diff options
| author | Nikhil Raj <nikhil.raj@arm.com> | 2023-02-24 10:28:19 +0000 |
|---|---|---|
| committer | Nikhil Raj <nikhil.raj@arm.com> | 2023-02-24 10:28:19 +0000 |
| commit | 8d2ca734165a068478df7cffa46185680b05cd20 (patch) | |
| tree | 0433a7e6b007fe4639334c4438e58e9872a34b20 /23.02/_cl_batch_mat_mul_workload_8cpp_source.xhtml | |
| parent | cb0630959aeae05bc2ae9f6d80cf5f5983a8fb77 (diff) | |
| download | armnn-8d2ca734165a068478df7cffa46185680b05cd20.tar.gz | |
Update Doxygen docu for 23.02
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ie6c19a27d50fefab2796b2b5875374e81f5bf971
Diffstat (limited to '23.02/_cl_batch_mat_mul_workload_8cpp_source.xhtml')
| -rw-r--r-- | 23.02/_cl_batch_mat_mul_workload_8cpp_source.xhtml | 154 |
1 files changed, 154 insertions, 0 deletions
diff --git a/23.02/_cl_batch_mat_mul_workload_8cpp_source.xhtml b/23.02/_cl_batch_mat_mul_workload_8cpp_source.xhtml new file mode 100644 index 0000000000..da9ae3868c --- /dev/null +++ b/23.02/_cl_batch_mat_mul_workload_8cpp_source.xhtml @@ -0,0 +1,154 @@ +<!-- Copyright (c) 2020 ARM Limited. --> +<!-- --> +<!-- SPDX-License-Identifier: MIT --> +<!-- --> +<!-- HTML header for doxygen 1.8.13--> +<!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 1.8.13"/> +<meta name="robots" content="NOINDEX, NOFOLLOW" /> +<meta name="viewport" content="width=device-width, initial-scale=1"/> +<title>ArmNN: src/backends/cl/workloads/ClBatchMatMulWorkload.cpp Source File</title> +<link href="tabs.css" rel="stylesheet" type="text/css"/> +<script type="text/javascript" src="jquery.js"></script> +<script type="text/javascript" src="dynsections.js"></script> +<link href="navtree.css" rel="stylesheet" type="text/css"/> +<script type="text/javascript" src="resize.js"></script> +<script type="text/javascript" src="navtreedata.js"></script> +<script type="text/javascript" src="navtree.js"></script> +<script type="text/javascript"> + $(document).ready(initResizable); +</script> +<link href="search/search.css" rel="stylesheet" type="text/css"/> +<script type="text/javascript" src="search/searchdata.js"></script> +<script type="text/javascript" src="search/search.js"></script> +<script type="text/x-mathjax-config"> + MathJax.Hub.Config({ + extensions: ["tex2jax.js"], + jax: ["input/TeX","output/HTML-CSS"], +}); +</script><script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script> +<link href="doxygen.css" rel="stylesheet" type="text/css" /> +<link href="stylesheet.css" rel="stylesheet" type="text/css"/> +</head> +<body> +<div id="top"><!-- do not remove this div, it is closed by doxygen! --> +<div id="titlearea"> +<table cellspacing="0" cellpadding="0"> + <tbody> + <tr style="height: 56px;"> + <img alt="ArmNN" src="Arm_NN_horizontal_blue.png" style="max-width: 10rem; margin-top: .5rem; margin-left 10px"/> + <td style="padding-left: 0.5em;"> + <div id="projectname"> +  <span id="projectnumber">23.02</span> + </div> + </td> + </tr> + </tbody> +</table> +</div> +<!-- end header part --> +<!-- Generated by Doxygen 1.8.13 --> +<script type="text/javascript"> +var searchBox = new SearchBox("searchBox", "search",false,'Search'); +</script> +<script type="text/javascript" src="menudata.js"></script> +<script type="text/javascript" src="menu.js"></script> +<script type="text/javascript"> +$(function() { + initMenu('',true,false,'search.php','Search'); + $(document).ready(function() { init_search(); }); +}); +</script> +<div id="main-nav"></div> +</div><!-- top --> +<div id="side-nav" class="ui-resizable side-nav-resizable"> + <div id="nav-tree"> + <div id="nav-tree-contents"> + <div id="nav-sync" class="sync"></div> + </div> + </div> + <div id="splitbar" style="-moz-user-select:none;" + class="ui-resizable-handle"> + </div> +</div> +<script type="text/javascript"> +$(document).ready(function(){initNavTree('_cl_batch_mat_mul_workload_8cpp_source.xhtml','');}); +</script> +<div id="doc-content"> +<!-- window showing the filter options --> +<div id="MSearchSelectWindow" + onmouseover="return searchBox.OnSearchSelectShow()" + onmouseout="return searchBox.OnSearchSelectHide()" + onkeydown="return searchBox.OnSearchSelectKey(event)"> +</div> + +<!-- iframe showing the search results (closed by default) --> +<div id="MSearchResultsWindow"> +<iframe src="javascript:void(0)" frameborder="0" + name="MSearchResults" id="MSearchResults"> +</iframe> +</div> + +<div class="header"> + <div class="headertitle"> +<div class="title">ClBatchMatMulWorkload.cpp</div> </div> +</div><!--header--> +<div class="contents"> +<a href="_cl_batch_mat_mul_workload_8cpp.xhtml">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">//</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment">// Copyright © 2022-2023 Arm Ltd and Contributors. All rights reserved.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment">// SPDX-License-Identifier: MIT</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment">//</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> </div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="preprocessor">#include "<a class="code" href="_cl_batch_mat_mul_workload_8hpp.xhtml">ClBatchMatMulWorkload.hpp</a>"</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span> </div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> <span class="preprocessor">#include "<a class="code" href="_cl_workload_utils_8hpp.xhtml">ClWorkloadUtils.hpp</a>"</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> </div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="preprocessor">#include <<a class="code" href="_arm_compute_tensor_utils_8hpp.xhtml">aclCommon/ArmComputeTensorUtils.hpp</a>></span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="preprocessor">#include <<a class="code" href="_arm_compute_utils_8hpp.xhtml">aclCommon/ArmComputeUtils.hpp</a>></span></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span> </div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span> <span class="preprocessor">#include <<a