Abstract: The performance of a neural network is improved by applying quantization to data at various points in the network. In an embodiment, a neural network includes two paths. A quantization is applied to each path, such that when an output from each path is combined, further quantization is not required. In an embodiment, the neural network is an autoencoder that includes at least one skip connection. In an embodiment, the system determines a set of quantization parameters based on the characteristics of the data in the primary path and in the skip connection, such that both network paths produce output data in the same fixed point format. As a result, the data from both network paths can be combined without requiring an additional quantization.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: A neural network structure, namely a warped external recurrent neural network, is disclosed for reconstructing images with synthesized effects. The effects can include motion blur, depth of field reconstruction (e.g., simulating lens effects), and/or anti-aliasing (e.g., removing artifacts caused by sampling frequency). The warped external recurrent neural network is not recurrent at each layer inside the neural network. Instead, the external state output by the final layer of the neural network is warped and provided as a portion of the input to the neural network for the next image in a sequence of images. In contrast, in a conventional recurrent neural network, hidden state generated at each layer is provided as a feedback input to the generating layer. The neural network can be implemented, at least in part, on a processor. In an embodiment, the neural network is implemented on at least one parallel processing unit.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: The performance of a neural network is improved by applying quantization to data at various points in the network. In an embodiment, a neural network includes two paths. A quantization is applied to each path, such that when an output from each path is combined, further quantization is not required. In an embodiment, the neural network is an autoencoder that includes at least one skip connection. In an embodiment, the system determines a set of quantization parameters based on the characteristics of the data in the primary path and in the skip connection, such that both network paths produce output data in the same fixed point format. As a result, the data from both network paths can be combined without requiring an additional quantization.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: It is presented a method for improving performance of generation of digitally represented graphics. Said method comprises the steps of: selecting (440) a tile comprising fragments to process; executing (452) a culling program for the tile, the culling program being replaceable; and executing a set of instructions, selected from a plurality of sets of instructions based on an output value of the culling program, for each of a plurality of subsets of the fragments. A corresponding display adapter and computer program product are also presented.

Abstract: It is presented a method for improving performance of generation of digitally represented graphics. Said method comprises the steps of: selecting (440) a tile comprising fragments to process; executing (452) a culling program for the tile, the culling program being replaceable; and executing a set of instructions, selected from a plurality of sets of instructions based on an output value of the culling program, for each of a plurality of subsets of the fragments. A corresponding display adapter and computer program product are also presented.

Abstract: Techniques to improve graphics processing unit (GPU) performance by introducing specialized code paths to process frequent common values are described. A shader compiler can determine instruction that, during operation, may output a common value and can introduce an enhanced shader instruction branch to process the common value to reduce overall computational requirements to execute the shader.

Abstract: Techniques to improve graphics processing unit (GPU) performance by introducing specialized code paths to process frequent common values are described. A shader compiler can determine instruction that, during operation, may output a common value and can introduce an enhanced shader instruction branch to process the common value to reduce overall computational requirements to execute the shader.

Abstract: A method for improving performance of generation of digitally represented graphics. The method comprises: receiving a first representation of a base primitive; providing a set of instructions associated with vertex position determination; executing said retrieved set of instructions on said first representation of said base primitive using bounded arithmetic for providing a second representation of said base primitive, and subjecting said second representation of said base primitive to a culling process. A corresponding apparatus and computer program product are also presented.

Abstract: Techniques to improve graphics processing unit (GPU) performance by introducing specialized code paths to process frequent common values are described. A shader compiler can determine instruction that, during operation, may output a common value and can introduce an enhanced shader instruction branch to process the common value to reduce overall computational requirements to execute the shader.

Abstract: A unified compression/decompression architecture is disclosed for reducing memory bandwidth requirements in 3D graphics processing applications. The techniques described erase several distinctions between a texture (compressed once, and decompressed many times), and buffers (compressed and decompressed repeatedly during rendering of an image). An exemplary method for processing graphics data according to one or more embodiments of the invention thus begins with the updating of one or more tiles of a first image array, which are then compressed, using a real-time buffer compression algorithm, to obtain compressed image array tiles. The compressed image array tiles are stored for subsequent use as a texture. During real-time rendering of a second image array, the compressed image array tiles are retrieved and decompressed using a decompression algorithm corresponding to the buffer compression algorithm.

Abstract: Techniques related to graphics rendering including techniques for color compression and/or decompression using adaptive quantization are described.

Abstract: It is presented a method for improving performance of generation of digitally represented graphics. Said method comprises the steps of: selecting (440) a tile comprising fragments to process; executing (452) a culling program for the tile, the culling program being replaceable; and executing a set of instructions, selected from a plurality of sets of instructions based on an output value of the culling program, for each of a plurality of subsets of the fragments. A corresponding display adapter and computer program product are also presented.

Abstract: A computer graphics processor and a method for rendering a three-dimensional image on a display screen. The computer graphics processor comprises a rasterizer configured to perform pixel traversal of a primitive after projection of the primitive. Furthermore, the rasterizer is configured to perform the pixel traversal of a first primitive for a plurality of views prior to performing pixel traversal of a next primitive for one or several views.

Abstract: Techniques related to graphics rendering including techniques for color compression and/or decompression using adaptive quantization are described.