Abstract: Embodiments of the inventive concept include a fast close path solution and circuit of a three path fused multiply-adder circuit. The fast close path circuit can include one or more compressors that can receive multiple operands and produce a result sum and a result carry. The close path circuit can include one or more leading zero anticipators (LZAs). The one or more LZAs can receive and process the result sum and the result carry. The close path circuit can include one or more adders. The one or more adders can receive and add the result sum and the result carry in parallel with the one or more LZAs processing the result sum and the result carry. Since the close path is the critical timing path, by performing the addition operations in parallel with the LZA and/or priority encode (PENC) operations, the logic depth and latency of the close path are reduced.

Abstract: A computing device (e.g., an FPGA or integrated circuit) processes an incoming packet comprising data to compute a Galois hash. The computing device includes a plurality of circuits, each circuit providing a respective result used to determine the Galois hash, and each circuit including: a first multiplier configured to receive a portion of the data; a first exclusive-OR gate configured to receive an output of the first multiplier as a first input, and to provide the respective result; and a second multiplier configured to receive an output of the first exclusive-OR gate, wherein the first exclusive-OR gate is further configured to receive an output of the second multiplier as a second input. In one embodiment, the computing device further comprises a second exclusive-OR gate configured to output the Galois hash, wherein each respective result is provided as an input to the second exclusive-OR gate.

Abstract: According to one general aspect, an apparatus may include a floating-point addition unit that includes a far path circuit, a close path circuit, and a final result selector circuit. The far path circuit may be configured to compute a far path result based upon either the addition or the subtraction of the two floating-point numbers regardless of whether the operands or the result include normal or denormal numbers. The close path circuit may be configured to compute a close path result based upon the subtraction of the two floating-point operands regardless of whether the operands or the result include normal or denormal numbers. The final result selector circuit may be configured to select between the far path result and the close path result based, at least in part, upon an amount of difference in the exponent portions of the two floating-point operands.

Abstract: A random number generator may include a first meta-stable inverter having an input terminal and an output terminal connected to each other and configured to generate a meta-stable voltage, an amplifier configured to amplify the meta-stable voltage, control circuitry configured to adjust a threshold voltage of the meta-stable voltage, and a sampler configured to generate a random number based on sampling the meta-stable voltage. The random number generator may be configured to be operated according to different modes of operation of a plurality of modes of operation. The amplifier may be a second meta-stable inverter configured to amplify the meta-stable voltage or include an input terminal and an output terminal that are connected to each other based on the random number generator being operated according to a first mode of operation or a second mode of operation, respectively, of the plurality of modes of operation.

Abstract: The embodiments described herein describe a chain of pattern generators organized in a ring topology. Each of the pattern generators in the chain includes asynchronous digital logic and implements an update rule that generates a bidirectional pattern within the chain of pattern generators. The asynchronous digital logic of a first pattern generator in the chain asynchronously updates a next state of the first pattern generator based on at least (a) a current state of the first pattern generator, (b) a second state of a second pattern generator that is before the first pattern generator in the chain, and (c) a third state of a third pattern generator that is after the first pattern generator in the chain.

Abstract: A method for generating a random number for use in a stochastic rounding operation is provided. The method includes executing an instruction that causes at least two operands to produce an intermediate result and incrementing a state of a random number generator. The method d further includes causing the random number generator to generate a random number in accordance with the state and producing a final result by utilizing the random number to determine a rounding of the intermediate result.

Abstract: The present invention is a data processing apparatus including a data input/output device for receiving data, a storage for storing the data received by the data input/output device, a data processing program storage for storing a data processing program that includes the steps of calculating, using a double exponential smoothing method, a first predicted value that is a predicted value of smoothed data and a second predicted value that is a predicted value of the gradient of the smoothed data, and calculating, using a double exponential smoothing method in which the second predicted value is set as input data, a third predicted value that is a predicted value of smoothed data and a fourth predicted value that is a predicted value of the gradient of the smoothed data, and a data calculation processing apparatus for performing the data processing under the data processing program.

Abstract: An arithmetic processing device includes arithmetic processing cores, and a control circuit that includes a request port accepting a request for a memory space; a processing circuit unit that executes processing of the request; a control pipeline that determines whether or not the processing is executable by the processing circuit unit on the request input through the request port, and that executes first abort processing for the request when the processing is not executable on the request, and issues the processing to the processing circuit unit when the processing is executable; and an identical-address request arbitration circuit that holds an occurrence order of requests with an identical address that is aborted due to the processing being not executable, and that executes second abort processing on those of requests input to the control pipeline which have the identical address and which are other than a leading request in the occurrence order.

Abstract: The present embodiments relate to circuitry that efficiently performs double-precision floating-point addition operations, single-precision floating-point addition operations, and fixed-point addition operations. Such circuitry may be implemented in specialized processing blocks. If desired, each specialized processing block may efficiently perform a single-precision floating-point addition operation, and multiple specialized processing blocks may be coupled together to perform a double-precision floating-point addition operation. In some embodiments, four specialized processing blocks that are arranged in a one-way cascade chain may compute the sum of two double-precision floating-point number. If desired, two specialized processing blocks that are arranged in a two-way cascade chain may compute the sum of two double-precision floating-point numbers.

