Abstract: Technology for a method for backing up and restoring game application state across multiple devices is disclosed herein. The method includes running an instance of a game application, by a distributed system, at a first electronic device, determining a backup event that occurs in the first electronic device, wherein the backup event suggests a backup of application state data and the application state data represent an application state of the game application at the backup event, and transmitting the application state data of the game application to a remote storage service, in response to the backup event. A second electronic device can retrieve the application state data from the remote storage service and restore the game application state.

Abstract: Technology for decomposing an application into fragments and streaming the application in fragments is disclosed herein. According to at least one embodiment, a computer-implemented method includes steps of determining multiple application fragments of a computer application, wherein each application fragment of the application fragments includes a code to present at least one interface of the computer application; storing the application fragments at a storage device; generating a resource dependency data structure, wherein for each specific application fragment of the application fragments, the resource dependency data structure includes identifications of resources that are needed for running the specific application fragment; and streaming, via a network component, at least one application fragment of the application fragments to a computing device.

Abstract: Technology for decomposing an application into fragments and streaming the application in fragments is disclosed herein. According to at least one embodiment, a computer-implemented method includes steps of determining multiple application fragments of a computer application, wherein each application fragment of the application fragments includes a code to present at least one interface of the computer application; storing the application fragments at a storage device; generating a resource dependency data structure, wherein for each specific application fragment of the application fragments, the resource dependency data structure includes identifications of resources that are needed for running the specific application fragment; and streaming, via a network component, at least one application fragment of the application fragments to a computing device.

Abstract: Techniques introduced here enable cloud-based file prefetching for gaming applications running on electronic devices. The electronic devices store certain gaming data files on a remote storage server and preload some of the files locally to include file access efficiency. Gaming data file access patterns on the electronic devices are analyzed, individually and collectively, using a cloud service to detect global access patterns and help determine which gaming data files to preload on each of the electronic devices.

Abstract: Techniques introduced here enable cloud-based file prefetching for gaming applications running on electronic devices. The electronic devices store certain gaming data files on a remote storage server and preload some of the files locally to include file access efficiency. Gaming data file access patterns on the electronic devices are analyzed, individually and collectively, using a cloud service to detect global access patterns and help determine which gaming data files to preload on each of the electronic devices.

Abstract: Technology is disclosed for decomposing an application into fragments and streaming the application fragments for execution on a mobile computing device. A fragment presents a user interface of the application and needs a set of resources, e.g., images, icons, etc. to be executed. A server determines a set of fragments for the application and streams them to the device as and when the device needs a particular fragment. The server determines the set of fragments in various ways. For example, the server executes an emulator that simulates the execution of the application by the user and determines fragment data including the set of fragments, resources needed by each of the fragments, and various possible navigations between the fragments. In another example, the server receives such fragment data from various users executing the application on various devices, and aggregates them based on aggregating policy to obtain an aggregated fragment data.

Abstract: Technology is disclosed for using computing devices (“the devices”) of a user as an edge cache of a distributed backup system to stream video files. In the distributed backup system, the user can store different data files of the user at different devices of the user and/or at a server. For example, the user may store video files at one of the devices of the user (“a first device”) in addition to storing at the server. When the user requests to stream a particular video file to a particular device, the technology streams the video file to the particular device either from the server or from the first device. If the first device is in proximity to the particular device, the video file is streamed from the first device instead of from the server, thereby minimizing the latency involved in streaming the video file from the server.

Abstract: At least one embodiment of this disclosure includes a method of sharing application states across different user profiles. The method can include: receiving a request from a first computing device associated with a first user profile to load an application state of a target application, wherein the application state is owned by a second user profile; verifying permission for the first user profile to load the application state owned by the second user profile; configuring a sharing instance of the application state of the target application by accessing application data of the application state associated with the second user profile in a storage service; and sending the sharing instance to be loaded onto the first computing device.

Abstract: Technology for decomposing an application into fragments and streaming the application in fragments is disclosed herein. According to at least one embodiment, a computer-implemented method includes steps of running an intermediary application at a mobile device to enable the mobile device to run the video game application by running multiple game application fragments, the intermediary application acting as an intermediary between the video game application and the game application fragments by determining a next game application fragment for each of the game application fragments; running, at the mobile device, an instance of the video game application by running a first application fragment of the game application fragments at the mobile device; requesting, by the intermediary application, a second application fragment of the game application fragments corresponding to a second portion of the video game application; and receiving, at the mobile device, the second application fragment.

Abstract: Disclosed are systems, methods, and machine-readable storage mediums for managing storage of a computing device associated with a user. In at least some embodiments, a method includes receiving a request to synchronize a data file from a cloud storage system from a the computing device, determining a classification of the computing device and an access pattern associated with the file, determining a storage optimization operation to be performed on the data file based on the access pattern and the classification, transmitting the file to the device subsequent to execution of the storage optimization operation, and transmitting an updated file based on an updated access pattern. The storage optimization operation can include downsampling, lossy compression, lossless compression, or a combination thereof.

