| <!-- 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: NEGEMM Class Reference</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('classarm__compute_1_1_n_e_g_e_m_m.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="summary"> |
| <a href="#pub-methods">Public Member Functions</a> | |
| <a href="#pub-static-methods">Static Public Member Functions</a> </div> |
| <div class="headertitle"> |
| <div class="title">NEGEMM Class Reference</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| |
| <p>Basic function to execute GEMM on NEON. |
| <a href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#details">More...</a></p> |
| |
| <p><code>#include <<a class="el" href="_n_e_g_e_m_m_8h_source.xhtml">NEGEMM.h</a>></code></p> |
| <div class="dynheader"> |
| Collaboration diagram for NEGEMM:</div> |
| <div class="dyncontent"> |
| <div class="center"><iframe scrolling="no" frameborder="0" src="classarm__compute_1_1_n_e_g_e_m_m__coll__graph.svg" width="91" height="112"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe> |
| </div> |
| <center><span class="legend">[<a target="top" href="graph_legend.xhtml">legend</a>]</span></center></div> |
| <table class="memberdecls"> |
| <tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pub-methods"></a> |
| Public Member Functions</h2></td></tr> |
| <tr class="memitem:abaa70c8f86d580a791200678388d0073"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#abaa70c8f86d580a791200678388d0073">NEGEMM</a> (std::shared_ptr< <a class="el" href="classarm__compute_1_1_i_memory_manager.xhtml">IMemoryManager</a> > memory_manager=nullptr)</td></tr> |
| <tr class="memdesc:abaa70c8f86d580a791200678388d0073"><td class="mdescLeft"> </td><td class="mdescRight">Constructor. <a href="#abaa70c8f86d580a791200678388d0073">More...</a><br /></td></tr> |
| <tr class="separator:abaa70c8f86d580a791200678388d0073"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a545e2af1971b9885b46f0f58b5893628"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a545e2af1971b9885b46f0f58b5893628">NEGEMM</a> (const <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> &)=delete</td></tr> |
| <tr class="memdesc:a545e2af1971b9885b46f0f58b5893628"><td class="mdescLeft"> </td><td class="mdescRight">Prevent instances of this class from being copied (As this class contains pointers) <a href="#a545e2af1971b9885b46f0f58b5893628">More...</a><br /></td></tr> |
| <tr class="separator:a545e2af1971b9885b46f0f58b5893628"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ac2d5f41869fc7a6313f453067c09c882"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#ac2d5f41869fc7a6313f453067c09c882">NEGEMM</a> (<a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> &&)=default</td></tr> |
| <tr class="memdesc:ac2d5f41869fc7a6313f453067c09c882"><td class="mdescLeft"> </td><td class="mdescRight">Default move constructor. <a href="#ac2d5f41869fc7a6313f453067c09c882">More...</a><br /></td></tr> |
| <tr class="separator:ac2d5f41869fc7a6313f453067c09c882"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a01cad4311af868f78ee3de9e09b4a6a8"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> & </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a01cad4311af868f78ee3de9e09b4a6a8">operator=</a> (const <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> &)=delete</td></tr> |
| <tr class="memdesc:a01cad4311af868f78ee3de9e09b4a6a8"><td class="mdescLeft"> </td><td class="mdescRight">Prevent instances of this class from being copied (As this class contains pointers) <a href="#a01cad4311af868f78ee3de9e09b4a6a8">More...</a><br /></td></tr> |
| <tr class="separator:a01cad4311af868f78ee3de9e09b4a6a8"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a296a65f1339d5d42de2fd545a9dc6c6d"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> & </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a296a65f1339d5d42de2fd545a9dc6c6d">operator=</a> (<a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> &&)=default</td></tr> |
| <tr class="memdesc:a296a65f1339d5d42de2fd545a9dc6c6d"><td class="mdescLeft"> </td><td class="mdescRight">Default move assignment operator. <a href="#a296a65f1339d5d42de2fd545a9dc6c6d">More...</a><br /></td></tr> |
| <tr class="separator:a296a65f1339d5d42de2fd545a9dc6c6d"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a385241dcc5062af6ecac8bdafe01bb2a"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a385241dcc5062af6ecac8bdafe01bb2a">configure</a> (const <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *a, const <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *b, const <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *c, <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> *d, float alpha, float beta, const <a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> &gemm_info=<a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a>())</td></tr> |
