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:
+65
-54
@@ -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: platform.h File Reference</title>
|
||||
<meta name="generator" content="Doxygen 1.8.11"/>
|
||||
<title>CUTLASS: platform.h File 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 +39,41 @@
|
||||
</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><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()"
|
||||
@@ -68,7 +90,7 @@ $(function() {
|
||||
|
||||
<div id="nav-path" class="navpath">
|
||||
<ul>
|
||||
<li class="navelem"><a class="el" href="dir_1417ee5ebebc309c36b7962f26a92c39.html">cutlass</a></li><li class="navelem"><a class="el" href="dir_c5917a9a879e9a6c73eaf5237444ab84.html">util</a></li> </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_df998829b150afe92f54393d2430470d.html">platform</a></li> </ul>
|
||||
</div>
|
||||
</div><!-- top -->
|
||||
<div class="header">
|
||||
@@ -91,20 +113,25 @@ $(function() {
|
||||
<code>#include <functional></code><br />
|
||||
<code>#include <utility></code><br />
|
||||
<code>#include "<a class="el" href="cutlass_8h_source.html">cutlass/cutlass.h</a>"</code><br />
|
||||
</div><div class="textblock"><div class="dynheader">
|
||||
Include dependency graph for platform.h:</div>
|
||||
<div class="dyncontent">
|
||||
<div class="center"><img src="platform_8h__incl.png" border="0" usemap="#platform_8h" alt=""/></div>
|
||||
<map name="platform_8h" id="platform_8h">
|
||||
</map>
|
||||
</div>
|
||||
</div><div class="textblock"><div class="dynheader">
|
||||
This graph shows which files directly or indirectly include this file:</div>
|
||||
<div class="dyncontent">
|
||||
<div class="center"><img src="platform_8h__dep__incl.png" border="0" usemap="#platform_8hdep" alt=""/></div>
|
||||
<map name="platform_8hdep" id="platform_8hdep">
|
||||
</map>
|
||||
</div>
|
||||
</div>
|
||||
<p><a href="platform_8h_source.html">Go to the source code of this file.</a></p>
|
||||
<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  </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1platform_1_1plus.html">cutlass::platform::plus< T ></a></td></tr>
|
||||
<tr class="memdesc:"><td class="mdescLeft"> </td><td class="mdescRight"><a class="el" href="structcutlass_1_1platform_1_1plus.html" title="platform::plus ">platform::plus</a> <a href="structcutlass_1_1platform_1_1plus.html#details">More...</a><br /></td></tr>
|
||||
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct  </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1platform_1_1less.html">cutlass::platform::less< T ></a></td></tr>
|
||||
<tr class="memdesc:"><td class="mdescLeft"> </td><td class="mdescRight">std::less <a href="structcutlass_1_1platform_1_1less.html#details">More...</a><br /></td></tr>
|
||||
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct  </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1platform_1_1greater.html">cutlass::platform::greater< T ></a></td></tr>
|
||||
<tr class="memdesc:"><td class="mdescLeft"> </td><td class="mdescRight">std::greater <a href="structcutlass_1_1platform_1_1greater.html#details">More...</a><br /></td></tr>
|
||||
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
<tr class="memitem:"><td class="memItemLeft" align="right" valign="top">struct  </td><td class="memItemRight" valign="bottom"><a class="el" href="structcutlass_1_1platform_1_1integral__constant.html">cutlass::platform::integral_constant< value_t, V ></a></td></tr>
|
||||
<tr class="memdesc:"><td class="mdescLeft"> </td><td class="mdescRight">std::integral_constant <a href="structcutlass_1_1platform_1_1integral__constant.html#details">More...</a><br /></td></tr>
|
||||
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
|
||||
@@ -439,9 +466,7 @@ Functions</h2></td></tr>
|
||||
</ul>
|
||||
<p>The idea is that, as we drop support for older compilers, we can simply #define the <code>__NV_STD_XYZ</code> macros and <code>platform</code> namespace to alias their C++ counterparts (or trivially find-and-replace their occurrences in code text). </p>
|
||||
</div><h2 class="groupheader">Macro Definition Documentation</h2>
|
||||
<a id="abd31f291635329bc15292954f1f01d38"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#abd31f291635329bc15292954f1f01d38">◆ </a></span>__NV_STD_MAX</h2>
|
||||
|
||||
<a class="anchor" id="abd31f291635329bc15292954f1f01d38"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -467,9 +492,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="a39e234a3e3b0018b58df720bcb143420"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#a39e234a3e3b0018b58df720bcb143420">◆ </a></span>__NV_STD_MIN</h2>
|
||||
|
||||
<a class="anchor" id="a39e234a3e3b0018b58df720bcb143420"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -495,9 +518,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="aece7fe71be5aaf8d12dc9e2372f97de4"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#aece7fe71be5aaf8d12dc9e2372f97de4">◆ </a></span>__platform_cat</h2>
|
||||
|
||||
<a class="anchor" id="aece7fe71be5aaf8d12dc9e2372f97de4"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -523,9 +544,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="acd148999a5caeba8f6fd52e7e288e659"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#acd148999a5caeba8f6fd52e7e288e659">◆ </a></span>__platform_cat_</h2>
|
||||
|
||||
<a class="anchor" id="acd148999a5caeba8f6fd52e7e288e659"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -551,9 +570,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="a72f0657181cca64b44eb186b707eb380"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#a72f0657181cca64b44eb186b707eb380">◆ </a></span>constexpr</h2>
|
||||
|
||||
<a class="anchor" id="a72f0657181cca64b44eb186b707eb380"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -565,9 +582,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="a189faadd7f99f6c354db09acbb2aafcd"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#a189faadd7f99f6c354db09acbb2aafcd">◆ </a></span>noexcept</h2>
|
||||
|
||||
<a class="anchor" id="a189faadd7f99f6c354db09acbb2aafcd"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -579,9 +594,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="ab979d9d4b4923f7c54d6caa6e1a61936"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#ab979d9d4b4923f7c54d6caa6e1a61936">◆ </a></span>nullptr</h2>
|
||||
|
||||
<a class="anchor" id="ab979d9d4b4923f7c54d6caa6e1a61936"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -593,9 +606,7 @@ Functions</h2></td></tr>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<a id="adde4c9ea91b753491851361a4198c009"></a>
|
||||
<h2 class="memtitle"><span class="permalink"><a href="#adde4c9ea91b753491851361a4198c009">◆ </a></span>static_assert</h2>
|
||||
|
||||
<a class="anchor" id="adde4c9ea91b753491851361a4198c009"></a>
|
||||
<div class="memitem">
|
||||
<div class="memproto">
|
||||
<table class="memname">
|
||||
@@ -624,9 +635,9 @@ Functions</h2></td></tr>
|
||||
</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