A Hierarchical Triangle-Level Culling Technique for Tile-Based Rendering

Current 3D graphics rendering relies on tens of thousand triangles to generate realistic images on screen. As the number of triangles increases, no specific order for their input sequence exists, thus, many triangles that do not contribute to a final image must still be rasterized and shaded. This study proposes a triangle-level hierarchical culling technique for tile-based rendering. With a novel hardware efficient technique focuses on the depth and coverage relationships among triangles, the invisible triangles can now be culled right after geometry stage. Intended advantages include: cull invisible triangles earlier, reduce storage pressure, reduce triangle and list data accesses (from external memory) during rendering. The results show the proposed mechanism culls 32.99% of triangles before rasterization. In addition, about 15% of storage requirements and external memory transfer are reduced as well.

[1]  S. Morein.  Ati radeon hyperz technology , 2000 .

[2]  Carlos González,et al.  ATTILA: a cycle-level execution-driven simulator for modern GPU architectures , 2006, 2006 IEEE International Symposium on Performance Analysis of Systems and Software.

[3]  Feng Xie,et al.  Adaptive hierarchical visibility in a tiled architecture , 1999, Workshop on Graphics Hardware.

[4]  Lee-Sup Kim,et al.  A hierarchical depth buffer for minimizing memory bandwidth in 3D rendering engine: Depth Filter , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[5]  Gavin S. P. Miller,et al.  Hierarchical Z-buffer visibility , 1993, SIGGRAPH.

[6]  Alan Watt,et al.  3D Computer Graphics , 1993 .

[7]  Lee-Sup Kim,et al.  Triangle-Level Depth Filter Method for Bandwidth Reduction in 3D Graphics Hardware , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[8]  Stamatis Vassiliadis,et al.  GRAAL: A Framework for Low-Power 3D Graphics Accelerators , 2008, IEEE Computer Graphics and Applications.

[9]  Chen-Yi Lee,et al.  Two-level hierarchical Z-Buffer for 3D graphics hardware , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[10]  Thomas H. Cormen,et al.  Introduction to algorithms [2nd ed.] , 2001 .

[11]  Chung-Ping Chung,et al.  A Hierarchical Primitive Lists Structure for Tile-Based Rendering , 2009, 2009 International Conference on Computational Science and Engineering.

[12]  Tomas Akenine-Möller,et al.  Graphics for the masses: a hardware rasterization architecture for mobile phones , 2003, ACM Trans. Graph..

[13]  Xiaohong Jiang,et al.  CoarseZ Buffer Bandwidth Model in 3D Rendering Pipeline , 2006, First International Multi-Symposiums on Computer and Computational Sciences (IMSCCS'06).