SlideShare a Scribd company logo
1 of 5
Download to read offline
International Journal of Innovative Research in Advanced Engineering (IJIRAE)
Volume 1 Issue 2 (April 2014)
_______________________________________________________________________________________________
ISSN: 2278-2311 IJIRAE | http://ijirae.com
© 2014, IJIRAE - All Rights Reserved Page - 62
A Parallel Computing-a Paradigm to achieve High
Performance
Prof.Ashwini M. Bhugul
Asst. prof. MMCOE, Pune
ashu_b53@rediffmail.com
Abstract-Over last few years there has been rapid changes found in computing field.today, we are using the latest
upgrade system which provides the faster output and high performance. User view towards computing is only to
get the correct and fast result. There are many techniques which improves the system performance. Today’s
widely use computing method is parallel computing. Parallel computing, including foundational and theoretical
aspects, systems, languages, architectures, tools, and applications. It will address all classes of parallel-
processing platforms including concurrent, multithreaded, multicore, accelerated, multiprocessor, clusters, and
supercomputers. This paper reviews the overview of parallel processing to show how parallel computing can
improve the system performance.
1. INTRODUCTION
Parallel computer architecture provides a proportional increase in performance with increase in performance with
increasing system resources. System resources are scaled by the number of processors used, memory capacity
enlarged, access latency tolerated, I/O bandwidth required, etc.parallel architecture has a higher potential to deliver
scalable performance Parallelism appears in various forms such as look ahead, pipelining, vectorization,
concurrency, data parallelism, etc.
Parallel computers are those that execute programs in MIMD code. There are two classes, namely-shared-
memory multiprocessors and message passing multicomputers.In parallel computing a large task is divided into
subtask and all the sub tasks will execute in parallel. This will help to reduce the waiting or stalled stages in pipeline
of the computer system. Lower the number of clock cycles required higher performance will be achieve by the
system. The degree of parallelism depends upon the parallel computer architecture. A parallel computer (or multiple
processor system) is a collection of communicating processing elements (processors) that cooperate to solve large
computational problems fast by dividing such problems into parallel tasks.
There are some classification made for parallel computing, one of is Flynn’s classification. Flynn’s classification is
based on multiplicity of instruction streams and data streams in computer system. Its machine organization includes
SISD (single instruction single data), SIMD (single instruction multiple data), MISD (multiple instruction single
data), and MIMD (multiple instruction multiple data).
Some Broad issues involved:
1. The concurrency and communication characteristics of parallel algorithms for a given computational problem.
2. What portions of the computation and data are allocated or mapped to each PE.
3. How the processing elements cooperate and communicate.
3. How data is shared/transmitted between processors.
4. Abstractions and primitives for cooperation/communication and synchronization.
Parallel computing improves the system performance, as the complete task is divided into stages, which will take
less time to execute the stream of data. Both data and instructions are fetched by memory module. Instructions are
decoded by the control unit, which sends to processor units for execution. Each instruction stream is generated by an
independent control unit. Multiple data stream originates from shared memory module. This improves the system
speedup and performance.
1.1General overview of parallel processing system:
International Journal of Innovative Research in Advanced Engineering (IJIRAE)
Volume 1 Issue 2 (April 2014)
_______________________________________________________________________________________________
ISSN: 2278-2311 IJIRAE | http://ijirae.com
© 2014, IJIRAE - All Rights Reserved Page - 63
CU-control unit
PU-processing unit
MEM-memory
Figure 1.1: SIMD architecture showing parallel computing
1.2 Need of Parallel Computing
Whenever there is need to work on large amount of data, system need a fast performance, more computing
cycles/memory needed, there will be overload on machine when it performs a whole task, parallel computing make
this task efficient by dividing a task into stages that will reduce the computing clock cycles and memory too. Some
of the applications of parallel computing are: Scientific/Engineering computing: CFD, Biology, Chemistry, Physics,
General-purpose computing: Video, Graphics, CAD, Databases, Transaction Processing, Gaming, etc.
Number of transistors on chip growing rapidly. Clock rates expected to continue to go up but only slowly.
Actual performance returns diminishing due to deeper pipelines. Increased transistor density allows integrating
multiple processor cores per creating Chip-Multiprocessors (CMPs) even for mainstream computing applications
that is also one of application of parallel processing The increased utilization of commodity of-the-shelf (COTS)
components in high performance parallel computing systems instead of costly custom components used in
traditional Super computers leading to much lower parallel system cost. Today’s microprocessors offer high-
performance and have multiprocessor support with parallel processing.
II. DIFFERENT GRANULARITIES OF PARALLELISM
In parallel computing units of work can be execute concurrently if sufficient recourses exists. There are two
granularities:
2.1 Thread level parallelism
2.2Instruction level parallelism
2.1Thread level parallelism (TLP)
A thread is separate process having its own instructions and data. Thread may be a separate process or single
program executing in parallel. In parallel computing, the thread offers different instructions and data so that the
processor can switch to another thread and can continue the instructions, this will include the thing that, processor
will continuously execute instructions without stalls, this will take less time to execute instructions.TLP is a
software that enables a program often a high end programs such as web application, etc.
There are two approaches to TLP:
1. Fine-grained multithreading
2. Coarse-grained multithreading
Fine grained multithreading switches threads on each instruction, that will execute multiple instructions
simultaneously, CPU must be able to switch threads every clock cycles. The advantage of using this technique is
that it can hide both short and long stalls. Coarse-grained multithreading switches threads only when current thread
is likely to stall for some time.it is more natural for any given thread and consume less time to switch threads. It is
also easier to implement switching process.
CU
PU1
PU2
PUn
MEM1
MEM2
MEMn
International Journal of Innovative Research in Advanced Engineering (IJIRAE)
Volume 1 Issue 2 (April 2014)
_______________________________________________________________________________________________
ISSN: 2278-2311 IJIRAE | http://ijirae.com
© 2014, IJIRAE - All Rights Reserved Page - 64
2.2 Instruction Level Parallelism
Instruction-level Parallelism CILP) is a family of processor and compiler design techniques that speed up execution
by causing individual machine operations to execute in parallel. Pipelining can overlap the execution of instructions
when they are independent on each other, this potential overlap among instructions is called as Instruction level
Parallelism. Processing instructions in parallel requires some tasks:
1. Checking independencies between instructions, if two instructions are independent on each other, they can
be group together to execute in parallel.
2. Assigning instructions to the functional units on hardware.
3. Determining when instructions are initiated. This include the technique called score boarding, it allows
instructions to execute out of order when there is sufficient resource available.
ILP architectures can be classified as follows.
 Sequential architectures: architectures for which the program is not expected to convey any explicit
information regarding parallelism. Superscalar processors are representative of ILP processor
