Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / ComputeLibrary / 0e205f7e1083bf26e6ffc33d96005999b541b8f9 / . / documentation / fft_8cl_source.xhtml
blob: 181bb45a10370a1c656c62c839736400d754d086 [file] [log] [blame]
<!-- HTML header for doxygen 1.8.15-->
<!-- Remember to use version doxygen 1.8.15 +-->
<!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 1.8.15"/>
<meta name="robots" content="NOINDEX, NOFOLLOW" /> <!-- Prevent indexing by search engines -->
<title>Compute Library: src/core/CL/cl_kernels/fft.cl Source File</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="navtreedata.js"></script>
<script type="text/javascript" src="navtree.js"></script>
<script type="text/javascript">
/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&amp;dn=gpl-2.0.txt GPL-v2 */
$(document).ready(initResizable);
/* @license-end */</script>
<link href="search/search.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript" src="search/searchdata.js"></script>
<script type="text/javascript" src="search/search.js"></script>
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
extensions: ["tex2jax.js"],
jax: ["input/TeX","output/HTML-CSS"],
});
</script><script type="text/javascript" async="async" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
<link href="doxygen.css" rel="stylesheet" type="text/css" />
<link href="stylesheet.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;">
<img alt="Compute Library" src="https://raw.githubusercontent.com/ARM-software/ComputeLibrary/gh-pages/ACL_logo.png" style="max-width: 100%;margin-top: 15px;margin-left: 10px"/>
<td style="padding-left: 0.5em;">
<div id="projectname">
&#160;<span id="projectnumber">19.11</span>
</div>
</td>
</tr>
</tbody>
</table>
</div>
<!-- end header part -->
<!-- Generated by Doxygen 1.8.15 -->
<script type="text/javascript">
/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&amp;dn=gpl-2.0.txt GPL-v2 */
var searchBox = new SearchBox("searchBox", "search",false,'Search');
/* @license-end */
</script>
<script type="text/javascript" src="menudata.js"></script>
<script type="text/javascript" src="menu.js"></script>
<script type="text/javascript">
/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&amp;dn=gpl-2.0.txt GPL-v2 */
$(function() {
initMenu('',true,false,'search.php','Search');
$(document).ready(function() { init_search(); });
});
/* @license-end */</script>
<div id="main-nav"></div>
</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">
/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&amp;dn=gpl-2.0.txt GPL-v2 */
$(document).ready(function(){initNavTree('fft_8cl_source.xhtml','');});
/* @license-end */
</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)">
</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">fft.cl</div> </div>
</div><!--header-->
<div class="contents">
<a href="fft_8cl.xhtml">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span>&#160;<span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span>&#160;<span class="comment"> * Copyright (c) 2019 ARM Limited.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span>&#160;<span class="comment"> * SPDX-License-Identifier: MIT</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span>&#160;<span class="comment"> * Permission is hereby granted, free of charge, to any person obtaining a copy</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span>&#160;<span class="comment"> * of this software and associated documentation files (the &quot;Software&quot;), to</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span>&#160;<span class="comment"> * deal in the Software without restriction, including without limitation the</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span>&#160;<span class="comment"> * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span>&#160;<span class="comment"> * sell copies of the Software, and to permit persons to whom the Software is</span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span>&#160;<span class="comment"> * furnished to do so, subject to the following conditions:</span></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span>&#160;<span class="comment"> * The above copyright notice and this permission notice shall be included in all</span></div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span>&#160;<span class="comment"> * copies or substantial portions of the Software.</span></div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span>&#160;<span class="comment"> * THE SOFTWARE IS PROVIDED &quot;AS IS&quot;, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span>&#160;<span class="comment"> * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,</span></div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span>&#160;<span class="comment"> * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE</span></div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span>&#160;<span class="comment"> * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER</span></div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span>&#160;<span class="comment"> * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,</span></div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span>&#160;<span class="comment"> * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE</span></div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span>&#160;<span class="comment"> * SOFTWARE.</span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span>&#160;<span class="preprocessor">#include &quot;<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml">helpers.h</a>&quot;</span></div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00026"></a><span class="lineno"> 26</span>&#160;<span class="comment">/** Calculates and applies the twiddle factor to a given input.</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span>&#160;<span class="comment"> * @param[in] phi The angle.</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span>&#160;<span class="comment"> * @param[in,out] input The input on which the factor should be applied.</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00031"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2"> 31</a></span>&#160;<span class="preprocessor">#define TWIDDLE_FACTOR_MULTIPLICATION(phi, input) \</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span>&#160;<span class="preprocessor"> float2 w, tmp; \</span></div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span>&#160;<span class="preprocessor"> w.x = native_cos(phi); \</span></div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span>&#160;<span class="preprocessor"> w.y = native_sin(phi); \</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span>&#160;<span class="preprocessor"> tmp.x = (w.x * input.x) - (w.y * input.y); \</span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span>&#160;<span class="preprocessor"> tmp.y = (w.x * input.y) + (w.y * input.x); \</span></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span>&#160;<span class="preprocessor"> input = tmp; \</span></div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span>&#160;<span class="comment">/** Computes radix-2 butterfly unit.</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span>&#160;<span class="comment"> * @param[in,out] c0 Complex input 0.</span></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span>&#160;<span class="comment"> * @param[in,out] c1 Complex input 1.</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00046"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a5a63ca1d5404d67d13382a90cfc9b6c3"> 46</a></span>&#160;<span class="preprocessor">#define DFT_2(c0, c1) \</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span>&#160;<span class="preprocessor"> float2 v0; \</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span>&#160;<span class="preprocessor"> v0 = c0; \</span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span>&#160;<span class="preprocessor"> c0 = v0 + c1; \</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span>&#160;<span class="preprocessor"> c1 = v0 - c1; \</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span>&#160;</div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span>&#160;<span class="comment">// radix-3 butterfly unit factors</span></div><div class="line"><a name="l00055"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#adec4b7ab0397cf3774d5971cc1296d9f"> 55</a></span>&#160;<span class="preprocessor">#define SQRT3DIV2 0.86602540378443f</span></div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>&#160;<span class="comment">/** Computes radix-3 butterfly unit.</span></div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>&#160;<span class="comment"> * @param[in,out] c0 Complex input 0.</span></div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span>&#160;<span class="comment"> * @param[in,out] c1 Complex input 1.</span></div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>&#160;<span class="comment"> * @param[in,out] c2 Complex input 2.</span></div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00063"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ac6ec77d2e41d56919c14c1483eee94ac"> 63</a></span>&#160;<span class="preprocessor">#define DFT_3(c0, c1, c2) \</span></div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>&#160;<span class="preprocessor"> float2 v0 = c1 + c2; \</span></div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>&#160;<span class="preprocessor"> float2 v1 = c1 - c2; \</span></div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>&#160;<span class="preprocessor"> c1.x = c0.x - 0.5f * v0.x + v1.y * SQRT3DIV2; \</span></div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>&#160;<span class="preprocessor"> c1.y = c0.y - 0.5f * v0.y - v1.x * SQRT3DIV2; \</span></div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>&#160;<span class="preprocessor"> c2.x = c0.x - 0.5f * v0.x - v1.y * SQRT3DIV2; \</span></div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>&#160;<span class="preprocessor"> c2.y = c0.y - 0.5f * v0.y + v1.x * SQRT3DIV2; \</span></div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>&#160;<span class="preprocessor"> c0 = c0 + v0; \</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>&#160;<span class="comment">/**Computes radix-4 butterfly unit.</span></div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>&#160;<span class="comment"> * @param[in,out] c0 Complex input 0.</span></div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>&#160;<span class="comment"> * @param[in,out] c1 Complex input 1.</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>&#160;<span class="comment"> * @param[in,out] c2 Complex input 2.</span></div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>&#160;<span class="comment"> * @param[in,out] c3 Complex input 3.</span></div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00081"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#af97e6d43f8b70bcf009d521f8909db25"> 81</a></span>&#160;<span class="preprocessor">#define DFT_4(c0, c1, c2, c3) \</span></div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>&#160;<span class="preprocessor"> float2 v0, v1, v2, v3; \</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>&#160;<span class="preprocessor"> v0 = c0 + c2; \</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>&#160;<span class="preprocessor"> v1 = c1 + c3; \</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>&#160;<span class="preprocessor"> v2 = c0 - c2; \</span></div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>&#160;<span class="preprocessor"> v3.x = c1.y - c3.y; \</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>&#160;<span class="preprocessor"> v3.y = c3.x - c1.x; \</span></div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>&#160;<span class="preprocessor"> c0 = v0 + v1; \</span></div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>&#160;<span class="preprocessor"> c2 = v0 - v1; \</span></div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>&#160;<span class="preprocessor"> c1 = v2 + v3; \</span></div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>&#160;<span class="preprocessor"> c3 = v2 - v3; \</span></div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>&#160;</div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>&#160;<span class="comment">// radix-5 butterfly unit factors</span></div><div class="line"><a name="l00096"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a3ddea99343f4804c61e3d3376d3bedc1"> 96</a></span>&#160;<span class="preprocessor">#define W5_A 0.30901699437494f</span></div><div class="line"><a name="l00097"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#aeb3e0b1f96e2ecec9df46338c274ab9f"> 97</a></span>&#160;<span class="preprocessor">#define W5_B 0.95105651629515f</span></div><div class="line"><a name="l00098"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#add4ae9e98c446aeb95bb6bf312996eb0"> 98</a></span>&#160;<span class="preprocessor">#define W5_C 0.80901699437494f</span></div><div class="line"><a name="l00099"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a55263f2a15f045ec5f4673b5bdda9bc4"> 99</a></span>&#160;<span class="preprocessor">#define W5_D 0.58778525229247f</span></div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span>&#160;<span class="comment">/** Computes radix-5 butterfly unit.</span></div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>&#160;<span class="comment"> * @param[in,out] c0 Complex input 0.</span></div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>&#160;<span class="comment"> * @param[in,out] c1 Complex input 1.</span></div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>&#160;<span class="comment"> * @param[in,out] c2 Complex input 2.</span></div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>&#160;<span class="comment"> * @param[in,out] c3 Complex input 3.</span></div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>&#160;<span class="comment"> * @param[in,out] c4 Complex input 4.</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00109"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a565f17c6fe3e9462057bb523e0127280"> 109</a></span>&#160;<span class="preprocessor">#define DFT_5(c0, c1, c2, c3, c4) \</span></div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>&#160;<span class="preprocessor"> float2 v0, v1, v2, v3, v4; \</span></div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span>&#160;<span class="preprocessor"> v0 = c0; \</span></div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>&#160;<span class="preprocessor"> v1 = W5_A * (c1 + c4) - W5_C * (c2 + c3); \</span></div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>&#160;<span class="preprocessor"> v2 = W5_C * (c1 + c4) - W5_A * (c2 + c3); \</span></div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span>&#160;<span class="preprocessor"> v3 = W5_D * (c1 - c4) - W5_B * (c2 - c3); \</span></div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span>&#160;<span class="preprocessor"> v4 = W5_B * (c1 - c4) + W5_D * (c2 - c3); \</span></div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>&#160;<span class="preprocessor"> c0 = v0 + c1 + c2 + c3 + c4; \</span></div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span>&#160;<span class="preprocessor"> c1 = v0 + v1 + (float2)(v4.y, -v4.x); \</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>&#160;<span class="preprocessor"> c2 = v0 - v2 + (float2)(v3.y, -v3.x); \</span></div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>&#160;<span class="preprocessor"> c3 = v0 - v2 + (float2)(-v3.y, v3.x); \</span></div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>&#160;<span class="preprocessor"> c4 = v0 + v1 + (float2)(-v4.y, v4.x); \</span></div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>&#160;</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>&#160;<span class="comment">// radix-7 butterfly unit factors</span></div><div class="line"><a name="l00125"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ac2612396f1dc9f3037fa59f6efd4e759"> 125</a></span>&#160;<span class="preprocessor">#define W7_A 0.62348980185873f</span></div><div class="line"><a name="l00126"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ab07d9041b925e9a79b953d01d170145d"> 126</a></span>&#160;<span class="preprocessor">#define W7_B 0.78183148246802f</span></div><div class="line"><a name="l00127"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a014e0a1952e8b2a95b66f244958adc86"> 127</a></span>&#160;<span class="preprocessor">#define W7_C 0.22252093395631f</span></div><div class="line"><a name="l00128"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a2e8bd73ebc6280cb023a90bff4b4e595"> 128</a></span>&#160;<span class="preprocessor">#define W7_D 0.97492791218182f</span></div><div class="line"><a name="l00129"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ad6991beebc37eaa9fec68f1a7ccf019f"> 129</a></span>&#160;<span class="preprocessor">#define W7_E 0.90096886790241f</span></div><div class="line"><a name="l00130"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a2c2804f21de28bb28c360d8d5b8ab98b"> 130</a></span>&#160;<span class="preprocessor">#define W7_F 0.43388373911755f</span></div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span>&#160;<span class="comment">/** Computes radix-7 butterfly unit.</span></div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>&#160;<span class="comment"> * @param[in,out] c0 Complex input 0.</span></div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>&#160;<span class="comment"> * @param[in,out] c1 Complex input 1.</span></div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>&#160;<span class="comment"> * @param[in,out] c2 Complex input 2.</span></div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>&#160;<span class="comment"> * @param[in,out] c3 Complex input 3.</span></div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>&#160;<span class="comment"> * @param[in,out] c4 Complex input 4.</span></div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>&#160;<span class="comment"> * @param[in,out] c5 Complex input 5.</span></div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>&#160;<span class="comment"> * @param[in,out] c6 Complex input 6.</span></div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00142"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ad04a4028658f997aaca067742c2e8a49"> 142</a></span>&#160;<span class="preprocessor">#define DFT_7(c0, c1, c2, c3, c4, c5, c6) \</span></div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>&#160;<span class="preprocessor"> float2 v0, v1, v2, v3, v4, v5, v6; \</span></div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>&#160;<span class="preprocessor"> v0 = c0; \</span></div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>&#160;<span class="preprocessor"> v1 = W7_A * (c1 + c6) - W7_C * (c2 + c5) - W7_E * (c3 + c4); \</span></div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>&#160;<span class="preprocessor"> v2 = W7_C * (c1 + c6) + W7_E * (c2 + c5) - W7_A * (c3 + c4); \</span></div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>&#160;<span class="preprocessor"> v3 = W7_E * (c1 + c6) - W7_A * (c2 + c5) + W7_C * (c3 + c4); \</span></div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>&#160;<span class="preprocessor"> v4 = W7_B * (c1 - c6) + W7_D * (c2 - c5) + W7_F * (c3 - c4); \</span></div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span>&#160;<span class="preprocessor"> v5 = W7_D * (c1 - c6) - W7_F * (c2 - c5) - W7_B * (c3 - c4); \</span></div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>&#160;<span class="preprocessor"> v6 = W7_F * (c1 - c6) - W7_B * (c2 - c5) + W7_D * (c3 - c4); \</span></div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>&#160;<span class="preprocessor"> c0 = v0 + c1 + c2 + c3 + c4 + c5 + c6; \</span></div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>&#160;<span class="preprocessor"> c1 = v0 + v1 + (float2)(v4.y, -v4.x); \</span></div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>&#160;<span class="preprocessor"> c2 = v0 - v2 + (float2)(v5.y, -v5.x); \</span></div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>&#160;<span class="preprocessor"> c3 = v0 - v3 + (float2)(v6.y, -v6.x); \</span></div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span>&#160;<span class="preprocessor"> c4 = v0 - v3 + (float2)(-v6.y, v6.x); \</span></div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>&#160;<span class="preprocessor"> c5 = v0 - v2 + (float2)(-v5.y, v5.x); \</span></div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span>&#160;<span class="preprocessor"> c6 = v0 + v1 + (float2)(-v4.y, v4.x); \</span></div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>&#160;<span class="comment">/** Computes radix-8 butterfly unit.</span></div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>&#160;<span class="comment"> * @param[in,out] c0 Complex input 0.</span></div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>&#160;<span class="comment"> * @param[in,out] c1 Complex input 1.</span></div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>&#160;<span class="comment"> * @param[in,out] c2 Complex input 2.</span></div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>&#160;<span class="comment"> * @param[in,out] c3 Complex input 3.</span></div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>&#160;<span class="comment"> * @param[in,out] c4 Complex input 4.</span></div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>&#160;<span class="comment"> * @param[in,out] c5 Complex input 5.</span></div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>&#160;<span class="comment"> * @param[in,out] c6 Complex input 6.</span></div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span>&#160;<span class="comment"> * @param[in,out] c7 Complex input 7.</span></div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00172"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a4c4ce3f10939dd4237d0adee00086a53"> 172</a></span>&#160;<span class="preprocessor">#define DFT_8(c0, c1, c2, c3, c4, c5, c6, c7) \</span></div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>&#160;<span class="preprocessor"> { \</span></div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>&#160;<span class="preprocessor"> float2 v0, v1, v2, v3, v4, v5, v6, v7; \</span></div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>&#160;<span class="preprocessor"> float2 s0, s1, s2, s3, s4, s5, s6, s7; \</span></div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span>&#160;<span class="preprocessor"> float2 t0, t1, t2; \</span></div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>&#160;<span class="preprocessor"> v0 = c0 + c4; \</span></div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>&#160;<span class="preprocessor"> v1 = c1 + c5; \</span></div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>&#160;<span class="preprocessor"> v2 = c2 + c6; \</span></div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>&#160;<span class="preprocessor"> v3 = c3 + c7; \</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>&#160;<span class="preprocessor"> v4 = c0 - c4; \</span></div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span>&#160;<span class="preprocessor"> v5 = c1 - c5; \</span></div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>&#160;<span class="preprocessor"> v6 = c2 - c6; \</span></div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span>&#160;<span class="preprocessor"> v7 = c3 - c7; \</span></div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span>&#160;<span class="preprocessor"> s0 = v0 + v2; \</span></div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span>&#160;<span class="preprocessor"> s1 = v1 + v3; \</span></div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span>&#160;<span class="preprocessor"> s2 = v0 - v2; \</span></div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span>&#160;<span class="preprocessor"> s3 = v1 - v3; \</span></div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span>&#160;<span class="preprocessor"> s4.x = v4.x - v6.y; \</span></div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span>&#160;<span class="preprocessor"> s4.y = v4.y + v6.x; \</span></div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span>&#160;<span class="preprocessor"> s5.x = v5.x - v7.y; \</span></div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span>&#160;<span class="preprocessor"> s5.y = v5.y + v7.x; \</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span>&#160;<span class="preprocessor"> s6.x = v4.x + v6.y; \</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span>&#160;<span class="preprocessor"> s6.y = v4.y - v6.x; \</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span>&#160;<span class="preprocessor"> s7.x = v5.x + v7.y; \</span></div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>&#160;<span class="preprocessor"> s7.y = v5.y - v7.x; \</span></div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>&#160;<span class="preprocessor"> t0.x = -s3.y; \</span></div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span>&#160;<span class="preprocessor"> t0.y = s3.x; \</span></div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>&#160;<span class="preprocessor"> t1.x = M_SQRT1_2_F * (s5.x - s5.y); \</span></div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>&#160;<span class="preprocessor"> t1.y = M_SQRT1_2_F * (s5.x + s5.y); \</span></div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span>&#160;<span class="preprocessor"> t2.x = -M_SQRT1_2_F * (s7.x + s7.y); \</span></div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>&#160;<span class="preprocessor"> t2.y = M_SQRT1_2_F * (s7.x - s7.y); \</span></div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>&#160;<span class="preprocessor"> c0 = s0 + s1; \</span></div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>&#160;<span class="preprocessor"> c1 = s6 - t2; \</span></div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>&#160;<span class="preprocessor"> c2 = s2 - t0; \</span></div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span>&#160;<span class="preprocessor"> c3 = s4 - t1; \</span></div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span>&#160;<span class="preprocessor"> c4 = s0 - s1; \</span></div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span>&#160;<span class="preprocessor"> c5 = s6 + t2; \</span></div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>&#160;<span class="preprocessor"> c6 = s2 + t0; \</span></div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span>&#160;<span class="preprocessor"> c7 = s4 + t1; \</span></div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>&#160;<span class="preprocessor"> }</span></div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span>&#160;<span class="comment">/** Computes the first stage of a radix-2 DFT on axis 0.