Preloading software applications in a cloud computing environment

Abstract

Apparatus, systems, and techniques for preloading a software application in a cloud computing environment. A method may include sending a preload request to preload an initial section of data for an application hosted on an application hosting platform, receiving the preload request before receiving the user input that identifies the application for execution. The method may include receiving an initial indication that the first section of data has been preloaded and receiving a user request to execute the application. The method may further include sending a load request to load a second section of data for the application, receiving a second indication that the second section of data has been loaded for the application, and causing the application to execute on the virtualized computing environment in response to receiving the second indication.

Description

TECHNICAL FIELD

[0001] At least one embodiment relates to processing resources used to perform and facilitate preloading of applications in a cloud computing environment. For example, at least one embodiment relates to processors or computing systems used to deploy and enable a gaming application to be preloaded on one or more virtualized computing environments hosted by an application hosting platform, according to various novel techniques described herein. BACKGROUND

[0002] In a cloud computing environment, users can access and stream software applications (such as gaming applications) via an application hosting platform on their local client device. The software application may load multiple files during a launch sequence, including assets, textures, graphics, user-associated data, and so on. Loading all of the files associated with the software application can be time-consuming. An application hosting platform can load the software application as soon as a user accesses an instance of the software application. However, such existing techniques can cause users to wait a significant amount of time before the software application is ready for streaming. This can degrade the overall user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] Various embodiments according to the present invention will be described with reference to the drawings, in which: Fig. 1 illustrates a block diagram of an example cloud computing environment system architecture, according to at least some embodiments; Fig. 2 illustrates a block diagram of a cloud environment, according to at least some embodiments; Fig. 3 illustrates a diagram of an example of preloading a software application, according to at least some embodiments; Fig. 4 illustrates a diagram of an example of preloading a software application, according to at least some embodiments; Fig. 5 illustrates a diagram of an example of preloading a software application, according to at least some embodiments; Fig. 6 illustrates a flow diagram of an example method for preloading a software application, according to at least some embodiments; Fig. 7A illustrates inference and / or training logic, according to at least some embodiments; Fig. 7B illustrates inference and / or training logic, according to at least some embodiments; Fig. 8 illustrates an example data center system, according to at least some embodiments; Fig. 9 illustrates a computer system, according to at least some embodiments; Fig. 10 illustrates a computer system, according to at least some embodiments; Fig. 11 illustrates at least portions of a graphics processor, according to at least some embodiments; Fig. 12 illustrates at least portions of a graphics processor, according to at least some embodiments; Fig. 13 illustrates an example data flow diagram for an evolved compute pipeline, according to at least some embodiments; Fig. 14 illustrates a system diagram for an example system for training, adapting, instantiating, and deploying a machine learning model in an advanced compute pipeline, according to at least some embodiments; and Fig. 15A and Fig. 15B illustrates a data flow diagram for a process to train a machine learning model, as well as a client-server architecture to enhance annotation tools with pre-trained annotation models, according to at least some embodiments. DETAILED DESCRIPTION

[0004] Software applications may be hosted on a cloud computing environment, for example, and without limitation, by an application hosting platform. For example, an instance of a software application hosted by the application hosting platform may run on a client device via a virtualized computing environment (e.g., on a virtual machine or a container). A user may access the software application (e.g., a video game or a mobile game) on a computing device (e.g., a computer, game console, mobile phone, smartphone, etc.) via the application hosting platform. For example, a user may access the application hosting platform (e.g., log in) and select a game application and execute or play it on their computing device.The application hosting platform may communicate with the game application through a set of application programming interfaces (APIs) and begin loading an instance of the game application onto a virtualized computing environment for the user device to access. For example, when the user selects the game application, the application hosting platform may launch the game application onto the virtualized computing environment using a command line interface (CLI). To launch the game application onto the virtualized computing environment, the application hosting platform may begin loading the game application files onto the virtualized computing environment for the user. In some examples, this may include generic game application data and user game application data.For example, generic game application data may include assets, textures, game application illustrations, background graphics, title screens, main menu screens, memory allocation of the game application on the user device, shaders, etc. User data may include data that the game application loads specifically for the user. For example, user data may include specific user settings (e.g., resolution or shader settings), custom content (e.g., customizations to a character in a game made by the user), custom key bindings, etc.

[0005] In some examples, the application hosting platform may take several minutes to load the generic data and user data onto the virtualized computing environment. More specifically, the application hosting platform may take several minutes to load the generic data—for example, if most of the data loaded by the application hosting platform from the gaming application is generic data. During this time, the user is unable to access the gaming application and is forced to wait. In some examples, the user may see a loading screen while the virtualized computing environment prepares for gameplay. Once initialized, the virtualized computing environment may be ready, and the user may access the gaming application and the main menu.The overall user experience of running an instance of the game application may be negatively impacted due to the long delay between the user selecting the game application and the user being able to access the game application. For example, the experience may be negatively impacted if the user must wait an excessive amount of time for the virtualized computing environment to sufficiently complete initializing and loading the generic data and user data before the game can be played.

[0006] Aspects of the present embodiment address the above and other deficiencies by enabling an application hosting platform to prepare (e.g., preload at least some portions) a virtualized computing environment (e.g., a virtual machine or container) to execute an instance of a software application and to reduce a time between selecting the instance of the software application and executing the instance of the software application for a user. That is, the application hosting platform has at least partially loaded the instance of the software application (using a preload mode) when the user selects the instance of the software application, e.g., the virtualized computing environment is partially loaded with the generic data of the software application when the user selects the software to execute.For example, the software application may send an initialization request to the application hosting platform via a first application programming interface (API) command. The initialization request may tell the application hosting platform whether the software application should be instructed to start in preload mode using a CLI command or a flag setting (e.g., in an application configuration file). Alternatively, or additionally, the software application should be instructed to start in preload mode by confirming that the software application is present in the cloud environment.

[0007] The application hosting platform may then request that generic data for an instance of the software application be loaded onto the virtualized computing environment. In response to the acknowledgment, the software application may begin loading generic data onto the virtualized computing environment for the instance of the software application. For example, the virtualized computing environment may be loaded with textures, shaders, background graphics, etc. upon receiving the acknowledgment—e.g., loading everything except the user data. Each software application may have varying amounts of generic data to be loaded; e.g., the generic data may be specific to a particular software application. In some examples, after loading the generic data, the software application may notify the application hosting platform that the loading of the generic data is complete.In some examples, the application hosting platform can use a machine learning model to predict when a specific software application will finish loading the generic data. When the application hosting platform receives notification that the software application has finished loading the generic data, the application hosting platform can cause the virtualized computing environment to be placed in an idle mode. This means that the virtualized computing environment can be ready for user access while consuming minimal computing resources.

[0008] When a user selects the instance of the software application, a virtualized computing environment service can notify the application hosting platform that the user is initializing a session. The application hosting platform can communicate with the application via an API command (e.g., a session callback) and instruct the software application to load user data. Accordingly, the virtualized computing environment can be loaded with the user data and ready for the user to start running the software application. The application hosting platform can request to preload multiple virtualized computing environments for a specific software application based on collected data. For example, the application hosting platform can determine an average duration that a virtualized computing environment remains idle, as well as how many users cannot access a preloaded virtualized computing environment—e.g.,there are not enough preloaded virtualized computing environments for users of the software application. Accordingly, based on the balance between the amount of time a virtualized computing environment is inactive and how many users cannot access a preloaded virtualized computing environment, the application hosting system may instruct the application hosting system to prepare a specific set of virtualized computing environments for a software application (e.g., gaming, content creation, etc.). Furthermore, the application hosting platform may instruct the application hosting system to deconstruct a virtualized computing environment when the software application undergoes an update—e.g., by deleting a virtual machine and preloading another virtual machine (or replacing stored generic data on the virtual machine) with updated generic data from the updated software application.

[0009] Because the generic data has already been loaded onto the virtualized computing environment, the amount of time the user must wait between initiating the software application and running the software application is reduced.

[0010] For example, the user can access the main menu and launch the software application after the user data is loaded, instead of waiting for the generic data and user data to load. This can improve the overall user experience and provide a more balanced use of network bandwidth and computing resources. Fig. 1 illustrates a block diagram of an example system architecture 100, according to at least one embodiment. The system architecture 100 (also referred to herein as a "system") includes an application hosting platform 102, an application developer platform 104, a server machine 106, client devices 108A-N (collectively and individually referred to as client device(s) 108), and a data store 112, each connected to a network 120. In implementations, a network 120 may include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN) or a wide area network (WAN)), a wired network (e.g., an Ethernet network), a wireless network (e.g., an 802.11 network or a WiFi network), a cellular network (e.g., a Long Term Evolution (LTE) network), routers, hubs, switches, server computers, and / or a combination thereof.

[0011] In some implementations, data store 112 is persistent storage capable of storing content items as well as data structures for tagging, organizing, and indexing the content items. Data store 112 may be hosted by one or more storage devices, such as main memory, magnetic or optical storage-based disks, tapes, or hard drives, NAS, SAN, and so on. In some implementations, data store 112 may be a network-attached file server, while in other embodiments, data store 112 may be another type of persistent storage, such as an object-oriented database, a relational database, and so on, which may be hosted by platform 102 or one or more different machines coupled to platform 102 via network 120.

[0012] The application hosting platform 102 may be configured to host files of one or more applications (e.g., application 130A, application 130B, etc.) provided by an application developer (e.g., via the application developer platform 104). The application developer platform 104 may be used by an application developer (e.g., a user, a company, an organization, etc.). For example, an application developer may be a video game developer who develops a video game (represented by application 130) for users to interact with client devices 108. The application hosting platform 102 may provide users with access to an application 130 (or an instance of an application 130) provided by the application developer platform 104 via a respective client device 108A-N.For example, application hosting platform 102 may enable a user to consume, upload, download, and / or search for applications 130. In some embodiments, application hosting platform 102 may include a website (e.g., one or more web pages) or a client application or component that may be used to provide users with access to applications 130. In some embodiments, each application 130 may consist of generic data 132 (e.g., data without user data) and user data 134—e.g., generic data 132A and user data 134A of application 130A, generic data 132B and user data 134B of application 130B, etc.In at least one embodiment, application hosting platform 102 may be an example of a cloud-hosted gaming service platform, a cloud-hosted collaborative content creation platform for heterogeneous content creation applications, a video streaming hosting platform, a testing platform for simulated or augmented content, a machine learning training platform, a machine learning deployment platform, or a video conferencing hosting platform. In at least one embodiment, application 130 (or an instance of application 130) may be an example of a gaming application, a video conferencing application, a content creation application, a cloud-hosted application, a collaborative content creation application, a cloud-hosted collaborative content creation application, a video streaming application, a machine learning application, or a simulation application.

[0013] In some embodiments, server 106 may host a virtualized computing environment 160 that executes an instance of application 130. For example, server 106 may be a computer system that includes one or more physical devices (e.g., a processing device (e.g., a GPU), memory, one or more I / O devices, etc.) and a hypervisor and / or a host operating system that manages one or more virtualized computing environments 160. A virtualized computing environment 160 may, for example, correspond to a virtual machine executing a guest operating system and one or more guest applications that include an instance of application 130, or a container that executes an application, such as an instance of application 130. One or more servers 106 may be deployed, and each server 106 may host one or more virtualized computing environments 160.In some embodiments, each server 106 may correspond to computer system 900 and / or computer system 1000 described with reference to FIG. Fig. 9 and Fig. 10 are described.

[0014] The application hosting platform 102 may include an application load manager 150 that enables staged loading of application data (generic data 132A and user data 134A) onto the virtualized computing environment 160 to reduce the time between the selection of the application 130A or 130B and the execution of an instance of the application 130A or 130B for a user, as explained in more detail herein. At least some of the generic data 132A and user data 134A may be displayed via a user interface (UI) on each client device accessing an instance of a respective application 130. The amount of generic data 132 and user data 134 may be specified for the application 130 by an application developer via the application developer platform 104.A user of the respective client device 108 may interact with the instance of the application 130 by intervening through a GUI provided by the application hosting platform 102, with an instance of the application 130 loaded with the generic data 132 and user data 134. The GUI of the application hosting platform 102 may be presented by a client component of the application hosting platform 102 or rendered by a web browser hosted by the client device 108.

[0015] The virtualized computing environment 160 may be instantiated to facilitate execution of the application instance 130 for access by the client device 108, and may be deconstructed after termination of the application instance, as requested by a user of the client device 108, according to embodiments provided herein. For example, a user accessing the application instance via the application hosting platform GUI on the client device 108 may log out of an account associated with the application 130 hosted by the application hosting platform 102. Upon detecting that the user has "logged out" of the associated account, the application load manager 150 may transmit a deconstruction request to the server 106, which may cause a hypervisor to deconstruct the virtualized computing environment 160.

[0016] A user of a respective client device 108 may engage (e.g., consume, interact, etc.) with the application 130 (e.g., via the application hosting platform GUI) loaded with the generic data 132 and user data 134 to progress through the application via the respective client device 108. In one illustrative example, applications 130A and 130B may be video game applications (e.g., game applications) developed by a video game developer. In another illustrative example, applications 130A and 130B may be content or asset creation applications of a cloud-hosted, collaborative content creation platform. Generic data 132 and user data 134 of a respective video game application 130 may be presented on an application hosting platform GUI on a client device 108 for consumption by a user of the client device 108.In some embodiments, generic data 132 may include assets, textures, illustrations of the application 130, background graphics, title screens, main menu screens, memory allocation of the game application 130 on the client device 108, shaders, etc. In some embodiments, user data 134 may include data that the application 130 loads specifically for a particular client device 108 that has selected the game application 130, e.g., for a specific user. For example, user data 134 may include specific user settings (e.g., resolution or shader settings), custom user content (e.g., customizations to a character in a game made by the user), custom key bindings, etc. Accordingly, a user may tailor the experience of running the game application 130 to their particular client device 108.

[0017] Client devices 108 may include devices including, but not limited to, televisions, smartphones, mobile phones, personal digital assistants (PDAs), portable media players, netbooks, laptops, electronic book readers, tablet computers, desktop computers, set-top boxes, software consoles, and the like. As discussed above, each client device 108 may include a client component of the application hosting platform 102 (or a web browser) that provides a graphical user interface (GUI) through which a user of the client device 108 may request execution of the application 130. The GUI may provide a rendered version of the generic data 132 and user data 134 for presentation during runtime of the application 130 and may allow the user to provide input during runtime of the application 130.

[0018] In some embodiments, server machine 106 may be separate from a server machine supporting application hosting platform 102. In other embodiments, server machine 106 may be part of application hosting platform 102. In some embodiments, one or more server machines 106, application hosting platforms 102, application developer platforms 104, and data storage 112 may be part of a cloud environment that client devices 108A-N may access via network 120.

[0019] Fig. Figure 2 illustrates a block diagram of a cloud environment 200, according to at least one embodiment. In some embodiments, the cloud environment 200 includes an application hosting platform 102, a login platform 250, and one or more servers 106, each providing one or more virtual computing environments 160. The client device 108 is connected to the cloud environment via the network 120, as described with reference to Fig. 1. In some embodiments, the login platform 250 may include an account manager 205, an account linking component 215, and an identity manager 210. The application hosting platform 102 may include an application load manager 150, which includes a scheduler 225 and a software application service 230. The application hosting platform 102 may also include a game application engine 240 and an application file repository 260.

[0020] In some embodiments, the account linking component 215 may link an account of a user of the client device 108 with an account associated with the application hosting platform 102. In some embodiments, the account linking component 215 may also determine whether an account of the user of the client device 108 associated with an application (e.g., the application 130, as described with reference to Fig. 1), or whether the user is "logged in." In at least one embodiment, if the user's account associated with application 130 is not linked, account linking component 215 may facilitate linking the account. In at least one embodiment, if the user's account associated with application 130 is linked, account linking component 215 may store the respective login credentials or access and refresh tokens (e.g., tokens used to provide a user with access to application 130). In some embodiments, account linking component 215 may link or maintain login credentials of many different users for a number of applications 130 hosted by application hosting platform 130.

[0021] In at least one embodiment, account manager 205 may manage an account associated with application 130 for a user of client device 108. For example, account manager 205 may provide a UI that enables the user of client device 108 to log into an account associated with application 130.

[0022] In at least one embodiment, the login platform 250 may include a unique account manager 205 for each unique application 130 hosted at the application hosting platform 102. In some embodiments, the identity manager 210 may validate (e.g., check) to ensure that the user's credentials are associated with an account of the application 130. That is, the identity manager 210 may allow the user to access their account associated with the application 130.