implementations for sequential architectures.
 Dependence architectures: This architecture provides information of those programs in which instructions
which are dependent on each other. Dataflow processors are one of the examples of this architecture.
 Independence architectures: architectures for which the program provides information as to which
operations are independent of one another. Very Long Instruction Word (VLIW) processors are examples
of the class of independence architectures.
III. SOME PARALLEL PROGRAMMING TECHNIQUES
Sometimes in large scale industries, there is a multiprocessor system, which requires number of instructions to be
executed simultaneously, as the system consists of number of processor connected together there may happens some
memory conflicts while performing tasks parallel. Processor needs to communicate with each or want to share some
data with each other; hence there are some parallel programming techniques, three of them are explained below:
3.1. Message passing parallel programming
In massage passing programming programs view their programs as a collection of cooperating processes
with private variables. This style is suitable for message passing parallel computers. This technique needs only two
primitives that is send and receive, that will send or receive instructions from one processor to another. Figure given
below showing Message-Passing example of Intel Paragon.
Figure 31: Sandia’s Intel Paragon XP/S-based Supercomputer
There are most widely used Message Passing Programming tools are:
1. Message Passing Interface (MPI):
It provides a standard for writing concurrent message-passing programs.MPI offers rich set of functions for
doing point to point communicaton.it will divide a task into stages and that separate tasks can communicate with
each other.MPI implementations include parallel libraries used by existing programming languages (C, C++).
2. Parallel Virtual Machine (PVM):
International Journal of Innovative Research in Advanced Engineering (IJIRAE)
Volume 1 Issue 2 (April 2014)
_______________________________________________________________________________________________
ISSN: 2278-2311 IJIRAE | http://ijirae.com
© 2014, IJIRAE - All Rights Reserved Page - 65
PVM is portable message passing programming system, designed to form separate host machines to from
“virtual machine”. Virtual machine is collection of processors that may work simultaneously or at different time. It
enables a collection of heterogeneous computers to use as a coherent and flexible concurrent computational
resource. PVM support software executes on each machine in a user configurable pool, and provides computational
environment of concurrent applications. User programs written for example in C, FORTRAN or Java are provided
access to PVM through the use of calls to PVM library routines.
3.2. Shared Memory Programming
In shared memory programming, programmers view their programs as a collection of cooperating processes that will
access a common pool of shared variables. In such computers, processors may not have private program or data
memory. a common data or program is stored in shared memory that will use by all processors. The main program
creates separate processes and assigns a tasks to every processor with a common shared memory, each processor
computes independently and after all, result of each processor stored in common memory. Two statements are use
for this purpose: 1. Fork 2. Join
Example: Process X; Process Y;
fork y;
join y;
end y;
Process X when it encounters fork y invokes another process y, after invoking y, it continues doing its work. Process
y starts executing concurrently in another processor. When X reaches join y statement has to wait till y finish its
work. In shared memory programming when multiple processors are in use and sharing a common memory so care
has to be taken that no two dependent instructions should execute simultaneously. For shared memory programming
three models of multiprocessors are:
1. The Uniform Memory Access (UMA) Model:
In this model all physical memory is shared by all processors. All processors have equal access to all memory
addresses.
2. Distributed memory or Non-uniform Memory Access (NUMA) Model:
In this model, Shared memory is physically distributed locally among processors. Access latency to remote memory
is higher.
3. The Cache-Only Memory Architecture (COMA) Model:
In this model, A special case of a NUMA machine where all distributed main memory is converted to caches. No
memory hierarchy at each processor.
3.3 Data parallel Programming
In Data Parallel Programming many programs can apply same operation to each element of composite
data.sometimes, looping statements performed repetitive tasks, using data parallelism this repetition carried out
automatically by having multiprocessors working concurrently. Logically, single thread of control, performs
sequential or parallel steps conceptually, a processor is associated with each data element.
Figure 3.3: Data parallel system (All PE’s are synchronized)
Control Processor
PE PE PE
PE PE PE
PE PE PE
International Journal of Innovative Research in Advanced Engineering (IJIRAE)
Volume 1 Issue 2 (April 2014)
_______________________________________________________________________________________________
ISSN: 2278-2311 IJIRAE | http://ijirae.com
© 2014, IJIRAE - All Rights Reserved Page - 66
Example machines, Thinking Machines CM-1, Maspar MP-1 and MP-2, etc.Data parallel programming
makes programs easy to read and write. Same program will be executed over different data sets simultaneously on
multiple processors. a popular data parallel programming language is high performance Fortran (HPF). figure 3.3
given below shows example of data parallel systems. Array of many simple processors each with little memory.
Processors don’t sequence through instructions. Attached to a control processor that issues instructions Specialized
and general communication, global synchronization
IV.CONCLUSION
At the end of this review paper, we may observe some current some current trends. High performance
computers are increasingly in demand, Parallel computing architecture is today’s widley used architecture which
provides speed and high performance. It is used in many scientific, engineering, medical, military and research areas
to achieve high system performance.
V.REFERENCES
1. Rafiqul Zaman Khan, Md Firoj A Comparative Study on Parallel Programming Tools in Parallel Distributed
Computing System: MPI and PVM, Department of Computer Science, Aligarh Muslim University, Aligarh-
202002,(U.P), India.
2 Ramakrishna Rau, Joseph A. Fisher, Instruction-Level Parallel Processing: History, Overview and Perspective,
Computer Systems Laboratory,HPL-92-132,October, 1992.
3. M. D. Smith, M. Horowitz and M. Lam. Efficient superscalar performance through boosting. Proc. Fifth
International Conference on Architectural Support for Programming& Laneua&es and Operating Systems
(Boston, Massachussetts, October 1992), 248-259.
4. R. Chaiken, B. Jenkins, P.-_A. Larson,B. Ramsey, D. Shakib, S. Weaver, and J. Zhou. SCOPE: Easy and
e_cient parallel processing of massive data sets. International Conference of Very Large Data Bases (VLDB),
August 2008.
5. D. DeWitt and J. Gray. Parallel database systems: The future of high performance database processing.
Communications of the ACM, 36(6), 1992.
6. R. Pike, S. Dorward, R. Griesemer, and S. Quinlan. Interpreting the data: Parallel analysis with Sawzall.
Scienti_c Programming,13(4):277{298, 2005.
7. F. Rabhi and S. Gorlatch. Patterns and Skeletons for Parallel and Distributed Computing. Springer, 2003.
8. Y. Yu, M. Isard, D. Fetterly, M. Budiu,U. Erlingsson, P. K. Gunda, and J. Currey.DryadLINQ: A system for
general-purpose distributed data-parallel computing using a high-level language. In Proceedings of the 8th
Symposium on Operating Systems Design and Implementation (OSDI), December 8-10 2008.
9. R. Z. Khan, A. Q. Ansari and Kalim Qureshi―Performance Prediction for Parallel Scientific Applicationǁ,
Malaysian Journal of Computer Science,Vol. 17 No. 1, June 2004, pp 65-73.
10. Kai Hwang, Faye A. Briggs, "Computer Architecture and Parallel Processing" McGraw-Hill international
Edition
11. Kai Hwang, "Advanced Computer Architecture", Tata McGraw-Hill
12. V.Rajaraman, L Sivaram Murthy, "Parallel Computers", PHI.

