Introduction

Computational
Complexity
Gaurav Trivedi
EEE Dept.
IIT Guwahati

In order to celebrate mathematics in the new millennium, The Clay Mathematics Institute of Cambridge, Massachusetts (CMI) has
named seven Prize Problems. The Scientific Advisory Board of CMI selected these problems, focusing on important classic
questions that have resisted solution over the years. The Board of Directors of CMI designated a $7 million prize fund for the
solution to these problems, with $1 million allocated to each. During the Millennium Meeting held on May 24, 2000 at the Collège
de France, Timothy Gowers presented a lecture entitled The Importance of Mathematics, aimed for the general public, while John
Tate and Michael Atiyah spoke on the problems. The CMI invited specialists to formulate each problem.
One hundred years earlier, on August 8, 1900, David Hilbert delivered his famous lecture about open mathematical problems at the
second International Congress of Mathematicians in Paris. This influenced our decision to announce the millennium problems as the
central theme of a Paris meeting.
The rules for the award of the prize have the endorsement of the CMI Scientific Advisory Board and the approval of the Directors.
The members of these boards have the responsibility to preserve the nature, the integrity, and the spirit of this prize.
Paris, May 24, 2000
Please send inquiries regarding the Millennium Prize Problems to prize.problems@claymath.org.
http://www.claymath.org/millennium/
We’ll talk about this first
one today.

Purpose of this talk
 Understand P and NP
 See what it would mean for them to be
equal (or distinct)
 See some examples
– SAT (Satisfaction)
– Minesweeper
– Tetris

P and NP, informally
 P and NP are two classes of problems
that can be solved by computers.
 P problems can be solved quickly.
– Quickly means seconds or minutes, maybe
even hours.
 NP problems can be solved slowly.
– Slowly can mean hundreds or thousands
or years.

An equivalent question
 Is there a clever way to turn a slow
algorithm into a fast one?
– If P=NP, the answer is yes.
– If P≠NP, the answer is no.

Why do we care?
 People like things to work fast.
 Encrypting information
– If there’s an easy way to turn a slow
algorithm into a fast one, there’s an easy
way to crack encrypted information.
– This is bad for government secret stuff and
for people who like to buy things online.

Currently…
 Most people think P≠NP.

General computing
 First, consider computer programs and what
they can do:
input output
(we hope)
Program

General computing
 They don’t always behave so nicely…
input No output
(Crash!)
Program
Gets stuck here.

What happens when things get
stuck?
Consider the program below:
Input:
number x
Program:
L1. If x < 15, output 1.
Otherwise, GOTO L1.
Output:
1 if x < 15,
Never stops
otherwise.

A couple of things to note
 There are lots of programs for any given
problem.
 Some are faster than others.
– We can always artificially slow them down.

Back to P and NP
 P and NP are classes of solvable
problems.
 Solvable means that there’s a program
that takes an input, runs for a while, but
eventually stops and gives the answer.

Computation “trees” for solvable
problems
Program:
Input x
L1. If x > 1,
set x = x-2,
and GoTo L1.
If x = 0,
output 0.
If x = 1,
output 1.
Example computation:
Input x = 3
x = 3 - 2 = 1
x>1, so …
x=1, so …
Output 1

More about the example…
 What does this program do?
– Outputs 0 if input is even,
– Outputs 1 if input is odd.
 Solves the problem “Is the input even or
odd?”
 The length of the computation tree depends
on the input.
– Time(3)= 2
– Time(4)= 3
– Time(x)≤ (x/2) + 1

Solvability versus Tractability
 A problem is solvable if there is a
program that always stops and gives
the answer.
 The number of steps it takes depends
on the input.
 A problem is tractable or in the class P if
it is solvable and we can say
Time(x)≤(some polynomial).

P problems are “fast”
 These problems are comparatively fast.
 For example, consider a program that
has compared to one with
.
– On the input 100, the computation times
compare as follows
6703,205,379,401,496,600,228,221,267,650,2000,10100 1002

2
)( xxTime 
x
xTime 2)( 

Okay… so what about NP?
 The description involves non-
deterministic programming.
– NP stands for “non-deterministic,
polynomial-time computable”
 The examples we’ve seen so far are
examples of deterministic programs.
– By the way, P stands for “polynomial-time
computable”

An example of non-deterministic
programming
 Non-deterministic programs use a new kind
of command that normal programs can’t
really use.
 Basically, they can guess the answer and
then check to see if the guess was right.
 And they can guess all possible answers
simultaneously (as long as it’s only finitely
many).

An example of non-deterministic
programming
Program:
Input x.
Guess y in {1, 2, 4, 9}.
If x+y > 10,
stop and output 0.
Otherwise,
If y is even,
Guess z in {2, 3},
If x+z is odd, stop,
output 1.
Otherwise, output 0.
Input x = 7
We branch
when there’s a
guess; one
path for each
guess.
guess y = 2guess y = 1 guess y = 4 guess y = 9
x+y>10,
Output 0
x+y>10,
Output 0
x+y<10
y is odd,
Output 0
guess
z = 2
guess
z = 3
x+z = 9
is odd,
Output 1
x+z = 10
is even
Output 0

Non-deterministic programming
 Convention:
– If any computation path ends with a 1, the answer
to the problem is 1 (we count this as “yes”).
– If all computation paths end with a 0, the answer
to the problem is 0 (we count this as “no”).
– Otherwise, we say the computation does not
converge.
 Again, we’re only interested in problems
where this third case never happens –
solvable problems.

The class NP
 If the computation halts on input x, the
length of the longest path is NTime(x).
 A problem is NP if it is solvable and
there is a non-deterministic program
that computes it so that
NTime(x)≤(Some polynomial).

Non-deterministic →
Deterministic
 A non-deterministic algorithm can be
converted into a deterministic algorithm
at the cost of time.
 Usually, the increase in computation
time is exponential.
 This means, for normal computers,
(deterministic ones), NP problems are
slow.

The picture so far…
All
solvable
problems
P
NP

SAT (The problem of
satisfiabity)
 Take a statement in propositional logic, (like
, for example).
 The problem is to determine if it is satisfiable.
(In other words, is there a line in the truth
table for this statement that has a “T” at the
end of it.)
 This problem can be solved in polynomial
time with a non-deterministic program.
qpqp 

SAT, cont.
 We can see this by thinking about the
process of constructing a truth table, and
what a non-deterministic algorithm would do:

SAT, cont.
 The length of each path in the
computation tree is a polynomial
function of the length of the input
statement.
 SAT is an NP problem.

NP completeness
 If P≠NP, SAT is a witness of this fact, that is,
SAT is NP but not P.
 It is among the “hardest” of the NP problems:
any other NP problem can be coded into it in
the following sense.
If R is a non-deterministic, polynomial-time algorithm that solves
another NP problem, then for any input, x, we can quickly find a
formula, f, so that f is satisfiable when R halts on x with output 1,
and f is not satisfiable when R halts on x with output 0.

NP complete problems
 Problems with this property that all NP
problems can be coded into them are
called NP-hard.
 If they are also NP, they are called NP-
complete.
 If P and NP are different, then the NP-
complete problems are NP, but not P.

The picture so far…
All
solvable
problems
P
NP
NP-
complete
problems
SAT lives
here

Question:
 Is there a clever way to change a non-
deterministic polynomial time algorithm into a
deterministic polynomial time algorithm,
without an exponential increase in
computation time?
 If we can compute an NP complete problem
quickly then all NP problems are solvable in
deterministic polynomial time.

On to examples…
 SAT is NP-complete
 The Minesweeper Consistency Problem
 Tetris

Minesweeper
 The Minesweeper consistency problem:
– Given a rectangular grid partially marked
with numbers and/or mines – some
squares being left blank – determine if
there is some pattern of mines in the blank
squares that give rise to the numbers seen.
That is, determine if the grid is consistent
for the rules of the game.

Minesweeper
 This is certainly an NP problem:
– We can guess all possible configurations of mines
in the blank squares and see if any work.
 To see that it is NP complete is much harder.
– The trick is to code logical expressions into
partially filled minesweeper grids. Then we will
have demonstrated that SAT can be coded into
Minesweeper, so Minesweeper is also NP-
complete.

Tetris
Rules:
The pieces fall, you
can rotate them.
When a line gets all
filled up, it is
“cleared”.
If 4 lines get filled
simultaneously, that’s a
“Tetris” – extra points!
You lose if the screen
fills up so no new
pieces can appear.

Tetris, the “offline” version
 You get to know all the pieces (there will
only be finitely many in this version),
and the order they will appear.
 You start with a partially filled board.

