Variable ratio tessellation
By employing variable-ratio tessellation technology in computing devices to dynamically adjust the tessellation factor of tiles, the performance degradation caused by over-tessellation is solved, improving the rendering efficiency and frame rate of the graphics processing unit.
Patent Information
- Application Number
- CN202380031191.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-04-08
- Filing Date
- 2023-03-23
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2043-03-23
AI Technical Summary
Existing technologies cannot effectively solve the problem of excessive surface subdivision in regions or primitives with reduced detail in computing devices, leading to a decrease in graphics processing performance.
The variable ratio tessellation (VRT) technique is used to dynamically adjust the tessellation factor by identifying tile characteristics such as shading rate and number of visible pixels, thereby reducing unnecessary tessellation operations and improving rendering efficiency.
While maintaining image quality, the rendering performance and frame rate of the graphics processing unit were improved, and the consumption of computing resources was reduced.
Smart Images

Figure CN118974779A_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims the U.S. patent application serial number 17 / 658,634 filed on April 8, 2022 and entitled “VARIABLE RATE TESSELLATION,” the entire contents of which are expressly incorporated herein by reference. Technical Field
[0003] The present disclosure relates generally to processing systems and, more particularly, to one or more techniques for graphics processing. Background Art
[0004] Computing devices typically perform graphics and / or display processing (e.g., using a graphics processing unit (GPU), a central processing unit (CPU), a display processor, etc.) to render and display visual content. Such computing devices may include, for example, computer workstations, mobile phones such as smart phones, embedded systems, personal computers, tablet computers, and video game consoles. The GPU is configured to execute a graphics processing pipeline, which includes one or more processing stages that operate together to execute graphics processing commands and output frames. The central processing unit (CPU) can control the operation of the GPU by issuing one or more graphics processing commands to the GPU. Modern CPUs are typically capable of executing multiple applications concurrently, each of which may require the use of a GPU during execution. The display processor may be configured to convert digital information received from the CPU into analog values, and may issue commands for displaying visual content to a display panel. A device that provides content for visual presentation on a display may utilize a CPU, a GPU, and / or a display processor.
[0005] Current techniques may not be able to address the problem of over-tessellation in areas or primitives where the level of detail (LOD) may be reduced. There is a need for improved tessellation techniques where LOD may be taken into account. Summary of the invention
[0006] A brief summary of one or more aspects is given below to provide a basic understanding of such aspects. This summary is not an extensive overview of all anticipated aspects, and is neither intended to identify key or important elements of all aspects, nor to delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.
[0007] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may receive data for geometry processing of a plurality of tiles in a draw call. Each of the plurality of tiles may include a plurality of primitives. Each of the plurality of primitives in each of the plurality of tiles may include one or more sub-primitives. The apparatus may reduce a tessellation factor of each of the plurality of tiles based on a characteristic of each of the plurality of tiles. The reduced tessellation factor may correspond to a tessellation reduction factor (TRF). The characteristic may correspond to a shading rate or a number of visible pixels. The apparatus may apply the TRF to each of the plurality of tiles. The apparatus may render each of the plurality of tiles based on the TRF applied to each of the plurality of tiles.
[0008] To accomplish the foregoing and related ends, one or more aspects include features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail certain illustrative features of one or more aspects. However, these features are indicative of only a few of the various ways in which the principles of the various aspects may be employed, and this description is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 is a block diagram illustrating an example content generation system in accordance with one or more techniques of this disclosure.
[0010] Figure 2 Example images or surfaces are shown in accordance with one or more techniques of this disclosure.
[0011] Figure 3 is a block diagram illustrating a graphics processing pipeline in accordance with one or more techniques of this disclosure.
[0012] Figure 4 is a block diagram illustrating an example graphics processing pipeline including a tessellation stage, in accordance with one or more techniques of this disclosure.
[0013] Figure 5A A triangle primitive including sub-primitives generated based on tessellation is shown, in accordance with one or more techniques of this disclosure.
[0014] Figure 5B A triangle primitive including sub-primitives generated based on tessellation at a higher tessellation factor is shown, in accordance with one or more techniques of this disclosure.
[0015] Fig. 6Ais a block diagram illustrating a graphics processing pipeline in which per-draw or per-primitive variable rate tessellation (VRT) is used, in accordance with one or more techniques of this disclosure.
[0016] Figure 6B is a block diagram illustrating a graphics processing pipeline in which screen-space image-based or pixel count-based VRT is used, in accordance with one or more techniques of this disclosure.
[0017] Figure 7 is a schematic diagram illustrating a screen-space image overlaid with a frame, in accordance with one or more techniques of this disclosure.
[0018] Figure 8 is a schematic diagram illustrating a screen-space image patch intersecting a triangle primitive, in accordance with one or more techniques of this disclosure.
[0019] Fig.9A is a diagram illustrating a triangle primitive including triangle sub-primitives generated based on tessellation, in accordance with one or more techniques of this disclosure.
[0020] Fig. 9B is a diagram illustrating a quadrilateral primitive including triangular sub-primitives generated based on tessellation, in accordance with one or more techniques of this disclosure.
[0021] Fig.10 is a call-flow diagram illustrating example communications between a first GPU component and a second GPU component, in accordance with one or more techniques of this disclosure.
[0022] Fig.11 is a flowchart of an example method of graphics processing in accordance with one or more techniques of this disclosure.
[0023] Fig.12 is a flowchart of an example method of graphics processing in accordance with one or more techniques of this disclosure. DETAILED DESCRIPTION
[0024] The following is a more complete description of various aspects of the system, device, computer program product and method with reference to the accompanying drawings. However, the present disclosure can be embodied in many different forms and should not be interpreted as being limited to any specific structure or function presented throughout the present disclosure. Specifically, these aspects are provided so that the present disclosure will be comprehensive and complete, and the scope of the present disclosure will be fully conveyed to those skilled in the art. Based on the teachings herein, it should be understood by those skilled in the art that the scope of the present disclosure is intended to cover any aspect of the system, device, computer program product and method disclosed herein, whether the aspect is implemented independently of other aspects of the present disclosure or implemented in combination with other aspects. For example, using any number of aspects set forth herein, a device can be implemented or a method can be practiced. In addition, the scope of the present disclosure is intended to cover such a device or method that is practiced using other structures, functions or structures and functions other than or different from the various aspects of the disclosure set forth herein. Any aspect disclosed herein can be embodied by one or more elements of the claims.
[0025] Although various aspects are described herein, many variations and permutations of these aspects fall within the scope of the present disclosure. Although some potential benefits and advantages of various aspects of the present disclosure are mentioned, the scope of the present disclosure is not intended to be limited to specific benefits, uses or objectives. Specifically, various aspects of the present disclosure are intended to be widely applicable to different wireless technologies, system configurations, processing systems, networks and transmission protocols, some of which are illustrated by way of example in the drawings and the description below. The detailed description and drawings are merely illustrative of the present disclosure and are not limiting, and the scope of the present disclosure is defined by the appended claims and their equivalents.
[0026] Several aspects are given with reference to various apparatus and methods. These apparatus and methods are described in the detailed description below and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.
[0027] For example, an element, or any part of an element, or any combination of elements may be implemented as a "processing system" including one or more processors (which may also be referred to as a processing unit). Examples of processors include: microprocessors, microcontrollers, graphics processing units (GPUs), general-purpose GPUs (GPGPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform various functions described throughout the present disclosure. One or more processors in a processing system may execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other, software may be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, etc.
[0028] The term application may refer to software. As described herein, one or more technologies may relate to an application (e.g., software) configured to perform one or more functions. In such an example, the application may be stored in a memory (e.g., an on-chip memory of a processor, a system memory, or any other memory). The hardware described herein (such as a processor) may be configured to execute an application. For example, an application may be described as including code, which, when executed by hardware, causes the hardware to perform one or more technologies described herein. For example, the hardware may access code from a memory and execute the code accessed from the memory to perform one or more technologies described herein. In some examples, components are identified in the present disclosure. In such an example, a component may be hardware, software, or a combination thereof. A component may be a separate component or a subcomponent of a single component.
[0029] In one or more examples described herein, the described functions can be implemented in hardware, software, or any combination thereof. If implemented in software, the functions can be stored or encoded on a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media. Storage media can be any available media that can be accessed by a computer. By way of example and not limitation, such computer-readable media can include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, a combination of computer-readable media of the above types, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.
[0030] As used herein, instances of the term "content" may refer to "graphic content," "images," and the like, regardless of whether the term is used as an adjective, noun, or other part of speech. In some examples, as used herein, the term "graphic content" may refer to content produced by one or more processes of a graphics processing pipeline. In further examples, as used herein, the term "graphic content" may refer to content produced by a processing unit configured to perform graphics processing. In further examples, as used herein, the term "graphic content" may refer to content produced by a graphics processing unit.
[0031] In computer graphics, there may be a tradeoff between the level of detail (LOD) of a rendered image and the performance of a rendering GPU, which may be measured in frames per second (FPS). The LOD may be reduced in certain portions of an image without having much impact on the perceived quality of the image. The performance of the rendering GPU may be improved by identifying such areas (e.g., patches) or draws and reducing the details in these areas or draws. In one or more aspects, a variable rate tessellation (VRT) technique may use a shading rate from a variable rate shading (VRS) feature and / or an average pixel count per sub-primitive value to identify areas or draws where a low LOD may be used. The VRT technique may then reduce the tessellation rate of such areas or draws.
