Abstract: Systems and methods are provided to perform multiply-accumulate operations of reduced precision numbers in a systolic array. Each row of the systolic array can receive reduced inputs from a respective reducer. The reduced input can include a reduced input data element and/or a reduced weight. The systolic array may lack support for inputs with a first bit-length and the reducers may reduce the bit-length of a given input from the first bit-length to a second shorter bit-length and provide the reduced input to the array. In order to reduce the bit-length, the reducer may reduce the number of trailing bits of the input. Further, the systolic array can receive a reduced and rounded input. The systolic array can propagate the reduced input through the processing elements in the systolic array. Each processing element may include a multiplier and/or an adder to perform arithmetical operations based on the reduced input.

Abstract: A system that displays a set of polygons is described. This system obtains a set of line segments that defines the set of polygons. The system forms a horizontal index that keeps track of where line segments vertically project onto a horizontal reference line and similarly forms a vertical index for horizontal projections onto a vertical reference line. The system obtains a clip rectangle that defines a view into the set of polygons and uses the horizontal and vertical indexes to determine intersections between borders of the clip rectangle and line segments in the set of line segments. Next, the system uses the determined intersections to clip polygons in the set of polygons that intersect the clip rectangle. Finally, the system transfers the clipped polygons, and also unclipped polygons that fit completely within the clip rectangle, to a display device that displays the view into the set of polygons.

Abstract: The present invention relates to a method of determining the coherence between a physical object and a numerical model representative of the shape of a physical object, wherein a specific use of the method according to the invention is assessing and quantifying manufacturing defects. The method is characterized by a set of steps comprising: capturing multiple images of the physical object; processing the images to produce a second numerical model of the physical object; in a computer, aligning the first numerical model and the second numerical model to generate a third numerical model according to specific sub-steps, wherein the third numerical model comprises a plurality of points representative of the shape of the captured physical object. Compared with the first numerical model, the third numerical model allows determining a measurement of the coherence between the physical object captured by means of images and the first numerical model representative thereof.

Abstract: Low precision computers can be efficient at finding possible answers to search problems. However, sometimes the task demands finding better answers than a single low precision search. A computer system augments low precision computing with a small amount of high precision computing, to improve search quality with little additional computing.

Abstract: A system that displays a set of polygons is described. This system obtains a set of line segments that defines the set of polygons. The system forms a horizontal index that keeps track of where line segments vertically project onto a horizontal reference line and similarly forms a vertical index for horizontal projections onto a vertical reference line. The system obtains a clip rectangle that defines a view into the set of polygons and uses the horizontal and vertical indexes to determine intersections between borders of the clip rectangle and line segments in the set of line segments. Next, the system uses the determined intersections to clip polygons in the set of polygons that intersect the clip rectangle. Finally, the system transfers the clipped polygons, and also unclipped polygons that fit completely within the clip rectangle, to a display device that displays the view into the set of polygons.

Abstract: Provided is a computer-implemented method for processing one or more video frames. The meth can include generating, by a processor, a change in value of one or more pixels obtained from the one or more video frames; classifying, by the processor, the change in value of the one or more pixels to produce one or more classes of the change in value of the one or more pixels, wherein the one or more classes include one or more of a stationary target, a moving target, a target insertion, a target removal, or a local change; and constructing, by the processor, a listing of detected targets based on the one or more classes.

Abstract: To provide a technology capable of calculating a position of an image displayed on a screen more flexibly. Provided is an information processing device including: a first reception unit configured to receive a first signal from a first input device; a second reception unit configured to receive a second signal different from the first signal from a second input device; a calculation unit configured to calculate a position of an image to be displayed on a screen on the basis of the first or second signal; and a display control unit configured to display the image at the position. The calculation unit has a first mode in which the position of the image is calculated on the basis of the first signal and a second mode in which the position of the image is calculated on the basis of the second signal, and switches a mode from the first mode to the second mode when a user manipulation event is detected in the first mode.

