Name
Abstract | ||
|---|---|---|
Multi-fragment effects play important roles on many graphics applications, which require operations on more than one fragment per pixel. The classical depth peeling algorithm [Everitt 2001] peels off one layer each pass, but the performance degrades for large scenes. We prefer to capture multiple fragments in a single pass, which is difficult because the fragments generated in graphics pipeline are not allowed to be scattered to arbitrary positions of the buffers. Compute unified device architecture (CUDA) [NVIDIA 2008] provides more flexible control over the GPU memory, but accessing of the fragments generated by graphics pipeline is not yet supported. In this work we design a CUDA rasterizer so that many graphics applications can benefit from the free control of GPU memory, especially for the multi-fragment effects. We present two efficient schemes to capture and sort multiple fragments per pixel in a single geometry pass via the atomic operations of CUDA without read-modify-write (RMW) hazards. Experimental results show significant speedup to classical depth peeling, especially for large scenes. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1145/1597990.1598069 | SIGGRAPH 2009: Talks |
Keywords | Field | DocType |
single geometry pass,gpu memory,graphics application,classical depth,large scene,cuda rasterizer,multi-fragment effect,multiple fragment,single pass,graphics pipeline,single pass depth,perception,animation,motion,read modify write | Computer graphics (images),CUDA,Computer science,Depth peeling,Artificial intelligence,Speedup,Graphics,Computer vision,Graphics pipeline,Parallel computing,General-purpose computing on graphics processing units,Pixel,CUDA Pinned memory | Conference |
Citations | PageRank | References |
11 | 0.98 | 1 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fang Liu | 1 | 84 | 7.37 |
| Meng-Cheng Huang | 2 | 89 | 7.45 |
| Xue-Hui Liu | 3 | 256 | 26.39 |
| Enhua Wu | 4 | 916 | 115.33 |