| <!-- HTML header for doxygen 1.8.17--> |
| <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "https://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 1.8.17"/> |
| <meta name="viewport" content="width=device-width, initial-scale=1"/> |
| <title>Arm NN: GpuFsaPreCompiledWorkload 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> |
| <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="customdoxygen.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="ArmNN" src="Arm_NN_horizontal_blue.png" style="max-width: 15rem; margin-top: .5rem; margin-left 13px"/> |
| <td id="projectalign" style="padding-left: 0.9em;"> |
| <div id="projectname"> |
|  <span id="projectnumber">24.05</span> |
| </div> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <!-- end header part --> |
| <!-- Generated by Doxygen 1.8.17 --> |
| <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('classarmnn_1_1_gpu_fsa_pre_compiled_workload.html',''); initResizable(); }); |
| /* @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="classarmnn_1_1_gpu_fsa_pre_compiled_workload-members.html">List of all members</a> </div> |
| <div class="headertitle"> |
| <div class="title">GpuFsaPreCompiledWorkload Class Reference</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| |
| <p><code>#include <<a class="el" href="_gpu_fsa_pre_compiled_workload_8hpp_source.html">GpuFsaPreCompiledWorkload.hpp</a>></code></p> |
| <div class="dynheader"> |
| Inheritance diagram for GpuFsaPreCompiledWorkload:</div> |
| <div class="dyncontent"> |
| <div class="center"><iframe scrolling="no" frameborder="0" src="classarmnn_1_1_gpu_fsa_pre_compiled_workload__inherit__graph.svg" width="430" height="294"><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.html">legend</a>]</span></center></div> |
| <div class="dynheader"> |
| Collaboration diagram for GpuFsaPreCompiledWorkload:</div> |
| <div class="dyncontent"> |
| <div class="center"><iframe scrolling="no" frameborder="0" src="classarmnn_1_1_gpu_fsa_pre_compiled_workload__coll__graph.svg" width="735" height="488"><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.html">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:aeef6e7488b495adc96f8abd7d29e3d5f"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_gpu_fsa_pre_compiled_workload.html#aeef6e7488b495adc96f8abd7d29e3d5f">GpuFsaPreCompiledWorkload</a> (const <a class="el" href="structarmnn_1_1_pre_compiled_queue_descriptor.html">PreCompiledQueueDescriptor</a> &descriptor, const <a class="el" href="structarmnn_1_1_workload_info.html">WorkloadInfo</a> &info)</td></tr> |
| <tr class="separator:aeef6e7488b495adc96f8abd7d29e3d5f"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ae071e8822437c78baea75c3aef3a263a"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_gpu_fsa_pre_compiled_workload.html#ae071e8822437c78baea75c3aef3a263a">Execute</a> () const override</td></tr> |
| <tr class="separator:ae071e8822437c78baea75c3aef3a263a"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="inherit_header pub_methods_classarmnn_1_1_base_workload"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classarmnn_1_1_base_workload')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classarmnn_1_1_base_workload.html">BaseWorkload< PreCompiledQueueDescriptor ></a></td></tr> |
| <tr class="memitem:af2ef420610280dc5a661cd3d4836d5a2 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#af2ef420610280dc5a661cd3d4836d5a2">BaseWorkload</a> (const <a class="el" href="structarmnn_1_1_pre_compiled_queue_descriptor.html">PreCompiledQueueDescriptor</a> &descriptor, const <a class="el" href="structarmnn_1_1_workload_info.html">WorkloadInfo</a> &info)</td></tr> |
| <tr class="separator:af2ef420610280dc5a661cd3d4836d5a2 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a163c04b26f9804eafc598a047128f887 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">virtual const std::string & </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#a163c04b26f9804eafc598a047128f887">GetName</a> () const override</td></tr> |
