| <!-- 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/arg_min_max.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&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"> |
|  <span id="projectnumber">20.02.1</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&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&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&dn=gpl-2.0.txt GPL-v2 */ |
| $(document).ready(function(){initNavTree('arg__min__max_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">arg_min_max.cl</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <a href="arg__min__max_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> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Copyright (c) 2019-2020 ARM Limited.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> *</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment"> * SPDX-License-Identifier: MIT</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> <span class="comment"> *</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <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> <span class="comment"> * of this software and associated documentation files (the "Software"), to</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> <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> <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> <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> <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> <span class="comment"> *</span></div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span> <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> <span class="comment"> * copies or substantial portions of the Software.</span></div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="comment"> *</span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="comment"> * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <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> <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> <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> <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> <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> <span class="comment"> * SOFTWARE.</span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span> <span class="comment"> */</span></div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> <span class="preprocessor">#include "<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml">helpers.h</a>"</span></div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span> </div><div class="line"><a name="l00026"></a><span class="lineno"> 26</span> <span class="preprocessor">#if defined(FLOAT_DATA_TYPE)</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor">#define ISGREATER(x, y) isgreater(x, y)</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#define ISLESS(x, y) isless(x, y)</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#else // !FLOAT_DATA_TYPE</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="preprocessor">#if defined(WIDTH)</span></div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#define ISGREATER(x, y) (x > y) ? 1 : 0</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="preprocessor">#define ISLESS(x, y) (x < y) ? 1 : 0</span></div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="preprocessor">#else // !defined(WIDTH)</span></div><div class="line"><a name="l00034"></a><span class="lineno"><a class="line" href="arg__min__max_8cl.xhtml#a40336a6b889813a08d55e615a26b511a"> 34</a></span> <span class="preprocessor">#define ISGREATER(x, y) select((VEC_DATA_TYPE(DATA_TYPE_SELECT, 16))0, (VEC_DATA_TYPE(DATA_TYPE_SELECT, 16)) - 1, x > y)</span></div><div class="line"><a name="l00035"></a><span class="lineno"><a class="line" href="arg__min__max_8cl.xhtml#afef444918bb4f103371e703041081971"> 35</a></span> <span class="preprocessor">#define ISLESS(x, y) select((VEC_DATA_TYPE(DATA_TYPE_SELECT, 16))0, (VEC_DATA_TYPE(DATA_TYPE_SELECT, 16)) - 1, x < y)</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="preprocessor">#endif // defined(WIDTH)</span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="preprocessor">#endif // defined(FLOAT_DATA_TYPE)</span></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> </div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="preprocessor">#if defined(ARG_MAX)</span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="preprocessor">#define CONDITION_TO_USE(x, y) ISGREATER(x, y)</span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="preprocessor">#elif defined(ARG_MIN)</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="preprocessor">#define CONDITION_TO_USE(x, y) ISLESS(x, y)</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="preprocessor">#else // !(defined(ARG_MAX) || defined(ARG_MIN))</span></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="preprocessor">#error "Unsupported reduction operation!"</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="preprocessor">#endif // defined(ARG_MAX)</span></div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> </div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="preprocessor">#if defined(DATA_TYPE_OUTPUT) && defined(DATA_TYPE_SELECT)</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="preprocessor">#if defined(WIDTH)</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> <span class="preprocessor">#if defined(ARG_MIN)</span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="preprocessor">#if defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="comment">/** Find index minimum value of a vector</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="comment"> *</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="comment"> * @param[in] input Pointer to the first value.</span></div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="comment"> *</span></div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> <span class="comment"> * @return index of the vector.</span></div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="comment"> */</span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="keyword">inline</span> DATA_TYPE_OUTPUT arg_idx_min_prev_out(__global <span class="keyword">const</span> <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, __global <span class="keyword">const</span> DATA_TYPE_OUTPUT *prev_res, <span class="keyword">const</span> <span class="keywordtype">int</span> x_idx)</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span> {</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <span class="keywordtype">int</span> end_elem = (x_idx + 1) * 16;</div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <span class="keywordflow">if</span>(end_elem > WIDTH)</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  {</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  end_elem = WIDTH - x_idx * 16;</div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  }</div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  DATA_TYPE_OUTPUT res = prev_res[0];</div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keywordflow">for</span>(<span class="keywordtype">int</span> x_v = 1; x_v < end_elem; ++x_v)</div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  {</div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, prev_res[x_v], *(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + prev_res[x_v]) < * (<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + res));</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  }</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <span class="keywordflow">return</span> res;</div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span> }</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span> <span class="preprocessor">#else // !defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment">/** Find index minimum value of a vector</span></div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment"> *</span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment"> * @param[in] input Pointer to the first value.