Description of document National Security Agency NSA report General and Special-Purpose Computers a Historical Look and Some Lessons Learned 1986 Requested date 15-June-2009 Released date 29-June-2010 Posted date 19-October-2010 Source of document National Security Agency ATTN FOIA Office DJP4 9800 Savage Road STE 6248 Ft George G Meade MD 20755-6248 Fax 443-479-3612 Online request form The governmentattic org web site “the site” is noncommercial and free to the public The site and materials made available on the site such as this file are for reference only The governmentattic org web site and its principals have made every effort to make this information as complete and as accurate as possible however there may be mistakes and omissions both typographical and in content The governmentattic org web site and its principals shall have neither liability nor responsibility to any person or entity with respect to any loss or damage caused or alleged to have been caused directly or indirectly by the information provided on the governmentattic org web site or in this file The public records published on the site were obtained from government agencies using proper legal channels Each document is identified as to the source Any concerns about the contents of the site should be directed to the agency originating the document in question GovernmentAttic org is not responsible for the contents of documents published on the website NATIONAL SECURITY AGENCY CENTRAL SECURITY SERVICE FORT GEORGE G MEADE MARYLAND 20755-6000 Serial MDR-59141 29 June 2010 This responds to your request of 15 June 2009 to have a 1986 report by Douglas Hogan entitled General and Special-Purpose Computers a Historical Look and Some Lessons Learned reviewed for declassification The material has been reviewed under the Mandatory Declassification Review MDR requirements of Executive Order E O 12958 as amended and is enclosed We have determined that some of the information in the material requires protection Some portions deleted from the document were found to be currently and properly classified in accordance with E O 12958 as amended The information denied meets the criteria for classification as set forth in Section 1 4 subparagraph c and remains classified TOP SECRET SECRET and CONFIDENTIAL as provided in Section 1 2 of E O 12958 as amended Section 3 5 cl of E O 12958 as amended allows for the protection afforded to information under the provisions of law Therefore the names of NSA CSS employees and information that would reveal NSA CSS functions and activities have been protected in accordance with Section 6 Public Law 86-36 50 U S Code 402 note In addition information regarding other individuals has been deleted from the enclosure in accordance with the sixth exemption of the Freedom of Information Act This exemption protects from disclosure information that would constitute a clearly unwarranted invasion of personal privacy In balancing the public interest for the information you request against the privacy interests involved we have determined that the privacy interests sufficiently satisfy the requirements for the application of the sixth exemption Since your request for declassification has been partially denied you are hereby advised of this Agency's appeal procedures The Initial Denial Authority for NSA is the Deputy Associate Director for Policy and Records Diane M Janosek Any person denied access to information may file an appeal to the NSA CSS MDR Appeal Authority_ The appeal must be postmarked no later than 60 calendar days after the date of the denial letter The appeal shall be in writing addressed to the NSA CSS MDR Appeal Authority DJP5 National security Agency 9800 Savage Road STE 6884 Fort George G Meade MD 20755-6884 The appeal shall reference the initial denial of access and shall contain in sufficient detail and particularity the grounds upon which the requester believes the release of information is required The NSA CSS MDR Appeal Authority will endeavor to respond to the appeal within 60 working days after receipt of the appeal Sincerely M YJIi P1 l L KRISTINA M GREIN Chief Declassification Services Encl a s p • ' f ' a I 23 May 96 l -' one LJ k-ru AND SPECIAL PURPOSE COMPUTERS