</span></div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00234"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#aea16049f33aa1fa59ca48e7092238bf0"> 234</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#aea16049f33aa1fa59ca48e7092238bf0">fft_radix_2_first_stage_axis_0</a>(</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>&#160; ,</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span>&#160;)</div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span>&#160;{</div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00247"></a><span class="lineno"> 247</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>&#160;</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>&#160; <span class="comment">// Load two complex input values</span></div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>&#160; float4 data = vload4(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>&#160;</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>&#160; <span class="comment">// Compute DFT N = 2</span></div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>&#160; <a class="code" href="fft_8cl.xhtml#a5a63ca1d5404d67d13382a90cfc9b6c3">DFT_2</a>(data.s01, data.s23);</div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>&#160;</div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span>&#160; <span class="comment">// Store two complex output values</span></div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>&#160; vstore4(data, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>&#160;}</div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>&#160;<span class="comment">/** Computes the first stage of a radix-2 DFT on axis 1.</span></div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00281"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ae919967e7eb2349552a120bd0ab40eb2"> 281</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#ae919967e7eb2349552a120bd0ab40eb2">fft_radix_2_first_stage_axis_1</a>(</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>&#160; ,</div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>&#160;)</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>&#160;{</div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>&#160;</div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span>&#160; <span class="comment">// Load two complex input values</span></div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00299"></a><span class="lineno"> 299</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 1, 0));</div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span>&#160;</div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span>&#160; <span class="comment">// Compute DFT N = 2</span></div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span>&#160; <a class="code" href="fft_8cl.xhtml#a5a63ca1d5404d67d13382a90cfc9b6c3">DFT_2</a>(data1, data2);</div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span>&#160;</div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span>&#160; <span class="comment">// Store two complex output values</span></div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 1, 0));</div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span>&#160;}</div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span>&#160;<span class="comment">/** Computes the first stage of a radix-3 DFT on axis 0.</span></div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00313"></a><span class="lineno"> 313</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00316"></a><span class="lineno"> 316</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00318"></a><span class="lineno"> 318</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00323"></a><span class="lineno"> 323</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00324"></a><span class="lineno"> 324</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00326"></a><span class="lineno"> 326</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00327"></a><span class="lineno"> 327</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00329"></a><span class="lineno"> 329</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00330"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a3a40d552a9d4c240e46db020bd606a2b"> 330</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a3a40d552a9d4c240e46db020bd606a2b">fft_radix_3_first_stage_axis_0</a>(</div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span>&#160; ,</div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span>&#160;)</div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span>&#160;{</div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00343"></a><span class="lineno"> 343</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00344"></a><span class="lineno"> 344</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00345"></a><span class="lineno"> 345</span>&#160;</div><div class="line"><a name="l00346"></a><span class="lineno"> 346</span>&#160; <span class="comment">// Load three complex input values</span></div><div class="line"><a name="l00347"></a><span class="lineno"> 347</span>&#160; float4 data0 = vload4(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 2, 0, 0));</div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span>&#160;</div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span>&#160; <span class="comment">// Compute DFT N = 3</span></div><div class="line"><a name="l00351"></a><span class="lineno"> 351</span>&#160; <a class="code" href="fft_8cl.xhtml#ac6ec77d2e41d56919c14c1483eee94ac">DFT_3</a>(data0.s01, data0.s23, data1.s01);</div><div class="line"><a name="l00352"></a><span class="lineno"> 352</span>&#160;</div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span>&#160; <span class="comment">// Store three complex output values</span></div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span>&#160; vstore4(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 2, 0, 0));</div><div class="line"><a name="l00356"></a><span class="lineno"> 356</span>&#160;}</div><div class="line"><a name="l00357"></a><span class="lineno"> 357</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span>&#160;<span class="comment">/** Computes the first stage of a radix-3 DFT on axis 1.</span></div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00365"></a><span class="lineno"> 365</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00366"></a><span class="lineno"> 366</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00367"></a><span class="lineno"> 367</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00368"></a><span class="lineno"> 368</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00370"></a><span class="lineno"> 370</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00371"></a><span class="lineno"> 371</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00376"></a><span class="lineno"> 376</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00377"></a><span class="lineno"> 377</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00379"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a45a776393b0fabafec290645e3d67010"> 379</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a45a776393b0fabafec290645e3d67010">fft_radix_3_first_stage_axis_1</a>(</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span>&#160; ,</div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00385"></a><span class="lineno"> 385</span>&#160;)</div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span>&#160;{</div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00390"></a><span class="lineno"> 390</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00391"></a><span class="lineno"> 391</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00392"></a><span class="lineno"> 392</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00393"></a><span class="lineno"> 393</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00394"></a><span class="lineno"> 394</span>&#160;</div><div class="line"><a name="l00395"></a><span class="lineno"> 395</span>&#160; <span class="comment">// Load three complex input values</span></div><div class="line"><a name="l00396"></a><span class="lineno"> 396</span>&#160; float2 data0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 1, 0));</div><div class="line"><a name="l00398"></a><span class="lineno"> 398</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2, 0));</div><div class="line"><a name="l00399"></a><span class="lineno"> 399</span>&#160;</div><div class="line"><a name="l00400"></a><span class="lineno"> 400</span>&#160; <span class="comment">// Compute DFT N = 3</span></div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span>&#160; <a class="code" href="fft_8cl.xhtml#ac6ec77d2e41d56919c14c1483eee94ac">DFT_3</a>(data0, data1, data2);</div><div class="line"><a name="l00402"></a><span class="lineno"> 402</span>&#160;</div><div class="line"><a name="l00403"></a><span class="lineno"> 403</span>&#160; <span class="comment">// Store three complex output values</span></div><div class="line"><a name="l00404"></a><span class="lineno"> 404</span>&#160; vstore2(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 1, 0));</div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2, 0));</div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span>&#160;}</div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span>&#160;<span class="comment">/** Computes the first stage of a radix-4 DFT on axis 0.</span></div><div class="line"><a name="l00410"></a><span class="lineno"> 410</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00411"></a><span class="lineno"> 411</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00412"></a><span class="lineno"> 412</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00413"></a><span class="lineno"> 413</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00417"></a><span class="lineno"> 417</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00420"></a><span class="lineno"> 420</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00421"></a><span class="lineno"> 421</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00424"></a><span class="lineno"> 424</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00428"></a><span class="lineno"> 428</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00429"></a><span class="lineno"> 429</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00430"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a67f435359dc175539c7d04d27c4bebb4"> 430</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a67f435359dc175539c7d04d27c4bebb4">fft_radix_4_first_stage_axis_0</a>(</div><div class="line"><a name="l00431"></a><span class="lineno"> 431</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00432"></a><span class="lineno"> 432</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00433"></a><span class="lineno"> 433</span>&#160; ,</div><div class="line"><a name="l00434"></a><span class="lineno"> 434</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00435"></a><span class="lineno"> 435</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00436"></a><span class="lineno"> 436</span>&#160;)</div><div class="line"><a name="l00437"></a><span class="lineno"> 437</span>&#160;{</div><div class="line"><a name="l00438"></a><span class="lineno"> 438</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00439"></a><span class="lineno"> 439</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00440"></a><span class="lineno"> 440</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00441"></a><span class="lineno"> 441</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00442"></a><span class="lineno"> 442</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00443"></a><span class="lineno"> 443</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00444"></a><span class="lineno"> 444</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00445"></a><span class="lineno"> 445</span>&#160;</div><div class="line"><a name="l00446"></a><span class="lineno"> 446</span>&#160; <span class="comment">// Load four complex input values</span></div><div class="line"><a name="l00447"></a><span class="lineno"> 447</span>&#160; float8 data = vload8(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00448"></a><span class="lineno"> 448</span>&#160;</div><div class="line"><a name="l00449"></a><span class="lineno"> 449</span>&#160; <span class="comment">// Compute DFT N = 4</span></div><div class="line"><a name="l00450"></a><span class="lineno"> 450</span>&#160; <a class="code" href="fft_8cl.xhtml#af97e6d43f8b70bcf009d521f8909db25">DFT_4</a>(data.s01, data.s23, data.s45, data.s67);</div><div class="line"><a name="l00451"></a><span class="lineno"> 451</span>&#160;</div><div class="line"><a name="l00452"></a><span class="lineno"> 452</span>&#160; <span class="comment">// Store four complex output values</span></div><div class="line"><a name="l00453"></a><span class="lineno"> 453</span>&#160; vstore8(data, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00454"></a><span class="lineno"> 454</span>&#160;}</div><div class="line"><a name="l00455"></a><span class="lineno"> 455</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00456"></a><span class="lineno"> 456</span>&#160;<span class="comment">/** Computes the first stage of a radix-4 DFT on axis 1.</span></div><div class="line"><a name="l00457"></a><span class="lineno"> 457</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00458"></a><span class="lineno"> 458</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00459"></a><span class="lineno"> 459</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00460"></a><span class="lineno"> 460</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00461"></a><span class="lineno"> 461</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00462"></a><span class="lineno"> 462</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00463"></a><span class="lineno"> 463</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00464"></a><span class="lineno"> 464</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00465"></a><span class="lineno"> 465</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00466"></a><span class="lineno"> 466</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00467"></a><span class="lineno"> 467</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00468"></a><span class="lineno"> 468</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00469"></a><span class="lineno"> 469</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00470"></a><span class="lineno"> 470</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00471"></a><span class="lineno"> 471</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00472"></a><span class="lineno"> 472</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00473"></a><span class="lineno"> 473</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00474"></a><span class="lineno"> 474</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00475"></a><span class="lineno"> 475</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00476"></a><span class="lineno"> 476</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00477"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#aa9b7071c5ccacded46ca51f250807be5"> 477</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#aa9b7071c5ccacded46ca51f250807be5">fft_radix_4_first_stage_axis_1</a>(</div><div class="line"><a name="l00478"></a><span class="lineno"> 478</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00479"></a><span class="lineno"> 479</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00480"></a><span class="lineno"> 480</span>&#160; ,</div><div class="line"><a name="l00481"></a><span class="lineno"> 481</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00482"></a><span class="lineno"> 482</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00483"></a><span class="lineno"> 483</span>&#160;)</div><div class="line"><a name="l00484"></a><span class="lineno"> 484</span>&#160;{</div><div class="line"><a name="l00485"></a><span class="lineno"> 485</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00486"></a><span class="lineno"> 486</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00487"></a><span class="lineno"> 487</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00488"></a><span class="lineno"> 488</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00489"></a><span class="lineno"> 489</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00490"></a><span class="lineno"> 490</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00491"></a><span class="lineno"> 491</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00492"></a><span class="lineno"> 492</span>&#160;</div><div class="line"><a name="l00493"></a><span class="lineno"> 493</span>&#160; <span class="comment">// Load four complex input values</span></div><div class="line"><a name="l00494"></a><span class="lineno"> 494</span>&#160; float2 data0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00495"></a><span class="lineno"> 495</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 1, 0));</div><div class="line"><a name="l00496"></a><span class="lineno"> 496</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2, 0));</div><div class="line"><a name="l00497"></a><span class="lineno"> 497</span>&#160; float2 data3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3, 0));</div><div class="line"><a name="l00498"></a><span class="lineno"> 498</span>&#160;</div><div class="line"><a name="l00499"></a><span class="lineno"> 499</span>&#160; <span class="comment">// Compute DFT N = 4</span></div><div class="line"><a name="l00500"></a><span class="lineno"> 500</span>&#160; <a class="code" href="fft_8cl.xhtml#af97e6d43f8b70bcf009d521f8909db25">DFT_4</a>(data0, data1, data2, data3);</div><div class="line"><a name="l00501"></a><span class="lineno"> 501</span>&#160;</div><div class="line"><a name="l00502"></a><span class="lineno"> 502</span>&#160; <span class="comment">// Store four complex output values</span></div><div class="line"><a name="l00503"></a><span class="lineno"> 503</span>&#160; vstore2(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00504"></a><span class="lineno"> 504</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 1, 0));</div><div class="line"><a name="l00505"></a><span class="lineno"> 505</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2, 0));</div><div class="line"><a name="l00506"></a><span class="lineno"> 506</span>&#160; vstore2(data3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3, 0));</div><div class="line"><a name="l00507"></a><span class="lineno"> 507</span>&#160;}</div><div class="line"><a name="l00508"></a><span class="lineno"> 508</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00509"></a><span class="lineno"> 509</span>&#160;<span class="comment">/** Computes the first stage of a radix-5 DFT on axis 0.</span></div><div class="line"><a name="l00510"></a><span class="lineno"> 510</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00511"></a><span class="lineno"> 511</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00512"></a><span class="lineno"> 512</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00513"></a><span class="lineno"> 513</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00514"></a><span class="lineno"> 514</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00515"></a><span class="lineno"> 515</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00516"></a><span class="lineno"> 516</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00517"></a><span class="lineno"> 517</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00518"></a><span class="lineno"> 518</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00519"></a><span class="lineno"> 519</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00520"></a><span class="lineno"> 520</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00521"></a><span class="lineno"> 521</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00522"></a><span class="lineno"> 522</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00523"></a><span class="lineno"> 523</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00524"></a><span class="lineno"> 524</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00525"></a><span class="lineno"> 525</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00526"></a><span class="lineno"> 526</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00527"></a><span class="lineno"> 527</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00528"></a><span class="lineno"> 528</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00529"></a><span class="lineno"> 529</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00530"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a11794801d4e717905406446d14cd313b"> 530</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a11794801d4e717905406446d14cd313b">fft_radix_5_first_stage_axis_0</a>(</div><div class="line"><a name="l00531"></a><span class="lineno"> 531</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00532"></a><span class="lineno"> 532</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00533"></a><span class="lineno"> 533</span>&#160; ,</div><div class="line"><a name="l00534"></a><span class="lineno"> 534</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00535"></a><span class="lineno"> 535</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00536"></a><span class="lineno"> 536</span>&#160;)</div><div class="line"><a name="l00537"></a><span class="lineno"> 537</span>&#160;{</div><div class="line"><a name="l00538"></a><span class="lineno"> 538</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00539"></a><span class="lineno"> 539</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00540"></a><span class="lineno"> 540</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00541"></a><span class="lineno"> 541</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00542"></a><span class="lineno"> 542</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00543"></a><span class="lineno"> 543</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00544"></a><span class="lineno"> 544</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00545"></a><span class="lineno"> 545</span>&#160;</div><div class="line"><a name="l00546"></a><span class="lineno"> 546</span>&#160; <span class="comment">// Load five complex input values</span></div><div class="line"><a name="l00547"></a><span class="lineno"> 547</span>&#160; float8 data0 = vload8(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00548"></a><span class="lineno"> 548</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 4, 0, 0));</div><div class="line"><a name="l00549"></a><span class="lineno"> 549</span>&#160;</div><div class="line"><a name="l00550"></a><span class="lineno"> 550</span>&#160; <span class="comment">// Compute DFT N = 5</span></div><div class="line"><a name="l00551"></a><span class="lineno"> 551</span>&#160; <a class="code" href="fft_8cl.xhtml#a565f17c6fe3e9462057bb523e0127280">DFT_5</a>(data0.s01, data0.s23, data0.s45, data0.s67, data1.s01);</div><div class="line"><a name="l00552"></a><span class="lineno"> 552</span>&#160;</div><div class="line"><a name="l00553"></a><span class="lineno"> 553</span>&#160; <span class="comment">// Store five complex output values</span></div><div class="line"><a name="l00554"></a><span class="lineno"> 554</span>&#160; vstore8(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00555"></a><span class="lineno"> 555</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 4, 0, 0));</div><div class="line"><a name="l00556"></a><span class="lineno"> 556</span>&#160;}</div><div class="line"><a name="l00557"></a><span class="lineno"> 557</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00558"></a><span class="lineno"> 558</span>&#160;<span class="comment">/** Computes the first stage of a radix-5 DFT on axis 1.