1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
|
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/>
<meta http-equiv="X-UA-Compatible" content="IE=9"/>
<meta name="generator" content="Doxygen 1.8.6"/>
<title>ViennaCL - The Vienna Computing Library: blas1.cpp</title>
<link href="tabs.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript" src="jquery.js"></script>
<script type="text/javascript" src="dynsections.js"></script>
<link href="navtree.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript" src="resize.js"></script>
<script type="text/javascript" src="navtree.js"></script>
<script type="text/javascript">
$(document).ready(initResizable);
$(window).load(resizeHeight);
</script>
<link href="search/search.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript" src="search/search.js"></script>
<script type="text/javascript">
$(document).ready(function() { searchBox.OnSelectItem(0); });
</script>
<link href="doxygen.css" rel="stylesheet" type="text/css" />
</head>
<body>
<div id="top"><!-- do not remove this div, it is closed by doxygen! -->
<div id="titlearea">
<table cellspacing="0" cellpadding="0">
<tbody>
<tr style="height: 56px;">
<td style="padding-left: 0.5em;">
<div id="projectname">ViennaCL - The Vienna Computing Library
 <span id="projectnumber">1.7.1</span>
</div>
<div id="projectbrief">Free open-source GPU-accelerated linear algebra and solver library.</div>
</td>
<td> <div id="MSearchBox" class="MSearchBoxInactive">
<span class="left">
<img id="MSearchSelect" src="search/mag_sel.png"
onmouseover="return searchBox.OnSearchSelectShow()"
onmouseout="return searchBox.OnSearchSelectHide()"
alt=""/>
<input type="text" id="MSearchField" value="Search" accesskey="S"
onfocus="searchBox.OnSearchFieldFocus(true)"
onblur="searchBox.OnSearchFieldFocus(false)"
onkeyup="searchBox.OnSearchFieldChange(event)"/>
</span><span class="right">
<a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a>
</span>
</div>
</td>
</tr>
</tbody>
</table>
</div>
<!-- end header part -->
<!-- Generated by Doxygen 1.8.6 -->
<script type="text/javascript">
var searchBox = new SearchBox("searchBox", "search",false,'Search');
</script>
</div><!-- top -->
<div id="side-nav" class="ui-resizable side-nav-resizable">
<div id="nav-tree">
<div id="nav-tree-contents">
<div id="nav-sync" class="sync"></div>
</div>
</div>
<div id="splitbar" style="-moz-user-select:none;"
class="ui-resizable-handle">
</div>
</div>
<script type="text/javascript">
$(document).ready(function(){initNavTree('blas1_8cpp-example.html','');});
</script>
<div id="doc-content">
<!-- window showing the filter options -->
<div id="MSearchSelectWindow"
onmouseover="return searchBox.OnSearchSelectShow()"
onmouseout="return searchBox.OnSearchSelectHide()"
onkeydown="return searchBox.OnSearchSelectKey(event)">
<a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(0)"><span class="SelectionMark"> </span>All</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(1)"><span class="SelectionMark"> </span>Classes</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(2)"><span class="SelectionMark"> </span>Namespaces</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(3)"><span class="SelectionMark"> </span>Files</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(4)"><span class="SelectionMark"> </span>Functions</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(5)"><span class="SelectionMark"> </span>Variables</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(6)"><span class="SelectionMark"> </span>Typedefs</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(7)"><span class="SelectionMark"> </span>Enumerations</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(8)"><span class="SelectionMark"> </span>Enumerator</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(9)"><span class="SelectionMark"> </span>Friends</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(10)"><span class="SelectionMark"> </span>Macros</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(11)"><span class="SelectionMark"> </span>Pages</a></div>
<!-- iframe showing the search results (closed by default) -->
<div id="MSearchResultsWindow">
<iframe src="javascript:void(0)" frameborder="0"
name="MSearchResults" id="MSearchResults">
</iframe>
</div>
<div class="header">
<div class="headertitle">
<div class="title">blas1.cpp</div> </div>
