SERVICE DEPLOYMENT FOR DATA NETWORKS
    2.
    发明专利

    公开(公告)号:JP2002237835A

    公开(公告)日:2002-08-23

    申请号:JP2001256093

    申请日:2001-08-27

    Applicant: IBM

    Abstract: PROBLEM TO BE SOLVED: To provide a method of deploying a service according to a service assigning policy in a data network including a plurality of network nodes. SOLUTION: According to an assigning policy, the selection of nodes is specified for deployment of a service. This method comprises a step of defining a service deployment hierarchy having a lowermost layer including network nodes and one or a plurality of gradually elevating layers where a group of nodes in the preceding layer are expressed by their respective logical nodes in each layer. The method comprises a step of generating a service distribution command for designating a service to be deployed. The service distribution command is supplied, together with the assigning policy, from a logical node of an upper layer of the hierarchy to a lower layer of the hierarchy or each lower layer. The service designated by the service distribution command is automatically introduced to network nodes selected according to the assigning policy.

    PROTOCOL INFORMATION MANAGEMENT FOR INTER-PRIVATE NETWORK INTERFACE HIERARCHY NETWORK

    公开(公告)号:JP2002051083A

    公开(公告)日:2002-02-15

    申请号:JP2001173974

    申请日:2001-06-08

    Applicant: IBM

    Abstract: PROBLEM TO BE SOLVED: To provide a method and a device for promoting an efficient constitution of a higher hierarchy topology to a physical ATM(Asynchronous Transfer Mode) network topology, concerning a protocol information management of a PNNi (inter-private network interface) network. SOLUTION: A PAR PTSE received from a network is checked by a device 1 for dealing with PAR of the network and redundant protocol information capsuled in the PAR PTSE is identified. Next, the protocol information of the received PAR PTSE is provided to a protocol device related to the device 1 for dealing with PAR. As one execution example, protocol information identified as redundant is excluded from protocol information to be provided to the protocol device. As the other execution example, the protocol information to be provided to the protocol device is tagged and the redundant protocol information is distinguished from non-redundant protocol information. Thus, the efficient constitution of a network topology concerning the relevant protocol is promoted.

    LOGICAL TO PHYSICAL ADDRESS MAPPING IN STORAGE SYSTEMS COMPRISING SOLID STATE MEMORY DEVICES
    5.
    发明申请
    LOGICAL TO PHYSICAL ADDRESS MAPPING IN STORAGE SYSTEMS COMPRISING SOLID STATE MEMORY DEVICES 审中-公开
    包含固态存储器件的存储系统中的逻辑到物理地址映射

    公开(公告)号:WO2012014140A3

    公开(公告)日:2012-03-22

    申请号:PCT/IB2011053299

    申请日:2011-07-25

    Abstract: The present idea provides a high read and write performance from/to a solid state memory device. The main memory (31) of the controller (1) is not blocked by a complete address mapping table covering the entire memory device (2). Instead such table is stored in the memory device (2) itself, and only selected portions of address mapping information are buffered in the main memory (31) in a read cache (311) and a write cache (312). A separation of the read cache (311) from the write cache (312) enables an address mapping entry being evictable from the read cache (311) without the need to update the related flash memory page storing such entry in the flash memory device (2). By this design, the read cache (311) may advantageously be stored on a DRAM even without power down protection, while the write cache (312) may preferably be implemented in nonvolatile or other fail-safe memory. This leads to a reduction of the overall provisioning of nonvolatile or fail-safe memory and to an improved scalability and performance.

