The Gateway to Computer Science Excellence
0 votes

Consider a 5 stage pipeline with IF , ID, EX, WB and MA having latencies (in ms) 3,8,5,6,4. What is average CPI of non pipeline CPU when speed up achieved by to pipeline is 4?

I think answer is wrong 

For non pipe line total time =  Total number of instruction * (26) 

As they have directly given time , we don’t need to do “number of cycles * time for each cycle” calculation

For pipeline version total time = Total number of instruction * max(3,8,5,6,4)

So No role of CPI 


in CO and Architecture by Active (4.8k points)
edited by | 37 views
then how can you find the answer to the given question ?

thank you @Shaik Masthan for reply , 

I think the  question itself is wrong.

this question could be correct if they have given 5 stages of pipeline takes 3,8,5,6,4 cycles , with each cycle time of 1 ms.


it should be 26/8.

look at the next line  it is corrected (8*4)/26.

@mehul vaidya

i mean to say, your understanding on this question is wrong !

By default we assume, Clock cycle time = 1, when we use CPI

Please log in or register to answer this question.

No related questions found

Quick search syntax
tags tag:apple
author user:martin
title title:apple
content content:apple
exclude -tag:apple
force match +apple
views views:100
score score:10
answers answers:2
is accepted isaccepted:true
is closed isclosed:true
50,650 questions
56,242 answers
95,938 users