Batch processing and data streaming Fourier-based convolutional neural network accelerator

Zibu Hu; Shurui Li; Russell L. T. Schwartz; Maria Solyanik-Gorgone; Behrouz Movahhed Nouri; Mario Miscuglio; Puneet Gupta; Hamed Dalir; Volker J. Sorger

doi:10.1117/12.2633917

3 October 2022 Batch processing and data streaming Fourier-based convolutional neural network accelerator

Zibu Hu, Shurui Li, Russell L. T. Schwartz, Maria Solyanik-Gorgone, Behrouz Movahhed Nouri, Mario Miscuglio, Puneet Gupta, Hamed Dalir, Volker J. Sorger

Author Affiliations +

Proceedings Volume 12204, Emerging Topics in Artificial Intelligence (ETAI) 2022; 1220409 (2022) https://doi.org/10.1117/12.2633917
Event: SPIE Nanoscience + Engineering, 2022, San Diego, California, United States

Abstract

Decision-making through artificial neural networks with minimal latency is critical for numerous applications such as navigation, tracking, and real-time machine action systems. This requires machine learning hardware to process multidimensional data at high throughput. Unfortunately, handling convolution operations, the primary computational tool for data classification tasks, obeys challenging runtime complexity scaling laws. However, homomorphically implementing the convolution theorem in a Fourier optics display light processor can achieve a non-iterative O(1) runtime complexity for data inputs beyond 1,000 × 1,000 large matrices. Following this approach, here we demonstrate data streaming multi-kernel image batching using a Fourier Convolutional Neural Network (FCNN) accelerator. We show image batch processing of large-scale matrices as 2 million dot product multiplications performed by a digital light processing module in the Fourier domain. Furthermore, we further parallelize this optical FCNN system by exploiting multiple spatially parallel diffraction orders, achieving a 98x throughput improvement over state-of-the-art FCNN accelerators. A comprehensive discussion of the practical challenges associated with working at the edge of system capabilities highlights the problem of crosstalk and resolution scaling laws in the Fourier domain. Accelerating convolution by exploiting massive parallelism in display technology brings non-Van Neumann-based machine learning acceleration.

Conference Presentation

Citation Download Citation

Zibu Hu, Shurui Li, Russell L. T. Schwartz, Maria Solyanik-Gorgone, Behrouz Movahhed Nouri, Mario Miscuglio, Puneet Gupta, Hamed Dalir, and Volker J. Sorger "Batch processing and data streaming Fourier-based convolutional neural network accelerator", Proc. SPIE 12204, Emerging Topics in Artificial Intelligence (ETAI) 2022, 1220409 (3 October 2022); https://doi.org/10.1117/12.2633917

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available