[0023] The application hosting platform 102 may include the application load manager 150, which may enable a staged loading of an instance of the application 130 onto the virtualized computing environment 160, and the application file repository 260, which stores files of various applications registered with the application hosting platform 102. In some embodiments, the application hosting platform 102 may cause an instance of the application 130 on the virtualized computing environment 160 to stream the application content to the client device 108, e.g., to the application hosting platform (AHP) GUI, as described with reference to Fig. 1. In one embodiment, application 130 may be an example of a gaming application (e.g., a video game) or a collaborative content creation platform or application. In such examples, virtualized computing environment 160 may store or load an instance of the gaming application. The instance of the gaming application may stream game content to client device 108 when a user of the client device initiates a session.

[0024] In at least one embodiment, the application load manager 150 of the application hosting platform 102 may include a scheduler 225. In one embodiment, the scheduler 225 may be configured to initiate or launch an instance of a gaming application 130 for a user of the client device 108. In one embodiment, the scheduler 225 may issue a request to allocate (e.g., create) a virtualized computing environment 160 at the server 106. For example, the scheduler 225 may initiate the creation of the virtualized computing environment 160 by sending a request to a virtual system manager (which manages the creation, deconstruction, etc., of virtualized computing environments 160 via the server 106) or directly to a hypervisor or host operating system of the server 106.In some embodiments, the scheduler 225 may also send a notification to the software application service 230, which may load an instance of the game application 130 onto the virtualized computing environment 160 in a preload mode.

[0025] In at least one embodiment, the application 130 is integrated with an application hosting platform (AHP) API plugin 235 (e.g., a designated software development kit (SDK)) that may be configured to communicate with the application hosting platform 104 via a predefined set of API commands to launch and / or load an instance of the gaming application 130 on the virtualized computing environment 160. In one embodiment, the AHP API plugin 235 may be configured to determine when a software application 130 is preloaded and fully loaded. In some embodiments, the application hosting platform 130 may have a unique AHP API plugin for each software application 130 it hosts. Alternatively, a common AHP API plugin may be operable with all software applications hosted / registered with the application hosting platform 102.

[0026] As with reference to Fig. 1, a software application 130 may include generic data and user data (e.g., the generic data and optionally some of the user data may be stored in the application file repository 260). As described herein, the application hosting platform may cause a software application 130 to be preloaded before a user of the client device 108 initiates a session. In such embodiments, the application hosting platform 102 may provide instructions to launch and preload the software application 130. In at least one embodiment, the application hosting platform 102 may enable loading of most (or all) of the generic data associated with the software application 130 before a user initiates (e.g., launches) the software application 130.This may allow the user to quickly begin streaming the content of an instance of the software application 130 to their client device 108 and enhance the overall user experience.

[0027] For example, scheduler 225 may issue a request to allocate (or create) a virtualized computing environment 160 in which to preload a gaming application 130. In some embodiments, scheduler 225 may request to allocate multiple different virtualized computing environments 160—e.g., so that multiple users initiating sessions at different times can access a preloaded instance of gaming application 130. In one embodiment, the number of virtualized computing environments 160 that scheduler 225 requests to allocate to a given gaming application 130 may be based on heuristics. For example, in one embodiment, scheduler 225 may analyze telemetry data (e.g.,collected by the game application engine 240 or another component) indicating an average duration that a virtualized computing environment 225 for a respective software application 130 is inactive or a number of users unable to access a pre-loaded instance of the software application 130. In one embodiment, the scheduler 225 may request to additionally allocate a virtualized computing environment 220 for a respective software application 225 when a number of users unable to access a pre-loaded instance of the software application 130 exceeds a threshold number, e.g., one (1).For example, if the number of users attempting to run the software application is greater than the number of virtualized computing environments 160 storing a pre-loaded instance of the software application, the application hosting platform 102 may allocate additional virtualized computing environments for the software application. In some embodiments, the threshold number may be based on how popular (e.g., how many users request to launch) the software application 130 is. In another embodiment, the scheduler 225 may decrease the number of allocated virtualized computing environments 160 for a given software application 130 if an average inactive period exceeds a threshold number—e.g., pre-loaded instances of the software application 130 remain inactive for a relatively long time (e.g., for at least a threshold period).

[0028] In one embodiment, after a virtualized computing environment 160 is allocated for a preloaded instance of the software application 130, the application hosting platform 102 may communicate with the software application 130 to initiate the loading of generic data. Upon loading the generic data, the AHP API plug-in 235 may notify the application hosting platform 102 that the instance of the software application 130 is preloaded. In such embodiments, the virtualized computing environment 160 may remain inactive until a user initiates a session. In some embodiments, when the user initiates the session, the application hosting platform 102 may facilitate the loading of user data onto the virtualized computing environment 220. Accordingly, the instance of the software application 130 on the virtualized computing environment 160 may be fully loaded and begin (e.g.,game or graphical) content of the instance of the software application 130 to the user's client device 108.

[0029] In some embodiments, the application hosting platform 102 may use the game application engine 240 to determine when an instance of a game application 130 has finished preloading, rather than receiving a notification from the AHP API plug-in 235. For example, the game application engine 240 may use one or more machine learning models trained to predict when the instance of the game application 130 has finished preloading. In some embodiments, the machine learning model may be trained using historical data indicating how long an application with certain characteristics (e.g., the size of application files, the type of content generated by the application, the graphics and sound effects used, etc.) takes to preload under certain network conditions.Alternatively or additionally, the machine learning model may be trained specifically for the software application 130. In some instances, the game application engine 240 may determine when the software application 130 is finished preloading based on detecting when the software application 130 reaches a main menu screen, e.g., a title sequence. Over time, the game application engine 240 may collect this data indicating how long previously spawned instances of the software application 130 took to preload under certain network conditions and provide this collected data as input data to train (or retrain) the machine learning model for the software application 130. In such embodiments, the game application engine 240 may use the trained machine learning model to predict when the software application will preload, e.g.,Determine a duration after which the game application will be preloaded. If the software application 130 undergoes an update or the duration until launch changes, the machine learning model can be retrained. Accordingly, the game application engine 240 can continuously improve its prediction accuracy as the software application is preloaded. By utilizing the game application engine 240, the application hosting platform 102 can allocate virtualized computing environments 160 for a particular software application more efficiently than waiting for notifications from the AHP API plug-in 235.

[0030] In one embodiment, once a number of virtualized computing environments 160 are pre-loaded for a respective software application, users initiating a session may access a pre-loaded instance of the software application 130 in a first-in, first-out scheme (e.g., on a first-come, first-served basis). In other embodiments, once a number of virtualized computing environments 160 are pre-loaded for a respective software application 325, users initiating a session may access the pre-loaded instance of the software application 130 in a tiered system, e.g., premium users may access the pre-loaded instance of the software application 130 before other users.

[0031] Additional details regarding the process of preloading the software application 130 and the set of APIs used are described with reference to Fig. 3-5 described.

[0032] Fig. 3 illustrates an example diagram of preloading a software application according to at least one embodiment. For example, diagram 300 illustrates preloading a software application with generic data before a user initiates a session to launch the software application. Diagram 400 may be performed by processing logic including hardware, software, firmware, or any combination thereof. In at least one embodiment, diagram 300 includes operations performed by cloud environment 200, including application hosting platform 102, application 130, application hosting platform (AHP) API plug-in 235, software application service 230, and scheduler 225, as described with reference to Fig. 2. Although shown in a particular sequence or order, unless otherwise noted, the order of the processes may be modified. Thus, the illustrated embodiments should be understood merely as examples, and the illustrated processes may be performed in a different order, and some processes may be performed in parallel. Additionally, one or more processes may be omitted in various embodiments. Thus, not all processes are required in every embodiment. Other diagrams illustrating preloading of a gaming application are possible.

[0033] At operation 305, the software application 130 may begin an initialization procedure using the AHP API plug-in 235. In at least one embodiment, the application hosting platform 102 may integrate the AHP API plug-in (e.g., a designated SDK (software development kit)) 235 into the software application to enable the software application to start in preload mode. That is, the software application may have a startup sequence (e.g., an initialization sequence) and an order in which it loads files. The application hosting platform 102 may integrate the AHP API plug-in 235 to modify certain sequences to load as much generic data as possible when starting in preload mode, e.g., sending the initialization request to the application hosting platform 102 before allocating virtualized computing environments 160.In some embodiments, the AHP API plugin 235 may also be configured to use a specific mechanism to request the software application to launch in preload mode. For example, based on information provided by the application developer platform 104 (when registering the software application with the application hosting platform 102), the AHP API plugin 235 may be configured to request launch in preload mode using a CLI command, a flag setting (e.g., in the application's configuration file), or confirmation that the software application is present in the cloud environment.

[0034] At operation 310, the software application 130 may communicate with the AHP API plug-in 235 to confirm that the software application will run in a cloud environment. For example, the application developer platform 104 may develop the software application to be played in both the cloud environment and non-cloud environments (e.g., loaded locally)—e.g., the application developer may develop the software application for different contexts. In some embodiments, for each context (e.g., for different computing devices or consoles), the software application may include different settings, launch sequences, etc. Accordingly, by confirming that the software application will run in the cloud environment, the software application will use the correct settings identified for the cloud environment 200.

[0035] At operation 315, the AHP API plug-in 235 may confirm to the software application 130 (e.g., using an API) that the software application is running in the cloud environment. In some embodiments, the AHP API plug-in 235 may return a "true" value if the software application 130 is running in a cloud environment and a "false" value if the software application 130 is not running in a cloud environment (e.g., running on the client device). In some embodiments, the AHP API plug-in 235 may also communicate with the software application 130 that it should be launched in preload mode upon sending the "true value." For example, the AHP API plug-in 235 may issue the command-line argument or the flag-on-disc at operation 315 to initiate the launch of the game application based on the initialization at operation 305.In embodiments where the software application is launched in preload mode based on being in the cloud environment, the software application 130 may begin launching before the AHP API plug-in 235 communicates the "true" value.

[0036] At operation 320, the software application 130 may begin loading generic data (e.g., from the application file repository 260) at the virtualized computing environment 160. In one embodiment, the generic data may include assets, textures, illustrations of the software application, background graphics, title screens, main menu screens, memory allocation of the software application on the client device, shaders, etc. for the software application—all or most of the data, excluding user data. The amount of generic data versus user data (e.g., a percentage of data that is generic data) may be unique for each software application and determined by the application developer.

[0037] At operation 325, the software application 130 may transmit an indication (e.g., via an API) that preloading is complete. In one embodiment, the software application 130 may issue a message via an API (e.g., RegisterSessionInitCallback or session-initialized callback) indicating that a session may start and the software application 130 may enter an inactive mode to await a callback to resume loading the remaining data—e.g., the user data. In some embodiments, the AHP API plug-in 235, a game application engine, or the application hosting platform 102 may predict when the preloading of the software application will be complete (e.g., based on machine learning), as described with reference to Fig. 2. In such embodiments, the AHP API plug-in 235 or the application load manager 150 may determine that the preloading of the software application has occurred without communicating an API message from the software application 130—e.g., the application hosting platform may forego operations 325 and 330.

[0038] At operation 330, the AHP API plug-in 235 may notify the software application service 230 that preloading of the software application is complete. In some embodiments, the software application service 230 may also notify the scheduler 225 that preloading of the software application has occurred. At operation 330, the preloaded instance of the software application may be ready for access by a user.

[0039] At operations 335, 340, and 345, the software application 130 and the AHP API plug-in 235 may be inactive. In some embodiments, the virtualized computing environment 160 hosting the instance of the preloaded game application may also be inactive with respect to the preloaded instance of the game application while waiting for a user to initiate a session and continue loading the remainder of the game application.

[0040] At operation 350, the scheduler 225 may indicate to the software application service 230 that a user is initiating a session of the gaming application. That is, a user may "log in" to their account and identify the gaming application for execution—e.g., select the gaming application to play. Additional details regarding the user interaction are described with reference to Fig. 4 and Fig. 5 described.

[0041] At operation 355, the software application service 230 may indicate to the AHP API plug-in 335 to initiate a user session of the game application.

[0042] At operation 360, the AHP API plug-in 335 may communicate a message to the software application 104 (e.g., via an API callback). In at least one embodiment, the AHP API plug-in 335 may transmit a message to the software application 130 to resume the operation—e.g., of the preloaded software application at the virtualized computing environment 160. In such embodiments, the AHP API plug-in 235 may communicate a message (e.g., API SessionIntCallback) indicating to resume the previously preloaded software application session. In some embodiments, the AHP API plug-in 235 may also indicate to the software application 130 to load the remaining data (e.g., the user data). Additional details regarding the communication of user data are provided with reference to Fig. 4 and Fig. 5 described.

[0043] At operation 365, the software application may load user data for the software application. In at least one embodiment, the software application may use the user data to load it to its title or main menu screen. That is, the software application 130 may continue loading the data (including user data) until it is ready to be played by a user of a client device 108.

[0044] At operation 370, the software application 130 may communicate that it is ready for the AHP API plug-in 235. In at least one embodiment, the software application 130 may communicate via an API (e.g., AppReady) to notify the AHP API plug-in 235 that the software application has been successfully loaded and is ready to be executed by a user.

[0045] At operation 375, the AHP API plug-in 235 may notify the software application service 230 that the software application is loaded and ready for execution by a user.

[0046] At operation 380, the software application service 230 may request to start streaming graphical or interface content of the instance of the software application. In at least one embodiment, the software content may be streamed to a client device 108. In some embodiments, the client device 108 may be associated with the user who initiated the session. In at least one embodiment, the user may not see a stream until the software application is ready to interact with, e.g., until the main menu or title sequence is loaded. In at least one embodiment, the overall user experience may be improved because the wait time for the user is reduced because the generic data is preloaded and the user is not shown the game until the software application is ready to be played.

[0047] Fig. 4 illustrates an example diagram of preloading a software application before a user "logs in" to an account, according to at least one embodiment. For example, a diagram 400 illustrates preloading before or as a user begins to access an account associated with the software application. The diagram 400 may be performed by processing logic comprising hardware, software, firmware, or any combination thereof. In at least one embodiment, the diagram 400 includes operations performed by the client 108 and the cloud environment 200, which may include the login platform 250 (the account manager 205, the identity manager 210, the account linker 215), the application hosting platform 102 (the software application service 230 and the scheduler 225), and the software application 130 with the AHP API plug-in 235 (e.g.,an instance of the software application with the AHP API plug-in on the virtualized computing environment 160), as described with reference to . Fig. 2. Although shown in a particular sequence or order, unless otherwise noted, the order of the processes may be modified. Thus, the illustrated embodiments should be understood merely as examples, and the illustrated processes may be performed in a different order, and some processes may be performed in parallel. Additionally, one or more processes may be omitted in various embodiments. Thus, not all processes are required in every embodiment. Other diagrams illustrating preloading of a software application are possible.

[0048] At operation 405, client device 108 and account linking component 215 may communicate to determine whether an account of a user of client device 108 is linked to the application hosting platform. In one embodiment, the user may request to launch a software application at client device 108. In such embodiments, client device 108 may check for account linking with account linking component 215. In one embodiment, account linking component 215 may determine that there is an account linking. In such embodiments, client device 108 may indicate (via a UI) that there is no account linking with the user. In some embodiments, account linking component 215 may determine that there is an account linking.That is, the account linking component 215 may determine whether a user's account is either stored or has previously been used to access the software application. In such examples, the account linking component 215 may proceed to operation 415.

[0049] At operation 410, a user account of client device 108 may be linked to application hosting platform 102 and software application 130. In one embodiment, upon determining that no link exists, client device 108 may render a UI that allows a user to select an option, enter their login credentials, and link their account. In some embodiments, client device 108 may invoke account linking via an API that communicates with account manager 205. In such embodiments, client device 108 may request a redirect URI (universal resource identifier) ​​that allows the user to enter their information.In some embodiments, the account manager 205 may redirect the client device 108 to display a link (a website link or a web user interface (UI)) to enable the user to log into their account associated with the software application. In such embodiments, the credentials (e.g., information) are sent to the identity manager 210. In some embodiments, the identity manager 210 may be configured to check or validate credentials and received information regarding a user's account. For example, the identity manager 210 may validate the credentials received from the user via the web UI. In some embodiments, if the account information is correct, the identity manager 210 may grant access to the account and generate refresh tokens.In some embodiments, if the account information is incorrect, the identity manager 210 may notify the user via the client device 108 that the information was incorrect.

[0050] During operation 410, the identity manager 210 may transmit a notification to the account linking component that the information provided by the user is correct. In some embodiments, the notification may include access and refresh tokens.

