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. 发明申请

WO2019118338A1 SYSTEMS AND METHODS FOR MAPPING SOFTWARE APPLICATIONS INTERDEPENDENCIES 审中-公开
公开(公告)号：WO2019118338A1
公开(公告)日：2019-06-20
申请号：PCT/US2018/064729
申请日：2018-12-10
申请人： VFUNCTION, INC.
发明人： RAPSON, Amir , SIMCHONI, Uri , SAPORTA, Ori
IPC分类号： G06F8/41 , G06F9/50 , G06F11/36
CPC分类号： G06F8/456 , G06F9/5066 , G06F11/3409 , G06F11/3466 , G06F2201/865
摘要： Systems and methods are described to enable the effective mapping of monolithic computer programs into clusters of functions that may be separated out of a computer program in a way that may ensure such functions are of a similar domain. Separating such a cluster of functions away from the computer program may allow the cluster to be offloaded and executed in a distributed environment. Such systems and methods may be used on existing or legacy computer programs to determine clusters of interdependent functions, which may be used to execute the legacy computer programs more efficiently at least in terms of time, cost, and scalability. Because of this, software developers may not need to change existing coding practices or existing computer programs in order to take advantage of distributed computing infrastructures. Further, such clusters may also be executed and re-executed in such a distributed infrastructure without the need to execute other, larger segments of the computer program, allowing for near-infinite scalability.

2. 发明申请

WO2019040222A1 RENDERING AN IMAGE FROM COMPUTER GRAPHICS USING TWO RENDERING COMPUTING DEVICES 审中-公开
公开(公告)号：WO2019040222A1
公开(公告)日：2019-02-28
申请号：PCT/US2018/043578
申请日：2018-07-24
申请人： QUALCOMM INCORPORATED
发明人： SCHMALSTIEG, Dieter , REITMAYR, Gerhard , DIAZ SPINDOLA, Serafin
IPC分类号： G06T15/00 , G06T11/00 , G06T15/04
CPC分类号： G06T15/80 , G06F9/5066 , G06T11/001 , G06T15/005 , G06T15/04 , G06T15/20 , G06T15/40 , G06T15/60
摘要： An example system includes a first computing device comprising a first graphics processing unit (GPU) implemented in circuitry, and a second computing device comprising a second GPU implemented in circuitry. The first GPU is configured to determine graphics primitives of a computer graphics scene that are visible from a camera viewpoint, generate a primitive atlas that includes data representing the graphics primitives that are visible from the camera viewpoint, and shade the visible graphics primitives in the primitive atlas to produce a shaded primitive atlas. The second GPU is configured to render an image using the shaded primitive atlas.

3. 发明申请

WO2018205246A1 PARALLEL COMPUTATION ENGINE FOR GRAPH DATA 审中-公开
公开(公告)号：WO2018205246A1
公开(公告)日：2018-11-15
申请号：PCT/CN2017/084083
申请日：2017-05-12
申请人： SHANGHAI PUTU TECHNOLOGY PARTNERSHIP (GENERAL PARTNERSHIP)
发明人： FAN, Wenfei , XU, Jingbo , YU, Wenyuan
IPC分类号： G06F17/30
CPC分类号： G06F16/00 , G06F9/5066
摘要： A parallel system for graph computations, comprising the steps of: partitioning G into (F 1 ,..., F m ) with P, and distributing F i 's across m shared-nothing virtual workers (P 1 ,..., P m ), given a partition strategy P and sequential PEval, IncEval and Assemble for a class Q of graph queries; mapping m virtual workers to n physical workers; constructing fragmentation graph GP; and upon receiving Q at coordinator P 0 , posting the same Q to all the workers.

4. 发明申请

WO2018118367A1 MID-RENDER COMPUTE FOR GRAPHICS PROCESSING 审中-公开
公开(公告)号：WO2018118367A1
公开(公告)日：2018-06-28
申请号：PCT/US2017/063806
申请日：2017-11-29
申请人： APPLE INC.
发明人： POTTER, Terence M. , TAYLOR, Ralph C. , SCHREYER, Richard W. , MUNSHI, Aaftab A. , HENSLEY, Justin A.
IPC分类号： G06T15/00 , G06F9/50 , G06F9/54 , G06T1/20 , G06T15/80
CPC分类号： G06T15/005 , G06F9/5038 , G06F9/5066 , G06F9/544 , G06T1/20 , G06T1/60 , G06T15/80 , Y02D10/22 , Y02D10/36
摘要： Techniques are disclosed relating to performing mid-render auxiliary compute tasks for graphics processing. In some embodiments, auxiliary compute tasks are performed during a render pass, using at least a portion of a memory context of the render pass, without accessing a shared memory during the render pass. Relative to flushing render data to shared memory to perform compute tasks, this may reduce memory accesses and/or cache thrashing, which may in turn increase performance and/or reduce power consumption.

