期刊文献+

基于绘制历史的sort-first集群绘制负载平衡方法 被引量:1

Load balancing method based on render history in cluster rendering
下载PDF
导出
摘要 负载平衡对sort-first集群并行绘制系统的性能有很大影响,但静态负载平衡方法适应性较差。而动态方法中,基于几何数据遍历的方法不具备实用性,基于粗粒度几何数据组织的方法在实际中得到应用,但依赖于对几何数据的预处理。为此,提出了一种实用的、基于绘制历史的负载平衡方法:它不依赖于几何数据,用以前帧的绘制时间和负载分布信息作为未来帧绘制负载分配计算的输入。在集群绘制平台上的测试和比较表明,该方法有很好的效果。 Performance of son-first cluster parallel rendering system is gready influenced by load balance. Static load balancing method is poorly adaptive. As to dynamical methods, those based on geometry data traversing are not practical, and those based on coarse geometry data granularity can be put into practice but depend on the pretreatment of geometry data. Therefore, a practical load balancing method based on render history was proposed. This method does not depend on geometry data, but utilizes render time of previous frame and its information of load distribution as the input of load balancing for the next frame's rendering. The method is tested on cluster rendering platform and the test results show that it is very effective.
出处 《计算机应用》 CSCD 北大核心 2006年第12期2843-2847,共5页 journal of Computer Applications
基金 浙江省自然科学基金资助项目(Y105324) 浙江省科技厅资助项目(2006C31065)
关键词 集群绘制 sort—first 负载平衡 绘制历史 cluster rendering sort-first load balance render history
  • 相关文献

参考文献16

  • 1DAVIS T,CHALMERS A,JENSEN HW.Practical Parallel Processing for Realistic Rendering[A].ACM S1GGRAPH[C].2000.
  • 2MOLNAR S,COX M,ELLSWORTH D,et al.A Sorting Classification of Parallel Rendering[A].IEEE computer graphics and applications[C].1994.23 -31.
  • 3HUMPHREYS G,ELDRIDGE M.WireGL:A Scalable Graphics System for Clusters[A].Proceedings of ACM SIGGRAPH[C].2001.
  • 4SAMANTA R,ZHENG J,FUNKHOUSER T,et al.Load Balancing for Multi-Projector Rendering Systems[A].Proceedings of the SIGGRAPH/Eurographics Workshop on Graphics Hardware[C].1999.
  • 5MONTRYM JS,BAUM DR,DIGNAM DL,et al.InfiniteReality:A Real-Time Graphics System[A].Proceedings of SIGGRAPH '97[C].1997.293 -302.
  • 6CROCKETT TW.Design Considerations for Parallel Graphics Libraries[R].ICASE Report No.94 -49,1994.
  • 7MOLNAR S,EYLES J,POULTON J.PixelFlow:High-Speed Rendering Using Image Composition[A].Proceedings of SIGGRAPH '92[C].Chicago,Illinois,1992.231 -240.
  • 8MITRA T,CHIUEH T.Implementation and Evaluation of Parallel Mesa Library[A].IEEE International Conference on Parallel and Distributed Systems[C].1998.
  • 9MOLL L,SHAND M,HEIRICH A.Sepia:Scalable 3D Compositing Using PCI Pamette[A].Laurent Proceedings of the Seventh Annual IEEE Symposium on Field-Programmable Custom Computing Machines[C].1998.
  • 10石教英,金哲凡.并行多边形绘制技术综述[J].计算机辅助设计与图形学学报,2003,15(6):637-642. 被引量:18

二级参考文献29

  • 1Montrym John S, Baum Daniel R, Dignam David L, et al. InfiniteReality: A real-time graphics system[A]. In: Computer Graphics Proceedings, Annual Conference Series, SIGGRAPH, Los Angeles, California, 1997. 293~302
  • 2Rudrajit Samanta, et al. Load balancing for multi-projector rendering systems[A]. In: Proceedings of the SIGGRAPH/EUROGRAPHICS Workshop on Graphics Hardware, Los Angeles, California, 1999. 107~116
  • 3Moll L, Shand Mark, Heirich Alan. Sepia: Scalable 3D compositing using PCI pamette[A]. In: Laurent Proceedings of the 7th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, Napa California, 1999. 146~157
  • 4Yang Jian, Shi Jiaoying, Jin Zhefan, et al. Design and implementation of a large-scale hybrid distributed graphics system[A]. In: Proceedings of Eurographics Workshop on Parallel Graphics and Visualization, Saarbruecken, Germany, 2002. 39~49
  • 5Matthew Eldridge, Homan Igehy, Pat Hanrahan. Pomegranate: A fully scalable graphics architecture[A]. In: Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH, New Orleans, Louisiana, 2000. 443~454
  • 6Owens John D, Dally William J, et al. Polygon rendering on a stream architecture[A]. In: Proceedings of the EUROGRAPHICS/SIGGRAPH Workshop on Graphics Hardware, Interlaken, Switzerland, 2000. 23~32
  • 7Olano Marc, Anselmo Lastra. A shading language on graphics hardware: The PixelFlow shading system[A]. In: Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH, Orlando, Florida, 1998. 159~168
  • 8Rudrajit Samanta, Thomas Funkhouser, Kai Li. Hybrid sort-first and sort-last parallel rendering with a cluster of PCs[A]. In: Proceedings of the SIGGRAPH/EUROGRAPHICS Workshop on Graphics Hardware, Interlaken, Switzerland, 2000. 97~108
  • 9Yang C, Sano B, Lebeck A R. Exploiting instruction level parallelism in geometry processing for three dimensional graphics applications[A]. In: Proceedings of the 31st Annual ACM/IEEE International Symposium on Microarchitecture, Dallas Texas, 1998. 14~24
  • 10Intel Corporation. Accelerated graphics port interface specification, Revision 2.0[OL]. Http://www.intel.com/technology/agp/agp index.htm, 1998

共引文献17

同被引文献6

  • 1彭浩宇,金哲凡,秦爱红,熊华,石教英.复式并行流水线在基于PC集群机的并行绘制中的应用[J].计算机辅助设计与图形学学报,2006,18(10):1581-1586. 被引量:5
  • 2Moloney B, Weiskopf D, Moiler T, et al. Scalable sort-first parallel direct volum rendering with dynamic load balancing [ C ]// Favre J M,Santos L P D, Reiners D. Eurographics Symposium on Parallel Graphics and Visualization. USA: A K Perters Ltd, 2007:45 - 52.
  • 3Molnar S, Cox M, Ellsworth D, et al. A sorting classification of parallel rendering [ J ]. IEEE Computer Graphics and Applications, 1994,14(4) :23 - 32.
  • 4Mueller C. The sort-first rendering architecture for high-performance graphics [ C ]//Zyda M. Symposium on Interactive 3D graphics. USA : ACM Press, 1995:75 - 84.
  • 5Abraham F,Celes W,Cerqueira R,et al. A load-balancing strategy for sort-first distributed rendering[ C ]//Remesh F. Proceedings of the Computer Graphics and Image Processing. USA : IEEE Computer Society,2004:292 - 299.
  • 6Hargreaves S. Deferred shading [ R/OL]. Santa Clara, CA: nVidia,2004 [ 2008 - 04 - 07 ]. http ://www. talula.demon. co. uk/DeferredShading. pdf.

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部