A HISTORICAL LOOK AND SOME LESSONS LEARNED INTRODUCTION 1 0 1' 1 86-36 EO 1 4 c I U This Research paper Center of has been written for thQ Institute for I the Qefense ' Oi l _r 0 ' SH t1 Purpose 1 1 Ib - · C L' IUAIl « 3B ____ OI'-LlBI J 1 _ __ Supercomputing Anal y es ' purpose is to explore the interaction between NSA's needs as pressed the limits of computing computing technology in the two In marit y systems it This computers • and in c oro linatior s of the the context of this paper the term that Of archi tecture and operating past technology was Qmployed in general purpose in spacial l po omputing systams It hardware I techn logy software and specialized languages are is pri- including dei'erred for another paper I The ------------------------------ areas addressed in this paper are not intended to provide an exhaustive or histor and rather detailed they have been selected to bring out key idees lessons learned which are in their mission int nded to be of value to IDA-SRC F 7ec Tla s' S 'if '-'ie 'd a ' n d- a ' p- 'p - ro v 'e- t 'J 'dfo- r- re le a - s - e b Y ' N S 'AlI 'o-n O '6- 'J 2 g -2 O ' 1' l O 'p u 'rs u a-n 'tt- o fdA R 59141 23 May 86 1 2 ORGANIZATION OF THE PAPER U In aggregating material for this paper it became evident that there was' no simple to organize the single material or truly logical way in which A number of different dimensions needed to be explored and a heterogeneous organization seemed to be appropriate Accordingly the paper is organized as follows TS Section 2 contains three case studies which are sentative 9f three kinds of activity 20 years from 1950 to 1970 ti luing attempt which needed The first spanning about describes what was in effect a con- to to obtain the maximum gene l handling abilities purpo e It includes the plans for NOMAD a level of technology that as not yet and the eventual development of HARVEST technology repre- at its maximum limit a data system 1 available a system which utilized The second case study deals with the series of machine aids that have been brought to bear on the These aids have been 1n the form of both special and general purpose machines reasons why one or the other was chosen are explored case study traces some of the ways in The third networking of computers has developed from simple remote terminal operat 1'on to high bandwidth connections among powerful which the p ocessors oncerning the AgencV's attempts to push computi ng technology to its 11 mi ts Bot'h successes and UI Section 3 p e«ents material failures which a e dis cussgd the fi 5t instances of true computer innovation« app a to have cll'i n M de at the Ag y al' e p sented P L 8636 EO 1 4 c -' I P L 86 36 EO 1 4 c 23 May 86 U Section 5 is a discussion of the purpose processors cessors levels of development of special their competition with general purpose parallelism and the effects of pro- automated design U Section 6 attempts to draw some useful general and specific conclusions from the material presented in Sections 2 through 5 U Section 7 presents references for the paper the references are also singled out as being of general for those pap r who would like to read farther in the area some of interest of this lP ' SlC lOG NUMBER i 2 Dz COCr-J-c df -- -_­ two SHEET 2 0 tf 9 June 86 cf' - O$a 7 _ _ CASE STUDIES Sl This chapter presents three diverse case studies lare intended to illuminate some of NSA's historical interactions with computers as they attempted tc press general purpose computing technology and mold it toward COMINT processing use computing device teChnology to periorm cryptanalysis provide remote access to machine resources for users i and to provide interchange among machine resourc es • In Section 2 1 there is a discussion of a lJ handling machine development major data NOMAD which did not come to fruiHARVEST tion and the machine which was eventually built which can be viewed as its logical successor TOOW for Section 2 2 trac es the development of m chine cryptanalysis aids 'fS Sec'tion powerful general brought together disc usses the way in 2 3 purpose and ar special which purpoise machines interC ' Jnnected on high speecl· networl s L 86-36 EO 1 4 Ie - groups local of were area 86 36 E0 1 - -8 ft N eLAt-M