callgrind/docs/cl-format.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="cl-format" xreflabel="Callgrind Format Specification">
<title>Callgrind Format Specification</title>

<para>This chapter describes the Callgrind Profile Format, Version 1.</para>

<para>A synonymous name is "Calltree Profile Format". These names actually mean
the same since Callgrind was previously named Calltree.</para>

<para>The format description is meant for the user to be able to understand the
file contents; but more important, it is given for authors of measurement or
visualization tools to be able to write and read this format.</para>

<sect1 id="cl-format.overview" xreflabel="Overview">
<title>Overview</title>

<para>The profile data format is ASCII based.
It is written by Callgrind, and it is upwards compatible
to the format used by Cachegrind (ie. Cachegrind uses a subset). It can
be read by callgrind_annotate and KCachegrind.</para>

<para>This chapter gives on overview of format features and examples.
For detailed syntax, look at the format reference.</para>

<sect2 id="cl-format.overview.basics" xreflabel="Basic Structure">
<title>Basic Structure</title>

<para>Each file has a header part of an arbitrary number of lines of the
format "key: value". After the header, lines specifying profile costs
follow. Everywhere, comments on own lines starting with '#' are allowed.
The header lines with keys "positions" and "events" define
the meaning of cost lines in the second part of the file: the value of
"positions" is a list of subpositions, and the value of "events" is a list
of event type names. Cost lines consist of subpositions followed by 64-bit
counters for the events, in the order specified by the "positions" and "events"
header line.</para>

<para>The "events" header line is always required in contrast to the optional
line for "positions", which defaults to "line", i.e. a line number of some
source file. In addition, the second part of the file contains position
specifications of the form "spec=name". "spec" can be e.g. "fn" for a
function name or "fl" for a file name. Cost lines are always related to
the function/file specifications given directly before.</para>

</sect2>

<sect2 id="cl-format.overview.example1" xreflabel="Simple Example">
<title>Simple Example</title>

<para>The event names in the following example are quite arbitrary, and are not
related to event names used by Callgrind. Especially, cycle counts matching
real processors probably will never be generated by any Valgrind tools, as these
are bound to simulations of simple machine models for acceptable slowdown.
However, any profiling tool could use the format described in this chapter.</para>

<para>
<screen>events: Cycles Instructions Flops
fl=file.f
fn=main
15 90 14 2
16 20 12</screen></para>

<para>The above example gives profile information for event types "Cycles",
"Instructions", and "Flops". Thus, cost lines give the number of CPU cycles
passed by, number of executed instructions, and number of floating point
operations executed while running code corresponding to some source
position. As there is no line specifying the value of "positions", it defaults
to "line", which means that the first number of a cost line is always a line
number.</para>

<para>Thus, the first cost line specifies that in line 15 of source file
<filename>file.f</filename> there is code belonging to function
<function>main</function>. While running, 90 CPU cycles passed by, and 2 of
the 14 instructions executed were floating point operations. Similarly, the
next line specifies that there were 12 instructions executed in the context
of function <function>main</function> which can be related to line 16 in
file <filename>file.f</filename>, taking 20 CPU cycles. If a cost line
specifies less event counts than given in the "events" line, the rest is
assumed to be zero.  I.e. there was no floating point instruction executed
relating to line 16.</para>

<para>Note that regular cost lines always give self (also called exclusive)
cost of code at a given position. If you specify multiple cost lines for the
same position, these will be summed up. On the other hand, in the example above
there is no specification of how many times function
<function>main</function> actually was
called: profile data only contains sums.</para>

</sect2>


<sect2 id="cl-format.overview.associations" xreflabel="Associations">
<title>Associations</title>

<para>The most important extension to the original format of Cachegrind is the
ability to specify call relationship among functions. More generally, you
specify associations among positions. For this, the second part of the
file also can contain association specifications. These look similar to
position specifications, but consist of two lines. For calls, the format
looks like
<screen>
 calls=(Call Count) (Target position)
 (Source position) (Inclusive cost of call)
</screen></para>

<para>The destination only specifies subpositions like line number. Therefore,
to be able to specify a call to another function in another source file, you
have to precede the above lines with a "cfn=" specification for the name of the
called function, and optionally a "cfi=" specification if the function is in
another source file ("cfl=" is an alternative specification for "cfi=" because
of historical reasons, and both should be supported by format readers).
The second line looks like a regular cost line with the difference
that inclusive cost spent inside of the function call has to be specified.</para>

<para>Other associations are for example (conditional) jumps. See the
reference below for details.</para>

