Skip to content

Commit

Permalink
deploy: 7f647ed
Browse files Browse the repository at this point in the history
  • Loading branch information
@wikfeldt
wikfeldt committed Dec 3, 2023
0 parents commit 1b16006
Show file tree
Hide file tree
Showing 564 changed files with 172,396 additions and 0 deletions.
4 changes: 4 additions & 0 deletions .buildinfo
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: c1986a5f46a754b585957e6698275afc
tags: d77d1c0d9ca2f4c8421862c7c5a0d620
Empty file added .nojekyll
Empty file.
245 changes: 245 additions & 0 deletions 0-setup/index.html

Large diffs are not rendered by default.

318 changes: 318 additions & 0 deletions 1-gpu-history/index.html

Large diffs are not rendered by default.

1,133 changes: 1,133 additions & 0 deletions 10-portable-kernel-models/index.html

Large diffs are not rendered by default.

490 changes: 490 additions & 0 deletions 11-gpu-porting/index.html

Large diffs are not rendered by default.

239 changes: 239 additions & 0 deletions 12-recommendations/index.html
Original file line number Diff line number Diff line change
@@ -0,0 +1,239 @@
<!DOCTYPE html>
<html class="writer-html5" lang="en">
<head>
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />

<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Recommendations &mdash; GPU programming: why, when and how? documentation</title>
<link rel="stylesheet" type="text/css" href="../_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="../_static/css/theme.css" />
<link rel="stylesheet" type="text/css" href="../_static/mystnb.4510f1fc1dee50b3e5859aac5469c37c29e427902b24a333a5f9fcb2f0b3ac41.css" />
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css" />
<link rel="stylesheet" type="text/css" href="../_static/togglebutton.css" />
<link rel="stylesheet" type="text/css" href="../_static/sphinx_lesson.css" />
<link rel="stylesheet" type="text/css" href="../_static/sphinx_rtd_theme_ext_color_contrast.css" />
<link rel="stylesheet" type="text/css" href="../_static/tabs.css" />
<link rel="stylesheet" type="text/css" href="../_static/overrides.css" />


<link rel="shortcut icon" href="../_static/favicon.ico"/>
<!--[if lt IE 9]>
<script src="../_static/js/html5shiv.min.js"></script>
<![endif]-->

<script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
<script src="../_static/jquery.js"></script>
<script src="../_static/underscore.js"></script>
<script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
<script src="../_static/doctools.js"></script>
<script src="../_static/sphinx_highlight.js"></script>
<script src="../_static/clipboard.min.js"></script>
<script src="../_static/copybutton.js"></script>
<script src="../_static/minipres.js"></script>
<script>let toggleHintShow = 'Click to show';</script>
<script>let toggleHintHide = 'Click to hide';</script>
<script>let toggleOpenOnPrint = 'true';</script>
<script src="../_static/togglebutton.js"></script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script data-domain="enccs.github.io/gpu-programming" defer="defer" src="https://plausible.io/js/script.js"></script>
<script src="../_static/js/theme.js"></script>
<link rel="index" title="Index" href="../genindex/" />
<link rel="search" title="Search" href="../search/" />
<link rel="next" title="GPU programming example: stencil computation" href="../13-examples/" />
<link rel="prev" title="Preparing code for GPU porting" href="../11-gpu-porting/" />
</head>

<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >



<a href="../" class="icon icon-home">
GPU programming: why, when and how?
<img src="../_static/ENCCS.jpg" class="logo" alt="Logo"/>
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../search/" method="get">
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
<p class="caption" role="heading"><span class="caption-text">Prerequisites</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../0-setup/">Setup</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">The lesson</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../1-gpu-history/">Why GPUs?</a></li>
<li class="toctree-l1"><a class="reference internal" href="../2-gpu-ecosystem/">The GPU hardware and software ecosystem</a></li>
<li class="toctree-l1"><a class="reference internal" href="../3-gpu-problems/">What problems fit to GPU?</a></li>
<li class="toctree-l1"><a class="reference internal" href="../4-gpu-concepts/">GPU programming concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../5-intro-to-gpu-prog-models/">Introduction to GPU programming models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../6-language-support/">High-level language support</a></li>
<li class="toctree-l1"><a class="reference internal" href="../7-directive-based-models/">Directive-based models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../8-multiple_gpu/">Multiple GPU programming with MPI</a></li>
<li class="toctree-l1"><a class="reference internal" href="../9-non-portable-kernel-models/">Non-portable kernel-based models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../10-portable-kernel-models/">Portable kernel-based models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../11-gpu-porting/">Preparing code for GPU porting</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Recommendations</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#portability">Portability</a></li>
<li class="toctree-l2"><a class="reference internal" href="#programming-effort">Programming Effort</a></li>
<li class="toctree-l2"><a class="reference internal" href="#performance-requirements">Performance Requirements</a></li>
<li class="toctree-l2"><a class="reference internal" href="#cost-benefit-analysis">Cost-benefit Analysis</a></li>
<li class="toctree-l2"><a class="reference internal" href="#choosing-between-frameworks">Choosing Between Frameworks</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../13-examples/">GPU programming example: stencil computation</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../quick-reference/">Quick Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../glossary/">Glossary</a></li>
<li class="toctree-l1"><a class="reference internal" href="../guide/">Instructor’s guide</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">About</span></p>
<ul>
<li class="toctree-l1"><a class="reference external" href="https://enccs.se/lessons/">All lessons</a></li>
<li class="toctree-l1"><a class="reference external" href="https://enccs.se/">ENCCS</a></li>
</ul>

