公开(公告)号：EP2126704A4

公开(公告)日：2012-12-26

申请号：EP08705921

申请日：2008-01-15

Applicant: IBM

Inventor： SU GONG

IPC: G06F12/00 ,  G06F9/46 ,  G06F9/52 ,  G06F12/08

CPC classification number: G06F12/0828 ,  G06F9/526 ,  G06F12/0811

公开(公告)号：JP2008047126A

公开(公告)日：2008-02-28

申请号：JP2007211128

申请日：2007-08-13

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： DILLENBERGER DONNA N ,  DYCK GREG A ,  HEISIG STEPHEN J ,  PIERCE BERNARD R ,  DONALD W SCHMIDT ,  SU GONG

IPC: G06F9/50

CPC classification number: G06F9/505 ,  G06F2209/5022

Abstract: PROBLEM TO BE SOLVED: To provide a processor load balancing method to overcome drawbacks of the prior art.
SOLUTION: A computer-implemented method for distributing a plurality of tasks to a plurality of processing nodes in a processor network includes: a step of calculating a task process consumption value with respect to the tasks; a step of calculating a measured node processor consumption value for the nodes; a step of calculating a target node processor consumption value for the nodes, the target node processor consumption value indicating optimal node processor consumption; a step of calculating a load index value as a difference between the calculated node processor consumption value for a node i and the target node processor consumption value for the node i; and a step of distributing the tasks among the nodes so as to balance a processor workload among the nodes, according to the calculated load index value, such that the calculated load index value of each node is substantially zero. Further, the method comprises a multidimensional balancing matrix with each dimension thereof representing a node corresponding to a different processor type and each cell representing tasks assigned to multiple nodes.
COPYRIGHT: (C)2008,JPO&INPIT

Abstract translation: 要解决的问题：提供一种处理器负载平衡方法来克服现有技术的缺点。 解决方案：一种用于将多个任务分配到处理器网络中的多个处理节点的计算机实现的方法包括：计算相对于所述任务的任务处理消耗值的步骤; 计算节点的测量节点处理器消耗值的步骤; 计算节点的目标节点处理器消耗值的步骤，指示最佳节点处理器消耗的目标节点处理器消耗值; 计算负载指标值作为节点i的计算节点处理器消耗值与节点i的目标节点处理器消耗值之间的差的步骤; 以及根据所计算的负载指数值，在所述节点之间分配所述任务以平衡所述节点之间的处理器工作负荷的步骤，使得所计算的每个节点的负载指数值基本上为零。 此外，该方法包括多维平衡矩阵，其每个维度表示对应于不同处理器类型的节点，并且每个小区表示分配给多个节点的任务。 版权所有（C）2008，JPO＆INPIT

公开(公告)号：WO2008091757A3

公开(公告)日：2008-12-18

申请号：PCT/US2008051047

申请日：2008-01-15

Applicant: IBM ,  SU GONG

Inventor： SU GONG

IPC: G06F12/00

CPC classification number: G06F12/0828 ,  G06F9/526 ,  G06F12/0811

Abstract: A method for implementing a spin lock in a system including a plurality of processing nodes, each node including at least one processor and a cache memory, the method including steps of: acquiring exclusivity to the cache memory; checking the availability of the spin lock; setting the spin lock to logical one if the spin lock is available; setting the spin lock to logical zero once processing is complete; and explicitly yielding the cache memory exclusivity. Yielding the cache memory exclusivity includes instructing the cache coherent hardware to mark the cache memory as non-exclusive. The cache memory is typically called level two cache.

Abstract translation: 一种用于在包括多个处理节点的系统中实现自旋锁定的方法，每个节点包括至少一个处理器和高速缓冲存储器，所述方法包括以下步骤：获得对高速缓冲存储器的排他性; 检查自旋锁的可用性; 如果自旋锁可用，则将自旋锁设置为逻辑1; 一旦处理完成，将自旋锁设置为逻辑零; 并明确地产生高速缓存存储器独占性。 产生高速缓存存储器专有性包括指示高速缓存一致硬件将高速缓存存储器标记为非排他性的。 高速缓存通常称为二级高速缓存。