</span></div><div class="line"><a name="l00559"></a><span class="lineno"> 559</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00560"></a><span class="lineno"> 560</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00561"></a><span class="lineno"> 561</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00562"></a><span class="lineno"> 562</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00563"></a><span class="lineno"> 563</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00564"></a><span class="lineno"> 564</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00565"></a><span class="lineno"> 565</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00566"></a><span class="lineno"> 566</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00567"></a><span class="lineno"> 567</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00568"></a><span class="lineno"> 568</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00569"></a><span class="lineno"> 569</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00570"></a><span class="lineno"> 570</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00571"></a><span class="lineno"> 571</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00572"></a><span class="lineno"> 572</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00573"></a><span class="lineno"> 573</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00574"></a><span class="lineno"> 574</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00575"></a><span class="lineno"> 575</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00576"></a><span class="lineno"> 576</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00577"></a><span class="lineno"> 577</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00578"></a><span class="lineno"> 578</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00579"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a6f8673fc7472554bb672ef796f6b91b7"> 579</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a6f8673fc7472554bb672ef796f6b91b7">fft_radix_5_first_stage_axis_1</a>(</div><div class="line"><a name="l00580"></a><span class="lineno"> 580</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00581"></a><span class="lineno"> 581</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00582"></a><span class="lineno"> 582</span>&#160; ,</div><div class="line"><a name="l00583"></a><span class="lineno"> 583</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00584"></a><span class="lineno"> 584</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00585"></a><span class="lineno"> 585</span>&#160;)</div><div class="line"><a name="l00586"></a><span class="lineno"> 586</span>&#160;{</div><div class="line"><a name="l00587"></a><span class="lineno"> 587</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00588"></a><span class="lineno"> 588</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00589"></a><span class="lineno"> 589</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00590"></a><span class="lineno"> 590</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00591"></a><span class="lineno"> 591</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00592"></a><span class="lineno"> 592</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00593"></a><span class="lineno"> 593</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00594"></a><span class="lineno"> 594</span>&#160;</div><div class="line"><a name="l00595"></a><span class="lineno"> 595</span>&#160; <span class="comment">// Load five complex input values</span></div><div class="line"><a name="l00596"></a><span class="lineno"> 596</span>&#160; float2 data0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00597"></a><span class="lineno"> 597</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 1, 0));</div><div class="line"><a name="l00598"></a><span class="lineno"> 598</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2, 0));</div><div class="line"><a name="l00599"></a><span class="lineno"> 599</span>&#160; float2 data3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3, 0));</div><div class="line"><a name="l00600"></a><span class="lineno"> 600</span>&#160; float2 data4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 4, 0));</div><div class="line"><a name="l00601"></a><span class="lineno"> 601</span>&#160;</div><div class="line"><a name="l00602"></a><span class="lineno"> 602</span>&#160; <span class="comment">// Compute DFT N = 5</span></div><div class="line"><a name="l00603"></a><span class="lineno"> 603</span>&#160; <a class="code" href="fft_8cl.xhtml#a565f17c6fe3e9462057bb523e0127280">DFT_5</a>(data0, data1, data2, data3, data4);</div><div class="line"><a name="l00604"></a><span class="lineno"> 604</span>&#160;</div><div class="line"><a name="l00605"></a><span class="lineno"> 605</span>&#160; <span class="comment">// Store five complex output values</span></div><div class="line"><a name="l00606"></a><span class="lineno"> 606</span>&#160; vstore2(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00607"></a><span class="lineno"> 607</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 1, 0));</div><div class="line"><a name="l00608"></a><span class="lineno"> 608</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2, 0));</div><div class="line"><a name="l00609"></a><span class="lineno"> 609</span>&#160; vstore2(data3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3, 0));</div><div class="line"><a name="l00610"></a><span class="lineno"> 610</span>&#160; vstore2(data4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 4, 0));</div><div class="line"><a name="l00611"></a><span class="lineno"> 611</span>&#160;}</div><div class="line"><a name="l00612"></a><span class="lineno"> 612</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00613"></a><span class="lineno"> 613</span>&#160;<span class="comment">/** Computes the first stage of a radix-7 DFT on axis 0.</span></div><div class="line"><a name="l00614"></a><span class="lineno"> 614</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00615"></a><span class="lineno"> 615</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00616"></a><span class="lineno"> 616</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00617"></a><span class="lineno"> 617</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00618"></a><span class="lineno"> 618</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00619"></a><span class="lineno"> 619</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00620"></a><span class="lineno"> 620</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00621"></a><span class="lineno"> 621</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00622"></a><span class="lineno"> 622</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00623"></a><span class="lineno"> 623</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00624"></a><span class="lineno"> 624</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00625"></a><span class="lineno"> 625</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00626"></a><span class="lineno"> 626</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00627"></a><span class="lineno"> 627</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00628"></a><span class="lineno"> 628</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00629"></a><span class="lineno"> 629</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00630"></a><span class="lineno"> 630</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00631"></a><span class="lineno"> 631</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00632"></a><span class="lineno"> 632</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00633"></a><span class="lineno"> 633</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00634"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#aba8f7b960aa49b876ac266447a78c416"> 634</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#aba8f7b960aa49b876ac266447a78c416">fft_radix_7_first_stage_axis_0</a>(</div><div class="line"><a name="l00635"></a><span class="lineno"> 635</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00636"></a><span class="lineno"> 636</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00637"></a><span class="lineno"> 637</span>&#160; ,</div><div class="line"><a name="l00638"></a><span class="lineno"> 638</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00639"></a><span class="lineno"> 639</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00640"></a><span class="lineno"> 640</span>&#160;)</div><div class="line"><a name="l00641"></a><span class="lineno"> 641</span>&#160;{</div><div class="line"><a name="l00642"></a><span class="lineno"> 642</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00643"></a><span class="lineno"> 643</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00644"></a><span class="lineno"> 644</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00645"></a><span class="lineno"> 645</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00646"></a><span class="lineno"> 646</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00647"></a><span class="lineno"> 647</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00648"></a><span class="lineno"> 648</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00649"></a><span class="lineno"> 649</span>&#160;</div><div class="line"><a name="l00650"></a><span class="lineno"> 650</span>&#160; <span class="comment">// Load seven complex input values</span></div><div class="line"><a name="l00651"></a><span class="lineno"> 651</span>&#160; float8 data0 = vload8(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00652"></a><span class="lineno"> 652</span>&#160; float4 data1 = vload4(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 4, 0, 0));</div><div class="line"><a name="l00653"></a><span class="lineno"> 653</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 6, 0, 0));</div><div class="line"><a name="l00654"></a><span class="lineno"> 654</span>&#160;</div><div class="line"><a name="l00655"></a><span class="lineno"> 655</span>&#160; <span class="comment">// Compute DFT N = 7</span></div><div class="line"><a name="l00656"></a><span class="lineno"> 656</span>&#160; <a class="code" href="fft_8cl.xhtml#ad04a4028658f997aaca067742c2e8a49">DFT_7</a>(data0.s01, data0.s23, data0.s45, data0.s67, data1.s01, data1.s23, data2.s01);</div><div class="line"><a name="l00657"></a><span class="lineno"> 657</span>&#160;</div><div class="line"><a name="l00658"></a><span class="lineno"> 658</span>&#160; <span class="comment">// Store seven complex output values</span></div><div class="line"><a name="l00659"></a><span class="lineno"> 659</span>&#160; vstore8(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00660"></a><span class="lineno"> 660</span>&#160; vstore4(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 4, 0, 0));</div><div class="line"><a name="l00661"></a><span class="lineno"> 661</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 6, 0, 0));</div><div class="line"><a name="l00662"></a><span class="lineno"> 662</span>&#160;}</div><div class="line"><a name="l00663"></a><span class="lineno"> 663</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00664"></a><span class="lineno"> 664</span>&#160;<span class="comment">/** Computes the first stage of a radix-7 DFT on axis 1.</span></div><div class="line"><a name="l00665"></a><span class="lineno"> 665</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00666"></a><span class="lineno"> 666</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00667"></a><span class="lineno"> 667</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00668"></a><span class="lineno"> 668</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00669"></a><span class="lineno"> 669</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00670"></a><span class="lineno"> 670</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00671"></a><span class="lineno"> 671</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00672"></a><span class="lineno"> 672</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00673"></a><span class="lineno"> 673</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00674"></a><span class="lineno"> 674</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00675"></a><span class="lineno"> 675</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00676"></a><span class="lineno"> 676</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00677"></a><span class="lineno"> 677</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00678"></a><span class="lineno"> 678</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00679"></a><span class="lineno"> 679</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00680"></a><span class="lineno"> 680</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00681"></a><span class="lineno"> 681</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00682"></a><span class="lineno"> 682</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00683"></a><span class="lineno"> 683</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00684"></a><span class="lineno"> 684</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00685"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a3f65de85962b99e35c4bd9abcbc7e660"> 685</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a3f65de85962b99e35c4bd9abcbc7e660">fft_radix_7_first_stage_axis_1</a>(</div><div class="line"><a name="l00686"></a><span class="lineno"> 686</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00687"></a><span class="lineno"> 687</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00688"></a><span class="lineno"> 688</span>&#160; ,</div><div class="line"><a name="l00689"></a><span class="lineno"> 689</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00690"></a><span class="lineno"> 690</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00691"></a><span class="lineno"> 691</span>&#160;)</div><div class="line"><a name="l00692"></a><span class="lineno"> 692</span>&#160;{</div><div class="line"><a name="l00693"></a><span class="lineno"> 693</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00694"></a><span class="lineno"> 694</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00695"></a><span class="lineno"> 695</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00696"></a><span class="lineno"> 696</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00697"></a><span class="lineno"> 697</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00698"></a><span class="lineno"> 698</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00699"></a><span class="lineno"> 699</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00700"></a><span class="lineno"> 700</span>&#160;</div><div class="line"><a name="l00701"></a><span class="lineno"> 701</span>&#160; <span class="comment">// Load seven complex input values</span></div><div class="line"><a name="l00702"></a><span class="lineno"> 702</span>&#160; float2 data0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00703"></a><span class="lineno"> 703</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 1, 0));</div><div class="line"><a name="l00704"></a><span class="lineno"> 704</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2, 0));</div><div class="line"><a name="l00705"></a><span class="lineno"> 705</span>&#160; float2 data3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3, 0));</div><div class="line"><a name="l00706"></a><span class="lineno"> 706</span>&#160; float2 data4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 4, 0));</div><div class="line"><a name="l00707"></a><span class="lineno"> 707</span>&#160; float2 data5 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 5, 0));</div><div class="line"><a name="l00708"></a><span class="lineno"> 708</span>&#160; float2 data6 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 6, 0));</div><div class="line"><a name="l00709"></a><span class="lineno"> 709</span>&#160;</div><div class="line"><a name="l00710"></a><span class="lineno"> 710</span>&#160; <span class="comment">// Compute DFT N = 7</span></div><div class="line"><a name="l00711"></a><span class="lineno"> 711</span>&#160; <a class="code" href="fft_8cl.xhtml#ad04a4028658f997aaca067742c2e8a49">DFT_7</a>(data0, data1, data2, data3, data4, data5, data6);</div><div class="line"><a name="l00712"></a><span class="lineno"> 712</span>&#160;</div><div class="line"><a name="l00713"></a><span class="lineno"> 713</span>&#160; <span class="comment">// Store seven complex output values</span></div><div class="line"><a name="l00714"></a><span class="lineno"> 714</span>&#160; vstore2(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00715"></a><span class="lineno"> 715</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 1, 0));</div><div class="line"><a name="l00716"></a><span class="lineno"> 716</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2, 0));</div><div class="line"><a name="l00717"></a><span class="lineno"> 717</span>&#160; vstore2(data3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3, 0));</div><div class="line"><a name="l00718"></a><span class="lineno"> 718</span>&#160; vstore2(data4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 4, 0));</div><div class="line"><a name="l00719"></a><span class="lineno"> 719</span>&#160; vstore2(data5, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 5, 0));</div><div class="line"><a name="l00720"></a><span class="lineno"> 720</span>&#160; vstore2(data6, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 6, 0));</div><div class="line"><a name="l00721"></a><span class="lineno"> 721</span>&#160;}</div><div class="line"><a name="l00722"></a><span class="lineno"> 722</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00723"></a><span class="lineno"> 723</span>&#160;<span class="comment">/** Computes the first stage of a radix-8 DFT on axis 0.</span></div><div class="line"><a name="l00724"></a><span class="lineno"> 724</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00725"></a><span class="lineno"> 725</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00726"></a><span class="lineno"> 726</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00727"></a><span class="lineno"> 727</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00728"></a><span class="lineno"> 728</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00729"></a><span class="lineno"> 729</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00730"></a><span class="lineno"> 730</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00731"></a><span class="lineno"> 731</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00732"></a><span class="lineno"> 732</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00733"></a><span class="lineno"> 733</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00734"></a><span class="lineno"> 734</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00735"></a><span class="lineno"> 735</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00736"></a><span class="lineno"> 736</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00737"></a><span class="lineno"> 737</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00738"></a><span class="lineno"> 738</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00739"></a><span class="lineno"> 739</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00740"></a><span class="lineno"> 740</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00741"></a><span class="lineno"> 741</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00742"></a><span class="lineno"> 742</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00743"></a><span class="lineno"> 743</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00744"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a008d11872b90493790f933f82c9f05b5"> 744</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a008d11872b90493790f933f82c9f05b5">fft_radix_8_first_stage_axis_0</a>(</div><div class="line"><a name="l00745"></a><span class="lineno"> 745</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00746"></a><span class="lineno"> 746</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00747"></a><span class="lineno"> 747</span>&#160; ,</div><div class="line"><a name="l00748"></a><span class="lineno"> 748</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00749"></a><span class="lineno"> 749</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00750"></a><span class="lineno"> 750</span>&#160;)</div><div class="line"><a name="l00751"></a><span class="lineno"> 751</span>&#160;{</div><div class="line"><a name="l00752"></a><span class="lineno"> 752</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00753"></a><span class="lineno"> 753</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00754"></a><span class="lineno"> 754</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00755"></a><span class="lineno"> 755</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00756"></a><span class="lineno"> 756</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00757"></a><span class="lineno"> 757</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00758"></a><span class="lineno"> 758</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00759"></a><span class="lineno"> 759</span>&#160;</div><div class="line"><a name="l00760"></a><span class="lineno"> 760</span>&#160; <span class="comment">// Load eight complex input values</span></div><div class="line"><a name="l00761"></a><span class="lineno"> 761</span>&#160; float16 data = vload16(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00762"></a><span class="lineno"> 762</span>&#160;</div><div class="line"><a name="l00763"></a><span class="lineno"> 763</span>&#160; <span class="comment">// Compute DFT N = 8</span></div><div class="line"><a name="l00764"></a><span class="lineno"> 764</span>&#160; <a class="code" href="fft_8cl.xhtml#a4c4ce3f10939dd4237d0adee00086a53">DFT_8</a>(data.s01, data.s23, data.s45, data.s67, data.s89, data.sAB, data.sCD, data.sEF);</div><div class="line"><a name="l00765"></a><span class="lineno"> 765</span>&#160;</div><div class="line"><a name="l00766"></a><span class="lineno"> 766</span>&#160; <span class="comment">// Store eight complex output values</span></div><div class="line"><a name="l00767"></a><span class="lineno"> 767</span>&#160; vstore16(data, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00768"></a><span class="lineno"> 768</span>&#160;}</div><div class="line"><a name="l00769"></a><span class="lineno"> 769</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00770"></a><span class="lineno"> 770</span>&#160;<span class="comment">/** Computes the first stage of a radix-8 DFT on axis 1.