Abstract: A server platform in a cloud computing system is determined to be in an unused state and a request from a remote computing system outside the data center system is received to control hardware of at least one of the server platforms of the cloud computing systems. A bare-metal-as-is (BMAI) session is initiated for the remote computing system to use the server platform based on the unused state, wherein exclusive control of at least a portion of hardware of the server platform is temporarily handed over to the remote computing system in the BMAI session. Control of the portion of the hardware of the server platform is reclaimed based on an end of the BMAI session.

Abstract: Data that is to be processed by a particular service executed by a first edge computing device in an application, is analyzed to determine characteristics of the data. An opportunity to replicate the particular service on a plurality of edge computing devices is determined based on characteristics of the data. A second edge computing device is determined to be available to execute a replicated instance of the particular service. Replication of the particular service is initiated on a plurality of edge computing devices including the second edge computing device. An output of an instance of the particular service executed on the first edge computing device and an output of the replicated instance of the particular service executed on the second edge computing device are combined to form a single output for the particular service.

Abstract: An apparatus is described. The apparatus includes a memory module. The memory module includes a memory. The memory module includes function execution circuitry. The function execution circuitry is configurable to execute a producer function and a consumer function of a multi-function process. The memory module includes an interface to be coupled to a memory controller.

Abstract: A cross-domain distributed network function may be constructed by instantiating a local-domain endpoint for a first application component. Here, the local-domain endpoint is in a first network domain that includes the first application component. A connection to an extra-domain endpoint may then be made. Here, the extra domain endpoint is in a second network domain that does not include the first network domain, and the second network domain includes a second application component for the application. The local-domain endpoint may then provide a network service for a third network domain that includes the application. The first application component may then use that network service to connect to the second application component.

Abstract: A method is described. The method includes receiving a request. The method includes allocating and/or configuring hardware to execute the request in accordance with an energy related input specified by a sender of the request. The method includes causing execution of the request in accordance with the energy related input.

Abstract: The techniques described herein implement a proxy service associated with a public cloud platform. A proxy server receives a connection request sent via an account. The connection request includes a connection parameter such as a specific time the request is initiated, a specific location of a device used to initiate the request, or an identification of the device used to initiate the request. The proxy server maps the account to a policy. The proxy server then determines whether the connection parameter included in the request is anomalous to a corresponding parameter defined in the policy. In an event the connection parameter is an anomalous parameter, the proxy server takes actions to determine whether the policy can be dynamically updated to accommodate the anomalous parameter. If an accommodation can be made, a user or device does not have to wait an extended period of time to gain access to the resource.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed. A first example apparatus disclosed herein is an autonomous mobile radio access network (RAN) node that includes communication circuitry, instructions, and programmable circuitry to cause the communication circuitry to transmit a workload to a server via a network, initiate local processing of the workload after a loss of connectivity with the server, and move the autonomous mobile RAN node from a first location to a second location. A second example apparatus disclosed herein is an autonomous mobile RAN node that includes communication circuitry, instructions, and programmable circuitry to cause communication of a workload from a client device to a server to process the workload, identify a second location relative to a first location of the compute device based on network performance, and cause the autonomous mobile RAN node to move from the first location to the second location.

Abstract: Dynamic resource reconfiguration based on workload semantics and behavior. A controller may receive, from a core network, a request for an end-to-end managed connection, the end-to-end managed connection for an application executing on a server and an application executing on a client device, where the client device is coupled to the controller via a radio access network (RAN). The controller may determine a policy for the end-to-end managed connection. The controller may apply one or more parameters of the policy to the end-to-end managed connection.

Abstract: Transportable storage devices are communicatively coupled behind one or more dedicated “edge” data servers to take advantage of the benefits of the data servers and transportable storage devices while limiting their disadvantages. Each edge data server ingests data from one or more client devices and copies the data to one or more of the transportable storage devices for eventual transport to a cloud data center for upload to a cloud storage system. Multiple versions of a segment of data (e.g., of a file or a blob) are maintained at various points in the disclosed system and the disclosed technology ensures that the most recent version is the version ultimately stored on the cloud storage system.

Abstract: Examples described herein relate to executing a first boot firmware code to receive an allocation of hardware devices and allocating, by the first boot firmware code, resource allocations to one or more secondary boot firmware codes. In some examples, the one or more secondary boot firmware codes allocate use of hardware devices to one or more operating systems (OSs).

