ComputerOrganizationandArchitecture,10th Edition,byWilliamStallings
CHAPTER 2: PERFORMANCE ISSUES
TRUE OR FALSE
T F 1. Yearbyyearthecostofcomputersystemscontinuestorise.
T F 2. Processorsaresoinexpensivethatwenowhavemicroprocessors wethrowaway.
T F 3. Workstationsystemscannotsupporthighlysophisticated engineeringandscientificapplications.
T F 4. TheIASistheprototypeofallsubsequentgeneral-purpose computers.
T F 5. Cloudserviceprovidersusemassivehigh-performancebanksof serverstosatisfyhigh-volume,high-transaction-rateapplications forabroadspectrumofclients.
T F 6. Therawspeedofthemicroprocessorwillnotachieveitspotential unlessitisfedaconstantstreamofworktodointheformof computerinstructions.
T F 7. Superscalarexecutionisthesameprincipleasseeninanassembly line.
T F 8. Branchpredictionpotentiallyincreasestheamountofwork availablefortheprocessortoexecute.
T F 9. Rawspeedisfarmoreimportantthanhowaprocessorperforms whenexecutingagivenapplication.
T F 10. Thecacheholdsrecentlyaccesseddata.
T F 11. Operationsperformedbyaprocessor,suchasfetchingan instruction,decodingtheinstruction,performinganarithmetic operation,andsoon,aregovernedbyasystemclock.
T F 12. Acommonmeasureofperformanceforaprocessoristherateat whichinstructionsareexecuted,expressedasmillionsof instructionspersecond(MIPS).
ComputerOrganizationandArchitecture,10th Edition,byWilliamStallings
T F 13. Designerswrestlewiththechallengeofbalancingprocessor performancewiththatofmainmemoryandothercomputer components.
T F 14. Astraightcomparisonofclockspeedsondifferentprocessors tellsthewholestoryaboutperformance.
T F 15. MeasuressuchasMIPSandMFLOPShaveprovenadequateto evaluatingtheperformanceofprocessors.
MULTIPLE CHOICE
1. Multipleparallelpipelinesareusedin__________.
A. speculativeexecution B. dataflowanalysis
C. superscalarexecution D. branchprediction
2. Thedesktopapplication(s)thatrequirethegreatpoweroftoday’s microprocessor-basedsystemsinclude___________.
A. imageprocessing B. speechrecognition
C. videoconferencing D. alloftheabove
3. ___________potentiallyincreasestheamountofworkavailableforthe processortoexecute.
A. Branchprediction B.Performancebalance
C. Pipelining D. BIPS
4. Theinterfacebetweenprocessorand___________isthemostcrucialpathway intheentirecomputerbecauseitisresponsibleforcarryingaconstantflow ofprograminstructionsanddatabetweenmemorychipsandtheprocessor.
A. mainmemory B. pipeline
C. clockspeed D. controlunit
ComputerOrganizationandArchitecture,10th Edition,byWilliamStallings
5. The__________isarelativelysmallfastmemoryinterposedbetweenalarger, slowermemoryandthelogicthataccessesthelargermemory.
A. peripheral B. cache
C. processor
D. arithmeticandlogicunit
6. Anincreaseinclockratemeansthatindividualoperationsareexecuted_____.
A. thesame
B. slower
C. withverylittlechange D. morerapidly
7. A__________isacoredesignedtoperformparalleloperationsongraphicsdata.
A. MIC B. ALU
C. GPU D. PGD
8. A(n)__________Meanisagoodcandidateforcomparingtheexecutiontime performanceofseveralsystems.
A. Composite B. Arithmetic
C. Harmonic D. Evaluation
9. __________lawdealswiththepotentialspeedupofaprogramusingmultiple processorscomparedtoasingleprocessor.
A. Moore’s B. Amdahl’s
C. Little’s D. Murphy’s
10.Oneincrement,orpulse,ofaclockisreferredtoasa__________.