</div><!--header-->
<div class="contents">
<p>This tutorial shows how the BLAS level 1 functionality available in ViennaCL can be used. Operator overloading in C++ is used extensively to provide an intuitive syntax.</p>
<p>We start off with including necessary headers: </p>
<div class="fragment"><div class="line"><span class="comment">// include necessary system headers</span></div>
<div class="line"><span class="preprocessor">#include <iostream></span></div>
<div class="line"></div>
<div class="line"><span class="comment">//include basic scalar and vector types of ViennaCL</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="scalar_8hpp.html">viennacl/scalar.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="vector_8hpp.html">viennacl/vector.hpp</a>"</span></div>
<div class="line"></div>
<div class="line"><span class="comment">//include the generic inner product functions of ViennaCL</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="inner__prod_8hpp.html">viennacl/linalg/inner_prod.hpp</a>"</span></div>
<div class="line"></div>
<div class="line"><span class="comment">//include the generic norm functions of ViennaCL</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="norm__1_8hpp.html">viennacl/linalg/norm_1.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="norm__2_8hpp.html">viennacl/linalg/norm_2.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="norm__inf_8hpp.html">viennacl/linalg/norm_inf.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="random_8hpp.html">viennacl/tools/random.hpp</a>"</span></div>
</div><!-- fragment --><p> In this tutorial we do not need additional auxiliary functions, allowing us to start right with <a class="el" href="tests_2src_2bisect_8cpp.html#ae66f6b31b5ad750f1fe042a706a4e3d4">main()</a>: </p>
<div class="fragment"><div class="line"><span class="keywordtype">int</span> <a name="a0"></a><a class="code" href="tests_2src_2bisect_8cpp.html#ae66f6b31b5ad750f1fe042a706a4e3d4">main</a>()</div>
<div class="line">{</div>
<div class="line"> <span class="comment">//Change this type definition to double if your gpu supports that</span></div>
<div class="line"> <span class="keyword">typedef</span> <span class="keywordtype">float</span> <a name="a1"></a><a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>;</div>
<div class="line"></div>
<div class="line"> <a name="_a2"></a><a class="code" href="classviennacl_1_1tools_1_1uniform__random__numbers.html">viennacl::tools::uniform_random_numbers<ScalarType></a> randomNumber;</div>
</div><!-- fragment --> <h2>Scalar Operations </h2>
<p>Although usually not very efficient because of PCI-Express latency, ViennaCL enables you to directly manipulate individual scalar values. As such, a viennacl::scalar<double> behaves very similar to a normal <code>double</code>.</p>
<p>Let us define a few CPU and ViennaCL scalars:</p>
<div class="fragment"><div class="line">ScalarType <a name="a3"></a><a class="code" href="global__variables_8cpp.html#a24573a2e279db4db9228d18dfbf27eae">s1</a> = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(3.1415926); <span class="comment">//note: writing ScalarType s1 = 3.1415926; leads to warnings with some compilers if ScalarType is 'float'.</span></div>
<div class="line">ScalarType <a name="a4"></a><a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a> = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(2.71763);</div>
<div class="line">ScalarType s3 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(42.0);</div>
<div class="line"></div>
<div class="line"><a name="_a5"></a><a class="code" href="classviennacl_1_1scalar.html">viennacl::scalar<ScalarType></a> vcl_s1;</div>
<div class="line"><a class="code" href="classviennacl_1_1scalar.html">viennacl::scalar<ScalarType></a> vcl_s2 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(1.0);</div>
<div class="line"><a class="code" href="classviennacl_1_1scalar.html">viennacl::scalar<ScalarType></a> vcl_s3 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(1.0);</div>
</div><!-- fragment --><p> CPU scalars can be transparently assigned to GPU scalars and vice versa: </p>
<div class="fragment"><div class="line">std::cout << <span class="stringliteral">"Copying a few scalars..."</span> << std::endl;</div>
<div class="line">vcl_s1 = <a class="code" href="global__variables_8cpp.html#a24573a2e279db4db9228d18dfbf27eae">s1</a>;</div>
