diff options
| author | David Monahan <david.monahan@arm.com> | 2023-03-22 16:48:58 +0000 |
|---|---|---|
| committer | David Monahan <david.monahan@arm.com> | 2023-03-22 16:48:58 +0000 |
| commit | ae050524109f1ce827962665436ef7430f2ac479 (patch) | |
| tree | a087fe0c77570971dd7979f2757426c24e91afc7 /23.02/_ref_gather_nd_workload_8cpp_source.xhtml | |
| parent | 8d2ca734165a068478df7cffa46185680b05cd20 (diff) | |
| download | armnn-ae050524109f1ce827962665436ef7430f2ac479.tar.gz | |
IVGCVSW-7255 Update Doxygen Documentation and publish on GitHub.
* Updating Doxygen documentation for 23.02 release.
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I545574ff7664b4595d2fe6a91a3c35d2ad55df82
Diffstat (limited to '23.02/_ref_gather_nd_workload_8cpp_source.xhtml')
| -rw-r--r-- | 23.02/_ref_gather_nd_workload_8cpp_source.xhtml | 167 |
1 files changed, 132 insertions, 35 deletions
diff --git a/23.02/_ref_gather_nd_workload_8cpp_source.xhtml b/23.02/_ref_gather_nd_workload_8cpp_source.xhtml index f35abf149c..566fb4655d 100644 --- a/23.02/_ref_gather_nd_workload_8cpp_source.xhtml +++ b/23.02/_ref_gather_nd_workload_8cpp_source.xhtml @@ -8,7 +8,7 @@ <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="generator" content="Doxygen 1.8.17"/> <meta name="robots" content="NOINDEX, NOFOLLOW" /> <meta name="viewport" content="width=device-width, initial-scale=1"/> <title>ArmNN: src/backends/reference/workloads/RefGatherNdWorkload.cpp Source File</title> @@ -19,9 +19,6 @@ <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> @@ -30,7 +27,8 @@ extensions: ["tex2jax.js"], jax: ["input/TeX","output/HTML-CSS"], }); -</script><script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script> +</script> +<script type="text/javascript" async="async" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script> <link href="doxygen.css" rel="stylesheet" type="text/css" /> <link href="stylesheet.css" rel="stylesheet" type="text/css"/> </head> @@ -51,18 +49,21 @@ </table> </div> <!-- end header part --> -<!-- Generated by Doxygen 1.8.13 --> +<!-- 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(); }); }); -</script> +/* @license-end */</script> <div id="main-nav"></div> </div><!-- top --> <div id="side-nav" class="ui-resizable side-nav-resizable"> @@ -76,7 +77,9 @@ $(function() { </div> </div> <script type="text/javascript"> -$(document).ready(function(){initNavTree('_ref_gather_nd_workload_8cpp_source.xhtml','');}); +/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ +$(document).ready(function(){initNavTree('_ref_gather_nd_workload_8cpp_source.xhtml',''); initResizable(); }); +/* @license-end */ </script> <div id="doc-content"> <!-- window showing the filter options --> @@ -98,40 +101,134 @@ $(document).ready(function(){initNavTree('_ref_gather_nd_workload_8cpp_source.xh <div class="title">RefGatherNdWorkload.cpp</div> </div> </div><!--header--> <div class="contents"> -<a href="_ref_gather_nd_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 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="_ref_gather_nd_workload_8hpp.xhtml">RefGatherNdWorkload.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="_gather_8hpp.xhtml">Gather.hpp</a>"</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="preprocessor">#include "<a class="code" href="_profiling_8hpp.xhtml">Profiling.hpp</a>"</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="preprocessor">#include "<a class="code" href="_ref_workload_utils_8hpp.xhtml">RefWorkloadUtils.hpp</a>"</span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="preprocessor">#include "<a class="code" href="_workload_utils_8hpp.xhtml">backendsCommon/WorkloadUtils.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="keyword">namespace </span><a class="code" href="namespacearmnn.xhtml">armnn</a></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> </div><div class="line"><a name="l00016"></a><span class="lineno"><a class="line" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a"> 16</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">RefGatherNdWorkload::Execute</a>()<span class="keyword"> const</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="keyword"></span>{</div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span>  <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">Execute</a>(<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>, <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>);</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> </div><div class="line"><a name="l00021"></a><span class="lineno"><a class="line" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae1c43d025fc90382d7aff7a500937e2c"> 21</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae1c43d025fc90382d7aff7a500937e2c">RefGatherNdWorkload::ExecuteAsync</a>(<a class="code" href="structarmnn_1_1experimental_1_1_execution_data.xhtml">ExecutionData</a>& executionData)</div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span> {</div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span>  <a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml">WorkingMemDescriptor</a>* workingMemDescriptor = <span class="keyword">static_cast<</span><a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml">WorkingMemDescriptor</a>*<span class="keyword">></span>(executionData.