123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265 |
- <html>
- <head>
- <meta http-equiv="Content-Type" content="text/html; charset=US-ASCII">
- <title>Performance considerations</title>
- <link rel="stylesheet" href="../../../../../../doc/src/boostbook.css" type="text/css">
- <meta name="generator" content="DocBook XSL Stylesheets V1.79.1">
- <link rel="home" href="../../index.html" title="Boost.Optional">
- <link rel="up" href="../../optional/tutorial.html" title="Tutorial">
- <link rel="prev" href="type_requirements.html" title="Type requirements">
- <link rel="next" href="../../optional/reference.html" title="Reference">
- </head>
- <body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
- <table cellpadding="2" width="100%"><tr>
- <td valign="top"><img alt="Boost C++ Libraries" width="277" height="86" src="../../../../../../boost.png"></td>
- <td align="center"><a href="../../../../../../index.html">Home</a></td>
- <td align="center"><a href="../../../../../../libs/libraries.htm">Libraries</a></td>
- <td align="center"><a href="http://www.boost.org/users/people.html">People</a></td>
- <td align="center"><a href="http://www.boost.org/users/faq.html">FAQ</a></td>
- <td align="center"><a href="../../../../../../more/index.htm">More</a></td>
- </tr></table>
- <hr>
- <div class="spirit-nav">
- <a accesskey="p" href="type_requirements.html"><img src="../../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../../optional/tutorial.html"><img src="../../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../../index.html"><img src="../../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="../../optional/reference.html"><img src="../../../../../../doc/src/images/next.png" alt="Next"></a>
- </div>
- <div class="section">
- <div class="titlepage"><div><div><h3 class="title">
- <a name="boost_optional.tutorial.performance_considerations"></a><a class="link" href="performance_considerations.html" title="Performance considerations">Performance
- considerations</a>
- </h3></div></div></div>
- <p>
- Technical details aside, the memory layout of <code class="computeroutput"><span class="identifier">optional</span><span class="special"><</span><span class="identifier">T</span><span class="special">></span></code>
- for a generic <code class="computeroutput"><span class="identifier">T</span></code> is more-less
- this:
- </p>
- <pre class="programlisting"><span class="keyword">template</span> <span class="special"><</span><span class="keyword">typename</span> <span class="identifier">T</span><span class="special">></span>
- <span class="keyword">class</span> <span class="identifier">optional</span>
- <span class="special">{</span>
- <span class="keyword">bool</span> <span class="identifier">_initialized</span><span class="special">;</span>
- <span class="identifier">std</span><span class="special">::</span><span class="identifier">aligned_storage_t</span><span class="special"><</span><span class="keyword">sizeof</span><span class="special">(</span><span class="identifier">t</span><span class="special">),</span> <span class="keyword">alignof</span><span class="special">(</span><span class="identifier">T</span><span class="special">)></span> <span class="identifier">_storage</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- Lifetime of the <code class="computeroutput"><span class="identifier">T</span></code> inside
- <code class="computeroutput"><span class="identifier">_storage</span></code> is manually controlled
- with placement-<code class="computeroutput"><span class="keyword">new</span></code>s and pseudo-destructor
- calls. However, for scalar <code class="computeroutput"><span class="identifier">T</span></code>s
- we use a different way of storage, by simply holding a <code class="computeroutput"><span class="identifier">T</span></code>:
- </p>
- <pre class="programlisting"><span class="keyword">template</span> <span class="special"><</span><span class="keyword">typename</span> <span class="identifier">T</span><span class="special">></span>
- <span class="keyword">class</span> <span class="identifier">optional</span>
- <span class="special">{</span>
- <span class="keyword">bool</span> <span class="identifier">_initialized</span><span class="special">;</span>
- <span class="identifier">T</span> <span class="identifier">_storage</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- We call it a <span class="emphasis"><em>direct</em></span> storage. This makes <code class="computeroutput"><span class="identifier">optional</span><span class="special"><</span><span class="identifier">T</span><span class="special">></span></code> a
- trivially-copyable type for scalar <code class="computeroutput"><span class="identifier">T</span></code>s.