<div class="line">s2 = vcl_s2;</div>
<div class="line">vcl_s3 = s3;</div>
</div><!-- fragment --><p> Operations between GPU scalars work just as for CPU scalars: (Note that such single compute kernels on the GPU are considerably slower than on the CPU) </p>
<div class="fragment"><div class="line">std::cout << <span class="stringliteral">"Manipulating a few scalars..."</span> << std::endl;</div>
<div class="line">std::cout << <span class="stringliteral">"operator +="</span> << std::endl;</div>
<div class="line">s1 += <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line">vcl_s1 += vcl_s2;</div>
<div class="line"></div>
<div class="line">std::cout << <span class="stringliteral">"operator *="</span> << std::endl;</div>
<div class="line">s1 *= <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line">vcl_s1 *= vcl_s2;</div>
<div class="line"></div>
<div class="line">std::cout << <span class="stringliteral">"operator -="</span> << std::endl;</div>
<div class="line">s1 -= <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line">vcl_s1 -= vcl_s2;</div>
<div class="line"></div>
<div class="line">std::cout << <span class="stringliteral">"operator /="</span> << std::endl;</div>
<div class="line">s1 /= <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line">vcl_s1 /= vcl_s2;</div>
<div class="line"></div>
<div class="line">std::cout << <span class="stringliteral">"operator +"</span> << std::endl;</div>
<div class="line">s1 = s2 + s3;</div>
<div class="line">vcl_s1 = vcl_s2 + vcl_s3;</div>
<div class="line"></div>
<div class="line">std::cout << <span class="stringliteral">"multiple operators"</span> << std::endl;</div>
<div class="line">s1 = s2 + s3 * s2 - s3 / <a class="code" href="global__variables_8cpp.html#a24573a2e279db4db9228d18dfbf27eae">s1</a>;</div>
<div class="line">vcl_s1 = vcl_s2 + vcl_s3 * vcl_s2 - vcl_s3 / vcl_s1;</div>
</div><!-- fragment --><p> Operations can also be mixed: </p>
<div class="fragment"><div class="line">std::cout << <span class="stringliteral">"mixed operations"</span> << std::endl;</div>
<div class="line">vcl_s1 = s1 * vcl_s2 + s3 - vcl_s3;</div>
</div><!-- fragment --><p> The output stream is overloaded as well for direct printing to e.g. a terminal: </p>
<div class="fragment"><div class="line">std::cout << <span class="stringliteral">"CPU scalar s3: "</span> << s3 << std::endl;</div>
<div class="line">std::cout << <span class="stringliteral">"GPU scalar vcl_s3: "</span> << vcl_s3 << std::endl;</div>
</div><!-- fragment --> <h2>Vector Operations</h2>
<p>Define a few vectors (from STL and plain C) and viennacl::vectors </p>
<div class="fragment"><div class="line">std::vector<ScalarType> std_vec1(10);</div>
<div class="line">std::vector<ScalarType> std_vec2(10);</div>
<div class="line">ScalarType plain_vec3[10]; <span class="comment">//plain C array</span></div>
<div class="line"></div>
<div class="line"><a name="_a6"></a><a class="code" href="classviennacl_1_1vector.html">viennacl::vector<ScalarType></a> vcl_vec1(10);</div>
<div class="line"><a class="code" href="classviennacl_1_1vector.html">viennacl::vector<ScalarType></a> vcl_vec2(10);</div>
<div class="line"><a class="code" href="classviennacl_1_1vector.html">viennacl::vector<ScalarType></a> vcl_vec3(10);</div>
</div><!-- fragment --><p> Let us fill the CPU vectors with random values: </p>
<div class="fragment"><div class="line"><span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = 0; i < 10; ++i)</div>
<div class="line">{</div>
<div class="line"> std_vec1[i] = randomNumber();</div>
<div class="line"> vcl_vec2(i) = randomNumber(); <span class="comment">//also works for GPU vectors, but is MUCH slower (approx. factor 10.000) than the CPU analogue</span></div>
<div class="line"> plain_vec3[i] = randomNumber();</div>
<div class="line">}</div>
</div><!-- fragment --><p> Copy the CPU vectors to the GPU vectors and vice versa </p>
<div class="fragment"><div class="line"><a name="a7"></a><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(std_vec1.begin(), std_vec1.end(), vcl_vec1.begin()); <span class="comment">//either the STL way</span></div>
<div class="line"><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec2.begin(), vcl_vec2.end(), std_vec2.begin()); <span class="comment">//either the STL way</span></div>