</span></div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span> <span class="comment"> *</span></div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span> <span class="comment"> * @return index of the vector.</span></div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span> <span class="comment"> */</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span> <span class="keyword">inline</span> DATA_TYPE_OUTPUT arg_idx_min(__global <span class="keyword">const</span> <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <span class="keyword">const</span> <span class="keywordtype">int</span> x_idx)</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span> {</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span> <span class="preprocessor">#if WIDTH < 16</span></div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  DATA_TYPE_OUTPUT res = 0;</div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  <span class="keywordflow">for</span>(DATA_TYPE_OUTPUT x_v = res + 1; x_v < <a class="code" href="namespacearm__compute.xhtml#a74ce3f7420453d3446218ff3b7453e02a49da85b69bc6285eeee286ca49fa7195">WIDTH</a>; ++x_v)</div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  {</div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, x_v, *(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + x_v) < * (<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + res));</div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  }</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  <span class="keywordflow">return</span> res;</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> <span class="preprocessor">#else // WIDTH >= 16</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  <span class="keywordtype">int</span> x_elem = x_idx * 16;</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x_goback = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(0, 16 - WIDTH % 16, x_elem + 16 > WIDTH);</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  x_elem -= x_goback;</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> </div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  in = vload16(0, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> - x_goback);</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  res = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 };</div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span> </div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_SELECT, 8)</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  idx_sel = (in.s01234567 <= in.s89abcdef);</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  in.s01234567 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(in.s89abcdef, in.s01234567, idx_sel);</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  res.s01234567 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s89abcdef, res.s01234567, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel, int8));</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span> </div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  idx_sel.s0123 = (in.s0123 < in.s4567) || (in.s0123 == in.s4567 && <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>((res.s0123 < res.s4567), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_SELECT, 4)));</div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  in.s0123 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(in.s4567, in.s0123, idx_sel.s0123);</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  res.s0123 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s4567, res.s0123, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel.s0123, int4));</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span> </div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  idx_sel.s01 = (in.s01 < in.s23) || (in.s01 == in.s23 && <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>((res.s01 < res.s23), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_SELECT, 2)));</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  in.s01 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(in.s23, in.s01, idx_sel.s01);</div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span>  res.s01 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s23, res.s01, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel.s01, int2));</div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> </div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  idx_sel.s0 = (in.s0 < in.s1) || (in.s0 == in.s1 && <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>((res.s0 < res.s1), DATA_TYPE_SELECT));</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  res.s0 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s1, res.s0, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel.s0, <span class="keywordtype">int</span>));</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span> </div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  return res.s0 + x_elem;</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span> <span class="preprocessor">#endif // WIDTH < 16</span></div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span> }</div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span> <span class="preprocessor">#endif // defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span> <span class="preprocessor">#endif // defined(ARG_MIN)</span></div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span> <span class="preprocessor">#if defined(ARG_MAX)</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span> <span class="preprocessor">#if defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span> <span class="comment">/** Find index maximum value of a vector</span></div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span> <span class="comment"> *</span></div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span> <span class="comment"> * @param[in] input Pointer to the first value.</span></div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span> <span class="comment"> *</span></div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span> <span class="comment"> * @return index of the vector.</span></div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> <span class="comment"> */</span></div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span> <span class="keyword">inline</span> DATA_TYPE_OUTPUT arg_idx_max_prev_out(__global <span class="keyword">const</span> <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, __global <span class="keyword">const</span> DATA_TYPE_OUTPUT *prev_res, <span class="keyword">const</span> <span class="keywordtype">int</span> x_idx)</div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span> {</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  <span class="keywordtype">int</span> end_elem = (x_idx + 1) * 16;</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span>  <span class="keywordflow">if</span>(end_elem > WIDTH)</div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span>  {</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  end_elem = <a class="code" href="namespacearm__compute.xhtml#a74ce3f7420453d3446218ff3b7453e02a49da85b69bc6285eeee286ca49fa7195">WIDTH</a> - x_idx * 16;</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span>  }</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  DATA_TYPE_OUTPUT res = prev_res[0];</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  <span class="keywordflow">for</span>(<span class="keywordtype">int</span> x_v = 1; x_v < end_elem; ++x_v)</div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  {</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, prev_res[x_v], *(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + prev_res[x_v]) > *(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + res));</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  }</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  <span class="keywordflow">return</span> res;</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span> }</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span> <span class="preprocessor">#else // !defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span> <span class="comment">/** Find index maximum value of a vector</span></div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span> <span class="comment"> *</span></div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span> <span class="comment"> * @param[in] input Pointer to the first value.