[0032] Figure 11 is a block diagram showing an example content generation system 100 configured to implement one or more techniques of the present disclosure. The content generation system 100 includes a device 104. The device 104 may include one or more components or circuits for performing various functions described herein. In some examples, one or more components of the device 104 may be components of a SOC. The device 104 may include one or more components configured to perform one or more techniques of the present disclosure. In the example shown, the device 104 may include a processing unit 120, a content encoder / decoder 122, and a system memory 124. In some aspects, the device 104 may include multiple optional components (e.g., a communication interface 126, a transceiver 132, a receiver 128, a transmitter 130, a display processor 127, and one or more displays 131). The display 131 may refer to one or more displays 131. For example, the display 131 may include a single display or multiple displays, which may include a first display and a second display. The first display may be a left-eye display, and the second display may be a right-eye display. In some examples, the first display and the second display may receive different frames for presentation thereon. In other examples, the first display and the second display may receive the same frame for presentation thereon. In further examples, the result of the graphics processing may not be displayed on the device, for example, the first display and the second display may not receive any frame for presentation thereon. Alternatively, the frame or graphics processing result may be transmitted to another device. In some aspects, this may be referred to as split rendering.
[0033] The processing unit 120 may include an internal memory 121. The processing unit 120 may be configured to perform graphics processing using the graphics processing pipeline 107. The content encoder / decoder 122 may include an internal memory 123. In some examples, the device 104 may include a processor that may be configured to perform one or more display processing techniques on one or more frames generated by the processing unit 120 before the frames are displayed by one or more displays 131. Although the processor in the example content generation system 100 is configured as a display processor 127, it should be understood that the display processor 127 is an example of a processor and other types of processors, controllers, etc. may be used in place of the display processor 127. The display processor 127 may be configured to perform display processing. For example, the display processor 127 may be configured to perform one or more display processing techniques on one or more frames generated by the processing unit 120. The one or more displays 131 may be configured to display or otherwise present the frames processed by the display processor 127. In some examples, one or more displays 131 may include one or more of the following: a liquid crystal display (LCD), a plasma display, an organic light emitting diode (OLED) display, a projection display device, an augmented reality display device, a virtual reality display device, a head-mounted display, or any other type of display device.
[0034] Memory external to the processing unit 120 and the content encoder / decoder 122, such as the system memory 124, may be accessible to the processing unit 120 and the content encoder / decoder 122. For example, the processing unit 120 and the content encoder / decoder 122 may be configured to read from and / or write to the external memory, such as the system memory 124. The processing unit 120 may be communicatively coupled to the system memory 124 via a bus. In some examples, the processing unit 120 and the content encoder / decoder 122 may be communicatively coupled to the internal memory 121 via a bus or via a different connection.
[0035] The content encoder / decoder 122 may be configured to receive graphics content from any source, such as the system memory 124 and / or the communication interface 126. The system memory 124 may be configured to store the received encoded or decoded graphics content. The content encoder / decoder 122 may be configured to receive the encoded or decoded graphics content in the form of encoded pixel data, for example, from the system memory 124 and / or the communication interface 126. The content encoder / decoder 122 may be configured to encode or decode any graphics content.
[0036] Internal memory 121 or system memory 124 may include one or more volatile or non-volatile memory or storage devices. In some examples, internal memory 121 or system memory 124 may include RAM, static random access memory (SRAM), dynamic random access memory (DRAM), erasable programmable ROM (EPROM), EEPROM, flash memory, magnetic data medium or optical storage medium, or any other type of memory. According to some examples, internal memory 121 or system memory 124 may be a non-transitory storage medium. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier or propagated signal. However, the term "non-transitory" should not be interpreted as meaning that internal memory 121 or system memory 124 is non-removable or its content is static. As an example, system memory 124 can be removed from device 104 and moved to another device. As another example, system memory 124 may be non-removable from device 104.
[0037] Processing unit 120 may be a CPU, GPU, GPGPU, or any other processing unit that may be configured to perform graphics processing. In some examples, processing unit 120 may be integrated into the motherboard of device 104. In a further example, processing unit 120 may be present on a graphics card installed in a port of the motherboard of device 104, or may be otherwise incorporated into a peripheral device configured to interoperate with device 104. Processing unit 120 may include one or more processors, such as one or more microprocessors, GPUs, ASICs, FPGAs, arithmetic logic units (ALUs), DSPs, discrete logic, software, hardware, firmware, other equivalent integrated or discrete logic circuits, or any combination thereof. If the technology is partially implemented in software, processing unit 120 may store instructions for software in a suitable non-temporary computer-readable storage medium (e.g., internal memory 121), and may use one or more processors to execute instructions in hardware to perform the technology of the present disclosure. Any of the foregoing contents including hardware, software, a combination of hardware and software, etc. may be considered to be one or more processors.
[0038] The content encoder / decoder 122 may be any processing unit configured to perform content decoding. In some examples, the content encoder / decoder 122 may be incorporated into the mainboard of the device 104. The content encoder / decoder 122 may include one or more processors, such as one or more microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), arithmetic logic units (ALUs), digital signal processors (DSPs), video processors, discrete logic, software, hardware, firmware, other equivalent integrated or discrete logic circuits, or any combination thereof. If the technology is partially implemented in software, the content encoder / decoder 122 may store instructions for the software in a suitable non-temporary computer-readable storage medium (e.g., internal memory 123), and may use one or more processors to execute instructions in the hardware to perform the technology of the present disclosure. Any of the foregoing contents including hardware, software, a combination of hardware and software, etc. may be considered to be one or more processors.
[0039] In some aspects, the content generation system 100 may include an optional communication interface 126. The communication interface 126 may include a receiver 128 and a transmitter 130. The receiver 128 may be configured to perform any receiving functions described herein with respect to the device 104. In addition, the receiver 128 may be configured to receive information (e.g., eye or head position information, rendering commands, and / or position information) from another device. The transmitter 130 may be configured to perform any sending functions described herein with respect to the device 104. For example, the transmitter 130 may be configured to send information that may include a request for content to another device. The receiver 128 and the transmitter 130 may be combined into a transceiver 132. In such an example, the transceiver 132 may be configured to perform any receiving functions and / or sending functions described herein with respect to the device 104.
[0040] Reference again Figure 1In some aspects, the display processor 127 may include a VRT unit 198 configured to receive data for geometry processing of multiple tiles in a draw call. Each of the multiple tiles may include multiple primitives. Each of the multiple primitives in each of the multiple tiles may include one or more sub-primitives. The VRT unit 198 may be configured to reduce the tessellation factor of each of the multiple tiles based on the characteristics of each of the multiple tiles. The reduced tessellation factor may correspond to a TRF. The characteristic may correspond to a shading rate or a number of visible pixels. The VRT unit 198 may be configured to apply a TRF to each of the multiple tiles. The VRT unit 198 may be configured to render each of the multiple tiles based on the TRF applied to each of the multiple tiles. Although the following description may focus on graphics processing, the concepts described herein may be applicable to other similar processing techniques.
[0041] A device such as device 104 may refer to any device, apparatus, or system configured to perform one or more techniques described herein. For example, a device may be a server, a base station, a user device, a client device, a station, an access point, a computer (such as a personal computer, a desktop computer, a laptop computer, a tablet computer, a computer workstation, or a mainframe computer), an end product, an apparatus, a phone, a smart phone, a server, a video game platform or console, a handheld device (such as a portable video game device or a personal digital assistant (PDA)), a wearable computing device (such as a smart watch, an augmented reality device, or a virtual reality device), a non-wearable device, a display or display device, a television, a television set-top box, an intermediate network device, a digital media player, a video streaming device, a content streaming device, an onboard computer, any mobile device, any device configured to generate graphics content, or any device configured to perform one or more techniques described herein. The process herein may be described as being performed by a specific component (e.g., a GPU), but in other embodiments, it may be performed using other components (e.g., a CPU) consistent with the disclosed embodiments.
[0042] The GPU can process multiple types of data or data packets in the GPU pipeline. For example, in some aspects, the GPU can process two types of data or data packets, such as context register packets and draw call data. The context register packet can be a global state information set that can manage how the graphics context will be processed, such as information about global registers, shader programs, or constant data. For example, the context register packet may include information about the color format. In some aspects of the context register packet, there may be a bit indicating which workload belongs to the context register. In addition, there may be multiple functions or programs that run simultaneously and / or in parallel. For example, a function or program may describe a specific operation, such as a color mode or color format. Therefore, the context register can define multiple states of the GPU.
[0043] The context state can be used to determine how a single processing unit (e.g., a vertex fetcher (VFD), a vertex shader (VS), a shader processor, or a geometry processor) operates, and / or in what mode the processing unit operates. To this end, the GPU can use context registers and programming data. In some aspects, the GPU can generate workloads in the pipeline, such as vertex or pixel workloads, based on context register definitions of modes or states. Certain processing units (e.g., VFDs) can use these states to determine certain functions, such as how to assemble vertices. Since these modes or states may change, the GPU may need to change the corresponding context. In addition, the workload corresponding to the mode or state can follow the changed mode or state.
[0044] The GPU can render images in a variety of different ways. In some instances, the GPU can use rendering and / or tile rendering to render images. In a tile rendering GPU, the image can be divided or separated into different parts or tiles. After the image is divided, each part or tile can be rendered separately. The tile rendering GPU can divide the computer graphics image into a grid format so that each part of the grid (i.e., tile) can be rendered separately. In some aspects, in a binning pass, the image can be divided into different bins or tiles. In some aspects, during the binning pass, a visibility stream can be constructed, in which visible primitives or drawing calls can be identified. Compared with tile rendering, direct rendering does not divide the frame into smaller bins or tiles. Instead, in direct rendering, the entire frame is rendered at a single time. In addition, some types of GPUs can allow both tile rendering and direct rendering (e.g., flexible rendering).