More Related Content

What's hot

Lecture 1
Lecture 1Lecture 1
Lecture 1Mr SMAK
 
OS introduction
OS introductionOS introduction
OS introductionanand hd
 
OS Memory Management
OS Memory ManagementOS Memory Management
OS Memory Managementanand hd
 
Introduction to Parallel Computing
Introduction to Parallel ComputingIntroduction to Parallel Computing
Introduction to Parallel ComputingRoshan Karunarathna
 
Parallel computing and its applications
Parallel computing and its applicationsParallel computing and its applications
Parallel computing and its applicationsBurhan Ahmed
 
PARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTES
PARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTESPARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTES
PARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTESsuthi
 
Introduction to parallel_computing
Introduction to parallel_computingIntroduction to parallel_computing
Introduction to parallel_computingMehul Patel
 
Applications of paralleL processing
Applications of paralleL processingApplications of paralleL processing
Applications of paralleL processingPage Maker
 
VIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMS
VIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMSVIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMS
VIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMScseij
 
Research Scope in Parallel Computing And Parallel Programming
Research Scope in Parallel Computing And Parallel ProgrammingResearch Scope in Parallel Computing And Parallel Programming
Research Scope in Parallel Computing And Parallel ProgrammingShitalkumar Sukhdeve
 
Design and implementation of microprocessor trainer bus system
Design and implementation of microprocessor trainer bus systemDesign and implementation of microprocessor trainer bus system
Design and implementation of microprocessor trainer bus systemIJARIIT
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)inventionjournals
 
Introduction to Embedded System I: Chapter 2 (5th portion)
Introduction to Embedded System I: Chapter 2 (5th portion)Introduction to Embedded System I: Chapter 2 (5th portion)
Introduction to Embedded System I: Chapter 2 (5th portion)Moe Moe Myint
 
Parallel computing in india
Parallel computing in indiaParallel computing in india
Parallel computing in indiaPreeti Chauhan
 

What's hot (18)

Lecture 1
Lecture 1Lecture 1
Lecture 1
 
OS introduction
OS introductionOS introduction
OS introduction
 
Parallel computing persentation
Parallel computing persentationParallel computing persentation
Parallel computing persentation
 
OS Memory Management
OS Memory ManagementOS Memory Management
OS Memory Management
 
Os
OsOs
Os
 
Introduction to Parallel Computing
Introduction to Parallel ComputingIntroduction to Parallel Computing
Introduction to Parallel Computing
 
Parallel computing and its applications
Parallel computing and its applicationsParallel computing and its applications
Parallel computing and its applications
 
PARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTES
PARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTESPARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTES
PARALLEL ARCHITECTURE AND COMPUTING - SHORT NOTES
 
Introduction to parallel_computing
Introduction to parallel_computingIntroduction to parallel_computing
Introduction to parallel_computing
 
Applications of paralleL processing
Applications of paralleL processingApplications of paralleL processing
Applications of paralleL processing
 
VIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMS
VIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMSVIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMS
VIEW OF MEMORY ALLOCATION AND MANAGEMENT IN COMPUTER SYSTEMS
 
Research Scope in Parallel Computing And Parallel Programming
Research Scope in Parallel Computing And Parallel ProgrammingResearch Scope in Parallel Computing And Parallel Programming
Research Scope in Parallel Computing And Parallel Programming
 
Design and implementation of microprocessor trainer bus system
Design and implementation of microprocessor trainer bus systemDesign and implementation of microprocessor trainer bus system
Design and implementation of microprocessor trainer bus system
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)
 
Introduction to Embedded System I: Chapter 2 (5th portion)
Introduction to Embedded System I: Chapter 2 (5th portion)Introduction to Embedded System I: Chapter 2 (5th portion)
Introduction to Embedded System I: Chapter 2 (5th portion)
 
Fundamentals
FundamentalsFundamentals
Fundamentals
 
Parallel computing in india
Parallel computing in indiaParallel computing in india
Parallel computing in india
 
Parallel processing Concepts
Parallel processing ConceptsParallel processing Concepts
Parallel processing Concepts
 

Viewers also liked

Natasha Cooper CV 2015 PA EA current
Natasha Cooper CV 2015 PA EA currentNatasha Cooper CV 2015 PA EA current
Natasha Cooper CV 2015 PA EA currentNatasha Cooper
 
