cachegrind/docs/cg-manual.xml

<?xml version="1.0"?> <!-- -*- sgml -*- -->
<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.2//EN"
  "http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd"
[ <!ENTITY % vg-entities SYSTEM "../../docs/xml/vg-entities.xml"> %vg-entities; ]>


<chapter id="cg-manual" xreflabel="Cachegrind: a cache and branch-prediction profiler">
<title>Cachegrind: a cache and branch-prediction profiler</title>

<para>To use this tool, you must specify
<option>--tool=cachegrind</option> on the
Valgrind command line.</para>

<sect1 id="cg-manual.overview" xreflabel="Overview">
<title>Overview</title>

<para>Cachegrind simulates how your program interacts with a machine's cache
hierarchy and (optionally) branch predictor.  It simulates a machine with
independent first level instruction and data caches (I1 and D1), backed by a
unified second level cache (L2).  This configuration is used by almost all
modern machines.</para>

<para>
It gathers the following statistics (abbreviations used for each statistic
is given in parentheses):</para>
<itemizedlist>
  <listitem>
    <para>I cache reads (<computeroutput>Ir</computeroutput>,
    which equals the number of instructions executed),
    I1 cache read misses (<computeroutput>I1mr</computeroutput>) and
    L2 cache instruction read misses (<computeroutput>I1mr</computeroutput>).
    </para>
  </listitem>
  <listitem>
    <para>D cache reads (<computeroutput>Dr</computeroutput>, which
    equals the number of memory reads),
    D1 cache read misses (<computeroutput>D1mr</computeroutput>), and
    L2 cache data read misses (<computeroutput>D2mr</computeroutput>).
    </para>
  </listitem>
  <listitem>
    <para>D cache writes (<computeroutput>Dw</computeroutput>, which equals
    the number of memory writes),
    D1 cache write misses (<computeroutput>D1mw</computeroutput>), and
    L2 cache data write misses (<computeroutput>D2mw</computeroutput>).
    </para>
  </listitem>
  <listitem>
    <para>Conditional branches executed (<computeroutput>Bc</computeroutput>) and
    conditional branches mispredicted (<computeroutput>Bcm</computeroutput>).
    </para>
  </listitem>
  <listitem>
    <para>Indirect branches executed (<computeroutput>Bi</computeroutput>) and
    indirect branches mispredicted (<computeroutput>Bim</computeroutput>).
    </para>
  </listitem>
</itemizedlist>

<para>Note that D1 total accesses is given by
<computeroutput>D1mr</computeroutput> +
<computeroutput>D1mw</computeroutput>, and that L2 total
accesses is given by <computeroutput>I2mr</computeroutput> +
<computeroutput>D2mr</computeroutput> +
<computeroutput>D2mw</computeroutput>.
</para>

<para>These statistics are presented for the entire program and for each
function in the program.  You can also annotate each line of source code in
the program with the counts that were caused directly by it.</para>

<para>On a modern machine, an L1 miss will typically cost
around 10 cycles, an L2 miss can cost as much as 200
cycles, and a mispredicted branch costs in the region of 10
to 30 cycles.  Detailed cache and branch profiling can be very useful
for understanding how your program interacts with the machine and thus how
to make it faster.</para>

<para>Also, since one instruction cache read is performed per
instruction executed, you can find out how many instructions are
executed per line, which can be useful for traditional profiling.</para>

</sect1>



<sect1 id="cg-manual.profile"
       xreflabel="Using Cachegrind, cg_annotate and cg_merge">
<title>Using Cachegrind, cg_annotate and cg_merge</title>

<para>First off, as for normal Valgrind use, you probably want to
compile with debugging info (the
<option>-g</option> option).  But by contrast with
normal Valgrind use, you probably do want to turn
optimisation on, since you should profile your program as it will
be normally run.</para>

<para>Then, you need to run Cachegrind itself to gather the profiling
information, and then run cg_annotate to get a detailed presentation of that
information.  As an optional intermediate step, you can use cg_merge to sum
together the outputs of multiple Cachegrind runs, into a single file which
you then use as the input for cg_annotate.</para>


<sect2 id="cg-manual.running-cachegrind" xreflabel="Running Cachegrind">
<title>Running Cachegrind</title>

<para>To run Cachegrind on a program <filename>prog</filename>, run:</para>
<screen><![CDATA[
valgrind --tool=cachegrind prog
]]></screen>

<para>The program will execute (slowly).  Upon completion,
summary statistics that look like this will be printed:</para>

<programlisting><![CDATA[
==31751== I   refs:      27,742,716
==31751== I1  misses:           276
==31751== L2i misses:           275
==31751== I1  miss rate:        0.0%
==31751== L2i miss rate:        0.0%
==31751== 
==31751== D   refs:      15,430,290  (10,955,517 rd + 4,474,773 wr)
==31751== D1  misses:        41,185  (    21,905 rd +    19,280 wr)
==31751== L2d misses:        23,085  (     3,987 rd +    19,098 wr)
==31751== D1  miss rate:        0.2% (       0.1%   +       0.4%)
==31751== L2d miss rate:        0.1% (       0.0%   +       0.4%)
==31751== 
==31751== L2 misses:         23,360  (     4,262 rd +    19,098 wr)
==31751== L2 miss rate:         0.0% (       0.0%   +       0.4%)]]></programlisting>

<para>Cache accesses for instruction fetches are summarised
first, giving the number of fetches made (this is the number of
instructions executed, which can be useful to know in its own
right), the number of I1 misses, and the number of L2 instruction
(<computeroutput>L2i</computeroutput>) misses.</para>

<para>Cache accesses for data follow. The information is similar
to that of the instruction fetches, except that the values are
also shown split between reads and writes (note each row's
<computeroutput>rd</computeroutput> and
<computeroutput>wr</computeroutput> values add up to the row's
total).</para>

<para>Combined instruction and data figures for the L2 cache
follow that.  Note that the L2 miss rate is computed relative to the total
number of memory accesses, not the number of L1 misses.  I.e.  it is
<computeroutput>(I2mr + D2mr + D2mw) / (Ir + Dr + Dw)</computeroutput>
not
<computeroutput>(I2mr + D2mr + D2mw) / (I1mr + D1mr + D1mw)</computeroutput>
</para>