</sect2>


<sect2 id="cl-format.overview.example2" xreflabel="Extended Example">
<title>Extended Example</title>

<para>The following example shows 3 functions, <function>main</function>,
<function>func1</function>, and <function>func2</function>. Function
<function>main</function> calls <function>func1</function> once and
<function>func2</function> 3 times. <function>func1</function> calls
<function>func2</function> 2 times.
<screen>events: Instructions

fl=file1.c
fn=main
16 20
cfn=func1
calls=1 50
16 400
cfi=file2.c
cfn=func2
calls=3 20
16 400

fn=func1
51 100
cfi=file2.c
cfn=func2
calls=2 20
51 300

fl=file2.c
fn=func2
20 700</screen></para>

<para>One can see that in <function>main</function> only code from line 16
is executed where also the other functions are called. Inclusive cost of
<function>main</function> is 820, which is the sum of self cost 20 and costs
spent in the calls: 400 for the single call to <function>func1</function>
and 400 as sum for the three calls to <function>func2</function>.</para>

<para>Function <function>func1</function> is located in
<filename>file1.c</filename>, the same as <function>main</function>.
Therefore, a "cfi=" specification for the call to <function>func1</function>
is not needed. The function <function>func1</function> only consists of code
at line 51 of <filename>file1.c</filename>, where <function>func2</function>
is called.</para>

</sect2>


<sect2 id="cl-format.overview.compression1" xreflabel="Name Compression">
<title>Name Compression</title>

<para>With the introduction of association specifications like calls it is
needed to specify the same function or same file name multiple times. As
absolute filenames or symbol names in C++ can be quite long, it is advantageous
to be able to specify integer IDs for position specifications.
Here, the term "position" corresponds to a file name (source or object file)
or function name.</para>

<para>To support name compression, a position specification can be not only of
the format "spec=name", but also "spec=(ID) name" to specify a mapping of an
integer ID to a name, and "spec=(ID)" to reference a previously defined ID
mapping. There is a separate ID mapping for each position specification,
i.e. you can use ID 1 for both a file name and a symbol name.</para>

<para>With string compression, the example from 1.4 looks like this:
<screen>events: Instructions

fl=(1) file1.c
fn=(1) main
16 20
cfn=(2) func1
calls=1 50
16 400
cfi=(2) file2.c
cfn=(3) func2
calls=3 20
16 400

fn=(2)
51 100
cfi=(2)
cfn=(3)
calls=2 20
51 300

fl=(2)
fn=(3)
20 700</screen></para>

<para>As position specifications carry no information themselves, but only change
the meaning of subsequent cost lines or associations, they can appear
everywhere in the file without any negative consequence. Especially, you can
define name compression mappings directly after the header, and before any cost
lines. Thus, the above example can also be written as
<screen>events: Instructions

# define file ID mapping
fl=(1) file1.c
fl=(2) file2.c
# define function ID mapping
fn=(1) main
fn=(2) func1
fn=(3) func2

fl=(1)
fn=(1)
16 20
...</screen></para>

</sect2>


<sect2 id="cl-format.overview.compression2" xreflabel="Subposition Compression">
<title>Subposition Compression</title>

<para>If a Callgrind data file should hold costs for each assembler instruction
of a program, you specify subposition "instr" in the "positions:" header line,
and each cost line has to include the address of some instruction. Addresses
are allowed to have a size of 64 bits to support 64-bit architectures. Thus,
repeating similar, long addresses for almost every line in the data file can
enlarge the file size quite significantly, and
motivates for subposition compression: instead of every cost line starting with
a 16 character long address, one is allowed to specify relative addresses.
This relative specification is not only allowed for instruction addresses, but
also for line numbers; both addresses and line numbers are called "subpositions".</para>

<para>A relative subposition always is based on the corresponding subposition
of the last cost line, and starts with a "+" to specify a positive difference,
a "-" to specify a negative difference, or consists of "*" to specify the same
subposition. Because absolute subpositions always are positive (ie. never
prefixed by "-"), any relative specification is non-ambiguous; additionally,
absolute and relative subposition specifications can be mixed freely.
Assume the following example (subpositions can always be specified
as hexadecimal numbers, beginning with "0x"):
<screen>positions: instr line
events: ticks

fn=func
0x80001234 90 1
0x80001237 90 5
0x80001238 91 6</screen></para>

<para>With subposition compression, this looks like
<screen>positions: instr line
events: ticks

fn=func
0x80001234 90 1
+3 * 5
+1 +1 6</screen></para>

<para>Remark: For assembler annotation to work, instruction addresses have to
be corrected to correspond to addresses found in the original binary. I.e. for
relocatable shared objects, often a load offset has to be subtracted.</para>