Vissco NewsLetter - THE COMFORT INDIA TIMES
Vissco NewsLetter - THE COMFORT INDIA TIMESVissco NewsLetter - THE COMFORT INDIA TIMES
Vissco NewsLetter - THE COMFORT INDIA TIMESVissco
 
Presentation1
Presentation1Presentation1
Presentation1Pup
 
Requisite Trust Based Routing Protocol for WSN
Requisite Trust Based Routing Protocol for WSNRequisite Trust Based Routing Protocol for WSN
Requisite Trust Based Routing Protocol for WSNAM Publications
 
Code of Behaviour - Carthagina
Code of Behaviour - CarthaginaCode of Behaviour - Carthagina
Code of Behaviour - CarthaginaCarthagina
 
โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)
โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)
โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)Sutita Saowakon
 

Viewers also liked (10)

Natasha Cooper CV 2015 PA EA current
Natasha Cooper CV 2015 PA EA currentNatasha Cooper CV 2015 PA EA current
Natasha Cooper CV 2015 PA EA current
 
Squares Profile.PDF
Squares Profile.PDFSquares Profile.PDF
Squares Profile.PDF
 
Vissco NewsLetter - THE COMFORT INDIA TIMES
Vissco NewsLetter - THE COMFORT INDIA TIMESVissco NewsLetter - THE COMFORT INDIA TIMES
Vissco NewsLetter - THE COMFORT INDIA TIMES
 
Cubic BF-Algebra
Cubic BF-AlgebraCubic BF-Algebra
Cubic BF-Algebra
 
Presentation1
Presentation1Presentation1
Presentation1
 
Requisite Trust Based Routing Protocol for WSN
Requisite Trust Based Routing Protocol for WSNRequisite Trust Based Routing Protocol for WSN
Requisite Trust Based Routing Protocol for WSN
 
Hibernate presentation
Hibernate presentationHibernate presentation
Hibernate presentation
 
Code of Behaviour - Carthagina
Code of Behaviour - CarthaginaCode of Behaviour - Carthagina
Code of Behaviour - Carthagina
 
โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)
โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)
โครงร่างโครงงานคอมพิวเตอร์ (เดี่ยว)
 
Yathreb_Trans.PDF
Yathreb_Trans.PDFYathreb_Trans.PDF
Yathreb_Trans.PDF
 

Similar to A Parallel Computing-a Paradigm to achieve High Performance

Performance evaluation of larger matrices over cluster of four nodes using mpi
Performance evaluation of larger matrices over cluster of four nodes using mpiPerformance evaluation of larger matrices over cluster of four nodes using mpi
Performance evaluation of larger matrices over cluster of four nodes using mpieSAT Journals
 
TIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KIT
TIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KITTIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KIT
TIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KITijesajournal
 
Unit 1os processes and threads
Unit 1os processes and threadsUnit 1os processes and threads
Unit 1os processes and threadsdonny101
 
Hardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmpHardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmpeSAT Publishing House
 
Operating Systems
Operating Systems Operating Systems
Operating Systems Fahad Shaikh
 
Parallel and Distributed Computing chapter 1
Parallel and Distributed Computing chapter 1Parallel and Distributed Computing chapter 1
Parallel and Distributed Computing chapter 1AbdullahMunir32
 
Methods Of Performance Evaluation And Verification On...
Methods Of Performance Evaluation And Verification On...Methods Of Performance Evaluation And Verification On...
Methods Of Performance Evaluation And Verification On...Maritza Tyson
 
Real Time Operating System ,Structures of Operating System (Monolithic, Micro...
Real Time Operating System ,Structures of Operating System(Monolithic, Micro...Real Time Operating System ,Structures of Operating System(Monolithic, Micro...
Real Time Operating System ,Structures of Operating System (Monolithic, Micro...VIJETHAK2
 
The Dynamic, Broad And Complex Nature Of Cloud Infrastructure
The Dynamic, Broad And Complex Nature Of Cloud InfrastructureThe Dynamic, Broad And Complex Nature Of Cloud Infrastructure
The Dynamic, Broad And Complex Nature Of Cloud InfrastructureRenee Delgado
 
parallel computing.ppt
parallel computing.pptparallel computing.ppt
parallel computing.pptssuser413a98
 
CS8603_Notes_003-1_edubuzz360.pdf
CS8603_Notes_003-1_edubuzz360.pdfCS8603_Notes_003-1_edubuzz360.pdf
CS8603_Notes_003-1_edubuzz360.pdfKishaKiddo
 
CC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdfCC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdfHasanAfwaaz1
 
LM1 - Computer System Overview, system calls
LM1 - Computer System Overview, system callsLM1 - Computer System Overview, system calls
LM1 - Computer System Overview, system callsmanideepakc
 
The influence of data size on a high-performance computing memetic algorithm ...
The influence of data size on a high-performance computing memetic algorithm ...The influence of data size on a high-performance computing memetic algorithm ...
The influence of data size on a high-performance computing memetic algorithm ...journalBEEI
 
Advanced It Outsourcing By Using Cloud Computing Model
Advanced It Outsourcing By Using Cloud Computing ModelAdvanced It Outsourcing By Using Cloud Computing Model
Advanced It Outsourcing By Using Cloud Computing ModelCarla Jardine
 
The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...
The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...
The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...ijceronline
 
Basic features of distributed system
Basic features of distributed systemBasic features of distributed system
Basic features of distributed systemsatish raj
 

Similar to A Parallel Computing-a Paradigm to achieve High Performance (20)

Performance evaluation of larger matrices over cluster of four nodes using mpi
Performance evaluation of larger matrices over cluster of four nodes using mpiPerformance evaluation of larger matrices over cluster of four nodes using mpi
Performance evaluation of larger matrices over cluster of four nodes using mpi
 
TIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KIT
TIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KITTIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KIT
TIME CRITICAL MULTITASKING FOR MULTICORE MICROCONTROLLER USING XMOS® KIT
 
Unit 1os processes and threads
Unit 1os processes and threadsUnit 1os processes and threads
Unit 1os processes and threads
 
Hardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmpHardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmp
 
Operating Systems
Operating Systems Operating Systems
Operating Systems
 
Parallel and Distributed Computing chapter 1
Parallel and Distributed Computing chapter 1Parallel and Distributed Computing chapter 1
Parallel and Distributed Computing chapter 1
 
Methods Of Performance Evaluation And Verification On...
Methods Of Performance Evaluation And Verification On...Methods Of Performance Evaluation And Verification On...
Methods Of Performance Evaluation And Verification On...
 