[0051] At operation 415, the account linking component 215 may store the access and refresh tokens. In at least one embodiment, by storing the access and refresh tokens, the account linking component 215 may link the user account to the software application and the application hosting platform.

[0052] At operation 420, a user may be notified that their account is linked to the software application and the hosting platform. For example, once the account linking component 215 determines the account information and / or the credentials are stored, the account linking component 215 may return the account name and token expiration (e.g., the access token expiration) to the client device 108. In response to receiving the account name, the client device 108 may cache the account link and account information. In such embodiments, the user may access the software application more quickly because the account information was previously provided and stored. In response to caching the account information, the client device 108 may display a UI that allows the user to see that the account is successfully linked.

[0053] In some embodiments, operations 425-445 may be performed prior to or concurrent with the user linking their account with the software application and the application hosting platform. That is, the application hosting platform may enable pre-loading of an instance of the software application (as described with reference to Fig. 2 and Fig. 3) before a user begins to initiate a session. As described with reference to Fig. 2 and Fig. 3, the scheduler may request to allocate a preload for an instance of a software application. In at least one embodiment, the request to allocate the preload may be based on heuristics, as described with reference to Fig. 2. In some embodiments, the application hosting platform may request to allocate multiple pre-loads—e.g., a single software application may be pre-loaded multiple times across multiple virtualized computing environments 160.

[0054] At operation 430, the software application service 230 may launch the software application in a preload mode via the AHP API plug-in 235. As described with reference to Fig. 4, the software application can be started by the AHP API plug-in 235 using a CLI command, a flag setting (in the application's configuration file), or an acknowledgment that the software application is running in the cloud environment.

[0055] At operation 435, the virtualized computing environment 160 may be preloaded with all (or most) of the generic data of the software application - e.g., the application development platform may load generic data onto the instance of the software application at the virtualized computing environment 160.

[0056] At operation 440, the instance of the software application may go idle on the hosting platform. In at least one embodiment, the instance of the software application may go idle and wait for a user to initiate a session. Because the instance of the software application is preloaded with the generic data, the loading time after the user initiates the session is reduced, improving the overall user experience.

[0057] At operation 445, the software application may transmit an indication (e.g., via an API message) that the software application is preloaded and waiting for a callback when a user initiates a session, as described with reference to Fig. 3 described.

[0058] Fig. 5 illustrates an example diagram for preloading a software application and loading user data, according to at least one embodiment. For example, diagram 500 illustrates preloading before a user initiates a session and subsequent loading of user data. The diagram 500 may be performed by processing logic comprising hardware, software, firmware, or any combination thereof. In at least one embodiment, the diagram 500 includes operations performed by the client 108 and the cloud environment 200, which includes the login platform 250 (the account manager 205, the identity manager 210, the account linker 215), the application hosting platform 102 (the software application service 230 and the scheduler 225), and the software application 130 with the AHP API plug-in 235 (e.g., the instance of the software application with the AHP API plug-in on the virtualized computing environment 160), as described with reference to Fig. 2. Although shown in a particular sequence or order, unless otherwise noted, the order of the processes may be modified. Thus, the illustrated embodiments should be understood merely as examples, and the illustrated processes may be performed in a different order, and some processes may be performed in parallel. Additionally, one or more processes may be omitted in various embodiments. Thus, not all processes are required in every embodiment. Other diagrams illustrating preloading of a software application are possible.

[0059] At operation 505, the application hosting platform 102 may launch an instance of a software application in a preload mode, as described with reference to operations 425-445 of Fig. 4. That is, the scheduler 225 of the application hosting platform 102 may instruct the scheduler 225 to allocate a virtualized computing environment (e.g., a running virtual machine (VM) or add a new VM) for an instance of the software application 130 and to launch and preload an instance of the gaming application 130 by loading generic data. The software application 130 may load the generic data, register for a session callback with the AHP API plug-in 235, and then go idle to wait for an API session callback from the AHP API plug-in 235. In some embodiments, the virtualized computing environment 160 may notify the scheduler 225 that it is available for a user session and transition to an idle state.

[0060] At operation 510, a user may initiate a session of the software application 130 and verify their account information for launching the software application. For example, a user may initiate launch of a software application on a client device 108—e.g., request to launch a software application via a UI.

[0061] In response to initiating the launch, the client device 108 may present the user with a loading UI—e.g., a loading screen, a notification that the software application has begun loading, etc. Additionally, in some embodiments, the client device 108 may check a cache (e.g., a local cache) to see if a user account is stored based on a previous account linking, as described with reference to Fig. 4. In some embodiments, if the client device 108 cannot find an account in the cache, the user may be prompted to enter their login credentials, as described with reference to operation 410 of Fig. 4. In at least one embodiment, the client device 108 may find the account information in the cache. In such embodiments, the client device 108 may communicate with the scheduler 225 of the application hosting platform 102. For example, the client device 108 may request to launch the instance of the software application with the user account, e.g., via an account-associated flag or an indication to load the software application with information associated with the user account. In response to receiving the flag, the scheduler 225 may request an exchange code from the account linking component to receive the information associated with the user account, e.g., user data.

[0062] During operation 510, in some embodiments, the account linking component 215 may redeem stored access and refresh tokens with an identity manager 210 to access information associated with the user account. That is, as described with reference to operation 415 of Fig. 4 describes that the account linking component 215 may store access and refresh tokens when a user "logs in" to their account. In some embodiments, the account linking component 215 may access the access and refresh tokens to re-access the account information. In some embodiments, in response to receiving the access and refresh tokens, the identity manager 210 may validate the access and refresh tokens, generate an exchange code, and generate new access and refresh tokens. That is, the identity manager 210 may verify that the tokens received from the account linking component 215 are associated with the user account—e.g., the information and credentials are correct.Once the identity manager 210 validates the tokens of the account linking component 215, the identity manager 210 may send the generated exchange code and the new access and refresh tokens to the account linking component. In some embodiments, the account linking component may store the new access and refresh tokens and send the exchange code to the scheduler 225. Accordingly, the application hosting platform 102 may validate the user account and access the user data associated with the respective launched software application.

[0063] At operation 515, the scheduler 225 may request to start a session with the software application for the user. In some embodiments, the scheduler 225 may send a notification to the game application service 230 to start the session with information associated with the user, e.g., user data.

[0064] At operation 520, the software application service may instruct the AHP API plug-in 235 to communicate with the software application 130 to initiate a session for the user and load the user data. In some embodiments, the software application service maintains a list of preloaded instances of the software application 130 on one or more virtualized computing environments 160, selects one of the preloaded instances from the list, identifies the corresponding AHP API plug-in 235 on the respective virtualized computing environment 160, and instructs it to communicate with the associated instance of the software application 130.

[0065] At operation 525, the AHP API plug-in 235 may communicate with the software application 130 to initiate a session of the software application using the preloaded instance of the software application. For example, the AHP API plug-in 235 may communicate an API session callback (e.g., SessionInitCallback) to the software application. In some embodiments, the AHP API plug-in 235 may communicate the session callback to begin loading the user data onto the software application instance preloaded at operation 505, as described above. In some embodiments, the AHP API plug-in 235 may indicate to load the software application with the exchange code received from the software application service, for example, to load the software application with the user data.

[0066] At operation 530, the software application may send the exchange code to the identity manager to log into the user's account. In some embodiments, the software application may access the user's account to obtain user data, e.g., specific user settings (e.g., resolution or shader settings), custom user content (e.g., customizations to a character in a game made by the user), custom key bindings, etc. In some embodiments, the software application may communicate with the identity manager 210 to verify the login credentials and access the user information.

[0067] At operation 535, the identity manager 210 may validate the exchange code. In at least one embodiment, the identity manager 210 associated with the software application may use the exchange code to initiate a session of the software application with the user data. For example, if the identity manager 210 verifies the exchange code (e.g., the exchange code matches the previously generated exchange code), the identity manager 210 may allow the software application to log into the user account and access the information.

[0068] At operation 540, the identity manager 210 may indicate to the software application that the exchange code is valid and that login to the user account was successful.

[0069] At operation 545, the software application may log into the user account and begin loading the user data. In at least one embodiment, the instance of the software application at the virtualized computing environment 160 may be loaded with specific user settings (e.g., resolution or shader settings), customized user content (e.g., customized adjustments to a character in a game made by the user), customized key bindings, etc. based on logging into the user account—e.g., the software application may customize the user experience based on user preferences and user account settings.

[0070] At operation 550, the software application may communicate with the AHP API plug-in 235 via an API (e.g., call AppReady). In some embodiments, the software application may notify the AHP API plug-in 235 that the instance of the software application at the virtualized computing environment 160 is ready for a user. That is, the software application may notify the AHP API plug-in 235 that both the user data and the generic data are loaded and that a user can access the main menu or title sequence of the software application.

[0071] At operation 555, the AHP API plug-in 235 may notify the software application service 230 that the instance of the software application is loaded and ready for the user.

[0072] At operation 560, the software application service 230 may initiate streaming of game or graphical content of the instance of the software application to the client device 108.

[0073] At operation 565, the client device 108 (e.g., the client component of the software application or the web browser) may display the streamed content of the instance of the software application to the user via a user interface (UI).

[0074] At operation 570, the user may begin playing the game, e.g., interacting with characters, advancing in storylines, playing in multi-player modes, etc. In some embodiments, by preloading most generic data before the user initiates or launches the software application, the wait time for the user is reduced and the overall user experience is improved.

[0075] Fig. 6 illustrates a flowchart of a method 600 for preloading software applications in a cloud computing environment. The method 600 may be performed by processing logic including hardware, software, firmware, or any combination thereof. In at least one embodiment, the method 600 is performed by the computing environment 200, as described with reference to Fig. 2-5. Although shown in a particular sequence or order, unless otherwise noted, the order of the processes may be modified. Thus, the illustrated embodiments should be understood merely as examples, and the illustrated processes may be performed in a different order, and some processes may be performed in parallel. Additionally, one or more processes may be omitted in various embodiments. Thus, not all processes are required in every embodiment. Other diagrams illustrating a method for preloading software applications are possible.

[0076] At operation 605, processing logic may send a preload request using an application hosting platform to preload a first portion of data for an application hosted using the application hosting platform. In one embodiment, processing logic may determine to allocate a number of virtualized computing environments to launch an instance of an application in a preload mode. In some embodiments, processing logic may determine the number of virtualized computing environments into which to preload the application based on an average duration of other virtualized computing environments where the preloaded portion is inactive. For example, processing logic may determine to allocate a smaller number of virtualized computing environments for the application if the inactive time is relatively long (e.g.,is below a threshold indicating that users are not running the application). In some embodiments, the preload request may be received before user input identifying the application for execution. That is, the processing logic may request the preload before a user selects the game for execution. In some embodiments, the first portion of data may be generic data—e.g., data with no data associated with a user request. In some embodiments, the processing logic may include a command-line interface or flag-on-disc in the first request to load the first portion of data.In some embodiments, the processing logic may transmit multiple preload requests using the application hosting platform to preload the first portion of data on multiple virtualized computing environments hosted by one or more computer systems on the cloud platform. In at least one embodiment, the application may include at least one of a gaming application, a video conferencing application, a content creation application, a cloud-hosted application, a collaborative content creation application, a cloud-hosted collaborative content creation application, a video streaming application, a machine learning application, or a simulation application.In some embodiments, the application hosting platform may comprise at least one of a cloud-hosted game service platform, a cloud-hosted collaborative content creation platform for heterogeneous content creation applications, a video streaming hosting platform, a testing platform for simulated or augmented content, a machine learning training platform, a machine learning deployment platform, or a video conferencing hosting platform.

[0077] At operation 610, processing logic using the application hosting platform may receive a first indication that the first portion of data for the application using the virtualized computing environment is preloaded. In some embodiments, the virtualized computing environment may transition to an inactive mode upon receiving the indication. That is, if the preloading has occurred and no user request is received—e.g., the application has not yet fully loaded—the processing logic may cause the virtualized computing environment to be placed in an inactive mode. In some embodiments, the processing logic may predict when the first portion of data for the application using the virtualized computing environment is preloaded.In such embodiments, the processing logic may monitor, store, and / or access average times it took to preload instances of the application at the virtualized computing environments and use this data to train a machine learning model. The processing logic may use the trained machine learning model to predict when the preload has occurred. In some embodiments, the processing logic may receive a third indication that the first portion of data is preloaded at the plurality of virtualized computing environments.

[0078] At operation 615, the processing logic may receive a user request to execute the application using the application hosting platform. In one embodiment, the processing logic may receive the user request upon receiving the first indication. In some embodiments, the user request may be associated with a user at a client device. In some embodiments, the processing logic may receive an indication from the application of an update to one or more files of the application prior to receiving the user request. In such embodiments, the processing logic may deconstruct the virtualized computing environment in response to receiving the indication that the one or more files associated with the application are updated and preload a second virtualized computing environment with the updated files.In some embodiments, the processing logic may receive a second user request to execute the application. In such embodiments, the processing logic may execute the application running on a second virtualized computing environment of the plurality of virtualized computing environments.

[0079] At operation 620, the processing logic, using the application hosting platform, may send a load request to load a second portion of data for the application onto the virtualized computing environment. In one embodiment, the second portion of data may be associated with user data, e.g., data associated with the user input or the user request. In at least one embodiment, the virtualized computing environment may transition from the inactive state to an active state to load the second portion of data. In some embodiments, the processing logic may also send a second load request to load the second portion of data for the application onto the second virtualized computing environment.

[0080] At operation 625, the processing logic, using the application hosting platform, may receive a second indication that the second portion of data for the application is loaded onto the virtualized computing environment. In one embodiment, the processing logic may receive an indication that the user data for the application is loaded onto the virtualized computing environment. In some embodiments, the second indication may also notify the processing logic that the application on the virtualized computing environment is ready to be launched, e.g., to engage a user. In some embodiments, the processing logic may receive a fourth indication that the second portion of data for the application is loaded onto the second virtualized computing environment.

[0081] At operation 630, the processing logic may cause the application to execute using the virtualized computing environment. As a result, the content of the application instance may be streamed to the user's device—e.g., the user may begin playing the application. In some embodiments, the processing logic may cause the application to execute on the second virtualized computing environment in response to the second user request.

[0082] Fig. 7A illustrates inference and / or training logic 715 used to perform inference and / or training operations associated with one or more embodiments. Details regarding inference and / or training logic 715 are described below in connection with Fig. 7A and / or Fig. 7B provided.

[0083] In at least one embodiment, the inference and / or training logic 715 may include, without limitation, code and / or data storage 701 to store feedforward and / or output weighting and / or input / output data and / or other parameters to configure neurons or layers of a neural network being trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, the training logic 715 may include or be wired to the code and / or data storage 701 to store graph code or other software to control the timing and / or order in which weighting and / or other parameter information is to be loaded to configure logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs)).In at least one embodiment, the code, such as graph code, loads weighting or other parameter information based on a neural network architecture to which the code corresponds to, onto the processor ALUs. In at least one embodiment, the code and / or data storage 701 stores the weighting parameters and / or input / output data of each layer of a neural network trained or used in connection with one or more embodiments during forward propagation of input / output data and / or weighting parameters during training and / or inferencing using aspects of one or more embodiments. In at least one embodiment, any portion of the code and / or data storage 701 may be included in other on-chip or off-chip data storage, including the L1, L2, or L3 cache or system memory of a processor.

[0084] In at least one embodiment, any portion of code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, code and / or data storage 701 may be cache memory, dynamic randomly addressable memory (DRAM), static randomly addressable memory (SRAM), non-volatile memory (e.g., flash memory), or other storage.In at least one embodiment, the choice of whether the code and / or code and / or data storage 701 is, for example, internal or external to a processor or consists of DRAM, SRAM, flash memory, or another type of storage may depend on the available on-chip storage versus off-chip storage, latency requirements of training and / or inference functions performed, the batch size of data used in inferring and / or training a neural network, or a combination of these factors.

