SYSTEM AND METHOD FOR POWER REDUCTION BY SEQUESTERING AT LEAST ONE DEVICE OR PARTITION IN A PLATFORM FROM OPERATING SYSTEM ACCESS
    91.
    发明申请
    SYSTEM AND METHOD FOR POWER REDUCTION BY SEQUESTERING AT LEAST ONE DEVICE OR PARTITION IN A PLATFORM FROM OPERATING SYSTEM ACCESS 有权
    通过在操作系统访问的平台中对至少一个设备进行排序或分区进行功率降低的系统和方法

    公开(公告)号:US20120317431A1

    公开(公告)日:2012-12-13

    申请号:US13487613

    申请日:2012-06-04

    IPC分类号: G06F1/32

    摘要: In some embodiments, the invention involves a system and method relating to managing power utilization in systems having multiple processing elements. In at least one embodiment, the present invention is intended to control the sleeping/wakefulness of processing elements, as necessary, to maintain a preferred level of power utilization in the platform. Activity is routed to sequestered processing elements instead of sleeping processing elements to save power.

    摘要翻译: 在一些实施例中,本发明涉及涉及在具有多个处理元件的系统中管理功率利用的系统和方法。 在至少一个实施例中,本发明旨在根据需要控制处理元件的睡眠/觉醒,以维持平台中的优选的功率利用水平。 活动被路由到隔离处理元件,而不是睡眠处理元件以节省电力。

    OFFLOADING THE PROCESSING OF A NETWORK PROTOCOL STACK
    92.
    发明申请
    OFFLOADING THE PROCESSING OF A NETWORK PROTOCOL STACK 有权
    卸载网络协议栈的处理

    公开(公告)号:US20120030457A1

    公开(公告)日:2012-02-02

    申请号:US13253637

    申请日:2011-10-05

    IPC分类号: G06F9/00

    摘要: A computer system is partitioned during a pre-boot phase of the computer system between a first partition and a second partition, wherein the first partition to include a first processing unit and the second partition to include a second processing unit. An Input/Output (I/O) operating system is booted on the first partition. A general purpose operating system is booted on the second partition. Network transactions are issued by the general purpose operating system to be performed by the I/O operating system. The network transactions are performed by the I/O operating system.

    摘要翻译: 计算机系统在计算机系统的预引导阶段在第一分区和第二分区之间进行分区,其中第一分区包括第一处理单元,第二分区包括第二处理单元。 在第一个分区上引导输入/输出(I / O)操作系统。 通用操作系统在第二个分区上启动。 网络事务由通用操作系统由I / O操作系统执行。 网络事务由I / O操作系统执行。

    METHOD AND SYSTEM FOR HANDLING A MANAGEMENT INTERRUPT EVENT IN A MULTI-PROCESSOR COMPUTING DEVICE
    94.
    发明申请
    METHOD AND SYSTEM FOR HANDLING A MANAGEMENT INTERRUPT EVENT IN A MULTI-PROCESSOR COMPUTING DEVICE 有权
    在多处理器计算设备中处理管理中断事件的方法和系统

    公开(公告)号:US20110271142A1

    公开(公告)日:2011-11-03

    申请号:US13183179

    申请日:2011-07-14

    IPC分类号: G06F13/24 G06F11/20

    摘要: A method and system for handling a management interrupt, such as a system management interrupt (SMI) and/or a platform management interrupt (PMI), includes allocating two or more processor cores from a plurality of processor cores to form a group of management interrupt handling processor cores. Generated management interrupts are directed to this first group of processor cores and not to remaining processor cores, which forma second group. At least one of the processor cores in the first group handles the management interrupt without disrupting the current operation of the processor cores in the second group.