Tetris, offline
 The following problems are NP-
complete:
– Maximizing the number of rows cleared.
– Maximizing the number of pieces placed
before losing.
– Maximizing the number of Tetrises.
– Maximizing the height of the highest filled
gridsquare over the course of the
sequence.

Tetris, offline
 It’s easy to see each of these is NP –
just guess the different ways to rotate
and place each piece, and see which is
largest.
 It’s (as usual) harder to show NP-
completeness.
– It is shown by reducing the 3-Partition
problem (which is known to be NP-
complete) to the Tetris problems.

Sudoku
(Due to Takyuki Yato and
Takahiro Seta at the
University of Tokyo)
Each row/column/square
has a single instance of
each number 1-9.
Solving a board is NP-
complete.

Battleship
 Sink the enemy’s ships – NP Compete!

Beyond NP
 Chess and checkers are both EXPTIME-
complete – solvable with a deterministic
program with computation bounded by
for some polynomial .
 Go (with the Japanese rules) is as well.
 Go (American rules) and Othello are
PSPACE-hard, and Othello is PSPACE-
complete (PSPACE is another complexity
class that considers memory usage instead of
computation time).
)(
2 xp
)(xp

References
 Kaye, Richard. Minesweeper is NP-
Complete. Mathematical Intelligencer vol. 22
no. 2, pgs 9-15. Spring 2000.
 Demaine, E., Hohenberger, S., Liben-Nowell,
D. Tetris is Hard, Even to Approximate.
Preprint, December 2005.

EE664: Introduction to Parallel Computing
Dr. Gaurav Trivedi
Lectures – 1-2-3-4

Overview
Concepts and Terminology
Parallel Computer Memory Architectures
Parallel Programming Models
Designing Parallel Programs
Parallel Algorithm Examples
2

What is Parallel Computing? (1)
 Traditionally, software has been written for serial
computation:
– To be run on a single computer having a single Central Processing
Unit (CPU);
– A problem is broken into a discrete series of instructions.
– Instructions are executed one after another.
– Only one instruction may execute at any moment in time.
3

What is Parallel Computing? (2)
 In the simplest sense, parallel computing is the simultaneous use of multiple
compute resources to solve a computational problem.
– To be run using multiple CPUs
– A problem is broken into discrete parts that can be solved concurrently
– Each part is further broken down to a series of instructions
 Instructions from each part execute simultaneously on different CPUs
4

5
Demand for Computational Speed
There is continual demand for greater computational speed
Areas requiring great computational speed include numerical
modeling and simulation of scientific and engineering problems.
Computations must be completed within a “reasonable” time period.

Parallel Computing: Resources
 The compute resources can include:
– A single computer with multiple processors;
– A single computer with (multiple) processor(s) and some
specialized computer resources (GPU, FPGA …)
– An arbitrary number of computers connected by a network;
– A combination of both.
6

Parallel Computing: The computational problem
 The computational problem usually demonstrates
characteristics such as the ability to be:
– Broken apart into discrete pieces of work that can be solved
simultaneously;
– Execute multiple program instructions at any moment in time;
– Solved in less time with multiple compute resources than with a
single compute resource.
7

Parallel Computing: what for? (1)
 Parallel computing is an evolution of serial computing that attempts
to emulate what has always been the state of affairs in the natural
world: many complex, interrelated events happening at the same
time, yet within a sequence.
 Some examples:
– Planetary and galactic orbits
– Weather and ocean patterns
– Tectonic plate drift
– Rush hour traffic in Guwahati/New Delhi/Bangalore/Mumbai
– Automobile assembly line
– Daily operations within a business
– Building a shopping mall
8

 Traditionally, parallel computing has been considered to
be "the high end of computing" and has been motivated
by numerical simulations of complex systems and "Grand
Challenge Problems" such as:
– weather and climate
– chemical and nuclear reactions
– biological, human genome
– geological, seismic activity
– mechanical devices - from prosthetics to spacecraft
– electronic circuits
– manufacturing processes
9

 Today, commercial applications are providing an equal or greater
driving force in the development of faster computers. These
applications require the processing of large amounts of data in
sophisticated ways. Example applications include:
– parallel databases, data mining
– oil exploration
– web search engines, web based business services
– computer-aided diagnosis in medicine
– management of national and multi-national corporations
– advanced graphics and virtual reality, particularly in the entertainment
industry
– networked video and multi-media technologies
– collaborative work environments
 Ultimately, parallel computing is an attempt to maximize the infinite
but seemingly scarce commodity called time.
10

Example: Global Weather Forecasting
Atmosphere modeled by dividing it into 3-dimensional cells.
Calculations of each cell repeated many times to model passage of
time.
Suppose whole global atmosphere (5  108 sq.miles) divided into cells of
size 1 mile  1 mile  1 mile to a height of 10 miles (10 cells high) 
50  108 cells.
Suppose each calculation requires 2000 FLOPs (floating point
operations). In one time step, 1013 FLOPs necessary.
To forecast the weather over 7 days using 1-minute intervals, a computer
operating at 10 Gflops (1010 floating point operations/s) takes 107
seconds or over 115 days.
To perform calculation in 50 minutes requires a computer operating at 34
Tflops (34  1012 floating point operations/sec).
(IBM Blue Gene is ~500 TFLOPS) 11

12
Modeling Motion of Astronomical Bodies
Each body attracted to each other body by gravitational
forces. Movement of each body predicted by calculating
total force on each body.
With N bodies, N - 1 forces to calculate for each body, or
approx. N2 calculations. (Nlog2N for an efficient approx.
algorithm). After determining new positions of bodies,
calculations repeated.
A galaxy might have 1011 stars.
If each calculation is done in 10-9 sec., it takes 1013 seconds
for one iteration using N2 algorithm (or 1013/86400 108
days)
103 sec. for one iteration using the Nlog2N algorithm.

Why Parallel Computing? (1)
 This is a legitime question! Parallel computing is complex
on any aspect!
 The primary reasons for using parallel computing:
– Save time - wall clock time
– Solve larger problems
– Provide concurrency (do multiple things at the same time)
13

Why Parallel Computing? (2)
 Other reasons might include:
– Taking advantage of non-local resources - using available compute
resources on a wide area network, or even the Internet when
local compute resources are scarce.
– Cost savings - using multiple "cheap" computing resources instead
of paying for time on a supercomputer.
– Overcoming memory constraints - single computers have very
finite memory resources. For large problems, using the memories
of multiple computers may overcome this obstacle.
14

Limitations of Serial Computing
 Limits to serial computing - both physical and practical reasons pose
significant constraints to simply building ever faster serial computers.
 Transmission speeds - the speed of a serial computer is directly dependent
upon how fast data can move through hardware. Absolute limits are the
speed of light (30 cm/nanosecond) and the transmission limit of copper wire
(9 cm/nanosecond). Increasing speeds necessitate increasing proximity of
processing elements.
 Limits to miniaturization - processor technology is allowing an increasing
number of transistors to be placed on a chip. However, even with molecular
or atomic-level components, a limit will be reached on how small
components can be.
 Economic limitations - it is increasingly expensive to make a single processor
faster. Using a larger number of moderately fast commodity processors to
achieve the same (or better) performance is less expensive.
15

The future
 during the past 10 years, the trends indicated by ever
faster networks, distributed systems, and multi-processor
computer architectures (even at the desktop level) clearly
show that parallelism is the future of computing.
 It will be multi-forms, mixing general purpose solutions
(your PC…) and very speciliazed solutions as IBM Cells,
ClearSpeed, GPGPU from NVidia …
16

Who and What? (1)
 Top500.org provides statistics on parallel computing users
- the charts below are just a sample. Some things to note:
– Sectors may overlap - for example, research may be classified
research. Respondents have to choose between the two.
 "Not Specified" is by far the largest application - probably
means multiple applications.
17

Von Neumann Architecture
 For over 40 years, virtually all computers have followed a
common machine model known as the von Neumann
computer. Named after the Hungarian mathematician
John von Neumann.
 A von Neumann computer uses the stored-program
concept. The CPU executes a stored program that specifies
a sequence of read and write operations on the memory.
Concepts and Terminology
19

Basic Design
 Basic design
– Memory is used to store both program
and data instructions
– Program instructions are coded data
which tell the computer to do something
– Data is simply information to be used by
the program
 A central processing unit (CPU) gets
instructions and/or data from
memory, decodes the instructions
and then sequentially performs them.
20

