1- <!DOCTYPE html>
1+ <!doctype html>
22< html >
3-
43 < head >
5- < meta charset ='utf-8 ' />
6- < meta http-equiv ="X-UA-Compatible " content ="chrome=1 " />
7- < meta name ="description " content ="Hands On OpenCL : An open source two-day lecture course for teaching and learning OpenCL " />
8-
9- < link rel ="stylesheet " type ="text/css " media ="screen " href ="stylesheets/stylesheet.css ">
4+ < meta charset ="utf-8 ">
5+ < meta http-equiv ="X-UA-Compatible " content ="chrome=1 ">
6+ < title > Hands On OpenCL by HandsOnOpenCL</ title >
7+ < link rel ="stylesheet " href ="stylesheets/styles.css ">
8+ < link rel ="stylesheet " href ="stylesheets/pygment_trac.css ">
9+ < script src ="https://ajax.googleapis.com/ajax/libs/jquery/1.7.1/jquery.min.js "> </ script >
10+ < script src ="javascripts/respond.js "> </ script >
11+ <!--[if lt IE 9]>
12+ <script src="//html5shiv.googlecode.com/svn/trunk/html5.js"></script>
13+ <![endif]-->
14+ <!--[if lt IE 8]>
15+ <link rel="stylesheet" href="stylesheets/ie.css">
16+ <![endif]-->
17+ < meta name ="viewport " content ="width=device-width, initial-scale=1, user-scalable=no ">
1018
11- < title > Hands On OpenCL</ title >
1219 </ head >
13-
1420 < body >
15-
16- <!-- HEADER -->
17- < div id ="header_wrap " class ="outer ">
18- < header class ="inner ">
19- < a id ="forkme_banner " href ="https://github.com/HandsOnOpenCL "> View on GitHub</ a >
20-
21- < h1 id ="project_title "> Hands On OpenCL</ h1 >
22- < h2 id ="project_tagline "> An open source two-day lecture course for teaching and learning OpenCL</ h2 >
23-
24- </ header >
25- </ div >
26-
27- <!-- MAIN CONTENT -->
28- < div id ="main_content_wrap " class ="outer ">
29- < section id ="main_content " class ="inner ">
30- < p > < strong > Note: This is a pre-release, in production version of the lecture material</ strong > </ p >
31-
32- < p > Check back soon for the final release!</ p >
33-
34- < h3 >
21+ < div id ="header ">
22+ < nav >
23+ < li class ="fork "> < a href ="https://github.com/HandsOnOpenCL "> View On GitHub</ a > </ li >
24+ </ nav >
25+ </ div > <!-- end header -->
26+
27+ < div class ="wrapper ">
28+
29+ < section >
30+ < div id ="title ">
31+ < h1 > Hands On OpenCL</ h1 >
32+ < p > An open source two-day lecture course for teaching and learning OpenCL</ p >
33+ < hr >
34+ < span class ="credits left "> Project maintained by < a href ="https://github.com/HandsOnOpenCL "> HandsOnOpenCL</ a > </ span >
35+ < span class ="credits right "> Hosted on GitHub Pages — Theme by < a href ="https://twitter.com/michigangraham "> mattgraham</ a > </ span >
36+ </ div >
37+
38+ < h3 >
3539< a name ="welcome " class ="anchor " href ="#welcome "> < span class ="octicon octicon-link "> </ span > </ a > Welcome</ h3 >
3640
37- < p > Introductory paragraph about the course</ p >
41+ < p > Hands On OpenCL is a two-day lecture course introducing OpenCL, the API for writing heterogeneous applications. Provided are slides for around twelve lectures, plus some appendicies, complete with Examples and Solutions in C, C++ and Python. The lecture series finishes with information on porting CUDA applications to OpenCL.</ p >
42+
43+ < p > These lectures, and their examples, and released under the "attribution CC BY" creative commons license.</ p >
3844
3945< h3 >
4046< a name ="course-structure " class ="anchor " href ="#course-structure "> < span class ="octicon octicon-link "> </ span > </ a > Course Structure</ h3 >
7177< p > Using CPUs and GPUs simultaneously, multiple platforms and devices</ p >
7278</ li >
7379< li >
80+ < p > < strong > Enabling portable performance via OpenCL</ strong > </ p >
81+
82+ < p > Autotuning using Flamingo</ p >
83+ </ li >
84+ < li >
7485< p > < strong > Optimizing OpenCL performance</ strong > </ p >
7586
76- < p > Profiling </ p >
87+ < p > Profiling using Extrae and Paraver
88+ Information on NVVP and CodeXL</ p >
7789</ li >
7890< li >
79- < p > < strong > Enabling portable performance via OpenCL</ strong > </ p >
91+ < p > < strong > Debugging OpenCL</ strong > </ p >
8092
81- < p > Autotuning </ p >
93+ < p > Using GDB </ p >
8294</ li >
83- < li > < p > < strong > Debugging OpenCL</ strong > </ p > </ li >
8495< li > < p > < strong > Porting CUDA to OpenCL</ strong > </ p > </ li >
8596</ ol > < h3 >
8697< a name ="examples " class ="anchor " href ="#examples "> < span class ="octicon octicon-link "> </ span > </ a > Examples</ h3 >
@@ -117,7 +128,12 @@ <h3>
117128< p > Write your first OpenCL kernel from scratch.</ p >
118129</ li >
119130< li >
120- < p > < strong > Optimize memory movement costs for Matrix Multiplication</ strong > </ p >
131+ < p > < strong > Using private memory</ strong > </ p >
132+
133+ < p > Use private memory to minimize memory costs.</ p >
134+ </ li >
135+ < li >
136+ < p > < strong > Using local memory</ strong > </ p >
121137
122138< p > Use local and private memory to minimize memory costs.</ p >
123139</ li >
@@ -132,14 +148,14 @@ <h3>
132148< p > Run your kernels on many devices.</ p >
133149</ li >
134150< li >
135- < p > < strong > Profiling OpenCL programs </ strong > </ p >
151+ < p > < strong > Optimize matrix multiplication </ strong > </ p >
136152
137- < p > Experiment making things run faster. </ p >
153+ < p > Look at portable performance (combining 9. and 10.) </ p >
138154</ li >
139155< li >
140- < p > < strong > Optimize matrix multiplication </ strong > </ p >
156+ < p > < strong > Profiling OpenCL programs </ strong > </ p >
141157
142- < p > Look at portable performance (combining 9. and 10.) </ p >
158+ < p > Experiment making things run faster. </ p >
143159</ li >
144160< li >
145161< p > < strong > Porting CUDA to OpenCL</ strong > </ p >
@@ -161,16 +177,9 @@ <h3>
161177
162178< p > Fixed a bug yourself? Please submit a pull request. Thanks.</ p >
163179 </ section >
164- </ div >
165180
166- <!-- FOOTER -->
167- < div id ="footer_wrap " class ="outer ">
168- < footer class ="inner ">
169- < p > Published with < a href ="http://pages.github.com "> GitHub Pages</ a > </ p >
170- </ footer >
171181 </ div >
172-
182+ <!--[if !IE]><script>fixScale(document);</script><![endif]-->
173183
174-
175184 </ body >
176- </ html >
185+ </ html >
0 commit comments