CN115393468A - Method for implementing geometric engine stage selection feedback mechanism of graphic processor - Google Patents
Method for implementing geometric engine stage selection feedback mechanism of graphic processor Download PDFInfo
- Publication number
- CN115393468A CN115393468A CN202211002007.8A CN202211002007A CN115393468A CN 115393468 A CN115393468 A CN 115393468A CN 202211002007 A CN202211002007 A CN 202211002007A CN 115393468 A CN115393468 A CN 115393468A
- Authority
- CN
- China
- Prior art keywords
- unit
- triangle
- vertex
- feedback
- primitive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Image Generation (AREA)
Abstract
The invention provides a method for realizing a geometric engine stage selection feedback mechanism of a graphic processor. The graphics processor comprises a vertex receiving and storing unit, a GP parameter configuration unit, a core computing unit, a vertex assembling and sending unit, a selection feedback unit, a task scheduling unit (JSU), an Image Processing Unit (IPU), a graphics function management unit (GFU), a PCIE and AXI writing DDR3 unit; the implementation method of the selection feedback mechanism comprises the following steps: step 1: judging a received primitive command; and 2, step: configuring parameters; and step 3: calculating the area of the triangle; and 4, step 4: and (5) primitive elimination. The invention provides a method for realizing the geometric engine stage selection feedback mechanism of a graphic processor, which can effectively realize the geometric engine stage selection feedback mechanism and realize the functions of selecting a certain area on a screen by a user and feeding back a rendering calculation result.
Description
Technical Field
The invention relates to the technical field of computer hardware, in particular to a method for realizing a geometric engine stage selection feedback mechanism of a graphic processor.
Background
Some graphics applications in image processors simply render static two-dimensional or three-dimensional images of objects. Still other applications allow a user to identify objects on the screen and move, modify, delete, or otherwise manipulate those objects. Such applications with interactive operation are supported. Since objects drawn on a screen typically undergo multiple rotations, movements and perspective transformations, it is difficult to determine which object the user has selected in a three-dimensional scene. To achieve this, it is determined by the selection mechanism which object the user has specified in a certain area. The selection allows a user of the application to select an object drawn on the screen, and allows the user to acquire information related to the object drawn on the screen through feedback.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides a method for realizing a geometric engine stage selection feedback mechanism of a graphic processor, which can effectively realize the functions of selecting information of a certain area on a screen by a user and feeding back a rendering calculation result.
The technical solution of the invention is as follows: a method for realizing a geometric engine stage selection feedback mechanism of a graphics processor comprises a vertex receiving and storing unit, a GP parameter configuration unit, a core computing unit, a vertex assembling and sending unit, a selection feedback unit, a task scheduling unit (JSU), an Image Processing Unit (IPU), a graphics function management unit (GFU), a PCIE and an AXI write DDR3 unit; it is characterized in that: the method comprises the following steps:
step 1: judging a received primitive command;
the vertex receiving and storing unit receives and analyzes the primitive vertex command sent by the preceding stage unit, and judges whether the currently received primitive command is a point, a line or a triangle;
when the received primitive command is a point and a line, the command is shot according to the production line and transmitted to a vertex assembly sending unit;
when the received primitive command is a triangle, taking out (X1, Y1) (X2, Y2) (X3, Y3) values of three vertex coordinates of the triangle to send to a lower-level core computing unit, and simultaneously shooting and transmitting a triangle primitive vertex boundary mark and the command to a vertex assembly sending unit according to a production line;
step 2: parameter configuration; and through a GP parameter configuration unit, the rotation direction of the current triangle, the front and back drawing mode and the current front, back or front and back triangle parameters are configured by the Opengl instruction.
And 3, step 3: calculating the area of the triangle;
the core calculating unit is used for equivalently converting the product of the modulus of the surface external normal vector of the triangle and the modulus of the sight line vector into the calculation of the area of the triangle, and calculating the A value of the triangle vertex coordinates (X1, Y1) (X2, Y2) (X3, Y3) output by the vertex receiving and storing unit according to A = X1 (Y2-Y3) + X2 (Y3-Y1) + X3 (Y1-Y2); meanwhile, the rotation direction of the current triangle is configured by combining with the Opengl instruction, and the front and back marks of the current triangle are calculated;
and 4, step 4: eliminating the primitive;
the vertex assembling and sending unit generates rejection marks according to the rejection front and back triangular parameters configured by the GP parameter configuration unit and the front and back triangular marks judged by the core calculation unit; and then according to the current triangle front and back drawing mode configured by the GP parameter configuration unit and whether the triangle front and back drawing mode is a boundary point or not and whether the triangle front and back drawing mode is a boundary edge or not transmitted by the vertex receiving and storing unit, and the boundary edge, the primitive elimination is carried out.
