CS2004D Computer Organization

Instructor: Sumesh T A
Department of Computer Science &
Engineering
NIT Calicut
Kerala, India
COMPUTER ORGANIZATION AND DESIGN 5th
The Hardware/Software Interface Edition

Chapter 1
Performance
When trying to choose among different computers,
performance is an important attribute.

Often, salespeople would like you to see their computer in

the best possible light, whether or not this light accurately
reflects the needs of the purchaser’s application.

Hence, understanding how best to measure performance

and the limitations of performance measurements is
important in selecting a computer.

When we say one computer has better performance than

another, what do wemean?
 Passenger airplane analogy

You could define the fastest plane as the one with the highest
cruising speed, taking a single passenger from one point to another
in the least time

If you were interested in transporting 450 passengers from one

point to another, however, the 747 would clearly be the fastest,
 §1.6 Performance
Defining Performance
 Which airplane has the best performance?

Boeing 777 Boeing 777

Boeing 747 Boeing 747

BAC/Sud Concorde BAC/Sud Concorde

Douglas DC-8-50 Douglas DC- 8-50

0 100 200 300 400 0 2000 4000 6000 8000 10000

500

Passenger Capacity Cruising Range (miles)

Boeing 777 Boeing 777

Boeing 747 Boeing 747

BAC/Sud BAC/Sud

Concorde Concorde
Douglas Douglas DC-
DC-8- 8-50
50
0 500 1000 1500 0 100000 200000 300000 400000

Cruising Speed (mph) Passengers x mph

Chapter 1 — Computer Abstractions and Technology — 5

Faster computer
If you were running a program on two different desktop
computers, you’d say that the faster one is the desktop
computer that gets the job done first.

If you were running a datacenter that had several

servers running jobs submitted by many users, you’d say
that the faster computer was the one that completed the
most jobs during a day.
• Response time - the time between the start and
completion of a task
• Through put - the total amount of work done in a
given time
 Response Time and Throughput
 Response time
 How long it takes to do a task
 Throughput
 Total work done per unit time
e.g., tasks/transactions/… per hour
Do the following changes to a computer system
increase throughput, decrease response time, or
both?
1. Replacing the processor in a computer with a
faster version
2. Adding additional processors to a system that
uses multiple processors for separate
We’ll focus on response time for now…
Chapter 1 — Computer Abstractions and Technology — 7
Time is the measure of computer performance: the computer
that performs the same amount of work in the least time is the
fastest.
Relative Performance
 Define Performance = 1/Execution Time
 “X is n times faster than Y”
Performanc e X Performanc e Y
 Execution time Y Execution time X  n
 Example: time taken to run a program
 10s on A, 15s on B
 Execution TimeB / Execution TimeA
= 15s / 10s = 1.5 = 1½
 So A is 1½ times faster than B
Chapter 1 — Computer Abstractions and Technology — 9
Measuring Execution Time
 Elapsed time
 Total response time, including all aspects
 Processing, I/O, OS overhead, idle time
 Determines system performance
 CPU time
 Time spent processing a given job
 Minus I/O time, other jobs’ shares
 Includes user CPU time and system CPU time
 Different programs are affected differently by CPU
and system performance
 Running on servers – I/O performance – hardware and
software
 Total elapsed time is of interest
 Define performance metric and then proceed
Chapter 1 — Computer Abstractions and Technology — 10
CPU Clocking
Operation of digital hardware governed by a
constant-rate clock
clock period is the length of each clock cycle.
Clock period

Clock (cycles)

Data transfer and computation

Update state

 Clock period: duration of a clock cycle

 e.g., 250ps = 0.25ns = 250×10–12s
 Clock frequency (rate): cycles per second
 e.g., 4.0GHz = 4000MHz = 4.0×109Hz
Chapter 1 — Computer Abstractions and Technology — 11
CPU Time
CPU Time  CPU Clock Cycles Clock Cycle
Time

CPU Clock Cycles Clock Rate


 Performance can be improved by
 Reducing number of clock cycles
 Increasing clock rate
 Hardware designer must often trade off clock
rate against cycle count

Chapter 1 — Computer Abstractions and Technology — 13

CPU Time Example
 Computer A: 2GHz clock, 10s CPU time
 Designing Computer B
 Aim for 6s CPU time
 Can do faster clock, but causes 1.2 × clock cycles
 How fast must Computer B clock be?

Clock RateB  Clock CyclesB  1.2 Clock

CPU TimeB 6s
CyclesA
Clock CyclesA  CPU Time A Clock RateA

 10s 2GHz  20 10 9

1.2  20 109 24
Clock RateB    4GHz
109 6s 6s
Chapter 1 — Computer Abstractions and Technology — 15
Instruction Count and CPI
Clock Cycles  Instruction Count  Cycles Per Instruction
CPU Time  Instruction Count  CPI Clock Cycle
Time

Instruction Count  CPI


 Instruction Count for a program
Clock Rate
 Determined by program, ISA, and compiler
 Average cycles per instruction
 Determined by CPU hardware
 If different instructions have different CPI
 Average CPI gets affected by instruction mix
(dynamic frequency of instructions)
Chapter 1 — Computer Abstractions and Technology — 16
Suppose we have two implementations of the same
instruction set architecture. Computer A has a clock
cycle time of 250 ps and a CPI of 2.0 for some
program, and computer B has a clock cycle time of
500 ps and a CPI of 1.2 for the same program.
Which computer is faster for this program and by
how much?
CPI Example
 Computer A: Cycle Time = 250ps, CPI = 2.0
 Computer B: Cycle Time = 500ps, CPI = 1.2
 Same ISA
 Which is faster? by how much?

