Samsung Electronics Co., Ltd.

Kongju National University Industry-university Cooperation Foundation

Young-sam Shin

Jeong-joon Yoo

Jae-don Lee

Seung-won Lee

Won-Jong Lee

Keun-soo Yim

Min-kyu Jeong

Han-cheol Kim

Jae-Don Lee

Dong-hoon Yoo

Jung-Keun Park

Keun Soo Yim

Hyun-sang Park

Soo-jung Ryu

Jeong-Wook Kim

Chae-seok Im

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

A method and apparatus for generating an acceleration structure. Primitives corresponding to at least one object on which rendering is to be performed may be aligned. Candidate split points are determined by scanning the aligned primitives. The candidate split points are stored according to a predetermined rule, and the acceleration structure is generated by sequentially reading the stored candidate split points and generating at least one node corresponding to the stored candidate split points.

Method and apparatus for generating acceleration structure

A method for generating an acceleration structure used for ray tracing includes generating a linear code, the linear code representing a position of each of a plurality of primitives included in a three-dimensional (3D) space, arranging the plurality of primitives according to the generated linear code, determining a rate of change of a size of a generated bounding box while sequentially inputting the plurality of arranged primitives into the generated bounding box, selecting one of the plurality of arranged primitives based on the rate of change of the size of the generated bounding box and classifying the plurality of arranged primitives into a plurality of determined bounding boxes according to the selected primitive.

A ray tracing method includes determining whether acceleration structure traversal data of a previous ray similar to a received ray is stored in a traversal cache, and reading the stored acceleration structure traversal data, and performing image rendering based on the read acceleration structure traversal data, based on a result of the determining.

Ray tracing method and apparatus

An apparatus and a method of using an acceleration structure in ray tracing, and a method of ray tracing are provided. The method involves setting a bit stack value of a level of an acceleration structure, moving to a child node among the ray-crossing child nodes and setting a route value of a corresponding level of the acceleration structure, and determining a pop level based on one or more bit stack values.

Apparatus and method of using acceleration structure in ray tracing

Provided is a method of accelerating ray tracing. The method includes extracting characteristics of an input ray at a ray scanner, determining a ray with characteristics similar to that of the input ray based on comparing characteristics of the input ray with characteristics of rays used in previous renderings, and conducting a set up for ray tracing of the input ray based on a ray tracing of the determined ray.

Method and apparatus for accelerating ray tracing

Provided are methods and apparatuses of performing ray tracing for rendering an image. The method includes performing, at a ray tracing core, a first intersection test based on a traversal of an acceleration structure using a generated primary ray, generating at least one type of secondary ray based on the first intersection test, classifying the generated secondary rays and storing identification information indicating a starting point and a direction of the secondary rays, and performing a second intersection test and shading using the stored identification information.

Method and apparatus for performing ray tracing for rendering image

A pipeline system includes input buffers, a relay for controlling withdrawal of data stored in the input buffers, and functional blocks for performing one or more processing operations. A method of operating a pipeline system includes withdrawing data from one of input buffers and performing different one or more processing operations.

Pipeline system including feedback routes and method of operating the same

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 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.

Growing community of inventors

Hwaseong-si, South Korea

Young-sam Shin