[0045] In some aspects, the GPU may apply a drawing or rendering process to different bins or patches. For example, the GPU may render for one bin and perform all drawing for the primitives or pixels in the bin. During the process of rendering for the bin, the rendering target may be located in the GPU internal memory (GMEM). In some instances, after rendering for one bin, the contents of the rendering target may be moved to the system memory, and the GMEM may be released to render the next bin. In addition, the GPU may render for another bin and perform drawing for the primitives or pixels in the bin. Therefore, in some aspects, there may be a small number of bins (e.g., four bins) that cover all drawing in one surface. Further, the GPU may loop through all drawing in one bin, but perform drawing for visible drawing calls (i.e., drawing calls including visible geometry). In some aspects, for example, in a binning pass, a visibility stream may be generated to determine visibility information for each primitive in an image or scene. For example, the visibility stream may identify whether a primitive is visible. In some aspects, this information may be used, for example, to remove invisible primitives in a rendering pass. Additionally, at least some of the primitives identified as visible may be rendered in the rendering pass.
[0046] In some aspects of patch rendering, there may be multiple processing stages or paths. For example, rendering may be performed in two paths, such as a visibility or bin-visibility path and a rendering or bin-rendering path. During the visibility path, the GPU may input a rendering workload, record the position of a primitive or triangle, and then determine which primitives or triangles fall into which bin or region. In some aspects of the visibility path, the GPU may also identify or mark the visibility of each primitive or triangle in the visibility stream. During the rendering path, the GPU may input a visibility stream and process one bin or region at a time. In some aspects, the visibility stream may be analyzed to determine which primitives or vertices of primitives are visible or invisible. Therefore, visible primitives or vertices of primitives may be processed. By doing so, the GPU may reduce unnecessary workloads for processing or rendering invisible primitives or triangles.
[0047] In some aspects, during the visibility pass, certain types of primitive geometries, such as position-only geometry, may be processed. In addition, primitives may be classified into different bins or regions based on the position or positioning of the primitives or triangles. In some instances, the classification of primitives or triangles into different bins may be performed by determining visibility information for the primitives or triangles. For example, the GPU may determine visibility information for each primitive in the primitives in each bin or region or write the visibility information, for example, to a system memory. The visibility information may be used to determine or generate a visibility stream. In the rendering pass, the primitives in each bin may be rendered separately. In these instances, the visibility stream may be extracted from a memory for discarding primitives that are not visible to the bin.
[0048] Some aspects of the GPU or GPU architecture can provide a variety of different options for rendering, such as software rendering and hardware rendering. In software rendering, the driver or CPU can copy the entire frame geometry by processing each view at a time. In addition, some different states can change depending on the view. Therefore, in software rendering, the software can copy the entire workload by changing some states that can be used to render for each viewpoint in the image. In some aspects, there may be an increased amount of overhead because the GPU may submit the same workload multiple times for each viewpoint in the image. In hardware rendering, the hardware or GPU may be responsible for copying or processing the geometry for each viewpoint in the image. Therefore, the hardware can manage the copying or processing of primitives or triangles for each viewpoint in the image.
[0049] Figure 2 An image or surface 200 is shown that includes a plurality of primitives divided into a plurality of bins, in accordance with one or more techniques of this disclosure. Figure 2 As shown, image or surface 200 includes region 202, which includes primitives 221, 222, 223, and 224. Primitives 221, 222, 223, and 224 are divided or placed into different bins, such as bins 210, 211, 212, 213, 214, and 215. Figure 2 An example of using tile-based rendering of multiple viewpoints for primitives 221-224 is shown. For example, primitives 221-224 are located in a first viewpoint 250 and a second viewpoint 251. Thus, a GPU processing or rendering an image or surface 200 including region 202 may utilize multiple viewpoints or multi-view rendering.
[0050] As indicated herein, a GPU or graphics processor unit may use a tiled rendering architecture to reduce power consumption or save memory bandwidth. As further stated above, such a rendering method may divide a scene into multiple bins, and include a visibility pass that identifies triangles visible in each bin. Thus, in tiled rendering, a full screen may be divided into multiple bins or tiles. The scene may then be rendered multiple times, for example, once or multiple times for each bin.
[0051] In various aspects of graphics rendering, some graphics applications may render to a single target (i.e., a render target) one or more times. For example, in graphics rendering, a frame buffer on a system memory may be updated multiple times. A frame buffer may be a portion of a memory or random access memory (RAM) (e.g., containing a bitmap or storage) to help store display data for a GPU. A frame buffer may also be a memory buffer containing a complete frame of data. Additionally, a frame buffer may be a logical buffer. In some aspects, updating a frame buffer may be performed in bin or tile rendering, where, as discussed above, a surface is divided into multiple bins or tiles, and each bin or tile may then be rendered separately. Further, in tile rendering, a frame buffer may be divided into multiple bins or tiles.
[0052] As indicated herein, in some aspects (such as in a bin or tile-based rendering architecture), a frame buffer may have data stored or written to it repeatedly, for example, when rendering from different types of memory. This may be referred to as parsing and unparsing frame buffers or system memory. For example, when storing or writing to one frame buffer and then switching to another frame buffer, the data or information on the frame buffer may be parsed from the GMEM at the GPU to system memory, i.e., memory in double data rate (DDR) RAM or dynamic RAM (DRAM).
[0053] In some aspects, system memory may also be a system on chip (SoC) memory or another chip-based memory for storing data or information, such as on a device or smartphone. System memory may also be a physical data storage shared by the CPU and / or GPU. In some aspects, system memory may be a DRAM chip, such as on a device or smartphone. Thus, SoC memory may be a chip-based way to store data.
[0054] In some aspects, GMEM can be an on-chip memory at the GPU, which can be implemented by static RAM (SRAM). In addition, GMEM can be stored on a device (e.g., a smart phone). As indicated herein, data or information can be transmitted between system memory or DRAM and GMEM, for example, at a device. In some aspects, the system memory or DRAM can be located at the CPU or GPU. In addition, data can be stored at DDR or DRAM. In some aspects (such as in bin or patch rendering), a small portion of the memory can be stored at the GPU (e.g., at GMEM). In some instances, storing data at GMEM may use a larger processing workload and / or power consumption than storing data at a frame buffer or system memory.
[0055] Figure 3 3 is a block diagram illustrating a graphics processing pipeline 300. The pipeline 300 includes an input assembler stage 382, a vertex shader stage 384, a geometry shader stage 386, a rasterizer stage 388, a pixel shader stage 390, and an output merger stage 392. In some examples, an application program interface (API) may be configured to use Figure 3 Each of these stages is shown in . Graphics processing pipeline 400 is described below as being performed by processing unit 120, but may be performed by various other graphics processors.
[0056] The graphics processing pipeline 300 generally includes programmable stages (e.g., shown with rounded angles) and fixed-function stages (e.g., shown with right angles). For example, graphics rendering operations associated with certain stages of the graphics rendering pipeline 300 are generally performed by programmable shader processors, while other graphics rendering operations associated with other stages of the graphics rendering pipeline 300 are generally performed by non-programmable fixed-function hardware units associated with the processing unit 120. Graphics rendering stages performed by shading units may generally be referred to as "programmable" stages, while stages performed by fixed-function units may generally be referred to as fixed-function stages. The indications herein as to whether different stages are programmable stages or fixed-function stages may be exemplary, and other combinations between programmable stages or fixed-function stages may also be used.
[0057] Input assembler stage 382 in Figure 3The input assembler stage 382 is shown as a fixed function stage in the example of , and is generally responsible for providing graphics data (e.g., triangles, lines, and points) to the graphics processing pipeline 300. For example, the input assembler stage 382 can collect vertex data for high-order surfaces, primitives, etc., and output the vertex data and attributes to the vertex shader stage 384. Therefore, the input assembler stage 382 can use fixed function operations to read vertices from off-chip memory. The input assembler stage 382 can then create pipeline work items from these vertices, while also generating vertex identifiers ("VertexID"), instance identifiers ("InstanceID", which can be used for vertex shaders), and primitive identifiers ("PrimitiveID", which can be used for geometry shaders and pixel shaders). The input assembler stage 382 can automatically generate VertexID, InstanceID, and PrimitiveID when reading vertices.
[0058] Vertex shader stage 384 may process the received vertex data and attributes. For example, vertex shader stage 384 may perform per-vertex processing such as transformations, skinning, vertex displacement, and calculate per-vertex material attributes. In some examples, vertex shader stage 384 may generate texture coordinates, vertex colors, vertex lighting, fog factors, etc. Vertex shader stage 384 typically takes a single input vertex and outputs a single processed output vertex.
[0059] The geometry shader stage 386 can receive a primitive defined by vertex data (e.g., three vertices of a triangle, two vertices of a line, or a single vertex of a point), and further process the primitive. For example, the geometry shader stage 386 can perform per-primitive processing (such as silhouette-edge detection and shadow volume extrusion) and other possible processing operations. Therefore, the geometry shader stage 386 can receive a primitive as input (which can include one or more vertices) and output zero, one or more primitives (which can also include one or more vertices). The output primitive can contain more data than the data that may be contained in the absence of the geometry shader stage 386. The total amount of output data can be equal to the vertex size multiplied by the vertex count, and can be limited per invocation. The stream output from the geometry shader stage 386 can allow the primitives arriving at this stage to be stored in off-chip memory. The stream output is usually associated with the geometry shader stage 386, and the two can be programmed together (e.g., using an API).
[0060] The rasterizer stage 388 may be a fixed function stage responsible for clipping primitives and preparing primitives for the pixel shader stage 390. For example, the rasterizer stage 388 may perform clipping (including custom clipping bounds), perspective partitioning, viewport / scissor selection and implementation, render target selection, and primitive setup. In this manner, the rasterizer stage 388 may generate multiple fragments for shading by the pixel shader stage 390.
