| <!-- 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: src/backends/gpuFsa/layers/GpuFsaBatchMatMul.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> |
| <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">24.02</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('_gpu_fsa_batch_mat_mul_8cpp_source.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="headertitle"> |
| <div class="title">GpuFsaBatchMatMul.cpp</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <a href="_gpu_fsa_batch_mat_mul_8cpp.html">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 © 2024 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="_gpu_fsa_batch_mat_mul_8hpp.html">GpuFsaBatchMatMul.hpp</a>"</span></div> |
| <div class="line"><a name="l00007"></a><span class="lineno"> 7</span> <span class="preprocessor">#include "<a class="code" href="_utils_gpu_fsa_8hpp.html">UtilsGpuFsa.hpp</a>"</span></div> |
| <div class="line"><a name="l00008"></a><span class="lineno"> 8</span>  </div> |
| <div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="preprocessor">#include <<a class="code" href="_arm_compute_tensor_utils_8hpp.html">aclCommon/ArmComputeTensorUtils.hpp</a>></span></div> |
| <div class="line"><a name="l00010"></a><span class="lineno"> 10</span>  </div> |
| <div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="preprocessor">#include <arm_compute/dynamic_fusion/sketch/gpu/GpuWorkloadContext.h></span></div> |
| <div class="line"><a name="l00012"></a><span class="lineno"> 12</span> <span class="preprocessor">#include <arm_compute/dynamic_fusion/sketch/gpu/GpuWorkloadSketch.h></span></div> |
| <div class="line"><a name="l00013"></a><span class="lineno"> 13</span> <span class="preprocessor">#include <arm_compute/dynamic_fusion/sketch/gpu/operators/GpuMatMul.h></span></div> |
| <div class="line"><a name="l00014"></a><span class="lineno"> 14</span> <span class="preprocessor">#include <arm_compute/dynamic_fusion/sketch/gpu/operators/GpuOutput.h></span></div> |
| <div class="line"><a name="l00015"></a><span class="lineno"> 15</span>  </div> |
| <div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="keyword">using namespace </span>arm_compute::experimental::dynamic_fusion;</div> |
| <div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="keyword">using namespace </span>armnn::armcomputetensorutils;</div> |
| <div class="line"><a name="l00018"></a><span class="lineno"> 18</span>  </div> |
| <div class="line"><a name="l00019"></a><span class="lineno"> 19</span> <span class="keyword">namespace </span><a class="code" href="namespacearmnn.html">armnn</a></div> |
| <div class="line"><a name="l00020"></a><span class="lineno"> 20</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"><a class="line" href="namespacearmnn.html#a47e56eb9bcbb170dddd202d770ed2cd8"> 22</a></span> <a class="code" href="namespacearmnn.html#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a> <a class="code" href="namespacearmnn.html#a47e56eb9bcbb170dddd202d770ed2cd8">GpuFsaBatchMatMulValidate</a>(<span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.html">TensorInfo</a>& input0,</div> |
| <div class="line"><a name="l00023"></a><span class="lineno"> 23</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.html">TensorInfo</a>& input1,</div> |
| <div class="line"><a name="l00024"></a><span class="lineno"> 24</span>  <span class="keyword">const</span> <a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.html">BatchMatMulDescriptor</a>& descriptor)</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="comment">// Create a new workload sketch, for validation purposes</span></div> |
| <div class="line"><a name="l00027"></a><span class="lineno"> 27</span>  <span class="keyword">auto</span> compileCtx = arm_compute::CLKernelLibrary::get().get_compile_context();</div> |
| <div class="line"><a name="l00028"></a><span class="lineno"> 28</span>  <span class="keyword">auto</span> workloadContext = GpuWorkloadContext(&compileCtx);</div> |
| <div class="line"><a name="l00029"></a><span class="lineno"> 29</span>  GpuWorkloadSketch sketch{ &workloadContext };</div> |
| <div class="line"><a name="l00030"></a><span class="lineno"> 30</span>  </div> |
