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

US10929805B2 Adjusting simulation times for cost simulation analysis of transportation lane proposals based on space and time granularities 有权
公开(公告)号：US10929805B2
公开(公告)日：2021-02-23
申请号：US16052560
申请日：2018-08-01
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Joao Goncalves , Parijat Dube
IPC分类号： G06Q10/08 , G06Q10/06 , G06Q30/06
摘要： A method and system of simulating a cost of shipment are provided. A request for quote (RFQ) is received by a computing device from a shipper having a plurality of trade lanes. A revenue generated from each trade lane is estimated and ranked based on the estimated revenue. An original time limit is assigned to each trade lane. A trade lane with a highest ranking that has not yet been selected is selected. For the selected trade lane, graphs for space and time granularity analysis are generated. Space and time granularities that maximize accuracy within the assigned time limit based on the generated graphs are calculated. Cost simulation analysis is performed using the calculated space and time granularities. Upon determining that there are trade lanes not yet selected, there is a return to the act of selecting a trade lane.

2. 发明授权

US10133774B2 Accelerating multiple query processing operations 有权
公开(公告)号：US10133774B2
公开(公告)日：2018-11-20
申请号：US14018646
申请日：2013-09-05
申请人： International Business Machines Corporation
发明人： Sameh W. Asaad , Parijat Dube , Hong Min , Bharat Sukhwani , Mathew S. Thoennes
IPC分类号： G06F17/30
摘要： Embodiments include methods, systems and computer program products a for offloading multiple processing operations to an accelerator includes receiving, by a processing device, a database query from an application. The method also includes performing analysis on the database query and selecting an accelerator template from a plurality of accelerator templates based on the analysis of the database query. The method further includes transmitting an indication of the accelerator template to the accelerator and executing at least a portion of the database query on the accelerator.

3. 发明授权

US09921809B2 Scaling a cloud infrastructure 有权
公开(公告)号：US09921809B2
公开(公告)日：2018-03-20
申请号：US15008552
申请日：2016-01-28
申请人： International Business Machines Corporation
发明人： Parijat Dube , Anshul Gandhi , Alexei Karve , Andrzej Kochut , Li Zhang
IPC分类号： G06F9/44 , H04L12/24 , H04L29/08 , G06F9/445 , G06F9/455
CPC分类号： G06F8/20 , G06F8/61 , G06F8/70 , G06F8/77 , G06F9/45558 , G06F2009/4557 , G06F2009/45595 , H04L41/12 , H04L41/14 , H04L41/5006 , H04L41/5054 , H04L67/10
摘要： A method for scaling a cloud infrastructure, comprises receiving at least one of resource-level metrics and application-level metrics, estimating parameters of at least one application based on the received metrics, automatically and dynamically determining directives for scaling application deployment based on the estimated parameters, and providing the directives to a cloud service provider to execute the scaling.

4. 发明申请

US20160357817A1 SCALABLE ACCELERATION OF DATABASE QUERY OPERATIONS 审中-公开
公开(公告)号：US20160357817A1
公开(公告)日：2016-12-08
申请号：US15239097
申请日：2016-08-17
申请人： International Business Machines Corporation
发明人： Sameh W. Asaad , Parijat Dube , Hong Min , Bharat Sukhwani , Mathew S. Thoennes
IPC分类号： G06F17/30
CPC分类号： G06F17/30469 , G06F17/30463 , G06F17/30466 , G06F17/30477
摘要： Embodiments include methods, systems and computer program products for offloading multiple processing operations to an accelerator. Aspects include receiving a database query from an application, performing an analysis on the query, and identifying a plurality of available accelerators. Aspects further include retrieving cost information for one or more templates available on each of the plurality of available accelerators, determining a query execution plan based on the cost information and the analysis on the query, and offloading one or more query operations to at least one of the plurality of accelerators based on the query execution plan.

