专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09563532B1 Allocation of tasks in large scale computing systems 有权
标题翻译：大规模计算系统任务分配
公开(公告)号：US09563532B1
公开(公告)日：2017-02-07
申请号：US13310054
申请日：2011-12-02
申请人： Robert Hundt , Lingjia Tang , Jason Mars
发明人： Robert Hundt , Lingjia Tang , Jason Mars
IPC分类号： G06F15/173 , G06F11/34
CPC分类号： G06F11/3409 , G06F11/3006 , G06F11/3442 , G06F11/3452 , G06F11/3466 , G06F2201/81
摘要： Aspects of the invention may be used to allocate tasks among computing machines in large scale computing systems. In one aspect, the method includes executing a first task in the plurality of tasks on a first computing machine and determining a performance degradation threshold for the first task. The method further includes calculating a predicted performance degradation of the first task when a second task is executed on the first computing machine, wherein the predicted performance degradation is determined by comparing a performance interference score of the second task with a performance sensitivity curve of the first task. The method further includes executing the second task on the first computing machine when the predicted performance degradation of the first task is below the performance degradation threshold.
摘要翻译：本发明的各方面可用于在大规模计算系统中的计算机之间分配任务。一方面，该方法包括在第一计算机上执行多个任务中的第一任务并确定第一任务的性能降级阈值。该方法还包括当在第一计算机上执行第二任务时，计算第一任务的预测性能下降，其中通过将第二任务的性能干扰得分与第一任务的性能敏感性曲线进行比较来确定预测的性能下降任务。该方法还包括当第一任务的预测性能下降低于性能降级阈值时，在第一计算机上执行第二任务。

2. 发明授权

US09268542B1 Cache contention management on a multicore processor based on the degree of contention exceeding a threshold 有权
标题翻译：基于超过阈值的争用程度，在多核处理器上进行缓存争用管理
公开(公告)号：US09268542B1
公开(公告)日：2016-02-23
申请号：US13096821
申请日：2011-04-28
申请人： Jason Mars , Robert Hundt , Neil A. Vachharajani
发明人： Jason Mars , Robert Hundt , Neil A. Vachharajani
IPC分类号： G06F9/46 , G06F13/00 , G06F9/45 , G06F9/30 , G06F9/52 , G06F13/372 , G06F13/30
CPC分类号： G06F8/4442 , G06F9/30 , G06F9/46 , G06F9/5016 , G06F9/526 , G06F13/30 , G06F13/372 , G06F2209/504 , G06F2209/508 , Y02D10/22
摘要： A first indicator of a first number of cache misses to a cache memory of a multicore processor for a first application over a first time period is received. The first application executes on a first core of the processor and a second application simultaneously executes on a second core of the processor during the first time period. The first and second cores share the cache memory. A second indicator of a second number of cache misses to the cache memory for the first application over a second time period is received. During the second time period, the first application executes on the first core and the second application does not execute on the second core. A degree of contention among the first and second applications is determined based on the first and second indicators, and execution of the second application is adjusted based on the determined degree of contention.
摘要翻译：接收在第一时间段内针对第一应用的多核处理器的高速缓冲存储器的第一数量的高速缓存未命中的第一指示符。第一应用在处理器的第一核上执行，并且第二应用在第一时间段期间同时在处理器的第二核上执行。第一和第二核共享缓存。接收在第二时间段内针对第一应用的高速缓存存储器的第二数量的高速缓存未命中的第二指示符。在第二时间段期间，第一应用在第一核上执行，第二应用不在第二核上执行。基于第一和第二指示符确定第一和第二应用程序之间的争用程度，并且基于所确定的争用程度来调整第二应用的执行。

3. 发明授权

US08578355B1 Scenario based optimization 有权
标题翻译：基于情景的优化
公开(公告)号：US08578355B1
公开(公告)日：2013-11-05
申请号：US12728099
申请日：2010-03-19
申请人： Jason Mars , Robert Hundt
发明人： Jason Mars , Robert Hundt
IPC分类号： G06F9/45
CPC分类号： G06F8/443
摘要： Techniques and systems for scenario based optimization can include generating multiple different versions of a program segment based on different respective execution scenarios associated with an execution of a program, the program operable to use the program segment versions. In another aspect, techniques and systems can include executing a program executable associated with multiple different versions of a program segment, analyzing the execution for an indication of at least one of the execution scenarios to select one of the program segment versions based on the indication, and causing the execution to use the selected program segment version during at least a portion of the execution.
摘要翻译：用于基于场景的优化的技术和系统可以包括基于与程序的执行相关联的不同的相应执行方案来生成程序段的多个不同版本，该程序可操作以使用程序段版本。在另一方面，技术和系统可以包括执行与程序段的多个不同版本相关联的程序可执行程序，分析执行以指示执行情景中的至少一个，以基于该指示来选择一个程序段版本，并且在执行的至少一部分期间使执行使用所选择的程序段版本。

