| <!-- HTML header for doxygen 1.8.15--> |
| <!-- Remember to use version doxygen 1.8.15 +--> |
| <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> |
| <html xmlns="http://www.w3.org/1999/xhtml"> |
| <head> |
| <meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/> |
| <meta http-equiv="X-UA-Compatible" content="IE=9"/> |
| <meta name="generator" content="Doxygen 1.8.15"/> |
| <meta name="robots" content="NOINDEX, NOFOLLOW" /> <!-- Prevent indexing by search engines --> |
| <title>Compute Library: src/runtime/NEON/functions/NEGEMM.cpp Source File</title> |
| <link href="tabs.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="jquery.js"></script> |
| <script type="text/javascript" src="dynsections.js"></script> |
| <link href="navtree.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="resize.js"></script> |
| <script type="text/javascript" src="navtreedata.js"></script> |
| <script type="text/javascript" src="navtree.js"></script> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| $(document).ready(initResizable); |
| /* @license-end */</script> |
| <link href="search/search.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="search/searchdata.js"></script> |
| <script type="text/javascript" src="search/search.js"></script> |
| <script type="text/x-mathjax-config"> |
| MathJax.Hub.Config({ |
| extensions: ["tex2jax.js"], |
| jax: ["input/TeX","output/HTML-CSS"], |
| }); |
| </script><script type="text/javascript" async="async" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script> |
| <link href="doxygen.css" rel="stylesheet" type="text/css" /> |
| <link href="stylesheet.css" rel="stylesheet" type="text/css"/> |
| </head> |
| <body> |
| <div id="top"><!-- do not remove this div, it is closed by doxygen! --> |
| <div id="titlearea"> |
| <table cellspacing="0" cellpadding="0"> |
| <tbody> |
| <tr style="height: 56px;"> |
| <img alt="Compute Library" src="https://raw.githubusercontent.com/ARM-software/ComputeLibrary/gh-pages/ACL_logo.png" style="max-width: 100%;margin-top: 15px;margin-left: 10px"/> |
| <td style="padding-left: 0.5em;"> |
| <div id="projectname"> |
|  <span id="projectnumber">19.08</span> |
| </div> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <!-- end header part --> |
| <!-- Generated by Doxygen 1.8.15 --> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| var searchBox = new SearchBox("searchBox", "search",false,'Search'); |
| /* @license-end */ |
| </script> |
| <script type="text/javascript" src="menudata.js"></script> |
| <script type="text/javascript" src="menu.js"></script> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| $(function() { |
| initMenu('',true,false,'search.php','Search'); |
| $(document).ready(function() { init_search(); }); |
| }); |
| /* @license-end */</script> |
| <div id="main-nav"></div> |
| </div><!-- top --> |
| <div id="side-nav" class="ui-resizable side-nav-resizable"> |
| <div id="nav-tree"> |
| <div id="nav-tree-contents"> |
| <div id="nav-sync" class="sync"></div> |
| </div> |
| </div> |
| <div id="splitbar" style="-moz-user-select:none;" |
| class="ui-resizable-handle"> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| $(document).ready(function(){initNavTree('_n_e_g_e_m_m_8cpp_source.xhtml','');}); |
| /* @license-end */ |
| </script> |
| <div id="doc-content"> |
| <!-- window showing the filter options --> |
| <div id="MSearchSelectWindow" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| onkeydown="return searchBox.OnSearchSelectKey(event)"> |
| </div> |
| |
| <!-- iframe showing the search results (closed by default) --> |
| <div id="MSearchResultsWindow"> |
| <iframe src="javascript:void(0)" frameborder="0" |
| name="MSearchResults" id="MSearchResults"> |
| </iframe> |
| </div> |
| |
| <div class="header"> |
| <div class="headertitle"> |
| <div class="title">NEGEMM.cpp</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <a href="_n_e_g_e_m_m_8cpp.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="_n_e_g_e_m_m_8h.xhtml">arm_compute/runtime/NEON/functions/NEGEMM.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">#include "<a class="code" href="_c_p_p_2_validate_8h.xhtml">arm_compute/core/CPP/Validate.h</a>"</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor">#include "<a class="code" href="_error_8h.xhtml">arm_compute/core/Error.h</a>"</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#include "<a class="code" href="arm__compute_2core_2_helpers_8h.xhtml">arm_compute/core/Helpers.h</a>"</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#include "<a class="code" href="_i_tensor_8h.xhtml">arm_compute/core/ITensor.h</a>"</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="preprocessor">#include "<a class="code" href="_tensor_info_8h.xhtml">arm_compute/core/TensorInfo.h</a>"</span></div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#include "<a class="code" href="arm__compute_2core_2_types_8h.xhtml">arm_compute/core/Types.h</a>"</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="preprocessor">#include "<a class="code" href="_validate_8h.xhtml">arm_compute/core/Validate.h</a>"</span></div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="preprocessor">#include "<a class="code" href="_shape_calculator_8h.xhtml">arm_compute/core/utils/misc/ShapeCalculator.h</a>"</span></div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span> <span class="preprocessor">#include "<a class="code" href="_n_e_scheduler_8h.xhtml">arm_compute/runtime/NEON/NEScheduler.h</a>"</span></div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span> <span class="preprocessor">#include "<a class="code" href="_n_e_g_e_m_m_assembly_dispatch_8h.xhtml">arm_compute/runtime/NEON/functions/NEGEMMAssemblyDispatch.h</a>"</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="preprocessor">#include "<a class="code" href="_tensor_allocator_8h.xhtml">arm_compute/runtime/TensorAllocator.h</a>"</span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="preprocessor">#include "<a class="code" href="_toolchain_support_8h.xhtml">support/ToolchainSupport.h</a>"</span></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> </div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="preprocessor">#include <cmath></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="keyword">using namespace </span><a class="code" href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml">arm_compute::misc::shape_calculator</a>;</div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> </div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="keyword">namespace </span><a class="code" href="namespacearm__compute.xhtml">arm_compute</a></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> {</div><div class="line"><a name="l00045"></a><span class="lineno"><a class="line" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#abaa70c8f86d580a791200678388d0073"> 45</a></span> <a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#abaa70c8f86d580a791200678388d0073">NEGEMM::NEGEMM</a>(std::shared_ptr<IMemoryManager> memory_manager)</div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  : _memory_group(memory_manager), _interleave_kernel(), _transpose_kernel(), _mm_kernel(), _asm_glue(memory_manager), _ma_kernel(), _tmp_a(), _tmp_b(), _original_b(nullptr),</div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  _run_vector_matrix_multiplication(false), _run_addition(false), _reshape_b_only_on_first_run(false), _is_prepared(false)</div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> {</div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> }</div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> </div><div class="line"><a name="l00051"></a><span class="lineno"><a class="line" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a385241dcc5062af6ecac8bdafe01bb2a"> 51</a></span> <span class="keywordtype">void</span> <a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a385241dcc5062af6ecac8bdafe01bb2a">NEGEMM::configure</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *a, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *c, <a class="code" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *d, <span class="keywordtype">float</span> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, <span class="keywordtype">float</span> beta, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> &gemm_info)</div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> {</div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  <a class="code" href="_error_8h.xhtml#a938dcd406ce611ef5345ad2531cdb948">ARM_COMPUTE_ERROR_THROW_ON</a>(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a3493ba7d1f2057740ff5931fa00a44ac">NEGEMM::validate</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>(), <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info(), (c != <span class="keyword">nullptr</span>) ? c-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>() : <span class="keyword">nullptr</span>, d-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>(), <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, beta, gemm_info));</div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> </div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span>  <span class="comment">// Check if we need to reshape the matrix B only on the first run</span></div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span>  _is_prepared = <span class="keyword">false</span>;</div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  _reshape_b_only_on_first_run = gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a4c8f9fa843de1086c27c86a6b8cf4582">reshape_b_only_on_first_run</a>();</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  _run_vector_matrix_multiplication = a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) < 2;</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  _original_b = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>;</div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> </div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <span class="keywordtype">bool</span> run_optimised = c == <span class="keyword">nullptr</span> && bool(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ae9f257420d216441868cad263ffa2775">NEGEMMAssemblyDispatch::validate</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>(), <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info(), c != <span class="keyword">nullptr</span> ? c-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>() : <span class="keyword">nullptr</span>, d-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>(), <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, beta, gemm_info));</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span> </div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  <span class="keywordflow">if</span>(run_optimised)</div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  {</div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keywordflow">if</span>(<a class="code" href="classarm__compute_1_1_m_e_m_info.xhtml#aacc842e7ef6389e970d92af1d62793a7">MEMInfo::get_policy</a>() == <a class="code" href="namespacearm__compute.xhtml#a4c9101ca1a1f72f48efff28b4b9a6495a704bfa6c1ed5e479c8cfb5bdfc8cccda">MemoryPolicy::MINIMIZE</a>)</div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  {</div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  <a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> gemm_info_ntb = gemm_info;</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  gemm_info_ntb.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#adfd4c40b75cbb4b1b2b2c2bac0051891">set_pretranpose_B</a>(<span class="keyword">false</span>);</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  _asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#a89a324550419139fd5b03254a70bbd36">configure</a>(a, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, c, d, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, beta, gemm_info_ntb);</div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  }</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  {</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  _asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#a89a324550419139fd5b03254a70bbd36">configure</a>(a, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, c, d, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, beta, gemm_info);</div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  }</div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <a class="code" href="_error_8h.xhtml#a54a6080c9f4df1f908e57a9bbb46f5da">ARM_COMPUTE_ERROR_ON</a>(!_asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ab7c16a89cb470f3fa85818ee85e1e1dd">is_configured</a>());</div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  }</div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  {</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <span class="keywordflow">if</span>(_run_vector_matrix_multiplication)</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  {</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  <span class="comment">// Configure the matrix multiply kernel</span></div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  _mm_kernel.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel.xhtml#a4ee07709711414457834cc5d1c2c6cdb">configure</a>(a, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, d, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, <span class="keyword">false</span>);</div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  }</div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  {</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> shape_tmp_a = a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a7c66505457d00ece3aa4b34cab80757d">tensor_shape</a>();</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> shape_tmp_b = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info()->tensor_shape();</div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span> </div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  shape_tmp_a.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a9c54fb6cea3557692fe7c00c40bb40ad">set</a>(0, a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(0) * 4);</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  shape_tmp_a.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a9c54fb6cea3557692fe7c00c40bb40ad">set</a>(1, std::ceil(a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) / 4.0f));</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> </div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="keyword">const</span> <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> transpose_w = 16 / <a class="code" href="namespacearm__compute.xhtml#abb7e0f23a4f2e63f39433f158dad47ab">data_size_from_type</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info()->data_type());</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  shape_tmp_b.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a9c54fb6cea3557692fe7c00c40bb40ad">set</a>(0, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info()->dimension(1) * transpose_w);</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  shape_tmp_b.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a9c54fb6cea3557692fe7c00c40bb40ad">set</a>(1, std::ceil(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info()->dimension(0) / static_cast<float>(transpose_w)));</div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span> </div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  <a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a> info_a = a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1misc_1_1_i_cloneable.xhtml#a4d10e5012a872e7f78f2b539b673049d">clone</a>()->set_tensor_shape(shape_tmp_a).set_is_resizable(<span class="keyword">true</span>);</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  <a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a> info_b = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info()->clone()->set_tensor_shape(shape_tmp_b).set_is_resizable(<span class="keyword">true</span>);</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> </div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  _tmp_a.<a class="code" href="classarm__compute_1_1_tensor.xhtml#adbd0cf83a8e1b335a9bf405a8e5019fa">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3fc6adad84b23f10d54d5a7b6928f872">init</a>(info_a);</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  _tmp_b.<a class="code" href="classarm__compute_1_1_tensor.xhtml#adbd0cf83a8e1b335a9bf405a8e5019fa">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3fc6adad84b23f10d54d5a7b6928f872">init</a>(info_b);</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span> </div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <span class="comment">// Manage intermediate buffers</span></div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  _memory_group.<a class="code" href="classarm__compute_1_1_memory_group_base.xhtml#ac1f67376afb7822f262a0174ef4a3104">manage</a>(&_tmp_a);</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  <span class="keywordflow">if</span>(!_reshape_b_only_on_first_run)</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  {</div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  _memory_group.<a class="code" href="classarm__compute_1_1_memory_group_base.xhtml#ac1f67376afb7822f262a0174ef4a3104">manage</a>(&_tmp_b);</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  }</div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> </div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  <span class="keywordtype">int</span> m = a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1);</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  <span class="keywordtype">int</span> n = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info()->dimension(0);</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <span class="keywordtype">int</span> k = a-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">info</a>()-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(0);</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span> </div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  <span class="comment">// Configure interleave kernel</span></div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  _interleave_kernel.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel.xhtml#a83a344e60eb7db895953a942abf16628">configure</a>(a, &_tmp_a);</div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span> </div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span>  <span class="comment">// Configure transpose kernel</span></div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  _transpose_kernel.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel.xhtml#a83a344e60eb7db895953a942abf16628">configure</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, &_tmp_b);</div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span> </div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  <span class="comment">// Configure matrix multiplication kernel</span></div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  _mm_kernel.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel.xhtml#a4ee07709711414457834cc5d1c2c6cdb">configure</a>(&_tmp_a, &_tmp_b, d, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, <span class="keyword">true</span>, <a class="code" href="classarm__compute_1_1_g_e_m_m_reshape_info.xhtml">GEMMReshapeInfo</a>(m, n, k));</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span> </div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  <span class="comment">// Allocate once the all configure methods have been called</span></div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  _tmp_a.