Abstract: Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components access to communicate with a GPU at a different component or physical machine in a data center or a network. A first physical machine starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The rendered graphics is then sent to the client via the gateway.

Abstract: Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components access to communicate with a GPU at a different component or physical machine in a data center or a network. A first physical machine starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The rendered graphics is then sent to the client via the gateway.

Abstract: Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components without GPU access to communicate with a GPU at a different component or physical machine in a data center or a network using remote direct memory access (RDMA). A first physical machine that excludes a GPU starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The render function communicates with the remote display driver function at the first physical machine. The rendered graphics is then sent to the client via the gateway.

Abstract: Embodiments for provided for using virtual desktop infrastructure (VDI) user level virtual channels (VCs) which allows client data prioritization within a Transmission Control Protocol (TCP) connection to a client. An embodiment method includes establishing a communication module at a user level of operation of a server, and establishing a TCP connection between the server and a client device. Additionally, the server establishes, at the user level of operation, a plurality of VCs for a plurality of respective services provided to the client device. The communication module at the user level communicates with service modules running at the server for executing the services. The data of the VCs are arranged into a plurality of respective priority queues according to priority of the services. The communication module exchanges the data of the services in the VCs on the TCP connection with the client device according to the priority queues.

Abstract: System and method embodiments are provided for enabling OpenGL graphics rendering on VM architecture. In an embodiment, a method implemented in a system comprising multiple virtual machines (VMs) includes intercepting, at a first VM that does not have direct access to a graphics processing unit (GPU), a command from an application to render graphics. The method further includes processing the command using hardware based GPU rendering at a second VM that has direct access to a GPU upon determining that the GPU is free or has capacity to handle workload of the command or processing the command using CPU based software rendering at the first VM upon determining that the GPU of the second VM is busy or does not have capacity to handle workload of the command and the graphics data.

Abstract: Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components without GPU access to communicate with a GPU at a different component or physical machine in a data center or a network using remote direct memory access (RDMA). A first physical machine that excludes a GPU starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The render function communicates with the remote display driver function at the first physical machine. The rendered graphics is then sent to the client via the gateway.

Abstract: System and method embodiments are provided for adaptive bandwidth management for transporting rendered graphics in a virtual desktop infrastructure. The embodiments include a video detection algorithm that enables a driver for a graphics processor at the server's end to identify displayed video data at the user'send. The driver identifies video traffic that is sent to the user device by tracking repeated bitmap operations at the same display area or block of an application displayed window at the user device. When the number of bitmap operations reaches a pre-determined threshold, then the corresponding area is considered a video display area. When detecting that a bandwidth threshold for transporting graphics data from the server to the device is reached, the data corresponding to the detected video area is compressed using a higher compression rate, thus increasing the loss rate of transferred video data to improve playback experience for the user.

Abstract: Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components without GPU access to communicate with a GPU at a different component or physical machine in a data center or a network using remote direct memory access (RDMA). A first physical machine that excludes a GPU starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The render function communicates with the remote display driver function at the first physical machine. The rendered graphics is then sent to the client via the gateway.

Abstract: A method and system for serving a virtual desktop to a client are introduced herein. In one embodiment, the method includes rendering and encoding an application frame on a first server, rendering and encoding a desktop frame that confines the application frame on a second server, communicating the application frame to the second server, and communicating the desktop frame and redirecting the application frame from the second server to the client.

Abstract: Embodiments for provided for using virtual desktop infrastructure (VDI) user level virtual channels (VCs) which allows client data prioritization within a Transmission Control Protocol (TCP) connection to a client. An embodiment method includes establishing a communication module at a user level of operation of a server, and establishing a TCP connection between the server and a client device. Additionally, the server establishes, at the user level of operation, a plurality of VCs for a plurality of respective services provided to the client device. The communication module at the user level communicates with service modules running at the server for executing the services. The data of the VCs are arranged into a plurality of respective priority queues according to priority of the services. The communication module exchanges the data of the services in the VCs on the TCP connection with the client device according to the priority queues.

Abstract: Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components without GPU access to communicate with a GPU at a different component or physical machine in a data center or a network using remote direct memory access (RDMA). A first physical machine that excludes a GPU starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The render function communicates with the remote display driver function at the first physical machine. The rendered graphics is then sent to the client via the gateway.

Abstract: The time required to login to a remote or virtual desktop can be reduced by caching image data in a persistent memory location of a client device in-between remote desktop sessions. For instance, image data related to an image displayed on the client device during a first virtual desktop session may be cached after terminating the first virtual desktop session. The cached data can then be used to display the same image, or a correlated image, on the client device during a subsequent remote desktop session, thereby avoiding the need to re-transport the image data over a network.

Abstract: The time required to login to a remote or virtual desktop can be reduced by caching image data in a persistent memory location in-between remote desktop sessions. For instance, image data related to an image displayed on a client device during a first virtual desktop session may be cached after terminating the first virtual desktop session. The cached data can then be used to display the same image, or a correlated image, on the client device during a subsequent remote desktop session, thereby avoiding the need to re-transport the image data over a network. In a similar manner, cached image data can be shared between multiple users sharing a common local area network (LAN) in order to improve collective virtual desktop performance.

Abstract: System and method embodiments are provided for adaptive bandwidth management for transporting rendered graphics in a virtual desktop infrastructure. The embodiments include a video detection algorithm that enables a driver for a graphics processor at the server's end to identify displayed video data at the user's end. The driver identifies video traffic that is sent to the user device by tracking repeated bitmap operations at the same display area or block of an application displayed window at the user device. When the number of bitmap operations reaches a pre-determined threshold, then the corresponding area is considered a video display area. When detecting that a bandwidth threshold for transporting graphics data from the server to the device is reached, the data corresponding to the detected video area is compressed using a higher compression rate, thus increasing the loss rate of transferred video data to improve playback experience for the user.

Abstract: The time required to login to a remote or virtual desktop can be reduced by caching image data in a persistent memory location in-between remote desktop sessions. For instance, image data related to an image displayed on a client device during a first virtual desktop session may be cached after terminating the first virtual desktop session. The cached data can then be used to display the same image, or a correlated image, on the client device during a subsequent remote desktop session, thereby avoiding the need to re-transport the image data over a network. In a similar manner, cached image data can be shared between multiple users sharing a common local area network (LAN) in order to improve collective virtual desktop performance.

Abstract: System and method embodiments are provided for improving the performance of OpenGL graphics rendering on VM architecture. In an embodiment, a method implemented in a system comprising multiple virtual machines (VMs) includes intercepting, at a first VM that does not have direct access to a graphics processing unit (GPU), a command from an application to render graphics. The method further includes processing the command using hardware based GPU rendering at a second VM that has direct access to a GPU upon determining that the GPU is free or has capacity to handle workload of the command or processing the command using software based GPU rendering at the first VM upon determining that the GPU of the second VM is busy or does not have capacity to handle workload of the command and the graphics data.

Abstract: The time required to login to a remote or virtual desktop can be reduced by caching image data in a persistent memory location in-between remote desktop sessions. For instance, image data related to an image displayed on a client device during a first virtual desktop session may be cached after terminating the first virtual desktop session. The cached data can then be used to display the same image, or a correlated image, on the client device during a subsequent remote desktop session, thereby avoiding the need to re-transport the image data over a network. In a similar manner, cached image data can be shared between multiple users sharing a common local area network (LAN) in order to improve collective virtual desktop performance.