Multi-core system and method of controlling operation of the same
AssigneeSamsung Electronics Co., Ltd.
InventorsBumgyu Park, Jonglae Park
Life of this patent
Estimating the term…
Abstract
A method of controlling an operation of a multi-core system including a plurality of processor cores, includes, monitoring task execution delay times with respect to tasks respectively assigned to the plurality of processor cores, monitoring core execution delay times with respect to the plurality of processor cores and controlling an operation of the multi-core system based on the task execution delay times and the core execution delay times.
Claims16
A method of controlling an operation of a system on chip (SoC) including a processor comprising a plurality of processor cores, the method comprising:
- the processor executing a kernel of an operating system to monitor a task queue of each of the processor cores for determining a task execution delay time for each task among a plurality of tasks respectively assigned to the plurality of processor cores, to generate a plurality of task execution delay times;
- determining, by the kernel, a core execution delay time for each core among the plurality of processor cores from a single time among the task execution delay times associated with the tasks assigned to the corresponding core, to generate a plurality of core execution delay times, wherein the single time is a largest time among the task execution delay times associated with the tasks assigned to the corresponding core;
- determining, by the kernel, whether a delay has occurred in a first processor core among the processor cores based on the core execution delay time of the first processor core;
- outputting, by the kernel, a control request to a performance controller of the SoC when the kernel determines the delay has occurred;
- and
- increasing, by the performance controller, a power level of the first processor core in response to receipt of the control request.
A method of controlling an operation of a system on chip (SoC) including a processor comprising a plurality of processor cores, the method comprising:
- the processor executing a kernel of an operating system to monitor a task queue of each of the processor cores for determining a task execution delay time for each task among a plurality of tasks respectively assigned to the plurality of processor cores, to generate a plurality of task execution delay times;
- determining, by the kernel, a core execution delay time for each core among the plurality of processor cores from a single time among the task execution delay times associated with the tasks assigned to the corresponding core, to generate a plurality of core execution delay times, wherein the single time is a largest time among the task execution delay times associated with the tasks assigned to the corresponding core;
- determining, by the kernel, whether a delay has occurred in a first processor core among the processor cores based on the core execution delay time of the first processor core;
- and
- relocating, by the kernel, a given task of the tasks assigned to the first processor core to a second other processor core among the processor cores when it is determined that the delay has occurred.
A method of controlling an operation of a system on chip (SoC) including a processor comprising a plurality of processor cores, the method comprising:
- the processor executing a kernel of an operating system to monitor a task queue of each of the processor cores for determining a task execution delay time for each task among a plurality of tasks respectively assigned to the plurality of processor cores, to generate a plurality of task execution delay times;
- determining, by the kernel, a core execution delay time for each core among the plurality of processor cores from a single time among the task execution delay times associated with the tasks assigned to the corresponding core, to generate a plurality of core execution delay times, wherein the single time is a largest time among the task execution delay times associated with the tasks assigned to the corresponding core;
- determining, by the kernel, whether a delay has occurred in a first processor core among the processor cores based on the core execution delay time of the first processor core;
- and
- increasing, by the kernel, a scheduling period of the first processor core when it is determined that the delay has occurred.
Dependencies are inferred from the claim text.