Disclosed embodiments relate to software control of graphics hardware that supports logical slots. In some embodiments, a GPU includes circuitry that implements a plurality of logical slots and a set of graphics processor sub-units that each implement multiple distributed hardware slots. Control circuitry may determine mappings between logical slots and distributed hardware slots for different sets of graphics work. Various mapping aspects may be software-controlled. For example, software may specify one or more of the following: priority information for a set of graphics work, to retain the mapping after completion of the work, a distribution rule, a target group of sub-units, a sub-unit mask, a scheduling policy, to reclaim hardware slots from another logical slot, etc. Software may also query status of the work.

In a computer system, an orchestration platform includes extensible components that interact with external systems and technology. The platform extension deploys a surrogate component or probe that acts as a bridge between the core platform and the extension technology.

Embodiments described herein provide for an election procedure, in a high availability (“HA”) environment, for a backup controller to assume operations performed by a master controller in the event that the master controller becomes unreachable. The master controller may be associated with (e.g., provisioned on) the same set of hardware as one or more worker nodes, and may control operation of the one or more worker nodes. The election procedure may be performed based on performance metrics, location, or efficiency metrics associated with candidate backup controllers (e.g., cloud-based backup controllers), including performance of communications between particular backup controllers and the one or more worker nodes.

Systems, computer-implemented methods and/or computer program products are provided for facilitating time management of a quantum program at one or more nodes of a system, such as a hybrid classical/quantum system. A system, such as a classic portion of the hybrid system, can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a time management component that can communicate with a node to trigger the node to execute one or more quantum program instructions relative to a counter of the node that is advanced by the communicating. The time management component can advance the counter at the node based upon a combination of time of another node and of a determined actual propagation time for the communicating.

Disclosed embodiments relate to controlling sets of graphics work (e.g., kicks) assigned to graphics processor circuitry. In some embodiments, tracking slot circuitry implements entries for multiple tracking slots. Slot manager circuitry may store, using an entry of the tracking slot circuitry, software-specified information for a set of graphics work, where the information includes: type of work, dependencies on other sets of graphics work, and location of data for the set of graphics work. The slot manager circuitry may prefetch, from the location and prior to allocating shader core resources for the set of graphics work, configuration register data for the set of graphics work. Control circuitry may program configuration registers for the set of graphics work using the prefetched data and initiate processing of the set of graphics work by the graphics processor circuitry according to the dependencies. Disclosed techniques may reduce kick-to-kick transition time, in some embodiments.

Within an interrupt routing structure, an interrupt handler is registered, the registering comprising storing a pointer to the interrupt handler in the interrupt routing structure. Responsive to determining that a received interrupt comprises a queuing bypass flag in a set state, the interrupt handler is executed, the executing bypassing an interrupt queueing mechanism.

Improved techniques for combining human tasks with robotic tasks and/or external tasks in an organized manner to define an automation workflow process for use by a software automation system. A workflow process platform can assist a developer in creating an automation workflow process and/or managing performance of an automation workflow process. The automation workflow process can carry out a process, such as a business process, by interrelating human tasks performed by users with robotic tasks performed by computing machines or external tasks performed by applications (e.g., local or cloud-based). The workflow process platform can be network-based and utilize various users and computing machines that are affiliated with different groups (e.g., teams, departments) of an organization. Advantageously, the improved techniques can enable automation of business processes using various persons, robotic agents and/or applications in an organized and controlled manner.

A speech-processing system may provide access to one or more skills via spoken commands and/or responses in the form of synthesized speech. The system may be capable of keeping one or more skills active in the background while a user interacts (e.g., provides inputs to and/or receives outputs from) with a skill running in the foreground. A background skill may receive some trigger data, and determine to request the system to return the background skill to the foreground to, for example, request a user input regarding an action previously requested by the user. In some cases, the user may invoke a background skill to continue a previous interaction. The system may return the background skill to the foreground. The resumed skill may continue a previous interaction to, for example, to query the user for instructions, provide an update or alert, or continue a previous output.

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.

A computational system includes one or more processors. Each processor has multiple registers, as well attached memory to hold instructions. The processor is coupled to one or more broadside interfaces. A broadside interface allows the processor to load or store an entire widget state in a single clock cycle of the processor. The broadside interface also allows the processor to move and store 32 bytes of information into RAM in less than four to five clock cycles of the processor while the processor concurrently performs one or more mathematical operations on the information while the move and store operation is taking place.