Real Time Operating System ,Structures of Operating System (Monolithic, Micro...
Real Time Operating System ,Structures of Operating System(Monolithic, Micro...Real Time Operating System ,Structures of Operating System(Monolithic, Micro...
Real Time Operating System ,Structures of Operating System (Monolithic, Micro...
 
Firo
FiroFiro
Firo
 
The Dynamic, Broad And Complex Nature Of Cloud Infrastructure
The Dynamic, Broad And Complex Nature Of Cloud InfrastructureThe Dynamic, Broad And Complex Nature Of Cloud Infrastructure
The Dynamic, Broad And Complex Nature Of Cloud Infrastructure
 
Chapter 10
Chapter 10Chapter 10
Chapter 10
 
parallel computing.ppt
parallel computing.pptparallel computing.ppt
parallel computing.ppt
 
CS8603_Notes_003-1_edubuzz360.pdf
CS8603_Notes_003-1_edubuzz360.pdfCS8603_Notes_003-1_edubuzz360.pdf
CS8603_Notes_003-1_edubuzz360.pdf
 
CC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdfCC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdf
 
Report_Internships
Report_InternshipsReport_Internships
Report_Internships
 
LM1 - Computer System Overview, system calls
LM1 - Computer System Overview, system callsLM1 - Computer System Overview, system calls
LM1 - Computer System Overview, system calls
 
The influence of data size on a high-performance computing memetic algorithm ...
The influence of data size on a high-performance computing memetic algorithm ...The influence of data size on a high-performance computing memetic algorithm ...
The influence of data size on a high-performance computing memetic algorithm ...
 
Advanced It Outsourcing By Using Cloud Computing Model
Advanced It Outsourcing By Using Cloud Computing ModelAdvanced It Outsourcing By Using Cloud Computing Model
Advanced It Outsourcing By Using Cloud Computing Model
 
The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...
The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...
The Parallel Architecture Approach, Single Program Multiple Data (Spmd) Imple...
 
Basic features of distributed system
Basic features of distributed systemBasic features of distributed system
Basic features of distributed system
 

More from AM Publications

DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...
DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...
DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...AM Publications
 
TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...
TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...
TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...AM Publications
 
THE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGN
THE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGNTHE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGN
THE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGNAM Publications
 
TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...
TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...
TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...AM Publications
 
USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...
USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...
USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...AM Publications
 
ANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISES
ANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISESANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISES
ANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISESAM Publications
 
REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS
REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS
REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS AM Publications
 
EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...
EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...
EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...AM Publications
 
HMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITION
HMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITIONHMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITION
HMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITIONAM Publications
 
PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...
PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...
PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...AM Publications
 
EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...
EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...
EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...AM Publications
 
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...AM Publications
 
REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...
REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...
REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...AM Publications
 
OPTICAL CHARACTER RECOGNITION USING RBFNN
OPTICAL CHARACTER RECOGNITION USING RBFNNOPTICAL CHARACTER RECOGNITION USING RBFNN
OPTICAL CHARACTER RECOGNITION USING RBFNNAM Publications
 
DETECTION OF MOVING OBJECT
DETECTION OF MOVING OBJECTDETECTION OF MOVING OBJECT
DETECTION OF MOVING OBJECTAM Publications
 
SIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENT
SIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENTSIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENT
SIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENTAM Publications
 
PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...
PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...
PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...AM Publications
 
ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...
ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...
ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...AM Publications
 
A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY
A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY
A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY AM Publications
 

More from AM Publications (20)

DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...
DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...
DEVELOPMENT OF TODDLER FAMILY CADRE TRAINING BASED ON ANDROID APPLICATIONS IN...
 
TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...
TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...
TESTING OF COMPOSITE ON DROP-WEIGHT IMPACT TESTING AND DAMAGE IDENTIFICATION ...
 
THE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGN
THE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGNTHE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGN
THE USE OF FRACTAL GEOMETRY IN TILING MOTIF DESIGN
 
TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...
TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...
TWO-DIMENSIONAL INVERSION FINITE ELEMENT MODELING OF MAGNETOTELLURIC DATA: CA...
 
USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...
USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...
USING THE GENETIC ALGORITHM TO OPTIMIZE LASER WELDING PARAMETERS FOR MARTENSI...
 
ANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISES
ANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISESANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISES
ANALYSIS AND DESIGN E-MARKETPLACE FOR MICRO, SMALL AND MEDIUM ENTERPRISES
 
REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS
REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS
REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS
 
EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...
EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...
EVALUATE THE STRAIN ENERGY ERROR FOR THE LASER WELD BY THE H-REFINEMENT OF TH...
 
HMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITION
HMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITIONHMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITION
HMM APPLICATION IN ISOLATED WORD SPEECH RECOGNITION
 
PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...
PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...
PEDESTRIAN DETECTION IN LOW RESOLUTION VIDEOS USING A MULTI-FRAME HOG-BASED D...
 
INTELLIGENT BLIND STICK
INTELLIGENT BLIND STICKINTELLIGENT BLIND STICK
INTELLIGENT BLIND STICK
 
EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...
EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...
EFFECT OF SILICON - RUBBER (SR) SHEETS AS AN ALTERNATIVE FILTER ON HIGH AND L...
 
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
UTILIZATION OF IMMUNIZATION SERVICES AMONG CHILDREN UNDER FIVE YEARS OF AGE I...
 
REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...
REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...
REPRESENTATION OF THE BLOCK DATA ENCRYPTION ALGORITHM IN AN ANALYTICAL FORM F...
 
