Abstract: A graphics processing pipeline within a parallel processing unit (PPU) is configured to perform path rendering by generating a collection of graphics primitives that represent each path to be rendered. The graphics processing pipeline determines the coverage of each primitive at a number of stencil sample locations within each different pixel. Then, the graphics processing pipeline reduces the number of stencil samples down to a smaller number of color samples, for each pixel. The graphics processing pipeline is configured to modulate a given color sample associated with a given pixel based on the color values of any graphics primitives that cover the stencil samples from which the color sample was reduced. The final color of the pixel is determined by downsampling the color samples associated with the pixel.

Abstract: One embodiment of the present invention includes a memory management unit (MMU) that is configured to manage sparse mappings. The MMU processes requests to translate virtual addresses to physical addresses based on page table entries (PTEs) that indicate a sparse status. If the MMU determines that the PTE does not include a mapping from a virtual address to a physical address, then the MMU responds to the request based on the sparse status. If the sparse status is active, then the MMU determines the physical address based on whether the type of the request is a write operation and, subsequently, generates an acknowledgement of the request. By contrast, if the sparse status is not active, then the MMU generates a page fault. Advantageously, the disclosed embodiments enable the computer system to manage sparse mappings without incurring the performance degradation associated with both page faults and conventional software-based sparse mapping management.

Abstract: One embodiment of the present invention sets forth a technique for distributing graphics commands and atomic commands to a color processing unit (CROP) in an efficient manner. The interleaving mechanism determines, at each clock cycle, which graphics command(s) or atomic command(s) is transmitted to the CROP based on different factors. First, the interleaving mechanism ensures that atomic commands or graphics commands associated with a multi-transaction command stream are processed together. Second, the interleaving mechanism selects consecutive graphics commands for transmission to the CROP that optimize the use of different memory caches. Third, the interleaving mechanism prioritizes atomic commands over graphics commands. At each clock cycle, the graphics command(s) or the atomic command(s) selected by the interleaving mechanism are transmitted to the CROP for processing.

Abstract: One embodiment sets forth a method for transforming 3-D images into 2-D rendered images using render target sample masks. A software application creates multiple render targets associated with a surface. For each render target, the software application also creates an associated render target sample mask configured to select one or more samples included in each pixel. Within the graphics pipeline, a pixel shader processes each pixel individually and outputs multiple render target-specific color values. For each render target, a ROP unit uses the associated render target sample mask to select covered samples included in the pixel. Subsequently, the ROP unit uses the render target-specific color value to update the selected samples in the render target, thereby achieving sample-level color granularity.

Abstract: A computer-implemented method for drawing graphical objects within a graphics processing pipeline is disclosed. The method includes determining that a bypass mode for a first primitive is a no-bypass mode. The method further includes rasterizing the first primitive to generate a first set of rasterization results. The method further includes generating a first set of colors for the first set of rasterization results via a pixel shader unit. The method further includes rasterizing a second primitive to generate a second set of rasterization results. The method further includes generating a second set of colors for the second set of rasterization results without the pixel shader unit performing any processing operations on the second set of rasterization results. The method further includes transmitting the first set of pixel colors and the second set of pixel colors to a raster operations (ROP) unit for further processing.

Abstract: Multisampling techniques provide temporal as well as spatial antialiasing. Coverage for a primitive is determined at multiple sample locations for a pixel. In one embodiment, coverage is determined using boundary equations representing a boundary surface of the primitive in a three-dimensional space-time. A shading value for the primitive is computed for the pixel and stored for each coverage sample location of the pixel that is covered by the primitive. The sample locations are distributed in both space and time, and multiple sample locations share a single shading computation. The multisampling techniques are extendable to other dimensions that correspond to other image attributes.

Abstract: One embodiment of the present invention includes a memory management unit (MMU) that is configured to manage sparse mappings. The MMU processes requests to translate virtual addresses to physical addresses based on page table entries (PTEs) that indicate a sparse status. If the MMU determines that the PTE does not include a mapping from a virtual address to a physical address, then the MMU responds to the request based on the sparse status. If the sparse status is active, then the MMU determines the physical address based on whether the type of the request is a write operation and, subsequently, generates an acknowledgement of the request. By contrast, if the sparse status is not active, then the MMU generates a page fault. Advantageously, the disclosed embodiments enable the computer system to manage sparse mappings without incurring the performance degradation associated with both page faults and conventional software-based sparse mapping management.

Abstract: One embodiment sets forth a method for transforming 3-D images into 2-D rendered images using render target sample masks. A software application creates multiple render targets associated with a surface. For each render target, the software application also creates an associated render target sample mask configured to select one or more samples included in each pixel. Within the graphics pipeline, a pixel shader processes each pixel individually and outputs multiple render target-specific color values. For each render target, a ROP unit uses the associated render target sample mask to select covered samples included in the pixel. Subsequently, the ROP unit uses the render target-specific color value to update the selected samples in the render target, thereby achieving sample-level color granularity.

Abstract: A graphics processing pipeline within a parallel processing unit (PPU) is configured to perform path rendering by generating a collection of graphics primitives that represent each path to be rendered. The graphics processing pipeline determines the coverage of each primitive at a number of stencil sample locations within each different pixel. Then, the graphics processing pipeline reduces the number of stencil samples down to a smaller number of color samples, for each pixel. The graphics processing pipeline is configured to modulate a given color sample associated with a given pixel based on the color values of any graphics primitives that cover the stencil samples from which the color sample was reduced. The final color of the pixel is determined by downsampling the color samples associated with the pixel.