| <tr class="separator:a163c04b26f9804eafc598a047128f887 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ae1c43d025fc90382d7aff7a500937e2c inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#ae1c43d025fc90382d7aff7a500937e2c">ExecuteAsync</a> (<a class="el" href="structarmnn_1_1experimental_1_1_execution_data.html">ExecutionData</a> &executionData) override</td></tr> |
| <tr class="separator:ae1c43d025fc90382d7aff7a500937e2c inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a81627f96ba06d76e147f7d392a8117ed inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#a81627f96ba06d76e147f7d392a8117ed">PostAllocationConfigure</a> () override</td></tr> |
| <tr class="separator:a81627f96ba06d76e147f7d392a8117ed inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a965cf380c7adf547d0f14b3f6d1da249 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">const <a class="el" href="structarmnn_1_1_pre_compiled_queue_descriptor.html">PreCompiledQueueDescriptor</a> & </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#a965cf380c7adf547d0f14b3f6d1da249">GetData</a> () const</td></tr> |
| <tr class="separator:a965cf380c7adf547d0f14b3f6d1da249 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:aaff95a48875d8fb4a616352906660ca9 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">arm::pipe::ProfilingGuid </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#aaff95a48875d8fb4a616352906660ca9">GetGuid</a> () const final</td></tr> |
| <tr class="separator:aaff95a48875d8fb4a616352906660ca9 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a0c326c344355d8423217e9431781f2ee inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">virtual bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#a0c326c344355d8423217e9431781f2ee">SupportsTensorHandleReplacement</a> () const override</td></tr> |
| <tr class="separator:a0c326c344355d8423217e9431781f2ee inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ab0a67f8179ddb997dda0070a6661f837 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#ab0a67f8179ddb997dda0070a6661f837">ReplaceInputTensorHandle</a> (<a class="el" href="classarmnn_1_1_i_tensor_handle.html">ITensorHandle</a> *tensorHandle, unsigned int slot) override</td></tr> |
| <tr class="separator:ab0a67f8179ddb997dda0070a6661f837 inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:acc08590544f05c641d21c724aedf26dd inherit pub_methods_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#acc08590544f05c641d21c724aedf26dd">ReplaceOutputTensorHandle</a> (<a class="el" href="classarmnn_1_1_i_tensor_handle.html">ITensorHandle</a> *tensorHandle, unsigned int slot) override</td></tr> |
| <tr class="separator:acc08590544f05c641d21c724aedf26dd inherit pub_methods_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="inherit_header pub_methods_classarmnn_1_1_i_workload"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classarmnn_1_1_i_workload')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classarmnn_1_1_i_workload.html">IWorkload</a></td></tr> |
| <tr class="memitem:a69c83c02ae8de866bc7a46c49e69c1ba inherit pub_methods_classarmnn_1_1_i_workload"><td class="memItemLeft" align="right" valign="top">virtual </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_i_workload.html#a69c83c02ae8de866bc7a46c49e69c1ba">~IWorkload</a> ()</td></tr> |
| <tr class="separator:a69c83c02ae8de866bc7a46c49e69c1ba inherit pub_methods_classarmnn_1_1_i_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a00f887eb14b9ed163d795b31c4964965 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memItemLeft" align="right" valign="top">virtual arm::pipe::ProfilingGuid </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_i_workload.html#a00f887eb14b9ed163d795b31c4964965">GetGuid</a> () const =0</td></tr> |
| <tr class="separator:a00f887eb14b9ed163d795b31c4964965 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a4295bd67f063570a3a378dc2fbf16df5 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memItemLeft" align="right" valign="top">virtual const std::string & </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_i_workload.html#a4295bd67f063570a3a378dc2fbf16df5">GetName</a> () const =0</td></tr> |
