64 results about "Geometry shader" patented technology

A graphics processor architecture provides for scan conversion and ray tracing approaches to visible surface determination as concurrent and separate processes. Surfaces can be identified for shading by scan conversion and ray tracing. Data produced by each can be normalized, so that instances of shaders, being executed on a unified shading computation resource, can shade surfaces originating from both ray tracing and rasterization. Such resource also may execute geometry shaders. The shaders can emit rays to be tested for intersection by the ray tracing process. Such shaders can complete, without waiting for those emitted rays to complete. Where scan conversion operates on tiles of 2-D screen pixels, the ray tracing can be tile aware, and controlled to prioritize testing of rays based on scan conversion status. Ray population can be controlled by feedback to any of scan conversion, and shading.

A graphics processor performs culling of invisible primitives in a vertex processing unit that includes a geometry shader or other processing engine that performs per-primitive operations. Primitives can be culled after clip space coordinates for the vertices have been computed and in some instances before at least one other vertex attribute has been computed. To the extent that this early culling reduces the number of vertices for which the full set of attributes is computed or reduces the number of primitives or vertices delivered to downstream units, throughput of the processor is increased.

Systems and methods for sharing a physical cache among one or more clients in a stream data processing pipeline are described. One embodiment, among others, is directed to a system for sharing caches between two or more clients. The system comprises a physical cache memory having a memory portion accessed through a cache index. The system further comprises at least two virtual cache spaces mapping to the memory portion and at least one virtual cache controller configured to perform a hit-miss test on the active window of the virtual cache space in response to a request from one of the clients for accessing the physical cache memory. In accordance with some embodiments, each of the virtual cache spaces has an active window which has a different size than the memory portion. Furthermore, data is accessed from the corresponding location of the memory portion when the hit-miss test of the cache index returns a hit.

One embodiment of the present invention sets forth a technique for redistributing geometric primitives generated by tessellation and geometry shaders for per-vertex by multiple graphics pipelines. Geometric primitives that are generated in a first processing stage are collected and redistributed more evenly and in smaller batches to the multiple graphics pipelines for vertex processing in a second processing stage. The smaller batches do not exceed the resource limits of a graphics pipeline and the per-vertex processing workloads of the graphics pipelines in the second stage are balanced. Therefore, the performance of the tessellation and geometry shaders is improved.

The invention discloses an image processing method for scene drawing. The method comprises the following steps of: constructing complex scene data, drawing a shadow map of the scene, and drawing the scene in a viewpoint vision cone. According to the method, a tiny object is represented by a semitransparent line segment, and the drawing effect retains rich detailed information; according to the manner of drawing for multiple times, the problem of data in small batch is avoided, and the drawing efficiency is improved; via model combination, single-stage level of detail (LOD) model output of a geometrical shader and model position point sequencing, columnar geometries with different thicknesses can be represented by line segment models with different transparency, thereby ensuring the accuracy of Alpha mixing, realizing semitransparent drawing, and keeping more details.

A graphics processor architecture provides for scan conversion and ray tracing approaches to visible surface determination as concurrent and separate processes. Surfaces can be identified for shading by scan conversion and ray tracing. Data produced by each can be normalized, so that instances of shaders, being executed on a unified shading computation resource, can shade surfaces originating from both ray tracing and rasterization. Such resource also may execute geometry shaders. The shaders can emit rays to be tested for intersection by the ray tracing process. Such shaders can complete, without waiting for those emitted rays to complete. Where scan conversion operates on tiles of 2-D screen pixels, the ray tracing can be tile aware, and controlled to prioritize testing of rays based on scan conversion status. Ray population can be controlled by feedback to any of scan conversion, and shading.

