arm_compute v18.08
diff --git a/documentation/copy__tensor_8cl.xhtml b/documentation/copy__tensor_8cl.xhtml
index 0f2fd4d..b95d3c4 100644
--- a/documentation/copy__tensor_8cl.xhtml
+++ b/documentation/copy__tensor_8cl.xhtml
@@ -40,7 +40,7 @@
  <tr style="height: 56px;">
   <td style="padding-left: 0.5em;">
    <div id="projectname">Compute Library
-   &#160;<span id="projectnumber">18.05</span>
+   &#160;<span id="projectnumber">18.08</span>
    </div>
   </td>
  </tr>
@@ -125,12 +125,12 @@
 <table class="memberdecls">
 <tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
 Functions</h2></td></tr>
-<tr class="memitem:a0386b0d38958a59b663a7237a672d514"><td class="memItemLeft" align="right" valign="top">__kernel void&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="copy__tensor_8cl.xhtml#a0386b0d38958a59b663a7237a672d514">copy_tensor</a> (__global uchar *in_ptr, uint in_stride_x, uint in_step_x, uint in_offset_first_element_in_bytes, __global uchar *out_ptr, uint out_stride_x, uint out_step_x, uint out_offset_first_element_in_bytes)</td></tr>
-<tr class="memdesc:a0386b0d38958a59b663a7237a672d514"><td class="mdescLeft">&#160;</td><td class="mdescRight">Performs a copy of input tensor to the output tensor.  <a href="#a0386b0d38958a59b663a7237a672d514">More...</a><br /></td></tr>
-<tr class="separator:a0386b0d38958a59b663a7237a672d514"><td class="memSeparator" colspan="2">&#160;</td></tr>
+<tr class="memitem:a5f7a81ece3c8141222bfaa46592f0913"><td class="memItemLeft" align="right" valign="top">__kernel void&#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="copy__tensor_8cl.xhtml#a5f7a81ece3c8141222bfaa46592f0913">copy_tensor</a> (__global uchar *in_ptr, uint <a class="el" href="depthwise__convolution_8cl.xhtml#a5447e2c4e1aae8fff9290b775fe813ff">in_stride_x</a>, uint in_step_x, uint <a class="el" href="depthwise__convolution_8cl.xhtml#ac353c0687abd8c71a4fa096d322b39ec">in_stride_y</a>, uint in_step_y, uint <a class="el" href="depthwise__convolution_8cl.xhtml#a32137dd220c1110408a7b498108de2c5">in_stride_z</a>, uint in_step_z, uint in_offset_first_element_in_bytes, __global uchar *out_ptr, uint <a class="el" href="depthwise__convolution_8cl.xhtml#a68fce1f0ee4080ed89c9427496d625f2">out_stride_x</a>, uint out_step_x, uint <a class="el" href="depthwise__convolution_8cl.xhtml#ac8b6b732372937bba276e6391944d1e1">out_stride_y</a>, uint out_step_y, uint <a class="el" href="depthwise__convolution_8cl.xhtml#a128f47cb6aacde29e07fde2c4b9f5dd2">out_stride_z</a>, uint out_step_z, uint out_offset_first_element_in_bytes)</td></tr>
+<tr class="memdesc:a5f7a81ece3c8141222bfaa46592f0913"><td class="mdescLeft">&#160;</td><td class="mdescRight">Performs a copy of input tensor to the output tensor.  <a href="#a5f7a81ece3c8141222bfaa46592f0913">More...</a><br /></td></tr>
+<tr class="separator:a5f7a81ece3c8141222bfaa46592f0913"><td class="memSeparator" colspan="2">&#160;</td></tr>
 </table>
 <h2 class="groupheader">Function Documentation</h2>
-<a class="anchor" id="a0386b0d38958a59b663a7237a672d514"></a>
+<a class="anchor" id="a5f7a81ece3c8141222bfaa46592f0913"></a>
 <div class="memitem">
 <div class="memproto">
       <table class="memname">
@@ -156,6 +156,30 @@
           <td class="paramkey"></td>
           <td></td>
           <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>in_stride_y</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>in_step_y</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>in_stride_z</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>in_step_z</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
           <td class="paramname"><em>in_offset_first_element_in_bytes</em>, </td>
         </tr>
         <tr>
@@ -180,6 +204,30 @@
           <td class="paramkey"></td>
           <td></td>
           <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>out_stride_y</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>out_step_y</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>out_stride_z</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
+          <td class="paramname"><em>out_step_z</em>, </td>
+        </tr>
+        <tr>
+          <td class="paramkey"></td>
+          <td></td>
+          <td class="paramtype">uint&#160;</td>
