Using optimized libraries to improve performance of deployed application code at runtime
    1.
    发明授权
    Using optimized libraries to improve performance of deployed application code at runtime 有权
    使用优化的库来提高运行时部署的应用程序代码的性能

    公开(公告)号:US07657881B2

    公开(公告)日:2010-02-02

    申请号:US11019803

    申请日:2004-12-21

    IPC分类号: G06F9/45

    CPC分类号: G06F9/45516

    摘要: A method to automatically replace computationally intensive functions with optimized functions in managed code is disclosed. If the underlying processor has associated optimized functions, managed application code is disassembled and parsed to find computationally intensive functions. The computationally intensive functions are then replaced with optimized functions, and the application code is re-compiled if necessary.

    摘要翻译: 公开了一种在托管代码中自动替换具有优化功能的计算密集型函数的方法。 如果底层处理器具有关联的优化功能,则管理的应用程序代码将被拆解并解析以查找计算密集型函数。 然后用优化的功能代替计算密集型函数,如果需要,应用代码被重新编译。

    Processing secure metadata at wire speed
    2.
    发明授权
    Processing secure metadata at wire speed 有权
    以线速处理安全元数据

    公开(公告)号:US07536681B2

    公开(公告)日:2009-05-19

    申请号:US11086827

    申请日:2005-03-22

    申请人: Gururaj Nagendra

    发明人: Gururaj Nagendra

    IPC分类号: G06F9/45

    CPC分类号: G06F17/2247 G06F17/2229

    摘要: In one embodiment, the present invention includes a method for receiving an Extensible Markup Language (XML) packet at a host processor of a resource-constrained device, such as a mobile device or the like, and forwarding the XML packet to a programmable accelerator of the resource-constrained device. Then, using the programmable accelerator, the XML packet may be processed and information from the XML packet may be provided to the host processor. Other embodiments are described and claimed.

    摘要翻译: 在一个实施例中,本发明包括一种用于在资源受限设备(诸如移动设备等)的主处理器处接收可扩展标记语言(XML)分组的方法,并且将XML分组转发到可编程加速器 资源有限的设备。 然后,使用可编程加速器,可以处理XML分组,并且可以向主处理器提供来自XML分组的信息。 描述和要求保护其他实施例。

    Processing secure metadata at wire speed

    公开(公告)号:US20060218527A1

    公开(公告)日:2006-09-28

    申请号:US11086827

    申请日:2005-03-22

    申请人: Gururaj Nagendra

    发明人: Gururaj Nagendra

    IPC分类号: G06F9/44

    CPC分类号: G06F17/2247 G06F17/2229

    摘要: In one embodiment, the present invention includes a method for receiving an Extensible Markup Language (XML) packet at a host processor of a resource-constrained device, such as a mobile device or the like, and forwarding the XML packet to a programmable accelerator of the resource-constrained device. Then, using the programmable accelerator, the XML packet may be processed and information from the XML packet may be provided to the host processor. Other embodiments are described and claimed.

    Methods and apparatus to optimize managed application program interfaces
    4.
    发明授权
    Methods and apparatus to optimize managed application program interfaces 有权
    优化托管应用程序接口的方法和设备

    公开(公告)号:US07516459B2

    公开(公告)日:2009-04-07

    申请号:US10783840

    申请日:2004-02-20

    CPC分类号: G06F9/45504

    摘要: Methods and apparatus to optimized managed application program interfaces are described herein. In an example method, a processor instruction proxy stub (PIPS) associated with one or more processor instructions is generated. Based on the PIPS, an optimized managed application program interface is generated to execute the one or more processor instructions.

    摘要翻译: 本文描述了优化托管应用程序接口的方法和装置。 在示例性方法中,生成与一个或多个处理器指令相关联的处理器指令代理存根(PIPS)。 基于PIPS,生成优化的托管应用程序接口以执行一个或多个处理器指令。

    Creating managed code from native code
    5.
    发明授权
    Creating managed code from native code 有权
    从本机代码创建托管代码

    公开(公告)号:US07472375B2

    公开(公告)日:2008-12-30

    申请号:US11092355

    申请日:2005-03-29

    IPC分类号: G06F9/44 G06F9/45

    CPC分类号: G06F8/52 G06F8/76

    摘要: In one embodiment, the present invention includes a method for generating an assembly that is usable in a managed environment. More specifically, the assembly may be an all-inclusive object file that contains a native code module, a managed wrapper and prototype information in a single assembly. The method may include forming an object file from a native code module, where the object file includes prototype information, generating a managed code wrapper using the prototype information, and creating a single assembly including the managed code wrapper and the native code module. In some embodiments, the managed code wrapper may be automatically created, reducing burden on a developer. Other embodiments are described and claimed.

    摘要翻译: 在一个实施例中,本发明包括用于生成可在管理环境中使用的组件的方法。 更具体地说,组件可以是包含本体代码模块,托管包装器和单个组件中的原型信息的全包对象文件。 该方法可以包括从本地代码模块形成目标文件,其中对象文件包括原型信息,使用原型信息生成托管代码封装器,以及创建包括托管代码封装器和本机代码模块的单个程序集。 在一些实施例中,托管代码包装器可以被自动创建,从而减轻开发者的负担。 描述和要求保护其他实施例。

    Using optimized libraries to improve performance of deployed application code at runtime
    6.
    发明申请
    Using optimized libraries to improve performance of deployed application code at runtime 有权
    使用优化的库来提高运行时部署的应用程序代码的性能

    公开(公告)号:US20060136712A1

    公开(公告)日:2006-06-22

    申请号:US11019803

    申请日:2004-12-21

    IPC分类号: H04L9/00

    CPC分类号: G06F9/45516

    摘要: A method to automatically replace computationally intensive functions with optimized functions in managed code is disclosed. If the underlying processor has associated optimized functions, managed application code is disassembled and parsed to find computationally intensive functions. The computationally intensive functions are then replaced with optimized functions, and the application code is re-compiled if necessary.