[0061] The pixel shader stage 390 may receive fragments from the rasterizer stage 388 and generate per-pixel data such as color. The pixel shader stage 390 may also perform per-pixel processing such as texture blending and lighting model calculations. Thus, the pixel shader stage 390 may receive a pixel as input and may output a pixel (or a zero value for the pixel) at the same relative position.
[0062] The output merger stage 392 may be responsible for combining various types of output data (such as pixel shader values, depth information, and stencil information) to generate a final result. For example, the output merger stage 392 may perform fixed function blending, depth, and / or stencil operations on a render target (pixel location). Although generally described above with respect to the vertex shader stage 384, the geometry shader stage 386, and the pixel shader stage 390, each of the foregoing descriptions may refer to one or more shading units designated by the GPU to perform the corresponding shading operations.
[0063] Some GPUs may not support Figure 3 . For example, due to hardware and / or software limitations (e.g., a limited number of shading units and associated components), some GPUs may not be able to designate a shading unit to perform more than two shading operations. In an example, some GPUs may not support operations associated with the geometry shader stage 386. Instead, the GPU may include support for designating a shading unit to perform the vertex shader stage 384 and the pixel shader stage 390. Therefore, the operations performed by the shading unit may follow the input / output interface associated with the vertex shader stage 384 and the pixel shader stage 390.
[0064] Furthermore, in some examples, the introduction of geometry shader stage 386 into the pipeline may result in additional reads and writes to memory cells relative to a graphics processing pipeline that does not include geometry shader stage 386. For example, as described above, vertex shader stage 384 may write vertices out to off-chip memory. Geometry shader stage 386 may read these vertices (the vertices output by vertex shader stage 384) and write new vertices, which are then pixel shaded.
[0065] Figure 4 4 is a block diagram illustrating an example graphics processing pipeline 400 including a tessellation stage. For example, pipeline 400 includes an input assembler stage 440, a vertex shader stage 442, a hull shader stage 444, a tessellator stage 446, a domain shader stage 448, a geometry shader stage 450, a rasterizer stage 452, a pixel shader stage 454, and an output merger stage 456. In some examples, the API may be configured to use Figure 4 Each of the stages shown in . Graphics processing pipeline 400 is described below as being performed by processing unit 120, but may also be performed by various other graphics processors.
[0066] exist Figure 4 Some of the stages shown in Figure 3 The stages shown and described are configured similarly or identically (e.g., assembler stage 440, vertex shader stage 442, geometry shader stage 450, rasterizer stage 452, pixel shader stage 454, and output merger stage 456). In addition, pipeline 400 includes additional stages for hardware tessellation. For example, in addition to the above description of Figure 3 In addition to the stages described above, graphics processing pipeline 400 also includes a hull shader stage 444, a tessellator stage 446, and a domain shader stage 448. That is, hull shader stage 444, tessellator stage 446, and domain shader stage 448 are included to accommodate tessellation performed by processing unit 120, rather than by an executing software application (e.g., by a CPU).
[0067] The hull shader stage 444 may receive primitives from the vertex shader stage 442 and may be responsible for performing at least two actions. First, the hull shader stage 444 may be responsible for determining a set of tessellation factors. The hull shader stage 444 may generate the tessellation factors once per primitive. The tessellation factor may be used by the tessellator stage 446 to determine how finely to tessellate (e.g., split the primitive into smaller parts) a given primitive. The hull shader stage 444 may also be responsible for generating control points that will be used later by the domain shader stage 448. That is, for example, the hull shader stage 444 may be responsible for generating control points that will be used by the domain shader stage 448 to create actual tessellated vertices that are ultimately used when rendering.
[0068] When the tessellator stage 446 receives data from the hull shader stage 444, the tessellator stage 446 may use one of several algorithms to determine an appropriate sampling pattern for the current primitive type. For example, typically, the tessellator stage 446 may convert a requested tessellation amount (as determined by the hull shader stage 444) into a set of coordinate points within the current "domain." That is, depending on the tessellation factor from the hull shader stage 444 and the particular configuration of the tessellator stage 446, the tessellator stage 446 may determine which points in the current primitive need to be sampled in order to tessellate the input primitive into smaller parts. The output of the tessellator stage 446 may be a set of domain points, which may include barycentric coordinates.
[0069] The domain shader stage 448 may take domain points in addition to the control points generated by the hull shader stage 444 and use them to create new vertices. The domain shader stage 448 may use the complete list of control points generated for the current primitive, texture, procedural algorithm, or any other algorithm to convert the centroid "position" for each tessellated point into an output geometry that is passed to the next stage in the pipeline. As mentioned above, some GPUs may not be able to support Figure 4 442 and pixel shader stage 454. Thus, the operations performed by the shading units may comply with the input / output interfaces associated with the vertex shader stage 442 and the pixel shader stage 454.
[0070] In computer graphics, there may be a tradeoff between the LOD of a rendered image and the performance of the rendering GPU (which may be measured in FPS). In other words, when the LOD is high, the FPS number may drop. Conversely, performance may be improved by lowering the LOD. The LOD may be reduced in certain portions of an image without having much impact on the perceived quality of the image. By identifying such areas (e.g., tiles) or draws and reducing the details in these areas or draws, the performance of the rendering GPU may be improved.
[0071] Examples of areas or objects where a low LOD may be acceptable may include objects far away from the camera, areas that are not in the user's focus (e.g., the focus of the user's eyes), moving objects (such objects may typically be motion blurred), or objects that are in shadow or not adequately lit.
[0072] The number of primitives of an object being rendered and the pixel shading rate of primitives being rasterized may affect the LOD of a rendering operation.
[0073] The number of primitives in a drawing or object can be changed in the vertex shader stage of the graphics pipeline. Changing the number of primitives specified by the developer may not be recommended because doing so may cause undesirable effects, such as breaking the watertightness of the object or drawing (e.g., a watertight mesh set may refer to a mesh consisting of one closed surface). For tessellated primitives, the number of interior (or inside) tessellated primitives can be modified without breaking the watertightness of the drawing. Sometimes, tessellation may generate a large number of sub-primitives, many of which may ultimately contribute little to the quality of the image. The internal tessellation rate of such a primitive can be reduced without much reduction in image quality.
[0074] Figure 5A A triangle primitive 500A is shown that includes sub-primitives generated based on tessellation. The shaded sub-primitives may correspond to the inner tessellated sub-primitives. The unshaded sub-primitives may correspond to the outer tessellated sub-primitives. Figure 5B 500B is shown, which includes sub-primitives generated based on tessellation at a higher tessellation factor. Triangle primitive 500B may be the same as triangle primitive 500A. Due to the higher tessellation factor, triangle primitive 500B may include many more sub-primitives than triangle primitive 500A. Similar to Figure 5A ,exist Figure 5B , the shaded sub-primitives may correspond to the inner tessellated sub-primitives, and the unshaded sub-primitives may correspond to the outer tessellated sub-primitives.
[0075] The tessellation rate may be specified by a tessellation factor (TessFactor). TessFactor may indicate how many times the edge of a primitive may be tessellated. There may be separate TessFactors for external edges and internal edges (ie, external TessFactor and internal TessFactor).
[0076] In one or more aspects, the VRT technique can use the shading rate and / or average pixel count per sub-primitive value from the VRS feature to identify areas or drawings where a low LOD can be used. The VRT technique can then reduce the tessellation rate of such areas or drawings.
[0077] VRS can be an API feature and can allow developers to specify different shading rates for different areas of a frame or draws. The shading rate can refer to the resolution at which a pixel shader (or fragment shader) is called. Without VRS, one pixel can be shaded for each pixel / fragment shader operation. With VRS, a group of nearby pixels can be shaded together in one operation. The group of pixels can be a block of 1x 2 (e.g., oriented horizontally), 2x 1 (e.g., oriented vertically), or 4x 4 pixels, etc. In areas where the LOD specification is low, developers can reduce the shading rate. In other words, more pixels can be shaded in one shader operation. In one or more aspects, based on VRT technology, if the shading rate is low, the tessellation rate can be reduced.
[0078] In one or more aspects, in addition to or in lieu of VRS-based shading rates, VRT techniques can use pixel counts to identify tessellation rates. Specifically, primitives with low pixel counts per sub-primitive can be identified, and the tessellation rates of such primitives can be reduced.
[0079] In one or more aspects, tessellation operations can be performed in quadrilateral (quad) and triangle (tri) domains using triangles as output primitive types.
[0080] In some examples, the internal TessFactor (rather than the external TessFactor) may be different. In such examples, the external TessFactor may not be changed, as doing so may destroy the watertightness of the drawing.
[0081] A tessellation reduction factor (TRF) may refer to a multiplicand by which an internal TessFactor may be multiplied in order to reduce the internal TessFactor. The TRF may fall within a range, for example, a (0-1] range (ie, excluding 0 and including 1). When the TRF is 1, the original TessFactor may be retained.
[0082] When geometry shaders are enabled, VRT technology may not be used. As mentioned above, geometry shaders can take one primitive as input and can output multiple primitives. Since the number of input primitives to a geometry shader can be reduced based on VRT, the output image may change significantly if VRT is used with geometry shaders. Geometry shaders and tessellation may rarely be enabled together.
[0083] Per-draw and per-primitive VRT techniques can be used in both tile-based (binned) or direct rendering architectures. Screen-space image-based and pixel-count-based VRT techniques can be used in tile-based architectures. The per-draw, per-primitive, screen-space image-based, and pixel-count-based approaches may be further explained in detail below.
[0084] In one or more aspects, as part of the VRT, a TRF can be identified based on a shading rate (eg, pixel pattern) that can be received from a VRS feature. According to one aspect, Table 1 below can provide TRFs corresponding to different shading rates.
