148 lines
67 KiB
HTML
148 lines
67 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 1.8.11"/>
|
|
<title>CUTLASS: mma_pipelined.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/javascript">
|
|
$(document).ready(function() { init_search(); });
|
|
</script>
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
extensions: ["tex2jax.js"],
|
|
jax: ["input/TeX","output/HTML-CSS"],
|
|
});
|
|
</script><script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
|
|
<link href="doxygen.css" rel="stylesheet" type="text/css" />
|
|
</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="projectlogo"><img alt="Logo" src="cutlass-logo-small.png"/></td>
|
|
<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 1.8.11 -->
|
|
<script type="text/javascript">
|
|
var searchBox = new SearchBox("searchBox", "search",false,'Search');
|
|
</script>
|
|
<div id="navrow1" class="tabs">
|
|
<ul class="tablist">
|
|
<li><a href="index.html"><span>Main Page</span></a></li>
|
|
<li><a href="modules.html"><span>Modules</span></a></li>
|
|
<li><a href="namespaces.html"><span>Namespaces</span></a></li>
|
|
<li><a href="annotated.html"><span>Classes</span></a></li>
|
|
<li class="current"><a href="files.html"><span>Files</span></a></li>
|
|
<li>
|
|
<div id="MSearchBox" class="MSearchBoxInactive">
|
|
<span class="left">
|
|
<img id="MSearchSelect" src="search/mag_sel.png"
|
|
onmouseover="return searchBox.OnSearchSelectShow()"
|
|
onmouseout="return searchBox.OnSearchSelectHide()"
|
|
alt=""/>
|
|
<input type="text" id="MSearchField" value="Search" accesskey="S"
|
|
onfocus="searchBox.OnSearchFieldFocus(true)"
|
|
onblur="searchBox.OnSearchFieldFocus(false)"
|
|
onkeyup="searchBox.OnSearchFieldChange(event)"/>
|
|
</span><span class="right">
|
|
<a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a>
|
|
</span>
|
|
</div>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
<div id="navrow2" class="tabs2">
|
|
<ul class="tablist">
|
|
<li><a href="files.html"><span>File List</span></a></li>
|
|
<li><a href="globals.html"><span>File Members</span></a></li>
|
|
</ul>
|
|
</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_d44c64559bbebec7f509842c48db8b23.html">include</a></li><li class="navelem"><a class="el" href="dir_6baf2bb612a2f0daa69af3101ede80a1.html">cutlass</a></li><li class="navelem"><a class="el" href="dir_9aa36bd9cfad59a1f88859a38871c977.html">gemm</a></li><li class="navelem"><a class="el" href="dir_ffb18c781d484e5d1c680f712f01a439.html">threadblock</a></li> </ul>
|
|
</div>
|
|
</div><!-- top -->
|
|
<div class="header">
|
|
<div class="headertitle">
|
|
<div class="title">mma_pipelined.h</div> </div>
|
|
</div><!--header-->
|
|
<div class="contents">
|
|
<a href="mma__pipelined_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) 2017-2019, 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="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#pragma once</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="preprocessor">#include "<a class="code" href="cutlass_8h.html">cutlass/cutlass.h</a>"</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="preprocessor">#include "<a class="code" href="array_8h.html">cutlass/array.h</a>"</span></div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="preprocessor">#include "<a class="code" href="aligned__buffer_8h.html">cutlass/aligned_buffer.h</a>"</span></div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span> <span class="preprocessor">#include "<a class="code" href="numeric__conversion_8h.html">cutlass/numeric_conversion.h</a>"</span></div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span> </div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="preprocessor">#include "<a class="code" href="numeric__types_8h.html">cutlass/numeric_types.h</a>"</span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="preprocessor">#include "<a class="code" href="matrix__shape_8h.html">cutlass/matrix_shape.h</a>"</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="preprocessor">#include "<a class="code" href="include_2cutlass_2gemm_2gemm_8h.html">cutlass/gemm/gemm.h</a>"</span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="preprocessor">#include "<a class="code" href="mma__base_8h.html">cutlass/gemm/threadblock/mma_base.h</a>"</span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> </div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> </div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="keyword">namespace </span><a class="code" href="namespacecutlass.html">cutlass</a> {</div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="keyword">namespace </span>gemm {</div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="keyword">namespace </span>threadblock {</div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> </div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> </div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="keyword">template</span> <</div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  <span class="keyword">typename</span> Shape_,</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span>  <span class="comment">// (concept: ReadableTileIterator | ForwardTileIterator | MaskedTileIterator)</span></div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span>  <span class="keyword">typename</span> IteratorA_,</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <span class="keyword">typename</span> SmemIteratorA_,</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <span class="comment">// (concept: ReadableTileIterator | ForwardTileIterator | MaskedTileIterator)</span></div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  <span class="keyword">typename</span> IteratorB_,</div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keyword">typename</span> SmemIteratorB_,</div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  <span