公开(公告)号：US10685473B2

公开(公告)日：2020-06-16

申请号：US15610192

申请日：2017-05-31

Applicant: VMware, Inc.

Inventor： Zack Rusin ,  Jose Fonseca

IPC: G06T1/20 ,  G06T15/00 ,  G06F9/455

Abstract: Techniques for emulating geometry shaders and stream output using compute shaders are provided. In one set of embodiments, a geometry shader/stream output (GS/SO) emulation module can receive a geometry shader defined by an application for execution via a geometry shader stage of a graphics processing unit (GPU) of a computer system, where the geometry shader comprises program code for processing an input primitive. The GS/SO emulation module can further convert the geometry shader into one or more compute shaders, where the one or more compute shaders incorporate the program code of the geometry shader. The GS/SO emulation module can then issue the one or more compute shaders to a graphics driver of the computer system for execution via a compute shader stage of the GPU.

公开(公告)号：US20200265631A1

公开(公告)日：2020-08-20

申请号：US16869364

申请日：2020-05-07

Applicant: VMware, Inc.

Inventor： Zack Rusin ,  Jose Fonseca

IPC: G06T15/00 ,  G06F9/455

Abstract: Techniques for emulating geometry shaders and stream output using compute shaders are provided. In one set of embodiments, a geometry shader/stream output (GS/SO) emulation module can receive a geometry shader defined by an application for execution via a geometry shader stage of a graphics processing unit (GPU) of a computer system, where the geometry shader comprises program code for processing an input primitive. The GS/SO emulation module can further convert the geometry shader into one or more compute shaders, where the one or more compute shaders incorporate the program code of the geometry shader. The GS/SO emulation module can then issue the one or more compute shaders to a graphics driver of the computer system for execution via a compute shader stage of the GPU.

公开(公告)号：US09298490B2

公开(公告)日：2016-03-29

申请号：US13723021

申请日：2012-12-20

Applicant: VMware, Inc.

Inventor： Salim Abiezzi ,  Jose Fonseca ,  Mark Sheldon

IPC: G06F9/455 ,  G06F9/50

CPC classification number: G06F9/45558 ,  G06F9/5044 ,  G06F2009/4557 ,  G06F2209/501

Abstract: Methods, techniques, and systems for dynamically allocating graphics processing units among virtual machines are provided. Example embodiments provide a dynamic GPU allocation system (“DGAS”), which enables the efficient allocation of physical GPU resources to one or more virtual machines. In one embodiment, the DGAS comprises a GPU allocation list for use in allocating the physical GPU resources comprising one or more virtual machine entries each containing a designation of a virtual machine, an indication of a GPU benefit factor associated with the designated virtual machine, and an indication of processing bandwidth requirements associated with the designated virtual machine. The entries are ranked based at least upon the GPU benefit factor associated with each designated virtual machine. Available GPU resources are allocated to some subset of these ranked virtual machines as physical GPU capacity is matched with the requirements of the subset.

Abstract translation: 提供了用于在虚拟机中动态分配图形处理单元的方法，技术和系统。 示例性实施例提供了一种动态GPU分配系统（“DGAS”），其能够将物理GPU资源有效地分配给一个或多个虚拟机。 在一个实施例中，DGAS包括用于分配包括一个或多个虚拟机条目的物理GPU资源的GPU分配列表，每个虚拟机条目包含虚拟机的指定，与指定虚拟机相关联的GPU利益因子的指示，以及 与指定虚拟机相关联的处理带宽要求的指示。 这些条目至少基于与每个指定虚拟机相关联的GPU有益因素进行排名。 可用的GPU资源被分配给这些排名的虚拟机的一些子集，因为物理GPU容量与子集的要求相匹配。

公开(公告)号：US09142004B2

公开(公告)日：2015-09-22

申请号：US13722998

申请日：2012-12-20

Applicant: VMware, Inc.

Inventor： Salim Abiezzi ,  Jose Fonseca ,  Mark Sheldon ,  Alan Hourihane

IPC: G06F15/80 ,  G06T1/20 ,  G06F9/455 ,  G06F9/50

CPC classification number: G06T1/20 ,  G06F9/45533 ,  G06F9/5044 ,  G06F9/505 ,  G06F2209/5021

Abstract: Methods, techniques, and systems for dynamically allocating graphics processing units among virtual machines are provided. Example embodiments provide a dynamic GPU allocation system (“DGAS”), which enables the efficient allocation of physical GPU resources to one or more virtual machines. In one embodiment, the DGAS comprises virtualization logic running on a server computing system that computes GPU benefit factors for the virtual machines on a dynamic basis, and combines the computed GBFs with static priorities to determine a ranked ordering of virtual machines. The available GPU resources are then allocated to some subset of these ranked virtual machines as physical GPU capacity is matched with the requirements of the subset. Physical GPU resources are then allocated to the subset of virtual machines that have the highest promise of GPU utilization.