<a class="code" href="structarmnn_1_1experimental_1_1_execution_data.xhtml#ad2b382076f26f48cd44783cfca2e3642">m_Data</a>);</div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span>  <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">Execute</a>(workingMemDescriptor-><a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>, workingMemDescriptor-><a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>);</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> </div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">RefGatherNdWorkload::Execute</a>(std::vector<ITensorHandle*> inputs, std::vector<ITensorHandle*> outputs)<span class="keyword"> const</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="keyword"></span>{</div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span>  <a class="code" href="_profiling_8hpp.xhtml#a5ccc65e2c464ac05ce311fdae7ede03a">ARMNN_SCOPED_PROFILING_EVENT</a>(<a class="code" href="namespacearmnn.xhtml#ae2f04a162585c0a5222a537efd5456aea83c2c4e9b658ccafbcbe6309c5d84c64">Compute::CpuRef</a>, <span class="stringliteral">"RefGatherNdWorkload_Execute"</span>);</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>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& inputInfo0 = <a class="code" href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">GetTensorInfo</a>(inputs[0]);</div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& inputInfo1 = <a class="code" href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">GetTensorInfo</a>(inputs[1]);</div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& outputInfo = <a class="code" href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">GetTensorInfo</a>(outputs[0]);</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>  std::unique_ptr<Decoder<float>> params_decoderPtr = MakeDecoder<float>(inputInfo0, inputs[0]->Map());</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>  <span class="keyword">const</span> int32_t* indicesDataPtr = <span class="keyword">reinterpret_cast<</span>int32_t*<span class="keyword">></span>(inputs[1]->Map());</div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span>  std::vector<int32_t> indices(indicesDataPtr, indicesDataPtr + inputInfo1.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a8846406ac37fbd2204f0be16ee05d5b7">GetNumElements</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>  std::unique_ptr<Encoder<float>> output_encoderPtr = MakeEncoder<float>(outputInfo, outputs[0]->Map());</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>  std::map<std::string, unsigned int> keyIndices = <a class="code" href="namespacearmnn.xhtml#ac40d3e4035af5fbe68d9e126a8d6367c">CalculateGatherNdKeyIndices</a>(inputInfo0, inputInfo1);</div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="comment"></span></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="comment"> /// Calculate flattened indices: flattenedIndices = indices * flattenedCoefficients</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="comment"></span> <span class="comment">// Calculate the flattened coefficients to use in the multiplication</span></div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  <span class="comment">// to calculate the flattened indices needed by gather</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <a class="code" href="classarmnn_1_1_tensor_shape.xhtml">TensorShape</a> paramsShape = inputInfo0.GetShape();</div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  std::vector<unsigned int> flattenedCoeff(keyIndices[<span class="stringliteral">"ND"</span>], 1);</div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = 1; i < keyIndices[<span class="stringliteral">"ND"</span>]; ++i)</div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span>  {</div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span>  flattenedCoeff[i-1] = paramsShape[i];</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>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = keyIndices[<span class="stringliteral">"ND"</span>]-1; i > 0; --i)</div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  {</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span>  flattenedCoeff[i-1] *= flattenedCoeff[i];</div><div class="line"><a name="l00056"></a><span class="lineno"> 56</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>  <span class="comment">// Prepare the vector to store the output of the matrix multiplication,</span></div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <span class="comment">// which will represent the flattened indices needed by gather</span></div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> flattenedIndices_Info = inputInfo1;</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  flattenedIndices_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"W"</span>] });</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  std::vector<int32_t> flattenedIndices(flattenedIndices_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a8846406ac37fbd2204f0be16ee05d5b7">GetNumElements</a>(), 0);</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>  <span class="comment">// Multiplication to calculate the flattened indices, which are the indices needed by gather.