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

US11755926B2 Prioritization and prediction of jobs using cognitive rules engine 有权
公开(公告)号：US11755926B2
公开(公告)日：2023-09-12
申请号：US16288739
申请日：2019-02-28
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Ritesh Kumar Gupta , Namit Kabra , Likhitha Maddirala , Eric Allen Jacobson , Scott Louis Brokaw , Jo Ramos
IPC分类号： G06F9/48 , G06F9/50 , G06N3/08 , G06N5/025 , H04L41/5022 , H04L41/5019
CPC分类号： G06N5/025 , G06F9/4881 , G06F9/5038 , G06N3/08 , H04L41/5022 , G06F2209/484 , G06F2209/5019 , H04L41/5019
摘要： A method, computer system, and a computer program product for data pipeline prioritization is provided. Embodiments may include receiving, by a cognitive rules engine, one or more data pipelines. Embodiments may then include analyzing, using a computational method of the cognitive rules engine, the one or more data pipelines. Embodiments may lastly include prioritizing the one or more data pipelines based on a result of the computational method of the cognitive rules engine.

2. 发明授权

US10614128B2 Methods and systems for starting computerized system modules 有权
公开(公告)号：US10614128B2
公开(公告)日：2020-04-07
申请号：US15412205
申请日：2017-01-23
申请人： International Business Machines Corporation
发明人： Michael Charles Osborne , Elaine Rivette Palmer , Tamas Visegrady
IPC分类号： G06F9/48 , G06F16/901 , G06F9/30
CPC分类号： G06F16/9024 , G06F9/30087 , G06F9/48 , G06F9/4881 , G06F2209/484
摘要： Graph data of a DAG is received. The data describes a module to be started by way of nodes connected by edges, wherein some nodes are submodule nodes that correspond to submodules of said module. Submodule nodes are connected via edge(s) that reflect a data dependency between the corresponding submodules. Each of said submodules is a hardware module or a software submodule, capable of producing and/or consuming data that can be consumed and/or produced, by other submodule(s) of said module, based on the DAG. Asynchronous execution is started of two of said submodules, respectively corresponding to two submodule nodes located in independent branches of the DAG. A third submodule node(s) is determined that is a descendant of each of said two submodule nodes, according to an outcome of the execution of the corresponding two submodules. Execution is started of a third submodule that corresponds to the determined third submodule node.

3. 发明授权

US10114853B2 Optimizing the initialization of a queue via a batch operation 审中-公开
公开(公告)号：US10114853B2
公开(公告)日：2018-10-30
申请号：US14845610
申请日：2015-09-04
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： David Hom , Charles E. Mari , Robert J. Miller, Jr. , Harris M. Morgenstern , Elpida Tzortzatos
IPC分类号： G06F9/52 , G06F17/30
CPC分类号： G06F17/30371 , G06F9/485 , G06F9/52 , G06F9/526 , G06F17/30368 , G06F2209/484 , G06F2209/548
摘要： A method, a computer program product, and a system for performing a batch processing are provided. The batch processing includes initializing a set of elements corresponding to a set of resources to produce an initialized group and chaining the initialized group to previously initialized elements to produce an element batch, when the previously initialized elements are available. The batch processing further includes setting a system lock on the set of resources after the element batch is produced; executing a service routine to move the element batch to a queue by referencing first and last elements of the element batch; and releasing the system lock on the set of resources once the service routine is complete.

4. 发明授权

US09928109B2 Method and system for processing nested stream events 有权
公开(公告)号：US09928109B2
公开(公告)日：2018-03-27
申请号：US13467804
申请日：2012-05-09
申请人： Luke Durant
发明人： Luke Durant
IPC分类号： G06F9/48 , G06F9/54
CPC分类号： G06F9/4881 , G06F9/542 , G06F2209/484
摘要： One embodiment of the present disclosure sets forth a technique for enforcing cross stream dependencies in a parallel processing subsystem such as a graphics processing unit. The technique involves queuing waiting events to create cross stream dependencies and signaling events to indicated completion to the waiting events. A scheduler kernel examines a task status data structure from a corresponding stream and updates dependency counts for tasks and events within the stream. When each task dependency for a waiting event is satisfied, an associated task may execute.