A. clockcycle
C. clockspeed
B. clockrate
D. cycletime
ComputerOrganizationandArchitecture,10th Edition,byWilliamStallings
11.Theuseofmultipleprocessorsonthesamechipisreferredtoas__________ andprovidesthepotentialtoincreaseperformancewithoutincreasingthe clockrate.
A. multicore B. GPU
C. datachannels
D. MPC
12.Withrespecttochangesinvalues,the__________Meangivesequalweighttoall ofthevaluesinthedataset.
A. Harmonic
C. Composite
B. Arithmetic
D. Geometric
13.The__________measurestheabilityofacomputertocompleteasingletask.
A. clockspeed
C. executecycle
B. speedmetric
D. cycletime
14. Ameasurementofhowmanytasksacomputercanaccomplishinacertain amountoftimeiscalleda(n)__________.
A. real-timesystem B. applicationanalysis
C. cyclespeed
D. throughput
15. ThebestknownoftheSPECbenchmarksuitesis__________.
A. SPECCPU2006
C. SPECsfs2008
SHORT ANSWER
B. SPECjvm2008
D. SPECSC2013
1. __________enablesaprocessortoworksimultaneouslyonmultiple instructionsbyperformingadifferentphaseforeachofthemultiple instructionsatthesametime.
2. ___________istheabilitytoissuemorethanoneinstructionineveryprocessor clockcycle.
3. With__________theprocessorlooksaheadintheinstructioncodefetchedfrom memoryandpredictswhichbranches,orgroupsofinstructions,arelikelyto beprocessednext.
4. __________enablestheprocessortokeepitsexecutionenginesasbusyas possiblebyexecutinginstructionsthatarelikelytobeneeded.
5. Traditionallyfoundonaplug-ingraphicscard,a_________isusedtoencode andrender2Dand3Dgraphicsaswellasprocessvideo.
6. __________Lawappliestoaqueuingsystem.
7. Thethreecommonformulasusedforcalculatingameanarearithmetic, harmonic,and__________.
8. The__________Meanusedforatime-basedvariable,suchasprogram executiontime,hastheimportantpropertythatitisdirectlyproportionalto thetotaltime.
9. The_________Meanispreferredwhencalculatingrates.
10. The__________Meangivesconsistentresultsregardlessofwhichsystemis usedasareference.
11. _________metricarerequiredforallreportedresultsandhavestrict guidelinesforcompilation.
12. A_________suiteisacollectionofprograms,definedinahigh-levellanguage, thattogetherattempttoprovidearepresentativetestofacomputerina particularapplicationorsystemprogrammingarea.
13. Atthemostfundamentallevel,thespeedofaprocessorisdictatedbythe pulsefrequencyproducedbytheclock,measuredincyclespersecond,or _________.
14. Thebest-knowncollectionofbenchmarksuitesisdefinedandmaintained byanindustryconsortiumknownas__________.
15. __________lawdealswiththepotentialspeedupofaprogramusingmultiple processorscomparedtoasingleprocessor.
ComputerOrganizationandArchitecture,10th Edition,byWilliamStallings
CHAPTER 2: PERFORMANCE ISSUES
TRUE OR FALSE
1. F 2. T 3. F 4. T 5. T 6. T 7. F 8. T 9. F 10. T 11. T 12. T 13. T 14. F 15. F
MULTIPLE CHOICE
1. C 2. D 3. A 4. A 5. B 6. D 7. C 8. B 9. B 10. A 11. A 12. D 13. B 14. D 15. A
ComputerOrganizationandArchitecture,10th Edition,byWilliamStallings
SHORT ANSWER
1. Pipelining
2. Superscalarexecution
3. branchprediction
4. Speculativeexecution
5. GPU(graphicsprocessingunits)
6. Little’s
7. geometric
8. Arithmetic
9. Harmonic
10. Geometric
11. Base
12. benchmark
13. Hertz(Hz)
14. SystemPerformanceEvaluationCorporation(SPEC)
15. Amdahl’s