Abstract:
An operating method of a system-on-chip (SoC) which includes a processor including a first core and a dynamic voltage and frequency scaling (DVFS) module and a clock management unit (CMU) for supplying an operating clock to the first core, the operating method including: obtaining a required performance of the first core; finding available frequencies meeting the required performance; obtaining information for calculating energy consumption for each of the available frequencies; calculating the energy consumption for each of the available frequencies, based on the information; determining a frequency, which causes minimum energy consumption, from among the available frequencies as an optimal frequency; and
adjusting an operating frequency to be supplied to the first core to the optimal frequency.
Abstract:
A semiconductor device is provided. The semiconductor device includes a processing device that provides resource usage information including a utilization value; and a prediction information generating device that generates resource usage prediction information based on the resource usage information and provides the resource usage prediction information to the processing device. The prediction information generating device includes: an error calculator to calculate an error value between the utilization value and a predicted value included in the resource usage prediction information; a margin value calculator to receive the error value from the error calculator and calculate a margin value using the error value; an anchor value calculator to calculate an anchor value using the utilization value; and a predictor to output the predicted value using the anchor value and the margin value. The processing device controls resource allocation of the processing device based on the resource usage prediction information.
Abstract:
A scheduling method of a system on chip including a multi-core processor includes receiving a schedule-requested task, converting a priority assigned to the schedule-requested task into a linear priority weight, selecting a plurality of candidate cores, to which the schedule-requested task will be assigned, from among cores of the multi-core processor, calculating a preemption compare index indicating a current load state of each of the plurality of candidate cores, comparing the linear priority weight with the preemption compare index of the each of the plurality of candidate cores to generate a comparison result, and assigning the schedule-requested task to one candidate core of the plurality of candidate cores depending on the comparison result.
Abstract:
A system-on-chip includes a symmetric multi-processor including a plurality of cores, each configured to operate in a high performance operating mode and a low performance operating mode. The system-on-chip further includes a clock management unit configured to provide an operating clock signal to the symmetric multi-processor, a state management unit configured to monitor operating states of the cores, a temperature management unit configured to monitor a temperature of the symmetric multi-processor, and a symmetric multi-processor control unit configured to determine the operating clock signal and the operating states of the cores based on a workload of the symmetric multi-processor. The symmetric multi-processor control unit is further configured to differentially determine a maximum operating clock frequency for the cores based on the temperature and the operating states of the cores, which indicate a quantity of cores that are currently in operation.
Abstract:
An operating method of a system-on-chip (SoC) which includes a processor including a first core and a dynamic voltage and frequency scaling (DVFS) module and a clock management unit (CMU) for supplying an operating clock to the first core, the operating method including: obtaining a required performance of the first core; finding available frequencies meeting the required performance; obtaining information for calculating energy consumption for each of the available frequencies; calculating the energy consumption for each of the available frequencies, based on the information; determining a frequency, which causes minimum energy consumption, from among the available frequencies as an optimal frequency; and adjusting an operating frequency to be supplied to the first core to the optimal frequency.
Abstract:
A method of operating a system-on-chip (SOC) including a central processing unit (CPU) and a target hardware to which a dynamic voltage and frequency scaling (DVFS) is applied, includes determining an operating scheme of the target hardware, setting a DVFS application scheme for applying the DVFS to the target hardware, based on the operating scheme of the target hardware, and performing the DVFS on the target hardware, based on the DVFS application scheme.
Abstract:
A method of dynamically scaling a power level of a microprocessor is provided. The method includes: receiving a plurality of workload rates of a microprocessor in a first duration period; determining a second duration period by adjusting a length of the first duration period; calculating a period workload rate based on the plurality of workload rates in the first duration period; dynamically scaling a power level of the microprocessor; and maintaining the scaled power level of the microprocessor in the second duration period.
Abstract:
A computing device and a method for operating the computing device are provided. The computing device includes a task classifying module and a task allocating and managing module. The task classifying module classifies a task scheduled to be processed by a multi-core processor into an expectable task or a normal task. The task allocating and managing module selects one core of the multi-core processor as a target core and allocates the task scheduled to be processed to the target core. In response to the task scheduled to be processed being classified as the normal task, the task allocating and managing module determines whether to allocate the normal task to the target core depending on whether the target core processes a previously allocated expectable task.
Abstract:
A scheduling method includes calculating required performance for a given task, calculating use performance and real performance of a candidate processor, calculating power corresponding to the real performance, calculating expected energy usage of the candidate processor based on the required performance, the use performance, the real performance, and the calculated power and calculating performance efficiency of the candidate processor by considering a ratio of the expected energy usage to the real performance.
Abstract:
Provided are multi-core control systems. A multi-core control system includes multiple cores including a first core; and a process dependency recognizer configured to recognize a dependency between processes each executed in the respective cores, wherein if the first core waits for a first period of time to execute a first process, the first core recognizes a process on which the first process depends by the process dependency recognizer.