- VLSI Project
DARPA's VLSI Project provided research funding to a wide variety of university-based teams in an effort to improve the state of the artin microprocessordesign, then known as VLSI. Although little known, notably in comparison to their work on what became the internet, the VLSI Project is likely one of the most influential research projects in modern computer history. Its offspring include the RISCprocessor concept, many of the CADtools still in use today, 32-bitgraphics workstations, fabless design houses and its own fab, MOSIS. A similar DARPA project partnering with industry, VHSIC, is generally considered to have had little or no impact.
The Project was the brainchild of
Caltechprofessor Carver Meadand Xerox PARCprogrammer Lynn Conwayin the late 1970s. At the time microprocessor design was plateauing at the 100,000 transistorlevel because the tools available to the designers were simply unable to deal with more complex designs. 16-bitand 16/32-bit designs were coming to market, but beyond that seemed too difficult and expensive to contemplate. Mead and Conway felt that there was no theoretical problem impeding progress, simply a number of practical ones, and set about solving these in order to make much more complex designs possible.
One of the primary efforts under VLSI was the creation of the hardware and software needed to automate the design process, which at that point was still largely manual. For a design containing hundreds of thousands of transistors, there was simply no machine short of a
supercomputerthat had the memory and performance needed to work on the design as a whole.
In order to address this problem and allow the "average company" to use automated tools, VLSI funded the Geometry Engine and Pixel-Planes projects at
Stanford Universityand University of North Carolina at Chapel Hill(respectively) to create suitable graphics hardware at the desktop level. The former evolved into an effort to design a networked CAD workstation, known as the Stanford University Network. This is better known today under its acronym, "SUN", as in Sun Microsystems, which commercialized the design.
In order to provide a common "software" platform to run these new tools on, VLSI also funded a Berkeley project to provide a standardized
Uniximplementation, known today as the Berkeley Software Distribution. BSD was used on almost all early workstations, including the designs that would evolve into Sun, SGI, Apollo Computerand others. BSD would later spawn several descendants, OpenBSD, FreeBSDand NetBSD.
CAD software itself was an important part of the VLSI effort as well. This led to major improvements in CAD technology for layout, design rule checking, and simulation. The tools developed in this program were used extensively in both academic research programs and in industry. The ideas were developed in commercial implementations by companies such as
VLSI Technology, Cadnetix, and Synopsis.
With these tools in hand, other VLSI funded projects were able to make huge strides in design complexity, sparking off the RISC revolution. The two major VLSI-related projects were
Berkeley RISCand Stanford MIPS, both of which relied heavily on the tools developed in previous VLSI projects. In order to allow the design teams to produce test examples, the project also funded the building of their own fab, MOSIS ("Metal Oxide Semiconductor Implementation Service"), which received their plans electronically. MOSISremains in operation today.
Another important part of their fabbing process was the development of the multichip wafer, which allowed a single wafer of silicon to be used to produce several chip designs at the same time. Previously a wafer would normally be used to produce a single design, which meant that there was a definite minimum production run one could consider starting up. In contrast the multichip wafer a small batch of a chip could be produced in the middle of a larger run, dramatically lowering the startup cost and prototyping stage.
Direct outcomes of the VLSI Project
Sun Microsystemswas an offshoot of the Stanford SUN workstation project
SGI's workstation design was based on the Geometry Engine concept
Pixel-Planes, PixelFlowand WarpEngineseries of parallel processorgraphics workstations
*Berkeley's RISC turned into
SPARCat Sun Micro
*Stanford's MIPS continues to this day at SGI and many embedded applications such as set-top boxes.
*BSD Unix and its derivatives remain a popular system
* [http://www.nap.edu/readingroom/books/hpcc/box1.2.html The ARPA VLSI Program]
* [http://accad.osu.edu/~waynec/history/PDFs/geometry-engine.pdf The Geometry Engine: A VLSI Geometry System for Graphics]
* [http://www.cs.unc.edu/~pxfl/ The Pixel-Planes Group]
Wikimedia Foundation. 2010.