GPU Tutorial/Open MP - Revision history

Marius-neumann-d848@uni-bielefeld.de at 15:22, 21 January 2022

2022-01-21T15:22:34Z

Xin-wu-0e5c@uni-paderborn.de at 12:30, 3 January 2022

2022-01-03T12:30:40Z

Xin-wu-0e5c@uni-paderborn.de at 12:28, 3 January 2022

2022-01-03T12:28:52Z

Marius-neumann-d848@uni-bielefeld.de at 10:23, 3 January 2022

2022-01-03T10:23:38Z

Marius-neumann-d848@uni-bielefeld.de at 10:18, 3 January 2022

2022-01-03T10:18:59Z

Marius-neumann-d848@uni-bielefeld.de at 10:18, 3 January 2022

2022-01-03T10:18:37Z

Marius-neumann-d848@uni-bielefeld.de at 10:15, 3 January 2022

2022-01-03T10:15:46Z

Marius-neumann-d848@uni-bielefeld.de: Created page with "GPU Computing (Open Mp) {{DISPLAYTITLE:GPU Computing (Open MP)}} {{Syllabus Introduction to GPU Computing}} TOC OpenM..."

2022-01-03T09:41:06Z

Created page with "GPU Computing (Open Mp)<nowiki /> {{DISPLAYTITLE:GPU Computing (Open MP)}}<nowiki /> {{Syllabus Introduction to GPU Computing}}<nowiki /> __TOC__ OpenM..."

New page

[[Category:Tutorials|GPU Computing (Open Mp)]]<nowiki />
{{DISPLAYTITLE:GPU Computing (Open MP)}}<nowiki />
{{Syllabus Introduction to GPU Computing}}<nowiki />
__TOC__

OpenMP 4.0 and later enables developers to program GPUs in C/C++ and Fortran by means of OpenMP directives. In this tutorial we present the basic OpenMP syntax for GPU offloading and give a step-by-step guide for implementing SAXPY with it.

=== Video === 

<youtube width="600" height="340" right>rgqORzT1oCw</youtube>

([[Media:GPU_tutorial_saxpy_cuda_c.pdf |Slides as pdf]])

=== Quiz === 
{{hidden begin
|title = 1. Which one of the following OpenMP directives can create a target region on GPU?}}
<quiz display=simple>
{
|type="()"}
- `#pragma omp target gpu`
|| `#pragma omp target gpu` is a syntax error in OpenMP.
- `#pragma omp target acc`
|| + `#pragma omp target acc` is a syntax error in OpenMP.
+ `#pragma omp target`
|| Correct: `#pragma omp target` defines a target region, which is a block of computation that operates on GPU.
</quiz>
{{hidden end}}

{{hidden begin
|title = 2. The OpenMP `map(to:...)` clause maps variables:}}
<quiz display=simple>
{
|type="()"}
+ from host to device data environment before execution
|| Correct
- from host to device data environment after execution
|| Not correct
- from device to host data environment before execution
|| Not correct
- from device to host data environment after execution
|| Not correct
</quiz>
{{hidden end}}

{{hidden begin
|title = 3. Which one of the following OpenMP directives can initialize a league of teams for execution on GPU?}}
<quiz display=simple>
{
|type="()"}
- `#pragma omp init teams`
|| `#pragma omp init teams` is a syntax error in OpenMP.
+ `#pragma omp teams`
|| Correct: `#pragma omp teams` creates a league of teams for execution on GPU.
- `#pragma omp gpu teams`
|| `#pragma omp init teams` is a syntax error in OpenMP.
</quiz>
{{hidden end}}

{{hidden begin
|title = 4. Which one of the following OpenMP directives can distribute iterations of for-loop across GPU threads in the teams?}}
<quiz display=simple>
{
|type="()"}
- `#pragma omp distribute for`
|| `#pragma omp distribute for` is a syntax error in OpenMP.
- `#pragma omp parallel for`
|| `#pragma omp parallel for` only parallelizes the for-loop iterations amongst the threads in one team.
+ `#pragma omp distribute parallel for`
|| Correct: `#pragma omp distribute parallel for` distributes the for-loop iterations across two levels of parallelism, which are the league of teams and the threads in each team.
</quiz>
{{hidden end}}

← Older revision		Revision as of 15:22, 21 January 2022
Line 8:		Line 8:

	=== Video === <!--T:5-->		=== Video === <!--T:5-->
		+
		+	<youtube width="600" height="340" right>EPflqxk4rfk</youtube>

	([[Media:GPU_tutorial_saxpy_openmp.pdf \|Slides as pdf]])		([[Media:GPU_tutorial_saxpy_openmp.pdf \|Slides as pdf]])

@@ Line 20: / Line 20: @@
 || <code>#pragma omp target gpu</code> is a syntax error in OpenMP.
 - <code>#pragma omp target acc</code>
-|| + <code>#pragma omp target acc</code> is a syntax error in OpenMP.
+|| <code>#pragma omp target acc</code> is a syntax error in OpenMP.
 + <code>#pragma omp target</code>
 || Correct: <code>#pragma omp target</code> defines a target region, which is a block of computation that operates on GPU.

