Samsung Electronics Co., Ltd.

Jeong-joon Yoo

Young-sam Shin

Jae-don Lee

Keun-soo Yim

Seung-won Lee

Min-kyu Jeong

Han-cheol Kim

Dong-hoon Yoo

Jung-Keun Park

Kyoung-ho Kang

Keun Soo Yim

Chae-seok Im

Woon-gee Kim

Dong-Hyun Lee

Soo-Jung Ryu

Woo-shik Kang

Jong-hwa Won

Ja-nam Ku

Sundeep Krishnadasan

Soo-jung Ryu

Jae-Don Lee

Jeong-Wook Kim

Chae-Seok Im

Chang-Woo Baek

Taek-hyun Kim

Jung-keun Park

A computing system is provided. The computing system includes: a memory configured to store a shader program; and a graphics processing unit (GPU) configured to obtain the shader program stored in the memory in a profile mode, the GPU being configured to perform: inserting, into the shader program, one or more monitor associative codes; compiling the shader program, into which the one or more monitor associative codes are inserted, into a language that is capable of being processed by a plurality of cores; and obtaining a runtime performance characteristic of the shader program by executing the compiled shader program and the one or more monitor associative codes.

Graphics processing unit for deriving runtime performance characteristics, computer system, and operation method thereof

An apparatus configured to render an object including a path includes a storage circuit, an arithmetic circuit configured to determine a direction of a plurality of primitives included in the path based on path data, generate primitive direction information, store the primitive direction information in the storage circuit, and generate a winding number of each of a plurality of pixels using the stored primitive direction information, and a determination circuit configured to determine whether a shading operation is to be performed based on the generated winding number.

Apparatus configured to render object including path, computing device including the apparatus, and rendering method of the apparatus

Provided are a graphics processing unit and a graphics processing method for performing path rendering. The graphics processing method may include receiving object information including primitive information regarding the object; generating a primitive mask with respect to respective pixels, the primitive mask corresponding to the primitive information and including a plurality of bits; generating, based on the primitive mask, winding numbers with respect to the respective pixels; and rendering the pixels, based on the winding numbers.

Graphics processing unit that performs path rendering, and a method of operating the same

Provided is a method of rendering a curve. The method includes determining a tessellation level of dividing a curve based on a control point of the curve, generating at least one triangle and at least two first sub-curves corresponding to the curve based on the tessellation level, and rendering the at least two first sub-curves and the at least one triangle.

Method and apparatus for rendering curve

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.

Method and apparatus for preventing stack overflow in embedded system

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.

Method, medium and apparatus scheduling tasks in a real time operating system

Provided are a multitasking method and apparatus. By continuously maintaining the intrinsic information of each peripheral processing unit of when a process-centered task is stopped, when a reconfigurable array stops executing the process-centered task and executes a different process-centered task, by stopping executing a control-centered task and executing a reconfiguration task, only when the reconfigurable array receives an execution request of the reconfiguration task while the reconfigurable array is performing the control-centered task, or by causing a predetermined number of processing units to execute each of a plurality of reconfiguration tasks that are to be simultaneously executed by the reconfigurable array, wherein the predetermined number of processing units is set in consideration of an expected data processing amount required for the reconfiguration task, the reconfigurable array can more quickly complete execution of multitasking.

Multitasking method and apparatus for reconfigurable array

A method, medium and apparatus for storing and restoring a register context for a fast context switching between tasks is disclosed. The method, medium and apparatus may improve overall operating speed of a system by increasing the speed of context switching. The method may include adding an update code for updating information of live registers to a task file that includes a code of a task to perform a specified function, converting the task file having the update code added thereto into a run file, updating the information of the live registers with the update code during running of the task using the run file, and storing a live register context according to the updated information of the registers.

Method, medium and apparatus storing and restoring register context for fast context switching between tasks

A method and apparatus for detecting errors in an application software of an embedded system are provided. The method of detecting errors in an application software includes determining a development language of the application software and an operating system on which the application software is executed; replacing an error detection syntax inserted in order to examine an error in a predetermined function of the application software, with an error detection syntax according to the result of the determination; and performing exception handling for an error occurring in the function according to the result of the replacement, and logging error information according to the exception handling. According to the method and apparatus, an error can be automatically detected and logged irrespective of a development language and an operating system.

Apparatus and method of detecting errors in embedded software

A kernel-aware debugging system, medium, and method. The kernel-aware debugging system may include a kernel-aware debugging interface including a conditional breakpoint setting unit which sets a kernel-aware conditional breakpoint by checking a currently operating object inside a kernel of a target system when a central processing unit (CPU) of the target system stops operating at a particular position where the breakpoint is set and making the CPU proceed to operate when it is determined that it is not intended that the currently operating object be debugged. Moreover, the kernel-aware debugging interface may include a unit which stores control flow information for detecting faults due to asynchronous events, a profiling unit which collects profile information and allows back-tracing when faults occur, and a unit which debugs a synchronization problem between multitasks.

Kernel-aware debugging system, medium, and method

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.

Transmitting and receiving method and apparatus in real-time system

An apparatus for managing memory in a real-time embedded system and a method of allocating, deallocating and managing memory in a real-time embedded system. The apparatus includes a defragmentation unit performing a defragmentation task according to a predetermined priority to collect together memory fragments, and a memory manager allocating or deallocating a predetermined area of memory upon request of a task, and calculating a memory fragmentation rate of the memory to determine a priority of the defragmentation task. The method of managing memory in a real-time embedded system includes determining whether the conditions under which the memory is used vary, and if the condition vary, calculating a memory fragmentation rate of the memory to determine a priority of the defragmentation task according to the memory fragmentation rate.

Apparatus for managing memory in real-time embedded system and method of allocating, deallocating and managing memory in real-time embedded system

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.

Method of managing memory in multiprocessor system on chip

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.

Method, medium and apparatus managing memory

A method of reducing a code size of a program by controlling a control flow of the program using software in a computer system is disclosed. The method includes the steps of storing a first program count of a first instruction in a first buffer when an error occurs while the first instruction having an Operand including Offset and Length is being executed among a plurality of instructions loaded in the code memory, changing a current program count of the code memory to a second program count which is obtained by adding the Offset to the first program count, storing a second instruction, which is located at a position shifted from the second program count by a value of the Length, in a second buffer, replacing the second instruction with a third instruction, which is not recognized by a microprocessor, replacing the third instruction with the second instruction stored in the second buffer when an error occurs while the third instruction is being executed, and changing the current program count of the code memory to a predetermined program count next to the first program count stored in the first buffer.

Method for reducing code size of a program in code memory by dynamically storing an instruction into a memory location following a group of instructions indicated by an offset operand and either a length operand or a bitmask operand of an echo instruction

Growing community of inventors

Yongin-si, South Korea

Jeong-joon Yoo