Paper Info
Title
FreePipe: a programmable parallel rendering architecture for efficient multi-fragment effects
Abstract
In the past decade, modern GPUs have provided increasing programmability with vertex, geometry and fragment shaders. However, many classical problems have not been efficiently solved using the current graphics pipeline where some stages are still fixed functions on chip. In particular, multi-fragment effects, especially order-independent transparency, require programmability of the blending stage, that makes it difficult to be solved in a single geometry pass. In this paper we present FreePipe, a system for programmable parallel rendering that can run entirely on current graphics hardware and has performance comparable with the traditional graphics pipeline. Within this framework, two schemes for the efficient rendering of multi-fragment effects in a single geometry pass have been developed by exploiting CUDA atomic operations. Both schemes have achieved significant speedups compared to the state-of-the-art methods that are based on traditional graphics pipelines.
Year
DOI
Venue
2010
10.1145/1730804.1730817
SI3D
Keywords
Field
DocType
blending stage,programmable parallel rendering,single geometry,current graphics pipeline,traditional graphics pipeline,single geometry pass,programmable parallel rendering architecture,current graphics hardware,multi-fragment effect,efficient multi-fragment effect,cuda atomic operation,efficient rendering,graphics hardware,rasterizer,chip,parallel rendering,atomic operation
Parallel rendering,Graphics pipeline,Computer graphics (images),Computer science,Parallel computing,Alternate frame rendering,Texture memory,General-purpose computing on graphics processing units,Rendering (computer graphics),Software rendering,Tiled rendering
Conference
Citations 
PageRank 
References 
31
1.46
29
Authors
4
Name
Order
Citations
PageRank
Fang Liu1847.37
Meng-Cheng Huang2897.45
Xue-Hui Liu325626.39
Enhua Wu4916115.33