Abstract: Methods and systems for identifying attributes included in a drawing. One method includes automatically, with a processing unit, identifying a plurality of attributes associated with a drawing and automatically, with the processing unit, assigning a unique identifier to each of the plurality of attributes. The method also includes automatically, with the processing unit, creating a symbol representing the assigned unique identifier for each of the plurality of attributes and displaying the symbol for each of the plurality of attributes on the drawing.

Abstract: A communication support system includes a network interface configured to receive, via a network, a captured image obtained in another location, a display configured to display the captured image received by the network interface, a cropping unit configured, in a case when the display superposes and displays a reference image as an upper layer over the captured image, to crop an image of an area having the reference image arranged therein out of the captured image, a specifying unit configured to specify a person area corresponding to a person within a cropped image obtained by the cropping unit, and a processing unit configured to make an area that is different from the person area specified by the specifying unit transparent in the cropped image. The display displays an output image obtained by superposing the reference image as an upper layer over the captured image and further superposing the cropped image processed by the processing unit as an upper layer over the reference image.

Abstract: A computer implemented method for performing floating point operations as part of a processor architecture that also includes fixed point operations is disclosed. The computer implemented method includes providing a group of instructions within the fixed point architecture. A floating point value is split between two programmer visible registers. In a system and method in accordance with the present invention a new form of floating point representation and associated processor operations, including efficient complex number representations and operations are utilized.

Abstract: An image processing device includes a recording control unit that controls recording of an image of a predetermined frame among images of a plurality of consecutive frames, a trim box setting unit that sets a plurality of trim boxes containing a subject area which is an area of a subject of interest in the image of the predetermined frame recorded by the recording control unit, and a generation control unit that controls generation of the plurality of trim images from the image of the predetermined frame recorded by the recording control unit, based on the plurality of trim boxes set by the trim box setting unit.

Abstract: A method, computer program product, and computing system for receiving an indication of a user selecting a selected portion of a piece of content for review on a display screen. A determination is made concerning whether the piece of content will fit within the display screen. If the piece of content will not fit within the display screen: a header portion of the piece of content is rendered within an upper portion of the display screen, and the selected portion of the piece of content is rendered within a main portion of the display screen.

Abstract: Disclosed is an edge management unit of accessing a memory including a first memory area and a second memory area. The edge management unit comprises an edge write controller writing bucket information corresponding to input edge data in the first memory area and the edge data at a location of the second memory area appointed by the bucket information; and an edge read controller responding to a scan line signal to read the bucket information from the first memory area and the edge data from a location of the second memory area appointed by the read bucket information.

Abstract: Provided are a clipping apparatus and clipping method for a three-dimensional (3D) graphic rendering. The clipping apparatus may reset or convert a triangular object based on distance information of vertices configuring or comprising the triangular object where a perspective projection scheme is applied.

Abstract: A method and device for performing and processing user-defined clipping in object space to reduce the number of computations needed for the clipping operation. The method and device also combine the modelview transformation of the vertex coordinates with projection transform. The user-defined clipping in object space provides a higher performance and less power consumption by avoiding generation of eye coordinates if there is no lighting. The device includes a driver for the user-defined clipping in the object space to perform dual mode user-defined clipping in object space when a lighting function is disabled and in eye space when the lighting function is enabled.

Abstract: One embodiment of the present invention sets forth a technique for generating a batch clip state stored in clip state machine (CSM) associated with a batch of vertices. Per-vertex clip state is generated for each vertex in the batch of vertices based on the position of each vertex relative to each clip plane. For a given vertex, per-vertex clip state indicates whether the vertex is inside or outside each of the one or more clip planes. The per-vertex clip states of all the vertices in the batch of vertices are coalesced into a batch clip state by determining whether each vertex in the batch of vertices is inside every clip plane, each vertex is outside at least one clip plane or neither. The batch clip state is stored in the CSM associated with the thread group that processes the batch of vertices that can be accessed by further stages of the graphics pipeline.

Abstract: An aspect of the present invention clips a sequence of data values within a known range (defined by a set of integer values) by a ceiling value and a floor value. In an embodiment, such a feature is obtained by first storing in each of a sequence of memory locations a respective value corresponding to each integer value, with a stored value in a memory location equaling the floor value if the memory location corresponds to an integer having a value less than the floor value, equaling the ceiling value if the memory location corresponds to an integer having a value greater than the ceiling value, and equaling the value of the corresponding integer otherwise. When a sequence of data values are thereafter received for clipping, the clipped value for each data value is obtained by merely retrieving a corresponding stored value from the corresponding location.

