leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

CUTLASS 2.0 (#62)

Browse Source 
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:
Andrew Kerr
2019-11-19 16:55:34 -08:00
committed by GitHub
parent b5cab177a9
commit fb335f6a5f
5434 changed files with 599799 additions and 250176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

106
docs/namespaces.html
View File

@@ -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: Namespace List</title>
<meta name="generator" content="Doxygen 1.8.11"/>
<title>CUTLASS: Namespace List</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&amp;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&amp;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&#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 class="current"><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>
</div><!-- top -->
<!-- window showing the filter options -->
<div id="MSearchSelectWindow"
@@ -73,21 +95,53 @@ $(function() {
</div><!--header-->
<div class="contents">
<div class="textblock">Here is a list of all namespaces with brief descriptions:</div><div class="directory">
<div class="levels">[detail level <span onclick="javascript:toggleLevel(1);">1</span><span onclick="javascript:toggleLevel(2);">2</span>]</div><table class="directory">
<div class="levels">[detail level <span onclick="javascript:toggleLevel(1);">1</span><span onclick="javascript:toggleLevel(2);">2</span><span onclick="javascript:toggleLevel(3);">3</span><span onclick="javascript:toggleLevel(4);">4</span><span onclick="javascript:toggleLevel(5);">5</span>]</div><table class="directory">
<tr id="row_0_" class="even"><td class="entry"><span style="width:0px;display:inline-block;">&#160;</span><span id="arr_0_" class="arrow" onclick="toggleFolder('0_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass.html" target="_self">cutlass</a></td><td class="desc"></td></tr>
<tr id="row_0_0_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_1_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm.html" target="_self">gemm</a></td><td class="desc"></td></tr>
<tr id="row_0_2_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1MatrixLayout.html" target="_self">MatrixLayout</a></td><td class="desc">Defines data layouts of various matrix formats usable by <a class="el" href="classcutlass_1_1TensorRef.html">TensorRef</a> and other classes </td></tr>
<tr id="row_0_3_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1platform.html" target="_self">platform</a></td><td class="desc"></td></tr>
<tr id="row_0_4_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reduction.html" target="_self">reduction</a></td><td class="desc"></td></tr>
<tr id="row_0_0_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1arch.html" target="_self">arch</a></td><td class="desc"></td></tr>
<tr id="row_0_1_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1debug.html" target="_self">debug</a></td><td class="desc"></td></tr>
<tr id="row_0_2_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_3_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1device__memory.html" target="_self">device_memory</a></td><td class="desc"></td></tr>
<tr id="row_0_4_"><td class="entry"><span style="width:16px;display:inline-block;">&#160;</span><span id="arr_0_4_" class="arrow" onclick="toggleFolder('0_4_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1epilogue.html" target="_self">epilogue</a></td><td class="desc"></td></tr>
<tr id="row_0_4_0_" class="even"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1epilogue_1_1thread.html" target="_self">thread</a></td><td class="desc"></td></tr>
<tr id="row_0_4_1_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span id="arr_0_4_1_" class="arrow" onclick="toggleFolder('0_4_1_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1epilogue_1_1threadblock.html" target="_self">threadblock</a></td><td class="desc"></td></tr>
<tr id="row_0_4_1_0_" class="even"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1epilogue_1_1threadblock_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_4_2_"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1epilogue_1_1warp.html" target="_self">warp</a></td><td class="desc"></td></tr>
<tr id="row_0_5_" class="even"><td class="entry"><span style="width:16px;display:inline-block;">&#160;</span><span id="arr_0_5_" class="arrow" onclick="toggleFolder('0_5_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm.html" target="_self">gemm</a></td><td class="desc"></td></tr>
<tr id="row_0_5_0_"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1device.html" target="_self">device</a></td><td class="desc"></td></tr>
<tr id="row_0_5_1_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span id="arr_0_5_1_" class="arrow" onclick="toggleFolder('0_5_1_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1kernel.html" target="_self">kernel</a></td><td class="desc"></td></tr>
<tr id="row_0_5_1_0_"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1kernel_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_5_2_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span id="arr_0_5_2_" class="arrow" onclick="toggleFolder('0_5_2_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1thread.html" target="_self">thread</a></td><td class="desc"></td></tr>