| <tr class="memdesc:a385241dcc5062af6ecac8bdafe01bb2a"><td class="mdescLeft"> </td><td class="mdescRight">Initialise the kernel's inputs, output. <a href="#a385241dcc5062af6ecac8bdafe01bb2a">More...</a><br /></td></tr> |
| <tr class="separator:a385241dcc5062af6ecac8bdafe01bb2a"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ad1717410afd0be936c6213a63c8005fb"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#ad1717410afd0be936c6213a63c8005fb">run</a> () override</td></tr> |
| <tr class="memdesc:ad1717410afd0be936c6213a63c8005fb"><td class="mdescLeft"> </td><td class="mdescRight">Run the kernels contained in the function. <a href="#ad1717410afd0be936c6213a63c8005fb">More...</a><br /></td></tr> |
| <tr class="separator:ad1717410afd0be936c6213a63c8005fb"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:aa9b93ef660fc3c5b4b19d3fc7b891b77"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77">prepare</a> () override</td></tr> |
| <tr class="memdesc:aa9b93ef660fc3c5b4b19d3fc7b891b77"><td class="mdescLeft"> </td><td class="mdescRight">Prepare the function for executing. <a href="#aa9b93ef660fc3c5b4b19d3fc7b891b77">More...</a><br /></td></tr> |
| <tr class="separator:aa9b93ef660fc3c5b4b19d3fc7b891b77"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="inherit_header pub_methods_classarm__compute_1_1_i_function"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classarm__compute_1_1_i_function')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classarm__compute_1_1_i_function.xhtml">IFunction</a></td></tr> |
| <tr class="memitem:ab921ecc3f3f6ae2b4bd61f3e1998d8c4 inherit pub_methods_classarm__compute_1_1_i_function"><td class="memItemLeft" align="right" valign="top">virtual </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_i_function.xhtml#ab921ecc3f3f6ae2b4bd61f3e1998d8c4">~IFunction</a> ()=default</td></tr> |
| <tr class="memdesc:ab921ecc3f3f6ae2b4bd61f3e1998d8c4 inherit pub_methods_classarm__compute_1_1_i_function"><td class="mdescLeft"> </td><td class="mdescRight">Destructor. <a href="classarm__compute_1_1_i_function.xhtml#ab921ecc3f3f6ae2b4bd61f3e1998d8c4">More...</a><br /></td></tr> |
| <tr class="separator:ab921ecc3f3f6ae2b4bd61f3e1998d8c4 inherit pub_methods_classarm__compute_1_1_i_function"><td class="memSeparator" colspan="2"> </td></tr> |
| </table><table class="memberdecls"> |
| <tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pub-static-methods"></a> |
| Static Public Member Functions</h2></td></tr> |
| <tr class="memitem:a3493ba7d1f2057740ff5931fa00a44ac"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classarm__compute_1_1_status.xhtml">Status</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#a3493ba7d1f2057740ff5931fa00a44ac">validate</a> (const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *a, const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *b, const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *c, const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *output, float alpha, float beta, const <a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> &gemm_info=<a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a>())</td></tr> |
| <tr class="memdesc:a3493ba7d1f2057740ff5931fa00a44ac"><td class="mdescLeft"> </td><td class="mdescRight">Static function to check if given info will lead to a valid configuration of <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a>. <a href="#a3493ba7d1f2057740ff5931fa00a44ac">More...</a><br /></td></tr> |
| <tr class="separator:a3493ba7d1f2057740ff5931fa00a44ac"><td class="memSeparator" colspan="2"> </td></tr> |
| </table> |
| <a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2> |
| <div class="textblock"><p>Basic function to execute GEMM on NEON. </p> |
| <p>This function calls the following NEON kernels:</p> |
| <ol type="1"> |
| <li><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m_interleave4x4_kernel.xhtml">NEGEMMInterleave4x4Kernel</a> (if the output tensor is a matrix)</li> |
| <li><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m_transpose1x_w_kernel.xhtml">NEGEMMTranspose1xWKernel</a> (if the output tensor is a matrix)</li> |
| <li><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_multiply_kernel.xhtml">NEGEMMMatrixMultiplyKernel</a></li> |
| <li><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m_matrix_addition_kernel.xhtml">NEGEMMMatrixAdditionKernel</a> (if c != nullptr and beta != 0.0) </li> |
| </ol> |
| |
| <p class="definition">Definition at line <a class="el" href="_n_e_g_e_m_m_8h_source.xhtml#l00050">50</a> of file <a class="el" href="_n_e_g_e_m_m_8h_source.xhtml">NEGEMM.h</a>.</p> |
| </div><h2 class="groupheader">Constructor & Destructor Documentation</h2> |
| <a id="abaa70c8f86d580a791200678388d0073"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#abaa70c8f86d580a791200678388d0073">◆ </a></span>NEGEMM() <span class="overload">[1/3]</span></h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> </td> |
| <td>(</td> |