CPU Time A  Instruction Count  CPIA  Cycle Time

A is faster…
A

 I 2.0  250ps  I 500ps

CPU TimeB  Instruction Count  CPIB  Cycle TimeB

CPU TimeB I 600ps …by this much
  1.2
 I1.2  500ps  I 600ps

CPU Time A I 500ps

Chapter 1 — Computer Abstractions and Technology — 18
CPI in More Detail
 If different instruction classes take different
numbers of cycles
n

Clock Cycles   (CPIi Instructio n

Count i )
 Weighted average CPI
i1

Clock Cycles n

CPI    CPIi  Instruction Count i
 Instruction
i1  Instruction Count 
Count
Relative frequency

Chapter 1 — Computer Abstractions and Technology — 19

CPI Example
 Alternative compiled code sequences using
instructions in classes A, B, C
Class A B C
CPI for class 1 2 3
IC in sequence 1 2 1 2
IC in sequence 2 4 1 1

 Sequence 1: IC = 5  Sequence 2: IC = 6
 Clock Cycles  Clock Cycles
= 2×1 + 1×2 + 2×3 = 4×1 + 1×2 + 1×3
= 10 =9
 Avg. CPI = 10/5 = 2.0  Avg. CPI = 9/6 = 1.5
Chapter 1 — Computer Abstractions and Technology — 21
The performance of a program depends on the algorithm, the
language, the compiler, the architecture, and the actual hardware.
IPC

Although you might expect that the minimum CPI is

1.0, as we’ll see in Chapter 4, some processors fetch
and execute multiple instructions per clock cycle.

To reflect that approach, some designers invert CPI

to talk about IPC, or instructions per clock cycle. If a
processor executes on average 2 instructions per
clock cycle, then it has an IPC of 2 and hence a CPI
of 0.5.
Performance Summary
The BIG Picture

Instructions Clock Cycles Seconds

CPU Time   
Program Instruction Clock Cycle

 Performance depends on
 Algorithm: affects IC, possibly CPI
 Programming language: affects IC, CPI
 Compiler: affects IC, CPI
 Instruction set architecture: affects IC, CPI, Tc
Chapter 1 — Computer Abstractions and Technology — 24
 §1.7 The Power Wall
Power Trends

Clock rate and Power for Intel x86 microprocessors over eight generations
 In CMOS IC technology
Power  Capacitive load Voltage 2
Frequency
×30 5V → 1V ×1000

Chapter 1 — Computer Abstractions and Technology — 25

Power
 Reducing Power
Suppose we developed a new, simpler processor that has 85% of the
capacitive load of the more complex older processor. Further, assume that
it has adjustable voltage so that it can reduce voltage 15% compared to
processor B, which results in a 15% shrink in frequency. What is the
impact on dynamic power?
P C  0.85  (V  0.85)2 F  0.85

 0.85 4 
Pnew old C V
old
2
F old
old old
old
old 0.52
 The power wall
 We can’t reduce voltage further
 We can’t remove more heat
 How else can we improve performance?
Chapter 1 — Computer Abstractions and Technology — 27
 §1.8 The Sea Change: The Switch to Multiprocessors
Technology driven
Uniprocessor Performance

Advanced architectural and organizational ideas

Constrained by power, instruction-level parallelism, memory latency

Chapter 1 — Computer Abstractions and Technology — 28

Multiprocessors
 Multicore microprocessors
 More than one processor per chip
 Requires explicitly parallel programming
 Compare with instruction level parallelism
 Hardware executes multiple instructions at once

 Hidden from the programmer

 Hard to do (Why?)
 Programming for performance

 Load balancing

 Optimizing communication and synchronization

For both this analogy and parallel programming, the challenges

include scheduling, load balancing, time for synchronization, and
overhead for communication between the parties.
Chapter 1 — Computer Abstractions and Technology — 29
 §1.9 Concluding Remarks
Concluding Remarks
 Cost/performance is improving
 Due to underlying technology development
 Hierarchical layers of abstraction
 In both hardware and software
 Instruction set architecture
 The hardware/software interface
 Execution time: the best performance
measure
 Power is a limiting factor
 Use parallelism to improve performance
Chapter 1 — Computer Abstractions and Technology — 30
Acknowledgement
The slides are adopted from Computer
Organization and Design, 5th Edition
by David A. Patterson and John L. Hennessy
2014, published by MK (Elsevier)

Chapter 1 — Computer Abstractions and Technology — 31