Pixel-Planes 4: A Summary

Eyles, John; Fuchs, Henry; Greer, Trey; Poulton, Joanna; Austin, John

doi:10.21236/ada201090

Cited by 2 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Easy to program, and with delivered performance (-35,000 shaded triangles/sec) still comparable to high-end systems, it has become the workhorse of our graphics research program [5].…”

Section: Pixel-planes Projectmentioning

confidence: 99%

Building Microelectronic Systems in a University Environment

Poulton¹

1990

Self Cite

View full text Add to dashboard Cite

q0qo I/ Invited PresentationThis paper describes a ten-year-long technical and social experiment in our department to build a laboratory that designs and fabricates microelectronic systems in support of research in computer architecture. This experiment has been fairly successful by several measures: We have built and demonstrated a number of systems, some of significant size and complexity, spanning a fairly wide range of approaches and applications. We have validated the laboratory's original premise, demonstrating economies of scale by sharing a system-building facility over multiple projects. Most importantly, we have fielded experimental systems on a long-term, maintainable basis. Our Microelectronic Systems Laboratory (MSL) may serve as a useful model for others who want to develop system-building capability in a university setting. III describe the model in three parts:I. An outline of the context, purpose, organization, and working style of the lab, along with a brief chronology and description of the experimental systems we have built. Laboratory ModelThe MSL exists within the Computer Science department at UNC, so a few words about the department are needed to understand the lab's context. It is relatively small (currently 22 faculty and 120 graduate students) and is primarily involved in graduate education and research. There are no undergraduate majors, though about 30 Math BS's graduate each year with a computer science concentration. The department does first-class research in interactive computer graphics and is also fairly strong in microelectronic design, natural 0 language processing, programming languages, and functional languages and machines. Founded as an autonomous department, it is not associated, for example, with electrical engineering (there are no traditional engineering curricula at Chapel Hill).Fred Brooks, the department's founder, has strongly stamped the its research style. Experimental computer science is emphasized; several groups have built complete, full-scale systems and put them in the hands of users, typically from outside the department and often outside computer science. Brooks measures success by asking questions such as, "Does the system allow users to produce useful, publishable results tON SATMNrV A Apzoved tot public thlons" 2 91 IL 10

show abstract

“…Easy to program, and with delivered performance (-35,000 shaded triangles/sec) still comparable to high-end systems, it has become the workhorse of our graphics research program [5].…”

Section: Pixel-planes Projectmentioning

confidence: 99%

Building Microelectronic Systems in a University Environment

Poulton¹

1990

Self Cite

View full text Add to dashboard Cite

show abstract

“…[Apgar88], the Iris 4D/70GT [Akeley88], Ardent Titan, and Pixel-planes [Eyles87], but suffers from decreasing returns as it is extended further and further. In all of these schemes clock speeds and bandwidth into frame buffer memory place strangleholds on maximum possible performance, regardless of the number of processors.…”

Section: Parallelismmentioning

confidence: 99%

“…Supersampling produces images of uniformly high quality, but at great computational expense; an image with N samples per pixel takes N times as long to render as a simple image. [Fuchs85] and [Eyles87] present a way to supersample an image in incremental fashion, presenting the raw image first at full speed, then refining it by performing a weighted average with further samples. This is done for as long as the image remains stationary.…”

Section: Surfacementioning

confidence: 99%

“…Transparency is difficult to handle in a z-buffer system since rendering transparent objects requires primitives to be sorted and rendered in order. One method to approximate transparency is to use a random screen to disable pixels on a transparent object This technique has been implemented on Pixel-planes 4 [Eyles87]. It can be annoying because it adds noise to the image, but the noise becomes less objectionable after a number of uncorrelated images have been averaged together, which occurs in the above antialiasing scheme.…”

Section: Transparencymentioning

confidence: 99%

“…A prototype for such a general purpose frame buffer/ALU exists: the UNC Pixel-planes system [Eyles87]. Pixel-planes contains a 512x512 frame buffer built of custom VLSI chips.…”

Section: End Of Frame Calculationsmentioning

confidence: 99%

See 2 more Smart Citations

Combining Z-buffer Engines for Higher-Speed Rendering

Molnár¹

1988

View full text Add to dashboard Cite

Described is a hardware architecture for combining the outputs of a number of zbuffer rendering engines to achieve higher performance than is possible with a single renderer. It allows a combination of renderers to achieve the same price/performance ratio as the individual renderers that compose it, and can be extended to create systems with arbitrarily high performance. The described architecture is based on a fusion of scan-line rendering and the conventional z-buffer algorithm. The frame buffers of several z-buffer engines are modified to scan out z-values as well as color values. Multiplexing devices combine the zlcolor streams from each pair of frame-buffers. These z/color streams are then combined by further multiplexers, creating a binary tree that funnels the z/color information from the many conventional frame buffers into a single z/color stream. The color stream is then used to drive a standard display device. The proposed architecture allows rendering rates of millions and even tens of millions of polygons per second. The basic architecture can b9 extend-d with additional hardware to perform antialiasing and texture-mapping. (,

show abstract

Pixel-Planes 4: A Summary

Cited by 2 publications

References 4 publications

Building Microelectronic Systems in a University Environment

Building Microelectronic Systems in a University Environment

Combining Z-buffer Engines for Higher-Speed Rendering

Contact Info

Product

Resources

About