| <td class="paramtype">std::shared_ptr< <a class="el" href="classarm__compute_1_1_i_memory_manager.xhtml">IMemoryManager</a> > </td> |
| <td class="paramname"><em>memory_manager</em> = <code>nullptr</code></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Constructor. </p> |
| |
| <p class="definition">Definition at line <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00045">45</a> of file <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml">NEGEMM.cpp</a>.</p> |
| <div class="fragment"><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(<span class="keyword">nullptr</span>),</div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  _run_vector_matrix_multiplication(<span class="keyword">false</span>), _run_addition(<span class="keyword">false</span>), _reshape_b_only_on_first_run(<span class="keyword">false</span>), _is_prepared(<span class="keyword">false</span>)</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><!-- fragment --> |
| </div> |
| </div> |
| <a id="a545e2af1971b9885b46f0f58b5893628"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a545e2af1971b9885b46f0f58b5893628">◆ </a></span>NEGEMM() <span class="overload">[2/3]</span></h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> </td> |
| <td>(</td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> & </td> |
| <td class="paramname"></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">delete</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Prevent instances of this class from being copied (As this class contains pointers) </p> |
| |
| </div> |
| </div> |
| <a id="ac2d5f41869fc7a6313f453067c09c882"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#ac2d5f41869fc7a6313f453067c09c882">◆ </a></span>NEGEMM() <span class="overload">[3/3]</span></h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> </td> |
| <td>(</td> |
| <td class="paramtype"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> && </td> |
| <td class="paramname"></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">default</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Default move constructor. </p> |
| |
| </div> |
| </div> |
| <h2 class="groupheader">Member Function Documentation</h2> |
| <a id="a385241dcc5062af6ecac8bdafe01bb2a"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a385241dcc5062af6ecac8bdafe01bb2a">◆ </a></span>configure()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">void configure </td> |
| <td>(</td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> * </td> |
| <td class="paramname"><em>a</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> * </td> |
| <td class="paramname"><em>b</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> * </td> |
| <td class="paramname"><em>c</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype"><a class="el" href="classarm__compute_1_1_i_tensor.xhtml">ITensor</a> * </td> |
| <td class="paramname"><em>d</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">float </td> |
| <td class="paramname"><em>alpha</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">float </td> |
| <td class="paramname"><em>beta</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> & </td> |
| <td class="paramname"><em>gemm_info</em> = <code><a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a>()</code> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Initialise the kernel's inputs, output. </p> |
| <dl class="section note"><dt>Note</dt><dd>GEMM: General Matrix Multiply - [alpha * A * B + beta * C]. </dd> |
| <dd> |
| GEMM: The tensors a, b, c, d must have the same data type. You should not mix data types when calling this function.</dd></dl> |
| <dl class="params"><dt>Parameters</dt><dd> |
| <table class="params"> |
| <tr><td class="paramdir">[in]</td><td class="paramname">a</td><td>First input tensor (Matrix A or <a class="el" href="struct_vector.xhtml" title="Structure to hold Vector information.">Vector</a> A). Data type supported: F16/F32 </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">b</td><td>Second input tensor (Matrix B). Data type supported: same as <code>a</code> </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">c</td><td>Third input tensor (Matrix C). It can be a nullptr if just the multiplication between <code>a</code> and <code>b</code> is needed. Data type supported: same as <code>a</code> </td></tr> |
| <tr><td class="paramdir">[out]</td><td class="paramname">d</td><td>Output tensor. Data type supported: same as <code>a</code> </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">alpha</td><td>Weight of the matrix product </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">beta</td><td>Weight of matrix C </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">gemm_info</td><td>(Optional) Specifies if the matrix A and/or matrix B have been reshaped and if the reshape of matrix B should happen only for the first run </td></tr> |
| </table> |