<tr id="row_0_5_2_0_"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1thread_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_5_3_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span id="arr_0_5_3_" class="arrow" onclick="toggleFolder('0_5_3_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1threadblock.html" target="_self">threadblock</a></td><td class="desc"></td></tr>
<tr id="row_0_5_3_0_"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1threadblock_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_5_4_" class="even"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1gemm_1_1warp.html" target="_self">warp</a></td><td class="desc"></td></tr>
<tr id="row_0_6_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1layout.html" target="_self">layout</a></td><td class="desc"></td></tr>
<tr id="row_0_7_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1library.html" target="_self">library</a></td><td class="desc"></td></tr>
<tr id="row_0_8_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1platform.html" target="_self">platform</a></td><td class="desc"></td></tr>
<tr id="row_0_9_" class="even"><td class="entry"><span style="width:16px;display:inline-block;">&#160;</span><span id="arr_0_9_" class="arrow" onclick="toggleFolder('0_9_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reduction.html" target="_self">reduction</a></td><td class="desc"></td></tr>
<tr id="row_0_9_0_"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reduction_1_1kernel.html" target="_self">kernel</a></td><td class="desc"></td></tr>
<tr id="row_0_9_1_" class="even"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reduction_1_1thread.html" target="_self">thread</a></td><td class="desc"></td></tr>
<tr id="row_0_10_"><td class="entry"><span style="width:16px;display:inline-block;">&#160;</span><span id="arr_0_10_" class="arrow" onclick="toggleFolder('0_10_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference.html" target="_self">reference</a></td><td class="desc"></td></tr>
<tr id="row_0_10_0_" class="even"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_10_1_"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span id="arr_0_10_1_" class="arrow" onclick="toggleFolder('0_10_1_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1device.html" target="_self">device</a></td><td class="desc"></td></tr>
<tr id="row_0_10_1_0_" class="even"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1device_1_1detail.html" target="_self">detail</a></td><td class="desc"></td></tr>
<tr id="row_0_10_1_1_"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span id="arr_0_10_1_1_" class="arrow" onclick="toggleFolder('0_10_1_1_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1device_1_1kernel.html" target="_self">kernel</a></td><td class="desc"></td></tr>
<tr id="row_0_10_1_1_0_" class="even"><td class="entry"><span style="width:80px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1device_1_1kernel_1_1detail.html" target="_self">detail</a></td><td class="desc">Defines several helpers </td></tr>
<tr id="row_0_10_1_2_"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1device_1_1thread.html" target="_self">thread</a></td><td class="desc"></td></tr>
<tr id="row_0_10_2_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span id="arr_0_10_2_" class="arrow" onclick="toggleFolder('0_10_2_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1host.html" target="_self">host</a></td><td class="desc"></td></tr>
<tr id="row_0_10_2_0_"><td class="entry"><span style="width:64px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1reference_1_1host_1_1detail.html" target="_self">detail</a></td><td class="desc">Defines several helpers </td></tr>
<tr id="row_0_11_" class="even"><td class="entry"><span style="width:32px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1thread.html" target="_self">thread</a></td><td class="desc"></td></tr>
<tr id="row_0_12_"><td class="entry"><span style="width:16px;display:inline-block;">&#160;</span><span id="arr_0_12_" class="arrow" onclick="toggleFolder('0_12_')">&#9660;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1transform.html" target="_self">transform</a></td><td class="desc"></td></tr>
<tr id="row_0_12_0_" class="even"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1transform_1_1thread.html" target="_self">thread</a></td><td class="desc"></td></tr>
<tr id="row_0_12_1_"><td class="entry"><span style="width:48px;display:inline-block;">&#160;</span><span class="icona"><span class="icon">N</span></span><a class="el" href="namespacecutlass_1_1transform_1_1threadblock.html" target="_self">threadblock</a></td><td class="desc"></td></tr>
</table>
</div><!-- directory -->
</div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
Generated on Fri Oct 26 2018 14:53:40 for Cutlass by &#160;<a href="http://www.doxygen.org/index.html">
Generated by &#160;<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>