KR20180015564A - Method and apparatus for performing tile-based rendering - Google Patents

Abstract

Disclosed is a method for performing tile-based rendering in a graphics processing device, which includes the steps of: receiving a first draw call used for rendering a first tile of a preceding frame; receiving a second draw call used for rendering a second tile of a succeeding frame corresponding to a position of the first tile; generating a signature of the first draw call and a signature of the second draw call; comparing the signature of the first draw call with the signature of the second draw call; and rendering the second tile by using a rendering result of the first tile according to a comparison result. Accordingly, the present invention can improve the performance of the graphics processing device.

Description

[0001] METHOD AND APPARATUS FOR PERFORMING TILE-BASED RENDERING [0002]

This disclosure relates to a Graphics Processing Unit (GPU), and more particularly, to a method and apparatus for performing tile-based rendering on a GPU.

GPUs, especially GPUs used in relatively low throughput electronic devices such as mobile phones and mobile phones, can facilitate data processing by separating frames into small units. The tiles are processed after being divided into small unit units and can be stitched together to render the image.

Conventionally, all displayed frames associated with data have been processed separately by tiles. However, in most cases, adjacent frames display the same / similar objects. In this case, adjacent frames may contain the same tiles. By rendering a tile of a succeeding frame that is the same as the tile of the preceding frame, the computational overhead can be reduced and the performance of the GPU can be improved as a result.

A method and system for tile rendering. The technical problem to be solved by this embodiment is not limited to the above-mentioned technical problems, and other technical problems can be deduced from the following embodiments.

As a technical means to achieve the above-mentioned technical object, a first aspect of the present disclosure relates to a method for rendering a first tile, comprising: receiving a first draw call used for rendering a first tile of a preceding frame; Receiving a second draw call used to render a second tile of a subsequent frame, corresponding to a position of the first tile; Generating a signature of the first draw call and the second draw call signature; Comparing a signature of the first draw call and a signature of the second draw call; And rendering the second tile using a rendering result of the first tile according to a result of the comparison. The tile-based rendering may be performed in the graphics processing apparatus.

Also, a second aspect of the present disclosure provides a computer program product, comprising: a memory for storing at least one instruction; And at least one processor executing the at least one instruction stored in the memory, wherein the processor executes the one or more instructions to receive a first draw call used to render a first tile of a preceding frame A second draw call used to render a second tile of a subsequent frame corresponding to a position of the first tile, generating a signature of the first draw call and a second draw call signature, Based rendering that compares a signature of a draw call with a signature of the second draw call and renders the second tile using a rendering result of the first tile according to a result of the comparison, Device can be provided.

Also, a third aspect of the present disclosure provides a method comprising: identifying at least one tile included in the same frame as a tile in the preceding frame by processing at least one draw call associated with a preceding frame and a subsequent frame, respectively; Storing the at least one tile from the preceding frame to render the subsequent frame; And rendering the subsequent frame using the stored at least one tile; Based rendering in a graphics processing device, which includes a rendering device and a rendering device.

Also, a fourth aspect of the present disclosure provides a computer program product, comprising: a memory for storing at least one instruction; And at least one processor executing the at least one instruction stored in the memory, wherein the at least one processor executes at least one instruction to generate at least one draw call associated with a preceding frame and a subsequent frame, respectively Identifying at least one tile included in the subsequent frame that is the same as a tile in the preceding frame by analyzing the processed draw calls and identifying the at least one tile from the preceding frame to render the subsequent frame A graphics processing device that performs tile-based rendering of a graphics processing device.

The at least one processor is further configured to execute the at least one instruction to identify from a signature of draw calls associated with the preceding frame a plurality of draw calls associated with the preceding frame and to identify the signature of the draw calls Identifies a plurality of draw calls associated with the subsequent frame, identifies at least one draw call that affects each of the preceding frame and the subsequent frame, and identifies at least one draw call associated with the next frame Based rendering that identifies at least one included draw call and identifies at least one tile in the preceding frame that can be rendered in the subsequent frame based on the similarity between the draw calls. Device can be provided.

