外文翻译中英文对照微机发展.docx

外文翻译中英文对照微机发展.docx

《外文翻译中英文对照微机发展.docx》由会员分享，可在线阅读，更多相关《外文翻译中英文对照微机发展.docx（14页珍藏版）》请在冰豆网上搜索。

外文翻译中英文对照微机发展

ProgressinComputers

PrestigeLecturedeliveredtoIEE,Cambridge,on5February2004

MauriceWilkes

ComputerLaboratory

UniversityofCambridge

Thefirststoredprogramcomputersbegantoworkaround1950.TheonewebuiltinCambridge,theEDSACwasfirstusedinthesummerof1949.

Theseearlyexperimentalcomputerswerebuiltbypeoplelikemyselfwithvaryingbackgrounds.Weallhadextensiveexperienceinelectronicengineeringandwereconfidentthatthatexperiencewouldstandusingoodstead.Thisprovedtrue,althoughwehadsomenewthingstolearn.Themostimportantofthesewasthattransientsmustbetreatedcorrectly;whatwouldcauseaharmlessflashonthescreenofatelevisionsetcouldleadtoaseriouserrorinacomputer.

Asfarascomputingcircuitswereconcerned,wefoundourselveswithanembarassderichess.Forexample,wecouldusevacuumtubediodesforgatesaswedidintheEDSACorpentodeswithcontrolsignalsonbothgrids,asystemwidelyusedelsewhere.Thissortofchoicepersistedandthetermfamiliesoflogiccameintouse.ThosewhohaveworkedinthecomputerfieldwillrememberTTL,ECLandCMOS.Ofthese,CMOShasnowbecomedominant.

Inthoseearlyyears,theIEEwasstilldominatedbypowerengineeringandwehadtofightanumberofmajorbattlesinordertogetradioengineeringalongwiththerapidlydevelopingsubjectofelectronics.dubbedintheIEElightcurrentelectricalengineering.properlyrecognisedasanactivityinitsownright.Irememberthatwehadsomedifficultyinorganisingaconferencebecausethepowerengineers’waysofdoingthingswerenotourways.AminorsourceofirritationwasthatallIEEpublishedpaperswereexpectedtostartwithalengthystatementofearlierpractice,somethingdifficulttodowhentherewasnoearlierpractice

Consolidationinthe1960s

Bythelate50sorearly1960s,theheroicpioneeringstagewasoverandthecomputerfieldwasstartingupinrealearnest.Thenumberofcomputersintheworldhadincreasedandtheyweremuchmorereliablethantheveryearlyones.Tothoseyearswecanascribethefirststepsinhighlevellanguagesandthefirstoperatingsystems.Experimentaltime-sharingwasbeginning,andultimatelycomputergraphicswastocomealong.

Aboveall,transistorsbegantoreplacevacuumtubes.Thischangepresentedaformidablechallengetotheengineersoftheday.Theyhadtoforgetwhattheyknewaboutcircuitsandstartagain.Itcanonlybesaidthattheymeasuredupsuperblywelltothechallengeandthatthechangecouldnothavegonemoresmoothly.

Soonitwasfoundpossibletoputmorethanonetransistoronthesamebitofsilicon,andthiswasthebeginningofintegratedcircuits.Astimewenton,asufficientlevelofintegrationwasreachedforonechiptoaccommodateenoughtransistorsforasmallnumberofgatesorflipflops.Thisledtoarangeofchipsknownasthe7400series.Thegatesandflipflopswereindependentofoneanotherandeachhaditsownpins.Theycouldbeconnectedbyoff-chipwiringtomakeacomputeroranythingelse.

Thesechipsmadeanewkindofcomputerpossible.Itwascalledaminicomputer.Itwassomethinglessthatamainframe,butstillverypowerful,andmuchmoreaffordable.Insteadofhavingoneexpensivemainframeforthewholeorganisation,abusinessorauniversitywasabletohaveaminicomputerforeachmajordepartment.

Beforelongminicomputersbegantospreadandbecomemorepowerful.Theworldwashungryforcomputingpowerandithadbeenveryfrustratingforindustrynottobeabletosupplyitonthescalerequiredandatareasonablecost.Minicomputerstransformedthesituation.

Thefallinthecostofcomputingdidnotstartwiththeminicomputer;ithadalwaysbeenthatway.ThiswaswhatImeantwhenIreferredinmyabstracttoinflationinthecomputerindustry‘goingtheotherway’.Astimegoesonpeoplegetmorefortheirmoney,notless.

ResearchinComputerHardware.

ThetimethatIamdescribingwasawonderfuloneforresearchincomputerhardware.Theuserofthe7400seriescouldworkatthegateandflip-floplevelandyettheoveralllevelofintegrationwassufficienttogiveadegreeofreliabilityfarabovethatofdiscreettransistors.Theresearcher,inauniversityorelsewhere,couldbuildanydigitaldevicethatafertileimaginationcouldconjureup.IntheComputerLaboratorywebuilttheCambridgeCAP,afull-scaleminicomputerwithfancycapabilitylogic.

The7400serieswasstillgoingstronginthemid1970sandwasusedfortheCambridgeRing,apioneeringwide-bandlocalareanetwork.PublicationofthedesignstudyfortheRingcamejustbeforetheannouncementoftheEthernet.Untilthesetwosystemsappeared,usershadmostlybeencontentwithteletype-basedlocalareanetworks.

