98 lines
50 KiB
HTML
98 lines
50 KiB
HTML
<!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 1.8.14"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
|
<title>Cutlass: wmma_gemm_multiply_add.h 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="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 src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
|
|
<link href="doxygen.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;">
|
|
<td id="projectalign" style="padding-left: 0.5em;">
|
|
<div id="projectname">Cutlass
|
|
</div>
|
|
<div id="projectbrief">CUDA Templates for Linear Algebra Subroutines and Solvers</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
<!-- end header part -->
|
|
<!-- Generated by Doxygen 1.8.14 -->
|
|
<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>
|
|
<!-- 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 id="nav-path" class="navpath">
|
|
<ul>
|
|
<li class="navelem"><a class="el" href="dir_1417ee5ebebc309c36b7962f26a92c39.html">cutlass</a></li><li class="navelem"><a class="el" href="dir_18d6a367a3982a494d65599933fc67a3.html">gemm</a></li> </ul>
|
|
</div>
|
|
</div><!-- top -->
|
|
<div class="header">
|
|
<div class="headertitle">
|
|
<div class="title">wmma_gemm_multiply_add.h</div> </div>
|
|
</div><!--header-->
|
|
<div class="contents">
|
|
<a href="wmma__gemm__multiply__add_8h.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 (c) 2017-2018, NVIDIA CORPORATION. All rights reserved.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> *</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment"> * Redistribution and use in source and binary forms, with or without modification, are permitted</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> <span class="comment"> * provided that the following conditions are met:</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="comment"> * * Redistributions of source code must retain the above copyright notice, this list of</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span> <span class="comment"> * conditions and the following disclaimer.</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> <span class="comment"> * * Redistributions in binary form must reproduce the above copyright notice, this list of</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="comment"> * conditions and the following disclaimer in the documentation and/or other materials</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="comment"> * provided with the distribution.</span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="comment"> * * Neither the name of the NVIDIA CORPORATION nor the names of its contributors may be used</span></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span> <span class="comment"> * to endorse or promote products derived from this software without specific prior written</span></div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span> <span class="comment"> * permission.</span></div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span> <span class="comment"> *</span></div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="comment"> * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR</span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="comment"> * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="comment"> * FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE</span></div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span> <span class="comment"> * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,</span></div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span> <span class="comment"> * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;</span></div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span> <span class="comment"> * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,</span></div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span> <span class="comment"> * STRICT LIABILITY, OR TOR (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE</span></div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span> <span class="comment"> * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.</span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span> <span class="comment"> *</span></div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> <span class="comment"> **************************************************************************************************/</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#pragma once</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> </div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="preprocessor">#include "<a class="code" href="wmma__matrix_8h.html">cutlass/wmma_matrix.h</a>"</span></div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#ifdef CUTLASS_USE_WMMA_API</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="preprocessor">#include "<a class="code" href="fragment_8h.html">cutlass/fragment.h</a>"</span></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="keyword">namespace </span><a class="code" href="namespacecutlass.html">cutlass</a> {</div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span> <span class="keyword">namespace </span>gemm {</div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> </div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> </div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="keyword">template</span> <<a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2b">MatrixLayout::Kind</a> kLayoutA_,</div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span>  <span class="keyword">typename</span> ScalarA_,</div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2b">MatrixLayout::Kind</a> kLayoutB_,</div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span>  <span class="keyword">typename</span> ScalarB_,</div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2b">MatrixLayout::Kind</a> kLayoutC_,</div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span>  <span class="keyword">typename</span> ScalarC_,</div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span>  <span class="keyword">typename</span> WarpGemmShape_,</div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  <span class="keyword">typename</span> InstructionShape_></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="keyword">struct </span>WmmaGemmMultiplyAdd {</div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <span class="keyword">typedef</span> InstructionShape_ InstructionShape;</div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span>  <span class="keyword">typedef</span> Shape<1, InstructionShape_::kH, InstructionShape_::kW> ThreadsPerWarp;</div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  <span class="keyword">typedef</span> WarpGemmShape_ WarpGemmShape;</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span>  <span class="keyword">typedef</span> WarpGemmShape_ AccumulatorsPerWarp;</div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  <span class="keyword">typedef</span> ScalarA_ ScalarA;</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <span class="keyword">typedef</span> ScalarB_ ScalarB;</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <span class="keyword">typedef</span> ScalarC_ ScalarC;</div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  <span class="keyword">typedef</span> <span class="keyword">typename</span> <a class="code" href="structcutlass_1_1ShapeDiv.html#a108ded386ef6708afc6fe769a77a234b">ShapeDiv<AccumulatorsPerWarp, InstructionShape>::Shape</a> Iterations;</div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> </div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  <span class="keyword">typedef</span> WmmaMatrix<GemmOperand::kA, kLayoutA_, ScalarA, InstructionShape> ElementA;</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  <span class="keyword">typedef</span> Fragment<ElementA, Iterations::kW> FragmentA;</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span> </div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <span class="keyword">typedef</span> WmmaMatrix<GemmOperand::kB, kLayoutB_, ScalarB, InstructionShape> ElementB;</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  <span class="keyword">typedef</span> Fragment<ElementB, Iterations::kH> FragmentB;</div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> </div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  <span class="keyword">typedef</span> WmmaMatrix<GemmOperand::kC, kLayoutC_, ScalarC, InstructionShape> ElementC;</div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  <span class="keyword">typedef</span> Fragment<ElementC, Iterations::kH * Iterations::kW> Accumulators;</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span> </div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  CUTLASS_DEVICE WmmaGemmMultiplyAdd() {}</div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span> </div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  CUTLASS_DEVICE <span class="keywordtype">void</span> multiply_add(FragmentA <span class="keyword">const</span>& a,</div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  FragmentB <span class="keyword">const</span>& b,</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  Accumulators <span class="keyword">const</span>& c,</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  Accumulators& d) {</div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> j = 0; j < Iterations::kH; ++j) {</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < Iterations::kW; ++i) {</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  <span class="comment">// The input elements.</span></div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  ElementA <span class="keyword">const</span>& elt_a = a[i];</div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  ElementB <span class="keyword">const</span>& elt_b = b[j];</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  ElementC <span class="keyword">const</span>& elt_c = c[j * Iterations::kW + i];</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span> </div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  <span class="comment">// The output element.</span></div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  ElementC& elt_d = d[j * Iterations::kW + i];</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span> </div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  <span class="comment">// The wmma instruction.