Memory Descriptor List Caching and Pipeline Processing

• US 20180173656A1
• Filed: 10/25/2017
• Published: 06/21/2018
• Est. Priority Date: 01/19/2015
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Wilson, Mei L., Krishnan, Jitesh, Karivaradaswamy, Sathyanarayanan
• Granted Patent: US 10,452,581 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 13/28 using burst mode transfer, e.g. direct memory access DMA, cycle steal G06F13/32 takes precedence
• CPC Class Codes: G06F 2212/306 In system interconnect, e.g. between two buses
• CPC Class Codes: G06F 2212/455 Image or video data
• CPC Class Codes: G06F 2212/464 Multimedia object, e.g. image, video

Abstract

Memory descriptor list caching and pipeline processing techniques are described. In one or more examples, a method is configured to increase efficiency of buffer usage within a pipeline of a computing device. The method includes creation of a buffer in memory of the computing device and caching of a memory descriptor list by the computing device that describes the buffer in a buffer information cache and has associated therewith a handle that acts as a lookup to the memory descriptor list. The method also includes passing the handle through the pipeline of the computing device for processing of data within the buffer by one or more stages of the pipeline such that access to the data is obtained by the one or more stages by using the handle as the lookup as part of a call to obtain the memory descriptor list for the buffer from the buffer information cache.

Claims

1. A method configured to increase efficiency of buffer usage within a pipeline of a computing device, the method comprising:

creating a buffer in memory of the computing device;

caching a memory descriptor list by the computing device that describes the buffer in a buffer information cache and has associated therewith a handle that acts as a lookup to the memory descriptor list; and

passing the handle through the pipeline of the computing device for processing of data within the buffer by one or more stages of the pipeline such that access to the data is obtained by the one or more stages by using the handle as the lookup as part of a call to obtain the memory descriptor list for the buffer from the buffer information cache.

2. A method as described in claim 1, wherein the memory descriptor list is cached in the buffer information cache of a device driver that is configured for execution in a kernel mode of an operating system of the computing device.

3. A method as described in claim 2, wherein the handle supports the lookup to memory description list in the kernel mode from a user mode of the operating system.

4. A method as described in claim 1, wherein the device driver corresponds to a camera and the data in the buffer is an image.

5. A method as described in claim 1, wherein the buffer is part of a circular allocator.

6. A method as described in claim 5, wherein the circular allocator is executed within a user mode of the operating system of the computing device.

7. A method as described in claim 1, further comprising passing the handle from the pipeline to a sink of the computing device such that access to the data is obtained by using the handle as part of a lookup to obtain the memory descriptor list for the buffer from the browser information cache.

8. A method as described in claim 7, further comprising rendering, communicating, or storing the data within the buffer by the sink.

9. A method as described in claim 1, further comprising detecting that an amount of available space in the memory has dropped below a threshold and in response reverting to use of the probe, lock, and map operations and ceasing use of the buffer information cache.

10. A method as described in claim 1, wherein the creating is performed using a probe, lock, and map operation and access to the data is obtained by the one or more stages by using the handle as the lookup as part of a call to obtain the memory descriptor list for the buffer from the buffer information cache without repeating the probe, lock, and map operation.

11. A method configured to increase efficiency of access to data within a buffer by a pipeline of a computing device, the method comprising:

receiving a handle by at least one stage of the pipeline of the computing device that is to access the data within a buffer;

making a call by the at least one stage to a source of the handle to obtain a memory descriptor list by the computing device that describes the buffer through use of the handle as a lookup in a buffer information cache; and

using the obtained memory descriptor list by the at least one stage to access the data within the buffer.

12. A method as described in relation to claim 11, wherein the buffer is created through a probe, lock, and map operation and the using of the memory description list by the at least one stage to access the data within the buffer is performed without using the probe, lock, and map operation.

13. A method as described in claim 11, wherein the memory descriptor list is cached in the buffer information cache of a device driver that is configured for execution in a kernel mode of an operating system of the computing device.

14. A method as described in claim 13, wherein the handle supports the lookup to memory description list in the kernel mode from a user mode of the operating system.

15. A method as described in claim 11, wherein the buffer is part of a circular allocator.

16. A computing device configured to increase efficiency of buffer usage within a pipeline of the computing device, the computing device comprising:

a processing system configured to perform one or more operations; and

memory configured to maintain instructions that are executable by the processing system to implement an operating system, the operating system configured to;

create a buffer in the memory by performing a probe, lock, and map operation;

cache a memory descriptor list that describes the buffer in a buffer information cache and has associated therewith a handle that supports a lookup to the memory descriptor list;

receive the handle by at least one stage of the pipeline that is to access the data within a buffer;

make a call by the at least one stage to a source of the handle to obtain the memory descriptor list; and

use the memory descriptor list by the at least one stage to access the data within the buffer

17. A computing device as described in relation to claim 16, wherein the buffer is created through a probe, lock, and map operation and the use of the memory description list by the at least one stage to access the data within the buffer is performed without using the probe, lock, and map operation.

18. A computing device as described in relation to claim 16, wherein the memory descriptor list is cached in the buffer information cache of a device driver that is configured for execution in a kernel mode of an operating system of the computing device.

19. A computing device as described in relation to claim 18, wherein the handle supports the lookup to memory description list in the kernel mode from a user mode of the operating system.

20. A computing device as described in relation to claim 16, wherein the buffer is part of a circular allocator.