CUTLASS 2.0 (#62)
CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
This commit is contained in:
@@ -3,21 +3,23 @@
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/>
|
||||
<meta http-equiv="X-UA-Compatible" content="IE=9"/>
|
||||
<meta name="generator" content="Doxygen 1.8.14"/>
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||||
<title>Cutlass: cutlass::PredicateVector< kPredicates_, kPredicatesPerByte_, kPredicateStart_ >::TrivialIterator Struct Reference</title>
|
||||
<meta name="generator" content="Doxygen 1.8.11"/>
|
||||
<title>CUTLASS: cutlass::PredicateVector< kPredicates_, kPredicatesPerByte_, kPredicateStart_ >::TrivialIterator Struct 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" async src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
|
||||
</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>
|
||||
@@ -26,8 +28,9 @@
|
||||
<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 id="projectname">CUTLASS
|
||||
</div>
|
||||
<div id="projectbrief">CUDA Templates for Linear Algebra Subroutines and Solvers</div>
|
||||
</td>
|
||||
@@ -36,22 +39,43 @@
|
||||
</table>
|
||||
</div>
|
||||
<!-- end header part -->
|
||||
<!-- Generated by Doxygen 1.8.14 -->
|
||||
<!-- Generated by Doxygen 1.8.11 -->
|
||||
<script type="text/javascript">
|
||||
/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */
|
||||
var searchBox = new SearchBox("searchBox", "search",false,'Search');
|
||||
/* @license-end */
|
||||
</script>
|
||||
<script type="text/javascript" src="menudata.js"></script>
|
||||
<script type="text/javascript" src="menu.js"></script>
|
||||
<script type="text/javascript">
|
||||
/* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */
|
||||
$(function() {
|
||||
initMenu('',true,false,'search.php','Search');
|
||||
$(document).ready(function() { init_search(); });
|
||||
});
|
||||
/* @license-end */</script>
|
||||
<div id="main-nav"></div>
|
||||
<div 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 class="current"><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="annotated.html"><span>Class List</span></a></li>
|
||||
<li><a href="classes.html"><span>Class Index</span></a></li>
|
||||
<li><a href="inherits.html"><span>Class Hierarchy</span></a></li>
|
||||
<li><a href="functions.html"><span>Class Members</span></a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<!-- window showing the filter options -->
|
||||
<div id="MSearchSelectWindow"
|
||||
onmouseover="return searchBox.OnSearchSelectShow()"
|
||||
@@ -91,7 +115,7 @@ Public Member Functions</h2></td></tr>
|
||||
<tr class="memdesc:a6cb3664b5cba4280b7055a65ddad7850"><td class="mdescLeft"> </td><td class="mdescRight">Constructor. <a href="#a6cb3664b5cba4280b7055a65ddad7850">More...</a><br /></td></tr>
|
||||
<tr class="separator:a6cb3664b5cba4280b7055a65ddad7850"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:ada8cd3ac6db568bb9bf268ba2c3a3e14"><td class="memItemLeft" align="right" valign="top"><a class="el" href="cutlass_8h.html#a28c2443a142676d3d71effdae1a986b1">CUTLASS_HOST_DEVICE</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1PredicateVector_1_1TrivialIterator.html#ada8cd3ac6db568bb9bf268ba2c3a3e14">TrivialIterator</a> (<a class="el" href="classcutlass_1_1PredicateVector_1_1Iterator.html">Iterator</a> const &it)</td></tr>
|
||||
<tr class="memdesc:ada8cd3ac6db568bb9bf268ba2c3a3e14"><td class="mdescLeft"> </td><td class="mdescRight"><a class="el" href="structcutlass_1_1Copy.html">Copy</a> constructor. <a href="#ada8cd3ac6db568bb9bf268ba2c3a3e14">More...</a><br /></td></tr>
|
||||
<tr class="memdesc:ada8cd3ac6db568bb9bf268ba2c3a3e14"><td class="mdescLeft"> </td><td class="mdescRight">Copy constructor. <a href="#ada8cd3ac6db568bb9bf268ba2c3a3e14">More...</a><br /></td></tr>
|
||||
<tr class="separator:ada8cd3ac6db568bb9bf268ba2c3a3e14"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:a3adf0440f9a0143a61b43d39c3f03721"><td class="memItemLeft" align="right" valign="top"><a class="el" href="cutlass_8h.html#a28c2443a142676d3d71effdae1a986b1">CUTLASS_HOST_DEVICE</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1PredicateVector_1_1TrivialIterator.html#a3adf0440f9a0143a61b43d39c3f03721">TrivialIterator</a> (<a class="el" href="structcutlass_1_1PredicateVector.html">PredicateVector</a> const &_vec)</td></tr>
|
||||
<tr class="memdesc:a3adf0440f9a0143a61b43d39c3f03721"><td class="mdescLeft"> </td><td class="mdescRight">Constructs an iterator from a <a class="el" href="structcutlass_1_1PredicateVector.html" title="Statically sized array of bits implementing. ">PredicateVector</a>. <a href="#a3adf0440f9a0143a61b43d39c3f03721">More...</a><br /></td></tr>
|
||||
@@ -102,14 +126,12 @@ Public Member Functions</h2></td></tr>
|
||||
<tr class="memitem:aa35b9165920b83b9a5a888df83925051"><td class="memItemLeft" align="right" valign="top"><a class="el" href="cutlass_8h.html#a28c2443a142676d3d71effdae1a986b1">CUTLASS_HOST_DEVICE</a> <a class="el" href="structcutlass_1_1PredicateVector_1_1TrivialIterator.html">TrivialIterator</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1PredicateVector_1_1TrivialIterator.html#aa35b9165920b83b9a5a888df83925051">operator++</a> (int)</td></tr>
|
||||