The selection feedback unit receives the function code related to the selection feedback and does not perform any operation if the current application program is in a drawing mode according to the mode of the current application program configured by the GP parameter configuration unit;
if the current application program is in a selection mode, receiving a function code related to selection to perform stack initialization, stack pushing, stack popping and stack top element replacement on the name stack, and writing the name stack element into the DDR through the AXI according to the name stack depth, the minimum depth value and the maximum depth value after the last click record;
if the current application program is in a feedback mode, the coordinates and the related attributes of the raster position are taken out from the IPU and the JSU and written into the DDR through the AXI when the function code related to the feedback is received, and if the current application program is in the feedback mode, the primitive vertex information is written into the DDR through the AXI according to the current feedback type configured by the GP parameter configuration unit when the primitive vertex information is received.
If the current application program is in a feedback mode and receives a function code related to feedback, the task scheduling unit retrieves the depth value, the color and the texture attribute of the raster position from the task scheduling unit.
The image processing unit retrieves the coordinates of the raster position and the valid flag from the image processing unit if the current application is in the feedback mode and the function code related to the feedback is received.
The graphic function management unit manages the graphic function codes in a unified way and broadcasts and sends the graphic function codes to each module.
The PCIE unit allocates a base address and a space size of the selection feedback AXI, and returns the number of times of selection click recording and the number of feedback primitives to the host side.
The invention has the advantages that: the invention provides a method for realizing a geometric engine stage selection feedback mechanism of a graphic processor, which can effectively realize the functions of selecting information of a certain area on a screen by a user and feeding back a rendering calculation result.
Drawings
FIG. 1 is a block diagram of a geometry engine phase selection feedback mechanism for a graphics processor according to the present invention;
FIG. 2 is a diagram of primitive vertex command format in the present invention;
FIG. 3 is a diagram of a vertex attribute data format in accordance with the present invention;
FIG. 4 is a diagram of the vertex command format in the simple mode of the present invention;
FIG. 5 is a diagram of vertex attribute data location and validity in a complex model according to the present invention;
FIG. 6 shows the glRenderMode datapath when exiting the select mode;
FIG. 7 shows the glRenderMode datapath when it exits the feedback mode.
Detailed Description
The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and the specific embodiments. The embodiments described are only a few embodiments of the present invention, rather than all embodiments, and all other embodiments that can be derived by one skilled in the art from the embodiments described herein are intended to be within the scope of the present invention.
A method for realizing a geometric engine stage selection feedback mechanism of a graphic processor comprises a vertex receiving and storing unit, a GP parameter configuration unit, a core computing unit, a vertex assembling and sending unit, a selection feedback unit, a task scheduling unit (JSU), an Image Processing Unit (IPU), a graphic function management unit (GFU), a PCIE and an AXI write DDR3 unit; it is characterized in that: the method comprises the following steps:
step 1: judging a received primitive command;
the vertex receiving and storing unit receives and analyzes the primitive vertex command sent by the preceding stage unit, and judges whether the currently received primitive command is a point, a line or a triangle;
when the received primitive command is a point and a line, the command is shot according to a production line and transmitted to a vertex assembly sending unit;
when the received primitive command is a triangle, taking out (X1, Y1) (X2, Y2) (X3, Y3) values of three vertex coordinates of the triangle to send to a lower-level core computing unit, and simultaneously shooting and transmitting a triangle primitive vertex boundary mark and the command to a vertex assembly sending unit according to a production line;
step 2: parameter configuration; and configuring the rotation direction and front and back drawing modes of the current triangle and rejecting the current front, back or front and back triangle parameters by the Opengl instruction through a GP parameter configuration unit.