    摘要翻译: 用于处理诸如系统管理中断(SMI)和/或平台管理中断(PMI)的管理中断的方法和系统包括从多个处理器核分配两个或多个处理器核以形成一组管理中断 处理处理器核心。 生成的管理中断针对第一组处理器内核,而不是剩余的处理器内核,这是第二组。 第一组中的至少一个处理器内核处理管理中断,而不会中断第二组中的处理器内核的当前操作。

    OPERATING SYSTEM INDEPENDENT NETWORK EVENT HANDLING
    95.
    发明申请
    OPERATING SYSTEM INDEPENDENT NETWORK EVENT HANDLING 有权
    操作系统独立网络事件处理

    公开(公告)号:US20110154065A1

    公开(公告)日:2011-06-23

    申请号:US12645145

    申请日:2009-12-22

    IPC分类号: G06F1/00

    CPC分类号: G06F1/3206 G06F1/3209

    摘要: Methods and apparatuses for re-instantiating a firmware environment that includes one or more firmware functions available at pre-boot time when transitioning the computing device from a wake state to a sleep state. A network event received by the computing device while in a sleep state may be handled by the firmware environment independent of the operating system and without returning the entire computing device to the wake state.

    摘要翻译: 在将计算设备从唤醒状态转换到休眠状态时,重新实例化固件环境的方法和装置,其包括在预引导时可用的一个或多个固件功能。 处于睡眠状态时由计算设备接收的网络事件可以由独立于操作系统的固件环境来处理,并且不使整个计算设备返回到唤醒状态。

    Parallel memory migration
    96.
    发明授权
    Parallel memory migration 有权
    并行内存迁移

    公开(公告)号:US07941624B2

    公开(公告)日:2011-05-10

    申请号:US11528887

    申请日:2006-09-28

    IPC分类号: G06F12/00 G06F15/167

    摘要: A method and apparatus is described herein for performing parallel memory migration, as well as execution of management tasks over a plurality of management window. Handlers are dispatched to multiple resources, such as cores or threads, to determine a proper memory migration handler. Each resource, during a management mode, executes a designated memory migration handler or an instance of a memory migration handler to perform a portion of a memory migration task in parallel. A task data structure is capable of supporting tracking of portions of memory migrated. In addition the task data structure is potentially also capable of tracking management tasks through plurality of management windows to support servicing of management tasks through multiple management windows.

    摘要翻译: 本文描述了用于执行并行存储器迁移以及在多个管理窗口上执行管理任务的方法和装置。 处理程序被分派到多个资源,例如内核或线程,以确定适当的内存迁移处理程序。 每个资源在管理模式期间执行指定的存储器迁移处理程序或存储器迁移处理程序的实例,以并行地执行存储器迁移任务的一部分。 任务数据结构能够支持对已迁移的内存的部分进行跟踪。 此外,任务数据结构还能够通过多个管理窗口跟踪管理任务,以通过多个管理窗口支持对管理任务的服务。

    System and method to enable parallelization of early platform initialization
    97.
    发明授权
    System and method to enable parallelization of early platform initialization 有权
    实现早期平台初始化并行化的系统和方法

    公开(公告)号:US07882341B2

    公开(公告)日:2011-02-01

    申请号:US11967613

    申请日:2007-12-31

    IPC分类号: G06F9/00 G06F9/24 G06F15/177

    CPC分类号: G06F9/4401 G06F8/456

    摘要: In some embodiments, the invention involves reducing the time required for a platform to boot to its target application/operating-system using parallelization of firmware image content decompression and loading. An embodiment dispatches alternate processing agents as a means to intelligently assist in off-loading some of the initialization tasks so that the main processor may share the burden of boot tasks. In at least one embodiment, it is intended to build firmware images that facilitate parallelization, utilizing co-processing agents that can split these transactions across various processing agents. Other embodiments are described and claimed.