[0085]
[0086]
[0087] Table 1
[0088] Here, the TRF can be selected so that the ratio of the number of pixels to the number of sub-primitives ((number of pixels) / (number of sub-primitives)) is maintained (or the variation is kept to a minimum). In different configurations, the number of pixels can refer to the number of effective pixels or the number of visible pixels, as will be explained in further detail below. For example, consider the case where the shading rate is 2x 2 pixels. Therefore, the effective pixel count can be reduced by a factor of 4 because 4 pixels can be grouped together to form 1 coarse (effective) pixel. In order to maintain the same ratio of the number of (effective) pixels to the number of sub-primitives, the number of sub-primitives can also be reduced by a factor of 4. Since the number of sub-primitives can vary roughly as the square of the internal TessFactor, the TRF can be chosen to be 1 / 2 in this case.
[0089] In the VRS feature, shading rates can be specified at different granularities. These can include per-draw granularity, per-primitive (e.g., per provoking vertex) granularity, per-screen-space image granularity, or any combination of the three.
[0090] The VRT technique associated with each of the shading rate granularities may be described in detail below. Specifically, the VRT technique may use the VRS input to identify an internal TessFactor.
[0091] Fig. 6A 6 is a block diagram showing a graphics processing pipeline 600A in which a per-draw or per-primitive VRT is used. The various stages may correspond to Figure 3 and Figure 4 . In the binning (visibility) path, block 602 may include an input assembler stage and a geometry processing stage. Block 604 may include a hull shader stage, which may generate and output an unmodified TessFactor. Block 606 may include a TessFactor adjuster stage, which may adjust TessFactor based on a VRS input including a shading rate of a drawing or primitive to output an adjusted TessFactor. Block 608 may include a tessellation stage, which may perform tessellation based on the adjusted TessFactor. Block 610 may include a domain shader stage, a low resolution Z (LRZ) stage, and a visibility stream compressor (VSC) stage. Block 610 may output a visibility stream, which may be processed in a rendering path. In a rendering path, block 612 may include an input assembler stage and a geometry processing stage. Block 614 may include a hull shader stage, which may generate and output an unmodified TessFactor. Block 616 may include a TessFactor adjuster stage that may adjust TessFactor based on VRS inputs including a shading rate of a draw or primitive to output an adjusted TessFactor. Block 618 may include a tessellator stage that may perform tessellation based on the adjusted TessFactor. Block 620 may include a domain shader stage and a pixel shader stage. Block 620 may output a rendered image.
[0092] In one aspect, using the VRS feature, a developer or application can specify a shading rate per draw in a command buffer. The LOD specified for each draw can be identified based on the shading rate. The VRT technology can receive the shading rate (e.g., at blocks 606 and 616) and can apply the corresponding TRF to all primitives in the draw call. In some examples, without specifying a shading rate per draw directly through the API, shading rate information for the same frame can be obtained on a per-draw or per-tile basis based on a binning pass. In a further example, the shading rate information can be obtained based on data from a previous frame.
[0093] The same TessFactor reduction technique can be applied in both the binning (visibility) pass and the rendering pass. Thus, the per-draw VRT technique can save cycles in the hardware tessellator and domain shader in both the binning pass and the rendering pass.
[0094] In one aspect, VRS can allow developers to specify shading rates on a per-primitive level (e.g., per-firing vertex (one of the vertices in an output primitive can be designated as the firing vertex, and that designation can be used by other processes (e.g., use the output from the firing vertex instead of the output from other vertices))). The shading rate on a per-primitive level can be specified along with the firing vertices in the command buffer. If the shading rate is not specified per-primitive, the shading rate can be assumed to be 1x 1.
[0095] Changing the per-primitive tessellation rate can be similar to changing the per-draw tessellation rate, except for the granularity at which the VRT technique is applied. Here, the VRT technique can recognize the TRF and can modify the internal TessFactor of each primitive based on the shading rate of the primitive.
[0096] Similar to per-draw VRT, per-primitive VRT techniques can also save cycles in the hardware tessellator and domain shader in both the binning (visibility) pass and the rendering pass.
[0097] Figure 6B 6 is a block diagram showing a graphics processing pipeline 600B in which a screen space image based or pixel count based VRT is used. The various stages may correspond to Figure 3 and Figure 4 662。Block 654 may include a visibility stream compressor stage. In the rendering path, block 656 may include an input assembler stage, a geometry processing stage, a shell shader stage, a tessellation stage, a domain shader stage, and an LRZ stage. In the binning (visibility) path, block 652 may include an input assembler stage, a geometry processing stage, a shell shader stage, a tessellation stage, a domain shader stage, and an LRZ stage. A TRF for each drawing or primitive in a drawing or primitive may be generated at block 652, and may be stored at a TRF buffer 662. Block 654 may include a visibility stream compressor stage. In the rendering path, block 656 may include an input assembler stage, a geometry processing stage, and a shell shader stage. The unmodified TessFactor provided by the shell shader stage may be adjusted based on the corresponding TRF value that may be obtained from the TRF buffer 662. Block 658 may include a tessellation stage and a domain shader stage. The tessellation stage may perform tessellation based on the adjusted TessFactor. Block 660 may include a pixel shader stage. Block 660 may output a rendered image.
[0098] In one aspect, in the VRS feature, using screen space images, developers can specify shading rates for different areas of the frame. Shading rates can be specified for blocks of pixel tiles (e.g., 8 x 8, 16 x 16, or 32 x 32 pixel tiles) as indicated by the VRS tile size. Based on the shading rate, the VRT technology can assign a TRF to each tile.
[0099] Figure 7 700 is a schematic diagram showing a screen space image overlapped with a frame. The origin (e.g., the upper left corner) of the screen space image can be aligned with the origin (e.g., the upper left corner) of the frame. If the frame is larger than the screen space image, the spill over region of the frame can have a TRF value set to "1" (i.e., no TessFactor reduction). Therefore, in Figure 7 In the example, based on different LOD specifications, the area of the frame that is within the screen space image can be associated with a low tessellation rate (for a low LOD specification), a medium tessellation rate (for a medium LOD specification), or a high tessellation rate (for a high LOD specification). The low, medium, or high tessellation rates can be associated with a low, medium, or high TRF value, respectively. The overflow area of the frame outside the screen space image can be associated with a default unmodified tessellation rate (i.e., the TRF value can be set to "1").
[0100] In screen-space image-based VRT, the positions of primitives output from the tessellator may be available after, rather than before, the geometry processing stage in the binning (visibility) pass in block 652. Therefore, VRT techniques may not be applied in the binning (visibility) pass.
[0101] The LRZ stage, which may come after the geometry processing stage, may have access to both the screen space image and the location of the primitive on the frame. At this stage of the graphics pipeline, TRF values may be calculated and assigned to each tile. Among the TRFs of tiles associated with (e.g., at least partially covered by) the primitive, the highest TRF value may be selected as the TRF for the primitive.
[0102] Figure 8 8 is a schematic diagram 800 showing screen space image patches intersecting with triangle primitives. The triangle primitives may be distributed across three screen space image patches. The numbers ("0.5", "0.5", "1", and "0.25") may be TRF values for the corresponding screen space image patches. The highest TRF value (which may correspond to the smallest TessFactor reduction) (which is "1" for the lower left patch) may be selected as the TRF for the triangle primitive.
[0103] Return to reference Figure 6B, the selected TRF value may be stored in the TRF buffer 662. In the rendering pass, for each tessellated primitive, the TRF may be retrieved from the TRF buffer 662, and the TessFactor may be modified accordingly. The adjusted TessFactor may then be sent to the hardware tessellator.
[0104] Screen-space based VRT techniques can save cycles in the hardware tessellator and domain shader in the rendering pass (but not in the binning pass).
[0105] In one aspect, the VRT technique can be based on pixel counts. The tessellator may sometimes over-tessellate a primitive. More tessellation generally results in a higher LOD. However, tessellation beyond a certain point may provide increasingly diminishing returns in image quality. For small primitives, the point of diminishing returns may be reached more quickly. Primitives that are farther from the camera may be associated with higher depth values, but with relatively smaller bounding boxes. Therefore, heavy tessellation may not be desirable for such primitives.
[0106] Some of the sub-primitives may be Z-culled or plane culled (i.e., more distant sub-primitives may be hidden by closer overlapping sub-primitives and may therefore be removed). Culled sub-primitives may not contribute to image quality. Primitives with a large number of culled sub-primitives may be effectively over-tessellated.
[0107] The ratio of the number of pixels to the number of sub-primitives can be a good indicator that can be used to identify over-tessellation. A low value of this ratio can indicate that on average each sub-primitive holds few pixels.
[0108] In a pixel count-based VRT, developers can specify a threshold associated with the ratio of the number of visible pixels to the number of sub-pixels. For primitives with a ratio below the threshold, the number of sub-pixels can be reduced so that the ratio becomes equal to the threshold.
[0109] The LRZ stage may include a counter for pixels per tile. Accumulating this value across all tiles of a primitive may provide the total number of visible pixels for the primitive. Using the pixel count and the threshold value, the expected new sub-primitive count may be calculated as follows.
[0110] Expected new sub-pixel count N_vrt = number of visible pixels / threshold
[0111] Based on N_vrt, an iterative method can be used to calculate the TRF of the primitive (i.e., different TRF values can be tried in order to find the TRF value that produces the sub-primitive count closest to the desired new sub-primitive count N_vrt). This will be explained in further detail below. An exact TRF value may not be necessary for VRT. Therefore, in some configurations, instead of using the above equation, a less accurate but simpler method can also be used.
[0112] The TRF value for each primitive may be stored in a TRF buffer 662 at the end of the binning (visibility) pass. This TRF may be used to modify the TessFactor of primitives in the rendering pass.
[0113] Pixel count-based VRT technology can save cycles in the hardware tessellator and domain shader in the rendering path.
