SlideShare a Scribd company logo
Multi processing
Multiple Processor Organization






Single instruction, single data stream - SISD
Single instruction, multiple data stream - SIMD
Multiple instruction, single data stream - MISD
Multiple instruction, multiple data stream- MIMD
Single Instruction, Single Data
Stream - SISD





Single processor
Single instruction stream
Data stored in single memory
Uni-processor
Single Instruction, Multiple Data
Stream - SIMD








Single machine instruction
Controls simultaneous execution
Number of processing elements
Lockstep basis
Each processing element has associated data
memory
Each instruction executed on different set of
data by different processors
Vector and array processors
Multiple Instruction, Single Data
Stream - MISD





Sequence of data
Transmitted to set of processors
Each processor executes different instruction
sequence
Never been implemented
Multiple Instruction, Multiple
Data Stream- MIMD





Set of processors
Simultaneously execute different instruction
sequences
Different sets of data
SMPs, clusters and NUMA systems
Taxonomy of Parallel Processor
Architectures
Parallel Organizations - SISD
Parallel Organizations - SIMD
Parallel Organizations - MIMD
Shared Memory
Parallel Organizations - MIMD
Distributed Memory
Symmetric Multiprocessors


A stand alone computer with the following characteristics
 Two or more similar processors of comparable capacity
 Processors share same memory and I/O
 Processors are connected by a bus or other internal connection
 Memory access time is approximately the same for each processor
Continue……
 All processors share access to I/O
○ Either through same channels or different channels giving

paths to same devices
 All processors can perform the same functions (hence

symmetric)
 System controlled by integrated operating system
○ providing interaction between processors
○ Interaction at job, task, file and data element levels
Block Diagram of Tightly Coupled
Multiprocessor
SMP Advantages


Performance
If some work can be done in parallel, then

system with multiple processors yield
greater performance than single processor
of the same type.


Availability
Since all processors can perform the same

functions, failure of a single processor does
not halt the system
SMP Advantages


Incremental growth
User can enhance performance by adding

additional processors


Scaling
Vendors can offer range of products with

different price and performance which are
based on number of processors configured in
the system
Multiprogramming and
Multiprocessing
Organization Classification




Time shared or common bus
Multiport memory
Central control unit
Time Shared Bus




Simplest form
Structure and interface similar to single
processor system
Following features provided
Addressing - distinguish modules on bus
Arbitration - any module can be temporary

master
Time sharing - if one module has the bus, others
must wait and may have to suspend


Now have multiple processors as well as
multiple I/O modules
Symmetric Multiprocessor
Organization
Time Share Bus - Advantages




Simplicity
Flexibility
Reliability
Time Share Bus - Disadvantage



Performance limited by bus cycle time
Each processor should have local cache
Reduce number of bus accesses



Leads to problems with cache coherence
Solved in hardware - see later

More Related Content

PPTX
Computer architecture multi processor
PPTX
Multiprocessor Architecture (Advanced computer architecture)
PPTX
Multiprocessor
PPTX
Multiprocessor system
PPTX
System interconnect architecture
PPT
Parallel processing
PPTX
file sharing semantics by Umar Danjuma Maiwada
DOCX
Parallel computing persentation
Computer architecture multi processor
Multiprocessor Architecture (Advanced computer architecture)
Multiprocessor
Multiprocessor system
System interconnect architecture
Parallel processing
file sharing semantics by Umar Danjuma Maiwada
Parallel computing persentation

What's hot (20)