class="code" href="_polymorphic_downcast_8hpp.xhtml">armnn/utility/PolymorphicDowncast.hpp</a>></span></div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span> </div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="preprocessor">#include <<a class="code" href="_permute_8hpp.xhtml">armnnUtils/Permute.hpp</a>></span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="preprocessor">#include <<a class="code" href="_tensor_utils_8hpp.xhtml">armnnUtils/TensorUtils.hpp</a>></span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> </div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span> <span class="preprocessor">#include <<a class="code" href="_workload_utils_8hpp.xhtml">backendsCommon/WorkloadUtils.hpp</a>></span></div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span> </div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span> <span class="preprocessor">#include <<a class="code" href="_cl_tensor_handle_8hpp.xhtml">cl/ClTensorHandle.hpp</a>></span></div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span> </div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span> <span class="preprocessor">#include <arm_compute/runtime/CL/functions/CLGEMM.h></span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span> <span class="preprocessor">#include <arm_compute/runtime/CL/functions/CLPermute.h></span></div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> </div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span> </div><div class="line"><a name="l00026"></a><span class="lineno"> 26</span> <span class="keyword">namespace </span><a class="code" href="namespacearmnn.xhtml">armnn</a></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> {</div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> </div><div class="line"><a name="l00029"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a2a57e49fbc4e44cfa0300229627d04ff"> 29</a></span> <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a> <a class="code" href="namespacearmnn.xhtml#a2a57e49fbc4e44cfa0300229627d04ff">ClBatchMatMulValidate</a>(<span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& inputX,</div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& inputY,</div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& output,</div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span>  <span class="keyword">const</span> <a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml">BatchMatMulDescriptor</a>& descriptor)</div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> {</div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span>  <span class="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a0cf8306be7d301de0f095fff9901a525">m_AdjointX</a> || descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#ad945fc98770356dd886a68e98a52e26b">m_AdjointY</a> )</div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span>  {</div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span>  <span class="keywordflow">throw</span> <a class="code" href="classarmnn_1_1_exception.xhtml">Exception</a>(<span class="stringliteral">"Support for adjoint not implemented."</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">if</span> (descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aedca000a005e091c23191e82d7e81b1d">m_DataLayoutX</a> != <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0a6b99f356fe3b30a2a850b5ea897c289f">armnn::DataLayout::NCHW</a> || descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aaf7828880989b4b9378d3e86aa6dc843">m_DataLayoutY</a> != <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0a6b99f356fe3b30a2a850b5ea897c289f">armnn::DataLayout::NCHW</a> )</div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span>  {</div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span>  <span class="keywordflow">throw</span> <a class="code" href="classarmnn_1_1_exception.xhtml">Exception</a>(<span class="stringliteral">"Only supported the MatMul in the last 2 dimensions"</span>);</div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span>  }</div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> </div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span>  <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a> statusGEMM = <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a>(arm_compute::ErrorCode::OK);</div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span>  <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a> statusPermuteX = <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a>(arm_compute::ErrorCode::OK);</div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span>  <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a> statusPermuteY = <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a>(arm_compute::ErrorCode::OK);</div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> </div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <span class="comment">// ClGemmMatrixMultiplyNativeKernel used by CLGEMM can only support 3 dimensional</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  <span class="comment">// tensors so try to reduce the dimensions to 3</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclInputXInfo = armcomputetensorutils::BuildArmComputeTensorInfo(inputX, descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aedca000a005e091c23191e82d7e81b1d">m_DataLayoutX</a>, 3);</div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclInputYInfo = armcomputetensorutils::BuildArmComputeTensorInfo(inputY, descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aaf7828880989b4b9378d3e86aa6dc843">m_DataLayoutY</a>, 3);</div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclOutputInfo = armcomputetensorutils::BuildArmComputeTensorInfo(output, descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aaf7828880989b4b9378d3e86aa6dc843">m_DataLayoutY</a>, 3);</div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> </div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  arm_compute::TensorInfo aclPermutedXInfo = arm_compute::TensorInfo();</div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  arm_compute::TensorInfo aclPermutedYInfo = arm_compute::TensorInfo();</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> </div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span>  <span class="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#acb441bb8db19bcce78d15cdd8ceb5ea0">m_TransposeX</a> == <span class="keyword">true</span>)</div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  {</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> inputXStripped = <a class="code" href="namespacearmnn_utils.xhtml#a2bff2aae3ae824ff74ba550488373886">armnnUtils::ReduceDims</a>(inputX, 3);</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> </div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <span class="keyword">auto</span> permutationXVector = <a class="code" href="namespacearmnn.xhtml#a15e2ba06d2ecd7ff6013118838e5d1be">GeneratePermutationVectorOnLastTwoDimensions</a>(inputXStripped.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclPermutationXVector = armcomputetensorutils::BuildArmComputePermutationVector(permutationXVector);</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a> permutedXInfo = <a class="code" href="namespacearmnn_utils.xhtml#abeaf4f6785039866fd075f4569ba8e84">armnnUtils::Permuted</a>(inputXStripped, permutationXVector);</div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  aclPermutedXInfo = armcomputetensorutils::BuildArmComputeTensorInfo(permutedXInfo, 3);</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>  statusPermuteX = arm_compute::CLPermute::validate(&aclInputXInfo,</div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  &aclPermutedXInfo,</div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  aclPermutationXVector);</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  }</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span> </div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  <span class="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a112b466e5d2ab9d1887178adbe3afa1c">m_TransposeY</a> == <span class="keyword">true</span>)</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>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> inputYStripped = <a class="code" href="namespacearmnn_utils.xhtml#a2bff2aae3ae824ff74ba550488373886">armnnUtils::ReduceDims</a>(inputY, 3);</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> </div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  <span class="keyword">auto</span> permutationYVector = <a class="code" href="namespacearmnn.xhtml#a15e2ba06d2ecd7ff6013118838e5d1be">GeneratePermutationVectorOnLastTwoDimensions</a>(inputYStripped.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclPermutationYVector = armcomputetensorutils::BuildArmComputePermutationVector(permutationYVector);</div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a> permutedYInfo = <a class="code" href="namespacearmnn_utils.xhtml#abeaf4f6785039866fd075f4569ba8e84">armnnUtils::Permuted</a>(inputYStripped, permutationYVector);</div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  aclPermutedYInfo = armcomputetensorutils::BuildArmComputeTensorInfo(permutedYInfo, 3);</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>  statusPermuteY = arm_compute::CLPermute::validate(&aclInputYInfo,</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  &aclPermutedYInfo,</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  aclPermutationYVector);</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> </div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <span class="keyword">const</span> arm_compute::GEMMInfo& gemm_info = arm_compute::GEMMInfo(<span class="keyword">false</span>, <span class="comment">// is inputX reshaped</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  <span class="keyword">false</span>, <span class="comment">// is inputY reshaped</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  <span class="keyword">false</span>); <span class="comment">// is inputY reshaped only 1st run</span></div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> </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>  statusGEMM = arm_compute::CLGEMM::validate(descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#acb441bb8db19bcce78d15cdd8ceb5ea0">m_TransposeX</a> ? &aclPermutedXInfo : &aclInputXInfo,</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a112b466e5d2ab9d1887178adbe3afa1c">m_TransposeY</a> ? &aclPermutedYInfo : &aclInputYInfo,</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  <span class="keyword">nullptr</span>,</div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  &aclOutputInfo,</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  1.0,</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  0,</div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  gemm_info);</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">if</span> (statusPermuteX.error_code() == arm_compute::ErrorCode::OK &&</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  statusPermuteY.error_code() == arm_compute::ErrorCode::OK &&</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  statusGEMM.error_code() == arm_compute::ErrorCode::OK)</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  {</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  <span class="keywordflow">return</span> <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a>(arm_compute::ErrorCode::OK,</div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <span class="stringliteral">"All Batch Mat Mul layers validate status OK."</span>);</div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  }</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  <span class="keywordflow">else</span></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="keywordflow">return</span> <a class="code" href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a>(arm_compute::ErrorCode::RUNTIME_ERROR,</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  <span class="stringliteral">"BatchMatMul layer validate status failed."