And step 3: calculating the area of the triangle;
the core calculation unit equivalently converts the product of the modulus of the surface external normal vector of the triangle and the modulus of the sight line vector into the calculation of the area of the triangle, and calculates the A value of the triangle vertex coordinates (X1, Y1) (X2, Y2) (X3, Y3) output by the vertex receiving and storing unit according to A = X1 (Y2-Y3) + X2 (Y3-Y1) + X3 (Y1-Y2); meanwhile, the rotation direction of the current triangle is configured by combining with the Opengl instruction, and the front and back marks of the current triangle are calculated;
and 4, step 4: eliminating the primitive;
the vertex assembly sending unit generates rejection marks according to the rejection front and back triangle parameters configured by the GP parameter configuration unit and the front and back triangle marks judged by the core calculation unit; and then according to the current triangle front and back drawing mode configured by the GP parameter configuration unit and whether the triangle front and back drawing mode is a boundary point or not and whether the triangle front and back drawing mode is a boundary edge or not transmitted by the vertex receiving and storing unit, and the boundary edge, the primitive elimination is carried out.
The selection feedback unit configures the mode of the current application program according to the GP parameter configuration unit, and if the current application program is in a drawing mode, the function code related to the selection feedback is received and no operation is performed;
if the current application program is in a selection mode, receiving a function code related to selection to perform stack initialization, stack pushing, stack popping and stack top element replacement on a name stack, and writing the name stack element into the DDR through AXI (advanced extensible interface) at the same time according to the name stack depth, the minimum depth value and the maximum depth value recorded since the last click;
if the current application program is in a feedback mode, the coordinates and the related attributes of the raster position are taken out from the IPU and the JSU and written into the DDR through the AXI when the function code related to the feedback is received, and if the current application program is in the feedback mode, the primitive vertex information is written into the DDR through the AXI according to the current feedback type configured by the GP parameter configuration unit when the primitive vertex information is received.
The task scheduling unit retrieves the depth value, color and texture attributes of the raster position from the task scheduling unit if the current application is in feedback mode and receives a function code related to the feedback.
The image processing unit retrieves the coordinates of the raster position and the valid flag from the image processing unit if the current application is in the feedback mode and the function code related to the feedback is received.
The graphic function management unit manages the graphic function codes in a unified way and broadcasts and sends the graphic function codes to each module.
The PCIE unit allocates the base address and the space size of the selection feedback AXI, and returns the times of selection click recording and the number of the feedback graphic elements to the host side.
It needs to be further explained that: referring to fig. 1-7, an implementation structure diagram of a geometric engine stage selection feedback mechanism of a graphics processor includes a vertex receiving and storing unit, a GP parameter configuration unit, a core computing unit, a vertex assembling and sending unit, a selection feedback unit, a task scheduling unit (JSU), an Image Processing Unit (IPU), a graphics function management unit (GFU), a PCIE and AXI write DDR3 unit.
The vertex receiving and storing unit receives a primitive command from a superior pipeline unit and performs decoding and analysis, wherein the primitive command has a format shown in fig. 2 and includes a 17-bit command header and six 128-bit attribute data bits, the structure of the command header is shown in table 1, and 7-9 bits of the command header are analyzed to determine whether the currently received primitive command is a point, a line or a triangle. The number of attributes (coordinates, front main color, front auxiliary color, back main color, back auxiliary color, 6-fold texture, and fog coordinates) carried by the vertex is shown in fig. 3, and the vertex command format is divided into a simple mode and a complex mode, which are shown in fig. 4 and 5, respectively. If the current received point and line are not processed, the command is directly beaten according to the production line and is transmitted downwards to a primitive vertex command assembling and transmitting unit; if the triangle primitive is received currently, extracting coordinates and boundary marks of three vertexes of the triangle primitive, outputting (X, Y) coordinates of the three vertexes of the triangle to an A value (area) calculation unit, and simultaneously shooting vertex boundary edges, boundary point marks and attributes of the vertexes of the triangle primitive carried by a command packet header according to the length of the running water and sending the vertex commands to a primitive vertex command assembly and sending unit.
And the GP parameter configuration unit configures the rotation direction and the front and back drawing mode of the current triangle and eliminates the current front, back or front and back triangle parameters according to the Opengl instruction.
