DESCRIPTION

Students:  Please note instructions in paper copy of quiz.  Save your
files often, make sure OMSI fills your entire screen at all times, etc.

A question may not fully fit into your OMSI question box, which is not
scrollable.  You can try adjusting the relative size of the question and
answer boxes, but remember that clicking CopyQtoA will copy the entire
question box to the answer box.

QUESTION

Consider the Mandelbrot code, pp.89ff.  Instead of watching whether z
stays in the disk of radius 2, centered at 0+0i, say we wish to use a
square centered there with each side of length 4, and with sides
parallel to the horizontal and vertical axes.  State what changes would
need to be made to the code.

QUESTION

Consider the scenario at the top of p.71 ("If we are unlucky...").
Which of the following scenarios is possible?  Assume that all threads
will be going through the code leading up to the barrier.  (Thread 12
will mean the thread currently running on processor 12, etc.)

(i) Thread 12 fails to go past the barrier, but the others do.

(ii) Thread 3 fails to go past the barrier, but the others do.

(iii) Both threads 3 and 12 fail to go past the barrier, but the others do.

(iv) All of the above are impossible.  Definitely no thread will go past
the barrier.

QUESTION 

In the code on p.100, consider the possibility of deleting one or both
of lines 103 and 105.  We wish to delete as many lines as possible, with
the sole criterion being whether the program runs correctly, i.e. gives
correct results; if the deletion slows things down, that is not an
issue.  Answer either None, Delete 103 only, Delete 105 only or Delete
both.  EXPLAIN YOUR ANSWER.

QUESTION -ext .c -com gcc -flags '-fopenmp' -run ./omsi_answer4

Here you will write OpenMP code that extracts a submatrix subMat from a
matrix m.  The submatrix will consist of a group of consecutive columns
of m.

#include<omp.h>
#include<stdio.h>
#include<stdlib.h>
#include<string.h>

int onedim(int row, int col, int nCols) { return row * nCols + col; }

// nColsSubM consecutive columns of m will be extracted, starting with
// column firstCol
int *getCols(int *m, int nRowsM, int nColsM, int firstCol, int nColsSubM) {
   int *subMat;
   #pragma omp parallel
   {  int *startFrom,*startTo;
      subMat = malloc(nRowsM * nColsSubM * sizeof(int));
      for (int row = 0; row < nRowsM; row++) {
         startFrom =            ;
         startTo =            ;
         memcpy(           );
      }
   }
   return subMat;
}

int main() {
   // intended as a 4x3 matrix
   int z[12] = {5,12,13,6,2,22,15,3,1,2,3,4};
   omp_set_num_threads(2);
   // extract the last 2 cols
   int *outM = getCols(z,4,3,1,2);
   // check output
   for (int i = 0; i < 4; i++) {
      printf("%d %d\n",outM[2*i],outM[2*i+1]);
   }
}