公开(公告)号：US07783858B2

公开(公告)日：2010-08-24

申请号：US11625296

申请日：2007-01-20

申请人： Men-Chow Chiang ,  Kiet H. Lam

发明人： Men-Chow Chiang ,  Kiet H. Lam

IPC分类号： G06F12/10

CPC分类号： G06F12/1036 ,  G06F12/1018 ,  G06F2212/152

摘要： Mechanisms for reducing memory overhead of a page table in a dynamic logical partitioning (LPAR) environment are provided. Each LPAR, upon its creation, is allowed to declare any maximum main memory size for the LPAR as long as the aggregate maximum main memory size for all LPARs does not exceed the total amount of available main memory. A single page table is used for all of the LPARs. Thus, the only page table in the computing system is shared by all LPARs and every memory access operation from any LPAR must go through the same page table for address translation. As a result, since only one page table is utilized, and the aggregate size of the main memory apportioned to each of the LPARs is limited to the size of the main memory, the size of the page table cannot exceed the size of the main memory.

摘要翻译： 提供了在动态逻辑分区（LPAR）环境中减少页表的内存开销的机制。 只要所有LPAR的总最大主内存大小不超过可用主内存的总量，LPAR将在创建时允许为LPAR声明任何最大主内存大小。 所有LPAR都使用单页表。 因此，计算系统中唯一的页表由所有LPAR共享，并且来自任何LPAR的每个存储器访问操作必须经过相同的页表以进行地址转换。 结果，由于仅使用一个页表，并且分配给每个LPAR的主存储器的聚合大小被限制为主存储器的大小，所以页表的大小不能超过主存储器的大小 。

公开(公告)号：US20050188175A1

公开(公告)日：2005-08-25

申请号：US10782497

申请日：2004-02-19

申请人： Men-Chow Chiang ,  Sujatha Kashyap

发明人： Men-Chow Chiang ,  Sujatha Kashyap

IPC分类号： G06F12/08 ,  G06F12/10

CPC分类号： G06F12/1036 ,  G06F12/109 ,  G06F2212/654

摘要： A mechanism for generating pre-translated segments for use in virtual to real address translation is provided in which segments that are determined to meet a density threshold are promoted to a pre-translated segment class. The pages of these segments are moved to a contiguous portion of memory and the segment table entry corresponding to the segment is updated to indicate the segment to be a pre-translated segment and to include the base real address for the contiguous portion of memory. In one embodiment, as each page is moved, its page table entry is updated to point to the new location of the page so that the page is still accessible during promotion of the segment to a pre-translated segment. In this way, virtual-to-real address translation may be performed by concatenating the segment base real address, the page identifier, and a byte offset into the page.

摘要翻译： 提供了一种用于生成用于虚拟到实际地址转换的预翻译段的机制，其中被确定为满足密度阈值的段被提升为预先转换的段类。 这些段的页面被移动到存储器的连续部分，并且对应于段的段表条目被更新以指示段作为预转换段并且包括存储器的连续部分的基本实地址。 在一个实施例中，当每个页面被移动时，其页表条目被更新以指向该页面的新位置，使得该页面在该段的推广期间仍可访问到预翻译的段。 以这种方式，可以通过将段基本实地址，页标识符和字节偏移连接到页中来执行虚拟到实地址转换。

公开(公告)号：US20120066688A1

公开(公告)日：2012-03-15

申请号：US12880534

申请日：2010-09-13

申请人： Men-Chow Chiang ,  Hong Lam Hua

发明人： Men-Chow Chiang ,  Hong Lam Hua

IPC分类号： G06F9/46

CPC分类号： G06F9/5083

摘要： An operating system of an information handling system (IHS) determines a process tree of data sharing threads in an application that the IHS executes. A load balancing manager assigns a home processor to each thread of the executing application process tree and dispatches the process tree to the home processor. The load balancing manager determines whether a particular poaching processor of a virtual or real processor group is available to execute threads of the executing application within the home processor of a processor group. If ready or run queues of a prospective poaching processor are empty, the load balancing manager may move or poach a thread or threads from the home processor ready queue to the ready queue of the prospective poaching processor. The poaching processor executes the poached threads to provide load balancing to the information handling system (IHS).