SS IRf'HE tlflr- IOA-SRC LOG NUMlIE llS s 3i COPY_ _L O OI'1 a two SHEET __ 7 0I' 1 o 7t -_ __ L 86-36 1 4 Ie ··· 9 June 86 These specifications must be considered in terms of the technology available at that time NOMAD was en i si oned as a machinll' L -________________________________ i n ordE not to inhibit suggestions of other technologies c1f1cations were called out 2-4 I only performance SPII'- IDA-SRC LOG NUMBEIi -I lNSI J1o SSIREB CO YJot1 I _ _ _ _ sHEET of· SI U1 -_ __ 8 two oowb 'P L 86-36 q 1 4 Ie 9 June 86 CU A-ftel evaluation o-f mull ipl bids the NOMAD c ontrac t ' was awarded to Raytheon in 1951 2 C'b 3 i Or - ----- I SRC LOG NUMBfIl UNeb JSIAEB two COpy SHEET l 9 OF L 86-36 ' 0 1 4 Ie 9 7 9 June 86 U schedule C hanges The NOMAD effort at Raytheon began to get badly This is attributable to a number of causes in senior projec t staff I behind including IDA-sac LOG NUMaER COPY two I JOD 3i otl - - ____• 9 June 96 SHErr lO OF-I ¢ 7'--___ U Finally in June result of too little 19 4 the NOMAD too late proje t and for too mu h was killed the money I 2 1 2 · L 86-36 EO 1 4_ c FARMER-NOMAD U In April 19 4 just prior to NOMAD's demise called FARMER was proposed omputer purpose ipated that efficiency and of a system this system was to provide a general with special purpose attachments su h a cmbinaticn cculd talc It was antl- advantagE special purpose prccessors see Section of belowl provide cap ability for very powerful and large scale With the termination of NOMAD a FARMER-NOMAD handling the de t a Speciat Study Group Agency's Was established for the purpo e of surveying needs for large-scale analytic equipment and rec ommendations far design studies SNY 64 2-7 the praparing Top S'flret I lmb a two IDMRC LOG NUMWi u» CO Y-LOF ''l _ _ SHeeT I J OF 7 o 1 4 c I L 86-36 9 June 86 - J U A number of studil s were begun within the Office of Analytic Equipment Development to consider the mix of general and special EO 1 4 0 P L 86-36 purpose sUbsytems In 1955 IBM approached about thE USE of STRETCH BLO J a of perfo mance their attempt to extend the Agency proposed machine rising out over the IBM 704 I o 1 4 c P L 86-36 9 June 86 two 2 1 3 HARVEST The Agency rejected STRETCH initially u but awarded - study c ontrac ts to IBM for high speed memory research SILOl fer system design studies for an Agency-oriented system PLANTA- TION HARVEST and IBM agreed on the design of HARVEST is especially SNY 64 the The upshot of these studies was that later RANCHO Agency and principal well SNY 82 system to documented in a number be of the called places As a result we shall cdnsider only -features of HAR'JEST that made advance for Agency applications it a substantial E9 1 4 c pj 86-36 ' 2 1 3 1 l The HARVEST CPU After the Agency's initial rejec tion'of STRETCH went to the Atomic Energy Commission AEC and propcsedto one for them IBM build This proposal was accepted by the AECLos A'tamos National Laboratory As III resul t I features of STRETCH HAR EST as procured by the Agency had the I -9 1M o 1 4 Ie two 58 t5iS 3 'b t l ' Copy SHEET oj 2 1 3 2 I' L 86-36 IDA-S C leG NUMSER OF '73 7 I 9 i tuns 96 HARVEST Memories ' U HARVEST had two typss of cors memory EO 1 4 Ie P L 86-3 U The other major memory advance for HARVEST was the TRACTOR storage systam which used wide 1 75 magnetic tape with 16 logical tracks the tapes were contained in large cartridges and these cartridges were retri ved bv automatic handlers I V 1' 0 1 4 tip 'It Qull'l1 e L 86-36 f'J June 86 two 41' 4ft ' I WI HARVEST provided 14 years of service from 1962 to 1976 Although livered comput ers STRETCH end like by TRETCH HARVEST was ahead of its time when the time it was retired the large scale had overtaken it in both performance and itself in it5 de- commercial reliability never became a commercial machine machine of the era wa5 the 7094 V J W' IBM's high variOU5 versions which was then superseded by thel ' I V -------------------- I EO 1 4 e P 'L 86-36 2 2 Evohltion of Machine AidSI 2-1 I 86 36 2% ix E0 91L 86 36 $301 4 21 1 P L 86e33 E9 'k r- l P L 86m36 Ego 86 36 E L 86 36 Ego 1 44 2 l 9 June 96 two EO l 4 Ie P L 86-36 2 3 Development of Networking reue Ori g1 nall y at the Agency as 611 sewhere computers were