<a class="code" href="classarm__compute_1_1_tensor.xhtml#adbd0cf83a8e1b335a9bf405a8e5019fa">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <span class="keywordflow">if</span>(!_reshape_b_only_on_first_run)</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>  _tmp_b.<a class="code" href="classarm__compute_1_1_tensor.xhtml#adbd0cf83a8e1b335a9bf405a8e5019fa">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  }</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  }</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>  <span class="comment">// Configure matrix addition kernel</span></div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  <span class="keywordflow">if</span>(beta != 0 && c != <span class="keyword">nullptr</span>)</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span>  {</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  _ma_kernel.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel.xhtml#abd3df2f9251266926538e4c020652996">configure</a>(c, d, beta);</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  _run_addition = <span class="keyword">true</span>;</div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  }</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  }</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span> }</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span> </div><div class="line"><a name="l00139"></a><span class="lineno"><a class="line" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a3493ba7d1f2057740ff5931fa00a44ac"> 139</a></span> <a class="code" href="classarm__compute_1_1_status.xhtml">Status</a> <a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a3493ba7d1f2057740ff5931fa00a44ac">NEGEMM::validate</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *a, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *c, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *output, <span class="keywordtype">float</span> <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, <span class="keywordtype">float</span> beta, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> &gemm_info)</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span> {</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  <a class="code" href="_error_8h.xhtml#a6dc630a6ae9cc063b3924bcea8dee9d6">ARM_COMPUTE_UNUSED</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>);</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="_c_p_p_2_validate_8h.xhtml#ad2633f3560322e1f8d926949dec1b730">ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED</a>(a);</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <a class="code" href="_validate_8h.xhtml#ae7eed178dac535c6e727061b1f5bc6eb">ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN</a>(a, 1, <a class="code" href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a56d8353718e6fdc78b8d69078a2cdb94">DataType::F16</a>, <a class="code" href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a44ad4ef5a76e6aa6fb3e3fa079a54fda">DataType::F32</a>);</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  <a class="code" href="_validate_8h.xhtml#a8f3ff7da485ff7e75dab07baadf5b4bd">ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES</a>(a, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, output);</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(0) != <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->dimension(1), <span class="stringliteral">"The product AB is defined only if the number of columns in A is equal to the number of rows in B"</span>);</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#aa7e9584d7080ca6442cec62afaff6cad">is_a_reshaped</a>(), <span class="stringliteral">"Matrix A already reshaped is not supported"</span>);</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a77964edb8d16bb8ec14ddd8985e03cb0">is_b_reshaped</a>(), <span class="stringliteral">"Matrix B already reshaped is not supported"</span>);</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span> </div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span>  <span class="keywordflow">if</span>(c != <span class="keyword">nullptr</span>)</div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  {</div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#abbd888f118c2209bf7578eb4f8942a07">depth_output_gemm3d</a>() != 0);</div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a00330b8913cac3b07029ac0c3350e806">reinterpret_input_as_3d</a>());</div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <a class="code" href="_validate_8h.xhtml#a8f3ff7da485ff7e75dab07baadf5b4bd">ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES</a>(a, c);</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) != c-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1), <span class="stringliteral">"The C matrix must have the same number of rows as the matrix A"</span>);</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->dimension(0) != c-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(0), <span class="stringliteral">"The C matrix must have the same number of columns as the matrix B"</span>);</div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  }</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span> </div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  <span class="keywordflow">if</span>(output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a18064e0011c3869d884653e9e7c47b66">total_size</a>() != 0)</div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  {</div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->dimension(0) != output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(0));</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  <span class="keywordflow">if</span>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#abbd888f118c2209bf7578eb4f8942a07">depth_output_gemm3d</a>() != 0)</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  {</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  <span class="keywordflow">if</span>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a00330b8913cac3b07029ac0c3350e806">reinterpret_input_as_3d</a>())</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  {</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) != output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1));</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(2) != output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(2));</div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  }</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span>  {</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) != output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) * output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(2));</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  }</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  }</div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  {</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span>  <a class="code" href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a>(a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) != output-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1));</div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  }</div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  }</div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span> </div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="comment">// Check if we need to run the optimized assembly kernel</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  <span class="keyword">const</span> <span class="keywordtype">bool</span> run_optimised = c == <span class="keyword">nullptr</span> && bool(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ae9f257420d216441868cad263ffa2775">NEGEMMAssemblyDispatch::validate</a>(a, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, c, output, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, beta, gemm_info));</div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span> </div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  <span class="keywordflow">if</span>(!run_optimised)</div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span>  {</div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a00330b8913cac3b07029ac0c3350e806">reinterpret_input_as_3d</a>(), <span class="stringliteral">"NEGEMM cannot reinterpret the input tensor as 3D"</span>);</div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span>  <a class="code" href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#abbd888f118c2209bf7578eb4f8942a07">depth_output_gemm3d</a>() != 0, <span class="stringliteral">"NEGEMM cannot reinterpret the output tensor as 3D"</span>);</div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span> </div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span>  <span class="comment">// Check if the first input tensor is a vector.</span></div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span>  <span class="keyword">const</span> <span class="keywordtype">bool</span> run_vector_matrix_multiplication = a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1) < 2;</div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span>  <span class="comment">// Check if we need to reshape the matrix A and matrix B</span></div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span>  <span class="keyword">const</span> <span class="keywordtype">bool</span> run_interleave_transpose = !run_vector_matrix_multiplication && !(gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a4c8f9fa843de1086c27c86a6b8cf4582">reshape_b_only_on_first_run</a>());</div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span> </div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span>  <span class="comment">// Arguments used by GEMMReshapeInfo</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span>  <span class="comment">// If we pass the matrix A and matrix B reshaped to NEGEMMMatrixMultiplyKernel, we need to pass m, n, k, mult_transpose1xW_width and mult_interleave4x4_height to NEGEMMReshapeInfo</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span>  <span class="comment">// in order to know how the matrices have been reshaped</span></div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> m = a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(1);</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> n = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->dimension(0);</div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span>  <span class="keyword">const</span> <span class="keywordtype">int</span> k = a-><a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">dimension</a>(0);</div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  <span class="keywordtype">int</span> mult_transpose1xW_width = 1;</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  <span class="keywordtype">int</span> mult_interleave4x4_height = 1;</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span> </div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_g_e_m_m_reshape_info.xhtml">GEMMReshapeInfo</a> reshape_info = <a class="code" href="classarm__compute_1_1_g_e_m_m_reshape_info.xhtml">GEMMReshapeInfo</a>(m, n, k, mult_transpose1xW_width, mult_interleave4x4_height, gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#abbd888f118c2209bf7578eb4f8942a07">depth_output_gemm3d</a>());</div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span> </div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *matrix_a_info = a;</div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *matrix_b_info = <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>;</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> </div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span>  <a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a> tmp_a_info{};</div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  <a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a> tmp_b_info{};</div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  <a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a> tmp_output_info = *output-><a class="code" href="classarm__compute_1_1misc_1_1_i_cloneable.xhtml#a4d10e5012a872e7f78f2b539b673049d">clone</a>();</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span> </div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  <span class="keywordflow">if</span>(run_interleave_transpose)</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  {</div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  matrix_a_info = &tmp_a_info;</div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  matrix_b_info = &tmp_b_info;</div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span> </div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  <span class="comment">// Validate interleave kernel</span></div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  <a class="code" href="namespacearm__compute.xhtml#a47be6fa38308d0003c25b60b7dbc45ce">auto_init_if_empty</a>(tmp_a_info, a-><a class="code" href="classarm__compute_1_1misc_1_1_i_cloneable.xhtml#a4d10e5012a872e7f78f2b539b673049d">clone</a>()->set_tensor_shape(<a class="code" href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml#a8d52adbbcd2c53f837c96b5a3d15c4fb">compute_interleaved_shape</a>(*a, mult_interleave4x4_height, gemm_info.<a class="code" href="classarm__compute_1_1_g_e_m_m_info.xhtml#a00330b8913cac3b07029ac0c3350e806">reinterpret_input_as_3d</a>())));</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  <a class="code" href="_error_8h.xhtml#a8a1e1c105f0bdaf37db408c7cfcb77a4">ARM_COMPUTE_RETURN_ON_ERROR</a>(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel.xhtml#a968b23a6ef327fcfb5b99d58e3fbe883">NEGEMMInterleave4x4Kernel::validate</a>(a, &tmp_a_info));</div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span> </div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span>  <span class="comment">// Validate transpose kernel</span></div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  <a class="code" href="namespacearm__compute.xhtml#a47be6fa38308d0003c25b60b7dbc45ce">auto_init_if_empty</a>(tmp_b_info, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->clone()->set_tensor_shape(<a class="code" href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml#a5797726a8fbee3b11b92757c2f0031d6">compute_transpose1xW_with_element_size_shape</a>(*<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, mult_transpose1xW_width)));</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  <a class="code" href="_error_8h.xhtml#a8a1e1c105f0bdaf37db408c7cfcb77a4">ARM_COMPUTE_RETURN_ON_ERROR</a>(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel.xhtml#a968b23a6ef327fcfb5b99d58e3fbe883">NEGEMMTranspose1xWKernel::validate</a>(<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>, &tmp_b_info));</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  }</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span> </div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  <span class="comment">// Validate matrix multiply</span></div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  <a class="code" href="namespacearm__compute.xhtml#a47be6fa38308d0003c25b60b7dbc45ce">auto_init_if_empty</a>(tmp_output_info, matrix_a_info-><a class="code" href="classarm__compute_1_1_tensor_info.xhtml#afbc359bde9be72a6edab175978e56662">clone</a>()->set_tensor_shape(<a class="code" href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml#adca241b012a5e00ddfcdc5a8db05a2a3">compute_mm_shape</a>(*matrix_a_info, *matrix_b_info, run_interleave_transpose, reshape_info)));</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  <a class="code" href="_error_8h.xhtml#a8a1e1c105f0bdaf37db408c7cfcb77a4">ARM_COMPUTE_RETURN_ON_ERROR</a>(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel.xhtml#ac91476ef04db46dad52f3cd1e2fae18e">NEGEMMMatrixMultiplyKernel::validate</a>(matrix_a_info, matrix_b_info, &tmp_output_info, <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">alpha</a>, run_interleave_transpose, reshape_info));</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  }</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">// Validate matrix addition kernel</span></div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  <span class="keywordflow">if</span>(beta != 0 && c != <span class="keyword">nullptr</span>)</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  {</div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  <a class="code" href="_error_8h.xhtml#a8a1e1c105f0bdaf37db408c7cfcb77a4">ARM_COMPUTE_RETURN_ON_ERROR</a>(<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel.xhtml#ae722d2edbab88977ea4604d5395d8463">NEGEMMMatrixAdditionKernel::validate</a>(c, output, beta));</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  }</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span> </div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>  <span class="keywordflow">return</span> <a class="code" href="classarm__compute_1_1_status.xhtml">Status</a>{};</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span> }</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span> </div><div class="line"><a name="l00239"></a><span class="lineno"><a class="line" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#ad1717410afd0be936c6213a63c8005fb"> 239</a></span> <span class="keywordtype">void</span> <a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#ad1717410afd0be936c6213a63c8005fb">NEGEMM::run</a>()</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>  <a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77">prepare</a>();</div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span> </div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  <a class="code" href="classarm__compute_1_1_memory_group_resource_scope.xhtml">MemoryGroupResourceScope</a> scope_mg(_memory_group);</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span> </div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  <span class="keywordflow">if</span>(_asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ab7c16a89cb470f3fa85818ee85e1e1dd">is_configured</a>())</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>  _asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ad1717410afd0be936c6213a63c8005fb">run</a>();</div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  }</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  {</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  <span class="keywordflow">if</span>(!_run_vector_matrix_multiplication)</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  {</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  <span class="comment">// Run interleave kernel</span></div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  <a class="code" href="classarm__compute_1_1_scheduler.xhtml#a0d63ca713bab377aabcfb63c192b8429">NEScheduler::get</a>().<a class="code" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">schedule</a>(&_interleave_kernel, <a class="code" href="classarm__compute_1_1_window.xhtml#ad2d402364fa822b0b7775081291eeca9">Window::DimY</a>);</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="keywordflow">if</span>(!_reshape_b_only_on_first_run)</div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  {</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  <span class="comment">// Run transpose kernel</span></div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  <a class="code" href="classarm__compute_1_1_scheduler.xhtml#a0d63ca713bab377aabcfb63c192b8429">NEScheduler::get</a>().