arm_compute v20.02
diff --git a/documentation/concatenate_8cl_source.xhtml b/documentation/concatenate_8cl_source.xhtml
index 6b9121d..961584a 100644
--- a/documentation/concatenate_8cl_source.xhtml
+++ b/documentation/concatenate_8cl_source.xhtml
@@ -40,7 +40,7 @@
<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">19.11.1</span>
+  <span id="projectnumber">20.02</span>
</div>
</td>
</tr>
@@ -100,7 +100,7 @@
<div class="title">concatenate.cl</div> </div>
</div><!--header-->
<div class="contents">
-<a href="concatenate_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) 2017-2019 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="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(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor">#define VEC_FLOAT VEC_DATA_TYPE(float, VEC_SIZE)</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#define VEC_INT VEC_DATA_TYPE(int, VEC_SIZE)</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#define VEC_UCHAR VEC_DATA_TYPE(uchar, VEC_SIZE)</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="preprocessor">#define CONVERT_RTE(x, type) (convert_##type##_rte((x)))</span></div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#define CONVERT_DOWN(x, type) CONVERT_RTE(x, type)</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="keyword">inline</span> <a class="code" href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a> requantize(<a class="code" href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <span class="keywordtype">float</span> in_offset, <span class="keywordtype">float</span> out_offset, <span class="keywordtype">float</span> in_scale, <span class="keywordtype">float</span> out_scale)</div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> {</div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span>  <span class="keyword">const</span> <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a> in_f32 = (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>) - (<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)((<span class="keywordtype">float</span>)in_offset)) * (<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)((<span class="keywordtype">float</span>)in_scale);</div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span>  <span class="keyword">const</span> <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a> out_f32 = in_f32 / ((<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)(<span class="keywordtype">float</span>)out_scale) + ((<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)((float)out_offset));</div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span>  <span class="keyword">const</span> <a class="code" href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a> res_u8 = <a class="code" href="direct__convolution1x1_8cl.xhtml#a1f15728672380ade7a238f5e783d54d2">CONVERT_SAT</a>(<a class="code" href="depth__convert_8cl.xhtml#a5b0d9908c0af31eaa7a31d0b5cf8e56d">CONVERT_DOWN</a>(out_f32, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#aee190caf3b3571e939ac129e12c368cd">VEC_INT</a>), <a class="code" href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a>);</div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span>  <span class="keywordflow">return</span> res_u8;</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">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> </div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="preprocessor">#if defined(DATA_TYPE) && defined(VEC_SIZE)</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="preprocessor">#if defined(DEPTH) && defined(ELEMENT_SIZE)</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> </div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="preprocessor">#if defined(INPUT1_WIDTH)</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> </div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="preprocessor">#if ELEMENT_SIZE == 1</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="preprocessor">#define COND_DATA_TYPE char</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="preprocessor">#elif ELEMENT_SIZE == 2</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> <span class="preprocessor">#define COND_DATA_TYPE short</span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="preprocessor">#elif ELEMENT_SIZE == 4</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="preprocessor">#define COND_DATA_TYPE int</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="preprocessor">#else // ELEMENT_SIZE</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="preprocessor">#error "Element size not supported"</span></div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="preprocessor">#endif // ELEMENT_SIZE</span></div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> </div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="preprocessor">#if VEC_SIZE == 2</span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="preprocessor">#define SEQ ((int2)(0, 1))</span></div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="preprocessor">#elif VEC_SIZE == 4</span></div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="preprocessor">#define SEQ ((int4)(0, 1, 2, 3))</span></div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> <span class="preprocessor">#elif VEC_SIZE == 8</span></div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span> <span class="preprocessor">#define SEQ ((int8)(0, 1, 2, 3, 4, 5, 6, 7))</span></div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span> <span class="preprocessor">#elif VEC_SIZE == 16</span></div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span> <span class="preprocessor">#define SEQ ((int16)(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15))</span></div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> <span class="preprocessor">#else // VEC_SIZE</span></div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span> <span class="preprocessor">#error "Vector size not supported"</span></div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span> <span class="preprocessor">#endif // VEC_SIZE</span></div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span> <span class="comment"></span></div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span> <span class="comment">/** This kernel concatenates two input tensors into the output tensor along the first dimension</span></div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span> <span class="comment"> *</span></div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment"> * @note The offset for the first spatial dimension has to be passed at compile time using -DWIDTH_OFFSET. i.e. -DWIDTH_OFFSET=128</span></div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment"> * @note First input tensor width should be given as a preprocessor argument using -DINPUT1_WIDTH=width. e.g. -DINPUT1_WIDTH=8</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"> * @param[in] src1_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span> <span class="comment"> * @param[in] src1_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span> <span class="comment"> * @param[in] src1_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span> <span class="comment"> * @param[in] src1_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span> <span class="comment"> * @param[in] src1_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span> <span class="comment"> * @param[in] src1_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span> <span class="comment"> * @param[in] src1_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span> <span class="comment"> * @param[in] src1_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span> <span class="comment"> * @param[in] src1_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span> <span class="comment"> * @param[in] src1_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> <span class="comment"> * @param[in] src2_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> <span class="comment"> * @param[in] src2_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span> <span class="comment"> * @param[in] src2_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span> <span class="comment"> * @param[in] src2_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span> <span class="comment"> * @param[in] src2_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> <span class="comment"> * @param[in] src2_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span> <span class="comment"> * @param[in] src2_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span> <span class="comment"> * @param[in] src2_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span> <span class="comment"> * @param[in] src2_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span> <span class="comment"> * @param[in] src2_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span> <span class="comment"> * @param[in] src1_pad_right Right paddings of the first input tensor in unit of elements</span></div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span> <span class="comment"> * @param[in] src1_pad_left Left paddings of the second input tensor in unit of elements</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> <span class="comment"> */</span></div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> __kernel <span class="keywordtype">void</span> concatenate_width_x2(</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src1),</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src2),</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>),</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  uint src1_pad_right,</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  uint src2_pad_left)</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>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span> </div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span>  <span class="comment">// Calculate input indices</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x = get_global_id(0) * (int)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>;</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> y = get_global_id(1);</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> z = get_global_id(2) % (int)DEPTH;</div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> = get_global_id(2) / (int)DEPTH;</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x1 = min(x, (<span class="keywordtype">int</span>)INPUT1_WIDTH + (<span class="keywordtype">int</span>)src1_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x2 = max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH, -(<span