ms108 computer system i lecture 2 metrics prof. xiaoyao liang 2014/2/28 1
TRANSCRIPT
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