Mechanism for minimal computation and power consumption for rendering synthetic 3D images, containing pixel overdraw and dynamically generated intermediate images

摘要

Embodiments disclosed include a mechanism in a system and method for significantly reducing power consumption by reducing computation and bandwidth. This mechanism is particularly applicable for modern 3D synthetic images which contain high pixel overdraw and dynamically generated intermediates images. Only blocks of computation which contribute to the final image are performed. This is accomplished by rendering in reverse order and by performing multiple visibility sort in a streaming fashion through the pipeline. Rendering of dynamically generated intermediate images is performed sparsely by projecting texture coordinates from a current image back into one or more dependent images in a recursive manner. The newly computed pixel values are then filtered and control is returned to the sampling shader of the current image. When only visible pixels are projected optimal computation is performed. Several implementations are presented with increasing efficiency. An acceleration structure, termed a Draw Buffer, simplifies the process of projecting backward and utilizes a hardware managed dynamic memory object. This mechanism reduces computation by 50%, with significant bandwidth and power savings.

主权项

1. A system for reducing power consumption comprising:
a rasterizer; a triangle processor; at least one electronically reconfigurable processor and a non-transitory electronically accessed memory storage element coupled to the said processor; encoded instructions stored in the said storage element, when implemented by the said processor configures the said system to reduce memory transactions and computation in graphics rendering, wherein the said system is further caused to:
perform computations which contribute to a final image, which computations comprise:sorting a stream of triangles into a collection of tile display lists, whereby an original index is electronically forwarded through the triangle processor to the rasterizer, wherein the rasterizer iterates over the triangle to determine which tile it intersects;determining which triangle will be written into an output command buffer for rendering by processing each tile's display list and iterating each triangle by the said rasterizer;rendering a plurality of intermediate images in reverse order wherein the said rendering further comprises projecting a plurality of texture coordinates from a current image back into a plurality of dependent images, such that only data from the dependent images which contributes to the current image are computed, recursively; andperforming a single or plurality of visibility sort operations in a streaming fashion through a rendering pipeline.