations during the backward integration. Therefore, the memory overhead of the adjoint method is proportional to the system size and the number of time steps, resulting in prohibitive memory costs for solving large-scale dynamic systems.In this paper, we propose a novel, memory-efficient adjoint sensitivity analysis method that significantly reduces the memory overhead of storing system state information by employing error-bounded lossy compression techniques. Our compression algorithm effectively utilizes the spatiotemporal characteristics of data in circuit simulations and incorporates stringent error control mechanisms. This approach achieves a two-order-ofmagnitude reduction in memory overhead during simulation while ensuring that the accuracy of the adjoint solution remains unaffected.
DOI:10.1109/DAC63849.2025.11132551