CONTROL OF MACHINE-LEARNING SYSTEMS

    公开(公告)号:US20220413721A1

    公开(公告)日:2022-12-29

    申请号:US17852059

    申请日:2022-06-28

    申请人: Google LLC

    IPC分类号: G06F3/06 G06F7/544

    摘要: A method includes: receiving control data at a first data selector of a plurality of data selectors, in which the control data comprises (i) a configuration registry address specifying a location in a configuration state registry and (ii) configuration data specifying a circuit configuration state of a circuit element of a computational circuit; transferring the control data, from the first data selector, to an entry in a trigger table registry; responsive to a first trigger event occurring, transferring the configuration data to the location in the configuration state registry specified by the configuration registry address; and updating a state of the circuit element based on the configuration data.

    EXPLICIT SCHEDULING OF ON-CHIP OPERATIONS

    公开(公告)号:US20220326988A1

    公开(公告)日:2022-10-13

    申请号:US17635772

    申请日:2020-08-14

    申请人: Google LLC

    摘要: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a first schedule, for a first hardware block of an integrated circuit device, where the first schedule identifies a first set of operations to be performed by the first hardware block. Obtaining a second schedule for a second hardware block of the integrated circuit device, where the second schedule identifies a second set of operations to be performed by the second hardware block and where operations of the second schedule are coordinated with operations of the first schedule such that the first schedule triggers the first hardware block to send data to the second block at a first pre-scheduled value of a counter, and the second schedule triggers the second hardware block to accept the data at an input at a second pre-scheduled value of the counter that is after the first pre-scheduled value. Performing, by the first hardware block, the first set of operations according to the first schedule, and performing, by the second hardware block, the second set of operations according to the second schedule.

    Dynamic partitioning
    5.
    发明授权

    公开(公告)号:US11361051B1

    公开(公告)日:2022-06-14

    申请号:US16725811

    申请日:2019-12-23

    申请人: Google LLC

    摘要: A matrix computation unit includes a systolic array of cells arranged along a first and second dimension, in which the systolic array of cells includes a first multiple of cells, each cell of the first multiple of cells including: a weight register configured to store a weight input; multiple activation registers, each activation register of the multiple activation registers configured to store a corresponding activation input; multiplexer circuitry communicatively coupled to the multiple activation registers and configured to select, from the multiple activation registers, one of the activation inputs as a selected activation input; and multiplication circuitry communicatively coupled to the weight register and to the multiplexer, in which the multiplication circuitry is configured to output a product of the weight input and the selected activation input.