Flynn's Classical Taxonomy
 There are different ways to classify parallel computers.
One of the more widely used classifications, in use since
1966, is called Flynn's Taxonomy.
 Flynn's taxonomy distinguishes multi-processor computer
architectures according to how they can be classified
along the two independent dimensions of Instruction and
Data. Each of these dimensions can have only one of two
possible states: Single or Multiple.
21

Flynn Matrix
 The matrix below defines the 4 possible classifications
according to Flynn
22

Single Instruction, Single Data (SISD)
 A serial (non-parallel) computer
 Single instruction: only one instruction
stream is being acted on by the CPU during
any one clock cycle
 Single data: only one data stream is being
used as input during any one clock cycle
 Deterministic execution
 This is the oldest and until recently, the most
prevalent form of computer
 Examples: most PCs, single CPU workstations
and mainframes
23

Single Instruction, Multiple Data (SIMD)
 A type of parallel computer
 Single instruction: All processing units execute the same instruction at any given clock
cycle
 Multiple data: Each processing unit can operate on a different data element
 This type of machine typically has an instruction dispatcher, a very high-bandwidth
internal network, and a very large array of very small-capacity instruction units.
 Best suited for specialized problems characterized by a high degree of regularity,such as
image processing.
 Synchronous (lockstep) and deterministic execution
 Two varieties: Processor Arrays and Vector Pipelines
 Examples:
– Processor Arrays: Connection Machine CM-2, Maspar MP-1, MP-2
– Vector Pipelines: IBM 9000, Cray C90, Fujitsu VP, NEC SX-2, Hitachi S820
24

Multiple Instruction, Single Data (MISD)
 A single data stream is fed into multiple processing units.
 Each processing unit operates on the data independently via
independent instruction streams.
 Few actual examples of this class of parallel computer have ever
existed. One is the experimental Carnegie-Mellon C.mmp computer
(1971).
 Some conceivable uses might be:
– multiple frequency filters operating on a single signal stream
 multiple cryptography algorithms attempting to crack a single coded
message.
25

Multiple Instruction, Multiple Data (MIMD)
 Currently, the most common type of parallel computer. Most modern
computers fall into this category.
 Multiple Instruction: every processor may be executing a different
instruction stream
 Multiple Data: every processor may be working with a different data
stream
 Execution can be synchronous or asynchronous, deterministic or non-
deterministic
 Examples: most current supercomputers, networked parallel
computer "grids" and multi-processor SMP computers - including
some types of PCs.
26

Some General Parallel Terminology
 Task
– A logically discrete section of computational work. A task is
typically a program or program-like set of instructions that is
executed by a processor.
 Parallel Task
– A task that can be executed by multiple processors safely (yields
correct results)
 Serial Execution
– Execution of a program sequentially, one statement at a time. In
the simplest sense, this is what happens on a one processor
machine. However, virtually all parallel tasks will have sections of
a parallel program that must be executed serially.
Like everything else, parallel computing has its own "jargon". Some of the
more commonly used terms associated with parallel computing are listed
below. Most of these will be discussed in more detail later.
27

 Parallel Execution
– Execution of a program by more than one task, with each task being able
to execute the same or different statement at the same moment in time.
 Shared Memory
– From a strictly hardware point of view, describes a computer architecture
where all processors have direct (usually bus based) access to common
physical memory. In a programming sense, it describes a model where
parallel tasks all have the same "picture" of memory and can directly
address and access the same logical memory locations regardless of
where the physical memory actually exists.
 Distributed Memory
– In hardware, refers to network based memory access for physical
memory that is not common. As a programming model, tasks can only
logically "see" local machine memory and must use communications to
access memory on other machines where other tasks are executing.
28

 Communications
– Parallel tasks typically need to exchange data. There are several ways this
can be accomplished, such as through a shared memory bus or over a
network, however the actual event of data exchange is commonly
referred to as communications regardless of the method employed.
 Synchronization
– The coordination of parallel tasks in real time, very often associated with
communications. Often implemented by establishing a synchronization
point within an application where a task may not proceed further until
another task(s) reaches the same or logically equivalent point.
– Synchronization usually involves waiting by at least one task, and can
therefore cause a parallel application's wall clock execution time to
increase.
29

 Granularity
– In parallel computing, granularity is a qualitative measure of the ratio of
computation to communication.
– Coarse: relatively large amounts of computational work are done
between communication events
– Fine: relatively small amounts of computational work are done between
communication events
 Observed Speedup
– Observed speedup of a code which has been parallelized, defined as:
wall-clock time of serial execution
wall-clock time of parallel execution
– One of the simplest and most widely used indicators for a parallel
program's performance.
30

 Parallel Overhead
– The amount of time required to coordinate parallel tasks, as opposed to
doing useful work. Parallel overhead can include factors such as:
 Task start-up time
 Synchronizations
 Data communications
 Software overhead imposed by parallel compilers, libraries, tools, operating
system, etc.
 Task termination time
 Massively Parallel
– Refers to the hardware that comprises a given parallel system - having
many processors. The meaning of many keeps increasing, but currently
BG/L pushes this number to 6 digits.
31

 Scalability
– Refers to a parallel system's (hardware and/or software) ability to
demonstrate a proportionate increase in parallel speedup with
the addition of more processors. Factors that contribute to
scalability include:
 Hardware - particularly memory-cpu bandwidths and network
communications
 Application algorithm
 Parallel overhead related
 Characteristics of your specific application and coding
32

33
Parallel Computing
Using more than one computer, or a computer with more than
one processor, to solve a problem.
Motives
n computers operating simultaneously can achieve the result n
times faster - it will not be n times faster for various reasons.
Other motives include: fault tolerance, larger amount of memory
available, ...

34
Speedup Factor
where ts is execution time on a single processor and tp is execution time on a
multiprocessor.
S(p) : increase in speed by using multiprocessor.
Use best sequential algorithm with single processor system. Underlying
algorithm for parallel implementation might be (and is usually) different.
Speedup factor can also be cast in terms of computational steps:
S(p) =
Execution time using one processor (best sequential algorithm)
Execution time using a multiprocessor with p processors
ts
tp
=
S(p) =
Number of computational steps using one processor
Number of parallel computational steps with p processors

35
**here Maximum Speedup
Maximum speedup is usually p with p processors (linear speedup).
Possible to get superlinear speedup (greater than p) but usually there
is a specific reason such as:
• Extra memory in multiprocessor system
• Nondeterministic algorithm

Maximum Speedup
Amdahl’s law
(b) Multiple
processors
p processors
...
(1-f)ts / ptp
Serial section Parallelizable sections
(a) One processor . . .
(1-f)tsfts
ts
36

37
Speedup factor is given by:
This equation is known as Amdahl’s law.
Even with infinite number of processors, maximum
speedup is limited to 1/f.
Example: With only 5% of computation being serial, maximum speedup is 20,
irrespective of number of processors.
f
pS
p
f
f
p
tf
ft
t
pS
p
s
s
s 1
)(lim
)1(
1
)1(
)( 








38
Superlinear Speedup
Example - searching
(a) Searching each sub-space sequentially
ts
Start Time
Solution found
Sub-space
search
x indeterminate
Dt
xts/p
ts/p

39
(b) Searching each sub-space in parallel
Solution found
Dt
Speed-up then given by
S(p)
x
ts
p
´
tD+
tD
=

40
Worst case for sequential search when solution found in last sub-
space search. Then parallel version offers greatest benefit, i.e.
as Dt tends to go to zeroS(p)
p - 1
p ts +´
Dt
=
Dt
Least advantage for parallel version when solution found in first sub-
space search of the sequential search, i.e.
Actual speed-up depends upon which subspace holds solution but could
be extremely large.
S(p) =
Dt
= 1
Dt

41
Conventional Computer
Consists of a processor executing a program stored in a (main)
memory:
Addresses start at 0 and extend to 2b - 1
Main memory
Processor
Instructions (to processor)
Data (to or from processor)

42
Shared Memory Multiprocessor System
Multiple processors connected to multiple memory modules such
that each processor can access any memory module :
Processors
Interconnection
network
Memory module
One
address
space
Parallel Computers
Shared memory vs. Distributed memory

Quad Pentium Shared Memory Multiprocessor
Processor
L2 Cache
Bus interface
L1 cache
Processor
L2 Cache
Bus interface
L1 cache
Processor
L2 Cache
Bus interface
L1 cache
Processor
L2 Cache
Bus interface
L1 cache
Memory controller
Memory
I/O interface
I/O bus
Processor/
memory
bus
Shared memory
Need to address Cache coherency problem!
43