| <div class="line"><a name="l00031"></a><span class="lineno"> 31</span>  arm_compute::TensorInfo aclInput0Info = BuildArmComputeTensorInfo(input0, input0.<a class="code" href="classarmnn_1_1_tensor_info.html#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div> |
| <div class="line"><a name="l00032"></a><span class="lineno"> 32</span>  arm_compute::TensorInfo aclInput1Info = BuildArmComputeTensorInfo(input1, input1.<a class="code" href="classarmnn_1_1_tensor_info.html#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</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>  aclInput0Info.set_are_values_constant(input0.<a class="code" href="classarmnn_1_1_tensor_info.html#a945263e85c27f3216a8323cfc16d8919">IsConstant</a>());</div> |
| <div class="line"><a name="l00035"></a><span class="lineno"> 35</span>  aclInput1Info.set_are_values_constant(input1.<a class="code" href="classarmnn_1_1_tensor_info.html#a945263e85c27f3216a8323cfc16d8919">IsConstant</a>());</div> |
| <div class="line"><a name="l00036"></a><span class="lineno"> 36</span>  </div> |
| <div class="line"><a name="l00037"></a><span class="lineno"> 37</span>  arm_compute::ITensorInfo* inputInfo0 = workloadContext.create_tensor_info(aclInput0Info);</div> |
| <div class="line"><a name="l00038"></a><span class="lineno"> 38</span>  arm_compute::ITensorInfo* inputInfo1 = workloadContext.create_tensor_info(aclInput1Info);</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>  MatMulAttributes matMulAttributes{};</div> |
| <div class="line"><a name="l00041"></a><span class="lineno"> 41</span>  matMulAttributes.adj_lhs(descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.html#acb441bb8db19bcce78d15cdd8ceb5ea0">m_TransposeX</a>);</div> |
| <div class="line"><a name="l00042"></a><span class="lineno"> 42</span>  matMulAttributes.adj_rhs(descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.html#a112b466e5d2ab9d1887178adbe3afa1c">m_TransposeY</a>);</div> |
| <div class="line"><a name="l00043"></a><span class="lineno"> 43</span>  GpuMatMulSettings matmulSettings{};</div> |
| <div class="line"><a name="l00044"></a><span class="lineno"> 44</span>  matmulSettings.m0(1);</div> |
| <div class="line"><a name="l00045"></a><span class="lineno"> 45</span>  matmulSettings.n0(1);</div> |
| <div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  matmulSettings.k0(1);</div> |
| <div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  </div> |
| <div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  <span class="keywordflow">return</span> GpuMatMul::validate_op(sketch, inputInfo0, inputInfo1, matMulAttributes, matmulSettings);</div> |
| <div class="line"><a name="l00049"></a><span class="lineno"> 49</span> }</div> |
| <div class="line"><a name="l00050"></a><span class="lineno"> 50</span>  </div> |
| <div class="line"><a name="l00051"></a><span class="lineno"><a class="line" href="namespacearmnn.html#a1334119d4ee3de23f273ee91aa256cbd"> 51</a></span> <span class="keywordtype">void</span> <a class="code" href="namespacearmnn.html#a1334119d4ee3de23f273ee91aa256cbd">GpuFsaBatchMatMulCreateOp</a>(<a class="code" href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html">GpuFsaPreCompiledBlob</a>* blob,</div> |
| <div class="line"><a name="l00052"></a><span class="lineno"> 52</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.html">TensorInfo</a>& input0,</div> |
| <div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.html">TensorInfo</a>& input1,</div> |
| <div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  <span class="keyword">const</span> <a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.html">BatchMatMulDescriptor</a>& descriptor)</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>  GpuWorkloadSketch* sketch = blob-><a class="code" href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#a14f92a9f65e32c3da896e7b1d45abd02">sketch</a>.get();</div> |
| <div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  GpuWorkloadContext* workloadContext = blob-><a class="code" href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#a255c9012137b149ffb46d83c23f2df43">workloadContext</a>.get();</div> |
| <div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  std::vector<arm_compute::ITensorInfo*> inputTensorInfos = {};</div> |
| <div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  std::vector<arm_compute::ITensorInfo*> outputTensorInfos = {};</div> |