| </dd> |
| </dl> |
| |
| <p class="definition">Definition at line <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00051">51</a> of file <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml">NEGEMM.cpp</a>.</p> |
| <div class="fragment"><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->info(), <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info(), (c != <span class="keyword">nullptr</span>) ? c->info() : <span class="keyword">nullptr</span>, d->info(), <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.reshape_b_only_on_first_run();</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  _run_vector_matrix_multiplication = a->info()->dimension(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->info(), <a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#aa76b4a6e74940dabc5b7fc6b2dab3545">b</a>->info(), c != <span class="keyword">nullptr</span> ? c->info() : <span class="keyword">nullptr</span>, d->info(), <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>  GEMMInfo gemm_info_ntb = gemm_info;</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  gemm_info_ntb.set_pretranpose_B(<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>  TensorShape shape_tmp_a = a->info()->tensor_shape();</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  TensorShape 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.set(0, a->info()->dimension(0) * 4);</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  shape_tmp_a.set(1, std::ceil(a->info()->dimension(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.set(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.set(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>  TensorInfo info_a = a->info()->clone()->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>  TensorInfo 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->info()->dimension(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->info()->dimension(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>, GEMMReshapeInfo(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="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="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="_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="_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="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_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_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_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_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_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="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="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="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_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_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_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><!-- fragment --> |
| <p class="reference">References <a class="el" href="src_2runtime_2_tensor_allocator_8cpp_source.xhtml#l00133">TensorAllocator::allocate()</a>, <a class="el" href="runtime_2_tensor_8cpp_source.xhtml#l00048">Tensor::allocator()</a>, <a class="el" href="_n_e_o_n_2_accumulate_8cpp_source.xhtml#l00103">arm_compute::test::validation::alpha</a>, <a class="el" href="_error_8h_source.xhtml#l00337">ARM_COMPUTE_ERROR_ON</a>, <a class="el" href="_error_8h_source.xhtml#l00327">ARM_COMPUTE_ERROR_THROW_ON</a>, <a class="el" href="_c_p_p_2_d_f_t_8cpp_source.xhtml#l00157">arm_compute::test::validation::b</a>, <a class="el" href="classarm__compute_1_1misc_1_1_i_cloneable.xhtml#a4d10e5012a872e7f78f2b539b673049d">ICloneable< T >::clone()</a>, <a class="el" href="_n_e_g_e_m_m_interleave4x4_kernel_8cpp_source.xhtml#l00179">NEGEMMInterleave4x4Kernel::configure()</a>, <a class="el" href="_n_e_g_e_m_m_matrix_addition_kernel_8cpp_source.xhtml#l00116">NEGEMMMatrixAdditionKernel::configure()</a>, <a class="el" href="_n_e_g_e_m_m_matrix_multiply_kernel_8cpp_source.xhtml#l00962">NEGEMMMatrixMultiplyKernel::configure()</a>, <a class="el" href="_n_e_g_e_m_m_transpose1x_w_kernel_8cpp_source.xhtml#l00096">NEGEMMTranspose1xWKernel::configure()</a>, <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00380">NEGEMMAssemblyDispatch::configure()</a>, <a class="el" href="arm__compute_2core_2_utils_8h_source.xhtml#l00109">arm_compute::data_size_from_type()</a>, <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">ITensorInfo::dimension()</a>, <a class="el" href="_m_e_m_utils_8cpp_source.xhtml#l00086">MEMInfo::get_policy()</a>, <a class="el" href="classarm__compute_1_1_i_tensor.xhtml#a0e95dc1e53c361348314873b168ae237">ITensor::info()</a>, <a class="el" href="src_2runtime_2_tensor_allocator_8cpp_source.xhtml#l00108">TensorAllocator::init()</a>, <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00434">NEGEMMAssemblyDispatch::is_configured()</a>, <a