中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

33 records (took 0.023 seconds)

    MATRIX SUMMATION USING INTEGRATED MATRICES WITH SCALAR INJECTION
    2.
    发明公开
    MATRIX SUMMATION USING INTEGRATED MATRICES WITH SCALAR INJECTION 审中-公开

    公开(公告)号：US20230367844A1

    公开(公告)日：2023-11-16

    申请号：US18225339

    申请日：2023-07-24

    Applicant: SambaNova Systems, Inc.

    Inventor： Pramod NATARAJA ,  Raghu PRABHAKAR ,  David Brian JACKSON ,  Ram SIVARAMAKRISHNAN

    IPC: G06F17/16

    CPC classification number: G06F17/16

    Abstract: A computing method comprises generating an integrated matrix having (K+P) number of columns, columns 1 through K of the integrated matrix comprising columns 1 through K of a multiplicand matrix and columns (K+1) though P of the integrated matrix comprising addend columns. The method computes K number of products of elements of a row of the integrated matrix multiplied by elements of a column of a second multiplicand matrix; computes a (K+1) product comprising an element of an addend column multiplied by a constant; and, computes a sum of the K number of products added to the (K+1) product. The sum is equivalent to a sum of products of a column of the M×K matrix multiplied by a row of the K×N matrix added to the an element of an addend column of the integrated matrix. A computing system and a computer program product can implement the method.

    RECONFIGURABLE DATAFLOW UNIT WITH STREAMING WRITE FUNCTIONALITY
    4.
    发明公开
    RECONFIGURABLE DATAFLOW UNIT WITH STREAMING WRITE FUNCTIONALITY 审中-公开

    公开(公告)号：US20240070111A1

    公开(公告)日：2024-02-29

    申请号：US18383744

    申请日：2023-10-25

    Applicant: SambaNova Systems, Inc.

    Inventor： Manish K. SHAH ,  Ram SIVARAMAKRISHNAN ,  Gregory Frederick GROHOSKI ,  Raghu PRABHAKAR

    IPC: G06F15/78 ,  G06F15/80

    CPC classification number: G06F15/7885 ,  G06F15/8023

    Abstract: A reconfigurable processing unit is disclosed, comprising a first internal network and a second internal network with different protocols, an interface to an external network with a different protocol, a first configurable unit connected to the first internal network, a second configurable unit connected to both the first internal network and the second internal network, and a third configurable unit connected to both the second internal network and the interface to the external network. The third configurable unit is configured to receive a payload from the external network and send the transaction type identifier and the source application ID to the second configurable unit over the second internal network. The second configurable unit sends information to the first configurable unit based on the transaction type identifier and the source application ID matching the local application ID retrieved from the register.

    USING INTEGRATED MATRICES IN BACK PROPAGATION COMPUTATIONS
    5.
    发明公开
    USING INTEGRATED MATRICES IN BACK PROPAGATION COMPUTATIONS 审中-公开

    公开(公告)号：US20230367845A1

    公开(公告)日：2023-11-16

    申请号：US18225365

    申请日：2023-07-24

    Applicant: SambaNova Systems, Inc.

    Inventor： Pramod NATARAJA ,  Raghu PRABHAKAR ,  David Brian JACKSON ,  Ram SIVARAMAKRISHNAN

    IPC: G06F17/16

    CPC classification number: G06F17/16

    Abstract: A method comprises executing (K+P) number of transposition cycles to generate a transpose-extended matrix having N rows and (K+P) columns, in which columns 1 to K comprise a transposition of a first matrix having K rows and N columns, and columns (K+1) to (K+P) comprise constants or elements of an N×1 matrix. The method includes computing a sum-product of a row of a second matrix, having M rows and N columns, multiplied by a column among columns 1 to K of the transpose-extended matrix; and, computing a second sum-product of the row of the second matrix multiplied by a column among columns (K+1) to (K+P) of the transpose-extended matrix. The sum-products can comprise gradients of input matrices. A transpose processing unit can execute the transposition cycles to read K rows of the first matrix and insert P number of constant or N×1 columns to generate the transpose-extended matrix.

    PEER-TO-PEER COMMUNICATION BETWEEN RECONFIGURABLE DATAFLOW UNITS
    9.
    发明公开
    PEER-TO-PEER COMMUNICATION BETWEEN RECONFIGURABLE DATAFLOW UNITS 审中-公开

    公开(公告)号：US20240073129A1

    公开(公告)日：2024-02-29

    申请号：US18383718

    申请日：2023-10-25

    Applicant: SambaNova Systems, Inc.

    Inventor： Manish K. SHAH ,  Ram SIVARAMAKRISHNAN ,  Gregory Frederick GROHOSKI ,  Raghu PRABHAKAR

    IPC: H04L45/00 ,  H04L45/44 ,  H04L45/745

    CPC classification number: H04L45/566 ,  H04L45/44 ,  H04L45/745

    Abstract: A computing system is disclosed, comprising a plurality of interconnected reconfigurable dataflow units (RDUs). Each RDU includes configurable units, internal networks, and external interfaces. The first configurable unit of the first RDU sends a request to access an external memory attached to the second RDU over its first internal network. The second configurable unit of the first RDU obtains a memory address for the request, determines an identifier for the second RDU, and sends the request, identifier, and memory address to the third configurable unit of the first RDU over its second internal network. The third configurable unit of the first RDU generates a routable address on the external network, synthesizes a payload, and sends it through an external network interface. The third configurable unit of the second RDU receives the payload, and the fourth configurable unit of the second RDU uses the address to access the external memory.

Patent Agency Ranking