</span></div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span> <span class="comment"> *</span></div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span> <span class="comment"> * @return index of the vector.</span></div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span> <span class="comment"> */</span></div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span> <span class="keyword">inline</span> DATA_TYPE_OUTPUT arg_idx_max(__global <span class="keyword">const</span> <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <span class="keyword">const</span> <span class="keywordtype">int</span> x_idx)</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span> {</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span> <span class="preprocessor">#if WIDTH < 16</span></div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span>  DATA_TYPE_OUTPUT res = 0;</div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  <span class="keywordflow">for</span>(DATA_TYPE_OUTPUT x_v = res + 1; x_v < <a class="code" href="namespacearm__compute.xhtml#a74ce3f7420453d3446218ff3b7453e02a49da85b69bc6285eeee286ca49fa7195">WIDTH</a>; ++x_v)</div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  {</div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, x_v, *(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + x_v) > *(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> + res));</div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  }</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <span class="keywordflow">return</span> res;</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> <span class="preprocessor">#else // WIDTH >= 16</span></div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  <span class="keywordtype">int</span> x_elem = x_idx * 16;</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x_goback = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(0, 16 - WIDTH % 16, x_elem + 16 > WIDTH);</div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  x_elem -= x_goback;</div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span> </div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  in = vload16(0, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a> - x_goback);</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  res = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 };</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span> </div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_SELECT, 8)</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  idx_sel = (in.s01234567 >= in.s89abcdef);</div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  in.s01234567 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(in.s89abcdef, in.s01234567, idx_sel);</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  res.s01234567 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s89abcdef, res.s01234567, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel, int8));</div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span> </div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  idx_sel.s0123 = (in.s0123 > in.s4567) || (in.s0123 == in.s4567 && <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>((res.s0123 < res.s4567), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_SELECT, 4)));</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  in.s0123 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(in.s4567, in.s0123, idx_sel.s0123);</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  res.s0123 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s4567, res.s0123, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel.s0123, int4));</div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span> </div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  idx_sel.s01 = (in.s01 > in.s23) || (in.s01 == in.s23 && <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>((res.s01 < res.s23), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_SELECT, 2)));</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span>  in.s01 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(in.s23, in.s01, idx_sel.s01);</div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  res.s01 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s23, res.s01, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel.s01, int2));</div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span> </div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  idx_sel.s0 = (in.s0 > in.s1) || (in.s0 == in.s1 && <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>((res.s0 < res.s1), DATA_TYPE_SELECT));</div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  res.s0 = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res.s1, res.s0, <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(idx_sel.s0, <span class="keywordtype">int</span>));</div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span> </div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span>  return res.s0 + x_elem;</div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span> <span class="preprocessor">#endif // WIDTH < 16</span></div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span> }</div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span> <span class="preprocessor">#endif // defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span> <span class="preprocessor">#endif // defined(ARG_MAX)</span></div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span> <span class="comment"></span></div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> <span class="comment">/** This kernel performs parallel reduction given an operation on x-axis.