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
|
<!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: viennacl/linalg/host_based/sse_kernels.hpp File Reference</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">1.6.2</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('sse__kernels_8hpp.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="summary">
<a href="#namespaces">Namespaces</a> |
<a href="#func-members">Functions</a> </div>
<div class="headertitle">
<div class="title">sse_kernels.hpp File Reference</div> </div>
</div><!--header-->
<div class="contents">
<p>optimized linear algebra operations for the CPU
<a href="#details">More...</a></p>
<div class="textblock"><code>#include <iostream></code><br/>
<code>#include <vector></code><br/>
<code>#include <algorithm></code><br/>
<code>#include "<a class="el" href="sse__blas_8hpp_source.html">viennacl/linalg/host_based/sse_blas.hpp</a>"</code><br/>
</div>
<p><a href="sse__kernels_8hpp_source.html">Go to the source code of this file.</a></p>
<table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="namespaces"></a>
Namespaces</h2></td></tr>
<tr class="memitem:namespaceviennacl"><td class="memItemLeft" align="right" valign="top">  </td><td class="memItemRight" valign="bottom"><a class="el" href="namespaceviennacl.html">viennacl</a></td></tr>
<tr class="memdesc:namespaceviennacl"><td class="mdescLeft"> </td><td class="mdescRight">Main namespace in ViennaCL. Holds all the basic types such as vector, matrix, etc. and defines operations upon them. <br/></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:namespaceviennacl_1_1linalg"><td class="memItemLeft" align="right" valign="top">  </td><td class="memItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg.html">viennacl::linalg</a></td></tr>
<tr class="memdesc:namespaceviennacl_1_1linalg"><td class="mdescLeft"> </td><td class="mdescRight">Provides all linear algebra operations which are not covered by operator overloads. <br/></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:namespaceviennacl_1_1linalg_1_1host__based"><td class="memItemLeft" align="right" valign="top">  </td><td class="memItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based.html">viennacl::linalg::host_based</a></td></tr>
<tr class="memdesc:namespaceviennacl_1_1linalg_1_1host__based"><td class="mdescLeft"> </td><td class="mdescRight">Holds all compute kernels with conventional host-based execution (buffers in CPU RAM). <br/></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:namespaceviennacl_1_1linalg_1_1host__based_1_1detail"><td class="memItemLeft" align="right" valign="top">  </td><td class="memItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based_1_1detail.html">viennacl::linalg::host_based::detail</a></td></tr>
<tr class="memdesc:namespaceviennacl_1_1linalg_1_1host__based_1_1detail"><td class="mdescLeft"> </td><td class="mdescRight">Helper functions for the host-based linear algebra backend. <br/></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
</table><table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
Functions</h2></td></tr>
<tr class="memitem:acd0ccc877ddce3ae3ac5c4cb1393ccea"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:acd0ccc877ddce3ae3ac5c4cb1393ccea"><td class="memTemplItemLeft" align="right" valign="top">bool </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based_1_1detail.html#acd0ccc877ddce3ae3ac5c4cb1393ccea">viennacl::linalg::host_based::detail::isHermitian</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **const A, vcl_size_t n)</td></tr>
<tr class="separator:acd0ccc877ddce3ae3ac5c4cb1393ccea"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a537ac5e83bd3ad6927f1ab8389451ebd"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:a537ac5e83bd3ad6927f1ab8389451ebd"><td class="memTemplItemLeft" align="right" valign="top">vcl_size_t </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based_1_1detail.html#a537ac5e83bd3ad6927f1ab8389451ebd">viennacl::linalg::host_based::detail::getHermitianBandwidth</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **const A, vcl_size_t n)</td></tr>
<tr class="separator:a537ac5e83bd3ad6927f1ab8389451ebd"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:af014b25ce5cbd2c46fd1316de20429c2"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:af014b25ce5cbd2c46fd1316de20429c2"><td class="memTemplItemLeft" align="right" valign="top">void </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based_1_1detail.html#af014b25ce5cbd2c46fd1316de20429c2">viennacl::linalg::host_based::detail::eliminateHermitian</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t row, vcl_size_t from, vcl_size_t to, vcl_size_t width, <a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> *ss)</td></tr>
<tr class="separator:af014b25ce5cbd2c46fd1316de20429c2"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a9d7508e012aea146e6f35e08bc09c339"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:a9d7508e012aea146e6f35e08bc09c339"><td class="memTemplItemLeft" align="right" valign="top">void </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based_1_1detail.html#a9d7508e012aea146e6f35e08bc09c339">viennacl::linalg::host_based::detail::tridiagonalizeHermitianBandedMatrix</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t n, vcl_size_t bandwidth)</td></tr>