    摘要翻译: 在一些实施例中,本发明涉及使用固件图像内容解压缩和加载的并行化来减少平台引导到其目标应用/操作系统所需的时间。 一个实施例调度替代处理代理作为智能地帮助卸载某些初始化任务的手段,使得主处理器可以共享引导任务的负担。 在至少一个实施例中,旨在构建便于并行化的固件图像,利用可以跨各种处理代理分割这些事务的协处理代理。 描述和要求保护其他实施例。

    System and method for automatic update of embedded data
    98.
    发明授权
    System and method for automatic update of embedded data 有权
    自动更新嵌入式数据的系统和方法

    公开(公告)号:US07870373B2

    公开(公告)日:2011-01-11

    申请号:US11317752

    申请日:2005-12-23

    IPC分类号: G06F15/177

    CPC分类号: G06F8/65

    摘要: A system and method for maintaining computer platform components in an optimal state. The method determines whether a platform includes an out-of-band processor, and if the platform includes an out-of-band processor, then the out-of-band processor is enabled to passively or proactively obtain firmware and/or option ROM (Read Only Memory) updates for add-in cards on the platform. Once the out-of-band processor has obtained the updates for the add-in cards on the platform, the out-of-band processor will place the updates in a platform mailbox and send an interrupt to the in-band processor indicating that firmware and/or option ROM updates are available in a platform mailbox. The in-band processor will launch the firmware and/or option ROM updates on the platform.

    摘要翻译: 一种用于将计算机平台组件维持在最佳状态的系统和方法。 该方法确定平台是否包括带外处理器,并且如果平台包括带外处理器,则带外处理器被允许被动地或主动地获得固件和/或选项ROM( 只读存储器)更新平台上的附加卡。 一旦带外处理器获得了平台上附加卡的更新,带外处理器将将更新放置在平台邮箱中,并向带内处理器发送指示固件的中断 和/或选项ROM更新在平台邮箱中可用。 带内处理器将在平台上启动固件和/或选件ROM更新。

    System and method to conditionally shrink an executable module
    99.
    发明授权
    System and method to conditionally shrink an executable module 有权
    有条件地收缩可执行模块的系统和方法

    公开(公告)号:US07853742B2

    公开(公告)日:2010-12-14

    申请号:US10832789

    申请日:2004-04-26

    IPC分类号: G06F13/12 G06F15/16

    摘要: An embodiment of the present invention is a system and method relating to shrinking, or optimizing, executable images resulting is a savings of storage space. In at least one embodiment, the present invention removes unnecessary fields, or information, from an executable image header before storing the image on a flash for a target platform. The removal of information that is irrelevant to the target platform allows the executable to take up less space on the flash memory. When loaded, the image is interpreted based on the optimized header information. In an embodiment, the image may be further compressed by known methods, to save additional space. Other embodiments are described and claimed.

    摘要翻译: 本发明的一个实施例是与缩小或优化可执行图像有关的系统和方法,从而节省了存储空间。 在至少一个实施例中,本发明在将图像存储在用于目标平台的闪存上之前,从可执行映像头中去除不必要的字段或信息。 删除与目标平台无关的信息允许可执行文件占用较少的闪存空间。 加载时,基于优化的标题信息来解释图像。 在一个实施例中,可以通过已知方法进一步压缩图像,以节省额外的空间。 描述和要求保护其他实施例。

    Platform management processor assisted resume
    100.
    发明授权
    Platform management processor assisted resume 有权
    平台管理处理器辅助简历

    公开(公告)号:US07822960B2

    公开(公告)日:2010-10-26

    申请号:US11644408

    申请日:2006-12-22

    IPC分类号: G06F9/00 G06F17/30

    CPC分类号: G06F12/1458 G06F12/1408

    摘要: In some embodiments, the invention involves system and method for resuming from sleep mode using protected storage accessible to an embedded controller. The boot script information is stored in memory that is available only to the embedded controller. Neither the firmware nor OS have access to the boot script. Upon a wake event, the embedded controller either plays the boot script itself, or sends the information to firmware for processing. Other embodiments are described and claimed.

    摘要翻译: 在一些实施例中,本发明涉及使用嵌入式控制器可访问的保护存储器从休眠模式恢复的系统和方法。 引导脚本信息存储在仅适用于嵌入式控制器的存储器中。 固件和操作系统都不能访问引导脚本。 在唤醒事件时,嵌入式控制器可以自己播放引导脚本,也可以将信息发送到固件进行处理。 描述和要求保护其他实施例。