Hypermultiplexed Integrated-Photonics-based Tensor Optical Processor
Preprint
- 23 July 2024
- preprint
- Published by Springer Nature in Research Square
Abstract
The escalating data volume and complexity resulting from the rapid expansion of artificial intelligence (AI), internet of things (IoT) and 5G/6G mobile networks is creating an urgent need for energy-efficient, scalable computing hardware. Here we demonstrate a hypermultiplexed integrated-photonics-based tensor optical processor (HITOP) that performs trillions of operations per second (TeraOPS) at the energy cost of 25 femtojoule per operation (25 fJ/OP). Based on space-time-wavelength three-dimensional (3D) data streaming, HITOP is built with arrays of wafer-fabricated III/V-based micron-scale lasers (spanning ~1 THz) incorporating thin-film Lithium-Niobate electro-optic (EO) photonics. Multidimensional parallelism allows matrix-matrix multiplications (N3 operations) using O(N) encoding devices, facilitating scalable on-chip integration with O(N2) computations per clockcycle. With each device activating 10 billion parameters per second, the HITOP scalability is validated in machine learning models with 405,000 parameters, which is 25,000 times more than previous integrated optical systems. A combination of high clockrates (10 GS/s), parallel processing and real-time reprogrammability unlocks the full potential of light for next-generation AI accelerators in applications ranging from training with trillions of parameters, real-time decision making in autonomous vehicles and robotics, dynamic optimization in smart manufacturing, to complex simulation for climate modeling and drug discovery.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- Harnessing AI and computing to advance climate modelling and predictionNature Climate Change, 2023
- ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scopeInternet of Things and Cyber-Physical Systems, 2023
- Mid‐Infrared Silicon‐on‐Lithium‐Niobate Electro‐Optic Modulators Toward Integrated Spectroscopic Sensing SystemsAdvanced Optical Materials, 2022
- Noise-resilient and high-speed deep learning with coherent silicon photonicsNature Communications, 2022
- Space-efficient optical computing with an integrated chip diffractive neural networkNature Communications, 2022
- An optical neural network using less than 1 photon per multiplicationNature Communications, 2022
- Deep learning with coherent nanophotonic circuitsNature Photonics, 2017
- Smart manufacturing must embrace big dataNature, 2017
- Low-Power High-Speed ADCs for Nanometer CMOS Integration2008
- InP-based VCSEL technology covering the wavelength range from 1.3 to 2.0μmJournal of Crystal Growth, 2003