With the proliferation of ultra-high-speed mobile networks and internet-connected devices, along with the rise of artificial intelligence, the world is generating exponentially increasing amounts of data-data that needs to be processed in a fast, efficient and 'smart' way. These developments are pushing the limits of existing computing paradigms, and highly parallelized, fast and scalable hardware concepts are becoming progressively more important. Here, we demonstrate a computational specific integrated photonic tensor core-the optical analog of an ASIC-capable of operating at Tera-Multiply-Accumulate per second (TMAC/s) speeds. The photonic core achieves parallelized photonic inmemory computing using phase-change memory arrays and photonic chip-based optical frequency combs (soliton microcombs). The computation is reduced to measuring the optical transmission of reconfigurable and non-resonant, i.e. broadband, passive components operating at a bandwidth exceeding 14 GHz, limited only by the speed of the modulators and photodetectors. Given recent advances in hybrid integration of soliton microcombs at microwave line rates, ultra-low loss silicon nitride waveguides, and high speed on-chip detectors and modulators, our approach provides a path towards full CMOS wafer-scale integration of the photonic tensor core. While we focus on convolution processing, more generally our results indicate the major potential of integrated photonics for parallel, fast, efficient and wafer-scale manufacturable computational hardware in demanding AI applications such as autonomous driving, live video processing, and next generation cloud computing services.The increased demand for machine learning on very large datasets 1 and the growing offering of artificial intelligence services on the cloud 2-4 has driven a resurgence in custom hardware designed to accelerate multiply and accumulate (MAC) computations-the fundamental mathematical element needed for matrix-vector multiplication (MVM) operations. Whilst various custom silicon computing hardware (i.e. FPGAs 5 , ASICs 6 , and GPUs 7 ) have been developed to improve computational throughput and efficiency, they still depend on the same underlying electrical components which are fundamentally limited in both speed and energy by Joule heating, RF crosstalk, and capacitance 8 . The last of these (capacitance) dominates energy consumption and limits the maximum operating speeds in neural network hardware accelerators 9 since the movement of data (e.g. trained network weights), rather than arithmetic operations, requires the charging and discharging of chip-level metal interconnects. Thus, improving the efficiency of logic gates at the device level provides diminutive returns in such applications, if the flow of data during computation is not simultaneously addressed 10 . Even recent developments in the use of memristive crossbar arrays [11][12][13] to compute in the analog domain, whilst promising, do not have the potential for parallelizing the MVM operations (save for physically repli...

No abstract

No abstract

One of the essential prerequisites for detection of Earth-like extra-solar planets or direct measurements of the cosmological expansion is the accurate and precise wavelength calibration of astronomical spectrometers. It has already been realized that the large number of exactly known optical frequencies provided by laser frequency combs (astrocombs) can significantly surpass conventionally used hollow-cathode lamps as calibration light sources. A remaining challenge, however, is generation of frequency combs with lines resolvable by astronomical spectrometers. Here we demonstrate an astrocomb generated via soliton formation in an on-chip microphotonic resonator (microresonator) with a resolvable line spacing of 23.7 GHz. This comb is providing wavelength calibration on the 10 cm/s radial velocity level on the GIANO-B high-resolution near-infrared spectrometer. As such, microresonator frequency combs have the potential of providing broadband wavelength calibration for the next-generation of astronomical instruments in planet-hunting and cosmological research.The existence of life on other planets and the evolution of our Universe are questions that extend far beyond a purely astronomical context into other domains of science and society. Observational contributions relevant to both questions can be made by measuring minute wavelength shifts of spectral features in astronomical objects. For instance, an Earth-like planet, too faint for a direct observation, can reveal its presence by periodically modifying the radial velocity of its host star and hence Doppler-shifting characteristic features in the stellar spectrum 1,2 . Similarly, it has been suggested that the changing expansion rate of the Universe could be directly measured by observing the cosmological redshift in distant quasars 3,4 . The major challenge for such measurements is the requirement of a precisely and accurately calibrated astronomical spectrometer capable of detecting frequency shifts equivalent to radial velocities of the order of 10 cm/s or smaller. Conventional approaches of spectrometer calibration typically rely on the emission lines of hollow-cathode gas lamps that are used as calibration markers. However, the limited stability over time, the sparsity and different intensities of emission lines as well as the sensitivity to line blending impose limitations that are incompatible with the observational requirements. Over the last decade it has been realized that laser frequency combs (LFCs) 5-11 provide new means of wavelength calibration with unprecedented accuracy and precision 12-15 . Such LFCs are typically derived from mode-locked lasers and consist of large sets of laser lines whose optical frequencies ν n are equidistantly spaced: nu n = n * f rep + f 0 (n is an integer number). The two parameters f rep and f 0 are radio-frequencies (RF) accessible by conventional electronics and refer to the pulse repetition rate and carrier-envelope offset frequency of the mode-locked laser.Via self-referencing and stabilization schemes, f rep and ...

Microcombs provide a path to broad-bandwidth integrated frequency combs with low power consumption, which are compatible with wafer-scale fabrication. Yet, electrically-driven, photonic chip-based microcombs are inhibited by the required high threshold power and the frequency agility of the laser for soliton initiation. Here we demonstrate an electrically-driven soliton microcomb by coupling a III–V-material-based (indium phosphide) multiple-longitudinal-mode laser diode chip to a high-Q silicon nitride microresonator fabricated using the photonic Damascene process. The laser diode is self-injection locked to the microresonator, which is accompanied by the narrowing of the laser linewidth, and the simultaneous formation of dissipative Kerr solitons. By tuning the laser diode current, we observe transitions from modulation instability, breather solitons, to single-soliton states. The system operating at an electronically-detectable sub-100-GHz mode spacing requires less than 1 Watt of electrical power, can fit in a volume of ca. 1 cm3, and does not require on-chip filters and heaters, thus simplifying the integrated microcomb.