Abstract: The subject technology retrieves information related to a set of instances of compute service managers, each instance of a particular compute service manager being associated with a set of virtual warehouses. The subject technology filters the information to determine a set of candidates from the set of instances of compute service managers. The subject technology sorts the set of candidates based at least in part on each workload of each of the set of candidates. The subject technology selects a candidate compute service manager from the set of instances of compute service managers to issue a query restart by randomly selecting an execution node, the execution node being included in a particular virtual warehouse associated with the candidate compute service manager, the selecting facilitating improving utilization of cluster resources and improving query execution on the selected candidate compute service manager.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for adjusting a computing load. The method in an illustrative embodiment includes: determining a total computing power demand of at least one user device that will be switched, due to movement, to being provided a computing service by a computing node; determining an available computing power of the computing node; and if the available computing power is unable to meet the total computing power demand, by adjusting a computing load of the computing node, adjusting the available computing power before the at least one user device is switched to being provided the computing service by the computing node, so as to meet the total computing power demand.

Abstract: A technique for managing pooled resources in a distributed computing environment includes a resource manager that receives resource allocation requests from workload managers for running one or more applications. The applications are initiated by a consumer through at least one of the workload managers where each workload manager is configured to translate demand requests from the applications into resource allocation requests. A determination is made whether there are available resources to satisfy the resource allocation requests. Responsive to determining that there is an unmet resource allocation request, a candidate resource meeting some but not all attributes needed to satisfy the unmet resource allocation request is identified and reconfigured to have the attributes needed to satisfy the unmet resource allocation request.

Abstract: A server-based desktop-virtual machines architecture may be extended to a client machine. In one embodiment, a user desktop is remotely accessed from a client system. The remote desktop is generated by a first virtual machine running on a server system, which may comprise one or more server computers. During execution of the first virtual machine, writes to a corresponding virtual disk are directed to a delta disk file or redo log. A copy of the virtual disk is created on the client system. When a user decides to “check out” his or her desktop, the first virtual machine is terminated (if it is running) and a copy of the delta disk is created on the client system. Once the delta disk is present on the client system, a second virtual machine can be started on the client system using the virtual disk and delta disk to provide local access to the user's desktop at the client system. This allows the user to then access his or her desktop without being connected to a network.

Abstract: Embodiments are disclosed that allow data to be sent between a Bluetooth enabled device and a virtual device associated with a corresponding physical device. In particular, embodiments of a virtual mobile device system may include one or more components for processing Bluetooth calls where these Bluetooth components may process received Bluetooth calls in a first manner in a connected state and process Bluetooth calls in a disconnected state in a second manner.

Abstract: A computing device may include a memory and a processor cooperating with the memory to generate connection leases for a plurality of client devices. The client devices may be configured to request virtual computing sessions from virtual delivery appliances in accordance with respective connection leases. Virtual delivery appliances within a first group may be configured to operate during off-peak hours, and virtual delivery appliances within a second group different than the first group may be configured not to operate during the off-peak hours. The processor may generate each connection lease to include at least one of the virtual delivery appliances from the first group.

Abstract: Systems, methods, and other embodiments associated with controlling an execution pipeline are described. In one embodiment, a method includes generating an execution pipeline for executing a plurality of tasks. The example method may also include evaluating execution definitions of the tasks to identify execution properties of the plurality of tasks. The example method may also include assigning each task to an execution environment selected from a set of execution environments based upon execution properties of the task matching execution properties of the execution environments. The example method may also include controlling the execution pipeline to execute each task within the assigned execution environments.

Abstract: Systems and methods may be used to determine where to run a service based on workload-based conditions or system-level conditions. An example method may include determining whether power available to a resource of a compute device satisfies a target power, for example to satisfy a target performance for a workload. When the power available is insufficient, an additional resource may be provided, for example on a remote device from the compute device. The additional resource may be used as a replacement for the resource of the compute device or to augment the resource of the compute device.

Abstract: The invention relates to a power distribution system (1), especially a Power-over-Ethernet system, comprising at least one dominant sensor, which may be located within a powered device (4) like a lighting device, and at least one non-dominant sensor, which may be located within another powered device (4), wherein the power distribution system is adapted such that in a system low power mode the at least one dominant sensor (6) consumes power provided by a power providing unit (3) and the at least one non-dominant sensor (6) does not consume the provided power and that the power distribution system (1) switches from the system low power mode to a system high power mode, if the at least one dominant sensor (6) has sensed an event. Since in the system low power mode the at least one non-dominant sensor does not consume power, the power consumption can be reduced.

Abstract: A method and system for distributing a compute model and data to process to heterogeneous and distributed compute devices. The compute model and a portion of the data is processed on a benchmark system and the timing used to make a job execution speed estimate for each compute device. Compute devices are selected and assigned data chunks based on the estimate so distributed processing is completed within a predefined time period. The compute model and data chunks can be sent to the respective compute devices using separate processes, such as a payload manager configured to transfer compute jobs to remote devices and a messaging engine configured to transfer data messages, and where the payload manager and messaging engine communicate with corresponding software engines on the compute devices.