class="keyword">typename</span> ElementC_,</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <span class="keyword">typename</span> LayoutC_,</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <span class="keyword">typename</span> Policy_,</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  <span class="keyword">typename</span> TransformA_ = NumericArrayConverter<</div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  <span class="keyword">typename</span> SmemIteratorA_::Element, </div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <span class="keyword">typename</span> IteratorA_::Element, </div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  IteratorA_::Fragment::kElements>,</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <span class="keyword">typename</span> TransformB_ = NumericArrayConverter<</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  <span class="keyword">typename</span> SmemIteratorB_::Element, </div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  <span class="keyword">typename</span> IteratorB_::Element, </div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  IteratorB_::Fragment::kElements>,</div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <span class="keyword">typename</span> Enable = <span class="keywordtype">bool</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span> ></div><div class="line"><a name="l00086"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html"> 86</a></span> <span class="keyword">class </span><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html">MmaPipelined</a> : <span class="keyword">public</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html">MmaBase</a><Shape_, Policy_, 2> {</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> <span class="keyword">public</span>:</div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span> </div><div class="line"><a name="l00090"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a1ca2ed2c51ec508a6b6bb4af5f969076"> 90</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html">Base</a> = <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html">MmaBase<Shape_, Policy_, 2></a>;</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> </div><div class="line"><a name="l00092"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#af42727c7f832320ae88178d163421dca"> 92</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#af42727c7f832320ae88178d163421dca">Shape</a> = Shape_; </div><div class="line"><a name="l00093"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a258197bea0d4894569c627c56a64203a"> 93</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a258197bea0d4894569c627c56a64203a">IteratorA</a> = IteratorA_; </div><div class="line"><a name="l00094"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3989c584460e66c75a3f37ef91ecf06d"> 94</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3989c584460e66c75a3f37ef91ecf06d">IteratorB</a> = IteratorB_; </div><div class="line"><a name="l00095"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a102ddf57c1f46f5ed411b9d953e3f802"> 95</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a102ddf57c1f46f5ed411b9d953e3f802">ElementC</a> = ElementC_; </div><div class="line"><a name="l00096"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3bfd1d89c66d37d5a81d36262ad333d7"> 96</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3bfd1d89c66d37d5a81d36262ad333d7">LayoutC</a> = LayoutC_; </div><div class="line"><a name="l00097"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a09e5e5bfa35c1398346c452eb3deeb97"> 97</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a09e5e5bfa35c1398346c452eb3deeb97">Policy</a> = Policy_; </div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> </div><div class="line"><a name="l00099"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aba5cccb236e9a9368a9ae1e1df869e57"> 99</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aba5cccb236e9a9368a9ae1e1df869e57">SmemIteratorA</a> = SmemIteratorA_;</div><div class="line"><a name="l00100"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a0bbed549aeb0185a8486faa5fde22dd0"> 100</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a0bbed549aeb0185a8486faa5fde22dd0">SmemIteratorB</a> = SmemIteratorB_;</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span> </div><div class="line"><a name="l00102"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abbab0f268458143773b2654f48b54c1c"> 102</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abbab0f268458143773b2654f48b54c1c">TransformA</a> = TransformA_;</div><div class="line"><a name="l00103"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a66d61ceb64d44f645a7ef8223ddac50d"> 103</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a66d61ceb64d44f645a7ef8223ddac50d">TransformB</a> = TransformB_;</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span> </div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  <span class="comment">//</span></div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  <span class="comment">// Dependent types</span></div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  <span class="comment">//</span></div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> </div><div class="line"><a name="l00110"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8ab2e07ec7f4cf23ef158974fe3b8dbb"> 110</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8ab2e07ec7f4cf23ef158974fe3b8dbb">FragmentA</a> = <span class="keyword">typename</span> IteratorA::Fragment;</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span> </div><div class="line"><a name="l00113"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8a6b28dec3f9687f46180d59ac9187fb"> 113</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8a6b28dec3f9687f46180d59ac9187fb">FragmentB</a> = <span