PPT
program flow mechanisms, advanced computer architecture
PPT
Distributed File Systems
PDF
Bus structure in Computer Organization.pdf
PPTX
Kernel. Operating System
PPT
Sequential consistency model
PDF
Unit 5 Advanced Computer Architecture
PPTX
Storage Structure in OS
PPTX
ADVANCED COMPUTER ARCHITECTURE AND PARALLEL PROCESSING
PPT
Multiprocessor Systems
PDF
Introduction to distributed file systems
PDF
Distributed Operating System_1
PPTX
Google File System
PPT
Clock synchronization in distributed system
PPTX
Presentation on Shared Memory Parallel Programming
PPTX
DMA and DMA controller
PPT
Chapter 14 replication
PPTX
OS multiprocessing -.pptx
PPT
parallel programming models
PDF
Parallel programming model, language and compiler in ACA.
program flow mechanisms, advanced computer architecture
Distributed File Systems
Bus structure in Computer Organization.pdf
Kernel. Operating System
Sequential consistency model
Unit 5 Advanced Computer Architecture
Storage Structure in OS
ADVANCED COMPUTER ARCHITECTURE AND PARALLEL PROCESSING
Multiprocessor Systems
Introduction to distributed file systems
Distributed Operating System_1
Google File System
Clock synchronization in distributed system
Presentation on Shared Memory Parallel Programming
DMA and DMA controller
Chapter 14 replication
OS multiprocessing -.pptx
parallel programming models
Parallel programming model, language and compiler in ACA.
Ad

Viewers also liked (20)

PPTX
Multiple processor (ppt 2010)
PDF
13. multiprocessing
PPTX
Multiprocessor architecture
PDF
Multiple processor systems
PPTX
Multiprocessor architecture and programming
PDF
Computer organiztion1
PPT
Distributed Systems
DOCX
Symmetric Multi Processor Multiprocessors
PPTX
Lecture 5 process concept
PPTX
Symmetric multiprocessing
PPTX
Desktop system,clustered system,Handheld system
PDF
Mp Os Survey
PPTX
Multiprocessor structures
PPT
Computer Architecture: A quantitative approach - Cap4 - Section 1
PPT
Computer Architecture: A quantitative approach - Cap4 - Section 3
PPT
Computer Architecture: A quantitative approach - Cap4 - Section 8
PPT
Computer Architecture: A quantitative approach - Cap4 - Section 6
PPT
Computer Architecture: A quantitative approach - Cap4 - Section 5
PPT
Chapter 2: Microprocessors
PPT
Real time operating system
Multiple processor (ppt 2010)
13. multiprocessing
Multiprocessor architecture
Multiple processor systems
Multiprocessor architecture and programming
Computer organiztion1
Distributed Systems
Symmetric Multi Processor Multiprocessors
Lecture 5 process concept
Symmetric multiprocessing
Desktop system,clustered system,Handheld system
Mp Os Survey
Multiprocessor structures
Computer Architecture: A quantitative approach - Cap4 - Section 1
Computer Architecture: A quantitative approach - Cap4 - Section 3
Computer Architecture: A quantitative approach - Cap4 - Section 8
Computer Architecture: A quantitative approach - Cap4 - Section 6
Computer Architecture: A quantitative approach - Cap4 - Section 5
Chapter 2: Microprocessors
Real time operating system
Ad

Similar to Multi processing (20)

PPTX
Parallel Processing
PPT
Parallel processing Concepts
PPT
Parallel processing extra
PPT
chapter-18-parallel-processing-multiprocessing (1).ppt
PPT
parallel processing.ppt
PDF
M7_L3_PPT.computer organization and archit
PPT
parallel-processing.ppt
PPT
18 parallel processing
PDF
Advanced processor Principles
PPTX
PPT
Parallel Computing
PPT
Multiprocessors Characters coherence.ppt
PPT
Parallel processing
PDF
Parallel Processing
PDF
M7_L1_PPT.computer organization and archi
PPT
System architecture
DOC
Symmetric multiprocessing and Microkernel
PPTX
Computer organisation and architecture unit 5, SRM
PPTX
OS UNIT1.pptx
PPTX
Week 13-14 Parrallel Processing-new.pptx
Parallel Processing
Parallel processing Concepts
Parallel processing extra
chapter-18-parallel-processing-multiprocessing (1).ppt
parallel processing.ppt
M7_L3_PPT.computer organization and archit
parallel-processing.ppt
18 parallel processing
Advanced processor Principles
Parallel Computing
Multiprocessors Characters coherence.ppt
Parallel processing
Parallel Processing
M7_L1_PPT.computer organization and archi
System architecture
Symmetric multiprocessing and Microkernel
Computer organisation and architecture unit 5, SRM
OS UNIT1.pptx
Week 13-14 Parrallel Processing-new.pptx