| <tr class="separator:a4295bd67f063570a3a378dc2fbf16df5 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:ab81312bd5e64cbae2803de9f243bdb32 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_i_workload.html#ab81312bd5e64cbae2803de9f243bdb32">RegisterDebugCallback</a> (const <a class="el" href="namespacearmnn.html#a15f3ad9b5e4e3d46b0a6dda246a7bc28">DebugCallbackFunction</a> &)</td></tr> |
| <tr class="separator:ab81312bd5e64cbae2803de9f243bdb32 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a2d2834d1029217934f504e3e59579081 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classarmnn_1_1_optional.html">armnn::Optional</a>< <a class="el" href="structarmnn_1_1_memory_requirements.html">armnn::MemoryRequirements</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_i_workload.html#a2d2834d1029217934f504e3e59579081">GetMemoryRequirements</a> ()</td></tr> |
| <tr class="separator:a2d2834d1029217934f504e3e59579081 inherit pub_methods_classarmnn_1_1_i_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| </table><table class="memberdecls"> |
| <tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="inherited"></a> |
| Additional Inherited Members</h2></td></tr> |
| <tr class="inherit_header pro_attribs_classarmnn_1_1_base_workload"><td colspan="2" onclick="javascript:toggleInherit('pro_attribs_classarmnn_1_1_base_workload')"><img src="closed.png" alt="-"/> Protected Attributes inherited from <a class="el" href="classarmnn_1_1_base_workload.html">BaseWorkload< PreCompiledQueueDescriptor ></a></td></tr> |
| <tr class="memitem:afb8d2c8817c75de9d01a4c0e0d5c160b inherit pro_attribs_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top"><a class="el" href="structarmnn_1_1_pre_compiled_queue_descriptor.html">PreCompiledQueueDescriptor</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a></td></tr> |
| <tr class="separator:afb8d2c8817c75de9d01a4c0e0d5c160b inherit pro_attribs_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a4c2b3ca86eec6c199364671af267cd2c inherit pro_attribs_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">const arm::pipe::ProfilingGuid </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#a4c2b3ca86eec6c199364671af267cd2c">m_Guid</a></td></tr> |
| <tr class="separator:a4c2b3ca86eec6c199364671af267cd2c inherit pro_attribs_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a77806f89d6edb879d3f6c6b6b18168a7 inherit pro_attribs_classarmnn_1_1_base_workload"><td class="memItemLeft" align="right" valign="top">const std::string </td><td class="memItemRight" valign="bottom"><a class="el" href="classarmnn_1_1_base_workload.html#a77806f89d6edb879d3f6c6b6b18168a7">m_Name</a></td></tr> |
| <tr class="separator:a77806f89d6edb879d3f6c6b6b18168a7 inherit pro_attribs_classarmnn_1_1_base_workload"><td class="memSeparator" colspan="2"> </td></tr> |
| </table> |
| <a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2> |
| <div class="textblock"> |
| <p class="definition">Definition at line <a class="el" href="_gpu_fsa_pre_compiled_workload_8hpp_source.html#l00030">30</a> of file <a class="el" href="_gpu_fsa_pre_compiled_workload_8hpp_source.html">GpuFsaPreCompiledWorkload.hpp</a>.</p> |
| </div><h2 class="groupheader">Constructor & Destructor Documentation</h2> |
| <a id="aeef6e7488b495adc96f8abd7d29e3d5f"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#aeef6e7488b495adc96f8abd7d29e3d5f">◆ </a></span>GpuFsaPreCompiledWorkload()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="memname"> |
| <tr> |
| <td class="memname"><a class="el" href="classarmnn_1_1_gpu_fsa_pre_compiled_workload.html">GpuFsaPreCompiledWorkload</a> </td> |
| <td>(</td> |
| <td class="paramtype">const <a class="el" href="structarmnn_1_1_pre_compiled_queue_descriptor.html">PreCompiledQueueDescriptor</a> & </td> |
| <td class="paramname"><em>descriptor</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">const <a class="el" href="structarmnn_1_1_workload_info.html">WorkloadInfo</a> & </td> |
| <td class="paramname"><em>info</em> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p class="definition">Definition at line <a class="el" href="_gpu_fsa_pre_compiled_workload_8cpp_source.html#l00031">31</a> of file <a class="el" href="_gpu_fsa_pre_compiled_workload_8cpp_source.html">GpuFsaPreCompiledWorkload.cpp</a>.</p> |