class="keywordtype">int</span>)src2_pad_left);</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> </div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span>  <span class="comment">// Calculate inputs and output addresses</span></div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  <span class="keyword">const</span> __global uchar *in1_ptr = src1_ptr + (int)src1_offset_first_element_in_bytes + x1 * (<span class="keywordtype">int</span>)src1_stride_x + y * (int)src1_stride_y + z * (<span class="keywordtype">int</span>)src1_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src1_stride_w;</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  <span class="keyword">const</span> __global uchar *in2_ptr = src2_ptr + (int)src2_offset_first_element_in_bytes + x2 * (<span class="keywordtype">int</span>)src2_stride_x + y * (int)src2_stride_y + z * (<span class="keywordtype">int</span>)src2_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src2_stride_w;</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> </div><div class="line"><a name="l00130"></a><span class="lineno"> 130</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  src1_values = <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> *)in1_ptr);</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  src2_values = <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> *)in2_ptr);</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span> </div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_IN2) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_IN2) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  src1_values = requantize(src1_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  src2_values = requantize(src2_values, OFFSET_IN2, OFFSET_OUT, SCALE_IN2, SCALE_OUT);</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_IN2) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_IN2) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) x_coords = SEQ + (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(x);</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  <span class="keyword">const</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src2_values, src1_values, cond);</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span> </div><div class="line"><a name="l00143"></a><span class="lineno"> 143</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="l00144"></a><span class="lineno"> 144</span>  (values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr);</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span> }</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span> </div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span> <span class="preprocessor">#if defined(INPUT2_WIDTH) && defined(INPUT3_WIDTH)</span></div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span> <span class="comment">/** This kernel concatenates four input tensors into the output tensor along the first dimension</span></div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span> <span class="comment"> *</span></div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span> <span class="comment"> * @note The offset for the first spatial dimension has to be passed at compile time using -DWIDTH_OFFSET. i.e. -DWIDTH_OFFSET=128</span></div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span> <span class="comment"> * @note First input tensor width should be given as a preprocessor argument using -DINPUT1_WIDTH=width. e.g. -DINPUT1_WIDTH=8</span></div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span> <span class="comment"> * @note Second input tensor width should be given as a preprocessor argument using -DINPUT2_WIDTH=width. e.g. -DINPUT2_WIDTH=8</span></div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> <span class="comment"> * @note Third input tensor width should be given as a preprocessor argument using -DINPUT3_WIDTH=width. e.g. -DINPUT3_WIDTH=8</span></div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span> <span class="comment"> *</span></div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span> <span class="comment"> * @param[in] src1_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span> <span class="comment"> * @param[in] src1_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span> <span class="comment"> * @param[in] src1_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span> <span class="comment"> * @param[in] src1_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span> <span class="comment"> * @param[in] src1_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span> <span class="comment"> * @param[in] src1_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span> <span class="comment"> * @param[in] src1_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span> <span class="comment"> * @param[in] src1_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span> <span class="comment"> * @param[in] src1_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span> <span class="comment"> * @param[in] src1_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span> <span class="comment"> * @param[in] src2_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span> <span class="comment"> * @param[in] src2_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span> <span class="comment"> * @param[in] src2_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span> <span class="comment"> * @param[in] src2_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span> <span class="comment"> * @param[in] src2_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span> <span class="comment"> * @param[in] src2_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span> <span class="comment"> * @param[in] src2_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span> <span class="comment"> * @param[in] src2_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span> <span class="comment"> * @param[in] src2_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span> <span class="comment"> * @param[in] src2_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span> <span class="comment"> * @param[in] src3_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span> <span class="comment"> * @param[in] src3_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span> <span class="comment"> * @param[in] src3_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span> <span class="comment"> * @param[in] src3_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span> <span class="comment"> * @param[in] src3_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span> <span class="comment"> * @param[in] src3_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span> <span class="comment"> * @param[in] src3_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span> <span class="comment"> * @param[in] src3_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span> <span class="comment"> * @param[in] src3_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span> <span class="comment"> * @param[in] src3_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> <span class="comment"> * @param[in] src4_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span> <span class="comment"> * @param[in] src4_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span> <span class="comment"> * @param[in] src4_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span> <span class="comment"> * @param[in] src4_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span> <span class="comment"> * @param[in] src4_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span> <span class="comment"> * @param[in] src4_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span> <span class="comment"> * @param[in] src4_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span> <span class="comment"> * @param[in] src4_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span> <span class="comment"> * @param[in] src4_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span> <span class="comment"> * @param[in] src4_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> <span class="comment"> * @param[in] src1_pad_right Right paddings of the first input tensor in unit of elements</span></div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span> <span class="comment"> * @param[in] src2_pad_left Left paddings of the second input tensor in unit of elements</span></div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span> <span class="comment"> * @param[in] src2_pad_right Right paddings of the second input tensor in unit of elements</span></div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span> <span class="comment"> * @param[in] src3_pad_left Left paddings of the third input tensor in unit of elements</span></div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span> <span class="comment"> * @param[in] src3_pad_right Right paddings of the third input tensor in unit of elements</span></div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span> <span class="comment"> * @param[in] src4_pad_left Left paddings of the fourth input tensor in unit of elements</span></div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span> <span class="comment"> */</span></div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span> __kernel <span class="keywordtype">void</span> concatenate_width_x4(</div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src1),</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#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src2),</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src3),</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#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src4),</div><div class="line"><a name="l00220"></a><span class="lineno"> 220</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>),</div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  uint src1_pad_right,</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  uint src2_pad_left,</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  uint src2_pad_right,</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  uint src3_pad_left,</div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  uint src3_pad_right,</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  uint src4_pad_left)</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span> {</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span> </div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <span class="comment">// Calculate input indices</span></div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x = get_global_id(0) * (int)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>;</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> y = get_global_id(1);</div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> z = get_global_id(2) % (int)DEPTH;</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> = get_global_id(2) / (int)DEPTH;</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span> </div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x1 = min(x, (<span class="keywordtype">int</span>)INPUT1_WIDTH + (<span class="keywordtype">int</span>)src1_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x2 = min(max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH, -(<span class="keywordtype">int</span>)src2_pad_left), (<span class="keywordtype">int</span>)INPUT2_WIDTH + (<span class="keywordtype">int</span>)src2_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x3 = min(max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH - (<span class="keywordtype">int</span>)INPUT2_WIDTH, -(<span class="keywordtype">int</span>)src3_pad_left), (<span class="keywordtype">int</span>)INPUT3_WIDTH + (<span class="keywordtype">int</span>)src3_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x4 = max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH - (<span class="keywordtype">int</span>)INPUT2_WIDTH - (<span class="keywordtype">int</span>)INPUT3_WIDTH, -(<span class="keywordtype">int</span>)src4_pad_left);</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="comment">// Calculate inputs and output addresses</span></div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  <span class="keyword">const</span> __global uchar *in1_ptr = src1_ptr + (int)src1_offset_first_element_in_bytes + x1 * (<span class="keywordtype">int</span>)src1_stride_x + y * (int)src1_stride_y + z * (<span class="keywordtype">int</span>)src1_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src1_stride_w;</div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  <span class="keyword">const</span> __global uchar *in2_ptr = src2_ptr + (int)src2_offset_first_element_in_bytes + x2 * (<span class="keywordtype">int</span>)src2_stride_x + y * (int)src2_stride_y + z * (<span class="keywordtype">int</span>)src2_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src2_stride_w;</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span>  <span class="keyword">const</span> __global uchar *in3_ptr = src3_ptr + (int)src3_offset_first_element_in_bytes + x3 * (<span class="keywordtype">int</span>)src3_stride_x + y * (int)src3_stride_y + z * (<span class="keywordtype">int</span>)src3_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src3_stride_w;</div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  <span class="keyword">const</span> __global uchar *in4_ptr = src4_ptr + (int)src4_offset_first_element_in_bytes + x4 * (<span class="keywordtype">int</span>)src4_stride_x + y * (int)src4_stride_y + z * (<span class="keywordtype">int</span>)src4_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src4_stride_w;</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span> </div><div class="line"><a name="l00247"></a><span class="lineno"> 247</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  src1_values = <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> *)in1_ptr);</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  src2_values = <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> *)in2_ptr);</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  src3_values = <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> *)in3_ptr);</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  src4_values = <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> *)in4_ptr);</div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span> </div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) && defined(OFFSET_IN2) && defined(SCALE_IN2) && defined(OFFSET_IN3) && defined(SCALE_IN3) && defined(OFFSET_IN4) && defined(SCALE_IN4)</span></div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  src1_values = requantize(src1_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  src2_values = requantize(src2_values, OFFSET_IN2, OFFSET_OUT, SCALE_IN2, SCALE_OUT);</div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  src3_values = requantize(src3_values, OFFSET_IN3, OFFSET_OUT, SCALE_IN3, SCALE_OUT);</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  src4_values = requantize(src4_values, OFFSET_IN4, OFFSET_OUT, SCALE_IN4, SCALE_OUT);</div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) && defined(OFFSET_IN2) && defined(SCALE_IN2) && defined(OFFSET_IN3) && defined(SCALE_IN3) && defined(OFFSET_IN4) && defined(SCALE_IN4) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span> </div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) x_coords = SEQ + (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(x);</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="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond_in2 = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond_in3 = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH + INPUT2_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond_in4 = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH + INPUT2_WIDTH + INPUT3_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span> </div><div class="line"><a name="l00269"></a><span class="lineno"> 269</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src2_values, src1_values, cond_in2);</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src3_values, values, cond_in3);</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src4_values, values, cond_in4);</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span> </div><div class="line"><a name="l00274"></a><span class="lineno"> 274</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="l00275"></a><span class="lineno"> 275</span>  (values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr);</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span> }</div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(INPUT2_WIDTH) && defined(INPUT3_WIDTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(INPUT1_WIDTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(DEPTH) && defined(ELEMENT_SIZE) */</span><span class="preprocessor"></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> <span class="preprocessor">#if defined(WIDTH_OFFSET) && defined(DEPTH)</span></div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span> <span class="comment">/** This kernel concatenates the input tensor into the output tensor along the first dimension</span></div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span> <span class="comment"> *</span></div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span> <span class="comment"> * @note The offset for the first spatial dimension has to be passed at compile time using -DWIDTH_OFFSET. i.e. -DWIDTH_OFFSET=128</span></div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span> <span class="comment"> *</span></div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00290"></a><span class="lineno"> 290</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="l00291"></a><span class="lineno"> 291</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="l00292"></a><span class="lineno"> 292</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="l00293"></a><span class="lineno"> 293</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="l00294"></a><span class="lineno"> 294</span> <span class="comment"> * @param[in] src_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> <span class="comment"> * @param[in] src_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span> <span class="comment"> * @param[in] src_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span> <span class="comment"> * @param[in] src_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00298"></a><span class="lineno"> 298</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="l00299"></a><span class="lineno"> 299</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr</span></div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span> <span class="comment"> */</span></div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span> </div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span> __kernel <span class="keywordtype">void</span> concatenate_width(</div><div class="line"><a name="l00312"></a><span class="lineno"> 312</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#a989ab3e96426615bb98e04e0235088ca">src</a>),</div><div class="line"><a name="l00313"></a><span class="lineno"> 313</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>))</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span> {</div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</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#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, DEPTH);</div><div class="line"><a name="l00316"></a><span class="lineno"> 316</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span> </div><div class="line"><a name="l00318"></a><span class="lineno"> 318</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span>  source_values = <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#a989ab3e96426615bb98e04e0235088ca">src</a>.ptr);</div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span> </div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>  <span class="keyword">const</span> <a class="code" href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a> out = requantize(source_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</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#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00324"></a><span class="lineno"> 324</span>  (out, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr) + WIDTH_OFFSET);</div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span> <span class="preprocessor">#else </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00326"></a><span class="lineno"> 326</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="l00327"></a><span class="lineno"> 327</span>  (source_values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr) + WIDTH_OFFSET);</div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></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> </div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(WIDTH_OFFSET) && defined(DEPTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span> </div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span> <span class="preprocessor">#if defined(HEIGHT_OFFSET) && defined(DEPTH) && defined(VEC_SIZE)</span></div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span> <span class="comment">/** This kernel concatenates the input tensor into the output tensor along the second dimension</span></div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span> <span class="comment"> *</span></div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span> <span class="comment"> * @note Vector sizes supported are 2,4,8 and 16.