Exercise 5: Matrix multiplication

• Review / Compile / Run the matrix multiply example code mm.c
• Use the function omp_get_wtime() compare the performance of each version of the pi code and find out the most efficient algorithm.
  
• Analyze the speedup and efficiency of the parallelized code.
  
• Vary the size of your matrices from 250, 500, 750, 1000, and 2000 and measure the runtime with one thread.
  
• For each matrix size, change the number of threads from 2 to 8, and plot the speedup versus the number of threads.
  
• Compute the efficiency.Explain whether or not the scaling behavior is as expected.

____________________________________________________________