<a class="code" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">schedule</a>(&_transpose_kernel, <a class="code" href="classarm__compute_1_1_window.xhtml#ad2d402364fa822b0b7775081291eeca9">Window::DimY</a>);</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  }</div><div class="line"><a name="l00261"></a><span class="lineno"> 261</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>  <a class="code" href="classarm__compute_1_1_scheduler.xhtml#a0d63ca713bab377aabcfb63c192b8429">NEScheduler::get</a>().<a class="code" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">schedule</a>(&_mm_kernel, _run_vector_matrix_multiplication ? <a class="code" href="classarm__compute_1_1_window.xhtml#aa96e81276ee4f87ab386cd05a5539a7d">Window::DimX</a> : <a class="code" href="classarm__compute_1_1_window.xhtml#ad2d402364fa822b0b7775081291eeca9">Window::DimY</a>);</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="comment">// Run matrix addition kernel</span></div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  <span class="keywordflow">if</span>(_run_addition)</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>  {</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span>  <a class="code" href="classarm__compute_1_1_scheduler.xhtml#a0d63ca713bab377aabcfb63c192b8429">NEScheduler::get</a>().<a class="code" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">schedule</a>(&_ma_kernel, <a class="code" href="classarm__compute_1_1_window.xhtml#ad2d402364fa822b0b7775081291eeca9">Window::DimY</a>);</div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span>  }</div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  }</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span> }</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span> </div><div class="line"><a name="l00273"></a><span class="lineno"><a class="line" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77"> 273</a></span> <span class="keywordtype">void</span> <a class="code" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77">NEGEMM::prepare</a>()</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span> {</div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  <span class="keywordflow">if</span>(!_is_prepared)</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="keywordflow">if</span>(_asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ab7c16a89cb470f3fa85818ee85e1e1dd">is_configured</a>())</div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  {</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  <a class="code" href="_error_8h.xhtml#a54a6080c9f4df1f908e57a9bbb46f5da">ARM_COMPUTE_ERROR_ON</a>(!_original_b-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a209ea2ddfdfa80703799c92da8beb643">is_used</a>());</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>  _asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77">prepare</a>();</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  }</div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span>  <span class="keywordflow">else</span> <span class="keywordflow">if</span>(_reshape_b_only_on_first_run && !_run_vector_matrix_multiplication && !_asm_glue.<a class="code" href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ab7c16a89cb470f3fa85818ee85e1e1dd">is_configured</a>())</div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>  {</div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span>  <a class="code" href="_error_8h.xhtml#a54a6080c9f4df1f908e57a9bbb46f5da">ARM_COMPUTE_ERROR_ON</a>(!_original_b-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a209ea2ddfdfa80703799c92da8beb643">is_used</a>());</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span> </div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>  _tmp_b.<a class="code" href="classarm__compute_1_1_tensor.xhtml#adbd0cf83a8e1b335a9bf405a8e5019fa">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>  <a class="code" href="classarm__compute_1_1_scheduler.xhtml#a0d63ca713bab377aabcfb63c192b8429">NEScheduler::get</a>().<a class="code" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">schedule</a>(&_transpose_kernel, <a class="code" href="classarm__compute_1_1_window.xhtml#ad2d402364fa822b0b7775081291eeca9">Window::DimY</a>);</div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span>  _original_b-><a class="code" href="classarm__compute_1_1_i_tensor.xhtml#a9bc00234de9adf8c99a21eb1d7d494c2">mark_as_unused</a>();</div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span>  }</div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span> </div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span>  _is_prepared = <span class="keyword">true</span>;</div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span>  }</div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span> }</div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> } <span class="comment">// namespace arm_compute</span></div><div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml_adfd4c40b75cbb4b1b2b2c2bac0051891"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml#adfd4c40b75cbb4b1b2b2c2bac0051891">arm_compute::GEMMInfo::set_pretranpose_B</a></div><div class="ttdeci">void set_pretranpose_B(bool flag)</div><div class="ttdoc">Set pre-transpose b flag.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l02015">Types.h:2015</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_xhtml_abaa70c8f86d580a791200678388d0073"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#abaa70c8f86d580a791200678388d0073">arm_compute::NEGEMM::NEGEMM</a></div><div class="ttdeci">NEGEMM(std::shared_ptr< IMemoryManager > memory_manager=nullptr)</div><div class="ttdoc">Constructor.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_8cpp_source.xhtml#l00045">NEGEMM.cpp:45</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_shape_xhtml"><div class="ttname"><a href="classarm__compute_1_1_tensor_shape.xhtml">arm_compute::TensorShape</a></div><div class="ttdoc">Shape of a tensor.</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_shape_8h_source.xhtml#l00039">TensorShape.h:39</a></div></div> |
| <div class="ttc" id="_toolchain_support_8h_xhtml"><div class="ttname"><a href="_toolchain_support_8h.xhtml">ToolchainSupport.h</a></div></div> |
| <div class="ttc" id="_i_tensor_8h_xhtml"><div class="ttname"><a href="_i_tensor_8h.xhtml">ITensor.h</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1misc_1_1shape__calculator_xhtml_a5797726a8fbee3b11b92757c2f0031d6"><div class="ttname"><a href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml#a5797726a8fbee3b11b92757c2f0031d6">arm_compute::misc::shape_calculator::compute_transpose1xW_with_element_size_shape</a></div><div class="ttdeci">TensorShape compute_transpose1xW_with_element_size_shape(const ITensorInfo &b, int mult_transpose1xW_width=1)</div><div class="ttdoc">Calculate the transposed 1xW width element shape.</div><div class="ttdef"><b>Definition:</b> <a href="_shape_calculator_8h_source.xhtml#l00301">ShapeCalculator.h:301</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_info_xhtml_afbc359bde9be72a6edab175978e56662"><div class="ttname"><a href="classarm__compute_1_1_tensor_info.xhtml#afbc359bde9be72a6edab175978e56662">arm_compute::TensorInfo::clone</a></div><div class="ttdeci">std::unique_ptr< ITensorInfo > clone() const override</div><div class="ttdoc">Provide a clone of the current object of class T.</div><div class="ttdef"><b>Definition:</b> <a href="src_2core_2_tensor_info_8cpp_source.xhtml#l00306">TensorInfo.cpp:306</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_allocator_xhtml_a3fc6adad84b23f10d54d5a7b6928f872"><div class="ttname"><a href="classarm__compute_1_1_tensor_allocator.xhtml#a3fc6adad84b23f10d54d5a7b6928f872">arm_compute::TensorAllocator::init</a></div><div class="ttdeci">void init(const TensorAllocator &allocator, const Coordinates &coords, TensorInfo &sub_info)</div><div class="ttdoc">Shares the same backing memory with another tensor allocator, while the tensor info might be differen...</div><div class="ttdef"><b>Definition:</b> <a href="src_2runtime_2_tensor_allocator_8cpp_source.xhtml#l00108">TensorAllocator.cpp:108</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_info_xhtml_a178f0d3d87f959e00a743328d95359d2"><div class="ttname"><a href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">arm_compute::ITensorInfo::dimension</a></div><div class="ttdeci">virtual size_t dimension(size_t index) const =0</div><div class="ttdoc">Return the size of the requested dimension.</div></div> |
| <div class="ttc" id="_n_e_g_e_m_m_8h_xhtml"><div class="ttname"><a href="_n_e_g_e_m_m_8h.xhtml">NEGEMM.h</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_aa76b4a6e74940dabc5b7fc6b2dab3545"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">arm_compute::test::validation::b</a></div><div class="ttdeci">SimpleTensor< float > b</div><div class="ttdef"><b>Definition:</b> <a href="_c_p_p_2_d_f_t_8cpp_source.xhtml#l00157">DFT.cpp:157</a></div></div> |
| <div class="ttc" id="_validate_8h_xhtml_a8f3ff7da485ff7e75dab07baadf5b4bd"><div class="ttname"><a href="_validate_8h.xhtml#a8f3ff7da485ff7e75dab07baadf5b4bd">ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES</a></div><div class="ttdeci">#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)</div><div class="ttdef"><b>Definition:</b> <a href="_validate_8h_source.xhtml#l00545">Validate.h:545</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_reshape_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_reshape_info.xhtml">arm_compute::GEMMReshapeInfo</a></div><div class="ttdoc">GEMM reshape information class.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01724">Types.h:1724</a></div></div> |
| <div class="ttc" id="_tensor_allocator_8h_xhtml"><div class="ttname"><a href="_tensor_allocator_8h.xhtml">TensorAllocator.h</a></div></div> |