</span></div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span> <span class="comment"> * @note The offset for the second spatial dimension has to be passed at compile time using -DHEIGHT_OFFSET. i.e. -DHEIGHT_OFFSET=128</span></div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span> <span class="comment"> *</span></div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00343"></a><span class="lineno"> 343</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="l00344"></a><span class="lineno"> 344</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="l00345"></a><span class="lineno"> 345</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="l00346"></a><span class="lineno"> 346</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="l00347"></a><span class="lineno"> 347</span> <span class="comment"> * @param[in] src_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span> <span class="comment"> * @param[in] src_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span> <span class="comment"> * @param[in] src_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span> <span class="comment"> * @param[in] src_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00351"></a><span class="lineno"> 351</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="l00352"></a><span class="lineno"> 352</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr</span></div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00356"></a><span class="lineno"> 356</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00357"></a><span class="lineno"> 357</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span> <span class="comment"> */</span></div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span> </div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span> __kernel <span class="keywordtype">void</span> concatenate_height(</div><div class="line"><a name="l00365"></a><span class="lineno"> 365</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#a989ab3e96426615bb98e04e0235088ca">src</a>),</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#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>))</div><div class="line"><a name="l00367"></a><span class="lineno"> 367</span> {</div><div class="line"><a name="l00368"></a><span class="lineno"> 368</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</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#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, DEPTH);</div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00370"></a><span class="lineno"> 370</span> </div><div class="line"><a name="l00371"></a><span class="lineno"> 371</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span>  source_values = <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#a989ab3e96426615bb98e04e0235088ca">src</a>.ptr);</div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span> </div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span>  <span class="keyword">const</span> <a class="code" href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a> out = requantize(source_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00376"></a><span class="lineno"> 376</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="l00377"></a><span class="lineno"> 377</span>  (out, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr + HEIGHT_OFFSET * dst_stride_y));</div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span> <span class="preprocessor">#else </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></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#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span>  (source_values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr + HEIGHT_OFFSET * dst_stride_y));</div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span> }</div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span> </div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(HEIGHT_OFFSET) && defined(DEPTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00385"></a><span class="lineno"> 385</span> <span class="comment"></span></div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span> <span class="comment">/** This kernel concatenates the input tensor into the output tensor along the third dimension</span></div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span> <span class="comment"> *</span></div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00390"></a><span class="lineno"> 390</span> <span class="comment"> *</span></div><div class="line"><a name="l00391"></a><span class="lineno"> 391</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: F16, F32</span></div><div class="line"><a name="l00392"></a><span class="lineno"> 392</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="l00393"></a><span class="lineno"> 393</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="l00394"></a><span class="lineno"> 394</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="l00395"></a><span class="lineno"> 395</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="l00396"></a><span class="lineno"> 396</span> <span class="comment"> * @param[in] src_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span> <span class="comment"> * @param[in] src_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00398"></a><span class="lineno"> 398</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="l00399"></a><span class="lineno"> 399</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr</span></div><div class="line"><a name="l00400"></a><span class="lineno"> 400</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00402"></a><span class="lineno"> 402</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00403"></a><span class="lineno"> 403</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00404"></a><span class="lineno"> 404</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span> <span class="comment"> * @param[in] offsets The offsets to the first valid element of the output tensor in bytes</span></div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span> <span class="comment"> */</span></div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span> __kernel <span class="keywordtype">void</span> concatenate(</div><div class="line"><a name="l00410"></a><span class="lineno"> 410</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#a989ab3e96426615bb98e04e0235088ca">src</a>),</div><div class="line"><a name="l00411"></a><span class="lineno"> 411</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>),</div><div class="line"><a name="l00412"></a><span class="lineno"> 412</span>  <span class="keywordtype">int</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>)</div><div class="line"><a name="l00413"></a><span class="lineno"> 413</span> {</div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span>  <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</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#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>);</div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span>  <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>);</div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span> </div><div class="line"><a name="l00417"></a><span class="lineno"> 417</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span>  source_values = <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#a989ab3e96426615bb98e04e0235088ca">src</a>.ptr);</div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span> </div><div class="line"><a name="l00420"></a><span class="lineno"> 420</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00421"></a><span class="lineno"> 421</span>  source_values = requantize(source_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span> </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#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span>  (source_values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr + <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>));</div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span> }</div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(DATA_TYPE) && defined(VEC_SIZE) */</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>
+<a href="concatenate_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) 2017-2020 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(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor">#define VEC_FLOAT VEC_DATA_TYPE(float, VEC_SIZE)</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#define VEC_INT VEC_DATA_TYPE(int, VEC_SIZE)</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#define VEC_QUANT VEC_DATA_TYPE(DATA_TYPE, VEC_SIZE)</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="preprocessor">#define CONVERT_RTE(x, type) (convert_##type##_rte((x)))</span></div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#define CONVERT_DOWN(x, type) CONVERT_RTE(x, type)</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="keyword">inline</span> VEC_QUANT requantize(VEC_QUANT <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <span class="keywordtype">float</span> in_offset, <span class="keywordtype">float</span> out_offset, <span class="keywordtype">float</span> in_scale, <span class="keywordtype">float</span> out_scale)</div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> {</div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span>  <span class="keyword">const</span> <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a> in_f32 = (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>) - (<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)((<span class="keywordtype">float</span>)in_offset)) * (<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)((<span class="keywordtype">float</span>)in_scale);</div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span>  <span class="keyword">const</span> <a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a> out_f32 = in_f32 / ((<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)(<span class="keywordtype">float</span>)out_scale) + ((<a class="code" href="activation__layer__quant_8cl.xhtml#ade2e33e6f303ce93468eef7e56d95c0c">VEC_FLOAT</a>)((float)out_offset));</div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span>  <span class="keyword">const</span> VEC_QUANT res_q8 = <a class="code" href="direct__convolution1x1_8cl.xhtml#a1f15728672380ade7a238f5e783d54d2">CONVERT_SAT</a>(<a