| <!-- 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/activation_layer_quant.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('activation__layer__quant_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">activation_layer_quant.cl</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <a href="activation__layer__quant_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) 2016-2019 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="activation__quant__helpers_8h.xhtml">activation_quant_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"><a class="line" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c"> 26</a></span> <span class="preprocessor">#define VEC_FLOAT VEC_DATA_TYPE(float, VEC_SIZE)</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> </div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#if defined(FLOAT_DOMAIN)</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="comment">// Activations performed in the float domain</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> </div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#include "<a class="code" href="activation__float__helpers_8h.xhtml">activation_float_helpers.h</a>"</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="comment"></span></div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="comment">/** This performs an activation function on quantized inputs with float transformations.</span></div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span> <span class="comment"> *</span></div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span> <span class="comment"> * @note In order to perform the activation function "in-place", the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="comment"> *</span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="comment"> * @note Datatype should be given as a preprocessor argument using -DDATA_TYPE=type. e.g. -DDATA_TYPE=short</span></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> <span class="comment"> * @note Vector size should be given as a preprocessor argument using -DVEC_SIZE=size. e.g. -DVEC_SIZE=16</span></div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="comment"> * @note A, B variables required by some activation functions are set using -DA_VAL= and -DB_VAL= respectively.</span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="comment"> * @note Quantization scales of the input/output tensors are passed in with -DS1_VAL= and -DS2_VAL= respectively.</span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="comment"> * @note Quantization offsets of the input/output tensors are passed in only if asymmetric with -DO1_VAL= and -DO2_VAL= respectively.</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="comment"> * @note Quantized value of constant zero should be given as a preprocessor argument using -DCONST_0=value. e.g. -DCONST_0=128.</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="comment"> *</span></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="comment"> * @param[in] input_ptr Pointer to the source image. Supported data types: QASYMM8/QSYMM16</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="comment"> * @param[in] input_stride_x Stride of the source image in X dimension (in bytes)</span></div><div class="line"><a name="l00046"></a><span class="lineno"> 46</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="l00047"></a><span class="lineno"> 47</span> <span class="comment"> * @param[in] input_stride_y Stride of the source image in Y dimension (in bytes)</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</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="l00049"></a><span class="lineno"> 49</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="l00050"></a><span class="lineno"> 50</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="l00051"></a><span class="lineno"> 51</span> <span class="comment"> * @param[in] input_offset_first_element_in_bytes The offset of the first element in the source image</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> <span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> <span class="comment"> */</span></div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span> __kernel <span class="keywordtype">void</span> activation_layer_quant_f32(</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</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="l00063"></a><span class="lineno"> 63</span> #ifndef IN_PLACE</div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  ,</div><div class="line"><a name="l00065"></a><span class="lineno"> 65</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="l00066"></a><span class="lineno"> 66</span> #endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span> )</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="comment">// Get pixels pointer</span></div><div class="line"><a name="l00070"></a><span class="lineno"> 70</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="l00071"></a><span class="lineno"> 71</span> <span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</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="l00075"></a><span class="lineno"> 75</span> <span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span> </div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  <span class="comment">// Load