Abstract: Provided are a power management method and apparatus that minimize power consumption in a virtualization system using different operating systems. The power management method operates on a virtualization layer, and may include: monitoring usage states of real processors actually performing tasks and usage states of virtual processors mapped with the real processors and executing operating systems or applications; predicting workload of a virtual processor; computing the utilization level of a real processor enough for supporting the predicted workload; and reconfiguring the mapping between real processors and virtual processors according to the computation result. Hence, different power management schemes of multiple operating systems or applications are managed at the virtualization layer in an integrated manner, preventing a conflict caused by application of different power management schemes. Power consumption in the overall system can be minimized through prediction of resource usage.

Abstract: A method and apparatus for compiling and executing an application including Central Processing Unit (CPU) source code and Graphic Processing Unit (GPU) source code. The apparatus includes a hardware device including a CPU and a GPU; a compiler that compiles the GPU source code into a GPU virtual instruction; and a hybrid virtualization block that executes an execution file by translating the GPU virtual instruction into GPU machine code.

Abstract: A method and apparatus for dynamic resource allocation in a system having at least one processing unit are disclosed. The method of dynamic resource allocation includes receiving information on a task to which resources are allocated and partitioning the task into one or more task parallel units; converting the task into a task block having a polygonal shape according to expected execution times of the task parallel units and dependency between the task parallel units; allocating resources to the task block by placing the task block on a resource allocation plane having a horizontal axis of time and a vertical axis of processing units; and executing the task according to the resource allocation information. Hence, CPU resources and GPU resources in the system can be used in parallel at the same time, increasing overall system efficiency.

Abstract: A method and apparatus for managing a virtual processor including resources for operating application through a real central processing unit, which includes determining a utilization of a plurality of real CPUs to which a plurality of virtual processors are divided to be allocated; and repartitioning the virtual processors and reallocating the repartitioned virtual processor to at least part of the real CPUs, when the utilization of any one of the real CPUs is at a threshold or less.

Abstract: A virtualization system for supporting at least two operating systems and resource allocation method of the virtualization system are provided. The method includes allocating resources to the operating systems, calculating, when one of the operating systems is running, workloads for each operating system, and adjusting resources allocated to the operating systems according to the calculated workloads. The present invention determines the workloads of a plurality of operating systems running in the virtualization system and allocates time resources dynamically according to the variation of the workloads.

Abstract: Provided are a power management method and apparatus that minimize power consumption in a virtualization system using different operating systems. The power management method operates on a virtualization layer, and may include: monitoring usage states of real processors actually performing tasks and usage states of virtual processors mapped with the real processors and executing operating systems or applications; predicting workload of a virtual processor; computing the utilization level of a real processor enough for supporting the predicted workload; and reconfiguring the mapping between real processors and virtual processors according to the computation result. Hence, different power management schemes of multiple operating systems or applications are managed at the virtualization layer in an integrated manner, preventing a conflict caused by application of different power management schemes. Power consumption in the overall system can be minimized through prediction of resource usage.

Abstract: The present invention relates to a terminal and a method for executing an application in the same, including the steps of: confirming the weight of the application when a code of the application to be executed is inputted; calculating an allocation index using the confirmed weight; selecting a processing device for executing the application between a central processing unit and a graphics processing unit through the calculated application index; and executing the application through the selected processing device. Accordingly, the present invention determines whether the execution of the application is assigned to the central processing unit or the graphics processing unit according to the weight designated by the user. Thus, the present invention can prevent the tipping effect of the workload only to one processing unit which is caused by an increase in the degree of freedom for the workload distribution.

Abstract: A method and apparatus for compiling and executing an application including Central Processing Unit (CPU) source code and Graphic Processing Unit (GPU) source code. The apparatus includes a hardware device including a CPU and a GPU; a compiler that compiles the GPU source code into a GPU virtual instruction; and a hybrid virtualization block that executes an execution file by translating the GPU virtual instruction into GPU machine code.

Abstract: A method and apparatus for dynamic resource allocation in a system having at least one processing unit are disclosed. The method of dynamic resource allocation includes receiving information on a task to which resources are allocated and partitioning the task into one or more task parallel units; converting the task into a task block having a polygonal shape according to expected execution times of the task parallel units and dependency between the task parallel units; allocating resources to the task block by placing the task block on a resource allocation plane having a horizontal axis of time and a vertical axis of processing units; and executing the task according to the resource allocation information. Hence, CPU resources and GPU resources in the system can be used in parallel at the same time, increasing overall system efficiency.

Abstract: A virtualization system for supporting at least two operating systems and resource allocation method of the virtualization system are provided. The method includes allocating resources to the operating systems, calculating, when one of the operating systems is running, workloads for each operating system, and adjusting resources allocated to the operating systems according to the calculated workloads. The present invention determines the workloads of a plurality of operating systems running in the virtualization system and allocates time resources dynamically according to the variation of the workloads.

Abstract: A method and apparatus for managing a virtual processor including resources for operating application through a real central processing unit, which includes determining a utilization of a plurality of real CPUs to which a plurality of virtual processors are divided to be allocated; and repartitioning the virtual processors and reallocating the repartitioned virtual processor to at least part of the real CPUs, when the utilization of any one of the real CPUs is at a threshold or less.