- This only works for compilers that support defaulted functions (including
- defaulted move assignment and constructor). On compilers without defaulted
- functions we still use the direct storage, but <code class="computeroutput"><span class="identifier">optional</span><span class="special"><</span><span class="identifier">T</span><span class="special">></span></code>
- is no longer recognized as trivially-copyable. Apart from scalar types, we
- leave the programmer a way of customizing her type, so that it is reconized
- by <code class="computeroutput"><span class="identifier">optional</span></code> as candidate
- for optimized storage, by specializing type trait <code class="computeroutput"><span class="identifier">boost</span><span class="special">::</span><span class="identifier">opitonal_config</span><span class="special">::</span><span class="identifier">optional_uses_direct_storage_for</span></code>:
- </p>
- <pre class="programlisting"><span class="keyword">struct</span> <span class="identifier">X</span> <span class="comment">// not trivial</span>
- <span class="special">{</span>
- <span class="identifier">X</span><span class="special">()</span> <span class="special">{}</span>
- <span class="special">};</span>
- <span class="keyword">namespace</span> <span class="identifier">boost</span> <span class="special">{</span> <span class="keyword">namespace</span> <span class="identifier">optional_config</span> <span class="special">{</span>
- <span class="keyword">template</span> <span class="special"><></span> <span class="keyword">struct</span> <span class="identifier">optional_uses_direct_storage_for</span><span class="special"><</span><span class="identifier">X</span><span class="special">></span> <span class="special">:</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">true_type</span> <span class="special">{};</span>
- <span class="special">}}</span>
- </pre>
- <h5>
- <a name="boost_optional.tutorial.performance_considerations.h0"></a>
- <span class="phrase"><a name="boost_optional.tutorial.performance_considerations.controlling_the_size"></a></span><a class="link" href="performance_considerations.html#boost_optional.tutorial.performance_considerations.controlling_the_size">Controlling
- the size</a>
- </h5>
- <p>
- For the purpose of the following analysis, considering memory layouts, we
- can think of it as:
- </p>
- <pre class="programlisting"><span class="keyword">template</span> <span class="special"><</span><span class="keyword">typename</span> <span class="identifier">T</span><span class="special">></span>
- <span class="keyword">class</span> <span class="identifier">optional</span>
- <span class="special">{</span>
- <span class="keyword">bool</span> <span class="identifier">_initialized</span><span class="special">;</span>
- <span class="identifier">T</span> <span class="identifier">_storage</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- Given type <code class="computeroutput"><span class="identifier">optional</span><span class="special"><</span><span class="keyword">int</span><span class="special">></span></code>, and
- assuming that <code class="computeroutput"><span class="keyword">sizeof</span><span class="special">(</span><span class="keyword">int</span><span class="special">)</span> <span class="special">==</span>
- <span class="number">4</span></code>, we will get <code class="computeroutput"><span class="keyword">sizeof</span><span class="special">(</span><span class="identifier">optional</span><span class="special"><</span><span class="keyword">int</span><span class="special">>)</span>
- <span class="special">==</span> <span class="number">8</span></code>.
- This is so because of the alignment rules, for our two members we get the
- following alignment:
- </p>
- <p>
- <span class="inlinemediaobject"><img src="../../images/opt_align1.png" alt="opt_align1"></span>
- </p>
- <p>
- This means you can fit twice as many <code class="computeroutput"><span class="keyword">int</span></code>s
- as <code class="computeroutput"><span class="identifier">optional</span><span class="special"><</span><span class="keyword">int</span><span class="special">></span></code>s into
- the same space of memory. Therefore, if the size of the objects is critical
- for your application (e.g., because you want to utilize your CPU cache in
- order to gain performance) and you have determined you are willing to trade
- the code clarity, it is recommended that you simply go with type <code class="computeroutput"><span class="keyword">int</span></code> and use some 'magic value' to represent
- <span class="emphasis"><em>not-an-int</em></span>, or use something like <a href="https://github.com/akrzemi1/markable" target="_top"><code class="computeroutput"><span class="identifier">markable</span></code></a> library.