Further, the at least one processor correlates the at least one draw call of the preceding frame and the subsequent frame by executing the at least one instruction, identifies the at least one change, Based rendering, wherein the input is identified based on at least one execution mode and input, the input including at least one vertex buffer, an index buffer, an attribute buffer, a shader, and a texture have.

The at least one processor may further execute the at least one instruction to render the at least one tile from the identified preceding frame again in the subsequent frame. Can be provided.

The at least one processor may also provide a graphics processing device that performs tile-based rendering, using the tile rendering in a dynamic texture, by executing the at least one instruction.

Further, the fifth aspect of the present disclosure can provide a computer-readable recording medium on which a program for causing a computer to execute the methods of the first aspect and the third aspect is recorded.

1 is a block diagram illustrating a graphics processing apparatus according to an exemplary embodiment of the present invention.
2 is a diagram illustrating an example of a preceding frame and a subsequent frame including an object according to one embodiment.
FIG. 3 is a flowchart illustrating a method of rendering a tile of a subsequent frame using a rendering result of a leading tile according to an exemplary embodiment.
4 is a diagram for explaining a dynamic texture according to an embodiment.
FIG. 5 is a flowchart illustrating a method of rendering a tile of a subsequent frame using a rendering result of a leading tile when there is a dynamic texture according to an exemplary embodiment.
6 is a diagram illustrating input and output of a graphics processing apparatus according to one embodiment.
7 is a block diagram illustrating components of a graphics processing apparatus according to an embodiment.
8 is a flow diagram of a method for performing tile-based rendering in a graphics processing apparatus according to one embodiment.
9 is a flow diagram of a method for identifying similar tiles included in a preceding frame and a subsequent frame for tile-based rendering in accordance with one embodiment.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented with various numbers of hardware and / or software configurations that perform particular functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or by circuit configurations for a given function. Also, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented with algorithms running on one or more processors. In addition, the present disclosure may employ conventional techniques for electronic configuration, signal processing, and / or data processing, and the like. Terms such as "mechanism," "element," "means," and " configuration "and the like are widely used and are not limited to mechanical and physical configurations.

Also, the connection lines or connection members between the components shown in the figures are merely illustrative of functional connections and / or physical or circuit connections. In practical devices, connections between components can be represented by various functional connections, physical connections, or circuit connections that can be replaced or added.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating a graphics processing apparatus according to an exemplary embodiment of the present invention.

1, the graphics processing apparatus 100 includes a GPU (Graphic Processing Unit) 10, a CPU (Central Processing Unit) 20, and a memory 30. It will be understood by those skilled in the art that other general-purpose components other than the components shown in FIG. 1 may be further included.

The graphics processing apparatus 100 may be a desktop computer, a notebook computer, a smart phone, a personal digital assistant (PDA), a portable media player, a video game console, a TV set top box, a tablet device, But is not limited thereto. That is, the graphics processing apparatus 100 is an apparatus having a graphics processing function for displaying contents, and various apparatuses may be included in the category of the graphics processing apparatus 100.

GPU 10 is a graphics-only processor that performs various versions and types of graphics pipelines such as OpenGL (Open Graphic Library), DirectX, CUDA (Compute Unified Device Architecture) Dimensional graphics pipeline in order to render the three-dimensional objects on the three-dimensional graphics pipeline to a two-dimensional image for display. For example, the GPU 10 may perform various functions such as shading, blending, illuminating, and various functions for generating pixel values for the pixels to be displayed.

The GPU 10 can receive an instruction from the CPU 20. [ A draw command is an instruction that indicates which object to render in an image or frame. For example, the draw command may be an instruction to draw a predetermined number of squares or triangles contained in an image or a frame. According to one embodiment, the draw command may be a draw call.

The GPU 10 may include at least one processor 11 and at least one cache 12. The processor 11 may store the graphics data included in the received draw call and the graphics data received from the memory 30 in the cache 12. Further, the processor 11 can execute each step of the graphics pipeline by using the graphics data stored in the cache 12 based on the graphics data included in the received draw call.