| <div class="fragment"><div class="line"><a name="l00033"></a><span class="lineno"> 33</span>  : BaseWorkload<PreCompiledQueueDescriptor>(descriptor, info), m_workloadInfo(info)</div> |
| <div class="line"><a name="l00034"></a><span class="lineno"> 34</span> {</div> |
| <div class="line"><a name="l00035"></a><span class="lineno"> 35</span>  <span class="comment">// Check that the workload is holding a pointer to a valid pre-compiled object</span></div> |
| <div class="line"><a name="l00036"></a><span class="lineno"> 36</span>  <span class="keywordflow">if</span> (<a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_pre_compiled_queue_descriptor.html#aa1fedd1a6371526cb68cc5cc58c87465">m_PreCompiledObject</a> == <span class="keyword">nullptr</span>)</div> |
| <div class="line"><a name="l00037"></a><span class="lineno"> 37</span>  {</div> |
| <div class="line"><a name="l00038"></a><span class="lineno"> 38</span>  <span class="keywordflow">throw</span> InvalidArgumentException(</div> |
| <div class="line"><a name="l00039"></a><span class="lineno"> 39</span>  <span class="stringliteral">"GpuFsaPrecompiledWorkload requires a valid pre-compiled object (GpuWorkloadSketch)."</span>);</div> |
| <div class="line"><a name="l00040"></a><span class="lineno"> 40</span>  }</div> |
| <div class="line"><a name="l00041"></a><span class="lineno"> 41</span> }</div> |
| </div><!-- fragment --> |
| <p class="reference">References <a class="el" href="namespacearmnn.html#a4dc0adc6737b5944e7671bee71788407acaf9b6b99962bf5c2264824231d7a40c">armnn::info</a>, <a class="el" href="_workload_8hpp_source.html#l00089">BaseWorkload< PreCompiledQueueDescriptor >::m_Data</a>, and <a class="el" href="_workload_data_8hpp_source.html#l00519">PreCompiledQueueDescriptor::m_PreCompiledObject</a>.</p> |
| |
| </div> |
| </div> |
| <h2 class="groupheader">Member Function Documentation</h2> |
| <a id="ae071e8822437c78baea75c3aef3a263a"></a> |
| <h2 class="memtitle"><span class="permalink"><a href="#ae071e8822437c78baea75c3aef3a263a">◆ </a></span>Execute()</h2> |
| |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">void Execute </td> |
| <td>(</td> |
| <td class="paramname"></td><td>)</td> |
| <td> const</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>Implements <a class="el" href="classarmnn_1_1_i_workload.html#a72ae00e6604850c8798c5e0d825ee7e4">IWorkload</a>.</p> |
| |
| <p class="definition">Definition at line <a class="el" href="_gpu_fsa_pre_compiled_workload_8cpp_source.html#l00043">43</a> of file <a class="el" href="_gpu_fsa_pre_compiled_workload_8cpp_source.html">GpuFsaPreCompiledWorkload.cpp</a>.</p> |
| <div class="fragment"><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> {</div> |
| <div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="comment">/*</span></div> |
| <div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="comment"> * The Execute function of the GpuFsa Backends PreCompiled workload needs to jump through various hoops in order to</span></div> |
| <div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="comment"> * create a valid sketch and runtime that can execute the kernel</span></div> |
| <div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="comment"> * First we need all of the data stored within the PreCompiled blob which was used to setup the workload, namely:</span></div> |
| <div class="line"><a name="l00049"></a><span class="lineno"> 49</span> <span class="comment"> * The GpuWorkloadContext, this is a context which contains the TensorInfos and is unique to the graph being run</span></div> |
| <div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="comment"> * The Sketch, this can contain one or many ops and acts as a subgraph within the context</span></div> |
| <div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="comment"> * The inputTensorInfos / outputTensorInfos, These are vectors containing the TensorInfos used when creating the sketch</span></div> |
| <div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="comment"> * It is very important that the Tensors passed into the Runtime being used to execute this sketch are created with</span></div> |
| <div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="comment"> * the same TensorInfos as used when creating the sketch. We do this by creating new tensors, getting the original</span></div> |
