公开(公告)号：US20180293487A1

公开(公告)日：2018-10-11

申请号：US15479814

申请日：2017-04-05

申请人： International Business Machines Corporation

发明人： Matthew Warren COPEL ,  James Bowler Hannon ,  Satoshi Oida ,  John Jacob Yurkas

IPC分类号： G06N3/063 ,  G06N3/04

CPC分类号： G06N3/0635 ,  G06N3/049 ,  G06N3/084 ,  G06N3/088 ,  G11C11/54 ,  G11C13/0069 ,  G11C2213/32 ,  G11C2213/77

摘要： A resistive element in an electrochemical artificial neural network, includes a transition metal oxide thin film forming a working electrode, a pair of first electrodes connected to the working electrode, and a reference electrode for electrochemical doping of the working electrode. The biasing of the pair of first electrodes with respect to the reference electrode according to a determination of conductivity between the pair of first electrodes controls the resistance of the working electrode.

公开(公告)号：US20140082357A1

公开(公告)日：2014-03-20

申请号：US13781624

申请日：2013-02-28

申请人： Alan James Chatt ,  Christopher Colin Paice ,  Cyril Peter Stewart

发明人： Alan James Chatt ,  Christopher Colin Paice ,  Cyril Peter Stewart

IPC分类号： H04L29/06

CPC分类号： H04L9/3247 ,  H04L9/3268 ,  H04L63/0428 ,  H04L63/0442 ,  H04L63/045 ,  H04L63/0464 ,  H04L63/0471 ,  H04L63/0823 ,  H04L63/101 ,  H04L63/123 ,  H04L63/126

摘要： A method provides cross enterprise communication in which intermediary communication components carry out cross enterprise communication. The method at a first sending enterprise comprises: receiving a signed encrypted message from a sender within a first enterprise; validating the sender; decrypting the message; encrypting the message for receipt by a second enterprise; signing the encrypted message by the first enterprise; and sending the re-signed re-encrypted message to a second enterprise. The method at the second receiving enterprise comprises: receiving a signed encrypted message from a first enterprise; validating that the first enterprise is the sender; decrypting the message; encrypting the message for receipt by one or more recipients at the second enterprise; signing the encrypted message by the second enterprise indicating that the message is from the first enterprise; and sending the re-signed re-encrypted message to the one or more recipients of the second enterprise.

摘要翻译： 一种方法提供跨企业通信，其中中间通信组件进行跨企业通信。 第一发送企业的方法包括：从第一企业内的发送者接收签名的加密消息; 验证发件人; 解密消息; 加密消息以供第二企业接收; 由第一企业签署加密消息; 并将重新签名的重新加密的消息发送到第二企业。 所述第二接收企业的方法包括：从第一企业接收签名的加密消息; 验证第一企业是发件人; 解密消息; 加密消息以供第一企业的一个或多个接收者接收; 由第二企业签署加密消息，指示消息来自第一企业; 以及将重新签名的重新加密的消息发送到第二企业的一个或多个接收者。

公开(公告)号：US20140012808A1

公开(公告)日：2014-01-09

申请号：US14016827

申请日：2013-09-03

申请人： IBM CORPORATION

发明人： Bruce Gilbert LINDSAY ,  Roger C. RAPHAEL ,  Paul Sherwood TAYLOR

IPC分类号： G06F17/30

CPC分类号： G06F9/5011 ,  G06F9/505 ,  G06F9/5061 ,  G06F9/5066 ,  G06F9/5088 ,  G06F9/54 ,  G06F17/30345

摘要： A method and system for distributing tasks from an external application among concurrent database application server instances in a database system for optimum load balancing, based on consensus among the instances. Each application instance identifies a task partition ownership by those in a membership group based on a time window and generates a new membership group and partition ownership based on the current partition ownership. The instance makes the new membership group and partition ownership known to other members by recoding them in the membership table and partition map. Each participation by an instance in the membership group is identified by a random number. The new membership group and partition ownership are generated and adjusted based on an average partition allocation to achieve consensus among the instances.