5. 发明申请

US20160224268A1 EXTENDIBLE INPUT/OUTPUT DATA MECHANISM FOR ACCELERATORS 有权
标题翻译：用于加速器的可扩展输入/输出数据机制
公开(公告)号：US20160224268A1
公开(公告)日：2016-08-04
申请号：US15092732
申请日：2016-04-07
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Sameh W. Asaad , Parijat Dube , Hong Min , Donald W. Schmidt , Bharat Sukhwani , Mathew S. Thoennes
IPC分类号： G06F3/06
CPC分类号： G06F9/5016 , G06F9/544 , G06F12/0835 , G06F12/084 , G06F12/0855
摘要： Embodiments include methods, systems and computer program products for providing an extendable job structure for executing instructions on an accelerator. The method includes creating a number of data descriptor blocks, each memory location addresses and a pointer to a next of the number of the data descriptor block. The method further includes creating a last data descriptor block having memory location addresses and a last block indicator. Based on determining that additional memory is required for executing instructions on the accelerator, the method includes modifying the last data descriptor block to become a data extender block having a pointer to one of one or more new data descriptor blocks and creating a new last data descriptor block.
摘要翻译：实施例包括用于提供用于在加速器上执行指令的可扩展作业结构的方法，系统和计算机程序产品。该方法包括创建多个数据描述符块，每个存储器位置地址和指向数据描述符块的下一个的指针。该方法还包括创建具有存储器位置地址和最后块指示符的最后数据描述符块。基于确定在加速器上执行指令所需的附加存储器，该方法包括修改最后数据描述符块以变成具有指向一个或多个新数据描述符块之一的指针的数据扩展器块，并且创建新的最后数据描述符块。

6. 发明授权

US09317497B2 Offloading projection of fixed and variable length database columns 有权
标题翻译：卸载固定和可变长度数据库列的投影
公开(公告)号：US09317497B2
公开(公告)日：2016-04-19
申请号：US13971302
申请日：2013-08-20
申请人： International Business Machines Corporation
发明人： Sameh W. Asaad , Parijat Dube , Hong Min , Bharat Sukhwani , Mathew S. Thoennes
IPC分类号： G06F17/30 , G06F17/27
CPC分类号： G06F17/30424 , G06F17/2705 , G06F17/30289 , G06F17/30315 , G06F17/30345 , G06F17/30442 , G06F17/30516
摘要： In an exemplary embodiment of this disclosure, a computer-implemented method includes determining that a database query warrants a first projection operation to project a plurality of input rows to a plurality of projected rows, where each of the plurality of input rows has one or more variable-length columns. A first projection control block is constructed, by a computer processor, to describe the first projection operation. The first projection operation is offloaded to a hardware accelerator. The first projection control block is provided to the hardware accelerator, and the first projection control block enables the hardware accelerator to perform the first projection operation at streaming rate.
摘要翻译：在本公开的示例性实施例中，计算机实现的方法包括确定数据库查询保证第一投影操作以将多个输入行投影到多个投影行，其中多个输入行中的每一个具有一个或多个可变长度的列。第一投影控制块由计算机处理器构成以描述第一投影操作。第一个投影操作被卸载到硬件加速器。第一投影控制块被提供给硬件加速器，并且第一投影控制块使得硬件加速器能够以流速执行第一投影操作。

7. 发明申请

US20160085587A1 DATA-AWARE WORKLOAD SCHEDULING AND EXECUTION IN HETEROGENEOUS ENVIRONMENTS 有权
标题翻译：数据识别工作载荷调度和异构环境中的执行
公开(公告)号：US20160085587A1
公开(公告)日：2016-03-24
申请号：US14489664
申请日：2014-09-18
申请人： International Business Machines Corporation
发明人： Parijat Dube , Li Zhang
IPC分类号： G06F9/50 , G06F9/48
CPC分类号： G06F9/4881 , G06F9/5005 , G06F9/5011 , G06F9/5027
摘要： In an approach for scheduling the execution of a workload in a computing environment, a computer receives a request for scheduling execution of a computing job, wherein the computing job includes a plurality of computing tasks to be executed in a sequence, and wherein at least one computing task requires access to a set of data. The computer identifies information related to the computing environment, wherein the information comprises at least processors available to execute each computing task of the plurality of computing tasks and storage device proximity to the processors. The computer determines an execution configuration for the computing job based, at least in part, on the received request, the information related to the computing environment, and current utilization of the processors' resources. The computer schedules execution of the execution configuration for the computing job.
摘要翻译：在计算环境中调度执行工作负载的方法中，计算机接收对计划作业的执行进行调度的请求，其中所述计算作业包括要按顺序执行的多个计算任务，并且其中至少一个计算任务需要访问一组数据。计算机识别与计算环境有关的信息，其中该信息至少包括可用于执行多个计算任务的每个计算任务的处理器和存储设备与处理器接近的处理器。所述计算机至少部分地基于所接收的请求，与所述计算环境相关的信息以及所述处理器的资源的当前利用来确定所述计算作业的执行配置。计算机计划执行计算作业的执行配置。