</span></div><div class="line"><a name="l00771"></a><span class="lineno"> 771</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00772"></a><span class="lineno"> 772</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00773"></a><span class="lineno"> 773</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00774"></a><span class="lineno"> 774</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00775"></a><span class="lineno"> 775</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00776"></a><span class="lineno"> 776</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00777"></a><span class="lineno"> 777</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00778"></a><span class="lineno"> 778</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00779"></a><span class="lineno"> 779</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00780"></a><span class="lineno"> 780</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00781"></a><span class="lineno"> 781</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00782"></a><span class="lineno"> 782</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00783"></a><span class="lineno"> 783</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00784"></a><span class="lineno"> 784</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00785"></a><span class="lineno"> 785</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00786"></a><span class="lineno"> 786</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00787"></a><span class="lineno"> 787</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00788"></a><span class="lineno"> 788</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00789"></a><span class="lineno"> 789</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00790"></a><span class="lineno"> 790</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00791"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a76f788853ef70fc0220ae4bb55db6d11"> 791</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a76f788853ef70fc0220ae4bb55db6d11">fft_radix_8_first_stage_axis_1</a>(</div><div class="line"><a name="l00792"></a><span class="lineno"> 792</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00793"></a><span class="lineno"> 793</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00794"></a><span class="lineno"> 794</span>&#160; ,</div><div class="line"><a name="l00795"></a><span class="lineno"> 795</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00796"></a><span class="lineno"> 796</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00797"></a><span class="lineno"> 797</span>&#160;)</div><div class="line"><a name="l00798"></a><span class="lineno"> 798</span>&#160;{</div><div class="line"><a name="l00799"></a><span class="lineno"> 799</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00800"></a><span class="lineno"> 800</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00801"></a><span class="lineno"> 801</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00802"></a><span class="lineno"> 802</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00803"></a><span class="lineno"> 803</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00804"></a><span class="lineno"> 804</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(output);</div><div class="line"><a name="l00805"></a><span class="lineno"> 805</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00806"></a><span class="lineno"> 806</span>&#160;</div><div class="line"><a name="l00807"></a><span class="lineno"> 807</span>&#160; <span class="comment">// Load eight complex input values</span></div><div class="line"><a name="l00808"></a><span class="lineno"> 808</span>&#160; float2 data0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00809"></a><span class="lineno"> 809</span>&#160; float2 data1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 1, 0));</div><div class="line"><a name="l00810"></a><span class="lineno"> 810</span>&#160; float2 data2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2, 0));</div><div class="line"><a name="l00811"></a><span class="lineno"> 811</span>&#160; float2 data3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3, 0));</div><div class="line"><a name="l00812"></a><span class="lineno"> 812</span>&#160; float2 data4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 4, 0));</div><div class="line"><a name="l00813"></a><span class="lineno"> 813</span>&#160; float2 data5 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 5, 0));</div><div class="line"><a name="l00814"></a><span class="lineno"> 814</span>&#160; float2 data6 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 6, 0));</div><div class="line"><a name="l00815"></a><span class="lineno"> 815</span>&#160; float2 data7 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 7, 0));</div><div class="line"><a name="l00816"></a><span class="lineno"> 816</span>&#160;</div><div class="line"><a name="l00817"></a><span class="lineno"> 817</span>&#160; <span class="comment">// Compute DFT N = 8</span></div><div class="line"><a name="l00818"></a><span class="lineno"> 818</span>&#160; <a class="code" href="fft_8cl.xhtml#a4c4ce3f10939dd4237d0adee00086a53">DFT_8</a>(data0, data1, data2, data3, data4, data5, data6, data7);</div><div class="line"><a name="l00819"></a><span class="lineno"> 819</span>&#160;</div><div class="line"><a name="l00820"></a><span class="lineno"> 820</span>&#160; <span class="comment">// Store eight complex output values</span></div><div class="line"><a name="l00821"></a><span class="lineno"> 821</span>&#160; vstore2(data0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00822"></a><span class="lineno"> 822</span>&#160; vstore2(data1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 1, 0));</div><div class="line"><a name="l00823"></a><span class="lineno"> 823</span>&#160; vstore2(data2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2, 0));</div><div class="line"><a name="l00824"></a><span class="lineno"> 824</span>&#160; vstore2(data3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3, 0));</div><div class="line"><a name="l00825"></a><span class="lineno"> 825</span>&#160; vstore2(data4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 4, 0));</div><div class="line"><a name="l00826"></a><span class="lineno"> 826</span>&#160; vstore2(data5, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 5, 0));</div><div class="line"><a name="l00827"></a><span class="lineno"> 827</span>&#160; vstore2(data6, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 6, 0));</div><div class="line"><a name="l00828"></a><span class="lineno"> 828</span>&#160; vstore2(data7, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 7, 0));</div><div class="line"><a name="l00829"></a><span class="lineno"> 829</span>&#160;}</div><div class="line"><a name="l00830"></a><span class="lineno"> 830</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00831"></a><span class="lineno"> 831</span>&#160;<span class="comment">/** Computes a stage of a radix-2 FFT on axis 0.</span></div><div class="line"><a name="l00832"></a><span class="lineno"> 832</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00833"></a><span class="lineno"> 833</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00834"></a><span class="lineno"> 834</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00835"></a><span class="lineno"> 835</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00836"></a><span class="lineno"> 836</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00837"></a><span class="lineno"> 837</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00838"></a><span class="lineno"> 838</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00839"></a><span class="lineno"> 839</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00840"></a><span class="lineno"> 840</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00841"></a><span class="lineno"> 841</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00842"></a><span class="lineno"> 842</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00843"></a><span class="lineno"> 843</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00844"></a><span class="lineno"> 844</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00845"></a><span class="lineno"> 845</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00846"></a><span class="lineno"> 846</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00847"></a><span class="lineno"> 847</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00848"></a><span class="lineno"> 848</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00849"></a><span class="lineno"> 849</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00850"></a><span class="lineno"> 850</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00851"></a><span class="lineno"> 851</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l00852"></a><span class="lineno"> 852</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l00853"></a><span class="lineno"> 853</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l00854"></a><span class="lineno"> 854</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00855"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a6d2d172d9e177ed439b6f6ddc0785b86"> 855</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a6d2d172d9e177ed439b6f6ddc0785b86">fft_radix_2_axis_0</a>(</div><div class="line"><a name="l00856"></a><span class="lineno"> 856</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00857"></a><span class="lineno"> 857</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00858"></a><span class="lineno"> 858</span>&#160; ,</div><div class="line"><a name="l00859"></a><span class="lineno"> 859</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00860"></a><span class="lineno"> 860</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00861"></a><span class="lineno"> 861</span>&#160; ,</div><div class="line"><a name="l00862"></a><span class="lineno"> 862</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l00863"></a><span class="lineno"> 863</span>&#160;{</div><div class="line"><a name="l00864"></a><span class="lineno"> 864</span>&#160; <span class="comment">// Each work-item computes a single radix-2</span></div><div class="line"><a name="l00865"></a><span class="lineno"> 865</span>&#160; uint kx = get_global_id(0);</div><div class="line"><a name="l00866"></a><span class="lineno"> 866</span>&#160;</div><div class="line"><a name="l00867"></a><span class="lineno"> 867</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l00868"></a><span class="lineno"> 868</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l00869"></a><span class="lineno"> 869</span>&#160;</div><div class="line"><a name="l00870"></a><span class="lineno"> 870</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l00871"></a><span class="lineno"> 871</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l00872"></a><span class="lineno"> 872</span>&#160;</div><div class="line"><a name="l00873"></a><span class="lineno"> 873</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00874"></a><span class="lineno"> 874</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00875"></a><span class="lineno"> 875</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + get_global_id(1) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l00876"></a><span class="lineno"> 876</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00877"></a><span class="lineno"> 877</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00878"></a><span class="lineno"> 878</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00879"></a><span class="lineno"> 879</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l00880"></a><span class="lineno"> 880</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += n * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + get_global_id(1) * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l00881"></a><span class="lineno"> 881</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00882"></a><span class="lineno"> 882</span>&#160;</div><div class="line"><a name="l00883"></a><span class="lineno"> 883</span>&#160; <span class="comment">// Load two complex input values</span></div><div class="line"><a name="l00884"></a><span class="lineno"> 884</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00885"></a><span class="lineno"> 885</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, Nx, 0, 0));</div><div class="line"><a name="l00886"></a><span class="lineno"> 886</span>&#160;</div><div class="line"><a name="l00887"></a><span class="lineno"> 887</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l00888"></a><span class="lineno"> 888</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l00889"></a><span class="lineno"> 889</span>&#160;</div><div class="line"><a name="l00890"></a><span class="lineno"> 890</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l00891"></a><span class="lineno"> 891</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l00892"></a><span class="lineno"> 892</span>&#160;</div><div class="line"><a name="l00893"></a><span class="lineno"> 893</span>&#160; <span class="comment">// Compute DFT N = 2</span></div><div class="line"><a name="l00894"></a><span class="lineno"> 894</span>&#160; <a class="code" href="fft_8cl.xhtml#a5a63ca1d5404d67d13382a90cfc9b6c3">DFT_2</a>(c0, c1);</div><div class="line"><a name="l00895"></a><span class="lineno"> 895</span>&#160;</div><div class="line"><a name="l00896"></a><span class="lineno"> 896</span>&#160; <span class="comment">// Store two complex output values</span></div><div class="line"><a name="l00897"></a><span class="lineno"> 897</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00898"></a><span class="lineno"> 898</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, Nx, 0, 0));</div><div class="line"><a name="l00899"></a><span class="lineno"> 899</span>&#160;}</div><div class="line"><a name="l00900"></a><span class="lineno"> 900</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00901"></a><span class="lineno"> 901</span>&#160;<span class="comment">/** Computes a stage of a radix-2 FFT on axis 1.</span></div><div class="line"><a name="l00902"></a><span class="lineno"> 902</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00903"></a><span class="lineno"> 903</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00904"></a><span class="lineno"> 904</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00905"></a><span class="lineno"> 905</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00906"></a><span class="lineno"> 906</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00907"></a><span class="lineno"> 907</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00908"></a><span class="lineno"> 908</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00909"></a><span class="lineno"> 909</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00910"></a><span class="lineno"> 910</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00911"></a><span class="lineno"> 911</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00912"></a><span class="lineno"> 912</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00913"></a><span class="lineno"> 913</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00914"></a><span class="lineno"> 914</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00915"></a><span class="lineno"> 915</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00916"></a><span class="lineno"> 916</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00917"></a><span class="lineno"> 917</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00918"></a><span class="lineno"> 918</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00919"></a><span class="lineno"> 919</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00920"></a><span class="lineno"> 920</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00921"></a><span class="lineno"> 921</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l00922"></a><span class="lineno"> 922</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l00923"></a><span class="lineno"> 923</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l00924"></a><span class="lineno"> 924</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00925"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ad4c7557777731327f741ef848e2b28c2"> 925</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#ad4c7557777731327f741ef848e2b28c2">fft_radix_2_axis_1</a>(</div><div class="line"><a name="l00926"></a><span class="lineno"> 926</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00927"></a><span class="lineno"> 927</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00928"></a><span class="lineno"> 928</span>&#160; ,</div><div class="line"><a name="l00929"></a><span class="lineno"> 929</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l00930"></a><span class="lineno"> 930</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00931"></a><span class="lineno"> 931</span>&#160; ,</div><div class="line"><a name="l00932"></a><span class="lineno"> 932</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l00933"></a><span class="lineno"> 933</span>&#160;{</div><div class="line"><a name="l00934"></a><span class="lineno"> 934</span>&#160; <span class="comment">// Each work-item computes a single radix-2</span></div><div class="line"><a name="l00935"></a><span class="lineno"> 935</span>&#160; uint kx = get_global_id(1);</div><div class="line"><a name="l00936"></a><span class="lineno"> 936</span>&#160;</div><div class="line"><a name="l00937"></a><span class="lineno"> 937</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l00938"></a><span class="lineno"> 938</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l00939"></a><span class="lineno"> 939</span>&#160;</div><div class="line"><a name="l00940"></a><span class="lineno"> 940</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l00941"></a><span class="lineno"> 941</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l00942"></a><span class="lineno"> 942</span>&#160;</div><div class="line"><a name="l00943"></a><span class="lineno"> 943</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l00944"></a><span class="lineno"> 944</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l00945"></a><span class="lineno"> 945</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += get_global_id(0) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l00946"></a><span class="lineno"> 946</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00947"></a><span class="lineno"> 947</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00948"></a><span class="lineno"> 948</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00949"></a><span class="lineno"> 949</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l00950"></a><span class="lineno"> 950</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += get_global_id(0) * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + n * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l00951"></a><span class="lineno"> 951</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00952"></a><span class="lineno"> 952</span>&#160;</div><div class="line"><a name="l00953"></a><span class="lineno"> 953</span>&#160; <span class="comment">// Load two complex input values</span></div><div class="line"><a name="l00954"></a><span class="lineno"> 954</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l00955"></a><span class="lineno"> 955</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, Nx, 0));</div><div class="line"><a name="l00956"></a><span class="lineno"> 956</span>&#160;</div><div class="line"><a name="l00957"></a><span class="lineno"> 957</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l00958"></a><span class="lineno"> 958</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l00959"></a><span class="lineno"> 959</span>&#160;</div><div class="line"><a name="l00960"></a><span class="lineno"> 960</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l00961"></a><span class="lineno"> 961</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l00962"></a><span class="lineno"> 962</span>&#160;</div><div class="line"><a name="l00963"></a><span class="lineno"> 963</span>&#160; <span class="comment">// Compute DFT N = 2</span></div><div class="line"><a name="l00964"></a><span class="lineno"> 964</span>&#160; <a class="code" href="fft_8cl.xhtml#a5a63ca1d5404d67d13382a90cfc9b6c3">DFT_2</a>(c0, c1);</div><div class="line"><a name="l00965"></a><span class="lineno"> 965</span>&#160;</div><div class="line"><a name="l00966"></a><span class="lineno"> 966</span>&#160; <span class="comment">// Store two complex output values</span></div><div class="line"><a name="l00967"></a><span class="lineno"> 967</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00968"></a><span class="lineno"> 968</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, Nx, 0));</div><div class="line"><a name="l00969"></a><span class="lineno"> 969</span>&#160;}</div><div class="line"><a name="l00970"></a><span class="lineno"> 970</span>&#160;<span class="comment"></span></div><div class="line"><a name="l00971"></a><span class="lineno"> 971</span>&#160;<span class="comment">/** Computes a stage of a radix-3 FFT on axis 0.</span></div><div class="line"><a name="l00972"></a><span class="lineno"> 972</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00973"></a><span class="lineno"> 973</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00974"></a><span class="lineno"> 974</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00975"></a><span class="lineno"> 975</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l00976"></a><span class="lineno"> 976</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00977"></a><span class="lineno"> 977</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00978"></a><span class="lineno"> 978</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00979"></a><span class="lineno"> 979</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00980"></a><span class="lineno"> 980</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00981"></a><span class="lineno"> 981</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00982"></a><span class="lineno"> 982</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00983"></a><span class="lineno"> 983</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00984"></a><span class="lineno"> 984</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00985"></a><span class="lineno"> 985</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00986"></a><span class="lineno"> 986</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00987"></a><span class="lineno"> 987</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00988"></a><span class="lineno"> 988</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00989"></a><span class="lineno"> 989</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00990"></a><span class="lineno"> 990</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00991"></a><span class="lineno"> 991</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l00992"></a><span class="lineno"> 992</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l00993"></a><span class="lineno"> 993</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l00994"></a><span class="lineno"> 994</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l00995"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#af5d6a654bacf45355b1dcaacc6441691"> 995</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#af5d6a654bacf45355b1dcaacc6441691">fft_radix_3_axis_0</a>(</div><div class="line"><a name="l00996"></a><span class="lineno"> 996</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l00997"></a><span class="lineno"> 997</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l00998"></a><span class="lineno"> 998</span>&#160; ,</div><div class="line"><a name="l00999"></a><span class="lineno"> 999</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01000"></a><span class="lineno"> 1000</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01001"></a><span class="lineno"> 1001</span>&#160; ,</div><div class="line"><a name="l01002"></a><span class="lineno"> 1002</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01003"></a><span class="lineno"> 1003</span>&#160;{</div><div class="line"><a name="l01004"></a><span class="lineno"> 1004</span>&#160; <span class="comment">// Each work-item computes a single radix-3</span></div><div class="line"><a name="l01005"></a><span class="lineno"> 1005</span>&#160; uint kx = get_global_id(0);</div><div class="line"><a name="l01006"></a><span class="lineno"> 1006</span>&#160;</div><div class="line"><a name="l01007"></a><span class="lineno"> 1007</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01008"></a><span class="lineno"> 1008</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01009"></a><span class="lineno"> 1009</span>&#160;</div><div class="line"><a name="l01010"></a><span class="lineno"> 1010</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01011"></a><span class="lineno"> 1011</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01012"></a><span class="lineno"> 1012</span>&#160;</div><div class="line"><a name="l01013"></a><span class="lineno"> 1013</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01014"></a><span class="lineno"> 1014</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01015"></a><span class="lineno"> 1015</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + get_global_id(1) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01016"></a><span class="lineno"> 1016</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01017"></a><span class="lineno"> 1017</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01018"></a><span class="lineno"> 1018</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01019"></a><span class="lineno"> 1019</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01020"></a><span class="lineno"> 1020</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += n * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + get_global_id(1) * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01021"></a><span class="lineno"> 1021</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01022"></a><span class="lineno"> 1022</span>&#160;</div><div class="line"><a name="l01023"></a><span class="lineno"> 1023</span>&#160; <span class="comment">// Load three complex input values</span></div><div class="line"><a name="l01024"></a><span class="lineno"> 1024</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01025"></a><span class="lineno"> 1025</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, Nx, 0, 0));</div><div class="line"><a name="l01026"></a><span class="lineno"> 1026</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 2 * Nx, 0, 0));</div><div class="line"><a name="l01027"></a><span class="lineno"> 1027</span>&#160;</div><div class="line"><a name="l01028"></a><span class="lineno"> 1028</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01029"></a><span class="lineno"> 1029</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01030"></a><span class="lineno"> 1030</span>&#160;</div><div class="line"><a name="l01031"></a><span class="lineno"> 1031</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01032"></a><span class="lineno"> 1032</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01033"></a><span class="lineno"> 1033</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01034"></a><span class="lineno"> 1034</span>&#160;</div><div class="line"><a name="l01035"></a><span class="lineno"> 1035</span>&#160; <span class="comment">// Compute DFT N = 3</span></div><div class="line"><a name="l01036"></a><span class="lineno"> 1036</span>&#160; <a class="code" href="fft_8cl.xhtml#ac6ec77d2e41d56919c14c1483eee94ac">DFT_3</a>(c0, c1, c2);</div><div class="line"><a name="l01037"></a><span class="lineno"> 1037</span>&#160;</div><div class="line"><a name="l01038"></a><span class="lineno"> 1038</span>&#160; <span class="comment">// Store three complex output values</span></div><div class="line"><a name="l01039"></a><span class="lineno"> 1039</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01040"></a><span class="lineno"> 1040</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, Nx, 0, 0));</div><div class="line"><a name="l01041"></a><span class="lineno"> 1041</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 2 * Nx, 0, 0));</div><div class="line"><a name="l01042"></a><span class="lineno"> 1042</span>&#160;}</div><div class="line"><a name="l01043"></a><span class="lineno"> 1043</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01044"></a><span class="lineno"> 1044</span>&#160;<span class="comment">/** Computes a stage of a radix-3 FFT on axis 1.