Methods and systems for processing a geometry shader program developed in a high-level shading language are disclosed. Specifically, in one embodiment, after having received the geometry shader program configured to be executed by a first processing unit in a programmable execution environment, the high-level shading language instructions of the geometry shader program is converted into low-level programming language instructions. The low-level programming language instructions are then linked with the low-level programming language instructions of a domain-specific shader program, which is configured to be executed by a second processing unit also residing in the programmable execution environment. The linked instructions of the geometry shader program are directed to the first processing unit, and the linked instructions of the domain-specific shader program are directed to the second processing unit.

The symmetrical properties of a group of vertices are leveraged to reconstruct the group using vertex data for a subset of the vertices and a set of control data. The subset of vertices is symmetrical to one or more other subsets of vertices in the group, and the control data includes information to reconstruct the one or more other subsets using the vertex data for the first set of vertices and symmetrical characteristics of the group. In some embodiments, reconstruction is performed using a geometry shader in a graphics processor to compute the additional vertices.

A geometry shader of a graphics processor is configured to generate at least a portion of a particle system. The geometry shader receives vertex data including a reference set of vertices. The geometry shader also receives control data including information on how to create additional vertices for the particle system using the vertex data. The geometry shader processes the vertex data and control data to generate the additional vertices for the particle system. In some embodiments, the control data also includes information on other attributes of the generated vertices.

A geometry shader of a graphics processor decompresses a set of vertex data representing a simplified model to create a more detailed representation. The geometry shader receives vertex data including a number of vertices representative of a simplified model. The geometry shader decompresses the vertex data by computing additional vertices to create the more detailed representation. In some embodiments, the geometry shader also receives rules data including information on how the vertex data is to be decompressed.

The present disclosure is directed to novel methods and apparatus for managing or performing the dynamic allocation or reallocation of processing resources among a vertex shader, a geometry shader, and pixel shader of a graphics processing unit. In one embodiment a method for graphics processing comprises assigning at least one execution unit to each of a plurality of shader units, the plurality of shader units comprising a vertex shader, a geometry shader, and a pixel shader, wherein an execution unit assigned to a given shader unit performs processing tasks for only that shader unit, determining that one of the plurality of shader units is bottlenecked, and reassigning at least one execution unit from a non-bottlenecked shader unit to the shader unit determined to be bottlenecked.

An exemplary embodiment of the present invention includes a method of registering images. The method includes: for each image, determining an optimum intensity threshold set from a plurality of intensity threshold sets that maximizes a variance between classes of each set, segmenting each image using the corresponding determined optimum intensity threshold set, generating mutual information from a joint histogram of at least two of the segmented images, and registering the at least two images using the mutual information. The joint histogram may be generated using a geometry shader of a graphical processing unit.

One embodiment of the present invention sets forth a technique for more effectively utilizing graphics hardware by allowing the developer to exploit parallelism at the primitive-level. In this technique, an algorithm is analyzed to break the total work associated with processing one primitive into discrete portions of work. The results of this analysis are used to program a geometry shader group that includes multiple geometry shaders. Upon receiving a single input primitive, the geometry shader group launches multiple parallel threads, one thread in each geometry shader in the group corresponding to each discrete portion of work. As each thread completes, the output of the thread is stored in on-chip GPU memory for processing by the next stage in the graphics pipeline. Since the overall work associated with a given input primitive is distributed across multiple threads, the output of each thread is smaller and, thus, the total memory required to implement the algorithm is reduced.

Methods and systems for processing a geometry shader program developed in a high-level shading language are disclosed. Specifically, in one embodiment, after having received the geometry shader program configured to be executed by a first processing unit in a programmable execution environment, the high-level shading language instructions of the geometry shader program is converted into low-level programming language instructions. The low-level programming language instructions are then linked with the low-level programming language instructions of a domain-specific shader program, which is configured to be executed by a second processing unit also residing in the programmable execution environment. The linked instructions of the geometry shader program are directed to the first processing unit, and the linked instructions of the domain-specific shader program are directed to the second processing unit.

