公开(公告)号：US20110167245A1

公开(公告)日：2011-07-07

申请号：US12655786

申请日：2010-01-06

申请人： Nick J. Lavrov ,  Nour Toukmaji

发明人： Nick J. Lavrov ,  Nour Toukmaji

IPC分类号： G06F9/30

CPC分类号： G06F9/4881

摘要： There is provided a multi-core system that provides automated task list generation, parallelism templates, and memory management. By constructing, profiling, and analyzing a sequential list of functions to be executed in a parallel fashion, corresponding parallel execution templates may be stored for future lookup in a database. A processor may then select a subset of functions from the sequential list of functions based on input data, select a template from the template database based on particular matching criteria such as high-level task parameters, finalize the template by resolving pointers and adding or removing transaction control blocks, and forward the resulting optimized task list to a scheduler for distribution to multiple slave processing cores. The processor may also analyze data dependencies between tasks to consolidate tasks working on the same data to a single core, thereby implementing memory management and efficient memory locality.

摘要翻译： 提供了一个提供自动化任务列表生成，并行模板和内存管理的多核系统。 通过构建，分析和分析要以并行方式执行的功能的顺序列表，可以存储相应的并行执行模板以用于在数据库中的将来查找。 然后，处理器可以基于输入数据从顺序的功能列表中选择功能的子集，基于诸如高级任务参数的特定匹配标准从模板数据库中选择模板，通过解析指针来完成模板以及添加或移除 事务控制块，并将生成的优化任务列表转发到调度程序以分发到多个从属处理核心。 处理器还可以分析任务之间的数据依赖性，以将在相同数据上工作的任务整合到单个核心，从而实现存储器管理和高效存储器局部性。

公开(公告)号：US08683471B2

公开(公告)日：2014-03-25

申请号：US12657406

申请日：2010-01-19

申请人： Jason B. Brent ,  Nour Toukmaji

发明人： Jason B. Brent ,  Nour Toukmaji

IPC分类号： G06F9/46

CPC分类号： G06F9/4881 ,  G06F9/4843 ,  G06F9/5027 ,  G06F9/5044

摘要： There is provided a highly distributed multi-core system with an adaptive scheduler. By resolving data dependencies in a given list of parallel tasks and selecting a subset of tasks to execute based on provided software priorities, applications can be executed in a highly distributed manner across several types of slave processing cores. Moreover, by overriding provided priorities as necessary to adapt to hardware or other system requirements, the task scheduler may provide for low-level hardware optimizations that enable the timely completion of time-sensitive workloads, which may be of particular interest for real-time applications. Through this modularization of software development and hardware optimization, the conventional demand on application programmers to micromanage multi-core processing for optimal performance is thus avoided, thereby streamlining development and providing a higher quality end product.

摘要翻译： 提供了具有自适应调度器的高度分布的多核系统。 通过解决给定的并行任务列表中的数据依赖关系，并且基于提供的软件优先级选择要执行的任务的子集，可以跨多个类型的从属处理核心以高度分布的方式执行应用程序。 此外，为了适应硬件或其他系统要求，通过覆盖提供的优先级，任务调度器可以提供能够及时完成时间敏感工作负载的低级硬件优化，这对于实时应用可能特别感兴趣 。 通过软件开发和硬件优化的模块化，避免了对应用程序员对微处理多核处理的最佳性能的传统需求，从而简化开发并提供更高质量的最终产品。

公开(公告)号：US09063779B2

公开(公告)日：2015-06-23

申请号：US12655786

申请日：2010-01-06

申请人： Nick J. Lavrov ,  Nour Toukmaji

发明人： Nick J. Lavrov ,  Nour Toukmaji

IPC分类号： G06F9/46 ,  G06F9/48

CPC分类号： G06F9/4881

摘要： There is provided a multi-core system that provides automated task list generation, parallelism templates, and memory management. By constructing, profiling, and analyzing a sequential list of functions to be executed in a parallel fashion, corresponding parallel execution templates may be stored for future lookup in a database. A processor may then select a subset of functions from the sequential list of functions based on input data, select a template from the template database based on particular matching criteria such as high-level task parameters, finalize the template by resolving pointers and adding or removing transaction control blocks, and forward the resulting optimized task list to a scheduler for distribution to multiple slave processing cores. The processor may also analyze data dependencies between tasks to consolidate tasks working on the same data to a single core, thereby implementing memory management and efficient memory locality.

