Lune

ISCA2025Top-tier venue

LightML: A Photonic Accelerator for Efficient General Purpose Machine Learning

Liang Liu, Sadra Rahimi Kari, Xin Xin, Nathan Youngblood, Youtao Zhang, Jun Yang

2025Year
3Citations

Abstract

The rapid integration of AI technologies into everyday life across sectors such as healthcare, autonomous driving, and smart home applications requires extensive computational resources, placing strain on server infrastructure and incurring significant costs.We present LightML, the first system-level photonic crossbar design, optimized for high-performance machine learning applications.This work provides the first complete memory and buffer architecture carefully designed to support the high-speed photonic crossbar, achieving over 80% utilization.LightML also introduces solutions for key ML functions, including large-scale matrix multiplication (MMM), element-wise operations, non-linear functions, and convolutional layers.Delivering 325 TOP/s at only 3 watts, LightML offers significant improvements in speed and power efficiency, making it ideal for both edge devices and dense data center workloads.

Ask about this paper

Ask your agent about it.

Lune has read the top-tier papers around this one, so every answer names the papers it rests on.

Questions to start from

Your agent calls

Lunesearch_papers

Ask in Lune

Free to start. No credit card required.

lune papers get 0f0a3da8-43a6-4cac-bbbb-dfa2ca871af8

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines