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

US06604167B1 Method and apparatus traversing stacks for just-in-time compilers for Java virtual machines 失效
标题翻译：用于Java虚拟机的即时编译器的方法和设备遍历堆栈
公开(公告)号：US06604167B1
公开(公告)日：2003-08-05
申请号：US09671867
申请日：2000-09-28
申请人： Geoffrey Owen Blandy , Andrew Johnson
发明人： Geoffrey Owen Blandy , Andrew Johnson
IPC分类号： G06F1200
CPC分类号： G06F9/45516
摘要： A method and apparatus in a data processing system for traversing a plurality of frames for a stack stored sequentially in a memory. A method block associated with a current frame is found. The method block is read to identify an offset to previous frame information in the current frame. A previous frame is located within the plurality of frames using the previous frame information.
摘要翻译：一种用于遍历存储器中顺序存储的堆叠的多个帧的数据处理系统中的方法和装置。找到与当前帧相关联的方法块。读取方法块以识别当前帧中的先前帧信息的偏移量。前一帧使用先前帧信息位于多个帧内。

2. 发明授权

US06295642B1 Method and apparatus for partial just in time compiling in a data processing system 有权
标题翻译：在数据处理系统中部分即时编译的方法和装置
公开(公告)号：US06295642B1
公开(公告)日：2001-09-25
申请号：US09303106
申请日：1999-04-29
申请人： Geoffrey Owen Blandy
发明人： Geoffrey Owen Blandy
IPC分类号： G06F945
CPC分类号： G06F9/45516
摘要： A method and apparatus for just in time compilation of Java bytecode methods and provides a means to compile only the paths that are actually executed. An iterative process is employed whereby bytecodes are compiled up to the next conditional flow bytecode or return, the compiled code is executed and any attempt to enter uncompiled paths of the method is monitored. When the executing thread attempts to execute an uncompiled path control is returned to the compiler and the process is repeated starting with the first bytecode of that path. The process continues until all paths have been compiled or until it is deemed likely that all the most commonly executed paths have been compiled. At that point final optimizations and housekeeping are performed.
摘要翻译：一种用于及时编译Java字节码方法的方法和装置，并提供了仅编译实际执行的路径的方法。使用迭代过程，其中字节码被编译到下一个条件流字节码或返回，编译代码被执行，并且任何尝试输入该方法的未编译路径被监视。当执行的线程尝试执行未编译的路径控制时，返回给编译器，并从该路径的第一个字节码开始重复进程。该过程一直持续到所有的路径都已被编译之前，或者直到被认为可能是所有最常执行的路径都被编译为止。在这一点上，执行最终优化和管理。

3. 发明授权

US06249912B1 Method and apparatus for determining most recently used methods 失效
公开(公告)号：US06249912B1
公开(公告)日：2001-06-19
申请号：US09425338
申请日：1999-10-22
申请人： Geoffrey Owen Blandy
发明人： Geoffrey Owen Blandy
IPC分类号： G06F945
CPC分类号： G06F11/3409 , G06F11/3419 , G06F2201/81 , G06F2201/88
摘要： A method in a data processing system for identifying recently used methods from a plurality of methods in a data processing system, wherein a counter is associated with each method within the plurality of methods. Periodic monitoring is performed to identify an executing method in a current period. The counter is divided using a number of periods since a last period during which the executing method was executed.

4. 发明授权

US5884080A System and method for instruction burst performance profiling for single-processor and multi-processor systems 失效
公开(公告)号：US5884080A
公开(公告)日：1999-03-16
申请号：US753569
申请日：1996-11-26
申请人： Geoffrey Owen Blandy , Maher Afif Saba
发明人： Geoffrey Owen Blandy , Maher Afif Saba
IPC分类号： G06F11/34 , G06F9/45
CPC分类号： G06F11/3466 , G06F11/3409 , G06F2201/865 , G06F2201/88
摘要： The present invention is directed to a system and method for monitoring system performance by sampling instructions in a burst mode, rather than once per interrupt. A burst mode may be configurable for a number of instructions per burst. Furthermore, these instructions are counted using a dynamic tree structure, rather than a log, which results in substantial savings in storage. The present invention requires minimal changes to the operating system, and no changes to application code that is being monitored. No recompilation is necessary to use the present invention. In addition, the present invention provides a system and method for monitoring code segments that are disabled for interrupts, and thus are difficult, if not impossible, to monitor using prior art performance tools. In a multi-processor system, the burst mode is active on all processors at the same time, and each processor has its own dynamic tree structure.