- </p>
- <p>
- Even if you cannot spare any value of <code class="computeroutput"><span class="keyword">int</span></code>
- to represent <span class="emphasis"><em>not-an-int</em></span> (e.g., because every value is
- useful, or you do want to signal <span class="emphasis"><em>not-an-int</em></span> explicitly),
- at least for <code class="computeroutput"><span class="identifier">Trivial</span></code> types
- you should consider storing the value and the <code class="computeroutput"><span class="keyword">bool</span></code>
- flag representing the <span class="emphasis"><em>null-state</em></span> separately. Consider
- the following class:
- </p>
- <pre class="programlisting"><span class="keyword">struct</span> <span class="identifier">Record</span>
- <span class="special">{</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="keyword">int</span><span class="special">></span> <span class="identifier">_min</span><span class="special">;</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="keyword">int</span><span class="special">></span> <span class="identifier">_max</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- Its memory layout can be depicted as follows:
- </p>
- <p>
- <span class="inlinemediaobject"><img src="../../images/opt_align2.png" alt="opt_align2"></span>
- </p>
- <p>
- This is exactly the same as if we had the following members:
- </p>
- <pre class="programlisting"><span class="keyword">struct</span> <span class="identifier">Record</span>
- <span class="special">{</span>
- <span class="keyword">bool</span> <span class="identifier">_has_min</span><span class="special">;</span>
- <span class="keyword">int</span> <span class="identifier">_min</span><span class="special">;</span>
- <span class="keyword">bool</span> <span class="identifier">_has_max</span><span class="special">;</span>
- <span class="keyword">int</span> <span class="identifier">_max</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- But when they are stored separately, we at least have an option to reorder
- them like this:
- </p>
- <pre class="programlisting"><span class="keyword">struct</span> <span class="identifier">Record</span>
- <span class="special">{</span>
- <span class="keyword">bool</span> <span class="identifier">_has_min</span><span class="special">;</span>
- <span class="keyword">bool</span> <span class="identifier">_has_max</span><span class="special">;</span>
- <span class="keyword">int</span> <span class="identifier">_min</span><span class="special">;</span>
- <span class="keyword">int</span> <span class="identifier">_max</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- Which gives us the following layout (and smaller total size):
- </p>
- <p>
- <span class="inlinemediaobject"><img src="../../images/opt_align3.png" alt="opt_align3"></span>
- </p>
- <p>
- Sometimes it requires detailed consideration what data we make optional.
- In our case above, if we determine that both minimum and maximum value can
- be provided or not provided together, but one is never provided without the
- other, we can make only one optional memebr:
- </p>
- <pre class="programlisting"><span class="keyword">struct</span> <span class="identifier">Limits</span>
- <span class="special">{</span>
- <span class="keyword">int</span> <span class="identifier">_min</span><span class="special">;</span>
- <span class="keyword">int</span> <span class="identifier">_max</span><span class="special">;</span>
- <span class="special">};</span>
- <span class="keyword">struct</span> <span class="identifier">Record</span>
- <span class="special">{</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="identifier">Limits</span><span class="special">></span> <span class="identifier">_limits</span><span class="special">;</span>
- <span class="special">};</span>
- </pre>
- <p>
- This would give us the following layout:
- </p>
- <p>
- <span class="inlinemediaobject"><img src="../../images/opt_align4.png" alt="opt_align4"></span>
- </p>
- <h5>
- <a name="boost_optional.tutorial.performance_considerations.h1"></a>
- <span class="phrase"><a name="boost_optional.tutorial.performance_considerations.optional_function_parameters"></a></span><a class="link" href="performance_considerations.html#boost_optional.tutorial.performance_considerations.optional_function_parameters">Optional
- function parameters</a>
- </h5>
- <p>
- Having function parameters of type <code class="computeroutput"><span class="keyword">const</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="identifier">T</span><span class="special">>&</span></code>
- may incur certain unexpected run-time cost connected to copy construction
- of <code class="computeroutput"><span class="identifier">T</span></code>. Consider the following
- code.
- </p>
- <pre class="programlisting"><span class="keyword">void</span> <span class="identifier">fun</span><span class="special">(</span><span class="keyword">const</span> <span class="identifier">optional</span><span class="special"><</span><span class="identifier">Big</span><span class="special">>&</span> <span class="identifier">v</span><span class="special">)</span>
- <span class="special">{</span>
- <span class="keyword">if</span> <span class="special">(</span><span class="identifier">v</span><span class="special">)</span> <span class="identifier">doSomethingWith</span><span class="special">(*</span><span class="identifier">v</span><span class="special">);</span>
- <span class="keyword">else</span> <span class="identifier">doSomethingElse</span><span class="special">();</span>
- <span class="special">}</span>
- <span class="keyword">int</span> <span class="identifier">main</span><span class="special">()</span>
- <span class="special">{</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="identifier">Big</span><span class="special">></span> <span class="identifier">ov</span><span class="special">;</span>
- <span class="identifier">Big</span> <span class="identifier">v</span><span class="special">;</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">none</span><span class="special">);</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">ov</span><span class="special">);</span> <span class="comment">// no copy</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">v</span><span class="special">);</span> <span class="comment">// copy constructor of Big</span>
- <span class="special">}</span>
- </pre>
- <p>
- No copy elision or move semantics can save us from copying type <code class="computeroutput"><span class="identifier">Big</span></code> here. Not that we need any copy, but
- this is how <code class="computeroutput"><span class="identifier">optional</span></code> works.