摘要翻译： 信息处理系统（IHS）的操作系统确定IHS执行的应用程序中数据共享线程的进程树。 负载平衡管理器为执行应用进程树的每个线程分配归属处理器，并将进程树分派到家庭处理器。 负载平衡管理器确定虚拟或实际处理器组的特定偷猎处理器是否可用于执行处理器组的家庭处理器内的执行应用的线程。 如果预期的偷猎处理器的准备好或运行的队列是空的，则负载平衡管理器可以将线程或线程从家庭处理器就绪队列移动或者从潜在的偷猎处理器的就绪队列中移走。 偷猎处理器执行水印线程以向信息处理系统（IHS）提供负载平衡。

公开(公告)号：US20090183169A1

公开(公告)日：2009-07-16

申请号：US11972361

申请日：2008-01-10

申请人： Men-Chow Chiang ,  Sujatha Kashyap ,  Mysore Sathyanarayana Srinivas

发明人： Men-Chow Chiang ,  Sujatha Kashyap ,  Mysore Sathyanarayana Srinivas

IPC分类号： G06F9/46 ,  G06F12/08

CPC分类号： G06F12/1036 ,  G06F9/5061

摘要： A system and method for allowing jobs originating from different partitions to simultaneously utilize different hardware threads on a processor by concatenating partition identifiers with virtual page identifiers within a processor's translation lookaside buffer is presented. The device includes a translation lookaside buffer that translates concatenated virtual addresses to system-wide real addresses. The device generates concatenated virtual addresses using a partition identifier, which corresponds to a job's originating partition, and a virtual page identifier, which corresponds to the executing instruction, such as an instruction address or data address. In turn, each concatenated virtual address is different, which translates in the translation lookaside buffer to a unique system-wide real address. As such, jobs originating from different partitions are able to simultaneously execute on the device and, therefore, fully utilize each of the device's hardware threads.

摘要翻译： 提出了一种用于允许源自不同分区的作业同时利用处理器中的不同硬件线程的系统和方法，其通过将分区标识符与处理器的翻译后备缓冲器内的虚拟页面标识符相连接。 该设备包括翻译后备缓冲区，将连接的虚拟地址转换为系统范围的实际地址。 设备使用对应于作业的始发分区的分区标识符和对应于执行指令（诸如指令地址或数据地址）的虚拟页面标识符来生成级联的虚拟地址。 反过来，每个连接的虚拟地址是不同的，这将翻译后备缓冲区转换为唯一的系统范围的实际地址。 因此，源自不同分区的作业能够在设备上同时执行，并因此充分利用设备的每个硬件线程。

公开(公告)号：US07318125B2

公开(公告)日：2008-01-08

申请号：US10850426

申请日：2004-05-20

申请人： Men-Chow Chiang ,  Kaivalya M. Dixit ,  Sujatha Kashyap

发明人： Men-Chow Chiang ,  Kaivalya M. Dixit ,  Sujatha Kashyap

IPC分类号： G06F9/00 ,  G06F12/00

CPC分类号： G06F9/383 ,  G06F8/70 ,  G06F9/3455 ,  G06F12/0862

摘要： A control mechanism that allows individual applications to turn hardware prefetch on or off is provided. By preliminary trial run one can determine precisely whether an application will benefit or suffer from hardware prefetch. The selective control of prefetching by individual applications is made possible by associating a status bit with individual processes in the machine status word of each processor. Using this prefetch bit, a process turns prefetching on or off to its own advantage in the processor core immediately after a context switch.