The present invention extends to methods, systems, and computer program products for providing domain, hull, and geometry shaders in a para-virtualized environment. As such, a guest application executing in a child partition is enabled use a programmable GPU pipeline of a physical GPU. A vGPU (executing in the child partition) is presented to the guest application. The vGPU exposes DDIs of a rendering framework. The DDIs enable the guest application to send graphics commands to the vGPU, including commands for utilizing a domain shader, a hull shader, and / or a geometric shader at a physical GPU. A render component (executing within the root partition) receives physical GPU-specific commands from the vGPU, including commands for using the domain shader, the hull shader, and / or the geometric shader. The render component schedules the physical GPU-specific command(s) for execution at the physical GPU.

One embodiment of the present invention sets forth a technique for redistributing geometric primitives generated by tessellation and geometry shaders for processing by multiple graphics pipelines. Geometric primitives that are generated in a first processing cycle are collected and redistributed more evenly and in smaller tasks to the multiple graphics pipelines for vertex processing in a second processing cycle. The smaller tasks do not exceed the resource limits of a graphics pipeline and the per-vertex processing workloads of the graphics pipelines in the second cycle are balanced and make full use of resources. Therefore, the performance of the tessellation and geometry shaders is improved.

Attributes of graphics objects are processed in a plurality of graphics processing pipelines. A streaming multiprocessor (SM) retrieves a first set of parameters associated with a set of graphics objects from a first set of buffers. The SM performs a first set of operations on the first set of parameters according to a first phase of processing to produce a second set of parameters stored in a second set of buffers. The SM performs a second set of operations on the second set of parameters according to a second phase of processing to produce a third set of parameters stored in a third set of buffers. One advantage of the disclosed techniques is that work is redistributed from a first phase to a second phase of graphics processing without having to copy the attributes to and retrieve the attributes from the cache or system memory, resulting in reduced power consumption.

A computer graphics system is described in which a new type of entity, referred to as a “phenomenon,” can be created, instantiated and used in rendering an image of a scene. A phenomenon is an encapsulated shader DAG comprising one or more nodes each comprising a shader, or an encapsulated set of such DAGs which are interconnected so as to cooperate, which are instantiated and attached to entities in the scene which are created during the scene definition process to define diverse types of features of a scene, including color and textural features of surfaces of objects in the scene, characteristics of volumes and geometries in the scene, features of light sources illuminating the scene, features of simulated cameras will be simulated during rendering, and numerous other features which are useful in rendering. Phenomena selected for use by an operator in connection with a scene may be predefined, or they may be constructed from base shader nodes by an operator using a phenomenon creator. The phenomenon creator ensures that phenomena are constructed so that the shaders in the DAG or cooperating DAGs can correctly cooperate during rendering of an image of the scene. Prior to being attached to a scene, a phenomenon is instantiated by providing values, or functions which are used to define the values, for each of the phenomenon's parameters, using a phenomenon editor. The phenomenon editor allows the operator to view the effects produced by various settings for the parameter values which are selected. During scene image generation, a scene image generator operates in a series of phases, including a including a preprocessing phase, a rendering phase and a post-processing phase. During a pre-processing phase, the scene image generator can perform pre-processing operations, such as shadow and photon mapping, multiple inheritance resolution, and the like. The scene image generator may perform pre-processing operations if, for example, a phenomenon attached to the scene includes a geometry shader to generate geometry defined thereby for the scene. During the rendering phase, the scene image generator renders the image. During the post-processing phase, the scene image generator may perform post-processing operations if, for example, a phenomenon attached to the scene includes a shader that defines post-processing operations.

The invention discloses a shader classification method and device based on surface signal fitting and tessellation and a graphics rendering method. A subdivision shader and a geometry shader are inserted into an original shader by utilizing a tessellation method to subdivide a rendering model, a fitting machine is used for calculating the values of a variable and an expression, in a corresponding subdivision pel of the subdivision model, in an original pixel shader, and the formed fitting machine is inserted into the original pixel shader to replace value calculation to the corresponding variable or expression so as to simplify the calculation of the original pixel shader and shorten calculation time. Furthermore, since the subdivision shader and the geometry shader are inserted, fitting calculation can be carried out on the subdivision pel so as to improve fitting precision and reduce rendering errors brought by simplifying the shader.

