Abstract: Approaches in accordance with various embodiments provide for the processing of sparse matrices for mathematical and programmatic operations. In particular, various embodiments enforce sparsity constraints for performing sparse matrix multiply-add instruction (MMA) operations. Deep neural networks can exhibit significant sparsity in the data used in operations, both in the activations and weights. The computational load can be reduced by excluding zero-valued data elements. A sparsity constraint is applied across all submatrices of a sparse matrix, providing fine-grained structured sparsity that is evenly distributed across the matrix. The matrix may then be compressed since a minimum number of elements of the matrix are known to have zero value. Matrix operations are then performed using these matrices.

Abstract: A data processor receives a first set of processor instructions for combining a first matrix with a second matrix to produce a third matrix and generates a second set of processor instructions therefrom by identifying values of non-zero elements of the first matrix stored in a memory of the data processor and determining memory locations of elements of the second matrix. An instruction of the second set of processor instructions includes a determined memory location and/or an explicit value of an identified non-zero element. The second set of processor instructions is executed by the data processor. The second set of processor instructions may be generated by just-in-time compilation of the first set of processor instructions and may include instructions of a custom instruction set architecture.

Abstract: Systems and methods of configuring an array of processors of an integrated circuit includes identifying a fast Fourier transform (FFT) matrix multiply of input data, wherein the FFT matrix multiply of the input data includes a bit-reversed input array, configuring the array of processing cores based on the bit-reversed input array, wherein the configuring the array of processing cores includes storing the input bits of the bit-reversed input array within memory circuits of distinct processing cores of an array of processing cores of the integrated circuit based on an input bit mapping that identifies a pre-determined storage location within the array of processing cores of each input bit of the bit-reversed input array, and performing matrix multiply computations between weight stages of the FFT matrix multiply and the input bits of the bit-reversed input array stored within the memory circuits of the distinct processing cores.

Abstract: The present invention relates to computing-implemented method and system that improves matrix multiplication efficiency, especially to method and system optimizing matrix multiplication using sparse basis approach. Matrices to be multiplied are organized into specially ordered vectors with zero values, facilitates speed up during linear combination computation or synthesis process.

Abstract: Phased array systems rely on the production of an exact carrier frequency to function. Reconstructing digital signals by specified amplitude and phase is accomplished explicitly by inducing frequency shifts away from a base frequency implied by phase changes. Shifting the carrier frequency of a digitally controlled phased array while preserving the timing of the individual phase pulses enables more efficient driving of the phased array system when the phase of the drive signals change dynamically in time.

Abstract: A matrix multiplication device and an operation method thereof are provided. The matrix multiplication device includes a plurality of unit circuits. Each of the unit circuits includes a multiplying-adding circuit, a first register, and a second register. A first input terminal and a second input terminal of the multiplying-adding circuit are respectively coupled to a corresponding first input line and a corresponding second input line. An input terminal and an output terminal of the first register are respectively coupled to an output terminal and a third input terminal of the multiplying-adding circuit. The second register is coupled to the first register to receive and temporarily store a multiplication accumulation result. Wherein, the second registers of the unit circuits output the multiplication accumulation results in a column direction in a first output mode, and output the multiplication accumulation results in a row direction in a second output mode.

Abstract: A signal processing method performed by a processor of a signal processing device and includes: generating a fundamental matrix according to at least one set of fundamental coefficients; generating a phase-shifted matrix according to a predetermined phase shift and the fundamental matrix; and generating an output sequence according to an input sequence and the phase-shifted matrix. The set of fundamental coefficients is used to generate at least one bit of a code sequence, the output sequence is a phase-shifted version of the input sequence being shifted by k cycle(s), and k is the predetermined phase shift.

Abstract: Methods and devices, the method including receiving a matrix of a neural network model; classifying at least a portion of the matrix as a first section based on a first distribution pattern of non-zero elements of the portion of the matrix; and identifying memory addresses of the non-zero elements in the first section of the matrix for loading, according to a first order determined based on the first distribution pattern, the non-zero elements in the first section into one or more vector registers.

Abstract: Example implementations relate to assigning dependent matrix-vector multiplication (MVM) operations to consecutive crossbars of a dot product engine (DPE). A method can comprise grouping a first MVM operation of a computation graph with a second MVM operation of the computation graph where the first MVM operation is dependent on a result of the second MVM operation, assigning a first crossbar of a DPE to an operand of the first MVM operation, and assigning a second crossbar of the DPE to an operand of the second MVM operation, wherein the first and second crossbars are consecutive.

Abstract: The disclosure is directed at a method of data compression using inferred data. By determining the number of leading zeroes for each data structure, a general header presenting all leading zeros can be generated and use to compress the data.

Abstract: Various arrangements for performing successive vector-matrix multiplication may include sequentially performing a first vector-matrix multiplication operation for each bit-order of values in an input vector. The first vector-matrix multiplication operation for each bit-order may generate an analog output. For each analog output generated by the vector-matrix multiplication operation, an analog output may be converted into one or more digital bit values, and the one or more digital bit values may be sent to a second vector-matrix multiplication operation.

