Difference between revisions of "OpenMP in Small Bites/Tasking and Data Scoping"
OpenMP in Small Bites/Tasking and Data Scoping
Jump to navigation
Jump to search
| Line 39: | Line 39: | ||
<code>#pragma omp parallel num_threads(4)</code><br/> | <code>#pragma omp parallel num_threads(4)</code><br/> | ||
<code>{</code><br/> | <code>{</code><br/> | ||
| − | <code> #pragma omp task</code>< | + | <div style="margin-left: 1em;"><code> #pragma omp task</code></div> |
| − | <code> {</code>< | + | <div style="margin-left: 1em;"><code> {</code></div> |
| − | <code> y += x;</code>< | + | <div style="margin-left: 2em;"><code> y += x;</code></div> |
| − | <code> }</code>< | + | <div style="margin-left: 1em;"><code> }</code></div> |
<code>}</code><br/> | <code>}</code><br/> | ||
<code>printf("y=%d\n", y);</code><br/> | <code>printf("y=%d\n", y);</code><br/> | ||
| Line 65: | Line 65: | ||
<code>#pragma omp parallel num_threads(4)</code><br/> | <code>#pragma omp parallel num_threads(4)</code><br/> | ||
<code>{</code><br/> | <code>{</code><br/> | ||
| − | <code> #pragma omp single</code>< | + | <div style="margin-left: 1em;"><code> #pragma omp single</code></div> |
| − | <code> {</code>< | + | <div style="margin-left: 1em;"><code> {</code></div> |
| − | <code> #pragma omp task</code>< | + | <div style="margin-left: 2em;"><code> #pragma omp task</code></div> |
| − | <code> {</code>< | + | <div style="margin-left: 2em;"><code> {</code></div> |
| − | <code> y += x;</code>< | + | <div style="margin-left: 3em;"><code> y += x;</code></div> |
| − | <code> }</code>< | + | <div style="margin-left: 2em;"><code> }</code></div> |
| − | <code> }</code>< | + | <div style="margin-left: 1em;"><code> }</code></div> |
<code>}</code><br/> | <code>}</code><br/> | ||
<code>printf("y=%d\n", y);</code><br/> | <code>printf("y=%d\n", y);</code><br/> | ||
Revision as of 18:05, 30 November 2020
| Tutorial | |
|---|---|
| Title: | OpenMP in Small Bites |
| Provider: | HPC.NRW
|
| Contact: | tutorials@hpc.nrw |
| Type: | Multi-part video |
| Topic Area: | Programming Paradigms |
| License: | CC-BY-SA |
| Syllabus
| |
| 1. Overview | |
| 2. Worksharing | |
| 3. Data Scoping | |
| 4. False Sharing | |
| 5. Tasking | |
| 6. Tasking and Data Scoping | |
| 7. Tasking and Synchronization | |
| 8. Loops and Tasks | |
| 9. Tasking Example: Sudoku Solver | |
| 10. Task Scheduling | |
| 11. Non-Uniform Memory Access | |
Video
Quiz
1. Consider the following code snippet
int x = 42;
#pragma omp parallel private(x)
{
#pragma omp task { x = 3; }}
printf("x=%d\n", x);
x and what is printed?
2. Consider the following code snippet
int x = 42;
int y = 0;
#pragma omp parallel num_threads(4)
{
#pragma omp task { y += x; }}
printf("y=%d\n", y);
x and what is printed?
3. Consider the following code snippet
int x = 42;
int y = 0;
#pragma omp parallel num_threads(4)
{
#pragma omp single { #pragma omp task { y += x; } }}
printf("y=%d\n", y);
x and what is printed?