Memory architecture for efficient utilization of SDRAM: a case study of the computation/memory access trade-off

ABSTRACT

This paper discusses the trade-off between calculations and memory accesses in a 3D graphics tile renderer for visualization of data from medical scanners. The performance requirement of this application is a frame rate of 25 frames per second when rendering 3D models with 2 million triangles, i.e. 50 million triangles per second, sustained (not peak). At present, a software implementation is capable of 3-4 frames per second for a 1 million triangle model.By using direct evaluation of certain interpolation parameters instead of forward differencing, writing back parameters to SDRAM is avoided. In software, forward differencing is usually better, but in this hardware implementation, the trade-off has made it possible to develop a very regular memory architecture with a buffering system, which can reach 95% bandwidth utilization using off-the-shelf SDRAM. This is achieved by changing the algorithm to use a memory access strategy with write-only and read-only phases, and a buffering system, which uses round-robin bank write-access combined with burst read-access.

REFERENCES

• 1: James D. Foley , Andries van Dam , Steven K. Feiner , John F. Hughes, Computer graphics: principles and practice (2nd ed.), Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1990
• 2: Thomas Gleerup, "ASIC for 3D Graphics Pipeline Back-End, Master's Thesis, Technical University of Denmark, Dept. of Information Technology, Lyngby, Denmark, 1999.
• 3: Hans Holten-Lund , Mogens Hvidtfeldt , Jan Madsen , Steen Pedersen, VRML visualization in a surgery planning and diagnostics application, Proceedings of the fifth symposium on Virtual reality modeling language (Web3D-VRML), p.111-118, February 20-24, 2000, Monterey, California, United States [doi>10.1145/330160.330234]
• 4: Hans Holten-Lund, Jan Madsen and Steen Pedersen, "A Case Study of a Hybrid Parallel 3D Surface Rendering Graphics Architecture, SASIMI 1997 Proceedings.
• 5: Hybris software renderer, http://www'it'dtu'dk/Nhahl/hybris'html'
• 6: Michael Kelley , Stephanie Winner , Kirk Gould, A scalable hardware render accelerator using a modified scanline algorithm, Proceedings of the 19th annual conference on Computer graphics and interactive techniques, p.241-248, July 1992
• 7: William E. Lorensen , Harvey E. Cline, Marching cubes: A high resolution 3D surface construction algorithm, ACM SIGGRAPH Computer Graphics, v.21 n.4, p.163-169, July 1987
• 8: Micron Technology Inc., "Synchronous DRAM Data Sheet, 64Mb SDRAM, rev. 10/98, Micron Technology Inc., 1998.
• 9: The Stanford 3D Scanning Repository, http://wwwgraphics, stanford.edu/data/3 Dscanrep/.

INDEX TERMS

Primary Classification:
  B. Hardware
  B.3 MEMORY STRUCTURES

Additional Classification:
  J. Computer Applications

General Terms:
Human Factors, Management, Performance

Keywords:
3D graphics, case study, memory architecture