</span></div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span> <span class="comment"> *</span></div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span> <span class="comment"> * @note In case the results of previous stages are passed the flag PREV_OUTPUT has to be passed using -DPREV_OUTPUT</span></div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span> <span class="comment"> * @note The data type must be passed at compile time using -DDATA_TYPE: e.g. -DDATA_TYPE=float</span></div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span> <span class="comment"> * @note The data type of the output must be passed at compile time using -DDATA_TYPE_OUTPUT: e.g. -DDATA_TYPE_OUTPUT=uint</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span> <span class="comment"> * @note The arg_max flag must be passed at compile time using -DARG_MAX if we want to compute the ArgMax</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span> <span class="comment"> * @note The arg_min flag must be passed at compile time using -DARG_MIN if we want to compute the ArgMin</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span> <span class="comment"> *</span></div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: S32/F16/F32</span></div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span> <span class="comment"> * @param[in] src_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span> <span class="comment"> * @param[in] src_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span> <span class="comment"> * @param[in] src_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span> <span class="comment"> * @param[in] src_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span> <span class="comment"> * @param[in] src_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span> <span class="comment"> * @param[in] prev_res_ptr (Optional) Pointer to previous results tensor. Supported data types: U32/S32</span></div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span> <span class="comment"> * @param[in] prev_res_stride_x (Optional) Stride of the output tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span> <span class="comment"> * @param[in] prev_res_step_x (Optional) prev_res_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span> <span class="comment"> * @param[in] prev_res_stride_y (Optional) Stride of the output tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> <span class="comment"> * @param[in] prev_res_step_y (Optional) prev_res_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span> <span class="comment"> * @param[in] prev_res_offset_first_element_in_bytes (Optional) The offset of the first element in the previous results tensor</span></div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> <span class="comment"> * @param[in] partial_res_ptr The local buffer to hold partial result values. Supported data types: U32/S32</span></div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span> <span class="comment"> * @param[in] partial_res_stride_x Stride of the output tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span> <span class="comment"> * @param[in] partial_res_step_x partial_res_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span> <span class="comment"> * @param[in] partial_res_stride_y Stride of the output tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span> <span class="comment"> * @param[in] partial_res_step_y partial_res_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span> <span class="comment"> * @param[in] partial_res_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span> <span class="comment"> * @param[in] local_results Local buffer for storing the partial result</span></div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span> <span class="comment"> */</span></div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span> __kernel <span class="keywordtype">void</span> arg_min_max_x(</div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a22f42fcf2077d951271df83b55c1a71a">IMAGE_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>),</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span> #<span class="keywordflow">if</span> defined(PREV_OUTPUT)</div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a22f42fcf2077d951271df83b55c1a71a">IMAGE_DECLARATION</a>(prev_res),</div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span> #endif <span class="comment">// defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a22f42fcf2077d951271df83b55c1a71a">IMAGE_DECLARATION</a>(partial_res),</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  __local DATA_TYPE_OUTPUT *local_results)</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span> {</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span> <span class="preprocessor">#if defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  <a class="code" href="struct_image.xhtml">Image</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a4334a4a76f8e9628c0fb9e1acf616e2a">CONVERT_TO_IMAGE_STRUCT_NO_STEP</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>);</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  <a class="code" href="struct_image.xhtml">Image</a> prev_res = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aebe814363556c244be043b13e7969197">CONVERT_TO_IMAGE_STRUCT</a>(prev_res);</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span> <span class="preprocessor">#else // !defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  <a class="code" href="struct_image.xhtml">Image</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aebe814363556c244be043b13e7969197">CONVERT_TO_IMAGE_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>);</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span> <span class="preprocessor">#endif // defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <a class="code" href="struct_image.xhtml">Image</a> partial_res = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aebe814363556c244be043b13e7969197">CONVERT_TO_IMAGE_STRUCT</a>(partial_res);</div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span> </div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> lsize = get_local_size(0);</div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> lid = get_local_id(0);</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span> </div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  <span class="keyword">const</span> uint x_idx = get_global_id(0);</div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>  <span class="keyword">const</span> uint y_idx = get_global_id(1);</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="keyword">const</span> __global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *src_in_row = (<span class="keyword">const</span> __global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(src_ptr + src_offset_first_element_in_bytes + y_idx * src_step_y);</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span> </div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  <span class="keywordflow">for</span>(<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> y = 0; y < get_local_size(1); ++y)</div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  {</div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span> <span class="preprocessor">#if defined(ARG_MAX)</span></div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span> <span class="preprocessor">#if defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  local_results[lid] = arg_idx_max_prev_out(src_in_row, (__global DATA_TYPE_OUTPUT *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&prev_res, 0, y), x_idx);</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span> <span class="preprocessor">#else // !defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  local_results[lid] = arg_idx_max((__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, 0, y), x_idx);</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span> <span class="preprocessor">#endif // defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00247"></a><span class="lineno"> 247</span> <span class="preprocessor">#else // defined(ARG_MIN)</span></div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span> <span class="preprocessor">#if defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  local_results[lid] = arg_idx_min_prev_out(src_in_row, (__global DATA_TYPE_OUTPUT *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&prev_res, 0, y), x_idx);</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span> <span class="preprocessor">#else // !defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  local_results[lid] = arg_idx_min((__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, 0, y), x_idx);</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span> <span class="preprocessor">#endif // defined(PREV_OUTPUT)</span></div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span> <span class="preprocessor">#endif // defined(ARG_MAX) || defined(ARG_MIN)</span></div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span> </div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  barrier(CLK_LOCAL_MEM_FENCE);</div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span> </div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  <span class="comment">// Looking for the next highest power of 2 (maximum value of lsize is 8)</span></div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> middle = lsize - 1;</div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  middle |= middle >> 1;</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  middle |= middle >> 2;</div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span>  middle += 1;</div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  <span class="comment">// Perform parallel reduction</span></div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  <span class="keywordflow">for</span>(<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = middle; i > 0; i >>= 1)</div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  {</div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  <span class="keywordflow">if</span>( lid < i && lid + i < lsize)</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  {</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>  <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> tmp0 = *(src_in_row + local_results[lid]);</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span>  <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> tmp1 = *(src_in_row + local_results[lid + i]);</div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span> <span class="preprocessor">#if defined(ARG_MAX)</span></div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  local_results[lid] = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  local_results[lid],</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  local_results[lid + i],</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  ((tmp0 == tmp1) && (local_results[lid + i] < local_results[lid])) || (tmp0 < tmp1));</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span> <span class="preprocessor">#else // defined(ARG_MIN)</span></div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  local_results[lid] = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span>  local_results[lid],</div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span>  local_results[lid + i],</div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  ((tmp0 == tmp1) && (local_results[lid + i] < local_results[lid])) || (tmp0 > tmp1));</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span> <span class="preprocessor">#endif // defined(ARG_MAX) || defined(ARG_MIN)</span></div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  }</div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span>  barrier(CLK_LOCAL_MEM_FENCE);</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  }</div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span> </div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>  <span class="keywordflow">if</span>(lid == 0)</div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span>  {</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span>  ((__global DATA_TYPE_OUTPUT *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&partial_res, get_group_id(0), y))[0] = local_results[0];</div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>  }</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>  }</div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span> }</div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span> <span class="preprocessor">#endif // defined(WIDTH)</span></div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span> </div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span> <span class="preprocessor">#if defined(HEIGHT)</span></div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span> <span class="comment">/** This kernel performs reduction on y-axis.</span></div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span> <span class="comment"> *</span></div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> <span class="comment"> * @note The input data type must be passed at compile time using -DDATA_TYPE: e.g. -DDATA_TYPE=float</span></div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span> <span class="comment"> * @note The data type of the output must be passed at compile time using -DDATA_TYPE_OUTPUT: e.g. -DDATA_TYPE_OUTPUT=uint</span></div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span> <span class="comment"> * @note The data type of the select results must be passed at compile time using -DDATA_TYPE_SELECT: e.g. -DDATA_TYPE_SELECT=int</span></div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span> <span class="comment"> * @note The height size must be passed at compile time using -DHEIGHT e.g. -DHEIGHT=128</span></div><div class="line"><a name="l00299"></a><span class="lineno"> 299</span> <span class="comment"> *</span></div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: S32/F16/F32</span></div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span> <span class="comment"> * @param[in] src_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span> <span class="comment"> * @param[in] src_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span> <span class="comment"> * @param[in] src_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span> <span class="comment"> * @param[in] src_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span> <span class="comment"> * @param[in] src_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span> <span class="comment"> * @param[in] output_ptr The local buffer to hold sumed values. Supported data types: U32/S32</span></div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span> <span class="comment"> * @param[in] output_stride_x Stride of the output tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span> <span class="comment"> * @param[in] output_step_x output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span> <span class="comment"> * @param[in] output_stride_y Stride of the output tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span> <span class="comment"> * @param[in] output_step_y output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span> <span class="comment"> * @param[in] output_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span> <span class="comment"> */</span></div><div class="line"><a name="l00313"></a><span class="lineno"> 313</span> __kernel <span class="keywordtype">void</span> arg_min_max_y(</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a22f42fcf2077d951271df83b55c1a71a">IMAGE_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>),</div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a22f42fcf2077d951271df83b55c1a71a">IMAGE_DECLARATION</a>(output))</div><div class="line"><a name="l00316"></a><span class="lineno"> 316</span> {</div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span>  <a class="code" href="struct_image.xhtml">Image</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a> = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aebe814363556c244be043b13e7969197">CONVERT_TO_IMAGE_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>);</div><div class="line"><a