44
Shared Memory Multiprocessors
Threads - programmer decomposes program into individual parallel
sequences, (threads), each being able to access shared variables.
Sequential programming language with preprocessor compiler
directives to declare shared variables and specify parallelism.
Example: OpenMP - industry standard - needs OpenMP compiler

45
Message-Passing Multicomputer
Complete computers connected through an interconnection network:
Processor
Interconnection
network
Local
Computers
Messages
memory

46
Interconnection Networks
2- and 3-dimensional meshes
Hypercube
Trees
Using Switches:
Crossbar
Multistage interconnection networks

47
Two-dimensional array (mesh)
Links
One-dimensional array
Links Computer/Processor

49
Three-dimensional hypercube
000 001
010 011
100
110
101
111

50
Four-dimensional hypercube
Hypercubes were very popular in 1980’s
0000 0001
0010 0011
0100
0110
0101
0111
1000 1001
1010 1011
1100
1110
1101
1111

51
Tree
Switch
element
Root
Links
Processors

52
Crossbar switch
SwitchesProcessors
Memories

53
Multistage Interconnection Network
Example: Omega network
000
001
010
011
100
101
110
111
000
001
010
011
100
101
110
111
Inputs Outputs
2 x 2 switch elements
(straight-through or
crossover connections)

54
Embedding a ring onto a hypercube
000 001
010 011
100
110
101
111
000 001 011 010 110 111 101 100
What is this sequence called? 3-bit Gray Code

Embedding a 2-D Mesh onto a hypercube
11
01
00
0000 0001 0011 0010 0110 0111 0101 0100 1100 1101
01 0110
11 0110
01 0111
4-bit graycode
2-bit graycode
55

56
Distributed Shared Memory
Making main memory of group of interconnected computers look as
though a single memory with single address space. Then can use
shared memory programming techniques.
Processor
Interconnection
network
Shared
Computers
Messages
memory

57
Networked Computers as a Computing Platform
A network of computers became a very attractive alternative to
expensive supercomputers and parallel computer systems for high-
performance computing in early 1990’s.
Notable early projects:
Berkeley NOW (network of workstations).
NASA Beowulf project.
Key Advantages:
 Very high performance workstations and PCs readily available at low cost.
 The latest processors can be easily incorporated into the system as they
become available.
 Existing software can be used or modified.

Parallel Algorithm Examples:
Odd-Even Transposition Sort
Basic idea is bubble sort, but concurrently comparing
odd indexed elements with an adjacent element, then
even indexed elements.
If there are n elements in an array and there are n/2
processors. The algorithm is effectively O(n)!
58

Parallel Algorithm Examples:
Odd Even Transposition Sort
Initial array:
 6, 5, 4, 3, 2, 1, 0
6, 4, 5, 2, 3, 0, 1
4, 6, 2, 5, 0, 3, 1
4, 2, 6, 0, 5, 1, 3
2, 4, 0, 6, 1, 5, 3
2, 0, 4, 1, 6, 3, 5
0, 2, 1, 4, 3, 6, 5
0, 1, 2, 3, 4, 5, 6
Worst case scenario.
Phase 1
Phase 2
Phase 1
Phase 2
Phase 1
Phase 2
Phase 1
Only 7 passes are required 59

Memory architectures
 Shared Memory
 Distributed Memory
 Hybrid Distributed-Shared Memory

Shared Memory : UMA vs. NUMA
 Uniform Memory Access (UMA):
– Most commonly represented today by Symmetric Multiprocessor (SMP)
machines
– Identical processors
– Equal access and access times to memory
– Sometimes called CC-UMA - Cache Coherent UMA. Cache coherent
means if one processor updates a location in shared memory, all the
other processors know about the update. Cache coherency is
accomplished at the hardware level.
 Non-Uniform Memory Access (NUMA):
– Often made by physically linking two or more SMPs
– One SMP can directly access memory of another SMP
– Not all processors have equal access time to all memories
– Memory access across link is slower
– If cache coherency is maintained, then may also be called CC-NUMA -
Cache Coherent NUMA

Shared Memory: Pro and Con
 Advantages
– Global address space provides a user-friendly programming perspective
to memory
– Data sharing between tasks is both fast and uniform due to the proximity
of memory to CPUs
 Disadvantages:
– Primary disadvantage is the lack of scalability between memory and
CPUs. Adding more CPUs can geometrically increases traffic on the
shared memory-CPU path, and for cache coherent systems, geometrically
increase traffic associated with cache/memory management.
– Programmer responsibility for synchronization constructs that insure
"correct" access of global memory.
– Expense: it becomes increasingly difficult and expensive to design and
produce shared memory machines with ever increasing numbers of
processors.

Distributed Memory
 Like shared memory systems, distributed memory systems vary widely but share a
common characteristic. Distributed memory systems require a communication network
to connect inter-processor memory.
 Processors have their own local memory. Memory addresses in one processor do not
map to another processor, so there is no concept of global address space across all
processors.
 Because each processor has its own local memory, it operates independently. Changes
it makes to its local memory have no effect on the memory of other processors. Hence,
the concept of cache coherency does not apply.
 When a processor needs access to data in another processor, it is usually the task of the
programmer to explicitly define how and when data is communicated. Synchronization
between tasks is likewise the programmer's responsibility.
 The network "fabric" used for data transfer varies widely, though it can can be as simple
as Ethernet.

Distributed Memory: Pro and Con
 Advantages
– Memory is scalable with number of processors. Increase the number of
processors and the size of memory increases proportionately.
– Each processor can rapidly access its own memory without interference
and without the overhead incurred with trying to maintain cache
coherency.
– Cost effectiveness: can use commodity, off-the-shelf processors and
networking.
 Disadvantages
– The programmer is responsible for many of the details associated with
data communication between processors.
– It may be difficult to map existing data structures, based on global
memory, to this memory organization.

Hybrid Distributed-Shared Memory
 The largest and fastest computers in the world today employ both shared and
distributed memory architectures.
 The shared memory component is usually a cache coherent SMP machine.
Processors on a given SMP can address that machine's memory as global.
 The distributed memory component is the networking of multiple SMPs.
SMPs know only about their own memory - not the memory on another SMP.
Therefore, network communications are required to move data from one SMP
to another.
 Current trends seem to indicate that this type of memory architecture will
continue to prevail and increase at the high end of computing for the
foreseeable future.
 Advantages and Disadvantages: whatever is common to both shared and
distributed memory architectures.

Hybrid Distributed-Shared Memory
Summarizing a few of the key characteristics of shared and
distributed memory machines

 Overview
 Shared Memory Model
 Threads Model
 Message Passing Model
 Data Parallel Model
 Other Models
Parallel Programming Models

Overview
 There are several parallel programming models in
common use:
– Shared Memory
– Threads
– Message Passing
– Data Parallel
– Hybrid
 Parallel programming models exist as an abstraction above
hardware and memory architectures.

Overview
 Although it might not seem apparent, these models are NOT specific to a
particular type of machine or memory architecture. In fact, any of these
models can (theoretically) be implemented on any underlying hardware.
 Shared memory model on a distributed memory machine: Kendall Square
Research (KSR) ALLCACHE approach.
– Machine memory was physically distributed, but appeared to the user as a single
shared memory (global address space). Generically, this approach is referred to as
"virtual shared memory".
– Note: although KSR is no longer in business, there is no reason to suggest that a
similar implementation will not be made available by another vendor in the future.
– Message passing model on a shared memory machine: MPI on SGI Origin.
 The SGI Origin employed the CC-NUMA type of shared memory architecture,
where every task has direct access to global memory. However, the ability to
send and receive messages with MPI, as is commonly done over a network of
distributed memory machines, is not only implemented but is very commonly
used.

Overview
 Which model to use is often a combination of what is
available and personal choice. There is no "best" model,
although there certainly are better implementations of
some models over others.
 The following sections describe each of the models
mentioned above, and also discuss some of their actual
implementations.

Shared Memory Model
 In the shared-memory programming model, tasks share a common
address space, which they read and write asynchronously.
 Various mechanisms such as locks / semaphores may be used to
control access to the shared memory.
 An advantage of this model from the programmer's point of view is
that the notion of data "ownership" is lacking, so there is no need to
specify explicitly the communication of data between tasks. Program
development can often be simplified.
 An important disadvantage in terms of performance is that it
becomes more difficult to understand and manage data locality.

Shared Memory Model: Implementations
 On shared memory platforms, the native compilers
translate user program variables into actual memory
addresses, which are global.
 No common distributed memory platform
implementations currently exist. However, as mentioned
previously in the Overview section, the KSR ALLCACHE
approach provided a shared memory view of data even
though the physical memory of the machine was
distributed.