[0114] To explain the process for finding the TRF value that produces the sub-primitive count that is closest to the desired new sub-primitive count N_vrt, some equations, functions, and variables may be defined as follows.
[0115] TF[x] = TessFactor[x], for edge x
[0116] P[x], odd parity for edge x =
[0117]
[0118] Table 2
[0119] For edge x, ( represents the upper limit function), variables representing the edges: b-bottom edge, l-left edge, t-top edge, r-right edge, i-inner edge (Tri domain), u-horizontal inner edge (Quad domain), and v-vertical inner edge (Quad domain).
[0120] Fig.9A is a schematic diagram showing a triangle primitive 900A including triangle sub-primitives generated based on surface tessellation. Fig.9A The left edge (l), right edge (r), bottom edge (b) and inner edge (i) are indicated in FIG. The number of triangle sub-primitives in a triangle primitive can be given by the following equation [1].
[0121] Number of sub-pixels = 2T[b] + 2T[l] + 2T[r] - P[b] - P[l] - P[r] + 4P[i] + 6T[i] (T[i] - 1 - P[i]) → Equation [1]
[0122] Fig. 9Bis a schematic diagram showing a quadrilateral primitive 900B including triangular sub-primitives generated based on surface tessellation. Fig. 9B The left edge (l), right edge (r), top edge (t), bottom edge (b), horizontal inner edge (u), and vertical inner edge (v) are indicated in . Further, a parameter c may be defined, where c may be 2 if P[u] & P[v] are equal to 1, or may be 0 if P[u] & P[v] are equal to 0. The number of triangle sub-primitives in a quadrilateral primitive may be given by the following equation [2].
[0123] Number of sub-pixels = 2T[b]+2T[l]+2T[t]+2T[r]-P[b]-P[l]-P[t]-P[r]+2P[u]+2P[v]-4T[v](P[u]+1)-4T[u](P[v]+1)+8T[u]T[v]+c → Equation [2]
[0124] To solve for the TRF value for triangle primitive 900A, equation [1] may be used. All external TessFactors may be known (e.g., they may be the same as the TessFactor of the original primitive). Therefore, T[x] and P[x] may be calculated for all external edges.
[0125] The new internal TesFactor(TF[i]) can be TF_original[i]*TRF. The values of T[i] and P[i] for internal edges can be found based on iterations with different TRF values.
[0126] The sub-primitive count can be found based on equation [1]. The TRF that gives the sub-primitive count closest to N_vrt can be selected.
[0127] If N_vrt is lower than or the same as the minimum possible value, TRF may be set to 1. The minimum possible value for N_vrt may be the sub-primitive count when the internal TessFactor is set to 1 (ie, TF[i]=1).
[0128] To solve for the TRF value for quadrilateral primitive 900B, equation [2] may be used. All external TessFactors may be known (e.g., they may be the same as the TessFactor of the original primitive). Therefore, T[x] and P[x] may be calculated for all external edges.
[0129] The new internal TessFactor(TF[u]) may be TRF*TF_original[u], and TF[v] may be TRF*TF_original[v]. The values of T[u], T[v], P[u], and P[v] for the internal edges may be found based on iterations with different TRF values.
[0130] The sub-pixel count can be found based on equation [2]. The TRF that gives the sub-pixel count closest to N_vrt can be selected.
[0131] If N_vrt is lower than or the same as the minimum possible value, TRF may be set to 1. The minimum possible value for N_vrt may be the sub-primitive count when the internal TessFactor is set to 1 (ie, TF[u]=1 and TF[v]=1).
[0132] Fig.10 1 is a call flow diagram 1000 illustrating example communications between a first GPU component 1002 (e.g., a processing unit, a shading unit, a tessellator, etc.) and a second GPU component 1004 (e.g., a cache, a buffer, an internal memory, etc.) in accordance with one or more techniques of this disclosure. At 1010, the first GPU component 1002 may receive data 1012 for geometry processing of a plurality of tiles in a draw call from the second GPU component 1004. Each tile of the plurality of tiles may include a plurality of primitives. Each of the plurality of primitives in each tile of the plurality of tiles may include one or more sub-primitives.
[0133] At 1020, first GPU component 1002 may receive a VRS input 1022 associated with a shading rate for each tile in the plurality of tiles from second GPU component 1004. A tessellation factor for each tile in the plurality of tiles may be reduced based on the VRS input.
[0134] In one configuration, the VRS input may be draw-based. The TRF for each of the plurality of tiles may be the same TRF. In one configuration, the TRF for each of the plurality of tiles may be applied in a binning pass or a rendering pass.
[0135] In one configuration, the VRS input may be primitive based. A first TRF for at least one tile in the plurality of tiles may be different from a second TRF for at least one other tile in the plurality of tiles. In one configuration, the TRF for each tile in the plurality of tiles may be applied in a binning pass or a rendering pass.
[0136] In one configuration, the VRS input may be image based.At 1030 , the first GPU component 1002 may create a TRF buffer for storing a TRF for each tile of the plurality of tiles based on the VRS input 1022 .
[0137] In one configuration, a TRF for each tile in the plurality of tiles may be applied in a rendering pass. In one configuration, the plurality of primitives may include a first primitive associated with the plurality of slices. The first TRF for the first primitive may correspond to a maximum second TRF for the plurality of slices.
[0138] At 1040, first GPU component 1002 can reduce a tessellation factor for each of the plurality of tiles based on a characteristic of each of the plurality of tiles. The characteristic can correspond to a shading rate or a number of visible pixels.
[0139] At 1050 , the first GPU component 1002 can apply a TRF for each tile of the plurality of tiles.
[0140] At 1060 , the first GPU component 1002 may render each of the plurality of tiles based on the TRF applied to each of the plurality of tiles.
[0141] In one configuration, the tessellation factor of each tile in the plurality of tiles may be reduced such that a ratio of a number of valid pixels to a number of one or more sub-primitives remains constant for each tile in the plurality of tiles.
[0142] In one configuration, the TRF may be dynamically identified based on a ratio of a number of visible pixels within each tile of the plurality of tiles to a number of one or more sub-primitives.The TRF may be identified based on an iterative process.
[0143] In one configuration, one or more inner tessellation factors including the tessellation factor of each tile in the plurality of tiles may be reduced. One or more outer tessellation factors may not be reduced.
[0144] Fig.11 1100 is a flowchart of an example method of image processing according to one or more techniques of the present disclosure. The method may be performed by an apparatus, such as in conjunction with Figure 1-10 Devices for graphics processing, GPU, CPU, wireless communication equipment, etc. used in the aspects.
[0145] At 1102, the apparatus may receive data for geometry processing of a plurality of tiles in a draw call. Each tile in the plurality of tiles may include a plurality of primitives. Each primitive in the plurality of primitives in each tile in the plurality of tiles may include one or more sub-primitives. Fig.10At 1010, the first GPU component 1002 may receive data 1012 for geometry processing of a plurality of tiles in a draw call. Further, Figure 1 The processing unit 120 in can perform operation 1102.
[0146] At 1104, the apparatus may reduce a tessellation factor of each of the plurality of tiles based on a characteristic of each of the plurality of tiles. The reduced tessellation factor may correspond to a TRF. The characteristic may correspond to a shading rate or a number of visible pixels. Fig.10 At 1040, the first GPU component 1002 may reduce a tessellation factor of each of the plurality of tiles based on a characteristic of each of the plurality of tiles. Further, Figure 1 The processing unit 120 in can perform operation 1104.
[0147] At 1106, the apparatus may apply a TRF to each tile in the plurality of tiles. Fig.10 At 1050, the first GPU component 1002 may apply the TRF to each tile in the plurality of tiles. Further, Figure 1 The processing unit 120 in can perform operation 1106.
[0148] At 1108, the apparatus may render each of the plurality of tiles based on the TRF applied to each of the plurality of tiles. Fig.10 At 1060, the first GPU component 1002 may render each of the plurality of tiles based on the TRF applied to each of the plurality of tiles. Further, Figure 1 The processing unit 120 in can perform operation 1108.
[0149] Fig.12 1200 is a flowchart of an example method of image processing according to one or more techniques of the present disclosure. The method may be performed by an apparatus, such as in conjunction with Figure 1-10 Devices for graphics processing, GPU, CPU, wireless communication equipment, etc. used in the aspects.
[0150] At 1202, the apparatus may receive data for geometry processing of a plurality of tiles in a draw call. Each tile in the plurality of tiles may include a plurality of primitives. Each primitive in the plurality of primitives in each tile in the plurality of tiles may include one or more sub-primitives. Fig.10 At 1010, the first GPU component 1002 may receive data 1012 for geometry processing of a plurality of tiles in a draw call. Further, Figure 1 The processing unit 120 in may perform operation 1202. In addition, Figure 6B Block 652 in may perform operation 1202 .
[0151] In one configuration, at 1204, the apparatus may receive a VRS input associated with a shading rate for each of the plurality of tiles. A tessellation factor for each of the plurality of tiles may be reduced based on the VRS input. Fig.10 At 1020, the first GPU component 1002 may receive a VRS input 1022 associated with a shading rate for each of the plurality of tiles. Further, Figure 1 The processing unit 120 in may perform operation 1204. In addition, Figure 6B Block 652 in may perform operation 1204 .
[0152] In one configuration, the VRS input may be draw-based. The TRF for each of the plurality of tiles may be the same TRF. In one configuration, the TRF for each of the plurality of tiles may be applied in a binning pass or a rendering pass.
[0153] In one configuration, the VRS input may be primitive based. A first TRF for at least one tile in the plurality of tiles may be different from a second TRF for at least one other tile in the plurality of tiles. In one configuration, the TRF for each tile in the plurality of tiles may be applied in a binning pass or a rendering pass.