Abstract: A method and system for framework clipping are disclosed. A user interface tree of widgets corresponding to widgets requiring clipping is traversed. For each encountered widget, layer allocation operations are performed which include selecting a current, previous, or next layer to which to allocate the widget and determining whether the selected layer can accommodate the widget, where a determination that the selected layer cannot accommodate the widget results in a bit from a stencil buffer being allocated to the selected layer. A value of the selected layer is incremented to account for the widget being allocated to the selected layer A stencil test mask is generated as a combination of value of the layers previous to a current layer. The stencil test mask is written to the stencil buffer, and the layer allocation operations are repeated for each remaining widget.

Abstract: A general moving image includes a plurality of objects in a frame image. At the time of playback, the temporal visual characteristic is taken into consideration uniformly in the overall frame image. It is therefore impossible to perform playback while particularly considering an object of interest. In this invention, when playing back a moving image including a plurality of time-divided frame images, the object adaptation time of each object image is acquired first in the frame image of interest of the plurality of frame images. An adaptation weight is calculated based on the acquired object adaptation time, and a low-pass image reflecting the adaptation weight is generated for each object image. Color adaptation conversion using the low-pass image makes it possible to perform, for the frame image of interest, color conversion based on the adaptation time of each object image and perform color conversion particularly considering an object of interest.

Abstract: An exemplary method includes determining a node having a drawable payload representing a surface portion of a curved three-dimensional model in a three-dimensional environment. The exemplary method also includes determining whether the virtual camera is located within a first substantially conical volume. The exemplary method further includes determining whether the virtual camera is located within a second substantially conical volume. The exemplary method also includes when the virtual camera is determined to be inside the first substantially conical volume and to be outside the second substantially conical volume, culling the node. The exemplary method further includes when the virtual camera is determined to be inside both the first substantially conical volume and the second substantially conical volume, rendering the drawable payload.

Abstract: A coordinate data read unit reads coordinate data of vertexes of a three-dimensional object stored in a memory into an internal storage unit. A coordinate transformation unit performs coordinate transformation on the coordinate data stored in the internal storage unit. A vertex deletion unit determines whether a piece of the attribute data of each vertex is to be read, based on the transformed pieces of the coordinate data stored in the internal storage unit. An attribute data read unit reads a piece of the attribute data of each vertex determined to be read by the vertex read unit from the memory into the internal storage unit. A display control unit performs drawing processing based on the pieces of the coordinate and the attribute data stored in the internal storage unit.

Abstract: One embodiment of the present invention sets forth a technique for rendering clipped paths by first generating clip stencil buffer state indicating pixels that are inside of the clip path. The clip stencil buffer state may also store an opacity value for each covered pixel to generate a mask that modulates the opacity of a draw path that is clipped. Clipped draw stencil buffer state is then generated indicating pixels of the draw path that should be covered based on the clip stencil buffer state and coverage of the draw path. The clipped draw path is then filled or stroked to produce the clipped draw path. The clip and draw paths may be filled or stroked without tessellating the paths. Path rendering may be accelerated when a GPU or other processor that is configured to perform operations to generate the clip stencil buffer state and the clipped draw stencil buffer state, and to fill or stroke the clipped draw path.

Abstract: Embodiments render polygonal data in a geographical information systems according to a viewing perspective of a geographical information systems user. The user may define a viewing perspective. A bounding box may be determined that includes the area being viewed in the viewing perspective. A spherical coordinate to Cartesian coordinate matrix may be determined to approximately convert spherical coordinates of the polygonal data to Cartesian coordinates to be rendered by a graphics processor. The graphics processor may then render the polygonal data and bias detail towards the viewing perspective of the user.

