You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
144 lines
7.7 KiB
HTML
144 lines
7.7 KiB
HTML
4 years ago
|
<html lang="en">
|
||
|
|
<head>
|
||
|
|
<title>Profile information - GNU Compiler Collection (GCC) Internals</title>
|
||
|
|
<meta http-equiv="Content-Type" content="text/html">
|
||
|
|
<meta name="description" content="GNU Compiler Collection (GCC) Internals">
|
||
|
|
<meta name="generator" content="makeinfo 4.13">
|
||
|
|
<link title="Top" rel="start" href="index.html#Top">
|
||
|
|
<link rel="up" href="Control-Flow.html#Control-Flow" title="Control Flow">
|
||
|
|
<link rel="prev" href="Edges.html#Edges" title="Edges">
|
||
|
|
<link rel="next" href="Maintaining-the-CFG.html#Maintaining-the-CFG" title="Maintaining the CFG">
|
||
|
|
<link href="http://www.gnu.org/software/texinfo/" rel="generator-home" title="Texinfo Homepage">
|
||
|
|
<!--
|
||
|
|
Copyright (C) 1988-2015 Free Software Foundation, Inc.
|
||
|
|
|
||
|
|
Permission is granted to copy, distribute and/or modify this document
|
||
|
|
under the terms of the GNU Free Documentation License, Version 1.3 or
|
||
|
|
any later version published by the Free Software Foundation; with the
|
||
|
|
Invariant Sections being ``Funding Free Software'', the Front-Cover
|
||
|
|
Texts being (a) (see below), and with the Back-Cover Texts being (b)
|
||
|
|
(see below). A copy of the license is included in the section entitled
|
||
|
|
``GNU Free Documentation License''.
|
||
|
|
|
||
|
|
(a) The FSF's Front-Cover Text is:
|
||
|
|
|
||
|
|
A GNU Manual
|
||
|
|
|
||
|
|
(b) The FSF's Back-Cover Text is:
|
||
|
|
|
||
|
|
You have freedom to copy and modify this GNU Manual, like GNU
|
||
|
|
software. Copies published by the Free Software Foundation raise
|
||
|
|
funds for GNU development.-->
|
||
|
|
<meta http-equiv="Content-Style-Type" content="text/css">
|
||
|
|
<style type="text/css"><!--
|
||
|
|
pre.display { font-family:inherit }
|
||
|
|
pre.format { font-family:inherit }
|
||
|
|
pre.smalldisplay { font-family:inherit; font-size:smaller }
|
||
|
|
pre.smallformat { font-family:inherit; font-size:smaller }
|
||
|
|
pre.smallexample { font-size:smaller }
|
||
|
|
pre.smalllisp { font-size:smaller }
|
||
|
|
span.sc { font-variant:small-caps }
|
||
|
|
span.roman { font-family:serif; font-weight:normal; }
|
||
|
|
span.sansserif { font-family:sans-serif; font-weight:normal; }
|
||
|
|
--></style>
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
<div class="node">
|
||
|
|
<a name="Profile-information"></a>
|
||
|
|
<p>
|
||
|
|
Next: <a rel="next" accesskey="n" href="Maintaining-the-CFG.html#Maintaining-the-CFG">Maintaining the CFG</a>,
|
||
|
|
Previous: <a rel="previous" accesskey="p" href="Edges.html#Edges">Edges</a>,
|
||
|
|
Up: <a rel="up" accesskey="u" href="Control-Flow.html#Control-Flow">Control Flow</a>
|
||
|
|
<hr>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<h3 class="section">14.3 Profile information</h3>
|
||
|
|
|
||
|
|
<p><a name="index-profile-representation-3194"></a>In many cases a compiler must make a choice whether to trade speed in
|
||
|
|
one part of code for speed in another, or to trade code size for code
|
||
|
|
speed. In such cases it is useful to know information about how often
|
||
|
|
some given block will be executed. That is the purpose for
|
||
|
|
maintaining profile within the flow graph.
|
||
|
|
GCC can handle profile information obtained through <dfn>profile
|
||
|
|
feedback</dfn>, but it can also estimate branch probabilities based on
|
||
|
|
statics and heuristics.
|
||
|
|
|
||
|
|
<p><a name="index-profile-feedback-3195"></a>The feedback based profile is produced by compiling the program with
|
||
|
|
instrumentation, executing it on a train run and reading the numbers
|
||
|
|
of executions of basic blocks and edges back to the compiler while
|
||
|
|
re-compiling the program to produce the final executable. This method
|
||
|
|
provides very accurate information about where a program spends most
|
||
|
|
of its time on the train run. Whether it matches the average run of
|
||
|
|
course depends on the choice of train data set, but several studies
|
||
|
|
have shown that the behavior of a program usually changes just
|
||
|
|
marginally over different data sets.
|
||
|
|
|
||
|
|
<p><a name="index-Static-profile-estimation-3196"></a><a name="index-branch-prediction-3197"></a><a name="index-predict_002edef-3198"></a>When profile feedback is not available, the compiler may be asked to
|
||
|
|
attempt to predict the behavior of each branch in the program using a
|
||
|
|
set of heuristics (see <samp><span class="file">predict.def</span></samp> for details) and compute
|
||
|
|
estimated frequencies of each basic block by propagating the
|
||
|
|
probabilities over the graph.
|
||
|
|
|
||
|
|
<p><a name="index-frequency_002c-count_002c-BB_005fFREQ_005fBASE-3199"></a>Each <code>basic_block</code> contains two integer fields to represent
|
||
|
|
profile information: <code>frequency</code> and <code>count</code>. The
|
||
|
|
<code>frequency</code> is an estimation how often is basic block executed
|
||
|
|
within a function. It is represented as an integer scaled in the
|
||
|
|
range from 0 to <code>BB_FREQ_BASE</code>. The most frequently executed
|
||
|
|
basic block in function is initially set to <code>BB_FREQ_BASE</code> and
|
||
|
|
the rest of frequencies are scaled accordingly. During optimization,
|
||
|
|
the frequency of the most frequent basic block can both decrease (for
|
||
|
|
instance by loop unrolling) or grow (for instance by cross-jumping
|
||
|
|
optimization), so scaling sometimes has to be performed multiple
|
||
|
|
times.
|
||
|
|
|
||
|
|
<p><a name="index-gcov_005ftype-3200"></a>The <code>count</code> contains hard-counted numbers of execution measured
|
||
|
|
during training runs and is nonzero only when profile feedback is
|
||
|
|
available. This value is represented as the host's widest integer
|
||
|
|
(typically a 64 bit integer) of the special type <code>gcov_type</code>.
|
||
|
|
|
||
|
|
<p>Most optimization passes can use only the frequency information of a
|
||
|
|
basic block, but a few passes may want to know hard execution counts.
|
||
|
|
The frequencies should always match the counts after scaling, however
|
||
|
|
during updating of the profile information numerical error may
|
||
|
|
accumulate into quite large errors.
|
||
|
|
|
||
|
|
<p><a name="index-REG_005fBR_005fPROB_005fBASE_002c-EDGE_005fFREQUENCY-3201"></a>Each edge also contains a branch probability field: an integer in the
|
||
|
|
range from 0 to <code>REG_BR_PROB_BASE</code>. It represents probability of
|
||
|
|
passing control from the end of the <code>src</code> basic block to the
|
||
|
|
<code>dest</code> basic block, i.e. the probability that control will flow
|
||
|
|
along this edge. The <code>EDGE_FREQUENCY</code> macro is available to
|
||
|
|
compute how frequently a given edge is taken. There is a <code>count</code>
|
||
|
|
field for each edge as well, representing same information as for a
|
||
|
|
basic block.
|
||
|
|
|
||
|
|
<p>The basic block frequencies are not represented in the instruction
|
||
|
|
stream, but in the RTL representation the edge frequencies are
|
||
|
|
represented for conditional jumps (via the <code>REG_BR_PROB</code>
|
||
|
|
macro) since they are used when instructions are output to the
|
||
|
|
assembly file and the flow graph is no longer maintained.
|
||
|
|
|
||
|
|
<p><a name="index-reverse-probability-3202"></a>The probability that control flow arrives via a given edge to its
|
||
|
|
destination basic block is called <dfn>reverse probability</dfn> and is not
|
||
|
|
directly represented, but it may be easily computed from frequencies
|
||
|
|
of basic blocks.
|
||
|
|
|
||
|
|
<p><a name="index-redirect_005fedge_005fand_005fbranch-3203"></a>Updating profile information is a delicate task that can unfortunately
|
||
|
|
not be easily integrated with the CFG manipulation API. Many of the
|
||
|
|
functions and hooks to modify the CFG, such as
|
||
|
|
<code>redirect_edge_and_branch</code>, do not have enough information to
|
||
|
|
easily update the profile, so updating it is in the majority of cases
|
||
|
|
left up to the caller. It is difficult to uncover bugs in the profile
|
||
|
|
updating code, because they manifest themselves only by producing
|
||
|
|
worse code, and checking profile consistency is not possible because
|
||
|
|
of numeric error accumulation. Hence special attention needs to be
|
||
|
|
given to this issue in each pass that modifies the CFG.
|
||
|
|
|
||
|
|
<p><a name="index-REG_005fBR_005fPROB_005fBASE_002c-BB_005fFREQ_005fBASE_002c-count-3204"></a>It is important to point out that <code>REG_BR_PROB_BASE</code> and
|
||
|
|
<code>BB_FREQ_BASE</code> are both set low enough to be possible to compute
|
||
|
|
second power of any frequency or probability in the flow graph, it is
|
||
|
|
not possible to even square the <code>count</code> field, as modern CPUs are
|
||
|
|
fast enough to execute $2^32$ operations quickly.
|
||
|
|
|
||
|
|
</body></html>
|
||
|
|
|