The core calculating unit is used for equivalently converting the product of the modulus of the surface normal vector of the triangle and the modulus of the sight line vector and the product of the cosine value of the included angle, the A value calculating unit receives the coordinate values of three vertexes of the triangle output by the vertex receiving and storing unit, and calculates the A value according to the formula A = X1 (Y2-Y3) + X2 (Y3-Y1) + X3 (Y1-Y2). And after the A value of the area of the triangle is obtained through calculation, determining the front and back surfaces of the current triangle by combining the rotation direction of the triangle configured by the open gl instruction of the GP parameter configuration unit. When the rotation direction of the configured triangle is anticlockwise and the calculated A value is greater than 0, the triangle is regarded as the front side, otherwise, the triangle is regarded as the back side; when the rotation direction of the configured triangle is clockwise and the received A value is less than 0, the triangle is considered to be the front side, otherwise, the triangle is considered to be the back side.
And the vertex assembly sending unit generates a rejection mark according to the front surface and the back surface of the triangle judged by the core computing unit and according to the rejection front surface, the rejection back surface or the front and back surface triangle configured by the Opengl instruction of the GP parameter configuration unit. And then, primitive elimination is carried out by combining a front drawing mode and a back drawing mode configured by the GP parameter configuration unit and whether the boundary points and the boundary edges are transmitted by the vertex receiving and storing unit. And when the calculated triangle is the front and is not rejected, the front drawing mode configured according to the Opengl instruction is dot drawing or line drawing, and the vertex receives the boundary points and the boundary edge marks sent by the storage unit, splits the boundary points and the boundary edge marks into corresponding points and lines and sends the points and the lines to the lower level pipeline unit, if the boundary points and the boundary edge marks are invalid, rejecting the triangle primitive and not outputting any command to the lower level pipeline. When the Opengl instruction configuration front drawing mode is a filling mode, sending the original primitive command to a lower level pipeline unit according to the received original primitive command; and when the calculated triangle is the front face and the front face is removed, directly removing the triangle without outputting any command to the lower-level pipeline. When the calculated triangle is the back side, the processing mode is consistent with the front side.
And the selection feedback unit completes a corresponding selection feedback function according to the mode of the current application program. When the current application program is in a selection mode and receives an initial _ name function code sent by a graphic function management unit, initializing a name stack with the depth of 64 and emptying the contents of the stack; when a push _ name function code sent by a graphic function management unit is received, a new name primitive is pushed into a name stack, and if the current name stack is full (the name stack depth is 64), the stack overflow error is caused by executing the glPushName; when receiving a pop _ name function code sent by a graphic function management unit, popping an element at the top of a name stack out of the stack, and if the current name stack is empty, executing the glPopName will cause a stack underflow error; when receiving the load _ name function code sent by the graphic function management unit, the top element of the name stack is replaced by a new name element, and if the current name stack is empty, the execution of the glloadName will cause invalid operation error. And simultaneously calculating the minimum value and the maximum value of the depth values of the vertexes of the received graphic primitives after entering the selection mode, and finally stacking the depth of the name, the minimum value and the minimum value of the vertex depth of the graphic primitives when exiting the selection mode, wherein stack elements are written into the DDR3 through an AXI bus and then returned to the host end through PCIE. The glRenderMode datapath when exiting the select mode is as shown in fig. 6.
When the current application program is in a feedback mode and receives primitive vertex information of a complex mode, if the feedback type is GL-2D, writing a primitive type mark token value and X and Y of primitive vertex coordinates into DDR3 through an AXI bus; if the feedback type is GL-3D, writing the token value of the primitive type mark and the X, Y and Z values of the vertex coordinates of the primitive into DDR3 through an AXI bus; if the feedback type is GL _3D _COLOR, writing the primitive type mark token value, the X, Y and Z values of the vertex coordinates of the primitive and the front main colors R, G, B and A values into DDR3 through an AXI bus; if the feedback type is GL _3D _ COLOR _TEXTUREat the moment, writing the value of a primitive type mark token, the values of X, Y and Z of the vertex coordinates of the primitive, the values of R, G, B and A of front main colors and the values of S, T, R and Q of 0-piece textures into DDR3 through an AXI bus; if the feedback type is GL _4d _color _textureat this time, the primitive type flag token value, the X, Y, Z, W values of the primitive vertex coordinates, the front main color R, G, B, a values, and the S, T, R, Q values of 0-heavy texture are written into DDR3 through the AXI bus. If the fed-back primitive type is triangle, a data 3 needs to be returned after the primitive type flag. And finally, returning the information in the DDR to the host end through the PCIE.