[0154] In one configuration, the VRS input may be image-based. At 1206, the apparatus may create a TRF buffer for storing a TRF for each tile of the plurality of tiles based on the VRS input. Fig.10 At 1030, the first GPU component 1002 may create a TRF buffer for storing a TRF for each tile in the plurality of tiles based on the VRS input 1022. Further, Figure 1 The processing unit 120 in may perform operation 1206. In addition, Figure 6B Block 662 in may perform operation 1206 .
[0155] In one configuration, a TRF for each tile in the plurality of tiles may be applied in a rendering pass. In one configuration, the plurality of primitives may include a first primitive associated with the plurality of slices. The first TRF for the first primitive may correspond to a maximum second TRF for the plurality of slices.
[0156] At 1208, the apparatus may reduce a tessellation factor of each of the plurality of tiles based on a characteristic of each of the plurality of tiles. The reduced tessellation factor may correspond to a TRF. The characteristic may correspond to a shading rate or a number of visible pixels. Fig.10 At 1040, the first GPU component 1002 may reduce a tessellation factor of each of the plurality of tiles based on a shading rate or a number of visible pixels of each of the plurality of tiles. Further, Figure 1 The processing unit 120 in may perform operation 1208. In addition, Fig. 6A Block 606 and / or Figure 6B Block 658 in may perform operation 1208 .
[0157] At 1210, the apparatus may apply a TRF to each tile of a plurality of tiles. Fig.10 At 1050, the first GPU component 1002 may apply the TRF to each tile in the plurality of tiles. Further, Figure 1 The processing unit 120 in may perform operation 1210. In addition, Figure 6B Block 658 in may perform operation 1210 .
[0158] At 1212, the apparatus may render each of the plurality of tiles based on the TRF applied to each of the plurality of tiles. Fig.10 At 1060, the first GPU component 1002 may render each of the plurality of tiles based on the TRF applied to each of the plurality of tiles. Further, Figure 1 The processing unit 120 in may perform operation 1212. In addition, Figure 6B Block 660 in may perform operation 1212 .
[0159] In one configuration, the tessellation factor of each tile in the plurality of tiles may be reduced such that a ratio of a number of valid pixels to a number of one or more sub-primitives remains constant for each tile in the plurality of tiles.
[0160] In one configuration, the TRF may be dynamically identified based on a ratio of a number of visible pixels within each tile of the plurality of tiles to a number of one or more sub-primitives.The TRF may be identified based on an iterative process.
[0161] In one configuration, one or more inner tessellation factors including the tessellation factor of each tile in the plurality of tiles may be reduced. One or more outer tessellation factors may not be reduced.
[0162] In various configurations, a method or apparatus for graphics processing is provided. The apparatus may be a GPU, a CPU, or some other processor that can perform graphics processing. In various aspects, the apparatus may be a processing unit 120 within a device 104, or may be some other hardware within a device 104 or another device. The apparatus may include a unit for receiving data for geometric processing of a plurality of tiles in a draw call. Each of the plurality of tiles may include a plurality of primitives. Each of the plurality of primitives in each of the plurality of tiles may include one or more sub-primitives. The apparatus may also include a unit for reducing a tessellation factor of each of the plurality of tiles based on a characteristic of each of the plurality of tiles. The reduced tessellation factor may correspond to a TRF. The characteristic may correspond to a shading rate or a number of visible pixels. The apparatus may also include a unit for applying a TRF to each of the plurality of tiles. The apparatus may also include a unit for rendering each of the plurality of tiles based on the TRF applied to each of the plurality of tiles.
[0163] In one configuration, the tessellation factor of each tile in the plurality of tiles may be reduced such that a ratio of a number of valid pixels to a number of one or more sub-primitives remains constant for each tile in the plurality of tiles.
[0164] In one configuration, the TRF may be dynamically identified based on a ratio of a number of visible pixels within each tile of the plurality of tiles to a number of one or more sub-primitives.The TRF may be identified based on an iterative process.
[0165] In one configuration, the apparatus may further include means for receiving a VRS input associated with a shading rate for each of the plurality of tiles. A tessellation factor for each of the plurality of tiles may be reduced based on the VRS input.
[0166] In one configuration, the VRS input may be rendering based.The TRF for each of the plurality of tiles may be the same TRF.
[0167] In one configuration, the TRF for each tile of the plurality of tiles may be applied in a binning pass or a rendering pass.
[0168] In one configuration, the VRS input may be primitive based.A first TRF for at least one tile of the plurality of tiles may be different from a second TRF for at least one other tile of the plurality of tiles.
[0169] In one configuration, the TRF for each tile of the plurality of tiles may be applied in a binning pass or a rendering pass.
[0170] In one configuration, the VRS input may be image based.The apparatus may also include means for creating a TRF buffer for storing a TRF for each tile of the plurality of tiles based on the VRS input.
[0171] In one configuration, a TRF for each tile of a plurality of tiles may be applied in a rendering pass.
[0172] In one configuration, the plurality of primitives may include a first primitive associated with the plurality of tiles.The first TRF for the first primitive may correspond to a maximum second TRF for the plurality of tiles.
[0173] In one configuration, one or more inner tessellation factors including the tessellation factor of each tile in the plurality of tiles may be reduced. One or more outer tessellation factors may not be reduced.
[0174] Return to reference Figure 6A-12 In the tessellation stage, when LOD is reduced based on shading rate and / or pixel count, TessFactor can be reduced. Even if TessFactor is significantly reduced, there may not be a noticeable reduction in image quality. At the same time, GPU rendering performance can be improved.
[0175] It should be understood that the specific order or hierarchy of the boxes / steps in the process, flow chart and / or call flow chart disclosed herein is an illustration of the exemplary method. It should be understood that the specific order or hierarchy of the boxes / steps in the process, flow chart and / or call flow chart can be rearranged based on design preferences. In addition, some boxes / steps can be combined and / or omitted. Other boxes / steps can also be added. The attached method claims provide the elements of each box / step in an exemplary order, and are not intended to be limited to the specific order or hierarchy provided.
[0176] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the various aspects shown herein, but are given the full scope consistent with the language of the claims, wherein, unless expressly stated to be so, reference to an element in the singular form is not intended to mean "one and only one", but "one or more". The word "exemplary" is used herein to mean "used as an example, instance, or illustration". Any aspect described herein as "exemplary" is not necessarily to be construed as being preferred over or having advantages over other aspects.
[0177] Unless explicitly stated otherwise, the term "some" refers to one or more, and the term "or" may be interpreted as "and / or" if the context does not dictate otherwise. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A, B, and C, wherein any such combination may include one or more members or several members of A, B, or C. All structural and functional equivalents of the elements of the various aspects described throughout the present disclosure, which are known or will be known later to those of ordinary skill in the art, are expressly incorporated herein by reference, and are intended to be included by the claims. In addition, there is no disclosure herein that is intended to be dedicated to the public, regardless of whether such disclosure is clearly recorded in the claims. The words "module", "mechanism", "element", "equipment" and the like may not be substitutes for the word "unit". Therefore, no claim element is to be interpreted as a functional unit module, unless the element is clearly recorded using the phrase "unit for ..."
[0178] In one or more examples, the functions described herein can be implemented in hardware, software, firmware, or any combination thereof. For example, although the term "processing unit" has been used throughout this disclosure, such a processing unit can be implemented in hardware, software, firmware, or any combination thereof. If any function, processing unit, technique described herein, or other module is implemented in software, any function, processing unit, technique described herein, or other module can be stored as one or more instructions or codes on a computer-readable medium or sent through it.
[0179] Computer-readable media may include computer data storage media or communication media, including any media that facilitates the transfer of a computer program from one place to another. In this manner, computer-readable media may generally correspond to: (1) a non-transitory tangible computer-readable storage medium; or (2) a communication medium such as a signal or carrier wave. Data storage media may be any available medium that can be accessed by one or more computers or one or more processors to obtain instructions, codes, and / or data structures for implementing the techniques described in the present disclosure. By way of example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, or other magnetic storage devices. As used herein, magnetic disks and optical disks include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, wherein magnetic disks typically reproduce data magnetically, while optical discs typically reproduce data optically using lasers. Combinations of the foregoing should also be included within the scope of computer-readable media. A computer program product may include computer-readable media.
[0180] The technology of the present disclosure can be implemented in a variety of devices or apparatuses, including wireless phones, integrated circuits (ICs), or a group of ICs (e.g., chipsets). Various components, modules, or units are described in the present disclosure to emphasize the functional aspects of the devices configured to perform the disclosed technology, but it is not necessarily necessary to implement them through different hardware units. Instead, as described above, the various units can be combined in any hardware unit, or provided by a collection of interoperable hardware units (including one or more processors as described above) in combination with suitable software and / or firmware. Accordingly, as used herein, the term "processor" may refer to any of the aforementioned structures or any other structure suitable for implementing the technology described herein. In addition, the technology can be fully implemented in one or more circuits or logic elements.
[0181] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein, but are not limited thereto.
[0182] Aspect 1 is a device for graphics processing, comprising: at least one processor coupled to a memory and configured to: receive data for geometry processing of multiple tiles in a drawing call, each of the multiple tiles including multiple primitives, each of the multiple primitives in each of the multiple tiles including one or more sub-primitives; reduce the tessellation factor of each of the multiple tiles based on characteristics of each of the multiple tiles, the reduced tessellation factor corresponding to a TRF, the characteristics corresponding to a shading rate or a number of visible pixels; apply the TRF for each of the multiple tiles; and render each of the multiple tiles based on the TRF applied to each of the multiple tiles.
[0183] Aspect 2 is an apparatus according to aspect 1, wherein the tessellation factor of each of the multiple tiles is reduced so that the ratio of the number of effective pixels to the number of the one or more sub-primitives for each of the multiple tiles remains constant.