OPTICAL CHARACTER RECOGNITION USING RBFNN
OPTICAL CHARACTER RECOGNITION USING RBFNNOPTICAL CHARACTER RECOGNITION USING RBFNN
OPTICAL CHARACTER RECOGNITION USING RBFNN
 
DETECTION OF MOVING OBJECT
DETECTION OF MOVING OBJECTDETECTION OF MOVING OBJECT
DETECTION OF MOVING OBJECT
 
SIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENT
SIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENTSIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENT
SIMULATION OF ATMOSPHERIC POLLUTANTS DISPERSION IN AN URBAN ENVIRONMENT
 
PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...
PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...
PREPARATION AND EVALUATION OF WOOL KERATIN BASED CHITOSAN NANOFIBERS FOR AIR ...
 
ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...
ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...
ANALYSIS ON LOAD BALANCING ALGORITHMS IMPLEMENTATION ON CLOUD COMPUTING ENVIR...
 
A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY
A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY
A MODEL BASED APPROACH FOR IMPLEMENTING WLAN SECURITY
 

Recently uploaded

Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...
Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...
Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...amrabdallah9
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Bahzad5
 
Test of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptxTest of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptxHome
 
Engineering Mechanics Chapter 5 Equilibrium of a Rigid Body
Engineering Mechanics  Chapter 5  Equilibrium of a Rigid BodyEngineering Mechanics  Chapter 5  Equilibrium of a Rigid Body
Engineering Mechanics Chapter 5 Equilibrium of a Rigid BodyAhmadHajasad2
 
Design of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxDesign of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxYogeshKumarKJMIT
 
Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...sahb78428
 
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...Amil baba
 
IT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptxIT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptxSAJITHABANUS
 
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchrohitcse52
 
solar wireless electric vechicle charging system
solar wireless electric vechicle charging systemsolar wireless electric vechicle charging system
solar wireless electric vechicle charging systemgokuldongala
 
ASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entenderASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entenderjuancarlos286641
 
Landsman converter for power factor improvement
Landsman converter for power factor improvementLandsman converter for power factor improvement
Landsman converter for power factor improvementVijayMuni2
 
Summer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdf
Summer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdfSummer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdf
Summer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdfNaveenVerma126
 
Dev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingDev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingMarian Marinov
 
The relationship between iot and communication technology
The relationship between iot and communication technologyThe relationship between iot and communication technology
The relationship between iot and communication technologyabdulkadirmukarram03
 
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratoryدليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide LaboratoryBahzad5
 
cloud computing notes for anna university syllabus
cloud computing notes for anna university syllabuscloud computing notes for anna university syllabus
cloud computing notes for anna university syllabusViolet Violet
 

Recently uploaded (20)

Lecture 2 .pptx
Lecture 2                            .pptxLecture 2                            .pptx
Lecture 2 .pptx
 
Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...
Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...
Strategies of Urban Morphologyfor Improving Outdoor Thermal Comfort and Susta...
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)
 
Test of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptxTest of Significance of Large Samples for Mean = µ.pptx
Test of Significance of Large Samples for Mean = µ.pptx
 
Engineering Mechanics Chapter 5 Equilibrium of a Rigid Body
Engineering Mechanics  Chapter 5  Equilibrium of a Rigid BodyEngineering Mechanics  Chapter 5  Equilibrium of a Rigid Body
Engineering Mechanics Chapter 5 Equilibrium of a Rigid Body
 
Design of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxDesign of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptx
 
Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...
 
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
 
IT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptxIT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptx
 
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
 
solar wireless electric vechicle charging system
solar wireless electric vechicle charging systemsolar wireless electric vechicle charging system
solar wireless electric vechicle charging system
 
ASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entenderASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entender
 
Landsman converter for power factor improvement
Landsman converter for power factor improvementLandsman converter for power factor improvement
Landsman converter for power factor improvement
 
Summer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdf
Summer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdfSummer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdf
Summer training report on BUILDING CONSTRUCTION for DIPLOMA Students.pdf
 
Dev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingDev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & Logging
 
The relationship between iot and communication technology
The relationship between iot and communication technologyThe relationship between iot and communication technology
The relationship between iot and communication technology
 
Présentation IIRB 2024 Marine Cordonnier.pdf
Présentation IIRB 2024 Marine Cordonnier.pdfPrésentation IIRB 2024 Marine Cordonnier.pdf
Présentation IIRB 2024 Marine Cordonnier.pdf
 
Présentation IIRB 2024 Chloe Dufrane.pdf
Présentation IIRB 2024 Chloe Dufrane.pdfPrésentation IIRB 2024 Chloe Dufrane.pdf
Présentation IIRB 2024 Chloe Dufrane.pdf
 
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratoryدليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
دليل تجارب الاسفلت المختبرية - Asphalt Experiments Guide Laboratory
 
cloud computing notes for anna university syllabus
cloud computing notes for anna university syllabuscloud computing notes for anna university syllabus
cloud computing notes for anna university syllabus
 

