Advanced Micro Devices Corporation

Ati Technologies Ulc

Todd Martin

Mangesh P Nijasure

Vineet Goel

Randy Wayne Ramsey

Nishank Pathak

Tad Robert Litwiller

Michael Mantor

Jason David Carroll

Saad Arrabi

Anirudh Rajendra Acharya

Swapnil Pradipkumar Sakharshete

Guohua Jin

Brian J Favela

Laurent Lefebvre

Christopher Jude Brennan

Mark M Leather

Usame Ceylan

Young In Yeo

Brian A Buchner

Robert A Gottlieb

Gianpaolo Tommasi

Vishrut Vaibhav

Richard A Burns

Ryan James Cash

Systems, apparatuses, and methods for performing geometry work in parallel on multiple chiplets are disclosed. A system includes a chiplet processor with multiple chiplets for performing graphics work in parallel. Instead of having a central distributor to distribute work to the individual chiplets, each chiplet determines on its own the work to be performed. For example, during a draw call, each chiplet calculates which portions to fetch and process of one or more index buffer(s) corresponding to one or more graphics object(s) of the draw call. Once the portions are calculated, each chiplet fetches the corresponding indices and processes the indices. The chiplets perform these tasks in parallel and independently of each other. When the index buffer(s) are processed, one or more subsequent step(s) in the graphics rendering process are performed in parallel by the chiplets.

Distributed geometry

Systems, apparatuses, and methods for preemptively reserving buffer space for primitives and positions in a graphics pipeline are disclosed. A system includes a graphics pipeline frontend with any number of geometry engines coupled to corresponding shader engines. Each geometry engine launches shader wavefronts to execute on a corresponding shader engine. The geometry engine preemptively reserves buffer space for each wavefront prior to the wavefront being launched on the shader engine. When the shader engine executes a wavefront, the shader engine exports primitive and position data to the reserved buffer space. Multiple scan converters will consume the primitive and position data, with each scan converter consuming primitive and position data based on the screen coverage of the scan converter. After consuming the primitive and position data, the scan converters mark the buffer space as freed so that the geometry engine can then allocate the freed buffer space to subsequent shader wavefronts.

Graphics primitives and positions through memory buffers

Systems, apparatuses, and methods for loading multiple primitives per thread in a graphics pipeline are disclosed. A system includes a graphics pipeline frontend with a geometry engine, shader processor input (SPI), and a plurality of compute units. The geometry engine generates primitives which are accumulated by the SPI into primitive groups. While accumulating primitives, the SPI tracks the number of vertices and primitives per group. The SPI determines wavefront boundaries based on mapping a single vertex to each thread of the wavefront while allowing more than one primitive per thread. The SPI launches wavefronts with one vertex per thread and potentially multiple primitives per thread. The compute units execute a vertex phase and a multi-cycle primitive phase for wavefronts with multiple primitives per thread.

Load multiple primitives per thread in a graphics pipeline

Improvements to graphics processing pipelines are disclosed. More specifically, the vertex shader stage, which performs vertex transformations, and the hull or geometry shader stages, are combined. If tessellation is disabled and geometry shading is enabled, then the graphics processing pipeline includes a combined vertex and graphics shader stage. If tessellation is enabled, then the graphics processing pipeline includes a combined vertex and hull shader stage. If tessellation and geometry shading are both disabled, then the graphics processing pipeline does not use a combined shader stage. The combined shader stages improve efficiency by reducing the number of executing instances of shader programs and associated resources reserved.

Combined world-space pipeline shader stages

A method of deferred vertex attribute shading includes computing, at a graphics processing pipeline of a graphics processing unit (GPU), a plurality of vertex attributes for vertices of each primitive of a set of primitives. The plurality of vertex attributes to be computed includes a vertex position attribute and at least a first non-position attribute for each primitive. One or more primitives of the set of primitives that do not contribute to a rendered image are discarded based upon the vertex position attribute for vertices of the set of primitives. A set of surviving primitives is generated based on the culling and deferred attribute shading is performed for at least a second non-position attribute for vertices of the set of surviving primitives.