A system, method, and computer program product are provided for tessellation using shaders. New graphics pipeline stages implemented by shaders are introduced, including an inner ring shader, an outer edge shader, and topologic shader, which work together with a domain shader and geometry shader to provide tessellated points and primitives. A hull shader is modified to compute values used by the new shaders to perform tessellation algorithms. This approach provides parallelism and customizability to the presently static tessellation engine implementation.

Systems and methods for sharing a physical cache among one or more clients in a stream data processing pipeline are described. One embodiment is directed to a system for sharing caches between two or more clients. The system comprises a physical cache memory having a memory portion accessed through a cache index. The system further comprises at least two virtual cache spaces mapping to the memory portion, each of the virtual cache spaces has an active window which has a different size than the memory portion. Further, the system comprises at least one virtual cache controller configured to perform a hit-miss test on the active window of the virtual cache space in response to a request from one of the clients for accessing the physical cache memory. Furthermore, data is accessed from the corresponding location of the memory portion when the hit-miss test of the cache index returns a hit.

The invention relates to a rapid spherical coordinate laser radar simulation method, and discloses a rapid simulation method for a laser radar. A CPU and a GPU perform collaborative operation; the CPUperforms partial initialization operation; the GPU performs coordinate conversion on vertex coordinates of triangular surfaces in a vertex shader; in a geometric shader, each triangular surface is changed into a rectangle composed of two triangles, and the coordinates of three vertexes ABC of the original triangular surface are mounted and output; and in a fragment shader, ray detection is performed on the triangular surface, collision point coordinates are calculated, and an output of the laser radar is calculated and mapped to a space (R, G, B, A). According to the method, traditional render pipelines are used, most types of display cards are compatible, and the acceleration performance of the modern display card can be obtained; and meanwhile, the problem of equidistant sampling in laser radar simulation is solved, and the high-speed and high-precision equiangular sampling is realized.

The invention discloses a method of a graphic processing device, a unit and execution triangular configuration and property configuration. Each embodiment thereof comprises at least one execution unit which can be used for the multithreading operation and also can execute at least one thread of the triangular configuration operation and the property configuration operation, and the thread used for the operation of a pixel shader, a geometry shader and a vertex shader. The inventive method of the graphic processing device, the unit and execution triangular configuration, and the property configuration, can reduce the number of the gates in the system via removing at least parts of the hardware components and cause the more effective graphics pipelines with flexibility and expansibility to the modification of the bugs, the accession of the new characters or the adjustment of the algorithm.

The invention belongs to the field of scientific visualization, and particularly relates to a dynamic two-dimensional vector field streamline visualization algorithm based on a GPU (Graphics Processing Unit). The algorithm comprises the following steps: carrying out random distribution on particles in a vector field so that the particles move along with the vector field, and utilizing a geometry shader mechanism of the GPU to generate streamlines; generating the probability density graph of the vector field by calculating a radial basis function taking the particles as the center so as to control the generation, extinction and multiresolution distribution of the particles. According to the algorithm, the complete picture of the vector field is displayed in a streamline mode, so that the density, length, motion speed and smooth degree of the streamlines can be changed in real time; the streamlines are continuous and independent from one another, so that complicated characteristics of the vector field can be well dynamically displayed, and the cognitive purpose of visualization is achieved. Moreover, the algorithm is realized based on the GPU, and the generation and control efficiency of the streamlines is higher.