class="keyword">typename</span> IteratorB::Fragment;</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span> </div><div class="line"><a name="l00116"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2993390a8feebe3cf4bfb77a23c5ef33"> 116</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2993390a8feebe3cf4bfb77a23c5ef33">FragmentC</a> = <span class="keyword">typename</span> Policy::Operator::FragmentC;</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span> </div><div class="line"><a name="l00119"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abecfbe5eb8946865dc9bbf14a6fc8aff"> 119</a></span>  <span class="keyword">using</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abecfbe5eb8946865dc9bbf14a6fc8aff">Operator</a> = <span class="keyword">typename</span> Policy::Operator;</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span> </div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <span class="comment">// staticaly assert kStages for MmaPipelined is two (Double-buffered pipeline)</span></div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  <a class="code" href="platform_8h.html#adde4c9ea91b753491851361a4198c009">static_assert</a>((<a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#ad1267d78374c170d9addd137310d2d9a">Base::kStages</a>==2), <span class="stringliteral">"MmaPipelined requires kStages set to value 2"</span>);</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span> </div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span> <span class="keyword">private</span>:</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> </div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span>  <span class="keyword">using</span> WarpFragmentA = <span class="keyword">typename</span> Operator::FragmentA;</div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  <span class="keyword">using</span> WarpFragmentB = <span class="keyword">typename</span> Operator::FragmentB;</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span> </div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> <span class="keyword">protected</span>:</div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span> </div><div class="line"><a name="l00132"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a9d3cbfd5a2bbe4d105df9555ddbeeb2d"> 132</a></span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aba5cccb236e9a9368a9ae1e1df869e57">SmemIteratorA</a> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a9d3cbfd5a2bbe4d105df9555ddbeeb2d">smem_iterator_A_</a>;</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span> </div><div class="line"><a name="l00135"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aec92c64ede1c4233dac30d0b2ec9e394"> 135</a></span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a0bbed549aeb0185a8486faa5fde22dd0">SmemIteratorB</a> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aec92c64ede1c4233dac30d0b2ec9e394">smem_iterator_B_</a>;</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span> </div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span> <span class="keyword">public</span>:</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span> </div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  CUTLASS_DEVICE</div><div class="line"><a name="l00141"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#ac8dc63b0f3ced3d8f615b56678e26400"> 141</a></span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#ac8dc63b0f3ced3d8f615b56678e26400">MmaPipelined</a>(</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span>  <span class="keyword">typename</span> Base::SharedStorage &shared_storage, </div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  <span class="keywordtype">int</span> thread_idx, </div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <span class="keywordtype">int</span> warp_idx, </div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  <span class="keywordtype">int</span> lane_idx </div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  ):</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html">Base</a>(shared_storage, thread_idx, warp_idx, lane_idx),</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  smem_iterator_A_(shared_storage.operand_A_ref(), thread_idx),</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  smem_iterator_B_(shared_storage.operand_B_ref(), thread_idx) {</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  <span class="comment">// Compute warp location within threadblock tile by mapping the warp_id to</span></div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  <span class="comment">// three coordinates:</span></div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  <span class="comment">// _m: the warp's position within the threadblock along the M dimension</span></div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="comment">// _n: the warp's position within the threadblock along the N dimension</span></div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <span class="comment">// _k: the warp's position within the threadblock along the K dimension</span></div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> </div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  <span class="keywordtype">int</span> warp_idx_mn = warp_idx % (<a class="code" href="structcutlass_1_1gemm_1_1GemmShape.html#a7a47fe0c44571a0a68a43c5a47cf676a">Base::WarpCount::kM</a> * <a class="code" href="structcutlass_1_1gemm_1_1GemmShape.html#a9fcbaa4b47b83d0c8a09979ad5c98a1e">Base::WarpCount::kN</a>);</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  <span class="keywordtype">int</span> warp_idx_k = warp_idx / (<a class="code" href="structcutlass_1_1gemm_1_1GemmShape.html#a7a47fe0c44571a0a68a43c5a47cf676a">Base::WarpCount::kM</a> * <a