name="l00318"></a><span class="lineno"> 318</span>  <a class="code" href="struct_image.xhtml">Image</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aebe814363556c244be043b13e7969197">CONVERT_TO_IMAGE_STRUCT</a>(output);</div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span> </div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span>  res = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, 0, 0)), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16));</div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span> </div><div class="line"><a name="l00323"></a><span class="lineno"> 323</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00324"></a><span class="lineno"> 324</span>  indx = 0;</div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span>  <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a0886942393a3ba0dfefaa7516b159784">for</a>(<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> y = 1; y < HEIGHT; ++y)</div><div class="line"><a name="l00326"></a><span class="lineno"> 326</span>  {</div><div class="line"><a name="l00327"></a><span class="lineno"> 327</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span>  in = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, 0, y)), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16));</div><div class="line"><a name="l00329"></a><span class="lineno"> 329</span> </div><div class="line"><a name="l00330"></a><span class="lineno"> 330</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span>  cond_conv = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(CONDITION_TO_USE(in, res), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16));</div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span>  indx = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(indx, y, cond_conv);</div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, in, CONDITION_TO_USE(in, res));</div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span>  }</div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span> </div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span>  <span class="comment">// Store result</span></div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span>  vstore16(indx, 0, (__global DATA_TYPE_OUTPUT *)output.ptr);</div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span> }</div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span> <span class="preprocessor">#endif // defined(HEIGHT)</span></div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span> </div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span> <span class="preprocessor">#if defined(DEPTH)</span></div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span> <span class="comment">/** This kernel performs reduction on z-axis.</span></div><div class="line"><a name="l00343"></a><span class="lineno"> 343</span> <span class="comment"> *</span></div><div class="line"><a name="l00344"></a><span class="lineno"> 344</span> <span class="comment"> * @note The data type must be passed at compile time using -DDATA_TYPE: e.g. -DDATA_TYPE=float</span></div><div class="line"><a name="l00345"></a><span class="lineno"> 345</span> <span class="comment"> * @note The data type of the select results must be passed at compile time using -DDATA_TYPE_SELECT: e.g. -DDATA_TYPE_SELECT=int</span></div><div class="line"><a name="l00346"></a><span class="lineno"> 346</span> <span class="comment"> * @note The depth size must be passed at compile time using -DDEPTH e.g. -DDEPTH=128</span></div><div class="line"><a name="l00347"></a><span class="lineno"> 347</span> <span class="comment"> *</span></div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span> <span class="comment"> * @param[in] input_ptr Pointer to the source tensor. Supported data types: S32/F16/F32</span></div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span> <span class="comment"> * @param[in] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span> <span class="comment"> * @param[in] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00351"></a><span class="lineno"> 351</span> <span class="comment"> * @param[in] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00352"></a><span class="lineno"> 352</span> <span class="comment"> * @param[in] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span> <span class="comment"> * @param[in] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span> <span class="comment"> * @param[in] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span> <span class="comment"> * @param[in] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00356"></a><span class="lineno"> 356</span> <span class="comment"> * @param[in] output_ptr The local buffer to hold sumed values. Supported data types: U32/S32</span></div><div class="line"><a name="l00357"></a><span class="lineno"> 357</span> <span class="comment"> * @param[in] output_stride_x Stride of the output tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span> <span class="comment"> * @param[in] output_step_x output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span> <span class="comment"> * @param[in] output_stride_y Stride of the output tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span> <span class="comment"> * @param[in] output_step_y output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span> <span class="comment"> * @param[in] output_stride_z Stride of the output tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span> <span class="comment"> * @param[in] output_step_z output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span> <span class="comment"> * @param[in] output_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span> <span class="comment"> */</span></div><div class="line"><a name="l00365"></a><span class="lineno"> 365</span> __kernel <span class="keywordtype">void</span> arg_min_max_z(</div><div class="line"><a name="l00366"></a><span class="lineno"> 366</span>  <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="l00367"></a><span class="lineno"> 367</span>  <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="l00368"></a><span class="lineno"> 368</span> {</div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span>  <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="l00370"></a><span class="lineno"> 370</span>  <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="l00371"></a><span class="lineno"> 371</span> </div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span>  res = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 0, 0)), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16));</div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span> </div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00376"></a><span class="lineno"> 376</span>  indx = 0;</div><div class="line"><a name="l00377"></a><span class="lineno"> 377</span>  <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a0886942393a3ba0dfefaa7516b159784">for</a>(DATA_TYPE_OUTPUT z = 1; z < DEPTH; ++z)</div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span>  {</div><div class="line"><a name="l00379"></a><span class="lineno"> 379</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span>  in = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a2101b2fe0193ce227ae4e0945e321d85">tensor3D_offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 0, z)), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16));</div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span> </div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span>  cond_conv = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(CONDITION_TO_USE(in, res), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16));</div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span>  