           <td class="paramname"><em>out_offset_first_element_in_bytes</em>&#160;</td>
         </tr>
         <tr>
@@ -193,25 +241,37 @@
 <p>Performs a copy of input tensor to the output tensor. </p>
 <dl class="params"><dt>Parameters</dt><dd>
   <table class="params">
-    <tr><td class="paramdir">[in]</td><td class="paramname">in_ptr</td><td>Pointer to the source image. Supported data types: U8. </td></tr>
-    <tr><td class="paramdir">[in]</td><td class="paramname">in_stride_x</td><td>Stride of the source image in X dimension (in bytes) </td></tr>
-    <tr><td class="paramdir">[in]</td><td class="paramname">in_step_x</td><td>in_stride_x * number of elements along X processed per work item (in bytes) </td></tr>
-    <tr><td class="paramdir">[in]</td><td class="paramname">in_offset_first_element_in_bytes</td><td>Offset of the first element in the source image </td></tr>
-    <tr><td class="paramdir">[out]</td><td class="paramname">out_ptr</td><td>Pointer to the destination image. Supported data types: U8. </td></tr>
-    <tr><td class="paramdir">[in]</td><td class="paramname">out_stride_x</td><td>Stride of the destination image in X dimension (in bytes) </td></tr>
-    <tr><td class="paramdir">[in]</td><td class="paramname">out_step_x</td><td>out_stride_x * number of elements along X processed per work item (in bytes) </td></tr>
-    <tr><td class="paramdir">[in]</td><td class="paramname">out_offset_first_element_in_bytes</td><td>Offset of the first element in the destination image </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_ptr</td><td>Pointer to the source tensor. Supported data types: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32 </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_stride_x</td><td>Stride of the source tensor in X dimension (in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_step_x</td><td>input_stride_x * number of elements along X processed per workitem(in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_stride_y</td><td>Stride of the source tensor in Y dimension (in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_step_y</td><td>input_stride_y * number of elements along Y processed per workitem(in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_stride_z</td><td>Stride of the source tensor in Z dimension (in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_step_z</td><td>input_stride_z * number of elements along Z processed per workitem(in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">in_offset_first_element_in_bytes</td><td>The offset of the first element in the source tensor </td></tr>
+    <tr><td class="paramdir">[out]</td><td class="paramname">out_ptr</td><td>Pointer to the destination tensor. Supported data types: same as <code>in_ptr</code> </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_stride_x</td><td>Stride of the destination tensor in X dimension (in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_step_x</td><td>output_stride_x * number of elements along X processed per workitem(in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_stride_y</td><td>Stride of the destination tensor in Y dimension (in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_step_y</td><td>output_stride_y * number of elements along Y processed per workitem(in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_stride_z</td><td>Stride of the source tensor in Z dimension (in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_step_z</td><td>output_stride_z * number of elements along Z processed per workitem(in bytes) </td></tr>
+    <tr><td class="paramdir">[in]</td><td class="paramname">out_offset_first_element_in_bytes</td><td>The offset of the first element in the destination tensor </td></tr>
   </table>
   </dd>
 </dl>
 
-<p>Definition at line <a class="el" href="copy__tensor_8cl_source.xhtml#l00037">37</a> of file <a class="el" href="copy__tensor_8cl_source.xhtml">copy_tensor.cl</a>.</p>
+<p>Definition at line <a class="el" href="copy__tensor_8cl_source.xhtml#l00045">45</a> of file <a class="el" href="copy__tensor_8cl_source.xhtml">copy_tensor.cl</a>.</p>
 