Abstract: A computer-implemented method for drawing graphical objects within a graphics processing pipeline is disclosed. The method includes determining that a bypass mode for a first primitive is a no-bypass mode. The method further includes rasterizing the first primitive to generate a first set of rasterization results. The method further includes generating a first set of colors for the first set of rasterization results via a pixel shader unit. The method further includes rasterizing a second primitive to generate a second set of rasterization results. The method further includes generating a second set of colors for the second set of rasterization results without the pixel shader unit performing any processing operations on the second set of rasterization results. The method further includes transmitting the first set of pixel colors and the second set of pixel colors to a raster operations (ROP) unit for further processing.

Abstract: One embodiment of the invention sets forth a CROP configured to perform both color raster operations and atomic transactions. Upon receiving an atomic transaction, the distribution unit within the CROP transmits a read request to the L2 cache for retrieving the destination operand. The distribution unit also transmits the source operands and the operation code to the latency buffer for storage until the destination operand is retrieved from the L2 cache. The processing pipeline transmits the operation code, the source and destination operands and an atomic flag to the blend unit for processing. The blend unit performs the atomic transaction on the source and destination operands based on the operation code and returns the result of the atomic transaction to the processing pipeline for storage in the internal cache. The processing pipeline writes the result of the atomic transaction to the L2 cache for storage at the memory location associated with the atomic transaction.

Abstract: One embodiment of the invention sets forth a CROP configured to perform both color raster operations and atomic transactions. Upon receiving an atomic transaction, the distribution unit within the CROP transmits a read request to the L2 cache for retrieving the destination operand. The distribution unit also transmits the source operands and the operation code to the latency buffer for storage until the destination operand is retrieved from the L2 cache. The processing pipeline transmits the operation code, the source and destination operands and an atomic flag to the blend unit for processing. The blend unit performs the atomic transaction on the source and destination operands based on the operation code and returns the result of the atomic transaction to the processing pipeline for storage in the internal cache. The processing pipeline writes the result of the atomic transaction to the L2 cache for storage at the memory location associated with the atomic transaction.

Abstract: One embodiment of the invention sets forth a CROP configured to perform both color raster operations and atomic transactions. Upon receiving an atomic transaction, the distribution unit within the CROP transmits a read request to the L2 cache for retrieving the destination operand. The distribution unit also transmits the source operands and the operation code to the latency buffer for storage until the destination operand is retrieved from the L2 cache. The processing pipeline transmits the operation code, the source and destination operands and an atomic flag to the blend unit for processing. The blend unit performs the atomic transaction on the source and destination operands based on the operation code and returns the result of the atomic transaction to the processing pipeline for storage in the internal cache. The processing pipeline writes the result of the atomic transaction to the L2 cache for storage at the memory location associated with the atomic transaction.

Abstract: An apparatus and method for translating fixed function state into a shader program. Fixed function state is received and stored and when a new shader program is detected the fixed function state is translated into shader program instructions. Registers specified by the program instructions are allocated for processing in the shader program. The registers may be remapped for more efficient use of the register storage space.

Abstract: An apparatus and method for translating fixed function state into a shader program. Fixed function state is received and stored and when a new shader program is detected the fixed function state is translated into shader program instructions. Registers specified by the program instructions are allocated for processing in the shader program. The registers may be remapped for more efficient use of the register storage space.

Abstract: An apparatus and method for translating fixed function state into a shader program. Fixed function state is received and stored and when a new shader program is detected the fixed function state is translated into shader program instructions. Registers specified by the program instructions are allocated for processing in the shader program. The registers may be remapped for more efficient use of the register storage space.

Abstract: An apparatus and method for converting color data from one color space to another color space. A driver determines that a set of shader program instructions perform a color conversion function and the set of shader program instructions are replaced with either a single shader program instruction or a flag is set within an existing shader program instruction to specify that output color data is represented in a nonlinear color format. The output color data is converted to the nonlinear color format prior to being stored in a frame buffer. Nonlinear color data read from the frame buffer is converted to a linear color format prior to shading, blending, or raster operations.

Abstract: Digital Image compositing using a programmable graphics processor is described. The programmable graphics processor supports high-precision data formats and can be programmed to complete a plurality of compositing operations in a single pass through a fragment processing pipeline within the programmable graphics processor. Source images for one or more compositing operations are stored in graphics memory, and a resulting composited image is output or stored in graphics memory. More-complex compositing operations, such as blur, warping, morphing, and the like, can be completed in multiple passes through the fragment processing pipeline. A composited image produced during a pass through the fragment processing pipeline is stored in graphics memory and is available as a source image for a subsequent pass.

Abstract: Circuits, methods, and apparatus that provide for partial texture load instructions. Instead of one instruction that may take several shader passes to complete, several instructions are issued, where each instruction is an instruction to retrieve a part or portion of a texture. While each instruction is performed, the other shader circuits can perform other instructions, thus increasing the utilization of the shader circuits when large textures are read from memory. Since several shader passes may be required to read a texture, if a particular instruction needs the texture, one exemplary embodiment reorders instructions such that other instructions are performed before the particular instruction that needs the texture.

Abstract: Multiple output buffers are supported in a graphics processor. Each output buffer has a unique identifier and may include data represented in a variety of fixed and floating-point formats (8-bit, 16-bit, 32-bit, 64-bit and higher). A fragment program executed by the graphics processor can access (read or write any of the output buffers. Each of the output buffers may be read from and used to process graphics data by an execution pipeline within the graphics processor. Likewise, each output buffer may be written to by the graphics processor, storing graphics data such as lighting parameters, indices, color, and depth.