indx = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(indx, z, cond_conv);</div><div class="line"><a name="l00385"></a><span class="lineno"> 385</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, in, CONDITION_TO_USE(in, res));</div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span>  }</div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span> </div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span>  <span class="comment">// Store result</span></div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span>  vstore16(indx, 0, (__global DATA_TYPE_OUTPUT *)output.ptr);</div><div class="line"><a name="l00390"></a><span class="lineno"> 390</span> }</div><div class="line"><a name="l00391"></a><span class="lineno"> 391</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(DEPTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00392"></a><span class="lineno"> 392</span> </div><div class="line"><a name="l00393"></a><span class="lineno"> 393</span> <span class="preprocessor">#if defined(BATCH) && defined(DEPTH)</span></div><div class="line"><a name="l00394"></a><span class="lineno"> 394</span> <span class="comment">/** This kernel performs reduction on w-axis.</span></div><div class="line"><a name="l00395"></a><span class="lineno"> 395</span> <span class="comment"> *</span></div><div class="line"><a name="l00396"></a><span class="lineno"> 396</span> <span class="comment"> * @note The data type must be passed at compile time using -DDATA_TYPE: e.g. -DDATA_TYPE=float</span></div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span> <span class="comment"> * @note The data type of the select results must be passed at compile time using -DDATA_TYPE_SELECT: e.g. -DDATA_TYPE_SELECT=int</span></div><div class="line"><a name="l00398"></a><span class="lineno"> 398</span> <span class="comment"> * @note The batch size must be passed at compile time using -DBATCH e.g. -DBATCH=128</span></div><div class="line"><a name="l00399"></a><span class="lineno"> 399</span> <span class="comment"> * @note The depth size must be passed at compile time using -DBATCH e.g. -DDEPTH=128</span></div><div class="line"><a name="l00400"></a><span class="lineno"> 400</span> <span class="comment"> *</span></div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span> <span class="comment"> * @param[in] input_ptr Pointer to the source tensor. Supported data types: S32/F16/F32</span></div><div class="line"><a name="l00402"></a><span class="lineno"> 402</span> <span class="comment"> * @param[in] input_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00403"></a><span class="lineno"> 403</span> <span class="comment"> * @param[in] input_step_x input_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00404"></a><span class="lineno"> 404</span> <span class="comment"> * @param[in] input_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span> <span class="comment"> * @param[in] input_step_y input_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span> <span class="comment"> * @param[in] input_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span> <span class="comment"> * @param[in] input_step_z input_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span> <span class="comment"> * @param[in] input_stride_w Stride of the source tensor in W dimension (in bytes)</span></div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span> <span class="comment"> * @param[in] input_step_w input_stride_w * number of elements along W processed per workitem(in bytes)</span></div><div class="line"><a name="l00410"></a><span class="lineno"> 410</span> <span class="comment"> * @param[in] input_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00411"></a><span class="lineno"> 411</span> <span class="comment"> * @param[in] output_ptr The local buffer to hold sumed values. Supported data types: U32/S32</span></div><div class="line"><a name="l00412"></a><span class="lineno"> 412</span> <span class="comment"> * @param[in] output_stride_x Stride of the output tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00413"></a><span class="lineno"> 413</span> <span class="comment"> * @param[in] output_step_x output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span> <span class="comment"> * @param[in] output_stride_y Stride of the output tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span> <span class="comment"> * @param[in] output_step_y output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span> <span class="comment"> * @param[in] output_stride_z Stride of the output tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00417"></a><span class="lineno"> 417</span> <span class="comment"> * @param[in] output_step_z output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span> <span class="comment"> * @param[in] output_stride_w Stride of the output tensor in W dimension (in bytes)</span></div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span> <span class="comment"> * @param[in] output_step_w output_stride_w * number of elements along W processed per workitem(in bytes)</span></div><div class="line"><a name="l00420"></a><span class="lineno"> 420</span> <span class="comment"> * @param[in] output_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> <span class="comment"> */</span></div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span> __kernel <span class="keywordtype">void</span> arg_min_max_w(</div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>),</div><div class="line"><a name="l00424"></a><span class="lineno"> 424</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(output))</div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span> {</div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</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#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, DEPTH);</div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> output = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a>(output, DEPTH);</div><div class="line"><a name="l00428"></a><span class="lineno"> 428</span> </div><div class="line"><a name="l00429"></a><span class="lineno"> 429</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00430"></a><span class="lineno"> 430</span>  res = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#ad442fb5ec8be1fff97f543150de5d822">tensor4D_offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 0, 0, 0)), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16));</div><div class="line"><a name="l00431"></a><span class="lineno"> 431</span> </div><div class="line"><a name="l00432"></a><span class="lineno"> 432</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00433"></a><span class="lineno"> 433</span>  indx = 0;</div><div class="line"><a name="l00434"></a><span class="lineno"> 434</span>  <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a0886942393a3ba0dfefaa7516b159784">for</a>(DATA_TYPE_OUTPUT <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> = 1; <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> < BATCH; ++<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a>)</div><div class="line"><a name="l00435"></a><span class="lineno"> 435</span>  {</div><div class="line"><a name="l00436"></a><span class="lineno"> 436</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00437"></a><span class="lineno"> 437</span>  in = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#ad442fb5ec8be1fff97f543150de5d822">tensor4D_offset</a>(&<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, 0, 0, 0, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a>)), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16));</div><div