On the other hand, the graphics data is data used for rendering. In one embodiment, the graphics data may include vertex data, index data, attribute data, shaders, and textures.

The CPU 20 is hardware that controls the overall operations and functions of the graphics processing apparatus 100. For example, the CPU 20 may run an operating system (OS), call a graphics API (Application Programming Interface) for the GPU 10, and execute a driver of the GPU 10. In addition, the CPU 20 can execute various applications stored in the memory 30, for example, a web browsing application, a game application, a video application, and the like.

The memory 30 is hardware for storing various data processed in the graphics processing apparatus 100 and may store data processed by the GPU 10 and data to be processed. In addition, the memory 30 may store applications, drivers, and the like to be driven by the GPU 10 and the CPU 20. [ The memory 30 may be a random access memory (RAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a dynamic random access memory (DRAM) ROM, Blu-ray or other optical disk storage, a hard disk drive (HDD), a solid state drive (SSD), or a flash memory, and further includes an external storage device that can be accessed by the graphics processing device 100 .

Meanwhile, the graphics processing apparatus 100 may further include a display (not shown). The display can display the rendered image received from the CPU 20 or the GPU 10.

2 is a diagram illustrating an example of a preceding frame and a subsequent frame including an object according to one embodiment.

Referring to FIG. 2, rectangles 211 and 221, triangles 212 and 222, and rabbits 213 and 223 may be included as objects in the preceding frame 210 and the following frame 220. On the other hand, when tile-based rendering is performed, the graphics processing apparatus 10 may perform rendering in units of tiles (tile a to tile d) that divide the leading frame 210 and the following frame 220.

In one embodiment, the graphics processing device 10 may render subsequent frames 220 using the rendering results of the preceding frame 210. [ For example, only the rabbits 213, 223 move in the preceding frame 210 and the subsequent frame 220, and the positions of the squares 211, 221, triangles 212, 222 may remain unchanged. In this case, the graphics processing apparatus 10 is configured to render the tile a of the subsequent frame 220 including the squares 211 and 221 and the triangles 212 and 222, Rendering results are available.

FIG. 3 is a flowchart illustrating a method of rendering a tile of a subsequent frame using a rendering result of a leading tile according to an exemplary embodiment.

In step 310, the graphics processing apparatus 10 may receive a first draw call used to render a first tile of a preceding frame. In step 320, the graphics processing device 10 may receive a second draw call that is used to render a second tile of a subsequent frame, corresponding to the location of the first tile.

On the other hand, in one embodiment, the first draw call used for rendering the first tile and the second draw call used for rendering the second tile may be plural.

In step 330, the graphics processing apparatus 10 may generate a signature of the first draw call and a second draw call signature. The signature of the draw call may be a specific string that is identifiable between draw calls.

In one embodiment, the graphics processing apparatus 10 may generate a signature using an execution context and graphics data relating to the first draw call and the second draw call. For example, the graphics processing apparatus 10 may generate a signature using an execution context including an openGL state (GL_TEXTURE_2D, GL_FOG, GL_BLEND, etc.) set during rendering. Also, the graphics processing apparatus 10 can generate a signature using graphics data, such as vertex data, index data, attribute data, shaders, textures, and uniforms. Meanwhile, the graphics processing apparatus 10 can calculate a checksum of a signature by using an execution context and graphics data.

In step 340, the graphics processing apparatus 10 may compare the signature of the first draw call and the signature of the second draw call. In one embodiment, the graphics processing device 10 may compare both signatures by calculating a signature of the first draw call and a checksum of the signature of the second draw call.

In step 360, the graphics processing apparatus 10 may render the second tile using the rendering result of the first tile, according to the comparison result. In one embodiment, when the signature of the first draw call and the signature of the second draw call match, the graphics processing apparatus 10 may render the second tile using the rendering result of the first tile. For example, the graphics processing device 10 may reuse the rendering result of the first tile to render the second tile. Also, if the signature of the first draw call and the signature of the second draw call do not match, the graphics processing apparatus 10 can render the second tile again.