4. 发明授权

US08387026B1 Compile-time feedback-directed optimizations using estimated edge profiles from hardware-event sampling 有权
标题翻译：使用来自硬件事件采样的估计边缘轮廓的编译时反馈优化
公开(公告)号：US08387026B1
公开(公告)日：2013-02-26
申请号：US12343635
申请日：2008-12-24
申请人： Robert Hundt , Vinodha Ramasamy , Dehao Chen
发明人： Robert Hundt , Vinodha Ramasamy , Dehao Chen
IPC分类号： G06F9/45
CPC分类号： G06F8/443
摘要： Traditional feedback-directed optimization (FDO) is not widely used due to the significant computational overhead involved in using instrumented binaries. The described embodiments provide methods that eliminate the need for instrumented binaries by permitting the conversion of hardware-event sampling information into edge frequencies usable by FDO compilers. Some advantages include: the ability to collect feedback data on production systems; the ability to perform FDO on the OS kernel; and the ability to avoid disrupting timing paths from instrumented binaries.
摘要翻译：传统的反馈导向优化（FDO）由于使用仪器化二进制文件所涉及的重大计算开销，未被广泛使用。所描述的实施例提供了通过允许将硬件事件采样信息转换成FDO编译器可用的边缘频率来消除对仪表二进制文件的需要的方法。一些优势包括：收集生产系统反馈数据的能力; 在OS内核上执行FDO的能力; 以及避免破坏仪器化二进制文件的时序路径的能力。

5. 发明授权

US07415699B2 Method and apparatus for controlling execution of a child process generated by a modified parent process 失效
标题翻译：用于控制由修改的父进程生成的子进程的执行的方法和装置
公开(公告)号：US07415699B2
公开(公告)日：2008-08-19
申请号：US10608330
申请日：2003-06-27
申请人： Eric Gouriou , Robert Hundt , Sujoy Saraswati , Sushanth Rai , Edward Sharpe
发明人： Eric Gouriou , Robert Hundt , Sujoy Saraswati , Sushanth Rai , Edward Sharpe
IPC分类号： G06F9/44
CPC分类号： G06F9/4843
摘要： A monitoring interface, includes logic responsive to a pre-fork event, the pre-fork event responsive to a vfork system call. The pre-fork event includes indicia that identifies a child process to be created in accordance with the vfork system call. A method for controlling the execution of a child process created from a parent process, where the parent process is monitored by a software tool includes, receiving indicia that a vfork system call will be executed by the parent process, suspending execution of the parent process, extracting a process identifier from the indicia of the vfork system call, the process identifier corresponding to a child process to be generated by the parent process when the parent process executes the vfork system call, setting a process monitor thread to observe the child process, and resuming execution of the parent process to enable the parent process to execute past the vfork system call.
摘要翻译：监视接口包括响应于前叉事件的逻辑，响应于vfork系统调用的前叉事件。前叉事件包括标记根据vfork系统调用创建的子进程的标记。用于控制由父进程创建的子进程的执行方法，其中父进程由软件工具监视，包括：接收由父进程执行的vfork系统调用的标记，暂停父进程的执行，从Vfork系统调用的标记中提取进程标识符，当父进程执行vfork系统调用时，由父进程生成的子进程对应的进程标识符，设置进程监视线程以观察子进程，以及恢复执行父进程以使父进程能够通过vfork系统调用执行。

6. 发明申请

US20050155023A1 Partitioning modules for cross-module optimization 失效
标题翻译：用于跨模块优化的分区模块
公开(公告)号：US20050155023A1
公开(公告)日：2005-07-14
申请号：US10756881
申请日：2004-01-13
申请人： XinLiang Li , Shin-Ming Liu , Dhruva Chakrabarti , Robert Hundt
发明人： XinLiang Li , Shin-Ming Liu , Dhruva Chakrabarti , Robert Hundt
IPC分类号： G06F9/45
CPC分类号： G06F8/443
摘要： Techniques for partitioning modules into smaller groups are disclosed. In various embodiments, cross-module optimization may be performed on these smaller groups. Further, related modules are grouped together based on a predefined algorithm. Relatedness, or closeness, or affinity, of modules are considered based on various factors including, for example, the number of calls between routines in different modules, possibility of in-lining a first routine in a first module into a second routine in a second module, characteristics of parameters being passed between routines in different modules, etc.
摘要翻译：公开了将模块分成较小组的技术。在各种实施例中，可以对这些较小的组执行交叉模块优化。此外，相关模块基于预定义的算法被分组在一起。基于各种因素考虑模块的相关性，或亲密性，或亲和性，例如包括例如不同模块中的例程之间的调用次数，将第一模块中的第一程序内插到第二程序中的第二程序的可能性模块，在不同模块中的例程之间传递参数的特性等

