Microsoft Technology Licensing, LLC

Microsoft Corporation

Cenk Ergan

Michael Richard Fortin

Mehmet Iyigun

Alexander Kirshenbaum

Yevgeniy Bak

Clark David Nicholson

William Jefferson Westerinen

Leonardo Esteban Blanco

Silvana Patricia Moncayo

Reiner Fink

Robert L Reinauer

Joshua Warren Priestley

Ruston Panabaker

Benjamin C Constable

Michael James Zwilling

Mark Joseph Zbikowski

Hanumantha Rao Kodavalla

Nathan Steven Obr

John M Parchem

Patrick L Stemen

Rajeev Y Nagar

Stuart Sechrest

Therron Powell

Dean L DeWhitt

Rafael V Cintron

Benjamin A Mickle

Surenda Verma

Dan Teodosiu

David Fields

Jason Joseph Weber

Kedar Hirve

Emily Nicole Hill

M David Fields, Jr

Michael D Decker

Walter V Von Koch

Samuel R Fortiner

Sandra G Roberts

Katerina V Sedova

Karen Elizabeth Parker Anderson

Qiang Chen

Prabhakar Marnadi

Landy Wang

Blake Douglas Pelton

Christian Fortini

Richard Keith James

Aaron Edward Dietrich

Jatinder Singh Mann

Justin Steventon

Eric Kochhar

Udayasimha Shivaswamy

Michael C Fanning

Adrian Mihail Marinescu

Robert P Fitzgerald

Mihai Costea

David Allen Goebel

Rico Mariani

Anil Francis Thomas

Emily Nicole Wilson

Iulian Doroftei Calinov

Li-Hsin Huang

Jack Creasey

Matthew Robert Ayers

Charles T Lenzmeier

Meir Shmouely

Omer Rosenbaum

Sandeep Prabhakar

Samarth Harish Shah

Padma Varadharajan

Robin Giese

Gregory Bershansky

Mahlon David Fields

George Cristian Chicioreanu

Matthew P Kotsenas

Marius Gheorghe Gheorghescu

Shaun Wiley

Raymond Duane Parsons

Aaron Rodriguez Hernandez

Taofiq Ezaz

Vijay Sundaram

Zachary Sandburg Holmes

Dan Li

Sathish Kumar Manivannan

Brandon Michael Heenan

Joshua Daniel Patterson

Alex Kirshenbaum

Daniel Teodosiu

Douglas R Earhart

Micah Brodsky

Yuval Peled

Yi Ming Zhou

Kieran Chin Cheong

Kelly Laurence Ford

Ben Mickle

Yuqing Li

Nikhil Bhatia

Erik V Day

Keren Shushan

Adrian Bivol

Embodiments relate to enabling software to interface with a power consumption telemetry system. A process may have tagging instructions that interface with an energy estimation engine. While the energy estimation engine is logging energy consumption by the process, the process may also mark, tag, or otherwise delineate periods of processing during the execution time of the process. The logic of the process may determine how such periods should be labeled and when they being and end. The tagged periods are correlated with energy consumed by the process so that details of what the process was doing during different periods of energy consumption may be understood.

Process-level activity tagging

To ensure that the contents of a non-volatile memory device cache may be relied upon as accurately reflecting data stored on disk storage, it may be determined whether the cache contents and/or disk contents are modified during a power transition, causing cache contents to no longer accurately reflect data stored in disk storage. The cache device may be removable from the computer, and unexpected removal of the cache device may cause cache contents to no longer accurately reflect data stored in disk storage. Cache metadata may be managed during normal operations and across power transitions, ensuring that cache metadata may be efficiently accessed and reliably saved and restored across power transitions. A state of a log used by a file system may be determined prior to and subsequent to reboot of an operating system in order to determine whether data stored on a cache device may be reliably used.

Method and system for ensuring reliability of cache data and metadata subsequent to a reboot

In order to provide a more efficient persistent storage device, one or more long-term storage media are included along with a non-volatile memory. In one embodiment, one portion of the non-volatile memory is used as a write buffer and a read cache for writes and reads to the long-term storage media. Interfaces are provided for controlling the use of the non-volatile memory as a write buffer and a read cache. Additionally, a portion of the non-volatile memory is used to provide a direct mapping for specified sectors of the long-term storage media. Descriptive data regarding the persistent storage device is stored in another portion of the non-volatile memory.

Non-volatile memory cache performance improvement

Virtual surface techniques are described. These techniques support the use of initialization and batching of updates, use of updates and lookaside lists, use of gutters, blending and BLT operations, use of surface optimization techniques such as push down as well as enumeration and clumping, mesh usage, and use of occlusion management techniques.

Virtual surface blending and BLT operations

Virtual surface update and composition techniques are described. These techniques include support of initialization and batching of updates, use of updates and lookaside lists, use of gutters, blending and BLT operations, surface optimization techniques such as push down as well as enumeration and clumping, mesh usage, and occlusion management techniques.

Virtual surface compaction

Virtual surface gutters

The invention is directed towards a system and method that utilizes external memory devices to cache sectors from a rotating storage device (e.g., a hard drive) to improve system performance. When an external memory device (EMD) is plugged into the computing device or onto a network in which the computing device is connected, the system recognizes the EMD and populates the EMD with disk sectors. The system routes I/O read requests directed to the disk sector to the EMD cache instead of the actual disk sector. The use of EMDs increases performance and productivity on the computing device systems for a fraction of the cost of adding memory to the computing device.

Using external memory devices to improve system performance

In one or more embodiments, an application program interface (API) is provided and enables an entity, such as an application, script, or other computing object to register to receive callbacks immediately and, without specifying a time constraint. In this approach, the API does not rely on a timer, such as a system timer. Rather, a non-timer based queue, such as a message queue-type approach is utilized. Specifically, callbacks that are registered through this API can be placed on the message queue and work associated with the registered callback can be performed through the normal course of processing messages and events in the message queue. Over time, such results in a callback pattern that allows an associated web browser and applications such as web applications to remain responsive, while increasing performance and power efficiencies.

Power efficient callback patterns

Various embodiments are directed to intelligently rendering or pre-rendering content that may likely be brought into an associated viewport during a user's interaction with the content. In at least some embodiments, the process of caching pre-rendered content is separated from a determination of which regions outside of the viewport are to be kept up to date over use and time. Further, at least some embodiments perform rendering activities in multiple passes in an effort to reduce potential delays in the user visible content reaching completion, without interfering with other work that an associated application or system performs during rendering.

Speculative render ahead and caching in multiple passes

Virtual surface techniques are described. These techniques include support of initialization and batching of updates, use of updates and lookaside lists, the use of gutters, the use of blending and BLT operations, surface optimization techniques such as push down as well as enumeration and clumping, mesh usage, and occlusion management techniques.

Display techniques using virtual surface allocation

Virtual surface rendering

In one or more embodiments, a framework is provided in which image decoding can be delayed based on heuristics, and later initiated based on a use type associated with the image or the likelihood that the image is going to be used. For example, a use history and priority system can enable images that are currently being rendered and/or are likely to get rendered to be decoded before images that have a history of being downloaded but never used. Accordingly, by decoupling image download from image decoding, CPU resources and memory can be more efficiently utilized.

Delayed image decoding

Growing community of inventors

Bellevue, WA, United States of America

Cenk Ergan