advanced computer architecture fundamental of computer design instruction set principles and...
TRANSCRIPT
![Page 1: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/1.jpg)
Advanced Computer Architecture
• Fundamental of Computer Design• Instruction Set Principles and Examples• Pipelining:Basic and Intermediate Concepts• Memory Hierarchy Design• Storage System• Instruction-Level Parallelism:Concepts and
Challenges• Exploiting Instruction-Level Parallelism with
Software Approaches• Multiprocessors and Thread-Level Parallelism
![Page 2: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/2.jpg)
Forces on Computer Architecture
ComputerArchitecture
Technology ProgrammingLanguages
OperatingSystems
History
Applications
(A = F / M)
![Page 3: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/3.jpg)
Fundamentals of Computer Design
• Introduction• The Task of the Computer Designer• Technology Trends• Cost Price, and Their Trends• Performance• Quantitative Principles of Computer Design• Putting It All Together: Performance and Price-
Performance• Power Consumption and Efficiency• Fallacies and Pitfalls
![Page 4: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/4.jpg)
Microprocessor Performance
![Page 5: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/5.jpg)
Cost of Downtime
![Page 6: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/6.jpg)
System Characteristics of the the Three Computing Classes
![Page 7: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/7.jpg)
Technology Trends• Clock Rate: ~30% per year• Transistor Density: ~35%• Chip Area: ~15%• Transistors per chip: ~55%• Total Performance Capability: ~100%• by the time you graduate...
– 3x clock rate (3-4 GHz)– 10x transistor count (1 Billion transistors)– 30x raw capability
• plus 16x DRAM density, 32x disk density
![Page 8: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/8.jpg)
The Most Important Functional Requirements and Architect Faces
![Page 9: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/9.jpg)
1.4 Cost, Price, and Their TrendsPrices of six generation of DRAMS
![Page 10: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/10.jpg)
The Price of an Intel Pentium III over Time
![Page 11: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/11.jpg)
What is “Computer Architecture”?
• Coordination of many levels of abstraction• Under a rapidly changing set of forces• Design, Measurement, and Evaluation
I/O systemInstr. Set Proc.
Compiler
OperatingSystem
Application
Digital DesignCircuit Design
Instruction Set Architecture
Firmware
Datapath & Control
Layout
![Page 12: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/12.jpg)
Computer Architecture Topics
• NetworksM
Interconnection NetworkS
PMPMPMP° ° °
Topologies,Routing,Bandwidth,Latency,Reliability
Processor-Memory-Switch
MultiprocessorsNetworks and Interconnections
Network Interfaces
Shared Memory,Message Passing,Data Parallelism
![Page 13: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/13.jpg)
Photograph of an Intel Pentium 4
![Page 14: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/14.jpg)
This 8-inch Wafer Contains 564 MIPS64 20k Processors
![Page 15: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/15.jpg)
areaDiesDiameterWafer
AreasDiesDiameterWafer
waferperDies
2
)2/( 2
![Page 16: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/16.jpg)
Die yield
areaDieareaunitperDefect
YieldWaferYieldDies 1
![Page 17: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/17.jpg)
Estimated distribution of PC Costs
DropCostRAM
![Page 18: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/18.jpg)
The components of price for a $1000 PC
![Page 19: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/19.jpg)
1.5 Measuring and Reporting Performance: Execution Time
Y
X
X
Y
X
Y
ePerformancePerformanc
ePerformanc
ePerformanctimeExecutiontimeExecution
n 1
1
![Page 20: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/20.jpg)
The programs in the SPEC CPU 2000 benchmark suites
![Page 21: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/21.jpg)
The Embedded Benchmark
EEMBC:The EDN Embedded Microprocessor Benchmarks ConsortiumEEMBC:The EDN Embedded Microprocessor Benchmarks Consortium
![Page 22: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/22.jpg)
The machine, software, and baseline tuning parameters for the CINT2000
![Page 23: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/23.jpg)
Comparing and Summarizing Performance
![Page 24: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/24.jpg)
Weighted arithmetic mean execution for three machines
![Page 25: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/25.jpg)
Execution times from Figure 1.15 normalized to each machine
![Page 26: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/26.jpg)
1.6 Quantitative Principles of Computer Design
• Amdahl’s Law
tenhancementheguwithouttaskentireforePerformancpossiblewhentenhancementhegutaskentireforcePerforrman
Speedupsin
sin
possiblewhentenhancementhegutaskentirefortimeExecutiontenhancementheguwithouttaskentirefortimeExecution
Speedupsin
sin
![Page 27: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/27.jpg)
Amdahl’s Law
• Enhancement more, Improvement more
))1((enhanced
enhancedenhancedoldnew Speedup
FractionFractiontimeExecutiontimeExecution
))1(
1
enhanced
enhancedenhanced
old
newoverall
SpeedupFraction
FractiontimeExecutiontimeExecution
Speedup
![Page 28: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/28.jpg)
Amdahl’s Law (Page41)
![Page 29: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/29.jpg)
Performance Comparison-Speedup Amdahl’s Law
![Page 30: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/30.jpg)
The CPU Performance Equation(Page42)
timecycleClockogramaforCyclesClockCPUtimeCPU Pr
timecycleClockninstructioperCyclesCountnInstructiotimeCPU
timecycleClockCPIICtimeCPU
ogramSeconds
cyclesClockSeconds
nInstructioCyclesClock
ogramnsInstructio
timeCPUPrPr
![Page 31: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/31.jpg)
CPU time
• Clock cycle time---Hardware technology and organization
• CPI---Organization and instruction set architecture
• Instruction count---Instruction set architecture and compiler technology
![Page 32: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/32.jpg)
Overall CPI
timecycleClockCPIICtimeCPU i
n
ii
)(
1
i
n
i
ii
n
ii
overall CPIcountnInstructio
ICcountnInstructio
CPIICCPI
1
1)(
![Page 33: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/33.jpg)
Overall CPI Comparison (Page44)
![Page 34: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/34.jpg)
CPI Com.
