A computing system may implement a low priority arbitration interrupt method that includes receiving a message signaled interrupt (MSI) message from an input output hub (I/O hub) transmitted over an interconnect fabric, selecting a processor to interrupt from a cluster of processors based on arbitration parameters, and communicating an interrupt service routine to the selected processor, wherein the I/O hub and the cluster of processors are located within a common domain.

Embodiments of the present invention provide a system for intelligently optimizing the utilization of clusters. The system is configured to continuously gather real-time hardware telemetric data associated with one or more entity systems via a hardware telemetric device, continuously convert the real-time hardware telemetric data into a first color coded representation, receive one or more tasks associated with one or more entity applications, queue the one or more tasks associated with the one or more entity applications, determine hardware requirements associated with the one or more tasks, determine one or more attributes associated with the one or more tasks, convert the hardware requirements and the one or more attributes of the one or more tasks into a second color coded representation, and allocate the one or more tasks to the one or more entity systems based on the first color coded representation and the second color coded representation.

Techniques are disclosed relating to tracking compute workgroup completions in a distributed processor. In some embodiments, an apparatus includes a plurality of shader processors configured to perform operations for compute workgroups included in compute kernels, a master workload parser circuit, a plurality of distributed workload parser circuits, and a communications fabric connected to the plurality of distributed workload parser circuits and the master workload parser circuit. In some embodiments, a distributed workload parser circuit is configured to maintain, for each of a set of the shader processors, a data structure that specifies a count of workgroup completions for one or more kernels processed by the shader processor, determine, for the set of shader processors based on counts of workgroup completions for a first kernel, an aggregate count of completions to report for the first kernel, send the aggregate count to the master workload parser circuit over the communications fabric, and adjust the data structures to reflect counts included in the aggregate count.

An electronic apparatus operated based on an OS is provided. The electronic apparatus includes a storage to store the OS, a virtual device program capable of generating a virtual device executed based on the OS, and at least one program; and at least one processor to execute the virtual device program to generate the virtual device, and to execute the OS to determine whether a first program having an administration authority assigned by the OS from among the at least one program has access authority to data about the virtual device in response to an attempt to access the data from the first program and to selectively permit the access to the data based on the determined access authority. With this, the electronic apparatus may restrain the access to the virtual device or the data thereabout according to a presence of the access authority, thereby safely protecting the virtual device or the data.

A heterogeneous computing system described herein includes a parallel processing module shared among a set of heterogeneous processors. The processors have different processor types, and each processor includes an internal memory unit to store its current context. The parallel processing module includes multiple execution units. A switch module is coupled to the processors and the parallel processing module. The switch module is operative to select, according to a control signal, one of the processors to use the parallel processing module for executing an instruction with multiple data entries in parallel.

Each of a plurality of engines executes data processing. While any engine of the plurality of engines is executing data processing as an execution engine, an engine selection unit (102) selects a takeover engine to take over execution of execution data processing being data processing executed by the execution engine, from the plurality of engines. An engine execution management unit (103) makes the execution engine suspend execution of the execution data processing, and makes the takeover engine take over execution of the execution data processing.

A method and device for data task scheduling, a storage medium, and a scheduling tool are involved. The method includes: acquiring a data task to be executed at present which is configured with a task relationship; in response to that the data task to be executed at present satisfies a preset condition, ranking, according to the task relationship, the data task to be executed at present to create a data task queue; acquiring a load situation of a plurality of node servers, to determine a target node server; and sending, based on the data task queue, the data task to be executed at present to the target node server for processing.

The illustrative embodiments described herein provide systems and methods for notifying a user when a set of characters are identified in a media file. In one embodiment, a method includes receiving a set of characters inputted by the user of a computing device, playing the media file, transcribing the media file to form a transcription, and determining whether the transcription of the media file includes the set of characters. The method also includes initiating a notification prompt on a graphical user interface of the computing device in response to determining that the media file includes the set of characters.

A method for scheduling guest systems and/or threads in a virtualization system that assigns processor time and memory space to guest systems and including a virtualization system scheduler, the method including running a first guest system that includes at least one first thread and at least one second thread running in the first guest system, and a guest system scheduler that assigns processing time to the at least one second thread, assigning a plurality of time reservations to the first guest system, wherein the plurality of time reservations include a first time reservation associated to one first thread and a second time reservation associated to the guest system scheduler of the first guest system, assigning processor time to the first guest system according to the second time reservation, and assigning processor time to the at least one first thread of the first guest system according to the first time reservation.

An information processing system for a multitenant service is proposed. The system includes memory queues and a processor. Processing requests issued from tenants are received through a network, where the number of the memory queues is smaller than the number of the tenants, and a priority is given to each of the memory queues. A priority of the processing request issued from each of the tenants is specified, based on a rank set with respect to each of the tenants and the amount of a used calculation resource for a predetermined period of time for each of the tenants, and the processing requests are retained in the memory queues according to the priorities. The retained processing requests are extracted from the memory queues in an order specified based on the priorities to execute processing corresponding to the processing requests.