class="code" href="depth__convert_8cl.xhtml#a5b0d9908c0af31eaa7a31d0b5cf8e56d">CONVERT_DOWN</a>(out_f32, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#aee190caf3b3571e939ac129e12c368cd">VEC_INT</a>), VEC_QUANT);</div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span>  <span class="keywordflow">return</span> res_q8;</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">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> </div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="preprocessor">#if defined(DATA_TYPE) && defined(VEC_SIZE)</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="preprocessor">#if defined(DEPTH) && defined(ELEMENT_SIZE)</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> </div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="preprocessor">#if defined(INPUT1_WIDTH)</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> </div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="preprocessor">#if ELEMENT_SIZE == 1</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="preprocessor">#define COND_DATA_TYPE char</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="preprocessor">#elif ELEMENT_SIZE == 2</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> <span class="preprocessor">#define COND_DATA_TYPE short</span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="preprocessor">#elif ELEMENT_SIZE == 4</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="preprocessor">#define COND_DATA_TYPE int</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="preprocessor">#else // ELEMENT_SIZE</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="preprocessor">#error "Element size not supported"</span></div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="preprocessor">#endif // ELEMENT_SIZE</span></div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> </div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="preprocessor">#if VEC_SIZE == 2</span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="preprocessor">#define SEQ ((int2)(0, 1))</span></div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="preprocessor">#elif VEC_SIZE == 4</span></div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="preprocessor">#define SEQ ((int4)(0, 1, 2, 3))</span></div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> <span class="preprocessor">#elif VEC_SIZE == 8</span></div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span> <span class="preprocessor">#define SEQ ((int8)(0, 1, 2, 3, 4, 5, 6, 7))</span></div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span> <span class="preprocessor">#elif VEC_SIZE == 16</span></div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span> <span class="preprocessor">#define SEQ ((int16)(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15))</span></div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> <span class="preprocessor">#else // VEC_SIZE</span></div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span> <span class="preprocessor">#error "Vector size not supported"</span></div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span> <span class="preprocessor">#endif // VEC_SIZE</span></div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span> <span class="comment"></span></div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span> <span class="comment">/** This kernel concatenates two input tensors into the output tensor along the first dimension</span></div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span> <span class="comment"> *</span></div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment"> * @note The offset for the first spatial dimension has to be passed at compile time using -DWIDTH_OFFSET. i.e. -DWIDTH_OFFSET=128</span></div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment"> * @note First input tensor width should be given as a preprocessor argument using -DINPUT1_WIDTH=width. e.g. -DINPUT1_WIDTH=8</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"> * @param[in] src1_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span> <span class="comment"> * @param[in] src1_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span> <span class="comment"> * @param[in] src1_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span> <span class="comment"> * @param[in] src1_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span> <span class="comment"> * @param[in] src1_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span> <span class="comment"> * @param[in] src1_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span> <span class="comment"> * @param[in] src1_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span> <span class="comment"> * @param[in] src1_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span> <span class="comment"> * @param[in] src1_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span> <span class="comment"> * @param[in] src1_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> <span class="comment"> * @param[in] src2_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> <span class="comment"> * @param[in] src2_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span> <span class="comment"> * @param[in] src2_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span> <span class="comment"> * @param[in] src2_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span> <span class="comment"> * @param[in] src2_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> <span class="comment"> * @param[in] src2_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span> <span class="comment"> * @param[in] src2_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span> <span class="comment"> * @param[in] src2_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span> <span class="comment"> * @param[in] src2_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span> <span class="comment"> * @param[in] src2_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span> <span class="comment"> * @param[in] src1_pad_right Right paddings of the first input tensor in unit of elements</span></div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span> <span class="comment"> * @param[in] src1_pad_left Left paddings of the second input tensor in unit of elements</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> <span class="comment"> */</span></div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> __kernel <span class="keywordtype">void</span> concatenate_width_x2(</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src1),</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src2),</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>),</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  uint src1_pad_right,</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  uint src2_pad_left)</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>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span> </div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span>  <span class="comment">// Calculate input indices</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x = get_global_id(0) * (int)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>;</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> y = get_global_id(1);</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> z = get_global_id(2) % (int)DEPTH;</div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> = get_global_id(2) / (int)DEPTH;</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x1 = min(x, (<span class="keywordtype">int</span>)INPUT1_WIDTH + (<span class="keywordtype">int</span>)src1_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x2 = max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH, -(<span class="keywordtype">int</span>)src2_pad_left);</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> </div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span>  <span class="comment">// Calculate inputs and output addresses</span></div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  <span class="keyword">const</span> __global uchar *in1_ptr = src1_ptr + (int)src1_offset_first_element_in_bytes + x1 * (<span class="keywordtype">int</span>)src1_stride_x + y * (int)src1_stride_y + z * (<span class="keywordtype">int</span>)src1_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src1_stride_w;</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  <span class="keyword">const</span> __global uchar *in2_ptr = src2_ptr + (int)src2_offset_first_element_in_bytes + x2 * (<span class="keywordtype">int</span>)src2_stride_x + y * (int)src2_stride_y + z * (<span class="keywordtype">int</span>)src2_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src2_stride_w;</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> </div><div class="line"><a name="l00130"></a><span class="lineno"> 130</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  src1_values = <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> *)in1_ptr);</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  src2_values = <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> *)in2_ptr);</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span> </div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_IN2) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_IN2) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  src1_values = requantize(src1_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  src2_values = requantize(src2_values, OFFSET_IN2, OFFSET_OUT, SCALE_IN2, SCALE_OUT);</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_IN2) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_IN2) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) x_coords = SEQ + (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(x);</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  <span class="keyword">const</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src2_values, src1_values, cond);</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span> </div><div class="line"><a name="l00143"></a><span class="lineno"> 143</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="l00144"></a><span class="lineno"> 144</span>  (values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr);</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span> }</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span> </div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span> <span class="preprocessor">#if defined(INPUT2_WIDTH) && defined(INPUT3_WIDTH)</span></div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span> <span class="comment">/** This kernel concatenates four input tensors into the output tensor along the first dimension</span></div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span> <span