Abstract translation: 提供了用于在虚拟机中动态分配图形处理单元的方法，技术和系统。 示例性实施例提供了一种动态GPU分配系统（“DGAS”），其能够将物理GPU资源有效地分配给一个或多个虚拟机。 在一个实施例中，DGAS包括在服务器计算系统上运行的虚拟化逻辑，其在动态基础上计算虚拟机的GPU利益因子，并且将计算出的GBF与静态优先级组合以确定虚拟机的排序顺序。 然后将可用的GPU资源分配给这些排名的虚拟机的一些子集，因为物理GPU容量与子集的要求相匹配。 然后将物理GPU资源分配给GPU利用率最高的虚拟机子集。

公开(公告)号：US11227425B2

公开(公告)日：2022-01-18

申请号：US16869364

申请日：2020-05-07

Applicant: VMware, Inc.

Inventor： Zack Rusin ,  Jose Fonseca

IPC: G06T15/00 ,  G06F9/455

Abstract: Techniques for emulating geometry shaders and stream output using compute shaders are provided. In one set of embodiments, a geometry shader/stream output (GS/SO) emulation module can receive a geometry shader defined by an application for execution via a geometry shader stage of a graphics processing unit (GPU) of a computer system, where the geometry shader comprises program code for processing an input primitive. The GS/SO emulation module can further convert the geometry shader into one or more compute shaders, where the one or more compute shaders incorporate the program code of the geometry shader. The GS/SO emulation module can then issue the one or more compute shaders to a graphics driver of the computer system for execution via a compute shader stage of the GPU.

公开(公告)号：US20180350027A1

公开(公告)日：2018-12-06

申请号：US15610192

申请日：2017-05-31

Applicant: VMware, Inc.

Inventor： Zack Rusin ,  Jose Fonseca

IPC: G06T1/20 ,  G06F9/455 ,  G06T15/00

Abstract: Techniques for emulating geometry shaders and stream output using compute shaders are provided. In one set of embodiments, a geometry shader/stream output (GS/SO) emulation module can receive a geometry shader defined by an application for execution via a geometry shader stage of a graphics processing unit (GPU) of a computer system, where the geometry shader comprises program code for processing an input primitive. The GS/SO emulation module can further convert the geometry shader into one or more compute shaders, where the one or more compute shaders incorporate the program code of the geometry shader. The GS/SO emulation module can then issue the one or more compute shaders to a graphics driver of the computer system for execution via a compute shader stage of the GPU.

公开(公告)号：US09460481B2

公开(公告)日：2016-10-04

申请号：US13849609

申请日：2013-03-25

Applicant: VMware, Inc.

Inventor： Jose Fonseca

IPC: G06T1/20 ,  G06F3/14

CPC classification number: G06T1/20 ,  G06F3/1462

Abstract: Systems and methods described herein facilitate processing or rendering desktop graphics for remote desktop display in, for example, a virtual desktop infrastructure (VDI), by decreasing the amount of data being transferred from a graphics processing unit (GPU). More specifically, the embodiments described herein include a host for hosting virtual machines within a VDI, the host includes a GPU that is configured to access a reference frame associated with desktop graphics. The GPU is further configured to generate a current frame associated with desktop graphics. The GPU is also configured to compare the reference frame with the current frame to identify one or more changed portions of the current frame relative to the reference frame, wherein the changed portions are used for the generation of an encoded frame that is configured to be displayed.

Abstract translation: 这里描述的系统和方法通过减少从图形处理单元（GPU）传送的数据量来促进处理或呈现用于例如虚拟桌面基础设施（VDI）中的远程桌面显示的桌面图形。 更具体地，本文描述的实施例包括用于托管VDI内的虚拟机的主机，主机包括被配置为访问与桌面图形相关联的参考帧的GPU。 GPU还被配置为生成与桌面图形相关联的当前帧。 GPU还被配置为将参考帧与当前帧进行比较，以识别当前帧相对于参考帧的一个或多个改变的部分，其中改变的部分用于生成被配置为被显示的编码帧 。

公开(公告)号：US09417929B2

公开(公告)日：2016-08-16

申请号：US13723035

申请日：2012-12-20

Applicant: VMware, Inc.

Inventor： Jose Fonseca ,  Salim Abiezzi

IPC: G06F9/46 ,  G06F9/455 ,  G06F9/50

CPC classification number: G06F9/5083 ,  G06F9/45558 ,  G06F2009/4557

Abstract: Methods, techniques, and systems for dynamically allocating graphics processing units among virtual machines are provided. Example embodiments provide a dynamic GPU allocation system (“DGAS”), which enables the efficient allocation of physical GPU resources to one or more virtual machines. In one embodiment, the DGAS determines runtime profiles of a plurality of virtual machines. The runtime profiles are determined by determining a runtime assessment of workload indicative of a potential benefit that the virtual machine can receive from using a GPU resource. The DGAS then causes the processing bandwidth of the physical GPU resources to be allocated to some of the plurality of virtual machines based upon the dynamically determined runtime assessments of workload.

Abstract translation: 提供了用于在虚拟机中动态分配图形处理单元的方法，技术和系统。 示例性实施例提供了一种动态GPU分配系统（“DGAS”），其能够将物理GPU资源有效地分配给一个或多个虚拟机。 在一个实施例中，DGAS确定多个虚拟机的运行时轮廓。 通过确定表示虚拟机可以从使用GPU资源接收的潜在利益的工作负载的运行时间评估来确定运行时概要文件。 然后，DGAS基于动态确定的工作负载的运行时间评估，使物理GPU资源的处理带宽分配给多个虚拟机中的一些。