</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span>  + statusGEMM.error_description()</div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  + statusPermuteX.error_description()</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  + statusPermuteY.error_description());</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  }</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> }</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span> </div><div class="line"><a name="l00115"></a><span class="lineno"><a class="line" href="classarmnn_1_1_cl_batch_mat_mul_workload.xhtml#acfe62a711ddf54011cb8c34f878de2ac"> 115</a></span> <a class="code" href="classarmnn_1_1_cl_batch_mat_mul_workload.xhtml#acfe62a711ddf54011cb8c34f878de2ac">ClBatchMatMulWorkload::ClBatchMatMulWorkload</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_batch_mat_mul_queue_descriptor.xhtml">BatchMatMulQueueDescriptor</a>& descriptor,</div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span>  <span class="keyword">const</span> <a class="code" href="structarmnn_1_1_workload_info.xhtml">WorkloadInfo</a>& info,</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  <span class="keyword">const</span> arm_compute::CLCompileContext& clCompileContext)</div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span>  : <a class="code" href="classarmnn_1_1_cl_base_workload.xhtml">ClBaseWorkload</a><<a class="code" href="structarmnn_1_1_batch_mat_mul_queue_descriptor.xhtml">BatchMatMulQueueDescriptor</a>>(descriptor, info)</div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span> {</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  <span class="comment">// Report Profiling Details</span></div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <a class="code" href="_profiling_8hpp.xhtml#a786492a3881a4c760ab1eec2149f4aba">ARMNN_REPORT_PROFILING_WORKLOAD_DESC</a>(<span class="stringliteral">"ClBatchMatMulWorkload_Construct"</span>,</div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>,</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  info,</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  this->GetGuid());</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> </div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span>  <span class="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a0cf8306be7d301de0f095fff9901a525">m_AdjointX</a> || descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#ad945fc98770356dd886a68e98a52e26b">m_AdjointY</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>  <span class="keywordflow">throw</span> <a class="code" href="classarmnn_1_1_exception.xhtml">Exception</a>(<span class="stringliteral">"Support for adjoint not implemented."</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="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aedca000a005e091c23191e82d7e81b1d">m_DataLayoutX</a> != <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0a6b99f356fe3b30a2a850b5ea897c289f">armnn::DataLayout::NCHW</a> ||</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aaf7828880989b4b9378d3e86aa6dc843">m_DataLayoutY</a> != <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0a6b99f356fe3b30a2a850b5ea897c289f">armnn::DataLayout::NCHW</a> )</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>  <span class="keywordflow">throw</span> <a class="code" href="classarmnn_1_1_exception.xhtml">Exception</a>(<span class="stringliteral">"Only supported the MatMul in the last 2 dimensions"</span>);</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  }</div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span> </div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  <a class="code" href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.xhtml#a765d2cee4ccce5b9467e0c2b6d25b84a">ValidateInputsOutputs</a>(<span class="stringliteral">"ClBatchMatMulWorkload"</span>, 2, 1);</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span> </div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  <span class="keyword">const</span> arm_compute::ICLTensor& inputX = PolymorphicDowncast<ClTensorHandle*>(<a class="code" href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.xhtml#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>[0])->GetTensor();</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  <span class="keyword">const</span> arm_compute::ICLTensor& inputY = PolymorphicDowncast<ClTensorHandle*>(<a class="code" href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.xhtml#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>[1])->GetTensor();</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  arm_compute::ICLTensor& output = PolymorphicDowncast<ClTensorHandle*>(<a class="code" href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor.xhtml#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>[0])->GetTensor();</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span> </div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span>  inputX.info()->set_data_layout(armcomputetensorutils::ConvertDataLayout(<a class="code" href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aedca000a005e091c23191e82d7e81b1d">m_DataLayoutX</a>));</div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  arm_compute::TensorShape inputXTensorInfo = armcomputetensorutils::BuildArmComputeTensorShape(</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  info.<a class="code" href="structarmnn_1_1_workload_info.xhtml#ac97905bfa0daab357b91df1347600309">m_InputTensorInfos</a>[0].GetShape(), 3);</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  inputX.info()->set_tensor_shape(inputXTensorInfo);</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  inputY.info()->set_data_layout(armcomputetensorutils::ConvertDataLayout(<a class="code" href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">m_Data</a>.