</span></div><div class="line"><a name="l01045"></a><span class="lineno"> 1045</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01046"></a><span class="lineno"> 1046</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01047"></a><span class="lineno"> 1047</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01048"></a><span class="lineno"> 1048</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01049"></a><span class="lineno"> 1049</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01050"></a><span class="lineno"> 1050</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01051"></a><span class="lineno"> 1051</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01052"></a><span class="lineno"> 1052</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01053"></a><span class="lineno"> 1053</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01054"></a><span class="lineno"> 1054</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01055"></a><span class="lineno"> 1055</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01056"></a><span class="lineno"> 1056</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01057"></a><span class="lineno"> 1057</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01058"></a><span class="lineno"> 1058</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01059"></a><span class="lineno"> 1059</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01060"></a><span class="lineno"> 1060</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01061"></a><span class="lineno"> 1061</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01062"></a><span class="lineno"> 1062</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01063"></a><span class="lineno"> 1063</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01064"></a><span class="lineno"> 1064</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01065"></a><span class="lineno"> 1065</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01066"></a><span class="lineno"> 1066</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01067"></a><span class="lineno"> 1067</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01068"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a6c378af2ec36adec6dd88b961151a057"> 1068</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a6c378af2ec36adec6dd88b961151a057">fft_radix_3_axis_1</a>(</div><div class="line"><a name="l01069"></a><span class="lineno"> 1069</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01070"></a><span class="lineno"> 1070</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01071"></a><span class="lineno"> 1071</span>&#160; ,</div><div class="line"><a name="l01072"></a><span class="lineno"> 1072</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01073"></a><span class="lineno"> 1073</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01074"></a><span class="lineno"> 1074</span>&#160; ,</div><div class="line"><a name="l01075"></a><span class="lineno"> 1075</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01076"></a><span class="lineno"> 1076</span>&#160;{</div><div class="line"><a name="l01077"></a><span class="lineno"> 1077</span>&#160; <span class="comment">// Each work-item computes a single radix-3</span></div><div class="line"><a name="l01078"></a><span class="lineno"> 1078</span>&#160; uint kx = get_global_id(1);</div><div class="line"><a name="l01079"></a><span class="lineno"> 1079</span>&#160;</div><div class="line"><a name="l01080"></a><span class="lineno"> 1080</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01081"></a><span class="lineno"> 1081</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01082"></a><span class="lineno"> 1082</span>&#160;</div><div class="line"><a name="l01083"></a><span class="lineno"> 1083</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01084"></a><span class="lineno"> 1084</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01085"></a><span class="lineno"> 1085</span>&#160;</div><div class="line"><a name="l01086"></a><span class="lineno"> 1086</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01087"></a><span class="lineno"> 1087</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01088"></a><span class="lineno"> 1088</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += get_global_id(0) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01089"></a><span class="lineno"> 1089</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01090"></a><span class="lineno"> 1090</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01091"></a><span class="lineno"> 1091</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01092"></a><span class="lineno"> 1092</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01093"></a><span class="lineno"> 1093</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += get_global_id(0) * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + n * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01094"></a><span class="lineno"> 1094</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01095"></a><span class="lineno"> 1095</span>&#160;</div><div class="line"><a name="l01096"></a><span class="lineno"> 1096</span>&#160; <span class="comment">// Load three complex input values</span></div><div class="line"><a name="l01097"></a><span class="lineno"> 1097</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01098"></a><span class="lineno"> 1098</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, Nx, 0));</div><div class="line"><a name="l01099"></a><span class="lineno"> 1099</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2 * Nx, 0));</div><div class="line"><a name="l01100"></a><span class="lineno"> 1100</span>&#160;</div><div class="line"><a name="l01101"></a><span class="lineno"> 1101</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01102"></a><span class="lineno"> 1102</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01103"></a><span class="lineno"> 1103</span>&#160;</div><div class="line"><a name="l01104"></a><span class="lineno"> 1104</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01105"></a><span class="lineno"> 1105</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01106"></a><span class="lineno"> 1106</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01107"></a><span class="lineno"> 1107</span>&#160;</div><div class="line"><a name="l01108"></a><span class="lineno"> 1108</span>&#160; <span class="comment">// Compute DFT N = 3</span></div><div class="line"><a name="l01109"></a><span class="lineno"> 1109</span>&#160; <a class="code" href="fft_8cl.xhtml#ac6ec77d2e41d56919c14c1483eee94ac">DFT_3</a>(c0, c1, c2);</div><div class="line"><a name="l01110"></a><span class="lineno"> 1110</span>&#160;</div><div class="line"><a name="l01111"></a><span class="lineno"> 1111</span>&#160; <span class="comment">// Store three complex output values</span></div><div class="line"><a name="l01112"></a><span class="lineno"> 1112</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01113"></a><span class="lineno"> 1113</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, Nx, 0));</div><div class="line"><a name="l01114"></a><span class="lineno"> 1114</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2 * Nx, 0));</div><div class="line"><a name="l01115"></a><span class="lineno"> 1115</span>&#160;}</div><div class="line"><a name="l01116"></a><span class="lineno"> 1116</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01117"></a><span class="lineno"> 1117</span>&#160;<span class="comment">/** Computes a stage of a radix-4 FFT on axis 0.</span></div><div class="line"><a name="l01118"></a><span class="lineno"> 1118</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01119"></a><span class="lineno"> 1119</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01120"></a><span class="lineno"> 1120</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01121"></a><span class="lineno"> 1121</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01122"></a><span class="lineno"> 1122</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01123"></a><span class="lineno"> 1123</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01124"></a><span class="lineno"> 1124</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01125"></a><span class="lineno"> 1125</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01126"></a><span class="lineno"> 1126</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01127"></a><span class="lineno"> 1127</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01128"></a><span class="lineno"> 1128</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01129"></a><span class="lineno"> 1129</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01130"></a><span class="lineno"> 1130</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01131"></a><span class="lineno"> 1131</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01132"></a><span class="lineno"> 1132</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01133"></a><span class="lineno"> 1133</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01134"></a><span class="lineno"> 1134</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01135"></a><span class="lineno"> 1135</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01136"></a><span class="lineno"> 1136</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01137"></a><span class="lineno"> 1137</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01138"></a><span class="lineno"> 1138</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01139"></a><span class="lineno"> 1139</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01140"></a><span class="lineno"> 1140</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01141"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a2f47b83634d50eb65c421bb579c7f056"> 1141</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a2f47b83634d50eb65c421bb579c7f056">fft_radix_4_axis_0</a>(</div><div class="line"><a name="l01142"></a><span class="lineno"> 1142</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01143"></a><span class="lineno"> 1143</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01144"></a><span class="lineno"> 1144</span>&#160; ,</div><div class="line"><a name="l01145"></a><span class="lineno"> 1145</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01146"></a><span class="lineno"> 1146</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01147"></a><span class="lineno"> 1147</span>&#160; ,</div><div class="line"><a name="l01148"></a><span class="lineno"> 1148</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01149"></a><span class="lineno"> 1149</span>&#160;{</div><div class="line"><a name="l01150"></a><span class="lineno"> 1150</span>&#160; <span class="comment">// Each work-item computes a single radix-4</span></div><div class="line"><a name="l01151"></a><span class="lineno"> 1151</span>&#160; uint kx = get_global_id(0);</div><div class="line"><a name="l01152"></a><span class="lineno"> 1152</span>&#160;</div><div class="line"><a name="l01153"></a><span class="lineno"> 1153</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01154"></a><span class="lineno"> 1154</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01155"></a><span class="lineno"> 1155</span>&#160;</div><div class="line"><a name="l01156"></a><span class="lineno"> 1156</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01157"></a><span class="lineno"> 1157</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01158"></a><span class="lineno"> 1158</span>&#160;</div><div class="line"><a name="l01159"></a><span class="lineno"> 1159</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01160"></a><span class="lineno"> 1160</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01161"></a><span class="lineno"> 1161</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + get_global_id(1) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01162"></a><span class="lineno"> 1162</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01163"></a><span class="lineno"> 1163</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01164"></a><span class="lineno"> 1164</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01165"></a><span class="lineno"> 1165</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01166"></a><span class="lineno"> 1166</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += n * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + get_global_id(1) * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01167"></a><span class="lineno"> 1167</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01168"></a><span class="lineno"> 1168</span>&#160;</div><div class="line"><a name="l01169"></a><span class="lineno"> 1169</span>&#160; <span class="comment">// Load four complex input values</span></div><div class="line"><a name="l01170"></a><span class="lineno"> 1170</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01171"></a><span class="lineno"> 1171</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, Nx, 0, 0));</div><div class="line"><a name="l01172"></a><span class="lineno"> 1172</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 2 * Nx, 0, 0));</div><div class="line"><a name="l01173"></a><span class="lineno"> 1173</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 3 * Nx, 0, 0));</div><div class="line"><a name="l01174"></a><span class="lineno"> 1174</span>&#160;</div><div class="line"><a name="l01175"></a><span class="lineno"> 1175</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01176"></a><span class="lineno"> 1176</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01177"></a><span class="lineno"> 1177</span>&#160;</div><div class="line"><a name="l01178"></a><span class="lineno"> 1178</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01179"></a><span class="lineno"> 1179</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01180"></a><span class="lineno"> 1180</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01181"></a><span class="lineno"> 1181</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01182"></a><span class="lineno"> 1182</span>&#160;</div><div class="line"><a name="l01183"></a><span class="lineno"> 1183</span>&#160; <span class="comment">// Compute DFT N = 4</span></div><div class="line"><a name="l01184"></a><span class="lineno"> 1184</span>&#160; <a class="code" href="fft_8cl.xhtml#af97e6d43f8b70bcf009d521f8909db25">DFT_4</a>(c0, c1, c2, c3);</div><div class="line"><a name="l01185"></a><span class="lineno"> 1185</span>&#160;</div><div class="line"><a name="l01186"></a><span class="lineno"> 1186</span>&#160; <span class="comment">// Store four complex output values</span></div><div class="line"><a name="l01187"></a><span class="lineno"> 1187</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01188"></a><span class="lineno"> 1188</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, Nx, 0, 0));</div><div class="line"><a name="l01189"></a><span class="lineno"> 1189</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 2 * Nx, 0, 0));</div><div class="line"><a name="l01190"></a><span class="lineno"> 1190</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 3 * Nx, 0, 0));</div><div class="line"><a name="l01191"></a><span class="lineno"> 1191</span>&#160;}</div><div class="line"><a name="l01192"></a><span class="lineno"> 1192</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01193"></a><span class="lineno"> 1193</span>&#160;<span class="comment">/** Computes a stage of a radix-4 FFT on axis 1.</span></div><div class="line"><a name="l01194"></a><span class="lineno"> 1194</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01195"></a><span class="lineno"> 1195</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01196"></a><span class="lineno"> 1196</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01197"></a><span class="lineno"> 1197</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01198"></a><span class="lineno"> 1198</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01199"></a><span class="lineno"> 1199</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01200"></a><span class="lineno"> 1200</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01201"></a><span class="lineno"> 1201</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01202"></a><span class="lineno"> 1202</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01203"></a><span class="lineno"> 1203</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01204"></a><span class="lineno"> 1204</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01205"></a><span class="lineno"> 1205</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01206"></a><span class="lineno"> 1206</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01207"></a><span class="lineno"> 1207</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01208"></a><span class="lineno"> 1208</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01209"></a><span class="lineno"> 1209</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01210"></a><span class="lineno"> 1210</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01211"></a><span class="lineno"> 1211</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01212"></a><span class="lineno"> 1212</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01213"></a><span class="lineno"> 1213</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01214"></a><span class="lineno"> 1214</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01215"></a><span class="lineno"> 1215</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01216"></a><span class="lineno"> 1216</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01217"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a1ab2cb321d9d68ffb9158faf4f4694ff"> 1217</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a1ab2cb321d9d68ffb9158faf4f4694ff">fft_radix_4_axis_1</a>(</div><div class="line"><a name="l01218"></a><span class="lineno"> 1218</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01219"></a><span class="lineno"> 1219</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01220"></a><span class="lineno"> 1220</span>&#160; ,</div><div class="line"><a name="l01221"></a><span class="lineno"> 1221</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01222"></a><span class="lineno"> 1222</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01223"></a><span class="lineno"> 1223</span>&#160; ,</div><div class="line"><a name="l01224"></a><span class="lineno"> 1224</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01225"></a><span class="lineno"> 1225</span>&#160;{</div><div class="line"><a name="l01226"></a><span class="lineno"> 1226</span>&#160; <span class="comment">// Each work-item computes a single radix-4</span></div><div class="line"><a name="l01227"></a><span class="lineno"> 1227</span>&#160; uint kx = get_global_id(1);</div><div class="line"><a name="l01228"></a><span class="lineno"> 1228</span>&#160;</div><div class="line"><a name="l01229"></a><span class="lineno"> 1229</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01230"></a><span class="lineno"> 1230</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01231"></a><span class="lineno"> 1231</span>&#160;</div><div class="line"><a name="l01232"></a><span class="lineno"> 1232</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01233"></a><span class="lineno"> 1233</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01234"></a><span class="lineno"> 1234</span>&#160;</div><div class="line"><a name="l01235"></a><span class="lineno"> 1235</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01236"></a><span class="lineno"> 1236</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01237"></a><span class="lineno"> 1237</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += get_global_id(0) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01238"></a><span class="lineno"> 1238</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01239"></a><span class="lineno"> 1239</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01240"></a><span class="lineno"> 1240</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01241"></a><span class="lineno"> 1241</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01242"></a><span class="lineno"> 1242</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += get_global_id(0) * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + n * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01243"></a><span class="lineno"> 1243</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01244"></a><span class="lineno"> 1244</span>&#160;</div><div class="line"><a name="l01245"></a><span class="lineno"> 1245</span>&#160; <span class="comment">// Load four complex input values</span></div><div class="line"><a name="l01246"></a><span class="lineno"> 1246</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01247"></a><span class="lineno"> 1247</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, Nx, 0));</div><div class="line"><a name="l01248"></a><span class="lineno"> 1248</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2 * Nx, 0));</div><div class="line"><a name="l01249"></a><span class="lineno"> 1249</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3 * Nx, 0));</div><div class="line"><a name="l01250"></a><span class="lineno"> 1250</span>&#160;</div><div class="line"><a name="l01251"></a><span class="lineno"> 1251</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01252"></a><span class="lineno"> 1252</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01253"></a><span class="lineno"> 1253</span>&#160;</div><div class="line"><a name="l01254"></a><span class="lineno"> 1254</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01255"></a><span class="lineno"> 1255</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01256"></a><span class="lineno"> 1256</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01257"></a><span class="lineno"> 1257</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01258"></a><span class="lineno"> 1258</span>&#160;</div><div class="line"><a name="l01259"></a><span class="lineno"> 1259</span>&#160; <span class="comment">// Compute DFT N = 4</span></div><div class="line"><a name="l01260"></a><span class="lineno"> 1260</span>&#160; <a class="code" href="fft_8cl.xhtml#af97e6d43f8b70bcf009d521f8909db25">DFT_4</a>(c0, c1, c2, c3);</div><div class="line"><a name="l01261"></a><span class="lineno"> 1261</span>&#160;</div><div class="line"><a name="l01262"></a><span class="lineno"> 1262</span>&#160; <span class="comment">// Store four complex output values</span></div><div class="line"><a name="l01263"></a><span class="lineno"> 1263</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01264"></a><span class="lineno"> 1264</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, Nx, 0));</div><div class="line"><a name="l01265"></a><span class="lineno"> 1265</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2 * Nx, 0));</div><div class="line"><a name="l01266"></a><span class="lineno"> 1266</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3 * Nx, 0));</div><div class="line"><a name="l01267"></a><span class="lineno"> 1267</span>&#160;}</div><div class="line"><a name="l01268"></a><span class="lineno"> 1268</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01269"></a><span class="lineno"> 1269</span>&#160;<span class="comment">/** Computes a stage of a radix-5 FFT on axis 0.