Name
Abstract | ||
|---|---|---|
This paper presents a rasterization rendering pipeline namely FreePipe. The system builds a bridge between the traditional graphics pipelines and the general purpose computing architecture CUDA by taking advantages of both sides. The core of FreePipe is a z-buffer based rasterizer entirely implemented in CUDA. The graphics pipeline can be easily mapped to the CUDA programming model with each stage fully open to the programmers. Within this flexible architecture, we propose a coherent depth test scheme for concurrent capture of both depth and color attributes using the atomicC AS operation in CUDA. The scheme can be easily extended to multiple level for efficient rendering of order independent transparency, which has significant performance improvement over the state-of-the-art methods based on traditional graphics pipelines. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1145/1900179.1900235 | VRCAI |
Keywords | Field | DocType |
traditional graphics pipeline,general purpose computing architecture,concurrent capture,rasterization rendering pipeline,flexible architecture,graphics pipeline,cuda programming model,multiple level,coherent depth test scheme,efficient rendering,programming model,computer architecture | Graphics,Pipeline transport,Order-independent transparency,Graphics pipeline,CUDA,Computer science,Parallel computing,Software rendering,Rendering (computer graphics),CUDA Pinned memory | Conference |
Citations | PageRank | References |
1 | 0.39 | 10 |
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 |