data</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  <a class="code" href="activation__quant__helpers_8h.xhtml#a5a392548f2df67370cb15d2a5d75cd7b">TYPE</a> data = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a287e2fc366c312b468382c95bb90f91f">VLOAD</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)(0, (__global <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>.ptr);</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>  <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a> data_flt = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(data, <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>);</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span> <span class="preprocessor">#if defined(O1_VAL)</span></div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  data_flt = <a class="code" href="namespacearm__compute.xhtml#aaae2b6b1c3f4404121346a4c27b22647">round</a>(data_flt - (<span class="keywordtype">float</span>)O1_VAL) * ((float)S1_VAL);</div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span> <span class="preprocessor">#else // defined(O1_VAL)</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  data_flt = <a class="code" href="namespacearm__compute.xhtml#aaae2b6b1c3f4404121346a4c27b22647">round</a>(data_flt) * ((float)S1_VAL);</div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span> <span class="preprocessor">#endif // defined(O1_VAL)</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  data_flt = <a class="code" href="activation__float__helpers_8h.xhtml#abbc420da5dec17216bb014c05ad65304">ACTIVATION</a>(ACT, <span class="keywordtype">float</span>, data_flt, A_VAL, B_VAL);</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> </div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span> <span class="preprocessor">#if defined(O2_VAL)</span></div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  data = <a class="code" href="direct__convolution1x1_8cl.xhtml#a1f15728672380ade7a238f5e783d54d2">CONVERT_SAT</a>(<a class="code" href="namespacearm__compute.xhtml#aaae2b6b1c3f4404121346a4c27b22647">round</a>(data_flt / ((<span class="keywordtype">float</span>)S2_VAL)) + (<span class="keywordtype">float</span>)O2_VAL, <a class="code" href="activation__quant__helpers_8h.xhtml#a5a392548f2df67370cb15d2a5d75cd7b">TYPE</a>);</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span> <span class="preprocessor">#else // defined(O2_VAL)</span></div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  data = <a class="code" href="direct__convolution1x1_8cl.xhtml#a1f15728672380ade7a238f5e783d54d2">CONVERT_SAT</a>(<a class="code" href="namespacearm__compute.xhtml#aaae2b6b1c3f4404121346a4c27b22647">round</a>(data_flt / ((<span class="keywordtype">float</span>)S2_VAL)), <a class="code" href="activation__quant__helpers_8h.xhtml#a5a392548f2df67370cb15d2a5d75cd7b">TYPE</a>);</div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span> <span class="preprocessor">#endif // defined(O2_VAL)</span></div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span> </div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  <span class="comment">// Store result</span></div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  (data, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span> }</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> </div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span> <span class="preprocessor">#else // defined(FLOAT_DOMAIN)</span></div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span> <span class="comment">// Activations performed in the quantized domain</span></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> <span class="preprocessor">#if defined(ACT)</span></div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span> <span class="comment">/** This performs an activation function on quantized inputs.</span></div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span> <span class="comment"> *</span></div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span> <span class="comment"> * @note In order to perform the activation function "in-place", the pre-processor -DIN_PLACE must be passed at compile time</span></div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span> <span class="comment"> *</span></div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span> <span class="comment"> * @note Datatype should be given as a preprocessor argument using -DDATA_TYPE=type. e.g. -DDATA_TYPE=short</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> <span class="comment"> * @note Vector size should be given as a preprocessor argument using -DVEC_SIZE=size. e.g. -DVEC_SIZE=16</span></div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> <span class="comment"> * @note Activation function should be given as a preprocessor argument using -DACT=name. e.g. -DACT=TANH</span></div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span> <span class="comment"> * @note A, B variables required by some activation functions are set using -DA_VAL= and -DB_VAL= respectively.</span></div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span> <span class="comment"> * @note Quantization scales of the input/output tensors are passed in with -DS1_VAL= and -DS2_VAL= respectively.