</div>
</div>
</nav>

<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../">GPU programming: why, when and how?</a>
</nav>

<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="../" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item active">Recommendations</li>
<li class="wy-breadcrumbs-aside">
<a href="https://github.com/ENCCS/gpu-programming/blob/main/content/12-recommendations.rst" class="fa fa-github"> Edit on GitHub</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">

<section id="recommendations">
<h1>Recommendations<a class="headerlink" href="#recommendations" title="Permalink to this heading"></a></h1>
<div class="admonition-questions questions admonition" id="questions-0">
<p class="admonition-title">Questions</p>
<ul class="simple">
<li><p>Which GPU programming framework is right for me and my project?</p></li>
</ul>
</div>
<div class="admonition-instructor-note instructor-note admonition" id="instructor-note-0">
<p class="admonition-title">Instructor note</p>
<ul class="simple">
<li><p>30 min teaching</p></li>
<li><p>15 min exercises</p></li>
</ul>
</div>
<section id="portability">
<h2>Portability<a class="headerlink" href="#portability" title="Permalink to this heading"></a></h2>
<p>One of the critical factors when diving into GPU programming is the portability of the chosen framework.
It’s crucial to ensure that the framework you decide to utilize is compatible with the GPU or GPUs you intend
to use. This might seem like a basic step, but it’s essential to avoid unnecessary hardware-software mismatches
that could lead to performance bottlenecks or, worse, a complete failure of the system.</p>
<p>Moreover, if you’re targeting multiple platforms or GPUs, it’s wise to consider using frameworks that support
portable kernel-based models or those that come with high-level language support.
The benefit of these frameworks is that they allow for efficient execution of your code on a variety of
hardware configurations without needing significant alterations.</p>
</section>
<section id="programming-effort">
<h2>Programming Effort<a class="headerlink" href="#programming-effort" title="Permalink to this heading"></a></h2>
<p>The amount of programming effort required is another factor to consider when choosing a GPU programming framework.
It’s advisable to select a framework that supports the programming language you’re comfortable with.
This consideration will ensure a smoother learning curve and a more efficient development process.</p>
<p>Furthermore, it’s important to check the availability of supportive resources for the chosen framework.
Comprehensive documentation, illustrative examples, and an active community are important when learning
a new framework or troubleshooting issues. They not only minimize the time spent on resolving bugs but also
foster continuous learning and mastery of the framework.</p>
</section>
<section id="performance-requirements">
<h2>Performance Requirements<a class="headerlink" href="#performance-requirements" title="Permalink to this heading"></a></h2>
<p>Every application or project has unique performance requirements. Therefore, it’s crucial to evaluate the
performance characteristics and optimization capabilities of the potential frameworks before choosing one.
Some frameworks offer extensive optimization features and can automatically tune your code to maximize its
performance. Knowing how well a framework can handle your specific workload requirements can save you
considerable time and resources in the long run.</p>
</section>
<section id="cost-benefit-analysis">
<h2>Cost-benefit Analysis<a class="headerlink" href="#cost-benefit-analysis" title="Permalink to this heading"></a></h2>
<p>Before finalizing your choice of a GPU programming framework, it’s recommended to perform a cost-benefit analysis.
Consider the specific requirements of your project, like the processing power needed, the complexity of the tasks,
the amount of data to be processed, and the cost associated with the potential framework.
Understanding these factors will help you determine the most suitable and cost-effective framework for your needs.</p>
</section>
<section id="choosing-between-frameworks">
<h2>Choosing Between Frameworks<a class="headerlink" href="#choosing-between-frameworks" title="Permalink to this heading"></a></h2>
<p>The decision of choosing between different GPU programming frameworks often depends on several factors, including:</p>
<ul class="simple">
<li><p><strong>The specifics of the problem</strong>: Different problems might need different computational capabilities.
Understand your problem thoroughly and evaluate which framework is best equipped to handle it.</p></li>
<li><p><strong>Starting point</strong>: If you’re starting from scratch, you might have more flexibility in choosing your framework than
if you’re building on top of existing code.</p></li>
<li><p><strong>Background knowledge of the programmer</strong>: The familiarity of the programmer with certain programming languages or
frameworks plays a big role in the decision-making process.</p></li>
<li><p><strong>Time investment</strong>: Some frameworks may have a steeper learning curve but offer more extensive capabilities,
while others might be easier to grasp but provide limited features.</p></li>
<li><p><strong>Performance needs</strong>: Some applications require maximum computational power, while others might not.
The performance capabilities of the framework should align with the needs of your project.</p></li>
</ul>
<p>By keeping these considerations in mind, you can make a more informed decision and choose a GPU programming
framework that best suits your needs.</p>
<div class="admonition-question-and-discussion-time discussion important admonition" id="discussion-0">
<p class="admonition-title">Question and discussion time</p>
<ul class="simple">
<li><p>Has your mental model of how GPUs work and how they are programmed changed?</p></li>
<li><p>Do you have a better idea about what framework is right for your code?</p></li>
<li><p>What questions do you have? Ask us anything!</p></li>
</ul>
</div>
</section>
</section>


</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="../11-gpu-porting/" class="btn btn-neutral float-left" title="Preparing code for GPU porting" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="../13-examples/" class="btn btn-neutral float-right" title="GPU programming example: stencil computation" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>

<hr/>

<div role="contentinfo">
<p>&#169; Copyright 2023, The contributors.</p>
</div>

Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.


</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>

</body>
</html>
Loading

0 comments on commit 1b16006

Please sign in to comment.