Scribd
Upload
104 views

4 Underlying Principles of Parallel

The document provides information about a cloud computing course for 4th year computer science students at KGiSL Institute of Technology in Coimbatore, India. The course aims to explain the fundamentals of cloud computing. The syllabus includes topics like the introduction to cloud computing, underlying principles of parallel and distributed computing, cloud characteristics, and elasticity in cloud. It also discusses concepts like parallel computing approaches, levels of parallelism, Flynn's taxonomy, and hardware architectures for parallel processing.

Uploaded by

selvajoe821
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
104 views

4 Underlying Principles of Parallel

The document provides information about a cloud computing course for 4th year computer science students at KGiSL Institute of Technology in Coimbatore, India. The course aims to explain the fundamentals of cloud computing. The syllabus includes topics like the introduction to cloud computing, underlying principles of parallel and distributed computing, cloud characteristics, and elasticity in cloud. It also discusses concepts like parallel computing approaches, levels of parallelism, Flynn's taxonomy, and hardware architectures for parallel processing.

Uploaded by

selvajoe821
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 25

KGiSL Institute of Technology

(Approved by AICTE, New Delhi; Affiliated to Anna University, Chennai)


Recognized by UGC, Accredited by NBA (IT)
365, KGiSL Campus, Thudiyalur Road, Saravanampatti, Coimbatore – 641035.

Department of Computer Science and Engineering

Name of the Faculty : Ms. T.N.Aruna

Subject Name & Code : CS8791/ Cloud Computing

Branch & Department : Computer Science and Engineering

Year & Semester : IV / VII

Academic Year :2023-24

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Course Outcome

CO 1 Explain the fundamentals of Cloud Computing.K2 LEVEL

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Syllabus
UNIT I INTRODUCTION
Introduction to Cloud Computing – Definition of Cloud – Evolution
of Cloud Computing –Underlying Principles of Parallel and
Distributed Computing – Cloud Characteristics – Elasticity in Cloud
– On Demand Provisioning

CS8791/CC/IVCSE/VIISEM/KG-KiTE
UNDERLYING PRINCIPLES OF
PARALLEL COMPUTING

Parallel computing is a form of computation in which many


instructions are carried out simultaneously operating on the principle
that large problems can often be divided into smaller ones, which
are then solved concurrently (in parallel)

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Parallel Computer Memory
Architectures
• Shared Memory
– Uniform Memory Access (UMA)
– Non-Uniform Memory Access (NUMA)
• Distributed Memory
• Hybrid Distributed-Shared Memory

UNIT-I CLOUD COMPUTING 5


Shared Memory

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Distributed Memory

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Parallel Processing
• The term “parallel” implies a tightly coupled system while
“distributed” refers to a wider class of system including those
who are tightly coupled.
• “Parallel computing” refers to a model where the computation is
divided among several processors sharing the same memory.
• The shared memory has a single address space, which is
accessible to all the processors.
• Parallel programs are then broken down into several units of
executions that can be allocated to different processors, and can
communicate with each other by means of the shared memory.

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Parallel Computing

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Approaches to Parallel Programming
• A sequential program is one which runs on a single processor and has a
single line of control.
• To make many processors collectively work on a single program, the
program must be divided into smaller independent chunks so that each
processor can work on separate chunks of the problem.
• The program decomposed in this way is a parallel program.
• The most prominent parallel programming approaches are the following:
● Data Parallelism
● Process Parallelism
● Farmer and Worker Mode

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Approaches to Parallel Programming

• Data Parallelism🡪 Divide & Conquer🡪 Data🡪 Multiple units🡪


processed by several processors

• Process Parallelism🡪 Multiple activities🡪 Different processors

• Farmer and worker mode🡪 Master Slave Approach

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Levels of Parallelism
Levels of parallelism are decided based on the lumps of code (grain
size)

It boosts processor efficiency by hiding latency

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Parallelism Levels
Parallelism within an application can be detected at several levels:
● Large-grain (or task-level)
● Medium-grain (or control-level)
● Fine-grain (data-level)
● Very-fine grain (multiple instruction issue)

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Parallelism levels

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Types of Parallelism

• Bit-level Parallelism
• Instructional Parallelism
• Data Parallelism
• Task Parallelism

UNIT-I CLOUD COMPUTING 15


Laws of Caution
Here are two important guidelines to take into account:
● Speed of computation is proportional to the square root of
system cost; they never increase linearly. Therefore, faster the
system, more the expense to increase its speed

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Speed Vs No. of Processors
Speed-up by a parallel computer increases as the logarithm of
the number of processors; (i.e., y = k*log(N)).

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Why use Parallel Computing?
• Save time and/or money
• Solve larger problems
• Provide concurrency
• Use of non-local resources
• Limits to serial computing

UNIT-I CLOUD COMPUTING 18


Approaches to Parallel Computing
Flynn’s Taxonomy
Hardware architectures for parallel Processing

•SISD (Single Instruction Single Data) Based on the number of


instructions and data
streams, that can be
•SIMD (Single Instruction Multiple Data) processed simultaneously,
computing systems are
•MISD (Multiple Instruction Single Data) classified into four
categories
•MIMD (Multiple Instruction Multiple Data)

UNIT-I CLOUD COMPUTING 19


SISD
(Single Instruction Single Data)

CS8791/CC/IVCSE/VIISEM/KG-KiTE
SIMD
(Single Instruction Multiple Data)

CS8791/CC/IVCSE/VIISEM/KG-KiTE
MISD
(Multiple Instruction Single Data)

CS8791/CC/IVCSE/VIISEM/KG-KiTE
MIMD
(Multiple Instruction Multiple Data)

CS8791/CC/IVCSE/VIISEM/KG-KiTE
Time To Think (T2T)
A term for simultaneous access to a resource, physical or logical.
(BT Level- Remember)
a) Multiprogramming
b) Multitasking
c) Threads
d) Concurrency
Ans: d

CS8791/CC/IVCSE/VIISEM/KG-KiTE
More to Know

https://www.youtube.com/watch?v=1XGo8K1boH4

CS8791/CC/IVCSE/VIISEM/KG-KiTE

You might also like