</span></div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span> <span class="comment"> * @note Quantization offsets of the input/output tensors are passed in with -DO1_VAL= and -DO2_VAL= respectively.</span></div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span> <span class="comment"> * @note Quantized value of constant zero should be given as a preprocessor argument using -DCONST_0=value. e.g. -DCONST_0=128.</span></div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span> <span class="comment"> *</span></div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span> <span class="comment"> * @param[in] input_ptr Pointer to the source image. Supported data types: QASYMM8/QSYMM16</span></div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span> <span class="comment"> * @param[in] input_stride_x Stride of the source image in X dimension (in bytes)</span></div><div class="line"><a name="l00117"></a><span class="lineno"> 117</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="l00118"></a><span class="lineno"> 118</span> <span class="comment"> * @param[in] input_stride_y Stride of the source image in Y dimension (in bytes)</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</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="l00120"></a><span class="lineno"> 120</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="l00121"></a><span class="lineno"> 121</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="l00122"></a><span class="lineno"> 122</span> <span class="comment"> * @param[in] input_offset_first_element_in_bytes The offset of the first element in the source image</span></div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span> <span class="comment"> * @param[out] output_ptr (Optional) Pointer to the destination image. Supported data types: same as @p input_ptr</span></div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span> <span class="comment"> * @param[in] output_stride_x (Optional) Stride of the destination image in X dimension (in bytes)</span></div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> <span class="comment"> * @param[in] output_step_x (Optional) output_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span> <span class="comment"> * @param[in] output_stride_y (Optional) Stride of the destination image in Y dimension (in bytes)</span></div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span> <span class="comment"> * @param[in] output_step_y (Optional) output_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span> <span class="comment"> * @param[in] output_stride_z (Optional) Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> <span class="comment"> * @param[in] output_step_z (Optional) output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span> <span class="comment"> * @param[in] output_offset_first_element_in_bytes (Optional) The offset of the first element in the destination image</span></div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span> <span class="comment"> */</span></div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span> __kernel <span class="keywordtype">void</span> activation_layer_quant(</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</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="l00134"></a><span class="lineno"> 134</span> #ifndef IN_PLACE</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>  <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="l00137"></a><span class="lineno"> 137</span> #endif <span class="comment">/* not IN_PLACE */</span></div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span> )</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="comment">// Get pixels pointer</span></div><div class="line"><a name="l00141"></a><span class="lineno"> 141</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="l00142"></a><span class="lineno"> 142</span> <span class="preprocessor">#ifdef IN_PLACE</span></div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> output = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>;</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span> <span class="preprocessor">#else </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00145"></a><span class="lineno"> 145</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="l00146"></a><span class="lineno"> 146</span> <span class="preprocessor">#endif </span><span class="comment">/* IN_PLACE */</span><span class="preprocessor"></span></div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span> </div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  <span class="comment">// Load data</span></div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  <a class="code" href="activation__quant__helpers_8h.xhtml#a5a392548f2df67370cb15d2a5d75cd7b">TYPE</a> data = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a287e2fc366c312b468382c95bb90f91f">VLOAD</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)(0, (__global <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>.ptr);</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  data = <a class="code" href="activation__quant__helpers_8h.xhtml#a66c59c0b2362216643d0e9db9a240013">PERFORM_ACTIVATION_QUANT</a>(ACT, data);</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>  <span class="comment">// Store result</span></div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  (data, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)output.<a class="code" href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">ptr</a>);</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> }</div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span> <span class="preprocessor">#endif // defined(ACT)</span></div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span> <span class="preprocessor">#endif // defined(FLOAT_DOMAIN)</span></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="activation__float__helpers_8h_xhtml"><div class="ttname"><a href="activation__float__helpers_8h.xhtml">activation_float_helpers.h</a></div></div> |