operated as stand-alone fa cilities users brought their jobs to trans erred between compu ers by punched cards or these were eventually supersade- l by magnetic tape pplicationli were generall 1 par ing process for the user W a Y5 Data was the computer or operated the computer themselves · f paper The computer an interactive problem solv- In thIS section we cliscuss some of the in which such ini eril ctior I • • ianhanced In using computers as near real-time t'_lrnar ' Jnd t J l s which a re direc ' ' y to individual analysts a tape th L- 2-IE work location In avsilabls - principle '7 Jun 86 much of this could be accomplished nowadays by stand-alone or by network d were PCs introduced At the tims the initial systems discuss d they reprssented both pow rful for the h re tim ' aids for the user and early institution of remote operation leading to modern networking '11 0 1 4 Ie P ·L 86-36 2 3 1 Early Remote Diagnostic Aids u A principal function in unknown cryptographic system quantity of cryptan lyi I 5 diagnosis of an The analyst iscohfranted with a ------------ -- ---- unknown data 1 I U The two earliest remotely operat d comput rs and ROB-ROY SNY 643 ROGUE ROGUE as a commercial computer the ALWAC IIle I It gave anal ysts accesS to the us of standard canned programs' as well as the ability to program their own specialized requirements U R06UE was succ eded by ROB-ROY a remotely operated version of B06ART • I ' 9 June 86 2 3 2 'mo 1 4 c 'L 86-36 RYE ' The elCpar nc with ROBUE and with U couraging ' 11ed R a Ro was that a large scale remote operation as 1963 the first increment of the RYE syste m so planned In I I - ITS ten It had been determined that individual users had wd t- many versions of nearly the same programs attempts were made to generali _ programs of common interests and Sene ral ------- 'l Utility Programs SUPs we re provided ' u ••• ' _ E L 86 36 two a ---C C i'' S RJC'Zt ®3 SHEET 27 'i' June 86 OF- 5L '--___ EO 1 4 Ie Figure 2 3-1 Tjl le 8Ei6RET P L 86-36 51 aw t i ioJ UI'1CLAS51 F 1bOb p L 86 36 310 1 4 Emmi SECRET three 3 0 9 June 86 PRESSING TECHNOLOGY In 5 this chapter we examine acme cf the tempts tc advance computing technology Agency'a at- I rBUB Agency In Secticn 3 1 some of the developments and computing and Bome of its consequences alized uses of memories which can be called These include the LIGHTNING program suc cesses are desc ribed technology involving enhancement of memories and speci- introduction of supercomputers and deployment of computers into the field FeWQ FOUD innovationa In Section 3 2 some of the failures are discussed Section in computing technolog'f whid- -------_ L I- __- _- - nated at the Agency 'EO 1 4 Ie P L 86-36 '- 3 3 provides a br·iaf discussion '9 of some belie' e -Jere origi- _______---' - 1 three 3 1 9 June 96 II SUCCE 'S S If 3 1 1 LIGHTNING LIGHTNING U Director of NSA was an attempt General Canine motivated by the first to advance computing technology by three orders of magnitude the goal was stated as 1000 Hcyde computation the we would now say nanosecond computation Some of is described by Campaigne CAM 59J and by Wigington work WIG 63J by NSA A series of reports summarizing the wdrk was prepared in 1962 these reports cannot be located as R D writing of this paper ives U with three IBM major contractors Radio 1958-1963 International Business Corporation of America RCA Univac RRU the two of the reports are in Snyder's arch- LIGHTNING program was a 5 year effort The of Machines and Remington smaller efforts were carried out by Rand PHilco Ohio State Uni' ersity the University of Kansas and MIT Ul Dudley ducting Agency IBM's LIGHTNING work concentrated on the JI cryotron ' Buck's invention of a magnetic field switchable supercondevice had operating at about 4 degrees K BUC 56J The tried to use cryotrons earlier - see Section 3 2 3 RCA's work concentrated on applications of diode 104 one the tunnel of the fastest switching devices known at that time RRU concentrated on thin magnetic film devices «f U A major problem in attac king such for the timel tramely high spe' d c ircLlits was that of adequate few Db ervi ny i n t ' '_t TI n ' t i on the e c i rcell ts was one Th 3-2 in$tr' ment tion development of of 't