Abstract: Technology disclosed herein includes a method for loading a carrier specific operating system (OS) onto a computing device depending on any corporation the computing device is associated with and the network the computing device is connected to. The computing device detects any corporation the computing device is associated with based on the subscriber number of the computing device. The computing device detects an identity of a network by examining a subscriber identification module (SIM) card electronically connected to the device. The device then sends a request including the identity of the corporation and the network to a remote registration service. In turn the device receives an instruction from the remote registration service identifying a distribution of an OS specific for the corporation and the network. After retrieving the OS distribution, the device loads the distribution of the OS on the computing device.

Abstract: A technique and apparatus for backing up and restoring game application state across multiple devices are disclosed herein. The method includes running an instance of a game application at a first device. Based on any of various criteria, such as the proximity between the first device and a second device, a computer makes a determination to synchronize the application state between the two devices. The computer causes the application state data, which represents an application state of the game application running on the first device, to be saved and made available to the second device, such as by saving the application state data to cloud storage. The second device receives the application state data and restores the game application state.

Abstract: Technology is disclosed for synchronizing audio files from a computing device of a user to an in-vehicle computing device, such as an audio system, installed in an automobile. In one example, when the user plays an audio file on the in-vehicle computing device from the computing device, the audio file is copied at the in-vehicle computing device. After copying the currently playing audio file, the in-vehicle computing device can also copy at least some of the audio files from the computing device. The in-vehicle computing device computes a popularity score of each of the audio files based on an access pattern of the audio files, and categorizes them into priority files and low-priority files based on their popularity score. While the in-vehicle computing device copies the priority files, it copies metafiles of the low-priority files. The metafiles can include information such as a title, artist, etc. of the audio files.

Abstract: At least one embodiment of this disclosure includes a method of sharing application states across different user profiles. The method can include: receiving a request from a first computing device associated with a first user profile to load an application state of a target application, wherein the application state is owned by a second user profile; verifying permission for the first user profile to load the application state owned by the second user profile; configuring a sharing instance of the application state of the target application by accessing application data of the application state associated with the second user profile in a storage service; and sending the sharing instance to be loaded onto the first computing device.

Abstract: At least one embodiment of this disclosure includes a method of resource balancing execution of an application involving multiple devices. The method can include: identifying an application executing on an operating system of a first computing device; identifying a resource type to facilitate the executing of the application; identifying multiple computing devices each having at least an available resource instance of the identified resource type, wherein the multiple computing devices are reachable by a communication protocol of the first computing device; and selecting a target computing device to offer up a target resource instance of the resource type to the application based at least partly on a comparable limitation of each available resource instance of the multiple computing devices.

Abstract: Technology is disclosed for backing up and retrieving data in a distributed backup system (“the technology”). Files of a user can be stored across multiple computing devices (“the devices”) of the user, e.g., mobile devices, and/or at a server, e.g., a cloud storage server, in the distributed backup system. The user can define various policies for storing different files at different devices. For example, the user may define a policy for storing video files on a device that has a bigger display. The devices can be used as an edge cache of the distributed backup system in serving files to the user. Upon receiving a request for retrieving a file, the technology determines if any of the user devices that are in proximity to the requesting device has the file. If yes, the file is transmitted to the user from the proximate device instead of from the server.

Abstract: Technology is disclosed for downloading image files associated with a user to a computing device of the user from a distributed backup system. Each of the image files is associated with a popularity score that is determined as a function of a user-related access pattern and a group-related access pattern of the image files. While the user-related access pattern is determined based on an access of the image files by the user, the group-related access pattern is determined based on an access by a group of users. The image files are categorized into priority files and non-priority files based on the popularity score of the image files. The priority files are downloaded in an original format and the non-priority files are downloaded in one or more image qualities that minimize the consumption of computing resources in downloading the image files.

Abstract: Technology is disclosed for utilizing version vector data of computing devices to optimize performance of the computing devices and/or other computer systems that provide various services to the computing devices (“the technology”). One embodiment includes analyzing version vectors of the computing devices to determining a user's usage pattern, such as the type of computing device used, the computer applications used on the computing device, and the time of day of usage. This information about usage pattern and other information that can be determined using the version vectors can enable system optimizations on both individual user level and a group of users level. For example, on the individual user level, knowing user's usage pattern may enable automatic file synchronization between multiple devices without user intervention. On the group level, a service provider may allocate resources (servers, bandwidth, etc.) to accommodate the group's usage pattern.

Abstract: At least one embodiment of this disclosure includes a method of sharing application states across different user profiles. The method can include: receiving a request from a first computing device associated with a first user profile to load an application state of a game application, wherein the application state is owned by a second user profile; verifying permission for the first user profile to load the application state owned by the second user profile; configuring a sharing instance of the application state of the game application by accessing gameplay state data of the application state associated with the second user profile in a storage service; and sending the sharing instance to be loaded onto the first computing device.