260:
minimum feature size possible using that process, which became known as λ (the Greek letter lambda). λ was set to be one half of the minimum width of a line of POLY or DIFF, and the rules expressed in those terms; "a line has to be two λ wide", "two lines on the same layer must be at least three λ apart", "lines on different layers must be one λ apart" and so forth. The end result was a short set of design rules that applied at any scale. Conway later noted "I vividly recall seeing Mead's jaw drop that spring morning in 1977 as I presented my strategy for λ-based rules on my whiteboard at PARC."
22:
256:
are closer than 2 micrometers apart". Dozens of such rules were developed for each layer to squeeze out maximum performance. In early 1977, Conway began developing a new set of completely generic rules. These would not offer the highest performance possible for any given system, but her concept was that it would so greatly reduce design time that it could be adapted to a new underling fabrication technology with little or no changes, and such a move would offer many times the performance benefit that using every published trick of the existing rules would.
385:, 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 design could be produced in the middle of a larger run, dramatically lowering the startup cost and prototyping stage.
259:
Starting with three colored whiteboard pens representing each of the types of layers, MET, POLY, DIFF, Conway developed a set of design rules that worked on every current process. Further development led to the realization that all of the dimensions could be expressed as multiples of some fundamental
205:
noted that the scale shrinking that formed the basis of Moore's law also affected the performance of the systems. These combined effects implied a massive increase in computing power was about to be unleashed on the industry. The report, published in 1976, suggested that ARPA fund development across
255:
The mid-1970s were a period of rapid change as new processes were being introduced at different companies at a rapid pace. Each new process led to a set of design rules that often ran to 40 pages. These would include details like "do not place to parallel lines on the metallization layer (MET) that
247:
and 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
346:
CAD software was an important part of the VLSI effort. 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
268:
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
584:
DARPA's VLSI program built upon these early efforts. Formally initiated by Robert Kahn in 1978, the DARPA program grew out of a study it commissioned at RAND Corporation in 1976 to evaluate the scope of research DARPA might support in VLSI (Sutherland,
248:
possible. Simply put, the solution was to simplify everything, inventing new practical rules-of-thumb for designers and applying computers to the problems that were larger. This process was aided by the recent introduction of depletion mode
229:
systems used on larger systems as the feature sizes shrank and
Dennard's speed predictions kicked in. It also implied that the entire ACS-1 mainframe would one day fit on a single chip. In 1976, Sutherland and Mead wrote an article in
366:, both of which relied heavily on the tools developed in previous VLSI projects. To allow design teams to produce test examples, the project also funded the building of their own fabrication facility,
358:
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
292:(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
488:
496:
492:
289:
352:
206:
a number of fields in order to deal with the complexity that was about to appear due to these "very-large-scale integrated circuits".
789:
570:
218:
213:. He suggested a joint effort between PARC and Caltech to begin studying these issues. Bert agreed to form a team, inviting
726:
394:
774:
Evolving the High
Performance Computing and Communications Initiative to Support the Nation's Information Infrastructure
618:
186:
65:
43:
109:
The VLSI Project is one of the most influential research projects in modern computer history. Its offspring include
36:
118:
138:
531:
316:
110:
861:
866:
103:
243:
level because the tools available to the designers were simply unable to deal with more complex designs.
276:
To address this problem, and thereby allow "average" companies to use automated tools, VLSI funded the
153:
817:
217:
and Doug
Fairbairn to join. Conway had previously worked at IBM on a supercomputer project known as
30:
812:
603:
Proceedings First IEEE International
Workshop on Electronic Design, Test and Applications '2002
311:
platform to run these new tools, VLSI also funded a
Berkeley project to provide a standardized
209:
Later that year, Sutherland wrote a letter to his brother Bert who was at that time working at
174:
47:
432:
226:
134:
122:
769:
8:
423:
285:
232:
189:
on the topic of microelectronics. Over the previous few years, Mead had coined the term "
319:(BSD). Almost all early workstations used BSD, including designs that evolved into Sun,
830:
749:
624:
500:
482:
417:
785:
614:
566:
408:
834:
628:
822:
800:
777:
770:"Box 1.2 An example of a Successful Federal R&D Program: The ARPA VLSI Program"
753:
741:
606:
558:
517:
478:
450:
404:
381:
Another important part of the MOSIS fabrication process was the development of the
320:
301:
221:. After considering the notes from Mead, Conway realized that the rapid scaling of
95:
473:
456:
441:
348:
324:
178:
856:
446:
437:
198:
190:
99:
745:
640:
MOSIS was started in 1981 by the U.S. Defense
Advanced Research Program Agency
610:
598:
850:
522:
509:
398:
363:
359:
273:
that had the memory and performance needed to work on the design as a whole.
270:
413:
340:
194:
826:
526:
504:
214:
170:
130:
252:, which greatly simplified the conceptual model of the active elements.