[0184] Aspect 3 is an apparatus according to Aspect 1, wherein the TRF is dynamically identified based on a ratio of the number of visible pixels within each of the multiple tiles to the number of the one or more sub-primitives, and the TRF is identified based on an iterative process.
[0185] Aspect 4 is a device according to any one of Aspects 1 and 2, wherein the at least one processor is further configured to: receive a VRS input associated with the shading rate of each of the multiple tiles, wherein the tessellation factor of each of the multiple tiles is reduced based on the VRS input.
[0186] Aspect 5 is the apparatus of aspect 4, wherein the VRS input is rendering based and the TRF for each tile of the plurality of tiles is the same TRF.
[0187] Clause 6 is the apparatus of clause 5, wherein the TRF for each tile of the plurality of tiles is applied in a binning pass or a rendering pass.
[0188] Aspect 7 is an apparatus according to aspect 4, wherein the VRS input is primitive-based and a first TRF for at least one tile of the plurality of tiles is different from a second TRF for at least one other tile of the plurality of tiles.
[0189] Clause 8 is the apparatus of clause 7, wherein the TRF for each tile of the plurality of tiles is applied in a binning pass or a rendering pass.
[0190] Aspect 9 is an apparatus according to aspect 4, wherein the VRS input is image-based, and the at least one processor is further configured to: create a TRF buffer for storing the TRF for each tile of the plurality of tiles based on the VRS input.
[0191] Clause 10 is the apparatus of clause 9, wherein the TRF for each tile of the plurality of tiles is applied in a rendering pass.
[0192] Aspect 11 is an apparatus according to any one of aspects 9 and 10, wherein the plurality of primitives includes a first primitive associated with a plurality of patches, and the first TRF for the first primitive corresponds to a maximum second TRF for the plurality of patches.
[0193] Aspect 12 is an apparatus according to any one of aspects 1-11, wherein one or more inner tessellation factors of the tessellation factors of each tile in the plurality of tiles are reduced and one or more outer tessellation factors are not reduced.
[0194] Aspect 13 is an apparatus according to any one of aspects 1-12, wherein the apparatus is a wireless communication device.
[0195] Aspect 14 is a method for implementing wireless communication according to any one of aspects 1-13.
[0196] Aspect 15 is an apparatus for graphics processing, comprising a unit for implementing the method as described in any one of Aspects 1-13.
[0197] Aspect 16 is a computer-readable medium storing computer-executable code, which, when executed by at least one processor, causes the at least one processor to implement the method as described in any one of aspects 1-13.
[0198] Various aspects have been described herein. These examples and other aspects are within the scope of the following claims.
Claims
1. A device for graphics processing, comprising: Memory; as well as at least one processor coupled to the memory and configured to: receiving data for geometry processing of a plurality of tiles in a draw call, each tile of the plurality of tiles comprising a plurality of primitives, each primitive of the plurality of primitives in each tile of the plurality of tiles comprising one or more sub-primitives; reducing a tessellation factor for each of the plurality of tiles based on a characteristic of each of the plurality of tiles, the reduced tessellation factor corresponding to a tessellation reduction factor (TRF), the characteristic corresponding to a shading rate or a number of visible pixels; applying the TRF to each tile of the plurality of tiles; as well as Each of the plurality of tiles is rendered based on the TRF applied to each of the plurality of tiles.
2. The device according to claim 1, wherein The tessellation factor of each tile of the plurality of tiles is reduced such that a ratio of a number of valid pixels to a number of the one or more sub-primitives remains constant for each tile of the plurality of tiles.
3. The device according to claim 1, wherein The TRF is dynamically identified based on a ratio of the number of visible pixels to the number of the one or more sub-primitives within each tile of the plurality of tiles, and the TRF is identified based on an iterative process.
4. The apparatus of claim 1 , wherein the at least one processor is further configured to: receiving a variable rate shading (VRS) input associated with the shading rate for each tile in the plurality of tiles, wherein The tessellation factor of each tile in the plurality of tiles is reduced based on the VRS input.
5. The device according to claim 4, wherein The VRS input is rendering-based, and the TRF for each tile of the plurality of tiles is the same TRF.
6. The device according to claim 5, wherein The TRF for each tile of the plurality of tiles is applied in a binning pass or a rendering pass.
7. The device according to claim 4, wherein The VRS input is primitive-based, and a first TRF for at least one tile of the plurality of tiles is different from a second TRF for at least one other tile of the plurality of tiles.
8. The device according to claim 7, wherein The TRF for each tile of the plurality of tiles is applied in a binning pass or a rendering pass.
9. The device according to claim 4, wherein The VRS input is image-based, and the at least one processor is further configured to: A TRF buffer for storing the TRF for each tile of the plurality of tiles is created based on the VRS input.
10. The device according to claim 9, wherein The TRF for each tile of the plurality of tiles is applied in a rendering pass.
11. The device according to claim 9, wherein The plurality of primitives includes a first primitive associated with a plurality of tiles, and a first TRF for the first primitive corresponds to a maximum second TRF for the plurality of tiles.
12. The device according to claim 1, wherein One or more inner tessellation factors of the tessellation factor comprising each tile of the plurality of tiles are reduced, and one or more outer tessellation factors are not reduced.
13. The device according to claim 1, wherein The apparatus is a wireless communication device.
14. A method for graphics processing, comprising: receiving data for geometry processing of a plurality of tiles in a draw call, each tile of the plurality of tiles comprising a plurality of primitives, each primitive of the plurality of primitives in each tile of the plurality of tiles comprising one or more sub-primitives; reducing a tessellation factor for each of the plurality of tiles based on a characteristic of each of the plurality of tiles, the reduced tessellation factor corresponding to a tessellation reduction factor (TRF), the characteristic corresponding to a shading rate or a number of visible pixels; applying the TRF to each tile of the plurality of tiles; as well as Each of the plurality of tiles is rendered based on the TRF applied to each of the plurality of tiles.
15. The method according to claim 14, wherein The tessellation factor of each tile of the plurality of tiles is reduced such that a ratio of a number of valid pixels to a number of the one or more sub-primitives remains constant for each tile of the plurality of tiles.
16. The method according to claim 14, wherein The TRF is dynamically identified based on a ratio of the number of visible pixels to the number of the one or more sub-primitives within each tile of the plurality of tiles, and the TRF is identified based on an iterative process.
17. The method according to claim 14, further comprising: A variable ratio shading (VRS) input associated with the shading rate of each tile in the plurality of tiles is received, wherein the tessellation factor of each tile in the plurality of tiles is reduced based on the VRS input.
18. The method according to claim 17, wherein The VRS input is rendering-based, and the TRF for each tile of the plurality of tiles is the same TRF.
19. The method according to claim 18, wherein The TRF for each tile of the plurality of tiles is applied in a binning pass or a rendering pass.
20. The method according to claim 17, wherein The VRS input is primitive-based, and a first TRF for at least one tile of the plurality of tiles is different from a second TRF for at least one other tile of the plurality of tiles.
21. The method according to claim 20, wherein The TRF for each tile of the plurality of tiles is applied in a binning pass or a rendering pass.
22. The method according to claim 17, wherein The VRS input is image-based, and the method further comprises: A TRF buffer for storing the TRF for each tile of the plurality of tiles is created based on the VRS input.
23. The method according to claim 22, wherein The TRF for each tile of the plurality of tiles is applied in a rendering pass.
24. The method according to claim 22, wherein The plurality of primitives includes a first primitive associated with a plurality of tiles, and a first TRF for the first primitive corresponds to a maximum second TRF for the plurality of tiles.
25. The method according to claim 14, wherein One or more inner tessellation factors of the tessellation factor comprising each tile of the plurality of tiles are reduced, and one or more outer tessellation factors are not reduced.
26. A non-transitory computer-readable medium storing computer-executable code, which, when executed by at least one processor, causes the at least one processor to: receiving data for geometry processing of a plurality of tiles in a draw call, each tile of the plurality of tiles comprising a plurality of primitives, each primitive of the plurality of primitives in each tile of the plurality of tiles comprising one or more sub-primitives; reducing a tessellation factor for each of the plurality of tiles based on a characteristic of each of the plurality of tiles, the reduced tessellation factor corresponding to a tessellation reduction factor (TRF), the characteristic corresponding to a shading rate or a number of visible pixels; applying the TRF to each tile of the plurality of tiles; as well as Each of the plurality of tiles is rendered based on the TRF applied to each of the plurality of tiles.
27. The non-transitory computer readable medium of claim 26, wherein: The tessellation factor of each tile of the plurality of tiles is reduced such that a ratio of a number of valid pixels to a number of the one or more sub-primitives remains constant for each tile of the plurality of tiles.
28. The non-transitory computer readable medium of claim 26, wherein: The TRF is dynamically identified based on a ratio of the number of visible pixels to the number of the one or more sub-primitives within each tile of the plurality of tiles, and the TRF is identified based on an iterative process.
29. The non-transitory computer-readable medium of claim 26, wherein the code further causes the at least one processor to: receiving a variable rate shading (VRS) input associated with the shading rate for each tile in the plurality of tiles, wherein The tessellation factor of each tile in the plurality of tiles is reduced based on the VRS input.
30. The non-transitory computer readable medium of claim 29, wherein: The VRS input is rendering-based, and the TRF for each tile of the plurality of tiles is the same TRF.
Citation Information
Patent Citations
Variable rate shading
CN110383337A
Graphics processing units and methods for controlling rendering complexity using cost indications for sets of tiles of a rendering space
EP3349181A1
Adaptive sub-patches system, apparatus and method
EP3396636A1
Methods and apparatus for reducing memory bandwidth in multi-pass tessellation
US11037358B1
Tessellation in tile-based rendering
US20130120380A1