class="comment"> *</span></div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span> <span class="comment"> * @note The offset for the first spatial dimension has to be passed at compile time using -DWIDTH_OFFSET. i.e. -DWIDTH_OFFSET=128</span></div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span> <span class="comment"> * @note First input tensor width should be given as a preprocessor argument using -DINPUT1_WIDTH=width. e.g. -DINPUT1_WIDTH=8</span></div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span> <span class="comment"> * @note Second input tensor width should be given as a preprocessor argument using -DINPUT2_WIDTH=width. e.g. -DINPUT2_WIDTH=8</span></div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> <span class="comment"> * @note Third input tensor width should be given as a preprocessor argument using -DINPUT3_WIDTH=width. e.g. -DINPUT3_WIDTH=8</span></div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span> <span class="comment"> *</span></div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span> <span class="comment"> * @param[in] src1_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span> <span class="comment"> * @param[in] src1_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span> <span class="comment"> * @param[in] src1_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span> <span class="comment"> * @param[in] src1_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span> <span class="comment"> * @param[in] src1_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span> <span class="comment"> * @param[in] src1_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span> <span class="comment"> * @param[in] src1_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span> <span class="comment"> * @param[in] src1_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span> <span class="comment"> * @param[in] src1_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span> <span class="comment"> * @param[in] src1_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span> <span class="comment"> * @param[in] src2_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span> <span class="comment"> * @param[in] src2_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span> <span class="comment"> * @param[in] src2_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span> <span class="comment"> * @param[in] src2_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span> <span class="comment"> * @param[in] src2_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span> <span class="comment"> * @param[in] src2_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span> <span class="comment"> * @param[in] src2_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span> <span class="comment"> * @param[in] src2_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span> <span class="comment"> * @param[in] src2_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span> <span class="comment"> * @param[in] src2_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span> <span class="comment"> * @param[in] src3_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span> <span class="comment"> * @param[in] src3_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span> <span class="comment"> * @param[in] src3_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span> <span class="comment"> * @param[in] src3_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span> <span class="comment"> * @param[in] src3_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span> <span class="comment"> * @param[in] src3_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span> <span class="comment"> * @param[in] src3_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span> <span class="comment"> * @param[in] src3_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span> <span class="comment"> * @param[in] src3_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span> <span class="comment"> * @param[in] src3_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> <span class="comment"> * @param[in] src4_ptr Pointer to the source tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span> <span class="comment"> * @param[in] src4_stride_x Stride of the source tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span> <span class="comment"> * @param[in] src4_step_x src_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span> <span class="comment"> * @param[in] src4_stride_y Stride of the source tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span> <span class="comment"> * @param[in] src4_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span> <span class="comment"> * @param[in] src4_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span> <span class="comment"> * @param[in] src4_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span> <span class="comment"> * @param[in] src4_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span> <span class="comment"> * @param[in] src4_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span> <span class="comment"> * @param[in] src4_offset_first_element_in_bytes The offset of the first element in the source tensor</span></div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src1_ptr</span></div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> <span class="comment"> * @param[in] src1_pad_right Right paddings of the first input tensor in unit of elements</span></div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span> <span class="comment"> * @param[in] src2_pad_left Left paddings of the second input tensor in unit of elements</span></div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span> <span class="comment"> * @param[in] src2_pad_right Right paddings of the second input tensor in unit of elements</span></div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span> <span class="comment"> * @param[in] src3_pad_left Left paddings of the third input tensor in unit of elements</span></div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span> <span class="comment"> * @param[in] src3_pad_right Right paddings of the third input tensor in unit of elements</span></div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span> <span class="comment"> * @param[in] src4_pad_left Left paddings of the fourth input tensor in unit of elements</span></div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span> <span class="comment"> */</span></div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span> __kernel <span class="keywordtype">void</span> concatenate_width_x4(</div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src1),</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#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src2),</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src3),</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#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(src4),</div><div class="line"><a name="l00220"></a><span class="lineno"> 220</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>),</div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  uint src1_pad_right,</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  uint src2_pad_left,</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  uint src2_pad_right,</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  uint src3_pad_left,</div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  uint src3_pad_right,</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  uint src4_pad_left)</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span> {</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span> </div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <span class="comment">// Calculate input indices</span></div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x = get_global_id(0) * (int)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>;</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> y = get_global_id(1);</div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> z = get_global_id(2) % (int)DEPTH;</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> = get_global_id(2) / (int)DEPTH;</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span> </div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x1 = min(x, (<span class="keywordtype">int</span>)INPUT1_WIDTH + (<span class="keywordtype">int</span>)src1_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x2 = min(max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH, -(<span class="keywordtype">int</span>)src2_pad_left), (<span class="keywordtype">int</span>)INPUT2_WIDTH + (<span class="keywordtype">int</span>)src2_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x3 = min(max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH - (<span class="keywordtype">int</span>)INPUT2_WIDTH, -(<span class="keywordtype">int</span>)src3_pad_left), (<span class="keywordtype">int</span>)INPUT3_WIDTH + (<span class="keywordtype">int</span>)src3_pad_right - (<span class="keywordtype">int</span>)<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>);</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> x4 = max(x - (<span class="keywordtype">int</span>)INPUT1_WIDTH - (<span class="keywordtype">int</span>)INPUT2_WIDTH - (<span class="keywordtype">int</span>)INPUT3_WIDTH, -(<span class="keywordtype">int</span>)src4_pad_left);</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="comment">// Calculate inputs and output addresses</span></div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  <span class="keyword">const</span> __global uchar *in1_ptr = src1_ptr + (int)src1_offset_first_element_in_bytes + x1 * (<span class="keywordtype">int</span>)src1_stride_x + y * (int)src1_stride_y + z * (<span class="keywordtype">int</span>)src1_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src1_stride_w;</div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  <span class="keyword">const</span> __global uchar *in2_ptr = src2_ptr + (int)src2_offset_first_element_in_bytes + x2 * (<span class="keywordtype">int</span>)src2_stride_x + y * (int)src2_stride_y + z * (<span class="keywordtype">int</span>)src2_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src2_stride_w;</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span>  <span class="keyword">const</span> __global uchar *in3_ptr = src3_ptr + (int)src3_offset_first_element_in_bytes + x3 * (<span class="keywordtype">int</span>)src3_stride_x + y * (int)src3_stride_y + z * (<span class="keywordtype">int</span>)src3_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src3_stride_w;</div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  <span class="keyword">const</span> __global