When the current application program is in a feedback mode and receives the glbitmap, gldrawpixel and glcopypixel function codes sent by the graphic function management unit, reading back the X and Y coordinates of the current raster position and the effective mark of the raster position from the IPU, reading back the Z and W coordinates of the current raster position, the front main colors R, G, B, A and 0 double texture S, T, R and Q information from the JSU, and finally writing in DDR3 through an AXI bus and returning to the host end through PCI. The glRenderMode datapath when exiting the feedback mode is as shown in fig. 7.
When the current application is in the drawing mode, the name stack-related function code and the glbitmap, gldrawpixel, and glcopypixel function codes are received without any operation. And returning the click-recorded data to the host end when exiting the selection mode, and returning the number of the feedback primitives to the host end when exiting the feedback mode.
It needs to be further explained that:
if the current application program is in a drawing mode, receiving a function code related to the selection feedback and not doing any operation; if the current application program is in a selection mode, receiving a function code related to selection to perform stack initialization, stack pushing, stack popping and stack top element replacement on the name stack, and writing the name stack element into the DDR through the AXI according to the name stack depth, the minimum depth value and the maximum depth value after the last click record; if the current application program is in a feedback mode, the coordinates and attributes of the positions of the rasters are taken out from the IPU and the JSU when a function code related to feedback is received, and the coordinates and attributes are written into the DDR through the AXI, and if the current application program is in the feedback mode, the primitive vertex information is written into the DDR through the AXI according to the current feedback type configured by the GP parameter configuration unit when the primitive vertex information is received.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. A method for realizing a geometric engine stage selection feedback mechanism of a graphics processor comprises a vertex receiving and storing unit, a GP parameter configuration unit, a core computing unit, a vertex assembling and sending unit, a selection feedback unit, a task scheduling unit (JSU), an Image Processing Unit (IPU), a graphics function management unit (GFU), a PCIE and an AXI write DDR3 unit; the method is characterized in that: the method comprises the following steps:
step 1: judging a received primitive command;
the vertex receiving and storing unit receives and analyzes the primitive vertex command sent by the preceding stage unit, and judges whether the currently received primitive command is a point, a line or a triangle;
when the received primitive command is a point and a line, the command is shot according to a production line and transmitted to a vertex assembly sending unit;
when the received primitive command is a triangle, taking out (X1, Y1) (X2, Y2) (X3, Y3) values of three vertex coordinates of the triangle to send to a lower-level core computing unit, and simultaneously shooting and transmitting a triangle primitive vertex boundary mark and the command to a vertex assembly sending unit according to a production line;
step 2: parameter configuration; and through a GP parameter configuration unit, the rotation direction of the current triangle, the front and back drawing mode and the current front, back or front and back triangle parameters are configured by the Opengl instruction.
And step 3: calculating the area of the triangle;
the core calculation unit equivalently converts the product of the model of the external normal vector of the surface of the triangle and the model of the sight line vector into the calculation of the area of the triangle, and calculates the A value of the triangle vertex coordinates (X1, Y1) (X2, Y2) (X3, Y3) output by the vertex receiving and storing unit according to A = X1 (Y2-Y3) + X2 (Y3-Y1) + X3 (Y1-Y2); meanwhile, the rotation direction of the current triangle is configured by combining with the Opengl instruction, and the front and back marks of the current triangle are calculated;
and 4, step 4: eliminating the graphics primitives;
the vertex assembly sending unit generates rejection marks according to the rejection front and back triangular parameters configured by the GP parameter configuration unit and the front and back triangular marks judged by the core calculation unit; and then according to the current triangle front and back drawing mode configured by the GP parameter configuration unit and whether the current triangle front and back drawing mode is a boundary point or not and whether the current triangle front and back drawing mode is a boundary edge or not transmitted by the vertex receiving and storing unit and the boundary edge, primitive elimination is carried out.