Abstract: Performing accelerated volume rendering of a scene in a computer system by: loading volumetric data into a first part of a system memory, the volumetric data represented as a three-dimensional array of data values; determining intersection points of each of a set of sample rays cast through the scene and intersecting the three-dimensional array, wherein the intersection points are determined as a function of sample times from beginning to end; using the intersection points, computing a subset of the three-dimensional array for placement into local storage; loading the subset of three-dimensional array into the local storage; and repeating the determining, computing, and loading acts for all sample times from beginning to end for all sets of sample rays cast by the processor device.

Abstract: Pixel depth values of a user-controlled virtual object in a three-dimensional scene may be re-scaled to avoid artifacts when the scene is displayed. Minimum and maximum threshold values can be determined for the three-dimensional scene. Each pixel depth value of the user-controlled virtual object can be compared to the minimum threshold value and the maximum threshold value. A depth value of each pixel of the user-controlled virtual object that falls below the minimum threshold value can be set to a corresponding low value. Each pixel depth value of the user-controlled virtual object that exceeds the maximum threshold value can be set to a corresponding high value.

Abstract: Systems, methods and apparatus for generating an asset for a simulated environment using digital image capture are disclosed. An outline of an object in a digital image is automatically traced to generate data representing a two-dimensional polygon that encompasses the object. The outline is traced without relying on further input from a user once the digital image of the object has been captured. A portion of the digital image bounded by the two-dimensional polygon is separated from a remaining portion of the digital image. The portion of the image bounded by the two-dimensional polygon is associated with an asset in the simulated environment.

Abstract: One embodiment of the present invention sets forth a technique for generating a batch clip state stored in clip state machine (CSM) associated with a batch of vertices. Per-vertex clip state is generated for each vertex in the batch of vertices based on the position of each vertex relative to each clip plane. For a given vertex, per-vertex clip state indicates whether the vertex is inside or outside each of the one or more clip planes. The per-vertex clip states of all the vertices in the batch of vertices are coalesced into a batch clip state by determining whether each vertex in the batch of vertices is inside every clip plane, each vertex is outside at least one clip plane or neither. The batch clip state is stored in the CSM associated with the thread group that processes the batch of vertices that can be accessed by further stages of the graphics pipeline.

Abstract: A computer implemented method for creating a depth range buffer for supporting clipping geometries for ray-casting includes inputting image data, establishing a depth range buffer for specifying a start and an end point of each ray, computing a near depth of the image data corresponding to the start point of each ray, computing a far depth of the image data corresponding to the end point of each ray, clipping the volume by restricting ray-casting within the start and end points of the depth range buffer, and rendering a portion of the image data corresponding to the visible depth range.

Abstract: Methods, systems, and computer-readable media are provided for distributing icons so that they do not overlap certain screen areas of a mobile device. In particular, screen areas of a background image displayed on a screen of a mobile device may be identified as image portions that are desirable for protection. After the desired image portions are identified, foreground screen areas corresponding to the desired image portions are designated as being unavailable to present icons. Icons are then presented on available screen areas of the mobile device so as to avoid overlapping desired image portions.

Abstract: Methods, apparatuses and systems directed to using viewport state data objects (VSDO) to render a series of video frames according to render instructions to achieve video compression. In a particular implementation, the video compression format exposes the VSDO and render instructions to a video render client, allowing the video render client to finish rendering a sequence of video frames from different spatial locations and view transform parameters. Implementations of this video compression format further allow any arbitrary client with enough graphics processing power and bandwidth to retransmit novel, completely rendered viewports to thin clients without taxing the root remote render devices.

Abstract: A network management system allows a network administrator to intuitively manage all components of a heterogeneous networked computer system using views of any component or any set of components. These views are generated in a multi-dimensional, virtual reality environment. Navigation tools are provided that allow an operator to travel through the network hierarchy's representation in the virtual environment using an automatic flight mode. Automatic flight mode determines a reasonable trajectory to a network component that avoids collisions with intervening objects in the virtual environment. Since the system is capable of managing a world-wide network, city, building, subnet, segment, and computer, a view may also display internal hardware, firmware, and software of any network component. Views of network components may be filtered so only components pertaining to a specific business or other interest are displayed.