</sect2>


<sect2 id="cl-format.overview.misc" xreflabel="Miscellaneous">
<title>Miscellaneous</title>

<sect3 id="cl-format.overview.misc.summary" xreflabel="Cost Summary Information">
<title>Cost Summary Information</title>

<para>For the visualization to be able to show cost percentage, a sum of the
cost of the full run has to be known. Usually, it is assumed that this is the
sum of all cost lines in a file. But sometimes, this is not correct. Thus, you
can specify a "summary:" line in the header giving the full cost for the
profile run. An import filter may use this to show a progress bar
while loading a large data file.</para>

</sect3>

<sect3 id="cl-format.overview.misc.events" xreflabel="Long Names for Event Types and inherited Types">
<title>Long Names for Event Types and inherited Types</title>

<para>Event types for cost lines are specified in the "events:" line with an
abbreviated name. For visualization, it makes sense to be able to specify some
longer, more descriptive name. For an event type "Ir" which means "Instruction
Fetches", this can be specified the header line
<screen>event: Ir : Instruction Fetches
events: Ir Dr</screen></para>

<para>In this example, "Dr" itself has no long name associated. The order of
"event:" lines and the "events:" line is of no importance. Additionally,
inherited event types can be introduced for which no raw data is available, but
which are calculated from given types. Suppose the last example, you could add
<screen>event: Sum = Ir + Dr</screen>
to specify an additional event type "Sum", which is calculated by adding costs
for "Ir and "Dr".</para>

</sect3>

</sect2>

</sect1>

<sect1 id="cl-format.reference" xreflabel="Reference">
<title>Reference</title>

<sect2 id="cl-format.reference.grammar" xreflabel="Grammar">
<title>Grammar</title>

<para>
<screen>ProfileDataFile := FormatVersion? Creator? PartData*</screen>
<screen>FormatVersion := "version: 1\n"</screen>
<screen>Creator := "creator:" NoNewLineChar* "\n"</screen>
<screen>PartData := (HeaderLine "\n")+ (BodyLine "\n")+</screen>
<screen>HeaderLine := (empty line)
  | ('#' NoNewLineChar*)
  | PartDetail
  | Description
  | EventSpecification
  | CostLineDef</screen>
<screen>PartDetail := TargetCommand | TargetID</screen>
<screen>TargetCommand := "cmd:" Space* NoNewLineChar*</screen>
<screen>TargetID := ("pid"|"thread"|"part") ":" Space* Number</screen>
<screen>Description := "desc:" Space* Name Space* ":" NoNewLineChar*</screen>
<screen>EventSpecification := "event:" Space* Name InheritedDef? LongNameDef?</screen>
<screen>InheritedDef := "=" InheritedExpr</screen>
<screen>InheritedExpr := Name
  | Number Space* ("*" Space*)? Name
  | InheritedExpr Space* "+" Space* InheritedExpr</screen>
<screen>LongNameDef := ":" NoNewLineChar*</screen>
<screen>CostLineDef := "events:" Space* Name (Space+ Name)*
  | "positions:" "instr"? (Space+ "line")?</screen>
<screen>BodyLine := (empty line)
  | ('#' NoNewLineChar*)
  | CostLine
  | PositionSpec
  | CallSpec
  | UncondJumpSpec
  | CondJumpSpec</screen>
<screen>CostLine := SubPositionList Costs?</screen>
<screen>SubPositionList := (SubPosition+ Space+)+</screen>
<screen>SubPosition := Number | "+" Number | "-" Number | "*"</screen>
<screen>Costs := (Number Space+)+</screen>
<screen>PositionSpec := Position "=" Space* PositionName</screen>
<screen>Position := CostPosition | CalledPosition</screen>
<screen>CostPosition := "ob" | "fl" | "fi" | "fe" | "fn"</screen>
<screen>CalledPosition := " "cob" | "cfi" | "cfl" | "cfn"</screen>
<screen>PositionName := ( "(" Number ")" )? (Space* NoNewLineChar* )?</screen>
<screen>CallSpec := CallLine "\n" CostLine</screen>
<screen>CallLine := "calls=" Space* Number Space+ SubPositionList</screen>
<screen>UncondJumpSpec := "jump=" Space* Number Space+ SubPositionList</screen>
<screen>CondJumpSpec := "jcnd=" Space* Number Space+ Number Space+ SubPositionList</screen>
<screen>Space := " " | "\t"</screen>
<screen>Number := HexNumber | (Digit)+</screen>
<screen>Digit := "0" | ... | "9"</screen>
<screen>HexNumber := "0x" (Digit | HexChar)+</screen>
<screen>HexChar := "a" | ... | "f" | "A" | ... | "F"</screen>
<screen>Name = Alpha (Digit | Alpha)*</screen>
<screen>Alpha = "a" | ... | "z" | "A" | ... | "Z"</screen>
<screen>NoNewLineChar := all characters without "\n"</screen>
</para>