5. 发明申请

WO2017191489A1 DISTRIBUTED NETWORK-AWARE SERVICE PLACEMENT UTILIZING CONSTRAINED KERNIGHAN-LIN HEURISTIC MODELS 审中-公开
标题翻译：分布式网络服务布局使用受约束的金斯林启发式模型
公开(公告)号：WO2017191489A1
公开(公告)日：2017-11-09
申请号：PCT/IB2016/052519
申请日：2016-05-03
申请人： TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
发明人： YAZIR, Yagiz Onat , HALÉN, Joacim , ABBASI, Zahra , BAUCKE, Stephan
IPC分类号： G06F9/50
CPC分类号： G06F9/5072 , G06F9/5066
摘要： Distributed agents perform network-aware service placement utilizing a modified constrained Kernighan-Lin (KL) based heuristic model. In a first phase, the distributed control agents cooperate to compute a set of placement solutions that meet the computational requirements. In the second phase, the constrained KL heuristic model is utilized to identify placements within that solution space that push the network load to the lower levels of the cloud infrastructure to thereby reduce the network load at the core and aggregate levels of the cloud system switching fabric. The constrained KL heuristic model generates initial partitions that are compliant with placement solutions provided by child agents, and gains are calculated only for admissible swaps.
摘要翻译：分布式代理使用修改的约束Kernighan-Lin（KL）启发式模型执行网络感知服务布局。在第一阶段，分布式控制代理合作计算满足计算要求的一组布局解决方案。在第二阶段，利用受约束的KL启发式模型来识别解决方案空间内的布局，将网络负载推送到云基础架构的较低级别，从而降低云系统交换结构的核心和聚合级别的网络负载。受约束的KL启发式模型生成的初始分区符合子代理商提供的安置解决方案，并且收益仅针对可接受的交换进行计算。

6. 发明申请

WO2017148503A1 METHOD AND STREAM PROCESSING SYSTEM FOR MANAGING DATA STREAM PROCESSING TASKS OF A PREDEFINED APPLICATION TOPOLOGY 审中-公开
标题翻译：用于管理预定应用拓扑的数据流处理任务的方法和流处理系统
公开(公告)号：WO2017148503A1
公开(公告)日：2017-09-08
申请号：PCT/EP2016/054242
申请日：2016-02-29
申请人： NEC EUROPE LTD.
发明人： CHENG, Bin , PAPAGEORGIOU, Apostolos , BAUER, Martin
IPC分类号： G06F9/48 , G06F9/50
CPC分类号： G06F9/4881 , G06F9/4843 , G06F9/5066 , G06F9/5083
摘要： A method for managing data stream processing tasks of a predefined application topology in a stream processing system, wherein said stream processing system comprises one or more data producers, one or more compute nodes and one or more result consumers, wherein geographic scope granularities are assigned to the data stream processing tasks of the application topology, wherein a result consumer sends a subscription to a task manager in order to trigger data processing for computing a result, wherein said subscription includes geographic scope related information concerning the triggered data processing, wherein, based on the geographic scope related information of said subscription, the task manager generates an execution plan including task instances for performing the triggered data processing, and wherein the task manager generates from the execution plan a deployment plan for deploying the task instances of the execution plan on the compute nodes. Furthermore, a corresponding stream processing system is disclosed.
摘要翻译：一种用于管理流处理系统中的预定义应用拓扑的数据流处理任务的方法，其中所述流处理系统包括一个或多个数据生成器，一个或多个计算节点以及一个或多个结果消费者，其中地理范围粒度被分配给应用拓扑的数据流处理任务，其中结果消费者向任务管理器发送预订以触发用于计算结果的数据处理，其中所述预订包括涉及与地理范围有关的信息其中，基于所述预订的地理范围相关信息，所述任务管理器生成包括用于执行所触发的数据处理的任务实例的执行计划，并且其中，所述任务管理器从所述执行计划生成用于部署所述触发数据处理的部署计划计算节点上执行计划的任务实例。此外，还公开了相应的流处理系统。

7. 发明申请

WO2017125146A1 METHOD AND SYSTEM FOR SUPPORTING STREAM PROCESSING FRAMEWORK FUNCTIONALITY 审中-公开
标题翻译：支持流处理框架功能的方法和系统
公开(公告)号：WO2017125146A1
公开(公告)日：2017-07-27
申请号：PCT/EP2016/051105
申请日：2016-01-20
申请人： NEC EUROPE LTD.
发明人： PAPAGEORGIOU, Apostolos , CHENG, Bin
IPC分类号： G06F9/50
CPC分类号： G06F9/5066
摘要： A method for supporting stream processing framework functionality in a stream processing system, wherein the system comprises one or more input modules, a stream processing platform and computing nodes, wherein said stream processing platform uses said input modules in order to prepare, deploy and execute tasks of at least one stream processing topology on the computing nodes, wherein the tasks are deployed on the computing nodes based on both stream processing topology-related information and stream processing topology-external information. Furthermore, a corresponding system for supporting stream processing framework functionality is disclosed.
摘要翻译：一种用于支持流处理系统中的流处理框架功能的方法，其中所述系统包括一个或多个输入模块，流处理平台和计算节点，其中所述流处理平台将所述输入模块用于以便在计算节点上准备，部署和执行至少一个流处理拓扑的任务，其中基于流处理拓扑相关信息和流处理拓扑外部信息两者在计算节点上部署任务。此外，还公开了一种用于支持流处理框架功能的相应系统。

