Described herein are systems, methods, and software to manage the migration of workloads from a first computing system to a second computing system. In one implementation, the first computing system identifies a request to migrate one or more workloads to a second computing system. In response to the request, the first computing system disables one or more services and disables all but one network interface on the first computing system. The first computing system then communicates configuration information to the second computing system and monitors for a cancel notification from the second computing system using the remining network interface. After receiving the cancel notification, the first computing system enables the other network interfaces may initiate the one or more services.

Aspects of workload reallocation within a software-defined data center (SDDC) undergoing an upgrade are described. As upgrades become available for services and other types of applications installed on a cluster of host devices within a data center, an upgrade of the installed services may be required for each of the host devices. During a cluster upgrade, the order in which hosts in the cluster are upgraded is determined as a function of evacuation costs and evacuation policies associated with each host device in the computing cluster. In addition, a maintenance cost associated with a workload needing to be evacuated from a host undergoing an upgrade is determined based on the upgrade sequence. The maintenance cost can then be used as a factor for selecting an optimal candidate host for migrating the workload to when the host the workload is currently running on is being upgraded.

A method of on-boarding a virtual infrastructure management (VIM) server appliance in which VIM software for locally managing a software-defined data center (SDDC) is installed, to enable the VIM server appliance to be centrally managed through a cloud service includes upgrading the VIM server appliance from a current version to a higher version that supports communication with agents of the cloud service, modifying configurations of the upgraded VIM server appliance according to a prescriptive configuration required by the cloud service, and deploying a gateway appliance for running the agents of the cloud service that communicate with the cloud service and the upgraded VIM server appliance.

Methods, systems, and devices for providing computer implemented services using managed systems are disclosed. To provide the computer implemented services, the managed systems may need to operate in a predetermined manner conducive to, for example, execution of applications that provide the computer implemented services. Similarly, the managed system may need access to certain hardware resources and software resources to provide the desired computer implemented services. To improve the likelihood of the computer implemented services being provided, the managed devices may be managed using a subscription based model. The subscription model may utilize a highly accessible service to facilitate system management. To facilitate system management, the highly available service may take into account both historic use of managed systems and changes to subscriptions to ascertain point in time when subscription limits may be reached. The identified points in time may be used to drive management decisions.

Methods, apparatus, and processor-readable storage media for automatically classifying cloud infrastructure components for prioritized multi-tenant cloud environment resolution using artificial intelligence techniques are provided herein. An example computer-implemented method includes obtaining historical data pertaining to a multi-tenant cloud environment; training one or more artificial intelligence techniques, using at least a portion of the obtained historical data, for classifying cloud infrastructure components for prioritizing incident-related resolution; classifying one or more cloud infrastructure components, within the multi-tenant cloud environment and associated with one or more server-related issues, into one or more of multiple resolution priority classes; and performing one or more automated actions based at least in part on the classifying of the one or more cloud infrastructure components.

Methods, systems, and computer storage media storing instructions for managing processing system efficiency. One of the methods includes obtaining data splitting a plurality of general-purpose processing units in a processing system into a high-priority domain and a low-priority domain, wherein the general-purpose processing units in the high-priority domain are assigned to perform one or more tasks comprising one or more high-priority tasks, and the general-purpose processing units in the low-priority domain are assigned to perform one or more low-priority tasks; and during runtime of the processing system, obtaining memory usage measurements that characterize usage of system memory by the high-priority domain and the low-priority domain; and adjusting, based on the memory usage measurements, a configuration of (i) the high-priority domain, (ii) the low-priority domain, or (iii) both to adjust utilization of the system memory by the general-purpose processing units.

A system for storing and extracting elements according to their priority takes into account not only the priorities of the elements but also three additional parameters, namely, a priority resolution p.sub.Δ and two priority limits p.sub.min and p.sub.max. By allowing an ordering error if the difference in the priorities of elements are within the priority resolution, an improvement in performance is achieved.

Scheduling work of a machine learning application includes instantiating kernel objects by a computer processor in response to input of kernel definitions. Each kernel object is of a kernel type indicating a compute circuit. The computer processor generates a graph in a memory. Each node represents a task and specifies an assignment of the task to one or more of the kernel objects, and each edge represents a data dependency. Task queues are created in the memory and assigned to queue tasks represented by the nodes. Kernel objects are assigned to the task queues, and the tasks are enqueued by threads executing the kernel objects, based on assignments of the kernel objects to the task queues and assignments of the tasks to the kernel objects. Tasks are dequeued by the threads, and the compute circuits are activated to initiate processing of the dequeued tasks.

A real-time computational device includes a programmable real-time processor, a communications input port which is connected to the programmable real-time processor through a first broadside interface, and a communications output port which is connected to the programmable real-time processor through a second broadside interface. Both broadside interfaces enable 1024 bits of data to be transferred across each of the broadside interfaces in a single clock cycle of the programmable real-time processor.

A method for scheduling tasks on a processor includes detecting, in a task selection device communicatively coupled to the processor, a condition of each of a plurality of components of a computer system comprising the processor, determining a plurality of tasks that can be next executed on the processor based on the condition of each of the plurality of components, transmitting a signal to an arbiter of the task selection device that the plurality of tasks can be executed, determining, at the arbiter, a next task to be executed on the processor, storing, by the task selection device, the entry point address of the next task to be executed on the processor, and transferring, by the processor, execution to the stored entry point address of the next task to be executed.