he majc r e · - high ac c omp 1 i '2ihm nts speed aT the CC Y-L - - ·- I1'4 - -'''''''''•• sHm 0i' -' ' l- 7 _ _ three LIGHTNING evident most long Tunnel lived had s Jitching program were work in magnetic thin films was one of technologies which came out although all of the device c iruitry tion The diodes speeds Other accomplishments of the program Ie 9 June 86 capable of di ficulties of extremely the fast inherent to a and were overtaken by advances the program switching two-terminal in transistor The cryotron proved not to scale to high speed opera- r ' as had been hoped and this topic is discussed mOre exten- sively in Section 3 2 3 below U Although some of the points cited in the previous para- graph do not sound very successful whole deemed to be a SUCcess a s i t stimulated wa s press on to higher speed circuits instrumentation understanding over lines circuit the LIGHTNING program as a industry to In a ddition to the high speed which furthered industrial work a far better of the problems associated with pulses transmitted on circ uit boards was developed In addition to deVelopments the potential of very high speed components provided some creative ideas in computer architecture For exam- pIe the idea of a very fa st although small scratc hpad memory was while e plored by RCA considering This study ore5hadowed the whether or not the programmer or ache memory the system should control its use EO 1 4 Ie P 86··36 3 1 2 Memories 3-3' EO 1 4 Ie p ·t 86-36 9 June 86 three MagnetiC Tape 3 1 2 1 ' and at one time was the major U I user « In addition S consumer over of digital tape and established what came to be the premier government tape te«tlng laboratory extremely recogni%ed which was The disc ussed 1 0 1 4 Ie L 86-36 In about 1970 there was an extensive e1'fort to obtain a terabi t and major s rd« high performance tape system of HARVEST was in Section 2 1 3 2 above W oq 5010 the Agency quic kly bec ama a eventually transfarred to the National Bureau of tape The Agenc y bec ame an early major usar 01' magnetic e memory This work was dene in conjunction with was an enhancement - A pex TABLON -1--' provided alterab12 tnlnsferred storage When 1'i l' ' s bec me sta ble they could be to TAB LON s other 'ass 5 orage sy t i m • L-______ I EO 1 4 Ie P L 86-36 PuLln 86W36 E10 1 4 C f 9 14 86 36 E0 9 11 86 36 130 1 4 13 4 '£lA-Sr C LOG NUMBE j COPY 3l£0F b three 3 1 3 SHEET OF o Ii Q v' ' C Q 81 - 1 4 Ie P t 86- 3 6 'II' ' June 86 Superc omputers 3-8 86 36 1 11 b a 86m36 lo 3m 13 29 1 86 36 13 0 EKL 86w36 i go 1 44 2 1 E L 86 36 go 1 4mm rfL 86 36 Elf 1 4 5 L 86-36 E01 4 c '9 June 86 three ' In the mid-1960sthe Josephson Junction JJ phe omenon Ul was discovered in which This is another very low temperatu e phen'omenon switching am electron tunneling junction between two states is accomplished by means of a magnetic field This tech- nology a issue has been described by Anacker ANA 79J and in of the technology in 1§ 9ycnsl B Q CI8M 80l The pot ential of JJ brought about a enewed inte est in cryogenic devic'ss spit e of the environmental problems p ented by operating system in liquid helium JJ gf special The two primary arguments in favor '4 of computing we fast switching speed and minimal energy dissi-' pation during switching I 85w36 Ego coPY-J-o three SHErr t' OF U r O '31 1 'S 7 ' IDA·SRC lOG NUMB It P L 86-36 EO L4 Ie 9 June 96 At a later time an attempt was made to consider the usa - of some macro-modules being developed at Washington University These of modules provided general arithmetic functions the investigation was that the overhead in line the upshot drivers and receivers and requirements for asynchronous operation appeared to offset the potential advantage of stockpiling to the It is interesting nota that some of these ideas have recently reappeared -- same Washington University group many like other topics in this paper conform to the reincarnation 3 2 5 This BAR 95J from topic wheel 0-1' CMYE 68J Microprogramming UI number In 1956 and 1957 interviews were held with a of computer programmers asklng about fea t tres which thought would cO ntribute to Agency processing C 3AF 56 3AF large they 57J Although a number of speciali ed instructions were proposed