-<p>References <a class="el" href="helpers_8h_source.xhtml#l00098">CONVERT_TO_VECTOR_STRUCT</a>, <a class="el" href="convolution3x3_8cl_source.xhtml#l00027">DATA_TYPE</a>, <a class="el" href="helpers_8h_source.xhtml#l00136">Vector::ptr</a>, and <a class="el" href="fixed__point_8h_source.xhtml#l00093">VEC_DATA_TYPE</a>.</p>
-<div class="fragment"><div class="line"><a name="l00040"></a><span class="lineno">   40</span>&#160;{</div><div class="line"><a name="l00041"></a><span class="lineno">   41</span>&#160;    <a class="code" href="struct_vector.xhtml">Vector</a> in  = <a class="code" href="helpers_8h.xhtml#a527bfdf5eeb306f1cf01c4a8e29f38e0">CONVERT_TO_VECTOR_STRUCT</a>(in);</div><div class="line"><a name="l00042"></a><span class="lineno">   42</span>&#160;    <a class="code" href="struct_vector.xhtml">Vector</a> out = <a class="code" href="helpers_8h.xhtml#a527bfdf5eeb306f1cf01c4a8e29f38e0">CONVERT_TO_VECTOR_STRUCT</a>(out);</div><div class="line"><a name="l00043"></a><span class="lineno">   43</span>&#160;</div><div class="line"><a name="l00044"></a><span class="lineno">   44</span>&#160;    <a class="code" href="fixed__point_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, 16)</div><div class="line"><a name="l00045"></a><span class="lineno">   45</span>&#160;    data = vload16(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)in.ptr);</div><div class="line"><a name="l00046"></a><span class="lineno">   46</span>&#160;</div><div class="line"><a name="l00047"></a><span class="lineno">   47</span>&#160;    vstore16(data, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)out.ptr);</div><div class="line"><a name="l00048"></a><span class="lineno">   48</span>&#160;}<div class="ttc" id="struct_vector_xhtml"><div class="ttname"><a href="struct_vector.xhtml">Vector</a></div><div class="ttdoc">Structure to hold Vector information. </div><div class="ttdef"><b>Definition:</b> <a href="helpers_8h_source.xhtml#l00134">helpers.h:134</a></div></div>
-<div class="ttc" id="helpers_8h_xhtml_a527bfdf5eeb306f1cf01c4a8e29f38e0"><div class="ttname"><a href="helpers_8h.xhtml#a527bfdf5eeb306f1cf01c4a8e29f38e0">CONVERT_TO_VECTOR_STRUCT</a></div><div class="ttdeci">#define CONVERT_TO_VECTOR_STRUCT(name)</div><div class="ttdef"><b>Definition:</b> <a href="helpers_8h_source.xhtml#l00098">helpers.h:98</a></div></div>
+<p>References <a class="el" href="helpers_8h_source.xhtml#l00127">CONVERT_TO_TENSOR3D_STRUCT</a>, <a class="el" href="convolution3x3_8cl_source.xhtml#l00027">DATA_TYPE</a>, <a class="el" href="_c_l_2_winograd_8cpp_source.xhtml#l00241">arm_compute::test::validation::in</a>, <a class="el" href="_c_l_2_winograd_8cpp_source.xhtml#l00242">arm_compute::test::validation::out</a>, <a class="el" href="helpers_8h_source.xhtml#l00161">Tensor3D::ptr</a>, <a class="el" href="helpers_8h_source.xhtml#l00056">VEC_DATA_TYPE</a>, <a class="el" href="helpers_8h_source.xhtml#l00050">VLOAD</a>, and <a class="el" href="helpers_8h_source.xhtml#l00053">VSTORE</a>.</p>
+<div class="fragment"><div class="line"><a name="l00048"></a><span class="lineno">   48</span>&#160;{</div><div class="line"><a name="l00049"></a><span class="lineno">   49</span>&#160;    <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#ad366eaa4cf2d106037d91c30795a5c76">in</a>  = <a class="code" href="helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(in);</div><div class="line"><a name="l00050"></a><span class="lineno">   50</span>&#160;    <a class="code" href="struct_tensor3_d.xhtml">Tensor3D</a> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#af8a8a0625e7981212a0af48deb9d2a09">out</a> = <a class="code" href="helpers_8h.xhtml#a31c8c760f08fb1a331b16b7c204321dc">CONVERT_TO_TENSOR3D_STRUCT</a>(out);</div><div class="line"><a name="l00051"></a><span class="lineno">   51</span>&#160;</div><div class="line"><a name="l00052"></a><span class="lineno">   52</span>&#160;    <span class="comment">// Load data</span></div><div class="line"><a name="l00053"></a><span class="lineno">   53</span>&#160;    <a class="code" href="helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a>(<a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a>, VEC_SIZE)</div><div class="line"><a name="l00054"></a><span class="lineno">   54</span>&#160;    data = <a