Threads Model
 In the threads model of parallel programming, a single process can have multiple,
concurrent execution paths.
 Perhaps the most simple analogy that can be used to describe threads is the concept of
a single program that includes a number of subroutines:
– The main program a.out is scheduled to run by the native operating system. a.out loads and
acquires all of the necessary system and user resources to run.
– a.out performs some serial work, and then creates a number of tasks (threads) that can be
scheduled and run by the operating system concurrently.
– Each thread has local data, but also, shares the entire resources of a.out. This saves the
overhead associated with replicating a program's resources for each thread. Each thread also
benefits from a global memory view because it shares the memory space of a.out.
– A thread's work may best be described as a subroutine within the main program. Any thread
can execute any subroutine at the same time as other threads.
– Threads communicate with each other through global memory (updating address locations).
This requires synchronization constructs to insure that more than one thread is not updating
the same global address at any time.
– Threads can come and go, but a.out remains present to provide the necessary shared
resources until the application has completed.
 Threads are commonly associated with shared memory architectures and operating
systems.

Threads Model Implementations
 From a programming perspective, threads implementations commonly comprise:
– A library of subroutines that are called from within parallel source code
– A set of compiler directives imbedded in either serial or parallel source code
 In both cases, the programmer is responsible for determining all parallelism.
 Threaded implementations are not new in computing. Historically, hardware vendors
have implemented their own proprietary versions of threads. These implementations
differed substantially from each other making it difficult for programmers to develop
portable threaded applications.
 Unrelated standardization efforts have resulted in two very different implementations
of threads: POSIX Threads and OpenMP.
 POSIX Threads
– Library based; requires parallel coding
– Specified by the IEEE POSIX 1003.1c standard (1995).
– C Language only
– Commonly referred to as Pthreads.
– Most hardware vendors now offer Pthreads in addition to their proprietary threads
implementations.
– Very explicit parallelism; requires significant programmer attention to detail.

Threads Model: OpenMP
 OpenMP
– Compiler directive based; can use serial code
– Jointly defined and endorsed by a group of major computer hardware
and software vendors. The OpenMP Fortran API was released October 28,
1997. The C/C++ API was released in late 1998.
– Portable / multi-platform, including Unix and Windows NT platforms
– Available in C/C++ and Fortran implementations
– Can be very easy and simple to use - provides for "incremental
parallelism"
 Microsoft has its own implementation for threads, which is not
related to the UNIX POSIX standard or OpenMP.

Message Passing Model
 The message passing model demonstrates the following
characteristics:
– A set of tasks that use their own local memory during
computation. Multiple tasks can reside on the same physical
machine as well across an arbitrary number of machines.
– Tasks exchange data through communications by sending and
receiving messages.
– Data transfer usually requires cooperative operations to be
performed by each process. For example, a send operation must
have a matching receive operation.

Message Passing Model Implementations: MPI
 From a programming perspective, message passing implementations
commonly comprise a library of subroutines that are imbedded in
source code. The programmer is responsible for determining all
parallelism.
 Historically, a variety of message passing libraries have been available
since the 1980s. These implementations differed substantially from
each other making it difficult for programmers to develop portable
applications.
 In 1992, the MPI Forum was formed with the primary goal of
establishing a standard interface for message passing
implementations.
 Part 1 of the Message Passing Interface (MPI) was released in 1994.
Part 2 (MPI-2) was released in 1996. Both MPI specifications are
available on the web at
www.mcs.anl.gov/Projects/mpi/standard.html.

Message Passing Model Implementations: MPI
 MPI is now the "de facto" industry standard for message passing, replacing
virtually all other message passing implementations used for production
work. Most, if not all of the popular parallel computing platforms offer at
least one implementation of MPI. A few offer a full implementation of MPI-2.
 For shared memory architectures, MPI implementations usually don't use a
network for task communications. Instead, they use shared memory (memory
copies) for performance reasons.

Data Parallel Model
 The data parallel model demonstrates the following characteristics:
– Most of the parallel work focuses on performing operations on a data set.
The data set is typically organized into a common structure, such as an
array or cube.
– A set of tasks work collectively on the same data structure, however, each
task works on a different partition of the same data structure.
– Tasks perform the same operation on their partition of work, for example,
"add 4 to every array element".
 On shared memory architectures, all tasks may have access to the
data structure through global memory. On distributed memory
architectures the data structure is split up and resides as "chunks" in
the local memory of each task.

Data Parallel Model Implementations
 Programming with the data parallel model is usually accomplished by
writing a program with data parallel constructs. The constructs can be
calls to a data parallel subroutine library or, compiler directives
recognized by a data parallel compiler.
 Fortran 90 and 95 (F90, F95): ISO/ANSI standard extensions to Fortran
77.
– Contains everything that is in Fortran 77
– New source code format; additions to character set
– Additions to program structure and commands
– Variable additions - methods and arguments
– Pointers and dynamic memory allocation added
– Array processing (arrays treated as objects) added
– Recursive and new intrinsic functions added
– Many other new features
 Implementations are available for most common parallel platforms.

Data Parallel Model Implementations
 High Performance Fortran (HPF): Extensions to Fortran 90 to support
data parallel programming.
– Contains everything in Fortran 90
– Directives to tell compiler how to distribute data added
– Assertions that can improve optimization of generated code added
– Data parallel constructs added (now part of Fortran 95)
– Implementations are available for most common parallel platforms.
 Compiler Directives: Allow the programmer to specify the distribution
and alignment of data. Fortran implementations are available for
most common parallel platforms.
 Distributed memory implementations of this model usually have the
compiler convert the program into standard code with calls to a
message passing library (MPI usually) to distribute the data to all the
processes. All message passing is done invisibly to the programmer.

Other Models
 Other parallel programming models besides those previously
mentioned certainly exist, and will continue to evolve along with the
ever changing world of computer hardware and software.
 Only three of the more common ones are mentioned here.
– Hybrid
– Single Program Multiple Data
– Multiple Program Multiple Data

Hybrid
 In this model, any two or more parallel programming models are
combined.
 Currently, a common example of a hybrid model is the combination of
the message passing model (MPI) with either the threads model
(POSIX threads) or the shared memory model (OpenMP). This hybrid
model lends itself well to the increasingly common hardware
environment of networked SMP machines.
 Another common example of a hybrid model is combining data
parallel with message passing. As mentioned in the data parallel
model section previously, data parallel implementations (F90, HPF) on
distributed memory architectures actually use message passing to
transmit data between tasks, transparently to the programmer.

Single Program Multiple Data (SPMD)
 Single Program Multiple Data (SPMD):
 SPMD is actually a "high level" programming model that can be built
upon any combination of the previously mentioned parallel
programming models.
 A single program is executed by all tasks simultaneously.
 At any moment in time, tasks can be executing the same or different
instructions within the same program.
 SPMD programs usually have the necessary logic programmed into
them to allow different tasks to branch or conditionally execute only
those parts of the program they are designed to execute. That is,
tasks do not necessarily have to execute the entire program - perhaps
only a portion of it.
 All tasks may use different data

Multiple Program Multiple Data (MPMD)
 Multiple Program Multiple Data (MPMD):
 Like SPMD, MPMD is actually a "high level" programming
model that can be built upon any combination of the
previously mentioned parallel programming models.
 MPMD applications typically have multiple executable
object files (programs). While the application is being run
in parallel, each task can be executing the same or
different program as other tasks.
 All tasks may use different data

EE664: Introduction to Parallel
Computing
1
Dr. Gaurav Trivedi
Lectures 5-14

 Automatic vs. Manual Parallelization
 Understand the Problem and the Program
 Partitioning
 Communications
 Synchronization
 Data Dependencies
 Load Balancing
 Granularity
 I/O
 Limits and Costs of Parallel Programming
 Performance Analysis and Tuning
Some Important Points

 Automatic vs. Manual Parallelization
 Understand the Problem and the Program
 Partitioning
 Communications
 Synchronization
 Data Dependencies
 Load Balancing
 Granularity
 I/O
 Limits and Costs of Parallel Programming
 Performance Analysis and Tuning

 Designing and developing parallel programs has characteristically
been a very manual process. The programmer is typically responsible
for both identifying and actually implementing parallelism.
 Very often, manually developing parallel codes is a time consuming,
complex, error-prone and iterative process.
 For a number of years now, various tools have been available to assist
the programmer with converting serial programs into parallel
programs. The most common type of tool used to automatically
parallelize a serial program is a parallelizing compiler or pre-processor.