class="code" href="structcutlass_1_1gemm_1_1GemmShape.html#a9fcbaa4b47b83d0c8a09979ad5c98a1e">Base::WarpCount::kN</a>);</div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span> </div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  <span class="keywordtype">int</span> warp_idx_m = warp_idx_mn % <a class="code" href="structcutlass_1_1gemm_1_1GemmShape.html#a7a47fe0c44571a0a68a43c5a47cf676a">Base::WarpCount::kM</a>;</div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  <span class="keywordtype">int</span> warp_idx_n = warp_idx_mn / <a class="code" href="structcutlass_1_1gemm_1_1GemmShape.html#a7a47fe0c44571a0a68a43c5a47cf676a">Base::WarpCount::kM</a>;</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span> </div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  <span class="comment">// Add per-warp offsets in units of warp-level tiles</span></div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>.add_tile_offset({warp_idx_m, <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a02f496a0fd1df929d8d4db9fea19160d">Base::kWarpGemmIterations</a> * warp_idx_k});</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>.add_tile_offset({<a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a02f496a0fd1df929d8d4db9fea19160d">Base::kWarpGemmIterations</a> * warp_idx_k, warp_idx_n});</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  }</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span> </div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  CUTLASS_DEVICE</div><div class="line"><a name="l00170"></a><span class="lineno"><a class="line" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2e45872db16c8ebe01289d7cb74fe3d7"> 170</a></span>  <span class="keywordtype">void</span> <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2e45872db16c8ebe01289d7cb74fe3d7">operator()</a>(</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  <span class="keywordtype">int</span> gemm_k_iterations, </div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2993390a8feebe3cf4bfb77a23c5ef33">FragmentC</a> &accum, </div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a258197bea0d4894569c627c56a64203a">IteratorA</a> iterator_A, </div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3989c584460e66c75a3f37ef91ecf06d">IteratorB</a> iterator_B, </div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2993390a8feebe3cf4bfb77a23c5ef33">FragmentC</a> <span class="keyword">const</span> &src_accum, </div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abbab0f268458143773b2654f48b54c1c">TransformA</a> transform_A = <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abbab0f268458143773b2654f48b54c1c">TransformA</a>(), </div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a66d61ceb64d44f645a7ef8223ddac50d">TransformB</a> transform_B = <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a66d61ceb64d44f645a7ef8223ddac50d">TransformB</a>()) { </div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span> </div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  <span class="comment">//</span></div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="comment">// Prologue</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  <span class="comment">//</span></div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span> </div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  <span class="comment">// Perform accumulation in the 'd' output operand</span></div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span>  accum = src_accum;</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>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8ab2e07ec7f4cf23ef158974fe3b8dbb">FragmentA</a> tb_frag_A;</div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8a6b28dec3f9687f46180d59ac9187fb">FragmentB</a> tb_frag_B;</div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> </div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span>  tb_frag_A.clear();</div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span>  tb_frag_B.clear();</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="comment">// The last kblock is loaded in the prolog</span></div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span>  iterator_A.load(tb_frag_A);</div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span>  iterator_B.load(tb_frag_B);</div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span> </div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  ++iterator_A;</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>  ++iterator_B;</div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span> </div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  this->smem_iterator_A_.store(transform_A(tb_frag_A));</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  this->smem_iterator_B_.store(transform_B(tb_frag_B));</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span> </div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a9d3cbfd5a2bbe4d105df9555ddbeeb2d">smem_iterator_A_</a>;</div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aec92c64ede1c4233dac30d0b2ec9e394">smem_iterator_B_</a>;</div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span> </div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  __syncthreads();</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> </div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span>  <span class="comment">// Pair of fragments used to overlap shared memory loads and math instructions</span></div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  WarpFragmentA warp_frag_A[2];</div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  WarpFragmentB