</span></div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = 0; i < keyIndices[<span class="stringliteral">"W"</span>]; ++i)</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="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> j = 0; j < keyIndices[<span class="stringliteral">"ND"</span>]; ++j)</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>  flattenedIndices[i] += indices[i * keyIndices[<span class="stringliteral">"ND"</span>] + j] * <span class="keyword">static_cast<</span>int32_t<span class="keyword">></span>(flattenedCoeff[j]);</div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  }</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  }</div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment"></span></div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment"> /// Call Gather with adequate shapes</span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment"></span> <span class="comment">// Reshape params into {K, C}</span></div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> params_K_C_Info = inputInfo0;</div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  params_K_C_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"K"</span>], keyIndices[<span class="stringliteral">"C"</span>] });</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">// Reshape indices into {N, W}</span></div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> indices_N_W_Info = inputInfo1;</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  indices_N_W_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"N"</span>], keyIndices[<span class="stringliteral">"W"</span>] });</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>  <span class="comment">// Reshape output to have the shape given by gather {N, W, C}</span></div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <span class="comment">// (the original outputInfo has the shape given by gatherNd)</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> outputGather_Info = outputInfo;</div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  outputGather_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"N"</span>], keyIndices[<span class="stringliteral">"W"</span>], keyIndices[<span class="stringliteral">"C"</span>] });</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> </div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  <span class="comment">// output_gather = gather(params_K_C, indices_N_W)</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  <a class="code" href="namespacearmnn.xhtml#a56943a0946e5f15e5e58054b8e7a04a4aad22c799930d644e8468fe44c0312d53">Gather</a>(params_K_C_Info, indices_N_W_Info, outputGather_Info,</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  *params_decoderPtr, flattenedIndices.data(), *output_encoderPtr, 0);</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> </div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span> } <span class="comment">//namespace armnn</span></div><div class="ttc" id="namespacearmnn_xhtml_ae2f04a162585c0a5222a537efd5456aea83c2c4e9b658ccafbcbe6309c5d84c64"><div class="ttname"><a href="namespacearmnn.xhtml#ae2f04a162585c0a5222a537efd5456aea83c2c4e9b658ccafbcbe6309c5d84c64">armnn::Compute::CpuRef</a></div><div class="ttdoc">CPU Execution: Reference C++ kernels. </div></div> -<div class="ttc" id="namespacearmnn_xhtml_ac40d3e4035af5fbe68d9e126a8d6367c"><div class="ttname"><a href="namespacearmnn.xhtml#ac40d3e4035af5fbe68d9e126a8d6367c">armnn::CalculateGatherNdKeyIndices</a></div><div class="ttdeci">std::map< std::string, unsigned int > CalculateGatherNdKeyIndices(TensorInfo inputInfo0, TensorInfo inputInfo1)</div><div class="ttdoc">Calculates the key index values needed for GatherNd: N, ND, K, W, C (N is always 1) ...</div><div class="ttdef"><b>Definition:</b> <a href="_workload_utils_8cpp_source.xhtml#l00300">WorkloadUtils.cpp:300</a></div></div> -<div class="ttc" id="_ref_workload_utils_8hpp_xhtml"><div class="ttname"><a href="_ref_workload_utils_8hpp.xhtml">RefWorkloadUtils.hpp</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_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="classarmnn_1_1_tensor_shape_xhtml"><div class="ttname"><a href="classarmnn_1_1_tensor_shape.xhtml">armnn::TensorShape</a></div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00020">Tensor.hpp:20</a></div></div> -<div class="ttc" id="_profiling_8hpp_xhtml_a5ccc65e2c464ac05ce311fdae7ede03a"><div class="ttname"><a href="_profiling_8hpp.xhtml#a5ccc65e2c464ac05ce311fdae7ede03a">ARMNN_SCOPED_PROFILING_EVENT</a></div><div class="ttdeci">#define ARMNN_SCOPED_PROFILING_EVENT(backendId, name)</div><div class="ttdef"><b>Definition:</b> <a href="_profiling_8hpp_source.xhtml#l00220">Profiling.hpp:220</a></div></div> -<div class="ttc" id="classarmnn_1_1_tensor_info_xhtml_abe8889e8150beef5fd204b2d87b49298"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">armnn::TensorInfo::SetShape</a></div><div