MS108 Computer System I Lecture 2 Metrics Prof. Xiaoyao Liang 2014/2/28 1

MS108 Computer System I

Lecture 2 Metrics

Prof. Xiaoyao Liang

2014/2/28 1

Performance MetricsPerformance Metrics

2

Performance MetricsPerformance Metrics

3

CPICPI

4

IPCIPC

5

IPCIPC

6

Amdahl’s LawAmdahl’s Law

7

Amdahl’s LawAmdahl’s Law

8

Amdahl’s LawAmdahl’s Law

9

Performance EquationPerformance Equation

10

• The Processor Performance Equation

11

Performance EquationPerformance Equation

Performance EquationPerformance Equation

12

• Different instruction types having different CPIs

13

MIPSMIPS

14

MFLOPSMFLOPS

15

GHzGHz

16

17

18

IC CostIC Cost

• Cost driven down by learning curve– Yield

• DRAM: price closely tracks cost

• Microprocessors: price depends on volume– 10% less for each doubling of volume

IC CostIC Cost

19

• Integrated circuit

• Bose-Einstein formula:

• Defects per unit area = 0.016-0.057 defects per square cm (2010)

• N = process-complexity factor = 11.5-15.5 (40 nm, 2010)

IC CostIC Cost

20

AvailabilityAvailability

Year 21

PowerPower

22

PowerPower

23

PowerPower

24

• Dynamic energy– Transistor switch from 0 -> 1 or 1 -> 0– ½1/2 x Capacitive load x Voltage2

• Dynamic power– ½ 1/2x Capacitive load x Voltage2 x Frequency

switched

• Reducing clock rate reduces power, not energy

PowerPower

25

• Static power consumption– Currentstatic x Voltage– Scales with number of transistors– To reduce: power gating

PowerPower

26

• Intel 80386 consumed ~ 2 W

• 3.3 GHz Intel Core i7 consumes 130 W

• Heat must be dissipated from 1.5 x 1.5 cm chip

• This is the limit of what can be cooled by air

BenchmarkBenchmark

27

BenchmarkBenchmark

28

29

BenchmarkBenchmark