<para>Branch prediction statistics are not collected by default.
To do so, add the option <option>--branch-sim=yes</option>.</para>

</sect2>


<sect2 id="cg-manual.outputfile" xreflabel="Output File">
<title>Output File</title>

<para>As well as printing summary information, Cachegrind also writes
more detailed profiling information to a file.  By default this file is named
<filename>cachegrind.out.&lt;pid&gt;</filename> (where
<filename>&lt;pid&gt;</filename> is the program's process ID), but its name
can be changed with the <option>--cachegrind-out-file</option> option.  This
file is human-readable, but is intended to be interpreted by the
accompanying program cg_annotate, described in the next section.</para>

<para>The default <computeroutput>.&lt;pid&gt;</computeroutput> suffix
on the output file name serves two purposes.  Firstly, it means you 
don't have to rename old log files that you don't want to overwrite.  
Secondly, and more importantly, it allows correct profiling with the
<option>--trace-children=yes</option> option of
programs that spawn child processes.</para>

<para>The output file can be big, many megabytes for large applications
built with full debugging information.</para>

</sect2>


  
<sect2 id="cg-manual.running-cg_annotate" xreflabel="Running cg_annotate">
<title>Running cg_annotate</title>

<para>Before using cg_annotate,
it is worth widening your window to be at least 120-characters
wide if possible, as the output lines can be quite long.</para>

<para>To get a function-by-function summary, run:</para>

<screen>cg_annotate &lt;filename&gt;</screen>

<para>on a Cachegrind output file.</para>

</sect2>


<sect2 id="cg-manual.the-output-preamble" xreflabel="The Output Preamble">
<title>The Output Preamble</title>

<para>The first part of the output looks like this:</para>

<programlisting><![CDATA[
--------------------------------------------------------------------------------
I1 cache:              65536 B, 64 B, 2-way associative
D1 cache:              65536 B, 64 B, 2-way associative
L2 cache:              262144 B, 64 B, 8-way associative
Command:               concord vg_to_ucode.c
Events recorded:       Ir I1mr I2mr Dr D1mr D2mr Dw D1mw D2mw
Events shown:          Ir I1mr I2mr Dr D1mr D2mr Dw D1mw D2mw
Event sort order:      Ir I1mr I2mr Dr D1mr D2mr Dw D1mw D2mw
Threshold:             99%
Chosen for annotation:
Auto-annotation:       off
]]></programlisting>


<para>This is a summary of the annotation options:</para>
                    
<itemizedlist>

  <listitem>
    <para>I1 cache, D1 cache, L2 cache: cache configuration.  So
    you know the configuration with which these results were
    obtained.</para>
  </listitem>

  <listitem>
    <para>Command: the command line invocation of the program
      under examination.</para>
  </listitem>

  <listitem>
   <para>Events recorded: which events were recorded.</para>
   <itemizedlist>
   </itemizedlist>

 </listitem>

 <listitem>
   <para>Events shown: the events shown, which is a subset of the events
   gathered.  This can be adjusted with the
   <option>--show</option> option.</para>
  </listitem>

  <listitem>
    <para>Event sort order: the sort order in which functions are
    shown.  For example, in this case the functions are sorted
    from highest <computeroutput>Ir</computeroutput> counts to
    lowest.  If two functions have identical
    <computeroutput>Ir</computeroutput> counts, they will then be
    sorted by <computeroutput>I1mr</computeroutput> counts, and
    so on.  This order can be adjusted with the
    <option>--sort</option> option.</para>

    <para>Note that this dictates the order the functions appear.
    It is <emphasis>not</emphasis> the order in which the columns
    appear; that is dictated by the "events shown" line (and can
    be changed with the <option>--show</option>
    option).</para>
  </listitem>

  <listitem>
    <para>Threshold: cg_annotate
    by default omits functions that cause very low counts
    to avoid drowning you in information.  In this case,
    cg_annotate shows summaries the functions that account for
    99% of the <computeroutput>Ir</computeroutput> counts;
    <computeroutput>Ir</computeroutput> is chosen as the
    threshold event since it is the primary sort event.  The
    threshold can be adjusted with the
    <option>--threshold</option>
    option.</para>
  </listitem>

  <listitem>
    <para>Chosen for annotation: names of files specified
    manually for annotation; in this case none.</para>
  </listitem>

  <listitem>
    <para>Auto-annotation: whether auto-annotation was requested
    via the <option>--auto=yes</option>
    option. In this case no.</para>
  </listitem>

</itemizedlist>

</sect2>


<sect2 id="cg-manual.the-global"
       xreflabel="The Global and Function-level Counts">
<title>The Global and Function-level Counts</title>

<para>Then follows summary statistics for the whole
program:</para>
  
<programlisting><![CDATA[
--------------------------------------------------------------------------------
Ir         I1mr I2mr Dr         D1mr   D2mr  Dw        D1mw   D2mw
--------------------------------------------------------------------------------
27,742,716  276  275 10,955,517 21,905 3,987 4,474,773 19,280 19,098  PROGRAM TOTALS]]></programlisting>

<para>
These are similar to the summary provided when Cachegrind finishes running.
</para>