5. 发明授权

US09665920B1 Simultaneous execution of compute and graphics applications 有权
公开(公告)号：US09665920B1
公开(公告)日：2017-05-30
申请号：US12641232
申请日：2009-12-17
申请人： Chad D. Walker , Rui M. Bastos , Narayan Kulshrestha
发明人： Chad D. Walker , Rui M. Bastos , Narayan Kulshrestha
IPC分类号： G06T1/20 , G06T1/60 , G06F9/54 , G06T15/00
CPC分类号： G06T1/20 , G06F9/38 , G06F9/4881 , G06F9/544 , G06F2209/484 , G06F2209/485 , G06T1/60 , G06T15/005
摘要： One embodiment of the present invention sets forth a technique for distributing graphics commands and atomic commands to a color processing unit (CROP) in an efficient manner. The interleaving mechanism determines, at each clock cycle, which graphics command(s) or atomic command(s) is transmitted to the CROP based on different factors. First, the interleaving mechanism ensures that atomic commands or graphics commands associated with a multi-transaction command stream are processed together. Second, the interleaving mechanism selects consecutive graphics commands for transmission to the CROP that optimize the use of different memory caches. Third, the interleaving mechanism prioritizes atomic commands over graphics commands. At each clock cycle, the graphics command(s) or the atomic command(s) selected by the interleaving mechanism are transmitted to the CROP for processing.

6. 发明授权

US09652286B2 Runtime handling of task dependencies using dependence graphs 有权
公开(公告)号：US09652286B2
公开(公告)日：2017-05-16
申请号：US14222273
申请日：2014-03-21
申请人： Oracle International Corporation
发明人： Bin Fan
IPC分类号： G06F9/46 , G06F9/48
CPC分类号： G06F9/4881 , G06F2209/484
摘要： Embodiments include systems and methods for handling task dependencies in a runtime environment using dependence graphs. For example, a computer-implemented runtime engine includes runtime libraries configured to handle tasks and task dependencies. The task dependencies can be converted into data dependencies. At runtime, as the runtime engine encounters tasks and associated data dependencies, it can add those identified tasks as nodes of a dependence graph, and can add edges between the nodes that correspond to the data dependencies without deadlock. The runtime engine can schedule the tasks for execution according to a topological traversal of the dependence graph in a manner that preserves task dependencies substantially as defined by the source code.

7. 发明授权

US09519530B2 Detecting conflicting operations and providing resolution in a tasking system 有权
标题翻译：检测冲突操作并在任务系统中提供解决方案
公开(公告)号：US09519530B2
公开(公告)日：2016-12-13
申请号：US13483706
申请日：2012-05-30
申请人： Jason L. Connor
发明人： Jason L. Connor
IPC分类号： G06F9/46 , G06F13/00 , G06F11/07 , G06F9/48
CPC分类号： G06F11/0715 , G06F9/4881 , G06F11/0766 , G06F2209/484 , G06F2209/485
摘要： A mechanism for detecting conflicting operations and providing resolutions in a tasking system is disclosed. A method includes receiving, by a processing device in a tasking system, a request for a call including at least one operation to be executed on at least one resource of a plurality of resources that are managed by the tasking system. The method also includes detecting an occurrence of a conflict between the at least one operation on the call request and queued operations associated with the plurality of resources. The method also includes generating at least one of a task or an error report for the at least one operation in the call request based on the conflict. The method further includes identifying task dependencies associated with the at least one task and executing the at least one task only after execution of the task dependencies.
摘要翻译：公开了一种检测冲突操作并在任务系统中提供分辨率的机制。一种方法包括：由任务系统中的处理设备接收包括对由所述任务系统管理的多个资源的至少一个资源执行的至少一个操作的呼叫请求。该方法还包括检测呼叫请求上的至少一个操作与与多个资源相关联的排队操作之间的冲突的发生。该方法还包括基于该冲突来生成呼叫请求中的至少一个操作的任务或错误报告中的至少一个。所述方法还包括识别与所述至少一个任务相关联的任务依赖性，并且仅在执行所述任务依赖性之后执行所述至少一个任务。

