英语 电子信息工程9PPT课件

Unit9DigitalSignalProcessing PassageABasicConceptsofDSPPassageBDigitalSignalProcessorsPassageCComparisonofDSPandASP PassageABasicConceptsofDSP Wedon tspeakinadigitalsignal Adigitalsignalisalanguageof1sand0sthatcanbeprocessedbymathematics Wespeakinreal world analogsignals Analogsignalsarerealworldsignalsthatweexperienceeveryday sound light temperature andpressure Adigitalsignalisanumericalrepresentationoftheanalogsignal Itmaybeeasierandmorecosteffectivetoprocessthesesignalsinthedigitalworld Intherealworld wecanconvertthesesignalsintodigitalsignalsthroughtheanalog to digitalconverter processthesignals andifneeded bringthesignalsbackouttotheanalogworldthroughthe digital to analogconverter 1 Theessentialsofanalog to digitalanddigital to analogconversion Thefirstessentialstepinanalog to digital A D conversion asshowninFigure9 1 istosampleananalogsignal Thisstepisperformedbyasampleandholdcircuit whichsamplesatregularintervalscalledsamplingintervals Thelengthofthesamplingintervalisthesameasthesamplingperiod andthereciprocalofthesamplingperiodisthesamplingfrequencyfs AccordingtotheNyquisttheorem asignalwithamaximumfrequencyofWHz calledaband limitedsignal mustbesampledatleast2Wsamplespersecondtoensureaccuraterecording Whenthisminimumisnotrespected distortioncalledaliasingoccurs Aliasingcauseshighfrequencysignalstoappearaslowerfrequencysignals Tobesurealiasingwillnotoccur samplingisalwaysprecededbylowpassfiltering Thelowpassfilter calledtheanti aliasingfilter removesallfrequenciesabovehalftheselectedsamplingrate Figure9 1Analog to DigitalConversions Afterabriefacquisitiontime duringwhichasampleisacquired thesampleandholdcircuitholdsthesamplesteadyfortheremainderofthesamplinginterval ThisholdtimeisneededtoallowtimeforanA Dconvertertogenerateadigitalcodethatbestcorrespondstotheanalogsample TheA Dconverterchoosesaquantizationlevelforeachanalogsample An N bitconverterchoosesamong2Npossiblequantizationlevels Thelargerthenumberoflevels thesmallerthequantizationerrors calculatedasthedifferencebetweenthequantizedlevelandthetruesamplelevel MostquantizationerrorsarelimitedinsizetohalfaquantizationstepQ ThequantizationstepsizeiscalculatedasQ R 2N whereRisthefullscalerangeoftheanalogsignalandNisthenumberofbitsusedbytheconverter Thestrengthofthesignalcomparedtothatofthequantizationerrorsismeasuredbydynamicrangeandsignal to noiseratio Adigitalsignalisrepresentedbyasetofverticallineswithcirclesatthetoptomarkthequantizationlevelsselectedforeachsample ThebitrateforanA DconverteristheNfs wherefsisthesamplingrate Finally eachdigitalsampleisassignedadigitalcode whichcompletestheA Dprocess Theresultisadigitalbitstream Itisthiscollectionofdigitalcodesthatis processedindigitalsignalprocessing Tosummarize A Dcomprisesanti aliasing sampling quantizationanddigitization Oncedigitalsignalprocessingiscomplete digital to analog D A conversion asshowninFigure9 2 mustoccur Thisprocessbeginsbyconvertingeachdigitalcodeintoananalogvoltagethatisproportionalinsizetothenumberrepresentedbythecode Thisvoltageisheldsteadythroughzeroorderholduntilthenextcodeisavailable one samplingintervallater Thiscreatesastaircase likesignalthatcontainsfrequenciesabove WHz Thesesignalsareremovedwithasmoothinglowpassfilter thelaststepinD Aconversion Figure9 2Digital to AnalogConversions Theimagesofeachfrequencyfpresentinasampledsignalappear throughsampling attheinfinitenumberoffrequencies kfs fHz WhenthesamplingrateislowerthantherequiredNyquistrate thatisfs 2W imagesofhighfrequencysignalserroneouslyappearinthebaseband orNyquistrange duetoaliasing Whilethisundersamplingisnormallyavoided