cutlass/docs/namespacecutlass_1_1gemm_1_...

513 lines
30 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: cutlass::gemm::kernel Namespace Reference</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&#160;Page</span></a></li>
<li><a href="modules.html"><span>Modules</span></a></li>
<li class="current"><a href="namespaces.html"><span>Namespaces</span></a></li>
<li><a href="annotated.html"><span>Classes</span></a></li>
<li><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="namespaces.html"><span>Namespace&#160;List</span></a></li>
<li><a href="namespacemembers.html"><span>Namespace&#160;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="namespacecutlass.html">cutlass</a></li><li class="navelem"><a class="el" href="namespacecutlass_1_1gemm.html">gemm</a></li><li class="navelem"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html">kernel</a></li> </ul>
</div>
</div><!-- top -->
<div class="header">
<div class="summary">
<a href="#namespaces">Namespaces</a> &#124;
<a href="#nested-classes">Classes</a> &#124;
<a href="#func-members">Functions</a> </div>
<div class="headertitle">
<div class="title">cutlass::gemm::kernel Namespace Reference</div> </div>
</div><!--header-->
<div class="contents">
<table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="namespaces"></a>
Namespaces</h2></td></tr>
<tr class="memitem:namespacecutlass_1_1gemm_1_1kernel_1_1detail"><td class="memItemLeft" align="right" valign="top"> &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel_1_1detail.html">detail</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
</table><table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="nested-classes"></a>
Classes</h2></td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm.html">DefaultGemm</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01layout_1_1ColumnMajorInterleave661fe54d13cc2c9153dcdf31e4beaa30.html">DefaultGemm&lt; ElementA, layout::ColumnMajorInterleaved&lt; InterleavedK &gt;, kAlignmentA, ElementB, layout::RowMajorInterleaved&lt; InterleavedK &gt;, kAlignmentB, ElementC, layout::ColumnMajorInterleaved&lt; InterleavedK &gt;, int32_t, arch::OpClassTensorOp, arch::Sm75, ThreadblockShape, WarpShape, InstructionShape, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator, IsBetaZero &gt;</a></td></tr>
<tr class="memdesc:"><td class="mdescLeft">&#160;</td><td class="mdescRight">Partial specialization for Turing Integer Matrix Multiply Interleaved layout. <a href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01layout_1_1ColumnMajorInterleave661fe54d13cc2c9153dcdf31e4beaa30.html#details">More...</a><br /></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01Edd80343e6570718ed237122e4ebf7fb5.html">DefaultGemm&lt; ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementC, layout::RowMajor, ElementAccumulator, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape&lt; 1, 1, 1 &gt;, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator &gt;</a></td></tr>
<tr class="memdesc:"><td class="mdescLeft">&#160;</td><td class="mdescRight">Partial specialization for SIMT. <a href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01Edd80343e6570718ed237122e4ebf7fb5.html#details">More...</a><br /></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01E044b039b2fe402f29b04a9f5feee5342.html">DefaultGemm&lt; ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementC, layout::RowMajor, ElementAccumulator, arch::OpClassTensorOp, arch::Sm70, ThreadblockShape, WarpShape, GemmShape&lt; 8, 8, 4 &gt;, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator &gt;</a></td></tr>
<tr class="memdesc:"><td class="mdescLeft">&#160;</td><td class="mdescRight">Partial specialization for Volta architecture. <a href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01E044b039b2fe402f29b04a9f5feee5342.html#details">More...</a><br /></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01E5d78d37a9ae2ec08d7d477d571df036e.html">DefaultGemm&lt; ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementC, layout::RowMajor, ElementAccumulator, arch::OpClassTensorOp, arch::Sm75, ThreadblockShape, WarpShape, InstructionShape, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator &gt;</a></td></tr>
<tr class="memdesc:"><td class="mdescLeft">&#160;</td><td class="mdescRight">Partial specialization for Turing Architecture. <a href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01ElementA_00_01LayoutA_00_01kAlignmentA_00_01E5d78d37a9ae2ec08d7d477d571df036e.html#details">More...</a><br /></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01int8__t_00_01LayoutA_00_01kAlignmentA_00_01inf48440732c1c5f42ddbfaba179861815.html">DefaultGemm&lt; int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementC, LayoutC, ElementAccumulator, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape&lt; 1, 1, 4 &gt;, EpilogueOutputOp, ThreadblockSwizzle, 2, SplitKSerial, Operator, false &gt;</a></td></tr>
<tr class="memdesc:"><td class="mdescLeft">&#160;</td><td class="mdescRight">Partial specialization for SIMT DP4A. <a href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemm_3_01int8__t_00_01LayoutA_00_01kAlignmentA_00_01inf48440732c1c5f42ddbfaba179861815.html#details">More...</a><br /></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemmSplitKParallel.html">DefaultGemmSplitKParallel</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1DefaultGemv.html">DefaultGemv</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1Gemm.html">Gemm</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1GemmBatched.html">GemmBatched</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct &#160;</td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1gemm_1_1kernel_1_1GemmSplitKParallel.html">GemmSplitKParallel</a></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2">&#160;</td></tr>