 A parallelizing compiler generally works in two different ways:
– Fully Automatic
 The compiler analyzes the source code and identifies opportunities for
parallelism.
 The analysis includes identifying inhibitors to parallelism and possibly a cost
weighting on whether or not the parallelism would actually improve
performance.
 Loops (do, for) loops are the most frequent target for automatic
parallelization.
– Programmer Directed
 Using "compiler directives" or possibly compiler flags, the programmer
explicitly tells the compiler how to parallelize the code.
 May be able to be used in conjunction with some degree of automatic
parallelization also.

 If you are beginning with an existing serial code and have time or
budget constraints, then automatic parallelization may be the answer.
However, there are several important caveats that apply to automatic
parallelization:
– Wrong results may be produced
– Performance may actually degrade
– Much less flexible than manual parallelization
– Limited to a subset (mostly loops) of code
– May actually not parallelize code if the analysis suggests there are
inhibitors or the code is too complex
– Most automatic parallelization tools are for Fortran
 The remainder of this section applies to the manual method of
developing parallel codes.

 Undoubtedly, the first step in developing parallel software
is to first understand the problem that you wish to solve in
parallel. If you are starting with a serial program, this
necessitates understanding the existing code also.
 Before spending time in an attempt to develop a parallel
solution for a problem, determine whether or not the
problem is one that can actually be parallelized.

Calculate the potential energy for each of several thousand
independent conformations of a molecule. When done,
find the minimum energy conformation.
 This problem is able to be solved in parallel. Each of the
molecular conformations is independently determinable.
The calculation of the minimum energy conformation is
also a parallelizable problem.
Example of Parallelizable Problem

Calculation of the Fibonacci series (1,1,2,3,5,8,13,21,...) by
use of the formula:
F(k + 2) = F(k + 1) + F(k)
 This is a non-parallelizable problem because the
calculation of the Fibonacci sequence as shown would
entail dependent calculations rather than independent
ones. The calculation of the k + 2 value uses those of both
k + 1 and k. These three terms cannot be calculated
independently and therefore, not in parallel.
Example of a Non-parallelizable Problem

Identify the program's hotspots
 Know where most of the real work is being done. The
majority of scientific and technical programs usually
accomplish most of their work in a few places.
 Profilers and performance analysis tools can help here
 Focus on parallelizing the hotspots and ignore those
sections of the program that account for little CPU usage.

Identify bottlenecks in the program
 Are there areas that are disproportionately slow, or cause
parallelizable work to halt or be deferred? For example,
I/O is usually something that slows a program down.
 May be possible to restructure the program or use a
different algorithm to reduce or eliminate unnecessary
slow areas

Other considerations
 Identify inhibitors to parallelism. One common class of
inhibitor is data dependence, as demonstrated by the
Fibonacci sequence above.
 Investigate other algorithms if possible. This may be the
single most important consideration when designing a
parallel application.

 One of the first steps in designing a parallel program is to
break the problem into discrete "chunks" of work that can
be distributed to multiple tasks. This is known as
decomposition or partitioning.
 There are two basic ways to partition computational work
among parallel tasks:
– domain decomposition
and
– functional decomposition

Domain Decomposition
 In this type of partitioning, the data associated with a
problem is decomposed. Each parallel task then works on
a portion of of the data.

Partitioning Data
 There are different ways to partition data

Functional Decomposition
 In this approach, the focus is on the computation that is to be
performed rather than on the data manipulated by the computation.
The problem is decomposed according to the work that must be
done. Each task then performs a portion of the overall work.
 Functional decomposition lends itself well to problems that can be
split into different tasks. For example
– Ecosystem Modeling
– Signal Processing
– Climate Modeling

Ecosystem Modeling
 Each program calculates the population of a given group,
where each group's growth depends on that of its
neighbors. As time progresses, each process calculates its
current state, then exchanges information with the
neighbor populations. All tasks then progress to calculate
the state at the next time step.

Signal Processing
 An audio signal data set is passed through four distinct computational
filters. Each filter is a separate process. The first segment of data must
pass through the first filter before progressing to the second. When it
does, the second segment of data passes through the first filter. By
the time the fourth segment of data is in the first filter, all four tasks
are busy.

Climate Modeling
 Each model component can be thought of as a separate task. Arrows
represent exchanges of data between components during
computation: the atmosphere model generates wind velocity data
that are used by the ocean model, the ocean model generates sea
surface temperature data that are used by the atmosphere model,
and so on.
 Combining these two types of problem decomposition is common and
natural.

Who Needs Communications?
 The need for communications between tasks depends upon your problem
 You DON'T need communications
– Some types of problems can be decomposed and executed in parallel with virtually
no need for tasks to share data. For example, imagine an image processing
operation where every pixel in a black and white image needs to have its color
reversed. The image data can easily be distributed to multiple tasks that then act
independently of each other to do their portion of the work.
– These types of problems are often called embarrassingly parallel because they are
so straight-forward. Very little inter-task communication is required.
 You DO need communications
– Most parallel applications are not quite so simple, and do require tasks to share
data with each other. For example, a 3-D heat diffusion problem requires a task to
know the temperatures calculated by the tasks that have neighboring data.
Changes to neighboring data has a direct effect on that task's data.

Factors to Consider (1)
 There are a number of important factors to consider when
designing your program's inter-task communications
 Cost of communications
– Inter-task communication virtually always implies overhead.
– Machine cycles and resources that could be used for computation
are instead used to package and transmit data.
– Communications frequently require some type of synchronization
between tasks, which can result in tasks spending time "waiting"
instead of doing work.
– Competing communication traffic can saturate the available
network bandwidth, further aggravating performance problems.

 Latency vs. Bandwidth
– latency is the time it takes to send a minimal (0 byte) message
from point A to point B. Commonly expressed as microseconds.
– bandwidth is the amount of data that can be communicated per
unit of time. Commonly expressed as megabytes/sec.
– Sending many small messages can cause latency to dominate
communication overheads. Often it is more efficient to package
small messages into a larger message, thus increasing the
effective communications bandwidth.

 Visibility of communications
– With the Message Passing Model, communications are explicit
and generally quite visible and under the control of the
programmer.
– With the Data Parallel Model, communications often occur
transparently to the programmer, particularly on distributed
memory architectures. The programmer may not even be able to
know exactly how inter-task communications are being
accomplished.

 Synchronous vs. asynchronous communications
– Synchronous communications require some type of "handshaking"
between tasks that are sharing data. This can be explicitly structured in
code by the programmer, or it may happen at a lower level unknown to
the programmer.
– Synchronous communications are often referred to as blocking
communications since other work must wait until the communications
have completed.
– Asynchronous communications allow tasks to transfer data
independently from one another. For example, task 1 can prepare and
send a message to task 2, and then immediately begin doing other work.
When task 2 actually receives the data doesn't matter.
– Asynchronous communications are often referred to as non-blocking
communications since other work can be done while the communications
are taking place.
– Interleaving computation with communication is the single greatest
benefit for using asynchronous communications.

 Scope of communications
– Knowing which tasks must communicate with each other is critical
during the design stage of a parallel code. Both of the two
scopings described below can be implemented synchronously or
asynchronously.
– Point-to-point - involves two tasks with one task acting as the
sender/producer of data, and the other acting as the
receiver/consumer.
– Collective - involves data sharing between more than two tasks,
which are often specified as being members in a common group,
or collective.

Collective Communications
 Examples

 Efficiency of communications
– Very often, the programmer will have a choice with regard to
factors that can affect communications performance. Only a few
are mentioned here.
– Which implementation for a given model should be used? Using
the Message Passing Model as an example, one MPI
implementation may be faster on a given hardware platform than
another.
– What type of communication operations should be used? As
mentioned previously, asynchronous communication operations
can improve overall program performance.
– Network media - some platforms may offer more than one
network for communications. Which one is best?

 Overhead and Complexity

Types of Synchronization
 Barrier
– Usually implies that all tasks are involved
– Each task performs its work until it reaches the barrier. It then stops, or "blocks".
– When the last task reaches the barrier, all tasks are synchronized.
– What happens from here varies. Often, a serial section of work must be done. In other cases,
the tasks are automatically released to continue their work.
 Lock / semaphore
– Can involve any number of tasks
– Typically used to serialize (protect) access to global data or a section of code. Only one task at
a time may use (own) the lock / semaphore / flag.
– The first task to acquire the lock "sets" it. This task can then safely (serially) access the
protected data or code.
– Other tasks can attempt to acquire the lock but must wait until the task that owns the lock
releases it.
– Can be blocking or non-blocking
 Synchronous communication operations
– Involves only those tasks executing a communication operation
– When a task performs a communication operation, some form of coordination is required with
the other task(s) participating in the communication. For example, before a task can perform a
send operation, it must first receive an acknowledgment from the receiving task that it is OK to
send.
– Discussed previously in the Communications section.