摘要翻译： 提供了一个提供自动化任务列表生成，并行模板和内存管理的多核系统。 通过构建，分析和分析要以并行方式执行的功能的顺序列表，可以存储相应的并行执行模板以用于在数据库中的将来查找。 然后，处理器可以基于输入数据从顺序的功能列表中选择功能的子集，基于诸如高级任务参数的特定匹配标准从模板数据库中选择模板，通过解析指针来完成模板以及添加或移除 事务控制块，并将生成的优化任务列表转发到调度程序以分发到多个从属处理核心。 处理器还可以分析任务之间的数据依赖性，以将在相同数据上工作的任务整合到单个核心，从而实现存储器管理和高效存储器局部性。

公开(公告)号：US20100131955A1

公开(公告)日：2010-05-27

申请号：US12657406

申请日：2010-01-19

申请人： Jason B. Brent ,  Nour Toukmaji

发明人： Jason B. Brent ,  Nour Toukmaji

IPC分类号： G06F9/46

CPC分类号： G06F9/4881 ,  G06F9/4843 ,  G06F9/5027 ,  G06F9/5044

摘要： There is provided a highly distributed multi-core system with an adaptive scheduler. By resolving data dependencies in a given list of parallel tasks and selecting a subset of tasks to execute based on provided software priorities, applications can be executed in a highly distributed manner across several types of slave processing cores. Moreover, by overriding provided priorities as necessary to adapt to hardware or other system requirements, the task scheduler may provide for low-level hardware optimizations that enable the timely completion of time-sensitive workloads, which may be of particular interest for real-time applications. Through this modularization of software development and hardware optimization, the conventional demand on application programmers to micromanage multi-core processing for optimal performance is thus avoided, thereby streamlining development and providing a higher quality end product.

摘要翻译： 提供了具有自适应调度器的高度分布的多核系统。 通过解决给定的并行任务列表中的数据依赖关系，并且基于提供的软件优先级选择要执行的任务的子集，可以跨多个类型的从属处理核心以高度分布的方式执行应用程序。 此外，为了适应硬件或其他系统要求，通过覆盖提供的优先级，任务调度器可以提供能够及时完成时间敏感工作负载的低级硬件优化，这对于实时应用可能特别感兴趣 。 通过软件开发和硬件优化的模块化，避免了对应用程序员对微处理多核处理的最佳性能的传统需求，从而简化开发并提供更高质量的最终产品。

公开(公告)号：US07036118B1

公开(公告)日：2006-04-25

申请号：US10029516

申请日：2001-12-20

申请人： James Ulery ,  Nour Toukmaji

发明人： James Ulery ,  Nour Toukmaji

IPC分类号： G06F9/45

CPC分类号： G06F8/4442

摘要： A system for executing computer programs on a target platform having a limited amount of memory. Directives are suitably placed in the computer program source code at natural boundaries. The system uses the directives to extract structural information from the computer program and to produce a description of all program objects; to estimate typical object usage; and, to trigger transparent object paging to and from the limited platform memory during execution of the computer program. The system makes paging decisions prior to runtime by using relevant factors such as the typical usage of program objects and the size of each program object.

摘要翻译： 一种用于在具有有限量的存储器的目标平台上执行计算机程序的系统。 指令适当地放置在自然边界的计算机程序源代码中。 系统使用指令从计算机程序中提取结构信息，并产生所有程序对象的描述; 估计典型的对象使用情况; 并且在执行计算机程序期间触发到和从有限平台存储器的透明对象寻呼。 系统通过使用诸如程序对象的典型用法和每个程序对象的大小等相关因素，在运行之前进行分页决策。