</span></div><div class="line"><a name="l01270"></a><span class="lineno"> 1270</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01271"></a><span class="lineno"> 1271</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01272"></a><span class="lineno"> 1272</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01273"></a><span class="lineno"> 1273</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01274"></a><span class="lineno"> 1274</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01275"></a><span class="lineno"> 1275</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01276"></a><span class="lineno"> 1276</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01277"></a><span class="lineno"> 1277</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01278"></a><span class="lineno"> 1278</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01279"></a><span class="lineno"> 1279</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01280"></a><span class="lineno"> 1280</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01281"></a><span class="lineno"> 1281</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01282"></a><span class="lineno"> 1282</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01283"></a><span class="lineno"> 1283</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01284"></a><span class="lineno"> 1284</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01285"></a><span class="lineno"> 1285</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01286"></a><span class="lineno"> 1286</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01287"></a><span class="lineno"> 1287</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01288"></a><span class="lineno"> 1288</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01289"></a><span class="lineno"> 1289</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01290"></a><span class="lineno"> 1290</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01291"></a><span class="lineno"> 1291</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01292"></a><span class="lineno"> 1292</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01293"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a4eb2e93f73d6b6409b675b4b2f56dcd0"> 1293</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a4eb2e93f73d6b6409b675b4b2f56dcd0">fft_radix_5_axis_0</a>(</div><div class="line"><a name="l01294"></a><span class="lineno"> 1294</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01295"></a><span class="lineno"> 1295</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01296"></a><span class="lineno"> 1296</span>&#160; ,</div><div class="line"><a name="l01297"></a><span class="lineno"> 1297</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01298"></a><span class="lineno"> 1298</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01299"></a><span class="lineno"> 1299</span>&#160; ,</div><div class="line"><a name="l01300"></a><span class="lineno"> 1300</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01301"></a><span class="lineno"> 1301</span>&#160;{</div><div class="line"><a name="l01302"></a><span class="lineno"> 1302</span>&#160; <span class="comment">// Each work-item computes a single radix-5</span></div><div class="line"><a name="l01303"></a><span class="lineno"> 1303</span>&#160; uint kx = get_global_id(0);</div><div class="line"><a name="l01304"></a><span class="lineno"> 1304</span>&#160;</div><div class="line"><a name="l01305"></a><span class="lineno"> 1305</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01306"></a><span class="lineno"> 1306</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01307"></a><span class="lineno"> 1307</span>&#160;</div><div class="line"><a name="l01308"></a><span class="lineno"> 1308</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01309"></a><span class="lineno"> 1309</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01310"></a><span class="lineno"> 1310</span>&#160;</div><div class="line"><a name="l01311"></a><span class="lineno"> 1311</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01312"></a><span class="lineno"> 1312</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01313"></a><span class="lineno"> 1313</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + get_global_id(1) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01314"></a><span class="lineno"> 1314</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01315"></a><span class="lineno"> 1315</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01316"></a><span class="lineno"> 1316</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01317"></a><span class="lineno"> 1317</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01318"></a><span class="lineno"> 1318</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += n * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + get_global_id(1) * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01319"></a><span class="lineno"> 1319</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01320"></a><span class="lineno"> 1320</span>&#160;</div><div class="line"><a name="l01321"></a><span class="lineno"> 1321</span>&#160; <span class="comment">// Load five complex input values</span></div><div class="line"><a name="l01322"></a><span class="lineno"> 1322</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01323"></a><span class="lineno"> 1323</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, Nx, 0, 0));</div><div class="line"><a name="l01324"></a><span class="lineno"> 1324</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 2 * Nx, 0, 0));</div><div class="line"><a name="l01325"></a><span class="lineno"> 1325</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 3 * Nx, 0, 0));</div><div class="line"><a name="l01326"></a><span class="lineno"> 1326</span>&#160; float2 c4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 4 * Nx, 0, 0));</div><div class="line"><a name="l01327"></a><span class="lineno"> 1327</span>&#160;</div><div class="line"><a name="l01328"></a><span class="lineno"> 1328</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01329"></a><span class="lineno"> 1329</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01330"></a><span class="lineno"> 1330</span>&#160;</div><div class="line"><a name="l01331"></a><span class="lineno"> 1331</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01332"></a><span class="lineno"> 1332</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01333"></a><span class="lineno"> 1333</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01334"></a><span class="lineno"> 1334</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01335"></a><span class="lineno"> 1335</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(4 * phi, c4);</div><div class="line"><a name="l01336"></a><span class="lineno"> 1336</span>&#160;</div><div class="line"><a name="l01337"></a><span class="lineno"> 1337</span>&#160; <span class="comment">// Compute DFT N = 5</span></div><div class="line"><a name="l01338"></a><span class="lineno"> 1338</span>&#160; <a class="code" href="fft_8cl.xhtml#a565f17c6fe3e9462057bb523e0127280">DFT_5</a>(c0, c1, c2, c3, c4);</div><div class="line"><a name="l01339"></a><span class="lineno"> 1339</span>&#160;</div><div class="line"><a name="l01340"></a><span class="lineno"> 1340</span>&#160; <span class="comment">// Store five complex output values</span></div><div class="line"><a name="l01341"></a><span class="lineno"> 1341</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01342"></a><span class="lineno"> 1342</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, Nx, 0, 0));</div><div class="line"><a name="l01343"></a><span class="lineno"> 1343</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 2 * Nx, 0, 0));</div><div class="line"><a name="l01344"></a><span class="lineno"> 1344</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 3 * Nx, 0, 0));</div><div class="line"><a name="l01345"></a><span class="lineno"> 1345</span>&#160; vstore2(c4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 4 * Nx, 0, 0));</div><div class="line"><a name="l01346"></a><span class="lineno"> 1346</span>&#160;}</div><div class="line"><a name="l01347"></a><span class="lineno"> 1347</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01348"></a><span class="lineno"> 1348</span>&#160;<span class="comment">/** Computes a stage of a radix-5 FFT on axis 1.</span></div><div class="line"><a name="l01349"></a><span class="lineno"> 1349</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01350"></a><span class="lineno"> 1350</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01351"></a><span class="lineno"> 1351</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01352"></a><span class="lineno"> 1352</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01353"></a><span class="lineno"> 1353</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01354"></a><span class="lineno"> 1354</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01355"></a><span class="lineno"> 1355</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01356"></a><span class="lineno"> 1356</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01357"></a><span class="lineno"> 1357</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01358"></a><span class="lineno"> 1358</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01359"></a><span class="lineno"> 1359</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01360"></a><span class="lineno"> 1360</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01361"></a><span class="lineno"> 1361</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01362"></a><span class="lineno"> 1362</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01363"></a><span class="lineno"> 1363</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01364"></a><span class="lineno"> 1364</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01365"></a><span class="lineno"> 1365</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01366"></a><span class="lineno"> 1366</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01367"></a><span class="lineno"> 1367</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01368"></a><span class="lineno"> 1368</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01369"></a><span class="lineno"> 1369</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01370"></a><span class="lineno"> 1370</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01371"></a><span class="lineno"> 1371</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01372"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#abb1a1c12ab2c72bbb439051b7ff5481b"> 1372</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#abb1a1c12ab2c72bbb439051b7ff5481b">fft_radix_5_axis_1</a>(</div><div class="line"><a name="l01373"></a><span class="lineno"> 1373</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01374"></a><span class="lineno"> 1374</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01375"></a><span class="lineno"> 1375</span>&#160; ,</div><div class="line"><a name="l01376"></a><span class="lineno"> 1376</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01377"></a><span class="lineno"> 1377</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01378"></a><span class="lineno"> 1378</span>&#160; ,</div><div class="line"><a name="l01379"></a><span class="lineno"> 1379</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01380"></a><span class="lineno"> 1380</span>&#160;{</div><div class="line"><a name="l01381"></a><span class="lineno"> 1381</span>&#160; <span class="comment">// Each work-item computes a single radix-5</span></div><div class="line"><a name="l01382"></a><span class="lineno"> 1382</span>&#160; uint kx = get_global_id(1);</div><div class="line"><a name="l01383"></a><span class="lineno"> 1383</span>&#160;</div><div class="line"><a name="l01384"></a><span class="lineno"> 1384</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01385"></a><span class="lineno"> 1385</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01386"></a><span class="lineno"> 1386</span>&#160;</div><div class="line"><a name="l01387"></a><span class="lineno"> 1387</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01388"></a><span class="lineno"> 1388</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01389"></a><span class="lineno"> 1389</span>&#160;</div><div class="line"><a name="l01390"></a><span class="lineno"> 1390</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01391"></a><span class="lineno"> 1391</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01392"></a><span class="lineno"> 1392</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += get_global_id(0) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01393"></a><span class="lineno"> 1393</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01394"></a><span class="lineno"> 1394</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01395"></a><span class="lineno"> 1395</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01396"></a><span class="lineno"> 1396</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01397"></a><span class="lineno"> 1397</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += get_global_id(0) * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + n * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01398"></a><span class="lineno"> 1398</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01399"></a><span class="lineno"> 1399</span>&#160;</div><div class="line"><a name="l01400"></a><span class="lineno"> 1400</span>&#160; <span class="comment">// Load five complex input values</span></div><div class="line"><a name="l01401"></a><span class="lineno"> 1401</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01402"></a><span class="lineno"> 1402</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, Nx, 0));</div><div class="line"><a name="l01403"></a><span class="lineno"> 1403</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2 * Nx, 0));</div><div class="line"><a name="l01404"></a><span class="lineno"> 1404</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3 * Nx, 0));</div><div class="line"><a name="l01405"></a><span class="lineno"> 1405</span>&#160; float2 c4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 4 * Nx, 0));</div><div class="line"><a name="l01406"></a><span class="lineno"> 1406</span>&#160;</div><div class="line"><a name="l01407"></a><span class="lineno"> 1407</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01408"></a><span class="lineno"> 1408</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01409"></a><span class="lineno"> 1409</span>&#160;</div><div class="line"><a name="l01410"></a><span class="lineno"> 1410</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01411"></a><span class="lineno"> 1411</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01412"></a><span class="lineno"> 1412</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01413"></a><span class="lineno"> 1413</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01414"></a><span class="lineno"> 1414</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(4 * phi, c4);</div><div class="line"><a name="l01415"></a><span class="lineno"> 1415</span>&#160;</div><div class="line"><a name="l01416"></a><span class="lineno"> 1416</span>&#160; <span class="comment">// Compute DFT N = 5</span></div><div class="line"><a name="l01417"></a><span class="lineno"> 1417</span>&#160; <a class="code" href="fft_8cl.xhtml#a565f17c6fe3e9462057bb523e0127280">DFT_5</a>(c0, c1, c2, c3, c4);</div><div class="line"><a name="l01418"></a><span class="lineno"> 1418</span>&#160;</div><div class="line"><a name="l01419"></a><span class="lineno"> 1419</span>&#160; <span class="comment">// Store five complex output values</span></div><div class="line"><a name="l01420"></a><span class="lineno"> 1420</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01421"></a><span class="lineno"> 1421</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, Nx, 0));</div><div class="line"><a name="l01422"></a><span class="lineno"> 1422</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2 * Nx, 0));</div><div class="line"><a name="l01423"></a><span class="lineno"> 1423</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3 * Nx, 0));</div><div class="line"><a name="l01424"></a><span class="lineno"> 1424</span>&#160; vstore2(c4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 4 * Nx, 0));</div><div class="line"><a name="l01425"></a><span class="lineno"> 1425</span>&#160;}</div><div class="line"><a name="l01426"></a><span class="lineno"> 1426</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01427"></a><span class="lineno"> 1427</span>&#160;<span class="comment">/** Computes a stage of a radix-7 FFT on axis 0.</span></div><div class="line"><a name="l01428"></a><span class="lineno"> 1428</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01429"></a><span class="lineno"> 1429</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01430"></a><span class="lineno"> 1430</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01431"></a><span class="lineno"> 1431</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01432"></a><span class="lineno"> 1432</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01433"></a><span class="lineno"> 1433</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01434"></a><span class="lineno"> 1434</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01435"></a><span class="lineno"> 1435</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01436"></a><span class="lineno"> 1436</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01437"></a><span class="lineno"> 1437</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01438"></a><span class="lineno"> 1438</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01439"></a><span class="lineno"> 1439</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01440"></a><span class="lineno"> 1440</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01441"></a><span class="lineno"> 1441</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01442"></a><span class="lineno"> 1442</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01443"></a><span class="lineno"> 1443</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01444"></a><span class="lineno"> 1444</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01445"></a><span class="lineno"> 1445</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01446"></a><span class="lineno"> 1446</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01447"></a><span class="lineno"> 1447</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01448"></a><span class="lineno"> 1448</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01449"></a><span class="lineno"> 1449</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01450"></a><span class="lineno"> 1450</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01451"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#ab6b1ce916618012474a0fa938fa69c6c"> 1451</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#ab6b1ce916618012474a0fa938fa69c6c">fft_radix_7_axis_0</a>(</div><div class="line"><a name="l01452"></a><span class="lineno"> 1452</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01453"></a><span class="lineno"> 1453</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01454"></a><span class="lineno"> 1454</span>&#160; ,</div><div class="line"><a name="l01455"></a><span class="lineno"> 1455</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01456"></a><span class="lineno"> 1456</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01457"></a><span class="lineno"> 1457</span>&#160; ,</div><div class="line"><a name="l01458"></a><span class="lineno"> 1458</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01459"></a><span class="lineno"> 1459</span>&#160;{</div><div class="line"><a name="l01460"></a><span class="lineno"> 1460</span>&#160; <span class="comment">// Each work-item computes a single radix-7</span></div><div class="line"><a name="l01461"></a><span class="lineno"> 1461</span>&#160; uint kx = get_global_id(0);</div><div class="line"><a name="l01462"></a><span class="lineno"> 1462</span>&#160;</div><div class="line"><a name="l01463"></a><span class="lineno"> 1463</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01464"></a><span class="lineno"> 1464</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01465"></a><span class="lineno"> 1465</span>&#160;</div><div class="line"><a name="l01466"></a><span class="lineno"> 1466</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01467"></a><span class="lineno"> 1467</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01468"></a><span class="lineno"> 1468</span>&#160;</div><div class="line"><a name="l01469"></a><span class="lineno"> 1469</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01470"></a><span class="lineno"> 1470</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01471"></a><span class="lineno"> 1471</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + get_global_id(1) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01472"></a><span class="lineno"> 1472</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01473"></a><span class="lineno"> 1473</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01474"></a><span class="lineno"> 1474</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01475"></a><span class="lineno"> 1475</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01476"></a><span class="lineno"> 1476</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += n * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + get_global_id(1) * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01477"></a><span class="lineno"> 1477</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01478"></a><span class="lineno"> 1478</span>&#160;</div><div class="line"><a name="l01479"></a><span class="lineno"> 1479</span>&#160; <span class="comment">// Load seven complex input values</span></div><div class="line"><a name="l01480"></a><span class="lineno"> 1480</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01481"></a><span class="lineno"> 1481</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, Nx, 0, 0));</div><div class="line"><a name="l01482"></a><span class="lineno"> 1482</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 2 * Nx, 0, 0));</div><div class="line"><a name="l01483"></a><span class="lineno"> 1483</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 3 * Nx, 0, 0));</div><div class="line"><a name="l01484"></a><span class="lineno"> 1484</span>&#160; float2 c4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 4 * Nx, 0, 0));</div><div class="line"><a name="l01485"></a><span class="lineno"> 1485</span>&#160; float2 c5 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 5 * Nx, 0, 0));</div><div class="line"><a name="l01486"></a><span class="lineno"> 1486</span>&#160; float2 c6 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 6 * Nx, 0, 0));</div><div class="line"><a name="l01487"></a><span class="lineno"> 1487</span>&#160;</div><div class="line"><a name="l01488"></a><span class="lineno"> 1488</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01489"></a><span class="lineno"> 1489</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01490"></a><span class="lineno"> 1490</span>&#160;</div><div class="line"><a name="l01491"></a><span class="lineno"> 1491</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01492"></a><span class="lineno"> 1492</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01493"></a><span class="lineno"> 1493</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01494"></a><span class="lineno"> 1494</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01495"></a><span class="lineno"> 1495</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(4 * phi, c4);</div><div class="line"><a name="l01496"></a><span class="lineno"> 1496</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(5 * phi, c5);</div><div class="line"><a name="l01497"></a><span class="lineno"> 1497</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(6 * phi, c6);</div><div class="line"><a name="l01498"></a><span class="lineno"> 1498</span>&#160;</div><div class="line"><a name="l01499"></a><span class="lineno"> 1499</span>&#160; <span class="comment">// Compute DFT N = 7</span></div><div class="line"><a name="l01500"></a><span class="lineno"> 1500</span>&#160; <a class="code" href="fft_8cl.xhtml#ad04a4028658f997aaca067742c2e8a49">DFT_7</a>(c0, c1, c2, c3, c4, c5, c6);</div><div class="line"><a name="l01501"></a><span class="lineno"> 1501</span>&#160;</div><div class="line"><a name="l01502"></a><span class="lineno"> 1502</span>&#160; <span class="comment">// Store seven complex output values</span></div><div class="line"><a name="l01503"></a><span class="lineno"> 1503</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01504"></a><span class="lineno"> 1504</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, Nx, 0, 0));</div><div class="line"><a name="l01505"></a><span class="lineno"> 1505</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 2 * Nx, 0, 0));</div><div class="line"><a name="l01506"></a><span class="lineno"> 1506</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 3 * Nx, 0, 0));</div><div class="line"><a name="l01507"></a><span class="lineno"> 1507</span>&#160; vstore2(c4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 4 * Nx, 0, 0));</div><div class="line"><a name="l01508"></a><span class="lineno"> 1508</span>&#160; vstore2(c5, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 5 * Nx, 0, 0));</div><div class="line"><a name="l01509"></a><span class="lineno"> 1509</span>&#160; vstore2(c6, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 6 * Nx, 0, 0));</div><div class="line"><a name="l01510"></a><span class="lineno"> 1510</span>&#160;}</div><div class="line"><a name="l01511"></a><span class="lineno"> 1511</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01512"></a><span class="lineno"> 1512</span>&#160;<span class="comment">/** Computes a stage of a radix-7 FFT on axis 1.