To get experience parallelizing programs with OpenMP.
For this lab, you will parallelize a sequential program for finding the prime factorization of a number, factor.c
This program will need to be compiled with the "-lm" option because it uses the math functions ceil and sqrt.
You should insert OpenMP directives such that the behavior of the program is the same, but performance is improved. You should be able to get the large test case (6569152) to complete in less than one second when you're done.
If the prime factors are printed in a different order, that is OK. The set of prime factors must be the same, however!
Below is an example run of the serial program:
$ ./factor 2311260 2 2 3 5 7 5503 $ ./factor 6569152 2 2 2 2 2 2 102643
Note that there are much more optimal serial algorithms for this task, but you only need to parallelize the existing solution.
After completing the parallelized version, test your program with the following parameters:
Threads | Value | Time |
1 | 2311260 | |
8 | 2311260 | |
1 | 6569152 | |
8 | 6569152 |
When you're finished, submit both the source code and the analysis (in a text document or comment) to Canvas.
Copyright © 2024 Ian Finlayson | Licensed under a Creative Commons BY-NC-SA 4.0 License.