1. What opportunities for parallelism do you see? What problems or challenges do you see limiting performance? How could the problems be overcome? Measure the time it takes to execute different parts of the serial program. If a part of a program has a very short execution time, how can you still measure the time relatively accurately?

2. Use your measurements to estimate the performance of your parallel approach. How efficient do you expect your code to be? Why? How many times faster than the sequential version do you expect your code to run on N processors? N being the number of processors available to you. In other words, what speedup do you expect?

3. Can you enforesee any overheads that can make your estimations inaccurate? What could these overheads be, if any?

#include #include 5 #include 6 #include 7 8 #define SIZE 10000000 9 10 volatile float a[SIZE]; 11 volatile float b[SIZE]; 12 13 int main(int argc, char **argv) 14 B{ 15 long int i; 16 double sum; 17 struct timeval time1, time2; 18 19 srand(time()); 20 21 for (i = 0; i