Method for enhanced block management
    91.
    发明授权
    Method for enhanced block management 有权
    增强块管理方法

    公开(公告)号:US07352621B2

    公开(公告)日:2008-04-01

    申请号:US11166842

    申请日:2005-06-23

    摘要: A method and apparatus is described herein for managing bad blocks/sectors in a nonvolatile memory. Upon detecting an input/output fault to a target block in a nonvolatile memory, the target block is remapped to a spare block, if the block is predicted as a bad block. Remapping is done for blocks used to store code both in serial execution code sequences and code sequences utilizing address translation. The remapping of bad blocks/sectors in nonvolatile memory allows nonvolatile memory in computer systems to be robust and resilient in handling bad blocks.

    摘要翻译: 这里描述了一种用于管理非易失性存储器中的坏块/扇区的方法和装置。 在非易失性存储器中检测到目标块的输入/输出故障时,如果块被预测为坏块,则将目标块重新映射到备用块。 用于在串行执行代码序列和使用地址转换的代码序列中存储代码的块进行重映射。 在非易失性存储器中重新映射坏块/扇区允许计算机系统中的非易失性存储器在处理坏块时具有鲁棒性和弹性。

    METHODS AND APPARATUS TO SELF-INITIALIZE A PROCESSOR
    92.
    发明申请
    METHODS AND APPARATUS TO SELF-INITIALIZE A PROCESSOR 有权
    自动初始化处理器的方法和设备

    公开(公告)号:US20080072027A1

    公开(公告)日:2008-03-20

    申请号:US11533243

    申请日:2006-09-19

    IPC分类号: G06F15/177

    CPC分类号: G06F9/4403

    摘要: Methods and apparatus are disclosed to self-initialize a processor. An example method disclosed herein detects a processor reset, receives initialization instructions from a core zone, establishes a core zone boundary, executes received initialization instructions, and publishes a data structure, the data structure comprising state information. Other embodiments are described and claimed.

    摘要翻译: 公开了方法和装置来自动初始化处理器。 这里公开的示例性方法检测处理器重置,从核心区域接收初始化指令,建立核心区域边界,执行接收到的初始化指令,并发布数据结构,该数据结构包括状态信息。 描述和要求保护其他实施例。

    System, Method and Apparatus to Accelerate Raid Operations
    93.
    发明申请
    System, Method and Apparatus to Accelerate Raid Operations 有权
    系统,方法和装置来加速突击操作

    公开(公告)号:US20080065858A1

    公开(公告)日:2008-03-13

    申请号:US11530246

    申请日:2006-09-08

    IPC分类号: G06F15/76

    摘要: A method according to one embodiment may include partitioning a plurality of core processors into a main partition comprising at least one processor core capable of executing a main operating system and an embedded partition comprising at least one different processor core configured to execute an embedded operating system. The method may also include exchanging, by the embedded partition, commands and data with a redundant array of independent disk (RAID) system coupled to the embedded partition; and generating by the embedded partition parity (P) data related to the RAID system.

    摘要翻译: 根据一个实施例的方法可以包括将多个核心处理器划分成主分区,所述主分区包括能够执行主操作系统的至少一个处理器核心和包括被配置为执行嵌入式操作系统的至少一个不同处理器核心的嵌入式分区。 该方法还可以包括通过嵌入式分区与耦合到嵌入式分区的独立盘(RAID)系统的冗余阵列交换命令和数据; 并通过与RAID系统相关的嵌入式分区奇偶校验(P)生成数据。

    System,method and apparatus to aggregate heterogeneous raid sets
    95.
    发明申请
    System,method and apparatus to aggregate heterogeneous raid sets 有权
    集成异构raid集的系统,方法和装置

    公开(公告)号:US20070239932A1

    公开(公告)日:2007-10-11

    申请号:US11394481

    申请日:2006-03-31

    IPC分类号: G06F12/16

    CPC分类号: G06F9/5077

    摘要: A method according to one embodiment may include partitioning a plurality of core processors into a main partition comprising at least one processor core capable of executing an operating system and an embedded partition comprising at least one different processor core. The main partition and embedded partition may communicate with each other through a bridge. The embedded partition of this embodiment may be capable of: mapping two or more mass storage systems, coupled to the embedded partition, into a single logical device; presenting the logical device to the bridge; and receiving at least one I/O request, generated by the main partition and directed to the logical device, and in response to the I/O request, the embedded partition may be further capable of communicating with at least one of the two or more mass storage systems using at least one communication protocol to process said I/O request; and reporting the status of the I/O request to the main partition, via the bridge.

    摘要翻译: 根据一个实施例的方法可以包括将多个核心处理器划分成主分区,所述主分区包括能够执行操作系统的至少一个处理器核心和包括至少一个不同处理器核心的嵌入式分区。 主分区和嵌入式分区可以通过网桥相互通信。 该实施例的嵌入式分区可能能够:将耦合到嵌入式分区的两个或更多个大容量存储系统映射到单个逻辑设备中; 向桥梁呈现逻辑设备; 以及接收由所述主分区生成且指向所述逻辑设备的至少一个I / O请求,并且响应于所述I / O请求,所述嵌入式分区还可以与所述两个或更多个中的至少一个进行通信 大容量存储系统使用至少一个通信协议来处理所述I / O请求; 并通过网桥向主分区报告I / O请求的状态。

    System and method to enable seamless diffusion of platform-based optimized routines via a network
    96.
    发明授权
    System and method to enable seamless diffusion of platform-based optimized routines via a network 失效
    通过网络实现基于平台的优化例程的无缝扩散的系统和方法

    公开(公告)号:US07281243B2

    公开(公告)日:2007-10-09

    申请号:US10748030

    申请日:2003-12-29

    IPC分类号: G06F9/44

    CPC分类号: G06F8/65

    摘要: A system and method to diffuse optimized libraries via a network. An optimized library including at least one optimized routine is received by a processing system via a network. The optimized routine is provided for use by an application executing on the processing system to interact with a hardware entity of the processing system.

