Arm Limited

David James Bermingham

Andreas Due Engh-Halstvedt

Amir Kleen

Jørn Nystad

Jakob Axel Fries

Peter William Harris

Ian Victor Devereux

Oskar Lars Flordal

Kenneth Edvard Østby

A graphics processing system sorts graphics primitives for rendering into lists corresponding to different sub-regions of a render output to be generated, each list indicating primitives to be processed for the render output. A primitive list building unit divides a render target into various sub-regions, determines which sub-regions a primitive falls within and adds the primitive to the primitive lists corresponding to those sub-regions. The primitive list building unit also records the positions of the primitives in a pair of histograms which show the distribution of primitives across the render output. Once all primitives for the render output have been sorted into lists, the histograms are outputted to a predictor processor. The predictor processor then determines a set of sub-region sizes to be used when sorting primitives for the next render output to be generated into lists, based on the histograms.

Method and apparatus for processing graphics

A graphics processing unitincludes a rasterizer, a thread spawner, a programmable execution unit, a varying interpolator, a texture mapper, and a blender. The programmable execution unitis able to communicate with the varying interpolator, the texture mapperand the blenderto request processing operations by those graphic specific accelerators. In addition to this, these graphics-specific accelerators are also able to communicate directly with each other and with the thread spawner, independently of the programmable execution unit. This allows for certain graphics processing operations to be performed using direct communication between the graphics-specific accelerators of the graphics processing unit, instead of executing instructions in the programmable execution unit to trigger the performance of those operations by the graphics-specific accelerators.

Data processing systems

A data processing system includes a processing pipeline for the parallel execution of a plurality of threads. An issue controller issues threads to the processing pipeline. A stall manager controls the stalling and unstalling of threads when a cache miss occurs within a cache memory. The issue controller issues the threads to the processing pipeline in accordance with both a main sequence and a pilot sequence. The pilot sequence is followed such that threads within the pilot sequence are issued at least a given time ahead of their neighbors within a main sequence. The given time corresponds approximately to the latency associated with a cache miss. The threads may be arranged in groups corresponding to blocks of pixels for processing within a graphics processing unit.

Thread issue control

Growing community of inventors

Cambridge, United Kingdom

David James Bermingham