A Parallel Computing-a Paradigm to achieve High Performance

  • 1. International Journal of Innovative Research in Advanced Engineering (IJIRAE) Volume 1 Issue 2 (April 2014) _______________________________________________________________________________________________ ISSN: 2278-2311 IJIRAE | http://ijirae.com © 2014, IJIRAE - All Rights Reserved Page - 62 A Parallel Computing-a Paradigm to achieve High Performance Prof.Ashwini M. Bhugul Asst. prof. MMCOE, Pune ashu_b53@rediffmail.com Abstract-Over last few years there has been rapid changes found in computing field.today, we are using the latest upgrade system which provides the faster output and high performance. User view towards computing is only to get the correct and fast result. There are many techniques which improves the system performance. Today’s widely use computing method is parallel computing. Parallel computing, including foundational and theoretical aspects, systems, languages, architectures, tools, and applications. It will address all classes of parallel- processing platforms including concurrent, multithreaded, multicore, accelerated, multiprocessor, clusters, and supercomputers. This paper reviews the overview of parallel processing to show how parallel computing can improve the system performance. 1. INTRODUCTION Parallel computer architecture provides a proportional increase in performance with increase in performance with increasing system resources. System resources are scaled by the number of processors used, memory capacity enlarged, access latency tolerated, I/O bandwidth required, etc.parallel architecture has a higher potential to deliver scalable performance Parallelism appears in various forms such as look ahead, pipelining, vectorization, concurrency, data parallelism, etc. Parallel computers are those that execute programs in MIMD code. There are two classes, namely-shared- memory multiprocessors and message passing multicomputers.In parallel computing a large task is divided into subtask and all the sub tasks will execute in parallel. This will help to reduce the waiting or stalled stages in pipeline of the computer system. Lower the number of clock cycles required higher performance will be achieve by the system. The degree of parallelism depends upon the parallel computer architecture. A parallel computer (or multiple processor system) is a collection of communicating processing elements (processors) that cooperate to solve large computational problems fast by dividing such problems into parallel tasks. There are some classification made for parallel computing, one of is Flynn’s classification. Flynn’s classification is based on multiplicity of instruction streams and data streams in computer system. Its machine organization includes SISD (single instruction single data), SIMD (single instruction multiple data), MISD (multiple instruction single data), and MIMD (multiple instruction multiple data). Some Broad issues involved: 1. The concurrency and communication characteristics of parallel algorithms for a given computational problem. 2. What portions of the computation and data are allocated or mapped to each PE. 3. How the processing elements cooperate and communicate. 3. How data is shared/transmitted between processors. 4. Abstractions and primitives for cooperation/communication and synchronization. Parallel computing improves the system performance, as the complete task is divided into stages, which will take less time to execute the stream of data. Both data and instructions are fetched by memory module. Instructions are decoded by the control unit, which sends to processor units for execution. Each instruction stream is generated by an independent control unit. Multiple data stream originates from shared memory module. This improves the system speedup and performance. 1.1General overview of parallel processing system:
  • 2. International Journal of Innovative Research in Advanced Engineering (IJIRAE) Volume 1 Issue 2 (April 2014) _______________________________________________________________________________________________ ISSN: 2278-2311 IJIRAE | http://ijirae.com © 2014, IJIRAE - All Rights Reserved Page - 63 CU-control unit PU-processing unit MEM-memory Figure 1.1: SIMD architecture showing parallel computing 1.2 Need of Parallel Computing Whenever there is need to work on large amount of data, system need a fast performance, more computing cycles/memory needed, there will be overload on machine when it performs a whole task, parallel computing make this task efficient by dividing a task into stages that will reduce the computing clock cycles and memory too. Some of the applications of parallel computing are: Scientific/Engineering computing: CFD, Biology, Chemistry, Physics, General-purpose computing: Video, Graphics, CAD, Databases, Transaction Processing, Gaming, etc. Number of transistors on chip growing rapidly. Clock rates expected to continue to go up but only slowly. Actual performance returns diminishing due to deeper pipelines. Increased transistor density allows integrating multiple processor cores per creating Chip-Multiprocessors (CMPs) even for mainstream computing applications that is also one of application of parallel processing The increased utilization of commodity of-the-shelf (COTS) components in high performance parallel computing systems instead of costly custom components used in traditional Super computers leading to much lower parallel system cost. Today’s microprocessors offer high- performance and have multiprocessor support with parallel processing. II. DIFFERENT GRANULARITIES OF PARALLELISM In parallel computing units of work can be execute concurrently if sufficient recourses exists. There are two granularities: 2.1 Thread level parallelism 2.2Instruction level parallelism 2.1Thread level parallelism (TLP) A thread is separate process having its own instructions and data. Thread may be a separate process or single program executing in parallel. In parallel computing, the thread offers different instructions and data so that the processor can switch to another thread and can continue the instructions, this will include the thing that, processor will continuously execute instructions without stalls, this will take less time to execute instructions.TLP is a software that enables a program often a high end programs such as web application, etc. There are two approaches to TLP: 1. Fine-grained multithreading 2. Coarse-grained multithreading Fine grained multithreading switches threads on each instruction, that will execute multiple instructions simultaneously, CPU must be able to switch threads every clock cycles. The advantage of using this technique is that it can hide both short and long stalls. Coarse-grained multithreading switches threads only when current thread is likely to stall for some time.it is more natural for any given thread and consume less time to switch threads. It is also easier to implement switching process. CU PU1 PU2 PUn MEM1 MEM2 MEMn
  • 3. International Journal of Innovative Research in Advanced Engineering (IJIRAE) Volume 1 Issue 2 (April 2014) _______________________________________________________________________________________________ ISSN: 2278-2311 IJIRAE | http://ijirae.com © 2014, IJIRAE - All Rights Reserved Page - 64 2.2 Instruction Level Parallelism Instruction-level Parallelism CILP) is a family of processor and compiler design techniques that speed up execution by causing individual machine operations to execute in parallel. Pipelining can overlap the execution of instructions when they are independent on each other, this potential overlap among instructions is called as Instruction level Parallelism. Processing instructions in parallel requires some tasks: 1. Checking independencies between instructions, if two instructions are independent on each other, they can be group together to execute in parallel. 2. Assigning instructions to the functional units on hardware. 3. Determining when instructions are initiated. This include the technique called score boarding, it allows instructions to execute out of order when there is sufficient resource available. ILP architectures can be classified as follows.  Sequential architectures: architectures for which the program is not expected to convey any explicit information regarding parallelism. Superscalar processors are representative of ILP processor implementations for sequential architectures.  