2. The method of claim 1, wherein the stage selection feedback mechanism comprises: the selection feedback unit is used for configuring the mode of the current application program according to the GP parameter configuration unit, and if the current application program is in the drawing mode, the function code related to the selection feedback is received and no operation is performed;
if the current application program is in a selection mode, receiving a function code related to selection to perform stack initialization, stack pushing, stack popping and stack top element replacement on a name stack, and writing the name stack element into the DDR through AXI (advanced extensible interface) at the same time according to the name stack depth, the minimum depth value and the maximum depth value recorded since the last click;
if the current application program is in a feedback mode, the coordinates and the related attributes of the raster position are taken out from the IPU and the JSU and written into the DDR through the AXI when the function code related to the feedback is received, and if the current application program is in the feedback mode, the primitive vertex information is written into the DDR through the AXI according to the current feedback type configured by the GP parameter configuration unit when the primitive vertex information is received.
3. The method of claim 1, wherein the stage selection feedback mechanism comprises: the task scheduling unit retrieves depth values, color and texture attributes for the raster position from the task scheduling unit if the current application is in feedback mode and a function code associated with the feedback is received.
4. The method of claim 1, wherein the stage selection feedback mechanism comprises: the image processing unit retrieves coordinates of the raster position and the valid flag from the image processing unit if the current application is in the feedback mode and receives a function code related to the feedback.
5. The method of claim 1, wherein the step of implementing the stage selection feedback mechanism comprises: and the graphic function management unit manages the graphic function codes in a unified way and broadcasts and sends the graphic function codes to each module.
6. The method of claim 1, wherein the stage selection feedback mechanism comprises: the PCIE unit allocates the base address and the space size of the selection feedback AXI, and simultaneously returns the times of selection click recording and the number of feedback graphic elements to the host side.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211002007.8A CN115393468A (en) | 2022-08-20 | 2022-08-20 | Method for implementing geometric engine stage selection feedback mechanism of graphic processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211002007.8A CN115393468A (en) | 2022-08-20 | 2022-08-20 | Method for implementing geometric engine stage selection feedback mechanism of graphic processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115393468A true CN115393468A (en) | 2022-11-25 |
Family
ID=84119833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211002007.8A Pending CN115393468A (en) | 2022-08-20 | 2022-08-20 | Method for implementing geometric engine stage selection feedback mechanism of graphic processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115393468A (en) |
-
2022
- 2022-08-20 CN CN202211002007.8A patent/CN115393468A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10134160B2 (en) | Anti-aliasing for graphics hardware | |
| EP3246880A1 (en) | Method and device for rendering an image of a scene comprising a real object and a virtual replica of the real object | |
| CN108230435B (en) | Graphics processing using cube map textures | |
| US11521342B2 (en) | Residency map descriptors | |
| US6664971B1 (en) | Method, system, and computer program product for anisotropic filtering and applications thereof | |
| WO2008053597A1 (en) | Device for accelerating the processing of extended primitive vertex cache | |
| JP2007514230A5 (en) | ||
| US5949421A (en) | Method and system for efficient register sorting for three dimensional graphics | |
| JP4234089B2 (en) | Entertainment device, object display device, object display method, program, and character display method | |
| US6756989B1 (en) | Method, system, and computer program product for filtering a texture applied to a surface of a computer generated object | |
| JP3629243B2 (en) | Image processing apparatus and method for rendering shading process using distance component in modeling | |
| US20030122820A1 (en) | Object culling in zone rendering | |
| US10269168B2 (en) | Graphics processing systems | |
| CN104050619A (en) | Stencil then cover path rendering with shared edges | |
| CN115393468A (en) | Method for implementing geometric engine stage selection feedback mechanism of graphic processor | |
| CN118043842A (en) | Rendering format selection method and related equipment thereof | |
| KR100848687B1 (en) | 3-dimension graphic processing apparatus and operating method thereof | |
| JP4995827B2 (en) | Image processing apparatus, integrated circuit for image processing, image processing system, input assembler apparatus, integrated circuit for input assembly | |
| JP2001134777A (en) | Three-dimensional graphics system, arithmetic processor and recording medium | |
| US20230410426A1 (en) | Volume intersection using rotated bounding volumes | |
| JP4482996B2 (en) | Data storage apparatus and method and image processing apparatus | |
| EP1390919A1 (en) | Method, apparatus, and article of manufacture for associating objects with regions in coordinate space | |
| JP4419480B2 (en) | Image processing apparatus and method | |
| WO2022084666A1 (en) | Graphics processing systems | |
| CN114004925A (en) | WebGL-based model rendering method, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |