You create an OpenMP application by using Microsoft Visual C++. You are debugging your application. The OpenMP parallel region contains a breakpoint. When the breakpoint is reached, the Threads window displays multiple threads that are running. You need to identify the point of execution of all threads in the OpenMP parallel region. What should you do?

You create an OpenMP application by using Microsoft Visual C++. You are debugging the application. You set a breakpoint to the first line of code inside an OpenMP parallel region.
The first thread execution inside the OpenMP parallel region must be debugged. You need to ensure that you debug the first thread in isolation when you step through the code.
What should you do?

You create an OpenMP application by using Microsoft Visual C++. The application includes an OpenMP parallel region. The region contains the following code segment.
(Line numbers are included for reference only.)

01 int global=0;
03 void PerformComputation(int value)
04 {
05 //…
07 global+=value;
08 }
10 int _tmain(int argc, _TCHAR* argv[])
11 {
12 #pragma omp parallel for
13 for(int count=0;count<100;count++)
14 {
15 //…
16 PerformComputation(count);
17 //…
18 }
19 }

For each iteration that updates the global variable, the for loop must call the PerformComputation method.
You need to ensure that shared memory access to the global variable is protected.
Which line of code should you insert at line 06?

You develop an application that reads data from a file, performs calculations on the data, and writes the result to another file. The read and write operations are atomic and are not parallelized.You divide the calculation tasks across a set of threads by using the following do construct. (Line numbers are included for reference only.)

01 #pragma omp parallel shared(in, out, len)
02 {
03 read_array(in, len);
05 #pragma omp for private(j)
06 for(j=1; j<len; j++)
07 compute_result(out(j),in,len);
08 write_array(out, len);
09 }

You need to ensure that the read and write tasks are performed by a single thread. Which two actions should you perform? (Each correct answer presents part of the solution.
Choose two.)

You are an application developer for your company. Users report that the performance of an application installed on your company s net wor k i s sl ow You use a profiler to identify the problem. You discover that in a parallel loop, one type of task takes only a few seconds to complete, whereas another type of task takes a few minutes to complete. You also discover that the tasks do not modify input data. The parallel loop is shown in the following code segment. (Line numbers are included for reference only.)

01 #pragma omp parallel shared(x) private(i, res)
03 {
04 #pragma omp for
05 for (i=0; i < N; i++)
06 {
07 res = f(i);
08 if (res < 7)
09 smallwork(x[i]);
10 else
11 bigwork(x[i]);
12 }
13 }

You need to ensure that the workload is balanced among the processors that run the application, regardless of the OpenMP API default settings. Which line of code should you use to replace the code at line 04?