Silicon photonics enabled universal cross-scale tensor processing on chip

Author:

Jiang Tian1ORCID,Ouyang Hao2,Tao Zilong3,You Jie4,Luo Yihao5,Hao Hao6,Du Shiyin3,Tang Shengjie7,Lv Hai-Bin8,Liu Xiaoping9,Zheng Xin4,Cheng Xiangai1,Zhang Jun3

Affiliation:

1. National University of Defense Technology

2. College of Advanced Interdisciplinary Studies, National University of Defense TechnologyCollege of Advanced Interdisciplinary Studies, National University of Defense Technology

3. State Key Laboratory of High Performance Computing College of Computer, National University of Defense Technology

4. National Innovation Institute of Defense Technology

5. College of Advanced Interdisciplinary Studies, National University of Defense Technology

6. Institute for Quantum Science and Technology, College of Science , National University of Defense Technology

7. School of Physical Science and Technology, ShanghaiTech University

8. Nanjing University

9. ShanghaiTech University

Abstract

Abstract In the rapidly evolving field of artificial intelligence, integrated photonic computing has emerged as a promising solution to address the growing demand for high-performance computing with increased speed and reduced energy consumption. This study presents a novel silicon photonic cross-scale tensor processing (SiP-CSTP) system on chip, designed to enhance the computing scale without increasing the hardware scale. By expanding the computing scale to accommodate the larger matrix processing scale, the SiP-CSTP system enables accelerated pooling, channel fusion, and matrix multiplication processes in convolutional neural networks. Notably, our architecture significantly reduces the number of operations required during pooling and channel fusion, distinguishing it from conventional computing systems. Experimental evaluations demonstrate the high-speed performance of the SiP-CSTP system, including a 14 Gbaud/s NRZ modulation rate for input tensors, a 6-bit accuracy for weight matrices, and an impressive total computing power of 0.252 TOPS, resulting computing power per unit as high as 0.06 TOPS /unit in a small hardware scale. Additionally, we conducted proof-of-concept application experiments on benchmark datasets, including the Modified National Institute of Standards and Technology (MNIST), Google quickdraw, and CIFAR-10. The results exhibited remarkable accuracies of 97.86%, 93.51%, and 70.22%, respectively, in deep image recognition and classification tasks. By enabling cross-scale operations in a universal tensor streaming processing system on a chip, this study opens new avenues for exploration and innovation at the intersection of silicon photonics, cross-scale computation, and artificial intelligence, shaping the future landscape of computing technologies.

Publisher

Research Square Platform LLC

Reference43 articles.

1. Liu, Y. et al. Summary of chatgpt/gpt-4 research and perspective towards the future of large language models. arXiv preprint arXiv:2304.01852, (2023).

2. Zhang, C. et al. A complete survey on generative AI (AIGC): Is chatGPT from GPT-4 to GPT-5 All you need? arXiv preprint arXiv:2303.11717, (2023).

3. Zhang, C. et al. in Proceedings of the 2015 ACM/SIGDA international symposium on field-programmable gate arrays. 161–170.

4. Jouppi, N. P. et al. in Proceedings of the 44th annual international symposium on computer architecture. 1–12.

5. O-cnn: Octree-based convolutional neural networks for 3d shape analysis;Wang P-S;ACM Transactions On Graphics (TOG),2017

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3