HBM based memory lookup engine for deep learning accelerator

    公开(公告)号:US12056379B2

    公开(公告)日:2024-08-06

    申请号:US18315821

    申请日:2023-05-11

    CPC classification number: G06F3/064 G06F3/0604 G06F3/0673 G06N3/08

    Abstract: A storage device and method of controlling a storage device are disclosed. The storage device includes a host, a logic die, and a high bandwidth memory stack including a memory die. A computation lookup table is stored on a memory array of the memory die. The host sends a command to perform an operation utilizing a kernel and a plurality of input feature maps, includes finding the product of a weight of the kernel and values of multiple input feature maps. The computation lookup table includes a row corresponding to a weight of the kernel, and a column corresponding to a value of the input feature maps. A result value stored at a position corresponding to a row and a column is the product of the weight corresponding to the row and the value corresponding to the column.

    HBM based memory lookup engine for deep learning accelerator

    公开(公告)号:US11681451B2

    公开(公告)日:2023-06-20

    申请号:US17473532

    申请日:2021-09-13

    CPC classification number: G06F3/064 G06F3/0604 G06F3/0673 G06N3/08

    Abstract: A storage device and method of controlling a storage device are disclosed. The storage device includes a host, a logic die, and a high bandwidth memory stack including a memory die. A computation lookup table is stored on a memory array of the memory die. The host sends a command to perform an operation utilizing a kernel and a plurality of input feature maps, includes finding the product of a weight of the kernel and values of multiple input feature maps. The computation lookup table includes a row corresponding to a weight of the kernel, and a column corresponding to a value of the input feature maps. A result value stored at a position corresponding to a row and a column is the product of the weight corresponding to the row and the value corresponding to the column.

    MEMORY LOOKUP COMPUTING MECHANISMS
    25.
    发明申请

    公开(公告)号:US20220164187A1

    公开(公告)日:2022-05-26

    申请号:US17538556

    申请日:2021-11-30

    Abstract: According to some example embodiments of the present disclosure, in a method for a memory lookup mechanism in a high-bandwidth memory system, the method includes: using a memory die to conduct a multiplication operation using a lookup table (LUT) methodology by accessing a LUT, which includes floating point operation results, stored on the memory die; sending, by the memory die, a result of the multiplication operation to a logic die including a processor and a buffer; and conducting, by the logic die, a matrix multiplication operation using computation units.

    MEMORY LOOKUP COMPUTING MECHANISMS
    27.
    发明申请

    公开(公告)号:US20190196953A1

    公开(公告)日:2019-06-27

    申请号:US15913758

    申请日:2018-03-06

    CPC classification number: G06F12/0207 G06F9/3001 G06F17/16 G06F2212/1024

    Abstract: According to some example embodiments of the present disclosure, in a method for a memory lookup mechanism in a high-bandwidth memory system, the method includes: using a memory die to conduct a multiplication operation using a lookup table (LUT) methodology by accessing a LUT, which includes floating point operation results, stored on the memory die; sending, by the memory die, a result of the multiplication operation to a logic die including a processor and a buffer; and conducting, by the logic die, a matrix multiplication operation using computation units.

Patent Agency Ranking