专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2016082073A1 SUPPORT FOR APPLICATION TRANSPARENT, HIGH AVAILABLE GPU COMPUTING WITH VM CHECKPOINTING 审中-公开
标题翻译：支持应用透明，高可用的GPU计算与VM检查
公开(公告)号：WO2016082073A1
公开(公告)日：2016-06-02
申请号：PCT/CN2014/092028
申请日：2014-11-24
申请人： INTEL CORPORATION , DONG, Yaozu , TIAN, Kun
发明人： DONG, Yaozu , TIAN, Kun
IPC分类号： G06F9/445
CPC分类号： G06F9/45558 , G06F2009/45579 , G06F2009/45583 , G06T1/20 , G06T1/60
摘要： Methods, software, and apparatus for application transparent, high available GPU computing with VM checkpointing. The guest access of certain GPU resources, such as MMIO resources, are trapped to keep a copy of guest context per semantics, and/or emulate the guest access of the resources prior to submission to the GPU, while other commands relating to certain graphics memory address regions are trapped before being passed through to the GPU. The trapped commands are scanned before submission to predict: a) potential to-be-dirtied graphics memory pages, and b) the execution time of intercepted commands, so the next checkpointing can be aligned to a predicted execution time. The GPU internal states are drained by flushing internal context/tlb/cache, at the completion of submitted commands, and then a snapshot of the vGPU state is taken, based on tracked GPU state, GPU context (through GPU-specific commands), detected dirty graphics memory pages and predicted to-be dirtied graphics memory pages.
摘要翻译：方法，软件和设备应用透明，高可用性GPU计算与VM检查点。诸如MMIO资源之类的特定GPU资源的访客访问被困于每个语义保留访客上下文的副本，和/或在提交给GPU之前模拟资源的访客访问，而与某些图形存储器相关的其他命令地址区域在被传递到GPU之前被捕获。被捕获的命令在提交之前被扫描以预测：a）潜在的脏污图形存储器页面，以及b）截取的命令的执行时间，因此下一个检查点可以对准预测的执行时间。在完成提交的命令时，通过刷新内部上下文/ tlb /缓存来排除GPU内部状态，然后基于跟踪的GPU状态，GPU上下文（通过GPU特定的命令），检测到vGPU状态的快照脏图形内存页面和预测的脏图形内存页面。

2. 发明申请

WO2017107059A1 METHOD AND APPARATUS FOR BEST EFFORT QUALITY OF SERVICE (QOS) SCHEDULING IN A GRAPHICS PROCESSING ARCHITECTURE 审中-公开
标题翻译：在图形处理体系结构中用于最佳服务质量（QOS）调度的方法和设备
公开(公告)号：WO2017107059A1
公开(公告)日：2017-06-29
申请号：PCT/CN2015/098296
申请日：2015-12-22
申请人： INTEL CORPORATION , DONG, Yaozu , TIAN, Kun , ZHANG, Tian , ZHANG, Yulei
发明人： DONG, Yaozu , TIAN, Kun , ZHANG, Tian , ZHANG, Yulei
IPC分类号： G05B15/00 , G06F9/38
CPC分类号： G06T1/20 , G06F9/46
摘要： An apparatus and method for best effort quality of service scheduling in a graphics processing architecture. For example, one embodiment of an apparatus comprises: a graphics processing unit (GPU) to perform graphics processing operations for a plurality of guests; a plurality of buffers to store one or more graphics commands associated with each guest to be executed by the GPU; and a scheduler to evaluate commands in the buffers of a first guest to estimate a cost of executing the commands, the scheduler to select all or a subset of the buffers of the first guest for execution on the GPU based on a determination that the selected buffers can be executed by the GPU within a remaining time slice allocated to the first guest.
摘要翻译：图形处理体系结构中用于尽力服务质量调度的设备和方法。例如，装置的一个实施例包括：图形处理单元（GPU），用于对多个访客执行图形处理操作; 多个缓冲器，用于存储与要由GPU执行的每个客人关联的一个或多个图形命令; 以及调度器，用于评估第一客户的缓冲器中的命令以估计执行所述命令的成本，所述调度器基于确定所选择的缓冲器来选择所述第一客户的缓冲器的全部或子集以在所述GPU上执行可以在分配给第一个客人的剩余时间片内由GPU执行。