</table><table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
Functions</h2></td></tr>
<tr class="memitem:a86f3df531e2d944aefa99773dc921610"><td class="memTemplParams" colspan="2">template&lt;typename Mma , typename Epilogue , typename ThreadblockSwizzle &gt; </td></tr>
<tr class="memitem:a86f3df531e2d944aefa99773dc921610"><td class="memTemplItemLeft" align="right" valign="top">__global__ void&#160;</td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html#a86f3df531e2d944aefa99773dc921610">GemmPipelined</a> (<a class="el" href="structcutlass_1_1gemm_1_1GemmCoord.html">cutlass::gemm::GemmCoord</a> problem_size, <a class="el" href="structcutlass_1_1gemm_1_1GemmCoord.html">cutlass::gemm::GemmCoord</a> grid_tiled_shape, typename Mma::IteratorA::Params params_A, typename Mma::IteratorA::TensorRef ref_A, typename Mma::IteratorB::Params params_B, typename Mma::IteratorB::TensorRef ref_B, typename Epilogue::Params params_epilogue)</td></tr>
<tr class="separator:a86f3df531e2d944aefa99773dc921610"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:a712b03b425a0709765e56d259169793a"><td class="memTemplParams" colspan="2">template&lt;typename GemvKernel , typename ElementAlphaBeta , bool BetaIsZero = false&gt; </td></tr>
<tr class="memitem:a712b03b425a0709765e56d259169793a"><td class="memTemplItemLeft" align="right" valign="top">CUTLASS_DEVICE void&#160;</td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html#a712b03b425a0709765e56d259169793a">GemvBatchedStridedDevice</a> (<a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a> problem_size, ElementAlphaBeta alpha, ElementAlphaBeta beta, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_C, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldc, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)</td></tr>
<tr class="separator:a712b03b425a0709765e56d259169793a"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:a8b54a05e5198735ec7e162dac8174a89"><td class="memTemplParams" colspan="2">template&lt;typename GemvKernel , typename ElementAlphaBeta , bool BetaIsZero&gt; </td></tr>
<tr class="memitem:a8b54a05e5198735ec7e162dac8174a89"><td class="memTemplItemLeft" align="right" valign="top">__global__ void&#160;</td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html#a8b54a05e5198735ec7e162dac8174a89">GemvBatchedStrided</a> (<a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a> problem_size, ElementAlphaBeta alpha, ElementAlphaBeta beta, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_C, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldc, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)</td></tr>
<tr class="separator:a8b54a05e5198735ec7e162dac8174a89"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:a55ddc9e826fb95a090031005c95f8502"><td class="memTemplParams" colspan="2">template&lt;typename GemvKernel , typename ElementAlphaBeta &gt; </td></tr>
<tr class="memitem:a55ddc9e826fb95a090031005c95f8502"><td class="memTemplItemLeft" align="right" valign="top">__global__ void&#160;</td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html#a55ddc9e826fb95a090031005c95f8502">GemvBatchedStrided</a> (<a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a> problem_size, ElementAlphaBeta alpha, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)</td></tr>
<tr class="separator:a55ddc9e826fb95a090031005c95f8502"><td class="memSeparator" colspan="2">&#160;</td></tr>
<tr class="memitem:a2dda6701792d7cac23aa4971a18daddf"><td class="memTemplParams" colspan="2">template&lt;typename GemvKernel &gt; </td></tr>
<tr class="memitem:a2dda6701792d7cac23aa4971a18daddf"><td class="memTemplItemLeft" align="right" valign="top">__global__ void&#160;</td><td class="memTemplItemRight" valign="bottom"><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html#a2dda6701792d7cac23aa4971a18daddf">GemvBatchedStrided</a> (<a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a> problem_size, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)</td></tr>
<tr class="separator:a2dda6701792d7cac23aa4971a18daddf"><td class="memSeparator" colspan="2">&#160;</td></tr>
</table>
<h2 class="groupheader">Function Documentation</h2>
<a class="anchor" id="a86f3df531e2d944aefa99773dc921610"></a>
<div class="memitem">
<div class="memproto">
<div class="memtemplate">
template&lt;typename Mma , typename Epilogue , typename ThreadblockSwizzle &gt; </div>
<table class="memname">
<tr>
<td class="memname">__global__ void cutlass::gemm::kernel::GemmPipelined </td>
<td>(</td>
<td class="paramtype"><a class="el" href="structcutlass_1_1gemm_1_1GemmCoord.html">cutlass::gemm::GemmCoord</a>&#160;</td>
<td class="paramname"><em>problem_size</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype"><a class="el" href="structcutlass_1_1gemm_1_1GemmCoord.html">cutlass::gemm::GemmCoord</a>&#160;</td>
<td class="paramname"><em>grid_tiled_shape</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename Mma::IteratorA::Params&#160;</td>
<td class="paramname"><em>params_A</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename Mma::IteratorA::TensorRef&#160;</td>
<td class="paramname"><em>ref_A</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename Mma::IteratorB::Params&#160;</td>
<td class="paramname"><em>params_B</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename Mma::IteratorB::TensorRef&#160;</td>
<td class="paramname"><em>ref_B</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename Epilogue::Params&#160;</td>
<td class="paramname"><em>params_epilogue</em>&#160;</td>
</tr>
<tr>
<td></td>
<td>)</td>
<td></td><td></td>