<para>Then comes function-by-function statistics:</para>

<programlisting><![CDATA[
--------------------------------------------------------------------------------
Ir        I1mr I2mr Dr        D1mr  D2mr  Dw        D1mw   D2mw    file:function
--------------------------------------------------------------------------------
8,821,482    5    5 2,242,702 1,621    73 1,794,230      0      0  getc.c:_IO_getc
5,222,023    4    4 2,276,334    16    12   875,959      1      1  concord.c:get_word
2,649,248    2    2 1,344,810 7,326 1,385         .      .      .  vg_main.c:strcmp
2,521,927    2    2   591,215     0     0   179,398      0      0  concord.c:hash
2,242,740    2    2 1,046,612   568    22   448,548      0      0  ctype.c:tolower
1,496,937    4    4   630,874 9,000 1,400   279,388      0      0  concord.c:insert
  897,991   51   51   897,831    95    30        62      1      1  ???:???
  598,068    1    1   299,034     0     0   149,517      0      0  ../sysdeps/generic/lockfile.c:__flockfile
  598,068    0    0   299,034     0     0   149,517      0      0  ../sysdeps/generic/lockfile.c:__funlockfile
  598,024    4    4   213,580    35    16   149,506      0      0  vg_clientmalloc.c:malloc
  446,587    1    1   215,973 2,167   430   129,948 14,057 13,957  concord.c:add_existing
  341,760    2    2   128,160     0     0   128,160      0      0  vg_clientmalloc.c:vg_trap_here_WRAPPER
  320,782    4    4   150,711   276     0    56,027     53     53  concord.c:init_hash_table
  298,998    1    1   106,785     0     0    64,071      1      1  concord.c:create
  149,518    0    0   149,516     0     0         1      0      0  ???:tolower@@GLIBC_2.0
  149,518    0    0   149,516     0     0         1      0      0  ???:fgetc@@GLIBC_2.0
   95,983    4    4    38,031     0     0    34,409  3,152  3,150  concord.c:new_word_node
   85,440    0    0    42,720     0     0    21,360      0      0  vg_clientmalloc.c:vg_bogus_epilogue]]></programlisting>

<para>Each function
is identified by a
<computeroutput>file_name:function_name</computeroutput> pair. If
a column contains only a dot it means the function never performs
that event (e.g. the third row shows that
<computeroutput>strcmp()</computeroutput> contains no
instructions that write to memory). The name
<computeroutput>???</computeroutput> is used if the the file name
and/or function name could not be determined from debugging
information. If most of the entries have the form
<computeroutput>???:???</computeroutput> the program probably
wasn't compiled with <option>-g</option>.</para>

<para>It is worth noting that functions will come both from
the profiled program (e.g. <filename>concord.c</filename>)
and from libraries (e.g. <filename>getc.c</filename>)</para>

</sect2>


<sect2 id="cg-manual.line-by-line" xreflabel="Line-by-line Counts">
<title>Line-by-line Counts</title>

<para>There are two ways to annotate source files -- by specifying them
manually as arguments to cg_annotate, or with the
<option>--auto=yes</option> option.  For example, the output from running
<filename>cg_annotate &lt;filename&gt; concord.c</filename> for our example
produces the same output as above followed by an annotated version of
<filename>concord.c</filename>, a section of which looks like:</para>

<programlisting><![CDATA[
--------------------------------------------------------------------------------
-- User-annotated source: concord.c
--------------------------------------------------------------------------------
Ir        I1mr I2mr Dr      D1mr  D2mr  Dw      D1mw   D2mw

        .    .    .       .     .     .       .      .      .  void init_hash_table(char *file_name, Word_Node *table[])
        3    1    1       .     .     .       1      0      0  {
        .    .    .       .     .     .       .      .      .      FILE *file_ptr;
        .    .    .       .     .     .       .      .      .      Word_Info *data;
        1    0    0       .     .     .       1      1      1      int line = 1, i;
        .    .    .       .     .     .       .      .      .
        5    0    0       .     .     .       3      0      0      data = (Word_Info *) create(sizeof(Word_Info));
        .    .    .       .     .     .       .      .      .
    4,991    0    0   1,995     0     0     998      0      0      for (i = 0; i < TABLE_SIZE; i++)
    3,988    1    1   1,994     0     0     997     53     52          table[i] = NULL;
        .    .    .       .     .     .       .      .      .
        .    .    .       .     .     .       .      .      .      /* Open file, check it. */
        6    0    0       1     0     0       4      0      0      file_ptr = fopen(file_name, "r");
        2    0    0       1     0     0       .      .      .      if (!(file_ptr)) {
        .    .    .       .     .     .       .      .      .          fprintf(stderr, "Couldn't open '%s'.\n", file_name);
        1    1    1       .     .     .       .      .      .          exit(EXIT_FAILURE);
        .    .    .       .     .     .       .      .      .      }
        .    .    .       .     .     .       .      .      .
  165,062    1    1  73,360     0     0  91,700      0      0      while ((line = get_word(data, line, file_ptr)) != EOF)
  146,712    0    0  73,356     0     0  73,356      0      0          insert(data->;word, data->line, table);
        .    .    .       .     .     .       .      .      .
        4    0    0       1     0     0       2      0      0      free(data);
        4    0    0       1     0     0       2      0      0      fclose(file_ptr);
        3    0    0       2     0     0       .      .      .  }]]></programlisting>

<para>(Although column widths are automatically minimised, a wide
terminal is clearly useful.)</para>
  
<para>Each source file is clearly marked
(<computeroutput>User-annotated source</computeroutput>) as
having been chosen manually for annotation.  If the file was
found in one of the directories specified with the
<option>-I</option>/<option>--include</option> option, the directory
and file are both given.</para>

<para>Each line is annotated with its event counts.  Events not
applicable for a line are represented by a dot.  This is useful
for distinguishing between an event which cannot happen, and one
which can but did not.</para>

<para>Sometimes only a small section of a source file is
executed.  To minimise uninteresting output, Cachegrind only shows
annotated lines and lines within a small distance of annotated
lines.  Gaps are marked with the line numbers so you know which
part of a file the shown code comes from, eg:</para>

<programlisting><![CDATA[
(figures and code for line 704)
-- line 704 ----------------------------------------
-- line 878 ----------------------------------------
(figures and code for line 878)]]></programlisting>

<para>The amount of context to show around annotated lines is
controlled by the <option>--context</option>
option.</para>

<para>To get automatic annotation, use the <option>--auto=yes</option> option.
cg_annotate will automatically annotate every source file it can
find that is mentioned in the function-by-function summary.
Therefore, the files chosen for auto-annotation are affected by
the <option>--sort</option> and
<option>--threshold</option> options.  Each
source file is clearly marked (<computeroutput>Auto-annotated
source</computeroutput>) as being chosen automatically.  Any
files that could not be found are mentioned at the end of the
output, eg:</para>

<programlisting><![CDATA[
------------------------------------------------------------------
The following files chosen for auto-annotation could not be found:
------------------------------------------------------------------
  getc.c
  ctype.c
  ../sysdeps/generic/lockfile.c]]></programlisting>