[0085] In at least one embodiment, the inference and / or training logic 715 may include, without limitation, code and / or data storage 705 to store backward and / or output weights and / or input / output data corresponding to neurons or layers of a neural network trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, the code and / or data storage 705 stores weighting parameters and / or input / output data of each layer of a neural network trained in connection with one or more embodiments during backpropagation of input / output data and / or weighting parameters used during training and / or inference using aspects of one or more embodiments.In at least one embodiment, the training logic 715 may include or be wired to a code and / or data storage 705 to store graph code or other software to control the timing and / or order in which weight and / or other parameter information is to be loaded to configure logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs)). In at least one embodiment, the code, such as the graph code, loads weight or other parameter information to the processor ALUs based on a neural network architecture corresponding to the code. In at least one embodiment, any portion of the code and / or data storage 705 may be included with other on-chip or off-chip data storage, including in an L1, L2, or L3 cache or system memory of a processor.In at least one embodiment, any portion of code and / or data storage 705 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, code and / or data storage 705 may be cache memory, DR_AM, SRAM, non-volatile memory (e.g., flash memory), or other storage.In at least one embodiment, the choice of whether the code and / or data storage 705 is, for example, internal or external to a processor, or consists of a DR_AM, an SRAM, a flash memory, or another type of storage, may depend on the available on-chip versus off-chip storage, latency requirements of training and / or inference functions performed, the batch size of data used in inferring and / or training a neural network, or a combination of these factors.

[0086] In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be separate storage structures. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be the same storage structure. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be partially the same storage structure and partially separate storage structures. In at least one embodiment, any portion of code and / or data storage 701 and code and / or data storage 705 may be included with other on-chip or off-chip data storage, including a processor's L1, L2, or L3 caches or system memory.

[0087] In at least one embodiment, the inference and / or training logic 715 may include, without limitation, one or more arithmetic logic units (ALU(s)) 710, including integer and / or floating-point units, to perform logical and / or mathematical operations based at least in part on or specified by training and / or inference code (e.g., graph code), a result of which may generate activations (e.g., output values ​​of layers or neurons within a neural network) stored in the activation storage 720 that are functions of input / output and / or weighting parameter data stored in the code and / or data storage 701 and / or the code and / or data storage 705.In at least one embodiment, activations stored in activation storage 720 are generated according to linear algebraic and / or matrix-based mathematics performed by ALU(s) 710 in response to the execution of instructions or other code, using weight values ​​stored in code and / or data storage 705 and / or code and / or data storage 701 as operands along with other values, such as bias values, gradient information, moment values, or other parameters or hyperparameters, any or all of which may be stored in code and / or data storage 705 or code and / or data storage 701 or other storage on-chip or off-chip.

[0088] In at least one embodiment, the ALU(s) 710 is / are included in one or more processors or other hardware logic devices or circuits, whereas in another embodiment, the ALU(s) 710 may be external to a processor or other hardware logic device or circuit that uses it (e.g., a coprocessor). In at least one embodiment, the ALUs may be included within execution units of a processor or otherwise in a bank of ALUs that can be accessed by the execution units of a processor, either within the same processor or distributed among different processors of different types (e.g., central processing units, graphics processing units, fixed function units, etc.).In at least one embodiment, the code and / or data storage 701, the code and / or data storage 705, and the enable storage 720 may be located on the same processor or other hardware logic device or circuit, whereas in another embodiment, they may be located on different processors or other hardware logic devices or circuits, or in a combination of the same and different processors or other hardware logic devices or circuits. In at least one embodiment, any portion of the enable storage 720 may be included in other on-chip or off-chip data storage, including in an L1, L2, or L3 cache or system memory of a processor.Furthermore, the inference and / or training code may be stored with other code accessible to a processor or other hardware logic or circuitry, and may be retrieved and / or processed using fetch, decode, scheduling, execution, elimination, and / or other logic circuitry of a processor.

[0089] In at least one embodiment, the activation storage 720 may be a cache memory, a DRAM, an SRAM, a non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the activation storage 720 may be internal or external, in whole or in part, to one or more processors or other logic circuits. In at least one embodiment, the choice of whether the activation storage 720 is, for example, internal or external to a processor, or consists of a DRAM, an SRAM, flash memory, or another type of storage, may depend on the available on-chip storage versus off-chip storage, the latency requirements of the training and / or inference functions performed, the batch size of the data used in inferencing and / or training a neural network, or a combination of these factors.In at least one embodiment, the method described in . Fig. 7A may be used in conjunction with an application-specific integrated circuit (“ASIC”), such as Google’s Tensorflow® processing unit, a Graphcore™ inference processing unit (IPU), or a Nervana® processor (e.g., “Lake Crest”) from Intel Corp. In at least one embodiment, the inference and / or training logic 715 illustrated in Fig. 7A may be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware, such as data processing unit (“DPU”) hardware or field programmable gate arrays (“FPGAs”).

[0090] Fig. 7B illustrates inference and / or training logic 715 according to at least one or more embodiments. In at least one embodiment, the inference and / or training logic 715 may include, without limitation, hardware logic in which computational resources are dedicated or otherwise used exclusively in connection with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, the inference and / or training logic 715 may Fig. 7B may be used in conjunction with an application-specific integrated circuit (ASIC), such as Google's Tensorflow® processing unit, a Graphcore™ inference processing unit (IPU), or a Nervana® processor (e.g., "Lake Crest") from Intel Corp. In at least one embodiment, the inference and / or training logic 715 illustrated in Fig. 7B may be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware, such as data processing unit (“DPU”) hardware or field programmable gate arrays (FPGAs). In at least one embodiment, the inference and / or training logic 715 includes, without limitation, code and / or data storage 701 and code and / or data storage 705, which may be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, moment values, and / or other parameter or hyperparameter information. In at least one embodiment, Fig. 7B, each of the code and / or data storage 701 and the code and / or data storage 705 is associated with a dedicated compute resource, such as the compute resource 702 and the compute resource 706, respectively. In at least one embodiment, each of the compute resource 702 and the compute resource 706 includes one or more ALUs that perform mathematical functions, such as linear algebraic functions, only on information stored in the code and / or data storage 701 and the code and / or data storage 705, respectively, the result of which is stored in the enable storage 720.

[0091] In at least one embodiment, each of the code and / or data storage 701 and 705 and the corresponding computational resource 702 and 706 corresponds to different layers of a neural network, such that the resulting activation of a "storage / compute pair 701 / 702" of the code and / or data storage 701 and the computational resource 702 is provided as input to the "storage / compute pair 705 / 706" of the code and / or data storage 705 and the computational resource 706 to mirror the conceptual organization of a neural network. In at least one embodiment, each of the storage / compute pairs 701 / 702 and 705 / 706 may correspond to more than one layer of a neural network. In at least one embodiment, additional storage / compute pairs (not shown) may be included after or in parallel with storage / compute pairs 701 / 702 and 705 / 706 in inference and / or training logic 715.

[0092] Fig. Figure 8 illustrates an example data center 800 in which at least one embodiment may be used. In at least one embodiment, data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0093] In at least one embodiment, as in Fig. 8, the data center infrastructure layer 810 may include a resource orchestrator 812, clustered compute resources 814, and node compute resources ("node RRs") 816(1)-816(N), where "N" represents any positive integer. In at least one embodiment, the node RRs 816(1)-816(N) may include any number of central processing units ("CPUs") or other processors (including accelerators, field-programmable gate arrays (FPGAs), graphics processors, etc.), memory devices (e.g., dynamic read-only memory), storage devices (e.g., solid-state or disk drives), network input / output ("NW I / O") devices, network switches, virtual machines ("VMs"), power modules and cooling modules, etc. In at least one embodiment, one or more of the node RRs 816(1)-816(N) may be a server having one or more of the computing resources mentioned above.

[0094] In at least one embodiment, the grouped computing resources 814 may include separate groupings of node RRs housed in one or more frames (not shown), or multiple frames housed in data centers at various geographical locations (also not shown). Separate groupings of node RRs within grouped computing resources 814 may include grouped computing, networking, memory, or storage resources that may be configured or allocated to support one or more workloads. In at least one embodiment, multiple node RRs, including CPUs or processors, may be grouped within one or more frames to provide computing resources to support one or more workloads.In at least one embodiment, one or more frames may also include any number of power modules, cooling modules, and network switches in any combination.

[0095] In at least one embodiment, resource orchestrator 812 may configure or otherwise control one or more node RRs 816(1)-816(N) and / or grouped computing resources 814. In at least one embodiment, resource orchestrator 812 may include a software design infrastructure ("SDI") management entity for data center 800. In at least one embodiment, the resource orchestrator may include hardware, software, or some combination thereof.

[0096] In at least one embodiment, as in Fig. 8, the framework layer 820 includes a task scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, the framework layer 820 may include a framework to support software 832 of the software layer 830 and / or one or more applications 842 of the application layer 840. In at least one embodiment, the software 832 or the application(s) 842 may each include web-based service software or applications, such as those provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 820 may be, but is not limited to, some type of free and open source software web application framework, such as Apache Spark™ (hereinafter "Spark"), which may utilize the distributed file system 828 for large-scale data processing (e.g., "Big Data").In at least one embodiment, the task scheduler 822 may include a Spark driver to facilitate scheduling workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be capable of configuring various layers, such as the software layer 830 and the framework layer 820, including Spark and the distributed file system 828, to support large-scale data processing. In at least one embodiment, the resource manager 826 may be capable of managing clustered or grouped compute resources allocated or allocated to support the distributed file system 828 and the task scheduler 822. In at least one embodiment, the clustered or grouped compute resources may include a clustered compute resource 814 on the data center infrastructure layer 810.In at least one embodiment, the resource manager 826 may coordinate with the resource coordinator 812 to manage these allocated or assigned computing resources.

[0097] In at least one embodiment, the software 832 included in software layer 830 may include software used by at least portions of node RRs 816(1) through 816(N), clustered computing resources 814, and / or distributed file system 828 of framework layer 820. The one or more types of software may include, but are not limited to, Internet website search software, email virus scanning software, database software, and video content streaming software.

[0098] In at least one embodiment, the application(s) 842 included in the application layer 840 may include one or more types of applications used by at least portions of node RRs 816(1) through 816(N), clustered computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of applications may include, but are not limited to, any number of a genomics application, a cognitive computing application, and a machine learning application that includes training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in connection with one or more embodiments.

[0099] In at least one embodiment, any one of the configuration manager 824, the resource manager 826, and the resource coordinator 812 may implement any number and type of self-modifying actions based on any amount and type of data collected in any technically feasible manner. In at least one embodiment, the self-modifying actions may relieve a data center operator of the data center 800 from potentially making poor configuration decisions and potentially avoid underutilized and / or malfunctioning portions of a data center.

[0100] In at least one embodiment, data center 800 may include tools, services, software, or other resources to train one or more machine learning models, or to predict or infer information using one or more machine learning models according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model may be trained by calculating weighting parameters according to a neural network architecture using software and computing resources described above with respect to data center 800.In at least one embodiment, trained machine learning models corresponding to one or more neural networks may be used to infer or predict information using resources described above with respect to data center 800 using weighting parameters calculated using one or more training techniques described herein.

[0101] In at least one embodiment, the data center may use CPUs, application-specific integrated circuits (ASICs), GPUs, FPGAs, or other hardware to perform training and / or inference using the resources described above. Furthermore, one or more of the software and / or hardware resources described above may be configured as a service to enable users to train or perform inference on information, such as image recognition, speech recognition, or other artificial intelligence services.

[0102] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are described below in connection with Fig. 7A and / or Fig. 7B. In at least one embodiment, the inference and / or training logic 715 in the system of Fig. 8 for inference or prediction operations based at least in part on weighting parameters calculated using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0103] Such components can be used to generate synthetic data that mimics failure cases in a network training process, which can help improve the network's performance while limiting the amount of synthetic data to avoid overfitting.

[0104] Fig. 9 is a block diagram illustrating an example computer system, which may be a system 900 with interconnected devices and components, a system-on-a-chip (SOC), or some combination thereof, and formed with a processor that may include execution units to execute an instruction, according to at least one embodiment. In at least one embodiment, the computer system 900 may include, without limitation, a component, such as a processor 902, for employing execution units that include logic to perform algorithms on process data, according to the present disclosure, such as in the embodiment described herein.In at least one embodiment, computer system 900 may include processors such as the PENTIUM® processor family, Xeon™, Itanium®, XScale™ and / or StrongARM™, Intel® Core™, or Intel® Nervana™ available from Intel Corporation of Santa Clara, California, although other systems (including PCs with other microprocessors, engineering workstations, set-top boxes, and the like) may be used. In at least one embodiment, computer system 900 may run a version of the WINDOWS operating system available from Microsoft Corporation of Redmond, Washington, although other operating systems (e.g., UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0105] The embodiments may be used on other devices, such as handheld devices and embedded applications. Some examples of portable devices include cellular phones, Internet Protocol devices, digital cameras, personal digital assistants ("PDAs"), and handheld PCs. In at least one embodiment, embedded applications may include a microcontroller, a digital signal processor ("DSP"), a system on a chip, network computers ("NetPCs"), set-top boxes, network hubs, wide area network ("WAN") switches, or any other system capable of performing one or more instructions, according to at least one embodiment.

[0106] In at least one embodiment, computer system 900 may include, without limitation, a processor 902, which may include, without limitation, one or more execution units 908 to perform training and / or inference of a machine learning model according to the techniques described herein. In at least one embodiment, computer system 900 is a single-processor desktop or server system, however, in another embodiment, computer system 900 may be a multi-processor system. In at least one embodiment, processor 902 may include, without limitation, a complex instruction set computing ("CISC") microprocessor, a reduced instruction set computing ("RISC") microprocessor, a very long instruction word ("VLIW") microprocessor, a processor implementing a combination of instruction sets, or any other processor device, such as, for example, a digital signal processor.In at least one embodiment, the processor 902 may be coupled to a processor bus 910 that may transmit data signals between the processor 902 and other components in the computer system 900.

[0107] In at least one embodiment, processor 902 may include, without limitation, an internal Level 1 ("L1") cache ("cache") 904. In at least one embodiment, processor 902 may include a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache may be external to processor 902. Other embodiments may also include a combination of both internal and external caches depending on the particular implementation and requirements. In at least one embodiment, register file 906 may store various types of data in various registers, including, without limitation, integer registers, floating-point registers, status registers, and instruction pointer registers.

[0108] In at least one embodiment, execution unit 908, which includes, without limitation, logic to perform integer and floating-point operations, is also located in processor 902. In at least one embodiment, processor 902 may also include microcode ("uCode") read-only memory (ROM) that stores microcode for certain macroinstructions. In at least one embodiment, execution unit 908 may include logic to handle a compressed instruction set 909. In at least one embodiment, by incorporating a compressed instruction set 909 into an instruction set of a general-purpose processor 902, along with associated circuitry to execute instructions, operations used by numerous multimedia applications may be performed using compressed data in a general-purpose processor 902.In one or more embodiments, numerous multimedia applications may be accelerated and executed more efficiently by using the full width of a processor data bus to perform operations on compressed data, which may eliminate the need to transfer smaller units of data across the processor data bus to perform one or more operations on only one piece of data at a time.

[0109] In at least one embodiment, execution unit 908 may also be used in microcontrollers, embedded processors, graphics devices, DSPs, and other logic circuits. In at least one embodiment, computer system 900 may include, without limitation, a memory 920. In at least one embodiment, memory 920 may be implemented as a dynamic random access memory (DRAM) device, a static random access memory (“SRAM”) device, a flash memory device, or another storage device. In at least one embodiment, memory 920 may store instruction(s) 919 and / or data 921 represented by data signals that may be executed by processor 902.

[0110] In at least one embodiment, a system logic chip may be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip may include, without limitation, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for storing instructions and data and for storing graphics commands, data, and textures. In at least one embodiment, the MCH 916 may route data signals between the processor 902, the memory 920, and other components in the computer system 900, and may bridge data signals between the processor bus 910, the memory 920, and a system I / O 922.In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 may be coupled to memory 920 via a high-bandwidth memory path 918, and a graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port ("AGP") interconnect 914.

[0111] In at least one embodiment, computer system 900 may use system I / O 922, which is a proprietary hub interface bus, to couple MCH 916 to I / O controller hub ("ICH") 930. In at least one embodiment, ICH 930 may provide direct connections to some I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, without limitation, a high-speed I / O bus for connecting peripherals to memory 920, chipset, and processor 902. Examples may include, without limitation, an audio controller 929, a firmware hub (“flash BIOS”) 928, a wireless transceiver 926, a data storage device 924, a legacy I / O controller 923 including user input and keyboard interfaces 925, a serial expansion port 927, such as a universal serial bus (“USB”), and a network controller 934.The data storage device 924 may include a hard disk drive, a floppy disk drive, a CD-ROM device, a flash memory device, or other mass storage device.

[0112] In at least one embodiment, Fig. 9 a system comprising interconnected hardware devices or “chips”, whereas in other embodiments Fig. 9 may illustrate an exemplary system on a chip ("SoC"). In at least one embodiment, the devices may be interconnected using proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of computer system 900 are interconnected using Compute Express Link (CXL) interconnects.