class="el" href="_memory_group_base_8h_source.xhtml#l00102">MemoryGroupBase< TensorType >::manage()</a>, <a class="el" href="namespacearm__compute.xhtml#a4c9101ca1a1f72f48efff28b4b9a6495a704bfa6c1ed5e479c8cfb5bdfc8cccda">arm_compute::MINIMIZE</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l01951">GEMMInfo::reshape_b_only_on_first_run()</a>, <a class="el" href="_tensor_shape_8h_source.xhtml#l00078">TensorShape::set()</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l02015">GEMMInfo::set_pretranpose_B()</a>, <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml#a7c66505457d00ece3aa4b34cab80757d">ITensorInfo::tensor_shape()</a>, <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00139">NEGEMM::validate()</a>, and <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00361">NEGEMMAssemblyDispatch::validate()</a>.</p> |
| |
| <p class="reference">Referenced by <a class="el" href="_n_e_r_n_n_layer_8cpp_source.xhtml#l00067">NERNNLayer::configure()</a>, <a class="el" href="_n_e_winograd_convolution_layer_8cpp_source.xhtml#l00244">NEWinogradConvolutionLayer::configure()</a>, and <a class="el" href="_n_e_l_s_t_m_layer_8cpp_source.xhtml#l00056">NELSTMLayer::configure()</a>.</p> |
| |
| </div> |
| </div> |
| <a id="a01cad4311af868f78ee3de9e09b4a6a8"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a01cad4311af868f78ee3de9e09b4a6a8">◆ </a></span>operator=() <span class="overload">[1/2]</span></h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a>& operator= </td> |
| <td>(</td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> & </td> |
| <td class="paramname"></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">delete</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Prevent instances of this class from being copied (As this class contains pointers) </p> |
| |
| </div> |
| </div> |
| <a id="a296a65f1339d5d42de2fd545a9dc6c6d"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a296a65f1339d5d42de2fd545a9dc6c6d">◆ </a></span>operator=() <span class="overload">[2/2]</span></h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a>& operator= </td> |
| <td>(</td> |
| <td class="paramtype"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a> && </td> |
| <td class="paramname"></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">default</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Default move assignment operator. </p> |
| |
| </div> |
| </div> |
| <a id="aa9b93ef660fc3c5b4b19d3fc7b891b77"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#aa9b93ef660fc3c5b4b19d3fc7b891b77">◆ </a></span>prepare()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">void prepare </td> |
| <td>(</td> |
| <td class="paramname"></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">override</span><span class="mlabel">virtual</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Prepare the function for executing. </p> |
| <p>Any one off pre-processing step required by the function is handled here</p> |
| <dl class="section note"><dt>Note</dt><dd>Prepare stage might not need all the function's buffers' backing memory to be available in order to execute </dd></dl> |
| |
| <p>Reimplemented from <a class="el" href="classarm__compute_1_1_i_function.xhtml#a820f7291c24155a2980512fae45aac26">IFunction</a>.</p> |
| |
| <p class="definition">Definition at line <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00273">273</a> of file <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml">NEGEMM.cpp</a>.</p> |
| <div class="fragment"><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="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="_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_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_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_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_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_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_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_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 --> |
| <p class="reference">References <a class="el" href="src_2runtime_2_tensor_allocator_8cpp_source.xhtml#l00133">TensorAllocator::allocate()</a>, <a class="el" href="runtime_2_tensor_8cpp_source.xhtml#l00048">Tensor::allocator()</a>, <a class="el" href="_error_8h_source.xhtml#l00337">ARM_COMPUTE_ERROR_ON</a>, <a class="el" href="_window_8h_source.xhtml#l00045">Window::DimY</a>, <a class="el" href="_scheduler_8cpp_source.xhtml#l00096">Scheduler::get()</a>, <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00434">NEGEMMAssemblyDispatch::is_configured()</a>, <a class="el" href="_i_tensor_8cpp_source.xhtml#l00162">ITensor::is_used()</a>, <a class="el" href="_i_tensor_8cpp_source.xhtml#l00167">ITensor::mark_as_unused()</a>, <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00421">NEGEMMAssemblyDispatch::prepare()</a>, and <a class="el" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">IScheduler::schedule()</a>.</p> |