class="code" href="helpers_8h.xhtml#a287e2fc366c312b468382c95bb90f91f">VLOAD</a>(VEC_SIZE)(0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)in.ptr);</div><div class="line"><a name="l00055"></a><span class="lineno">   55</span>&#160;</div><div class="line"><a name="l00056"></a><span class="lineno">   56</span>&#160;    <span class="comment">// Store result</span></div><div class="line"><a name="l00057"></a><span class="lineno">   57</span>&#160;    <a class="code" href="helpers_8h.xhtml#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a>(VEC_SIZE)</div><div class="line"><a name="l00058"></a><span class="lineno">   58</span>&#160;    (data, 0, (__global <a class="code" href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a> *)out.ptr);</div><div class="line"><a name="l00059"></a><span class="lineno">   59</span>&#160;}<div class="ttc" id="helpers_8h_xhtml_a287e2fc366c312b468382c95bb90f91f"><div class="ttname"><a href="helpers_8h.xhtml#a287e2fc366c312b468382c95bb90f91f">VLOAD</a></div><div class="ttdeci">#define VLOAD(size)</div><div class="ttdef"><b>Definition:</b> <a href="helpers_8h_source.xhtml#l00050">helpers.h:50</a></div></div>
+<div class="ttc" id="helpers_8h_xhtml_a31c8c760f08fb1a331b16b7c204321dc"><div class="ttname"><a href="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="helpers_8h_source.xhtml#l00127">helpers.h:127</a></div></div>
 <div class="ttc" id="convolution3x3_8cl_xhtml_afb8c72ce35c4a1f4a2588d6573e54aa1"><div class="ttname"><a href="convolution3x3_8cl.xhtml#afb8c72ce35c4a1f4a2588d6573e54aa1">DATA_TYPE</a></div><div class="ttdeci">#define DATA_TYPE</div><div class="ttdef"><b>Definition:</b> <a href="convolution3x3_8cl_source.xhtml#l00027">convolution3x3.cl:27</a></div></div>
-<div class="ttc" id="fixed__point_8h_xhtml_a36f754c05b6fddf6df0d8d0a74f8159f"><div class="ttname"><a href="fixed__point_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a></div><div class="ttdeci">#define VEC_DATA_TYPE(type, size)</div><div class="ttdef"><b>Definition:</b> <a href="fixed__point_8h_source.xhtml#l00093">fixed_point.h:93</a></div></div>
+<div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_ad366eaa4cf2d106037d91c30795a5c76"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#ad366eaa4cf2d106037d91c30795a5c76">arm_compute::test::validation::in</a></div><div class="ttdeci">CLTensor in</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_winograd_8cpp_source.xhtml#l00241">Winograd.cpp:241</a></div></div>
+<div class="ttc" id="struct_tensor3_d_xhtml"><div class="ttname"><a href="struct_tensor3_d.xhtml">Tensor3D</a></div><div class="ttdoc">Structure to hold 3D tensor information. </div><div class="ttdef"><b>Definition:</b> <a href="helpers_8h_source.xhtml#l00159">helpers.h:159</a></div></div>
+<div class="ttc" id="helpers_8h_xhtml_acb282042d1edeeaa3cc979a206f78b54"><div class="ttname"><a href="helpers_8h.xhtml#acb282042d1edeeaa3cc979a206f78b54">VSTORE</a></div><div class="ttdeci">#define VSTORE(size)</div><div class="ttdef"><b>Definition:</b> <a href="helpers_8h_source.xhtml#l00053">helpers.h:53</a></div></div>
+<div class="ttc" id="helpers_8h_xhtml_a36f754c05b6fddf6df0d8d0a74f8159f"><div class="ttname"><a href="helpers_8h.xhtml#a36f754c05b6fddf6df0d8d0a74f8159f">VEC_DATA_TYPE</a></div><div class="ttdeci">#define VEC_DATA_TYPE(type, size)</div><div class="ttdef"><b>Definition:</b> <a href="helpers_8h_source.xhtml#l00056">helpers.h:56</a></div></div>
+<div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_af8a8a0625e7981212a0af48deb9d2a09"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#af8a8a0625e7981212a0af48deb9d2a09">arm_compute::test::validation::out</a></div><div class="ttdeci">CLTensor out</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_winograd_8cpp_source.xhtml#l00242">Winograd.cpp:242</a></div></div>
 </div><!-- fragment -->
 </div>
 </div>
@@ -221,7 +281,7 @@
 <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="copy__tensor_8cl.xhtml">copy_tensor.cl</a></li>
-    <li class="footer">Generated on Wed May 23 2018 11:36:39 for Compute Library by
+    <li class="footer">Generated on Wed Aug 29 2018 15:31:37 for Compute Library by
     <a href="http://www.doxygen.org/index.html">
     <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.11 </li>
   </ul>