class="line"><a name="l00438"></a><span class="lineno"> 438</span> </div><div class="line"><a name="l00439"></a><span class="lineno"> 439</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16)</div><div class="line"><a name="l00440"></a><span class="lineno"> 440</span>  cond_conv = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(CONDITION_TO_USE(in, res), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(DATA_TYPE_OUTPUT, 16));</div><div class="line"><a name="l00441"></a><span class="lineno"> 441</span>  indx = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(indx, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a>, cond_conv);</div><div class="line"><a name="l00442"></a><span class="lineno"> 442</span>  res = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(res, in, CONDITION_TO_USE(in, res));</div><div class="line"><a name="l00443"></a><span class="lineno"> 443</span>  }</div><div class="line"><a name="l00444"></a><span class="lineno"> 444</span> </div><div class="line"><a name="l00445"></a><span class="lineno"> 445</span>  <span class="comment">// Store result</span></div><div class="line"><a name="l00446"></a><span class="lineno"> 446</span>  vstore16(indx, 0, (__global DATA_TYPE_OUTPUT *)output.ptr);</div><div class="line"><a name="l00447"></a><span class="lineno"> 447</span> }</div><div class="line"><a name="l00448"></a><span class="lineno"> 448</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(BATCH) && defined(DEPTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00449"></a><span class="lineno"> 449</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(DATA_TYPE_OUTPUT) && defined(DATA_TYPE_SELECT) */</span><span class="preprocessor"></span></div><div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a009469e4d9b8fce3b6d5e97d2077827d"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a></div><div class="ttdeci">__global uchar * offset(const Image *img, int x, int y)</div><div class="ttdoc">Get the pointer position of a Image.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00510">helpers.h:510</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a1a367830ae09bf6138df822888ec1d71"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">arm_compute::test::validation::w</a></div><div class="ttdeci">SimpleTensor< float > w</div><div class="ttdef"><b>Definition:</b> <a href="_c_p_p_2_d_f_t_8cpp_source.xhtml#l00156">DFT.cpp:156</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_aa8d95ba04fc73845abc6045952cae5be"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a></div><div class="ttdeci">#define CONVERT(x, type)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00261">helpers.h:261</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_aebe814363556c244be043b13e7969197"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aebe814363556c244be043b13e7969197">CONVERT_TO_IMAGE_STRUCT</a></div><div class="ttdeci">#define CONVERT_TO_IMAGE_STRUCT(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00311">helpers.h:311</a></div></div> |
| <div class="ttc" id="convolution3x3_8cl_xhtml_afb8c72ce35c4a1f4a2588d6573e54aa1"><div class="ttname"><a href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a></div><div class="ttdeci">#define DATA_TYPE</div><div class="ttdef"><b>Definition:</b> <a href="convolution3x3_8cl_source.xhtml#l00027">convolution3x3.cl:27</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a22f42fcf2077d951271df83b55c1a71a"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a22f42fcf2077d951271df83b55c1a71a">IMAGE_DECLARATION</a></div><div class="ttdeci">#define IMAGE_DECLARATION(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00275">helpers.h:275</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a0886942393a3ba0dfefaa7516b159784"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a0886942393a3ba0dfefaa7516b159784">arm_compute::test::validation::for</a></div><div class="ttdeci">for(size_t k=0;k< _target.size();++k)</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_unstack_8cpp_source.xhtml#l00091">Unstack.cpp:91</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="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="struct_tensor4_d_xhtml"><div class="ttname"><a href="struct_tensor4_d.xhtml">Tensor4D</a></div><div class="ttdoc">Structure to hold 4D tensor information.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00368">helpers.h:368</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a4334a4a76f8e9628c0fb9e1acf616e2a"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a4334a4a76f8e9628c0fb9e1acf616e2a">CONVERT_TO_IMAGE_STRUCT_NO_STEP</a></div><div class="ttdeci">#define CONVERT_TO_IMAGE_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#l00314">helpers.h:314</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_ad442fb5ec8be1fff97f543150de5d822"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#ad442fb5ec8be1fff97f543150de5d822">tensor4D_offset</a></div><div class="ttdeci">__global const uchar * tensor4D_offset(const Tensor4D *tensor, int x, int y, int z, int w)</div><div class="ttdoc">Get the pointer position of a Tensor4D.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00535">helpers.h:535</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a23b9032d1b9d59547545e457f82ee478"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a></div><div class="ttdeci">#define CONVERT_TO_TENSOR4D_STRUCT(name, mod_size)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00333">helpers.h:333</a></div></div> |
| <div class="ttc" id="struct_image_xhtml"><div class="ttname"><a href="struct_image.xhtml">Image</a></div><div class="ttdoc">Structure to hold Image information.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00349">helpers.h:349</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="namespacearm__compute_1_1test_1_1validation_xhtml_af77145fbdc6b0c8931148f5597d9de53"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">arm_compute::test::validation::select</a></div><div class="ttdeci">CLSelect select</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_select_8cpp_source.xhtml#l00164">Select.cpp:164</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="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a481bdc6d61b3df9dcdbdb244f0f97790"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a></div><div class="ttdeci">#define TENSOR4D_DECLARATION(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00293">helpers.h:293</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_a74ce3f7420453d3446218ff3b7453e02a49da85b69bc6285eeee286ca49fa7195"><div class="ttname"><a href="namespacearm__compute.xhtml#a74ce3f7420453d3446218ff3b7453e02a49da85b69bc6285eeee286ca49fa7195">arm_compute::DataLayoutDimension::WIDTH</a></div><div class="ttdoc">width</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="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="namespacearm__compute_1_1test_1_1validation_xhtml_a989ab3e96426615bb98e04e0235088ca"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">arm_compute::test::validation::src</a></div><div class="ttdeci">cast configure & src</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_cast_8cpp_source.xhtml#l00169">Cast.cpp:169</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a36f754c05b6fddf6df0d8d0a74f8159f"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a></div><div class="ttdeci">#define VEC_DATA_TYPE(type, size)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00255">helpers.h:255</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="arg__min__max_8cl.xhtml">arg_min_max.cl</a></li> |
| <li class="footer">Generated on Thu Mar 5 2020 16:06:57 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> |
