There has been an ever-increasing demand for artificial intelligence and fifth-generation communications globally, resulting in very large computing power and memory requirements. The slowdown or even failure of Moore’s Law makes it increasingly difficult to improve their performance and energy efficiency by relying on advanced semiconductor technology. Optical devices can have very high bandwidth and low power consumption.
And light has ultra-high frequency up to 100 THz and multiple degrees of freedom in their quantum state, making optical computing one of the most competitive candidates for high-capacity matrix information processing. and low latency in the “More than Moore” era. In recent years, photonic matrix multiplication has been rapidly developed and widely used in photonic acceleration fields such as optical signal processing, artificial intelligence, and photonic neural networks. These applications based on matrix multiplication show the great potential and opportunities of the photonic accelerator.
In a new review published in Light Science & Application, a team of scientists, led by Professor Jianji Dong of Wuhan National Optoelectronics Laboratory, Huazhong University of Science and Technology in China, and his colleagues introduced the methods of photonic matrix multiplication, and summarize the stages of development of photonic matrix multiplication and related applications.
Then, their detailed advances in applications to optical signal processing and artificial neural networks in recent years were reviewed. Comments on the challenges and prospects of photon matrix multiplication and photon acceleration were also discussed.
The paper reviewed and discussed advances in photonic accelerators from a unique perspective of photonic matrix multiplication. These scientists summarize the main content of this review:
“Matrix-vector photon multiplication (MVM) methods mainly fall into three categories: the plane light conversion (PLC) method, the Mach-Zehnder interferometer (MZI) method, and the division multiplexing method. in wavelength (WDM).”
“The photonic matrix multiplication network itself can be used as a general linear photonic loop for photonic signal processing. In recent years, MVM has been developed as a powerful tool for a variety of photonic signal processing methods. “
“AI technology has been widely used in various electronic industries, such as deep learning-based speech recognition and image processing. MVM, as the basic building block of ANNs, occupies the most computing tasks, like more than 80% for GoogleNet and OverFeat models. Improving MVM performance is one of the most effective ways for ANN acceleration. Compared to electrical computing, optical computing is poor in data storage and flow control, and the low efficiency of optical nonlinearities limits applications in nonlinear computing, such as as activation functions.Although it has significant advantages over massively parallel computing through wavelength, mode and polarization multiplexing strategies, extremely high data modulation speeds up to 100 GHz.Therefore, photonic networks are pretty good at MVM. The combination of optical computing and AI should realize smart photonic processors and photonic accelerators. In recent years, AI technology has also seen rapid developments in the field of optics.”
“In general, photonic computing has obvious advantages in terms of signal throughput, latency, power consumption, and computational density, and its accuracy is generally lower than that of electrical computing.”
“Before fully optical ANNs are mature, especially in optical nonlinear effect and optical cascade, optoelectronic-hybrid AI is a more practical and competitive candidate for deep ANNs. Therefore, the development of “A highly efficient and dedicated optoelectronic-hybrid AI hardware chip system is one of the main research directions of photonics AI.”