5. 发明授权

US07149870B2 Assigning sections within a memory heap for efficient garbage collection of large objects 失效
标题翻译：在内存堆中分配部分，以便高效地对大型对象进行垃圾收集
公开(公告)号：US07149870B2
公开(公告)日：2006-12-12
申请号：US10862138
申请日：2004-06-04
申请人： Geoffrey Owen Blandy
发明人： Geoffrey Owen Blandy
IPC分类号： G06F12/00
CPC分类号： G06F12/0269 , Y10S707/99953 , Y10S707/99957
摘要： A method, system, and program for assigning sections within a memory heap for efficient garbage collection of large objects are provided. A first portion of a memory heap is distributed among a first number of sections from among multiple sections, wherein the first number of sections correspond to a number of helper threads allocable for bitwise sweeping of the memory heap during garbage collection. A section portion of the memory heap is distribution among a second number of sections, wherein a size of the memory heap distribution of the second number of sections progressively decreases, such that the total number of sections within the memory is minimized, but any disparity between each of the helper threads completing sweeps of all the sections is reduced.
摘要翻译：提供了一种方法，系统和程序，用于在内存堆中分配部分以实现大对象的高效垃圾收集。内存堆的第一部分分布在多个部分中的第一数量的部分之间，其中第一数量的部分对应于可以在垃圾收集期间对存储器堆进行逐位扫描的可分配的辅助线程数。存储器堆的部分部分是在第二数量的部分之间的分布，其中第二数量的部分的存储器堆分布的大小逐渐减小，使得存储器内的部分的总数最小化，但是，完成所有部分的扫描的每个辅助线程减少。

6. 发明授权

US07149866B2 Free item distribution among multiple free lists during garbage collection for more efficient object allocation 失效
标题翻译：在垃圾收集期间，在多个空闲列表之间分配免费项目以实现更有效的对象分配
公开(公告)号：US07149866B2
公开(公告)日：2006-12-12
申请号：US10862151
申请日：2004-06-04
申请人： Geoffrey Owen Blandy
发明人： Geoffrey Owen Blandy
IPC分类号： G06F13/00
CPC分类号： G06F12/0253 , G06F12/023 , Y10S707/99953 , Y10S707/99957
摘要： A method, system, and program for improving free item distribution among multiple free lists during garbage collection for more efficient object allocation are provided. A garbage collector predicts future allocation requirements and then distributes free items to multiple subpool free lists and a TLH free list during the sweep phase according to the future allocation requirements. The sizes of subpools and number of free items in subpools are predicted as the most likely to match future allocation requests. In particular, once a subpool free list is filled with the number of free items needed according to the future allocation requirements, any additional free items designated for the subpool free list can be divided into multiple TLH sized free items and placed on the TLH free list. Allocation threads are enabled to acquire free items from the TLH free list and to replenish a current TLH without acquiring heap lock.
摘要翻译：提供了一种方法，系统和程序，用于在垃圾收集期间改善多个空闲列表之间的免费项目分配，从而实现更有效的对象分配。垃圾收集器预测未来的分配要求，然后根据未来的分配要求，在扫描阶段将免费项目分配到多个子空闲列表和TLH空闲列表。 subpools的大小和子项目中的免费项目数量被预测为最有可能匹配未来分配请求。特别是，一旦一个子空闲免费列表填充了根据未来分配要求所需的免费项目数量，则为子空闲列表指定的任何额外的免费项目可以分为多个TLH大小的免费项目并放置在TLH免费列表。分配线程可以从TLH空闲列表中获取免费项目，并且在不获取堆锁的情况下补充当前的TLH。

7. 发明授权

US06912647B1 Apparatus and method for creating instruction bundles in an explicitly parallel architecture 失效
标题翻译：在显式并行架构中创建指令束的装置和方法
公开(公告)号：US06912647B1
公开(公告)日：2005-06-28
申请号：US09671875
申请日：2000-09-28
申请人： Geoffrey Owen Blandy
发明人： Geoffrey Owen Blandy
IPC分类号： G06F9/38
CPC分类号： G06F9/3853 , G06F9/3885
摘要： An apparatus and method for creating instruction groups for explicitly parallel architectures is provided. The apparatus and method accept instruction groups as input and determine a number of each possible type of instruction in the instruction group. Based on the number of each possible type of instruction in the instruction group, instruction bundling is performed such that the instructions in the instruction group are bundled into efficiently executed bundles. The instruction bundling further accommodates intra-bundle stop bundles in the event that more efficient bundles are not possible. The instruction bundling is performed based on a most restrictive instruction type placement first and proceeds to less restrictive instruction type placement.
摘要翻译：提供了一种用于创建用于显式并行架构的指令组的装置和方法。该装置和方法接受指令组作为输入，并确定指令组中每种可能类型的指令的数量。基于指令组中的每种可能类型的指令的数量，执行指令捆绑，使得指令组中的指令被捆绑成有效执行的包。如果不可能实现更高效的捆绑，则指令捆绑进一步适应了捆绑束内捆绑包。指令捆绑是基于最严格的指令类型放置首先进行的，并进行限制较少的指令类型放置。