3. 发明申请

WO2017107001A1 APPARATUS AND METHOD FOR PATTERN-DRIVEN PAGE TABLE SHADOWING FOR GRAPHICS VIRTUALIZATION 审中-公开
标题翻译：用于图形虚拟化的图案驱动页表渐变的装置和方法
公开(公告)号：WO2017107001A1
公开(公告)日：2017-06-29
申请号：PCT/CN2015/098046
申请日：2015-12-21
申请人： INTEL CORPORATION , TIAN, Kun , DONG, Yaozu
发明人： TIAN, Kun , DONG, Yaozu
IPC分类号： G06F9/455
CPC分类号： G06F9/45508 , G06F9/45533
摘要： An apparatus and method are described for pattern driven page table updates. For example, one embodiment of an apparatus comprises a graphics processing unit (GPU) to process graphics commands and responsively render a plurality of image frames; a hypervisor to virtualize the GPU to share the GPU among a plurality of virtual machines (VMs); a first guest page table managed within a first VM, the first guest page table comprising a plurality of page table entries; a first shadow page table managed by the hypervisor and comprising page table entries corresponding to the page table entries of the first guest page table; and a command parser to analyze a current working set of commands submitted from the first VM to the GPU, the command parser to responsively update the first shadow page table responsive to determining a set of page table entries predicted to be used based on the analysis of the working set of commands.
摘要翻译：描述了一种用于模式驱动页面表更新的装置和方法。例如，设备的一个实施例包括图形处理单元（GPU）以处理图形命令并响应地呈现多个图像帧; 虚拟化GPU以在多个虚拟机（VM）之间共享GPU的管理程序; 在第一VM内管理的第一客户页面表，所述第一客户页面表包括多个页面表项; 由所述管理程序管理的第一影子页表，所述第一影子页表包括对应于所述第一客户页面表的页面表项的页面表项; 以及命令解析器，用于分析从第一VM提交给GPU的当前工作命令集合，命令解析器响应于响应于基于以下分析而确定预测要使用的一组页面表项目来更新第一影子页面表格：一组工作的命令。

4. 发明申请

WO2016205977A1 TECHNIQUES TO RUN ONE OR MORE CONTAINERS ON VIRTUAL MACHINE 审中-公开
标题翻译：在虚拟机上运行一个或多个容器的技术
公开(公告)号：WO2016205977A1
公开(公告)日：2016-12-29
申请号：PCT/CN2015/000464
申请日：2015-06-26
申请人： INTEL CORPORATION , DONG, Yaozu , TIAN, Kun
发明人： DONG, Yaozu , TIAN, Kun
IPC分类号： G06F9/455
CPC分类号： G06F9/45558 , G06F9/5077 , G06F2009/45562 , G06F2009/4557 , G06F2009/45583
摘要： Examples may include techniques to run one or more containers on a virtual machine (VM). Examples include cloning a first VM to result in a second VM. The cloned first VM may run at least a set ofcontainers capable of separately executing one or more applications. In some examples, some cloned containers are stopped at either the first or second VMs to allow for at least some resources provisioned to support the first or second VMs to be reused or recycled at a hosting node. In other examples, the second VM is migrated from the hosting node to a destination hosting node to further enable resources to be reused or recycled at the hosting node.
摘要翻译：示例可以包括在虚拟机（VM）上运行一个或多个容器的技术。示例包括克隆第一个VM以产生第二个VM。克隆的第一VM可以运行至少一组能够单独执行一个或多个应用的容器。在一些示例中，一些克隆的容器停止在第一或第二VM处，以允许至少一些资源被提供以支持第一或第二VM在主机节点被重新使用或再循环。在其他示例中，第二VM从主机节点迁移到目的地主机节点，以进一步使资源在主机节点被重用或再循环。