[0113] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are described below in connection with Fig. 7A and / or Fig. 7B. In at least one embodiment, the inference and / or training logic 715 in the system of Fig. 9 for inference or prediction operations based at least in part on weighting parameters calculated using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0114] Such components can be used to generate synthetic data that mimics failure cases in a network training process, which can help improve the network's performance while limiting the amount of synthetic data to avoid overfitting.

[0115] Fig. 10 is a block diagram illustrating an electronic device 1000 for utilizing a processor 1010 according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example and without limitation, a notebook, a tower server, a rack server, a blade server, a laptop, a desktop, a tablet, a mobile device, a phone, an embedded computer, or any other suitable electronic device.

[0116] In at least one embodiment, system 1000 may include, without limitation, processor 1010 communicatively coupled to any number or type of components, peripherals, modules, or devices. In at least one embodiment, processor 1010 is coupled using a bus or interface, such as a 1°C bus, a System Management Bus ("SMBus"), a Low Pin Count (LPC) bus, a Serial Peripheral Interface ("SPI"), a High Definition Audio ("HDA") bus, a Serial Advance Technology Attachment ("SATA") bus, a Universal Serial Bus ("USB") (versions 1, 2, 3), or a Universal Asynchronous Receiver / Transmitter ("UART") bus. In at least one embodiment, Fig. 10 a system comprising interconnected hardware devices or “chips”, whereas in other embodiments Fig. 10 may illustrate an exemplary system on a chip (“SoC”). In at least one embodiment, the Fig. 10 may be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of Fig. 10 interconnected using Compute Express Link (CXL) interconnects.

[0117] In at least one embodiment, Fig. 10 a display 1024, a touch screen 1025, a touchpad 1030, a near field communications unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, an express chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash memory (“BIOS, FW-Flash”) 1022, a DSP 1060, a drive 1020, such as a solid state drive (“SSD”) or a hard disk drive (“HDD”), a wireless local area network unit (“WLAN”) 1050, a Bluetooth unit 1052, a wireless wide area network unit (“WWAN”) 1056, a global positioning system (GPS) 1055, a camera (“USB 3.0 camera”) 1054, such as a USB 3.0 camera and / or a low-power double data rate ("LPDDR") memory unit ("LPDDR3") 1015, implemented, for example, in an LPDDR3 standard. These components may each be implemented in a suitable manner.

[0118] In at least one embodiment, other components may be communicatively coupled to processor 1010 via previously discussed components. In at least one embodiment, an accelerometer 1041, an ambient light sensor ("ALS") 1042, a compass 1043, and a gyroscope 1044 may be communicatively coupled to sensor hub 1040. In at least one embodiment, a thermal sensor 1039, a fan 1037, a keyboard 1046, and a touchpad 1030 may be communicatively coupled to EC 1035. In at least one embodiment, a speaker 1063, a headset 1064, and a microphone ("mic") 1065 may be communicatively coupled to an audio unit ("Class-D audio codec and amplifier") 1062, which in turn may be communicatively coupled to DSP 1060. In at least one embodiment, the audio unit 1064 may include, for example and without limitation, an audio encoder / decoder ("codec") and a Class D amplifier.In at least one embodiment, a SIM card ("SIM") 1057 may be communicatively coupled to the WWAN unit 1056. In at least one embodiment, components such as the WLAN unit 1050 and the Bluetooth unit 1052, as well as the WWAN unit 1056, may be implemented in a next generation form factor (NGFF).

[0119] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are described below in connection with Fig. 7A and / or Fig. 7B. In at least one embodiment, the inference and / or training logic 715 in the system of Fig. 10 for inference or prediction operations based at least in part on weighting parameters calculated using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0120] Such components can be used to generate synthetic data that mimics failure cases in a network training process, which can help improve the network's performance while limiting the amount of synthetic data to avoid overfitting.

[0121] Fig. 11 is a block diagram of a processing system according to at least one embodiment. In at least one embodiment, system 1100 includes one or more processors 1102 and one or more graphics processors 1108, and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a large number of processors 1102 or processor cores 1107. In at least one embodiment, system 1100 is a processing platform embodied in a system-on-a-chip (SoC) integrated circuit for use in mobile, handheld, or embedded devices.

[0122] In at least one embodiment, system 1100 may include or be incorporated into a server-based gaming platform, a game console including a game and media console, a mobile gaming console, a handheld game console, or an online game console. In at least one embodiment, system 1100 is a mobile phone, a smartphone, a tablet computing device, or a mobile internet device. In at least one embodiment, processing system 1100 may also include, be coupled to, or integrated with a wearable device, such as a wearable smart watch device, a smart eyeware device, an augmented reality device, or a virtual reality device.In at least one embodiment, processing system 1100 is a television or set-top box device that includes one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0123] In at least one embodiment, one or more processors 1102 each include one or more processor cores 1107 to process instructions that, when executed, perform operations for system and user software. In at least one embodiment, each of one or more processor cores 1107 is configured to execute a specific instruction set 1109. In at least one embodiment, the instruction set 1109 may enable Complex Instruction Set Computing (CISC), Reduced Instruction Set Computing (RISC), or Very Long Instruction Word (VLIW) computing. In at least one embodiment, the processor cores 1107 may each process a different instruction set 1109, which may include instructions to enable emulation of other instruction sets.In at least one embodiment, the processor core 1107 may also include other processing devices, such as a digital signal processor (DSP).

[0124] In at least one embodiment, processor 1102 includes a cache memory 1104. In at least one embodiment, processor 1102 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory is shared by various components of processor 1102. In at least one embodiment, processor 1102 also uses an external cache (e.g., a Level 3 (L3) cache or Last Level Cache (LLC)) (not shown), which may be shared by processor cores 1107 using known cache coherence techniques. In at least one embodiment, register file 1106 is additionally included in processor 1102, which may include various types of registers for storing various types of data (e.g., integer registers, floating-point registers, status registers, and an instruction pointer register).In at least one embodiment, register file 1106 may include general-purpose registers or other registers.

[0125] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 for communicating communication signals, such as address, data, or control signals, between the processor 1102 and other components in the system 1100. In at least one embodiment, the interface bus 1110 may be a processor bus, such as a version of a Direct Media Interface (DMI) bus. In at least one embodiment, the interface 1110 is not limited to a DMI bus and may include one or more peripheral component interconnect buses (e.g., PCI, PCI Express), memory buses, or other interface buses. In at least one embodiment, the processor(s) 1102 include an integrated memory controller 1116 and a platform controller hub 1130.In at least one embodiment, the storage controller 1116 enables communication between a storage device and other components of the system 1100, while the platform controller hub (PCH) 1130 provides connections to I / O devices via a local I / O bus.

[0126] In at least one embodiment, memory device 1120 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase-change memory device, or some other memory device having suitable performance to serve as process memory. In at least one embodiment, memory device 1120 may operate as system memory for system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process. In at least one embodiment, memory controller 1116 is also coupled to an optional external graphics processor 1112 that can communicate with one or more graphics processors 1108 in processors 1102 to perform graphics and media operations.In at least one embodiment, a display device 1111 may be connected to the processor(s) 1102. In at least one embodiment, the display device 1111 may comprise one or more of an internal display device, such as in a mobile electronic device or a laptop device, or an external display device connected via a display interface (e.g., DisplayPort, etc.). In at least one embodiment, the display device 1111 may comprise a head-mounted display (HMD), such as a stereoscopic display device for use in virtual reality (VR) applications or augmented reality (AR) applications.

[0127] In at least one embodiment, the platform controller hub 1130 enables peripherals to connect to the storage device 1120 and the processor 1102 via a fast I / O bus. In at least one embodiment, the I / O peripherals include, without limitation, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, touch sensors 1125, and a data storage device 1124 (e.g., a hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 may be connected via a storage interface (e.g., SATA) or via a peripheral bus, such as a peripheral component interconnect bus (e.g., PCI, PCI Express). In at least one embodiment, the touch sensors 1125 may include touch screen sensors, pressure sensors, or fingerprint sensors.In at least one embodiment, the wireless transceiver 1126 may be a WiFi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or Long Term Evolution (LTE) transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and may be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, the network controller 1134 may enable network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to the interface bus 1110. In at least one embodiment, the audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, the system 1100 includes an optional legacy I / O controller 1140 for coupling legacy devices (e.g.,Personal System 2 (PS / 2) devices) to the system. In at least one embodiment, the platform controller hub 1130 may also be connected to one or more universal serial bus (USB) controllers 1142, interconnect input devices such as keyboard and mouse 1143 combinations, a camera 1144, or other USB input devices.

[0128] In at least one embodiment, an instance of the memory controller 1116 and the platform controller hub 1130 may be integrated into a discrete external graphics processor, such as an external graphics processor 1112. In at least one embodiment, the platform controller hub 1130 and / or memory controller 1116 may be external to the one or more processors 1102. For example, in at least one embodiment, the system 1100 may include an external memory controller 1116 and a platform controller hub 1130, which may be configured as a memory controller hub and a peripheral controller hub within a system chipset that communicates with the one or more processors 1102.

[0129] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are described below in connection with Fig. 7A and / or Fig. 7B. In at least one embodiment, portions or all of the inference and / or training logic 715 may be integrated into the graphics processor 1500. For example, in at least one embodiment, the training and / or inference techniques described herein may utilize one or more of the ALUs embodied in a graphics processor. Furthermore, in at least one embodiment, the inference and / or training operations described herein may be performed using logic other than that described in Fig. 7A or Fig. 7B. In at least one embodiment, weighting parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALUs of a graphics processor to perform one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0130] Such components can be used to generate synthetic data that mimics failure cases in a network training process, which can help improve the network's performance while limiting the amount of synthetic data to avoid overfitting.

[0131] Fig. 12 is a block diagram of a processor 1200 including one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208, according to at least one embodiment. In at least one embodiment, the processor 1200 may include additional cores, up to and including the additional core 1202N, represented by dashed boxes. In at least one embodiment, each of the processor cores 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core also has access to one or more shared cache units 1206.

[0132] In at least one embodiment, internal cache units 1204A-1204N and shared cache units 1206 represent a cache hierarchy within processor 1200. In at least one embodiment, cache units 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of shared mid-level cache, such as a Level 2 (L2), Level 3 (L3), Level 4 (L4), or other cache levels, with a highest cache level prior to external memory classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0133] In at least one embodiment, the processor 1200 may also include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCI Express buses. In at least one embodiment, the system agent core 1210 provides management functionality for various processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 to manage access to various external memory devices (not shown).

[0134] In at least one embodiment, one or more of the processor cores 1202A-1202N include support for a concurrent multithreaded element. In at least one embodiment, the system agent core 1210 includes components for coordinating and operating the cores 1202A-1202N during multithreaded processing. In at least one embodiment, the system agent core 1210 may additionally include a power control unit (PCU) that includes logic and components to regulate one or more power states of the processor cores 1202A-1202N and the graphics processor 1208.

[0135] In at least one embodiment, processor 1200 additionally includes a graphics processor 1208 to perform graphics processing operations. In at least one embodiment, graphics processor 1208 is coupled to shared cache units 1206 and system agent core 1210, which includes one or more integrated memory controllers 1214. In at least one embodiment, system agent core 1210 also includes a display controller 1211 to drive the graphics processor output to one or more coupled displays. In at least one embodiment, display controller 1211 may also be a separate module coupled to graphics processor 1208 via at least one interconnect, or may be integrated within graphics processor 1208.

[0136] In at least one embodiment, a ring-based interconnect 1212 is used to couple internal components of processor 1200. In at least one embodiment, an alternative interconnect, such as a point-to-point interconnect, a switched interconnect, or other techniques, may be used. In at least one embodiment, graphics processor 1208 is coupled to ring interconnect 1212 via an I / O link 1213.

[0137] In at least one embodiment, I / O link 1213 represents at least one of several versions of I / O interconnects, including an in-chassis I / O interconnect that enables communication between various processor components and an embedded high-performance memory module 1218, such as an eDRAM module. In at least one embodiment, each of the processor cores 1202A-1202N and the graphics processor 1208 uses embedded memory modules 1218 as a shared last-level cache.

[0138] In at least one embodiment, processor cores 1202A-1202N are homogeneous cores executing a common instruction set architecture. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in the instruction set architecture (ISA) sense, where one or more of processor cores 1202A-1202N execute a common instruction set, while one or more other cores of processor cores 1202A-1202N execute a subset of a common instruction set or a different instruction set. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in the microarchitectural sense, where one or more cores having relatively higher power consumption are coupled with one or more power cores having lower power consumption. In at least one embodiment, processor 1200 may be implemented on one or more chips or as an integrated circuit (SoC).

[0139] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are described below in connection with Fig. 7A and / or Fig. 7B. In at least one embodiment, portions of or all of the inference and / or training logic 715 may be integrated into the processor 1200. For example, in at least one embodiment, the training and / or inference techniques described herein may utilize one or more of the ALUs included in a graphics processor 1212, one or more graphics cores 1202A-1202N, or other components in Fig. 12. Furthermore, in at least one embodiment, the inference and / or training operations described herein may be performed using logic other than that described in Fig. 7A or Fig. 7B. In at least one embodiment, weighting parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALUs of a graphics processor 1200 to perform one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0140] Such components can be used to generate synthetic data that mimics failure cases in a network training process, which can help improve the network's performance while limiting the amount of synthetic data to avoid overfitting.

[0141] Fig. 13 is an example data flow diagram for a process 1300 for creating and deploying an image processing and inference pipeline, according to at least one embodiment. In at least one embodiment, the process 1300 may be provided for use with imaging devices, processing devices, and / or other device types in one or more facilities 1302. The process 1300 may be executed in a training system 1304 and / or in a deployment system 1306. In at least one embodiment, the training system 1304 may be used to perform training, deployment, and implementation of machine learning models (e.g., neural networks, object recognition algorithms, computer vision algorithms, etc.) for use in the deployment system 1306.In at least one embodiment, deployment system 1306 may be configured to offload processing and computing resources among a distributed computing environment to reduce infrastructure requirements at facility 1302. In at least one embodiment, one or more applications in a pipeline may use or consume services (e.g., inference, visualization, compute, AI, etc.) of deployment system 1306 during application execution.

[0142] In at least one embodiment, some of the applications used in advanced processing and inference pipelines may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, the machine learning models may be trained at device 1302 using imaging or sequencing data 1308 generated at device 1302 (and stored in one or more picture archiving and communication system (PACS) servers at device 1302), trained using imaging or sequencing data 1308 from one or more other devices, or a combination thereof.In at least one embodiment, the training system 1304 may be used to provide applications, services, and / or other resources for generating working, deployable machine learning models for the deployment system 1306.

[0143] In at least one embodiment, a model registry 1324 may be secured by object storage that may support versioning and object metadata. In at least one embodiment, the object storage may be secured, for example, by application programming interface (API) compatible cloud storage (e.g., the cloud 1426 of Fig. 14) be accessible from within a cloud platform. In at least one embodiment, the machine learning models within the model registry 1324 may be listed, modified, or deleted by developers or partners of a system that interacts with an API. In at least one embodiment, an API may provide access to methods that allow users with appropriate credentials to associate models with applications, so that models may be executed as part of the execution of containerized instantiations of applications.

[0144] In at least one embodiment, the training pipeline 1404 ( Fig. 14) may include a scenario where device 1302 is training its own machine learning model or has an existing machine learning model that needs to be optimized or updated. In at least one embodiment, imaging data 1308 generated by one or more imaging devices, sequencing devices, and / or other device types may be received. In at least one embodiment, once the imaging data 1308 is received, AI-assisted annotation 1310 may be used to assist in generating annotations corresponding to the imaging data 1308 to be used as ground truth data for a machine learning model. In at least one embodiment, AI-assisted annotation 1310 may include one or more machine learning models (e.g.,Convolutional neural networks (CNNs) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, the AI-assisted annotations 1310 can then be used directly or can be adjusted or fine-tuned using an annotation tool to generate baseline reference data. In at least one embodiment, AI-assisted annotations 1310, labeled clinical data 1312, or a combination thereof can be used as baseline reference data for training a machine learning model.

[0145] In at least one embodiment, a trained machine learning model may be referred to as output model 1316 and used by deployment system 1306 as described herein.