On the other hand, when there are a plurality of the first draw call and the second draw call, if the signatures of the plurality of first draw calls and the signatures of the plurality of second draw calls are the same or satisfy predetermined criteria, the graphics processing apparatus 10 May render the second tile using the rendering result of the first tile.

In addition, the graphics processing apparatus 10 can determine whether the camera view point for the subsequent frame is the same as the camera point for the preceding frame. The graphics processing apparatus 10 can determine the camera viewpoint by analyzing the vertex shaders and / or uniforms of the draw call. For example, when the uniforms between the preceding frame and the subsequent frame are equal to or greater than a predetermined value, the graphics processing apparatus 10 can determine that the camera viewpoint is the same in the preceding frame and the subsequent frame.

In one embodiment, if it is determined that the camera viewpoint is the same in the preceding frame and the subsequent frame, the graphics processing device 10 may determine whether to use the rendering result of the first tile to render the second tile. Further, in another embodiment, if it is determined that the camera viewpoint is not the same in the preceding frame and the subsequent frame, the graphics processing apparatus 10 may re-render all the tiles included in the subsequent frame.

4 is a diagram for explaining a dynamic texture according to an embodiment.

Referring to FIG. 4, a dynamic texture means that a dynamic image rendered in real time is utilized as a texture. For example, if there is an object corresponding to the electric signboard 411 among the objects to be displayed on the frame 401, an image of a scene may be displayed on the screen of the electric signboard object. The image to be displayed on the screen of the electric sign board may also be dynamically changed to correspond to the frame change.

Similarly, a scene of an automobile in operation may be rendered on the frame 402. Since the exterior of the vehicle is displayed in the side mirror 412 of the vehicle, the image to be displayed on the side mirror 412 can be dynamically changed to correspond to the frame change.

The dynamic texture described in one embodiment may refer to a texture to be textured in a frame when a separate object exists in which frame the dynamic image is to be displayed.

FIG. 5 is a flowchart illustrating a method of rendering a tile of a subsequent frame using a rendering result of a leading tile when there is a dynamic texture according to an exemplary embodiment.

In step 510, the graphics processing device 10 may determine whether the dynamic texture is applied to the first tile and the second tile. On the other hand, the texture used in the graphic processing process may be predetermined and stored in the memory, but may be generated in real time. The texture generated in real time during the graphic processing is called dynamic texture. Dynamic textures can go through a process of compression before being stored in memory to reduce memory bandwidth and power consumption for reading / writing.

In step 512, when the dynamic texture is applied to the first tile and the second tile, the graphics processing apparatus 10 may determine whether there is a dependency between the rendering result of the first tile and the second tile. In one embodiment, the graphics processing apparatus 10 analyzes the shader included in the first draw call and the shader included in the second draw call, and maps the dynamic texture to the first draw call and the second draw call. , It can be determined whether the final image to be rendered depends on the dynamic texture. However, the method of determining whether the final image to be rendered depends on the dynamic texture is not limited thereto.

In step 514, the graphics processing device 10 may use the rendering result of the first tile to generate a dynamic texture used for rendering the second tile, if there is a dependency between the rendering result of the first tile and the second tile have. In one embodiment, when there is a dependency between the rendering result of the first tile and the second tile, the graphics processing apparatus 10 uses the rendered image of the first tile to determine the dynamic texture used to render the second tile Lt; / RTI >

In step 516, the graphics processing device 10 may render the second tile using the generated dynamic texture.

6 is a diagram illustrating input and output of a graphics processing apparatus, according to one embodiment.

Graphics processing device 600 may receive at least one application input to initiate rendering of the image. The application input may include association information necessary for draw call and tile rendering. The association information may include data such as instructions that instruct the graphics processing device 600 to read data from memory, write data to memory, and set the environment to execute a draw call, It does not. The graphics processing device 600 may process the received application input in response to the application input and identify the draw call (s) associated with each frame belonging to the image to be displayed. The application input may be related to rendering a plurality of frames. However, the graphics processing device 600 may render one frame at a time. Graphics processing device 600 may process the draw call (s) and identify the same tile (s) in two frames (hereinafter, the preceding frame and the succeeding frame). On the other hand, processing of draw calls may include processing all or part of the draw calls. In one embodiment, the preceding frame and subsequent frames may be contiguous / contiguous frames. In other embodiments, the preceding frame and subsequent frames may be any two frames included in the application to be displayed, and the preceding frame and subsequent frames may not be contiguous (contiguous). On the other hand, an application may include any suitable data capable of generating images, video, video games, and a series of frames.