    摘要翻译: 公开了一种在托管代码中自动替换具有优化功能的计算密集型函数的方法。 如果底层处理器具有关联的优化功能,则管理的应用程序代码将被拆解并解析以查找计算密集型函数。 然后用优化的功能代替计算密集型函数,如果需要,应用代码被重新编译。

    Method and apparatus to manage power consumption in a computer
    7.
    发明申请
    Method and apparatus to manage power consumption in a computer 审中-公开
    管理计算机功耗的方法和装置

    公开(公告)号:US20070192641A1

    公开(公告)日:2007-08-16

    申请号:US11351373

    申请日:2006-02-10

    IPC分类号: G06F1/26 G06F1/32

    CPC分类号: G06F1/3203

    摘要: A method and apparatus to manage power consumption in a computer have been presented. In one embodiment, the method includes registering one or more applications with a power management module in a computer, the one or more applications being operable on a virtual machine in the computer. The method may further include learning usage and behavior of the one or more applications at runtime and dynamically changing power consumption in the computer in response to at least one of the usage and the performance of the one or more applications.

    摘要翻译: 已经提出了一种管理计算机功耗的方法和装置。 在一个实施例中,该方法包括将一个或多个应用与计算机中的电源管理模块进行注册,所述一个或多个应用可在计算机中的虚拟机上操作。 所述方法还可以包括响应于所述一个或多个应用的​​使用和执行中的至少一个,在运行时学习所述一个或多个应用的​​学习使用和行为以及动态地改变所述计算机中的功耗。

    Multi-level ring peer-to-peer network structure for peer and object discovery
    8.
    发明授权
    Multi-level ring peer-to-peer network structure for peer and object discovery 有权
    用于对等和对象发现的多级环对等网络结构

    公开(公告)号:US07231463B2

    公开(公告)日:2007-06-12

    申请号:US10036466

    申请日:2002-01-04

    IPC分类号: G06F15/16 G06F15/167

    摘要: In one embodiment of the invention, a Peer-to-Peer (P2P) subsystem includes a cache of a current peer and a peer locator. The current peer is in a current ring at a current level. The cache stores information of ring peers within the current ring. The current ring is part of a hierarchical ring structure of P2P nodes. The hierarchical ring structure has at least one of a lower level and a upper level. The peer locator locates a target peer in the cache in response to a request.

    摘要翻译: 在本发明的一个实施例中,对等(P2P)子系统包括当前对等体和对等定位符的高速缓存。 当前对等体处于当前级别的当前环。 高速缓存存储当前环内的环对等体的信息。 当前的环是P2P节点的分层环结构的一部分。 分层环结构具有下层和上层中的至少一层。 对等体定位器响应于请求在缓存中定位目标对等体。

    Creating managed code from native code
    9.
    发明申请
    Creating managed code from native code 有权
    从本机代码创建托管代码

    公开(公告)号:US20060225033A1

    公开(公告)日:2006-10-05

    申请号:US11092355

    申请日:2005-03-29

    IPC分类号: G06F9/44

    CPC分类号: G06F8/52 G06F8/76

    摘要: In one embodiment, the present invention includes a method for generating an assembly that is usable in a managed environment. More specifically, the assembly may be an all-inclusive object file that contains a native code module, a managed wrapper and prototype information in a single assembly. The method may include forming an object file from a native code module, where the object file includes prototype information, generating a managed code wrapper using the prototype information, and creating a single assembly including the managed code wrapper and the native code module. In some embodiments, the managed code wrapper may be automatically created, reducing burden on a developer. Other embodiments are described and claimed.

    摘要翻译: 在一个实施例中,本发明包括用于生成可在管理环境中使用的组件的方法。 更具体地说,组件可以是包含本体代码模块,托管包装器和单个组件中的原型信息的全包对象文件。 该方法可以包括从本地代码模块形成目标文件,其中对象文件包括原型信息,使用原型信息生成托管代码封装器,以及创建包括托管代码封装器和本机代码模块的单个程序集。 在一些实施例中,托管代码包装器可以被自动创建,从而减轻开发者的负担。 描述和要求保护其他实施例。

    Methods and apparatus to optimize managed application program interfaces
    10.
    发明申请
    Methods and apparatus to optimize managed application program interfaces 有权
    优化托管应用程序接口的方法和设备

    公开(公告)号:US20050188382A1

    公开(公告)日:2005-08-25

    申请号:US10783840

    申请日:2004-02-20

    IPC分类号: G06F9/45 G06F9/455 G06F9/46

    CPC分类号: G06F9/45504

    摘要: Methods and apparatus to optimized managed application program interfaces are described herein. In an example method, a processor instruction proxy stub (PIPS) associated with one or more processor instructions is generated. Based on the PIPS, an optimized managed application program interface is generated to execute the one or more processor instructions.

    摘要翻译: 本文描述了优化托管应用程序接口的方法和装置。 在示例性方法中,生成与一个或多个处理器指令相关联的处理器指令代理存根(PIPS)。 基于PIPS,生成优化的托管应用程序接口以执行一个或多个处理器指令。