摘要翻译： 基于实例之间的一致性，用于在数据库系统中的并发数据库应用程序服务器实例之间从外部应用程序分发任务以实现最佳负载平衡的方法和系统。 每个应用程序实例基于时间窗口标识成员组中的任务分区所有权，并根据当前分区所有权生成新的成员组和分区所有权。 该实例通过在成员资格表和分区映射中对它们进行重新编码，使其他成员获得了新的成员组和分区所有权。 会员组中的实例的每个参与由随机数来标识。 根据平均分区分配生成和调整新成员组和分区所有权，以实现实例之间的一致。

公开(公告)号：US08586478B2

公开(公告)日：2013-11-19

申请号：US13424932

申请日：2012-03-20

申请人： Eiichi Soda ,  Yunpeng Yin ,  Sivananda Kanakasabapathy

发明人： Eiichi Soda ,  Yunpeng Yin ,  Sivananda Kanakasabapathy

IPC分类号： H01L21/44

CPC分类号： H01L21/31144 ,  H01L21/0337 ,  H01L21/76811 ,  H01L21/76816 ,  H01L21/76897

摘要： An improved method of making interconnect structures with self-aligned vias in semiconductor devices utilizes sidewall image transfer to define the trench pattern. The sidewall height acts as a sacrificial mask during etching of the via and subsequent etching of the trench, so that the underlying metal hard mask is protected. Thinner hard masks and/or a wider range of etch chemistries may thereby be utilized.

摘要翻译： 在半导体器件中制造具有自对准通孔的互连结构的改进方法利用侧壁图像转移来限定沟槽图案。 在蚀刻通孔和​​随后蚀刻沟槽期间，侧壁高度用作牺牲掩模，使得下面的金属硬掩模被保护。 因此可以利用更薄的硬掩模和/或更广泛的蚀刻化学物质。

公开(公告)号：US20130290918A1

公开(公告)日：2013-10-31

申请号：US13455839

申请日：2012-04-25

申请人： Jason R. Baumgartner ,  Robert L. Kanzelman ,  Hari Mony

发明人： Jason R. Baumgartner ,  Michael L. Case ,  Robert L. Kanzelman ,  Hari Mony

IPC分类号： G06F17/50

CPC分类号： G06F17/505 ,  G06F17/504

摘要： A computer-implemented method simplifies a netlist, verifies the simplified netlist using induction, and remaps resulting inductive counterexamples via inductive trace lifting within a multi-algorithm verification framework. The method includes: a processor deriving a first unreachable state information that can be utilized to simplify the netlist; performing a simplification of the netlist utilizing the first unreachable state information; determining whether the first unreachable state information can be inductively proved on an original version of the netlist; and in response to the first unreachable state information not being inductively provable on the original netlist: projecting the first unreachable state information to a minimal subset; and adding the projected unreachable state information as an invariant to further constrain a child induction process. Adding the projected state information as an invariant ensures that any resulting induction counterexamples can be mapped to valid induction counterexamples on the original netlist before undergoing the simplification.

摘要翻译： 计算机实现的方法简化了网表，使用归纳验证简化的网表，并通过多算法验证框架内的归纳跟踪提升重新生成归纳反例。 该方法包括：处理器导出可用于简化网表的第一不可达状态信息; 利用第一不可达状态信息来执行网表的简化; 确定在网表的原始版本上是否可以感应地证明第一不可达状态信息; 并且响应于在原始网表上不被感应地证明的第一不可达状态信息：将第一不可达状态信息投射到最小子集; 并且将预测的不可达状态信息添加为不变量以进一步约束儿童归纳过程。 将投影状态信息添加为不变量确保在进行简化之前，任何导致的归因反例可以映射到原始网表上的有效归纳反例。

公开(公告)号：US20130212330A1

公开(公告)日：2013-08-15

申请号：US13371906

申请日：2012-02-13

申请人： Mark A. Brittain ,  John S. Dodson ,  Stephen J. Powell ,  Eric E. Retter ,  Jeffrey A. Stuecheli

发明人： Mark A. Brittain ,  John S. Dodson ,  Stephen J. Powell ,  Eric E. Retter ,  Jeffrey A. Stuecheli

IPC分类号： G06F12/00

CPC分类号： G11C11/40607 ,  G06F13/1626 ,  G06F13/1689

摘要： A memory system and data processing system for controlling memory refresh operations in dynamic random access memories. The memory controller comprises logic that: tracks a time remaining before a scheduled time for performing a high priority, high latency operation a first memory rank of the memory system; responsive to the time remaining reaching a pre-established early notification time before the schedule time for performing the high priority, high latency operation, biases the re-order queue containing memory access operations targeting the plurality of ranks to prioritize scheduling of any first memory access operations that target the first memory rank. The logic further: schedules the first memory access operations to the first memory rank for early completion relative to other memory access operations in the re-order queue that target other memory ranks; and performs the high priority, high latency operation at the first memory rank at the scheduled time.