there was a distinct disinterest in microprogramming No one thought i hat the ani' '1st or orogr mmet' w nted to be concerned wi th such ' 3-17 ·P L 86-36 EO 1 4 e iietAt s1FIEO thrllllll 9 JunEii 86 topic Innovat 'on$ 3 3 UI In innovations invented not to this section we describe briefly in computer architecture which were speci'l'ic probably - first They tendel'd be publicized and most did not get implemented in their It seemed t o be of interest to list them here Stack and Tagged Architecture W few or implemented at t he Agency c r IDA-eRD or1g1nal form 3 3 1 a Both of these concepts were invented for NOMAD and are r• discussed in Sect ion 2 1 They certainly predate all other work such as that at Rice University and at Burroughs known to this author 3 3 2 77 Instruction U Mitchell of This instruction s MIT for the CDC 1604 6U at IDA-eRD in 1961 was proposed by It took advantage an unused opcode on that machine to provide a microprogrammed instruction dealing with logic and counting on registers T EO 1 4 e P L 86-36 3-1'2 iietASSIFIEa t hree IOA-SRC LOG NUMBER COPY 4 $HEEr 3 3 3 9 June SO £P OF_ '3 ''-__ I Cache Memory U As not ed in Section 3 1 1 it became clear 1n the early days of project LIGHTNING that although there could be some very high speed memory it would be in short supply an effective Both and consequently way of making use of that memory would be stack and cache type memory configurations were needed proposed At the time of writing this paper no reference material for these architectural features in the LIGHTNING work can be found 3 3 4 Fast Adders P L 86-36 EO 1 4 Ie 3- 10 '1'0 s ·• DUItilII v- - 11· - IDA-SRC lOG NUM8E1l r z COPY OF t t _ __ four 2 June 86 HEn Cf -IJ'5 J 1_ _ _ _• 4 0 ALGORITHMS M 1 4 c P L 86-36 4 1 Introduct1on faeWI ways Advances in computing applications are·made in many They may be the result of advances in hardware technology in software technology and programmer aids result treme they may also be the of better fitting of the problll m to a computer An e - case of this latter is one in which an apparently complex andlor very large computational process can be restated or transformed into a lel is complex and or less cess Many science of these processes are to be found in the literature 1 4-1 largecomputation pro- computer 86-36 mo 1 4 E L 86 36 Ea 1 4 03 6 E30 1 4 - E L 86 36 1 4 P L 86 36 133 1 4 an 'fnur' 2 June Elas- 5031 4 c 86 36 fi ve 2 Juns 96 5 0 THE ROLE OF SPECIAL PURPOSE PROCESSORS P L 86-36 EO 1 4 Ie 5 1 Introduction TS In earlier sections of this report we noted many in- stances of sp cial purpose processors Which have b n constructed and used by the Agency for cryptanalytically oriented These functions purpose •• howevsr closely follow the gensral trsnd commercial communications and will not be discussed chapter contains two major sectionsl her in This the first discusses special purpos proc ssors and the second discusses general purpcse spe- 5 2 Special Purpose Processors CE r fo'eCO In 1977 the National Security Agency Scientific Advisory Board NSASAB established an ad hoc group to prepare Report This use on report contains much of the histor-y And rational of Agency special it interesting report to Technology for Special Purpose Processors SAB Is pur-pose pr-ocassor-s by the National recommended to anyone reading sIdelight is the concern expressed this in for- 7BJ th Secur-ity paper the a An NSASAB report that NSA should be pr pared to detect and respond a slowing of the commercial development of supercomputers This slowing predicted nine years ago has not happened yet 5-1 five 2 June 86 5 2 Special Purpose ProcessorS Cal - The discussion of this section is principally concerned with the computer sCience computer architecture issues ta e not doe It into account two major topics discussed in tSAB 78J 1 the e tent to which a special purposE processor is classified by its inherent design and the management and cost conetructi ng 1 tin-house or under contrilct liiii difficul iss of and 2 the ciec ' si or to the lifetime of the prcblem versus the lead time to prcdL ce a machine and its ex pected lifetime s General Discussion 1 aTfec ive U Special purpose processors SPPs can be very eol 'et cally when comp rsd