Optimizing primitive shaders

A graphics pipeline reduces the number of tessellation factors written to and read from a graphics memory. A hull shader stage of the graphics pipeline detects whether at least a threshold percentage of the tessellation factors for a thread group of patches are the same and, in some embodiments, whether at least the threshold percentage of the tessellation factors for a thread group of patches have a same value that either indicates that the plurality of patches are to be culled or that the plurality of patches are to be passed to a tessellator stage of the graphics pipeline. In response to detecting that at least the threshold percentage of the tessellation factors for the thread group are the same (or, additionally, that at least the threshold percentage of the tessellation factors have a value that either indicates that the plurality of patches are to be culled or that the plurality of patches are to be passed to a tessellator stage of the graphics pipeline), the hull shader stage bypasses writing at least a subset of the tessellation factors for the thread group of patches to the graphics memory, thus reducing bandwidth and increasing efficiency of the graphics pipeline.

Reduced bandwidth tessellation factors

A graphics pipeline includes a tessellator stage having a sub-patch distributor and a plurality of tessellators. The sub-patch distributor divides an input patch into a plurality of sub-primitive groups, with the primitive group limit governing the maximum permissible size for a given group of sub-primitives to be assigned to a tessellator. The sub-patch distributor recursively identifies a plurality of regions of the input patch, with the size and number of primitives of each region based on the specified primitive group limit. The sub-patch distributor assigns different regions to different sub-patch groups and distributes the sub-patch groups among the plurality of tessellators.

Tessellator sub-patch distribution based on group limits

Improvements in the graphics processing pipeline are disclosed. More specifically, a new primitive shader stage performs tasks of the vertex shader stage or a domain shader stage if tessellation is enabled, a geometry shader if enabled, and a fixed function primitive assembler. The primitive shader stage is compiled by a driver from user-provided vertex or domain shader code, geometry shader code, and from code that performs functions of the primitive assembler. Moving tasks of the fixed function primitive assembler to a primitive shader that executes in programmable hardware provides many benefits, such as removal of a fixed function crossbar, removal of dedicated parameter and position buffers that are unusable in general compute mode, and other benefits.

Primitive shader

A graphics processing unit (GPU) includes a packet management component that automatically aggregates data from input packets. In response to determining that a received first input packet does not indicate a send condition, and in response to determining that a generated output packet would be smaller than an output size threshold, the packet management component aggregates data corresponding to the first input packet with data corresponding to a second input packet stored at a packet buffer. In response to determining that a received third input packet indicates a send condition, the packet management component sends the aggregated data to a compute unit in an output packet and performs an operation indicated by the send condition.

GPU packet aggregation system

Improvements in the graphics processing pipeline that allow multiple pipelines to cooperate to render a single frame are disclosed. Two approaches are provided. In a first approach, world-space pipelines for the different graphics processing pipelines process all work for draw calls received from a central processing unit (CPU). In a second approach, the world-space pipelines divide up the work. Work that is divided is synchronized and redistributed at various points in the world-space pipeline. In either approach, the triangles output by the world-space pipelines are distributed to the screen-space pipelines based on the portions of the render surface overlapped by the triangles. Triangles are rendered by screen-space pipelines associated with the render surface portions overlapped by those triangles.

Split frame rendering

Techniques for removing reset indices from, and identifying primitives in, an index stream that defines a set of primitives to be rendered, are disclosed. The index stream may be specified by an application program executing on the central processing unit. The technique involves classifying the primitive topology for the index stream as either requiring an offset-based technique or requiring a non-offset-based technique. This classification is done by determining whether, according to the primitive topology, each subsequent index can form a primitive with prior indices (e.g., line strip, triangle strip). If each subsequent index can form a primitive with prior indices, then the technique used is the non-offset-based technique. If each subsequent index does not form a primitive with prior indices, but instead at least two indices are required to form a new primitive (e.g., line list, triangle list), then the technique used is the offset-based technique.

Identifying primitives in input index stream

A method and system for compiler optimization includes analyzing a representation of source code to identify an original conditional construct having both a high-latency instruction and one or more instructions dependent on the high-latency instruction in a branch of the conditional construct. A set of one or more instructions following the conditional construct in the representation of source code and independent of the high-latency instruction is selected. An optimized representation of the source code is generated, whereby the optimized representation replaces the original conditional construct with a first split conditional construct positioned prior to the selected set of one or more instructions and a second split conditional construct positioned following the selected set of one or more instructions, The method further includes generating an executable representation of the source code based on the optimized representation of the source code.

Growing community of inventors

Orlando, FL, United States of America

Todd Martin