The invention provides a GPU (graphic processing unit) acceleration real-time three-dimensional rendering method comprising the following steps of: respectively building a left model of a rendering scene and a right model of the rendering scene; calculating a left model view matrix of the rendering scene, a right model view matrix of the rendering scene and a projection matrix; executing vertex processing operation of the rendering scene; receiving elements transmitted by a vertex shader in a geometrical shader; rendering multiple rendering targets by utilizing a renderer; storing rendering result of each rendering target into two independent caches; and correspondingly displaying stereopair by adopting a three-dimensional recovery method according to the rendering result of each rendering target which is stored in two independent caches respectively. By applying the method provided by the invention, real-time three-dimensional rendering can be realized on a complex rendering scene, and rendering time required for carrying out three-dimensional rendering on a complex scene can be greatly shortened.

An exemplary embodiment of the present invention includes a method of registering images. The method includes: for each image, determining an optimum intensity threshold set from a plurality of intensity threshold sets that maximizes a variance between classes of each set, segmenting each image using the corresponding determined optimum intensity threshold set, generating mutual information from a joint histogram of at least two of the segmented images, and registering the at least two images using the mutual information. The joint histogram may be generated using a geometry shader of a graphical processing unit.

The invention discloses a method for constructing a streamline animation under the wind field driving of a particle system based on a GS (Geometry Shader). A great quantity of particle belts forms the streamline animation of the wind field; each particle belt takes m control vertexes as a basis and consists of a corresponding triangular facet; one particle belt is one moving streamline in the streamline animation of the wind field; firstly, a control point processing module is established for controlling the initial position, the life cycle and the intensity element of the control point of the particle belt of each wind field streamline; a GS module is established for dynamically generating more vertexes in a display card on the basis of the control point in the GS processing stage of the programmable pipeline of the display card so as to construct the triangular facet required by each particle. By use of the method, the rendering pipeline of a traditional fixed pipeline is abandoned, the programmable pipeline of the display card on the basis of Direct3D 11 is used, the vast majority of calculation is finished in the stream processor array of the display card, and the calculation burden of a CPU (Central Processing Unit) is fundamentally solved.

The disclosure describes techniques for executing shader programs in a graphics processing unit (GPU). In some examples, the techniques for executing shader programs may include executing, with a shader unit of a graphics processor, a shader program that performs vertex shader processing and that generates multiple output vertices for each input vertex that is received by the shader program. In further examples, the techniques for executing shader programs may include executing a merged vertex / geometry shader program using a non-replicated mode of execution. The non-replicated mode of execution may involve assigning each of a plurality of primitives to one merged vertex / geometry shader program instance per primitive and causing each of the instances to output a plurality of vertices. In additional examples, the techniques for executing shader programs may include techniques for selecting one of a non-replicated mode and a replicated mode for executing a merged vertex / geometry shader program.

A system and method are provided for rendering a hogel in a single rendering pass. Data representative of a geometric shape having multiple vertices are processed to determine if the geometric shape has at least one vertex on a first side and at least one vertex on a second side of a hologram plane. When the geometric shape has at least one vertex on the first side of a hologram plane and at least one vertex on the second side of the hologram plane, the geometric shape is simultaneously duplicated, in a geometry shader, on the first side of the hologram plane and on the second side of the hologram plane.

The invention belongs to the field of digital image processing technology and discloses a straight line detection method based on an IMX6 graphics processing unit. The method uses OpenGL's off-screen rendering technology to render an image in a frame buffer object and read data in the frame buffer object through a CPU, thus overcoming the shortcomings that some of the GPUs do not support a geometry shader and cannot dynamically increase the vertices and improving the versatility of an algorithm; and the OpenGL image mixing technology is used for transforming the problem of finding an intersection of a straight line into the problem of finding the maximum value of the pixel value of a grayscale image, and a straight line equation to be detected can be calculated by the obtained maximum value coordinate. The method of the invention is less restricted by hardware, thereby improving the versatility of the algorithm; and has the characteristics of saving development cost and having low calculating complexity and high running speed.