Abstract
Image composition architecture for polygon rendering is the most promising candidate for high performance. It does not suffer from any disadvantage of screen subdivision architecture (i.e., load imbalance and increased clipping time). However, in this architecture, the image composition operation cannot be overlapped with the calculation operation for computing an image and the memory requirement for local frame buffer is very large. The object based parallel rendering system (OBPRS) that is based on the image composition architecture is proposed and the objective of the OBPRS is to remove the disadvantages of the image composition architecture. According to the simulation results with a 64-renderer system, the OBPRS takes only about 80% of the rendering time of the image composition architecture. Also, it requires only 85% of the memory requirement for local frame buffer of the screen subdivision architecture. Thus the OBPRS turns out to be an effective system model, providing high performance to cost ratio.
Original language | English |
---|---|
Title of host publication | Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 766-771 |
Number of pages | 6 |
ISBN (Electronic) | 0769505902, 9780769505909 |
DOIs | |
Publication status | Published - 2000 |
Event | 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000 - Beijing, China Duration: 2000 May 14 → 2000 May 17 |
Publication series
Name | Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000 |
---|---|
Volume | 2 |
Other
Other | 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000 |
---|---|
Country/Territory | China |
City | Beijing |
Period | 00/5/14 → 00/5/17 |
Bibliographical note
Publisher Copyright:© 2000 IEEE.
All Science Journal Classification (ASJC) codes
- Computational Theory and Mathematics
- Computer Networks and Communications
- Computer Science Applications