<para>This is quite common for library files, since libraries are
usually compiled with debugging information, but the source files
are often not present on a system.  If a file is chosen for
annotation both manually and automatically, it
is marked as <computeroutput>User-annotated
source</computeroutput>. Use the
<option>-I</option>/<option>--include</option> option to tell Valgrind where
to look for source files if the filenames found from the debugging
information aren't specific enough.</para>

<para>Beware that cg_annotate can take some time to digest large
<filename>cachegrind.out.&lt;pid&gt;</filename> files,
e.g. 30 seconds or more.  Also beware that auto-annotation can
produce a lot of output if your program is large!</para>

</sect2>


<sect2 id="cg-manual.assembler" xreflabel="Annotating Assembly Code Programs">
<title>Annotating Assembly Code Programs</title>

<para>Valgrind can annotate assembly code programs too, or annotate
the assembly code generated for your C program.  Sometimes this is
useful for understanding what is really happening when an
interesting line of C code is translated into multiple
instructions.</para>

<para>To do this, you just need to assemble your
<computeroutput>.s</computeroutput> files with assembly-level debug
information.  You can use compile with the <option>-S</option> to compile C/C++
programs to assembly code, and then assemble the assembly code files with
<option>-g</option> to achieve this.  You can then profile and annotate the
assembly code source files in the same way as C/C++ source files.</para>

</sect2>

<sect2 id="ms-manual.forkingprograms" xreflabel="Forking Programs">
<title>Forking Programs</title>
<para>If your program forks, the child will inherit all the profiling data that
has been gathered for the parent.</para>

<para>If the output file format string (controlled by
<option>--cachegrind-out-file</option>) does not contain <option>%p</option>,
then the outputs from the parent and child will be intermingled in a single
output file, which will almost certainly make it unreadable by
cg_annotate.</para>
</sect2>


<sect2 id="cg-manual.annopts.warnings" xreflabel="cg_annotate Warnings">
<title>cg_annotate Warnings</title>

<para>There are a couple of situations in which
cg_annotate issues warnings.</para>

<itemizedlist>
  <listitem>
    <para>If a source file is more recent than the
    <filename>cachegrind.out.&lt;pid&gt;</filename> file.
    This is because the information in
    <filename>cachegrind.out.&lt;pid&gt;</filename> is only
    recorded with line numbers, so if the line numbers change at
    all in the source (e.g.  lines added, deleted, swapped), any
    annotations will be incorrect.</para>
  </listitem>
  <listitem>
    <para>If information is recorded about line numbers past the
    end of a file.  This can be caused by the above problem,
    i.e. shortening the source file while using an old
    <filename>cachegrind.out.&lt;pid&gt;</filename> file.  If
    this happens, the figures for the bogus lines are printed
    anyway (clearly marked as bogus) in case they are
    important.</para>
  </listitem>
</itemizedlist>

</sect2>



<sect2 id="cg-manual.annopts.things-to-watch-out-for"
       xreflabel="Unusual Annotation Cases">
<title>Unusual Annotation Cases</title>

<para>Some odd things that can occur during annotation:</para>

<itemizedlist>
  <listitem>
    <para>If annotating at the assembler level, you might see
    something like this:</para>
<programlisting><![CDATA[
      1    0    0  .    .    .  .    .    .          leal -12(%ebp),%eax
      1    0    0  .    .    .  1    0    0          movl %eax,84(%ebx)
      2    0    0  0    0    0  1    0    0          movl $1,-20(%ebp)
      .    .    .  .    .    .  .    .    .          .align 4,0x90
      1    0    0  .    .    .  .    .    .          movl $.LnrB,%eax
      1    0    0  .    .    .  1    0    0          movl %eax,-16(%ebp)]]></programlisting>

    <para>How can the third instruction be executed twice when
    the others are executed only once?  As it turns out, it
    isn't.  Here's a dump of the executable, using
    <computeroutput>objdump -d</computeroutput>:</para>
<programlisting><![CDATA[
      8048f25:       8d 45 f4                lea    0xfffffff4(%ebp),%eax
      8048f28:       89 43 54                mov    %eax,0x54(%ebx)
      8048f2b:       c7 45 ec 01 00 00 00    movl   $0x1,0xffffffec(%ebp)
      8048f32:       89 f6                   mov    %esi,%esi
      8048f34:       b8 08 8b 07 08          mov    $0x8078b08,%eax
      8048f39:       89 45 f0                mov    %eax,0xfffffff0(%ebp)]]></programlisting>

    <para>Notice the extra <computeroutput>mov
    %esi,%esi</computeroutput> instruction.  Where did this come
    from?  The GNU assembler inserted it to serve as the two
    bytes of padding needed to align the <computeroutput>movl
    $.LnrB,%eax</computeroutput> instruction on a four-byte
    boundary, but pretended it didn't exist when adding debug
    information.  Thus when Valgrind reads the debug info it
    thinks that the <computeroutput>movl
    $0x1,0xffffffec(%ebp)</computeroutput> instruction covers the
    address range 0x8048f2b--0x804833 by itself, and attributes
    the counts for the <computeroutput>mov
    %esi,%esi</computeroutput> to it.</para>
  </listitem>

  <!--
  I think this isn't true any more, not since cost centres were moved from
  being associated with instruction addresses to being associated with
  source line numbers.
  <listitem>
    <para>Inlined functions can cause strange results in the
    function-by-function summary.  If a function
    <computeroutput>inline_me()</computeroutput> is defined in
    <filename>foo.h</filename> and inlined in the functions
    <computeroutput>f1()</computeroutput>,
    <computeroutput>f2()</computeroutput> and
    <computeroutput>f3()</computeroutput> in
    <filename>bar.c</filename>, there will not be a
    <computeroutput>foo.h:inline_me()</computeroutput> function
    entry.  Instead, there will be separate function entries for
    each inlining site, i.e.
    <computeroutput>foo.h:f1()</computeroutput>,
    <computeroutput>foo.h:f2()</computeroutput> and
    <computeroutput>foo.h:f3()</computeroutput>.  To find the
    total counts for
    <computeroutput>foo.h:inline_me()</computeroutput>, add up
    the counts from each entry.</para>