| <div class="line"><a name="l00055"></a><span class="lineno"> 55</span> <span class="comment"> * TensorInfos from the vectors of tensorInfos stored in the blob, and then importing the buffers from our own</span></div> |
| <div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="comment"> * TensorHandles directly into these newly created Tensors. This allows us to link the externally visible Tensors</span></div> |
| <div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="comment"> * from ArmNN to the Tensors which are needed to execute with the Sketch.</span></div> |
| <div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <span class="keyword">using namespace </span>arm_compute::experimental::dynamic_fusion;</div> |
| <div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <span class="comment">// Get the runtime and configure it with the precompiled sketch</span></div> |
| <div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  ClWorkloadRuntime runtime;</div> |
| <div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  GpuFsaPreCompiledBlob *preCompiledBlob = <span class="keyword">static_cast<</span>GpuFsaPreCompiledBlob*<span class="keyword">></span>(<a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_pre_compiled_queue_descriptor.html#aa1fedd1a6371526cb68cc5cc58c87465">m_PreCompiledObject</a>);</div> |
| <div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  <span class="keyword">auto</span> sketch = preCompiledBlob->sketch.release();</div> |
| <div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keyword">auto</span> status = runtime.configure(*sketch);</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>  <span class="comment">// Get the TensorInfos stored within the PreCompiledBlob and check they're the right size</span></div> |
| <div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  <span class="keyword">auto</span> inputTensorInfos = preCompiledBlob->inputTensorInfos.get();</div> |
| <div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <span class="keyword">auto</span> outputTensorInfos = preCompiledBlob->outputTensorInfos.get();</div> |
| <div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  <span class="keywordflow">if</span> (inputTensorInfos->size() != <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>.size())</div> |
| <div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  {</div> |
| <div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  <span class="keywordflow">throw</span> InvalidArgumentException(fmt::format(<span class="stringliteral">"GpuFsaPreCompiledWorkload::Execute: The number of inputTensorInfos"</span></div> |
| <div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  <span class="stringliteral">" {} does not match the number of inputs {}."</span>,</div> |
| <div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  inputTensorInfos->size(), <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>.size()));</div> |
| <div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  }</div> |
| <div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  <span class="keywordflow">if</span> (outputTensorInfos->size() != <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>.size())</div> |
| <div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  {</div> |
| <div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  <span class="keywordflow">throw</span> InvalidArgumentException(fmt::format(<span class="stringliteral">"GpuFsaPreCompiledWorkload::Execute: The number of outputTensorInfos"</span></div> |
| <div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <span class="stringliteral">" {} does not match the number of outputs {}."</span>,</div> |
| <div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  outputTensorInfos->size(), <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>.size()));</div> |
| <div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  }</div> |
| <div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  </div> |
| <div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <span class="comment">// (Important) Allocate auxiliary tensor memory if there are any</span></div> |
