=head1 NAME
-Benchmark - benchmark running times of code
-
-timethis - run a chunk of code several times
-
-timethese - run several chunks of code several times
-
-timeit - run a chunk of code and see how long it goes
+Benchmark - benchmark running times of Perl code
=head1 SYNOPSIS
+ use Benchmark qw(:all) ;
+
timethis ($count, "code");
# Use Perl code in strings...
'Name2' => sub { ...code2... },
});
+ # cmpthese can be used both ways as well
+ cmpthese($count, {
+ 'Name1' => '...code1...',
+ 'Name2' => '...code2...',
+ });
+
+ cmpthese($count, {
+ 'Name1' => sub { ...code1... },
+ 'Name2' => sub { ...code2... },
+ });
+
+ # ...or in two stages
+ $results = timethese($count,
+ {
+ 'Name1' => sub { ...code1... },
+ 'Name2' => sub { ...code2... },
+ },
+ 'none'
+ );
+ cmpthese( $results ) ;
+
$t = timeit($count, '...other code...')
print "$count loops of other code took:",timestr($t),"\n";
+ $t = countit($time, '...other code...')
+ $count = $t->iters ;
+ print "$count loops of other code took:",timestr($t),"\n";
+
+ # enable hires wallclock timing if possible
+ use Benchmark ':hireswallclock';
+
=head1 DESCRIPTION
The Benchmark module encapsulates a number of routines to help you
figure out how long it takes to execute some code.
+timethis - run a chunk of code several times
+
+timethese - run several chunks of code several times
+
+cmpthese - print results of timethese as a comparison chart
+
+timeit - run a chunk of code and see how long it goes
+
+countit - see how many times a chunk of code runs in a given time
+
+
=head2 Methods
=over 10
$t = timeit(10, ' 5 ** $Global ');
debug Benchmark 0;
+=item iters
+
+Returns the number of iterations.
+
=back
=head2 Standard Exports
Returns the difference between two Benchmark times as a Benchmark
object suitable for passing to timestr().
-=item timesum ( T1, T2 )
-
-Returns the sum of two Benchmark times as a Benchmark object suitable
-for passing to timestr().
-
=item timestr ( TIMEDIFF, [ STYLE, [ FORMAT ] ] )
Returns a string that formats the times in the TIMEDIFF object in
Clear all cached times.
-=item cmpthese ( COUT, CODEHASHREF, [ STYLE ] )
+=item cmpthese ( COUNT, CODEHASHREF, [ STYLE ] )
+
+=item cmpthese ( RESULTSHASHREF, [ STYLE ] )
+
+Optionally calls timethese(), then outputs comparison chart. This:
+
+ cmpthese( -1, { a => "++\$i", b => "\$i *= 2" } ) ;
+
+outputs a chart like:
-=item cmpthese ( RESULTSHASHREF )
+ Rate b a
+ b 2831802/s -- -61%
+ a 7208959/s 155% --
-Optionally calls timethese(), then outputs comparison chart. This
-chart is sorted from slowest to highest, and shows the percent
-speed difference between each pair of tests. Can also be passed
-the data structure that timethese() returns:
+This chart is sorted from slowest to fastest, and shows the percent speed
+difference between each pair of tests.
- $results = timethese( .... );
+c<cmpthese> can also be passed the data structure that timethese() returns:
+
+ $results = timethese( -1, { a => "++\$i", b => "\$i *= 2" } ) ;
cmpthese( $results );
-Returns the data structure returned by timethese().
+in case you want to see both sets of results.
+
+Returns a reference to an ARRAY of rows, each row is an ARRAY of cells from the
+above chart, including labels. This:
+
+ my $rows = cmpthese( -1, { a => '++$i', b => '$i *= 2' }, "none" );
+
+returns a data structure like:
+
+ [
+ [ '', 'Rate', 'b', 'a' ],
+ [ 'b', '2885232/s', '--', '-59%' ],
+ [ 'a', '7099126/s', '146%', '--' ],
+ ]
+
+B<NOTE>: This result value differs from previous versions, which returned
+the C<timethese()> result structure. If you want that, just use the two
+statement C<timethese>...C<cmpthese> idiom shown above.
+
+Incidently, note the variance in the result values between the two examples;
+this is typical of benchmarking. If this were a real benchmark, you would
+probably want to run a lot more iterations.
+
+=item countit(TIME, CODE)
+
+Arguments: TIME is the minimum length of time to run CODE for, and CODE is
+the code to run. CODE may be either a code reference or a string to
+be eval'd; either way it will be run in the caller's package.