Further, the graphics processing apparatus 600 may process the preceding frames and the subsequent frames one at a time. For example, the graphics processing device 600 may process the draw calls associated with the preceding frame, and the signature of the processed draw calls may be generated and stored in a corresponding database in a storage space associated with the graphics processing device 600 have. Graphics processing device 600 may also process subsequent frames to generate signatures of drawcalls associated with subsequent frames. The graphics processing device 600 may also compare the signature of the draw calls associated with the subsequent frame to the signature of the draw calls associated with the preceding frame to identify the same tile (s) in the preceding frame and subsequent frames.

In one embodiment, when the preceding frame is first processed by the graphics processing device 600, a signature of the draw calls associated with the preceding frame may be generated, and the signature of the draw calls associated with the preceding frame may be used for later reference purposes And can be stored in a database. Also, the signatures of the drawcalls associated with subsequent frames can be stored in the database, so that they can be compared to the signature of another frame to identify the same tile (s) at any time.

In addition, if it is determined that the identified at least one tile is common to the preceding frame and the subsequent frame, based on the signature of the draw calls associated with the preceding frame and the signature of the draw calls associated with the preceding frame, To identify the application input to be made. For example, if it is determined that one tile is common to the preceding frame as well as the subsequent frame, the common tile may be copied as is in the subsequent frame (i. E., Reused in subsequent frames). The remaining tiles of the subsequent frame may be identified as part of the application input re-rendered by the graphics processing device 600 and rendered again.

7 is a block diagram illustrating components of a graphics processing apparatus according to an embodiment. The graphics processing apparatus 600 may include an input / output (I / O) interface 701, a memory 702, a graphics processing unit (GPU) 703, and a graphics driver 704.

The I / O interface 701 may provide at least one channel to the application to communicate with the GPU 703. In addition, the I / O interface 701 may include at least one output interface for displaying a frame to be rendered to a user. For example, a display screen may be used to display the output of the GPU to users.

The memory 702 may store all sorts of data associated with the image rendering process. For example, the memory 702 may store the data to be rendered in frame form and store corresponding draw calls. Memory 702 may also store data associated with tiles in the preceding frame and in subsequent frames and may provide information about the stored data to identify common tiles within the preceding frame and subsequent frames. In addition, the memory 702 may store information about rendered tiles and re-rendered tiles in each frame, for future reference purposes. The memory 702 may operate as a buffer in which one or more tiles within a frame may be maintained to be rendered in a subsequent frame. In addition, the memory 702 may store a signature corresponding to all of the frames being processed.

GPU 703 and driver 704 may retrieve similar tiles in at least seven frames. In one embodiment, two frames, the preceding frame and the subsequent frame, may be processed one at a time. When processing frames, the driver module 704 may fetch the draw calls associated with the frames being processed. In addition, by processing the draw calls and any associated data, a frame specific draw call signature can be generated. In the case of a draw call using a dynamic texture, the dynamic texture may not be part of the signature of the draw call. The signature of the draw calls of the subsequent frame is compared with the signature of the draw calls of the preceding frame, so that the modified draw calls can be identified. In various embodiments, if the draw call is no longer in a subsequent frame, or if the draw call produces a different output in a subsequent frame (ignoring it if dynamic textures are present) As shown in Fig. Similarly, a draw call added in a subsequent frame (a draw call that does not exist in the preceding frame) can be judged as a modified draw call. A list of modified draw calls may be provided at the input of the GPU 703. The GPU 703 may identify the tile (s) that are common to the analyzed frames by analyzing the list of modified draw calls received from the driver module 704. Based on the information associated with the common tiles, the GPU 703 may identify application inputs associated with subsequent frames that need to be rendered. The GPU 703 may determine that the identified tile (s) as common tiles can be reused from the preceding frame. The GPU 703 may also render or re-render the appropriate tiles in response to the received application input.