Abstract: A gateway device is connected via one or more networks to electronic controllers on-board a vehicle. The gateway device includes one or more memories, and circuitry that acquires firmware update information. The circuitry determines whether or not a first electronic controller satisfies a second condition based on second information about the first electronic controller, where the second information is whether the first electronic controller includes a firmware cache for performing a pre-update firmware cache operation. The circuitry also causes, when the second condition is not satisfied, the gateway device to execute a proxy process, where the gateway device requests the first electronic controller to transmit boot ROM data to the gateway device, creates updated boot ROM data with the updated firmware, and transmits the updated boot ROM data to the first electronic controller that updates the boot ROM and resets the first electronic controller with the updated firmware.

Abstract: A system for controlling one or more fans, comprising an open loop control system configured to receive a CPU power level and to maintain a fan speed at an open loop fan speed level. A closed loop control system configured to receive the CPU power level and temperature, and to modify the fan speed as a function of the CPU power level and temperature, wherein the fan speed is maintained at a level that is not lower than the open loop fan speed level.

Abstract: System and method for benchmarking a container orchestration platform in a computing environment uses data contained in a configuration file, which specifies at least one benchmark operation having benchmark actions for container orchestration resource types to be performed in the container orchestration platform, to create a resource manager for each container orchestration resource type specified in the configuration file. Using the created resource managers, a routine for each benchmark action is spawned and executed on container orchestration objects in the container orchestration platform. As the routines are executed, performance metrics are collected and at least some of the collected performance metrics are displayed.

Abstract: A method for containerized workload scheduling can include determining a network state for a first hypervisor in a virtual computing cluster (VCC). The method can further include determining a network state for a second hypervisor. Containerized workload scheduling can further include deploying a container to run a containerized workload on a virtual computing instance (VCI) deployed on the first hypervisor or the second hypervisor based, at least in part, on the determined network state for the first hypervisor and the second hypervisor.

Abstract: A request is received to schedule a new software process. Description data associated with the new software process is retrieved. A workload resource prediction is requested and received for the new software process. A landscape directory is analyzed to determine a computing host in a managed landscape on which to load the new software process. The new software process is executed on the computing host.

Abstract: Examples described herein relate to method and system for determining a response time for an action. A request for an action may be communicated from a source entity to a target entity. The action is generated by the source entity and which is to be responded by the target entity. Further, a response time corresponding to the action may be determined based on prior execution experience of one or more jobs associated with the action and a learning rate. Thereafter, the source entity may be allowed to wait for a response corresponding to a completion of the action from the target entity for at least a time duration corresponding to the response time.

Abstract: In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a pod manager. The pod manager receives receive a request for composing a target composed-node. The pod manager employs a first set of pooled hardware resources of the computing pod to build the target composed-node. The pod manager determines to reserve a second set of pooled hardware resources of the computing pod for a backup node of the target composed-node. The pod manager determines that the target composed-node has failed. The pod manager employs the second set of pooled hardware resources to build the backup node.

Abstract: A method and an apparatus that schedule a plurality of executables in a schedule queue for execution in one or more physical compute devices such as CPUs or GPUs concurrently are described. One or more executables are compiled online from a source having an existing executable for a type of physical compute devices different from the one or more physical compute devices. Dependency relations among elements corresponding to scheduled executables are determined to select an executable to be executed by a plurality of threads concurrently in more than one of the physical compute devices. A thread initialized for executing an executable in a GPU of the physical compute devices are initialized for execution in another CPU of the physical compute devices if the GPU is busy with graphics processing threads.

Abstract: A neural network processor and a control method are provided. The neural network processor includes a neural network processor cluster formed by multiple single-core neural network processors and a peripheral module. The peripheral module includes a main control unit and a DMA module. The DMA module is used to convey a first task descriptor to the main control unit. The main control unit is used to: analyze the first task descriptor, determine, according to an analysis result, a subtask to be distributed to each selected processor; modify the first task descriptor to acquire a second task descriptor respectively corresponding to each selected processor; and distribute each second task descriptor to each corresponding selected processor, and activate each selected processor to process the corresponding subtask. The main control unit schedules and manages all of the single-core neural network processors, thereby leveraging operational performance of the neural network processor.

Abstract: A method for database management is disclosed. The method may include receiving an algorithm from a user. Based on the algorithm, a hierarchical dataflow graph (hDFG) may be generated. The method may further include generating an architecture for a chip based on the hDFG. The architecture for a chip may retrieve a data table from a database. The data table may be associated with the architecture for a chip. Finally, the algorithm may be executed against the data table, such that an action included in the algorithm is performed.