| <div class="ttc" id="_error_8h_xhtml_a8a1e1c105f0bdaf37db408c7cfcb77a4"><div class="ttname"><a href="_error_8h.xhtml#a8a1e1c105f0bdaf37db408c7cfcb77a4">ARM_COMPUTE_RETURN_ON_ERROR</a></div><div class="ttdeci">#define ARM_COMPUTE_RETURN_ON_ERROR(status)</div><div class="ttdoc">Checks if a status contains an error and returns it.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00193">Error.h:193</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1misc_1_1shape__calculator_xhtml_adca241b012a5e00ddfcdc5a8db05a2a3"><div class="ttname"><a href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml#adca241b012a5e00ddfcdc5a8db05a2a3">arm_compute::misc::shape_calculator::compute_mm_shape</a></div><div class="ttdeci">TensorShape compute_mm_shape(const ITensorInfo &input0, const ITensorInfo &input1, bool is_interleaved_transposed, const GEMMReshapeInfo &reshape_info)</div><div class="ttdoc">Calculate the matrix multiplication output shape of two tensors.</div><div class="ttdef"><b>Definition:</b> <a href="_shape_calculator_8h_source.xhtml#l00822">ShapeCalculator.h:822</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_xhtml_a209ea2ddfdfa80703799c92da8beb643"><div class="ttname"><a href="classarm__compute_1_1_i_tensor.xhtml#a209ea2ddfdfa80703799c92da8beb643">arm_compute::ITensor::is_used</a></div><div class="ttdeci">bool is_used() const</div><div class="ttdoc">Flags if the tensor is used or not.</div><div class="ttdef"><b>Definition:</b> <a href="_i_tensor_8cpp_source.xhtml#l00162">ITensor.cpp:162</a></div></div> |
| <div class="ttc" id="_validate_8h_xhtml_ae7eed178dac535c6e727061b1f5bc6eb"><div class="ttname"><a href="_validate_8h.xhtml#ae7eed178dac535c6e727061b1f5bc6eb">ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN</a></div><div class="ttdeci">#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)</div><div class="ttdef"><b>Definition:</b> <a href="_validate_8h_source.xhtml#l00791">Validate.h:791</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_ab4e88c89b3b7ea1735996cc4def22d58a44ad4ef5a76e6aa6fb3e3fa079a54fda"><div class="ttname"><a href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a44ad4ef5a76e6aa6fb3e3fa079a54fda">arm_compute::Format::F32</a></div><div class="ttdoc">1 channel, 1 F32 per channel</div></div> |
| <div class="ttc" id="_error_8h_xhtml_a54a6080c9f4df1f908e57a9bbb46f5da"><div class="ttname"><a href="_error_8h.xhtml#a54a6080c9f4df1f908e57a9bbb46f5da">ARM_COMPUTE_ERROR_ON</a></div><div class="ttdeci">#define ARM_COMPUTE_ERROR_ON(cond)</div><div class="ttdoc">If the condition is true then an error message is printed and an exception thrown.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00337">Error.h:337</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_i_tensor_info.xhtml">arm_compute::ITensorInfo</a></div><div class="ttdoc">Store the tensor's metadata.</div><div class="ttdef"><b>Definition:</b> <a href="_i_tensor_info_8h_source.xhtml#l00040">ITensorInfo.h:40</a></div></div> |
| <div class="ttc" id="_error_8h_xhtml_a938dcd406ce611ef5345ad2531cdb948"><div class="ttname"><a href="_error_8h.xhtml#a938dcd406ce611ef5345ad2531cdb948">ARM_COMPUTE_ERROR_THROW_ON</a></div><div class="ttdeci">#define ARM_COMPUTE_ERROR_THROW_ON(status)</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00327">Error.h:327</a></div></div> |
| <div class="ttc" id="_n_e_g_e_m_m_assembly_dispatch_8h_xhtml"><div class="ttname"><a href="_n_e_g_e_m_m_assembly_dispatch_8h.xhtml">NEGEMMAssemblyDispatch.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml_abbd888f118c2209bf7578eb4f8942a07"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml#abbd888f118c2209bf7578eb4f8942a07">arm_compute::GEMMInfo::depth_output_gemm3d</a></div><div class="ttdeci">int depth_output_gemm3d() const</div><div class="ttdoc">Depth of the output when GEMM output is reinterpreted as 3D tensor.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01959">Types.h:1959</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_a4c9101ca1a1f72f48efff28b4b9a6495a704bfa6c1ed5e479c8cfb5bdfc8cccda"><div class="ttname"><a href="namespacearm__compute.xhtml#a4c9101ca1a1f72f48efff28b4b9a6495a704bfa6c1ed5e479c8cfb5bdfc8cccda">arm_compute::MemoryPolicy::MINIMIZE</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_status_xhtml"><div class="ttname"><a href="classarm__compute_1_1_status.xhtml">arm_compute::Status</a></div><div class="ttdoc">Status class.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00052">Error.h:52</a></div></div> |
| <div class="ttc" id="_tensor_info_8h_xhtml"><div class="ttname"><a href="_tensor_info_8h.xhtml">TensorInfo.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch_xhtml_ad1717410afd0be936c6213a63c8005fb"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ad1717410afd0be936c6213a63c8005fb">arm_compute::NEGEMMAssemblyDispatch::run</a></div><div class="ttdeci">void run() override</div><div class="ttdoc">Run the kernels contained in the function.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00439">NEGEMMAssemblyDispatch.cpp:439</a></div></div> |
| <div class="ttc" id="_error_8h_xhtml_a206d6e247e0957ac3dee45d27756fc25"><div class="ttname"><a href="_error_8h.xhtml#a206d6e247e0957ac3dee45d27756fc25">ARM_COMPUTE_RETURN_ERROR_ON</a></div><div class="ttdeci">#define ARM_COMPUTE_RETURN_ERROR_ON(cond)</div><div class="ttdoc">If the condition is true, an error is returned.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00244">Error.h:244</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_xhtml"><div class="ttname"><a href="classarm__compute_1_1_i_tensor.xhtml">arm_compute::ITensor</a></div><div class="ttdoc">Interface for NEON tensor.</div><div class="ttdef"><b>Definition:</b> <a href="_i_tensor_8h_source.xhtml#l00036">ITensor.h:36</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel_xhtml_ae722d2edbab88977ea4604d5395d8463"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel.xhtml#ae722d2edbab88977ea4604d5395d8463">arm_compute::NEGEMMMatrixAdditionKernel::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *input, const ITensorInfo *output, float beta)</div><div class="ttdoc">Static function to check if given info will lead to a valid configuration of NEGEMMMatrixAdditionKern...</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_matrix_addition_kernel_8cpp_source.xhtml#l00144">NEGEMMMatrixAdditionKernel.cpp:144</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1misc_1_1shape__calculator_xhtml_a8d52adbbcd2c53f837c96b5a3d15c4fb"><div class="ttname"><a href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml#a8d52adbbcd2c53f837c96b5a3d15c4fb">arm_compute::misc::shape_calculator::compute_interleaved_shape</a></div><div class="ttdeci">TensorShape compute_interleaved_shape(const ITensorInfo &a, int mult_interleave4x4_height=1, bool reinterpret_input_as_3d=false)</div><div class="ttdoc">Calculate the interleaved shape of an input tensor.</div><div class="ttdef"><b>Definition:</b> <a href="_shape_calculator_8h_source.xhtml#l00224">ShapeCalculator.h:224</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel_xhtml_a968b23a6ef327fcfb5b99d58e3fbe883"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel.xhtml#a968b23a6ef327fcfb5b99d58e3fbe883">arm_compute::NEGEMMTranspose1xWKernel::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *input, const ITensorInfo *output)</div><div class="ttdoc">Static function to check if given info will lead to a valid configuration of NEGEMMTranspose1xWKernel...</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_transpose1x_w_kernel_8cpp_source.xhtml#l00115">NEGEMMTranspose1xWKernel.cpp:115</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml"><div class="ttname"><a href="namespacearm__compute.xhtml">arm_compute</a></div><div class="ttdoc">Copyright (c) 2017-2018 ARM Limited.</div><div class="ttdef"><b>Definition:</b> <a href="00__introduction_8dox_source.xhtml#l00024">00_introduction.dox:24</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_a47be6fa38308d0003c25b60b7dbc45ce"><div class="ttname"><a href="namespacearm__compute.xhtml#a47be6fa38308d0003c25b60b7dbc45ce">arm_compute::auto_init_if_empty</a></div><div class="ttdeci">bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())</div><div class="ttdoc">Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...</div><div class="ttdef"><b>Definition:</b> <a href="_helpers_8inl_source.xhtml#l00201">Helpers.inl:201</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml_a77964edb8d16bb8ec14ddd8985e03cb0"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml#a77964edb8d16bb8ec14ddd8985e03cb0">arm_compute::GEMMInfo::is_b_reshaped</a></div><div class="ttdeci">bool is_b_reshaped() const</div><div class="ttdoc">Flag which specifies if the matrix B has been reshaped.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01941">Types.h:1941</a></div></div> |
