公开(公告)号：JP2013254524A

公开(公告)日：2013-12-19

申请号：JP2013195581

申请日：2013-09-20

Applicant: INTEL CORP

Inventor： CHINYA GAUTHAM N ,  HAUN WARNE ,  MATHAIKUTTY DEEPAK A ,  COLLINS JAMISON D ,  SCHUCHMAN ETHAN ,  HELD JAMES P ,  BHATT AJAY V ,  SETHI PRASHANT ,  WHALLEY STEPHEN F

IPC: G06F12/10 ,  G06F12/08

Abstract: PROBLEM TO BE SOLVED: To provide hardware support for virtual memory shared between local physical memory and remote physical memory.SOLUTION: A method comprises: receiving a memory access request including a virtual address; analyzing an entry corresponding to the virtual address stored in a translation lookaside buffer (TLB) of a processor in order to determine if a physical address (PA) corresponding to the virtual address is present in a local memory associated with the processor or a remote memory associated with an accelerator coupled to the processor via a non-coherent link; and if the PA is present in the remote memory, sending a reverse proxy execution request to the remote memory in order to perform the memory access request. The local memory and the remote memory collectively form a shared virtual memory space.

公开(公告)号：JP2012003761A

公开(公告)日：2012-01-05

申请号：JP2011130887

申请日：2011-06-13

Applicant: Intel Corp ,  インテル コーポレイション

Inventor： GUILHERME D OTTONI ,  HAUN WARNE ,  WAY LEE

IPC: G06F9/30 ,  G06F9/455

CPC classification number: G06F8/441 ,  G06F9/45525

Abstract: PROBLEM TO BE SOLVED: To reduce emulation overhead of a register by using efficient register mapping, because a problem of dynamic binary conversion is overhead.SOLUTION: A system and a method for mapping registers from a system including more registers to a system including less registers are provided. A region is configured so as to include one or more code blocks for performing relatively high-frequency register access. A source register which is the most frequently accessed is mapped to a target register. Each block in the region is bounded by a prologue and at least one epilogue. The prologue is configured so as to mount register mapping, and the epilogue is configured so as to manage a program flow from a block in the region to the other block in the region or out of the region.

Abstract translation: 要解决的问题：通过使用高效的寄存器映射来减少寄存器的仿真开销，因为动态二进制转换的问题是开销。 解决方案：提供了一种用于将包括更多寄存器的系统的寄存器映射到包括较少寄存器的系统的系统和方法。 区域被配置为包括用于执行相对高频寄存器访问的一个或多个代码块。 最常访问的源寄存器映射到目标寄存器。 该地区的每个街区都有一个序言和至少一个结尾。 序言被配置为安装寄存器映射，并且结尾被配置为管理从区域中的块到区域中的区域或区域外的另一块的程序流。 版权所有（C）2012，JPO＆INPIT