428:
249:
240:
210:
91:
145:, starting in 1981. A similar DARPA project partnering with industry,
552:
197:'s 1965 prediction for the growth rate of complexity, and in 1974,
87:
781:
562:
332:
328:
297:
239:
At the time, microprocessor design was plateauing at the 100,000
182:
841:
554:
Funding a
Revolution: Government Support for Computing Research
336:
244:
225:
being predicted would allow it to surpass the otherwise faster
126:
513:
469:
375:
146:
142:
83:
90:
in 1978 that provided research funding to a wide variety of
312:
222:
114:
801:"The Geometry Engine: A VLSI Geometry System for Graphics"
767:
202:
463:
327:, and others. BSD later spawned several descendants,
692:
690:
677:
675:
662:
660:
702:
236:on the challenges presented by the new complexity.
687:
672:
657:
645:
599:"Evolution of the MOSIS VLSI educational program"
848:
372:Metal Oxide Semiconductor Implementation Service
347:commercial implementations by companies such as
525:are used in many embedded applications such as
152:The VLSI Project was central in promoting the
534:and its derivatives remain a popular system
290:University of North Carolina at Chapel Hill
816:
263:
94:-based teams in an effort to improve the
66:Learn how and when to remove this message
776:. National Academies Press. p. 19.
374:), which received plans electronically.
29:This article includes a list of general
590:
481:'s workstation design was based on the
296:. This is better known today under its
849:
727:"Reminiscences of the VLSI Revolution"
724:
708:
696:
681:
666:
651:
798:
596:
15:
464:Direct outcomes of the VLSI Project
315:implementation, known today as the
304:, which commercialized the design.
164:
13:
768:National Research Council (1995).
734:IEEE Solid-State Circuits Magazine
35:it lacks sufficient corresponding
14:
878:
761:
557:. National Academy Press. 1999.
472:was an offshoot of the Stanford
388:
125:(CAD) tools still in use today,
119:reduced instruction set computer
20:
718:
459:, Caesar and Magic design tools
139:semiconductor fabrication plant
137:and design houses, and its own
121:(RISC) processor concept, many
545:
317:Berkeley Software Distribution
111:Berkeley Software Distribution
1:
597:Pina, C. A. (7 August 2002).
538:
378:remains in operation today.
104:Very Large Scale Integration
7:
294:Stanford University Network
10:
883:
799:Clark, James (July 1982).
725:Conway, Lynn (Fall 2012).
159:
154:Mead and Conway revolution
746:10.1109/MSSC.2012.2215752
611:10.1109/DELTA.2002.994612
149:had little or no impact.
483:Geometry Engine concept
474:SUN workstation project
50:more precise citations.
842:The Pixel-Planes Group
264:Internet based process
102:design, then known as
86:-program initiated by
827:10.1145/965145.801272
156:throughout industry.
135:fabless manufacturing
123:computer-aided design
862:History of computing
605:. pp. 187–191.
307:To provide a common
867:Integrated circuits
286:Stanford University
233:Scientific American
185:wrote a report for
501:parallel processor
418:Connection Machine
805:Computer Graphics
791:978-0-309-05277-1
572:978-0-309-06278-7
409:MIPS architecture
76:
75:
68:
874:
838:
820:
795:
757:
731:
712:
706:
700:
694:
685:
679:
670:
664:
655:
649:
643:
642:
637:
635:
594:
588:
587:
581:
579:
549:
518:Sun Microsystems
479:Silicon Graphics
405:John L. Hennessy
355:, and Synopsis.
302:Sun Microsystems
165:New design rules
96:state of the art
71:
64:
60:
57:
51:
46:this article by
37:inline citations
24:
23:
16:
882:
881:
877:
876:
875:
873:
872:
871:
847:
846:
818:10.1.1.359.8519
792:
764:
729:
721:
716:
715:
707:
703:
695:
688:
680:
673:
665:
658:
650:
646:
633:
631:
621:
595:
591:
577:
575:
573:
551:
550:
546:
541:
466:
457:John Ousterhout
442:Geometry Engine
422:Charles Seitz,
395:David Patterson
391:
383:multichip wafer
349:VLSI Technology
325:Apollo Computer
300:, "SUN", as in
278:Geometry Engine
266:
179:Ivan Sutherland
167:
162:
72:
61:
55:
52:
42:Please help to
41:
25:
21:
12:
11:
5:
880:
870:
869:
864:
859:
845:
844:
839:
811:(3): 127–133.