Abstract: A data processing apparatus for a collision check with respect to a plurality of rays. A control unit may generate a plurality of packets with respect to a plurality of rays associated with a first node in a spatial data structure. At least one of the plurality of packets may include information about k rays, and k may be a natural number. A processor may sequentially receive the plurality of packets and determine which child node of the first node is associated with each of the plurality of rays associated with the first node.

Abstract: A method and device for performing and processing user-defined clipping in object space to reduce the number of computations needed for the clipping operation. The method and device also combine the modelview transformation of the vertex coordinates with projection transform. The user-defined clipping in object space provides a higher performance and less power consumption by avoiding generation of eye coordinates if there is no lighting. The device includes a driver for the user-defined clipping in the object space to perform dual mode user-defined clipping in object space when a lighting function is disabled and in eye space when the lighting function is enabled.

Abstract: A method for generating 3D visualization of a large-scale environment comprising the steps of: acquiring a 3D model of the large-scale environment; dividing the 3D model into a near-field part and a far-field part; rendering an array of images of the far-field part; creating a 3D visualization of the near-field part combined with the array of rendered images of the far-field part and displaying the combined rendered images.

Abstract: A display processing system for providing video signals for displaying an image is provided. The display processing system comprises input channels for receiving a plurality of component images, each component image being a portion of the complete image for display, the image data of each component image being defined by a view frustum having a clipping plane, and a combiner for combining the image data of the component images. According to the present invention, at least two clipping planes of two of the view frustums are non-coplanar. Such display processing system corrects for the defect of driving angular resolution to the edges of the field of view of a display system, in particular for large field-of-view display systems, and balances the overall system angular resolution by allowing each image generator channel to render to an optimal view frustum for its portion of the complete image.

Abstract: A method. for use in animation includes the steps of establishing a model having a plurality of joints, exposing a region of a first normal map based on a position of one or more of the joints, and applying the exposed region of the first normal map to the model. A system for use in animation is configured to accomplish these steps.

Abstract: An image forming system includes: a resource information storage unit that previously stores resource information to be combined with input print information; a first setting unit that sets an image characteristic of the resource information stored in the resource information storage unit; a second setting unit that sets an image characteristic of the input print information; and a color conversion unit that, when the image characteristic set by the first setting unit and the image characteristic set by the second setting unit are different, performs color conversion on the resource information based on the image characteristic set by the first setting unit, and performs color conversion on the print information based on the image characteristic set by the second setting unit.

Abstract: A system, method, and computer program product are provided for selecting a ray tracing entity from a group of ray tracing entities for processing by a parallel processing architecture. In operation, it is determined whether at least one thread in a parallel processing architecture has completed processing a ray tracing entity. Further, an additional ray tracing entity is selected from a group of ray tracing entities for processing by the parallel processing architecture, based on the determination.

Abstract: A system, method, and computer program product are provided for postponing the execution of primitive intersection. In operation, at, least one node traversal operation and at least one primitive intersection operation is executed, utilizing a parallel processing architecture. Additionally, the execution of the at least one primitive intersection operation is postponed.

Abstract: A system, method, and computer program product are provided for executing node traversal or primitive intersection using a parallel processing architecture. In operation, it is determined whether a plurality of threads in a parallel processing architecture are to execute node traversal or primitive intersection. Additionally, the node traversal or the primitive intersection is executed, based on the determination.

Abstract: A printing system includes a converter for replacing graphic elements of a color matched document (104). Conversion replaces original elements (2-4) with replacement elements (21-24, 40-42) having modified transparency attributes so that overprinting elements that overlap areas (10-15) appear as intended when subjected to color matching.

Abstract: An enhanced graphics pipeline is provided that enables common core hardware to perform as different components of the graphics pipeline, programmability of primitives including lines and triangles by a component in the pipeline, and a stream output before or simultaneously with the rendering a graphical display with the data in the pipeline. The programmer does not have to optimize the code, as the common core will balance the load of functions necessary and dynamically allocate those instructions on the common core hardware. The programmer may program primitives using algorithms to simplify all vertex calculations by substituting with topology made with lines and triangles. The programmer takes the calculated output data and can read it before or while it is being rendered. Thus, a programmer has greater flexibility in programming.