class="ttdeci">void SetShape(const TensorShape &newShape)</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00193">Tensor.hpp:193</a></div></div> -<div class="ttc" id="structarmnn_1_1experimental_1_1_working_mem_descriptor_xhtml"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml">armnn::experimental::WorkingMemDescriptor</a></div><div class="ttdef"><b>Definition:</b> <a href="_working_mem_descriptor_8hpp_source.xhtml#l00018">WorkingMemDescriptor.hpp:18</a></div></div> -<div class="ttc" id="structarmnn_1_1experimental_1_1_working_mem_descriptor_xhtml_a4b50e46a6810018f3edecfb68b2a76b3"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a4b50e46a6810018f3edecfb68b2a76b3">armnn::experimental::WorkingMemDescriptor::m_Inputs</a></div><div class="ttdeci">std::vector< ITensorHandle * > m_Inputs</div><div class="ttdef"><b>Definition:</b> <a href="_working_mem_descriptor_8hpp_source.xhtml#l00020">WorkingMemDescriptor.hpp:20</a></div></div> -<div class="ttc" id="classarmnn_1_1_ref_gather_nd_workload_xhtml_ae071e8822437c78baea75c3aef3a263a"><div class="ttname"><a href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">armnn::RefGatherNdWorkload::Execute</a></div><div class="ttdeci">void Execute() const override</div><div class="ttdef"><b>Definition:</b> <a href="_ref_gather_nd_workload_8cpp_source.xhtml#l00016">RefGatherNdWorkload.cpp:16</a></div></div> -<div class="ttc" id="structarmnn_1_1experimental_1_1_execution_data_xhtml_ad2b382076f26f48cd44783cfca2e3642"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_execution_data.xhtml#ad2b382076f26f48cd44783cfca2e3642">armnn::experimental::ExecutionData::m_Data</a></div><div class="ttdeci">void * m_Data</div><div class="ttdef"><b>Definition:</b> <a href="_execution_data_8hpp_source.xhtml#l00016">ExecutionData.hpp:16</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< GatherNdQueueDescriptor >::m_Data</a></div><div class="ttdeci">GatherNdQueueDescriptor 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_a56943a0946e5f15e5e58054b8e7a04a4aad22c799930d644e8468fe44c0312d53"><div class="ttname"><a href="namespacearmnn.xhtml#a56943a0946e5f15e5e58054b8e7a04a4aad22c799930d644e8468fe44c0312d53">armnn::LayerType::Gather</a></div></div> -<div class="ttc" id="_ref_gather_nd_workload_8hpp_xhtml"><div class="ttname"><a href="_ref_gather_nd_workload_8hpp.xhtml">RefGatherNdWorkload.hpp</a></div></div> -<div class="ttc" id="_gather_8hpp_xhtml"><div class="ttname"><a href="_gather_8hpp.xhtml">Gather.hpp</a></div></div> -<div class="ttc" id="structarmnn_1_1experimental_1_1_execution_data_xhtml"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_execution_data.xhtml">armnn::experimental::ExecutionData</a></div><div class="ttdef"><b>Definition:</b> <a href="_execution_data_8hpp_source.xhtml#l00014">ExecutionData.hpp:14</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="structarmnn_1_1experimental_1_1_working_mem_descriptor_xhtml_a6abd491bb99ffe88bd472c1ae5a1ed1a"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a6abd491bb99ffe88bd472c1ae5a1ed1a">armnn::experimental::WorkingMemDescriptor::m_Outputs</a></div><div class="ttdeci">std::vector< ITensorHandle * > m_Outputs</div><div class="ttdef"><b>Definition:</b> <a href="_working_mem_descriptor_8hpp_source.xhtml#l00021">WorkingMemDescriptor.hpp:21</a></div></div> -<div class="ttc" id="classarmnn_1_1_ref_gather_nd_workload_xhtml_ae1c43d025fc90382d7aff7a500937e2c"><div class="ttname"><a href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae1c43d025fc90382d7aff7a500937e2c">armnn::RefGatherNdWorkload::ExecuteAsync</a></div><div class="ttdeci">void ExecuteAsync(ExecutionData &executionData) override</div><div class="ttdef"><b>Definition:</b> <a href="_ref_gather_nd_workload_8cpp_source.xhtml#l00021">RefGatherNdWorkload.cpp:21</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="_profiling_8hpp_xhtml"><div class="ttname"><a href="_profiling_8hpp.xhtml">Profiling.hpp</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 class="ttc" id="classarmnn_1_1_tensor_info_xhtml_a8846406ac37fbd2204f0be16ee05d5b7"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml#a8846406ac37fbd2204f0be16ee05d5b7">armnn::TensorInfo::GetNumElements</a></div><div class="ttdeci">unsigned int GetNumElements() const</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00196">Tensor.hpp:196</a></div></div> -<div class="ttc" id="namespacearmnn_xhtml_aa815fde54f6d8e8aa5b4f0301cf4178b"><div class="ttname"><a href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">armnn::GetTensorInfo</a></div><div class="ttdeci">const TensorInfo & GetTensorInfo(const ITensorHandle *tensorHandle)</div><div class="ttdoc">float32 helpers </div><div class="ttdef"><b>Definition:</b> <a href="_ref_workload_utils_8hpp_source.xhtml#l00027">RefWorkloadUtils.hpp:27</a></div></div> +<a href="_ref_gather_nd_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 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="_ref_gather_nd_workload_8hpp.xhtml">RefGatherNdWorkload.