| |
| <p class="reference">Referenced by <a class="el" href="_n_e_r_n_n_layer_8cpp_source.xhtml#l00120">NERNNLayer::prepare()</a>, <a class="el" href="_n_e_fully_connected_layer_8cpp_source.xhtml#l00380">NEFullyConnectedLayer::prepare()</a>, <a class="el" href="_n_e_g_e_m_m_convolution_layer_8cpp_source.xhtml#l00600">NEGEMMConvolutionLayer::prepare()</a>, and <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00239">NEGEMM::run()</a>.</p> |
| |
| </div> |
| </div> |
| <a id="ad1717410afd0be936c6213a63c8005fb"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#ad1717410afd0be936c6213a63c8005fb">◆ </a></span>run()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">void run </td> |
| <td>(</td> |
| <td class="paramname"></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">override</span><span class="mlabel">virtual</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Run the kernels contained in the function. </p> |
| <p>For NEON kernels:</p><ul> |
| <li>Multi-threading is used for the kernels which are parallelisable.</li> |
| <li>By default std::thread::hardware_concurrency() threads are used.</li> |
| </ul> |
| <dl class="section note"><dt>Note</dt><dd><a class="el" href="classarm__compute_1_1_c_p_p_scheduler.xhtml#ae64eebaa07f4d2da6cc2ba538c3cb095">CPPScheduler::set_num_threads()</a> can be used to manually set the number of threads</dd></dl> |
| <p>For OpenCL kernels:</p><ul> |
| <li>All the kernels are enqueued on the queue associated with <a class="el" href="classarm__compute_1_1_c_l_scheduler.xhtml" title="Provides global access to a CL context and command queue.">CLScheduler</a>.</li> |
| <li>The queue is then flushed.</li> |
| </ul> |
| <dl class="section note"><dt>Note</dt><dd>The function will not block until the kernels are executed. It is the user's responsibility to wait. </dd> |
| <dd> |
| Will call <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml#aa9b93ef660fc3c5b4b19d3fc7b891b77" title="Prepare the function for executing.">prepare()</a> on first run if hasn't been done </dd></dl> |
| |
| <p>Implements <a class="el" href="classarm__compute_1_1_i_function.xhtml#a18954417d3124a8095783ea13dc6d00b">IFunction</a>.</p> |
| |
| <p class="definition">Definition at line <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00239">239</a> of file <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml">NEGEMM.cpp</a>.</p> |
| <div class="fragment"><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>  MemoryGroupResourceScope 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="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="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="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_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_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_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_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 --> |
| <p class="reference">References <a class="el" href="_window_8h_source.xhtml#l00043">Window::DimX</a>, <a class="el" href="_window_8h_source.xhtml#l00045">Window::DimY</a>, <a class="el" href="_scheduler_8cpp_source.xhtml#l00096">Scheduler::get()</a>, <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00434">NEGEMMAssemblyDispatch::is_configured()</a>, <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00273">NEGEMM::prepare()</a>, <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00439">NEGEMMAssemblyDispatch::run()</a>, and <a class="el" href="classarm__compute_1_1_i_scheduler.xhtml#a4e58f95544bd5ac6559a421671bd9842">IScheduler::schedule()</a>.</p> |
| |
| <p class="reference">Referenced by <a class="el" href="_n_e_winograd_convolution_layer_8cpp_source.xhtml#l00520">NEWinogradConvolutionLayer::run()</a>, <a class="el" href="_n_e_r_n_n_layer_8cpp_source.xhtml#l00103">NERNNLayer::run()</a>, <a class="el" href="_n_e_fully_connected_layer_8cpp_source.xhtml#l00344">NEFullyConnectedLayer::run()</a>, <a class="el" href="_n_e_l_s_t_m_layer_8cpp_source.xhtml#l00611">NELSTMLayer::run()</a>, and <a class="el" href="_n_e_g_e_m_m_convolution_layer_8cpp_source.xhtml#l00551">NEGEMMConvolutionLayer::run()</a>.</p> |
| |
| </div> |
| </div> |
| <a id="a3493ba7d1f2057740ff5931fa00a44ac"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#a3493ba7d1f2057740ff5931fa00a44ac">◆ </a></span>validate()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarm__compute_1_1_status.xhtml">Status</a> validate </td> |
| <td>(</td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> * </td> |
| <td class="paramname"><em>a</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> * </td> |
| <td class="paramname"><em>b</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> * </td> |
| <td class="paramname"><em>c</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> * </td> |
