公开(公告)号：US20150012722A1

公开(公告)日：2015-01-08

申请号：US13935382

申请日：2013-07-03

Applicant: VMware, Inc.

Inventor： Yury BASKAKOV ,  Alexander Thomas Garthwaite ,  Rajesh Venkatasubramanian ,  Irene Zhang ,  Seongbeom Kim ,  Nikhil Bhatia ,  Kiran Tati

IPC: G06F12/10

CPC classification number: G06F12/121 ,  G06F9/45558 ,  G06F12/023 ,  G06F12/1009 ,  G06F12/1027 ,  G06F2009/45583 ,  G06F2212/1016 ,  G06F2212/1044

Abstract: Memory performance in a computer system that implements large page mapping is improved even when memory is scarce by identifying page sharing opportunities within the large pages at the granularity of small pages and breaking up the large pages so that small pages within the large page can be freed up through page sharing. In addition, the number of small page sharing opportunities within the large pages can be used to estimate the total amount of memory that could be reclaimed through page sharing.

Abstract translation: 通过在小页面的大小页面上识别大页面中的页面共享机会，并分解大页面，使大页面中的小页面可以被释放，即使在内存不足的情况下，也可以提高实现大页面映射的计算机系统中的内存性能 通过页面共享。 此外，大页面中的小页面共享机会数量可用于估计可通过页面共享回收的总内存量。

公开(公告)号：US10339236B2

公开(公告)日：2019-07-02

申请号：US14023293

申请日：2013-09-10

Applicant: VMware, Inc.

Inventor： Kalyan Saladi ,  Aravind Pavuluri ,  Nikhil Bhatia

IPC: G06F17/50 ,  G06F9/455

Abstract: A computer implemented method receives a request to run a group of instruction sets. Each instruction set is associated with a sequence of common instructions. The method executes the sequence of common instructions in a first virtual machine (VM) to generate a result which is stored in a first memory associated with the first VM. The method then clones a second VM that shares the first memory with the first VM. The method continues by executing a first instruction set in the second VM. Since the second VM shares memory with the first VM, the second VM can use the result stored in the first memory and the sequence of common instructions does not need to be executed on the second VM. In one example, the result is a run-time model of a circuit and the second VM runs the first instruction set on the run-time model.

公开(公告)号：US09977747B2

公开(公告)日：2018-05-22

申请号：US15051940

申请日：2016-02-24

Applicant: VMware, Inc.

Inventor： Yury Baskakov ,  Alexander Thomas Garthwaite ,  Rajesh Venkatasubramanian ,  Irene Zhang ,  Seongbeom Kim ,  Nikhil Bhatia ,  Kiran Tati

IPC: G06F12/00 ,  G06F12/121 ,  G06F12/1009 ,  G06F12/02 ,  G06F9/455 ,  G06F12/1027

CPC classification number: G06F12/121 ,  G06F9/45558 ,  G06F12/023 ,  G06F12/1009 ,  G06F12/1027 ,  G06F2009/45583 ,  G06F2212/1016 ,  G06F2212/1044

Abstract: Memory performance in a computer system that implements large page mapping is improved even when memory is scarce by identifying page sharing opportunities within the large pages at the granularity of small pages and breaking up the large pages so that small pages within the large page can be freed up through page sharing. In addition, the number of small page sharing opportunities within the large pages can be used to estimate the total amount of memory that could be reclaimed through page sharing.

公开(公告)号：US09292452B2

公开(公告)日：2016-03-22

申请号：US13935382

申请日：2013-07-03

Applicant: VMware, Inc.

Inventor： Yury Baskakov ,  Alexander Thomas Garthwaite ,  Rajesh Venkatasubramanian ,  Irene Zhang ,  Seongbeom Kim ,  Nikhil Bhatia ,  Kiran Tati

IPC: G06F12/00 ,  G06F12/10 ,  G06F12/02

CPC classification number: G06F12/121 ,  G06F9/45558 ,  G06F12/023 ,  G06F12/1009 ,  G06F12/1027 ,  G06F2009/45583 ,  G06F2212/1016 ,  G06F2212/1044

Abstract: Memory performance in a computer system that implements large page mapping is improved even when memory is scarce by identifying page sharing opportunities within the large pages at the granularity of small pages and breaking up the large pages so that small pages within the large page can be freed up through page sharing. In addition, the number of small page sharing opportunities within the large pages can be used to estimate the total amount of memory that could be reclaimed through page sharing.

Abstract translation: 通过在小页面的大小页面上识别大页面中的页面共享机会，并分解大页面，使大页面中的小页面可以被释放，即使在内存不足的情况下，也可以提高实现大页面映射的计算机系统中的内存性能 通过页面共享。 此外，大页面中的小页面共享机会数量可用于估计可通过页面共享回收的总内存量。

公开(公告)号：US20150074662A1

公开(公告)日：2015-03-12

申请号：US14023293

申请日：2013-09-10

Applicant: VMware, Inc.

Inventor： Kalyan Saladi ,  Aravind Pavuluri ,  Nikhil Bhatia

IPC: G06F9/455

CPC classification number: G06F17/5022 ,  G06F9/45558 ,  G06F2009/45562

Abstract: A computer implemented method receives a request to run a group of instruction sets. Each instruction set is associated with a sequence of common instructions. The method executes the sequence of common instructions in a first virtual machine (VM) to generate a result which is stored in a first memory associated with the first VM. The method then clones a second VM that shares the first memory with the first VM. The method continues by executing a first instruction set in the second VM. Since the second VM shares memory with the first VM, the second VM can use the result stored in the first memory and the sequence of common instructions does not need to be executed on the second VM. In one example, the result is a run-time model of a circuit and the second VM runs the first instruction set on the run-time model.

Abstract translation: 计算机实现的方法接收运行一组指令集的请求。 每个指令集与一系列通用指令相关联。 该方法在第一虚拟机（VM）中执行公共指令的序列，以产生存储在与第一VM相关联的第一存储器中的结果。 然后，该方法克隆与第一VM共享第一存储器的第二VM。 该方法通过执行第二VM中的第一指令集来继续。 由于第二VM与第一VM共享存储器，所以第二VM可以使用存储在第一存储器中的结果，并且不需要在第二VM上执行公共指令序列。 在一个示例中，结果是电路的运行时模型，第二个VM在运行时模型上运行第一个指令集。