Abstract: A data compression device includes an analog to digital converter (ADC) configured to convert an analog signal into a digital signal including in-phase and quadrature components; and a compressor configured to generate a 28-bit fixed-point digital signal in which bits of the in-phase and quadrature components are alternately arranged, generate an exponent bit string by comparing n most significant bits of a data bit string excluding two sign bits in the 28-bit fixed-point digital signal with preset mapping data, wherein the exponent bit string includes 4 bits, generate a mantissa bit string composed of 14 bits corresponding to up to 14th bit from a bit next to the n most significant bits of the data bit string, and generate a 20-bit floating point digital signal by combining the two sign bits, the exponent bit string, and the mantissa bit string, wherein n is a natural number equal to or greater than 2 and equal to or less than 12.

Abstract: A method for performing an operation based on at least two operands is proposed, in which steps of the operation are performed in time-randomized fashion. In addition, an apparatus, a computer program product and a computer-readable storage medium are accordingly specified.

Abstract: Examples disclosed herein relate to very large-scale integration (VLSI) list manipulation circuits. In accordance with some examples disclosed herein, a list manipulation circuit may include a progressive population count circuit to generate population count values. The population count values may be fed into various types of circuits, such as list conversion circuits, list compactor circuits, and list reordering circuits.

Abstract: Integrated circuits with specialized processing blocks are provided. The specialized processing blocks may include floating-point multiplier circuits that can be configured to support variable precision. A multiplier circuit may include a first carry-propagate adder (CPA), a second carry-propagate adder (CPA), and an associated rounding circuit. The first CPA may be wide enough to handle the required precision of the mantissa. In a bridged mode, the first CPA may borrow an additional bit from the second CPA while the rounding circuit will monitor the appropriate bits to select the proper multiplier output. A parallel prefix tree operable in a non-bridged mode or the bridged mode may be used to compute multiple multiplier outputs. The multiplier circuit may also include exponent and exception handling circuitry using various masks corresponding to the desired precision width.

Abstract: A method and computer system are provided for performing a comparison computation, e.g. for use in a check procedure for a reciprocal square root operation. The comparison computation compares a multiplication of three values with a predetermined value. The computer system performs the multiplication using multiplier logic which is configured to perform multiply operations in which two values are multiplied together. A first and second of the three values are multiplied to determine a first intermediate result, w1. The digits of w1 are separated into two portions, w1,1 and w1,2. The third of the three values is multiplied with w1,2 and the result is added into a multiplication of the third of the three values with w1,1 to thereby determine the result of multiplying the three values together. In this way the comparison is performed with high accuracy, while keeping the area and power consumption of the multiplier logic low.

Abstract: Embodiments of the present invention provide methods, computer program products, and systems for solving a linear equation system using a hardware-implemented extended solver, wherein a calculation precision is adapted in each iteration step of a solving process is provided. Embodiments of the present invention can be used to perform on-the-fly interpolations using the data associated with the highest resolution of the three-dimensional finite element voxel model to a lower resolution than the highest resolution as well as to perform solving computations of the solving process in the lower resolution.

Abstract: A method and apparatus for processing data are provided. The processor includes an input buffer, a data extractor, a multiplier, and an adder. The input buffer receives data and stores the data. The data extractor extracts kernel data corresponding to a kernel in the data from the input buffer. The multiplier multiplies the extracted kernel data by a convolution coefficient. The adder calculates a sum of multiplication results from the multiplier.

Abstract: A random number generator (RNG) is disclosed. The RNG comprises a memory bit array having a plurality of bits, wherein each bit is configured to present an initial logic state when the memory bit array is powered on; and a first folding circuit coupled to the memory bit array, wherein the first folding circuit is configured to: read initial logic states of a first bit and a second bit of the memory bit array, perform a first logic function on the initial logic state of the first bit, and perform a second logic function on the initial logic state of the second bit to contaminate the initial logic state of the second bit so as to provide an altered initial logic state of the second bit.

Abstract: Systems and methods for using single-precision floating-point operation digital signal processing (DSP) blocks in conjunction to perform double-precision floating-point operations.

Abstract: A discrete time filter, DTF, is described that comprises a summing node; N parallel branches, each branch having a set of input unit sampling capacitances where each unit sampling capacitance is independently selectively coupleable to the summing node; and an output capacitance connected to the summing node. The output capacitance has a value equal to a sum of the sampling capacitances that are to be selectively connected to the summing node; and the discrete time filter further comprises an inductance connected between the summing node and the output capacitance.

Abstract: An arithmetic processing block in which two inputs are provided for a multiplier, the block also including a pre-adder for combining the inputs to provide an additional option for a multiplier input.