5. 发明申请

WO2016037344A1 MEMORY AND RESOURCE MANAGEMENT IN A VIRTUAL COMPUTING ENVIRONMENT 审中-公开
标题翻译：虚拟计算环境中的记忆和资源管理
公开(公告)号：WO2016037344A1
公开(公告)日：2016-03-17
申请号：PCT/CN2014/086360
申请日：2014-09-12
申请人： INTEL CORPORATION , DONG, Yaozu , TIAN, Kun
发明人： DONG, Yaozu , TIAN, Kun
IPC分类号： G06F9/455
CPC分类号： G06F9/45558 , G06F3/0604 , G06F3/0659 , G06F3/0664 , G06F3/0683 , G06F2009/45583
摘要： Systems and techniques for memory and resource management in a virtual computing environment are disclosed herein. For example, in some embodiments, an apparatus for memory management in a virtual computing environment may include: a storage device; memory page comparison logic, coupled to the storage device, to determine that a first memory page of instructions, stored in the storage device, for a guest machine in the virtual computing environment is identical to a second memory page of instructions, stored in the storage device, for a host machine in the virtual computing environment, wherein the guest machine is hosted by the host machine; and merge logic, coupled to the memory page comparison logic, to, in response to a determination that the first memory page is identical to the second memory page, map the first memory page to the second memory page. Other embodiments may be disclosed and/or claimed.
摘要翻译：本文公开了虚拟计算环境中的存储器和资源管理的系统和技术。例如，在一些实施例中，用于虚拟计算环境中的存储器管理的装置可以包括：存储设备; 存储器页比较逻辑，耦合到所述存储设备，以确定存储在所述存储设备中的用于所述虚拟计算环境中的客机的指令的第一存储器页面与存储在所述存储器中的指令的第二存储器页面相同设备，用于虚拟计算环境中的主机，其中所述客机由所述主机托管; 以及耦合到所述存储器页比较逻辑的合并逻辑，以响应于所述第一存储器页与所述第二存储器页相同的确定，将所述第一存储器页映射到所述第二存储器页。可以公开和/或要求保护其他实施例。

6. 发明申请

WO2019000358A1 TECHNIQUES FOR LIVE MIGRATION SUPPORT FOR GRAPHICS PROCESSING UNIT VIRTUALIZATION 审中-公开
公开(公告)号：WO2019000358A1
公开(公告)日：2019-01-03
申请号：PCT/CN2017/090990
申请日：2017-06-30
申请人： INTEL CORPORATION , HUANG, Xiao , TIAN, Kun , DONG, Yaozu
发明人： HUANG, Xiao , TIAN, Kun , DONG, Yaozu
IPC分类号： G06F9/46
摘要： Examples include techniques to live migrate a virtual machine (VM) between servers. Examples include identifying memory addresses for memory allocated to store content associated with the VM executing an application that uses a virtual graphics processing unit (vGPU) for graphics processing and then monitoring the identified memory addresses for changes in content during the live migration to determine dirty (vGPU) memory pages to copy at a stop-and-copy phase of the live migration.

7. 发明申请

WO2016206047A1 TECHNIQUES FOR RELIABLE PRIMARY AND SECONDARY CONTAINERS 审中-公开
标题翻译：可靠的主要和次要容器的技术
公开(公告)号：WO2016206047A1
公开(公告)日：2016-12-29
申请号：PCT/CN2015/082345
申请日：2015-06-25
申请人： INTEL CORPORATION , DONG, Yaozu , JIANG, Yunhong , TIAN, Kun
发明人： DONG, Yaozu , JIANG, Yunhong , TIAN, Kun
IPC分类号： G06F11/16
CPC分类号： G06F11/1471 , G06F9/547 , G06F11/1482 , G06F11/1641 , G06F11/1687 , G06F2201/805 , G06F2201/82 , H04L1/08
摘要： It includes techniques to provide for reliable primary and secondary containers arranged to separately execute an application that receives request packets for processing by the application. The request packets may be received from a client coupled with a server arranged to host the primary container or the secondary container. The client coupled with the server through a network. Coarse-grained lock-stepping (COLO) methods may be utilized to facilitate in providing the reliable primary and secondary containers.
摘要翻译：它包括提供可靠的主容器和辅助容器的技术，该容器被设置成分别执行接收请求数据包以供应用程序处理的应用程序。可以从与被布置为主持主容器或辅助容器的服务器耦合的客户端接收请求分组。客户端通过网络与服务器相连。可以使用粗粒度锁步（COLO）方法来提供可靠的主容器和辅助容器。

