1ChallengesChallengesShift toShift touuReuse StrategyReuse StrategyuuHigher Level of Higher Level of AbstractionsAbstractionsuuSoftware !!!Software !!!2PERCENT OF TRANSISTORS WITHIN EMBEDDED PERCENT OF TRANSISTORS WITHIN EMBEDDED IP (EXCLUDES MEMORY) IP (EXCLUDES MEMORY) 1005Random LogicTransistorsTransistors WithinEmbedded IP0.35 0.25 0.18 0.15 0.13 0.11 0.10 0.08 0.07FeatureDimension (µm):20051997 1998 1999 2000 2001 2002 2003 2004Year:Transistors (%)3TRENDS IN EMBEDDED IPTRENDS IN EMBEDDED IPDESIGNS WITH EMBEDDED IP WILL DOMINATE THE SYSTEM IC BUSINESS IN THE FUTURE IC MarketSystem ICMarketDesignsWithEmbeddedIP0501001502002503003504001998 1999 2000 2001 2002 2003 2004 2005 2006YearValue ($B)1998 1999 2000 2001 2002 2003 2004 2005 2006 Total IC Value ($M) 112,005 133,426 174,723 164,592 173,506 197,118 227,752 269,078 313,214 Growth rate (%) NA 19.1 31.0 (5.8) 5.4 13.6 15.5 18.1 16.4 System IC Value ($M) 43,506 50,493 64,366 67,581 76,034 92,804 115,123 145,700 175,767 Growth rate (%) NA 16.1 27.5 5.0 12.5 22.1 24.0 26.6 20.6 Percent total (%) 38.8 37.8 36.8 41.1 43.8 47.1 50.5 54.1 56.1 IP-based design Value ($M) 15,706 19,894 30,123 39,129 51,247 68,582 90,602 122,679 153,093 Growth rate (%) NA 26.7 51.4 29.9 31.0 33.8 32.1 35.4 24.8 Percent system IC (%) 36.1 39.4 46.8 57.9 67.4 73.9 78.7 84.2 87.14Computing for Embedded SystemsComputing for Embedded SystemsImage “borrowed” from an Iomega advertisement for Y2K software and disk drives, Scientific American, September 1999.5EMBEDDED SYSTEM: THE REAL STORYEMBEDDED SYSTEM: THE REAL STORYFABIO ROMEOFABIO ROMEODesign Design Automation ConferenceAutomation ConferenceLas Vegas, Las Vegas, JuneJune20th, 200120th, 20016COMPLEXITY, QUALITY, TIMECOMPLEXITY, QUALITY, TIME--TOTO--MARKET: TODAY MARKET: TODAY MEMORYMEMORY 256 KB256 KB 128 KB128 KB 184 KB184 KB 8 MB8 MBLINES OF CODELINES OF CODE 50.00050.000 30.00030.000 45.00045.000 300.000300.000CHANGING RATECHANGING RATE 3 YEARS3 YEARS 2 YEARS2 YEARS 1 YEAR1 YEAR < 1 YEAR< 1 YEARDEV. EFFORTDEV. EFFORT 40 MAN40 MAN--YEARYEAR 12 MAN12 MAN--YEARYEAR 30 MAN30 MAN--YEARYEAR 200 MAN200 MAN--YEARYEARVALIDATION TIMEVALIDATION TIME 5 MONTHS5 MONTHS 1 MONTH1 MONTH 2 MONTHS2 MONTHS 2 MONTHS2 MONTHSTIME TO MARKETTIME TO MARKET 24 MONTHS24 MONTHS 18 MONTHS18 MONTHS 12 MONTHS12 MONTHS < 12 MONTHS< 12 MONTHSPWT UNITPWT UNIT BODY GATEWAYBODY GATEWAYTELEMATICTELEMATICUNITUNITINSTRUMENTINSTRUMENTCLUSTERCLUSTERPRODUCTIVITYPRODUCTIVITY 6 LINES/DAY6 LINES/DAY 10 LINES/DAY10 LINES/DAY 6 LINES/DAY6 LINES/DAY 10 LINES/DAY*10 LINES/DAY*RESIDUAL DEFECTRESIDUAL DEFECTRATE @ END OF RATE @ END OF DEVDEV3000 PPM3000 PPM 2500 PPM2500 PPM 2000PPM2000PPM 1000 PPM1000 PPM* C++CODE7SW Complexity01002003004005006007008001995 1997 2000 2003 2005K-Linesof codeSW defects at End-of-Design1101001000100001995 1997 2000 2003 2005ppmKEY DRIVERSKEY DRIVERS•• QUALITYQUALITY•• TIMETIME--TOTO--MARKETMARKET•• COMPLEXITY MGMTCOMPLEXITY MGMTWINNING SOLUTIONSWINNING SOLUTIONS••PLATFORM & APPLICATIONSPLATFORM & APPLICATIONS••DESIGN METHODOLOGIESDESIGN METHODOLOGIES••TESTINGTESTINGCOMPLEXITY, QUALITY, TIMECOMPLEXITY, QUALITY, TIME--TOTO--MARKET: FUTURE TRENDS MARKET: FUTURE TRENDS Time-to-Market05101520253035401995 1997 2000 2003 2005MonthsTelematicsTelematics Power TrainPower TrainBody Body andand NetworkNetworkSoftware ProductivitySoftware ProductivityRoger G. FordhamRoger G. FordhamDirector, Performance ExcellenceDirector, Performance ExcellenceMotorola, Global Software GroupMotorola, Global Software [email protected]@Motorola.comJune 6,June 6,200120019The Software Development ProblemThe Software Development ProblemuuProduct Quality is POORProduct Quality is POORuuDevelopment Productivity is LOWDevelopment Productivity is LOWuuDevelopment CycleDevelopment Cycle--time is TOO LONGtime is TOO LONGSource of Industry Data: Capers Jones(2000) Software Assessments, Benchmarks, and Best Practices, Addison-Wesley, pp339-340.Industry Average4.13Ind. Best-in-Class8.76Customer Expectation>40PRODUCTIVITYFunction Point per Staff MonthIndustry Average0.44Ind. Best-in-Class0.08Customer Expectation<0.00044QUALITYDelivered Defects per Function PointIndustry Average36Ind. Best-in-Class25Customer Expectation<3-6CYCLETIMESchedule in MonthsSystem Software (of size 10,000 Function Points)10What are the Remedies?What are the Remedies?uuSignificant commitment to CONTINUOUS IMPROVEMENTSignificant commitment to CONTINUOUS IMPROVEMENTuuEffective use of DESIGN METHODOLOGIESEffective use of DESIGN METHODOLOGIESuuEffective use of development/management AUTOMATIONEffective use of development/management AUTOMATIONP / PCBalance90 : 10 %SDLUMLFML11Software Architecture TodaySoftware Architecture TodayPoor common infrastructure. Weak specialization of functions. Poor resource management. Poor planning.12Software Architecture Tomorrow?Software Architecture Tomorrow?13The “C” or “Java” ParadigmThe “C” or “Java” ParadigmuuNot abstract enough to capture functionality onlyNot abstract enough to capture functionality onlyuuNot detailed enough to capture important parameters such as Not detailed enough to capture important parameters such as performance, energy consumption, “size”performance, energy consumption, “size”14What about “real time”?What about “real time”?“Make it faster!”15Problems with Past Design MethodProblems with Past Design MethoduuLack of unified hardwareLack of unified hardware--software representationsoftware representationuuPartitions are defined Partitions are defined a prioria priorissCan't verify the entire systemCan't verify the entire systemssHard to find incompatibilities across HWHard to find incompatibilities across HW--SW boundarySW boundary(often found only when prototype is built)(often found only when prototype is built)uuLack of wellLack of well--defined design flowdefined design flowssTimeTime--toto--market problemsmarket problemsssSpecification revision becomes difficultSpecification revision becomes difficult16TodayDesign Effort vs. System Design ValueDesign Effort vs. System Design ValueEffort/ValueLevel of AbstractionFunctionHW/SWArchitectureRTL - SWMask - ASMTomorrowRTL/Gate “platform”RTL/Gate “platform”Design Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelDesign Entry LevelConceptualConceptualGapGapDesign Entry LevelDesign Entry
View Full Document
Unlocking...