Ringsneedhighreliabilitybecause,asthepulsesgorepeatedlyroundthering,theymustbecontinuallyamplifiedandregenerated.Itwasthehighreliabilityprovidedbythe7400seriesofchipsthatgaveusthecourageneededtoembarkontheprojectfortheCambridgeRing.

TheRISCMovementandItsAftermath

Earlycomputershadsimpleinstructionsets.Astimewentondesignersofcommerciallyavailablemachinesaddedadditionalfeatureswhichtheythoughtwouldimproveperformance.Fewcomparativemeasurementsweredoneandonthewholethechoiceoffeaturesdependeduponthedesigner’sintuition.

In1980,theRISCmovementthatwastochangeallthisbrokeontheworld.ThemovementopenedwithapaperbyPattersonandDitzelentitledTheCasefortheReducedInstructionsSetComputer.

Apartfromleadingtoastrikingacronym,thistitleconveyslittleoftheinsightsintoinstructionsetdesignwhichwentwiththeRISCmovement,inparticularthewayitfacilitatedpipelining,asystemwherebyseveralinstructionsmaybeindifferentstagesofexecutionwithintheprocessoratthesametime.Pipeliningwasnotnew,butitwasnewforsmallcomputers

TheRISCmovementbenefitedgreatlyfrommethodswhichhadrecentlybecomeavailableforestimatingtheperformancetobeexpectedfromacomputerdesignwithoutactuallyimplementingit.Irefertotheuseofapowerfulexistingcomputertosimulatethenewdesign.Bytheuseofsimulation,RISCadvocateswereabletopredictwithsomeconfidencethatagoodRISCdesignwouldbeabletoout-performthebestconventionalcomputersusingthesamecircuittechnology.Thispredictionwasultimatelybornoutinpractice.

Simulationmaderapidprogressandsooncameintouniversalusebycomputerdesigners.Inconsequence,computerdesignhasbecomemoreofascienceandlessofanart.Today,designersexpecttohavearoomfulof,computersavailabletodotheirsimulations,notjustone.Theyrefertosucharoomfulbytheattractivenameofcomputerfarm.

Thex86InstructionSet

Littleisnowheardofpre-RISCinstructionsetswithonemajorexception,namelythatoftheIntel8086anditsprogeny,collectivelyreferredtoasx86.ThishasbecomethedominantinstructionsetandtheRISCinstructionsetsthatoriginallyhadaconsiderablemeasureofsuccessarehavingtoputupahardfightforsurvival.

Thisdominanceofx86disappointspeoplelikemyselfwhocomefromtheresearchwings.bothacademicandindustrial.ofthecomputerfield.Nodoubt,businessconsiderationshavealottodowiththesurvivalofx86,butthereareotherreasonsaswell.Howevermuchweresearchorientedpeoplewouldliketothinkotherwise.highlevellanguageshavenotyeteliminatedtheuseofmachinecodealtogether.Weneedtokeepremindingourselvesthatthereismuchtobesaidforstrictbinarycompatibilitywithprevioususagewhenthatcanbeattained.Nevertheless,thingsmighthavebeendifferentifIntel’smajorattempttoproduceagoodRISCchiphadbeenmoresuccessful.Iamreferringtothei860（notthei960,whichwassomethingdifferent）.Inmanywaysthei860wasanexcellentchip,butitssoftwareinterfacedidnotfitittobeusedinaworkstation.

Thereisaninterestingstinginthetailofthisapparentlyeasytriumphofthex86instructionset.ItprovedimpossibletomatchthesteadilyincreasingspeedofRISCprocessorsbydirectimplementationofthex86instructionsetashadbeendoneinthepast.Instead,designerstookaleafoutoftheRISCbook;althoughitisnotobvious,onthesurface,amodernx86processorchipcontainshiddenwithinitaRISC-styleprocessorwithitsowninternalRISCcoding.Theincomingx86codeis,aftersuitablemassaging,convertedintothisinternalcodeandhandedovertotheRISCprocessorwherethecriticalexecutionisperformed.

InthissummingupoftheRISCmovement,IrelyheavilyonthelatesteditionofHennessyandPatterson’sbooksoncomputerdesignasmysupportingauthority;seeinparticularComputerArchitecture,thirdedition,2003,pp146,151-4,157-8.

TheIA-64instructionset.

Sometimeago,IntelandHewlett-PackardintroducedtheIA-64instructionset.Thiswasprimarilyintendedtomeetagenerallyrecognisedneedfora64bitaddressspace.Inthis,itfollowedtheleadofthedesignersoftheMIPSR4000andAlpha.HoweveronewouldhavethoughtthatIntelwouldhavestressedcompatibilitywiththex86;thepuzzleisthattheydidtheexactopposite.

Moreover,builtintothedesignofIA-64isafeatureknownaspredicationwhichmakesitincompatibleinamajorwaywithallotherinstructionsets.Inparticular,itneeds6extrabitswitheachinstruction.Thisupsetsthetraditionalbalancebetweeninstructionwordlengthandinformationcontent,anditchangessignificantlythebriefofthecompilerwriter.

Inspiteofhavinganentirelynewinstructionset,IntelmadethepuzzlingclaimthatchipsbasedonIA-64would