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="_gather_8hpp.xhtml">Gather.hpp</a>"</span></div> +<div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="preprocessor">#include "<a class="code" href="_profiling_8hpp.xhtml">Profiling.hpp</a>"</span></div> +<div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="preprocessor">#include "<a class="code" href="_ref_workload_utils_8hpp.xhtml">RefWorkloadUtils.hpp</a>"</span></div> +<div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="preprocessor">#include "<a class="code" href="_workload_utils_8hpp.xhtml">backendsCommon/WorkloadUtils.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="keyword">namespace </span><a class="code" href="namespacearmnn.xhtml">armnn</a></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>  </div> +<div class="line"><a name="l00016"></a><span class="lineno"><a class="line" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a"> 16</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">RefGatherNdWorkload::Execute</a>()<span class="keyword"> const</span></div> +<div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="keyword"></span>{</div> +<div class="line"><a name="l00018"></a><span class="lineno"> 18</span>  <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">Execute</a>(<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>, <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>);</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>  </div> +<div class="line"><a name="l00021"></a><span class="lineno"><a class="line" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae1c43d025fc90382d7aff7a500937e2c"> 21</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae1c43d025fc90382d7aff7a500937e2c">RefGatherNdWorkload::ExecuteAsync</a>(<a class="code" href="structarmnn_1_1experimental_1_1_execution_data.xhtml">ExecutionData</a>& executionData)</div> +<div class="line"><a name="l00022"></a><span class="lineno"> 22</span> {</div> +<div class="line"><a name="l00023"></a><span class="lineno"> 23</span>  <a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml">WorkingMemDescriptor</a>* workingMemDescriptor = <span class="keyword">static_cast<</span><a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml">WorkingMemDescriptor</a>*<span class="keyword">></span>(executionData.<a class="code" href="structarmnn_1_1experimental_1_1_execution_data.xhtml#ad2b382076f26f48cd44783cfca2e3642">m_Data</a>);</div> +<div class="line"><a name="l00024"></a><span class="lineno"> 24</span>  <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">Execute</a>(workingMemDescriptor-><a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a4b50e46a6810018f3edecfb68b2a76b3">m_Inputs</a>, workingMemDescriptor-><a class="code" href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a6abd491bb99ffe88bd472c1ae5a1ed1a">m_Outputs</a>);</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>  </div> +<div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">RefGatherNdWorkload::Execute</a>(std::vector<ITensorHandle*> inputs, std::vector<ITensorHandle*> outputs)<span class="keyword"> const</span></div> +<div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="keyword"></span>{</div> +<div class="line"><a name="l00029"></a><span class="lineno"> 29</span>  <a class="code" href="_profiling_8hpp.xhtml#a5ccc65e2c464ac05ce311fdae7ede03a">ARMNN_SCOPED_PROFILING_EVENT</a>(<a class="code" href="namespacearmnn.xhtml#ae2f04a162585c0a5222a537efd5456aea83c2c4e9b658ccafbcbe6309c5d84c64">Compute::CpuRef</a>, <span class="stringliteral">"RefGatherNdWorkload_Execute"</span>);</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>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& inputInfo0 = <a class="code" href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">GetTensorInfo</a>(inputs[0]);</div> +<div class="line"><a name="l00032"></a><span class="lineno"> 32</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& inputInfo1 = <a class="code" href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">GetTensorInfo</a>(inputs[1]);</div> +<div class="line"><a name="l00033"></a><span class="lineno"> 33</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>& outputInfo = <a class="code" href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">GetTensorInfo</a>(outputs[0]);</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>  std::unique_ptr<Decoder<float>> params_decoderPtr = MakeDecoder<float>(inputInfo0, inputs[0]-><a class="code" href="namespacearmnn.xhtml#a56943a0946e5f15e5e58054b8e7a04a4a46f3ea056caa3126b91f3f70beea068c">Map</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>  <span class="keyword">const</span> int32_t* indicesDataPtr = <span class="keyword">reinterpret_cast<</span>int32_t*<span class="keyword">></span>(inputs[1]->Map());</div> +<div class="line"><a name="l00038"></a><span class="lineno"> 38</span>  std::vector<int32_t> indices(indicesDataPtr, indicesDataPtr + inputInfo1.