Taheri, Ebadollah, authorMahdian, Mohammad Amin, authorPasricha, Sudeep, authorNikdast, Mahdi, authorACM, publisher2024-11-112024-11-112023-10-28Ebadollah Taheri, Mohammad Amin Mahdian, Sudeep Pasricha, Mahdi Nikdast. 2023. In TRINE: A Tree-Based Silicon Photonic Interposer Network for Energy-Efficient 2.5D Machine Learning Acceleration. NoCArc '23: Proceedings of the 16th International Workshop on Network on Chip Architectures. Pages 15-20. https://doi.org/10.1145/3610396.3618091https://hdl.handle.net/10217/2395222.5D chiplet systems have showcased low manufacturing costs and modular designs for machine learning (ML) acceleration. Nevertheless, communication challenges arise from chiplet interconnectivity and high-bandwidth demands among chiplets. To address these challenges, we present TRINE, a novel tree-based silicon photonic interposer network for energy-efficient ML acceleration. Leveraging silicon photonics and broadband optical switching, TRINE enables efficient inter-chiplet communication with reduced latency and improved energy efficiency. Considering several ML workloads, our simulation results demonstrate significant improvements in the average energy efficiency by 61.7% and 40% when comparing TRINE with two recently proposed silicon photonic interposer networks. By overcoming communication limitations in 2.5D ML accelerators, this work is a promising step towards advancing 2.5D photonic-based ML accelerator design.born digitalarticleseng© Ebadollah Taheri, et al. | ACM 2023. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in NoCArc '2023, https://dx.doi.org/10.1145/3610396.3618091.hardwarephotonic and optical interconnectnetwork on chipTexthttps://doi.org/10.1145/3610396.3618091