</tr>
</table>
</div><div class="memdoc">
</div>
</div>
<a class="anchor" id="a8b54a05e5198735ec7e162dac8174a89"></a>
<div class="memitem">
<div class="memproto">
<div class="memtemplate">
template&lt;typename GemvKernel , typename ElementAlphaBeta , bool BetaIsZero&gt; </div>
<table class="memname">
<tr>
<td class="memname">__global__ void cutlass::gemm::kernel::GemvBatchedStrided </td>
<td>(</td>
<td class="paramtype"><a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a>&#160;</td>
<td class="paramname"><em>problem_size</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">ElementAlphaBeta&#160;</td>
<td class="paramname"><em>alpha</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">ElementAlphaBeta&#160;</td>
<td class="paramname"><em>beta</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef&#160;</td>
<td class="paramname"><em>ref_A</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>lda</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef&#160;</td>
<td class="paramname"><em>ref_B</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldb</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef&#160;</td>
<td class="paramname"><em>ref_C</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldc</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef&#160;</td>
<td class="paramname"><em>ref_D</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldd</em>&#160;</td>
</tr>
<tr>
<td></td>
<td>)</td>
<td></td><td></td>
</tr>
</table>
</div><div class="memdoc">
</div>
</div>
<a class="anchor" id="a55ddc9e826fb95a090031005c95f8502"></a>
<div class="memitem">
<div class="memproto">
<div class="memtemplate">
template&lt;typename GemvKernel , typename ElementAlphaBeta &gt; </div>
<table class="memname">
<tr>
<td class="memname">__global__ void cutlass::gemm::kernel::GemvBatchedStrided </td>
<td>(</td>
<td class="paramtype"><a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a>&#160;</td>
<td class="paramname"><em>problem_size</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">ElementAlphaBeta&#160;</td>
<td class="paramname"><em>alpha</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef&#160;</td>
<td class="paramname"><em>ref_A</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>lda</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef&#160;</td>
<td class="paramname"><em>ref_B</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldb</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef&#160;</td>
<td class="paramname"><em>ref_D</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldd</em>&#160;</td>
</tr>
<tr>
<td></td>
<td>)</td>
<td></td><td></td>
</tr>
</table>
</div><div class="memdoc">
</div>
</div>
<a class="anchor" id="a2dda6701792d7cac23aa4971a18daddf"></a>
<div class="memitem">
<div class="memproto">
<div class="memtemplate">
template&lt;typename GemvKernel &gt; </div>
<table class="memname">
<tr>
<td class="memname">__global__ void cutlass::gemm::kernel::GemvBatchedStrided </td>
<td>(</td>
<td class="paramtype"><a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a>&#160;</td>
<td class="paramname"><em>problem_size</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef&#160;</td>
<td class="paramname"><em>ref_A</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>lda</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef&#160;</td>
<td class="paramname"><em>ref_B</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldb</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef&#160;</td>
<td class="paramname"><em>ref_D</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldd</em>&#160;</td>
</tr>
<tr>
<td></td>
<td>)</td>
<td></td><td></td>
</tr>
</table>
</div><div class="memdoc">
</div>
</div>
<a class="anchor" id="a712b03b425a0709765e56d259169793a"></a>
<div class="memitem">
<div class="memproto">
<div class="memtemplate">
template&lt;typename GemvKernel , typename ElementAlphaBeta , bool BetaIsZero = false&gt; </div>
<table class="memname">
<tr>
<td class="memname">CUTLASS_DEVICE void cutlass::gemm::kernel::GemvBatchedStridedDevice </td>
<td>(</td>
<td class="paramtype"><a class="el" href="structcutlass_1_1gemm_1_1BatchedGemmCoord.html">cutlass::gemm::BatchedGemmCoord</a>&#160;</td>
<td class="paramname"><em>problem_size</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">ElementAlphaBeta&#160;</td>
<td class="paramname"><em>alpha</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">ElementAlphaBeta&#160;</td>
<td class="paramname"><em>beta</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef&#160;</td>
<td class="paramname"><em>ref_A</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorA::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>lda</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef&#160;</td>
<td class="paramname"><em>ref_B</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorB::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldb</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef&#160;</td>
<td class="paramname"><em>ref_C</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldc</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef&#160;</td>
<td class="paramname"><em>ref_D</em>, </td>
</tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">typename GemvKernel::IteratorCD::TensorRef::LongIndex&#160;</td>
<td class="paramname"><em>ldd</em>&#160;</td>
</tr>
<tr>
<td></td>
<td>)</td>
<td></td><td></td>
</tr>
</table>
</div><div class="memdoc">
</div>
</div>
</div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
Generated by &#160;<a href="http://www.doxygen.org/index.html">
<img class="footer" src="doxygen.png" alt="doxygen"/>
</a> 1.8.11
</small></address>
</body>
</html>