itcanbeexploited Forexample signalswhosefrequenciesare restrictedtoanarrowbandofhighfrequenciescanbesampledataratesimilartotwicethewidthofthebandinsteadoftwicethemaximumfrequency Alloftheimportantsignalcharacteristicscanbededucedfromthecopyofthespectrumthatappearsinthebasebandthroughsampling Dependingontherelationshipbetweenthesignalfrequenciesandthesamplingrate spectralinversionmaycausetheshapeofthespectruminthebasebandtobeinvertedfromthetruespectrumofthesignal 1 2 Technologiesfordigitalsignalprocessing Ifauniversalmicroprocessorsolutionexistedwithwhicheverydesigncouldberealized theelectronicsindustrywouldn tbeaverycompetitiveplace 2 However typicallyinmostelectronicdesigns morethanoneprocessortechnologycanbeusedtoimplementtherequiredfunctions Thetrickis ofcourse tochoosetheonethatbestdeliverstheperformance size powerconsumption features softwareandtoolstogetthejobdonefast withoutbreakingthebudget Afteralmosttwodecadesofdevelopment digitalsignalprocessorscontinuetotaketheplaceofcompetitiveprocessors Digitalsignalprocessorsare afterall atthecenterofsignalprocessing Adigitalsignalprocessor DSP isatypeofmicroprocessor onethatisincrediblyfastandpowerful ADSPisuniquebecauseitprocessesdatainrealtime Thisreal timecapabilitymakesaDSPperfectforapplicationsthatcannottolerateanydelays Forexample didyouevertalkonacellphonewheretwopeoplecouldn ttalkatonce Youhadtowaituntiltheotherpersonfinishedtalking Ifyoubothspokesimultaneously thesignalwascut youdidn theartheotherperson Withtoday sdigitalcellphones whichuseDSP youcantalknormally TheDSPinsidecellphonesprocesssoundssorapidlyyouhearthemasquicklyasyoucanspeak inrealtime HerearejustsomeoftheadvantagesofdesigningwithDSPsoverothermicroprocessors Single cyclemultiply accumulateoperations Real timeperformancesimulationandemulation Flexibility Reliability Increasedsystemperformance Reducedsystemcost However therearesomeoftheotheralternativesavailablefordigitalsignalprocessing HowtheycomparetoDSPs TheFPGAAlternative Field ProgrammableGateArrays FPGA havethecapabilityofbeingreconfigurablewithinasystem whichcanbeabigadvantageinapplicationsthatneedmultipletrialversionswithindevelopment offeringreasonablyfasttimetomarket Theyalsooffergreaterrawperformanceperspecificoperationbecauseoftheresultingdedicatedlogiccircuit However FPGAsaresignificantlymoreexpensiveandtypicallyhavemuchhigherpowerdissipationthanDSPswithsimilarfunctionality Assuch evenwhenFPGAsarethechosenperformancetechnologyindesignssuchaswirelessinfrastructure DSPsaretypicallyusedinconjunctionwithFPGAstoprovidegreaterflexibility betterprice performanceratios andlowersystempower TheASICAlternative Application specificICs ASIC canbetailoredtoperformspecificfunctionsextremely well andcanbemadequitepowerefficient However sinceASICSarenotfield programmable theirfunctionalitycannotbeiterativelychangedorupdatedwhileinproductdevelopment Assuch everynewversionoftheproductrequiresaredesignandtripsthroughthefoundry anexpensiveproposition andanimpedimenttorapidtime to market 3 ProgrammableDSPs ontheotherhand canbeupdatedwithoutchangingthe silicon merelychangethesoftwareprogram greatlyreducingdevelopmentcosts and availingaftermarketfeatureenhancementswithmerecodedownloads Consequently more oftenthannot whenyouseeASICsinrealtimesignalprocessingapplications theyaretypicallyemployedasbusinterfaces gluelogic and orfunctionalacceleratorsforaprogrammableDSP basedsystem TheGPPAlternative IncontrasttoASICsthatareoptimizedforspecificfunctions general purposemicroprocessors GPPs arebestsuitedforperformingabroadarrayoftasks However forapplicationsinwhichtheendproductmustprocessanswersinrealtime