UNALIGNED DATA COALESCING
    11.
    发明申请

    公开(公告)号:US20180173621A1

    公开(公告)日:2018-06-21

    申请号:US15897797

    申请日:2018-02-15

    发明人: David A. Palmer

    IPC分类号: G06F12/02

    摘要: The present disclosure includes methods and systems for coalescing unaligned data. One method includes receiving a first write command associated with a first unaligned portion of data, receiving a second write command associated with a second unaligned portion of data, and coalescing the first unaligned portion of data and the second unaligned portion of data, wherein coalescing includes writing the first unaligned portion of data and the second unaligned portion of data to a page in a memory device.

    Write command overlap detection
    12.
    发明授权

    公开(公告)号:US09916089B2

    公开(公告)日:2018-03-13

    申请号:US14819652

    申请日:2015-08-06

    发明人: David A. Palmer

    IPC分类号: G06F12/00 G06F3/06

    摘要: The present disclosure includes methods and apparatuses that include write command overlap detection. A number of embodiments include receiving an incoming write command and comparing a logical address of the incoming write command to logical addresses of a number of write commands in a queue using a tree data structure, wherein a starting logical address and/or an ending logical address of the incoming write command and a starting logical address and/or an ending logical address of each of the number of write commands are associated with nodes in the tree data structure.

    DATA ALIGNMENT FOR LOGICAL TO PHYSICAL TABLE COMPRESSION

    公开(公告)号:US20230185728A1

    公开(公告)日:2023-06-15

    申请号:US18081474

    申请日:2022-12-14

    发明人: David A. Palmer

    IPC分类号: G06F12/1009

    CPC分类号: G06F12/1009 G06F2212/7201

    摘要: Methods, systems, and devices for data alignment for logical to physical table compression are described. A controller coupled with the memory array may receive a command to access a logical block address associated with a memory device. In some cases, a first portion of a physical address of the memory device associated with the logical block address may be identified. The controller may perform an operation on the logical block address included in the command and identify a second portion of the physical address based on performing the operation. The physical address of the memory device may be accessed based on identifying the first portion and the second portion.

    Adaptive readahead cache manager based on detected active streams of read commands

    公开(公告)号:US11360902B2

    公开(公告)日:2022-06-14

    申请号:US17103811

    申请日:2020-11-24

    发明人: David A. Palmer

    摘要: A method for managing a readahead cache in a memory subsystem based on one or more active streams of read commands is described. The method includes receiving a read command that requests data from a memory component and determining whether the read command is part of an active stream of read commands based on a comparison of a set of addresses of the read command with one or more of (1) a command history table, which stores a set of command entries that each correspond to a received read command that has not been associated with an active stream, or (2) an active stream table, which stores a set of stream entries that each corresponds to active streams of read commands. The method further includes modifying a stream entry in the set of stream entries in response to determining that the read command is part of an active stream.

    Quantization of peak power for allocation to memory dice

    公开(公告)号:US11175837B2

    公开(公告)日:2021-11-16

    申请号:US16820478

    申请日:2020-03-16

    发明人: David A. Palmer

    摘要: A method for managing power amongst a set of memory devices that are provided a peak power that is quantized into a set number of power tokens. The method includes determining that the first memory die is to change from a lower power state that requires a first number of tokens to a higher power state that requires a second number of tokens. The method further includes transmitting a message in response to determining that the sum of the second number and a third number of power tokens allocated to other memory devices in the set of memory devices satisfies a threshold number of power tokens. The message includes the second number and is transmitted on a bus that is shared by the set of memory devices.

    Peak power management of dice in a power network

    公开(公告)号:US11079829B2

    公开(公告)日:2021-08-03

    申请号:US16510696

    申请日:2019-07-12

    摘要: Exemplary methods, apparatuses, and systems include a first die in a power network receiving, from each of a plurality of dice in the power network, a first activity state value indicating that the respective die is in a high current state, a second activity state value indicating that the respective die is a moderate current state, or a third activity state value indicating that the respective die is a low current state. The received activity state values include at least one second or third activity state value. The first die determines, using the received activity state values, a first sum of the activity state values. The first die further selects an activity state based upon the first sum and sends, to the plurality of dice, an activity state value corresponding to the selected activity state.

    PEAK POWER MANAGEMENT OF DICE IN A POWER NETWORK

    公开(公告)号:US20210011538A1

    公开(公告)日:2021-01-14

    申请号:US16510696

    申请日:2019-07-12

    摘要: Exemplary methods, apparatuses, and systems include a first die in a power network receiving, from each of a plurality of dice in the power network, a first activity state value indicating that the respective die is in a high current state, a second activity state value indicating that the respective die is a moderate current state, or a third activity state value indicating that the respective die is a low current state. The received activity state values include at least one second or third activity state value. The first die determines, using the received activity state values, a first sum of the activity state values. The first die further selects an activity state based upon the first sum and sends, to the plurality of dice, an activity state value corresponding to the selected activity state.

    Unaligned data coalescing
    18.
    发明授权

    公开(公告)号:US10853238B2

    公开(公告)日:2020-12-01

    申请号:US16221846

    申请日:2018-12-17

    发明人: David A. Palmer

    IPC分类号: G06F12/02 G06F12/04

    摘要: The present disclosure includes methods and systems for coalescing unaligned data. One method includes receiving a first write command associated with a first unaligned portion of data, receiving a second write command associated with a second unaligned portion of data, and coalescing the first unaligned portion of data and the second unaligned portion of data, wherein coalescing includes writing the first unaligned portion of data and the second unaligned portion of data to a page in a memory device.

    SEQUENTIAL GARBAGE COLLECTION
    19.
    发明公开

    公开(公告)号:US20240070063A1

    公开(公告)日:2024-02-29

    申请号:US17899137

    申请日:2022-08-30

    发明人: David A. Palmer

    IPC分类号: G06F12/02

    摘要: An example apparatus for sequential garbage collection can include a memory device including a plurality of memory blocks associated with a plurality of logical block addresses (LBAs). The example apparatus can include a controller coupled to the memory device. The controller can be configured to monitor a quantity of read operations and a quantity of write operations associated with a plurality of command sizes performed on a portion of the plurality of memory blocks. The controller can be configured to monitor a quantity of read operations and a quantity of write operations associated with a particular LBA. The controller can be configured to determine a type of garbage collection operation to perform based on the monitoring.

    Power down workload estimation
    20.
    发明授权

    公开(公告)号:US11853558B2

    公开(公告)日:2023-12-26

    申请号:US17718386

    申请日:2022-04-12

    IPC分类号: G06F3/06

    摘要: Apparatuses and methods can be related power down workload estimations using artificial neural networks. Workload estimation can include predicting a duration of a subsequent power down event of the memory device. A quantity of maintenance operations to be performed on the memory device, may be predicted based on the predicted duration of the subsequent power down event, when the memory device is powered on after the subsequent power down event using an artificial neural network. The quantity of maintenance operations may be performed on the memory device prior to the subsequent power down event of the memory device.