TeMPO: Efficient time-multiplexed dynamic photonic tensor core for edge AI with compact slow-light electro-optic modulator
Journal of Applied Physics · 14.06.2024 · 135 (22)
DOI: 10.1063/5.0203036 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Physics, online erschienen am 12.06.2024. Verfasst von Meng Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Focus Center, Science, Mathematics, And Research For Transformation Scholarship Program.
Abstract (Originalsprache)
Electronic–photonic computing systems offer immense potential in energy-efficient artificial intelligence (AI) acceleration tasks due to the superior computing speed and efficiency of optics, especially for real-time, low-energy deep neural network inference tasks on resource-restricted edge platforms. However, current optical neural accelerators based on foundry-available devices and conventional system architecture still encounter a performance gap compared to highly customized electronic counterparts. To bridge the performance gap due to lack of domain specialization, we present a time-multiplexed dynamic photonic tensor accelerator, dubbed TeMPO, with cross-layer device/circuit/architecture customization. At the device level, we present foundry-compatible, customized photonic devices, including a slow-light electro-optic modulator with experimental demonstration, optical splitters, and phase shifters that significantly reduce the footprint and power in input encoding and dot-product calculation. At the circuit level, partial products are hierarchically accumulated via parallel photocurrent aggregation, lightweight capacitive temporal integration, and sequential digital summation, considerably relieving the analog-to-digital conversion bottleneck. We also employ a multi-tile, multi-core architecture to maximize hardware sharing for higher efficiency. Across diverse edge AI workloads, TeMPO delivers digital-comparable task accuracy with superior quantization/noise tolerance. We achieve a 368.6 TOPS peak performance, 22.3 TOPS/W energy efficiency, and 1.2 TOPS/mm2 compute density, pushing the Pareto frontier in edge AI hardware. This work signifies the power of cross-layer co-design and domain-specific customization, paving the way for future electronic–photonic accelerators with even greater performance and efficiency.
Förderung
- Focus Center
- Science, Mathematics, And Research For Transformation Scholarship Program
Zitieren
APA
Zhang, M., Yin, D., Gangi, N., Begović, A., Chen, A., Huang, Z. R., & Gu, J. (2024). TeMPO: Efficient time-multiplexed dynamic photonic tensor core for edge AI with compact slow-light electro-optic modulator. Journal of Applied Physics, 135(22). https://doi.org/10.1063/5.0203036
Vancouver
Zhang M, Yin D, Gangi N, Begović A, Chen A, Huang ZR, et al. TeMPO: Efficient time-multiplexed dynamic photonic tensor core for edge AI with compact slow-light electro-optic modulator. Journal of Applied Physics. 2024;135(22). doi:10.1063/5.0203036
BibTeX
@article{Zhang2024,
author = {Zhang, Meng and Yin, Dennis and Gangi, Nicholas and Begović, Amir and Chen, Alexander and Huang, Zhaoran Rena and Gu, Jiaqi},
title = {TeMPO: Efficient time-multiplexed dynamic photonic tensor core for edge AI with compact slow-light electro-optic modulator},
journal = {Journal of Applied Physics},
year = {2024},
volume = {135},
number = {22},
doi = {10.1063/5.0203036}
}
EUVIMED