| <td class="paramname"><em>output</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">float </td> |
| <td class="paramname"><em>alpha</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">float </td> |
| <td class="paramname"><em>beta</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a> & </td> |
| <td class="paramname"><em>gemm_info</em> = <code><a class="el" href="classarm__compute_1_1_g_e_m_m_info.xhtml">GEMMInfo</a>()</code> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Static function to check if given info will lead to a valid configuration of <a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a>. </p> |
| <dl class="params"><dt>Parameters</dt><dd> |
| <table class="params"> |
| <tr><td class="paramdir">[in]</td><td class="paramname">a</td><td>First input tensor info (Matrix or <a class="el" href="struct_vector.xhtml" title="Structure to hold Vector information.">Vector</a> A). Data types supported: F16/F32 </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">b</td><td>Second input tensor info (Matrix B). Data type supported: same as <code>a</code>. </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">c</td><td>Third input tensor info (Matrix C). It can be a nullptr if just the multiplication between <code>a</code> and <code>b</code> is needed. Data type supported: same as <code>a</code>. </td></tr> |
| <tr><td class="paramdir">[out]</td><td class="paramname">output</td><td>Output tensor info. Data type supported: same as <code>a</code> </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">alpha</td><td>Weight of the matrix product </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">beta</td><td>Weight of matrix C </td></tr> |
| <tr><td class="paramdir">[in]</td><td class="paramname">gemm_info</td><td>(Optional) Specifies if the matrix A and/or matrix B have been reshaped and if the reshape of matrix B should happen only for the first run</td></tr> |
| </table> |
| </dd> |
| </dl> |
| <dl class="section return"><dt>Returns</dt><dd>a status </dd></dl> |
| |
| <p class="definition">Definition at line <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00139">139</a> of file <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml">NEGEMM.cpp</a>.</p> |
| <div class="fragment"><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->dimension(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.is_a_reshaped(), <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.is_b_reshaped(), <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.depth_output_gemm3d() != 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.reinterpret_input_as_3d());</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->dimension(1) != c->dimension(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->dimension(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->total_size() != 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->dimension(0));</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  <span class="keywordflow">if</span>(gemm_info.depth_output_gemm3d() != 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.reinterpret_input_as_3d())</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->dimension(1) != output->dimension(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->dimension(2) != output->dimension(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->dimension(1) != output->dimension(1) * output->dimension(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->dimension(1) != output->dimension(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.reinterpret_input_as_3d(), <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.depth_output_gemm3d() != 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->dimension(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.reshape_b_only_on_first_run());</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->dimension(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->dimension(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> GEMMReshapeInfo reshape_info = GEMMReshapeInfo(m, n, k, mult_transpose1xW_width, mult_interleave4x4_height, gemm_info.depth_output_gemm3d());</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> ITensorInfo *matrix_a_info = a;</div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  <span class="keyword">const</span> ITensorInfo *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>  TensorInfo tmp_a_info{};</div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  TensorInfo tmp_b_info{};</div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  TensorInfo tmp_output_info = *output->clone();</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->clone()->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.reinterpret_input_as_3d())));</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->clone()->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> Status{};</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span> }</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="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="_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="_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_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_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_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="_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="_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="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="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="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_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><!