| <div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  </div> |
| <div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  arm_compute::TensorInfo aclInput0Info = BuildArmComputeTensorInfo(input0, input0.<a class="code" href="classarmnn_1_1_tensor_info.html#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div> |
| <div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  arm_compute::TensorInfo aclInput1Info = BuildArmComputeTensorInfo(input1, input1.<a class="code" href="classarmnn_1_1_tensor_info.html#a157e27d41e9f6b21f0d3c025fa47dc24">GetNumDimensions</a>());</div> |
| <div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  </div> |
| <div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  aclInput0Info.set_are_values_constant(input0.<a class="code" href="classarmnn_1_1_tensor_info.html#a945263e85c27f3216a8323cfc16d8919">IsConstant</a>());</div> |
| <div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  aclInput1Info.set_are_values_constant(input1.<a class="code" href="classarmnn_1_1_tensor_info.html#a945263e85c27f3216a8323cfc16d8919">IsConstant</a>());</div> |
| <div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  </div> |
| <div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  inputTensorInfos.emplace_back(workloadContext->create_tensor_info(aclInput0Info));</div> |
| <div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  inputTensorInfos.emplace_back(workloadContext->create_tensor_info(aclInput1Info));</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>  MatMulAttributes matMulAttributes{};</div> |
| <div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  matMulAttributes.adj_lhs(descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.html#acb441bb8db19bcce78d15cdd8ceb5ea0">m_TransposeX</a>);</div> |
| <div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  matMulAttributes.adj_rhs(descriptor.<a class="code" href="structarmnn_1_1_batch_mat_mul_descriptor.html#a112b466e5d2ab9d1887178adbe3afa1c">m_TransposeY</a>);</div> |
| <div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  GpuMatMulSettings matmulSettings{};</div> |
| <div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  matmulSettings.m0(1);</div> |
| <div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  matmulSettings.n0(1);</div> |
| <div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  matmulSettings.k0(1);</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="comment">// Validate operator, check status and update reasonIfUnsupported</span></div> |
| <div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <a class="code" href="namespacearmnn.html#a67a0db04d321a74b7e7fcfd3f1a3f70b">arm_compute::Status</a> aclStatus = GpuMatMul::validate_op(*sketch,</div> |
| <div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  inputTensorInfos[0],</div> |
| <div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  inputTensorInfos[1],</div> |
| <div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  matMulAttributes,</div> |
| <div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  matmulSettings);</div> |
| <div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  </div> |
| <div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  <span class="keyword">const</span> <span class="keywordtype">bool</span> supported = aclStatus.error_code() == arm_compute::ErrorCode::OK;</div> |
| <div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  <span class="keywordflow">if</span> (!supported)</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>  <span class="keywordflow">throw</span> <a class="code" href="classarmnn_1_1_backend_capability_exception.html">BackendCapabilityException</a>(<span class="stringliteral">"\"GpuFsa\" backend failed during elementwise binary add validation"</span>);</div> |
| <div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  }</div> |
| <div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  </div> |
| <div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  arm_compute::ITensorInfo* addOutputInfo = GpuMatMul::create_op(*sketch,</div> |
| <div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  inputTensorInfos[0],</div> |
| <div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  inputTensorInfos[1],</div> |
| <div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  matMulAttributes,</div> |