ormustdosowhilepoweredbyconsumerbatteries GPPscomparativelypoorrealtimeperformanceandhighpowerconsumptionallbutrulesthemout 4 Moreandmore theseprocessorsarebeingseenasthedinosaursoftheindustry tooencumberedwithPCcompatibilityanddesktopfeaturestoadapttothechangingrealtimemarketplace Astheworldembracestinyhand heldwireless enabledproductsthatrequirepowerdissipationmeasuredinmilliwatts notthewattsthattheseprocessorsconsume DSPsaretheprogrammabletechnologyofchoice ThattrendisboundtocontinueasdigitalInternetappliancesgetsmaller fasterandmoreportable Notes 1 Dependingontherelationshipbetweenthesignalfrequenciesandthesamplingrate spectralinversionmaycausetheshapeofthespectruminthebasebandtobeinvertedfromthetruespectrumofthesignal 根据信号频率和采样频率之间的关系的不同 可能出现 频谱反转 现象 基带频谱的形状和信号真实频谱的形状正好相反 beinvertedfrom 和 相反 所谓基带是指不加任何调制过程的数字信号传输 基带带宽全部用来传送数字脉冲信号 并可以通过时分复用的方式进行多路数字信号的传输 2 Ifauniversalmicroprocessorsolutionexistedwithwhicheverydesigncouldrealized theelectronicsindustrywouldn tbeaverycompetitiveplace 假如存在可用以实现任何设计的通用微处理器的话 电子行业就不会竞争得如此激烈了 本句为虚拟语气 3 Assuch everynewversionoftheproductrequiresaredesignandtripsthroughthefoundry anexpensiveproposition andanimpedimenttorapidtime to market 而且 每次推出一个新产品都需要重新设计并经历所有制造流程 这样做不但造价昂贵 而且不利于迅速上市 time to market的意思为 上市时间 foundry是指为第三方制造芯片的半导体制造商 可以指那些出售其富余生产能力的大型芯片制造企业 也可以是指专为其他公司制造芯片的企业 4 However forapplicationsinwhichtheendproductmustprocessanswersinrealtime ormustdosowhilepoweredbyconsumerbatteries GPPscomparativelypoorrealtimeperformanceandhighpowerconsumptionallbutrulesthemout 然而 在最终产品必须实时响应的应用中 或者必须在电池供电下实现实时响应的应用中 由于GPP实时性能较差 功耗大 因此就被排除在外了 allbut此处作rulethemout的状语 涵义为 几乎 差一点 ruleout的意思是 将 排除在外 Exercises 1 Fillintheblanks 1 Thefirstessentialstepinconversionistosampleananalogsignal 2 Thelengthoftheisthesameasthe andthereciprocalofthesamplingperiodisthesamplingfrequencyfs 3 Tosummarize A Dcomprises and 4 Aisatypeofmicroprocessor onethatisincrediblyfastandpowerful 5 IncontrasttoASICsthatareoptimizedforspecificfunctions arebestsuitedforperformingabroadarrayoftasks 6 havethecapabilityofbeingreconfigurablewithinasystem whichcanbeabigadvantageinapplicationsthatneedmultipletrialversionswithindevelopment offeringreasonablyfasttimetomarket 2 TranslatethefollowingparagraphintoChinese Thefirststepinconvertingananalogsignalissampling Thisstepisaccomplished usingasampleandholdcircuit whichgrabsasamplefromthesignalandholdsitsteadyuntilthenextsamplingtime Samplesarenormallycollectedatregulartimeintervals calledsamplingperiods Iftherateofthesamplingisnotadequate distortioncalledaliasingcanoccur TheoutputfromthesampleandholdcircuitispassedtoanA Dconverter whichchoosesaquantizationlevelthatisclosesttotheactualamplitudeofthesignal ThisisthesecondstepinA Dconversion Thenumberoflevelstochoosefromdependsonthenumberofbitsusedbytheconverter forNbits 2Nlevelsarepossible Sinceanalog amplitudescannotingeneralberepresentedperfectlyinadigitalsystem quantizationerrorsoccur 3 TranslatethefollowingsentencesintoEnglish 1 数字信号处理是无数家用和商用系统中的关键部分 其应用领域与日俱增 因此 DSP正在成为技术专家和工程师专业知识的一个重要组成部分 2 数字信号处理可分为定点和浮点两大类 定点和浮点指的是器件内用于存储和操作数据的格式 定点数字信号处理通常用最少16位来表示每个数据 典型的浮点数字信号处理器用最少32位来存储每个数据 3 和其他科学和工程应用一样 数字信号处理器通常使用汇编语言或者C语言进行编程 然而 DSP程序和传统软件任务不同 首先 程序通常短得多 如100行而不是1万行 其次 执行速度往往是其应用的关键部分 PassageBDigitalSignalProcessors Digitalsignalprocessingtaskscanbeperformedbyallprocessors Specializeddigitalsignalprocessors DSPs however performthesetasksmostefficientlyandmostquickly WhiletraditionalprocessorsfollowtheVonNeumannarchitecturemodel asshowninFigure9 3 whichassumesasharedsinglememorytobeusedforbothprograminstructionsanddata