-- fragment --> |
| <p class="reference">References <a class="el" href="_n_e_o_n_2_accumulate_8cpp_source.xhtml#l00103">arm_compute::test::validation::alpha</a>, <a class="el" href="_error_8h_source.xhtml#l00244">ARM_COMPUTE_RETURN_ERROR_ON</a>, <a class="el" href="_c_p_p_2_validate_8h_source.xhtml#l00071">ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED</a>, <a class="el" href="_validate_8h_source.xhtml#l00791">ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN</a>, <a class="el" href="_validate_8h_source.xhtml#l00545">ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES</a>, <a class="el" href="_error_8h_source.xhtml#l00214">ARM_COMPUTE_RETURN_ERROR_ON_MSG</a>, <a class="el" href="_error_8h_source.xhtml#l00193">ARM_COMPUTE_RETURN_ON_ERROR</a>, <a class="el" href="_error_8h_source.xhtml#l00160">ARM_COMPUTE_UNUSED</a>, <a class="el" href="_helpers_8inl_source.xhtml#l00201">arm_compute::auto_init_if_empty()</a>, <a class="el" href="_c_p_p_2_d_f_t_8cpp_source.xhtml#l00157">arm_compute::test::validation::b</a>, <a class="el" href="classarm__compute_1_1misc_1_1_i_cloneable.xhtml#a4d10e5012a872e7f78f2b539b673049d">ICloneable< T >::clone()</a>, <a class="el" href="src_2core_2_tensor_info_8cpp_source.xhtml#l00306">TensorInfo::clone()</a>, <a class="el" href="_shape_calculator_8h_source.xhtml#l00224">arm_compute::misc::shape_calculator::compute_interleaved_shape()</a>, <a class="el" href="_shape_calculator_8h_source.xhtml#l00822">arm_compute::misc::shape_calculator::compute_mm_shape()</a>, <a class="el" href="_shape_calculator_8h_source.xhtml#l00301">arm_compute::misc::shape_calculator::compute_transpose1xW_with_element_size_shape()</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l01959">GEMMInfo::depth_output_gemm3d()</a>, <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml#a178f0d3d87f959e00a743328d95359d2">ITensorInfo::dimension()</a>, <a class="el" href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a56d8353718e6fdc78b8d69078a2cdb94">arm_compute::F16</a>, <a class="el" href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a44ad4ef5a76e6aa6fb3e3fa079a54fda">arm_compute::F32</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l01933">GEMMInfo::is_a_reshaped()</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l01941">GEMMInfo::is_b_reshaped()</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l01967">GEMMInfo::reinterpret_input_as_3d()</a>, <a class="el" href="arm__compute_2core_2_types_8h_source.xhtml#l01951">GEMMInfo::reshape_b_only_on_first_run()</a>, <a class="el" href="classarm__compute_1_1_i_tensor_info.xhtml#a18064e0011c3869d884653e9e7c47b66">ITensorInfo::total_size()</a>, <a class="el" href="_n_e_g_e_m_m_interleave4x4_kernel_8cpp_source.xhtml#l00214">NEGEMMInterleave4x4Kernel::validate()</a>, <a class="el" href="_n_e_g_e_m_m_matrix_addition_kernel_8cpp_source.xhtml#l00144">NEGEMMMatrixAdditionKernel::validate()</a>, <a class="el" href="_n_e_g_e_m_m_matrix_multiply_kernel_8cpp_source.xhtml#l00987">NEGEMMMatrixMultiplyKernel::validate()</a>, <a class="el" href="_n_e_g_e_m_m_transpose1x_w_kernel_8cpp_source.xhtml#l00115">NEGEMMTranspose1xWKernel::validate()</a>, and <a class="el" href="_n_e_g_e_m_m_assembly_dispatch_8cpp_source.xhtml#l00361">NEGEMMAssemblyDispatch::validate()</a>.</p> |
| |
| <p class="reference">Referenced by <a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml#l00051">NEGEMM::configure()</a>, and <a class="el" href="_n_e_l_s_t_m_layer_8cpp_source.xhtml#l00381">NELSTMLayer::validate()</a>.</p> |
| |
| </div> |
| </div> |
| <hr/>The documentation for this class was generated from the following files:<ul> |
| <li>arm_compute/runtime/NEON/functions/<a class="el" href="_n_e_g_e_m_m_8h_source.xhtml">NEGEMM.h</a></li> |
| <li>src/runtime/NEON/functions/<a class="el" href="_n_e_g_e_m_m_8cpp_source.xhtml">NEGEMM.cpp</a></li> |
| </ul> |
| </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="namespacearm__compute.xhtml">arm_compute</a></li><li class="navelem"><a class="el" href="classarm__compute_1_1_n_e_g_e_m_m.xhtml">NEGEMM</a></li> |
| <li class="footer">Generated on Mon Sep 2 2019 11:47:37 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> |