8. 发明申请

WO2016201589A1 COMPUTING APPARATUS AND METHOD WITH PERSISTENT MEMORY 审中-公开
标题翻译：计算机和方法与持续记忆
公开(公告)号：WO2016201589A1
公开(公告)日：2016-12-22
申请号：PCT/CN2015/000423
申请日：2015-06-17
申请人： INTEL CORPORATION , DONG, Yaozu , TIAN, Kun
发明人： DONG, Yaozu , TIAN, Kun
IPC分类号： G06F12/16
CPC分类号： G06F12/1009 , G06F9/45558 , G06F11/00 , G06F11/0712 , G06F11/073 , G06F12/16 , G06F2009/45583
摘要： Apparatuses, methods and storage medium associated with computing that include usage and backup of persistent memory are disclosed herein. In embodiments, an apparatus for computing may comprise one or more processors and persistent memory to host operation of one or more virtual machines； and one or more page tables to store a plurality of mappings to map a plurality of virtual memory pages of a virtualization of the persistent memory of the one or more virtual machines to a plurality of physical memory pages of the persistent memory allocated to the one or more virtual machines. The apparatus may further include a memory manager to manage accesses of the persistent memory that includes a copy-on-write mechanism to service write instructions that address virtual memory pages mapped to physical memory pages that are marked as read-only. Other embodiments may be described and/or claimed.
摘要翻译：本文公开了包括持久存储器的使用和备份的与计算相关联的装置，方法和存储介质。在实施例中，用于计算的装置可以包括一个或多个处理器和持久存储器，以托管一个或多个虚拟机的操作; 以及一个或多个页表，用于存储多个映射以将一个或多个虚拟机的持久存储器的虚拟化的多个虚拟存储器页面映射到分配给该一个或多个虚拟机的持久存储器的多个物理存储器页面，更多虚拟机。该装置还可以包括一个存储器管理器来管理持久存储器的访问，该存储器包括一个写时复制机制来服务写入指令，该指令映射映射到被标记为只读的物理存储器页面的虚拟存储器页面。可以描述和/或要求保护其他实施例。

9. 发明申请

WO2016191908A1 CONTAINER ACCESS TO GRAPHICS PROCESSING UNIT RESOURCES 审中-公开
标题翻译：容器访问图形处理单元资源
公开(公告)号：WO2016191908A1
公开(公告)日：2016-12-08
申请号：PCT/CN2015/080213
申请日：2015-05-29
申请人： INTEL CORPORATION , TIAN, Kun , DONG, Yaozu , LV, Zhiyuan
发明人： TIAN, Kun , DONG, Yaozu , LV, Zhiyuan
IPC分类号： G06F9/455
CPC分类号： G06F9/455 , G06F9/4411
摘要： Systems and methods for container access to graphics processing unit (GPU) resources are disclosed herein. In some embodiments, a computing system may include a physical GPU and kernel-mode driver circuitry, to communicatively couple with the physical GPU to create a plurality of emulated GPUs and a corresponding plurality of device nodes. Each device node may be associated with a single corresponding user-side container to enable communication between the user-side container and the corresponding emulated GPU. Other embodiments may be disclosed and/or claimed.
摘要翻译：本文公开了用于容器访问图形处理单元（GPU）资源的系统和方法。在一些实施例中，计算系统可以包括物理GPU和内核模式驱动器电路，以与物理GPU通信地耦合以创建多个仿真GPU以及对应的多个设备节点。每个设备节点可以与单个对应的用户侧容器相关联，以实现用户侧容器和相应的仿真GPU之间的通信。可以公开和/或要求保护其他实施例。

10. 发明申请

WO2015000106A1 EFFICIENT GRAPHICS VIRTUALIZATION WITH ADDRESS BALLOONING 审中-公开
标题翻译：有效的图形虚拟化与地址气球
公开(公告)号：WO2015000106A1
公开(公告)日：2015-01-08
申请号：PCT/CN2013/078577
申请日：2013-07-01
申请人： INTEL CORPORATION , DONG, Yaozu , TIAN, Kun , YU, Ke
发明人： DONG, Yaozu , TIAN, Kun , YU, Ke
IPC分类号： G06F12/08
CPC分类号： G06F9/45558 , G06F9/455 , G06F9/45533 , G06F9/5077 , G06F12/08 , G06F2009/45583 , G06T1/60
摘要： Systems and methods may provide for identifying an assigned address space of a virtual machine (VM), wherein the assigned address space is associated with a graphics memory. Additionally, the assigned address space may be ballooned to disable usage by the VM of a remaining address space in the graphics memory that is not assigned to the VM. In one example, a view of the assigned address space by the VM may be identical to a view of the assigned address space by a virtual machine monitor (VMM) associated with the VM.
摘要翻译：系统和方法可以提供用于识别虚拟机（VM）的分配的地址空间，其中所分配的地址空间与图形存储器相关联。此外，分配的地址空间可以被气球化以禁止虚拟机使用未分配给VM的图形存储器中的剩余地址空间。在一个示例中，VM分配的地址空间的视图可以与由VM关联的虚拟机监视器（VMM）分配的地址空间的视图相同。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式