Array processing, Computer Engineering

Array Processing

We have seen that for performing vector operations, the pipelining concept has been taken. There is another method for vector operations. If we have an array of n processing elements (PEs) i.e., multiple ALUs for storing many operands of the vector, then an n instruction, for example, vector addition, is broadcast to all PEs such that they add all                                            

Operands of the vector at the similar time. It means all PEs will present computation in parallel. All PEs are synchronized under one control unit. This organization of synchronous array of PEs for vector operations is known as Array Processor. The organization is similar as in SIMD which we studied in unit 2. An array processor can handle single instruction multiple data streams as we have seen earlier in case of SIMD organization. Thus, array processors are also known as SIMD array computers.

The organization of an array processor is given in Figure. The following components are organized in an array processor:

                                     47_Array Processing.png

                                                              Organisation of SIMD Array Processor

Posted Date: 3/4/2013 5:20:05 AM | Location : United States







Related Discussions:- Array processing, Assignment Help, Ask Question on Array processing, Get Answer, Expert's Help, Array processing Discussions

Write discussion on Array processing
Your posts are moderated
Related Questions
Single Instruction and Multiple Data stream (SIMD) In this organisation, multiple processing elements are working under the control of a one control unit. It has multiple data

Structural Classification Flynn's classification examine the behavioural concept and does not receive into consideration the computer's structure. Parallel computers can be cla

Q. Illustrate working of T Flip-Flop? T (Toggle) flip-flop is attained from JK flip-flop by combining inputs J and K together. The implementation of T flip-flop is displayed in

Define miss penalty? The extra time required to bring the desired information into the cache is known as miss penalty.

An operating system contains 3 resource classes. The number of resource units in these classes is 7, 7 and 10. The current resource allocation state is shown below:

Your logic function for this assignment is to be derived from your own student number. The number 1224583 will be used as an example as to how you should derive your function and e

Final Implementation of Object oriented modelling Final Implementation: At this phase, the final execution of classes and  relationships developed while object design takes

The logic 0 level of a CMOS logic device is approximately ? Ans. The low level is 0 volts approx in CMOS logic device.

Give the regular expression of the set of all even strings over the alphabet {a, b} along with at least one of the two substrings aa or bb. As well construct the finite automata wh

Explain Language Processor Development Tools (LPDTs) through schematic diagram. LPDT that is Language processor development tools focuses upon generation of the analysis phase