摘要:
Die Erfindung betrifft ein Verfahren zur Ausführung eines industriellen Automatisierungsprogramms (user program) auf einer Automatisierungskomponente mit mehreren Prozessorkernen (Core 0, Core 1), wobei das Automatisierungsprogramm (user program) mit einem modularen Betriebssystem zusammenwirkt. Dabei werden zumindest einige oder alle Module des Betriebssystems und/oder das Automatisierungsprogramm (user program) funktionalen Kategorien (K1, K2, K3) zugeordnet, wobei anhand der jeweils zugeordneten Kategorie (K1, K2, K3) diese Module jeweils einem der Prozessorkerne (Core 0, Core 1) zur Ausführung zugewiesen werden. Dadurch können die Module und die durch die Module abzuarbeitenden Prozesse ("threads") derart auf die verfügbaren Prozessorkerne verteilt, dass eine gegenseitige Beeinflussung (Behinderung) und die damit verbundenen Performance-Nachteile minimiert oder verhindert werden. Dabei ist dieselbe Software auch in unveränderter Form auf anderen Systemen mit abweichender Anzahl an Prozessorkernen ablauffähig, so dass keine spezifischen Varianten erzeugt werden müssen.
摘要:
A method of managing a control system includes: executing a first iteration of a program in a first processor core of a multi-core computer system during a first period (S1501), executing a second iteration of the program in a second processor core of the multi-core system during a second period that overlaps the first period (S1502); and using outputs of the iterations to control the control system (S1503).
摘要:
Systems and methods for instruction entity allocation and scheduling on multi-processors is provided. In at least one embodiment, a method for generating an execution schedule for a plurality of instruction entities for execution on a plurality of processing units comprises arranging the plurality of instruction entities into a sorted order and allocating instruction entities in the plurality of instruction entities to individual processing units in the plurality of processing units. The method further comprises scheduling instances of the instruction entities in scheduled time windows in the execution schedule, wherein the instances of the instruction entities are scheduled in scheduled time windows according to the sorted order of the plurality of instruction entities and organizing the execution schedule into execution groups.
摘要:
Load balancing may be achieved in heterogeneous computing environments by first evaluating the operating environment and workload within that environment. Then, if energy usage is a constraint, energy usage per task for each device may be evaluated for the identified workload and operating environments. Work is scheduled on the device that maximizes the performance metric of the heterogeneous computing environment.
摘要:
A method is disclosed for reducing peak power usage in a large computer system with multiple nodes by identifying jobs which can be scheduled to run at reduced frequency in order to reduce total power usage during certain time periods. The backfill scheduler of the computer system's operating system performs steps providing for selected jobs on selected nodes of the computer system to be run at reduced frequency such that those jobs are partially processed during previously underutilized holes in the computer system schedule in order to reduce overall peak power during a period of processing.
摘要:
A software engine for decomposing work to be done into tasks, and distributing the tasks to multiple, independent CPUs for execution is described. The engine utilizes dynamic code generation, with run-time specialization of variables, to achieve high performance. Problems are decomposed according to methods that enhance parallel CPU operation, and provide better opportunities for specialization and optimization of dynamically generated code. A specific application of this engine, a software three dimensional (3D) graphical image renderer, is described.
摘要:
A system and method are provided for sequencing radio events in a mobile device with a multi downlink multi carrier receiver. In the mobile device, there is a processor (102) in communication with a timing control unit (TCU), whereby the TCU (150) is in communication with two or more radios (14 and 16). The processor collects one or more radio events corresponding to the two or more radios and then sorts the radio events from highest priority to lowest priority to form a sorted list. The processor then loads the sorted list, beginning with a highest priority radio event, onto the TCU.
摘要:
A method for scheduling schedulable entities onto an execution timeline for a processing entity in a constrained environment includes determining available capacity on the execution timeline for the processing entity based on constraints on the execution timeline over a plurality of time periods, wherein schedulable entities can only be scheduled onto the execution timeline during schedulable windows of time that are not precluded by constraints. The method further includes determining whether enough available capacity exists to schedule a schedulable entity with a budget at a rate. The method further includes when enough available capacity exists to schedule the schedulable entity with the budget at the rate, scheduling the schedulable entity onto the execution timeline for the processing entity during a schedulable window of time. The method further includes when the schedulable entity is scheduled onto the execution timeline, updating available capacity to reflect the capacity utilized by the schedulable entity.
摘要:
Parallel processor task management in a cell processor having a main memory, one or more central processors and one or more secondary processing elements, each secondary processing element having a processor and a local memory is described. A task manager running on one or more of the secondary processing elements reads one or more task definitions stored in the main memory into the local memory of a selected secondary processing element. Based on information contained in the task definitions the secondary processing element loads code and/or data related to the task definitions from the main memory into the local memory associated with the selected secondary processing element. The selected secondary processing element then performs one or more tasks using the code and/or data.
摘要:
This invention relates to scheduling threads in a multicore processor. Executable transactions may scheduled using at least one distribution queue, which lists executable transactions in order of eligibility for execution, and multilevel scheduler which comprises a plurality of linked individual executable transaction schedulers. Each of these includes a scheduling algorithm for determining the most eligible executable transaction for execution. The most eligible executable transaction is outputted from the multilevel scheduler to the at least one distribution queue.