| <div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  matmulSettings);</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="comment">// Temporary fix until fusing attempt is make for GpuFsa backend and Output layer workload is created.</span></div> |
| <div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  outputTensorInfos.emplace_back(workloadContext->create_tensor_info());</div> |
| <div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  GpuOutput::create_op(*sketch, addOutputInfo, outputTensorInfos[0]);</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="comment">// Store the TensorInfos within the blob as unique_ptrs to be used later</span></div> |
| <div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  blob-><a class="code" href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#a479b90f0b24c427502d94b716117e034">inputTensorInfos</a> = std::make_unique<std::vector<arm_compute::ITensorInfo*>>(inputTensorInfos);</div> |
| <div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  blob-><a class="code" href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#ac49bf679a23aa84f06a6bde3440a4c40">outputTensorInfos</a> = std::make_unique<std::vector<arm_compute::ITensorInfo*>>(outputTensorInfos);</div> |
| <div class="line"><a name="l00104"></a><span class="lineno"> 104</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="comment">// namespace armnn</span></div> |
| </div><!-- fragment --></div><!-- contents --> |
| </div><!-- doc-content --> |
| <div class="ttc" id="astructarmnn_1_1_batch_mat_mul_descriptor_html_acb441bb8db19bcce78d15cdd8ceb5ea0"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.html#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.html#l01612">Descriptors.hpp:1612</a></div></div> |
| <div class="ttc" id="anamespacearmnn_html_a1334119d4ee3de23f273ee91aa256cbd"><div class="ttname"><a href="namespacearmnn.html#a1334119d4ee3de23f273ee91aa256cbd">armnn::GpuFsaBatchMatMulCreateOp</a></div><div class="ttdeci">void GpuFsaBatchMatMulCreateOp(GpuFsaPreCompiledBlob *blob, const TensorInfo &input0, const TensorInfo &input1, const BatchMatMulDescriptor &descriptor)</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_batch_mat_mul_8cpp_source.html#l00051">GpuFsaBatchMatMul.cpp:51</a></div></div> |
| <div class="ttc" id="aclassarmnn_1_1_tensor_info_html"><div class="ttname"><a href="classarmnn_1_1_tensor_info.html">armnn::TensorInfo</a></div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.html#l00152">Tensor.hpp:152</a></div></div> |
| <div class="ttc" id="aclassarmnn_1_1_tensor_info_html_a157e27d41e9f6b21f0d3c025fa47dc24"><div class="ttname"><a href="classarmnn_1_1_tensor_info.html#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.html#l00197">Tensor.hpp:197</a></div></div> |
| <div class="ttc" id="aclassarmnn_1_1_tensor_info_html_a945263e85c27f3216a8323cfc16d8919"><div class="ttname"><a href="classarmnn_1_1_tensor_info.html#a945263e85c27f3216a8323cfc16d8919">armnn::TensorInfo::IsConstant</a></div><div class="ttdeci">bool IsConstant() const</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8cpp_source.html#l00509">Tensor.cpp:509</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_gpu_fsa_pre_compiled_blob_html_a479b90f0b24c427502d94b716117e034"><div class="ttname"><a href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#a479b90f0b24c427502d94b716117e034">armnn::GpuFsaPreCompiledBlob::inputTensorInfos</a></div><div class="ttdeci">std::unique_ptr< std::vector< arm_compute::ITensorInfo * > > inputTensorInfos</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_backend_8hpp_source.html#l00037">GpuFsaBackend.hpp:37</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_batch_mat_mul_descriptor_html_a112b466e5d2ab9d1887178adbe3afa1c"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.html#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.html#l01613">Descriptors.hpp:1613</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_gpu_fsa_pre_compiled_blob_html_a14f92a9f65e32c3da896e7b1d45abd02"><div class="ttname"><a href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#a14f92a9f65e32c3da896e7b1d45abd02">armnn::GpuFsaPreCompiledBlob::sketch</a></div><div class="ttdeci">std::unique_ptr< arm_compute::experimental::dynamic_fusion::GpuWorkloadSketch > sketch</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_backend_8hpp_source.html#l00034">GpuFsaBackend.hpp:34</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_batch_mat_mul_descriptor_html"><div class="ttname"><a href="structarmnn_1_1_batch_mat_mul_descriptor.html">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.html#l01584">Descriptors.hpp:1584</a></div></div> |