Definitions
 A dependence exists between program statements when
the order of statement execution affects the results of the
program.
 A data dependence results from multiple use of the same
location(s) in storage by different tasks.
 Dependencies are important to parallel programming
because they are one of the primary inhibitors to
parallelism.

Examples (1): Loop carried data dependence
 The value of A(J-1) must be computed before the value of
A(J), therefore A(J) exhibits a data dependency on A(J-1).
Parallelism is inhibited.
 If Task 2 has A(J) and task 1 has A(J-1), computing the
correct value of A(J) necessitates:
– Distributed memory architecture - task 2 must obtain the value of
A(J-1) from task 1 after task 1 finishes its computation
– Shared memory architecture - task 2 must read A(J-1) after task 1
updates it
DO 500 J = MYSTART,MYEND
A(J) = A(J-1) * 2.0500
CONTINUE

Examples (2): Loop independent data dependence
 As with the previous example, parallelism is inhibited. The value of Y
is dependent on:
– Distributed memory architecture - if or when the value of X is
communicated between the tasks.
– Shared memory architecture - which task last stores the value of X.
 Although all data dependencies are important to identify when
designing parallel programs, loop carried dependencies are
particularly important since loops are possibly the most common
target of parallelization efforts.
task 1 task 2
------ ------
X = 2 X = 4
. .
. .
Y = X**2 Y = X**3

How to Handle Data Dependencies?
 Distributed memory architectures - communicate required
data at synchronization points.
 Shared memory architectures -synchronize read/write
operations between tasks.

Definition
 Load balancing refers to the practice of distributing work among tasks
so that all tasks are kept busy all of the time. It can be considered a
minimization of task idle time.
 Load balancing is important to parallel programs for performance
reasons. For example, if all tasks are subject to a barrier
synchronization point, the slowest task will determine the overall
performance.

How to Achieve Load Balance? (1)
 Equally partition the work each task receives
– For array/matrix operations where each task performs similar
work, evenly distribute the data set among the tasks.
– For loop iterations where the work done in each iteration is
similar, evenly distribute the iterations across the tasks.
– If a heterogeneous mix of machines with varying performance
characteristics are being used, be sure to use some type of
performance analysis tool to detect any load imbalances. Adjust
work accordingly.

How to Achieve Load Balance? (2)
 Use dynamic work assignment
– Certain classes of problems result in load imbalances even if data is
evenly distributed among tasks:
 Sparse arrays - some tasks will have actual data to work on while others have
mostly "zeros".
 Adaptive grid methods - some tasks may need to refine their mesh while
others don't.
 N-body simulations - where some particles may migrate to/from their original
task domain to another task's; where the particles owned by some tasks
require more work than those owned by other tasks.
– When the amount of work each task will perform is intentionally variable,
or is unable to be predicted, it may be helpful to use a scheduler - task
pool approach. As each task finishes its work, it queues to get a new
piece of work.
– It may become necessary to design an algorithm which detects and
handles load imbalances as they occur dynamically within the code.

Definitions
 Computation / Communication Ratio:
– In parallel computing, granularity is a qualitative measure of the
ratio of computation to communication.
– Periods of computation are typically separated from periods of
communication by synchronization events.
 Fine grain parallelism
 Coarse grain parallelism

Fine-grain Parallelism
 Relatively small amounts of computational work are
done between communication events
 Low computation to communication ratio
 Facilitates load balancing
 Implies high communication overhead and less
opportunity for performance enhancement
 If granularity is too fine it is possible that the
overhead required for communications and
synchronization between tasks takes longer than
the computation.

Coarse-grain Parallelism
 Relatively large amounts of computational
work are done between
communication/synchronization events
 High computation to communication ratio
 Implies more opportunity for performance
increase
 Harder to load balance efficiently

Which is Best?
 The most efficient granularity is dependent on the
algorithm and the hardware environment in which it runs.
 In most cases the overhead associated with
communications and synchronization is high relative to
execution speed so it is advantageous to have coarse
granularity.
 Fine-grain parallelism can help reduce overheads due to
load imbalance.

The bad News
 I/O operations are generally regarded as inhibitors to
parallelism
 Parallel I/O systems are immature or not available for all
platforms
 In an environment where all tasks see the same filespace,
write operations will result in file overwriting
 Read operations will be affected by the fileserver's ability
to handle multiple read requests at the same time
 I/O that must be conducted over the network (NFS, non-
local) can cause severe bottlenecks

The good News
 Some parallel file systems are available. For example:
– GPFS: General Parallel File System for AIX (IBM)
– Lustre: for Linux clusters (Cluster File Systems, Inc.)
– PVFS/PVFS2: Parallel Virtual File System for Linux clusters
(Clemson/Argonne/Ohio State/others)
– PanFS: Panasas ActiveScale File System for Linux clusters (Panasas, Inc.)
– HP SFS: HP StorageWorks Scalable File Share. Lustre based parallel file
system (Global File System for Linux) product from HP
 The parallel I/O programming interface specification for MPI has been
available since 1996 as part of MPI-2. Vendor and "free"
implementations are now commonly available.

Some Options
 If you have access to a parallel file system, investigate using it. If you
don't, keep reading...
 Rule #1: Reduce overall I/O as much as possible
 Confine I/O to specific serial portions of the job, and then use parallel
communications to distribute data to parallel tasks. For example, Task
1 could read an input file and then communicate required data to
other tasks. Likewise, Task 1 could perform write operation after
receiving required data from all other tasks.
 For distributed memory systems with shared filespace, perform I/O in
local, non-shared filespace. For example, each processor may have
/tmp filespace which can used. This is usually much more efficient
than performing I/O over the network to one's home directory.
 Create unique filenames for each tasks' input/output file(s)

Amdahl's Law
1
speedup = --------
1 - P
 If none of the code can be parallelized, P = 0 and the
speedup = 1 (no speedup). If all of the code is parallelized,
P = 1 and the speedup is infinite (in theory).
 If 50% of the code can be parallelized, maximum speedup
= 2, meaning the code will run twice as fast.
Amdahl's Law states that potential
program speedup is defined by the
fraction of code (P) that can be
parallelized:

Amdahl's Law
 Introducing the number of processors performing the
parallel fraction of work, the relationship can be modeled
by
 where P = parallel fraction, N = number of processors and
S = serial fraction
1
speedup = ------------
P + S
---
N

Amdahl's Law
 It soon becomes obvious that there are limits to the
scalability of parallelism. For example, at P = .50, .90
and .99 (50%, 90% and 99% of the code is parallelizable)
speedup
--------------------------------
N P = .50 P = .90 P = .99
----- ------- ------- -------
10 1.82 5.26 9.17
100 1.98 9.17 50.25
1000 1.99 9.91 90.99
10000 1.99 9.91 99.02

Amdahl's Law
 However, certain problems demonstrate increased performance by
increasing the problem size. For example:
– 2D Grid Calculations 85 seconds 85%
– Serial fraction 15 seconds 15%
 We can increase the problem size by doubling the grid dimensions
and halving the time step. This results in four times the number of
grid points and twice the number of time steps. The timings then look
like:
– 2D Grid Calculations 680 seconds 97.84%
– Serial fraction 15 seconds 2.16%
 Problems that increase the percentage of parallel time with their size
are more scalable than problems with a fixed percentage of parallel
time.

Complexity
 In general, parallel applications are much more complex than
corresponding serial applications, perhaps an order of magnitude. Not
only do you have multiple instruction streams executing at the same
time, but you also have data flowing between them.
 The costs of complexity are measured in programmer time in virtually
every aspect of the software development cycle:
– Design
– Coding
– Debugging
– Tuning
– Maintenance
 Adhering to "good" software development practices is essential when
when working with parallel applications - especially if somebody
besides you will have to work with the software.

Portability
 Thanks to standardization in several APIs, such as MPI, POSIX threads,
HPF and OpenMP, portability issues with parallel programs are not as
serious as in years past. However...
 All of the usual portability issues associated with serial programs
apply to parallel programs. For example, if you use vendor
"enhancements" to Fortran, C or C++, portability will be a problem.
 Even though standards exist for several APIs, implementations will
differ in a number of details, sometimes to the point of requiring code
modifications in order to effect portability.
 Operating systems can play a key role in code portability issues.
 Hardware architectures are characteristically highly variable and can
affect portability.

