Michael Deering
Abstract
Current affordable architectures for high-speed display of shaded 3D objects operate orders of magnitude too slowly. Recent advances in floating point chip technology have outpaced polygon fill time, making the memory access bottleneck between the drawing processor and the frame buffer the most significant factor to be accelerated. Massively parallel VLSI system have the potential to bypass this bottleneck, but to date only at very high cost. We describe a new more affordable VLSI solution. A pipeline of triangle processors rasterizes the geometry, then a further pipeline of shading processors applies Phong shading with multiple light sources. The triangle processor pipeline performs 100 billion additions per second, and the shading pipeline performs two billion multiplies per second. This allows 3D graphics systems to be built capable of displaying more than one million triangles per second. We show the results of an anti-aliasing technique, and discuss extensions to texture mapping, shadows, and environment maps.
- 1 Gary Bishop and David M. Weimer. Fast Phong shading. Proceedings of SIGGRAPH'86 (Dallas, Texas, August 18-22, 1986). In Computer Graphics, pages 103-106, 1986. Google Scholar
Digital Library
- 2 James. H. Clark. The geometry engine, a VLSI geometry system for graphics. Proceedings of SIC- GRAPH'82 (Boston, Massachusetts, July 26-30, 1982). In Computer Graphics, pages 127-133, 1982. Google ScholarDigital Library
- 3 Robert. L. Cook. Stochastic sampling in computer graphics. A CM Transactions on Computer Graphics, 5(1):51-72, January 1986. Google ScholarDigital Library
- 4 Stefan Demetreseu. High speed image rasterizatlon using scan llne access memories. In 1985 Chapel Hill Conference on Very .Large Scale Integration, pages 221-243, Computer Science Press, 1985.Google Scholar
- 5 Henry Fuchs and John Poulton. Pixel-planes: a VLSI-oriented design for a raster graphics engine. VLSI Design, 2(3):20-28, 1981.Google Scholar
- 6 Nader Gharachorloo and Christopher Pottle. SUPER BUFFER: a systolic VLSI graphics engine for real time raster image generation. In 1985 Chapel Hill Conference on Very Large Scale Integration, pages 285-305, Computer Science Press, 1985.Google Scholar
- 7 Paul S. Heckbert. Survey of texture mapping. IEEE Computer Graphics and Applications, 6(11):56- 67, November 1986. Google ScholarDigital Library
- 8 Adam Levinthal and Thomas Porter. Chap - a SIMD graphics processor. Proceedings of SIC- GRAPH'84 (Minneapolis, Minnesota, July 23-27, 1984). In Computer Graphics, pages 77-82, 1984. Google ScholarDigital Library
- 9 Leonard MeMillan. Graphics at 820 MFLOPS. ESD: THE Electronic Systems Design Magazine, 17(9):87-95, September 1987.Google Scholar
- 10 Teiji Nishlzawa et al. A hidden surface processor for 3-dimension graphics. In Proceedings of ISSCC'88, pages 166-167,351, 1988.Google Scholar
- 11 John Poulton et al. PIXEL-PLANES: building a VLSI-based graphic system. In 1985 Chapel Hill Conference on Very Large Scale Integratlon, pages 35-60, Computer Science Press, 1985.Google Scholar
- 12 William T. Reeves, David H. Salesin, and Robert L. Cook. Rendering antialiased shadows with depth maps. Proceedings of SIGGRAPH'87 (Anaheim, California, July 27-31, 1987). In Computer Graphics, pages 283-291, 1987. Google ScholarDigital Library
- 13 Roger W. Swanson and Larry J. Thayer. A fast shaded-polygon renderer. Proceedings of SIG- GRAPH'86 (Dallas, Texas, August 18-22, 1986). In Computer Graphics, pages 95-101, 1986. Google ScholarDigital Library
- 14 John G. Torborg. A parallel processor architecture for graphics arithmetic operations. Proceedings of SIGGRAPH'87 (Anaheim, California, July 27-31, 1987). In Computer Graphics, pages 197-204, 1987. Google ScholarDigital Library
- 15 Andries van Dam et al. PHIGS+ functional description rev. 2.0. July 20 1987. Jointly developed PHIGS+ specification.Google Scholar
Index Terms
- The triangle processor and normal vector shader: a VLSI system for high performance graphics
Recommendations
An improved illumination model for shaded display
To accurately render a two-dimensional image of a three-dimensional scene, global illumination information that affects the intensity of each pixel of the image must be known at the time the intensity is calculated. In a simplified form, this ...
The triangle processor and normal vector shader: a VLSI system for high performance graphics
SIGGRAPH '88: Proceedings of the 15th annual conference on Computer graphics and interactive techniquesCurrent affordable architectures for high-speed display of shaded 3D objects operate orders of magnitude too slowly. Recent advances in floating point chip technology have outpaced polygon fill time, making the memory access bottleneck between the ...
VLSI drawing processor utilizing multiple parallel scan-line processors
EGGH'87: Proceedings of the Second Eurographics conference on Advances in Computer Graphics HardwareIn a typical graphics system, a single drawing processor is used to perform pixel level drawing operations, one pixel at a time. A VLSI based drawing processor and image memory controller is presented which takes advantage of scan-line partitioning of ...
Comments