摘要翻译： 一种用于控制动态随机存取存储器中的存储器刷新操作的存储器系统和数据处理系统。 存储器控制器包括以下逻辑：跟踪在用于执行高优先级高等待时间操作的预定时间之前的剩余时间存储器系统的第一存储器等级; 响应于在执行高优先级高等待时间操作的调度时间之前达到预先建立的早期通知时间的时间，偏置包含针对多个等级的存储器访问操作的重新排序队列，以优先排序任何第一存储器访问 针对第一个内存排名的操作。 该逻辑进一步：将第一存储器访问操作调度到第一存储器等级以便相对于针对其他存储器排序的重新排序队列中的其他存储器访问操作来提前完成; 并且在预定时间在第一存储器等级执行高优先级，高延迟操作。

公开(公告)号：US20130073823A1

公开(公告)日：2013-03-21

申请号：US13621230

申请日：2012-09-15

申请人： Graham Hunter ,  James Mulcahy

发明人： Graham Hunter ,  James Mulcahy

IPC分类号： G06F12/16

CPC分类号： G06F9/45533 ,  G06F11/2038 ,  G06F11/2097 ,  G06F2201/815

摘要： A method for mirroring virtual machines from a primary host to a secondary host. The method includes tracking changes for each of a plurality of memory pages and processor states for one or more primary host virtual machines. Responsive to an occurrence of a checkpoint, the primary host virtual machines are stopped. A determination is made if each of the memory pages is frequently changed. In response to the memory page being frequently changed, the frequently changed memory page is marked as being writeable and copied to a buffer. In response to the memory page being infrequently changed, the infrequently changed memory page is marked as being read only. The one or more primary host virtual machines are resumed. A copy of the memory pages, the buffer and changes to the processor states are transmitted to the secondary host.

摘要翻译： 用于将虚拟机从主主机镜像到辅助主机的方法。 该方法包括跟踪针对一个或多个主要主机虚拟机的多个存储器页面和处理器状态中的每一个的变化。 响应于出现检查点，主机虚拟机被停止。 如果每个存储器页面被频繁地改变，则确定。 响应于频繁更改的内存页，频繁更改的内存页面被标记为可写入并复制到缓冲区。 响应于内存页不经常更改，不经常更改的内存页被标记为只读。 恢复一个或多个主要主机虚拟机。 存储器页面的副本，缓冲区和处理器状态的更改被传送到辅助主机。

公开(公告)号：US20130046998A1

公开(公告)日：2013-02-21

申请号：US13212027

申请日：2011-08-17

申请人： Alexander B. Brown ,  Neil A. Campbell ,  Ryan J. Cocks

发明人： Alexander B. Brown ,  Neil A. Campbell ,  Ryan J. Cocks

IPC分类号： G06F1/26

CPC分类号： G06F1/3234 ,  G06F1/3287 ,  H04L12/6418 ,  Y02D10/171

摘要： A system and computer program product allocates energy entitlement to a logical partition (LPAR) executing on a data processing system. An energy entitlement allocation (EEA) utility enables an administrator to specify a minimum and/or maximum energy entitlement and An LPAR priority. When the relevant LPARs utilize the respective minimum energy entitlement based on respective energy consumption, the EEA utility determines whether the LPAR (and other LPARs) has satisfied a respective maximum energy entitlement. When the LPAR has not satisfied its maximum energy entitlement, the EEA utility allocates unused energy entitlement from the data processing system to the LPAR, according to an allocation policy. Additionally, the EEA utility dynamically adjusts a priority level for the LPAR to efficiently control resource allocation, according to the LPAR's energy consumption relative to its energy entitlement. In addition, the EEA utility is able to transfer unused energy entitlement to other data processing systems requiring further allocation of energy entitlement.