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aaf7828880989b4b9378d3e86aa6dc843">m_DataLayoutY</a>));</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  arm_compute::TensorShape inputYTensorInfo = armcomputetensorutils::BuildArmComputeTensorShape(</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  info.<a class="code" href="structarmnn_1_1_workload_info.xhtml#ac97905bfa0daab357b91df1347600309">m_InputTensorInfos</a>[1].GetShape(), 3);</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  inputY.info()->set_tensor_shape(inputYTensorInfo);</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  arm_compute::TensorInfo aclPermutedXInfo = arm_compute::TensorInfo();</div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  arm_compute::TensorInfo aclPermutedYInfo = arm_compute::TensorInfo();</div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span> </div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#acb441bb8db19bcce78d15cdd8ceb5ea0">m_TransposeX</a> == <span class="keyword">true</span>)</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  {</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> strippedInfo = <a class="code" href="namespacearmnn_utils.xhtml#a2bff2aae3ae824ff74ba550488373886">armnnUtils::ReduceDims</a>(info.<a class="code" href="structarmnn_1_1_workload_info.xhtml#ac97905bfa0daab357b91df1347600309">m_InputTensorInfos</a>[0], 3);</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>  <a class="code" href="classarmnn_1_1_permutation_vector.xhtml">armnn::PermutationVector</a> permutationXVector</div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  = <a class="code" href="namespacearmnn.xhtml#a15e2ba06d2ecd7ff6013118838e5d1be">GeneratePermutationVectorOnLastTwoDimensions</a>(strippedInfo.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a> permutedXInfo = <a class="code" href="namespacearmnn_utils.xhtml#abeaf4f6785039866fd075f4569ba8e84">armnnUtils::Permuted</a>(strippedInfo, permutationXVector);</div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclPermutationXVector = armcomputetensorutils::BuildArmComputePermutationVector(permutationXVector);</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  armcomputetensorutils::BuildArmComputeTensor(m_PermutedTensorX, permutedXInfo);</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  armcomputetensorutils::InitialiseArmComputeTensorEmpty(m_PermutedTensorX);</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span> </div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  <span class="keyword">auto</span> permuteLayerX = std::make_unique<arm_compute::CLPermute>();</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  permuteLayerX->configure(clCompileContext,</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  &inputX,</div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  &m_PermutedTensorX,</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  aclPermutationXVector);</div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span>  m_PermuteLayerX.reset(permuteLayerX.release());</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  }</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>  <span class="keywordflow">if</span> (descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a112b466e5d2ab9d1887178adbe3afa1c">m_TransposeY</a> == <span class="keyword">true</span>)</div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  {</div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> strippedInfo = <a class="code" href="namespacearmnn_utils.xhtml#a2bff2aae3ae824ff74ba550488373886">armnnUtils::ReduceDims</a>(info.<a class="code" href="structarmnn_1_1_workload_info.xhtml#ac97905bfa0daab357b91df1347600309">m_InputTensorInfos</a>[1], 3);</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span> </div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  <a class="code" href="classarmnn_1_1_permutation_vector.xhtml">armnn::PermutationVector</a> permutationYVector</div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  = <a class="code" href="namespacearmnn.xhtml#a15e2ba06d2ecd7ff6013118838e5d1be">GeneratePermutationVectorOnLastTwoDimensions</a>(strippedInfo.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a> permutedYInfo = <a class="code" href="namespacearmnn_utils.xhtml#abeaf4f6785039866fd075f4569ba8e84">armnnUtils::Permuted</a>(strippedInfo, permutationYVector);</div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="keyword">const</span> <span class="keyword">auto</span> aclPermutationYVector = armcomputetensorutils::BuildArmComputePermutationVector(permutationYVector);</div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  armcomputetensorutils::BuildArmComputeTensor(m_PermutedTensorY, permutedYInfo);</div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span>  armcomputetensorutils::InitialiseArmComputeTensorEmpty(m_PermutedTensorY);</div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span> </div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span>  <span class="keyword">auto</span> permuteLayerY = std::make_unique<arm_compute::CLPermute>();</div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span>  permuteLayerY->configure(clCompileContext,</div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span>  &inputY,</div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span>  &m_PermutedTensorY,</div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span>  aclPermutationYVector);</div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span>  m_PermuteLayerY.reset(permuteLayerY.release());</div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span>  }</div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span> </div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span>  <span class="keyword">const</span> arm_compute::GEMMInfo& gemm_info = arm_compute::GEMMInfo(<span class="keyword">false</span>, <span class="comment">// is inputX reshaped</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span>  <span class="keyword">false</span>, <span class="comment">// is inputY reshaped</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span>  <span class="keyword">false</span>); <span class="comment">// is inputY reshaped only 1st run</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span>  <span class="keyword">auto</span> gemmLayer = std::make_unique<arm_compute::CLGEMM>();</div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  gemmLayer->configure(clCompileContext,</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>  descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#acb441bb8db19bcce78d15cdd8ceb5ea0">m_TransposeX</a> ? &m_PermutedTensorX : &inputX,</div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span>  descriptor.