Superconducting Digital (SCD) technology offers significant potential for enhancing the performance of next generation large scale compute workloads. By leveraging advanced lithography and a 300 mm platform, SCD devices can reduce energy consumption and boost computational power. This paper presents a cross-layer modeling approach to evaluate the system-level performance benefits of SCD architectures for Large Language Model (LLM) training and inference. Our findings, based on experimental data and Pulse Conserving Logic (PCL) design principles, demonstrate substantial performance gain in both training and inference. We are, thus, able to convincingly show that the SCD technology can address memory and interconnect limitations of present day solutions for next-generation compute systems.
@article{arxiv.2411.08645,
title = {A System Level Performance Evaluation for Superconducting Digital Systems},
author = {Joyjit Kundu and Debjyoti Bhattacharjee and Nathan Josephsen and Ankit Pokhrel and Udara De Silva and Wenzhe Guo and Steven Van Winckel and Steven Brebels and Manu Perumkunnil and Quentin Herr and Anna Herr},
journal= {arXiv preprint arXiv:2411.08645},
year = {2024}
}