Abstract: Systems, apparatuses, and methods implementing a hybrid matrix multiplication pipeline are disclosed. A hybrid matrix multiplication pipeline is able to execute a plurality of different types of instructions in a plurality of different formats by reusing execution circuitry in an efficient manner. For a first type of instruction for source operand elements of a first size, the pipeline uses N multipliers to perform N multiplication operations on N different sets of operands, where N is a positive integer greater than one. For a second type of instruction for source operand elements of a second size, the N multipliers work in combination to perform a single multiplication operation on a single set of operands, where the second size is greater than the first size. The pipeline also shifts element product results in an efficient manner when implementing a dot product operation.

Abstract: A disclosed apparatus to multiply matrices includes a compute engine. The compute engine includes multipliers in a two dimensional array that has a plurality of array locations defined by columns and rows. The apparatus also includes a plurality of adders in columns. A broadcast interconnect between a cache and the multipliers broadcasts a first set of operand data elements to multipliers in the rows of the array. A unicast interconnect unicasts a second set of operands between a data buffer and the multipliers. The multipliers multiply the operands to generate a plurality of outputs, and the adders add the outputs generated by the multipliers.

Abstract: The present specification provides a method for identifying risky vertices, including: constructing multiple medium networks, each of the multiple medium networks being constructed from one or more black seeds of the same type and including vertices and media connected to the vertices; determining a first risk value of each vertex based on a quantity of upper-layer media connected to the vertex and a quantity of risk conditions that the vertex meets; determining a final risk value of each vertex based on a quantity of overlapping times of the vertex in a stacked medium network structure and the first risk value; and determining a high-risk vertex based on the final risk value.

Abstract: A sum-of-products operator including: a first circuit configured to generate a plurality of signals, each of which corresponds to each of a plurality of data; a second circuit including a first operation circuit configured to multiply each of the signals generated by the first circuit by a weight using a plurality of variable resistive elements having variable resistance values, and to calculate a sum of a plurality of results of multiplications; a third circuit configured to calculate a result of summing values corresponding to the data or a result of the summing value after being adjusted; and a fourth circuit including a differential circuit configured to output a difference between a calculated result in the first operation circuit of the second circuit and a calculated result in the third circuit.

Abstract: Embodiments of the present invention disclose a matrix multiplier, and relate to the field of data computing technologies, so as to divide two matrices into blocks for computation. The matrix multiplier includes: a first memory, a second memory, an operation circuit, and a controller, where the operation circuit, the first memory, and the second memory may perform data communication by using a bus; and the controller is configured to control, according to a preset program or instruction, a first matrix and a second matrix to be divided into blocks, and control the operation circuit to perform a multiplication operation on corresponding blocks in the first memory and the second memory based on block division results of the controller. The matrix multiplier may be configured to perform a multiplication operation on two matrices.

Abstract: A hybrid data processing environment comprising a classical computing system and a quantum computing system is configured. A configuration of a first quantum circuit is produced from the classical computing system, the first quantum circuit being executable using the quantum computing system. Using the quantum computing system, the first quantum circuit is executed. Using a pattern recognition technique, a portion of the first quantum circuit that can be transformed using a first transformation operation to satisfy a constraint on the quantum circuit design is identified. The portion is transformed to a second quantum circuit according to the first transformation operation, wherein the first transformation operation comprises reconfiguring a gate in the first quantum circuit such that a qubit used in the gate complies with the constraint on the quantum circuit design while participating in the second quantum circuit. Using the quantum computing system, the second quantum circuit is executed.

Abstract: A system for analog computing, an analog computing system with sub-binary radix weight representation is provided. The analog computing system comprises an input node, a multiplexer (MUX), a digital to analog converter (DAC), a SRAM-based Sub-Binary Multiplier (SSBM), an analog to digital converter (ADC), a switch, an output node and a calibration module. The calibration module is configured to control the analog computing system to switch between a calibration mode and a normal operation mode. Prior to being switched to the normal operation mode, the analog computing system is configured to perform a process to calibrate a weight parameter stored in the SSBM. The ADC comprises a plurality of multipliers associated with a plurality of sub-binary weight radixes. The weight parameter stored in the SSBM and the plurality of sub-binary weight radixes are configured to represent a plurality of weights for the analog computing system.

Abstract: Methods and systems for performing hardware computations of mathematical functions are provided. In one example, a system comprises a mapping table that maps each base value of a plurality of base values to parameters related to a mathematical function; a selection module configured to select, based on an input value, a first base value and first parameters mapped to the first base value in the mapping table; and arithmetic circuits configured to: receive, from the mapping table, the first base value and the first plurality of parameters; and compute, based on a relationship between the input value and the first base value, and based on the first parameters, an estimated output value of the mathematical function for the input value.

Abstract: It is described a mathematical solving circuit (100) comprising: a crosspoint matrix (MG) including a plurality of row conductors (Li), a plurality of column conductors (Cj) and a plurality of analog resistive memories (Gij), each connected between a row conductor and a column conductor; a plurality of operational amplifiers (OAi) each having: a first input terminal (IN1i) connected to a respective row conductor (Li), a second input terminal (IN2i) connected to a ground terminal (GR) at least one operational amplifier (OAi) of the plurality being such to take the respective first input terminal (IN1i) to a virtual ground.