[0146] In at least one embodiment, a training pipeline 1404 ( Fig. 14) may include a scenario where device 1302 requires a machine learning model for use in performing one or more processing tasks for one or more applications in deployment system 1306, wherein device 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for such purposes). In at least one embodiment, an existing machine learning model may be selected from model registry 1324. In at least one embodiment, model registry 1324 may include machine learning models trained to perform a variety of different inference tasks on imaging data. In at least one embodiment, the machine learning model in model registry 1324 may be trained on imaging data from devices other than device 1302 (e.g.,remotely located facilities). In at least one embodiment, the machine learning models may have been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when trained on imaging data from a specific location, the training may take place at that location or at least in a manner that protects the confidentiality of the imaging data or restricts the imaging data from being transferred out of the facility. Once a model is trained or partially trained at a location, in at least one embodiment, a machine learning model may be added to the model registry 1324.In at least one embodiment, a machine learning model may then be retrained or updated at any number of other facilities, and a retrained or updated model may be made available in model registry 1324. In at least one embodiment, a machine learning model may then be selected from model registry 1324 and designated as output model 1316 and used in deployment system 1306 to perform one or more processing tasks for one or more deployment system applications.

[0147] In at least one embodiment, the training pipeline 1404 ( Fig. 14) include a scenario of device 1302 requiring a machine learning model for use in performing one or more processing tasks for one or more applications in deployment system 1306, but device 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for such purposes). In at least one embodiment, a machine learning model selected from the model registry may not be fine-tuned or optimized for imaging data 1308 generated at device 1302 due to differences in populations, the robustness of training data used to train a machine learning model, the diversity of training data anomalies, and / or other issues with the training data.In at least one embodiment, AI-assisted annotation 1310 may be used to assist in generating annotations corresponding to imaging data 1308 to be used as baseline reference data for retraining or updating a machine learning model. In at least one embodiment, labeled data 1312 may be used as baseline reference data for training a machine learning model. In at least one embodiment, retraining or updating a machine learning model may be referred to as model training 1314. In at least one embodiment, model training 1314, e.g., AI-assisted annotations 1310, labeled clinical data 1312, or a combination thereof, may be used as baseline reference data for retraining or updating a machine learning model.In at least one embodiment, a trained machine learning model may be referred to as output model 1316 and used by deployment system 1306 as described herein.

[0148] In at least one embodiment, deployment system 1306 may include software 1318, services 1320, hardware 1322, and / or other components, features, and functionality. In at least one embodiment, deployment system 1306 may include a software "stack," such that software 1318 may be built on top of services 1320 and may use services 1320 to perform some or all of the processing tasks and services 1320, and software 1318 may be built on top of hardware 1322 and may use hardware 1322 to perform processing, storage, and / or other computational tasks of deployment system 1306. In at least one embodiment, software 1318 may include any number of different containers, each container capable of executing an instantiation of an application.In at least one embodiment, each application may perform one or more processing tasks in an advanced processing and inference pipeline (e.g., inferencing, object detection, feature detection, segmentation, image enhancement, calibration, etc.). In at least one embodiment, an advanced processing and inference pipeline may be defined based on selections of various containers desired or required for processing imaging data 1308, in addition to containers that receive and configure imaging data for use by each container and / or for use by device 1302 after processing via a pipeline (e.g., to convert outputs back into a usable data type).In at least one embodiment, a combination of containers within software 1318 (e.g., forming a pipeline) may be referred to as a virtual instrument (as described in more detail herein), and a virtual instrument may leverage services 1320 and hardware 1322 to perform some or all of the processing tasks of applications instantiated in containers.

[0149] In at least one embodiment, a data processing pipeline may receive input data (e.g., imaging data 1308) in a specific format in response to an inference request (e.g., a request from a user of the deployment system 1306). In at least one embodiment, the input data may be representative of one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data may undergo preprocessing as part of the data processing pipeline to prepare data for processing by one or more applications.In at least one embodiment, post-processing may be performed on an output of one or more inference tasks or other processing tasks of a pipeline to prepare output data for a subsequent application and / or to prepare output data for transmission and / or use by a user (e.g., in response to an inference request). In at least one embodiment, the inference tasks may be performed by one or more machine learning models, such as trained or deployed neural networks, which may include output models 1316 of the training system 1304.

[0150] In at least one embodiment, the tasks of the data processing pipeline may be encapsulated in container(s), each representing a discrete, fully functioning instantiation of an application and a virtual computing environment capable of referencing machine learning models. In at least one embodiment, containers or applications may be published in a private (e.g., limited access) area of ​​a container registry (described in more detail herein), and trained or deployed models may be stored in the model registry 1324 and associated with one or more applications. In at least one embodiment, images of applications (e.g.,Container images) must be available in a container registry, and once selected by a user from a container registry for use in a pipeline, an image can be used to create a container for an instantiation of an application for use by a user's system.

[0151] In at least one embodiment, developers (e.g., software developers, clinicians, physicians, etc.) may develop, publish, and store applications (e.g., as containers) for performing image processing and / or inference on supplied data. In at least one embodiment, the development, publishing, and / or storage may be performed using a software development kit (SDK) associated with a system (e.g., to ensure that a developed application and / or container is compliant or compatible with a system). In at least one embodiment, an application that is developed may be deployed locally (e.g., in a first device to data from a first device) with an SDK that may support at least some of the services 1320, as a system (e.g., as a system 1400 of Fig. 14). In at least one embodiment, because DICOM objects may contain any number from one to hundreds of images or other data types, and due to data variation, a developer may be responsible for managing (e.g., setting constructs for, incorporating preprocessing into an application, etc.), extraction, and preparation of incoming data. In at least one embodiment, once an application has been validated by system 1400 (e.g., for accuracy), it may be available in a container registry for selection and / or implementation by a user to perform one or more processing tasks with respect to data at a user's device (e.g., a second device).

[0152] In at least one embodiment, developers may then deploy applications or containers over a network for access and use by users of a system (e.g., the system 1400 of Fig. 14). In at least one embodiment, completed and validated applications or containers may be stored in a container registry, and associated machine learning models may be stored in the model registry 1324. In at least one embodiment, a requesting entity providing an inference or image processing request may search a container registry and / or the model registry 1324 for an application, container, dataset, machine learning model, etc., select a desired combination of elements for inclusion in the data processing pipeline, and submit an imaging processing request.In at least one embodiment, a request may include input data (and associated patient data in some examples) necessary to perform a request and / or may include a selection of one or more applications and / or machine learning models to be executed in processing a request. In at least one embodiment, a request may then be passed to one or more components of the deployment system 1306 (e.g., a cloud) to perform processing of the data processing pipelines. In at least one embodiment, processing by the deployment system 1306 may include referencing selected items (e.g., applications, containers, models, etc.) from a container registry and / or the model registry 1324. In at least one embodiment, once the results are generated by a pipeline, the results may be provided to a user for reference (e.g.,for visualization in a visualization application package running on a local on-site workstation or end device).

[0153] In at least one embodiment, to assist in the processing or execution of applications or containers in pipelines, services 1320 may be leveraged. In at least one embodiment, services 1320 may include compute services, artificial intelligence (AI) services, visualization services, and / or other types of services. In at least one embodiment, services 1320 may provide functionality common to one or more applications in software 1318, such that the functionality may be abstracted to a service that may be invoked or leveraged by the applications. In at least one embodiment, the functionality provided by services 1320 may be executed more dynamically and efficiently while also scaling well by allowing applications to process data in parallel (e.g., using a parallel computing platform 1430 ( Fig. 14)). In at least one embodiment, instead of requiring each application sharing a similar functionality offered by service 1320 to have a respective instance of service 1320, service 1320 may be shared between and among different applications. In at least one embodiment, the services may include an inference server or inference engine that may be used to perform, as non-limiting examples, recognition or segmentation tasks. In at least one embodiment, a model training service may be included to train and / or retrain machine learning models. In at least one embodiment, a data augmentation service may be further included that enables the extraction, resizing, scaling, and / or other augmentation of GPU-accelerated data (e.g., DICOM data, RIS data, CIS data, RESTful data, RPC data, raw data, etc.). In at least one embodiment, a visualization service may be used that can add image rendering effects, such as ray tracing, rasterization, denoising, sharpening, etc., to make two-dimensional (2D) and / or three-dimensional (3D) models more realistic. In at least one embodiment, virtual instrument services may be included that provide beamforming, segmentation, inferencing, imaging, and / or support for other applications within the virtual instrument pipelines.

[0154] In at least one embodiment where a service 1320 comprises an AI service (e.g., an inference service), one or more machine learning models may be executed by invoking an inference service (e.g., an inference server) (e.g., as an API call) to execute machine learning models or their processing as part of application execution. In at least one embodiment where another application comprises one or more machine learning models for segmentation tasks, an application may invoke an inference service to execute machine learning models to perform one or more processing operations associated with segmentation tasks.In at least one embodiment, the software 1318 implementing the advanced processing and inference pipeline including a segmentation application and anomaly detection application may be streamlined because each application may call the same inference service to perform one or more inference tasks.

[0155] In at least one embodiment, hardware 1322 may include GPUs, CPUs, DPUs, graphics cards, an AI / deep learning system (e.g., an AI supercomputer such as NVIDIA's DGX), a cloud platform, or a combination thereof. In at least one embodiment, various types of hardware 1322 may be used to provide efficient, purpose-built support for software 1318 and services 1320 in deployment system 1306. In at least one embodiment, the use of GPU processing may be implemented for local processing (e.g., at device 1302), in an AI / deep learning system, in a cloud system, and / or in other processing components of deployment system 1306 to improve the efficiency, accuracy, and effectiveness of image processing and generation.In at least one embodiment, software 1318 and / or services 1320 may be optimized for GPU processing related to deep learning, machine learning, and / or high-performance computing, as non-limiting examples. In at least one embodiment, at least some of the computing environment of deployment system 1306 and / or training system 1304 may be executed in a data center, on one or more supercomputers, or high-performance computing systems with GPU-optimized software (e.g., a hardware and software combination of NVIDIA's DGX system). In at least one embodiment, hardware 1322 may include any number of GPUs that may be invoked to perform processing of data in parallel, as described herein.In at least one embodiment, the cloud platform may further comprise GPU processing for GPU-optimized execution of deep learning tasks, machine learning tasks, or other computational tasks. In at least one embodiment, the cloud platform may further comprise DPU processing to transfer data received over a network and / or through a network controller or other network interface directly to (e.g., a memory of) one or more GPU(s). In at least one embodiment, the cloud platform (e.g., NVIDIA's NGC) may be executed using one or more AI / supercomputer deep learning and / or GPU-optimized software (e.g., as provided on NVIDIA's DGX systems) as a hardware abstraction and scaling platform. In at least one embodiment, the cloud platform may comprise an application container clustering system or an orchestration system (e.g.,KUBERNETES) on multiple GPUs to enable seamless scaling and load balancing.

[0156] Fig. 14 is a system diagram for an exemplary system 1400 for creating and deploying an imaging deployment pipeline, according to at least one embodiment. In at least one embodiment, the system 1400 may be used to implement the process 1300 of Fig. 13 and / or other processes, including advanced processing and inference pipelines. In at least one embodiment, system 1400 may include training system 1304 and deployment system 1306. In at least one embodiment, training system 1304 and deployment system 1306 may be implemented using software 1318, services 1320, and / or hardware 1322, as described herein.

[0157] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) may be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 may be implemented locally with respect to a healthcare provider organization or as a combination of both cloud and local computing resources. In at least one embodiment, access to APIs in cloud 1426 may be restricted to authorized users through mandated security measures or protocols. In at least one embodiment, a security protocol may include web tokens, which may be signed by an authentication service (e.g., AuthN, AuthZ, Gluecon, etc.) and may carry appropriate authorization.In at least one embodiment, the APIs of virtual instruments (described herein) or other instantiations of system 1400 may be restricted to a set of public IPs that have been verified or authorized for interaction.

[0158] In at least one embodiment, various components of system 1400 may communicate using one of a variety of different network types, including local area networks (LANs) and / or wide area networks (WANs), via wired and / or wireless communication protocols. In at least one embodiment, communication between devices and components of system 1400 (e.g., for transmitting inference requests, for receiving results of inference requests, etc.) may be communicated via one or more data buses, wireless data protocols (WiFi), wired data protocols (e.g., Ethernet), etc.

[0159] In at least one embodiment, the training system 1304 may execute training pipelines 1404 similar to those described herein with reference to Fig. 13. In at least one embodiment, where one or more machine learning models are to be used in the deployment pipelines 1410 by the deployment system 1306, training pipelines 1404 may be used to train or retrain one or more (e.g., pre-trained) models, and / or to implement one or more pre-trained models 1406 (e.g., without requiring retraining or updating). In at least one embodiment, one or more output models 1316 may be generated as a result of the training pipelines 1404. In at least one embodiment, the training pipelines 1404 may include any number of processing steps, such as, but not limited to, transforming or adapting imaging data (or other input data).In at least one embodiment, different training pipelines 1404 may be used for different machine learning models used by the deployment system 1306. In at least one embodiment, the training pipeline 1404 may be similar to one described with reference to FIG. Fig. 13 is to be used for a first machine learning model, the training pipeline 1404, which is similar to one with reference to Fig. 13, can be used for a second machine learning model, and the training pipeline 1404, which is similar to one with respect to Fig. 13 may be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 may be used depending on what is required for each particular machine learning model. In at least one embodiment, one or more of the machine learning models may already be trained and ready for deployment, such that the machine learning models do not receive any processing by the training system 1304 and may be implemented by the deployment system 1306.

[0160] In at least one embodiment, one or more output models 1316 and / or pre-trained models 1406 may comprise any type of machine learning model depending on the implementation or embodiment. In at least one embodiment, and without limitation, the machine learning models used by system 1400 may comprise one or more machine learning models that utilize linear regression, logistic regression, decision trees, support vector machines (SVMs), Naive Bayes, k-nearest neighbors (Knn), K-means clustering, random forest, dimensionality reduction algorithms, gradient boosting algorithms, one or more neural networks (e.g., autoencoders, convolutional algorithms, recurrent algorithms, perceptrons, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolutional, generative adversarial, and / or liquid state machines, etc.) and / or other types of machine learning models.

[0161] In at least one embodiment, training pipelines 1404 may include AI-assisted annotation, as described here at least with respect to Fig. 16B. In at least one embodiment, labeled data 1312 (e.g., conventional annotation) may be generated by any number of techniques. In at least one embodiment, labels or other annotations may be generated in a drawing program (e.g., an annotation program), a CAD (computer-aided design) program, a labeling program, another type of program suitable for generating ground truth annotations or labels, and / or, in some examples, hand-drawn. In at least one embodiment, the ground truth data may be synthetically generated (e.g., from computer models or renderings), physically generated (e.g., designed and generated from real data), machine-automated (e.g., using feature analysis and learning to extract features from data and then generate labels), human-annotated (e.g.,a labeling or annotation expert determines the location of the markers) and / or a combination thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data type used by machine learning models), there may be corresponding ground truths generated by the training system 1304. In at least one embodiment, the AI-assisted annotation may be performed as part of the deployment pipelines 1410, either in addition to or instead of the AI-assisted annotation included in the training pipelines 1410. In at least one embodiment, the system 1400 may include a multi-layer platform including an application layer (e.g., software 1318) of diagnostic applications (or other application types) that can perform one or more medical imaging and diagnostic functions. In at least one embodiment, the system 1400 may be communicatively (e.g.,via encrypted connections) to PACS server networks of one or more facilities. In at least one embodiment, system 1400 may be configured to access and reference data from PACS servers to perform operations such as training machine learning models, deploying machine learning models, image processing, inference, and / or other operations.

[0162] In at least one embodiment, a software layer may be implemented as a secure, encrypted, and / or authenticated API through which applications or containers may be invoked from one or more external environments (e.g., device 1302). In at least one embodiment, applications may then invoke or execute one or more services 1320 for performing computational, AI, or visualization tasks associated with the respective applications, and the software 1318 and / or services 1320 may leverage the hardware 1322 to perform processing tasks in an effective and efficient manner.

[0163] In at least one embodiment, deployment system 1306 may execute deployment pipelines 1410. In at least one embodiment, deployment pipelines 1410 may include any number of applications that may be applied sequentially, non-sequentially, or otherwise to imaging data (and / or other types of data) generated by imaging devices, sequencing devices, genomics devices, etc., including AI-assisted annotation, as described above. In at least one embodiment, as described herein, a deployment pipeline 1410 for an individual device may be referred to as a virtual device for a device (e.g., a virtual ultrasound device, a virtual CT scan device, a virtual sequencing device, etc.). In at least one embodiment, there may be more than one deployment pipeline 1410 for a single device, depending on what information is desired from the data generated by a device.At least in one embodiment where detecting abnormalities from an MRI machine is desired, there may be a first deployment pipeline 1410, and where image enhancement from the output of an MRI machine is desired, there may be a second deployment pipeline 1410.