uchar *in4_ptr = src4_ptr + (int)src4_offset_first_element_in_bytes + x4 * (<span class="keywordtype">int</span>)src4_stride_x + y * (int)src4_stride_y + z * (<span class="keywordtype">int</span>)src4_stride_z + <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a1a367830ae09bf6138df822888ec1d71">w</a> * (int)src4_stride_w;</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span> </div><div class="line"><a name="l00247"></a><span class="lineno"> 247</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  src1_values = <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> *)in1_ptr);</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  src2_values = <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> *)in2_ptr);</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  src3_values = <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> *)in3_ptr);</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  src4_values = <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> *)in4_ptr);</div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span> </div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) && defined(OFFSET_IN2) && defined(SCALE_IN2) && defined(OFFSET_IN3) && defined(SCALE_IN3) && defined(OFFSET_IN4) && defined(SCALE_IN4)</span></div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  src1_values = requantize(src1_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  src2_values = requantize(src2_values, OFFSET_IN2, OFFSET_OUT, SCALE_IN2, SCALE_OUT);</div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  src3_values = requantize(src3_values, OFFSET_IN3, OFFSET_OUT, SCALE_IN3, SCALE_OUT);</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  src4_values = requantize(src4_values, OFFSET_IN4, OFFSET_OUT, SCALE_IN4, SCALE_OUT);</div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) && defined(OFFSET_IN2) && defined(SCALE_IN2) && defined(OFFSET_IN3) && defined(SCALE_IN3) && defined(OFFSET_IN4) && defined(SCALE_IN4) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span> </div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) x_coords = SEQ + (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(x);</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="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond_in2 = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond_in3 = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH + INPUT2_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>  <span class="keyword">const</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>) cond_in4 = <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#aa8d95ba04fc73845abc6045952cae5be">CONVERT</a>(x_coords < (<a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<span class="keywordtype">int</span>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>))(INPUT1_WIDTH + INPUT2_WIDTH + INPUT3_WIDTH), <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(COND_DATA_TYPE, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>));</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span> </div><div class="line"><a name="l00269"></a><span class="lineno"> 269</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src2_values, src1_values, cond_in2);</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src3_values, values, cond_in3);</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  values = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af77145fbdc6b0c8931148f5597d9de53">select</a>(src4_values, values, cond_in4);</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span> </div><div class="line"><a name="l00274"></a><span class="lineno"> 274</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="l00275"></a><span class="lineno"> 275</span>  (values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr);</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span> }</div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(INPUT2_WIDTH) && defined(INPUT3_WIDTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(INPUT1_WIDTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(DEPTH) && defined(ELEMENT_SIZE) */</span><span class="preprocessor"></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> <span class="preprocessor">#if defined(WIDTH_OFFSET) && defined(DEPTH)</span></div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span> <span class="comment">/** This kernel concatenates the input tensor into the output tensor along the first dimension</span></div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span> <span class="comment"> *</span></div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span> <span class="comment"> * @note The offset for the first spatial dimension has to be passed at compile time using -DWIDTH_OFFSET. i.e. -DWIDTH_OFFSET=128</span></div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span> <span class="comment"> *</span></div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00290"></a><span class="lineno"> 290</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="l00291"></a><span class="lineno"> 291</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="l00292"></a><span class="lineno"> 292</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="l00293"></a><span class="lineno"> 293</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="l00294"></a><span class="lineno"> 294</span> <span class="comment"> * @param[in] src_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> <span class="comment"> * @param[in] src_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span> <span class="comment"> * @param[in] src_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span> <span class="comment"> * @param[in] src_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00298"></a><span class="lineno"> 298</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="l00299"></a><span class="lineno"> 299</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr</span></div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span> <span class="comment"> */</span></div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span> </div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span> __kernel <span class="keywordtype">void</span> concatenate_width(</div><div class="line"><a name="l00312"></a><span class="lineno"> 312</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#a989ab3e96426615bb98e04e0235088ca">src</a>),</div><div class="line"><a name="l00313"></a><span class="lineno"> 313</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>))</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span> {</div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</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#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, DEPTH);</div><div class="line"><a name="l00316"></a><span class="lineno"> 316</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span> </div><div class="line"><a name="l00318"></a><span class="lineno"> 318</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span>  source_values = <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#a989ab3e96426615bb98e04e0235088ca">src</a>.ptr);</div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span> </div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>  <span class="keyword">const</span> VEC_QUANT out = requantize(source_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</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#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00324"></a><span class="lineno"> 324</span>  (out, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr) + WIDTH_OFFSET);</div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span> <span class="preprocessor">#else </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00326"></a><span class="lineno"> 326</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="l00327"></a><span class="lineno"> 327</span>  (source_values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr) + WIDTH_OFFSET);</div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></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> </div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(WIDTH_OFFSET) && defined(DEPTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span> </div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span> <span class="preprocessor">#if defined(HEIGHT_OFFSET) && defined(DEPTH) && defined(VEC_SIZE)</span></div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span> <span class="comment">/** This kernel concatenates the input tensor into the output tensor along the second dimension</span></div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span> <span class="comment"> *</span></div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span> <span class="comment"> * @note Vector sizes supported are 2,4,8 and 16.</span></div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span> <span class="comment"> * @note The offset for the second spatial dimension has to be passed at compile time using -DHEIGHT_OFFSET. i.e. -DHEIGHT_OFFSET=128</span></div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span> <span class="comment"> * @note Tensor depth should be given as a preprocessor argument using -DDEPTH=size. e.g. -DDEPTH=16</span></div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span> <span class="comment"> *</span></div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/F32</span></div><div class="line"><a name="l00343"></a><span class="lineno"> 343</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="l00344"></a><span class="lineno"> 344</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="l00345"></a><span class="lineno"> 345</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="l00346"></a><span class="lineno"> 346</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="l00347"></a><span class="lineno"> 347</span> <span class="comment"> * @param[in] src_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span> <span class="comment"> * @param[in] src_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span> <span class="comment"> * @param[in] src_stride_w Stride of the first source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span> <span class="comment"> * @param[in] src_step_w src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00351"></a><span class="lineno"> 351</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="l00352"></a><span class="lineno"> 352</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr</span></div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00356"></a><span class="lineno"> 356</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00357"></a><span