- In order to avoid copying in this case, one could provide second overload
- of <code class="computeroutput"><span class="identifier">fun</span></code>:
- </p>
- <pre class="programlisting"><span class="keyword">void</span> <span class="identifier">fun</span><span class="special">(</span><span class="keyword">const</span> <span class="identifier">Big</span><span class="special">&</span> <span class="identifier">v</span><span class="special">)</span>
- <span class="special">{</span>
- <span class="identifier">doSomethingWith</span><span class="special">(</span><span class="identifier">v</span><span class="special">);</span>
- <span class="special">}</span>
- <span class="keyword">int</span> <span class="identifier">main</span><span class="special">()</span>
- <span class="special">{</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="identifier">Big</span><span class="special">></span> <span class="identifier">ov</span><span class="special">;</span>
- <span class="identifier">Big</span> <span class="identifier">v</span><span class="special">;</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">ov</span><span class="special">);</span> <span class="comment">// no copy</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">v</span><span class="special">);</span> <span class="comment">// no copy: second overload selected</span>
- <span class="special">}</span>
- </pre>
- <p>
- Alternatively, you could consider using an optional reference instead:
- </p>
- <pre class="programlisting"><span class="keyword">void</span> <span class="identifier">fun</span><span class="special">(</span><span class="identifier">optional</span><span class="special"><</span><span class="keyword">const</span> <span class="identifier">Big</span><span class="special">&></span> <span class="identifier">v</span><span class="special">)</span> <span class="comment">// note where the reference is</span>
- <span class="special">{</span>
- <span class="keyword">if</span> <span class="special">(</span><span class="identifier">v</span><span class="special">)</span> <span class="identifier">doSomethingWith</span><span class="special">(*</span><span class="identifier">v</span><span class="special">);</span>
- <span class="keyword">else</span> <span class="identifier">doSomethingElse</span><span class="special">();</span>
- <span class="special">}</span>
- <span class="keyword">int</span> <span class="identifier">main</span><span class="special">()</span>
- <span class="special">{</span>
- <span class="identifier">optional</span><span class="special"><</span><span class="identifier">Big</span><span class="special">></span> <span class="identifier">ov</span><span class="special">;</span>
- <span class="identifier">Big</span> <span class="identifier">v</span><span class="special">;</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">none</span><span class="special">);</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">ov</span><span class="special">);</span> <span class="comment">// doesn't compile</span>
- <span class="identifier">fun</span><span class="special">(</span><span class="identifier">v</span><span class="special">);</span> <span class="comment">// no copy</span>
- <span class="special">}</span>
- </pre>
- </div>
- <table xmlns:rev="http://www.cs.rpi.edu/~gregod/boost/tools/doc/revision" width="100%"><tr>
- <td align="left"></td>
- <td align="right"><div class="copyright-footer">Copyright © 2003-2007 Fernando Luis Cacciola Carballal<br>Copyright © 2014-2018 Andrzej Krzemieński<p>
- Distributed under the Boost Software License, Version 1.0. (See accompanying
- file LICENSE_1_0.txt or copy at <a href="http://www.boost.org/LICENSE_1_0.txt" target="_top">http://www.boost.org/LICENSE_1_0.txt</a>)
- </p>
- </div></td>
- </tr></table>
- <hr>
- <div class="spirit-nav">
- <a accesskey="p" href="type_requirements.html"><img src="../../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../../optional/tutorial.html"><img src="../../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../../index.html"><img src="../../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="../../optional/reference.html"><img src="../../../../../../doc/src/images/next.png" alt="Next"></a>
- </div>
- </body>
- </html>
|