Delivering GPU resources across machine boundaries

Patent metadata

Field	Value
Publication number	US-9135189-B2
Application number	US-201113227101-A
Country	US
Kind code	B2
Filing date	Sep 7, 2011
Priority date	Sep 7, 2011
Publication date	Sep 15, 2015
Grant date	Sep 15, 2015

Abstract

Described herein is providing GPU resources across machine boundaries. Data centers tend to have racks of servers that have limited access to GPUs. Accordingly, disclosed herein is providing GPU resources to computing devices that have limited access to GPUs across machine boundaries.

First claim

What is claimed:

1. A method for providing graphics processing unit (GPU) resources, the method comprising:
processing a request from an application operating on a virtual machine comprising a first system to perform at least one GPU operation;
sending data associated with the performance of at least one GPU operation to a Virtual graphics driver on the virtual machine to a separate system comprising a GPU for processing of the data by the GPU on the separate system, wherein the separate system mounts a state corresponding to the virtual machine and maintains the state between two or more GPU processing tasks, the GPU processing tasks comprising at least one operation;
receiving processed data from the separate system after the at least one GPU operation is performed; and
providing an indication to the application that the at least one GPU operation is completed.

2. The method of claim 1 wherein the separate system comprises a graphics server manager.

3. The method of claim 1 wherein the separate system comprises a proxy graphics application to process the data on the separate system with the GPU.

4. The method of claim 1 wherein a first GPU processing task of the two or more processing tasks is received from the virtual machine on a processor, and wherein a second GPU processing task of the two or more processing tasks is received from the virtual machine on a another processor of the system.

5. The method of claim 1 wherein the application is a remote desktop session.

6. The method of claim 1 wherein the virtual machine comprises a remote desktop session for a client.

7. A data center comprising:
one or more host servers in communication with one or more graphics server managers;
a first virtual machine hosted on the one or more host servers; and
a plurality of graphics processing unit (GPU) hosts in communication with the one or more graphics server managers and in communication with the one or more host servers,
one or more processing units associated with the one or more host servers configured to determine, based on the requirements of the first virtual machine, to send a GPU processing task to the plurality of GPU hosts allocated by the one or more graphics server managers, the plurality of GPU host configured to mount a state corresponding to the first virtual machine, and the plurality of GPU hosts configured to perform the GPU processing task and to send a processed GPU task to the one or more host servers, wherein the state is maintained between two or more GPU processing tasks.

8. The data center of claim 7 wherein the first virtual machine comprises a remote desktop session for a client computer.

9. The data center of claim 7 wherein the processed GPU task is sent from the one or more graphics server managers to the one or more host servers.

10. The data center of claim 7 wherein the processed GPU task is sent from the plurality of GPU hosts to the one or more host servers.

11. The data center of claim 7 wherein a first GPU processing task of the two or more processing tasks is received from the first set of one or more host processors, and wherein a second GPU processing task of the two or more processing tasks is received from the virtual machine on a second set of one or more processing units.

12. A computer readable storage device having stored thereon instructions that when executed by one or more processors comprising a data center, cause the one or more processors to perform the steps of:
processing a request from an application operating on a virtual machine comprising a first system to perform at least one GPU operation;
sending data associated with the performance of at least one GPU operation from a virtual graphics driver on the virtual machine to a separate system comprising a GPU for processing of the data by the GPU on the separate system, wherein the separate system mounts a state corresponding to the virtual machine and maintains the state between two or more GPU processing tasks, the GPU processing tasks comprising at least one operation;
receiving processed data from the separate system after the at least one GPU operation is performed; and
providing an indication to the application that the at least one GPU operation is completed.

13. The computer readable storage medium of claim 12 wherein the virtual machine hosts a remote desktop session.

Assignees

• Chakraborty Parag
• Post Bradley Stephen
• Pavlov Vladimir
• Kumar B Anil
• Microsoft Technology Licensing Llc

Inventors

• Chakraborty Parag
• Post Bradley Stephen
• Pavlov Vladimir
• Kumar B Anil

Classifications

• G06F9/455

  Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines · CPC title

• G09G5/363

  Graphics controllers · CPC title

• G09G5/003 Primary

  Details of a display terminal, the details relating to the control arrangement of the display terminal and to the interfaces thereto (specific for a CRT G09G1/165; for a flat panel G09G3/2092) · CPC title

• G06F2009/4557

  Distribution of virtual machine instances; Migration and load balancing · CPC title

• G06T1/20

  Processor architectures; Processor configuration, e.g. pipelining · CPC title