class="lineno"> 357</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span> <span class="comment"> * @param[in] dst_stride_w Stride of the destination tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span> <span class="comment"> * @param[in] dst_step_w output_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span> <span class="comment"> */</span></div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span> </div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span> __kernel <span class="keywordtype">void</span> concatenate_height(</div><div class="line"><a name="l00365"></a><span class="lineno"> 365</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#a989ab3e96426615bb98e04e0235088ca">src</a>),</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#a481bdc6d61b3df9dcdbdb244f0f97790">TENSOR4D_DECLARATION</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>))</div><div class="line"><a name="l00367"></a><span class="lineno"> 367</span> {</div><div class="line"><a name="l00368"></a><span class="lineno"> 368</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</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#a23b9032d1b9d59547545e457f82ee478">CONVERT_TO_TENSOR4D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>, DEPTH);</div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span>  <a class="code" href="struct_tensor4_d.xhtml">Tensor4D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>, DEPTH);</div><div class="line"><a name="l00370"></a><span class="lineno"> 370</span> </div><div class="line"><a name="l00371"></a><span class="lineno"> 371</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span>  source_values = <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#a989ab3e96426615bb98e04e0235088ca">src</a>.ptr);</div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span> </div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span>  <span class="keyword">const</span> VEC_QUANT out = requantize(source_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00376"></a><span class="lineno"> 376</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="l00377"></a><span class="lineno"> 377</span>  (out, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr + HEIGHT_OFFSET * dst_stride_y));</div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span> <span class="preprocessor">#else </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></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#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span>  (source_values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr + HEIGHT_OFFSET * dst_stride_y));</div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span> }</div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span> </div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(HEIGHT_OFFSET) && defined(DEPTH) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00385"></a><span class="lineno"> 385</span> <span class="comment"></span></div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span> <span class="comment">/** This kernel concatenates the input tensor into the output tensor along the third dimension</span></div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span> <span class="comment"> *</span></div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span> <span class="comment"> * @note The data type has to be passed at compile time using -DDATA_TYPE. i.e. -DDATA_TYPE=float</span></div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span> <span class="comment"> * @note Vector size has to be passed at compile time using -DVEC_SIZE. i.e. -DVEC_SIZE=16</span></div><div class="line"><a name="l00390"></a><span class="lineno"> 390</span> <span class="comment"> *</span></div><div class="line"><a name="l00391"></a><span class="lineno"> 391</span> <span class="comment"> * @param[in] src_ptr Pointer to the source tensor. Supported data types: F16, F32</span></div><div class="line"><a name="l00392"></a><span class="lineno"> 392</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="l00393"></a><span class="lineno"> 393</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="l00394"></a><span class="lineno"> 394</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="l00395"></a><span class="lineno"> 395</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="l00396"></a><span class="lineno"> 396</span> <span class="comment"> * @param[in] src_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span> <span class="comment"> * @param[in] src_step_z src_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00398"></a><span class="lineno"> 398</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="l00399"></a><span class="lineno"> 399</span> <span class="comment"> * @param[out] dst_ptr Pointer to the destination tensor. Supported data types: same as @p src_ptr</span></div><div class="line"><a name="l00400"></a><span class="lineno"> 400</span> <span class="comment"> * @param[in] dst_stride_x Stride of the destination tensor in X dimension (in bytes)</span></div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span> <span class="comment"> * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)</span></div><div class="line"><a name="l00402"></a><span class="lineno"> 402</span> <span class="comment"> * @param[in] dst_stride_y Stride of the destination tensor in Y dimension (in bytes)</span></div><div class="line"><a name="l00403"></a><span class="lineno"> 403</span> <span class="comment"> * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)</span></div><div class="line"><a name="l00404"></a><span class="lineno"> 404</span> <span class="comment"> * @param[in] dst_stride_z Stride of the source tensor in Z dimension (in bytes)</span></div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span> <span class="comment"> * @param[in] dst_step_z dst_stride_z * number of elements along Z processed per workitem(in bytes)</span></div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span> <span class="comment"> * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination tensor</span></div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span> <span class="comment"> * @param[in] offsets The offsets to the first valid element of the output tensor in bytes</span></div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span> <span class="comment"> */</span></div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span> __kernel <span class="keywordtype">void</span> concatenate(</div><div class="line"><a name="l00410"></a><span class="lineno"> 410</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#a989ab3e96426615bb98e04e0235088ca">src</a>),</div><div class="line"><a name="l00411"></a><span class="lineno"> 411</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>),</div><div class="line"><a name="l00412"></a><span class="lineno"> 412</span>  <span class="keywordtype">int</span> <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>)</div><div class="line"><a name="l00413"></a><span class="lineno"> 413</span> {</div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span>  <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</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#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a989ab3e96426615bb98e04e0235088ca">src</a>);</div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span>  <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</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#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>);</div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span> </div><div class="line"><a name="l00417"></a><span class="lineno"> 417</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>, <a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span>  source_values = <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#a989ab3e96426615bb98e04e0235088ca">src</a>.ptr);</div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span> </div><div class="line"><a name="l00420"></a><span class="lineno"> 420</span> <span class="preprocessor">#if defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT)</span></div><div class="line"><a name="l00421"></a><span class="lineno"> 421</span>  source_values = requantize(source_values, OFFSET_IN1, OFFSET_OUT, SCALE_IN1, SCALE_OUT);</div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(OFFSET_IN1) && defined(OFFSET_OUT) && defined(SCALE_IN1) && defined(SCALE_OUT) */</span><span class="preprocessor"></span></div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span> </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#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(<a class="code" href="depthwise__convolution__quantized_8cl.xhtml#a3fffea119c04c7680f2e9cf3fadf63b4">VEC_SIZE</a>)</div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span>  (source_values, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#adbf67dcee294e673cf796f1ed8aeb6a4">dst</a>.ptr + <a class="code" href="src_2core_2_c_l_2cl__kernels_2_helpers_8h.xhtml#a009469e4d9b8fce3b6d5e97d2077827d">offset</a>));</div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span> }</div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span> <span class="preprocessor">#endif </span><span class="comment">/* defined(DATA_TYPE) && defined(VEC_SIZE) */</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="depth__convert_8cl_xhtml_a5b0d9908c0af31eaa7a31d0b5cf8e56d"><div class="ttname"><a href="depth__convert_8cl.xhtml#a5b0d9908c0af31eaa7a31d0b5cf8e56d">CONVERT_DOWN</a></div><div class="ttdeci">#define CONVERT_DOWN(x, type)</div><div class="ttdef"><b>Definition:</b> <a href="depth__convert_8cl_source.xhtml#l00034">depth_convert.cl:34</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>
@@ -117,7 +117,6 @@
<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="softmax__layer__quantized_8cl_xhtml_af5987b09a234231612b2b1eded343025"><div class="ttname"><a href="softmax__layer__quantized_8cl.xhtml#af5987b09a234231612b2b1eded343025">VEC_UCHAR</a></div><div class="ttdeci">#define VEC_UCHAR</div><div class="ttdef"><b>Definition:</b> <a href="softmax__layer__quantized_8cl_source.xhtml#l00063">softmax_layer_quantized.cl:63</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="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="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>
@@ -130,7 +129,7 @@
<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="concatenate_8cl.xhtml">concatenate.cl</a></li>
- <li class="footer">Generated on Wed Jan 22 2020 18:07:38 for Compute Library by
+ <li class="footer">Generated on Fri Feb 21 2020 11:10:11 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>