摘要翻译： 系统和计算机程序产品将能量权利分配给在数据处理系统上执行的逻辑分区（LPAR）。 能源权利分配（EEA）实用程序使管理员能够指定最小和/或最大能量权利和LPAR优先级。 当相关LPAR基于相应的能量消耗利用相应的最小能量权利时，EEA实用程序确定LPAR（和其他LPAR）是否已经满足相应的最大能量权利。 当LPAR尚未满足其最大能源权限时，EEA实用程序根据分配策略将数据处理系统中的未使用的能源权利分配给LPAR。 此外，根据LPAR相对于其能源权益的能耗，EEA实用程序可动态调整LPAR的优先级，以有效控制资源分配。 此外，EEA实用程序能够将未使用的能源权利转移到需要进一步分配能源权利的其他数据处理系统。

公开(公告)号：US20130014243A1

公开(公告)日：2013-01-10

申请号：US13342237

申请日：2012-01-03

申请人： Li Long Chen ,  Elaine Zhan ,  Lin Zhi Zou

发明人： Li Long Chen ,  Elaine Zhan ,  Lin Zhi Zou

IPC分类号： G06F21/00 ,  G06F21/20

CPC分类号： H04L67/141 ,  H04L63/0815 ,  H04L67/143 ,  H04L67/2804 ,  H04L67/2814

摘要： The present application provides a method and system for Cross Domain Single Sign On. The method comprises: receiving a request from a user to a service provider; processing the user request prior to relaying the request to the service provider; forwarding the processed request to the corresponding service provider according, to the type of request; in response to receiving a response to the request from the service provider, processing the response, and forwarding the processed response to the user. By adopting the method and system of the present application, a Single Sign On management proxy is introduced as a united management system for a session lifetime of the user. The SSO management proxy manages operations of logging in, checking a session expiration and recovering, logging out, URL mapping, error processing, and access control, and effectively improves the availability, security, functional continuity of the service as well as the user's experience.

摘要翻译： 本申请提供了跨域单点登录的方法和系统。 该方法包括：从用户接收服务提供商的请求; 在将请求中继到服务提供商之前处理用户请求; 根据请求的类型将处理的请求转发到相应的服务提供商; 响应于从所述服务提供商接收到对所述请求的响应，处理所述响应，以及将所处理的响应转发给所述用户。 通过采用本申请的方法和系统，引入单一登录管理代理作为用户的会话生存期的联合管理系统。 SSO管理代理管理登录的操作，检查会话到期和恢复，注销，URL映射，错误处理和访问控制，有效提高服务的可用性，安全性，功能连续性以及用户体验。

公开(公告)号：US20130013897A1

公开(公告)日：2013-01-10

申请号：US13621211

申请日：2012-09-15

申请人： Gregory H. Bellows ,  Brian H. Horton ,  Joaquin Madruga ,  Barry L. Minor

发明人： Gregory H. Bellows ,  Brian H. Horton ,  Joaquin Madruga ,  Barry L. Minor

IPC分类号： G06F9/312

CPC分类号： G06F9/5066 ,  G06F9/4843

摘要： A method provides efficient dispatch/completion of an N Dimensional (ND) Range command in a data processing system (DPS). The method comprises: a compiler generating one or more commands from received program instructions; ND Range work processing (WP) logic determining when a command generated by the compiler will be implemented over an ND configuration of operands, where N is greater than one (1); automatically decomposing the ND configuration of operands into a one (1) dimension (1D) work element comprising P sequentially ordered work items that each represent one of the operands; placing the 1D work element within a command queue of the DPS; enabling sequential dispatching of 1D work items in ordered sequence from to one or more processing units; and generating an ND Range output by mapping the 1D work output result to an ND position corresponding to an original location of the operand represented by the 1D work item.

摘要翻译： 一种方法在数据处理系统（DPS）中提供N维（ND）范围命令的有效调度/完成。 该方法包括：编译器从接收的程序指令生成一个或多个命令; ND范围工作处理（WP）逻辑确定编译器生成的命令何时将通过操作数的ND配置来实现，其中N大于1（1）; 将所述操作数的ND配置自动分解为一（1）维（1D）工作元素，其包括每个表示所述操作数之一的P个顺序排列的工作项; 将1D工作元素放置在DPS的命令队列中; 使1D工作项目从有序序列顺序排列到一个或多个处理单元; 并通过将1D工作输出结果映射到对应于由1D工作项表示的操作数的原始位置的ND位置来生成ND范围输出。