![Page 35: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/35.jpg)
Speedup
• Pipeline(Operation manual,Regular design ,…)
• Principle of locality-Temporal and Spatial
• Parallelism-Multiple Units, processors and Cluster Servers, Distributed Computing,…
• Clock Rate ,(Circuits, Devices,…..)
• Optics,…..
![Page 36: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/36.jpg)
1.7 Performance and Price-performance Seven different desktop systems
![Page 37: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/37.jpg)
Performance and price-performance
![Page 38: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/38.jpg)
Performance and price-performance
![Page 39: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/39.jpg)
Cluster Systems
![Page 40: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/40.jpg)
The performance and the price-performance of cluster systems
![Page 41: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/41.jpg)
Price-performance of cluster systems
![Page 42: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/42.jpg)
Five different embedded processors
![Page 43: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/43.jpg)
Relative performance of five different embedded processors for three of the five EEMBC
benchmark suites
EEMBC:The EDN Embedded Microprocessor Benchmarks Consortium
![Page 44: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/44.jpg)
Relative price-performance of five different embedded processors for three of the five
EEMBC benchmark suites
![Page 45: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/45.jpg)
1.8 Power Consumption and Efficiency as the metric
![Page 46: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/46.jpg)
1.9 Fallacies and Pitfalls
• Fallacies—misbelieves(F)• Pitfalls---Easily made mistakes(P)
– The relative performance of two processors with the same instruction set architecture(ISA) can be judged by clock rate or by the performance of a single benchmark suite. (F)(Fig.1.28)
– Benchmarks remain valid indefinitely. (F)(Fig. 1.29)– Comparing hand-coded assembly and compiler-generated
high-level language performance.(P)– Peak performance tracks observed performance. (F)
![Page 47: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/47.jpg)
1.9 Fallacies and Pitfalls
• The Best design for a computer is the one that optimizes the primary objective without considering implementation.(F)
• Neglecting the cost of software in either evaluating a system or examining cost-performance. (P)
• Falling prey to Amdahl’s Law.(P)• Synthetic benchmarks predict performance for real
programs.
![Page 48: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/48.jpg)
1.9 Fallacies and Pitfalls
• MIPS is an accurate measure for computing performance among computers.(F)
66 1010
CPIrateClock
timeExcutioncountnInstructio
MIPS
610
MIPScountnInstructio
timeExcution
![Page 49: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/49.jpg)
1.9 Fallacies and Pitfalls
• The problem with using MIPS as a measure for comparison– MIPS is dependent on the instruction set,
making it difficult to compare MIPS of computer with different instruction sets.
– MIPS varies between programs on the same computer.
– Most importantly, MIPS can vary inversely to performance
![Page 50: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/50.jpg)
P4 and P3 performance comparison-Relative performance
![Page 51: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/51.jpg)
The tuning parameters for the SPEC CFP2000 report
![Page 52: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/52.jpg)
The evolution of the SPEC benchmarks
over time
![Page 53: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/53.jpg)
The performance of three embedded processors
![Page 54: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/54.jpg)
Measurements of peak performance and actual performance
![Page 55: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/55.jpg)
1.10 Concluding Remarks
• Make the common case fast• Chap. 2:The interaction between compiler
and instruction set design.• Part 3: Pipeline(Appendix A)• Part 4: Memory Design(Chap.5)• Part 5: Storage System (Chap. 7)• (Page1-86),(page87-168),(page A-1~A-87)
…..
![Page 56: Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory](https://reader036.vdocuments.site/reader036/viewer/2022062403/56649ef65503460f94c0a29f/html5/thumbnails/56.jpg)
1.11 Historical Perspective and References
• The First General-purpose Electronic Computers
• Important special-purpose machines
• Commercial Developments
• Development of Quantitative Performance Measures:Successes and Failures
reference
reference
MM MIPS
ePerformancePerformanc
MIPS