Computational accuracy in a crossbar array

    公开(公告)号:US10482940B2

    公开(公告)日:2019-11-19

    申请号:US16062578

    申请日:2015-12-17

    Abstract: Example implementations of the present disclosure relate to improved computational accuracy in a crossbar array. An example system may include a crossbar array, having a plurality of memory elements at junctions, usable in performance of computations. The example system may further include a calculate engine to calculate ideal conductance of memory elements at a plurality of junctions of the crossbar array and a determine engine to determine conductance of the memory elements at the plurality of junctions of the crossbar array. An adjust engine of the example system may be used to adjust conductance of at least one memory element to improve computational accuracy by reduction of a difference between the ideal conductance and the determined conductance of the at least one memory element.

    Double bias memristive dot product engine for vector processing

    公开(公告)号:US10109348B2

    公开(公告)日:2018-10-23

    申请号:US15522364

    申请日:2014-10-30

    Abstract: A double bias dot-product engine for vector processing is described. The dot product engine includes a crossbar array having N×M memory elements to store information corresponding to values contained in an N×M matrix, each memory element being a memristive storage device. First and second vector input registers including N voltage inputs, each voltage input corresponding to a value contained in a vector having N×1 values. The vector input registers are connected to the crossbar array to supply voltage inputs to each of N row electrodes at two locations along the electrode. A vector output register is also included to receive voltage outputs from each of M column electrodes.

    Resistive elements to operate as a matrix of probabilities

    公开(公告)号:US09847124B2

    公开(公告)日:2017-12-19

    申请号:US15500500

    申请日:2015-04-23

    CPC classification number: G11C13/0021 G06F7/588 G06F17/18 G06G7/122 G06N7/005

    Abstract: An example apparatus includes a crossbar array of signal lines and control lines. The example apparatus also includes an input controller in circuit with the control lines. The input control is to select one of the control lines. The example apparatus also includes first resistive elements connected between corresponding ones of the control lines and corresponding ones of the signal lines. The first resistive elements have first conductances set to operate as a matrix of probabilities that define a fixed transition kernel of a Markov Chain. The example apparatus also includes second resistive elements in circuit with the signal lines. The second resistive elements have second conductances set to select one of the signal lines exclusive of others of the signal lines based on a subset of the probabilities in the matrix of the probabilities.

    DOUBLE BIAS MEMRISTIVE DOT PRODUCT ENGINE FOR VECTOR PROCESSING

    公开(公告)号:US20190035463A1

    公开(公告)日:2019-01-31

    申请号:US16148468

    申请日:2018-10-01

    Abstract: A double bias dot-product engine for vector processing is described. The dot product engine includes a crossbar array having N×M memory elements to store information corresponding to values contained in an N×M matrix, each memory element being a memristive storage device. First and second vector input registers including N voltage inputs, each voltage input corresponding to a value contained in a vector having N×1 values. The vector input registers are connected to the crossbar array to supply voltage inputs to each of N row electrodes at two locations along the electrode. A vector output register is also included to receive voltage outputs from each of M column electrodes.

Patent Agency Ranking