</span></div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  nvcuda::wmma::mma_sync(elt_d, elt_a, elt_b, elt_c);</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>  }</div><div class="line"><a name="l00102"></a><span class="lineno"> 102</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> </div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span> </div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span> <span class="preprocessor">#ifdef CUTLASS_USE_SUBBYTE_WMMA</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> <span class="keyword">template</span><<span class="keyword">typename</span> WarpGemmShape_></div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span> <span class="keyword">struct </span>WmmaGemmMultiplyAdd <MatrixLayout::<a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">kRowMajor</a>,</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  Vector<bin1_t, 32>,</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  Vector<bin1_t, 32>,</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  int,</div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span>  WarpGemmShape_,</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  Shape<128, 8, 8> >{</div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  <span class="keyword">typedef</span> Shape<128, 8, 8> InstructionShape;</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <span class="keyword">typedef</span> Shape<1, 4, 8> ThreadsPerWarp;</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  <span class="keyword">typedef</span> WarpGemmShape_ WarpGemmShape;</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span>  <span class="keyword">typedef</span> WarpGemmShape_ AccumulatorsPerWarp;</div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  <span class="keyword">typedef</span> Vector<bin1_t, 32> ScalarA;</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span>  <span class="keyword">typedef</span> Vector<bin1_t, 32> ScalarB;</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  <span class="keyword">typedef</span> <span class="keywordtype">int</span> ScalarC;</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  <span class="keyword">typedef</span> <span class="keyword">typename</span> <a class="code" href="structcutlass_1_1ShapeDiv.html#a108ded386ef6708afc6fe769a77a234b">ShapeDiv<AccumulatorsPerWarp, InstructionShape>::Shape</a> Iterations;</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span> </div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0cac2b9fe9e3679a059d1a6c946b2a2c31a">GemmOperand::kA</a>,</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">MatrixLayout::kRowMajor</a>,</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  Vector<bin1_t, 32>,</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  InstructionShape> ElementA;</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  <span class="keyword">typedef</span> Fragment<ElementA, Iterations::kW> FragmentA;</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span> </div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0caad0876342d150cef7da6ae149d5e99f9">GemmOperand::kB</a>,</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  Vector<bin1_t, 32>,</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  InstructionShape> ElementB;</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  <span class="keyword">typedef</span> Fragment<ElementB, Iterations::kH> FragmentB;</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0ca7598e104da2001a76ec344f1c1b9c6dc">GemmOperand::kC</a>,</div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  int,</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  InstructionShape> ElementC;</div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  <span class="keyword">typedef</span> Fragment<ElementC, Iterations::kH * Iterations::kW> Accumulators;</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span> </div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  CUTLASS_DEVICE WmmaGemmMultiplyAdd() {}</div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span> </div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  CUTLASS_DEVICE <span class="keywordtype">void</span> multiply_add(FragmentA <span class="keyword">const</span>& a,</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  FragmentB <span class="keyword">const</span>& b,</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  Accumulators <span class="keyword">const</span>& c,</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  Accumulators& d) {</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> j = 0; j < Iterations::kH; ++j) {</div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < Iterations::kW; ++i) {</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  <span class="comment">// The input elements.</span></div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span>  ElementA <span class="keyword">const</span>& elt_a = a[i];</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  ElementB <span class="keyword">const</span>& elt_b = b[j];</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  ElementC <span class="keyword">const</span>& elt_c = c[j * Iterations::kW + i];</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span> </div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  <span class="comment">// The output element.</span></div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  ElementC& elt_d = d[j * Iterations::kW + i];</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>  <span class="comment">// The wmma instruction.