CD-FiLM: Contrastive Masked Decoder With Feature-Wise Linear Modulation for Power–Signal Integrity Co-Analysis of High-Speed Transmitters

High-speed serial links are crucial for data transmission in high-performance systems, where increasing data rates demand robust transmitter (TX) performance. Maintaining signal and power integrity (SI/PI) in highly nonlinear TXs is essential, especially as lower power supply levels heighten their sensitivity to power supply noise (PSN). The interaction between PSN and input signals through coupled pathways further complicates PI-SI co-analysis of TXs. In this work, we propose a physical-inspired TX model, a Contrastive Masked Decoder with Feature-Wise Linear Modulation (CD-FiLM), for PI-SI co-analysis of high-speed TXs. We identify that the input and output features of the circuit correspond to different modalities under the same circuit state. By incorporating contrastive learning into a supervised learning framework, CD-FiLM aligns input and output to the same circuit-state space, enhancing robust feature representations, and thus improving the accuracy of noisy output signal predictions. We design an effective feature fusion module that captures signal and circuit interactions by modulating the input and PSN signals with circuit parameters, forming a comprehensive circuit state representation. To efficiently capture the temporal dependencies within the highly nonlinear TX output signals, we use masked data modeling for structural learning of long-sequence signals, employing a masked decoder for efficient parallel decoding. Experimental results show that CD-FiLM achieves efficient PI-SI co-analysis for TXs in high-speed links operating up to hundreds of GHz, producing eye diagrams with mean relative errors of 0.10-2.24% and 100–134× speedup.