<a class="code" href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">m_Parameters</a>.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a112b466e5d2ab9d1887178adbe3afa1c">m_TransposeY</a> ? &m_PermutedTensorY : &inputY,</div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  <span class="keyword">nullptr</span>,</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  &output,</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span>  1.0,</div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  0,</div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  gemm_info);</div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  m_GEMMLayer.reset(gemmLayer.release());</div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span> }</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> </div><div class="line"><a name="l00207"></a><span class="lineno"><a class="line" href="classarmnn_1_1_cl_batch_mat_mul_workload.xhtml#ae071e8822437c78baea75c3aef3a263a"> 207</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_cl_batch_mat_mul_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">ClBatchMatMulWorkload::Execute</a>()<span class="keyword"> const</span></div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> <span class="keyword"></span>{</div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  <a class="code" href="_cl_workload_utils_8hpp.xhtml#ae96fe8349d05e83e891129d63d8e2263">ARMNN_SCOPED_PROFILING_EVENT_CL_GUID</a>(<span class="stringliteral">"ClBatchMatMulWorkload_Execute"</span>, this-><a class="code" href="classarmnn_1_1_base_workload.xhtml#aaff95a48875d8fb4a616352906660ca9">GetGuid</a>());</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  <span class="keywordflow">if</span> (m_PermuteLayerX)</div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  {</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  m_PermuteLayerX->run();</div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  }</div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  <span class="keywordflow">if</span> (m_PermuteLayerY)</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>  m_PermuteLayerY->run();</div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  }</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  m_GEMMLayer->run();</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">//namespace armnn</span></div><div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml_ad945fc98770356dd886a68e98a52e26b"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#ad945fc98770356dd886a68e98a52e26b">armnn::BatchMatMulDescriptor::m_AdjointY</a></div><div class="ttdeci">bool m_AdjointY</div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01565">Descriptors.hpp:1565</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml_aaf7828880989b4b9378d3e86aa6dc843"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aaf7828880989b4b9378d3e86aa6dc843">armnn::BatchMatMulDescriptor::m_DataLayoutY</a></div><div class="ttdeci">DataLayout m_DataLayoutY</div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01569">Descriptors.hpp:1569</a></div></div> +<div class="ttc" id="_cl_workload_utils_8hpp_xhtml_ae96fe8349d05e83e891129d63d8e2263"><div class="ttname"><a href="_cl_workload_utils_8hpp.xhtml#ae96fe8349d05e83e891129d63d8e2263">ARMNN_SCOPED_PROFILING_EVENT_CL_GUID</a></div><div class="ttdeci">#define ARMNN_SCOPED_PROFILING_EVENT_CL_GUID(name, guid)</div><div class="ttdef"><b>Definition:</b> <a href="_cl_workload_utils_8hpp_source.xhtml#l00028">ClWorkloadUtils.hpp:28</a></div></div> +<div class="ttc" id="_arm_compute_utils_8hpp_xhtml"><div class="ttname"><a href="_arm_compute_utils_8hpp.xhtml">ArmComputeUtils.hpp</a></div></div> +<div class="ttc" id="namespacearmnn_xhtml_a15e2ba06d2ecd7ff6013118838e5d1be"><div class="ttname"><a href="namespacearmnn.xhtml#a15e2ba06d2ecd7ff6013118838e5d1be">armnn::GeneratePermutationVectorOnLastTwoDimensions</a></div><div class="ttdeci">armnn::PermutationVector GeneratePermutationVectorOnLastTwoDimensions(unsigned int rank)</div><div class="ttdoc">Generates a permutation vector of size rank that permutes the 2 most right dimensions. </div><div class="ttdef"><b>Definition:</b> <a href="_workload_utils_8cpp_source.xhtml#l00344">WorkloadUtils.cpp:344</a></div></div> +<div class="ttc" id="classarmnn_1_1_tensor_info_xhtml"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a></div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00152">Tensor.hpp:152</a></div></div> +<div class="ttc" id="namespacearmnn_utils_xhtml_a2bff2aae3ae824ff74ba550488373886"><div class="ttname"><a href="namespacearmnn_utils.xhtml#a2bff2aae3ae824ff74ba550488373886">armnnUtils::ReduceDims</a></div><div class="ttdeci">armnn::TensorShape ReduceDims(const armnn::TensorShape &tensorInfo, unsigned int dimensions)</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_utils_8cpp_source.xhtml#l00106">TensorUtils.cpp:106</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml_acb441bb8db19bcce78d15cdd8ceb5ea0"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#acb441bb8db19bcce78d15cdd8ceb5ea0">armnn::BatchMatMulDescriptor::m_TransposeX</a></div><div class="ttdeci">bool m_TransposeX</div><div class="ttdoc">Transpose the slices of each input tensor Transpose and Adjoint can not both be set to true for the s...