    <para>The reason for this is that although the debug info
    output by GCC indicates the switch from
    <filename>bar.c</filename> to <filename>foo.h</filename>, it
    doesn't indicate the name of the function in
    <filename>foo.h</filename>, so Valgrind keeps using the old
    one.</para>
  </listitem>
  -->

  <listitem>
    <para>Sometimes, the same filename might be represented with
    a relative name and with an absolute name in different parts
    of the debug info, eg:
    <filename>/home/user/proj/proj.h</filename> and
    <filename>../proj.h</filename>.  In this case, if you use
    auto-annotation, the file will be annotated twice with the
    counts split between the two.</para>
  </listitem>

  <listitem>
    <para>Files with more than 65,535 lines cause difficulties
    for the Stabs-format debug info reader.  This is because the line
    number in the <computeroutput>struct nlist</computeroutput>
    defined in <filename>a.out.h</filename> under Linux is only a
    16-bit value.  Valgrind can handle some files with more than
    65,535 lines correctly by making some guesses to identify
    line number overflows.  But some cases are beyond it, in
    which case you'll get a warning message explaining that
    annotations for the file might be incorrect.</para>
    
    <para>If you are using GCC 3.1 or later, this is most likely
    irrelevant, since GCC switched to using the more modern DWARF2 
    format by default at version 3.1.  DWARF2 does not have any such
    limitations on line numbers.</para>
  </listitem>

  <listitem>
    <para>If you compile some files with
    <option>-g</option> and some without, some
    events that take place in a file without debug info could be
    attributed to the last line of a file with debug info
    (whichever one gets placed before the non-debug-info file in
    the executable).</para>
  </listitem>

</itemizedlist>

<para>This list looks long, but these cases should be fairly
rare.</para>

</sect2>


<sect2 id="cg-manual.cg_merge" xreflabel="cg_merge">
<title>Merging Profiles with cg_merge</title>

<para>
cg_merge is a simple program which
reads multiple profile files, as created by Cachegrind, merges them
together, and writes the results into another file in the same format.
You can then examine the merged results using
<computeroutput>cg_annotate &lt;filename&gt;</computeroutput>, as
described above.  The merging functionality might be useful if you
want to aggregate costs over multiple runs of the same program, or
from a single parallel run with multiple instances of the same
program.</para>

<para>
cg_merge is invoked as follows:
</para>

<programlisting><![CDATA[
cg_merge -o outputfile file1 file2 file3 ...]]></programlisting>

<para>
It reads and checks <computeroutput>file1</computeroutput>, then read
and checks <computeroutput>file2</computeroutput> and merges it into
the running totals, then the same with
<computeroutput>file3</computeroutput>, etc.  The final results are
written to <computeroutput>outputfile</computeroutput>, or to standard
out if no output file is specified.</para>

<para>
Costs are summed on a per-function, per-line and per-instruction
basis.  Because of this, the order in which the input files does not
matter, although you should take care to only mention each file once,
since any file mentioned twice will be added in twice.</para>

<para>
cg_merge does not attempt to check
that the input files come from runs of the same executable.  It will
happily merge together profile files from completely unrelated
programs.  It does however check that the
<computeroutput>Events:</computeroutput> lines of all the inputs are
identical, so as to ensure that the addition of costs makes sense.
For example, it would be nonsensical for it to add a number indicating
D1 read references to a number from a different file indicating L2
write misses.</para>

<para>
A number of other syntax and sanity checks are done whilst reading the
inputs.  cg_merge will stop and
attempt to print a helpful error message if any of the input files
fail these checks.</para>

</sect2>


</sect1>



<sect1 id="cg-manual.cgopts" xreflabel="Cachegrind Command-line Options">
<title>Cachegrind Command-line Options</title>

<!-- start of xi:include in the manpage -->
<para>Cachegrind-specific options are:</para>

<variablelist id="cg.opts.list">

  <varlistentry id="opt.I1" xreflabel="--I1">
    <term>
      <option><![CDATA[--I1=<size>,<associativity>,<line size> ]]></option>
    </term>
    <listitem>
      <para>Specify the size, associativity and line size of the level 1
      instruction cache.  </para>
    </listitem>
  </varlistentry>

  <varlistentry id="opt.D1" xreflabel="--D1">
    <term>
      <option><![CDATA[--D1=<size>,<associativity>,<line size> ]]></option>
    </term>
    <listitem>
      <para>Specify the size, associativity and line size of the level 1
      data cache.</para>
    </listitem>
  </varlistentry>

  <varlistentry id="opt.L2" xreflabel="--L2">
    <term>
      <option><![CDATA[--L2=<size>,<associativity>,<line size> ]]></option>
    </term>
    <listitem>
      <para>Specify the size, associativity and line size of the level 2
      cache.</para>
    </listitem>
  </varlistentry>

  <varlistentry id="opt.cache-sim" xreflabel="--cache-sim">
    <term>
      <option><![CDATA[--cache-sim=no|yes [yes] ]]></option>
    </term>
    <listitem>
      <para>Enables or disables collection of cache access and miss
            counts.</para>
    </listitem>
  </varlistentry>

  <varlistentry id="opt.branch-sim" xreflabel="--branch-sim">
    <term>
      <option><![CDATA[--branch-sim=no|yes [no] ]]></option>
    </term>
    <listitem>
      <para>Enables or disables collection of branch instruction and
            misprediction counts.  By default this is disabled as it
            slows Cachegrind down by approximately 25%.  Note that you
            cannot specify <option>--cache-sim=no</option>
            and <option>--branch-sim=no</option>
            together, as that would leave Cachegrind with no
            information to collect.</para>
    </listitem>
  </varlistentry>

  <varlistentry id="opt.cachegrind-out-file" xreflabel="--cachegrind-out-file">
    <term>
      <option><![CDATA[--cachegrind-out-file=<file> ]]></option>
    </term>
    <listitem>
      <para>Write the profile data to 
            <computeroutput>file</computeroutput> rather than to the default
            output file,
            <filename>cachegrind.out.&lt;pid&gt;</filename>.  The
            <option>%p</option> and <option>%q</option> format specifiers
            can be used to embed the process ID and/or the contents of an
            environment variable in the name, as is the case for the core
            option <option><xref linkend="opt.log-file"/></option>.
      </para>
    </listitem>
  </varlistentry>