    摘要翻译: 一种通过网络扩散优化库的系统和方法。 包括至少一个优化例程的优化库被处理系统经由网络接收。 优化的例程被提供供在处理系统上执行的应用程序使用以与处理系统的硬件实体进行交互。

    Integrated circuit capable of pre-fetching data
    98.
    发明授权
    Integrated circuit capable of pre-fetching data 有权
    能够预取数据的集成电路

    公开(公告)号:US07263579B2

    公开(公告)日:2007-08-28

    申请号:US10808182

    申请日:2004-03-24

    IPC分类号: G06F12/00

    摘要: A method according to one embodiment may include retrieving selected data from one or more mass storage devices, based at least in part on historical device access information of at least one requester of data. A method according to another embodiment may include retrieving, by an integrated circuit, device data layout information from one or more mass storage devices, and storing, by the integrated circuit, the device data layout information in cache memory. Of course, many alternatives, variations, and modifications are possible without departing from this embodiment.

    摘要翻译: 根据一个实施例的方法可以包括至少部分地基于至少一个数据请求者的历史设备访问信息来从一个或多个大容量存储设备检索所选择的数据。 根据另一实施例的方法可以包括通过集成电路检索来自一个或多个大容量存储设备的设备数据布局信息,并且由集成电路将设备数据布局信息存储在高速缓冲存储器中。 当然,在不偏离本实施例的情况下,可以进行许多替代,变化和修改。

    Method for distributed update of firmware across a clustered platform infrastructure
    99.
    发明授权
    Method for distributed update of firmware across a clustered platform infrastructure 有权
    集群平台基础设施上固件的分布式更新方法

    公开(公告)号:US07222339B2

    公开(公告)日:2007-05-22

    申请号:US10460922

    申请日:2003-06-13

    IPC分类号: G06F9/44 G06F9/445

    CPC分类号: G06F8/65

    摘要: Methods, apparatus, and systems for updating firmware for clustered computing platforms. Firmware provided on each platform is loaded for operating system runtime availability. The firmware update process begins by issuing an update directive that includes firmware update data to a first platform. That platform then interacts with firmware running on other platforms to update the firmware for those platforms, wherein communications between the platforms is enabled via an out-of-band (OOB) communication channel or network. In one embodiment, OOB communications are facilitated by a hidden execution mode known as the System Management Mode (SMM), which has the ability to receive and respond to periodic System Management Interrupts (SMI) and execute corresponding SMI handlers configured to support inter-platform communication in a manner that is transparent to operating systems running on the platforms. The method allows firmware to be updated across multiple platforms, such as server blades, using a single administrative action.

    摘要翻译: 用于更新集群计算平台固件的方法,装置和系统。 加载每个平台上提供的固件可用于操作系统运行时可用性。 固件更新过程开始于向第一平台发布包含固件更新数据的更新指令。 然后该平台与在其他平台上运行的固件进行交互,以更新这些平台的固件,其中通过带外(OOB)通信信道或网络启用平台之间的通信。 在一个实施例中,通过被称为系统管理模式(SMM)的隐藏执行模式来促进OOB通信,所述系统管理模式(SMM)具有接收和响应周期性系统管理中断(SMI)并且执行配置为支持平台间的对应SMI处理程序 以对平台上运行的操作系统透明的方式进行通信。 该方法允许使用单一管理操作在多个平台(如服务器刀片)上更新固件。

    Pushing capabilities into firmware by an operating system
    100.
    发明授权
    Pushing capabilities into firmware by an operating system 有权
    通过操作系统将功能推入固件

    公开(公告)号:US07185190B2

    公开(公告)日:2007-02-27

    申请号:US10748458

    申请日:2003-12-29

    IPC分类号: G06F15/177 G06F9/24

    CPC分类号: G06F9/4411

    摘要: A method and system to push capabilities into firmware by an operating system. A pre-boot driver is accessed at a computer system during operating system runtime of the computer system. The pre-boot driver is deposited in a repository available to firmware of the computer system. The pre-boot driver is found at the repository by the firmware during a subsequent pre-boot phase of the computer system. The pre-boot driver is executed during the subsequent pre-boot phase. In one embodiment, the computer system includes firmware that operates in accordance with the Extensible Firmware Interface (EFI) framework standard.

    摘要翻译: 一种通过操作系统将功能推送到固件的方法和系统。 在计算机系统的操作系统运行期间,计算机系统可以访问预引导驱动程序。 预引导驱动程序存储在可用于计算机系统固件的存储库中。 在计算机系统的后续预引导阶段期间,固件会在存储库中找到预引导驱动程序。 预引导驱动程序在后续的预引导阶段执行。 在一个实施例中,计算机系统包括根据可扩展固件接口(EFI)框架标准操作的固件。