squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
a8f2c80db0
cutlass/docs/command__line_8h_source.html

130 lines
49 KiB
HTML
Raw Normal View History

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.
2019-11-20 08:55:34 +08:00
<!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: command_line.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&#160;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&#160;List</span></a></li>
<li><a href="globals.html"><span>File&#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="dir_4eeb864c4eec08c7d6b9d3b0352cfdde.html">tools</a></li><li class="navelem"><a class="el" href="dir_88de82f9e8d739a2f42f92d95f0d7933.html">util</a></li><li class="navelem"><a class="el" href="dir_7e9e609009df72bf6226de354e72c328.html">include</a></li><li class="navelem"><a class="el" href="dir_ade2f6ff57439d30f4164e14e54bcf30.html">cutlass</a></li><li class="navelem"><a class="el" href="dir_ff60863f958a43c892071bb1f8a4c81a.html">util</a></li> </ul>
</div>
</div><!-- top -->
<div class="header">
<div class="headertitle">
<div class="title">command_line.h</div> </div>
</div><!--header-->
<div class="contents">
Fix typos 2 (#842) Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
2023-03-10 12:22:56 +08:00
<a href="command__line_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>&#160;<span class="comment">/******************************************************************************</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span>&#160;<span class="comment"> * Copyright (c) 2011-2019, NVIDIA CORPORATION. All rights reserved.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span>&#160;<span class="comment"> * Redistribution and use in source and binary forms, with or without</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span>&#160;<span class="comment"> * modification, are not permitted.</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span>&#160;<span class="comment"> * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS &quot;AS IS&quot; AND</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span>&#160;<span class="comment"> * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span>&#160;<span class="comment"> * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span>&#160;<span class="comment"> * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY</span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span>&#160;<span class="comment"> * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES</span></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span>&#160;<span class="comment"> * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;</span></div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span>&#160;<span class="comment"> * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND</span></div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span>&#160;<span class="comment"> * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT</span></div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span>&#160;<span class="comment"> * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS</span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span>&#160;<span class="comment"> * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span>&#160;<span class="comment"> *</span></div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span>&#160;<span class="comment"> ******************************************************************************/</span></div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span>&#160;</div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span>&#160;<span class="preprocessor">#pragma once</span></div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span>&#160;</div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span>&#160;<span class="preprocessor">#include &lt;iostream&gt;</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span>&#160;<span class="preprocessor">#include &lt;limits&gt;</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span>&#160;<span class="preprocessor">#include &lt;sstream&gt;</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span>&#160;<span class="preprocessor">#include &lt;string&gt;</span><
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.
2019-11-20 08:55:34 +08:00
<div class="ttc" id="structcutlass_1_1CommandLine_html_a206ae1ef3a4cc1a10dabd9d651be50d0"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a206ae1ef3a4cc1a10dabd9d651be50d0">cutlass::CommandLine::get_cmd_line_argument</a></div><div class="ttdeci">void get_cmd_line_argument(const char *arg_name, value_t &amp;val, value_t const &amp;_default=value_t()) const </div><div class="ttdef"><b>Definition:</b> command_line.h:127</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a38f905a17e6c6e7bd2d1bea9e0c72088"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a38f905a17e6c6e7bd2d1bea9e0c72088">cutlass::CommandLine::get_cmd_line_argument_pairs</a></div><div class="ttdeci">void get_cmd_line_argument_pairs(const char *arg_name, std::vector&lt; std::pair&lt; std::string, std::string &gt; &gt; &amp;tokens, char delim= ',', char sep= ':') const </div><div class="ttdef"><b>Definition:</b> command_line.h:169</div></div>