</div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01559">Descriptors.hpp:1559</a></div></div> +<div class="ttc" id="namespacearmnn_xhtml_a2a57e49fbc4e44cfa0300229627d04ff"><div class="ttname"><a href="namespacearmnn.xhtml#a2a57e49fbc4e44cfa0300229627d04ff">armnn::ClBatchMatMulValidate</a></div><div class="ttdeci">arm_compute::Status ClBatchMatMulValidate(const TensorInfo &inputX, const TensorInfo &inputY, const TensorInfo &output, const BatchMatMulDescriptor &descriptor)</div><div class="ttdef"><b>Definition:</b> <a href="_cl_batch_mat_mul_workload_8cpp_source.xhtml#l00029">ClBatchMatMulWorkload.cpp:29</a></div></div> +<div class="ttc" id="classarmnn_1_1_base_workload_xhtml_aaff95a48875d8fb4a616352906660ca9"><div class="ttname"><a href="classarmnn_1_1_base_workload.xhtml#aaff95a48875d8fb4a616352906660ca9">armnn::BaseWorkload< BatchMatMulQueueDescriptor >::GetGuid</a></div><div class="ttdeci">arm::pipe::ProfilingGuid GetGuid() const final</div><div class="ttdef"><b>Definition:</b> <a href="_workload_8hpp_source.xhtml#l00061">Workload.hpp:61</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml_a0cf8306be7d301de0f095fff9901a525"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a0cf8306be7d301de0f095fff9901a525">armnn::BatchMatMulDescriptor::m_AdjointX</a></div><div class="ttdeci">bool m_AdjointX</div><div class="ttdoc">Adjoint the slices of each input tensor Transpose and Adjoint can not both be set to true for the sam...</div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01564">Descriptors.hpp:1564</a></div></div> +<div class="ttc" id="_arm_compute_tensor_utils_8hpp_xhtml"><div class="ttname"><a href="_arm_compute_tensor_utils_8hpp.xhtml">ArmComputeTensorUtils.hpp</a></div></div> +<div class="ttc" id="structarmnn_1_1_queue_descriptor_xhtml_a765d2cee4ccce5b9467e0c2b6d25b84a"><div class="ttname"><a href="structarmnn_1_1_queue_descriptor.xhtml#a765d2cee4ccce5b9467e0c2b6d25b84a">armnn::QueueDescriptor::ValidateInputsOutputs</a></div><div class="ttdeci">void ValidateInputsOutputs(const std::string &descName, unsigned int numExpectedIn, unsigned int numExpectedOut) const</div><div class="ttdef"><b>Definition:</b> <a href="_workload_data_8cpp_source.xhtml#l00475">WorkloadData.cpp:475</a></div></div> +<div class="ttc" id="namespacearmnn_xhtml"><div class="ttname"><a href="namespacearmnn.xhtml">armnn</a></div><div class="ttdoc">Copyright (c) 2021 ARM Limited and Contributors. </div><div class="ttdef"><b>Definition:</b> <a href="01__00__quick__start_8dox_source.xhtml#l00006">01_00_quick_start.dox:6</a></div></div> +<div class="ttc" id="structarmnn_1_1_queue_descriptor_with_parameters_xhtml_aad91b9bbf7aa365d304febe79a3d1333"><div class="ttname"><a href="structarmnn_1_1_queue_descriptor_with_parameters.xhtml#aad91b9bbf7aa365d304febe79a3d1333">armnn::QueueDescriptorWithParameters::m_Parameters</a></div><div class="ttdeci">LayerDescriptor m_Parameters</div><div class="ttdef"><b>Definition:</b> <a href="_workload_data_8hpp_source.xhtml#l00066">WorkloadData.hpp:66</a></div></div> +<div class="ttc" id="_polymorphic_downcast_8hpp_xhtml"><div class="ttname"><a href="_polymorphic_downcast_8hpp.xhtml">PolymorphicDowncast.hpp</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml_aedca000a005e091c23191e82d7e81b1d"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#aedca000a005e091c23191e82d7e81b1d">armnn::BatchMatMulDescriptor::m_DataLayoutX</a></div><div class="ttdeci">DataLayout m_DataLayoutX</div><div class="ttdoc">Data layout of each input tensor, such as NHWC/NDHWC (leave as default for arbitrary layout) ...</div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01568">Descriptors.hpp:1568</a></div></div> +<div class="ttc" id="structarmnn_1_1_workload_info_xhtml_ac97905bfa0daab357b91df1347600309"><div class="ttname"><a href="structarmnn_1_1_workload_info.xhtml#ac97905bfa0daab357b91df1347600309">armnn::WorkloadInfo::m_InputTensorInfos</a></div><div class="ttdeci">std::vector< TensorInfo > m_InputTensorInfos</div><div class="ttdef"><b>Definition:</b> <a href="include_2armnn_2backends_2_workload_info_8hpp_source.xhtml#l00018">WorkloadInfo.hpp:18</a></div></div> +<div class="ttc" id="_permute_8hpp_xhtml"><div class="ttname"><a href="_permute_8hpp.xhtml">Permute.hpp</a></div></div> +<div class="ttc" id="classarmnn_1_1_base_workload_xhtml_afb8d2c8817c75de9d01a4c0e0d5c160b"><div class="ttname"><a href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">armnn::BaseWorkload< BatchMatMulQueueDescriptor >::m_Data</a></div><div class="ttdeci">BatchMatMulQueueDescriptor m_Data</div><div class="ttdef"><b>Definition:</b> <a href="_workload_8hpp_source.xhtml#l00083">Workload.hpp:83</a></div></div> +<div class="ttc" id="namespacearmnn_xhtml_a67a0db04d321a74b7e7fcfd3f1a3f70b"><div class="ttname"><a href="namespacearmnn.xhtml#a67a0db04d321a74b7e7fcfd3f1a3f70b">armnn::Status</a></div><div class="ttdeci">Status</div><div class="ttdoc">enumeration </div><div class="ttdef"><b>Definition:</b> <a href="_types_8hpp_source.xhtml#l00042">Types.hpp:42</a></div></div> +<div class="ttc" id="classarmnn_1_1_cl_base_workload_xhtml"><div class="ttname"><a href="classarmnn_1_1_cl_base_workload.xhtml">armnn::ClBaseWorkload</a></div><div class="ttdef"><b>Definition:</b> <a href="_cl_base_workload_8hpp_source.xhtml#l00013">ClBaseWorkload.hpp:13</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml_a112b466e5d2ab9d1887178adbe3afa1c"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml#a112b466e5d2ab9d1887178adbe3afa1c">armnn::BatchMatMulDescriptor::m_TransposeY</a></div><div class="ttdeci">bool m_TransposeY</div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01560">Descriptors.hpp:1560</a></div></div> +<div class="ttc" id="classarmnn_1_1_permutation_vector_xhtml"><div class="ttname"><a href="classarmnn_1_1_permutation_vector.xhtml">armnn::PermutationVector</a></div><div class="ttdef"><b>Definition:</b> <a href="_types_8hpp_source.xhtml#l00295">Types.hpp:295</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_descriptor_xhtml"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.xhtml">armnn::BatchMatMulDescriptor</a></div><div