</span></div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  nvcuda::wmma::bmma_sync(elt_d,</div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  elt_a,</div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  elt_b,</div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  elt_c,</div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span>  nvcuda::wmma::experimental::bmmaBitOpXOR,</div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  nvcuda::wmma::experimental::bmmaAccumulateOpPOPC);</div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span>  }</div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span>  }</div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span>  }</div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span> };</div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00189"></a><span class="lineno"> 189</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="preprocessor">#ifdef CUTLASS_USE_SUBBYTE_WMMA</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span> <span class="keyword">template</span><<span class="keyword">typename</span> WarpGemmShape_></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span> <span class="keyword">struct </span>WmmaGemmMultiplyAdd <MatrixLayout::<a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">kRowMajor</a>,</div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  Vector<int4_t, 8>,</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span>  Vector<int4_t, 8>,</div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  int,</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span>  WarpGemmShape_,</div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  Shape<32, 8, 8> >{</div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  <span class="keyword">typedef</span> Shape<32, 8, 8> InstructionShape;</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span>  <span class="keyword">typedef</span> Shape<1, 4, 8> ThreadsPerWarp;</div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  <span class="keyword">typedef</span> WarpGemmShape_ WarpGemmShape;</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  <span class="keyword">typedef</span> WarpGemmShape_ AccumulatorsPerWarp;</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  <span class="keyword">typedef</span> Vector<int4_t, 8> ScalarA;</div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  <span class="keyword">typedef</span> Vector<int4_t, 8> ScalarB;</div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  <span class="keyword">typedef</span> <span class="keywordtype">int</span> ScalarC;</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  <span class="keyword">typedef</span> <span class="keyword">typename</span> <a class="code" href="structcutlass_1_1ShapeDiv.html#a108ded386ef6708afc6fe769a77a234b">ShapeDiv<AccumulatorsPerWarp, InstructionShape>::Shape</a> Iterations;</div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span> </div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0cac2b9fe9e3679a059d1a6c946b2a2c31a">GemmOperand::kA</a>,</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">MatrixLayout::kRowMajor</a>,</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  Vector<int4_t, 8>,</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  InstructionShape> ElementA;</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  <span class="keyword">typedef</span> Fragment<ElementA, Iterations::kW> FragmentA;</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span> </div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0caad0876342d150cef7da6ae149d5e99f9">GemmOperand::kB</a>,</div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  Vector<int4_t, 8>,</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  InstructionShape> ElementB;</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="keyword">typedef</span> Fragment<ElementB, Iterations::kH> FragmentB;</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span> </div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0ca7598e104da2001a76ec344f1c1b9c6dc">GemmOperand::kC</a>,</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  int,</div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  InstructionShape> ElementC;</div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  <span class="keyword">typedef</span> Fragment<ElementC, Iterations::kH * Iterations::kW> Accumulators;</div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span> </div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  CUTLASS_DEVICE WmmaGemmMultiplyAdd() {}</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span> </div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  CUTLASS_DEVICE <span class="keywordtype">void</span> multiply_add(FragmentA <span class="keyword">const</span>& a,</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  FragmentB <span class="keyword">const</span>& b,</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  Accumulators <span class="keyword">const</span>& c,</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  Accumulators& d) {</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> j = 0; j < Iterations::kH; ++j) {</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < Iterations::kW; ++i) {</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  <span class="comment">// The input elements.</span></div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  ElementA <span class="keyword">const</span>& elt_a = a[i];</div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span>  ElementB <span class="keyword">const</span>& elt_b = b[j];</div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  ElementC <span class="keyword">const</span>& elt_c = c[j * Iterations::kW + i];</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span> </div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  <span class="comment">// The output element.</span></div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  ElementC& elt_d = d[j * Iterations::kW + i];</div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span> </div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  <span class="comment">// The wmma instruction.