<div class="line"><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec2, std_vec2); <span class="comment">//using the short hand notation for objects that provide .begin() and .end() members</span></div>
<div class="line"><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec2.begin(), vcl_vec2.end(), plain_vec3); <span class="comment">//copy to plain C vector</span></div>
</div><!-- fragment --><p> Also partial copies by providing the corresponding iterators are possible: </p>
<div class="fragment"><div class="line"><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(std_vec1.begin() + 4, std_vec1.begin() + 8, vcl_vec1.begin() + 4); <span class="comment">//cpu to gpu</span></div>
<div class="line"><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec1.begin() + 4, vcl_vec1.begin() + 8, vcl_vec2.begin() + 1); <span class="comment">//gpu to gpu</span></div>
<div class="line"><a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec1.begin() + 4, vcl_vec1.begin() + 8, std_vec1.begin() + 1); <span class="comment">//gpu to cpu</span></div>
</div><!-- fragment --><p> Compute the inner product of two GPU vectors and write the result to either CPU or GPU </p>
<div class="fragment"><div class="line">vcl_s1 = <a name="a8"></a><a class="code" href="namespaceviennacl_1_1linalg.html#ab35950c4374eb3be08a03d852508c01a">viennacl::linalg::inner_prod</a>(vcl_vec1, vcl_vec2);</div>
<div class="line">s1 = <a class="code" href="namespaceviennacl_1_1linalg.html#ab35950c4374eb3be08a03d852508c01a">viennacl::linalg::inner_prod</a>(vcl_vec1, vcl_vec2);</div>
<div class="line">s2 = <a class="code" href="namespaceviennacl_1_1linalg.html#ab35950c4374eb3be08a03d852508c01a">viennacl::linalg::inner_prod</a>(std_vec1, std_vec2); <span class="comment">//inner prod can also be used with std::vector (computations are carried out on CPU then)</span></div>
</div><!-- fragment --><p> Compute norms: </p>
<div class="fragment"><div class="line">s1 = <a name="a9"></a><a class="code" href="namespaceviennacl_1_1linalg.html#a2efad0d090dde0c127fa8b25a73836e4">viennacl::linalg::norm_1</a>(vcl_vec1);</div>
<div class="line">vcl_s2 = <a name="a10"></a><a class="code" href="namespaceviennacl_1_1linalg.html#ae46f15d01c01f92a153b3f555a15096b">viennacl::linalg::norm_2</a>(vcl_vec2);</div>
<div class="line">s3 = <a name="a11"></a><a class="code" href="namespaceviennacl_1_1linalg.html#ae4de9152d556e89d823eb47a683ead11">viennacl::linalg::norm_inf</a>(vcl_vec3);</div>
</div><!-- fragment --><p> Plane rotation of two vectors: </p>
<div class="fragment"><div class="line"><a name="a12"></a><a class="code" href="namespaceviennacl_1_1linalg.html#acbacf04789215a3a748eca63743d50af">viennacl::linalg::plane_rotation</a>(vcl_vec1, vcl_vec2, 1.1f, 2.3f);</div>
</div><!-- fragment --><p> Use <a class="el" href="classviennacl_1_1vector.html">viennacl::vector</a> via the overloaded operators just as you would write it on paper: </p>
<div class="fragment"><div class="line"><span class="comment">//simple expression:</span></div>
<div class="line">vcl_vec1 = vcl_s1 * vcl_vec2 / vcl_s3;</div>
<div class="line"></div>
<div class="line"><span class="comment">//more complicated expression:</span></div>
<div class="line">vcl_vec1 = vcl_vec2 / vcl_s3 + vcl_s2 * (vcl_vec1 - vcl_s2 * vcl_vec2);</div>
</div><!-- fragment --><p> Swap the content of two vectors without a temporary vector: </p>
<div class="fragment"><div class="line"><a name="a13"></a><a class="code" href="namespaceviennacl.html#a49233dc20718f52e98e8b06e9711b375">viennacl::swap</a>(vcl_vec1, vcl_vec2); <span class="comment">//swaps all entries in memory</span></div>
<div class="line"><a name="a14"></a><a class="code" href="namespaceviennacl.html#a495321f19d07b98a5ba433332cb590da">viennacl::fast_swap</a>(vcl_vec1, vcl_vec2); <span class="comment">//swaps OpenCL memory handles only</span></div>
</div><!-- fragment --><p> The vectors can also be cleared directly: </p>
<div class="fragment"><div class="line">vcl_vec1.clear();</div>
<div class="line">vcl_vec2.clear();</div>
</div><!-- fragment --><p> That's it, the tutorial is completed. </p>
<div class="fragment"><div class="line"> std::cout << <span class="stringliteral">"!!!! TUTORIAL COMPLETED SUCCESSFULLY !!!!"</span> << std::endl;</div>
<div class="line"></div>
<div class="line"> <span class="keywordflow">return</span> EXIT_SUCCESS;</div>
<div class="line">}</div>
</div><!-- fragment --> <h2>Full Example Code</h2>