| <div class="ttc" id="_c_p_p_2_validate_8h_xhtml_ad2633f3560322e1f8d926949dec1b730"><div class="ttname"><a href="_c_p_p_2_validate_8h.xhtml#ad2633f3560322e1f8d926949dec1b730">ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED</a></div><div class="ttdeci">#define ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED(tensor)</div><div class="ttdef"><b>Definition:</b> <a href="_c_p_p_2_validate_8h_source.xhtml#l00071">Validate.h:71</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_ab4e88c89b3b7ea1735996cc4def22d58a56d8353718e6fdc78b8d69078a2cdb94"><div class="ttname"><a href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a56d8353718e6fdc78b8d69078a2cdb94">arm_compute::Format::F16</a></div><div class="ttdoc">1 channel, 1 F16 per channel</div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_xhtml_adbd0cf83a8e1b335a9bf405a8e5019fa"><div class="ttname"><a href="classarm__compute_1_1_tensor.xhtml#adbd0cf83a8e1b335a9bf405a8e5019fa">arm_compute::Tensor::allocator</a></div><div class="ttdeci">TensorAllocator * allocator()</div><div class="ttdoc">Return a pointer to the tensor's allocator.</div><div class="ttdef"><b>Definition:</b> <a href="runtime_2_tensor_8cpp_source.xhtml#l00048">Tensor.cpp:48</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_xhtml_a9bc00234de9adf8c99a21eb1d7d494c2"><div class="ttname"><a href="classarm__compute_1_1_i_tensor.xhtml#a9bc00234de9adf8c99a21eb1d7d494c2">arm_compute::ITensor::mark_as_unused</a></div><div class="ttdeci">void mark_as_unused() const</div><div class="ttdoc">Marks a tensor as unused.</div><div class="ttdef"><b>Definition:</b> <a href="_i_tensor_8cpp_source.xhtml#l00167">ITensor.cpp:167</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch_xhtml_a89a324550419139fd5b03254a70bbd36"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#a89a324550419139fd5b03254a70bbd36">arm_compute::NEGEMMAssemblyDispatch::configure</a></div><div class="ttdeci">void configure(const ITensor *a, const ITensor *b, const ITensor *c, ITensor *d, float alpha, float beta, const GEMMInfo &gemm_info)</div><div class="ttdoc">If supported create an ACL function else fallback to the arm_gemm function.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00380">NEGEMMAssemblyDispatch.cpp:380</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_xhtml_a3493ba7d1f2057740ff5931fa00a44ac"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a3493ba7d1f2057740ff5931fa00a44ac">arm_compute::NEGEMM::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *c, const ITensorInfo *output, float alpha, float beta, const GEMMInfo &gemm_info=GEMMInfo())</div><div class="ttdoc">Static function to check if given info will lead to a valid configuration of NEGEMM.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_8cpp_source.xhtml#l00139">NEGEMM.cpp:139</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_xhtml_ad1717410afd0be936c6213a63c8005fb"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#ad1717410afd0be936c6213a63c8005fb">arm_compute::NEGEMM::run</a></div><div class="ttdeci">void run() override</div><div class="ttdoc">Run the kernels contained in the function.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_8cpp_source.xhtml#l00239">NEGEMM.cpp:239</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_window_xhtml_aa96e81276ee4f87ab386cd05a5539a7d"><div class="ttname"><a href="classarm__compute_1_1_window.xhtml#aa96e81276ee4f87ab386cd05a5539a7d">arm_compute::Window::DimX</a></div><div class="ttdeci">static constexpr size_t DimX</div><div class="ttdoc">Alias for dimension 0 also known as X dimension.</div><div class="ttdef"><b>Definition:</b> <a href="_window_8h_source.xhtml#l00043">Window.h:43</a></div></div> |
| <div class="ttc" id="_error_8h_xhtml_a6dc630a6ae9cc063b3924bcea8dee9d6"><div class="ttname"><a href="_error_8h.xhtml#a6dc630a6ae9cc063b3924bcea8dee9d6">ARM_COMPUTE_UNUSED</a></div><div class="ttdeci">#define ARM_COMPUTE_UNUSED(...)</div><div class="ttdoc">To avoid unused variables warnings.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00160">Error.h:160</a></div></div> |
| <div class="ttc" id="_c_p_p_2_validate_8h_xhtml"><div class="ttname"><a href="_c_p_p_2_validate_8h.xhtml">Validate.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_memory_group_base_xhtml_ac1f67376afb7822f262a0174ef4a3104"><div class="ttname"><a href="classarm__compute_1_1_memory_group_base.xhtml#ac1f67376afb7822f262a0174ef4a3104">arm_compute::MemoryGroupBase::manage</a></div><div class="ttdeci">void manage(TensorType *obj)</div><div class="ttdoc">Sets a object to be managed by the given memory group.</div><div class="ttdef"><b>Definition:</b> <a href="_memory_group_base_8h_source.xhtml#l00102">MemoryGroupBase.h:102</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch_xhtml_aa9b93ef660fc3c5b4b19d3fc7b891b77"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77">arm_compute::NEGEMMAssemblyDispatch::prepare</a></div><div class="ttdeci">void prepare() override</div><div class="ttdoc">Runs a preparation step, usually for pre-transposing matrix b.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00421">NEGEMMAssemblyDispatch.cpp:421</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_info_xhtml_a7c66505457d00ece3aa4b34cab80757d"><div class="ttname"><a href="classarm__compute_1_1_i_tensor_info.xhtml#a7c66505457d00ece3aa4b34cab80757d">arm_compute::ITensorInfo::tensor_shape</a></div><div class="ttdeci">virtual const TensorShape & tensor_shape() const =0</div><div class="ttdoc">Size for each dimension of the tensor.</div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch_xhtml_ab7c16a89cb470f3fa85818ee85e1e1dd"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ab7c16a89cb470f3fa85818ee85e1e1dd">arm_compute::NEGEMMAssemblyDispatch::is_configured</a></div><div class="ttdeci">bool is_configured() const</div><div class="ttdoc">Was the function successfully configured ?</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00434">NEGEMMAssemblyDispatch.cpp:434</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel_xhtml_a968b23a6ef327fcfb5b99d58e3fbe883"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel.xhtml#a968b23a6ef327fcfb5b99d58e3fbe883">arm_compute::NEGEMMInterleave4x4Kernel::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *input, const ITensorInfo *output)</div><div class="ttdoc">Static function to check if given info will lead to a valid configuration of NEGEMMInterleave4x4Kerne...</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_interleave4x4_kernel_8cpp_source.xhtml#l00214">NEGEMMInterleave4x4Kernel.cpp:214</a></div></div> |
| <div class="ttc" id="_error_8h_xhtml_a86084036bd3851575ef871ad5bf079a7"><div class="ttname"><a href="_error_8h.xhtml#a86084036bd3851575ef871ad5bf079a7">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a></div><div class="ttdeci">#define ARM_COMPUTE_RETURN_ERROR_ON_MSG(cond,...)</div><div class="ttdoc">If the condition is true, an error is returned.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00214">Error.h:214</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_allocator_xhtml_a6e509c2a177b0b29e9e2369535094dee"><div class="ttname"><a href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">arm_compute::TensorAllocator::allocate</a></div><div class="ttdeci">void allocate() override</div><div class="ttdoc">Allocate size specified by TensorInfo of CPU memory.</div><div class="ttdef"><b>Definition:</b> <a href="src_2runtime_2_tensor_allocator_8cpp_source.xhtml#l00133">TensorAllocator.cpp:133</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel_xhtml_a83a344e60eb7db895953a942abf16628"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel.xhtml#a83a344e60eb7db895953a942abf16628">arm_compute::NEGEMMInterleave4x4Kernel::configure</a></div><div class="ttdeci">void configure(const ITensor *input, ITensor *output)</div><div class="ttdoc">Initialise the kernel's input and output.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_interleave4x4_kernel_8cpp_source.xhtml#l00179">NEGEMMInterleave4x4Kernel.cpp:179</a></div></div> |
| <div class="ttc" id="_shape_calculator_8h_xhtml"><div class="ttname"><a href="_shape_calculator_8h.xhtml">ShapeCalculator.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1misc_1_1_i_cloneable_xhtml_a4d10e5012a872e7f78f2b539b673049d"><div class="ttname"><a href="classarm__compute_1_1misc_1_1_i_cloneable.xhtml#a4d10e5012a872e7f78f2b539b673049d">arm_compute::misc::ICloneable::clone</a></div><div class="ttdeci">virtual std::unique_ptr< T > clone() const =0</div><div class="ttdoc">Provide a clone of the current object of class T.</div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_xhtml_a0e95dc1e53c361348314873b168ae237"><div class="ttname"><a href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">arm_compute::ITensor::info</a></div><div class="ttdeci">virtual ITensorInfo * info() const =0</div><div class="ttdoc">Interface to be implemented by the child class to return the tensor's metadata.</div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_abb7e0f23a4f2e63f39433f158dad47ab"><div class="ttname"><a href="namespacearm__compute.xhtml#abb7e0f23a4f2e63f39433f158dad47ab">arm_compute::data_size_from_type</a></div><div class="ttdeci">size_t data_size_from_type(DataType data_type)</div><div class="ttdoc">The size in bytes of the data type.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_utils_8h_source.xhtml#l00109">Utils.h:109</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_m_e_m_info_xhtml_aacc842e7ef6389e970d92af1d62793a7"><div class="ttname"><a href="classarm__compute_1_1_m_e_m_info.xhtml#aacc842e7ef6389e970d92af1d62793a7">arm_compute::MEMInfo::get_policy</a></div><div class="ttdeci">static MemoryPolicy get_policy()</div><div class="ttdef"><b>Definition:</b> <a href="_m_e_m_utils_8cpp_source.xhtml#l00086">MEMUtils.cpp:86</a></div></div> |
| <div class="ttc" id="_n_e_scheduler_8h_xhtml"><div class="ttname"><a href="_n_e_scheduler_8h.xhtml">NEScheduler.h</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a3161c2c93c655dd30953372064ec627b"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a3161c2c93c655dd30953372064ec627b">arm_compute::test::validation::alpha</a></div><div class="ttdeci">const float alpha</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_o_n_2_accumulate_8cpp_source.xhtml#l00103">Accumulate.cpp:103</a></div></div> |
