论文信息 - BREAKING THE FRAMEBUFFER BOTTLENECK : THE CASE FOR LOGIC-ENHANCED MEMORIES

BREAKING THE FRAMEBUFFER BOTTLENECK : THE CASE FOR LOGIC-ENHANCED MEMORIES

A central problem in designing interactive graphics systems is the bandwidth bottleneck between the rasterizer, the engine that computes pixel values for each primitive in a scene, and the frame buffer, the memory system that stores pixel values. Despite remarkable advances in semiconductor storage, this problem not only is still with us, but increasingly is the barrier to further improvements in interactive systems. Current highend graphics systems are approaching performance limits imposed by the design of commercial DRAMs.

Henry Fuchs | Steven Molnar | John Eyles | John Poulton

[1] T. F. Knight,et al. A self-terminating low-voltage swing CMOS output driver , 1988 .

[2] John G. Eyles,et al. PixelFlow: high-speed rendering using image composition , 1992, SIGGRAPH.

[3] Andy Goris,et al. A Configurable Pixel Cache for Fast Image Generation , 1987, IEEE Computer Graphics and Applications.

[4] Neil Hunt,et al. The triangle processor and normal vector shader: a VLSI system for high performance graphics , 1988, SIGGRAPH.

[5] Satish Gupta,et al. Subanosecond pixel rendering with million transistor chips , 1988, SIGGRAPH.

[6] Brian Apgar,et al. A display system for the Stellar graphics supercomputer model GS1000 , 1988, SIGGRAPH.

[7] Don Speck. The Mosaic fast 512K scalable CMOS dRAM , 1991 .

[8] Henry Fuchs,et al. Pixel-planes 5: a heterogeneous multiprocessor graphics system using processor-enhanced memories , 1989, SIGGRAPH.

[9] Henry Fuchs,et al. Pixel-Planes 4: A Summary , 1987, Advances in Computer Graphics Hardware.

[10] Henry Fuchs,et al. Distributing a visible surface algorithm over multiple processors , 1977, ACM '77.

[11] Ulrich Neumann,et al. Parallel Architectures and Algorithms for Real-Time Synthesis of High Quality Images Using Deferred Shading , 1989 .