class="ttdoc">A BatchMatMulDescriptor for the BatchMatMul operator. </div><div class="ttdef"><b>Definition:</b> <a href="_descriptors_8hpp_source.xhtml#l01531">Descriptors.hpp:1531</a></div></div> +<div class="ttc" id="classarmnn_1_1_cl_batch_mat_mul_workload_xhtml_acfe62a711ddf54011cb8c34f878de2ac"><div class="ttname"><a href="classarmnn_1_1_cl_batch_mat_mul_workload.xhtml#acfe62a711ddf54011cb8c34f878de2ac">armnn::ClBatchMatMulWorkload::ClBatchMatMulWorkload</a></div><div class="ttdeci">ClBatchMatMulWorkload(const BatchMatMulQueueDescriptor &descriptor, const WorkloadInfo &info, const arm_compute::CLCompileContext &clCompileContext)</div><div class="ttdef"><b>Definition:</b> <a href="_cl_batch_mat_mul_workload_8cpp_source.xhtml#l00115">ClBatchMatMulWorkload.cpp:115</a></div></div> +<div class="ttc" id="_tensor_utils_8hpp_xhtml"><div class="ttname"><a href="_tensor_utils_8hpp.xhtml">TensorUtils.hpp</a></div></div> +<div class="ttc" id="_cl_tensor_handle_8hpp_xhtml"><div class="ttname"><a href="_cl_tensor_handle_8hpp.xhtml">ClTensorHandle.hpp</a></div></div> +<div class="ttc" id="structarmnn_1_1_queue_descriptor_xhtml_a6abd491bb99ffe88bd472c1ae5a1ed1a"><div class="ttname"><a href="structarmnn_1_1_queue_descriptor.xhtml#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.xhtml#l00027">WorkloadData.hpp:27</a></div></div> +<div class="ttc" id="classarmnn_1_1_exception_xhtml"><div class="ttname"><a href="classarmnn_1_1_exception.xhtml">armnn::Exception</a></div><div class="ttdoc">Base class for all ArmNN exceptions so that users can filter to just those. </div><div class="ttdef"><b>Definition:</b> <a href="_exceptions_8hpp_source.xhtml#l00046">Exceptions.hpp:46</a></div></div> +<div class="ttc" id="_profiling_8hpp_xhtml_a786492a3881a4c760ab1eec2149f4aba"><div class="ttname"><a href="_profiling_8hpp.xhtml#a786492a3881a4c760ab1eec2149f4aba">ARMNN_REPORT_PROFILING_WORKLOAD_DESC</a></div><div class="ttdeci">#define ARMNN_REPORT_PROFILING_WORKLOAD_DESC(name, desc, infos, guid)</div><div class="ttdef"><b>Definition:</b> <a href="_profiling_8hpp_source.xhtml#l00227">Profiling.hpp:227</a></div></div> +<div class="ttc" id="structarmnn_1_1_batch_mat_mul_queue_descriptor_xhtml"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_queue_descriptor.xhtml">armnn::BatchMatMulQueueDescriptor</a></div><div class="ttdef"><b>Definition:</b> <a href="_workload_data_8hpp_source.xhtml#l00743">WorkloadData.hpp:743</a></div></div> +<div class="ttc" id="_cl_batch_mat_mul_workload_8hpp_xhtml"><div class="ttname"><a href="_cl_batch_mat_mul_workload_8hpp.xhtml">ClBatchMatMulWorkload.hpp</a></div></div> +<div class="ttc" id="classarmnn_1_1_cl_batch_mat_mul_workload_xhtml_ae071e8822437c78baea75c3aef3a263a"><div class="ttname"><a href="classarmnn_1_1_cl_batch_mat_mul_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">armnn::ClBatchMatMulWorkload::Execute</a></div><div class="ttdeci">virtual void Execute() const override</div><div class="ttdef"><b>Definition:</b> <a href="_cl_batch_mat_mul_workload_8cpp_source.xhtml#l00207">ClBatchMatMulWorkload.cpp:207</a></div></div> +<div class="ttc" id="structarmnn_1_1_workload_info_xhtml"><div class="ttname"><a href="structarmnn_1_1_workload_info.xhtml">armnn::WorkloadInfo</a></div><div class="ttdoc">Contains information about TensorInfos of a layer. </div><div class="ttdef"><b>Definition:</b> <a href="include_2armnn_2backends_2_workload_info_8hpp_source.xhtml#l00016">WorkloadInfo.hpp:16</a></div></div> +<div class="ttc" id="structarmnn_1_1_queue_descriptor_xhtml_a4b50e46a6810018f3edecfb68b2a76b3"><div class="ttname"><a href="structarmnn_1_1_queue_descriptor.xhtml#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.xhtml#l00026">WorkloadData.hpp:26</a></div></div> +<div class="ttc" id="namespacearmnn_xhtml_ad1d5cce2d9e9a5d61c243e5c989112e0a6b99f356fe3b30a2a850b5ea897c289f"><div class="ttname"><a href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0a6b99f356fe3b30a2a850b5ea897c289f">armnn::DataLayout::NCHW</a></div></div> +<div class="ttc" id="_cl_workload_utils_8hpp_xhtml"><div class="ttname"><a href="_cl_workload_utils_8hpp.xhtml">ClWorkloadUtils.hpp</a></div></div> +<div class="ttc" id="classarmnn_1_1_tensor_info_xhtml_a157e27d41e9f6b21f0d3c025fa47dc24"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml#a157e27d41e9f6b21f0d3c025fa47dc24">armnn::TensorInfo::GetNumDimensions</a></div><div class="ttdeci">unsigned int GetNumDimensions() const</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00195">Tensor.hpp:195</a></div></div> +<div class="ttc" id="namespacearmnn_utils_xhtml_abeaf4f6785039866fd075f4569ba8e84"><div class="ttname"><a href="namespacearmnn_utils.xhtml#abeaf4f6785039866fd075f4569ba8e84">armnnUtils::Permuted</a></div><div class="ttdeci">armnn::TensorShape Permuted(const armnn::TensorShape &srcShape, const armnn::PermutationVector &mappings)</div><div class="ttdef"><b>Definition:</b> <a href="_permute_8cpp_source.xhtml#l00098">Permute.cpp:98</a></div></div> +<div class="ttc" id="_workload_utils_8hpp_xhtml"><div class="ttname"><a href="_workload_utils_8hpp.xhtml">WorkloadUtils.hpp</a></div></div> +</div><!-- fragment --></div><!-- contents --> +</div><!-- doc-content --> +<!-- start footer part --> +<div id="nav-path" class="navpath"><!-- id is needed for treeview function! --> + <ul> + <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.xhtml">src</a></li><li class="navelem"><a class="el" href="dir_0f3cdec46afbc61a1ded8e1687c9c9a0.xhtml">backends</a></li><li class="navelem"><a class="el" href="dir_1ad86c6d39ab715a831555571b9e98a5.xhtml">cl</a></li><li class="navelem"><a class="el" href="dir_2d9c087bc7f49a1d7a25fdc615d2f0c9.xhtml">workloads</a></li><li class="navelem"><a class="el" href="_cl_batch_mat_mul_workload_8cpp.xhtml">ClBatchMatMulWorkload.cpp</a></li> + <li class="footer">Generated on Fri Feb 24 2023 10:24:26 for ArmNN by + <a href="http://www.doxygen.org/index.html"> + <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.13 </li> + </ul> +</div> +</body> +</html> |