7. 发明授权

US06851110B2 Optimizing an executable computer program having address-bridging code segments 有权
标题翻译：优化具有地址桥接代码段的可执行计算机程序
公开(公告)号：US06851110B2
公开(公告)日：2005-02-01
申请号：US09876655
申请日：2001-06-07
申请人： Robert Hundt , Vinodha Ramasamy
发明人： Robert Hundt , Vinodha Ramasamy
IPC分类号： G06F9/45
CPC分类号： G06F8/4441
摘要： Method and apparatus for optimizing an executable computer program having address-bridging code segments. Various embodiments are described for optimizing an executable computer program that occupies a first address space and has address-bridging code segments. Address-bridging code segments, target code segments referenced by the address-bridging segments, and calling code segments that reference the address-bridging segments are identified during execution of the program. A second address space is allocated for storage of relocated functions. The calling code segments and the target code segments are relocated to the second address space, and references to the address-bridging code segments are replaced with references to the target code segments in the second address space. For references to the calling code segments in the first address space, control is directed to the calling code segments in the second address space.
摘要翻译：用于优化具有地址桥接代码段的可执行计算机程序的方法和装置。描述了用于优化占用第一地址空间并具有地址桥接代码段的可执行计算机程序的各种实施例。地址桥接代码段，由地址桥接段引用的目标代码段以及引用地址桥接段的调用代码段在程序执行期间被识别。分配第二个地址空间用于存储重新定位的功能。调用代码段和目标代码段被重定位到第二地址空间，并且对地址桥接代码段的引用被替换为对第二地址空间中的目标代码段的引用。对于对第一地址空间中的调用代码段的引用，控制被引导到第二地址空间中的调用代码段。

8. 发明授权

US07165162B2 Partitioning modules for cross-module optimization 失效
标题翻译：用于跨模块优化的分区模块
公开(公告)号：US07165162B2
公开(公告)日：2007-01-16
申请号：US10756881
申请日：2004-01-13
申请人： XinLiang David Li , Shin-Ming Liu , Dhruva R. Chakrabarti , Robert Hundt
发明人： XinLiang David Li , Shin-Ming Liu , Dhruva R. Chakrabarti , Robert Hundt
IPC分类号： G06F12/06
CPC分类号： G06F8/443
摘要： Techniques for partitioning modules into smaller groups are disclosed. In various embodiments, cross-module optimization may be performed on these smaller groups. Further, related modules are grouped together based on a predefined algorithm. Relatedness, or closeness, or affinity, of modules are considered based on various factors including, for example, the number of calls between routines in different modules, possibility of in-lining a first routine in a first module into a second routine in a second module, characteristics of parameters being passed between routines in different modules, etc.
摘要翻译：公开了将模块分成较小组的技术。在各种实施例中，可以对这些较小的组执行交叉模块优化。此外，相关模块基于预定义的算法被分组在一起。基于各种因素考虑模块的相关性，或亲密性，或亲和性，例如包括例如不同模块中的例程之间的调用次数，将第一模块中的第一程序内插到第二程序中的第二程序的可能性模块，在不同模块中的例程之间传递参数的特性等

9. 发明授权

US07103878B2 Method and system to instrument virtual function calls 失效
公开(公告)号：US07103878B2
公开(公告)日：2006-09-05
申请号：US10020631
申请日：2001-12-13
申请人： Brian Fahs , Robert Hundt , Tara Krishnaswamy
发明人： Brian Fahs , Robert Hundt , Tara Krishnaswamy
IPC分类号： G06F9/44 , G06F9/45
CPC分类号： G06F11/3612 , G06F9/449 , G06F11/3644
摘要： A method and system for analyzing a virtual function. In one embodiment, the present invention determines whether a virtual table exists for a virtual function, and determines a call type for the virtual function. In the present embodiment, provided the virtual table is located, the present invention replaces an existing address for the virtual function with a new address such that the new address points to instrumentation code. In this embodiment, upon a call to the virtual function, the present invention loads the new address from the virtual table such that execution is directed to the instrumentation code. The present embodiment continues execution and executes the instrumentation code such that control is delivered to the instrumentor.

10. 发明授权

US07401330B2 Cloning programming code 有权
标题翻译：克隆编程代码
公开(公告)号：US07401330B2
公开(公告)日：2008-07-15
申请号：US10734551
申请日：2003-12-11
申请人： David Xinliang Li , Robert Hundt , Sungdo Moon , Loreena Wong
发明人： David Xinliang Li , Robert Hundt , Sungdo Moon , Loreena Wong
IPC分类号： G06F9/44
CPC分类号： G06F8/54 , G06F8/443
摘要： Techniques for cloning programming code are disclosed. In an embodiment, the cloned code is in the form of functions in the C language. Further, in a method embodiment, a clone of a function is invoked, and information mapping the clone to the function is generated. At link time, if no function body of the clone is accessible by a linker, then the linker uses information mapping the clone to the function to satisfy a linker's requirement. At load time, if no function body of the clone is accessible by a loader, then the loader, based on the mapping information, allows selection of a body of the function. However, if the body function of the clone is accessible by the loader, then the loader allows selection of the body of the clone.
摘要翻译：公开了克隆程序代码的技术。在一个实施例中，克隆的代码是C语言中的函数的形式。此外，在方法实施例中，调用功能的克隆，并且生成将克隆映射到功能的信息。在链接时，如果链接器不能访问克隆的函数体，则链接器将使用将该克隆映射到该函数以满足链接器要求的信息。在加载时，如果克隆的功能主体不能由加载程序访问，则加载程序基于映射信息，允许选择一个主体的功能。但是，如果克隆的正文功能可由加载程序访问，则加载程序允许选择克隆的正文。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式