to classical vcn Neuman st rs r - gram computers ciency c an be taken by asking how busy each both logic and memory in the system is binary element In a 5PP many regis- ters and many data paths can be kept busy at the same time sort of specialization is found in general purpose This processors GPPs in pipelined arithmetic units in use of multiple arithmetic units whiC h have sim ltaneous in overlap cpe ation struction processing and arithmetic processing cussing ferent keeping binary elements busy we must cost for m mory ac tor elements versus logic element s are much less e pensive etc performed function When disin the elements by logic or by table look up mic ropr grammed 5-2 Memory a func tion can Further c an be performed in ROM table look up it c an performed with wired or di ­ hence it is sometimes possible to make trade-offs between memory size and logic be in- o logic a fiKed also be ·P L 86-36 EOl 4 c five Te hnclggy 2 June 86 DiscussigM 5 2 2 Functignality 3-3 'Ep a6 36 i we 2 June ED 1 4 86n36 I - 2 Line 86 1115 ssmsa five 2 0mm 3 6 Etc 1 4 PEEL 86w36 Five 2' June as PoL 86-36 EO L4 c five 2 June 96 5 3 Seneral-Purpose Special Purpose Processors Ul Again as noted in SAB 78J GPPs have been used in c njc nction with 5PPs to provide th us int rfac s th lID i scme cases secondary testing cf results I L-______________________- J etc A a r sult we can think of mixed pr Jces50r5 which are a combinaticn oo ' SPPs and SPPs 5 tetem -Functicn t dominant The view 'of Is an array prcc5s5cr or its associated c mpuAddi ti onall y evel' since micropl 'egramming began being used in computer implementatien general pUl 'pose pretesscrs have been capable of being specialized fer efficiency intlarrower P L 86-36 tasks EO 1 4 Ie 5 3 1 5-8 'EO 1 4 Ie P L 86-36 2 June 86 five 5 4 Summary It seams clear that the Agency will continue to U e both general and special purpose computers in the future as t ey hav General purpoSe computers provide a base w ich can 1n the past i run a deSired lot p ogram about as soon as it is matc hing problem w ittan W have le ned requirements to domputer I idiosyncrasies EO 1 4 Ie P L 86-36 5-9 I Pu L 86-36 13 i we 2 Juna 86 5mm 9 June 86 6 0 gy LESSONS LEARNED at the same time especially for a single or a few machines The time scale to completion is most likely to stretch out to the point where the completed machine is no longer There are two major reasOns fo cost effective this lost of cost effectivenes5 il the extra cost of development because of the extended opment time devel- 2 the 1055 in expected performance because of the delay in beginning use vis-a-vis outside developments EQ 1 4 Ie P L 86-36 J g lS l£_ U Don't allow technical political arguments delay planning af a system It will result In tao lit tle - too ·late ' j gr gll l£_ U Dan't let technalogy delay strestch out the development time or the window of opportunity will be past Examplel Josephson Junction Section 3 2 3 EO 1 4 Ie P L 86-36 6-1 9 June 86 six - TSBW When should proc ssSle be plac ed on general mac hines or special purpose machines sis are well suired tc SP machines I purpose Experimentaticn and analy- P L 86-36 EO 1 4 c 6-2 9 Juna 86 P L 86-36 six EO 4 Ie '7 June 96 b it§ l QD_ T91 Not enough attention i$ given to reprogramming matte or otherwise 6-4 auto- 9 June 96 b ii9 l_§ TSI Algorithms are imortant ----II L -_ _ _ _ _ _ 1' 1 86-36 EO 1 4 Ie 513 9 June 86 10 P L 86 36 9 June 86 SiK U l Dces reccnfiguraticn merit ccntinued attenticn P r 86-36 EO 1 4 Ie 6-7 six 9 Juna 9a Lg Qn_ 86 36 EQJH4JC li O 1 4 e P' J 86-36 seven 7 0 ALL 81 2 JLlne 86 REFERENCES All en G R A ReconT gLlrabl e ArchitectLlre for Arrays of Microprogrammable Processors Chapt r 8 in §e G d l emE yja§I 8csoUs OjaYCl l1 fec Eiilja il l ECSS l lli ii oS K S FLI and T ANA 79 Ichikawa eds Boca Raton CRCPress 1981 Anacker Wi 11 CompLlti ng at 4 Degrees Kelvi n 1 E 5 §e lls1 Y l 19 5 26-37 May 1979 BAG 81 Bagg Thomas C and Mary E Stevens InformatiOI1 Selection Systems RetrieVing Replica Copies · NBS·· Technical Note 157 December 31 1961 BAR 85 Barney Clifford Logic DeSigners Toss OLlt the Clock gl€S 9Qi 5 December 9 1985 1010 42-45 BLO 59 Bloch Erich The Engineering Design cf the Stretch Computer Pt gc E