<div class="fragment"><div class="line"><span class="comment">/* =========================================================================</span></div>
<div class="line"><span class="comment"> Copyright (c) 2010-2016, Institute for Microelectronics,</span></div>
<div class="line"><span class="comment"> Institute for Analysis and Scientific Computing,</span></div>
<div class="line"><span class="comment"> TU Wien.</span></div>
<div class="line"><span class="comment"> Portions of this software are copyright by UChicago Argonne, LLC.</span></div>
<div class="line"><span class="comment"></span></div>
<div class="line"><span class="comment"> -----------------</span></div>
<div class="line"><span class="comment"> ViennaCL - The Vienna Computing Library</span></div>
<div class="line"><span class="comment"> -----------------</span></div>
<div class="line"><span class="comment"></span></div>
<div class="line"><span class="comment"> Project Head: Karl Rupp rupp@iue.tuwien.ac.at</span></div>
<div class="line"><span class="comment"></span></div>
<div class="line"><span class="comment"> (A list of authors and contributors can be found in the PDF manual)</span></div>
<div class="line"><span class="comment"></span></div>
<div class="line"><span class="comment"> License: MIT (X11), see file LICENSE in the base directory</span></div>
<div class="line"><span class="comment">============================================================================= */</span></div>
<div class="line"></div>
<div class="line"><span class="comment">// include necessary system headers</span></div>
<div class="line"><span class="preprocessor">#include <iostream></span></div>
<div class="line"></div>
<div class="line"><span class="comment">//include basic scalar and vector types of ViennaCL</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="scalar_8hpp.html">viennacl/scalar.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="vector_8hpp.html">viennacl/vector.hpp</a>"</span></div>
<div class="line"></div>
<div class="line"><span class="comment">//include the generic inner product functions of ViennaCL</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="inner__prod_8hpp.html">viennacl/linalg/inner_prod.hpp</a>"</span></div>
<div class="line"></div>
<div class="line"><span class="comment">//include the generic norm functions of ViennaCL</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="norm__1_8hpp.html">viennacl/linalg/norm_1.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="norm__2_8hpp.html">viennacl/linalg/norm_2.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="norm__inf_8hpp.html">viennacl/linalg/norm_inf.hpp</a>"</span></div>
<div class="line"><span class="preprocessor">#include "<a class="code" href="random_8hpp.html">viennacl/tools/random.hpp</a>"</span></div>
<div class="line"></div>
<div class="line"></div>
<div class="line"><span class="keywordtype">int</span> <a class="code" href="tests_2src_2bisect_8cpp.html#ae66f6b31b5ad750f1fe042a706a4e3d4">main</a>()</div>
<div class="line">{</div>
<div class="line"> <span class="comment">//Change this type definition to double if your gpu supports that</span></div>
<div class="line"> <span class="keyword">typedef</span> <span class="keywordtype">float</span> <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>;</div>
<div class="line"></div>
<div class="line"> <a class="code" href="classviennacl_1_1tools_1_1uniform__random__numbers.html">viennacl::tools::uniform_random_numbers<ScalarType></a> randomNumber;</div>
<div class="line"></div>
<div class="line"> ScalarType s1 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(3.1415926); <span class="comment">//note: writing ScalarType s1 = 3.1415926; leads to warnings with some compilers if ScalarType is 'float'.</span></div>
<div class="line"> ScalarType s2 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(2.71763);</div>
<div class="line"> ScalarType s3 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(42.0);</div>
<div class="line"></div>
<div class="line"> <a class="code" href="classviennacl_1_1scalar.html">viennacl::scalar<ScalarType></a> vcl_s1;</div>
<div class="line"> <a class="code" href="classviennacl_1_1scalar.html">viennacl::scalar<ScalarType></a> vcl_s2 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(1.0);</div>
