Optical computing has shown immense application prospects in the post-Moore era.However,as a crucial component of logic computing,the digital multiplier can only be realized on a small scale in optics,restrained by th...Optical computing has shown immense application prospects in the post-Moore era.However,as a crucial component of logic computing,the digital multiplier can only be realized on a small scale in optics,restrained by the limited functionalities and inevitable loss of optical nonlinearity.In this paper,we propose a time-space multiplexed architecture to realize large-scale photonic-electronic digital multiplication.展开更多
Matrix computation,as a fundamental building block of information processing in science and technology,contributes most of the computational overheads in modern signal processing and artificial intelligence algorithms...Matrix computation,as a fundamental building block of information processing in science and technology,contributes most of the computational overheads in modern signal processing and artificial intelligence algorithms.Photonic accelerators are designed to accelerate specific categories of computing in the optical domain,especially matrix multiplication,to address the growing demand for computing resources and capacity.Photonic matrix multiplication has much potential to expand the domain of telecommunication,and artificial intelligence benefiting from its superior performance.Recent research in photonic matrix multiplication has flourished and may provide opportunities to develop applications that are unachievable at present by conventional electronic processors.In this review,we first introduce the methods of photonic matrix multiplication,mainly including the plane light conversion method,Mach–Zehnder interferometer method and wavelength division multiplexing method.We also summarize the developmental milestones of photonic matrix multiplication and the related applications.Then,we review their detailed advances in applications to optical signal processing and artificial neural networks in recent years.Finally,we comment on the challenges and perspectives of photonic matrix multiplication and photonic acceleration.展开更多
Silicon photonic integrated devices used for nonlinear optical signal processing play a key role in ultrafast switching,computing,and modern optical communications.However,current devices suffer from limited operation...Silicon photonic integrated devices used for nonlinear optical signal processing play a key role in ultrafast switching,computing,and modern optical communications.However,current devices suffer from limited operation speeds and low conversion efficiencies due to the intrinsically low nonlinear index of silicon.In this paper,we experimentally demonstrate enhanced optical nonlinearity in a silicon–organic hybrid slot waveguide consisting of an ultranarrow slot waveguide coated with a highly nonlinear organic material.The fabricated slot area is as narrow as 45 nm,which is,to the best of our knowledge,the narrowest slot width that has been experimentally reported in silicon slot waveguides.The nonlinear coefficient of the proposed device with a length of 3 mm is measured to be up to 1.43×10^(6) W^(-1)km^(-1).Based on the nanostructure design,the conversion efficiencies of degenerate four-wave mixing showed enhancements of more than 12 dB and 5 dB compared to those measured for an identical device without the organic material and a silicon strip waveguide,respectively.As a proof of concept,all-optical canonical logic units based on the prepared device with two inputs at 40 Gb/s are analyzed.The obtained logic results showed clear temporal waveforms and wide-open eye diagrams with error-free performance,illustrating that our device has great potential for use in high-speed all-optical signal processing and high-performance computing in the nodes and terminals of optical networks.展开更多
基金National Key Research and Development Program of China(2023YFB2806502)National Natural Science Foundation of China(62075075,62275088,U21A20511)Innovation Project of Optics Valley Laboratory(OVL2021BG001)。
文摘Optical computing has shown immense application prospects in the post-Moore era.However,as a crucial component of logic computing,the digital multiplier can only be realized on a small scale in optics,restrained by the limited functionalities and inevitable loss of optical nonlinearity.In this paper,we propose a time-space multiplexed architecture to realize large-scale photonic-electronic digital multiplication.
基金Chaoran Huang would like to thank Alexander Tait,Bhavin Shastri and Paul Prucnal for the fruitful discussions.J.J.D.acknowledges the support of the National Key Research and Development Project of China(2018YFB2201901)the National Natural Science Foundation of China(61805090,62075075).
文摘Matrix computation,as a fundamental building block of information processing in science and technology,contributes most of the computational overheads in modern signal processing and artificial intelligence algorithms.Photonic accelerators are designed to accelerate specific categories of computing in the optical domain,especially matrix multiplication,to address the growing demand for computing resources and capacity.Photonic matrix multiplication has much potential to expand the domain of telecommunication,and artificial intelligence benefiting from its superior performance.Recent research in photonic matrix multiplication has flourished and may provide opportunities to develop applications that are unachievable at present by conventional electronic processors.In this review,we first introduce the methods of photonic matrix multiplication,mainly including the plane light conversion method,Mach–Zehnder interferometer method and wavelength division multiplexing method.We also summarize the developmental milestones of photonic matrix multiplication and the related applications.Then,we review their detailed advances in applications to optical signal processing and artificial neural networks in recent years.Finally,we comment on the challenges and perspectives of photonic matrix multiplication and photonic acceleration.
基金National Key Research and Development Program of China(2017YFA0305200,2019YFB2203102)National Natural Science Foundation of China(61805151,61905083)+1 种基金Natural Science Foundation of Guangdong Province(2020A1515011492)Key Technologies Research and Development Program of Shenzhen(JSGG20201102173200001)。
文摘Silicon photonic integrated devices used for nonlinear optical signal processing play a key role in ultrafast switching,computing,and modern optical communications.However,current devices suffer from limited operation speeds and low conversion efficiencies due to the intrinsically low nonlinear index of silicon.In this paper,we experimentally demonstrate enhanced optical nonlinearity in a silicon–organic hybrid slot waveguide consisting of an ultranarrow slot waveguide coated with a highly nonlinear organic material.The fabricated slot area is as narrow as 45 nm,which is,to the best of our knowledge,the narrowest slot width that has been experimentally reported in silicon slot waveguides.The nonlinear coefficient of the proposed device with a length of 3 mm is measured to be up to 1.43×10^(6) W^(-1)km^(-1).Based on the nanostructure design,the conversion efficiencies of degenerate four-wave mixing showed enhancements of more than 12 dB and 5 dB compared to those measured for an identical device without the organic material and a silicon strip waveguide,respectively.As a proof of concept,all-optical canonical logic units based on the prepared device with two inputs at 40 Gb/s are analyzed.The obtained logic results showed clear temporal waveforms and wide-open eye diagrams with error-free performance,illustrating that our device has great potential for use in high-speed all-optical signal processing and high-performance computing in the nodes and terminals of optical networks.