warp_frag_B[2];</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span> </div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>.set_kgroup_index(0);</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>.set_kgroup_index(0);</div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span> </div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>.load(warp_frag_A[0]);</div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>.load(warp_frag_B[0]);</div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span> </div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>;</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>;</div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span> </div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span>  <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abecfbe5eb8946865dc9bbf14a6fc8aff">Operator</a> warp_mma;</div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span> </div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  <span class="keywordtype">int</span> smem_write_stage_idx = 1;</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span> </div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  <span class="comment">// Avoid reading out of bounds</span></div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  <span class="keywordflow">if</span> (gemm_k_iterations <= 1) {</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  iterator_A.clear_mask();</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  iterator_B.clear_mask();</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  }</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span> </div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <span class="comment">// Issue loads during the first warp-level matrix multiply-add *AFTER* issuing </span></div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  <span class="comment">// shared memory loads (which have the tightest latency requirement).</span></div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span> </div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  <span class="comment">//</span></div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="comment">// Mainloop</span></div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  <span class="comment">//</span></div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span> </div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="comment">// Note: The main loop does not support Base::kWarpGemmIterations == 2.</span></div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  <a class="code" href="cutlass_8h.html#a8e18ced39c05ab3304bb4fcdc0cc9f71">CUTLASS_GEMM_LOOP</a></div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  <span class="keywordflow">for</span> (; gemm_k_iterations > 0; --gemm_k_iterations) {</div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  <span class="comment">//</span></div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span>  <span class="comment">// Loop over GEMM K dimension</span></div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  <span class="comment">//</span></div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span> </div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span>  <a class="code" href="cutlass_8h.html#a4b1c9f25ab6eaa25e1f2258dd63e6ce4">CUTLASS_PRAGMA_UNROLL</a></div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> warp_mma_k = 0; warp_mma_k < <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a02f496a0fd1df929d8d4db9fea19160d">Base::kWarpGemmIterations</a>; ++warp_mma_k) {</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span> </div><div class="line"><a name="l00247"></a><span class="lineno"> 247</span>  <span class="comment">// Load warp-level tiles from shared memory, wrapping to k offset if this is the last group</span></div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  <span class="comment">// as the case may be.</span></div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span> </div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  <span class="keywordflow">if</span> (warp_mma_k == Base::kWarpGemmIterations - 1) {</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span> </div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  <span class="comment">// Write fragments to shared memory</span></div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  this->smem_iterator_A_.store(transform_A(tb_frag_A));</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span> </div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  this->smem_iterator_B_.store(transform_B(tb_frag_B));</div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span> </div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  __syncthreads();</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>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aec92c64ede1c4233dac30d0b2ec9e394">smem_iterator_B_</a>;</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a9d3cbfd5a2bbe4d105df9555ddbeeb2d">smem_iterator_A_</a>;</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">// Add negative offsets to return iterators to the 'start' of the circular buffer in shared memory</span></div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  <span class="keywordflow">if</span> (smem_write_stage_idx == 1) {</div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  this->smem_iterator_A_.add_tile_offset({0, -<a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#ad1267d78374c170d9addd137310d2d9a">Base::kStages</a>});</div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  this->smem_iterator_B_.add_tile_offset({-<a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#ad1267d78374c170d9addd137310d2d9a">Base::kStages</a>, 0});</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>  <span class="keywordflow">else</span> {</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>.add_tile_offset(</div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span>  {0, -<a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#ad1267d78374c170d9addd137310d2d9a">Base::kStages</a> * Policy::kPartitionsK * Base::kWarpGemmIterations});</div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>.add_tile_offset(</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  {-<a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#ad1267d78374c170d9addd137310d2d9a">Base::kStages</a> * Policy::kPartitionsK * <a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a02f496a0fd1df929d8d4db9fea19160d">Base::kWarpGemmIterations</a>,</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  0});</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  }</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span> </div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  smem_write_stage_idx ^= 1;</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span>  }</div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span> </div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>.set_kgroup_index((warp_mma_k + 1) % Base::kWarpGemmIterations);</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>.set_kgroup_index((warp_mma_k + 1) % Base::kWarpGemmIterations);</div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  </div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>.load(warp_frag_A[(warp_mma_k + 1) % 2]);</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>.load(warp_frag_B[(warp_mma_k + 1) % 2]);</div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span> </div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">warp_tile_iterator_A_</a>;</div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span>  ++this-><a class="code" href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">warp_tile_iterator_B_</a>;</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span> </div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>  <span class="keywordflow">if</span> (warp_mma_k == 0) {</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span> </div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span>  iterator_A.load(tb_frag_A);</div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span>  iterator_B.load(tb_frag_B);</div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span> </div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span>  ++iterator_A;</div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span>  ++iterator_B;</div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span> </div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span>  <span class="comment">// Avoid reading out of bounds if this was the last loop iteration</span></div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  <span class="keywordflow">if</span> (gemm_k_iterations <= 2) {</div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span>  iterator_A.clear_mask();</div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span>  iterator_B.clear_mask();</div><div class="line"><a name="l00299"></a><span class="lineno"> 299</span>  }</div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span>  }</div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span> </div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span>  warp_mma(accum, warp_frag_A[warp_mma_k % 2], warp_frag_B[warp_mma_k % 2], accum);</div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span>  }</div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span>  }</div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span> </div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span>  }</div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span> };</div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span> </div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span> </div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span> } <span class="comment">// namespace threadblock</span></div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span> } <span class="comment">// namespace gemm</span></div><div class="line"><a name="l00313"></a><span class="lineno"> 313</span> } <span class="comment">// namespace cutlass</span></div><div class="ttc" id="structcutlass_1_1gemm_1_1GemmShape_html_a7a47fe0c44571a0a68a43c5a47cf676a"><div class="ttname"><a href="structcutlass_1_1gemm_1_1GemmShape.html#a7a47fe0c44571a0a68a43c5a47cf676a">cutlass::gemm::GemmShape::kM</a></div><div class="ttdeci">static int const kM</div><div class="ttdef"><b>Definition:</b> include/cutlass/gemm/gemm.h:58</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a3bfd1d89c66d37d5a81d36262ad333d7"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3bfd1d89c66d37d5a81d36262ad333d7">cutlass::gemm::threadblock::MmaPipelined::LayoutC</a></div><div class="ttdeci">LayoutC_ LayoutC</div><div class="ttdoc">Layout of accumulator matrix. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:96</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a66d61ceb64d44f645a7ef8223ddac50d"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a66d61ceb64d44f645a7ef8223ddac50d">cutlass::gemm::threadblock::MmaPipelined::TransformB</a></div><div class="ttdeci">TransformB_ TransformB</div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:103</div></div>
|
|
<div class="ttc" id="namespacecutlass_html"><div class="ttname"><a href="namespacecutlass.html">cutlass</a></div><div class="ttdef"><b>Definition:</b> aligned_buffer.h:35</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a09e5e5bfa35c1398346c452eb3deeb97"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a09e5e5bfa35c1398346c452eb3deeb97">cutlass::gemm::threadblock::MmaPipelined::Policy</a></div><div class="ttdeci">Policy_ Policy</div><div class="ttdoc">Policy describing tuning details. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:97</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_html_a3ccfb6c23f8be68463a081dc18a7b6f1"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a3ccfb6c23f8be68463a081dc18a7b6f1">cutlass::gemm::threadblock::MmaBase< Shape_, Policy_, 2 >::warp_tile_iterator_B_</a></div><div class="ttdeci">Operator::IteratorB warp_tile_iterator_B_</div><div class="ttdoc">Iterator to load a warp-scoped tile of B operand from shared memory. </div><div class="ttdef"><b>Definition:</b> mma_base.h:193</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html">cutlass::gemm::threadblock::MmaPipelined</a></div><div class="ttdoc">Structure to compute the matrix product targeting CUDA cores and SIMT math instructions. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:86</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a3989c584460e66c75a3f37ef91ecf06d"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a3989c584460e66c75a3f37ef91ecf06d">cutlass::gemm::threadblock::MmaPipelined::IteratorB</a></div><div class="ttdeci">IteratorB_ IteratorB</div><div class="ttdoc">Iterates over tiles of B operand in global memory. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:94</div></div>