[0164] In at least one embodiment, an application for generating images may include a processing task that includes the use of a machine learning model. In at least one embodiment, a user may wish to use their own machine learning model or select a machine learning model from the model registry 1224. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to include in an application for performing a processing task. In at least one embodiment, applications may be selected and customized, and by defining constructs of applications, the deployment and implementation of applications for a particular user is presented as a more seamless user experience.In at least one embodiment, deployment pipelines 1410 may be even more user-friendly, provide easier integration, and deliver more accurate, efficient, and timely results by leveraging other features of system 1400, such as services 1320 and hardware 1322.

[0165] In at least one embodiment, deployment system 1306 may include a user interface 1414 (e.g., a graphical user interface, a web interface, etc.) that may be used to select applications for inclusion in deployment pipeline(s) 1410, arrange, modify, or change applications or parameters or constructs thereof, use and interact with deployment pipeline(s) 1410 during setup and / or deployment, and / or otherwise interact with deployment system 1306. In at least one embodiment, although not illustrated with respect to deployment system 1304, user interface 1414 (or another user interface) may be used to select models for use in deployment system 1306, select models for retraining in deployment system 1304, and / or otherwise interact with deployment system 1304.

[0166] In at least one embodiment, the pipeline manager 1412 may be used in addition to an application orchestration system 1428 to manage the interaction between applications or containers of the deployment pipeline(s) 1410 and services 1320 and / or the hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate application-to-application, application-to-service 1320, and / or application or service-to-hardware 1322 interactions. In at least one embodiment, the pipeline manager 1412, although shown as being included in the software 1318, may be included in the services 1320 (e.g., as shown in Fig. 11). In at least one embodiment, the application orchestration system 1428 (e.g., Kubernetes, DOCKER, etc.) may include a container orchestration system that can group applications into containers as logical units for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from the deployment pipeline(s) 1410 (e.g., a reconstruction application, a segmentation application, etc.) with individual containers, each application may be executed in a self-contained environment (e.g., at the kernel level) to increase speed and efficiency.

[0167] In at least one embodiment, each application and / or container (or an image thereof) may be developed, modified, and deployed individually (e.g., a first user or developer may develop a first application, and a second user or developer may develop, modify, and deploy a second application separately from a first user or developer), thereby allowing focus and attention to a task of a single application and / or one or more containers without being hindered by tasks of one or more other applications or containers. In at least one embodiment, communication and cooperation between different containers or applications may be supported by the pipeline manager 1412 and the application orchestration system 1428.In at least one embodiment, as long as an expected input and / or output of each container or application is known to a system (e.g., based on application or container constructs), the application orchestration system 1428 and / or the pipeline manager 1412 may facilitate communication among and between, and resource sharing among, each of the applications or containers. In at least one embodiment, since one or more of the applications or one or more of the containers in the deployment pipeline(s) 1410 may share the same services and resources, the application orchestration system 1428 may orchestrate, load balance, and determine sharing between and among different applications or containers.In at least one embodiment, a scheduler may be used to track resource requests from applications or containers, the current or planned usage of those resources, and resource availability. Thus, in at least one embodiment, a scheduler may allocate resources to different applications and distribute resources between and among applications in light of system requirements and availability. In some examples, a scheduler (and / or another component of the application orchestration system 1428) may determine the availability and distribution of resources based on constraints imposed on a system (e.g., user constraints), such as quality of service (QoS), urgency of the need for data output (e.g., to determine whether to perform real-time or deferred processing), etc.

[0168] In at least one embodiment, services 1320 leveraged and shared by applications or containers in the deployment system 1306 may include compute services 1416, AI services 1418, visualization services 1420, and / or other types of services. In at least one embodiment, applications may invoke (e.g., execute) one or more of the services 1320 to perform processing operations for an application. In at least one embodiment, compute services 1416 may be leveraged by applications to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, one or more compute services 1416 may be leveraged to enable parallel processing (e.g.,using a parallel computing platform 1430) for processing data by one or more of the applications and / or to perform one or more tasks of a single application substantially concurrently. In at least one embodiment, the parallel computing platform 1430 (e.g., NVIDIA's CUDA) may enable universal computing on GPUs (e.g., GPUs 1422). In at least one embodiment, a software layer of a parallel computing platform 1430 may provide access to virtual instruction sets and parallel compute elements of GPUs to execute compute cores. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, memory may be shared between and among multiple containers and / or between and among different processing tasks within a single container.In at least one embodiment, inter-process communication (IPC) calls may be generated for multiple containers and / or for multiple processes within a container to use the same data from a shared memory segment of a parallel computing platform 1430 (e.g., where multiple different stages of an application or multiple applications process the same information). In at least one embodiment, instead of making a copy of the data and moving data to different locations in memory (e.g., a read / write operation), data at the same memory location may be used for any number of processing tasks (e.g., concurrently, at different times, etc.).In at least one embodiment, since data is used to generate new data as a result of processing, this information about a new data location can be stored and shared between different applications. In at least one embodiment, the location of the data and a location of updated or modified data can be part of a definition of how a payload is understood within containers.

[0169] In at least one embodiment, AI services 1418 may be leveraged to perform inference services for executing one or more machine learning models associated with applications (e.g., tasked with performing one or more processing tasks of an application). In at least one embodiment, AI services 1418 may leverage an AI system 1424 to execute one or more machine learning models (e.g., neural networks such as CNNs) for segmentation, reconstruction, object detection, feature recognition, classification, and / or other inference tasks. In at least one embodiment, applications of deployment pipeline(s) 1410 may use one or more of the output models 1316 from the training system 1304 and / or other application models to perform inference on imaging data.In at least one embodiment, two or more examples of inferencing using the application orchestration system 1428 (e.g., a scheduler) may be available. In at least one embodiment, a first category may include a high priority / low latency path that can achieve higher service level agreements, such as to perform inference on urgent requests during an emergency or for a radiologist during diagnosis. In at least one embodiment, a second category may include a standard priority path that can be used for requests that may not be urgent or where analysis can be performed at a later time. In at least one embodiment, the application orchestration system 1428 may allocate resources (e.g.,Services 1320 and / or hardware 1322) based on priority paths for different inference tasks of AI services 1418.

[0170] In at least one embodiment, shared storage for AI services 1418 may be deployed in system 1400. In at least one embodiment, the shared storage may operate as a cache (or other type of storage device) and may be used to process inference requests from applications. In at least one embodiment, when an inference request is submitted, a request may be received by a set of API instances of deployment system 1306, and one or more instances may be selected (e.g., for best fit, load balancing, etc.) to process a request.In at least one embodiment, to process a request, a request may be entered into a database, a machine learning model may be located by the model registry 1324 if it is not already in a cache, a validation step may ensure that a corresponding machine learning model is loaded into a cache (e.g., shared storage), and / or a copy of a model may be stored in a cache. In at least one embodiment, a scheduler (e.g., of the pipeline manager 1412) may be used to launch an application referenced by a request if an application is not already running or if there are not enough instances of an application. In at least one embodiment, if an inference server has not already been started to execute a model, an inference server may be started.Any number of inference servers can be started per model. In at least one embodiment, in a pull model where inference servers are clustered, models can be cached whenever load balancing is advantageous. In at least one embodiment, inference servers can be statically loaded into corresponding, distributed servers.

[0171] In at least one embodiment, inference may be performed using an inference server running in a container. In at least one embodiment, an instance of an inference server may be associated with a model (and optionally multiple versions of a model). In at least one embodiment, if an instance of an inference server does not exist when a request to perform inference on a model is received, a new instance may be loaded. In at least one embodiment, a model may be passed to an inference server upon starting an inference server, so that the same container may be used to serve different models, as long as the inference server runs as a different instance.

[0172] In at least one embodiment, during application execution, an inference request for a given application may be received, and a container (e.g., hosting an instance of an inference server) may be loaded (if not already loaded), and a startup procedure may be invoked. In at least one embodiment, preprocessing logic in a container may load incoming data, decode it, and / or perform any additional preprocessing on the data (e.g., using CPU(s) and / or GPU(s) and / or DPU(s)). In at least one embodiment, once the data is prepared for inference, a container may perform inference on data as needed. In at least one embodiment, this may involve a single inference call on one image (e.g., a hand x-ray) or may require inference on hundreds of images (e.g., a chest CT).In at least one embodiment, an application may summarize the results before completion, which may include, without limitation, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating a visualization, or generating text to summarize findings. In at least one embodiment, different models or applications may be assigned different priorities. For example, some models may have a real-time priority (turnaround time (TAT) < 1 min), while others may have a lower priority (e.g., turnaround time < 12 min). In at least one embodiment, model execution times may be measured by the requesting institution or entity and may include time to traverse the partner network as well as execution on an inference service.

[0173] In at least one embodiment, the transfer of requests between services 1320 and inference applications may be hidden behind a software development kit (SDK), and robust transport may be provided via a queue. In at least one embodiment, a request is placed in a queue via an API for a custom application / tenant ID combination, and an SDK fetches a request from a queue and passes the request to an application. In at least one embodiment, a queue name may be provided in an environment from which an SDK retrieves it. In at least one embodiment, asynchronous communication through a queue may be useful because it allows each instance of an application to begin work as it becomes available.The results may be propagated back through a queue to ensure that no data is lost. In at least one embodiment, queues may also provide the ability to segment work, as highest-priority work may go into a queue to which most instances of an application are connected, while lowest-priority work may go into a queue to which a single instance is connected and processes the tasks in a received order. In at least one embodiment, an application may run on a GPU-accelerated instance spawned in the cloud 1426, and an inference service may perform inferencing on a GPU.

[0174] In at least one embodiment, visualization services 1420 may be leveraged to generate visualizations for visualizing outputs from applications and / or from one or more deployment pipelines 1410. In at least one embodiment, GPUs 1422 of visualization services 1420 may be leveraged to generate visualizations. In at least one embodiment, rendering effects, such as ray tracing, may be implemented by the visualization services 1420 to generate higher quality visualizations. In at least one embodiment, visualizations may include, without limitation, 2D image renderings, 3D volume renderings, 3D volume reconstructions, 2D tomography slices, virtual reality displays, augmented reality displays, etc. In at least one embodiment, virtualized environments may be used to create a virtual interactive display or environment (e.g.,a virtual environment) for interaction by users of a system (e.g., doctors, nurses, radiologists, etc.). In at least one embodiment, the visualization services 1420 may include an internal visualizer, kinematics, and / or other rendering or image processing capabilities or functionality (e.g., ray tracing, rasterization, internal optics, etc.).

[0175] In at least one embodiment, hardware 1322 may include GPUs 1422, an AI system 1424, a cloud 1426, and / or any other hardware used to execute a training system 1304 and / or a deployment system 1306. In at least one embodiment, GPUs 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs that may be used to perform processing tasks of compute services 1416, AI services 1418, visualization services 1420, other services, and / or any of the features or functionality of software 1318. For example, with respect to AI services 1418, the GPUs 1422 may be used to perform preprocessing on imaging data (or other data types used by machine learning models), postprocessing on outputs of machine learning models, and / or inferencing (e.g.,to execute machine learning models). In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may utilize GPUs 1422. In at least one embodiment, cloud 1426 may comprise a GPU-optimized platform for deep learning tasks. In at least one embodiment, AI system 1424 may utilize GPUs, and cloud 1426—or at least a portion tasked with deep learning or inferencing—may be executed using one or more AI systems 1424. Therefore, although hardware 1322 is illustrated as discrete components, this is not intended to be limiting, and any components of hardware 1322 may be combined or leveraged with any other components of hardware 1322.

[0176] In at least one embodiment, the AI ​​system 1424 may include a purpose-built computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, the AI ​​system 1424 (e.g., NVIDIA's DGX) may include GPU-optimized software (e.g., a software stack) that may be executed using one or more GPUs 1422 in addition to the DPUs, CPUs, RAM, storage, and / or other components, features, or functionality. In at least one embodiment, one or more AI systems 1424 may be implemented in a cloud 1426 (e.g., in a data center) for performing one or all of the AI-based processing tasks of the system 1400.

[0177] In at least one embodiment, cloud 1426 may include a GPU-accelerated infrastructure (e.g., NGC from NVIDIA) that may provide a GPU-optimized platform for running processing tasks of system 1400. In at least one embodiment, cloud 1426 may include AI system(s) 1424 for performing one or more of the AI-based tasks of system 1400 (e.g., as a hardware abstraction and scaling platform). In at least one embodiment, cloud 1426 may be integrated with application orchestration system 1428 and leverage multiple GPUs to enable seamless scaling and load balancing between and among applications and services 1320. In at least one embodiment, cloud 1426 may be tasked with running at least some of the services 1320 of system 1400, including compute services 1416, AI services 1418, and / or visualization services 1420, as described herein.In at least one embodiment, the cloud 1426 may perform small and large batch inference (e.g., running NVIDIA's TENSOR RT), provide an accelerated parallel computing API and platform 1430 (e.g., NVIDIA's CUDA), run the application orchestration system 1428 (e.g., KUBERNETES), provide a graphics rendering API and platform (e.g., for ray tracing, 2D graphics, 3D graphics, and / or other rendering techniques to produce higher quality kinematics), and / or may provide other functionality for the system 1400.

[0178] Fig. 15A illustrates a data flow diagram for a process 1500 to train, retrain, or update a machine learning model, according to at least one embodiment. In at least one embodiment, the process 1500 may be performed using, as a non-limiting example, the system 1400 of Fig. 14. In at least one embodiment, process 1500 may leverage services 1320 and / or hardware 1322 of system 1400, as described herein. In at least one embodiment, refined models 1512 generated by process 1500 may be executed by a deployment system 1306 for one or more containerized applications in deployment pipelines 1410.

[0179] In at least one embodiment, model training 1314 may include retraining or updating an initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data, such as a customer record 1506 and / or new baseline reference data associated with the input data). In at least one embodiment, to retrain or update the initial model 1504, an output or loss layer(s) of the initial model 1504 may be reset or deleted and / or replaced with an updated or new output or loss layer(s). In at least one embodiment, the initial model 1504 may have previously fine-tuned parameters (e.g.,weights and / or biases) left over from the previous training, so that training or retraining 1314 does not take as long or require as much processing as training a model from scratch. In at least one embodiment, during model training 1314, by resetting or replacing the output or loss layer(s) of the initial model 1504, the parameters for a new dataset may be adjusted based on loss calculations that match the accuracy of the output or loss layer(s) in generating predictions on a new customer dataset 1506 (e.g., image data 1308 from . Fig. 13) are updated and re-aligned.

[0180] In at least one embodiment, pre-trained models 1406 may be stored in a data store or registry (e.g., the model registry 1324 of Fig. 13). In at least one embodiment, the pre-trained models 1406 may have been trained, at least in part, in one or more facilities other than a facility executing the process 1500. In at least one embodiment, to protect the privacy and rights of patients, subjects, or customers of different facilities, the pre-trained models 1406 may have been trained on-site using customer or patient data generated on-site. In at least one embodiment, the pre-trained models 1406 may be trained using the cloud 1426 and / or other hardware 1322, but no confidential, privacy-protected patient data may be transmitted to, used by, or accessible by any components of the cloud 1426 (or other external hardware).In at least one embodiment where a pre-trained model 1406 is trained using patient data from more than one facility, the pre-trained model 1406 may have been individually trained for each facility before being trained with patient or customer data from another facility. In at least one embodiment, such as when customer or patient data has been exempted from privacy concerns (e.g., through a waiver, for experimental use, etc.) or when customer or patient data is included in a public dataset, customer or patient data from any number of facilities may be used to train the pre-trained model 1406 on and / or off-premises, such as in a data center or other cloud computing infrastructure.

[0181] In at least one embodiment, when selecting applications for use in the deployment pipelines 1410, a user may also select machine learning models to be used for specific applications. In at least one embodiment, a user may not have a model to use, so a user may select a pre-trained model 1406 for use with an application. In at least one embodiment, the pre-trained model 1406 may not be optimized to produce accurate results on the customer data set 1506 of a user's facility (e.g., based on patient diversity, demographic data, types of medical imaging devices used, etc.).In at least one embodiment, prior to deploying a pre-trained model 1406 into a deployment pipeline 1410 for use with an application(s), the pre-trained model 1406 may be updated, retrained, and / or fine-tuned for use in a particular device.

