Digital Principles and Computer Organization: Chapter 10: Parallel Processing

Flynn's Classification

Questions: 1. Explain the Flynn's classification. 2. Discuss about SISD, MIMD, SIMD, SPMD and VECTOR systems. 3. Explain in detail Flynn's classification of parallel hardware. 4. Explain Flynn's classification of parallel processing with necessary diagrams. 5. Define the classes in Flynn's Taxonomy of computer architectures. Give one example for each class.

Flynn's Classification

• Parallel processing can be classified in many ways. It can be classified according to internal organization of processors, according to interconnection structure used between processors or according to flow of information through the system.

• One such classification is introduced by M. J. Flynn. We know that a typical processing unit operates by fetching instructions and operands from the main memory, executing the instructions, and placing the results in the main memory. The steps associated with the processing of an instruction form an instruction cycle. The instruction can be viewed as forming an instruction stream flowing from main memory to the processor, while the operands form another stream, the data stream, flowing to and from the processor, as shown in Fig. 10.4.1.


• In 1966, Micheal J. Flynn has made an informal and widely used classification of processor parallelism based on the number of simultaneous instruction and data streams seen by the processor during program execution.

 

• The classification made by Micheal J. Flynn divides computers into four major groups.

■ Single Instruction Stream–Single Data stream (SISD).

■ Single Instruction Stream–Multiple Data streams (SIMD).

■ Multiple Instruction Streams–Single Data stream (MISD).

■ Multiple Instruction Streams–Multiple Data streams (MIMD).

 

1. Single Instruction stream Single Data Stream (SISD) : Most conventional machines with one CPU containing a single arithmetic–logic unit capable only of scalar arithmetic fall into this category. SISD computers and sequential computers are thus synonymous. In SISD computers instructions are executed sequentially but may overlap in their execution stages (Pipelining). They may have more than one functional unit, but all functional units are control by a single control unit.


 

2. Single Instruction stream Multiple Data streams (SIMD) : This category corresponds to array processors. They have multiple processing/execution units and one control unit. Therefore, all processing/execution units are supervised by the single control unit. Here, all processing elements received same instruction from control unit but operate on different data sets from distinct data streams. This category is also known as single program, multiple data stream (SPMD).


 

3. Multiple Instruction streams Single Data stream (MISD) : Not many parallel processors fit well into this category. In MISD, there are n processor units. Each receiving distinct instructions operating over the same data stream and its derivatives. The results of one processor become the input of the next processor in the micropipe. The fault–tolerant computers where several processing units process the same data using different programs belongs to the MISD class. The results of such apparently redundant computations can be compared and used to detect and eliminate faulty results.


 

4. Multiple Instruction streams Multiple Data streams (MIMD) : Most multiprocessors system and multiple computers system can be classified in this category. In MIMD, there are more than one processor unit having the ability to execute several program simultaneously. MIMD computer implies interactions among the multiple processors because all memory streams are derived from the same data space shared by all processors. If the n data streams are derived from disjointed sub spaces of the shared memories then we would have the so–called Multiple SISD (MSISD) operation.


 

5. Vector systems : A more efficient interpretation of SIMD is called a vector architecture. Rather than having 64 ALUS perform 64 additions simultaneously, like the old array processors, the vector architectures pipelined the ALU to get good performance at lower cost.

• Vector architecture consists of a set of vector registers.

• Vector architectures collect data elements from memory, put them in order into a large set of registers, operate on them sequentially in registers and then write the results back to memory.

• Table 10.4.1 shows example of machines and their Flynn's classification.


 

Review Questions

1. Explain the Flynn's classification.

2. Discuss about SISD, MIMD, SIMD, SPMD and VECTOR systems.

3. Explain in detail Flynn's classification of parallel hardware.

4. Explain Flynn's classification of parallel processing with necessary diagrams.

5. Define the classes in Flynn's Taxonomy of computer architectures. Give one example for each class.

 

Digital Principles and Computer Organization: Chapter 10: Parallel Processing : Tag: : - Flynn's Classification


Digital Principles and Computer Organization: Chapter 10: Parallel Processing



Under Subject


Digital Principles and Computer Organization

CS25C06 2nd Semester AIDS, CSE, IT, CSE(CY) Dept | 2025 Regulation | 2nd Semester 2025 Regulation



Related Subjects


English Essentials II

EN25C02 2nd Semester | 2025 Regulation | 2nd Semester 2025 Regulation



Linear Algebra

MA25C02 2nd Semester | 2025 Regulation


Applied Physics (CSIE) II

PH25C03 2nd Semester AIDS, CSE, IT, CSE(CY) Dept | 2025 Regulation | 2nd Semester 2025 Regulation


Digital Principles and Computer Organization

CS25C06 2nd Semester AIDS, CSE, IT, CSE(CY) Dept | 2025 Regulation | 2nd Semester 2025 Regulation


Basic Electrical and Electronics Engineering

EE25C01 2nd Semester | 2025 Regulation | 2nd Semester 2025 Regulation


Python for Data Science

AD25201 2nd Semester AIDS Dept | 2025 Regulation | 2nd Semester 2025 Regulation


Re-Engineering for Innovation

ME25C05 2nd Semester | 2025 Regulation | 2nd Semester 2025 Regulation


Python for Data Science - Laboratory

AD25201 2nd Semester AIDS Dept | 2025 Regulation | 2nd Semester 2025 Regulation