← Older revision		Revision as of 10:23, 3 January 2022
Line 8:		Line 8:

	=== Video === <!--T:5-->		=== Video === <!--T:5-->
		+
		+	([[Media:GPU_tutorial_saxpy_openmp.pdf \|Slides as pdf]])

	=== Quiz === <!--T:5-->		=== Quiz === <!--T:5-->

@@ Line 1: / Line 1: @@
-[[Category:Tutorials|GPU Computing (Open Mp)]]<nowiki />
+[[Category:Tutorials|GPU Computing (OpenMP)]]<nowiki />
-{{DISPLAYTITLE:GPU Computing (Open MP)}}<nowiki />
+{{DISPLAYTITLE:GPU Computing (OpenMP)}}<nowiki />
 {{Syllabus Introduction to GPU Computing}}<nowiki />
 __TOC__
-This video discusses the SAXPY via Open MP GPU offloading.
+This video discusses the SAXPY via OpenMP GPU offloading.
 OpenMP 4.0 and later enables developers to program GPUs in C/C++ and Fortran by means of OpenMP directives. In this tutorial we present the basic OpenMP syntax for GPU offloading and give a step-by-step guide for implementing SAXPY with it.

← Older revision		Revision as of 10:18, 3 January 2022
Line 4:		Line 4:
	__TOC__		__TOC__

		+	This video discusses the SAXPY via Open MP GPU offloading.
	OpenMP 4.0 and later enables developers to program GPUs in C/C++ and Fortran by means of OpenMP directives. In this tutorial we present the basic OpenMP syntax for GPU offloading and give a step-by-step guide for implementing SAXPY with it.		OpenMP 4.0 and later enables developers to program GPUs in C/C++ and Fortran by means of OpenMP directives. In this tutorial we present the basic OpenMP syntax for GPU offloading and give a step-by-step guide for implementing SAXPY with it.

@@ Line 17: / Line 17: @@
+{
 |type="()"}
-- `#pragma omp target gpu`
+- <code>#pragma omp target gpu</code>
-|| `#pragma omp target gpu` is a syntax error in OpenMP.
+|| <code>#pragma omp target gpu</code> is a syntax error in OpenMP.
-- `#pragma omp target acc`
+- <code>#pragma omp target acc</code>
-|| + `#pragma omp target acc` is a syntax error in OpenMP.
+|| + <code>#pragma omp target acc</code> is a syntax error in OpenMP.
-+ `#pragma omp target`
++ <code>#pragma omp target</code>
-|| Correct: `#pragma omp target` defines a target region, which is a block of computation that operates on GPU.
+|| Correct: <code>#pragma omp target</code> defines a target region, which is a block of computation that operates on GPU.
 </quiz>
 {{hidden end}}
@@ Line 49: / Line 49: @@
+{
 |type="()"}
-- `#pragma omp init teams`
+- <code>#pragma omp init teams</code>
-|| `#pragma omp init teams` is a syntax error in OpenMP.
+|| <code>#pragma omp init teams</code> is a syntax error in OpenMP.
-+ `#pragma omp teams`
++ <code>#pragma omp teams</code>
-|| Correct: `#pragma omp teams` creates a league of teams for execution on GPU.
+|| Correct: <code>#pragma omp teams</code> creates a league of teams for execution on GPU.
-- `#pragma omp gpu teams`
+- <code>#pragma omp gpu teams</code>
-|| `#pragma omp init teams` is a syntax error in OpenMP.
+|| <code>#pragma omp init teams</code> is a syntax error in OpenMP.
 </quiz>
 {{hidden end}}
@@ Line 64: / Line 64: @@
+{
 |type="()"}
-- `#pragma omp distribute for`
+- <code>#pragma omp distribute for</code>
-|| `#pragma omp distribute for` is a syntax error in OpenMP.
+|| <code>#pragma omp distribute for</code> is a syntax error in OpenMP.
-- `#pragma omp parallel for`
+- <code>#pragma omp parallel for</code>
-|| `#pragma omp parallel for` only parallelizes the for-loop iterations amongst the threads in one team.
+|| <code>#pragma omp parallel for</code> only parallelizes the for-loop iterations amongst the threads in one team.
-+ `#pragma omp distribute parallel for`
++ <code>#pragma omp distribute parallel for</code>
-|| Correct: `#pragma omp distribute parallel for` distributes the for-loop iterations across two levels of parallelism, which are the league of teams and the threads in each team.
+|| Correct: <code>#pragma omp distribute parallel for</code> distributes the for-loop iterations across two levels of parallelism, which are the league of teams and the threads in each team.
 </quiz>
 {{hidden end}}

← Older revision		Revision as of 10:15, 3 January 2022
Line 7:		Line 7:

	=== Video === <!--T:5-->		=== Video === <!--T:5-->
−
−	~~<youtube width="600" height="340" right>rgqORzT1oCw</youtube>~~
−
−	~~([[Media:GPU_tutorial_saxpy_cuda_c.pdf \|Slides as pdf]])~~
−
−

	=== Quiz === <!--T:5-->		=== Quiz === <!--T:5-->

GPU Tutorial/Open MP - Revision history

Marius-neumann-d848@uni-bielefeld.de at 15:22, 21 January 2022

Xin-wu-0e5c@uni-paderborn.de at 12:30, 3 January 2022

Xin-wu-0e5c@uni-paderborn.de at 12:28, 3 January 2022

Marius-neumann-d848@uni-bielefeld.de at 10:23, 3 January 2022

Marius-neumann-d848@uni-bielefeld.de at 10:18, 3 January 2022

Marius-neumann-d848@uni-bielefeld.de at 10:18, 3 January 2022

Marius-neumann-d848@uni-bielefeld.de at 10:15, 3 January 2022

Marius-neumann-d848@uni-bielefeld.de: Created page with "GPU Computing (Open Mp) {{DISPLAYTITLE:GPU Computing (Open MP)}} {{Syllabus Introduction to GPU Computing}} __TOC__ OpenM..."

Marius-neumann-d848@uni-bielefeld.de: Created page with "GPU Computing (Open Mp) {{DISPLAYTITLE:GPU Computing (Open MP)}} {{Syllabus Introduction to GPU Computing}} TOC OpenM..."