8. 发明申请

WO2017117216A1 SYSTEMS AND METHODS FOR CACHING TASK EXECUTION 审中-公开
标题翻译：用于缓存任务执行的系统和方法
公开(公告)号：WO2017117216A1
公开(公告)日：2017-07-06
申请号：PCT/US2016/068869
申请日：2016-12-28
申请人： TAO, Tao , BARDWAJ, Santosh , KUMAR, Subodh , EUGLEY, Brian
发明人： TAO, Tao , BARDWAJ, Santosh , KUMAR, Subodh , EUGLEY, Brian
IPC分类号： G06F9/00 , G06F9/46 , G06F9/50
CPC分类号： G06F9/4881 , G06F9/5033 , G06F9/5066 , H04L67/04 , H04L67/10 , H04L67/2842 , H04L67/32 , H04L67/322 , H04L67/327
摘要： Certain disclosed embodiments provide improved systems and methods for processing jobs. The method comprises steps including receiving, from a client device over a network, information representing a job and generating at least two tasks representative of the job. The method further comprises, for each task, assigning, by a processor, a signature to the task representative of whether the task has been processed, determining at least one dataset related to the task, and assigning a signature to the determined at least one dataset. The method further comprises searching, by the processor, a data structure for the task signature, and based on the searching, sending the task over a network to a task executor for processing or locating results associated with the task. The method further comprises sending, over a network, a job result to the client device. Systems and computer readable media are also provided.
摘要翻译：某些公开的实施例提供了用于处理作业的改进的系统和方法。该方法包括以下步骤：包括通过网络从客户端设备接收表示作业的信息并生成表示作业的至少两个任务。该方法进一步包括，对于每个任务，由处理器向代表该任务是否已经处理的任务分配签名，确定与该任务相关的至少一个数据集，以及将签名分配给确定的至少一个数据集。该方法还包括由处理器搜索任务签名的数据结构，并且基于搜索，通过网络将任务发送给任务执行器，以处理或定位与该任务相关联的结果。该方法进一步包括通过网络向客户端设备发送作业结果。还提供系统和计算机可读介质。

9. 发明申请

WO2017108119A1 RACK AWARENESS 审中-公开
公开(公告)号：WO2017108119A1
公开(公告)日：2017-06-29
申请号：PCT/EP2015/081101
申请日：2015-12-23
申请人： HUAWEI TECHNOLOGIES CO., LTD. , SAGIE, Gal , GAL-OR, Eshed
发明人： SAGIE, Gal , GAL-OR, Eshed
IPC分类号： G06F9/50 , H04L12/24
CPC分类号： G06F9/5066 , G06F9/5072 , H04L41/12
摘要： The present invention relates to a method for discovering network-level proximity between nodes (141, 143, 205, 206) of a software-defined data centre, SDDC, (100, 200), wherein the SDDC (100, 200) comprises hosts (111-118, 121-128, 211-218, 221-228), each host being connected to one of the nodes (141, 143, 205, 206), the method comprising discovering the network-level proximity between the nodes based on a software-defined networking, SDN, control plane protocol.
摘要翻译：本发明涉及一种用于发现软件定义数据中心SDDC（100,200）的节点（141,143,205,206）之间的网络级接近度的方法，其中所述 SDDC（100,200）包括主机（111-118,121-128,211-218,221-228），每个主机连接到节点（141,143,205,206）之一，该方法包括发现基于软件定义网络，SDN，控制平面协议的节点之间的网络级接近度。

10. 发明申请

WO2017106606A2 SYSTEM AND METHODS FOR THE COMPUTATION OF THE FORWARD AND INVERSE DISCRETE PERIODIC RADON TRANSFORM ON GPUs AND CPUs 审中-公开
标题翻译：用于在GPU和CPU上计算前向和反向离散周期性氡变换的系统和方法
公开(公告)号：WO2017106606A2
公开(公告)日：2017-06-22
申请号：PCT/US2016/067110
申请日：2016-12-16
申请人： STC.UNM
发明人： PATTICHIS, Marios Stephanou , CARRANZA, Cesar , LLAMOCCA OBREGON, Daniel Rolando
CPC分类号： G06F9/5066 , G01V2210/46 , G06T11/006
摘要： Fast and a scalable algorithms and methods adaptable to available resources for computing (1) the DPRT on multicore CPUs by distributing the computation of the DPRT primary directions among the different cores, and (2) the DPRT on GPUs using parallel, distributed, and synchronized ray computations among the GPU cores with "ray" referring to one of the sums required for computing the DPRT or its inverse along a prime direction.
摘要翻译：快速且可扩展的算法和方法适用于计算（1）通过在不同核心之间分配DPRT主方向的计算的多核CPU上的DPRT，以及（2）DPRT在在GPU核心之间使用并行，分布式和同步光线计算的GPU具有“射线” 指的是按照主要方向计算DPRT或其倒数所需的总和之一。

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