<div class="line"> <a class="code" href="classviennacl_1_1scalar.html">viennacl::scalar<ScalarType></a> vcl_s3 = <a class="code" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a>(1.0);</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"Copying a few scalars..."</span> << std::endl;</div>
<div class="line"> vcl_s1 = <a class="code" href="global__variables_8cpp.html#a24573a2e279db4db9228d18dfbf27eae">s1</a>;</div>
<div class="line"> s2 = vcl_s2;</div>
<div class="line"> vcl_s3 = s3;</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"Manipulating a few scalars..."</span> << std::endl;</div>
<div class="line"> std::cout << <span class="stringliteral">"operator +="</span> << std::endl;</div>
<div class="line"> s1 += <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line"> vcl_s1 += vcl_s2;</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"operator *="</span> << std::endl;</div>
<div class="line"> s1 *= <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line"> vcl_s1 *= vcl_s2;</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"operator -="</span> << std::endl;</div>
<div class="line"> s1 -= <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line"> vcl_s1 -= vcl_s2;</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"operator /="</span> << std::endl;</div>
<div class="line"> s1 /= <a class="code" href="global__variables_8cpp.html#a8163feae57063e5c0bb2e640ff4e8c7a">s2</a>;</div>
<div class="line"> vcl_s1 /= vcl_s2;</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"operator +"</span> << std::endl;</div>
<div class="line"> s1 = s2 + s3;</div>
<div class="line"> vcl_s1 = vcl_s2 + vcl_s3;</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"multiple operators"</span> << std::endl;</div>
<div class="line"> s1 = s2 + s3 * s2 - s3 / <a class="code" href="global__variables_8cpp.html#a24573a2e279db4db9228d18dfbf27eae">s1</a>;</div>
<div class="line"> vcl_s1 = vcl_s2 + vcl_s3 * vcl_s2 - vcl_s3 / vcl_s1;</div>
<div class="line"></div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"mixed operations"</span> << std::endl;</div>
<div class="line"> vcl_s1 = s1 * vcl_s2 + s3 - vcl_s3;</div>
<div class="line"></div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"CPU scalar s3: "</span> << s3 << std::endl;</div>
<div class="line"> std::cout << <span class="stringliteral">"GPU scalar vcl_s3: "</span> << vcl_s3 << std::endl;</div>
<div class="line"></div>
<div class="line"></div>
<div class="line"> std::vector<ScalarType> std_vec1(10);</div>
<div class="line"> std::vector<ScalarType> std_vec2(10);</div>
<div class="line"> ScalarType plain_vec3[10]; <span class="comment">//plain C array</span></div>
<div class="line"></div>
<div class="line"> <a class="code" href="classviennacl_1_1vector.html">viennacl::vector<ScalarType></a> vcl_vec1(10);</div>
<div class="line"> <a class="code" href="classviennacl_1_1vector.html">viennacl::vector<ScalarType></a> vcl_vec2(10);</div>
<div class="line"> <a class="code" href="classviennacl_1_1vector.html">viennacl::vector<ScalarType></a> vcl_vec3(10);</div>
<div class="line"></div>
<div class="line"> <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = 0; i < 10; ++i)</div>
<div class="line"> {</div>
<div class="line"> std_vec1[i] = randomNumber();</div>
<div class="line"> vcl_vec2(i) = randomNumber(); <span class="comment">//also works for GPU vectors, but is MUCH slower (approx. factor 10.000) than the CPU analogue</span></div>
<div class="line"> plain_vec3[i] = randomNumber();</div>
<div class="line"> }</div>
<div class="line"></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(std_vec1.begin(), std_vec1.end(), vcl_vec1.<a name="a15"></a><a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>()); <span class="comment">//either the STL way</span></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec2.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>(), vcl_vec2.<a name="a16"></a><a class="code" href="classviennacl_1_1vector__base.html#aba8a76bd4c96435ba68cf96b9e5132a6">end</a>(), std_vec2.begin()); <span class="comment">//either the STL way</span></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec2, std_vec2); <span class="comment">//using the short hand notation for objects that provide .begin() and .end() members</span></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec2.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>(), vcl_vec2.<a class="code" href="classviennacl_1_1vector__base.html#aba8a76bd4c96435ba68cf96b9e5132a6">end</a>(), plain_vec3); <span class="comment">//copy to plain C vector</span></div>