8. 发明授权

US06779188B1 Apparatus and method for improved devirtualization of method calls 有权
标题翻译：用于改进方法调用的虚拟化的装置和方法
公开(公告)号：US06779188B1
公开(公告)日：2004-08-17
申请号：US09671876
申请日：2000-09-28
申请人： Geoffrey Owen Blandy , Andrew Johnson
发明人： Geoffrey Owen Blandy , Andrew Johnson
IPC分类号： G06F300
CPC分类号： G06F9/45516 , G06F9/449
摘要： Apparatus and methods are provided for improving devirtualization of method calls. The apparatus and methods reduce the amount of processing time used in performing lookups of methods by limiting such lookups to calls of methods that have been either overridden or overloaded. If a method has not been overridden or overloaded, a branch to the compiled method code is directly taken. If a method has been overridden or overloaded, a lookup routine is executed for looking-up the appropriate method to be invoked on the passed object. The identification of whether to use a lookup routine may be performed in many different ways including providing an extra field in a method block of the method, inserting code into a prolog of the method, and the like.
摘要翻译：提供了提高方法调用的半虚拟化的装置和方法。该装置和方法通过将这种查找限制为已经被覆盖或重载的方法的调用来减少用于执行方法查找的处理时间量。如果一个方法没有被覆盖或重载，那么直接对编译的方法代码进行分支。如果方法已被覆盖或重载，则执行查找例程以查找要在传递的对象上调用的适当方法。是否使用查找例程的识别可以以许多不同的方式执行，包括在方法的方法块中提供额外的字段，将代码插入方法的序言等。

9. 发明授权

US06385764B1 Method and apparatus for improving invocation speed of Java methods 有权
标题翻译：提高Java方法调用速度的方法和装置
公开(公告)号：US06385764B1
公开(公告)日：2002-05-07
申请号：US09240013
申请日：1999-01-29
申请人： Geoffrey Owen Blandy , Bentley John Hargrave
发明人： Geoffrey Owen Blandy , Bentley John Hargrave
IPC分类号： G06F945
CPC分类号： G06F9/449
摘要： A method and apparatus for executing a method. A bytecode invoking a method is detected. A method block is located associated with the method, wherein the method block includes an identification of an invoker. The invoker is called, wherein the invoker performs setup for execution of the method. The setup performed by the invoker is tailored specifically to the method. A completion of the method is detected and returns control to the invoker, wherein the invoker completes processing of the method.
摘要翻译：一种用于执行方法的方法和装置。检测到调用方法的字节码。与该方法相关联的方法块，其中方法块包括调用者的标识。调用调用者，其中调用者执行该方法的执行设置。调用者执行的设置是针对该方法量身定制的。检测到该方法的完成，并且向调用者返回控制，其中调用者完成该方法的处理。

10. 发明授权

US6006032A System and method for instruction burst performance profiling for single-processor and multi-processor systems 有权
标题翻译：用于单处理器和多处理器系统的指令突发性能分析的系统和方法
公开(公告)号：US6006032A
公开(公告)日：1999-12-21
申请号：US154897
申请日：1998-09-17
申请人： Geoffrey Owen Blandy , Maher Afif Saba
发明人： Geoffrey Owen Blandy , Maher Afif Saba
IPC分类号： G06F11/34 , G06F9/445
CPC分类号： G06F11/3466 , G06F11/3409 , G06F2201/865 , G06F2201/88
摘要： The present invention is directed to a system and method for monitoring system performance by sampling instructions in a burst mode, rather than once per interrupt. A burst mode may be configurable for a number of instructions per burst. Furthermore, these instructions are counted using a dynamic tree structure, rather than a log, which results in substantial savings in storage. The present invention requires minimal changes to the operating system, and no changes to application code that is being monitored. No recompilation is necessary to use the present invention. In addition, the present invention provides a system and method for monitoring code segments that are disabled for interrupts, and thus are difficult, if not impossible, to monitor using prior art performance tools. In a multi-processor system, the burst mode is active on all processors at the same time, and each processor has its own dynamic tree structure.
摘要翻译：本发明涉及一种用于通过以突发模式采样指令而不是每次中断一次来监视系统性能的系统和方法。可以针对每个突发的多个指令来配置突发模式。此外，这些指令使用动态树结构进行计数，而不是日志，从而大大节省存储空间。本发明需要对操作系统的最小的改变，并且不改变正被监视的应用程序代码。不需要重新编译来使用本发明。此外，本发明提供了一种用于监视对于中断被禁用的代码段的系统和方法，并且因此难以（如果不是不可能）使用现有技术的性能工具进行监视。在多处理器系统中，突发模式在所有处理器上同时处于活动状态，每个处理器都有自己的动态树结构。

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