| <div class="ttc" id="depthwise__convolution__quantized_8cl_xhtml_a3fffea119c04c7680f2e9cf3fadf63b4"><div class="ttname"><a href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a></div><div class="ttdeci">#define VEC_SIZE</div><div class="ttdef"><b>Definition:</b> <a href="depthwise__convolution__quantized_8cl_source.xhtml#l00031">depthwise_convolution_quantized.cl:31</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="activation__quant__helpers_8h_xhtml_a5a392548f2df67370cb15d2a5d75cd7b"><div class="ttname"><a href="activation__quant__helpers_8h.xhtml#a5a392548f2df67370cb15d2a5d75cd7b">TYPE</a></div><div class="ttdeci">#define TYPE</div><div class="ttdef"><b>Definition:</b> <a href="activation__quant__helpers_8h_source.xhtml#l00027">activation_quant_helpers.h:27</a></div></div> |
| <div class="ttc" id="direct__convolution1x1_8cl_xhtml_a1f15728672380ade7a238f5e783d54d2"><div class="ttname"><a href="direct__convolution1x1_8cl.xhtml#a1f15728672380ade7a238f5e783d54d2">CONVERT_SAT</a></div><div class="ttdeci">#define CONVERT_SAT(a, b)</div><div class="ttdef"><b>Definition:</b> <a href="direct__convolution1x1_8cl_source.xhtml#l00030">direct_convolution1x1.cl:30</a></div></div> |
| <div class="ttc" id="activation__quant__helpers_8h_xhtml_a66c59c0b2362216643d0e9db9a240013"><div class="ttname"><a href="activation__quant__helpers_8h.xhtml#a66c59c0b2362216643d0e9db9a240013">PERFORM_ACTIVATION_QUANT</a></div><div class="ttdeci">#define PERFORM_ACTIVATION_QUANT(act, data)</div><div class="ttdef"><b>Definition:</b> <a href="activation__quant__helpers_8h_source.xhtml#l00080">activation_quant_helpers.h:80</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="activation__layer__quant_8cl_xhtml_ade2e33e6f303ce93468eef7e56d95c0c"><div class="ttname"><a href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a></div><div class="ttdeci">#define VEC_FLOAT</div><div class="ttdef"><b>Definition:</b> <a href="activation__layer__quant_8cl_source.xhtml#l00026">activation_layer_quant.cl:26</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_aaae2b6b1c3f4404121346a4c27b22647"><div class="ttname"><a href="namespacearm__compute.xhtml#aaae2b6b1c3f4404121346a4c27b22647">arm_compute::round</a></div><div class="ttdeci">int round(float x, RoundingPolicy rounding_policy)</div><div class="ttdoc">Return a rounded value of x.</div><div class="ttdef"><b>Definition:</b> <a href="_rounding_8cpp_source.xhtml#l00035">Rounding.cpp:35</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="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_acb282042d1edeeaa3cc979a206f78b54"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a></div><div class="ttdeci">#define VSTORE(size)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00198">helpers.h:198</a></div></div> |
| <div class="ttc" id="struct_tensor3_d_xhtml_acf52c23cbd7424606c10a606524e3e32"><div class="ttname"><a href="struct_tensor3_d.xhtml#acf52c23cbd7424606c10a606524e3e32">Tensor3D::ptr</a></div><div class="ttdeci">__global uchar * ptr</div><div class="ttdoc">Pointer to the starting postion of the buffer.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00360">helpers.h:360</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a287e2fc366c312b468382c95bb90f91f"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a287e2fc366c312b468382c95bb90f91f">VLOAD</a></div><div class="ttdeci">#define VLOAD(size)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00195">helpers.h:195</a></div></div> |
| <div class="ttc" id="src_2core_2_c_l_2cl__kernels_2_helpers_8h_xhtml_a6b83038822d1ae7ab619b684ed3b7fc0"><div class="ttname"><a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a6b83038822d1ae7ab619b684ed3b7fc0">TENSOR3D_DECLARATION</a></div><div class="ttdeci">#define TENSOR3D_DECLARATION(name)</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_c_l_2cl__kernels_2_helpers_8h_source.xhtml#l00283">helpers.h:283</a></div></div> |
| <div class="ttc" id="activation__quant__helpers_8h_xhtml"><div class="ttname"><a href="activation__quant__helpers_8h.xhtml">activation_quant_helpers.h</a></div></div> |
| <div class="ttc" id="activation__float__helpers_8h_xhtml_abbc420da5dec17216bb014c05ad65304"><div class="ttname"><a href="activation__float__helpers_8h.xhtml#abbc420da5dec17216bb014c05ad65304">ACTIVATION</a></div><div class="ttdeci">#define ACTIVATION(op, DATA_TYPE, x, A_VAL, B_VAL)</div><div class="ttdef"><b>Definition:</b> <a href="activation__float__helpers_8h_source.xhtml#l00073">activation_float_helpers.h:73</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="activation__layer__quant_8cl.xhtml">activation_layer_quant.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> |