</span></div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  nvcuda::wmma::mma_sync(elt_d, elt_a, elt_b, elt_c);</div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  }</div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  }</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  }</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span> };</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span> </div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span> </div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span> <span class="preprocessor">#ifdef CUTLASS_USE_SUBBYTE_WMMA</span></div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span> <span class="keyword">template</span><<span class="keyword">typename</span> WarpGemmShape_></div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span> <span class="keyword">struct </span>WmmaGemmMultiplyAdd <MatrixLayout::<a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">kRowMajor</a>,</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span>  Vector<uint4_t, 8>,</div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  Vector<uint4_t, 8>,</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  int,</div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span>  WarpGemmShape_,</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  Shape<32, 8, 8> >{</div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>  <span class="keyword">typedef</span> Shape<32, 8, 8> InstructionShape;</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span>  <span class="keyword">typedef</span> Shape<1, 4, 8> ThreadsPerWarp;</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>  <span class="keyword">typedef</span> WarpGemmShape_ WarpGemmShape;</div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span>  <span class="keyword">typedef</span> WarpGemmShape_ AccumulatorsPerWarp;</div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span>  <span class="keyword">typedef</span> Vector<uint4_t, 8> ScalarA;</div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span>  <span class="keyword">typedef</span> Vector<uint4_t, 8> ScalarB;</div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  <span class="keyword">typedef</span> <span class="keywordtype">int</span> ScalarC;</div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span>  <span class="keyword">typedef</span> <span class="keyword">typename</span> <a class="code" href="structcutlass_1_1ShapeDiv.html#a108ded386ef6708afc6fe769a77a234b">ShapeDiv<AccumulatorsPerWarp, InstructionShape>::Shape</a> Iterations;</div><div class="line"><a name="l00299"></a><span class="lineno"> 299</span> </div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0cac2b9fe9e3679a059d1a6c946b2a2c31a">GemmOperand::kA</a>,</div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">MatrixLayout::kRowMajor</a>,</div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span>  Vector<uint4_t, 8>,</div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span>  InstructionShape> ElementA;</div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span>  <span class="keyword">typedef</span> Fragment<ElementA, Iterations::kW> FragmentA;</div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span> </div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0caad0876342d150cef7da6ae149d5e99f9">GemmOperand::kB</a>,</div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span>  Vector<uint4_t, 8>,</div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span>  InstructionShape> ElementB;</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span>  <span class="keyword">typedef</span> Fragment<ElementB, Iterations::kH> FragmentB;</div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span> </div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span>  <span class="keyword">typedef</span> WmmaMatrix<<a class="code" href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0ca7598e104da2001a76ec344f1c1b9c6dc">GemmOperand::kC</a>,</div><div class="line"><a name="l00318"></a><span class="lineno"> 318</span>  <a class="code" href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">MatrixLayout::kColumnMajor</a>,</div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span>  int,</div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span>  InstructionShape> ElementC;</div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>  <span class="keyword">typedef</span> Fragment<ElementC, Iterations::kH * Iterations::kW> Accumulators;</div><div class="line"><a name="l00323"></a><span class="lineno"> 323</span> </div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span>  CUTLASS_DEVICE WmmaGemmMultiplyAdd() {}</div><div class="line"><a name="l00326"></a><span class="lineno"> 326</span> </div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span>  CUTLASS_DEVICE <span class="keywordtype">void</span> multiply_add(FragmentA <span class="keyword">const</span>& a,</div><div class="line"><a name="l00329"></a><span class="lineno"> 329</span>  FragmentB <span class="keyword">const</span>& b,</div><div class="line"><a name="l00330"></a><span class="lineno"> 330</span>  Accumulators <span class="keyword">const</span>& c,</div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span>  Accumulators& d) {</div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> j = 0; j < Iterations::kH; ++j) {</div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < Iterations::kW; ++i) {</div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span>  <span class="comment">// The input elements.