| <div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <span class="keywordflow">for</span>(<span class="keyword">auto</span> &data : runtime.get_auxiliary_tensors())</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>  arm_compute::CLTensor* tensor = std::get<0>(data);</div> |
| <div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  arm_compute::TensorInfo <a class="code" href="namespacearmnn.html#a4dc0adc6737b5944e7671bee71788407acaf9b6b99962bf5c2264824231d7a40c">info</a> = std::get<1>(data);</div> |
| <div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  arm_compute::experimental::dynamic_fusion::AuxMemoryInfo aux_mem_req = std::get<2>(data);</div> |
| <div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  tensor->allocator()->init(info, aux_mem_req.alignment);</div> |
| <div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  tensor->allocator()->allocate(); <span class="comment">// Use ACL allocated memory</span></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>  </div> |
| <div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  <span class="comment">// Create and initialize user tensors</span></div> |
| <div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  std::vector<arm_compute::CLTensor*> inputsWeightsOutputs;</div> |
| <div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  inputsWeightsOutputs.reserve(<a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>.size() + <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>.size());</div> |
| <div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  </div> |
| <div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  <span class="keywordflow">for</span> (uint32_t inputSlotIdx = 0; inputSlotIdx < <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>.size(); ++inputSlotIdx)</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>  arm_compute::CLTensor* input = <span class="keyword">new</span> arm_compute::CLTensor{};</div> |
| <div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  <span class="comment">// inputTensorInfos is a ptr to a vector of ptrs, so we need to do a double dereference</span></div> |
| <div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  input->allocator()->init(*((*inputTensorInfos)[inputSlotIdx]));</div> |
| <div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <span class="keyword">auto</span>* inputHandle = PolymorphicDowncast<GpuFsaTensorHandle*>(<a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>[inputSlotIdx]);</div> |
| <div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  input->allocator()->import_memory(inputHandle->GetTensor().cl_buffer());</div> |
| <div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  inputsWeightsOutputs.emplace_back(std::move(input));</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>  <span class="comment">// Set the outputs</span></div> |
| <div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  <span class="keywordflow">for</span> (uint32_t outputSlotIdx = 0; outputSlotIdx < <a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>.size(); ++outputSlotIdx)</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>  arm_compute::CLTensor* output = <span class="keyword">new</span> arm_compute::CLTensor{};</div> |
| <div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  <span class="comment">// outputTensorInfos is a ptr to a vector of ptrs, so we need to do a double dereference</span></div> |
| <div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  output->allocator()->init(*((*outputTensorInfos)[outputSlotIdx]));</div> |
| <div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  <span class="keyword">auto</span>* outputHandle = PolymorphicDowncast<GpuFsaTensorHandle*>(<a class="code" href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.html#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>[outputSlotIdx]);</div> |
| <div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  output->allocator()->import_memory(outputHandle->GetTensor().cl_buffer());</div> |
| <div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  inputsWeightsOutputs.emplace_back(std::move(output));</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>  runtime.run(inputsWeightsOutputs);</div> |
