Dynamic allocation for efficient management of variable sized data within a nonvolatile memory
    1.
    发明授权
    Dynamic allocation for efficient management of variable sized data within a nonvolatile memory 失效
    用于在非易失性存储器内高效管理可变大小数据的动态分配

    公开(公告)号:US06226728B1

    公开(公告)日:2001-05-01

    申请号:US09063954

    申请日:1998-04-21

    IPC分类号: G06F1206

    摘要: A method of storing data in a nonvolatile memory includes the step of receiving the data to be stored. A storage structure is selected for the data according to the relative size (z) of the data with respect to a plurality of thresholds including: a minimum number of instances (m), a maximum single instance size (s*g), and an allocation granularity (g). The data is then stored in the selected structure within the nonvolatile memory. If z is less than a first threshold, the data is stored within a multiple instance object structure. If z is less than a second threshold, the data is stored as a single instance object. If z exceeds the second threshold, the data is fragmented. The fragmented data can then be stored among the plurality of blocks of nonvolatile memory. If the number of fragments is less than a maximum sequence table size, then a sequence table indicative of the order and the locations of the data fragments is stored in the nonvolatile memory. If the number of data fragments exceeds the maximum sequence table size, then a plurality of sequence table fragments and a group table are stored in the nonvolatile memory. The group table indicates the order and the location of the sequence table fragments which in turn indicate the order and the location of the data fragments within the nonvolatile memory.

    摘要翻译: 将数据存储在非易失性存储器中的方法包括接收要存储的数据的步骤。 根据数据相对于多个阈值的相对大小(z)为数据选择存储结构,包括:最小实例数(m),最大单个实例大小(s * g)和 分配粒度(g)。 然后将数据存储在非易失性存储器内的所选结构中。 如果z小于第一阈值,则数据存储在多个实例对象结构中。 如果z小于第二个阈值,则将数据存储为单个实例对象。 如果z超过第二个阈值,数据将被分段。 分段数据然后可以存储在多个非易失性存储器块中。 如果片段数小于最大序列表大小,则表示数据片段的顺序和位置的序列表被存储在非易失性存储器中。 如果数据片段数超过最大序列表大小,则多个序列表片段和组表存储在非易失性存储器中。 组表指示序列表片段的顺序和位置,其依次表示数据片段在非易失性存储器内的顺序和位置。

    Increased reliability of data stored on flash memory in applications sensitive to power-loss
    2.
    发明授权
    Increased reliability of data stored on flash memory in applications sensitive to power-loss 失效
    在对功率损耗敏感的应用中,存储在闪存中的数据的可靠性提高

    公开(公告)号:US06839823B1

    公开(公告)日:2005-01-04

    申请号:US09675578

    申请日:2000-09-29

    IPC分类号: G06F12/02 G06F12/12

    摘要: Methods for storing data in an erasable nonvolatile memory are described herein. In one embodiment, an example method includes allocating a space within a block of an erasable nonvolatile memory for an object, wherein the allocated space is within a single block of the erasable nonvolatile memory and the allocated space includes a plurality of areas capable of storing multiple instances of the object, storing a first instance of the object in one of the areas within the allocated space, storing a superseding second instance of the object in another one of the areas within the allocated space without erasing any of the allocated space, and for each of the first and second instances of the object, storing status information corresponding to the respective instance of the object within the allocated space which is within the single block of the erasable nonvolatile memory.

    摘要翻译: 这里描述了将数据存储在可擦除非易失性存储器中的方法。 在一个实施例中,示例性方法包括在对象的可擦除非易失性存储器的块的块内分配空间,其中所分配的空间在可擦除非易失性存储器的单个块内,并且所分配的空间包括能够存储多个的多个区域 将对象的第一实例存储在所分配的空间中的一个区域中,将对象的替代的第二实例存储在所分配的空间中的另一个区域中,而不擦除所分配的空间中的任何一个,并且为 对象的第一和第二实例中的每一个,存储与在可擦除非易失性存储器的单个块内的分配的空间内的对象的相应实例相对应的状态信息。