<para>A profile data file ("ProfileDataFile") starts with basic information
  such as the version and creator information, and then has a list of parts, where
  each part has its own header and body. Parts typically are different threads
  and/or time spans/phases within a profiled application run.</para>

<para>Note that callgrind_annotate currently only supports profile data files with
  one part. Callgrind may produce multiple parts for one profile run, but defaults
  to one output file for each part.</para>

</sect2>

<sect2 id="cl-format.reference.header" xreflabel="Description of Header Lines">
<title>Description of Header Lines</title>

<para>Basic information in the first lines of a profile data file:</para>

<itemizedlist>
  <listitem>
    <para><computeroutput>version: number</computeroutput> [Callgrind]</para>
    <para>This is used to distinguish future profile data formats.  A
    major version of 0 or 1 is supposed to be upwards compatible with
    Cachegrind's format.  It is optional; if not appearing, version 1
    is assumed.  Otherwise, this has to be the first header line.</para>
  </listitem>

  <listitem>
    <para><computeroutput>creator: string</computeroutput> [Callgrind]</para>
    <para>This is an arbitrary string to denote the creator of this file.
      Optional.</para>
  </listitem>

</itemizedlist>

<para>The header for each part has an arbitrary number of lines of the format
"key: value". Possible <emphasis>key</emphasis> values for the header are:</para>

<itemizedlist>

  <listitem>
    <para><computeroutput>pid: process id</computeroutput> [Callgrind]</para>
    <para>Optional. This specifies the process ID of the supervised application
    for which this profile was generated.</para>
  </listitem>

  <listitem>
    <para><computeroutput>cmd: program name + args</computeroutput> [Cachegrind]</para>
    <para>Optional. This specifies the full command line of the supervised
    application for which this profile was generated.</para>
  </listitem>

  <listitem>
    <para><computeroutput>part: number</computeroutput> [Callgrind]</para>
    <para>Optional. This specifies a sequentially incremented number for each dump
    generated, starting at 1.</para>
  </listitem>

  <listitem>
    <para><computeroutput>desc: type: value</computeroutput> [Cachegrind]</para>
    <para>This specifies various information for this dump.  For some
    types, the semantic is defined, but any description type is allowed.
    Unknown types should be ignored.</para>
    <para>There are the types "I1 cache", "D1 cache", "LL cache", which
    specify parameters used for the cache simulator.  These are the only
    types originally used by Cachegrind.  Additionally, Callgrind uses
    the following types:  "Timerange" gives a rough range of the basic
    block counter, for which the cost of this dump was collected.
    Type "Trigger" states the reason of why this trace was generated.
    E.g. program termination or forced interactive dump.</para>
  </listitem>

  <listitem>
    <para><computeroutput>positions: [instr] [line]</computeroutput> [Callgrind]</para>
    <para>For cost lines, this defines the semantic of the first numbers.
    Any combination of "instr", "bb" and "line" is allowed, but has to be
    in this order which corresponds to position numbers at the start of
    the cost lines later in the file.</para>
    <para>If "instr" is specified, the position is the address of an
    instruction whose execution raised the events given later on the
    line.  This address is relative to the offset of the binary/shared
    library file to not have to specify relocation info.  For "line",
    the position is the line number of a source file, which is
    responsible for the events raised. Note that the mapping of "instr"
    and "line" positions are given by the debugging line information
    produced by the compiler.</para>
    <para>This header line is optional, defaulting to "positions:
    line" if not specified.</para>
  </listitem>

  <listitem>
    <para><computeroutput>events: event type abbreviations</computeroutput> [Cachegrind]</para>
    <para>A list of short names of the event types logged in cost
      lines in this part of the profile data file. Arbitrary short
      names are allowed.  The order given specifies the required order
      in cost lines. Thus, the first event type is the second or third
      number in a cost line, depending on the value of "positions".
      Required to appear for each header part exactly once.</para>
  </listitem>