</span></div><div class="line"><a name="l01513"></a><span class="lineno"> 1513</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01514"></a><span class="lineno"> 1514</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01515"></a><span class="lineno"> 1515</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01516"></a><span class="lineno"> 1516</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01517"></a><span class="lineno"> 1517</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01518"></a><span class="lineno"> 1518</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01519"></a><span class="lineno"> 1519</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01520"></a><span class="lineno"> 1520</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01521"></a><span class="lineno"> 1521</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01522"></a><span class="lineno"> 1522</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01523"></a><span class="lineno"> 1523</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01524"></a><span class="lineno"> 1524</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01525"></a><span class="lineno"> 1525</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01526"></a><span class="lineno"> 1526</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01527"></a><span class="lineno"> 1527</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01528"></a><span class="lineno"> 1528</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01529"></a><span class="lineno"> 1529</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01530"></a><span class="lineno"> 1530</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01531"></a><span class="lineno"> 1531</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01532"></a><span class="lineno"> 1532</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01533"></a><span class="lineno"> 1533</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01534"></a><span class="lineno"> 1534</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01535"></a><span class="lineno"> 1535</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01536"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a76f9319802469601e05d6624e9d8d67c"> 1536</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a76f9319802469601e05d6624e9d8d67c">fft_radix_7_axis_1</a>(</div><div class="line"><a name="l01537"></a><span class="lineno"> 1537</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01538"></a><span class="lineno"> 1538</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01539"></a><span class="lineno"> 1539</span>&#160; ,</div><div class="line"><a name="l01540"></a><span class="lineno"> 1540</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01541"></a><span class="lineno"> 1541</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01542"></a><span class="lineno"> 1542</span>&#160; ,</div><div class="line"><a name="l01543"></a><span class="lineno"> 1543</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01544"></a><span class="lineno"> 1544</span>&#160;{</div><div class="line"><a name="l01545"></a><span class="lineno"> 1545</span>&#160; <span class="comment">// Each work-item computes a single radix-7</span></div><div class="line"><a name="l01546"></a><span class="lineno"> 1546</span>&#160; uint kx = get_global_id(1);</div><div class="line"><a name="l01547"></a><span class="lineno"> 1547</span>&#160;</div><div class="line"><a name="l01548"></a><span class="lineno"> 1548</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01549"></a><span class="lineno"> 1549</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01550"></a><span class="lineno"> 1550</span>&#160;</div><div class="line"><a name="l01551"></a><span class="lineno"> 1551</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01552"></a><span class="lineno"> 1552</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01553"></a><span class="lineno"> 1553</span>&#160;</div><div class="line"><a name="l01554"></a><span class="lineno"> 1554</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01555"></a><span class="lineno"> 1555</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01556"></a><span class="lineno"> 1556</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += get_global_id(0) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01557"></a><span class="lineno"> 1557</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01558"></a><span class="lineno"> 1558</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01559"></a><span class="lineno"> 1559</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01560"></a><span class="lineno"> 1560</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01561"></a><span class="lineno"> 1561</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += get_global_id(0) * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + n * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01562"></a><span class="lineno"> 1562</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01563"></a><span class="lineno"> 1563</span>&#160;</div><div class="line"><a name="l01564"></a><span class="lineno"> 1564</span>&#160; <span class="comment">// Load seven complex input values</span></div><div class="line"><a name="l01565"></a><span class="lineno"> 1565</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01566"></a><span class="lineno"> 1566</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, Nx, 0));</div><div class="line"><a name="l01567"></a><span class="lineno"> 1567</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2 * Nx, 0));</div><div class="line"><a name="l01568"></a><span class="lineno"> 1568</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3 * Nx, 0));</div><div class="line"><a name="l01569"></a><span class="lineno"> 1569</span>&#160; float2 c4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 4 * Nx, 0));</div><div class="line"><a name="l01570"></a><span class="lineno"> 1570</span>&#160; float2 c5 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 5 * Nx, 0));</div><div class="line"><a name="l01571"></a><span class="lineno"> 1571</span>&#160; float2 c6 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 6 * Nx, 0));</div><div class="line"><a name="l01572"></a><span class="lineno"> 1572</span>&#160;</div><div class="line"><a name="l01573"></a><span class="lineno"> 1573</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01574"></a><span class="lineno"> 1574</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01575"></a><span class="lineno"> 1575</span>&#160;</div><div class="line"><a name="l01576"></a><span class="lineno"> 1576</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01577"></a><span class="lineno"> 1577</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01578"></a><span class="lineno"> 1578</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01579"></a><span class="lineno"> 1579</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01580"></a><span class="lineno"> 1580</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(4 * phi, c4);</div><div class="line"><a name="l01581"></a><span class="lineno"> 1581</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(5 * phi, c5);</div><div class="line"><a name="l01582"></a><span class="lineno"> 1582</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(6 * phi, c6);</div><div class="line"><a name="l01583"></a><span class="lineno"> 1583</span>&#160;</div><div class="line"><a name="l01584"></a><span class="lineno"> 1584</span>&#160; <span class="comment">// Compute DFT N = 7</span></div><div class="line"><a name="l01585"></a><span class="lineno"> 1585</span>&#160; <a class="code" href="fft_8cl.xhtml#ad04a4028658f997aaca067742c2e8a49">DFT_7</a>(c0, c1, c2, c3, c4, c5, c6);</div><div class="line"><a name="l01586"></a><span class="lineno"> 1586</span>&#160;</div><div class="line"><a name="l01587"></a><span class="lineno"> 1587</span>&#160; <span class="comment">// Store seven complex output values</span></div><div class="line"><a name="l01588"></a><span class="lineno"> 1588</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01589"></a><span class="lineno"> 1589</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, Nx, 0));</div><div class="line"><a name="l01590"></a><span class="lineno"> 1590</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2 * Nx, 0));</div><div class="line"><a name="l01591"></a><span class="lineno"> 1591</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3 * Nx, 0));</div><div class="line"><a name="l01592"></a><span class="lineno"> 1592</span>&#160; vstore2(c4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 4 * Nx, 0));</div><div class="line"><a name="l01593"></a><span class="lineno"> 1593</span>&#160; vstore2(c5, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 5 * Nx, 0));</div><div class="line"><a name="l01594"></a><span class="lineno"> 1594</span>&#160; vstore2(c6, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 6 * Nx, 0));</div><div class="line"><a name="l01595"></a><span class="lineno"> 1595</span>&#160;}</div><div class="line"><a name="l01596"></a><span class="lineno"> 1596</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01597"></a><span class="lineno"> 1597</span>&#160;<span class="comment">/** Computes a stage of a radix-8 FFT on axis 0.</span></div><div class="line"><a name="l01598"></a><span class="lineno"> 1598</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01599"></a><span class="lineno"> 1599</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01600"></a><span class="lineno"> 1600</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01601"></a><span class="lineno"> 1601</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01602"></a><span class="lineno"> 1602</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01603"></a><span class="lineno"> 1603</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01604"></a><span class="lineno"> 1604</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01605"></a><span class="lineno"> 1605</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01606"></a><span class="lineno"> 1606</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01607"></a><span class="lineno"> 1607</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01608"></a><span class="lineno"> 1608</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01609"></a><span class="lineno"> 1609</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01610"></a><span class="lineno"> 1610</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01611"></a><span class="lineno"> 1611</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01612"></a><span class="lineno"> 1612</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01613"></a><span class="lineno"> 1613</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01614"></a><span class="lineno"> 1614</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01615"></a><span class="lineno"> 1615</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01616"></a><span class="lineno"> 1616</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01617"></a><span class="lineno"> 1617</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01618"></a><span class="lineno"> 1618</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01619"></a><span class="lineno"> 1619</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01620"></a><span class="lineno"> 1620</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01621"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#a73b5ddb25a62a1505d20c02aab7f69cd"> 1621</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#a73b5ddb25a62a1505d20c02aab7f69cd">fft_radix_8_axis_0</a>(</div><div class="line"><a name="l01622"></a><span class="lineno"> 1622</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01623"></a><span class="lineno"> 1623</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01624"></a><span class="lineno"> 1624</span>&#160; ,</div><div class="line"><a name="l01625"></a><span class="lineno"> 1625</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01626"></a><span class="lineno"> 1626</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01627"></a><span class="lineno"> 1627</span>&#160; ,</div><div class="line"><a name="l01628"></a><span class="lineno"> 1628</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01629"></a><span class="lineno"> 1629</span>&#160;{</div><div class="line"><a name="l01630"></a><span class="lineno"> 1630</span>&#160; <span class="comment">// Each work-item computes a single radix-8</span></div><div class="line"><a name="l01631"></a><span class="lineno"> 1631</span>&#160; uint kx = get_global_id(0);</div><div class="line"><a name="l01632"></a><span class="lineno"> 1632</span>&#160;</div><div class="line"><a name="l01633"></a><span class="lineno"> 1633</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01634"></a><span class="lineno"> 1634</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01635"></a><span class="lineno"> 1635</span>&#160;</div><div class="line"><a name="l01636"></a><span class="lineno"> 1636</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01637"></a><span class="lineno"> 1637</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01638"></a><span class="lineno"> 1638</span>&#160;</div><div class="line"><a name="l01639"></a><span class="lineno"> 1639</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01640"></a><span class="lineno"> 1640</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01641"></a><span class="lineno"> 1641</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + get_global_id(1) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01642"></a><span class="lineno"> 1642</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01643"></a><span class="lineno"> 1643</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01644"></a><span class="lineno"> 1644</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01645"></a><span class="lineno"> 1645</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01646"></a><span class="lineno"> 1646</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += n * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + get_global_id(1) * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01647"></a><span class="lineno"> 1647</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01648"></a><span class="lineno"> 1648</span>&#160;</div><div class="line"><a name="l01649"></a><span class="lineno"> 1649</span>&#160; <span class="comment">// Load eight complex input values</span></div><div class="line"><a name="l01650"></a><span class="lineno"> 1650</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01651"></a><span class="lineno"> 1651</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, Nx, 0, 0));</div><div class="line"><a name="l01652"></a><span class="lineno"> 1652</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 2 * Nx, 0, 0));</div><div class="line"><a name="l01653"></a><span class="lineno"> 1653</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 3 * Nx, 0, 0));</div><div class="line"><a name="l01654"></a><span class="lineno"> 1654</span>&#160; float2 c4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 4 * Nx, 0, 0));</div><div class="line"><a name="l01655"></a><span class="lineno"> 1655</span>&#160; float2 c5 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 5 * Nx, 0, 0));</div><div class="line"><a name="l01656"></a><span class="lineno"> 1656</span>&#160; float2 c6 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 6 * Nx, 0, 0));</div><div class="line"><a name="l01657"></a><span class="lineno"> 1657</span>&#160; float2 c7 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 7 * Nx, 0, 0));</div><div class="line"><a name="l01658"></a><span class="lineno"> 1658</span>&#160;</div><div class="line"><a name="l01659"></a><span class="lineno"> 1659</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01660"></a><span class="lineno"> 1660</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01661"></a><span class="lineno"> 1661</span>&#160;</div><div class="line"><a name="l01662"></a><span class="lineno"> 1662</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01663"></a><span class="lineno"> 1663</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01664"></a><span class="lineno"> 1664</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01665"></a><span class="lineno"> 1665</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01666"></a><span class="lineno"> 1666</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(4 * phi, c4);</div><div class="line"><a name="l01667"></a><span class="lineno"> 1667</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(5 * phi, c5);</div><div class="line"><a name="l01668"></a><span class="lineno"> 1668</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(6 * phi, c6);</div><div class="line"><a name="l01669"></a><span class="lineno"> 1669</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(7 * phi, c7);</div><div class="line"><a name="l01670"></a><span class="lineno"> 1670</span>&#160;</div><div class="line"><a name="l01671"></a><span class="lineno"> 1671</span>&#160; <span class="comment">// Compute DFT N = 8</span></div><div class="line"><a name="l01672"></a><span class="lineno"> 1672</span>&#160; <a class="code" href="fft_8cl.xhtml#a4c4ce3f10939dd4237d0adee00086a53">DFT_8</a>(c0, c1, c2, c3, c4, c5, c6, c7);</div><div class="line"><a name="l01673"></a><span class="lineno"> 1673</span>&#160;</div><div class="line"><a name="l01674"></a><span class="lineno"> 1674</span>&#160; <span class="comment">// Store eight complex output values</span></div><div class="line"><a name="l01675"></a><span class="lineno"> 1675</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01676"></a><span class="lineno"> 1676</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, Nx, 0, 0));</div><div class="line"><a name="l01677"></a><span class="lineno"> 1677</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 2 * Nx, 0, 0));</div><div class="line"><a name="l01678"></a><span class="lineno"> 1678</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 3 * Nx, 0, 0));</div><div class="line"><a name="l01679"></a><span class="lineno"> 1679</span>&#160; vstore2(c4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 4 * Nx, 0, 0));</div><div class="line"><a name="l01680"></a><span class="lineno"> 1680</span>&#160; vstore2(c5, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 5 * Nx, 0, 0));</div><div class="line"><a name="l01681"></a><span class="lineno"> 1681</span>&#160; vstore2(c6, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 6 * Nx, 0, 0));</div><div class="line"><a name="l01682"></a><span class="lineno"> 1682</span>&#160; vstore2(c7, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 7 * Nx, 0, 0));</div><div class="line"><a name="l01683"></a><span class="lineno"> 1683</span>&#160;}</div><div class="line"><a name="l01684"></a><span class="lineno"> 1684</span>&#160;<span class="comment"></span></div><div class="line"><a name="l01685"></a><span class="lineno"> 1685</span>&#160;<span class="comment">/** Computes a stage of a radix-8 FFT on axis 1.</span></div><div class="line"><a name="l01686"></a><span class="lineno"> 1686</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01687"></a><span class="lineno"> 1687</span>&#160;<span class="comment"> * @note In order to perform the FFT function &quot;in-place&quot;, the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l01688"></a><span class="lineno"> 1688</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l01689"></a><span class="lineno"> 1689</span>&#160;<span class="comment"> * @param[in,out] input_ptr Pointer to the source tensor. Supported data types: F32</span></div><div class="line"><a name="l01690"></a><span class="lineno"> 1690</span>&#160;<span class="comment"> * @param[in,out] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l01691"></a><span class="lineno"> 1691</span>&#160;<span class="comment"> * @param[in,out] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01692"></a><span class="lineno"> 1692</span>&#160;<span class="comment"> * @param[in,out] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l01693"></a><span class="lineno"> 1693</span>&#160;<span class="comment"> * @param[in,out] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01694"></a><span class="lineno"> 1694</span>&#160;<span class="comment"> * @param[in,out] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01695"></a><span class="lineno"> 1695</span>&#160;<span class="comment"> * @param[in,out] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01696"></a><span class="lineno"> 1696</span>&#160;<span class="comment"> * @param[in,out] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l01697"></a><span class="lineno"> 1697</span>&#160;<span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l01698"></a><span class="lineno"> 1698</span>&#160;<span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l01699"></a><span class="lineno"> 1699</span>&#160;<span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l01700"></a><span class="lineno"> 1700</span>&#160;<span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l01701"></a><span class="lineno"> 1701</span>&#160;<span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l01702"></a><span class="lineno"> 1702</span>&#160;<span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l01703"></a><span class="lineno"> 1703</span>&#160;<span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l01704"></a><span class="lineno"> 1704</span>&#160;<span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l01705"></a><span class="lineno"> 1705</span>&#160;<span class="comment"> * @param[in] Nx The butterfly span. Products of radix order of previous radix&#39;s stage</span></div><div class="line"><a name="l01706"></a><span class="lineno"> 1706</span>&#160;<span class="comment"> * @param[in] Ni Nx * Ny.