</variablelist>
<!-- end of xi:include in the manpage -->

</sect1>



<sect1 id="cg-manual.annopts" xreflabel="cg_annotate Command-line Options">
<title>cg_annotate Command-line Options</title>

<!-- start of xi:include in the manpage -->
<variablelist id="cg_annotate.opts.list">

  <varlistentry>
    <term>
      <option><![CDATA[-h --help ]]></option>
    </term>
    <listitem>
      <para>Show the help message.</para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[--version ]]></option>
    </term>
    <listitem>
      <para>Show the version number.</para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[--show=A,B,C [default: all, using order in
      cachegrind.out.<pid>] ]]></option>
    </term>
    <listitem>
      <para>Specifies which events to show (and the column
      order). Default is to use all present in the
      <filename>cachegrind.out.&lt;pid&gt;</filename> file (and
      use the order in the file).  Useful if you want to concentrate on, for
      example, I cache misses (<option>--show=I1mr,I2mr</option>), or data
      read misses (<option>--show=D1mr,D2mr</option>), or L2 data misses
      (<option>--show=D2mr,D2mw</option>).  Best used in conjunction with
      <option>--sort</option>.</para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[--sort=A,B,C [default: order in
      cachegrind.out.<pid>] ]]></option>
    </term>
    <listitem>
      <para>Specifies the events upon which the sorting of the
      function-by-function entries will be based.</para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[--threshold=X [default: 99%] ]]></option>
    </term>
    <listitem>
      <para>Sets the threshold for the function-by-function
      summary.  Functions are shown that account for more than X%
      of the primary sort event.  If auto-annotating, also affects
      which files are annotated.</para>
        
      <para>Note: thresholds can be set for more than one of the
      events by appending any events for the
      <option>--sort</option> option with a colon
      and a number (no spaces, though).  E.g. if you want to see
      the functions that cover 99% of L2 read misses and 99% of L2
      write misses, use this option:</para>
      <para><option>--sort=D2mr:99,D2mw:99</option></para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[--auto=<no|yes> [default: no] ]]></option>
    </term>
    <listitem>
      <para>When enabled, automatically annotates every file that
      is mentioned in the function-by-function summary that can be
      found.  Also gives a list of those that couldn't be found.</para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[--context=N [default: 8] ]]></option>
    </term>
    <listitem>
      <para>Print N lines of context before and after each
      annotated line.  Avoids printing large sections of source
      files that were not executed.  Use a large number
      (e.g. 100000) to show all source lines.</para>
    </listitem>
  </varlistentry>

  <varlistentry>
    <term>
      <option><![CDATA[-I<dir> --include=<dir> [default: none] ]]></option>
    </term>
    <listitem>
      <para>Adds a directory to the list in which to search for
      files.  Multiple <option>-I</option>/<option>--include</option>
      options can be given to add multiple directories.</para>
    </listitem>
  </varlistentry>

</variablelist>
<!-- end of xi:include in the manpage -->
  
</sect1>



<sect1 id="cg-manual.acting-on"
       xreflabel="Acting on Cachegrind's Information">
<title>Acting on Cachegrind's Information</title>
<para>
Cachegrind gives you lots of information, but acting on that information
isn't always easy.  Here are some rules of thumb that we have found to be
useful.</para>

<para>
First of all, the global hit/miss counts and miss rates are not that useful.
If you have multiple programs or multiple runs of a program, comparing the
numbers might identify if any are outliers and worthy of closer
investigation.  Otherwise, they're not enough to act on.</para>

<para>
The function-by-function counts are more useful to look at, as they pinpoint
which functions are causing large numbers of counts.  However, beware that
inlining can make these counts misleading.  If a function
<function>f</function> is always inlined, counts will be attributed to the
functions it is inlined into, rather than itself.  However, if you look at
the line-by-line annotations for <function>f</function> you'll see the
counts that belong to <function>f</function>.  (This is hard to avoid, it's
how the debug info is structured.)  So it's worth looking for large numbers
in the line-by-line annotations.</para>

<para>
The line-by-line source code annotations are much more useful.  In our
experience, the best place to start is by looking at the
<computeroutput>Ir</computeroutput> numbers.  They simply measure how many
instructions were executed for each line, and don't include any cache
information, but they can still be very useful for identifying
bottlenecks.</para>

<para>
After that, we have found that L2 misses are typically a much bigger source
of slow-downs than L1 misses.  So it's worth looking for any snippets of
code with high <computeroutput>D2mr</computeroutput> or
<computeroutput>D2mw</computeroutput> counts.  (You can use
<option>--show=D2mr
--sort=D2mr</option> with cg_annotate to focus just on
<literal>D2mr</literal> counts, for example.) If you find any, it's still
not always easy to work out how to improve things.  You need to have a
reasonable understanding of how caches work, the principles of locality, and
your program's data access patterns.  Improving things may require
redesigning a data structure, for example.</para>

<para>
Looking at the <computeroutput>Bcm</computeroutput> and
<computeroutput>Bim</computeroutput> misses can also be helpful.
In particular, <computeroutput>Bim</computeroutput> misses are often caused
by <literal>switch</literal> statements, and in some cases these
<literal>switch</literal> statements can be replaced with table-driven code.
For example, you might replace code like this:</para>

<programlisting><![CDATA[
enum E { A, B, C };
enum E e;
int i;
...
switch (e)
{
    case A: i += 1;
    case B: i += 2;
    case C: i += 3;
}
]]></programlisting>

<para>with code like this:</para>

<programlisting><![CDATA[
enum E { A, B, C };
enum E e;
enum E table[] = { 1, 2, 3 };
int i;
...
i += table[e];
]]></programlisting>

<para>
This is obviously a contrived example, but the basic principle applies in a
wide variety of situations.</para>

<para>
In short, Cachegrind can tell you where some of the bottlenecks in your code
are, but it can't tell you how to fix them.  You have to work that out for
yourself.  But at least you have the information!
</para>

