Abstract: According to one embodiment, an arithmetic device includes one or a plurality of arithmetic units. One of the one or the arithmetic units includes a memory part including a plurality of memory regions, and an arithmetic part. At least one of the memory regions includes a line-shaped magnetic part.

Abstract: A method for concurrent reading of mixed radix DFT/IDFT data, a method for concurrent calculation of mixed radix DFT/IDFT method, an apparatus for concurrent reading of mixed radix DFT/IDFT data, and an apparatus for concurrent calculation of mixed radix DFT/IDFT. The method for concurrent reading includes: configuring dual circulation parameters according to the number of points corresponding to the number of series to be computed and the number of points corresponding to the number of series accomplished; then, determining the value size between the maximum number of concurrently read data and the product of the number of points corresponding to the number of series accomplished; and based on the result of determination, calculating the dual circulation parameters corresponding thereto according to the result of determination, and concurrently reading data based on the calculated dual circulation parameters.

Abstract: A binary logic circuit for determining y=x mod(2m?1), where x is an n-bit integer, y is an m-bit integer, and n>m, includes reduction logic configured to reduce x to a sum of a first m-bit integer ? and a second m-bit integer ?; and addition logic configured to calculate an addition output represented by the m least significant bits of the following sum right-shifted by m: a first binary value of length 2m, the m most significant bits and the m least significant bits each being the string of bit values represented by ?; a second binary value of length 2m, the m most significant bits and the m least significant bits each being the string of bit values represented by ?; and the binary value 1.

Abstract: A random code generator is installed in a semiconductor chip and includes a PUF cell array, a control circuit and a verification circuit. The PUF cell array includes m×n PUF cells. The control circuit is connected with the PUF cell array. While a enroll action is performed, the control circuit enrolls the PUF cell array. The verification circuit is connected with the PUF cell array. While a verification action is performed, the verification circuit determines that p PUF cells of the PUF cell array are normal PUF cells and generates a corresponding a mapping information, wherein p is smaller than m×n. While the semiconductor chip is enabled, the control circuit reads states of the p normal PUF cells of the PUF cell array according to the mapping information and generates a random code according to the states.

Abstract: A binary logic circuit converts a number in floating point format having an exponent E of ew bits, an exponent bias B given by B=2ew-1?1, and a significand comprising a mantissa M of mw bits into a fixed point format with an integer width of iw bits and a fractional width of fw bits. The circuit includes a shifter operable to receive a significand input comprising a contiguous set of the most significant bits of the significand and configured to left-shift the significand input by a number of bits equal to the value represented by k least significant bits of the exponent to generate a shifter output, wherein min{(ew?1), bitwidth(iw?2?sy)}?k?(ew?1) where sy=1 for a signed floating point number and sy=0 for an unsigned floating point number, and a multiplexer coupled to the shifter and configured to: receive an input comprising a contiguous set of bits of the shifter output; and output the input if the most significant bit of the exponent is equal to one.

Abstract: A method, computer readable medium, and system are disclosed for rounding numerical values. A set of bits from an input value is identified as a rounding value. A second set of bits representing a second value is extracted from the input value and added with the rounding value to produce a sum. The sum is truncated to produce the rounded output value. Thus, the present invention provides a stochastic rounding technique that rounds up an input value as a function of a second value and a rounding value, both of which were obtained from the input value. When the second value and rounding value are obtained from consistent bit locations of the input value, the resulting output value is deterministic. Stochastic rounding, which is deterministic, is advantageously applicable in deep learning applications.

Abstract: An example multiply accumulate (MACC) circuit includes a multiply-accumulator having an accumulator output register, a scaler, coupled to the multiply accumulator, and a control circuit coupled to the multiply-accumulator and the scaler. The control circuit is configured to provide control data to the scaler, the control data indicative of: a most-significant bit (MSB) to least significant bit (LSB) range for selecting bit indices from the accumulator output register for implementing a first right shift; a multiplier; and a second right shift.

Abstract: An integrated circuit may include normalization circuitry that can be used when converting a fixed-point number to a floating-point number. The normalization circuitry may include at least a floating-point generation circuit that receives the fixed-point number and that creates a corresponding floating-point number. The normalization circuitry may then leverage an embedded digital signal processing (DSP) block on the integrated circuit to perform an arithmetic operation by removing the leading one from the created floating-point number. The resulting number may have a fractional component and an exponent value, which can then be used to derive the final normalized value.

Abstract: This application relates to apparatus and methods for the multiplication of signals. A multiplication circuit (100) has first and second time-encoding modulators (103a, 103b) configured to receive first and second combined signals (SC1, SC2) respectively, and generate respective first and second PWM signals (SPWM1, SPWM2), each with a cycle frequency that depends substantially on the square of the value of the input combined signal. The first combined signal (SC1) corresponds to a sum of a first and second input signals (S1, S2) and the second combined signal (SC2) corresponds to the difference between the first and second input signals (S1, S2). First and second time-decoding converters (104a, 104b) receive the first and second PWM signals and provide respective first and count values (D1, D2) based on a parameter related to the frequency of the respective first or second PWM signal.

Abstract: A combined residue circuit configured to receive data and to provide a first residue result and a second residue result. The first residue result is based on a first modulo value, and the second residue result is based on a second modulo value. The first modulo value is different than the second modulo value. The first residue result is to be used to protect data based on a first radix, and the second residue result is to be used to protect data based on a second radix different from the first radix.

