Abstract: A method and apparatus for efficiently allocating jobs to processing cores included in a computing system, are provided. The multi-core system includes a plurality of cores that may collect performance information of each respective core while the cores are executing a requested task in parallel. The multi-core system allocates additional jobs of the requested task to the cores based on the performance information and the amount of jobs remaining.

Abstract: There are a secondary battery having a pouch-type outer casing and a manufacturing method thereof. In one embodiment, a secondary battery includes an electrode assembly and an outer casing. The electrode assembly has positive and negative electrode plates, a separator interposed therebetween, and positive and negative electrode tabs having one ends respectively connected to the positive and negative electrode plates. The outer casing accommodates the electrode assembly so that the other ends of the positive and negative electrode tabs are extracted from a first side to the exterior thereof. The outer casing has a sealing portion sealed at least twice. The sealing portion is primarily sealed to be fractured under a predetermined internal pressure of the outer casing. After the aging of a battery, the sealing portion is fractured under the predetermined internal pressure, thereby exhausting internal gas. After the exhaustion of the internal gas, the sealing portion is secondarily sealed.

Abstract: An apparatus and method for managing stacks in a virtual machine are provided. The apparatus includes a first memory which checks the space of a stack chunk and allocates a frame pointer if at least one of a push and a pop are performed in a virtual machine; and a second memory which is connected with an external bus, and stores frame pointers copied from the first memory via the external bus.

Abstract: A method and apparatus for changing a channel in a digital broadcasting receiver and for hiding a delay that occurs due to the change of the channel are provided. The method includes receiving broadcasting data of at least one channel except for a current channel by using a time division method, based on a pre-set schedule; storing the received broadcasting data; and when a control signal for changing a channel is input, outputting broadcasting contents of the changed channel, which corresponds to the control signal, to the display device by using the stored broadcasting data.

Abstract: An apparatus and method for accelerating Java translation are provided. The apparatus includes a lookup table which stores an lookup table having arrangements of bytecodes and native codes corresponding to the bytecodes, a decoder which generates pointer to the native code corresponding to the feed bytecode in the lookup table, a parameterized bytecode processing unit which detects parameterized bytecode among the feed bytecode, and generating pointer to native code required for constant embedding in the lookup table, a constant embedding unit which embeds constants into the native code with the pointer generated by the parameterized bytecode processing unit, and a native code buffer which stores the native code generated by the decoder or the constant embedding unit.

Abstract: Provided are a method and apparatus for increasing task-execution speed, and, more particularly, a method and apparatus for increasing task-execution speed by compiling code to bytecodes, and executing native code in units of blocks instead of bytecodes, in which a block is a group of a series of bytecodes. The apparatus includes a receiving unit which receives a bytecode, a control unit which identifies whether the received bytecode is the last bytecode of a block, and a transmitting unit which transmits an address of a first native code of one or more native codes that correspond to one or more bytecodes included in the block based on the identification result.

Abstract: A parallel processing apparatus and method are provided. The parallel processing apparatus includes: a control unit determining whether one or more threads can access one or more control blocks of a first container that exists in a direction in which at least one of the one or more threads perform a task; a container generating unit generating a second container that includes one or more control blocks on the basis of the result of the determination; and a container management unit connecting the one or more control blocks of the first container or the one or more control blocks of the first container and the one or more control blocks of the second container and control blocks in which the one or more threads perform tasks, in a ring shape.

Abstract: An apparatus and method for managing stacks in a virtual machine are provided. The apparatus includes a first memory which checks the space of a stack chunk and allocates a frame pointer if at least one of a push and a pop are performed in a virtual machine; and a second memory which is connected with an external bus, and stores frame pointers copied from the first memory via the external bus.

Abstract: A motion estimation method for enhancing a video compression speed, and a video encoder using the same are provided. The motion estimation method includes determining a global motion type of a previous frame from motion vectors of the previous frame, setting a search area for a specified motion block included in a current frame based on the global motion type, and searching for a motion vector within the set search area.

Abstract: A system and method for reducing the bytecode execution time in the Java virtual machine are disclosed. The system includes a DB cache to store old machine code converted from a bytecode, a machine code change unit to change the old machine code to new machine code by removing a predetermined instruction included therein, a register management unit to manage stack data necessary for operations of the new machine code and a register file to provide a register region to conduct the operations, and a machine code information storage unit to store basic block information on the new machine code and spill and fill execution information in the stack of the register file.

Abstract: A system for shortening the class loading process in a Java program according to the present invention includes a class loader unit for loading Java program class files from an auxiliary memory, performing linking and initialization processes and generating runtime data; a first memory unit for maintaining the runtime data generated by the class loader unit in an accessible state; a second memory unit for storing the runtime data, which have been loaded into the first memory unit in an accessible state, in the form of images; a runtime data search unit for loading the runtime data, which have been stored in the second memory unit in the form of images, into the first memory unit upon the request of the class loader unit; and an execution unit for executing the runtime data that have been loaded into the first memory unit in an accessible state.