|
|
<div class="ttc" id="include_2cutlass_2gemm_2gemm_8h_html"><div class="ttname"><a href="include_2cutlass_2gemm_2gemm_8h.html">gemm.h</a></div><div class="ttdoc">Defines common types used for all GEMM-like operators. </div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a2e45872db16c8ebe01289d7cb74fe3d7"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2e45872db16c8ebe01289d7cb74fe3d7">cutlass::gemm::threadblock::MmaPipelined::operator()</a></div><div class="ttdeci">CUTLASS_DEVICE void operator()(int gemm_k_iterations, FragmentC &accum, IteratorA iterator_A, IteratorB iterator_B, FragmentC const &src_accum, TransformA transform_A=TransformA(), TransformB transform_B=TransformB())</div><div class="ttdoc">Perform a threadblock-scoped matrix multiply-accumulate. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:170</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a258197bea0d4894569c627c56a64203a"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a258197bea0d4894569c627c56a64203a">cutlass::gemm::threadblock::MmaPipelined::IteratorA</a></div><div class="ttdeci">IteratorA_ IteratorA</div><div class="ttdoc">Iterates over tiles of A operand in global memory. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:93</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a8a6b28dec3f9687f46180d59ac9187fb"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8a6b28dec3f9687f46180d59ac9187fb">cutlass::gemm::threadblock::MmaPipelined::FragmentB</a></div><div class="ttdeci">typename IteratorB::Fragment FragmentB</div><div class="ttdoc">Fragment of operand B loaded from global memory. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:113</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_aba5cccb236e9a9368a9ae1e1df869e57"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aba5cccb236e9a9368a9ae1e1df869e57">cutlass::gemm::threadblock::MmaPipelined::SmemIteratorA</a></div><div class="ttdeci">SmemIteratorA_ SmemIteratorA</div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:99</div></div>
|
|
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Statically sized array of elements that accommodates all CUTLASS-supported numeric types and is safe ...</div></div>
|
|
<div class="ttc" id="cutlass_8h_html_a4b1c9f25ab6eaa25e1f2258dd63e6ce4"><div class="ttname"><a href="cutlass_8h.html#a4b1c9f25ab6eaa25e1f2258dd63e6ce4">CUTLASS_PRAGMA_UNROLL</a></div><div class="ttdeci">#define CUTLASS_PRAGMA_UNROLL</div><div class="ttdef"><b>Definition:</b> cutlass.h:110</div></div>
|
|
<div class="ttc" id="numeric__conversion_8h_html"><div class="ttname"><a href="numeric__conversion_8h.html">numeric_conversion.h</a></div><div class="ttdoc">Boost-like numeric conversion operator for CUTLASS numeric types. </div></div>
|
|
<div class="ttc" id="matrix__shape_8h_html"><div class="ttname"><a href="matrix__shape_8h.html">matrix_shape.h</a></div><div class="ttdoc">Defines a Shape template for matrix tiles. </div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_html_a02f496a0fd1df929d8d4db9fea19160d"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a02f496a0fd1df929d8d4db9fea19160d">cutlass::gemm::threadblock::MmaBase< Shape_, Policy_, 2 >::kWarpGemmIterations</a></div><div class="ttdeci">static int const kWarpGemmIterations</div><div class="ttdoc">Number of warp-level GEMM oeprations. </div><div class="ttdef"><b>Definition:</b> mma_base.h:108</div></div>
|
|
<div class="ttc" id="mma__base_8h_html"><div class="ttname"><a href="mma__base_8h.html">mma_base.h</a></div><div class="ttdoc">Template for a double-buffered threadblock-scoped GEMM kernel. </div></div>
|
|
<div class="ttc" id="aligned__buffer_8h_html"><div class="ttname"><a href="aligned__buffer_8h.html">aligned_buffer.h</a></div><div class="ttdoc">AlignedBuffer is a container for trivially copyable elements suitable for use in unions and shared me...</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_af42727c7f832320ae88178d163421dca"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#af42727c7f832320ae88178d163421dca">cutlass::gemm::threadblock::MmaPipelined::Shape</a></div><div class="ttdeci">Shape_ Shape</div><div class="ttdoc">Size of the Gemm problem - concept: gemm::GemmShape<> </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:92</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_html_ad1267d78374c170d9addd137310d2d9a"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#ad1267d78374c170d9addd137310d2d9a">cutlass::gemm::threadblock::MmaBase< Shape_, Policy_, 2 >::kStages</a></div><div class="ttdeci">static int const kStages</div><div class="ttdoc">Number of stages. </div><div class="ttdef"><b>Definition:</b> mma_base.h:112</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a8ab2e07ec7f4cf23ef158974fe3b8dbb"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a8ab2e07ec7f4cf23ef158974fe3b8dbb">cutlass::gemm::threadblock::MmaPipelined::FragmentA</a></div><div class="ttdeci">typename IteratorA::Fragment FragmentA</div><div class="ttdoc">Fragment of operand A loaded from global memory. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:110</div></div>