<div class="ttc" id="namespacestd_html"><div class="ttname"><a href="namespacestd.html">std</a></div><div class="ttdoc">STL namespace. </div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a604c5d891f1328b071290d5341119c2c"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a604c5d891f1328b071290d5341119c2c">cutlass::CommandLine::get_cmd_line_arguments</a></div><div class="ttdeci">void get_cmd_line_arguments(const char *arg_name, std::vector&lt; value_t &gt; &amp;vals, char sep= ',') const </div><div class="ttdef"><b>Definition:</b> command_line.h:146</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a440c25cfb006f218ff4705a43320a28b"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a440c25cfb006f218ff4705a43320a28b">cutlass::CommandLine::tokenize</a></div><div class="ttdeci">static void tokenize(std::vector&lt; std::string &gt; &amp;tokens, std::string const &amp;str, char delim= ',', char sep= ':')</div><div class="ttdoc">Tokenizes a comma-delimited list of string pairs delimited by &amp;#39;:&amp;#39;. </div><div class="ttdef"><b>Definition:</b> command_line.h:239</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a5a20785501f9ed3d4a57241b08399552"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a5a20785501f9ed3d4a57241b08399552">cutlass::CommandLine::check_cmd_line_flag</a></div><div class="ttdeci">bool check_cmd_line_flag(const char *arg_name) const </div><div class="ttdef"><b>Definition:</b> command_line.h:81</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a1603f1c65c6d8d3d4262443b40e5c290"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a1603f1c65c6d8d3d4262443b40e5c290">cutlass::CommandLine::keys</a></div><div class="ttdeci">std::vector&lt; std::string &gt; keys</div><div class="ttdef"><b>Definition:</b> command_line.h:45</div></div>
<div class="ttc" id="namespacecutlass_html_a2d34a68d49bf2a35de81b6600425b645"><div class="ttname"><a href="namespacecutlass.html#a2d34a68d49bf2a35de81b6600425b645">cutlass::arg</a></div><div class="ttdeci">CUTLASS_HOST_DEVICE T arg(complex&lt; T &gt; const &amp;z)</div><div class="ttdoc">Returns the magnitude of the complex number. </div><div class="ttdef"><b>Definition:</b> complex.h:319</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a1944da52162e04b12a82ce0c1ade676e"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a1944da52162e04b12a82ce0c1ade676e">cutlass::CommandLine::tokenize</a></div><div class="ttdeci">static void tokenize(std::vector&lt; std::pair&lt; std::string, std::string &gt; &gt; &amp;tokens, std::string const &amp;str, char delim= ',', char sep= ':')</div><div class="ttdoc">Tokenizes a comma-delimited list of string pairs delimited by &amp;#39;:&amp;#39;. </div><div class="ttdef"><b>Definition:</b> command_line.h:211</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a06962a53ee69752551c0353e1eb98d98"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a06962a53ee69752551c0353e1eb98d98">cutlass::CommandLine::get_cmd_line_argument</a></div><div class="ttdeci">void get_cmd_line_argument(int index, value_t &amp;val) const </div><div class="ttdef"><b>Definition:</b> command_line.h:102</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a9ac897e414cfeddad031b1384ffe815e"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a9ac897e414cfeddad031b1384ffe815e">cutlass::CommandLine::get_cmd_line_argument</a></div><div class="ttdeci">void get_cmd_line_argument(const char *arg_name, bool &amp;val, bool _default=true) const </div><div class="ttdef"><b>Definition:</b> command_line.h:113</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a0bee40a3cc6078a08eec5d4ca4711f61"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a0bee40a3cc6078a08eec5d4ca4711f61">cutlass::CommandLine::num_naked_args</a></div><div class="ttdeci">int num_naked_args() const </div><div class="ttdef"><b>Definition:</b> command_line.h:94</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a935f23b162d87148cadb56f9a16e094e"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a935f23b162d87148cadb56f9a16e094e">cutlass::CommandLine::get_cmd_line_argument_ranges</a></div><div class="ttdeci">void get_cmd_line_argument_ranges(const char *arg_name, std::vector&lt; std::vector&lt; std::string &gt; &gt; &amp;vals, char delim= ',', char sep= ':') const </div><div class="ttdef"><b>Definition:</b> command_line.h:185</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_ade127841e9730589f611b618e9440012"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#ade127841e9730589f611b618e9440012">cutlass::CommandLine::values</a></div><div class="ttdeci">std::vector&lt; std::string &gt; values</div><div class="ttdef"><b>Definition:</b> command_line.h:46</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a7156975dc884e8b58b91c710495fc79d"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a7156975dc884e8b58b91c710495fc79d">cutlass::CommandLine::CommandLine</a></div><div class="ttdeci">CommandLine(int argc, const char **argv)</div><div class="ttdef"><b>Definition:</b> command_line.h:52</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html_a6a338671a8d323882f9d9463863eb1c1"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a6a338671a8d323882f9d9463863eb1c1">cutlass::CommandLine::args</a></div><div class="ttdeci">std::vector&lt; std::string &gt; args</div><div class="ttdef"><b>Definition:</b> command_line.h:47</div></div>
<div class="ttc" id="structcutlass_1_1CommandLine_html"><div class="ttname"><a href="structcutlass_1_1CommandLine.html">cutlass::CommandLine</a></div><div class="ttdef"><b>Definition:</b> command_line.h:44</div></div>
Fix typos 2 (#842) Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
2023-03-10 12:22:56 +08:00
<div class="ttc" id="structcutlass_1_1CommandLine_html_a5f86e4b2bd8c44b739c83530d77c5590"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a5f86e4b2bd8c44b739c83530d77c5590">cutlass::CommandLine::separate_string</a></div><div class="ttdeci">static void separate_string(std::string const &amp;str, std::vector&lt; value_t &gt; &amp;vals, char sep= ',')</div><div class="ttdef"><b>Definition:</b> command_line.h:254</div></div>
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.
2019-11-20 08:55:34 +08:00
<div class="ttc" id="structcutlass_1_1CommandLine_html_a228e1a273d223eec4b2f6d73135d3c1e"><div class="ttname"><a href="structcutlass_1_1CommandLine.html#a228e1a273d223eec4b2f6d73135d3c1e">cutlass::CommandLine::parsed_argc</a></div><div class="ttdeci">int parsed_argc() const </div><div class="ttdef"><b>Definition:</b> command_line.h:204</div></div>
</div><!-- fragment --></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>
Reference in New Issue Copy Permalink