摘要翻译： 提供允许各个应用程序打开或关闭硬件预取的控制机制。 通过初步试运行，可以准确确定应用程序是否将受益于硬件预取。 通过将状态位与每个处理器的机器状态字中的各个进程相关联，可以通过各个应用程序进行预取的选择性控制。 使用这个预取位，一个进程在上下文切换之后立即在处理器核心中开启或关闭其自身的优势。

公开(公告)号：US20050262307A1

公开(公告)日：2005-11-24

申请号：US10850426

申请日：2004-05-20

申请人： Men-Chow Chiang ,  Kaivalya Dixit ,  Sujatha Kashyap

发明人： Men-Chow Chiang ,  Kaivalya Dixit ,  Sujatha Kashyap

IPC分类号： G06F9/38 ,  G06F9/44 ,  G06F12/00 ,  G06F12/08

CPC分类号： G06F9/383 ,  G06F8/70 ,  G06F9/3455 ,  G06F12/0862

摘要： A control mechanism that allows individual applications to turn hardware prefetch on or off is provided. By preliminary trial run one can determine precisely whether an application will benefit or suffer from hardware prefetch. The selective control of prefetching by individual applications is made possible by associating a status bit with individual processes in the machine status word of each processor. Using this prefetch bit, a process turns prefetching on or off to its own advantage in the processor core immediately after a context switch.

摘要翻译： 提供允许单个应用程序打开或关闭硬件预取的控制机制。 通过初步试运行，可以准确确定应用程序是否将受益于硬件预取。 通过将每个处理器的机器状态字中的状态位与各个进程相关联，可以通过各个应用程序进行预取的选择性控制。 使用这个预取位，一个进程在上下文切换之后立即在处理器核心中开启或关闭其自身的优势。

公开(公告)号：US08413158B2

公开(公告)日：2013-04-02

申请号：US12880534

申请日：2010-09-13

申请人： Men-Chow Chiang ,  Hong Lam Hua

发明人： Men-Chow Chiang ,  Hong Lam Hua

IPC分类号： G06F9/46

CPC分类号： G06F9/5083

摘要： An operating system of an information handling system (IHS) determines a process tree of data sharing threads in an application that the IHS executes. A load balancing manager assigns a home processor to each thread of the executing application process tree and dispatches the process tree to the home processor. The load balancing manager determines whether a particular poaching processor of a virtual or real processor group is available to execute threads of the executing application within the home processor of a processor group. If ready or run queues of a prospective poaching processor are empty, the load balancing manager may move or poach a thread or threads from the home processor ready queue to the ready queue of the prospective poaching processor. The poaching processor executes the poached threads to provide load balancing to the information handling system (IHS).

摘要翻译： 信息处理系统（IHS）的操作系统确定IHS执行的应用程序中数据共享线程的进程树。 负载平衡管理器为执行应用进程树的每个线程分配归属处理器，并将进程树分派到家庭处理器。 负载平衡管理器确定虚拟或实际处理器组的特定偷猎处理器是否可用于执行处理器组的家庭处理器内的执行应用的线程。 如果预期的偷猎处理器的准备好或运行的队列是空的，则负载平衡管理器可以将线程或线程从家庭处理器就绪队列移动或者从潜在的偷猎处理器的就绪队列中移走。 偷猎处理器执行水印线程以向信息处理系统（IHS）提供负载平衡。

公开(公告)号：US20080168125A1

公开(公告)日：2008-07-10

申请号：US11621200

申请日：2007-01-09

申请人： WEN-TZER THOMAS CHEN ,  Men-Chow Chiang ,  William A. Maron ,  Mysore Sathyanarayana Srinivas

发明人： WEN-TZER THOMAS CHEN ,  Men-Chow Chiang ,  William A. Maron ,  Mysore Sathyanarayana Srinivas

IPC分类号： G06F15/16

CPC分类号： G06F9/5027 ,  G06F2209/5021

摘要： A system for prioritizing resource requests. One or more resource requests are received. The one or more resource requests are prioritized in a queue according to a priority attribute that is associated with each of the one or more resource requests. A resource request with a highest priority in the queue is selected and processed. Then, a response to the resource request with the highest priority is sent.