<tr class="memdesc:aa35b9165920b83b9a5a888df83925051"><td class="mdescLeft"> </td><td class="mdescRight">Post-increment. <a href="#aa35b9165920b83b9a5a888df83925051">More...</a><br /></td></tr>
|
||||
<tr class="separator:aa35b9165920b83b9a5a888df83925051"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:a78016158f99dd87e822a2a2cbd4cec78"><td class="memItemLeft" align="right" valign="top"><a class="el" href="cutlass_8h.html#a28c2443a142676d3d71effdae1a986b1">CUTLASS_HOST_DEVICE</a> bool </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1PredicateVector_1_1TrivialIterator.html#a78016158f99dd87e822a2a2cbd4cec78">operator*</a> () const</td></tr>
|
||||
<tr class="memdesc:a78016158f99dd87e822a2a2cbd4cec78"><td class="mdescLeft"> </td><td class="mdescRight">Dereferences iterator. <a href="#a78016158f99dd87e822a2a2cbd4cec78">More...</a><br /></td></tr>
|
||||
<tr class="separator:a78016158f99dd87e822a2a2cbd4cec78"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:aa6774c80e75fdd469bf1e42d98f8959a"><td class="memItemLeft" align="right" valign="top"><a class="el" href="cutlass_8h.html#a28c2443a142676d3d71effdae1a986b1">CUTLASS_HOST_DEVICE</a> bool </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1PredicateVector_1_1TrivialIterator.html#aa6774c80e75fdd469bf1e42d98f8959a">operator*</a> () const </td></tr>
|
||||
<tr class="memdesc:aa6774c80e75fdd469bf1e42d98f8959a"><td class="mdescLeft"> </td><td class="mdescRight">Dereferences iterator. <a href="#aa6774c80e75fdd469bf1e42d98f8959a">More...</a><br /></td></tr>
|
||||
<tr class="separator:aa6774c80e75fdd469bf1e42d98f8959a"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
</table>
|
||||
<h2 class="groupheader">Constructor & Destructor Documentation</h2>
|
||||
<a id="a6cb3664b5cba4280b7055a65ddad7850"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#a6cb3664b5cba4280b7055a65ddad7850">◆ </a></span>TrivialIterator() <span class="overload">[1/3]</span></h2>
|
||||
|
||||
<a class="anchor" id="a6cb3664b5cba4280b7055a65ddad7850"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<div class="memtemplate">
|
||||
@@ -134,9 +156,7 @@ template<int kPredicates_, int kPredicatesPerByte_ = 4, int kPredicateStart_
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="ada8cd3ac6db568bb9bf268ba2c3a3e14"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#ada8cd3ac6db568bb9bf268ba2c3a3e14">◆ </a></span>TrivialIterator() <span class="overload">[2/3]</span></h2>
|
||||
|
||||
<a class="anchor" id="ada8cd3ac6db568bb9bf268ba2c3a3e14"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<div class="memtemplate">
|
||||
@@ -162,9 +182,7 @@ template<int kPredicates_, int kPredicatesPerByte_ = 4, int kPredicateStart_
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="a3adf0440f9a0143a61b43d39c3f03721"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#a3adf0440f9a0143a61b43d39c3f03721">◆ </a></span>TrivialIterator() <span class="overload">[3/3]</span></h2>
|
||||
|
||||
<a class="anchor" id="a3adf0440f9a0143a61b43d39c3f03721"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<div class="memtemplate">
|
||||
@@ -191,9 +209,7 @@ template<int kPredicates_, int kPredicatesPerByte_ = 4, int kPredicateStart_
|
||||
</div>
|
||||
</div>
|
||||
<h2 class="groupheader">Member Function Documentation</h2>
|
||||
<a id="a78016158f99dd87e822a2a2cbd4cec78"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#a78016158f99dd87e822a2a2cbd4cec78">◆ </a></span>operator*()</h2>
|
||||
|
||||
<a class="anchor" id="aa6774c80e75fdd469bf1e42d98f8959a"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<div class="memtemplate">
|
||||
@@ -218,9 +234,7 @@ template<int kPredicates_, int kPredicatesPerByte_ = 4, int kPredicateStart_
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="ad24e9b451064e99fb19955f772c30e6a"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#ad24e9b451064e99fb19955f772c30e6a">◆ </a></span>operator++() <span class="overload">[1/2]</span></h2>
|
||||
|
||||
<a class="anchor" id="ad24e9b451064e99fb19955f772c30e6a"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<div class="memtemplate">
|
||||
@@ -245,9 +259,7 @@ template<int kPredicates_, int kPredicatesPerByte_ = 4, int kPredicateStart_
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="aa35b9165920b83b9a5a888df83925051"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#aa35b9165920b83b9a5a888df83925051">◆ </a></span>operator++() <span class="overload">[2/2]</span></h2>
|
||||
|
||||
<a class="anchor" id="aa35b9165920b83b9a5a888df83925051"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<div class="memtemplate">
|
||||
@@ -279,9 +291,9 @@ template<int kPredicates_, int kPredicatesPerByte_ = 4, int kPredicateStart_
|
||||
</div><!-- contents -->
|
||||
<!-- start footer part -->
|
||||
<hr class="footer"/><address class="footer"><small>
|
||||
Generated on Fri Oct 26 2018 14:53:34 for Cutlass by  <a href="http://www.doxygen.org/index.html">
|
||||
Generated by  <a href="http://www.doxygen.org/index.html">
|
||||
<img class="footer" src="doxygen.png" alt="doxygen"/>
|
||||
</a> 1.8.14
|
||||
</a> 1.8.11
|
||||
</small></address>
|
||||
</body>
|
||||
</html>
|
||||
|
||||
Reference in New Issue
Block a user