| <div class="ttc" id="_error_8h_xhtml"><div class="ttname"><a href="_error_8h.xhtml">Error.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml_a00330b8913cac3b07029ac0c3350e806"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml#a00330b8913cac3b07029ac0c3350e806">arm_compute::GEMMInfo::reinterpret_input_as_3d</a></div><div class="ttdeci">bool reinterpret_input_as_3d() const</div><div class="ttdoc">Flag which specifies if the input tensor has to be reinterpreted as 3D.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01967">Types.h:1967</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel_xhtml_a83a344e60eb7db895953a942abf16628"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel.xhtml#a83a344e60eb7db895953a942abf16628">arm_compute::NEGEMMTranspose1xWKernel::configure</a></div><div class="ttdeci">void configure(const ITensor *input, ITensor *output)</div><div class="ttdoc">Initialise the kernel's input and output.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_transpose1x_w_kernel_8cpp_source.xhtml#l00096">NEGEMMTranspose1xWKernel.cpp:96</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml_aa7e9584d7080ca6442cec62afaff6cad"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml#aa7e9584d7080ca6442cec62afaff6cad">arm_compute::GEMMInfo::is_a_reshaped</a></div><div class="ttdeci">bool is_a_reshaped() const</div><div class="ttdoc">Flag which specifies if the matrix A has been reshaped.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01933">Types.h:1933</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_window_xhtml_ad2d402364fa822b0b7775081291eeca9"><div class="ttname"><a href="classarm__compute_1_1_window.xhtml#ad2d402364fa822b0b7775081291eeca9">arm_compute::Window::DimY</a></div><div class="ttdeci">static constexpr size_t DimY</div><div class="ttdoc">Alias for dimension 1 also known as Y dimension.</div><div class="ttdef"><b>Definition:</b> <a href="_window_8h_source.xhtml#l00045">Window.h:45</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_memory_group_resource_scope_xhtml"><div class="ttname"><a href="classarm__compute_1_1_memory_group_resource_scope.xhtml">arm_compute::MemoryGroupResourceScope</a></div><div class="ttdoc">Memory group resources scope handling class.</div><div class="ttdef"><b>Definition:</b> <a href="_i_memory_group_8h_source.xhtml#l00046">IMemoryGroup.h:46</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_info_xhtml_a18064e0011c3869d884653e9e7c47b66"><div class="ttname"><a href="classarm__compute_1_1_i_tensor_info.xhtml#a18064e0011c3869d884653e9e7c47b66">arm_compute::ITensorInfo::total_size</a></div><div class="ttdeci">virtual size_t total_size() const =0</div><div class="ttdoc">Returns the total size of the tensor in bytes.</div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_scheduler_xhtml_a4e58f95544bd5ac6559a421671bd9842"><div class="ttname"><a href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">arm_compute::IScheduler::schedule</a></div><div class="ttdeci">virtual void schedule(ICPPKernel *kernel, const Hints &hints)=0</div><div class="ttdoc">Runs the kernel in the same thread as the caller synchronously.</div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel_xhtml_a4ee07709711414457834cc5d1c2c6cdb"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel.xhtml#a4ee07709711414457834cc5d1c2c6cdb">arm_compute::NEGEMMMatrixMultiplyKernel::configure</a></div><div class="ttdeci">void configure(const ITensor *input0, const ITensor *input1, ITensor *output, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info=GEMMReshapeInfo())</div><div class="ttdoc">Initialise the kernel's input and output.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_matrix_multiply_kernel_8cpp_source.xhtml#l00962">NEGEMMMatrixMultiplyKernel.cpp:962</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_xhtml_a385241dcc5062af6ecac8bdafe01bb2a"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a385241dcc5062af6ecac8bdafe01bb2a">arm_compute::NEGEMM::configure</a></div><div class="ttdeci">void configure(const ITensor *a, const ITensor *b, const ITensor *c, ITensor *d, float alpha, float beta, const GEMMInfo &gemm_info=GEMMInfo())</div><div class="ttdoc">Initialise the kernel's inputs, output.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_8cpp_source.xhtml#l00051">NEGEMM.cpp:51</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel_xhtml_abd3df2f9251266926538e4c020652996"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel.xhtml#abd3df2f9251266926538e4c020652996">arm_compute::NEGEMMMatrixAdditionKernel::configure</a></div><div class="ttdeci">void configure(const ITensor *input, ITensor *output, float beta)</div><div class="ttdoc">Initialise the kernel's input and output.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_matrix_addition_kernel_8cpp_source.xhtml#l00116">NEGEMMMatrixAdditionKernel.cpp:116</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_xhtml_aa9b93ef660fc3c5b4b19d3fc7b891b77"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77">arm_compute::NEGEMM::prepare</a></div><div class="ttdeci">void prepare() override</div><div class="ttdoc">Prepare the function for executing.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_8cpp_source.xhtml#l00273">NEGEMM.cpp:273</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_shape_xhtml_a9c54fb6cea3557692fe7c00c40bb40ad"><div class="ttname"><a href="classarm__compute_1_1_tensor_shape.xhtml#a9c54fb6cea3557692fe7c00c40bb40ad">arm_compute::TensorShape::set</a></div><div class="ttdeci">TensorShape & set(size_t dimension, size_t value, bool apply_dim_correction=true)</div><div class="ttdoc">Accessor to set the value of one of the dimensions.</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_shape_8h_source.xhtml#l00078">TensorShape.h:78</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_tensor_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_tensor_info.xhtml">arm_compute::TensorInfo</a></div><div class="ttdoc">Store the tensor's metadata.</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_info_8h_source.xhtml#l00045">TensorInfo.h:45</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml_a4c8f9fa843de1086c27c86a6b8cf4582"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml#a4c8f9fa843de1086c27c86a6b8cf4582">arm_compute::GEMMInfo::reshape_b_only_on_first_run</a></div><div class="ttdeci">bool reshape_b_only_on_first_run() const</div><div class="ttdoc">Flag which specifies if the reshape of matrix B should executed only for the first.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01951">Types.h:1951</a></div></div> |
| <div class="ttc" id="arm__compute_2core_2_helpers_8h_xhtml"><div class="ttname"><a href="arm__compute_2core_2_helpers_8h.xhtml">Helpers.h</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1misc_1_1shape__calculator_xhtml"><div class="ttname"><a href="namespacearm__compute_1_1misc_1_1shape__calculator.xhtml">arm_compute::misc::shape_calculator</a></div><div class="ttdef"><b>Definition:</b> <a href="_shape_calculator_8h_source.xhtml#l00040">ShapeCalculator.h:40</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel_xhtml_ac91476ef04db46dad52f3cd1e2fae18e"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel.xhtml#ac91476ef04db46dad52f3cd1e2fae18e">arm_compute::NEGEMMMatrixMultiplyKernel::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info)</div><div class="ttdoc">Static function to check if given info will lead to a valid configuration of NEGEMMMatrixMultiplyKern...</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_matrix_multiply_kernel_8cpp_source.xhtml#l00987">NEGEMMMatrixMultiplyKernel.cpp:987</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_g_e_m_m_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_g_e_m_m_info.xhtml">arm_compute::GEMMInfo</a></div><div class="ttdoc">GEMM information class.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l01880">Types.h:1880</a></div></div> |
| <div class="ttc" id="arm__compute_2core_2_types_8h_xhtml"><div class="ttname"><a href="arm__compute_2core_2_types_8h.xhtml">Types.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch_xhtml_ae9f257420d216441868cad263ffa2775"><div class="ttname"><a href="classarm__compute_1_1_n_e_g_e_m_m_assembly_dispatch.xhtml#ae9f257420d216441868cad263ffa2775">arm_compute::NEGEMMAssemblyDispatch::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *c, const ITensorInfo *d, float alpha, float beta, const GEMMInfo &gemm_info)</div><div class="ttdoc">Indicates whether or not this function can be used to process the given parameters.</div><div class="ttdef"><b>Definition:</b> <a href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00361">NEGEMMAssemblyDispatch.cpp:361</a></div></div> |
| <div class="ttc" id="_validate_8h_xhtml"><div class="ttname"><a href="_validate_8h.xhtml">Validate.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_scheduler_xhtml_a0d63ca713bab377aabcfb63c192b8429"><div class="ttname"><a href="classarm__compute_1_1_scheduler.xhtml#a0d63ca713bab377aabcfb63c192b8429">arm_compute::Scheduler::get</a></div><div class="ttdeci">static IScheduler & get()</div><div class="ttdoc">Access the scheduler singleton.</div><div class="ttdef"><b>Definition:</b> <a href="_scheduler_8cpp_source.xhtml#l00096">Scheduler.cpp:96</a></div></div> |
| </div><!-- fragment --></div><!-- contents --> |
| </div><!-- doc-content --> |
| <!-- start footer part --> |
| <div id="nav-path" class="navpath"><!-- id is needed for treeview function! --> |
| <ul> |
| <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.xhtml">src</a></li><li class="navelem"><a class="el" href="dir_bf9f26469d00835ba20ff8d80ee5a804.xhtml">runtime</a></li><li class="navelem"><a class="el" href="dir_a36523fc4c32a6b0076906589b6fc202.xhtml">NEON</a></li><li class="navelem"><a class="el" href="dir_4d03f28cfd35f8f734a3b0a2f1168d27.xhtml">functions</a></li><li class="navelem"><a class="el" href="_n_e_g_e_m_m_8cpp.xhtml">NEGEMM.cpp</a></li> |
| <li class="footer">Generated on Mon Sep 2 2019 11:47:26 for Compute Library by |
| <a href="http://www.doxygen.org/index.html"> |
| <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.15 </li> |
| </ul> |
| </div> |
| </body> |
| </html> |