Abstract: A method for creating a cutout surface for volume rendering includes providing a digitized medical image volume comprising a plurality of intensities corresponding to a 3-dimensional grid of points, identifying a surface of interest in said image volume, representing said surface-of-interest by a polygonal mesh, extracting a set of curves on said surface-of-interest where a cutout surface will intersect, extending a vector defined on one of said curves toward a viewing point, and sweeping said extended vector along said curve to create said cutout surface.

Abstract: A graphics system supports arrays of cube map textures. In one implementation, a cube map texture is utilized as an index into a set of cube map textures. The set of cube map textures may further be arranged into an atlas of two-dimensional textures.

Abstract: A method, system, and computer-readable storage medium are disclosed for editing an image comprising a first spatial dimension and a second spatial dimension. Input specifying one or more key locations on a first spatial coordinate line may be received. The first spatial coordinate line may correspond to the first spatial dimension of the image, and boundaries for a plurality of partitions of the image may be determined by the one or more key locations on the first spatial coordinate line. Input specifying one or more respective parameter values for an effect at each of the one or more key locations on the first spatial coordinate line may be received. The effect may be automatically applied within each of the plurality of partitions of the image based on the one or more parameter values at the respective boundaries for each of the plurality of partitions.

Abstract: In a raster stage of a graphics pipeline, a method for accelerated start tile rasterization. The method includes defining a window for clipping a generated image and receiving a graphics primitive for rasterization in a raster stage of a graphics processor. A binary search related to the window is performed to determine a start tile having at least a partial coverage of the graphics primitive, wherein the start tile comprises a plurality of pixels. Based upon the start tile, the raster stage rasterizes the graphics primitive by generating a plurality of adjacent tiles having at least a partial coverage of the graphics primitive.

Abstract: A distributed clipping scheme is provided, view frustum culling is distributed in several places in a graphics processing pipeline to simplify hardware implementation and improve performance. In general, many 3D objects are outside viewing frustum. In one embodiment, clipping is performed on these objects with a simple algorithm in the PA module, such as near Z clipping, trivial rejection and trivial acceptance. In one embodiment, the SE and RA modules perform the rest of clipping, such as X, Y and far Z clipping. In one embodiment, the SE module performs clipping by way of computing a initial point of rasterization. In one embodiment, the RA module performs clipping by way of conducting the rendering step of the rasterization process. This approach distributes the complexity in the graphics processing pipeline and makes the design simpler and faster, therefore design complexity, cost and performance may all be improved in hardware implementation.

Abstract: A processor having a compare extension of an instruction set architecture which incorporates a set of high performance floating point operations. The instruction set architecture incorporates a variety of data formats including single precision and double precision data formats, as well as the paired-single data format that allows two simultaneous operations on a pair of operands. The extension includes instructions directed to a magnitude compare of floating point numbers and conversions between a pair of 32-bit fixed point integers and paired-single floating point format.

Abstract: A system, method and computer program product are provided for programmable vertex processing. Initially, a vertex program is identified including branch labels and instruction sequences with branch commands. The vertex program is then converted to a binary format capable of being executed by a hardware graphics pipeline. The vertex program may then be executed in the binary format utilizing the hardware graphics pipeline for transforming vertices. As an option, the vertex program is initially written in a textual format capable of being read by a human prior to being converted.

Abstract: Subsets of volume data are sequentially stored for volume rendering from two dimensional textures. For example, pairs of adjacent two-dimensional images are loaded into RAM or cache. Strips of texture data are interpolated for polygons extending between the two-dimensional images. The strips or polygons are more orthogonal to a viewing direction than the two-dimensional images. After interpolating texture data from the two-dimensional images for a plurality of non-coplanar polygons, the texture data is rendered. The rendered information represents one portion of the three dimensional representation. Other portions are rendered by repeating the process for other pairs or subset groups of adjacent two-dimensional images. A lower cost apparatus, such as a programmed computer or a GPU with a limited amount of memory, is able to render images for three dimensional representations of very large three-dimensional arrays. The images may be rendered without copying volume data for different main axes.