Search for: All records

Though photonic computing systems offer advantages in speed, scalability, and power consumption, they often have a limited dynamic encoding range due to low signal-to-noise ratios. Compared to digital floating-point encoding, photonic fixed-point encoding limits the precision of photonic computing when applied to scientific problems. In the case of iterative algorithms such as those commonly applied in machine learning or differential equation solvers, techniques like precision decomposition and residue iteration can be applied to increase accuracy at a greater computing cost. However, the analog nature of photonic symbols allows for modulation of both amplitude and frequency, opening the possibility of encoding both the significand and exponent of floating-point values on photonic computing systems to expand the dynamic range without expending additional energy. With appropriate schema, element-wise floating-point multiplication can be performed intrinsically through the interference of light. Herein, we present a method for configurable, signed, floating-point encoding and multiplication on a limited precision photonic primitive consisting of a directly modulated Mach–Zehnder interferometer. We demonstrate this method using Newton's method to find the Golden Ratio within ±0.11%, with six-level exponent encoding for a signed trinary digit-equivalent significand, corresponding to an effective increase of 243× in the photonic primitive's dynamic range. 

We present a method for configurable, signed, floating-point encoding and multiplication on limited precision photonic primitives, demonstrating Newton’s method with improved accuracy and expanding the dynamic range of the photonic solver by over 200×. 

We present an inversely designed integrated photonic dot-product core based on mode-division multiplexing. The core features a 5µm×3µm footprint for scalability and can perform general-purpose vector dot-products with easily reconfigurable inputs for various computing applications. 

A coherent multi-dimensional photonic tensor accelerator performing high-speed matrix-matrix multiplication is proposed and demonstrated. A pattern recognition experiment is demonstrated at a 25Gbps modulation speed exploiting orthogonal dimensions of light including time, wavelength, and spatial mode. 

We propose a coherent multi-dimensional (wavelength, spatial mode, polarization, etc.) photonic tensor accelerator capable of matrix-vector, matrix-matrix, and batch matrix multiplications in a single clock cycle. A proof-of-concept 2x2 matrix-matrix multiplication at 25GBd with 4.67 bit precision was experimentally demonstrated. 

Mode-group multiplexing (MGM) can increase the capacity of short-reach few-mode optical fiber communication links while avoiding complex digital signal processing. In this paper, we present the design and experimental demonstration of a novel mode-group demultiplexer (MG DeMux) using Fabry-Perot (FP) thin-film filters (TFFs). The MG DeMux supports low-crosstalk mode-group demultiplexing, with degeneracies commensurate with those of graded-index (GRIN) multimode fibers. We experimentally demonstrate this functionality by using a commercial six-cavity TFF that was intended for 100 GHz channel spaced wavelength-division multiplexing (WDM) system. 

Abstract Accurate characterization of an attosecond pulse from streaking trace is an indispensable step in studying the ultrafast electron dynamics on the attosecond scale. Conventional attosecond pulse retrieval methods face two major challenges: the ability to incorporate a complete physics model of the streaking process, and the ability to model the uncertainty of pulse reconstruction in the presence of noise. Here we propose a pulse retrieval method based on conditional variational generative network (CVGN) that can address both demands. Instead of learning the inverse mapping from a streaking trace to a pulse profile, the CVGN models the distribution of the pulse profile conditioned on a given streaking trace measurement, and is thus capable of assessing the uncertainty of the retrieved pulses. This capability is highly desirable for low-photon level measurement, which is typical in attosecond streaking experiments in the water window X-ray range. In addition, the proposed scheme incorporates a refined physics model that considers the Coulomb-laser coupling and photoelectron angular distribution in streaking trace generation. CVGN pulse retrievals under various simulated noise levels and experimental measurement have been demonstrated. The results showed high pulse reconstruction consistency for streaking traces when peak signal-to-noise ratio (SNR) exceeds 6, which could serve as a reference for future learning-based attosecond pulse retrieval.