Abstract: Systems and methods for remote command access in a hybrid cloud to on-premises devices are described. An example method includes receiving, by a gateway service, a request for a connection between a remote support service agent and an on-premises device. The method further includes receiving, by the gateway service, consent from an authorized user associated with the on-premises device. The method further includes creating, by the gateway service, a first session with the on-premises device, where a scope of the consent is limited to the first session. The method further includes provisioning, by the gateway service, a device-specific hybrid connection endpoint for the first session. The method further includes forming, by the gateway service a secure session by binding the device-specific hybrid connection endpoint with a second session, the secure session allowing for transport of data and a set of commands based on a scope of the consent.

Abstract: Transportable storage devices are communicatively coupled behind one or more dedicated “edge” data servers to take advantage of the benefits of the data servers and transportable storage devices while limiting their disadvantages. Each edge data server ingests data from one or more client devices and copies the data to one or more of the transportable storage devices for eventual transport to a cloud data center for upload to a cloud storage system. Multiple versions of a segment of data (e.g., of a file or a blob) are maintained at various points in the disclosed system and the disclosed technology ensures that the most recent version is the version ultimately stored on the cloud storage system.

Abstract: Examples described herein relate to controlling power available to processes and hardware devices to control a monetary cost of utilized electricity and/or amount of energy utilized from non-renewable energy sources. The system can modify operating configurations of processes and/or hardware based on the available power. The system can control total power drawn to control a monetary cost of power and/or avoid drawing power from non-renewable sources (e.g., fossil fuel sources or grid including gas or coal-based energy sources).

Abstract: Transportable storage devices are communicatively coupled behind one or more dedicated “edge” data servers to take advantage of the benefits of the data servers and transportable storage devices while limiting their disadvantages. Each edge data server ingests data from one or more client devices and copies the data to one or more of the transportable storage devices for eventual transport to a cloud data center for upload to a cloud storage system. Multiple versions of a segment of data (e.g., of a file or a blob) are maintained at various points in the disclosed system and the disclosed technology ensures that the most recent version is the version ultimately stored on the cloud storage system.

Abstract: Methods, apparatus, and software for efficient accelerator offload in multi-accelerator frameworks. One multi-accelerator framework employs a compute platform including a plurality of processor cores and a plurality of accelerator devices. An application is executed on a first core and a portion of the application workload is offloaded to a first accelerator device. In connection with moving execution of the application to a second core, a second accelerator devices to be used for the offloaded workload is selected based on core-to-accelerator cost information for the second core. This core-to-accelerator cost information includes core-accelerator cost information for combinations of core-accelerator pairs, which are based, at least on part, on latencies projected for interconnect paths between cores and accelerators. Both single-socket and multi-socket platform are supported.

Abstract: Transportable storage devices are communicatively coupled behind one or more dedicated “edge” data servers to take advantage of the benefits of the data servers and transportable storage devices while limiting their disadvantages. Each edge data server ingests data from one or more client devices and copies the data to one or more of the transportable storage devices for eventual transport to a cloud data center for upload to a cloud storage system. Object identifiers of objects stored on the transportable storage devices are maintained in a namespace of the data servers after decoupling of the transportable storage devices from the data servers so that the object identifiers remain visible to client devices.

Abstract: Transportable storage devices are communicatively coupled behind one or more dedicated “edge” data servers to take advantage of the benefits of the data servers and transportable storage devices while limiting their disadvantages. Each edge data server ingests data from one or more client devices and copies the data to one or more of the transportable storage devices for eventual transport to a cloud data center for upload to a cloud storage system. Object identifiers of objects stored on the transportable storage devices are maintained in a namespace of the data servers after decoupling of the transportable storage devices from the data servers so that the object identifiers remain visible to client devices.

Abstract: Transportable storage devices are communicatively coupled behind one or more dedicated “edge” data servers to take advantage of the benefits of the data servers and transportable storage devices while limiting their disadvantages. Each edge data server ingests data from one or more client devices and copies the data to one or more of the transportable storage devices for eventual transport to a cloud data center for upload to a cloud storage system. Multiple versions of a segment of data (e.g., of a file or a blob) are maintained at various points in the disclosed system and the disclosed technology ensures that the most recent version is the version ultimately stored on the cloud storage system.