</sect1>


<sect1 id="cg-manual.sim-details"
       xreflabel="Simulation Details">
<title>Simulation Details</title>
<para>
This section talks about details you don't need to know about in order to
use Cachegrind, but may be of interest to some people.
</para>

<sect2 id="cache-sim" xreflabel="Cache Simulation Specifics">
<title>Cache Simulation Specifics</title>

<para>Specific characteristics of the cache simulation are as
follows:</para>

<itemizedlist>

  <listitem>
    <para>Write-allocate: when a write miss occurs, the block
    written to is brought into the D1 cache.  Most modern caches
    have this property.</para>
  </listitem>

  <listitem>
    <para>Bit-selection hash function: the set of line(s) in the cache
    to which a memory block maps is chosen by the middle bits
    M--(M+N-1) of the byte address, where:</para>
    <itemizedlist>
      <listitem>
        <para>line size = 2^M bytes</para>
      </listitem>
      <listitem>
        <para>(cache size / line size / associativity) = 2^N bytes</para>
      </listitem>
    </itemizedlist> 
  </listitem>

  <listitem>
    <para>Inclusive L2 cache: the L2 cache typically replicates all
    the entries of the L1 caches, because fetching into L1 involves
    fetching into L2 first (this does not guarantee strict inclusiveness,
    as lines evicted from L2 still could reside in L1).  This is
    standard on Pentium chips, but AMD Opterons, Athlons and Durons
    use an exclusive L2 cache that only holds
    blocks evicted from L1.  Ditto most modern VIA CPUs.</para>
  </listitem>

</itemizedlist>

<para>The cache configuration simulated (cache size,
associativity and line size) is determined automatically using
the x86 CPUID instruction.  If you have a machine that (a)
doesn't support the CPUID instruction, or (b) supports it in an
early incarnation that doesn't give any cache information, then
Cachegrind will fall back to using a default configuration (that
of a model 3/4 Athlon).  Cachegrind will tell you if this
happens.  You can manually specify one, two or all three levels
(I1/D1/L2) of the cache from the command line using the
<option>--I1</option>,
<option>--D1</option> and
<option>--L2</option> options.
For cache parameters to be valid for simulation, the number
of sets (with associativity being the number of cache lines in
each set) has to be a power of two.</para>

<para>On PowerPC platforms
Cachegrind cannot automatically 
determine the cache configuration, so you will 
need to specify it with the
<option>--I1</option>,
<option>--D1</option> and
<option>--L2</option> options.</para>


<para>Other noteworthy behaviour:</para>

<itemizedlist>
  <listitem>
    <para>References that straddle two cache lines are treated as
    follows:</para>
    <itemizedlist>
      <listitem>
        <para>If both blocks hit --&gt; counted as one hit</para>
      </listitem>
      <listitem>
        <para>If one block hits, the other misses --&gt; counted
        as one miss.</para>
      </listitem>
      <listitem>
        <para>If both blocks miss --&gt; counted as one miss (not
        two)</para>
      </listitem>
    </itemizedlist>
  </listitem>

  <listitem>
    <para>Instructions that modify a memory location
    (e.g. <computeroutput>inc</computeroutput> and
    <computeroutput>dec</computeroutput>) are counted as doing
    just a read, i.e. a single data reference.  This may seem
    strange, but since the write can never cause a miss (the read
    guarantees the block is in the cache) it's not very
    interesting.</para>

    <para>Thus it measures not the number of times the data cache
    is accessed, but the number of times a data cache miss could
    occur.</para>
  </listitem>

</itemizedlist>

<para>If you are interested in simulating a cache with different
properties, it is not particularly hard to write your own cache
simulator, or to modify the existing ones in
<computeroutput>cg_sim.c</computeroutput>. We'd be
interested to hear from anyone who does.</para>

</sect2>


<sect2 id="branch-sim" xreflabel="Branch Simulation Specifics">
<title>Branch Simulation Specifics</title>

<para>Cachegrind simulates branch predictors intended to be
typical of mainstream desktop/server processors of around 2004.</para>

<para>Conditional branches are predicted using an array of 16384 2-bit
saturating counters.  The array index used for a branch instruction is
computed partly from the low-order bits of the branch instruction's
address and partly using the taken/not-taken behaviour of the last few
conditional branches.  As a result the predictions for any specific
branch depend both on its own history and the behaviour of previous
branches.  This is a standard technique for improving prediction
accuracy.</para>

<para>For indirect branches (that is, jumps to unknown destinations)
Cachegrind uses a simple branch target address predictor.  Targets are
predicted using an array of 512 entries indexed by the low order 9
bits of the branch instruction's address.  Each branch is predicted to
jump to the same address it did last time.  Any other behaviour causes
a mispredict.</para>

<para>More recent processors have better branch predictors, in
particular better indirect branch predictors.  Cachegrind's predictor
design is deliberately conservative so as to be representative of the
large installed base of processors which pre-date widespread
deployment of more sophisticated indirect branch predictors.  In
particular, late model Pentium 4s (Prescott), Pentium M, Core and Core
2 have more sophisticated indirect branch predictors than modelled by
Cachegrind.  </para>

<para>Cachegrind does not simulate a return stack predictor.  It
assumes that processors perfectly predict function return addresses,
an assumption which is probably close to being true.</para>

<para>See Hennessy and Patterson's classic text "Computer
Architecture: A Quantitative Approach", 4th edition (2007), Section
2.3 (pages 80-89) for background on modern branch predictors.</para>

</sect2>

<sect2 id="cg-manual.annopts.accuracy" xreflabel="Accuracy">
<title>Accuracy</title>

<para>Valgrind's cache profiling has a number of
shortcomings:</para>

<itemizedlist>
  <listitem>
    <para>It doesn't account for kernel activity -- the effect of system
    calls on the cache and branch predictor contents is ignored.</para>
  </listitem>

  <listitem>
    <para>It doesn't account for other process activity.
    This is probably desirable when considering a single
    program.</para>
  </listitem>