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a8846406ac37fbd2204f0be16ee05d5b7">GetNumElements</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>  std::unique_ptr<Encoder<float>> output_encoderPtr = MakeEncoder<float>(outputInfo, outputs[0]-><a class="code" href="namespacearmnn.xhtml#a56943a0946e5f15e5e58054b8e7a04a4a46f3ea056caa3126b91f3f70beea068c">Map</a>());</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>  std::map<std::string, unsigned int> keyIndices = <a class="code" href="namespacearmnn.xhtml#ac40d3e4035af5fbe68d9e126a8d6367c">CalculateGatherNdKeyIndices</a>(inputInfo0, inputInfo1);</div> +<div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="comment"></span> </div> +<div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="comment"> /// Calculate flattened indices: flattenedIndices = indices * flattenedCoefficients</span></div> +<div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="comment"></span> <span class="comment">// Calculate the flattened coefficients to use in the multiplication</span></div> +<div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  <span class="comment">// to calculate the flattened indices needed by gather</span></div> +<div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <a class="code" href="classarmnn_1_1_tensor_shape.xhtml">TensorShape</a> paramsShape = inputInfo0.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a8b5d0f8a24e9d9238f412260a552acf8">GetShape</a>();</div> +<div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  std::vector<unsigned int> flattenedCoeff(keyIndices[<span class="stringliteral">"ND"</span>], 1);</div> +<div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = 1; i < keyIndices[<span class="stringliteral">"ND"</span>]; ++i)</div> +<div class="line"><a name="l00050"></a><span class="lineno"> 50</span>  {</div> +<div class="line"><a name="l00051"></a><span class="lineno"> 51</span>  flattenedCoeff[i-1] = paramsShape[i];</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>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = keyIndices[<span class="stringliteral">"ND"</span>]-1; i > 0; --i)</div> +<div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  {</div> +<div class="line"><a name="l00055"></a><span class="lineno"> 55</span>  flattenedCoeff[i-1] *= flattenedCoeff[i];</div> +<div class="line"><a name="l00056"></a><span class="lineno"> 56</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>  <span class="comment">// Prepare the vector to store the output of the matrix multiplication,</span></div> +<div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <span class="comment">// which will represent the flattened indices needed by gather</span></div> +<div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> flattenedIndices_Info = inputInfo1;</div> +<div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  flattenedIndices_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"W"</span>] });</div> +<div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  std::vector<int32_t> flattenedIndices(flattenedIndices_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#a8846406ac37fbd2204f0be16ee05d5b7">GetNumElements</a>(), 0);</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>  <span class="comment">// Multiplication to calculate the flattened indices, which are the indices needed by gather.</span></div> +<div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i = 0; i < keyIndices[<span class="stringliteral">"W"</span>]; ++i)</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="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> j = 0; j < keyIndices[<span class="stringliteral">"ND"</span>]; ++j)</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>  flattenedIndices[i] += indices[i * keyIndices[<span class="stringliteral">"ND"</span>] + j] * <span class="keyword">static_cast<</span>int32_t<span class="keyword">></span>(flattenedCoeff[j]);</div> +<div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  }</div> +<div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  }</div> +<div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment"></span> </div> +<div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment"> /// Call Gather with adequate shapes</span></div> +<div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment"></span> <span class="comment">// Reshape params into {K, C}</span></div> +<div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> params_K_C_Info = inputInfo0;</div> +<div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  params_K_C_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"K"</span>], keyIndices[<span class="stringliteral">"C"</span>] });</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">// Reshape indices into {N, W}</span></div> +<div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> indices_N_W_Info = inputInfo1;</div> +<div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  indices_N_W_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"N"</span>], keyIndices[<span class="stringliteral">"W"</span>] });</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>  <span class="comment">// Reshape output to have the shape given by gather {N, W, C}</span></div> +<div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <span class="comment">// (the original outputInfo has the shape given by gatherNd)</span></div> +<div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">armnn::TensorInfo</a> outputGather_Info = outputInfo;</div> +<div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  outputGather_Info.