Lecture_8.pdf

Hi iam zuhaib alam. And this is my presentation topic , today i share this with you.. download this nd enjoy... Thanks

1. CSC334 Parallel & Distributed Computing
Lecture # 08
Feng’s Classification
By, Zia Ur Rehman
Department of Computer Science GDC Chitral (University of Peshawar)

2. Feng’s Classification
•Tse-yun Feng in 1972 suggested the use of degree of parallelism to classify various
computer architectures.
•It is based on serial Versus Parallel processing.
•The maximum number of binary digits that can be processed within a unit time by a
computer system is called the maximum parallelism degree P.
•In Feg’s classification parallelism is exhibited (presented) by word length(n) and a bit-slice
length (m).
➢A bit slice is a string of bits one from each of the words at the same vertical position.
➢World length is the number of bits in a word.

3. Feng’s Computer Systems Classification:
•Word Serial and Bit Serial (WSBS)
•Word Parallel and Bit Serial (WPBS)
•Word Serial and Bit Parallel(WSBP)
•Word Parallel and Bit Parallel (WPBP)

4. Continue…
➢ WSBS has been called bit parallel processing because one bit of a selected
word is processed at a time. This corresponds to serial processing and hence
requires maximum processing time.
➢WSBP is found in most existing computers and has been called as Word
Slice processing because all the bits of a selected word are processed
simultaneously, but one word at a time. Hence bit parallel indicates the
selection of all the bits of a word. Hence it is slightly parallel processing.

5. Continue…
➢ WPBS has been called bit slice processing because one selected bit from
all the specified words (m-bit slice) is processed at a time. Hence word
parallel indicates the selection of multiple words. WSBP can be said to be
row parallelism while WPBS can be said as column parallelism.
➢WPBP is known as fully parallel processing in which an array on n x m bits
is processes at one time. all the bits of all the specified words are operated
on simultaneously. Hence this gives the maximum parallelism thereby
minimum time for execution.

6. Example
N=Word Length
M=Bit-Slice Length

7. That’s all for today!!