| <div class="ttc" id="anamespacearmnn_html_a67a0db04d321a74b7e7fcfd3f1a3f70b"><div class="ttname"><a href="namespacearmnn.html#a67a0db04d321a74b7e7fcfd3f1a3f70b">armnn::Status</a></div><div class="ttdeci">Status</div><div class="ttdef"><b>Definition:</b> <a href="_types_8hpp_source.html#l00042">Types.hpp:42</a></div></div> |
| <div class="ttc" id="aclassarmnn_1_1_backend_capability_exception_html"><div class="ttname"><a href="classarmnn_1_1_backend_capability_exception.html">armnn::BackendCapabilityException</a></div><div class="ttdef"><b>Definition:</b> <a href="_exceptions_8hpp_source.html#l00152">Exceptions.hpp:152</a></div></div> |
| <div class="ttc" id="anamespacearmnn_html"><div class="ttname"><a href="namespacearmnn.html">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.html#l00006">01_00_quick_start.dox:6</a></div></div> |
| <div class="ttc" id="a_arm_compute_tensor_utils_8hpp_html"><div class="ttname"><a href="_arm_compute_tensor_utils_8hpp.html">ArmComputeTensorUtils.hpp</a></div></div> |
| <div class="ttc" id="a_gpu_fsa_batch_mat_mul_8hpp_html"><div class="ttname"><a href="_gpu_fsa_batch_mat_mul_8hpp.html">GpuFsaBatchMatMul.hpp</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_gpu_fsa_pre_compiled_blob_html_a255c9012137b149ffb46d83c23f2df43"><div class="ttname"><a href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#a255c9012137b149ffb46d83c23f2df43">armnn::GpuFsaPreCompiledBlob::workloadContext</a></div><div class="ttdeci">std::shared_ptr< arm_compute::experimental::dynamic_fusion::GpuWorkloadContext > workloadContext</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_backend_8hpp_source.html#l00035">GpuFsaBackend.hpp:35</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_gpu_fsa_pre_compiled_blob_html"><div class="ttname"><a href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html">armnn::GpuFsaPreCompiledBlob</a></div><div class="ttdoc">A structure which contains all the elements needed to execute a fused workload in the GpuFsa Backend.</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_backend_8hpp_source.html#l00032">GpuFsaBackend.hpp:32</a></div></div> |
| <div class="ttc" id="a_utils_gpu_fsa_8hpp_html"><div class="ttname"><a href="_utils_gpu_fsa_8hpp.html">UtilsGpuFsa.hpp</a></div></div> |
| <div class="ttc" id="astructarmnn_1_1_gpu_fsa_pre_compiled_blob_html_ac49bf679a23aa84f06a6bde3440a4c40"><div class="ttname"><a href="structarmnn_1_1_gpu_fsa_pre_compiled_blob.html#ac49bf679a23aa84f06a6bde3440a4c40">armnn::GpuFsaPreCompiledBlob::outputTensorInfos</a></div><div class="ttdeci">std::unique_ptr< std::vector< arm_compute::ITensorInfo * > > outputTensorInfos</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_backend_8hpp_source.html#l00038">GpuFsaBackend.hpp:38</a></div></div> |
| <div class="ttc" id="anamespacearmnn_html_a47e56eb9bcbb170dddd202d770ed2cd8"><div class="ttname"><a href="namespacearmnn.html#a47e56eb9bcbb170dddd202d770ed2cd8">armnn::GpuFsaBatchMatMulValidate</a></div><div class="ttdeci">arm_compute::Status GpuFsaBatchMatMulValidate(const TensorInfo &input0, const TensorInfo &input1, const BatchMatMulDescriptor &descriptor)</div><div class="ttdef"><b>Definition:</b> <a href="_gpu_fsa_batch_mat_mul_8cpp_source.html#l00022">GpuFsaBatchMatMul.cpp:22</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="dir_68267d1309a1af8e8297ef4c3efbcdba.html">src</a></li><li class="navelem"><a class="el" href="dir_0f3cdec46afbc61a1ded8e1687c9c9a0.html">backends</a></li><li class="navelem"><a class="el" href="dir_dd5880bc3520e42c5318e86a9fdc97f6.html">gpuFsa</a></li><li class="navelem"><a class="el" href="dir_6735d107a3ea44e973a098b746f1b3bd.html">layers</a></li><li class="navelem"><a class="el" href="_gpu_fsa_batch_mat_mul_8cpp.html">GpuFsaBatchMatMul.cpp</a></li> |
| <li class="footer">Generated on Wed Feb 14 2024 16:36:16 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> |