利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

55 条记录 (耗时 0.035 秒)

    Dynamic affinity mapping to reduce usage of less reliable resources
    8.
    发明授权
    Dynamic affinity mapping to reduce usage of less reliable resources 有权
    动态亲和力映射以减少可靠资源的使用

    公开(公告)号：US08020165B2

    公开(公告)日：2011-09-13

    申请号：US11467600

    申请日：2006-08-28

    申请人： Madhusudhan Rangarajan ,  Allen Chester Wynn

    发明人： Madhusudhan Rangarajan ,  Allen Chester Wynn

    IPC分类号： G06F9/46 ,  G06F13/00 ,  G06F11/00

    CPC分类号： G06F9/5016

    摘要： In an information handling system, a plurality of system resources are usable by at least one processor. An affinity structure includes elements describing the relative accessibility of the plurality of system resources to the processor. An affinity manager adjusts the affinity structure in response to a least a first one of the plurality of system resources operating outside of at least one operating parameter.

    摘要翻译： 在信息处理系统中，多个系统资源可由至少一个处理器使用。 亲和度结构包括描述多个系统资源对处理器的相对可访问性的元素。 亲和力管理器响应于在至少一个操作参数之外操作的多个系统资源中的至少第一个系统资源中的至少一个来调整亲和结构。

    Systems and Methods for Logging Correctable Memory Errors
    9.
    发明申请
    Systems and Methods for Logging Correctable Memory Errors 有权
    记录可纠正内存错误的系统和方法

    公开(公告)号：US20100192029A1

    公开(公告)日：2010-07-29

    申请号：US12361814

    申请日：2009-01-29

    申请人： Bi-Chong Wang ,  Vijay Nijhawan ,  Madhusudhan Rangarajan

    发明人： Bi-Chong Wang ,  Vijay Nijhawan ,  Madhusudhan Rangarajan

    IPC分类号： G06F11/22

    CPC分类号： G06F11/2284

    摘要： In accordance with certain embodiments of the present disclosure, an information handling system is provided. The information handling system may include a plurality of processors, each processor comprising multiple cores, a memory system coupled to the plurality of processors, and a controller coupled to the plurality of processors. The controller may be configured to: receive a local system management interrupt (SMI) signal regarding an error associated with at least one of the multiple cores, determine that the received local SMI signal triggers a global SMI based on a global SMI trigger rule, cause the plurality of processors to enter a global system management mode (SMM), and log the error in a shared resource shared by the plurality of processors during the global SMM.

    摘要翻译： 根据本公开的某些实施例，提供了一种信息处理系统。 信息处理系统可以包括多个处理器，每个处理器包括多个核心，耦合到多个处理器的存储器系统以及耦合到多个处理器的控制器。 控制器可以被配置为：接收关于与多个核心中的至少一个相关联的错误的本地系统管理中断（SMI）信号，确定接收到的本地SMI信号基于全局SMI触发规则触发全局SMI，导致 所述多个处理器进入全局系统管理模式（SMM），并且在所述全局SMM期间将所述错误记录在由所述多个处理器共享的共享资源中。

    Thermal Control of Memory Modules Using Proximity Information
    10.
    发明申请
    Thermal Control of Memory Modules Using Proximity Information 有权
    使用接近信息对内存模块进行热控制

    公开(公告)号：US20090125695A1

    公开(公告)日：2009-05-14

    申请号：US12356259

    申请日：2009-01-20

    申请人： Madhusudhan Rangarajan ,  Allen Chester Wynn

    发明人： Madhusudhan Rangarajan ,  Allen Chester Wynn

    IPC分类号： G06F12/06

    CPC分类号： G06F12/0223 ,  G06F1/206 ,  G06F12/0646

    摘要： An information handling system includes a processor having access to a system memory. The system is operable to detect a thermal alert and identify an associated portion of system memory. The system may then modify memory allocation information used by an operating system to allocate system memory. When the thermal alert indicates a rising memory module temperature that exceeds a specified threshold, the modification of the memory allocation information causes the memory to appear to be more “distant” from the system processor(s) and thereby allocated less preferentially than other memory. If the temperature continues to rise beyond a higher threshold, a second modification of the memory allocation information is performed to simulate a “hot eject” of the memory module. As the memory module cools, the memory allocation information can be restored to simulate a hot add of the memory module and to restore the proximity of the memory module.

    摘要翻译： 信息处理系统包括具有对系统存储器的访问的处理器。 该系统可操作以检测热警报并识别系统存储器的相关部分。 系统然后可以修改由操作系统使用的内存分配信息来分配系统存储器。 当热警报指示上升的存储器模块温度超过指定的阈值时，存储器分配信息的修改使得存储器看起来与系统处理器更“远”，从而比其他存储器更优先地分配。 如果温度继续上升超过更高的阈值，则执行存储器分配信息的第二修改以模拟存储器模块的“热喷射”。 当存储器模块冷却时，可以恢复存储器分配信息以模拟存储器模块的热添加并恢复存储器模块的接近。