Problems Chapter 17 Parallel Processsing: 17.14 An Application Program Is Executed On A Nine-Computer Cluster. A
Problems Chapter 17 Parallel Processsing: 17.14 An Application Program Is Executed On A Nine-Computer Cluster. A
NIM : 205150207111061
Answer :
a. Given values,
n =9
α = 25%
= 0,25
Effective speedup can be calculated using the formula [nα – α + 1]
Substitute the above values in Equation (3),
[nα – α + 1] = [9 x 0,25 – 0.25 + 1]
= [2 + 1]
` =3
Therefore, the effective speedup value of 3.
The amount of code that has been parallelized is “α = 0.25” with 9 processors. So,
totally it is “2.25”.
So, the percentage is calculated as follows:
Percentage of code has been parallelized
Therefore, the percentage of code that has been parallelized is 75%.
Answer :
If only the L1 cache is used, then 89% of the accesses are to L1 and the remaining
11% of the accesses are to main memory. Therefore, the average penalty is
(1 × 0.89) + (32 × 0.11) = 4.41.
If both L1 and L2 are present, the average penalty is
(1 × 0.89) + (5 × 0.05) + (32 × 0.06) = 3.06. This normalizes to 3.06/4.41 = 0.69.
Thus, with the addition of the L2 cache, the average penalty is reduced to 69% of
that with only one cache.
If all three caches are present, the average penalty is
(1 × 0.89) + (5 × 0.05) + (14 × 0.03) + (32 × 0.03) = 2.52, and normalized average
penalty is 2.52/4.41 = 0.57.
The reduction of the average penalty from 0.69 to 0.57 would seem to justify the
inclusion of the L3 cache.
2. Review Questions Chapter 18 Multicore Computers
18.2 Give several reasons for the choice by designers to move to a multicore
organization rather than increase parallelism within a single processor.
Answer :
Reasons to move to multicore organization:
Reasons to move to multicore organisation rather than increase parallelism within single
processor are
Managing multiple threads with pipeline limits threads and pipelines used
effectively.
4. To avoid things with respect to the above points we move to multicore organisation
Answer :