8 is a flow diagram of a method for performing tile-based rendering in a graphics processing device, according to one embodiment.

When the graphics processing apparatus 600 receives an application input for rendering a frame, the graphics processing apparatus 600 may collect drawcalls, associated data, and auxiliary instructions corresponding to the application input. In one embodiment, the application input may be related to rendering a plurality of frames. Meanwhile, the graphics processing apparatus 600 may render only one frame at a time.

In step 802, the graphics processing apparatus 600 may sequentially process the draw calls associated with the subsequent frame. In one embodiment, drawcalls belonging to at least seven frames may be processed one by one by the graphics processing apparatus 600, one by one.

At step 804, the graphics processing device 600 may identify tiles of subsequent frames that are identical to the tiles of the selected preceding frame. In one embodiment, based on the drawcalls associated with each tile, the graphics processing device 600 may identify the similarity between the tiles of the preceding frame and the tiles of the subsequent frame. In one embodiment, if the tiles are not changed over different frames, the draw calls corresponding to the tiles are also kept the same. On the other hand, in one embodiment, the processed frames (i.e., the preceding frame and the subsequent frame) may be adjacent to each other. In other embodiments, the frames being processed may not be adjacent to each other.

In step 806, based on the identified common tiles (if any), graphics processing device 600 may identify application inputs that need to be rendered in subsequent frames. In one embodiment, if common tile (s) are identified between a preceding frame and a subsequent frame, then the identified common tile (s) remains intact in the subsequent frame and the remaining portion of the application input May be re-rendered by the graphics processing device 600. < RTI ID = 0.0 >

9 is a flow diagram of a method for identifying similar tiles included in a preceding frame and a subsequent frame for tile-based rendering, according to one embodiment.

In step 902, the graphics processing apparatus 600 may check the camera position of the preceding frame and the subsequent frame. In one embodiment, the graphics driver 704 can detect and verify the camera position of the preceding frame and subsequent frames to verify that the camera position has changed across the frames. In one embodiment, the graphics driver 704 may identify a change in the camera position based on input to the vertex shader.

If the "model view transform" matrix remains the same in the preceding and following frames for most drawcalls, the camera position in the preceding frame and the subsequent frame may be determined to be the same. If the camera position is changed in a subsequent frame, then almost all of the tiles of the subsequent frame can be determined to have changed compared to the tile of the preceding frame, which can be determined to be the same tile in the preceding frame and subsequent frames being analyzed.

In step 904, the graphics processing apparatus 600 may determine whether the camera position in the preceding frame and in the subsequent frame is different. If it is determined that the camera position is different, the process may proceed to step 914. In step 914, the graphics processing device 600 may indicate that the entire subsequent frame is to be rendered again. On the other hand, if it is determined that the camera positions are the same, the process can proceed to step 906.

In step 906, the graphics processing apparatus 600 may correlate the draw calls of the preceding frame and the subsequent frame. In one embodiment, if the camera positions are the same across frames, the draw calls associated with the frames under analysis may be processed by the graphics driver 704 and correlated. On the other hand, various parameters such as execution mode, vertex / index / attribute buffer, shader and textures specific to the drawcalls can be compared to identify any change and degree of modification.

In step 908, the graphics processing device 600 may identify the draw call (s) that affect each of the tiles included in the subsequent frame. In one embodiment, the draw call (s) that affect each of the tiles in the frames being processed may be identified by the GPU 703.

In step 910, the graphics processing device 600 may identify whether the final image to be rendered depends on the dynamic texture. In one embodiment, when a dynamic texture is present, the GPU 703 or the graphics driver 704 may determine whether the final image to be rendered depends on the dynamic texture. In addition, dependencies between the dynamic texture over different tiles and the final image to be rendered can also be identified.