    Abstract translation: 目前的想法提供了对固态存储器设备的高读写性能。 控制器(1)的主存储器(31)不被覆盖整个存储器设备(2)的完整地址映射表阻塞。 相反,这样的表被存储在存储器设备(2)本身中,并且只有地址映射信息的所选部分被缓存在读取高速缓存(311)和写入高速缓存(312)中的主存储器(31)中。 读取高速缓存(311)与写入高速缓存(312)的分离使得地址映射条目能够从读取高速缓存(311)中逐出,而不需要更新在闪存器件(2)中存储这样的条目的相关的闪存页面 )。 通过这种设计,即使没有断电保护,读取高速缓存(311)也可以有利地存储在DRAM上,而写入高速缓存(312)可以优选地在非易失性或其他故障安全存储器中实现。 这导致非易失性存储器或故障安全存储器的整体配置减少并且可扩展性和性能得到改善。

    VACUUM TRANSITION FOR SOLDER BUMP MOLD FILLING
    6.
    发明申请
    VACUUM TRANSITION FOR SOLDER BUMP MOLD FILLING 审中-公开
    真空过滤器用于焊接模具填充

    公开(公告)号:WO2011028644A3

    公开(公告)日:2011-06-03

    申请号:PCT/US2010047078

    申请日:2010-08-30

    CPC classification number: B23K3/0623 B23K2201/42

    Abstract: A bond metal injection tool can include a fill head having a sealed chamber for containing a molten bond metal (e.g., solder) and a gas, and a nozzle for directing a flow of the molten bond metal into cavities in a major surface of a mold. A pressure control device can controllably apply pressure within the chamber to eject the bond metal from the nozzle into the cavities. The pressure control device may also controllably reduce a pressure within the chamber to inhibit the bond metal from being ejected from the nozzle, such as when the fill head is being moved onto the mold surface from a parking location or when the fill head is being moved off the mold surface onto a parking location.

    Abstract translation: 粘结金属注射工具可以包括具有用于容纳熔融金属(例如焊料)和气体的密封室的填充头,以及用于将熔融粘合金属流引导到模具的主表面中的空腔中的喷嘴 。 压力控制装置可以可控制地在室内施加压力以将接合金属从喷嘴喷射到空腔中。 压力控制装置还可以可控制地减小腔室内的压力以阻止接合金属从喷嘴喷射,例如当填充头​​从停车位置移动到模具表面上时或当填充头被移动时 离开模具表面到停车位置。

    Verfahren und Speichercontroller zur Bestimmung einer Zugriffscharakteristik einer Datenentität

    公开(公告)号:DE102012212183B4

    公开(公告)日:2017-10-05

    申请号:DE102012212183

    申请日:2012-07-12

    Applicant: IBM

    Abstract: Verfahren zur Bestimmung einer Charakteristik einer Datenentität, wobei diese Charakteristik auf einer Zugriffshäufigkeit auf diese Datenentität in einem Speichersystem beruht, umfassend das – Bereitstehen eines zählenden Bloomfilters (CBF), um während eines Zeitintervalls betrieben zu werden, wobei das zählende Bloomfilter (CBF) eine Gruppe (S1) von Zählern (C) umfasst, – Bereitstellen einer Datenstruktur, umfassend eine Gruppe von Elementen, wobei jedes Element der Gruppe von Elementen einem Zähler der Gruppe von Zählern zugeordnet ist, – Bestimmen der Charakteristik dieser Datenentität abhängig von einem Wert mindestens eines Elements der Gruppe von Elementen, – wobei für jedes Einzelzeitintervall, in welchem das zählende Bloomfilter betrieben wird, – die Zähler der Gruppe von Zählern am Anfang des Einzelzeitintervalls auf Null gesetzt werden, – ein Wert mindestens eines Zählers (C) jedes Mal, wenn während des Einzelzeitintervalls auf die Datenentität zugegriffen wird, erhöht wird, – Bestimmen der Charakteristik der Datenentität durch Gewichten des zugeordneten Zählerwertes (C) nach dem Einzelzeitiintervall (j) und Addieren des gewichteten Wertes (Ci) zu Beginn des Einzelzeitintervalls (j) anhand der folgenden Regel ci = αci + (1 –α)cj i – wobei α ein Gewichtungsfaktor ist, der auf 0,75 bis 0,95 gesetzt ist.

Patent Agency Ranking