Abstract: Multiple transform sizes improve video coding efficiency, but also increase the implementation complexity. Furthermore, both forward and inverse transforms need to be supported in various consumer devices. Embodiments provide a unified forward and inverse transform architecture that supports computation of both forward and inverse transforms for multiple transforms sizes using shared hardware circuits. The unified architecture exploits the symmetry properties of forward and inverse transform matrices to achieve hardware sharing across the different transform sizes and also between forward and inverse transform computations.

Abstract: Aspect of the present disclosure provide for a circuit. In an example, the circuit comprises a multiplexer having a first input, a second input, a control input, and an output. The circuit further comprises a first register having an input coupled to the output of the multiplexer and an output. The circuit further comprises a second register having an input coupled to the output of the first register and an output. The circuit further comprises a subtractor having a first input coupled to the output of the multiplexer and a second input coupled to the output of the second register. The circuit further comprises a third register having an input coupled to the output of the subtractor and an output coupled to the first input of the multiplexer.

Abstract: A tensor processing technique includes: accessing a first tensor representing interconnections of a plurality of nodes, the first tensor being a tensor of three or more dimensions; accessing a second tensor; convolving the first tensor with the second tensor to generate a convolution result tensor; and outputting at least a portion of the convolution result tensor.

Abstract: A method for compressing an initial weight matrix includes generating a first weight matrix and a second weight matrix according to the initial weight matrix where the initial weight matrix is a Kronecker product of a transposed matrix of the second weight matrix and the first weight matrix; optimizing the first and second weight matrixes to generate an optimized first weight matrix and an optimized second weight matrix; generating a processed data matrix according to an initial data matrix where the initial data matrix is vectorization of the processed data matrix; multiplying the processed data matrix by the optimized first weight matrix to generate a first product; multiplying the optimized second weight matrix by the first product to generate a second product; and vectorizing the second product. The initial weight matrix requires a larger memory space than a combined memory space of the first and second weight matrixes.

Abstract: A tensor processing technique includes: accessing a tensor, wherein the tensor: represents interconnections of nodes across one or more dimensions, comprises a plurality of matrices, and forms a plurality of vectors across at least one of the one or more dimensions; applying Fourier Transform on the tensor to obtain a plurality of harmonic matrices; performing singular value decompositions (SVDs) on the plurality of harmonic matrices to obtain a plurality of corresponding SVD results; reducing the plurality of corresponding SVD results, including selecting one or more dominant components in the plurality of corresponding SVD results to obtain one or more reduced results; and performing Inverse Fourier Transform on the one or more reduced results to obtain a de-noised tensor.

Abstract: Massively parallel neural inference computing elements are provided. A plurality of multipliers is arranged in a plurality of equal-sized groups. Each of the plurality of multipliers is adapted to, in parallel, apply a weight to an input activation to generate an output. A plurality of adders is operatively coupled to one of the groups of multipliers. Each of the plurality of adders is adapted to, in parallel, add the outputs of the multipliers within its associated group to generate a partial sum. A plurality of function blocks is operatively coupled to one of the plurality of adders. Each of the plurality of function blocks is adapted to, in parallel, apply a function to the partial sum of its associated adder to generate an output value.

Abstract: The present application discloses a data processing method and apparatus. A specific embodiment of the method includes: preprocessing received to-be-processed input data; obtaining a storage address of configuration parameters of the to-be-processed input data based on a result of the preprocessing and a result obtained by linearly fitting an activation function, the configuration parameters being preset according to curve characteristics of the activation function; acquiring the configuration parameters of the to-be-processed input data according to the storage address; and processing the result of the preprocessing of the to-be-processed input data based on the configuration parameters of the to-be-processed input data and a preset circuit structure, to obtain a processing result.

Abstract: A data processing apparatus is provided. Intermediate value generation circuitry generates an intermediate value from a first floating point number and a second floating point number. The intermediate value includes a number of leading 0s indicative of a prediction of a number of leading 0s in a difference between absolute values of the first floating point number and the second floating point number. The prediction differs by at most one from the number of leading 0s in the difference between absolute values of the first floating point number and the second floating point number. Count circuitry counts the number of leading 0s in said intermediate value and mask generation circuitry produces one or more masks using the intermediate value. The mask generation circuitry produces the one or more masks at the same time or before the count circuitry counts the number of leading 0s in the intermediate value.

Abstract: A system and method according to one embodiment are provided for random number generation based on measuring quadrature fluctuations of a single mode thermal state using an optical homodyne detector.

Abstract: An arithmetic unit includes a multiplier multiplying first and second inputs to output a multiplication result, an adder adding the third input to the multiplication result to output a multiplication addition result, a normalization shift circuit shifting the multiplication addition result left with a left shift amount, and a left shift amount prediction circuit. The adder includes a carry-save adder adding a first addition value and a first carry value to the third input and a full adder outputting the multiplication addition result. The left shift amount prediction circuit includes a leading zero count circuit generating a leading zero count, a leading one count circuit generating a leading one count, and a correction circuit correcting the leading one count to zero when NOR of respective least significant bits of the M upper order bits of the second addition value and the second carry value of the full adder is true.