Abstract: Provided is a hardware acceleration apparatus, method and computer-readable medium efficiently processing multi-core synchronization. A processor core that fails to acquire a lock variable may be switched to a low power sleep mode and a waste of power may be reduced. Additionally, when a lock variable is returned, a wakeup signal may be transmitted to a processor core operated in the low power sleep mode, and the processor core may be activated.

Abstract: Provided is a method of managing memory in a multiprocessor system on chip (MPSoC). According to an aspect of the present invention, locality of memory can be reflected and restricted memory resources can be efficiently used by determining a storage location of a variable or a function which corresponds to a symbol with reference to a symbol table based on memory access frequency of the variable or the function, comparing the determined storage location and a previous storage location, and copying the variable or the function stored in the previous storage location to the determined storage location if the determined storage location is different from the previous storage location.

Abstract: Provided is a computing system having a hierarchical memory structure. When a data structure is allocated with respect to a task processed in the computing system, the data structure is divided and a portion of the data structure is allocated to a high speed memory of the hierarchical memory structure and a remaining data structure is allocated to a low speed memory of the hierarchical memory.

Abstract: Disclosed are a system, method and computer-readable medium related to processing debug information from an embedded system. Source code of an application program to be used in an embedded system may be compiled by a computing system. The application program may include a debug code line. A minimum amount of debug information is stored in an embedded system, reducing memory overhead and waste of clock cycles of a processor.

Abstract: A method and apparatus for managing a memory are provided. It is possible to rapidly recover the area allocated or desired to be returned by easily recognizing a range of the area allocated or desired to be returned over the entire area of the memory by recognizing an original area of a predetermined memory chunk interrupted by a neighboring memory chunk among a series of memory chunks that make up the memory by considering an original area of the neighboring memory chunk and by recovering the predetermined memory chunk and the recognized area to their original areas, when the area allocated to or returned by an application program is interrupted.

Abstract: Disclosed is a scratch pad memory management device and a method thereof. The scratch pad memory management device divides a scratch pad memory into a plurality of unit blocks, maintains a memory allocation table corresponding to indices of the plurality of unit blocks in a main memory, and manages the scratch pad memory.

Abstract: Provided is a method of managing memory in a multiprocessor system on chip (MPSoC). According to an aspect of the present invention, locality of memory can be reflected and restricted memory resources can be efficiently used by determining a storage location of a variable or a function which corresponds to a symbol with reference to a symbol table based on memory access frequency of the variable or the function, comparing the determined storage location and a previous storage location, and copying the variable or the function stored in the previous storage location to the determined storage location if the determined storage location is different from the previous storage location.

Abstract: Provided is a method of managing memory in a multiprocessor system on chip (MPSoC). According to an aspect of the present invention, locality of memory can be reflected and restricted memory resources can be efficiently used by determining a storage location of a variable or a function which corresponds to a symbol with reference to a symbol table based on memory access frequency of the variable or the function, comparing the determined storage location and a previous storage location, and copying the variable or the function stored in the previous storage location to the determined storage location if the determined storage location is different from the previous storage location.

Abstract: A central processing unit (CPU) and a real-time scheduling method applicable in the CPU are disclosed. The CPU may determine a first task set and a second task set from among assigned tasks, schedule the determined first task set in a single core to enable the task to be processed, and schedule the determined second task set in a multi-core to enable the task to be processed.

Abstract: Provided is a method of managing memory in a multiprocessor system on chip (MPSoC). According to an aspect of the present invention, locality of memory can be reflected and restricted memory resources can be efficiently used by determining a storage location of a variable or a function which corresponds to a symbol with reference to a symbol table based on memory access frequency of the variable or the function, comparing the determined storage location and a previous storage location, and copying the variable or the function stored in the previous storage location to the determined storage location if the determined storage location is different from the previous storage location.

Abstract: A method and apparatus for managing a memory are provided. It is possible to rapidly recover the area allocated or desired to be returned by easily recognizing a range of the area allocated or desired to be returned over the entire area of the memory by recognizing an original area of a predetermined memory chunk interrupted by a neighboring memory chunk among a series of memory chunks that make up the memory by considering an original area of the neighboring memory chunk and by recovering the predetermined memory chunk and the recognized area to their original areas, when the area allocated to or returned by an application program is interrupted.

Abstract: A scheduling method, medium and apparatus are provided. In the scheduling method, medium and apparatus, it is possible to prevent the possibility that the order between the priorities of the tasks represented by the expired timers and the tasks requested by the interrupt is reversed while also not deteriorating the performance of a real time operating system (RTOS), even though the number of timers expired when the interrupt occurs or that are already expired before the interrupt occurs is large, by selecting a timer for representing a point of time corresponding to a point of time when an interrupt occurs from among one or more timers each of which representing a task, a point of time assigned to the tasks, and a priority assigned to the task and executing a task represented by the selected timer and one or more tasks requested by the interrupt in order of priority.

Abstract: A method and apparatus transmitting and receiving in a real-time system are disclosed. The method of transmitting in a real-time system includes scheduling a task included in a socket based on a predetermined transmission option designated to the socket, and transmitting a packet generated by the scheduled task based on the predetermined transmission option, so that real-time communications of a network communication can be secured and resources of the system can be efficiently used, thereby, transmitting and receiving data according to the required characteristics of transmission and reception.

Abstract: Provided is a method and apparatus for preventing a stack overflow in an embedded system. The method of preventing a stack overflow includes: reading a maximum stack usage of at least one function for executing a requested operation from maximum stack usages of functions provided from a kernel, which are stored in advance; and processing the requested operation on the basis of the read maximum stack usage of the at least one function and a size of a usable region in a stack for the requested operation. Accordingly, the stack overflow can be prevented without generating a run-time overhead.