  <listitem>
    <para>It doesn't account for virtual-to-physical address
    mappings.  Hence the simulation is not a true
    representation of what's happening in the
    cache.  Most caches and branch predictors are physically indexed, but
    Cachegrind simulates caches using virtual addresses.</para>
  </listitem>

  <listitem>
    <para>It doesn't account for cache misses not visible at the
    instruction level, e.g. those arising from TLB misses, or
    speculative execution.</para>
  </listitem>

  <listitem>
    <para>Valgrind will schedule
    threads differently from how they would be when running natively.
    This could warp the results for threaded programs.</para>
  </listitem>

  <listitem>
    <para>The x86/amd64 instructions <computeroutput>bts</computeroutput>,
    <computeroutput>btr</computeroutput> and
    <computeroutput>btc</computeroutput> will incorrectly be
    counted as doing a data read if both the arguments are
    registers, eg:</para>
<programlisting><![CDATA[
    btsl %eax, %edx]]></programlisting>

    <para>This should only happen rarely.</para>
  </listitem>

  <listitem>
    <para>x86/amd64 FPU instructions with data sizes of 28 and 108 bytes
    (e.g.  <computeroutput>fsave</computeroutput>) are treated as
    though they only access 16 bytes.  These instructions seem to
    be rare so hopefully this won't affect accuracy much.</para>
  </listitem>

</itemizedlist>

<para>Another thing worth noting is that results are very sensitive.
Changing the size of the the executable being profiled, or the sizes
of any of the shared libraries it uses, or even the length of their
file names, can perturb the results.  Variations will be small, but
don't expect perfectly repeatable results if your program changes at
all.</para>

<para>More recent GNU/Linux distributions do address space
randomisation, in which identical runs of the same program have their
shared libraries loaded at different locations, as a security measure.
This also perturbs the results.</para>

<para>While these factors mean you shouldn't trust the results to
be super-accurate, they should be close enough to be useful.</para>

</sect2>

</sect1>



<sect1 id="cg-manual.impl-details"
       xreflabel="Implementation Details">
<title>Implementation Details</title>
<para>
This section talks about details you don't need to know about in order to
use Cachegrind, but may be of interest to some people.
</para>

<sect2 id="cg-manual.impl-details.how-cg-works"
       xreflabel="How Cachegrind Works">
<title>How Cachegrind Works</title>
<para>The best reference for understanding how Cachegrind works is chapter 3 of
"Dynamic Binary Analysis and Instrumentation", by Nicholas Nethercote.  It
is available on the <ulink url="&vg-pubs-url;">Valgrind publications
page</ulink>.</para>
</sect2>

<sect2 id="cg-manual.impl-details.file-format"
       xreflabel="Cachegrind Output File Format">
<title>Cachegrind Output File Format</title>
<para>The file format is fairly straightforward, basically giving the
cost centre for every line, grouped by files and
functions.  It's also totally generic and self-describing, in the sense that
it can be used for any events that can be counted on a line-by-line basis,
not just cache and branch predictor events.  For example, earlier versions
of Cachegrind didn't have a branch predictor simulation.  When this was
added, the file format didn't need to change at all.  So the format (and
consequently, cg_annotate) could be used by other tools.</para>

<para>The file format:</para>
<programlisting><![CDATA[
file         ::= desc_line* cmd_line events_line data_line+ summary_line
desc_line    ::= "desc:" ws? non_nl_string
cmd_line     ::= "cmd:" ws? cmd
events_line  ::= "events:" ws? (event ws)+
data_line    ::= file_line | fn_line | count_line
file_line    ::= "fl=" filename
fn_line      ::= "fn=" fn_name
count_line   ::= line_num ws? (count ws)+
summary_line ::= "summary:" ws? (count ws)+
count        ::= num | "."]]></programlisting>

<para>Where:</para>
<itemizedlist>
  <listitem>
    <para><computeroutput>non_nl_string</computeroutput> is any
    string not containing a newline.</para>
  </listitem>
  <listitem>
    <para><computeroutput>cmd</computeroutput> is a string holding the
    command line of the profiled program.</para>
  </listitem>
  <listitem>
    <para><computeroutput>event</computeroutput> is a string containing
    no whitespace.</para>
  </listitem>
  <listitem>
    <para><computeroutput>filename</computeroutput> and
    <computeroutput>fn_name</computeroutput> are strings.</para>
  </listitem>
  <listitem>
    <para><computeroutput>num</computeroutput> and
    <computeroutput>line_num</computeroutput> are decimal
    numbers.</para>
  </listitem>
  <listitem>
    <para><computeroutput>ws</computeroutput> is whitespace.</para>
  </listitem>
</itemizedlist>

<para>The contents of the "desc:" lines are printed out at the top
of the summary.  This is a generic way of providing simulation
specific information, e.g. for giving the cache configuration for
cache simulation.</para>

<para>More than one line of info can be presented for each file/fn/line number.
In such cases, the counts for the named events will be accumulated.</para>

<para>Counts can be "." to represent zero.  This makes the files easier for
humans to read.</para>

<para>The number of counts in each
<computeroutput>line</computeroutput> and the
<computeroutput>summary_line</computeroutput> should not exceed
the number of events in the
<computeroutput>event_line</computeroutput>.  If the number in
each <computeroutput>line</computeroutput> is less, cg_annotate
treats those missing as though they were a "." entry.  This saves space.
</para>

<para>A <computeroutput>file_line</computeroutput> changes the
current file name.  A <computeroutput>fn_line</computeroutput>
changes the current function name.  A
<computeroutput>count_line</computeroutput> contains counts that
pertain to the current filename/fn_name.  A "fn="
<computeroutput>file_line</computeroutput> and a
<computeroutput>fn_line</computeroutput> must appear before any
<computeroutput>count_line</computeroutput>s to give the context
of the first <computeroutput>count_line</computeroutput>s.</para>

<para>Each <computeroutput>file_line</computeroutput> will normally be
immediately followed by a <computeroutput>fn_line</computeroutput>.  But it
doesn't have to be.</para>

<para>The summary line is redundant, because it just holds the total counts
for each event.  But this serves as a useful sanity check of the data;  if
the totals for each event don't match the summary line, something has gone
wrong.</para>

</sect2>

</sect1>
</chapter>