8. 发明申请

US20150026220A1 OFFLOADING PROJECTION OF FIXED AND VARIABLE LENGTH DATABASE COLUMNS 有权
标题翻译：固定和可变长度数据库列的卸载投影
公开(公告)号：US20150026220A1
公开(公告)日：2015-01-22
申请号：US13971302
申请日：2013-08-20
申请人： International Business Machines Corporation
发明人： Sameh W. Asaad , Parijat Dube , Hong Min , Bharat Sukhwani , Mathew S. Thoennes
IPC分类号： G06F17/30
CPC分类号： G06F17/30424 , G06F17/2705 , G06F17/30289 , G06F17/30315 , G06F17/30345 , G06F17/30442 , G06F17/30516
摘要： In an exemplary embodiment of this disclosure, a computer-implemented method includes determining that a database query warrants a first projection operation to project a plurality of input rows to a plurality of projected rows, where each of the plurality of input rows has one or more variable-length columns. A first projection control block is constructed, by a computer processor, to describe the first projection operation. The first projection operation is offloaded to a hardware accelerator. The first projection control block is provided to the hardware accelerator, and the first projection control block enables the hardware accelerator to perform the first projection operation at streaming rate.
摘要翻译：在本公开的示例性实施例中，计算机实现的方法包括确定数据库查询保证第一投影操作以将多个输入行投影到多个投影行，其中多个输入行中的每一个具有一个或多个可变长度的列。第一投影控制块由计算机处理器构成以描述第一投影操作。第一个投影操作被卸载到硬件加速器。第一投影控制块被提供给硬件加速器，并且第一投影控制块使得硬件加速器能够以流速执行第一投影操作。

9. 发明申请

US20140201451A1 METHOD, APPARATUS AND COMPUTER PROGRAMS PROVIDING CLUSTER-WIDE PAGE MANAGEMENT 有权
标题翻译：方法，设备和计算机程序提供集群页面管理
公开(公告)号：US20140201451A1
公开(公告)日：2014-07-17
申请号：US13967857
申请日：2013-08-15
申请人： International Business Machines Corporation
发明人： Parijat Dube , Xavier R. Guerin , Seetharami R. Seelam
IPC分类号： G06F12/08
CPC分类号： G06F12/084 , G06F9/45558 , G06F12/08 , G06F12/0864 , G06F17/30 , G06F2009/45583 , G06F2212/152 , G06F2212/163 , G06F2212/62
摘要： A data processing system includes a plurality of virtual machines each having associated memory pages; a shared memory page cache that is accessible by each of the plurality of virtual machines; and a global hash map that is accessible by each of the plurality of virtual machines. The data processing system is configured such that, for a particular memory page stored in the shared memory page cache that is associated with two or more of the plurality of virtual machines, there is a single key stored in the global hash map that identifies at least a storage location in the shared memory page cache of the particular memory page. The system can be embodied at least partially in a cloud computing system.
摘要翻译：数据处理系统包括多个虚拟机，每个虚拟机具有关联的存储器页面; 可由所述多个虚拟机中的每一个访问的共享存储器页面缓存; 以及可由所述多个虚拟机中的每一个访问的全局散列图。数据处理系统被配置为使得对于存储在与多个虚拟机中的两个或更多个虚拟机相关联的共享存储器页面高速缓存中的特定存储器页面，存在存储在全局散列图中的单个密钥，其至少标识特定存储器页面的共享存储器页面缓存中的存储位置。该系统可以至少部分地体现在云计算系统中。

10. 发明授权

US11151410B2 Generating and augmenting transfer learning datasets with pseudo-labeled images 有权
公开(公告)号：US11151410B2
公开(公告)日：2021-10-19
申请号：US16125153
申请日：2018-09-07
申请人： International Business Machines Corporation
发明人： Patrick Watson , Bishwaranjan Bhattacharjee , Siyu Huo , Noel C. Codella , Brian M. Belgodere , Parijat Dube , Michael R. Glass , John R. Kender , Matthew L. Hill
IPC分类号： G06K9/62 , G06F16/51
摘要： A computer-implemented method for data labeling is provided. The computer-implemented method assigns pseudo-labels to unlabeled examples of data using a similarity metric on an embedding space to produce pseudo-labeled examples. A curriculum learning model is trained using the pseudo-labeled examples. The curriculum learning model trained with the pseudo-labeled examples is employed in in a fine-tuning task to enhance classification accuracy of the data.

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