Method for executing sequential code on the scalable processor at increased frequency while switching off the non-scalable processor core of a multicore chip

摘要

Method and scheduler in an operating system, for scheduling processing resources on a multi-core chip. The multi-core chip comprises a plurality of processor cores. The operating system is configured to schedule processing resources to an application to be executed on the multi-core chip. The method comprises allocating a plurality of processor cores to the application. Also, the method comprises switching off another processor core allocated to the application, not executing the sequential portion of the application, when a sequential portion of the application is executing on only one processor core. In addition, the method comprises increasing the frequency of the one processor core executing the application to the second frequency, such that the processing speed is increased more than predicted by Amdahl's law.

主权项

1. A method in an operating system for scheduling a plurality of processor cores on a multi-core chip to an application to be executed on the multi-core chip, the method comprises the steps of:
allocating at least a portion of the plurality of processor cores to the application, wherein the plurality of processor cores comprises at least one core of a scalable type, which is adapted to be switched off and to be operable in any one of a plurality of frequencies, and at least one processor core of a non-scalable type, which is adapted to operate on only a first operating frequency and to be switched off, when a sequential portion of code of the application is executing on only one processor core of the scalable type: switching off at least one processor core of the non-scalable type allocated to the application but not executing the sequential portion of code of the application, and increasing the frequency of the one processor core of the scalable type executing the sequential portion of code of the application, such that the processing speed is increased more than predicted by Amdahl's law, and when the sequential portion of code of the application executing on only one processor core of the scalable type is terminated: restoring the frequency of the one processor core of the scalable type to the frequency performed before the step of increasing the frequency and switching back on the at least one processor core of the non-scalable type.