CC 19 59 48- 59 _____ ns ructlon Manual Vol 1 August 197 R324 SECRET S-211 801 Bue 56 Buck Duclley A The Cryotron A Superconductive Com ' puter Element fees B5 s 482-493 1956 P L 86-36 EO 1 4 c 7-1 EO 1 4 Ie P L 86-36 seven i June 86 I CDC 79 _____ • AF Specification Control Data Corperatipn InformationSciences Division December 1 1979 EO 1 486· CDC 85 _____ • An Introduction to the Cyberplu5 Parallel Processing System Control Data Corperation 1965 P L CRO 57 EVA 86 Crowe J W Trapped-Flux Superconducting Memory l OuC· B 1 295-303 October 1957 Evans B D SYstem 360 A Retrospective View 1 4 Ie eooih Sli t l iI tSlC SIt 'gmQY Jg 2 p 160 P L 86-36 April 1986 f 1 4 Ie P L 86-36 7-2 I P L 86-36 J ' 01 4 c seven 2 June 86 ' FRE 83 Fraund Commsmts on Supercomputi no t 1 g Q1Qg 'g l C 1 6 1-2 Spring-Summer 1983 11-21 GAF 56 l3a-f-fny Joan M Report on P og amm Int vi IIIIWII ' Dec 1956 SECRET 9-85 940 I3AF 57 l3a-ffny Joan M P oposedMachine Features RIl D Feb 1957 CONFIDENTIAL 8-85 942 GEN 71a Gentile R 8 and J R Lucas The TABLON Mass Storage Network 12Z § pp 345-356 AFIP8 P ess GEN 71b l3entUe R B and R W Grove Mass Storage Utility Considration fo Shared Storage Applications Iss§ Ic os 00 gn tlcs eG 7 4 848-952 Dec 71 IBM eo IBM 82 _____ Special Issue on Josephson Computer Technology gf B g § 2 Mar 1980 l gyC __ __ Josephson Junction Applications Study Final Report Contract MDA 904-81-C-0425 IBM Federal Systems Division Gaithersburg MD March 1982 UNCLASSIFIED Report w th SECRET Appendi 7-3 seven 2 June S6 IBM 93 _____ Josephson Junction Applications Study Phasa II Final Report Contract MDA 904-81-C- 42 IBM Faderal Systems Division Gaithersburg MD November 198 UNCLASSIFIED report with SECRET Appendix KEY 85 Keyserling Charles SPD Impact on Supercomputer Needs RS 1985 TOP SECRET CODEWORD KRD 76 Kronlage Carl R FLEMING Completion Report NeA R32S t February 1976 TOP SECRET CODEWORD 5-213 554 LEI 72 Leibler Ric ard A Mathematics and Computers in Cryptanalysis §aI Special CLO Issue on Changing Frontiers in Comouter Cryptology 1973 15-22 TOP SECRET CODEWORD LUC 104 Lucas Joseph R •• Jr CAM II eeI 1 2 27-7 FOUO MAT 60 Matthews Chcr Q$ W Qui k R eranca Memory T c ni­ cal Memorandum 352-7 1 17 26 oc ober 1960 Fa o S-1 25- 38 MCE 77 McEliece R Ib@g g£ lQfg matigQ Og bggi09L e atb@matl'al Eg ngetlgQ ig gmm Qi'mtigQ AddisonWesley 1977 MCW 78 MCWilliams J F and N J Sloane rOg b@g gf E ro gCC 11Qg god@ Elsevier 1978 MIT 61 Mitchell G J Rice R A•• and E Stoffel A Des cription of a 77 order for the CDC 1604 IDA-eRD Working Paper No 20 April 1961 S-134 709 I 'P L 86-36 EO 1 4 c 7-4 · W 1 Ie pi 86 36 sevem 2 June 86 -' MOO 61 Moore O P a nd J 0 SwH t Note o Sorti ng R@peats SCAMP Working Pa per No 1 61 IDA 4 August 1961 MYE 68 Myers T H and I E Sutherlanc t Dnt he Design 0 Display Process Gl2 at t § a z 6 410 414 June 1968 NOTE also discussed in SIE 92 NEV 64 Nevins W D The REDMAN Program t §eIlZ I 1 Winter 1964 97-195 UNCLASSIFIED NEW 59 Newhouse V L and J W Sreme High-Speed Superconductive Switching Element Suitable for Two-Dimen' ' sional Fabrication gy eggli g En¥ i Q 14 e-1459 I 19 9 OME 74 _____ The OMEN Processor AppendiK Kin H tla e l l 9 l sol fi' sll§ f gs Og P Enslow ed Wi1 ey 1974 7-5 P· L 86-36 EO 1 4 Ie seven srE 92 SLA 56 Siewor-ek D P C G Bell and A Newell eels ' Qmr ty § §t y t J §lli E ci O iQl i lli 5 O t l$ 5 1l e l§ 1'1c I3 awHi 11 1'182 Slade yCC VAT 37 AI A Cr-yotr-cn Catalog Memor-y Dec ember- 1'156 Yates F Design and Analysis OT Factor- al Exper-imenta Harpenden Imper-ial Bureau oT Social SCience 1937 7-6 lasre - 23 may 86_ E0 86 35 CLASSIFIED REFERENCES 'P L 86-36 EO 1 4 0 clasre-f IBM 80 23 May 96 _____ • Special Issue on Josephson Co puter Technology gf B 2 Mar 1980 QYr 2 l L 86-36 EO 1 4 Ie cla5ref 23 May 86 IBM 82 --___ • Josephson Junction Applications Study Final Report Contract MOA 904-81-C-0425 IBM Federal Systems Dlvi5ion Gaithersburg MD Marth 1982 SECRET Appendix IBM 83 ----- Josephson Junction Applicat''l pns Study Phase II Final Report Contract MDA 904-el-C 0425 IBM Federal Systems Division Gaithersburg MD November 1983 SECRET A lDendi Ie Ego 1 44m 86w36 1a5re 23 May E6 1 am 2 23 8 5 3 3 86w36 m 1 4 86 36 330 1 4 9 2 86 36 41 9W3 R L 86m36_ Pyg 86-36 E0