Systems and methods for performing matrix operations using a path-number balanced optical network are provided. The optical network is formed as an array including active optical components and passive optical components arranged at a substantially central location of the array. The optical network includes at least NM active optical components which are used to implement a first matrix of any size N×M by embedding the first matrix in a second matrix of a larger size. The optical network performs matrix-vector and matrix-matrix operations by propagating one or more pluralities of optical signals corresponding to an input vector through the optical network.

Examples described herein generally relate to performing conformance testing of a computational operation. A reference result including one or more reference intermediate products and a reference accumulator output at a first level of precision can be generated for the computational operation and based on one or more inputs. A hardware result can similarly be created using hardware at a second level of precision. The reference result can be compared to the hardware result to determine a variance value. A conformance result can be output based on whether the variance value is within a threshold range.

A system for parallel photonic computation, preferably including a source module, a plurality of input modulator units, an optical interference unit (OIU), and a plurality of detector banks. An OIU, preferably including one or more unitary matrix modules and optionally including a diagonal matrix module. An input modulator, which can include one or more waveguides, couplers, and/or modulator banks. A method for parallel photonic computing, preferably including encoding input vectors, performing a desired matrix operation, and receiving output values, and optionally including performing electronic computations and/or performing further optical computations based on the outputs, which can function to compute the results of a matrix operation on many different input vectors in parallel.

An arrangement for use in a matrix-vector-multiplier, comprising a stack of material layers arranged on a substrate, and a waveguide element formed in at least one material layer in the stack is disclosed. In one aspect, the arrangement further comprises a transducer arrangement which is coupled to the waveguide element. The transducer arrangement is configured to generate and detect spin wave(s) in the waveguide element, and wherein the waveguide element is configured to confine and to provide interference of the at spin wave(s) propagating therein. The arrangement further comprises a control mechanism comprising at least one control element coupled to the waveguide element, and a direct current electric source coupled to the at least one control element. The control mechanism, via the at least one control element, is configured to modify the phase velocity of the spin wave(s) propagating in the waveguide element.

A method of performing a multiplication operation in the optical domain using a device (100) comprising: an optical waveguide (101), and a modulating element (102) that is optically coupled to the optical waveguide (101), the modulating element (102) modifying a transmission, reflection or absorption characteristic of the waveguide (101) dependant on its state, wherein the state of the modulating element (102) is adjustable by a write signal (103). The method comprises: encoding a first value to the write signal (103), using the write signal (103) to map the first value to a state of the modulating element (102); encoding a second value to a read signal (104); producing an output signal intensity as the transmitted or reflected read signal, wherein the product of the first value and the second value is encoded in the output signal intensity.

Systems and methods that include: providing input information in an electronic format; converting at least a part of the electronic input information into an optical input vector; optically transforming the optical input vector into an optical output vector based on an optical matrix multiplication; converting the optical output vector into an electronic format; and electronically applying a non-linear transformation to the electronically converted optical output vector to provide output information in an electronic format. In some examples, a set of multiple input values are encoded on respective optical signals carried by optical waveguides. For each of at least two subsets of one or more optical signals, a corresponding set of one or more copying modules splits the subset of one or more optical signals into two or more copies of the optical signals. For each of at least two copies of a first subset of one or more optical signals, a corresponding multiplication module multiplies the one or more optical signals of the first subset by one or more matrix element values using optical amplitude modulation. For results of two or more of the multiplication modules, a summation module produces an electrical signal that represents a sum of the results of the two or more of the multiplication modules.

A system comprises a processor, and a resistive processing resistive processing unit coupled to the processor. The resistive processing unit comprises an array of cells, wherein the cells respectively comprise resistive memory devices, wherein at least a portion of the resistive memory devices are programmable to store weight values of a given matrix in the array of cells. The processor is configured to store the given matrix in the array of cells of the resistive processing unit, and perform a calibration process to generate a first set of calibration parameters for calibrating forward pass matrix-vector multiplication operations performed on the stored matrix in the array of cells of the resistive processing unit, and a second set of calibration parameters for calibrating backward pass matrix-vector multiplication operations performed on a transpose of the stored matrix in the array of cells of the resistive processing unit.

Systems and methods for performing matrix operations using a path-number balanced optical network are provided. The optical network is formed as an array including active optical components and passive optical components arranged at a substantially central location of the array. The optical network includes at least NM active optical components which are used to implement a first matrix of any size N×M by embedding the first matrix in a second matrix of a larger size. The optical network performs matrix-vector and matrix-matrix operations by propagating one or more pluralities of optical signals corresponding to an input vector through the optical network.

Systems and methods for performing matrix operations using a path-number balanced optical network are provided. The optical network is formed as an array including active optical components and passive optical components arranged at a substantially central location of the array. The optical network includes at least NM active optical components which are used to implement a first matrix of any size N×M by embedding the first matrix in a second matrix of a larger size. The optical network performs matrix-vector and matrix-matrix operations by propagating one or more pluralities of optical signals corresponding to an input vector through the optical network.

Aspects relate to methods and systems for optical matrix calculation. An exemplary system includes at least a first light source configured to output at least a first optical output having a first wavelength, at least a second light source configured to output at least a second optical output having a second wavelength substantially different from the first wavelength, at least an optical modulator configured to modulate the at least a first optical output, at least an optical matrix multiplier configured to perform at least two matrix multiplications, a first matrix multiplication as a function of the first optical output and a second matrix multiplication as a function of the second optical output, and at least a photodetector configured to measure the at least a first optical output and the at least a second optical output.