In step 912, the graphics processing device 600 may identify tiles contained in subsequent frames that need to be rendered again. In one embodiment, the GPU 703 analyzes the draw calls and can identify the tile (s) that are common in the preceding frame and subsequent frames, based on the similarity between the draw calls under analysis. GPU 703 may keep the identified tile (s) available for use in subsequent frames and may also determine a portion of the application input to be rendered again. In one embodiment, if one or more tiles from a preceding frame are determined to remain unchanged and present in a subsequent frame, the tiles remain in the subsequent frame and only the remaining tiles of the subsequent frame are re-rendered, thereby reducing data throughput .

On the other hand, the various operations of Figs. 3, 5, 8 and 9 may be performed in the order shown, different order from the order shown, or concurrently. Further, in some embodiments, the steps shown in Figures 3-6 may be omitted.

The embodiments disclosed herein can specify a mechanism for rendering tiles in a GPU. The mechanism may enable tile rendering to provide the system. Thus, the scope of protection extends to such systems and extends to computer-readable means comprising a message therein, which computer-readable means is understood to include program code for implementing one or more steps of the method . The program may be executed on a server or mobile device or on any suitable programmable device. The method may be implemented, for example, in a preferred embodiment using the system with the written software program. A high speed integrated circuit VHDL (Hardware Description Language), another programming language, or one or more VHDL or software modules running on at least one hardware device. A hardware device may be any type of programmable device, such as a server or any kind of computer, such as a personal computer, or any combination thereof (e.g., one processor, two FPGAs) have. The device may also include hardware means such as an ASIC or a combination of hardware means and software means (ASIC and FPGA), or at least one memory with at least one microprocessor and software module installed. Thus, the means is at least one hardware means or at least one hardware and software means. The method embodiments described herein may be implemented entirely in hardware, or partially in hardware, and in part in software. Alternatively, one embodiment may be implemented using a different hardware device, e.g., a plurality of CPUs.

The embodiments may also be embodied in the form of a recording medium including instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically comprise any information delivery media, including computer readable instructions, data structures, program modules, or other data of a modulated data signal such as a carrier wave, or other transport mechanism.

Also, in this specification, the term "part" may be a hardware component such as a processor or a circuit, and / or a software component executed by a hardware component such as a processor.

It will be understood by those skilled in the art that the foregoing description of the specification is for illustrative purposes only and that those skilled in the art will readily understand that various changes in form and details may be made therein without departing from the spirit and scope of the invention. It will be possible. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the foregoing detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be interpreted as including the claims.

Claims (19)