|
|
<div class="ttc" id="numeric__types_8h_html"><div class="ttname"><a href="numeric__types_8h.html">numeric_types.h</a></div><div class="ttdoc">Top-level include for all CUTLASS numeric types. </div></div>
|
|
<div class="ttc" id="platform_8h_html_adde4c9ea91b753491851361a4198c009"><div class="ttname"><a href="platform_8h.html#adde4c9ea91b753491851361a4198c009">static_assert</a></div><div class="ttdeci">#define static_assert(__e, __m)</div><div class="ttdef"><b>Definition:</b> platform.h:153</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_html"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html">cutlass::gemm::threadblock::MmaBase</a></div><div class="ttdef"><b>Definition:</b> mma_base.h:83</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a2993390a8feebe3cf4bfb77a23c5ef33"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a2993390a8feebe3cf4bfb77a23c5ef33">cutlass::gemm::threadblock::MmaPipelined::FragmentC</a></div><div class="ttdeci">typename Policy::Operator::FragmentC FragmentC</div><div class="ttdoc">Fragment of accumulator tile. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:116</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase_html_a98647e72bab767b280e69679bdf9947f"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaBase.html#a98647e72bab767b280e69679bdf9947f">cutlass::gemm::threadblock::MmaBase< Shape_, Policy_, 2 >::warp_tile_iterator_A_</a></div><div class="ttdeci">Operator::IteratorA warp_tile_iterator_A_</div><div class="ttdoc">Iterator to load a warp-scoped tile of A operand from shared memory. </div><div class="ttdef"><b>Definition:</b> mma_base.h:190</div></div>
|
|
<div class="ttc" id="cutlass_8h_html_a8e18ced39c05ab3304bb4fcdc0cc9f71"><div class="ttname"><a href="cutlass_8h.html#a8e18ced39c05ab3304bb4fcdc0cc9f71">CUTLASS_GEMM_LOOP</a></div><div class="ttdeci">#define CUTLASS_GEMM_LOOP</div><div class="ttdef"><b>Definition:</b> cutlass.h:112</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a102ddf57c1f46f5ed411b9d953e3f802"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a102ddf57c1f46f5ed411b9d953e3f802">cutlass::gemm::threadblock::MmaPipelined::ElementC</a></div><div class="ttdeci">ElementC_ ElementC</div><div class="ttdoc">Data type of accumulator matrix. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:95</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a9d3cbfd5a2bbe4d105df9555ddbeeb2d"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a9d3cbfd5a2bbe4d105df9555ddbeeb2d">cutlass::gemm::threadblock::MmaPipelined::smem_iterator_A_</a></div><div class="ttdeci">SmemIteratorA smem_iterator_A_</div><div class="ttdoc">Iterator to write threadblock-scoped tile of A operand to shared memory. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:132</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_a0bbed549aeb0185a8486faa5fde22dd0"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#a0bbed549aeb0185a8486faa5fde22dd0">cutlass::gemm::threadblock::MmaPipelined::SmemIteratorB</a></div><div class="ttdeci">SmemIteratorB_ SmemIteratorB</div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:100</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_aec92c64ede1c4233dac30d0b2ec9e394"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#aec92c64ede1c4233dac30d0b2ec9e394">cutlass::gemm::threadblock::MmaPipelined::smem_iterator_B_</a></div><div class="ttdeci">SmemIteratorB smem_iterator_B_</div><div class="ttdoc">Iterator to write threadblock-scoped tile of B operand to shared memory. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:135</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_ac8dc63b0f3ced3d8f615b56678e26400"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#ac8dc63b0f3ced3d8f615b56678e26400">cutlass::gemm::threadblock::MmaPipelined::MmaPipelined</a></div><div class="ttdeci">CUTLASS_DEVICE MmaPipelined(typename Base::SharedStorage &shared_storage, int thread_idx, int warp_idx, int lane_idx)</div><div class="ttdoc">Construct from tensor references. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:141</div></div>
|
|
<div class="ttc" id="cutlass_8h_html"><div class="ttname"><a href="cutlass_8h.html">cutlass.h</a></div><div class="ttdoc">Basic include for CUTLASS. </div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_abbab0f268458143773b2654f48b54c1c"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abbab0f268458143773b2654f48b54c1c">cutlass::gemm::threadblock::MmaPipelined::TransformA</a></div><div class="ttdeci">TransformA_ TransformA</div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:102</div></div>
|
|
<div class="ttc" id="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined_html_abecfbe5eb8946865dc9bbf14a6fc8aff"><div class="ttname"><a href="classcutlass_1_1gemm_1_1threadblock_1_1MmaPipelined.html#abecfbe5eb8946865dc9bbf14a6fc8aff">cutlass::gemm::threadblock::MmaPipelined::Operator</a></div><div class="ttdeci">typename Policy::Operator Operator</div><div class="ttdoc">Warp-level Mma. </div><div class="ttdef"><b>Definition:</b> mma_pipelined.h:119</div></div>
|
|
<div class="ttc" id="structcutlass_1_1gemm_1_1GemmShape_html_a9fcbaa4b47b83d0c8a09979ad5c98a1e"><div class="ttname"><a href="structcutlass_1_1gemm_1_1GemmShape.html#a9fcbaa4b47b83d0c8a09979ad5c98a1e">cutlass::gemm::GemmShape::kN</a></div><div class="ttdeci">static int const kN</div><div class="ttdef"><b>Definition:</b> include/cutlass/gemm/gemm.h:59</div></div>
|
|
</div><!-- fragment --></div><!-- contents -->
|
|
<!-- start footer part -->
|
|
<hr class="footer"/><address class="footer"><small>
|
|
Generated by  <a href="http://www.doxygen.org/index.html">
|
|
<img class="footer" src="doxygen.png" alt="doxygen"/>
|
|
</a> 1.8.11
|
|
</small></address>
|
|
</body>
|
|
</html>
|