Resource Requirements
 The primary intent of parallel programming is to decrease execution
wall clock time, however in order to accomplish this, more CPU time
is required. For example, a parallel code that runs in 1 hour on 8
processors actually uses 8 hours of CPU time.
 The amount of memory required can be greater for parallel codes
than serial codes, due to the need to replicate data and for overheads
associated with parallel support libraries and subsystems.
 For short running parallel programs, there can actually be a decrease
in performance compared to a similar serial implementation. The
overhead costs associated with setting up the parallel environment,
task creation, communications and task termination can comprise a
significant portion of the total execution time for short runs.

Scalability
 The ability of a parallel program's performance to scale is a result of a
number of interrelated factors. Simply adding more machines is rarely
the answer.
 The algorithm may have inherent limits to scalability. At some point,
adding more resources causes performance to decrease. Most parallel
solutions demonstrate this characteristic at some point.
 Hardware factors play a significant role in scalability. Examples:
– Memory-cpu bus bandwidth on an SMP machine
– Communications network bandwidth
– Amount of memory available on any given machine or set of machines
– Processor clock speed
 Parallel support libraries and subsystems software can limit scalability
independent of your application.

 As with debugging, monitoring and analyzing parallel
program execution is significantly more of a challenge
than for serial programs.
 A number of parallel tools for execution monitoring and
program analysis are available.
 Some are quite useful; some are cross-platform also.
 Work remains to be done, particularly in the area of
scalability.

Parallel Examples
 Array Processing
 PI Calculation
 Simple Heat Equation
 1-D Wave Equation

Array Processing
 This example demonstrates calculations on 2-dimensional array
elements, with the computation on each array element being
independent from other array elements.
 The serial program calculates one element at a time in sequential
order.
 Serial code could be of the form:
do j = 1,n
do i = 1,n
a(i,j) = fcn(i,j)
end do
end do
 The calculation of elements is independent of one another - leads to
an embarrassingly parallel situation.
 The problem should be computationally intensive.

Array Processing Solution 1
 Arrays elements are distributed so that each processor owns a portion of an array
(subarray).
 Independent calculation of array elements insures there is no need for communication
between tasks.
 Distribution scheme is chosen by other criteria, e.g. unit stride (stride of 1) through the
subarrays. Unit stride maximizes cache/memory usage.
 Since it is desirable to have unit stride through the subarrays, the choice of a
distribution scheme depends on the programming language.
 After the array is distributed, each task executes the portion of the loop corresponding
to the data it owns. For example, with Fortran block distribution:
do j = mystart, myend
do i = 1,n
a(i,j) = fcn(i,j)
end do
end do
 Notice that only the outer loop variables are different from the serial solution.

One possible implementation
 Implement as SPMD model.
 Master process initializes array, sends info to worker
processes and receives results.
 Worker process receives info, performs its share of
computation and sends results to master.
 Using the Fortran storage scheme, perform block
distribution of the array.
 Pseudo code solution: red highlights changes for
parallelism.

One possible implementation

Array Processing Solution 2: Pool of Tasks
 The previous array solution demonstrated static load
balancing:
– Each task has a fixed amount of work to do
– May be significant idle time for faster or more lightly loaded
processors - slowest tasks determines overall performance.
 Static load balancing is not usually a major concern if all
tasks are performing the same amount of work on
identical machines.
 If you have a load balance problem (some tasks work
faster than others), you may benefit by using a "pool of
tasks" scheme.

Pool of Tasks Scheme
 Two processes are employed
 Master Process:
– Holds pool of tasks for worker processes to do
– Sends worker a task when requested
– Collects results from workers
 Worker Process: repeatedly does the following
– Gets task from master process
– Performs computation
– Sends results to master
 Worker processes do not know before runtime which portion of array
they will handle or how many tasks they will perform.
 Dynamic load balancing occurs at run time: the faster tasks will get
more work to do.
 Pseudo code solution: red highlights changes for parallelism.

Array Processing Solution 2 Pool of Tasks Scheme

Pi Calculation
 The value of PI can be calculated in a number of ways.
Consider the following method of approximating PI
– Inscribe a circle in a square
– Randomly generate points in the square
– Determine the number of points in the square that are also in the
circle
– Let r be the number of points in the circle divided by the number
of points in the square
– PI ~ 4 r
 Note that the more points generated, the better the
approximation

Discussion
 In the above pool of tasks example, each task calculated
an individual array element as a job. The computation to
communication ratio is finely granular.
 Finely granular solutions incur more communication
overhead in order to reduce task idle time.
 A more optimal solution might be to distribute more work
with each job. The "right" amount of work is problem
dependent.

Algorithm
npoints = 10000
circle_count = 0
do j = 1,npoints
generate 2 random numbers between
0 and 1
xcoordinate = random1 ;
ycoordinate = random2
if (xcoordinate, ycoordinate)
inside circle then circle_count =
circle_count + 1
end do
PI = 4.0*circle_count/npoints
Note that most of the time in running this program
would be spent executing the loop
Leads to an embarrassingly parallel solution
- Computationally intensive
- Minimal communication
- Minimal I/O

PI Calculation
Parallel Solution
 Parallel strategy: break the loop into
portions that can be executed by the
tasks.
 For the task of approximating PI:
– Each task executes its portion of the
loop a number of times.
– Each task can do its work without
requiring any information from the
other tasks (there are no data
dependencies).
– Uses the SPMD model. One task acts as
master and collects the results.
 Pseudo code solution: red highlights
changes for parallelism.

PI Calculation
Parallel Solution

Simple Heat Equation
 Most problems in parallel computing require communication among
the tasks. A number of common problems require communication
with "neighbor" tasks.
 The heat equation describes the temperature
change over time, given initial temperature
distribution and boundary conditions.
 A finite differencing scheme is employed to
solve the heat equation numerically on a
square region.
 The initial temperature is zero on the
boundaries and high in the middle.
 The boundary temperature is held at zero.
 For the fully explicit problem, a time stepping
algorithm is used. The elements of a 2-dimensional array represent
the temperature at points on the square.

Simple Heat Equation
 The calculation of an element is dependent upon neighbor
element values.
 A serial program would contain code like:

Parallel Solution 1
 Implement as an SPMD model
 The entire array is partitioned and distributed
as subarrays to all tasks. Each task owns a
portion of the total array.
 Determine data dependencies
– interior elements belonging to a task are independent of other tasks
– border elements are dependent upon a neighbor task's data,
necessitating communication.
 Master process sends initial info to workers, checks for convergence
and collects results
 Worker process calculates solution, communicating as necessary with
neighbor processes
 Pseudo code solution: red highlights changes for parallelism.

Parallel Solution 2
Overlapping Communication and Computation
 In the previous solution, it was assumed that blocking
communications were used by the worker tasks. Blocking
communications wait for the communication process to complete
before continuing to the next program instruction.
 In the previous solution, neighbor tasks communicated border data,
then each process updated its portion of the array.
 Computing times can often be reduced by using non-blocking
communication. Non-blocking communications allow work to be
performed while communication is in progress.
 Each task could update the interior of its part of the solution array
while the communication of border data is occurring, and update its
border after communication has completed.
 Pseudo code for the second solution: red highlights changes for non-
blocking communications.

Parallel Solution 2
Overlapping Communication and Computation

1-D Wave Equation
 In this example, the amplitude along a uniform, vibrating
string is calculated after a specified amount of time has
elapsed.
 The calculation involves:
– the amplitude on the y axis
– i as the position index along the x axis
– node points imposed along the string
– update of the amplitude at discrete time steps.

1-D Wave Equation
 The equation to be solved is the one-dimensional wave
equation:
where c is a constant
 Note that amplitude will depend on previous timesteps (t,
t-1) and neighboring points (i-1, i+1). Data dependence
will mean that a parallel solution will involve
communications.

1-D Wave Equation
Parallel Solution
 Implement as an SPMD model
 The entire amplitude array is partitioned and distributed as subarrays
to all tasks. Each task owns a portion of the total array.
 Load balancing: all points require equal work, so the points should be
divided equally
 A block decomposition would have the work partitioned into the
number of tasks as chunks, allowing each task to own mostly
contiguous data points.
 Communication need only occur on data borders. The larger the block
size the less the communication.

1-D Wave Equation Parallel Solution

Introduction

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Introduction (20)

More from Gopi Saiteja (20)

Recently uploaded (20)

Introduction