More from Muhammad Ishaq (20)

PPT
Causality in special relativity
PPT
Business proposal
PPT
Artificial neural network model & hidden layers in multilayer artificial neur...
PPTX
Artificial Neural Network
PPTX
Writting process
PPTX
Business
PPTX
PPTX
Brochures
PPTX
Dependencies
PPTX
Input output
PPTX
Multi core processor
PPTX
Dram and its types
PPTX
Micro operation control of processor
PPTX
Computer architecture overview
PPTX
Raid 1 3
PPT
Cache memory
PPT
Cache memory
PPTX
Addressing
PPTX
Clusters
PPTX
Raid level 4
Causality in special relativity
Business proposal
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial Neural Network
Writting process
Business
Brochures
Dependencies
Input output
Multi core processor
Dram and its types
Micro operation control of processor
Computer architecture overview
Raid 1 3
Cache memory
Cache memory
Addressing
Clusters
Raid level 4

Multi processing

  • 2. Multiple Processor Organization     Single instruction, single data stream - SISD Single instruction, multiple data stream - SIMD Multiple instruction, single data stream - MISD Multiple instruction, multiple data stream- MIMD
  • 3. Single Instruction, Single Data Stream - SISD     Single processor Single instruction stream Data stored in single memory Uni-processor
  • 4. Single Instruction, Multiple Data Stream - SIMD        Single machine instruction Controls simultaneous execution Number of processing elements Lockstep basis Each processing element has associated data memory Each instruction executed on different set of data by different processors Vector and array processors
  • 5. Multiple Instruction, Single Data Stream - MISD     Sequence of data Transmitted to set of processors Each processor executes different instruction sequence Never been implemented
  • 6. Multiple Instruction, Multiple Data Stream- MIMD     Set of processors Simultaneously execute different instruction sequences Different sets of data SMPs, clusters and NUMA systems
  • 7. Taxonomy of Parallel Processor Architectures
  • 10. Parallel Organizations - MIMD Shared Memory
  • 11. Parallel Organizations - MIMD Distributed Memory
  • 12. Symmetric Multiprocessors  A stand alone computer with the following characteristics  Two or more similar processors of comparable capacity  Processors share same memory and I/O  Processors are connected by a bus or other internal connection  Memory access time is approximately the same for each processor
  • 13. Continue……  All processors share access to I/O ○ Either through same channels or different channels giving paths to same devices  All processors can perform the same functions (hence symmetric)  System controlled by integrated operating system ○ providing interaction between processors ○ Interaction at job, task, file and data element levels
  • 14. Block Diagram of Tightly Coupled Multiprocessor
  • 15. SMP Advantages  Performance If some work can be done in parallel, then system with multiple processors yield greater performance than single processor of the same type.  Availability Since all processors can perform the same functions, failure of a single processor does not halt the system
  • 16. SMP Advantages  Incremental growth User can enhance performance by adding additional processors  Scaling Vendors can offer range of products with different price and performance which are based on number of processors configured in the system
  • 18. Organization Classification    Time shared or common bus Multiport memory Central control unit
  • 19. Time Shared Bus    Simplest form Structure and interface similar to single processor system Following features provided Addressing - distinguish modules on bus Arbitration - any module can be temporary master Time sharing - if one module has the bus, others must wait and may have to suspend  Now have multiple processors as well as multiple I/O modules
  • 21. Time Share Bus - Advantages    Simplicity Flexibility Reliability
  • 22. Time Share Bus - Disadvantage   Performance limited by bus cycle time Each processor should have local cache Reduce number of bus accesses  Leads to problems with cache coherence Solved in hardware - see later