8. 发明授权

US09400680B2 Transportation network micro-simulation with pre-emptive decomposition 有权
标题翻译：运输网络微模拟与抢先分解
公开(公告)号：US09400680B2
公开(公告)日：2016-07-26
申请号：US14532127
申请日：2014-11-04
申请人： Xerox Corporation
发明人： Guillaume Bouchard , Luis Rafael Ulloa Paredes
IPC分类号： G06F9/46 , G06F9/48 , G06N7/00
CPC分类号： G06N7/005 , G06F9/4887 , G06F2209/483 , G06F2209/484
摘要： In a parallel computing method performed by a parallel computing system comprising a plurality of central processing units (CPUs), a main process executes. Tasks are executed in parallel with the main process on CPUs not used in executing the main process. Results of completed tasks are stored in a cache, from which the main process retrieves completed task results when needed. The initiation of task execution is controlled by a priority ranking of tasks based on at least probabilities that task results will be needed by the main process and time limits for executing the tasks. The priority ranking of tasks is from the vantage point of a current execution point in the main process and is updated as the main process executes. An executing task may be pre-empted by a task having higher priority if no idle CPU is available.
摘要翻译：在由包括多个中央处理单元（CPU）的并行计算系统执行的并行计算方法中，执行主处理。任务与执行主进程中未使用的CPU的主进程并行执行。完成的任务的结果存储在缓存中，主进程在需要时从中获取完成的任务结果。任务执行的启动由任务基于至少概率的优先级排序来控制，任务结果将由主进程和执行任务的时间限制所需要。任务的优先级排序来自主进程当前执行点的有利位置，并在主进程执行时更新。如果没有空闲CPU可用，则执行任务可以被具有较高优先级的任务抢占。

9. 发明申请

US20160124770A1 TRANSPORTATION NETWORK MICRO-SIMULATION PRE-EMPTIVE DECOMPOSITION 有权
标题翻译：运输网络微模拟预分解
公开(公告)号：US20160124770A1
公开(公告)日：2016-05-05
申请号：US14532127
申请日：2014-11-04
申请人： Xerox Corporation
发明人： Guillaume Bouchard , Luis Ulloa
IPC分类号： G06F9/48 , G06N7/00
CPC分类号： G06N7/005 , G06F9/4887 , G06F2209/483 , G06F2209/484
摘要： In a parallel computing method performed by a parallel computing system comprising a plurality of central processing units (CPUs), a main process executes. Tasks are executed in parallel with the main process on CPUs not used in executing the main process. Results of completed tasks are stored in a cache, from which the main process retrieves completed task results when needed. The initiation of task execution is controlled by a priority ranking of tasks based on at least probabilities that task results will be needed by the main process and time limits for executing the tasks. The priority ranking of tasks is from the vantage point of a current execution point in the main process and is updated as the main process executes. An executing task may be pre-empted by a task having higher priority if no idle CPU is available.
摘要翻译：在由包括多个中央处理单元（CPU）的并行计算系统执行的并行计算方法中，执行主处理。任务与执行主进程中未使用的CPU的主进程并行执行。完成的任务的结果存储在缓存中，主进程在需要时从中获取完成的任务结果。任务执行的启动由任务基于至少概率的优先级排序来控制，任务结果将由主进程和执行任务的时间限制所需要。任务的优先级排序来自主进程当前执行点的有利位置，并在主进程执行时更新。如果没有空闲CPU可用，则执行任务可以被具有较高优先级的任务抢占。

10. 发明授权

US09286119B2 System, method, and computer program product for management of dependency between tasks 有权
标题翻译：系统，方法和计算机程序产品，用于管理任务之间的依赖关系
公开(公告)号：US09286119B2
公开(公告)日：2016-03-15
申请号：US13766595
申请日：2013-02-13
申请人： NVIDIA Corporation
发明人： Igor Sevastiyanov , Brian Matthew Fahs , Nicholas Wang , Scott Ricketts , Luke David Durant , Brian Scott Pharris
IPC分类号： G06F9/46 , G06F9/48
CPC分类号： G06F9/4881 , G06F2209/484
摘要： A system, method, and computer program product for management of dynamic task-dependency graphs. The method includes the steps of generating a first task data structure in a memory for a first task, generating a second task data structure in the memory, storing a pointer to the second task data structure in a first output dependence field of the first task data structure, setting a reference counter field of the second task data structure to a threshold value that indicates a number of dependent events associated with the second task, and launching the second task when the reference counter field stores a particular value. The second task data structure is a placeholder for a second task that is dependent on the first task.
摘要翻译：一种用于管理动态任务依赖图的系统，方法和计算机程序产品。该方法包括以下步骤：在用于第一任务的存储器中生成第一任务数据结构，在存储器中生成第二任务数据结构，在第一任务数据的第一输出依赖字段中存储指向第二任务数据结构的指针将第二任务数据结构的参考计数器字段设置为指示与第二任务相关联的依赖事件的数量的阈值，以及当参考计数器字段存储特定值时启动第二任务。第二任务数据结构是依赖于第一任务的第二任务的占位符。

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