<a class="code" href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">SetShape</a>({ keyIndices[<span class="stringliteral">"N"</span>], keyIndices[<span class="stringliteral">"W"</span>], keyIndices[<span class="stringliteral">"C"</span>] });</div> +<div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  </div> +<div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  <span class="comment">// output_gather = gather(params_K_C, indices_N_W)</span></div> +<div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  <a class="code" href="namespacearmnn.xhtml#a4f1a1b88b01d8dfda3803776e0778a49">Gather</a>(params_K_C_Info, indices_N_W_Info, outputGather_Info,</div> +<div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  *params_decoderPtr, flattenedIndices.data(), *output_encoderPtr, 0);</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>  </div> +<div class="line"><a name="l00092"></a><span class="lineno"> 92</span> } <span class="comment">//namespace armnn</span></div> </div><!-- fragment --></div><!-- contents --> </div><!-- doc-content --> +<div class="ttc" id="anamespacearmnn_xhtml_aa815fde54f6d8e8aa5b4f0301cf4178b"><div class="ttname"><a href="namespacearmnn.xhtml#aa815fde54f6d8e8aa5b4f0301cf4178b">armnn::GetTensorInfo</a></div><div class="ttdeci">const TensorInfo & GetTensorInfo(const ITensorHandle *tensorHandle)</div><div class="ttdoc">float32 helpers</div><div class="ttdef"><b>Definition:</b> <a href="_ref_workload_utils_8hpp_source.xhtml#l00027">RefWorkloadUtils.hpp:27</a></div></div> +<div class="ttc" id="anamespacearmnn_xhtml_ac40d3e4035af5fbe68d9e126a8d6367c"><div class="ttname"><a href="namespacearmnn.xhtml#ac40d3e4035af5fbe68d9e126a8d6367c">armnn::CalculateGatherNdKeyIndices</a></div><div class="ttdeci">std::map< std::string, unsigned int > CalculateGatherNdKeyIndices(TensorInfo inputInfo0, TensorInfo inputInfo1)</div><div class="ttdoc">Calculates the key index values needed for GatherNd: N, ND, K, W, C (N is always 1)</div><div class="ttdef"><b>Definition:</b> <a href="_workload_utils_8cpp_source.xhtml#l00300">WorkloadUtils.cpp:300</a></div></div> +<div class="ttc" id="aclassarmnn_1_1_ref_gather_nd_workload_xhtml_ae1c43d025fc90382d7aff7a500937e2c"><div class="ttname"><a href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae1c43d025fc90382d7aff7a500937e2c">armnn::RefGatherNdWorkload::ExecuteAsync</a></div><div class="ttdeci">void ExecuteAsync(ExecutionData &executionData) override</div><div class="ttdef"><b>Definition:</b> <a href="_ref_gather_nd_workload_8cpp_source.xhtml#l00021">RefGatherNdWorkload.cpp:21</a></div></div> +<div class="ttc" id="anamespacearmnn_xhtml_a56943a0946e5f15e5e58054b8e7a04a4a46f3ea056caa3126b91f3f70beea068c"><div class="ttname"><a href="namespacearmnn.xhtml#a56943a0946e5f15e5e58054b8e7a04a4a46f3ea056caa3126b91f3f70beea068c">armnn::LayerType::Map</a></div><div class="ttdeci">@ Map</div></div> +<div class="ttc" id="astructarmnn_1_1experimental_1_1_working_mem_descriptor_xhtml_a4b50e46a6810018f3edecfb68b2a76b3"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a4b50e46a6810018f3edecfb68b2a76b3">armnn::experimental::WorkingMemDescriptor::m_Inputs</a></div><div class="ttdeci">std::vector< ITensorHandle * > m_Inputs</div><div class="ttdef"><b>Definition:</b> <a href="_working_mem_descriptor_8hpp_source.xhtml#l00020">WorkingMemDescriptor.hpp:20</a></div></div> +<div class="ttc" id="astructarmnn_1_1experimental_1_1_execution_data_xhtml"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_execution_data.xhtml">armnn::experimental::ExecutionData</a></div><div class="ttdef"><b>Definition:</b> <a href="_execution_data_8hpp_source.xhtml#l00014">ExecutionData.hpp:14</a></div></div> +<div class="ttc" id="astructarmnn_1_1experimental_1_1_execution_data_xhtml_ad2b382076f26f48cd44783cfca2e3642"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_execution_data.xhtml#ad2b382076f26f48cd44783cfca2e3642">armnn::experimental::ExecutionData::m_Data</a></div><div class="ttdeci">void * m_Data</div><div class="ttdef"><b>Definition:</b> <a href="_execution_data_8hpp_source.xhtml#l00016">ExecutionData.hpp:16</a></div></div> +<div class="ttc" id="astructarmnn_1_1experimental_1_1_working_mem_descriptor_xhtml"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml">armnn::experimental::WorkingMemDescriptor</a></div><div class="ttdef"><b>Definition:</b> <a href="_working_mem_descriptor_8hpp_source.xhtml#l00018">WorkingMemDescriptor.hpp:18</a></div></div> +<div class="ttc" id="aclassarmnn_1_1_base_workload_xhtml_afb8d2c8817c75de9d01a4c0e0d5c160b"><div class="ttname"><a href="classarmnn_1_1_base_workload.xhtml#afb8d2c8817c75de9d01a4c0e0d5c160b">armnn::BaseWorkload< GatherNdQueueDescriptor >::m_Data</a></div><div class="ttdeci">GatherNdQueueDescriptor 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="anamespacearmnn_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="aclassarmnn_1_1_tensor_shape_xhtml"><div class="ttname"><a