</span></div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span>  ElementA <span class="keyword">const</span>& elt_a = a[i];</div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span>  ElementB <span class="keyword">const</span>& elt_b = b[j];</div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span>  ElementC <span class="keyword">const</span>& elt_c = c[j * Iterations::kW + i];</div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span> </div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span>  <span class="comment">// The output element.</span></div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span>  ElementC& elt_d = d[j * Iterations::kW + i];</div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span> </div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span>  <span class="comment">// The wmma instruction.</span></div><div class="line"><a name="l00343"></a><span class="lineno"> 343</span>  nvcuda::wmma::mma_sync(elt_d, elt_a, elt_b, elt_c);</div><div class="line"><a name="l00344"></a><span class="lineno"> 344</span>  }</div><div class="line"><a name="l00345"></a><span class="lineno"> 345</span>  }</div><div class="line"><a name="l00346"></a><span class="lineno"> 346</span>  }</div><div class="line"><a name="l00347"></a><span class="lineno"> 347</span> };</div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span> </div><div class="line"><a name="l00351"></a><span class="lineno"> 351</span> </div><div class="line"><a name="l00352"></a><span class="lineno"> 352</span> } <span class="comment">// namespace gemm</span></div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span> } <span class="comment">// namespace cutlass</span></div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span> </div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span> <span class="preprocessor">#endif // defined CUTLASS_USE_WMMA_API</span></div><div class="ttc" id="wmma__matrix_8h_html"><div class="ttname"><a href="wmma__matrix_8h.html">wmma_matrix.h</a></div><div class="ttdoc">Abstractions for loading and storing matrices using the CUDA WMMA API. </div></div>
|
|
<div class="ttc" id="namespacecutlass_html"><div class="ttname"><a href="namespacecutlass.html">cutlass</a></div><div class="ttdef"><b>Definition:</b> convert.h:33</div></div>
|
|
<div class="ttc" id="namespacecutlass_1_1MatrixLayout_html_a97ef07af21b122c1804245b0c7784d2b"><div class="ttname"><a href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2b">cutlass::MatrixLayout::Kind</a></div><div class="ttdeci">Kind</div><div class="ttdoc">Enumeration defining fundamental contiguous layouts. </div><div class="ttdef"><b>Definition:</b> matrix_traits.h:159</div></div>
|
|
<div class="ttc" id="structcutlass_1_1GemmOperand_html_ab209ea3de198efabe8e8707dfe8e0a0ca7598e104da2001a76ec344f1c1b9c6dc"><div class="ttname"><a href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0ca7598e104da2001a76ec344f1c1b9c6dc">cutlass::GemmOperand::kC</a></div><div class="ttdef"><b>Definition:</b> matrix_traits.h:357</div></div>
|
|
<div class="ttc" id="structcutlass_1_1ShapeDiv_html_a108ded386ef6708afc6fe769a77a234b"><div class="ttname"><a href="structcutlass_1_1ShapeDiv.html#a108ded386ef6708afc6fe769a77a234b">cutlass::ShapeDiv::Shape</a></div><div class="ttdeci">Shape< A_::kD/B_::kD, A_::kH/B_::kH, A_::kW/B_::kW, A_::kC/B_::kC > Shape</div><div class="ttdef"><b>Definition:</b> shape.h:126</div></div>
|
|
<div class="ttc" id="structcutlass_1_1GemmOperand_html_ab209ea3de198efabe8e8707dfe8e0a0caad0876342d150cef7da6ae149d5e99f9"><div class="ttname"><a href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0caad0876342d150cef7da6ae149d5e99f9">cutlass::GemmOperand::kB</a></div><div class="ttdef"><b>Definition:</b> matrix_traits.h:357</div></div>
|
|
<div class="ttc" id="namespacecutlass_1_1MatrixLayout_html_a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b"><div class="ttname"><a href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2bac15988acba79c11072d38b295f163a2b">cutlass::MatrixLayout::kColumnMajor</a></div><div class="ttdef"><b>Definition:</b> matrix_traits.h:159</div></div>
|
|
<div class="ttc" id="namespacecutlass_1_1MatrixLayout_html_a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb"><div class="ttname"><a href="namespacecutlass_1_1MatrixLayout.html#a97ef07af21b122c1804245b0c7784d2ba6a287c17f9f5bf53528ae68296beeedb">cutlass::MatrixLayout::kRowMajor</a></div><div class="ttdef"><b>Definition:</b> matrix_traits.h:159</div></div>
|
|
<div class="ttc" id="structcutlass_1_1GemmOperand_html_ab209ea3de198efabe8e8707dfe8e0a0cac2b9fe9e3679a059d1a6c946b2a2c31a"><div class="ttname"><a href="structcutlass_1_1GemmOperand.html#ab209ea3de198efabe8e8707dfe8e0a0cac2b9fe9e3679a059d1a6c946b2a2c31a">cutlass::GemmOperand::kA</a></div><div class="ttdef"><b>Definition:</b> matrix_traits.h:357</div></div>
|
|
<div class="ttc" id="fragment_8h_html"><div class="ttname"><a href="fragment_8h.html">fragment.h</a></div><div class="ttdoc">Defines Fragment, a statically-sized array for storing parts of matrices within a thread&#39;s registers...</div></div>
|
|
</div><!-- fragment --></div><!-- contents -->
|
|
<!-- start footer part -->
|
|
<hr class="footer"/><address class="footer"><small>
|
|
Generated on Fri Oct 26 2018 14:53:33 for Cutlass by  <a href="http://www.doxygen.org/index.html">
|
|
<img class="footer" src="doxygen.png" alt="doxygen"/>
|
|
</a> 1.8.14
|
|
</small></address>
|
|
</body>
|
|
</html>
|