</span></div><div class="line"><a name="l01707"></a><span class="lineno"> 1707</span>&#160;<span class="comment"> * @param[in] exp_const Exponent constant</span></div><div class="line"><a name="l01708"></a><span class="lineno"> 1708</span>&#160;<span class="comment"> */</span></div><div class="line"><a name="l01709"></a><span class="lineno"><a class="line" href="fft_8cl.xhtml#aa056502bc3783dce7428acc17ce9ee94"> 1709</a></span>&#160;kernel <span class="keywordtype">void</span> <a class="code" href="fft_8cl.xhtml#aa056502bc3783dce7428acc17ce9ee94">fft_radix_8_axis_1</a>(</div><div class="line"><a name="l01710"></a><span class="lineno"> 1710</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>)</div><div class="line"><a name="l01711"></a><span class="lineno"> 1711</span>&#160;#ifndef IN_PLACE</div><div class="line"><a name="l01712"></a><span class="lineno"> 1712</span>&#160; ,</div><div class="line"><a name="l01713"></a><span class="lineno"> 1713</span>&#160; <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a>(output)</div><div class="line"><a name="l01714"></a><span class="lineno"> 1714</span>&#160;#endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l01715"></a><span class="lineno"> 1715</span>&#160; ,</div><div class="line"><a name="l01716"></a><span class="lineno"> 1716</span>&#160; uint Nx, uint Ni, <span class="keywordtype">float</span> exp_const)</div><div class="line"><a name="l01717"></a><span class="lineno"> 1717</span>&#160;{</div><div class="line"><a name="l01718"></a><span class="lineno"> 1718</span>&#160; <span class="comment">// Each work-item computes a single radix-8</span></div><div class="line"><a name="l01719"></a><span class="lineno"> 1719</span>&#160; uint kx = get_global_id(1);</div><div class="line"><a name="l01720"></a><span class="lineno"> 1720</span>&#160;</div><div class="line"><a name="l01721"></a><span class="lineno"> 1721</span>&#160; <span class="comment">// Compute nx</span></div><div class="line"><a name="l01722"></a><span class="lineno"> 1722</span>&#160; uint nx = kx % Nx;</div><div class="line"><a name="l01723"></a><span class="lineno"> 1723</span>&#160;</div><div class="line"><a name="l01724"></a><span class="lineno"> 1724</span>&#160; <span class="comment">// Compute n index</span></div><div class="line"><a name="l01725"></a><span class="lineno"> 1725</span>&#160; uint n = nx + (kx / Nx) * Ni;</div><div class="line"><a name="l01726"></a><span class="lineno"> 1726</span>&#160;</div><div class="line"><a name="l01727"></a><span class="lineno"> 1727</span>&#160; <span class="comment">// Get tensor pointers</span></div><div class="line"><a name="l01728"></a><span class="lineno"> 1728</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>);</div><div class="line"><a name="l01729"></a><span class="lineno"> 1729</span>&#160; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr += get_global_id(0) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_x + n * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_y + get_global_id(2) * <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.stride_z;</div><div class="line"><a name="l01730"></a><span class="lineno"> 1730</span>&#160;<span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l01731"></a><span class="lineno"> 1731</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l01732"></a><span class="lineno"> 1732</span>&#160;<span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01733"></a><span class="lineno"> 1733</span>&#160; <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a>(output);</div><div class="line"><a name="l01734"></a><span class="lineno"> 1734</span>&#160; output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a> += get_global_id(0) * output.<a class="code" href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">stride_x</a> + n * output.<a class="code" href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">stride_y</a> + get_global_id(2) * output.<a class="code" href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">stride_z</a>;</div><div class="line"><a name="l01735"></a><span class="lineno"> 1735</span>&#160;<span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l01736"></a><span class="lineno"> 1736</span>&#160;</div><div class="line"><a name="l01737"></a><span class="lineno"> 1737</span>&#160; <span class="comment">// Load eight complex input values</span></div><div class="line"><a name="l01738"></a><span class="lineno"> 1738</span>&#160; float2 c0 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>.ptr);</div><div class="line"><a name="l01739"></a><span class="lineno"> 1739</span>&#160; float2 c1 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, Nx, 0));</div><div class="line"><a name="l01740"></a><span class="lineno"> 1740</span>&#160; float2 c2 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 2 * Nx, 0));</div><div class="line"><a name="l01741"></a><span class="lineno"> 1741</span>&#160; float2 c3 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 3 * Nx, 0));</div><div class="line"><a name="l01742"></a><span class="lineno"> 1742</span>&#160; float2 c4 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 4 * Nx, 0));</div><div class="line"><a name="l01743"></a><span class="lineno"> 1743</span>&#160; float2 c5 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 5 * Nx, 0));</div><div class="line"><a name="l01744"></a><span class="lineno"> 1744</span>&#160; float2 c6 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 6 * Nx, 0));</div><div class="line"><a name="l01745"></a><span class="lineno"> 1745</span>&#160; float2 c7 = vload2(0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 7 * Nx, 0));</div><div class="line"><a name="l01746"></a><span class="lineno"> 1746</span>&#160;</div><div class="line"><a name="l01747"></a><span class="lineno"> 1747</span>&#160; <span class="comment">// Compute phi</span></div><div class="line"><a name="l01748"></a><span class="lineno"> 1748</span>&#160; <span class="keywordtype">float</span> phi = (float)nx * exp_const;</div><div class="line"><a name="l01749"></a><span class="lineno"> 1749</span>&#160;</div><div class="line"><a name="l01750"></a><span class="lineno"> 1750</span>&#160; <span class="comment">// Multiply by twiddle factor</span></div><div class="line"><a name="l01751"></a><span class="lineno"> 1751</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(phi, c1);</div><div class="line"><a name="l01752"></a><span class="lineno"> 1752</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(2 * phi, c2);</div><div class="line"><a name="l01753"></a><span class="lineno"> 1753</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(3 * phi, c3);</div><div class="line"><a name="l01754"></a><span class="lineno"> 1754</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(4 * phi, c4);</div><div class="line"><a name="l01755"></a><span class="lineno"> 1755</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(5 * phi, c5);</div><div class="line"><a name="l01756"></a><span class="lineno"> 1756</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(6 * phi, c6);</div><div class="line"><a name="l01757"></a><span class="lineno"> 1757</span>&#160; <a class="code" href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a>(7 * phi, c7);</div><div class="line"><a name="l01758"></a><span class="lineno"> 1758</span>&#160;</div><div class="line"><a name="l01759"></a><span class="lineno"> 1759</span>&#160; <span class="comment">// Compute DFT N = 8</span></div><div class="line"><a name="l01760"></a><span class="lineno"> 1760</span>&#160; <a class="code" href="fft_8cl.xhtml#a4c4ce3f10939dd4237d0adee00086a53">DFT_8</a>(c0, c1, c2, c3, c4, c5, c6, c7);</div><div class="line"><a name="l01761"></a><span class="lineno"> 1761</span>&#160;</div><div class="line"><a name="l01762"></a><span class="lineno"> 1762</span>&#160; <span class="comment">// Store eight complex output values</span></div><div class="line"><a name="l01763"></a><span class="lineno"> 1763</span>&#160; vstore2(c0, 0, (__global <span class="keywordtype">float</span> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l01764"></a><span class="lineno"> 1764</span>&#160; vstore2(c1, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, Nx, 0));</div><div class="line"><a name="l01765"></a><span class="lineno"> 1765</span>&#160; vstore2(c2, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 2 * Nx, 0));</div><div class="line"><a name="l01766"></a><span class="lineno"> 1766</span>&#160; vstore2(c3, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 3 * Nx, 0));</div><div class="line"><a name="l01767"></a><span class="lineno"> 1767</span>&#160; vstore2(c4, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 4 * Nx, 0));</div><div class="line"><a name="l01768"></a><span class="lineno"> 1768</span>&#160; vstore2(c5, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 5 * Nx, 0));</div><div class="line"><a name="l01769"></a><span class="lineno"> 1769</span>&#160; vstore2(c6, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 6 * Nx, 0));</div><div class="line"><a name="l01770"></a><span class="lineno"> 1770</span>&#160; vstore2(c7, 0, (__global <span class="keywordtype">float</span> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&amp;output, 0, 7 * Nx, 0));</div><div class="line"><a name="l01771"></a><span class="lineno"> 1771</span>&#160;}</div><div class="ttc" id="fft_8cl_xhtml_ad4dcc4a8b94f263cd19c59fdc2cec3d2"><div class="ttname"><a href="fft_8cl.xhtml#ad4dcc4a8b94f263cd19c59fdc2cec3d2">TWIDDLE_FACTOR_MULTIPLICATION</a></div><div class="ttdeci">#define TWIDDLE_FACTOR_MULTIPLICATION(phi, input)</div><div class="ttdoc">Calculates and applies the twiddle factor to a given input.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00031">fft.cl:31</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_aba8f7b960aa49b876ac266447a78c416"><div class="ttname"><a href="fft_8cl.xhtml#aba8f7b960aa49b876ac266447a78c416">fft_radix_7_first_stage_axis_0</a></div><div class="ttdeci">kernel void fft_radix_7_first_stage_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-7 DFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00634">fft.cl:634</a></div></div>
<div class="ttc" id="struct_tensor3_d_xhtml_ad5ff7a2b2bd0eec50fe09c254b127d1c"><div class="ttname"><a href="struct_tensor3_d.xhtml#ad5ff7a2b2bd0eec50fe09c254b127d1c">Tensor3D::stride_z</a></div><div class="ttdeci">int stride_z</div><div class="ttdoc">Stride of the image in Z dimension (in bytes)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00364">helpers.h:364</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_ac6ec77d2e41d56919c14c1483eee94ac"><div class="ttname"><a href="fft_8cl.xhtml#ac6ec77d2e41d56919c14c1483eee94ac">DFT_3</a></div><div class="ttdeci">#define DFT_3(c0, c1, c2)</div><div class="ttdoc">Computes radix-3 butterfly unit.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00063">fft.cl:63</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a565f17c6fe3e9462057bb523e0127280"><div class="ttname"><a href="fft_8cl.xhtml#a565f17c6fe3e9462057bb523e0127280">DFT_5</a></div><div class="ttdeci">#define DFT_5(c0, c1, c2, c3, c4)</div><div class="ttdoc">Computes radix-5 butterfly unit.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00109">fft.cl:109</a></div></div>
<div class="ttc" id="struct_tensor3_d_xhtml_ae01febbfd0689ef709f3ff6fdd2abc7e"><div class="ttname"><a href="struct_tensor3_d.xhtml#ae01febbfd0689ef709f3ff6fdd2abc7e">Tensor3D::stride_x</a></div><div class="ttdeci">int stride_x</div><div class="ttdoc">Stride of the image in X dimension (in bytes)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00362">helpers.h:362</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a4c4ce3f10939dd4237d0adee00086a53"><div class="ttname"><a href="fft_8cl.xhtml#a4c4ce3f10939dd4237d0adee00086a53">DFT_8</a></div><div class="ttdeci">#define DFT_8(c0, c1, c2, c3, c4, c5, c6, c7)</div><div class="ttdoc">Computes radix-8 butterfly unit.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00172">fft.cl:172</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a6f8673fc7472554bb672ef796f6b91b7"><div class="ttname"><a href="fft_8cl.xhtml#a6f8673fc7472554bb672ef796f6b91b7">fft_radix_5_first_stage_axis_1</a></div><div class="ttdeci">kernel void fft_radix_5_first_stage_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-5 DFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00579">fft.cl:579</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_aa056502bc3783dce7428acc17ce9ee94"><div class="ttname"><a href="fft_8cl.xhtml#aa056502bc3783dce7428acc17ce9ee94">fft_radix_8_axis_1</a></div><div class="ttdeci">kernel void fft_radix_8_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-8 FFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01709">fft.cl:1709</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a3f65de85962b99e35c4bd9abcbc7e660"><div class="ttname"><a href="fft_8cl.xhtml#a3f65de85962b99e35c4bd9abcbc7e660">fft_radix_7_first_stage_axis_1</a></div><div class="ttdeci">kernel void fft_radix_7_first_stage_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-7 DFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00685">fft.cl:685</a></div></div>
<div class="ttc" id="struct_tensor3_d_xhtml"><div class="ttname"><a href="struct_tensor3_d.xhtml">Tensor3D</a></div><div class="ttdoc">Structure to hold 3D tensor information.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00358">helpers.h:358</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_ad04a4028658f997aaca067742c2e8a49"><div class="ttname"><a href="fft_8cl.xhtml#ad04a4028658f997aaca067742c2e8a49">DFT_7</a></div><div class="ttdeci">#define DFT_7(c0, c1, c2, c3, c4, c5, c6)</div><div class="ttdoc">Computes radix-7 butterfly unit.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00142">fft.cl:142</a></div></div>
<div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a8fcf2ddd9a1d58b1b280f5c0aed71845"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">arm_compute::test::validation::input</a></div><div class="ttdeci">auto input</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_l_s_t_m_layer_quantized_8cpp_source.xhtml#l00487">LSTMLayerQuantized.cpp:487</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a5a63ca1d5404d67d13382a90cfc9b6c3"><div class="ttname"><a href="fft_8cl.xhtml#a5a63ca1d5404d67d13382a90cfc9b6c3">DFT_2</a></div><div class="ttdeci">#define DFT_2(c0, c1)</div><div class="ttdoc">Computes radix-2 butterfly unit.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00046">fft.cl:46</a></div></div>
<div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a79e8e562daa6599317d2d1cd86ef1bf2"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a79e8e562daa6599317d2d1cd86ef1bf2">CONVERT_TO_TENSOR3D_STRUCT_NO_STEP</a></div><div class="ttdeci">#define CONVERT_TO_TENSOR3D_STRUCT_NO_STEP(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00330">helpers.h:330</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_ad4c7557777731327f741ef848e2b28c2"><div class="ttname"><a href="fft_8cl.xhtml#ad4c7557777731327f741ef848e2b28c2">fft_radix_2_axis_1</a></div><div class="ttdeci">kernel void fft_radix_2_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-2 FFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00925">fft.cl:925</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_af5d6a654bacf45355b1dcaacc6441691"><div class="ttname"><a href="fft_8cl.xhtml#af5d6a654bacf45355b1dcaacc6441691">fft_radix_3_axis_0</a></div><div class="ttdeci">kernel void fft_radix_3_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-3 FFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00995">fft.cl:995</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a76f788853ef70fc0220ae4bb55db6d11"><div class="ttname"><a href="fft_8cl.xhtml#a76f788853ef70fc0220ae4bb55db6d11">fft_radix_8_first_stage_axis_1</a></div><div class="ttdeci">kernel void fft_radix_8_first_stage_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-8 DFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00791">fft.cl:791</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a67f435359dc175539c7d04d27c4bebb4"><div class="ttname"><a href="fft_8cl.xhtml#a67f435359dc175539c7d04d27c4bebb4">fft_radix_4_first_stage_axis_0</a></div><div class="ttdeci">kernel void fft_radix_4_first_stage_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-4 DFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00430">fft.cl:430</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a11794801d4e717905406446d14cd313b"><div class="ttname"><a href="fft_8cl.xhtml#a11794801d4e717905406446d14cd313b">fft_radix_5_first_stage_axis_0</a></div><div class="ttdeci">kernel void fft_radix_5_first_stage_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-5 DFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00530">fft.cl:530</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a6c378af2ec36adec6dd88b961151a057"><div class="ttname"><a href="fft_8cl.xhtml#a6c378af2ec36adec6dd88b961151a057">fft_radix_3_axis_1</a></div><div class="ttdeci">kernel void fft_radix_3_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-3 FFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01068">fft.cl:1068</a></div></div>
<div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a31c8c760f08fb1a331b16b7c204321dc"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a></div><div class="ttdeci">#define CONVERT_TO_TENSOR3D_STRUCT(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00326">helpers.h:326</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a4eb2e93f73d6b6409b675b4b2f56dcd0"><div class="ttname"><a href="fft_8cl.xhtml#a4eb2e93f73d6b6409b675b4b2f56dcd0">fft_radix_5_axis_0</a></div><div class="ttdeci">kernel void fft_radix_5_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-5 FFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01293">fft.cl:1293</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_ae919967e7eb2349552a120bd0ab40eb2"><div class="ttname"><a href="fft_8cl.xhtml#ae919967e7eb2349552a120bd0ab40eb2">fft_radix_2_first_stage_axis_1</a></div><div class="ttdeci">kernel void fft_radix_2_first_stage_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-2 DFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00281">fft.cl:281</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_ab6b1ce916618012474a0fa938fa69c6c"><div class="ttname"><a href="fft_8cl.xhtml#ab6b1ce916618012474a0fa938fa69c6c">fft_radix_7_axis_0</a></div><div class="ttdeci">kernel void fft_radix_7_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-7 FFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01451">fft.cl:1451</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a1ab2cb321d9d68ffb9158faf4f4694ff"><div class="ttname"><a href="fft_8cl.xhtml#a1ab2cb321d9d68ffb9158faf4f4694ff">fft_radix_4_axis_1</a></div><div class="ttdeci">kernel void fft_radix_4_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-4 FFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01217">fft.cl:1217</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_aa9b7071c5ccacded46ca51f250807be5"><div class="ttname"><a href="fft_8cl.xhtml#aa9b7071c5ccacded46ca51f250807be5">fft_radix_4_first_stage_axis_1</a></div><div class="ttdeci">kernel void fft_radix_4_first_stage_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-4 DFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00477">fft.cl:477</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a2f47b83634d50eb65c421bb579c7f056"><div class="ttname"><a href="fft_8cl.xhtml#a2f47b83634d50eb65c421bb579c7f056">fft_radix_4_axis_0</a></div><div class="ttdeci">kernel void fft_radix_4_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-4 FFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01141">fft.cl:1141</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a6d2d172d9e177ed439b6f6ddc0785b86"><div class="ttname"><a href="fft_8cl.xhtml#a6d2d172d9e177ed439b6f6ddc0785b86">fft_radix_2_axis_0</a></div><div class="ttdeci">kernel void fft_radix_2_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-2 FFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00855">fft.cl:855</a></div></div>
<div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml">helpers.h</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a008d11872b90493790f933f82c9f05b5"><div class="ttname"><a href="fft_8cl.xhtml#a008d11872b90493790f933f82c9f05b5">fft_radix_8_first_stage_axis_0</a></div><div class="ttdeci">kernel void fft_radix_8_first_stage_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-8 DFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00744">fft.cl:744</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a45a776393b0fabafec290645e3d67010"><div class="ttname"><a href="fft_8cl.xhtml#a45a776393b0fabafec290645e3d67010">fft_radix_3_first_stage_axis_1</a></div><div class="ttdeci">kernel void fft_radix_3_first_stage_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-3 DFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00379">fft.cl:379</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_aea16049f33aa1fa59ca48e7092238bf0"><div class="ttname"><a href="fft_8cl.xhtml#aea16049f33aa1fa59ca48e7092238bf0">fft_radix_2_first_stage_axis_0</a></div><div class="ttdeci">kernel void fft_radix_2_first_stage_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-2 DFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00234">fft.cl:234</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_af97e6d43f8b70bcf009d521f8909db25"><div class="ttname"><a href="fft_8cl.xhtml#af97e6d43f8b70bcf009d521f8909db25">DFT_4</a></div><div class="ttdeci">#define DFT_4(c0, c1, c2, c3)</div><div class="ttdoc">Computes radix-4 butterfly unit.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00081">fft.cl:81</a></div></div>
<div class="ttc" id="struct_tensor3_d_xhtml_acf52c23cbd7424606c10a606524e3e32"><div class="ttname"><a href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">Tensor3D::ptr</a></div><div class="ttdeci">__global uchar * ptr</div><div class="ttdoc">Pointer to the starting postion of the buffer.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00360">helpers.h:360</a></div></div>
<div class="ttc" id="struct_tensor3_d_xhtml_a4f0b90c9ecd6e57ceb3f37332fefe8f1"><div class="ttname"><a href="struct_tensor3_d.xhtml#a4f0b90c9ecd6e57ceb3f37332fefe8f1">Tensor3D::stride_y</a></div><div class="ttdeci">int stride_y</div><div class="ttdoc">Stride of the image in Y dimension (in bytes)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00363">helpers.h:363</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a3a40d552a9d4c240e46db020bd606a2b"><div class="ttname"><a href="fft_8cl.xhtml#a3a40d552a9d4c240e46db020bd606a2b">fft_radix_3_first_stage_axis_0</a></div><div class="ttdeci">kernel void fft_radix_3_first_stage_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes)</div><div class="ttdoc">Computes the first stage of a radix-3 DFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l00330">fft.cl:330</a></div></div>
<div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a6b83038822d1ae7ab619b684ed3b7fc0"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a></div><div class="ttdeci">#define TENSOR3D_DECLARATION(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00283">helpers.h:283</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a76f9319802469601e05d6624e9d8d67c"><div class="ttname"><a href="fft_8cl.xhtml#a76f9319802469601e05d6624e9d8d67c">fft_radix_7_axis_1</a></div><div class="ttdeci">kernel void fft_radix_7_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-7 FFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01536">fft.cl:1536</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_a73b5ddb25a62a1505d20c02aab7f69cd"><div class="ttname"><a href="fft_8cl.xhtml#a73b5ddb25a62a1505d20c02aab7f69cd">fft_radix_8_axis_0</a></div><div class="ttdeci">kernel void fft_radix_8_axis_0(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-8 FFT on axis 0.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01621">fft.cl:1621</a></div></div>
<div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a2101b2fe0193ce227ae4e0945e321d85"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a></div><div class="ttdeci">__global const uchar * tensor3D_offset(const Tensor3D *tensor, int x, int y, int z)</div><div class="ttdoc">Get the pointer position of a Tensor3D.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00522">helpers.h:522</a></div></div>
<div class="ttc" id="fft_8cl_xhtml_abb1a1c12ab2c72bbb439051b7ff5481b"><div class="ttname"><a href="fft_8cl.xhtml#abb1a1c12ab2c72bbb439051b7ff5481b">fft_radix_5_axis_1</a></div><div class="ttdeci">kernel void fft_radix_5_axis_1(__global uchar *input_ptr, uint input_stride_x, uint input_step_x, uint input_stride_y, uint input_step_y, uint input_stride_z, uint input_step_z, uint input_offset_first_element_in_bytes, __global uchar *output_ptr, uint output_stride_x, uint output_step_x, uint output_stride_y, uint output_step_y, uint output_stride_z, uint output_step_z, uint output_offset_first_element_in_bytes, uint Nx, uint Ni, float exp_const)</div><div class="ttdoc">Computes a stage of a radix-5 FFT on axis 1.</div><div class="ttdef"><b>Definition:</b> <a href="fft_8cl_source.xhtml#l01372">fft.cl:1372</a></div></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="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.xhtml">src</a></li><li class="navelem"><a class="el" href="dir_aebb8dcc11953d78e620bbef0b9e2183.xhtml">core</a></li><li class="navelem"><a class="el" href="dir_8c278f79c760e5c5fbd911f9870614c1.xhtml">CL</a></li><li class="navelem"><a class="el" href="dir_25885286e9dad4fa105b7b25a8031bbf.xhtml">cl_kernels</a></li><li class="navelem"><a class="el" href="fft_8cl.xhtml">fft.cl</a></li>
<li class="footer">Generated on Thu Nov 28 2019 16:52:57 for Compute Library by
<a href="http://www.doxygen.org/index.html">
<img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.15 </li>
</ul>
</div>
</body>
</html>