<div class="line"></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(std_vec1.begin() + 4, std_vec1.begin() + 8, vcl_vec1.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>() + 4); <span class="comment">//cpu to gpu</span></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec1.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>() + 4, vcl_vec1.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>() + 8, vcl_vec2.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>() + 1); <span class="comment">//gpu to gpu</span></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a10b7f8cf6b8864a7aa196d670481a453">viennacl::copy</a>(vcl_vec1.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>() + 4, vcl_vec1.<a class="code" href="classviennacl_1_1vector__base.html#a762d98e2f912fc534951f25555b6077f">begin</a>() + 8, std_vec1.begin() + 1); <span class="comment">//gpu to cpu</span></div>
<div class="line"></div>
<div class="line"> vcl_s1 = <a class="code" href="namespaceviennacl_1_1linalg.html#ab35950c4374eb3be08a03d852508c01a">viennacl::linalg::inner_prod</a>(vcl_vec1, vcl_vec2);</div>
<div class="line"> s1 = <a class="code" href="namespaceviennacl_1_1linalg.html#ab35950c4374eb3be08a03d852508c01a">viennacl::linalg::inner_prod</a>(vcl_vec1, vcl_vec2);</div>
<div class="line"> s2 = <a class="code" href="namespaceviennacl_1_1linalg.html#ab35950c4374eb3be08a03d852508c01a">viennacl::linalg::inner_prod</a>(std_vec1, std_vec2); <span class="comment">//inner prod can also be used with std::vector (computations are carried out on CPU then)</span></div>
<div class="line"></div>
<div class="line"> s1 = <a class="code" href="namespaceviennacl_1_1linalg.html#a2efad0d090dde0c127fa8b25a73836e4">viennacl::linalg::norm_1</a>(vcl_vec1);</div>
<div class="line"> vcl_s2 = <a class="code" href="namespaceviennacl_1_1linalg.html#ae46f15d01c01f92a153b3f555a15096b">viennacl::linalg::norm_2</a>(vcl_vec2);</div>
<div class="line"> s3 = <a class="code" href="namespaceviennacl_1_1linalg.html#ae4de9152d556e89d823eb47a683ead11">viennacl::linalg::norm_inf</a>(vcl_vec3);</div>
<div class="line"></div>
<div class="line"></div>
<div class="line"> <a class="code" href="namespaceviennacl_1_1linalg.html#acbacf04789215a3a748eca63743d50af">viennacl::linalg::plane_rotation</a>(vcl_vec1, vcl_vec2, 1.1f, 2.3f);</div>
<div class="line"></div>
<div class="line"> <span class="comment">//simple expression:</span></div>
<div class="line"> vcl_vec1 = vcl_s1 * vcl_vec2 / vcl_s3;</div>
<div class="line"></div>
<div class="line"> <span class="comment">//more complicated expression:</span></div>
<div class="line"> vcl_vec1 = vcl_vec2 / vcl_s3 + vcl_s2 * (vcl_vec1 - vcl_s2 * vcl_vec2);</div>
<div class="line"></div>
<div class="line"></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a49233dc20718f52e98e8b06e9711b375">viennacl::swap</a>(vcl_vec1, vcl_vec2); <span class="comment">//swaps all entries in memory</span></div>
<div class="line"> <a class="code" href="namespaceviennacl.html#a495321f19d07b98a5ba433332cb590da">viennacl::fast_swap</a>(vcl_vec1, vcl_vec2); <span class="comment">//swaps OpenCL memory handles only</span></div>
<div class="line"></div>
<div class="line"> vcl_vec1.<a name="a17"></a><a class="code" href="classviennacl_1_1vector__base.html#abf5acd243b2b1571cc7a486e89485ca0">clear</a>();</div>
<div class="line"> vcl_vec2.<a class="code" href="classviennacl_1_1vector__base.html#abf5acd243b2b1571cc7a486e89485ca0">clear</a>();</div>
<div class="line"></div>
<div class="line"> std::cout << <span class="stringliteral">"!!!! TUTORIAL COMPLETED SUCCESSFULLY !!!!"</span> << std::endl;</div>
<div class="line"></div>
<div class="line"> <span class="keywordflow">return</span> EXIT_SUCCESS;</div>
<div class="line">}</div>
<div class="line"></div>
</div><!-- fragment --> </div><!-- contents -->
</div><!-- doc-content -->
<!-- start footer part -->
<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
<ul>
<li class="footer">Generated on Wed Jan 20 2016 22:32:38 for ViennaCL - The Vienna Computing Library by
<a href="http://www.doxygen.org/index.html">
<img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.6 </li>
</ul>
</div>
</body>
</html>
|