[0182] In at least one embodiment, a user may select the pre-trained model 1406 to be updated, retrained, and / or fine-tuned, and this pre-trained model 1406 may be referred to as the initial model 1504 for the training system 1304 within the process 1500. In at least one embodiment, a customer data set 1506 (e.g., imaging data, genomics data, sequencing data, or other types of data generated by devices in a facility) may be used to perform model training 1314 (which may include, without limitation, transfer learning) on ​​the initial model 1504 to generate a refined model 1512. In at least one embodiment, baseline reference data corresponding to the customer data set 1506 may be generated by the training system 1304.In at least one embodiment, basic reference data may be generated at least in part by clinicians, scientists, physicians, general practitioners in an institution (e.g., as labeled clinical data 1312 of . Fig. 13) are generated.

[0183] In at least one embodiment, AI-assisted annotation 1310 may be used to generate baseline reference data, in some examples. In at least one embodiment, AI-assisted annotation 1310 (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted baseline reference data for a customer record. In at least one embodiment, user 1510 may use annotation tools in a user interface (a graphical user interface (GUI)) on computing device 1508.

[0184] In at least one embodiment, user 1510 may interact with a GUI via computing device 1508 to edit or fine-tune (automatic) annotations. In at least one embodiment, a polygon editing feature may be used to move the vertices of a polygon to multiple precise or fine-tuned locations.

[0185] In at least one embodiment, once the customer data set 1506 has associated baseline reference data, the baseline reference data (e.g., from AI-assisted annotation, manual labeling, etc.) may be used during model training 1314 to generate the refined model 1512. In at least one embodiment, the customer data set 1506 may be applied to the initial model 1504 any number of times, and baseline reference data may be used to update the parameters of the initial model 1504 until an acceptable level of accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 has been generated, the refined model 1512 may be deployed within one or more deployment pipelines 1410 in a device for performing one or more processing tasks with respect to medical imaging data.

[0186] In at least one embodiment, the refined model 1512 may be uploaded to pre-trained models 1406 in a model registry 1324 for selection by another entity. In at least one embodiment, this process may be completed with any number of entities, allowing the refined model 1512 to be further refined on new datasets as often as desired to produce a more universal model.

[0187] Fig. 15B is an example illustration of a client-server architecture 1532 for enhancing annotation tools with pre-trained annotation models, according to at least one embodiment. In at least one embodiment, AI-assisted annotation tools 1536 may be instantiated based on a client-server architecture 1532. In at least one embodiment, annotation tools 1536 may, for example, assist radiologists in identifying organs and abnormalities in imaging applications. In at least one embodiment, the imaging applications may include software tools that assist the user 1510, as a non-limiting example, in identifying some extreme points on a particular organ of interest in raw images 1534 (e.g., in a 3D MRI or CT scan) and automatically receive annotated results for all 2D slices of a particular organ.In at least one embodiment, the results may be stored in a data store as training data 1538 and used (by way of example and without limitation) as baseline reference data for training. In at least one embodiment, when computing device 1508 sends extreme points for AI-assisted annotation 1310, a deep learning model, for example, may receive this data as input and return inference results of a segmented organ or anomaly. In at least one embodiment, pre-instantiated annotation tools, such as AI-assisted annotation tool 1536B in FIG. Fig.15B, may be enhanced by making API calls (e.g., an API call 1544) to a server, such as an annotation assistance server 1540, which may include a set of pre-trained models 1542 stored, for example, in an annotation model registry. In at least one embodiment, an annotation model registry may store pre-trained models 1542 (e.g., machine learning models such as deep learning models) that are pre-trained to perform AI-assisted annotation on a particular organ or anomaly. These models may be further updated using training pipelines 1404. In at least one embodiment, pre-installed annotation tools may be enhanced over time as new labeled clinical data 1312 is added.

[0188] Such components can be used to generate synthetic data that mimics failure cases in a network training process, which can help improve the network's performance while limiting the amount of synthetic data to avoid overfitting.

[0189] Other variations are within the spirit of the present disclosure. Thus, while the disclosed techniques are susceptible to various modifications and alternative constructions, certain illustrative embodiments thereof are shown in the drawings and have been described in detail above. It should be understood, however, that there is no intention to limit the invention to any specific form or forms disclosed; on the contrary, the invention is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the appended claims.

[0190] The use of the terms "a" and "an" and "the" or similar references in the context of describing the disclosed embodiments (particularly in the context of the following claims) is to be interpreted to cover both singular and plural, unless otherwise indicated herein or clearly contradicted by the context. The terms "comprising," "having," and "include" are to be interpreted as open-ended terms (i.e., "including but not limited to") unless otherwise specified. The term "connected," when unmodified and referring to physical connections, is to be interpreted as partially or wholly contained in, attached to, or coupled to one another, even if something intervening.Citation of ranges of values ​​herein is meant merely as a shorthand method of individually referring to each value falling within that range, unless otherwise indicated herein, and each value is incorporated into the specification as if individually cited herein. The use of the term "set" (e.g., "set of elements") or "subset" is, unless otherwise stated or contradicted by the context, to refer to a non-empty collection having one or more elements. Furthermore, unless otherwise stated or contradicted by the context, the term "subset" of a corresponding set does not necessarily denote an exact subset of the set; rather, the subset and the corresponding set may be the same.

[0191] Conjunctive language, such as phrases in the form of "at least one of A, B, and C" or "at least one of A, B, and C," on the other hand, unless explicitly stated otherwise or otherwise clearly contradicted by the context, is to be understood with the context as being generally used to present that an element, term, etc., is either A or B or C, or any non-empty subclause of the set of A, B, and C. For example, in the illustrated example of a sentence with three elements, the conjunctive phrases "at least one of A, B, and C" and "at least one of A, B, and C" refer to each of the following sentences: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Therefore, such conjunctive language is not generally intended to imply that certain embodiments require that at least one of A, at least one of B, and at least one of C be present.Additionally, unless otherwise specified or contradicted by context, the term "plurality" indicates a plural state (e.g., "a plurality of elements" indicates multiple elements). The number of elements in a plurality is at least two but may be more if indicated either explicitly or by context. Furthermore, unless otherwise specified or clear by context, the phrase "based on" means "based at least in part on" and not "based solely on."

[0192] Operations of processes described herein may be performed in any suitable order, unless otherwise indicated herein or clearly contradicted by context. In at least one embodiment, a process, such as those processes described herein (or variations and / or combinations thereof), is performed under the control of one or more computer systems configured with executable instructions, and is implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that execute collectively on one or more processors, using hardware, or combinations thereof. In at least one embodiment, the code is stored on a computer-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors.In at least one embodiment, the computer-readable medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagating transient electrical or electromagnetic transmission) but includes non-transitory data storage circuitry (e.g., buffers, caches, and queues) within transceivers of transient signals. In at least one embodiment, code (e.g., executable code or source code) is stored on a set of one or more non-transitory computer-readable storage media having stored thereon executable instructions (or other memory to store executable instructions) that, when executed by one or more processors of a computer system (i.e., as a result of being executed), cause the computer system to perform the operations described herein.In at least one embodiment, a set of non-transitory computer-readable storage media comprises, in one embodiment, a plurality of non-transitory computer-readable storage media, and one or more individual non-transitory storage media of the plurality of non-transitory computer-readable storage media lacks any code at all, while the plurality of non-transitory computer-readable storage media collectively store all code. In at least one embodiment, the executable instructions are executed such that different instructions are executed by different processors.

[0193] Accordingly, in at least one embodiment, computer systems are configured to implement one or more services that individually or collectively perform the processes described herein, and such computer systems are configured with applicable hardware and / or software that enable the operations to be performed. Furthermore, a computer system implementing at least one embodiment of the present disclosure is a single device, and in another embodiment, is a distributed computer system that includes multiple devices that operate differently such that the distributed computer system performs the operations described herein, and such that no single device performs all of the operations.

[0194] The use of any and all examples or exemplary language provided herein (e.g., "such as") is intended merely to better illustrate embodiments of the disclosure and does not impose any limitation on the scope of the invention unless otherwise claimed. No language in the specification should be construed to identify any unclaimed element as essential to practicing the disclosure.

[0195] All references, including publications, patent applications, and patents cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and set forth in its entirety herein.

[0196] Throughout the description and claims, the terms "coupled" and "connected," along with their derivatives, may be used. It should be understood that these terms are not intended to be synonymous with each other. Rather, in specific examples, "connected" or "coupled" may be used to indicate that two or more elements are directly or indirectly in physical or electrical contact with each other. "Coupled" may also mean that two or more elements are not in direct contact with each other, yet still cooperate or interact with each other.

[0197] Unless specifically stated otherwise, it will be appreciated that, throughout the specification, terms such as "process," "compute," "calculate," "determine," or the like refer to the action and / or processes of a computer or computer system, or similar electronic computing device, that manipulate and / or transform data represented as physical, such as electronic, quantities within the computer system's registers and / or memory into other data also represented as physical quantities within the memory, registers, or other such information storage, transmission, or display devices.

[0198] Similarly, the term "processor" may refer to any device or part of a device that processes electronic data from registers and / or memory and transforms that electronic data into other electronic data that can be stored in registers and / or memory. As used herein, "software processes" may include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Also, any process may refer to multiple processes for dispatching instructions in sequence or in parallel, continuously or intermittently. In at least one embodiment, the terms "system" and "method" are used interchangeably herein in that the system may embody one or more methods, and the methods may be considered a system.

[0199] In this document, reference may be made to obtaining, acquiring, receiving, or inputting analog or digital data to a subsystem, computer system, or computer-implemented machine. In at least one embodiment, the process of obtaining, acquiring, receiving, or inputting analog and digital data may be accomplished in a variety of ways, such as by receiving the data as a parameter of a function call or a call to an application programming interface.In at least one embodiment, processes of obtaining, acquiring, receiving, or inputting analog or digital data may be achieved by transmitting the data over a serial or parallel interface. In at least one embodiment, processes of obtaining, acquiring, receiving, or inputting analog or digital data may be achieved by transmitting the data from the providing entity to the acquiring entity over a computer network. Reference may also be made to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data may be achieved by transmitting the data as an input or output parameter of a function call, a parameter of a programming interface, or an interprocess communication mechanism.

[0200] Although descriptions herein set forth exemplary embodiments of described techniques, other architectures may be used to implement the described functionality and are intended to be within the scope of the disclosure. Furthermore, although specific distributions of responsibilities are defined above for purposes of illustration, various functions and responsibilities could be distributed and allocated in different ways depending on the circumstances.

[0201] Furthermore, although the subject matter has been described in language referring to structural features and / or methodological acts, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or acts described. Rather, certain features and acts are disclosed as exemplary forms of implementing the claims.

Claims

[1] Method comprising: Sending, using an application hosting platform, a preload request to preload a first portion of data for an application hosted using the application hosting platform, the preload request being received prior to receiving user input identifying the application for execution; Receiving, using the application hosting platform, a first indication that the first portion of data is preloaded for the application using a virtualized computing environment; Receiving, using the application hosting platform, a user request to run the application; Sending, using the application hosting platform, a load request to load a second portion of data for the application onto the virtualized computing environment; Receiving, using the application hosting platform, a second indication that the second portion of data for the application is loaded onto the virtualized computing environment; and In response to receiving the second indication, causing the application to execute using the virtualized computing environment. [2] The method of claim 1, wherein the first portion of data is data excluding data associated with the user request and the second portion of data is associated with the user request. [3] The method of claim 1, further comprising: Sending, using the application hosting platform, a plurality of preload requests to preload the first portion of data for the application to a plurality of virtualized computing environments, wherein the plurality of preload requests are received prior to receiving user input identifying the application for execution; and Receiving, using the application hosting platform, a third indication that the first portion of data is preloaded for the application at the plurality of virtualized computing environments. [4] The method of claim 3, further comprising: Receiving, using the application hosting platform, a second user request to execute the application running on a second virtualized computing environment of the plurality of virtualized computing environments; Sending, using the application hosting platform, a second load request to load the second portion of data for the application onto the second virtualized computing environment; Receiving, using the application hosting platform, a fourth indication that the second portion of data for the application is loaded onto the second virtualized computing environment; and In response to receiving the fourth indication, causing the application to execute on the second virtualized computing environment. [5] The method of claim 2, further comprising: Determining a number of virtualized computing environments to preload based on an average duration that the virtualized computing environment is inactive. [6] The method of claim 1, wherein the virtualized computing environment is placed in an inactive state upon receiving the indication that the first data is preloaded. [7] The method of claim 1, wherein preloading of the game is requested using a command line interface (CLI) command or a flag in a configuration file of the application. [8] The method of claim 1, further comprising: Predicting that the first portion of data is pre-loaded for application to the virtualized computing environment using a machine learning model trained at least in part based on prior durations to pre-load the first portion of data for application to one or more virtualized computing environments. [9] The method of claim 1, further comprising: Receiving, using the application, an indication that one or more files associated with the application have been updated; and Causing the virtualized computing environment to deconstruct in response to receiving the indication that one or more files associated with the application have been updated. [10] System comprising: an application hosting platform to: request allocation of a virtualized computing environment to launch an application hosted on the hosting platform in a preload mode before receiving user input identifying the application for execution, the preload mode associated with preloading a first portion of data for the application; transmit instructions to launch the application in the preload mode at the virtualized computing environment in response to a first indication that the virtualized computing environment has been allocated for the application; receive a second indication that the first portion of data is loaded onto the virtualized computing environment; and cause the virtualized computing environment to enter an inactive state in response to receiving the second indication. [11] The system of claim 10, wherein the application hosting platform further comprises: receive a request to execute the application on the virtualized computing environment, the request being associated with user input that identifies the application for execution; and second instructions to load a second section of data for the application onto the virtualized computing environment. [12] The system of claim 11, wherein the application hosting platform further comprises: receive a third indication that the second portion of data is loaded onto the virtualized computing environment; and cause the application to execute on the virtualized computing environment in response to receiving the second indication. [13] The system of claim 11, wherein the application hosting platform further comprises: to access an account associated with the user input in response to receiving the request to execute the application on the virtualized computing environment, the account comprising the second portion of data. [14] The system of claim 10, wherein the application is instructed to start in preload mode using a command line interface (CLI) command or a flag in a configuration file of the application. [15] The system of claim 10, wherein the application hosting platform further comprises: receive an initialization sequence before allocating the virtualized computing environment; and receive the indication that the first section of data is loaded onto the virtualized computing environment after receiving the initialization sequence based on the application running in a cloud environment. [16] The system of claim 10, wherein the application hosting platform further comprises: determine a number of user inputs associated with the application that is greater than a number of virtualized computing environments on which the application is launched, wherein allocating the virtualized computing environment is based on determining that the number of user inputs is greater than the number of virtualized computing environments. [17] System according to claim 10, wherein the application comprises at least one of the following: a gaming application; a video conferencing application; a content creation application; a cloud-hosted application; a collaborative content creation application; a cloud-hosted collaborative content creation application; a video streaming application; an application of machine learning; or a simulation application. [18] The system of claim 10, wherein the application hosting platform comprises at least one of the following: a cloud-hosted gaming service platform; a cloud-hosted collaborative content creation platform for heterogeneous content creation applications; a video streaming hosting platform; a testing platform for simulated or augmented content; a machine learning training platform; a machine learning deployment platform; or a video conferencing hosting platform. [19] A non-transitory computer-readable medium having instructions stored thereon, the instructions, when executed by a processing device, causing the processing device to: send a preload request to preload a first portion of the data for an application hosted using an application hosting platform, the preload request being received prior to receiving user input identifying the application for execution; receive, using the application hosting platform, a first indication that the first portion of data is pre-loaded for the application using a virtualized computing environment; receive a user request to run the application using the application hosting platform; send a load request using the application hosting platform to load a second portion of data for the application onto the virtualized computing environment; receive a second indication that the second portion of data for the application is loaded onto the virtualized computing environment; and cause the application to execute using the virtualized computing environment in response to receiving the second indication. [20] The non-transitory computer-readable medium of claim 19, wherein the first portion of data is data without data associated with the user request and the second portion of data is associated with the user request. [21] The non-transitory computer-readable medium of claim 19, wherein the instructions, when executed by the processing device, further cause the processing device to: send a plurality of preload requests to preload the first portion of data for the application using a plurality of virtualized computing environments, wherein the plurality of preload requests are received prior to receiving user input identifying the application for execution; and Receiving a third indication that the first portion of data is preloaded for the application on the plurality of virtualized computing environments. [22] The non-transitory computer-readable medium of claim 21, wherein the instructions, when executed by a processing device, further cause the processing device to: receive a second user request to execute the application using a second virtualized computing environment of the plurality of virtualized computing environments; send a second load request to load the second portion of data for the application onto the second virtualized computing environment; receive a fourth indication that the second portion of data for the application is loaded using the second virtualized computing environment; and cause the application to execute using the second virtualized computing environment in response to receiving the fourth indication.

Images