DSPsusetheHarvardormodifiedHarvardarchitecture asshownin Figure9 4 whichincludesmultipleprogramanddatamemories alongwithmultiplebusestoaccessthem 1 Thisarrangementmeansthatmuchlesswaitingisrequiredwhen instructionsor numbersarefetchedfrommemory Infactatleastoneofeachcanbefetchedsimultaneously Suchoverlappingoftasksiscalledpipelining Inadditiontomultiplememoriesandbuses allDSPshavefastmultipliers accumulators andshifters andmanyhavehardwaresupportforcircularbuffers Addressgeneratorscanspeedupaccessestomemorylocationsreferencedbyregisters Figure9 3VonNeumannArchitecture Figure9 4HarvardArchitecture DSPsareavailableintwomajorclasses fixedpointandfloatingpoint Thefixedpointclassrepresentsrealnumbersinafixednumberofbits Thepositionofthebinarypoint similartothedecimalpoint canbecontrolledbytheprogrammer anddeterminestherangeofnumbersthatcanberepresented Astherangeincreases though theavailableprecisiongoesdown sincefewerbitslietotherightofthebinarypoint In16bits theformats16 0 15 1 14 2 13 3 12 4 11 5 10 6 9 7 8 8 7 9 6 10 5 11 4 12 3 13 2 14 and1 15arepossible Thedynamicrange calculatedas20log FullScaleRange SmallestResolvableDifference remainsthesameforall16 bitformats 20log216 96 3dB FloatingpointDSPsrepresentrealnumbersusingamantissaandanexponent similartoscientificnotation Manycombinemantissaandexponentintoa32 bitnumber The dynamicrangeforfloatingpointdevicesiscalculatedfromthelargestandsmallestmultipliers2E whereEistheexponent Thus forarepresentationthatuses24bitsforthemantissaand8bitsforthesignedexponent thedynamicrangeis20lg 2127 2 128 1535 3dB Alargedynamicrangemeansthesystemhasgreatpowertorepresentawiderangeofinput signals fromverysmalltoverylarge AssemblylanguageisthecommandlanguageforDSPs DSPsoftenhavespecializedinstructionsthatmakeprogrammingforcommonDSPtasksmoreconvenientandmore efficient Forexample mostDSPsoffermulti functioninstructionsthatexploittheirparallelarchitecture Otherconstructsthatarefrequentlyofferedareefficientloopingschemes sincesomanyDSPoperationsinvolveagreatdealofrepetition ChoosingaDSPforaparticularapplicationisnotalwayseasy Thefirstdecisionisonwhethertochooseafixedpointorafloatingpointdevice 2 Generally fixedpointdevicesarecheaperandquicker butfloatingpointdevicesaremoreconvenienttoprogramandmoresuitedtocalculation intensivealgorithms Second thedatawidthoftheDSPdetermineshowaccuratelyitcanrepresentnumbers Speedisanotherissue notonlyhowmanycyclesoccurineachsecond butalsohowmanyinstructionsexecuteineachcycleandhowmuchworkeachoftheseinstructionsaccomplishes OnewaytoassesstheminimumrequirementsfortheDSPistoestimatehowmanyinstructionsmustbeexecutedforeachreceivedsample Whenthisnumberismultipliedbythesamplingfrequency theminimumrequirednumberofinstructionspersecondisobtained ThespecifichardwareandsoftwarefeaturesofferedbyaparticularDSPcanmakeonechoicebetterthananother ascantheamountofon chipmemoryavailable SometimesDSPsarechosenbecausewell matchedsupportinghardware particularlyA DandD Aconverters isobtainable Frequently thequalityandconvenienceofthesoftwaretools forbothlowlevelandhighlevelprogramminglanguages arealsomajorfactors asistheavailabilityofthirdpartysoftware Asalways costisafactor Infact quiteoften theDSPthatisfastestandoffersthemostfeatures butalsofitsthebudget istheoneselected DSPscanbepurchasedinthreeforms asacore asaprocessor andasaboardlevelproduct InDSP theterm core referstothesectionoftheprocessorwherethekeytasksarecarriedout includingthedataregisters multiplier ALU addressgenerator andprogramsequencer Acompleteprocessorrequirescombiningthecorewithmemoryandinterfacestotheoutsideworld Whilethecoreandtheseperipheralsectionsare