公开(公告)号：DE102013204521A1

公开(公告)日：2013-10-02

申请号：DE102013204521

申请日：2013-03-15

Applicant: IBM

Inventor： CAIN III HAROLD WADE ,  DILLENBERGER DONNA N ,  HACK MICHEL H T ,  MIN HONG ,  SU GONG ,  TENG JAMES ZU-CHIA

IPC: G06F17/30 ,  G06F9/44

Abstract: Hierin werden Systeme, Verfahren und Produkte zur Transaktionsverwaltung für Datenbanksysteme bereitgestellt. Ein Aspekt sieht das Annotieren eines auf einer Datenverarbeitungseinheit vorhandenen Datenobjektes mittels der Datenverarbeitungseinheit unter Verwendung wenigstens eines Transaktions-Tag vor, wobei das wenigstens eine Transaktions-Tag so konfiguriert ist, dass es einen Status eines dazugehörigen Datenobjektes anzeigt; das Verarbeiten wenigstens einer Datenbanktransaktion unter Verwendung eines transaktionsorientierten Speicherprozesses, wobei ein Zugriff auf das wenigstens eine Datenobjekt auf der Grundlage des Status des wenigstens einen Datenobjektes festgelegt wird; und das Aktualisieren des Status des wenigstens einen Datenobjektes als Reaktion auf einen versuchten Zugriff auf das wenigstens eine Datenobjekt durch die wenigstens eine Datenbanktransaktion. Hierein werden darüber hinaus weitere Ausführungsformen und Aspekte beschrieben.

公开(公告)号：GB2501800B

公开(公告)日：2014-10-08

申请号：GB201303662

申请日：2013-03-01

Applicant: IBM

Inventor： MIN HONG ,  HACK MICHEL ,  TENG JAMES ZU-CHIA ,  SU GONG ,  CAIN HAROLD WADE III ,  DILLENBERGER DONNA N

IPC: G06F17/30 ,  G06F9/46

Abstract: Systems, methods, and products for database system transaction management are provided herein. One aspect provides for annotating via a computing device at least one data object residing on the computing device utilizing at least one transaction tag, the at least one transaction tag being configured to indicate a status of an associated data object; processing at least one database transaction utilizing a transactional memory process, wherein access to the at least one data object is determined based on the status of the at least one data object; and updating the status of the at least one data object responsive to an attempted access of the at least one data object by the at least one database transaction. Other embodiments and aspects are also described herein.

公开(公告)号：DE112021000881T5

公开(公告)日：2023-01-12

申请号：DE112021000881

申请日：2021-03-24

Applicant: IBM

Inventor： ZHANG QI ,  SU GONG ,  IYENGAR ARUN KWANGIL

IPC: G06F12/1018 ,  G06F3/06 ,  G06F9/52 ,  G06F12/02

Abstract: Ein System, ein Computerprogrammprodukt und ein Verfahren werden bereitgestellt, um eine oder mehrere Speicherseiten parallel zu deduplizieren. Mehrere Deduplizierungsprozesse arbeiten parallel, wobei jeder Deduplizierungsprozess mit mindestens zwei Datenstrukturen betriebsfähig verbunden ist, und wobei des Weiteren Transaktionsspeicher genutzt wird, um Zugriffskonflikte zu verringern.

公开(公告)号：AU2021265928A1

公开(公告)日：2022-09-15

申请号：AU2021265928

申请日：2021-03-24

Applicant: IBM

Inventor： ZHANG QI ,  SU GONG ,  IYENGAR ARUN KWANGIL

IPC: G06F9/455

Abstract: A system, computer program product, and method are provided to de-duplicate one or more memory pages in parallel. Multiple de-duplication processes operate in parallel, with each de-duplication process operatively coupled to at least two data structures, and further leveraging transactional memory to mitigate access conflicts.

公开(公告)号：GB2501800A

公开(公告)日：2013-11-06

申请号：GB201303662

申请日：2013-03-01

Applicant: IBM

Inventor： MIN HONG ,  DILLENBERGER DONNA N ,  HACK MICHEL ,  TENG JAMES ZU-CHIA ,  SU GONG ,  CAIN HAROLD WADE III

IPC: G06F17/30 ,  G06F9/46

Abstract: Database system transaction management comprises annotating via a computing device at least one database data object (e.g. table 202, page 203, rows 204 within database 201) residing on the computing device utilizing at least one transaction tag 205, the at least one transaction tag 205 being configured to indicate a status of an associated data object; processing at least one database transaction utilizing a transactional memory (TM) process, wherein access to the at least one data object is determined based on the status of the at least one data object; and updating the status of the at least one data object responsive to an attempted access of the at least one data object by the at least one database transaction. The tag updates may be handled utilizing hardware transaction management (HTM) optimistically lock-free.