摘要翻译： 用于优先考虑资源请求的系统。 接收一个或多个资源请求。 根据与一个或多个资源请求中的每个资源请求相关联的优先级属性，一个或多个资源请求在队列中被优先排列。 选择并处理队列中具有最高优先级的资源请求。 然后，发送对具有最高优先级的资源请求的响应。

公开(公告)号：US07117337B2

公开(公告)日：2006-10-03

申请号：US10782676

申请日：2004-02-19

申请人： Men-Chow Chiang ,  Sujatha Kashyap

发明人： Men-Chow Chiang ,  Sujatha Kashyap

IPC分类号： G06F12/10

CPC分类号： G06F12/1036 ,  G06F2212/654

摘要： A mechanism for generating pre-translated segments for use in virtual to real address translation is provided in which segments that are determined to meet a density threshold are promoted to a pre-translated segment class. The pages of these segments are moved to a contiguous portion of memory and the segment table entry corresponding to the segment is updated to indicate the segment to be a pre-translated segment and to include the base real address for the contiguous portion of memory. In one embodiment, as each page is moved, its page table entry is updated to point to the new location of the page so that the page is still accessible during promotion of the segment to a pre-translated segment. In this way, virtual-to-real address translation may be performed by concatenating the segment base real address, the page identifier, and a byte offset into the page.

摘要翻译： 提供了一种用于生成用于虚拟到实际地址转换的预翻译段的机制，其中被确定为满足密度阈值的段被提升为预先转换的段类。 这些段的页面被移动到存储器的连续部分，并且对应于段的段表条目被更新以指示段作为预转换段并且包括存储器的连续部分的基本实地址。 在一个实施例中，当每个页面被移动时，其页表条目被更新以指向该页面的新位置，使得该页面在该段的推广期间仍可访问到预翻译的段。 以这种方式，可以通过将段基本实地址，页标识符和字节偏移连接到页中来执行虚拟到实地址转换。

公开(公告)号：US20080177974A1

公开(公告)日：2008-07-24

申请号：US11625296

申请日：2007-01-20

申请人： Men-Chow Chiang ,  Kiet H. Lam

发明人： Men-Chow Chiang ,  Kiet H. Lam

IPC分类号： G06F12/02

CPC分类号： G06F12/1036 ,  G06F12/1018 ,  G06F2212/152

摘要： A system and method for reducing memory overhead of a page table in a dynamic logical partitioning (LPAR) environment are provided. Each LPAR, upon its creation, is allowed to declare any maximum main memory size for the LPAR as long as the aggregate maximum main memory size for all LPARs does not exceed the total amount of available main memory. A single page table is used for all of the LPARs. Thus, the only page table in the computing system is shared by all LPARs and every memory access operation from any LPAR must go through the same page table for address translation. As a result, since only one page table is utilized, and the aggregate size of the main memory apportioned to each of the LPARs is limited to the size of the main memory, the size of the page table cannot exceed the size of the main memory.

摘要翻译： 提供了一种用于减少动态逻辑分区（LPAR）环境中的页表的内存开销的系统和方法。 只要所有LPAR的总最大主内存大小不超过可用主内存的总量，LPAR将在创建时允许为LPAR声明任何最大主内存大小。 所有LPAR都使用单页表。 因此，计算系统中唯一的页表由所有LPAR共享，并且来自任何LPAR的每个存储器访问操作必须经过相同的页表以进行地址转换。 结果，由于仅使用一个页表，并且分配给每个LPAR的主存储器的聚合大小被限制为主存储器的大小，所以页表的大小不能超过主存储器的大小 。