A method of performing tile-based rendering in a graphics processing device,
The method comprising: receiving a first draw call used for rendering a first tile of a preceding frame;
Receiving a second draw call used to render a second tile of a succeeding frame, corresponding to a position of the first tile;
Generating a signature of the first draw call and the second draw call signature;
Comparing a signature of the first draw call and a signature of the second draw call;
Rendering the second tile using a rendering result of the first tile according to the comparison result;
/ RTI > The method according to claim 1,
Wherein rendering the second tile comprises:
Rendering the second tile using the rendering result of the first tile if the signature of the first draw call matches the signature of the second draw call;
/ RTI > The method according to claim 1,
Wherein rendering the second tile comprises:
Generating a dynamic texture used for rendering the second tile using a rendering result of the first tile when there is a dependency between the rendering result of the first tile and the second tile; And
Rendering the second tile using the generated dynamic texture;
≪ / RTI > The method of claim 3,
The method comprises:
Analyzing whether a shader included in the first draw call and a shader included in the second draw call are the same;
Identifying whether the dynamic texture is mapped to the first draw call and the second draw call; And
Determining whether there is a dependency between the rendering result of the first tile and the second tile based on the result of the valuation analysis and the identification result;
≪ / RTI > The method according to claim 1,
Wherein the generating the signature comprises:
The signature of the first draw call and the signature of the second draw call using the openGL state, vertex data, index data, attribute data, shader and texture relating to the first draw call and the second draw call, And generating a signature of the signature,
Wherein the signature is a character string capable of identifying between the first draw call and the second draw call. The method according to claim 1,
Wherein the first tile and the second tile each comprise a plurality of adjacent base size tiles that divide the preceding frame and the subsequent frame, respectively. The method according to claim 1,
The method comprises:
Determining whether a camera viewpoint for the subsequent frame is the same as a camera viewpoint for the preceding frame;
Further comprising:
And comparing the signature of the first draw call with the signature of the second draw call if the camera viewpoint is determined to be the same. 1. A graphics processing apparatus for performing tile-based rendering,
A memory for storing at least one instruction; And
And at least one processor executing the at least one instruction stored in the memory,
The processor executing the one or more instructions,
A first draw call used for rendering a first tile of a preceding frame,
A second draw call used to render a second tile of a subsequent frame, corresponding to a position of the first tile,
Generates a signature of the first draw call and the second draw call signature,
The signature of the first draw call is compared with the signature of the second draw call,
And render the second tile using a rendering result of the first tile according to the comparison result. 9. The method of claim 8,
Wherein the at least one processor executes the one or more instructions,
And render the second tile using the rendering result of the first tile if the signature of the first draw call matches the signature of the second draw call. 9. The method of claim 8,
Wherein the at least one processor executes the one or more instructions,
Generating a dynamic texture used for rendering the second tile using a rendering result of the first tile when there is a dependency between the rendering result of the first tile and the second tile,
And render the second tile using the generated dynamic texture. 11. The method of claim 10,
Wherein the at least one processor executes the one or more instructions,
The shader included in the first draw call and the shader included in the second draw call are the same,
Identify whether the dynamic texture is mapped to the first draw call and the second draw call,
And determines whether there is a dependency between the rendering result of the first tile and the second tile, based on the result of the shopping arc analysis and the identification result. 9. The method of claim 8,
Wherein the at least one processor executes the one or more instructions,
The signature of the first draw call and the signature of the second draw call using the openGL state, vertex data, index data, attribute data, shader and texture relating to the first draw call and the second draw call, Lt; / RTI > signature,
Wherein the signature is a character string capable of identifying between the first draw call and the second draw call. 9. The method of claim 8,
Wherein the at least one processor executes the one or more instructions,
Wherein the first tile and the second tile each include a plurality of adjacent base size tiles that divide the preceding frame and the subsequent frame, respectively. 9. The method of claim 8,
Wherein the at least one processor executes the one or more instructions,
Determines whether a camera viewpoint for the subsequent frame is the same as a camera point for the preceding frame,
And compares the signature of the first draw call with the signature of the second draw call when the camera viewpoint is determined to be the same. A method of performing tile-based rendering in a graphics processing device,
Identifying at least one tile included in the subsequent frame that is the same as a tile in the preceding frame by processing at least one draw call associated with each of the preceding frame and the subsequent frame;
Storing the at least one tile from the preceding frame to render the subsequent frame; And
Rendering the subsequent frame using the stored at least one tile;
/ RTI > 16. The method of claim 15,
Wherein the processing of the at least one draw call comprises:
Identifying a plurality of draw calls associated with the preceding frame from a signature of draw calls associated with the preceding frame;
Identifying a plurality of draw calls associated with the subsequent frame from a signature of draw calls associated with the subsequent frame;
Identifying at least one draw call affecting each of the preceding frame and the subsequent frame;
Identifying at least one draw call included in the subsequent frame that is the same as the draw call included in the preceding frame; And
Identifying at least one tile in the preceding frame that can be rendered in the subsequent frame, based on the similarity between the draw calls;
≪ / RTI > 17. The method of claim 16,
Wherein identifying the at least one change between the at least one draw call of the preceding frame and the subsequent frame comprises:
Correlating the at least one draw call of the preceding frame and the subsequent frame; And
Identifying the at least one change;
Further comprising:
Wherein the at least one change is identified based on at least one execution mode and input and the input comprises at least one of a vertex buffer, an index buffer, an attribute buffer, a shader, And a texture. 17. The method of claim 16,
Wherein the at least one tile from the identified preceding frame is re-rendered in the subsequent frame. 16. The method of claim 15,
Wherein the tile rendering is used for dynamic textures.

Images