公开(公告)号：US08453132B2

公开(公告)日：2013-05-28

申请号：US11812639

申请日：2007-06-20

Applicant: Sandya S. Mannarswamy ,  Virendra Kumar Mehta ,  Prakash Sathyanath Raghavendra

Inventor： Sandya S. Mannarswamy ,  Virendra Kumar Mehta ,  Prakash Sathyanath Raghavendra

IPC: G06F9/45 ,  G06F9/44

CPC classification number: G06F8/4442

Abstract: A technique for reducing non-local access, in dynamically generated code that resides in a code buffer of a non-uniform memory access computer system including multiple nodes, for improving overall performance of dynamic optimization systems. In one example embodiment, this is accomplished by partitioning the code buffer into multiple smaller code buffers and assigning each of the multiple smaller code buffers to one of the multiple nodes. Statically determining which methods in the generated code are executed by a thread and then to place those methods in associated one of the multiple smaller code buffers to reduce memory latencies introduced by non-local accesses.

Abstract translation: 一种在动态生成的代码中减少非本地访问的技术，该代码位于包含多个节点的非均匀内存访问计算机系统的代码缓冲区中，以提高动态优化系统的整体性能。 在一个示例实施例中，这是通过将代码缓冲器分成多个较小的代码缓冲器并将多个较小代码缓冲器中的每一个分配给多个节点之一来实现的。 静态确定生成的代码中的哪些方法由线程执行，然后将这些方法放置在多个较小代码缓冲器中的相关联的一个中，以减少非本地访问引入的内存延迟。

公开(公告)号：US07926042B2

公开(公告)日：2011-04-12

申请号：US11264651

申请日：2005-10-31

Applicant: Virendra Kumar Mehta ,  Sandya S. Mannarswamy

Inventor： Virendra Kumar Mehta ,  Sandya S. Mannarswamy

IPC: G06F9/45

CPC classification number: G06F11/3676

Abstract: A system and method for dynamic instrumentation of an interpreted application. The method includes the operation of loading an interpreted code unit into a virtual machine. Testing instrumentation can then be inserted into the interpreted code unit using the virtual machine while the interpreted application continues executing. Another operation is executing the interpreted code unit with the testing instrumentation.

Abstract translation: 用于解释应用程序的动态仪表的系统和方法。 该方法包括将解释的代码单元加载到虚拟机中的操作。 然后，在解释的应用程序继续执行时，使用虚拟机将测试仪器插入解释的代码单元。 另一个操作是使用测试仪器执行解释的代码单元。

公开(公告)号：US20100319518A1

公开(公告)日：2010-12-23

申请号：US12820291

申请日：2010-06-22

Applicant: Virendra Kumar Mehta

Inventor： Virendra Kumar Mehta

IPC: G10H1/08

CPC classification number: G10H1/0058 ,  G10H2220/106 ,  G10H2240/175

Abstract: A new approach is proposed that contemplates systems and methods to enable a musician to connect with other musicians online in a social network, or work with their past work that is available to use. The musicians may use an in-browser mixer to select tracks from the site for a specific song, change their individual settings like volume, starting positions, pan and the like, mix tracks and play them together, and then record their own track alongside. A musician may also connect with other musicians online in a social network, or work with their past work that is available to use.

Abstract translation: 提出了一种新的方法，考虑系统和方法，使音乐家能够在社交网络中在线联系其他音乐家，或者与他们过去可以使用的作品进行交流。 音乐家可以使用浏览器内的混音器，从站点中选择特定歌曲的曲目，更改音量，起始位置，平移等各种设置，混合曲目并将它们一起播放，然后将它们自己的曲目一起录制。 音乐家也可以在社交网络中与其他音乐家在线连接，或者与他们过去可以使用的作品进行交流。

公开(公告)号：US20110029819A1

公开(公告)日：2011-02-03

申请号：US12533625

申请日：2009-07-31

Applicant: Virendra Kumar Mehta ,  Xiaohua Zhang

Inventor： Virendra Kumar Mehta ,  Xiaohua Zhang

IPC: G06F11/07 ,  G06F9/45 ,  G06F11/36

CPC classification number: G06F11/3644

Abstract: There is provided a system and method of providing program tracking information. An exemplary method comprises compiling a program into a plurality of instruction bundles. The exemplary method also comprises placing an instruction to store program tracking information in a local path table or a global path table into at least one of the plurality of instruction bundles.

Abstract translation: 提供了一种提供节目跟踪信息的系统和方法。 一种示例性方法包括将程序编译成多个指令束。 该示例性方法还包括将本地路径表或全局路径表中的程序跟踪信息存储到多个指令束中的至少一个中的指令。

公开(公告)号：US07877740B2

公开(公告)日：2011-01-25

申请号：US11152466

申请日：2005-06-13

Applicant: Virendra Kumar Mehta

Inventor： Virendra Kumar Mehta

IPC: G06F9/45

CPC classification number: G06F9/4812 ,  G06F2209/481

Abstract: Embodiments of the invention relate to exceptions. In a Java embodiment, if the count of a program statement that causes the exception reaches a threshold, then the Java Virtual Machine (JVM) searches for the throw statement corresponding to that program statement. The JVM then identifies the catch clause corresponding to the throw statement, and depending on implementations, the JVM may replace the throw statement with the catch block or replace the throw statement with a jump to the catch block. As a result, in both situations, program execution, when being supposed to execute the throw statement, executes instructions of the catch block, and avoids execution of the throw statement that would invoke the exception handler, which improves system performance.

Abstract translation: 本发明的实施例涉及例外。 在Java实施例中，如果导致异常的程序语句的计数达到阈值，则Java虚拟机（JVM）将搜索与该程序语句相对应的throw语句。 JVM然后识别与throw语句对应的catch子句，并且根据实现，JVM可以使用catch块替换throw语句，或者通过跳转到catch块来替换throw语句。 因此，在这两种情况下，程序执行时，当执行throw语句时，执行catch块的指令，避免执行调用异常处理程序的throw语句，从而提高系统性能。

公开(公告)号：US20080028179A1

公开(公告)日：2008-01-31

申请号：US11812639

申请日：2007-06-20

Applicant: Sandya S. Mannarswamy ,  Virendra Kumar Mehta ,  Prakash Sathyanath Raghavendra

Inventor： Sandya S. Mannarswamy ,  Virendra Kumar Mehta ,  Prakash Sathyanath Raghavendra

IPC: G06F12/00

CPC classification number: G06F8/4442

Abstract: A technique for reducing non-local access, in dynamically generated code that resides in a code buffer of a NUMA computer system including multiple nodes, for improving overall performance of dynamic optimization systems. In one example embodiment, this is accomplished by partitioning the code buffer into multiple smaller code buffers and assigning each of the multiple smaller code buffers to one of the multiple nodes. Statically determining which methods in the generated code are executed by a thread and then to place those methods in associated one of the multiple smaller code buffers to reduce memory latencies introduced by non-local accesses.

Abstract translation: 一种在动态生成的代码中减少非本地访问的技术，该代码位于包含多个节点的NUMA计算机系统的代码缓冲区中，以改善动态优化系统的整体性能。 在一个示例实施例中，这是通过将代码缓冲器分成多个较小的代码缓冲器并将多个较小代码缓冲器中的每一个分配给多个节点之一来实现的。 静态确定生成的代码中的哪些方法由线程执行，然后将这些方法放置在多个较小代码缓冲器中的相关联的一个中，以减少非本地访问引入的内存延迟。