href="classarmnn_1_1_tensor_shape.xhtml">armnn::TensorShape</a></div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00020">Tensor.hpp:20</a></div></div> +<div class="ttc" id="a_ref_workload_utils_8hpp_xhtml"><div class="ttname"><a href="_ref_workload_utils_8hpp.xhtml">RefWorkloadUtils.hpp</a></div></div> +<div class="ttc" id="a_profiling_8hpp_xhtml_a5ccc65e2c464ac05ce311fdae7ede03a"><div class="ttname"><a href="_profiling_8hpp.xhtml#a5ccc65e2c464ac05ce311fdae7ede03a">ARMNN_SCOPED_PROFILING_EVENT</a></div><div class="ttdeci">#define ARMNN_SCOPED_PROFILING_EVENT(backendId, name)</div><div class="ttdef"><b>Definition:</b> <a href="_profiling_8hpp_source.xhtml#l00220">Profiling.hpp:220</a></div></div> +<div class="ttc" id="aclassarmnn_1_1_tensor_info_xhtml_a8846406ac37fbd2204f0be16ee05d5b7"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml#a8846406ac37fbd2204f0be16ee05d5b7">armnn::TensorInfo::GetNumElements</a></div><div class="ttdeci">unsigned int GetNumElements() const</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00196">Tensor.hpp:196</a></div></div> +<div class="ttc" id="aclassarmnn_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="anamespacearmnn_xhtml_a4f1a1b88b01d8dfda3803776e0778a49"><div class="ttname"><a href="namespacearmnn.xhtml#a4f1a1b88b01d8dfda3803776e0778a49">armnn::Gather</a></div><div class="ttdeci">void Gather(const TensorInfo &paramsInfo, const TensorInfo &indicesInfo, const TensorInfo &outputInfo, Decoder< float > &params, const int32_t *indices, Encoder< float > &output, const int32_t axis_int)</div><div class="ttdef"><b>Definition:</b> <a href="_gather_8cpp_source.xhtml#l00014">Gather.cpp:14</a></div></div> +<div class="ttc" id="aclassarmnn_1_1_tensor_info_xhtml_a8b5d0f8a24e9d9238f412260a552acf8"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml#a8b5d0f8a24e9d9238f412260a552acf8">armnn::TensorInfo::GetShape</a></div><div class="ttdeci">const TensorShape & GetShape() const</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00191">Tensor.hpp:191</a></div></div> +<div class="ttc" id="aclassarmnn_1_1_ref_gather_nd_workload_xhtml_ae071e8822437c78baea75c3aef3a263a"><div class="ttname"><a href="classarmnn_1_1_ref_gather_nd_workload.xhtml#ae071e8822437c78baea75c3aef3a263a">armnn::RefGatherNdWorkload::Execute</a></div><div class="ttdeci">void Execute() const override</div><div class="ttdef"><b>Definition:</b> <a href="_ref_gather_nd_workload_8cpp_source.xhtml#l00016">RefGatherNdWorkload.cpp:16</a></div></div> +<div class="ttc" id="astructarmnn_1_1experimental_1_1_working_mem_descriptor_xhtml_a6abd491bb99ffe88bd472c1ae5a1ed1a"><div class="ttname"><a href="structarmnn_1_1experimental_1_1_working_mem_descriptor.xhtml#a6abd491bb99ffe88bd472c1ae5a1ed1a">armnn::experimental::WorkingMemDescriptor::m_Outputs</a></div><div class="ttdeci">std::vector< ITensorHandle * > m_Outputs</div><div class="ttdef"><b>Definition:</b> <a href="_working_mem_descriptor_8hpp_source.xhtml#l00021">WorkingMemDescriptor.hpp:21</a></div></div> +<div class="ttc" id="a_gather_8hpp_xhtml"><div class="ttname"><a href="_gather_8hpp.xhtml">Gather.hpp</a></div></div> +<div class="ttc" id="astructarmnn_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="aclassarmnn_1_1_tensor_info_xhtml_abe8889e8150beef5fd204b2d87b49298"><div class="ttname"><a href="classarmnn_1_1_tensor_info.xhtml#abe8889e8150beef5fd204b2d87b49298">armnn::TensorInfo::SetShape</a></div><div class="ttdeci">void SetShape(const TensorShape &newShape)</div><div class="ttdef"><b>Definition:</b> <a href="_tensor_8hpp_source.xhtml#l00193">Tensor.hpp:193</a></div></div> +<div class="ttc" id="a_workload_utils_8hpp_xhtml"><div class="ttname"><a href="_workload_utils_8hpp.xhtml">WorkloadUtils.hpp</a></div></div> +<div class="ttc" id="a_ref_gather_nd_workload_8hpp_xhtml"><div class="ttname"><a href="_ref_gather_nd_workload_8hpp.xhtml">RefGatherNdWorkload.hpp</a></div></div> +<div class="ttc" id="anamespacearmnn_xhtml_ae2f04a162585c0a5222a537efd5456aea83c2c4e9b658ccafbcbe6309c5d84c64"><div class="ttname"><a href="namespacearmnn.xhtml#ae2f04a162585c0a5222a537efd5456aea83c2c4e9b658ccafbcbe6309c5d84c64">armnn::Compute::CpuRef</a></div><div class="ttdeci">@ CpuRef</div><div class="ttdoc">CPU Execution: Reference C++ kernels.</div></div> +<div class="ttc" id="astructarmnn_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="a_profiling_8hpp_xhtml"><div class="ttname"><a href="_profiling_8hpp.xhtml">Profiling.hpp</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.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_efae4012d0e357ebeaba7d02491d70e5.xhtml">reference</a></li><li class="navelem"><a class="el" href="dir_d2f3b8e2e64df3181ebe92efcc0a3012.xhtml">workloads</a></li><li class="navelem"><a class="el" href="_ref_gather_nd_workload_8cpp.xhtml">RefGatherNdWorkload.cpp</a></li> - <li class="footer">Generated on Fri Feb 24 2023 10:24:27 for ArmNN by + <li class="footer">Generated on Wed Mar 22 2023 15:53:02 for ArmNN by <a href="http://www.doxygen.org/index.html"> - <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.13 </li> + <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.17 </li> </ul> </div> </body> |