Future scheduling by direct representation of possible dependencies
    3.
    发明授权
    Future scheduling by direct representation of possible dependencies 有权
    通过直接表示可能依赖的未来调度

    公开(公告)号:US08225326B2

    公开(公告)日:2012-07-17

    申请号:US12049914

    申请日:2008-03-17

    IPC分类号: G06F9/46 G06F9/52

    CPC分类号: G06F9/524

    摘要: A method for evaluating objects in a data structure is provided. The method includes assigning one or more objects to one or more nodes in a data structure having at least a root node, in which the objects are assigned to the nodes in accordance with a first order to maintain pre-existing dependencies between the objects and to allow the objects to be evaluated in a serial manner to avoid deadlock when concurrently executing threads to evaluate the objects, and selecting a first object for evaluation, in response to determining that the current object is unevaluated.

    摘要翻译: 提供了一种用于评估数据结构中的对象的方法。 该方法包括将一个或多个对象分配给具有至少根节点的数据结构中的一个或多个节点,其中根据第一顺序将对象分配给节点,以保持对象之间的预先存在的依赖关系,以及 允许以串行方式评估对象,以在同时执行线程以评估对象时选择第一对象以进行评估,以响应于确定当前对象未被评估而避免死锁。

    System and method for enforcing application security policies using authenticated system calls
    4.
    发明授权
    System and method for enforcing application security policies using authenticated system calls 有权
    使用经过身份验证的系统调用实施应用程序安全策略的系统和方法

    公开(公告)号:US07913092B1

    公开(公告)日:2011-03-22

    申请号:US11321479

    申请日:2005-12-29

    IPC分类号: G06F11/30

    CPC分类号: G06F21/54

    摘要: Disclosed is an approach to system call monitoring in which authenticated system calls from an application are easily verified by an operating system kernel. The authenticated system call may be a system call augmented with extra arguments, which specify the policy for that call as well as a cryptographic message authentication code (MAC) that guarantees the integrity of the policy and the system call arguments. This extra information is used by the operating system kernel to verify the system call with little processing overhead. Versions of the applications in which regular system calls have been replaced by authenticated calls are generated automatically by a trusted installer program that reads the application binary, uses static analysis to generate policies, and then rewrites the binary with the authenticated calls. As a result, hacker attacks, malicious software and the like are less likely to be successful in compromising any computers or networks that employ such authenticated system calls.

    摘要翻译: 公开了一种系统呼叫监控的方法,其中来自应用的认证系统调用容易由操作系统内核验证。 经认证的系统调用可以是增加额外的参数的系统调用,其中指定该调用的策略以及保证策略和系统调用参数的完整性的加密消息认证码(MAC)。 这些额外的信息被操作系统内核用来验证系统调用,而且处理开销很小。 常规系统调用被认证呼叫替换的应用程序的版本由读取应用程序二进制文件的可信安装程序自动生成,使用静态分析生成策略,然后使用已认证的呼叫重写二进制文件。 因此,黑客攻击,恶意软件等不太可能成功地破坏任何使用这种经过身份验证的系统呼叫的计算机或网络。

    Concurrent management of adaptive programs
    5.
    发明授权
    Concurrent management of adaptive programs 有权
    并发管理适应性方案

    公开(公告)号:US08627301B2

    公开(公告)日:2014-01-07

    申请号:US11750441

    申请日:2007-05-18

    IPC分类号: G06F9/44 G06F9/45

    CPC分类号: G06F9/5066

    摘要: A method for concurrent management of adaptive programs is disclosed wherein changes in a set of modifiable references are initially identified. A list of uses of the changed references is next computed using records made in structures of the references. The list is next inserted into an elimination queue. Comparison is next made of each of the uses to the other uses to determine independence or dependence thereon. Determined dependent uses are eliminated and the preceding steps are repeated for all determined independent uses until all dependencies have been eliminated.

    摘要翻译: 公开了一种用于并行管理自适应程序的方法,其中初始地识别一组可修改参考文献中的改变。 接下来使用在引用的结构中作出的记录来计算更改的引用的使用列表。 列表接下来插入消除队列。 下一步将对其他用途的各种用途进行比较,以确定其独立性或依赖性。 消除确定的依赖用途,并且对于所有确定的独立使用重复前述步骤,直到所有依赖关系被消除。

    NON-BLOCKING WAIT-FREE DATA-PARALLEL SCHEDULER
    6.
    发明申请
    NON-BLOCKING WAIT-FREE DATA-PARALLEL SCHEDULER 有权
    非阻塞等待数据并行调度器

    公开(公告)号:US20120159495A1

    公开(公告)日:2012-06-21

    申请号:US12971891

    申请日:2010-12-17

    IPC分类号: G06F9/46

    CPC分类号: G06F9/4881 G06F9/5066

    摘要: Methods, systems, and mediums are described for scheduling data parallel tasks onto multiple thread execution units of processing system. Embodiments of a lock-free queue structure and methods of operation are described to implement a method for scheduling fine-grained data-parallel tasks for execution in a computing system. The work of one of a plurality of worker threads is wait-free with respect to the other worker threads. Each node of the queue holds a reference to a task that may be concurrently performed by multiple thread execution units, but each on a different subset of data. Various embodiments relate to software-based scheduling of data-parallel tasks on a multi-threaded computing platform that does not perform such scheduling in hardware. Other embodiments are also described and claimed.

    摘要翻译: 描述了用于将数据并行任务调度到处理系统的多个线程执行单元上的方法,系统和介质。 描述无锁队列结构和操作方法的实施例以实现用于调度细粒度数据并行任务以在计算系统中执行的方法。 多个工作线程之一的工作相对于其他工作线程是等待的。 队列的每个节点都保存对可以由多个线程执行单元同时执行的任务的引用,但每个节点都在不同的数据子集上。 各种实施例涉及在不在硬件中执行这样的调度的多线程计算平台上的数据并行任务的基于软件的调度。 还描述和要求保护其他实施例。

    FUTURE SCHEDULING BY DIRECT REPRESENTATION OF POSSIBLE DEPENDENCIES
    8.
    发明申请
    FUTURE SCHEDULING BY DIRECT REPRESENTATION OF POSSIBLE DEPENDENCIES 有权
    未来可能直接表示可能的依赖性

    公开(公告)号:US20090235273A1

    公开(公告)日:2009-09-17

    申请号:US12049914

    申请日:2008-03-17

    IPC分类号: G06F9/46

    CPC分类号: G06F9/524

    摘要: A method for evaluating objects in a data structure is provided. The method comprises assigning one or more objects to one or more nodes in a data structure having at least a root node, wherein the objects are assigned to the nodes in accordance with a first order to maintain pre-existing dependencies between said objects and to allow the objects to be evaluated in a serial manner to avoid deadlock when concurrently executing threads to evaluate the objects; and selecting a first object for evaluation, in response to determining that the current object is unevaluated.

    摘要翻译: 提供了一种用于评估数据结构中的对象的方法。 该方法包括将一个或多个对象分配给具有至少根节点的数据结构中的一个或多个节点,其中根据第一顺序将对象分配给节点,以维持所述对象之间的预先存在的依赖关系并允许 要以串行方式评估的对象,以在同时执行线程来评估对象时避免死锁; 以及响应于确定当前对象未被评估,选择用于评估的第一对象。