796:
790:
763:
762:External links
760:
759:
758:
720:
717:
714:
713:
701:
686:
671:
656:
644:
619:
589:
571:
543:
542:
540:
537:
536:
535:
529:
520:
507:
485:
476:
465:
462:
461:
460:
454:
447:Forest Baskett
444:
435:
426:
420:
411:
402:
390:
387:
265:
262:
199:Robert Dennard
193:" to describe
166:
163:
161:
158:
100:microprocessor
74:
73:
56:September 2020
28:
26:
19:
9:
6:
4:
3:
2:
879:
868:
865:
863:
860:
858:
855:
854:
852:
843:
840:
836:
832:
828:
824:
819:
814:
810:
806:
802:
797:
793:
787:
783:
782:10.17226/4948
779:
775:
771:
766:
765:
755:
751:
747:
743:
739:
735:
728:
723:
722:
711:, p. 10.
710:
705:
698:
693:
691:
683:
678:
676:
668:
663:
661:
653:
648:
641:
630:
626:
622:
620:0-7695-1453-7
616:
612:
608:
604:
600:
593:
586:
574:
568:
564:
563:10.17226/6323
560:
556:
555:
548:
544:
533:
530:
528:
527:set-top boxes
524:
523:Stanford MIPS
521:
519:
515:
511:
510:Berkeley RISC
508:
506:
502:
498:
494:
490:
486:
484:
480:
477:
475:
471:
468:
467:
458:
455:
452:
448:
445:
443:
439:
436:
434:
430:
427:
425:
421:
419:
415:
412:
410:
406:
403:
401:RISC I and II
400:
399:Berkeley_RISC
396:
393:
392:
389:Investigators
386:
384:
379:
377:
373:
369:
365:
364:Stanford MIPS
361:
360:Berkeley RISC
356:
354:
350:
344:
342:
338:
334:
330:
326:
322:
318:
314:
310:
305:
303:
299:
295:
291:
287:
283:
279:
274:
272:
271:supercomputer
261:
257:
253:
251:
246:
242:
237:
235:
234:
228:
224:
220:
216:
212:
207:
204:
200:
196:
192:
188:
184:
180:
176:
172:
157:
155:
150:
148:
144:
140:
136:
132:
128:
124:
120:
116:
112:
107:
105:
101:
97:
93:
89:
85:
81:
70:
67:
59:
49:
45:
39:
38:
32:
27:
18:
17:
808:
804:
773:
740:(44): 8–31.
737:
733:
719:Bibliography
704:
699:, p. 8.
684:, p. 7.
669:, p. 6.
654:, p. 5.
647:
639:
634:17 September
632:. Retrieved
602:
592:
583:
578:17 September
576:. Retrieved
553:
547:
512:turned into
505:workstations
489:Pixel-Planes
414:Danny Hillis
382:
380:
371:
367:
357:
345:
341:DragonFlyBSD
308:
306:
293:
284:projects at
282:Pixel-Planes
281:
277:
275:
267:
258:
254:
238:
231:
208:
195:Gordon Moore
175:Tom Everhart
168:
151:
131:workstations
108:
80:VLSI Project
79:
77:
62:
53:
34:
709:Conway 2012
697:Conway 2012
682:Conway 2012
667:Conway 2012
652:Conway 2012
424:Cosmic Cube
215:Lynn Conway
191:Moore's law
171:Carver Mead
88:Robert Kahn
48:introducing
851:Categories
539:References
499:series of
497:WarpEngine
453:networking
429:H. T. Kung
250:NMOS logic
241:transistor
211:Xerox PARC
92:university
31:references
813:CiteSeerX
503:graphics
493:PixelFlow
438:Jim Clark
169:In 1975,
129:graphics
835:10223583
629:35695273
532:BSD Unix
353:Cadnetix
309:software
106:(VLSI).
754:9286356
333:FreeBSD
329:OpenBSD
298:acronym
183:Caltech
160:Project
141:(fab),
44:improve
833:
815:
788:
752:
627:
617:
585:1976).
569:
487:UNC's
339:, and
337:NetBSD
245:16-bit
127:32-bit
117:, the
113:(BSD)
82:was a
33:, but
857:DARPA
831:S2CID
750:S2CID
730:(PDF)
625:S2CID
514:SPARC
470:Sun-1
376:MOSIS
368:MOSIS
219:ACS-1
147:VHSIC
143:MOSIS
84:DARPA
786:ISBN
636:2020
615:ISBN
580:2020
567:ISBN
495:and
433:WARP
362:and
313:Unix
288:and
280:and
223:CMOS
187:ARPA
177:and
115:Unix
78:The
823:doi
778:doi
742:doi
607:doi
559:doi
516:at
451:SUN
321:SGI
227:ECL
203:IBM
201:of
181:of
98:in
853::
829:.
821:.
809:16
807:.
803:.
784:.
772:.
748:.
736:.
732:.
689:^
674:^
659:^
638:.
623:.
613:.
601:.
582:.
565:.
491:,
449:,
440:,
431:,
416:,
407:,
397:,
351:,
343:.
335:,
331:,
323:,
173:,
133:,
837:.
825::
794:.
780::
756:.
744::
738:4
609::
561::
370:(
69:)
63:(
58:)
54:(
40:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.