Dependence architectures: This architecture provides information of those programs in which instructions which are dependent on each other. Dataflow processors are one of the examples of this architecture.  Independence architectures: architectures for which the program provides information as to which operations are independent of one another. Very Long Instruction Word (VLIW) processors are examples of the class of independence architectures. III. SOME PARALLEL PROGRAMMING TECHNIQUES Sometimes in large scale industries, there is a multiprocessor system, which requires number of instructions to be executed simultaneously, as the system consists of number of processor connected together there may happens some memory conflicts while performing tasks parallel. Processor needs to communicate with each or want to share some data with each other; hence there are some parallel programming techniques, three of them are explained below: 3.1. Message passing parallel programming In massage passing programming programs view their programs as a collection of cooperating processes with private variables. This style is suitable for message passing parallel computers. This technique needs only two primitives that is send and receive, that will send or receive instructions from one processor to another. Figure given below showing Message-Passing example of Intel Paragon. Figure 31: Sandia’s Intel Paragon XP/S-based Supercomputer There are most widely used Message Passing Programming tools are: 1. Message Passing Interface (MPI): It provides a standard for writing concurrent message-passing programs.MPI offers rich set of functions for doing point to point communicaton.it will divide a task into stages and that separate tasks can communicate with each other.MPI implementations include parallel libraries used by existing programming languages (C, C++). 2. Parallel Virtual Machine (PVM):
  • 4. International Journal of Innovative Research in Advanced Engineering (IJIRAE) Volume 1 Issue 2 (April 2014) _______________________________________________________________________________________________ ISSN: 2278-2311 IJIRAE | http://ijirae.com © 2014, IJIRAE - All Rights Reserved Page - 65 PVM is portable message passing programming system, designed to form separate host machines to from “virtual machine”. Virtual machine is collection of processors that may work simultaneously or at different time. It enables a collection of heterogeneous computers to use as a coherent and flexible concurrent computational resource. PVM support software executes on each machine in a user configurable pool, and provides computational environment of concurrent applications. User programs written for example in C, FORTRAN or Java are provided access to PVM through the use of calls to PVM library routines. 3.2. Shared Memory Programming In shared memory programming, programmers view their programs as a collection of cooperating processes that will access a common pool of shared variables. In such computers, processors may not have private program or data memory. a common data or program is stored in shared memory that will use by all processors. The main program creates separate processes and assigns a tasks to every processor with a common shared memory, each processor computes independently and after all, result of each processor stored in common memory. Two statements are use for this purpose: 1. Fork 2. Join Example: Process X; Process Y; fork y; join y; end y; Process X when it encounters fork y invokes another process y, after invoking y, it continues doing its work. Process y starts executing concurrently in another processor. When X reaches join y statement has to wait till y finish its work. In shared memory programming when multiple processors are in use and sharing a common memory so care has to be taken that no two dependent instructions should execute simultaneously. For shared memory programming three models of multiprocessors are: 1. The Uniform Memory Access (UMA) Model: In this model all physical memory is shared by all processors. All processors have equal access to all memory addresses. 2. Distributed memory or Non-uniform Memory Access (NUMA) Model: In this model, Shared memory is physically distributed locally among processors. Access latency to remote memory is higher. 3. The Cache-Only Memory Architecture (COMA) Model: In this model, A special case of a NUMA machine where all distributed main memory is converted to caches. No memory hierarchy at each processor. 3.3 Data parallel Programming In Data Parallel Programming many programs can apply same operation to each element of composite data.sometimes, looping statements performed repetitive tasks, using data parallelism this repetition carried out automatically by having multiprocessors working concurrently. Logically, single thread of control, performs sequential or parallel steps conceptually, a processor is associated with each data element. Figure 3.3: Data parallel system (All PE’s are synchronized) Control Processor PE PE PE PE PE PE PE PE PE
  • 5. International Journal of Innovative Research in Advanced Engineering (IJIRAE) Volume 1 Issue 2 (April 2014) _______________________________________________________________________________________________ ISSN: 2278-2311 IJIRAE | http://ijirae.com © 2014, IJIRAE - All Rights Reserved Page - 66 Example machines, Thinking Machines CM-1, Maspar MP-1 and MP-2, etc.Data parallel programming makes programs easy to read and write. Same program will be executed over different data sets simultaneously on multiple processors. a popular data parallel programming language is high performance Fortran (HPF). figure 3.3 given below shows example of data parallel systems. Array of many simple processors each with little memory. Processors don’t sequence through instructions. Attached to a control processor that issues instructions Specialized and general communication, global synchronization IV.CONCLUSION At the end of this review paper, we may observe some current some current trends. High performance computers are increasingly in demand, Parallel computing architecture is today’s widley used architecture which provides speed and high performance. It is used in many scientific, engineering, medical, military and research areas to achieve high system performance. V.REFERENCES 1. Rafiqul Zaman Khan, Md Firoj A Comparative Study on Parallel Programming Tools in Parallel Distributed Computing System: MPI and PVM, Department of Computer Science, Aligarh Muslim University, Aligarh- 202002,(U.P), India. 2 Ramakrishna Rau, Joseph A. Fisher, Instruction-Level Parallel Processing: History, Overview and Perspective, Computer Systems Laboratory,HPL-92-132,October, 1992. 3. M. D. Smith, M. Horowitz and M. Lam. Efficient superscalar performance through boosting. Proc. Fifth International Conference on Architectural Support for Programming& Laneua&es and Operating Systems (Boston, Massachussetts, October 1992), 248-259. 4. R. Chaiken, B. Jenkins, P.-_A. Larson,B. Ramsey, D. Shakib, S. Weaver, and J. Zhou. SCOPE: Easy and e_cient parallel processing of massive data sets. International Conference of Very Large Data Bases (VLDB), August 2008. 5. D. DeWitt and J. Gray. Parallel database systems: The future of high performance database processing. Communications of the ACM, 36(6), 1992. 6. R. Pike, S. Dorward, R. Griesemer, and S. Quinlan. Interpreting the data: Parallel analysis with Sawzall. Scienti_c Programming,13(4):277{298, 2005. 7. F. Rabhi and S. Gorlatch. Patterns and Skeletons for Parallel and Distributed Computing. Springer, 2003. 8. Y. Yu, M. Isard, D. Fetterly, M. Budiu,U. Erlingsson, P. K. Gunda, and J. Currey.DryadLINQ: A system for general-purpose distributed data-parallel computing using a high-level language. In Proceedings of the 8th Symposium on Operating Systems Design and Implementation (OSDI), December 8-10 2008. 9. R. Z. Khan, A. Q. Ansari and Kalim Qureshi―Performance Prediction for Parallel Scientific Applicationǁ, Malaysian Journal of Computer Science,Vol. 17 No. 1, June 2004, pp 65-73. 10. Kai Hwang, Faye A. Briggs, "Computer Architecture and Parallel Processing" McGraw-Hill international Edition 11. Kai Hwang, "Advanced Computer Architecture", Tata McGraw-Hill 12. V.Rajaraman, L Sivaram Murthy, "Parallel Computers", PHI.