  <listitem>
    <para><computeroutput>summary: costs</computeroutput> [Callgrind]</para>
    <para>Optional. This header line specifies a summary cost, which should be
    equal or larger than a total over all self costs. It may be larger as
    the cost lines may not represent all cost of the program run.</para>
  </listitem>

  <listitem>
    <para><computeroutput>totals: costs</computeroutput> [Cachegrind]</para>
    <para>Optional. Should appear at the end of the file (although
    looking like a header line). Must give the total of all cost lines,
    to allow for a consistency check.</para>
  </listitem>

</itemizedlist>

</sect2>

<sect2 id="cl-format.reference.body" xreflabel="Description of Body Lines">
<title>Description of Body Lines</title>

<para>The regular body line is a cost line consisting of one or two
position numbers (depending on "positions:" header line, see above)
and an array of cost numbers. A position number either is a
line numbers into a source file or an instruction address within binary
code, with source/binary file names specified as position names (see
below). The cost numbers get mapped to event types in the same order
as specified in the "events:" header line. If less numbers than event
types are given, the costs default to zero for the remaining event
types.</para>

<para>Further, there exist lines
<computeroutput>spec=position name</computeroutput>.  A position name
is an arbitrary string. If it starts with "(" and a
digit, it's a string in compressed format.  Otherwise it's the real
position string.  This allows for file and symbol names as position
strings, as these never start with "(" + <emphasis>digit</emphasis>.
The compressed format is either "(" <emphasis>number</emphasis> ")"
<emphasis>space</emphasis> <emphasis>position</emphasis> or only
"(" <emphasis>number</emphasis> ")".  The first relates
<emphasis>position</emphasis> to <emphasis>number</emphasis> in the
context of the given format specification from this line to the end of
the file; it makes the (<emphasis>number</emphasis>) an alias for
<emphasis>position</emphasis>.  Compressed format is always
optional.</para>

<para>Position specifications allowed:</para>
<itemizedlist>

  <listitem>
    <para><computeroutput>ob=</computeroutput> [Callgrind]</para>
    <para>The ELF object where the cost of next cost lines happens.</para>
  </listitem>

  <listitem>
    <para><computeroutput>fl=</computeroutput> [Cachegrind]</para>
  </listitem>

  <listitem>
    <para><computeroutput>fi=</computeroutput> [Cachegrind]</para>
  </listitem>

  <listitem>
    <para><computeroutput>fe=</computeroutput> [Cachegrind]</para>
    <para>The source file including the code which is responsible for
    the cost of next cost lines. "fi="/"fe=" is used when the source
    file changes inside of a function, i.e. for inlined code.</para>
  </listitem>

  <listitem>
    <para><computeroutput>fn=</computeroutput> [Cachegrind]</para>
    <para>The name of the function where the cost of next cost lines
    happens.</para>
  </listitem>

  <listitem>
     <para><computeroutput>cob=</computeroutput> [Callgrind]</para>
    <para>The ELF object of the target of the next call cost lines.</para>
  </listitem>

  <listitem>
    <para><computeroutput>cfi=</computeroutput> [Callgrind]</para>
    <para>The source file including the code of the target of the
    next call cost lines.</para>
  </listitem>

  <listitem>
    <para><computeroutput>cfl=</computeroutput> [Callgrind]</para>
    <para>Alternative spelling for <computeroutput>cfi=</computeroutput>
    specification (because of historical reasons).</para>
  </listitem>

  <listitem>
    <para><computeroutput>cfn=</computeroutput> [Callgrind]</para>
    <para>The name of the target function of the next call cost
    lines.</para>
  </listitem>

</itemizedlist>

<para>The last type of body line provides specific costs not just
related to one position as regular cost lines. It starts with specific
strings similar to position name specifications.</para>

<itemizedlist>

  <listitem>
    <para><computeroutput>calls=count target-position</computeroutput> [Callgrind]</para>
    <para>Call executed "count" times to "target-position".
    After a "calls=" line there MUST be a cost line. This provides the source position
    of the call and the cost spent in the called function in total.</para>
  </listitem>

  <listitem>
    <para><computeroutput>jump=count target-position</computeroutput> [Callgrind]</para>
    <para>Unconditional jump, executed "count" times, to "target-position".</para>
  </listitem>

  <listitem>
    <para><computeroutput>jcnd=exe-count jump-count target-position</computeroutput> [Callgrind]</para>
    <para>Conditional jump, executed "exe-count" times with "jump-count" jumps
    happening (rest is fall-through) to "target-position".</para>
  </listitem>

</itemizedlist>

</sect2>

</sect1>

</chapter>