Advanced Micro Devices Corporation

Ati Technologies Ulc

Nishank Pathak

Tad Robert Litwiller

Todd Martin

Randy Wayne Ramsey

Christopher Jude Brennan

Mangesh P Nijasure

Michael Mantor

Rex Eldon McCrary

Jimshed B Mirza

Mark M Leather

Anthony Chan

Ricky Wai Yeung Iu

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 implementing a discard engine in a graphics pipeline are disclosed. A system includes a graphics pipeline with a geometry engine launching shaders that generate attribute data for vertices of each primitive of a set of primitives. The attribute data is consumed by pixel shaders, with each pixel shader generating a deallocation message when the pixel shader no longer needs the attribute data. A discard engine gathers deallocations from multiple pixel shaders and determines when the attribute data is no longer needed. Once a block of attributes has been consumed by all potential pixel shader consumers, the discard engine deallocates the given block of attributes. The discard engine sends a discard command to the caches so that the attribute data can be invalidated and not written back to memory.

Graphics discard engine

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

A processing system includes hull shader circuitry that launches thread groups including one or more primitives. The hull shader circuitry also generates tessellation factors that indicate subdivisions of the primitives. The processing system also includes throttling circuitry that estimates a primitive launch time interval for the domain shader based on the tessellation factors and selectively throttles launching of the thread groups from the hull shader circuitry based on the primitive launch time interval of the domain shader and a hull shader latency. In some cases, the throttling circuitry includes a first counter that is incremented in response to launching a thread group from the buffer and a second counter that modifies the first counter based on a measured latency of the domain shader.

Throttling hull shaders based on tessellation factors in a graphics pipeline

A processing system includes a graphics pipeline that executes a first shader of a first type and a second shader of a second type. In some cases, the first shader is a geometry shader and the second shader is a pixel shader. The processing system also includes buffers that hold primitives generated by the first shader and provide the primitives to the second shader. The processing system also includes a primitive hub that monitors fullness of the buffers. Launching of waves from the first shader is throttled based on the fullness of the buffers. A shader processor input (SPI) selectively throttles the waves launched by the geometry shader based on a signal from the primitive hub indicating the fullness, an indication of relative resource usage of geometry waves and pixel waves in the graphics pipeline, or an indication of lifetimes of the geometry waves.

Throttling shaders based on resource usage in a graphics pipeline

A graphics pipeline includes a first shader that generates first wave groups, a shader processor input (SPI) that launches the first wave groups for execution by shaders, and a scan converter that generates second waves for execution on the shaders based on results of processing the first wave groups the one or more shaders. The first wave groups are selectively throttled based on a comparison of in-flight first wave groups and second waves pending execution on the at least one second shader. A cache holds information that is written to the cache in response to the first wave groups finishing execution on the shaders. Information is read from the cache in response to read requests issued by the second waves. In some cases, the first wave groups are selectively throttled by comparing how many first wave groups are in-flight and how many read requests to the cache are pending.

Wave throttling based on a parameter buffer

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 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.

Growing community of inventors

Orlando, FL, United States of America

Nishank Pathak