designedseparately theywillbefabricatedonthesamepieceofsilicon makingthe processorasingleintegratedcircuit SupposeyoubuildcellulartelephonesandwanttoincludeaDSPinthedesign YouwillprobablywanttopurchasetheDSPasaprocessor thatis anintegratedcircuitthatcontainsthecore memoryandotherinternalfeatures ToincorporatethisICinyourproduct youhavetodesignaprintedcircuitboardwhereitwillbesolderedinnexttoyourotherelectronics ThisisthemostcommonwaythatDSPsareused Now supposethecompanyyouworkformanufacturesitsownintegratedcircuits Inthiscase youmightnotwanttheentireprocessor justthedesignofthecore Aftercompletingtheappropriatelicensingagreement youcanstartmakingchipsthatarehighlycustomizedtoyourparticularapplication Thisgivesyoutheflexibilityofselectinghowmuchmemoryisincluded howthechipreceivesandtransmitsdata howitispackaged andsoon CustomdevicesofthistypeareanincreasinglyimportantsegmentoftheDSPmarketplace ThereareseveraldozencompaniesthatwillsellyouDSPsalreadymountedonaprintedcircuitboard ThesehavesuchfeaturesasyourDSPsalreadymountedonaextramemory A DandD Aconverters EPROMsockets multipleprocessorsonthesameboard andsoon Whilesomeoftheseboardsareintendedtobeusedasstandalonecomputers mostareconfiguredtobepluggedintoahost suchasapersonalcomputer CompaniesthatmakethesetypesofboardsarecalledThirdPartyDevelopers ThebestwaytofindthemistoaskthemanufactureroftheDSPyouwanttouse LookattheDSPmanufacturer swebsite ifyoudon tfindalistthere sendthemane mail Theywillbemorethanhappytotellyouwhoareusingtheirproductsandhowtocontactthem KeepinmindthatthedistinctionbetweenDSPsandothermicroprocessorsisnot alwaysaclearline Forinstance lookathowInteldescribestheMMXtechnologyadditiontoitsPentiumprocessor Intelengineershaveadded57powerfulnewinstructionsspecificallydesignedtomanipulateandprocessvideo audioandgraphicaldataefficiently Theseinstructionsareorientedtothehighlyparallel repetitivesequencesoftenfoundinmultimediaoperations Inthefuture wewillundoubtedlyseemoreDSP likefunctionsmergedintotraditionalmicroprocessorsandmicrocontrollers TheInternetandothermultimediaapplicationsareastrongdrivingforceforthesechanges Theseapplicationsareexpandingsorapidly intwentyyearsitisverypossiblethatthedigitalsignalprocessormaybethe traditional microprocessor Notes 1 WhiletraditionalprocessorsfollowtheVonNeumannarchitecturemodel whichassumesasharedsinglememorytobeusedforbothprograminstructionsanddata DSPsusetheHarvardormodifiedHarvardarchitecture whichincludesmultipleprogramanddatamemories alongwithmultiplebusestoaccessthem 传统的处理器遵循冯 诺依曼模型 该模型采用一个单一的共享存储器 同时存储程序指令和数据 而数字信号处理器使用的是哈佛结构或改进的哈佛结构 该结构包含多个程序和数据存储器以及访问这些存储器的多套总线 冯 诺依曼结构 取名自美国杰出的数学家约翰 冯 诺依曼 JohnVon Neumann 1903 1957 他引导了20世纪初许多重大数学发现 他的主要成就包括 提出了存储程序计算机 storedprogramcomputer 的概念 对量子力学的数学公式化及在原子弹方面的工作 哈佛结构 取名自20世纪40年代HowardAiken 1900 1973 领导的在哈佛大学 HarvardUniversity 做的研究工作 2 Thefirstdecisionisonwhethertochooseafixedpointorafloatingpointdevice 首先要决定的是选择定点器件还是浮点器件 定点和浮点指的是器件内用于存储和操作数据的格式 通常 定点数字信号处理最少用16位来表示每个数据 典型的浮点数字信号处理器最少用32位来存储每个数据 Exercises 1 Fillintheblanks 1 Thefirstdecisionisonwhethertochooseapointorapointdevice 2 ThespecifichardwareandsoftwarefeaturesofferedbyaparticularDSPcanmakeonechoicebetterthananother ascantheamountofavailable 3 SometimesDSPsarechosenbecausesupportinghardware particularly A DandD Aconverters isobtainable 4 DSPscanbepurchasedinthreeforms and 5 Companiesthatmakethesetypesofboardsarecalled 6 Acompleteprocessorrequirescombiningthecorewithand totheoutsideworld 2 TranslatethefollowingparagraphsintoChinese 1 Theprimaryreasonforprocessingreal worldsignalsistoextractinformationfromthem Thisinformationnormal