<tr class="separator:a9d7508e012aea146e6f35e08bc09c339"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:ada3cb15238c1c502bde216d770949a00"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:ada3cb15238c1c502bde216d770949a00"><td class="memTemplItemLeft" align="right" valign="top">void </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based_1_1detail.html#ada3cb15238c1c502bde216d770949a00">viennacl::linalg::host_based::detail::reduceHermitianToBandedMatrix</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t n, vcl_size_t block_size, vcl_size_t num_threads)</td></tr>
<tr class="separator:ada3cb15238c1c502bde216d770949a00"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a186586aced1407e7106fd3f7f432f582"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:a186586aced1407e7106fd3f7f432f582"><td class="memTemplItemLeft" align="right" valign="top">void </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based.html#a186586aced1407e7106fd3f7f432f582">viennacl::linalg::host_based::inplace_tred2</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t n, vcl_size_t block_size=1, vcl_size_t num_threads=1)</td></tr>
<tr class="memdesc:a186586aced1407e7106fd3f7f432f582"><td class="mdescLeft"> </td><td class="mdescRight">Inplace reduction of a dense n x n row-major or column-major hermitian (or real symmetric) matrix to tridiagonal form using householder similarity transforms (preserving eigenvalues) <a href="#a186586aced1407e7106fd3f7f432f582">More...</a><br/></td></tr>
<tr class="separator:a186586aced1407e7106fd3f7f432f582"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a29a882acaad6a548f7fadf54598bdc42"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:a29a882acaad6a548f7fadf54598bdc42"><td class="memTemplItemLeft" align="right" valign="top">bool </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based.html#a29a882acaad6a548f7fadf54598bdc42">viennacl::linalg::host_based::lu_factorize_row_major</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t m, vcl_size_t n, vcl_size_t *piv=NULL, vcl_size_t block_size=8)</td></tr>
<tr class="memdesc:a29a882acaad6a548f7fadf54598bdc42"><td class="mdescLeft"> </td><td class="mdescRight">Inplace lu factorization of an m x n dense row-major matrix with optional partial pivoting, returning true for an even number of pivots, false for an odd number of pivots. Factorization is successful if there are no nonzero values on the diagonal. <a href="#a29a882acaad6a548f7fadf54598bdc42">More...</a><br/></td></tr>
<tr class="separator:a29a882acaad6a548f7fadf54598bdc42"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:aaa3af08473cb3a7f5116d54302c02d86"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:aaa3af08473cb3a7f5116d54302c02d86"><td class="memTemplItemLeft" align="right" valign="top">std::vector< <a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> > </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based.html#aaa3af08473cb3a7f5116d54302c02d86">viennacl::linalg::host_based::inplace_qr_col_major</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t m, vcl_size_t n, vcl_size_t block_size=8)</td></tr>
<tr class="memdesc:aaa3af08473cb3a7f5116d54302c02d86"><td class="mdescLeft"> </td><td class="mdescRight">Inplace qr factorization of an m x n dense column-major matrix, returning the householder normalization coefficients. <a href="#aaa3af08473cb3a7f5116d54302c02d86">More...</a><br/></td></tr>
<tr class="separator:aaa3af08473cb3a7f5116d54302c02d86"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:ab1ca91eea2771be83df0a807951388d3"><td class="memTemplParams" colspan="2">template<typename ScalarType > </td></tr>
<tr class="memitem:ab1ca91eea2771be83df0a807951388d3"><td class="memTemplItemLeft" align="right" valign="top">std::vector< <a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> > </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespaceviennacl_1_1linalg_1_1host__based.html#ab1ca91eea2771be83df0a807951388d3">viennacl::linalg::host_based::inplace_qr_row_major</a> (<a class="el" href="fft__1d_8cpp.html#ad5c19ca4f47d3f8ec21232a5af2624e5">ScalarType</a> **A, vcl_size_t m, vcl_size_t n, vcl_size_t block_size=8, vcl_size_t num_threads=1)</td></tr>
<tr class="memdesc:ab1ca91eea2771be83df0a807951388d3"><td class="mdescLeft"> </td><td class="mdescRight">Inplace qr factorization of an m x n dense row-major matrix, returning the householder normalization coefficients. <a href="#ab1ca91eea2771be83df0a807951388d3">More...</a><br/></td></tr>
<tr class="separator:ab1ca91eea2771be83df0a807951388d3"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
<div class="textblock"><p>optimized linear algebra operations for the CPU </p>
<p>Contributed by Alex Christensen. </p>
<p>Definition in file <a class="el" href="sse__kernels_8hpp_source.html">sse_kernels.hpp</a>.</p>
</div></div><!-- contents -->
</div><!-- doc-content -->
<!-- start footer part -->
<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
<ul>
<li class="navelem"><a class="el" href="dir_c82e3d11dd171600f4a6e0cab1ec1e0d.html">viennacl</a></li><li class="navelem"><a class="el" href="dir_63cde087767c4ed65c7901ffc6e293fe.html">linalg</a></li><li class="navelem"><a class="el" href="dir_8d734bf48796b8afc2ea3e50ddaea273.html">host_based</a></li><li class="navelem"><a class="el" href="sse__kernels_8hpp.html">sse_kernels.hpp</a></li>
<li class="footer">Generated on Thu Dec 11 2014 23:28:05 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>
|