| <div class="line"><a name="l00117"></a><span class="lineno"> 117</span> }</div> |
| </div><!-- fragment --> |
| <p class="reference">References <a class="el" href="namespacearmnn.html#a4dc0adc6737b5944e7671bee71788407acaf9b6b99962bf5c2264824231d7a40c">armnn::info</a>, <a class="el" href="_gpu_fsa_backend_8hpp_source.html#l00037">GpuFsaPreCompiledBlob::inputTensorInfos</a>, <a class="el" href="_workload_8hpp_source.html#l00089">BaseWorkload< PreCompiledQueueDescriptor >::m_Data</a>, <a class="el" href="_workload_data_8hpp_source.html#l00026">QueueDescriptor::m_Inputs</a>, <a class="el" href="_workload_data_8hpp_source.html#l00027">QueueDescriptor::m_Outputs</a>, <a class="el" href="_workload_data_8hpp_source.html#l00519">PreCompiledQueueDescriptor::m_PreCompiledObject</a>, <a class="el" href="_gpu_fsa_backend_8hpp_source.html#l00038">GpuFsaPreCompiledBlob::outputTensorInfos</a>, and <a class="el" href="_gpu_fsa_backend_8hpp_source.html#l00034">GpuFsaPreCompiledBlob::sketch</a>.</p> |
| |
| </div> |
| </div> |
| <hr/>The documentation for this class was generated from the following files:<ul> |
| <li>src/backends/gpuFsa/workloads/<a class="el" href="_gpu_fsa_pre_compiled_workload_8hpp_source.html">GpuFsaPreCompiledWorkload.hpp</a></li> |
| <li>src/backends/gpuFsa/workloads/<a class="el" href="_gpu_fsa_pre_compiled_workload_8cpp_source.html">GpuFsaPreCompiledWorkload.cpp</a></li> |
| </ul> |
| </div><!-- contents --> |
| </div><!-- doc-content --> |
| <div class="ttc" id="astructarmnn_1_1_pre_compiled_queue_descriptor_html_aa1fedd1a6371526cb68cc5cc58c87465"><div class="ttname"><a href="structarmnn_1_1_pre_compiled_queue_descriptor.html#aa1fedd1a6371526cb68cc5cc58c87465">armnn::PreCompiledQueueDescriptor::m_PreCompiledObject</a></div><div class="ttdeci">void * m_PreCompiledObject</div><div class="ttdef"><b>Definition:</b> <a href="_workload_data_8hpp_source.html#l00519">WorkloadData.hpp:519</a></div></div> |
| <div class="ttc" id="anamespacearmnn_html_a4dc0adc6737b5944e7671bee71788407acaf9b6b99962bf5c2264824231d7a40c"><div class="ttname"><a href="namespacearmnn.html#a4dc0adc6737b5944e7671bee71788407acaf9b6b99962bf5c2264824231d7a40c">armnn::BoostLogSeverityMapping::info</a></div><div class="ttdeci">@ info</div></div> |
| <div class="ttc" id="astructarmnn_1_1_queue_descriptor_html_a6abd491bb99ffe88bd472c1ae5a1ed1a"><div class="ttname"><a href="structarmnn_1_1_queue_descriptor.html#a6abd491bb99ffe88bd472c1ae5a1ed1a">armnn::QueueDescriptor::m_Outputs</a></div><div class="ttdeci">std::vector< ITensorHandle * > m_Outputs</div><div class="ttdef"><b>Definition:</b> <a href="_workload_data_8hpp_source.html#l00027">WorkloadData.hpp:27</a></div></div> |
| <div class="ttc" id="aclassarmnn_1_1_base_workload_html_afb8d2c8817c75de9d01a4c0e0d5c160b"><div class="ttname"><a href="classarmnn_1_1_base_workload.html#afb8d2c8817c75de9d01a4c0e0d5c160b">armnn::BaseWorkload< PreCompiledQueueDescriptor >::m_Data</a></div><div class="ttdeci">PreCompiledQueueDescriptor m_Data</div><div class="ttdef"><b>Definition:</b> <a href="_workload_8hpp_source.html#l00089">Workload.hpp:89</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_queue_descriptor_html_a4b50e46a6810018f3edecfb68b2a76b3"><div class="ttname"><a href="structarmnn_1_1_queue_descriptor.html#a4b50e46a6810018f3edecfb68b2a76b3">armnn::QueueDescriptor::m_Inputs</a></div><div class="ttdeci">std::vector< ITensorHandle * > m_Inputs</div><div class="ttdef"><b>Definition:</b> <a href="_workload_data_8hpp_source.html#l00026">WorkloadData.hpp:26</a></div></div> |
| <!-- start footer part --> |
| <div id="nav-path" class="navpath"><!-- id is needed for treeview function! --> |
| <ul> |
| <li class="navelem"><a class="el" href="namespacearmnn.html">armnn</a></li><li class="navelem"><a class="el" href="classarmnn_1_1_gpu_fsa_pre_compiled_workload.html">GpuFsaPreCompiledWorkload</a></li> |
| <li class="footer">Generated on Thu May 16 2024 09:31:56 for Arm NN by |
| <a href="http://www.doxygen.org/index.html"> |
| <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.17 </li> |
| </ul> |
| </div> |
| </body> |
| </html> |