+
+TIME is I<not> negative. countit() will run the loop many times to
+calculate the speed of CODE before running it for TIME. The actual
+time run for will usually be greater than TIME due to system clock
+resolution, so it's best to look at the number of iterations divided
+by the times that you are concerned with, not just the iterations.
+
+Returns: a Benchmark object.
=item disablecache ( )
rounds of the null loop will be calculated only once for each
different COUNT used.
+=item timesum ( T1, T2 )
+
+Returns the sum of two Benchmark times as a Benchmark object suitable
+for passing to timestr().
+
=back
+=head2 :hireswallclock
+
+If the Time::HiRes module has been installed, you can specify the
+special tag C<:hireswallclock> for Benchmark (if Time::HiRes is not
+available, the tag will be silently ignored). This tag will cause the
+wallclock time to be measured in microseconds, instead of integer
+seconds. Note though that the speed computations are still conducted
+in CPU time, not wallclock time.
+
=head1 NOTES
The data is stored as a list of values from the time and times
functions:
- ($real, $user, $system, $children_user, $children_system)
+ ($real, $user, $system, $children_user, $children_system, $iters)
in seconds for the whole loop (not divided by the number of rounds).
Caching is off by default, as it can (usually slightly) decrease
accuracy and does not usually noticably affect runtimes.
+=head1 EXAMPLES
+
+For example,
+
+ use Benchmark qw( cmpthese ) ;
+ $x = 3;
+ cmpthese( -5, {
+ a => sub{$x*$x},
+ b => sub{$x**2},
+ } );
+
+outputs something like this:
+
+ Benchmark: running a, b, each for at least 5 CPU seconds...
+ Rate b a
+ b 1559428/s -- -62%
+ a 4152037/s 166% --
+
+
+while
+
+ use Benchmark qw( timethese cmpthese ) ;
+ $x = 3;
+ $r = timethese( -5, {
+ a => sub{$x*$x},
+ b => sub{$x**2},
+ } );
+ cmpthese $r;
+
+outputs something like this:
+
+ Benchmark: running a, b, each for at least 5 CPU seconds...
+ a: 10 wallclock secs ( 5.14 usr + 0.13 sys = 5.27 CPU) @ 3835055.60/s (n=20210743)
+ b: 5 wallclock secs ( 5.41 usr + 0.00 sys = 5.41 CPU) @ 1574944.92/s (n=8520452)
+ Rate b a
+ b 1574945/s -- -59%
+ a 3835056/s 144% --
+
+
=head1 INHERITANCE
Benchmark inherits from no other class, except of course
=head1 CAVEATS
Comparing eval'd strings with code references will give you
-inaccurate results: a code reference will show a slower
+inaccurate results: a code reference will show a slightly slower
execution time than the equivalent eval'd string.
The real time timing is done using time(2) and
more than the system time of the loop with the actual
code and therefore the difference might end up being E<lt> 0.
+=head1 SEE ALSO
+
+L<Devel::DProf> - a Perl code profiler
+
=head1 AUTHORS
Jarkko Hietaniemi <F<jhi@iki.fi>>, Tim Bunce <F<Tim.Bunce@ig.co.uk>>
September, 1999; by Barrie Slaymaker: math fixes and accuracy and
efficiency tweaks. Added cmpthese(). A result is now returned from
-timethese().
+timethese(). Exposed countit() (was runfor()).
+
+December, 2001; by Nicholas Clark: make timestr() recognise the style 'none'
+and return an empty string. If cmpthese is calling timethese, make it pass the
+style in. (so that 'none' will suppress output). Make sub new dump its
+debugging output to STDERR, to be consistent with everything else.
+All bugs found while writing a regression test.
+
+September, 2002; by Jarkko Hietaniemi: add ':hireswallclock' special tag.
=cut
use Carp;
use Exporter;
@ISA=(Exporter);
-@EXPORT=qw(timeit timethis timethese timediff timesum timestr);
-@EXPORT_OK=qw(clearcache clearallcache cmpthese disablecache enablecache);
+@EXPORT=qw(timeit timethis timethese timediff timestr);
+@EXPORT_OK=qw(timesum cmpthese countit
+ clearcache clearallcache disablecache enablecache);
+%EXPORT_TAGS=( all => [ @EXPORT, @EXPORT_OK ] ) ;
+
+$VERSION = 1.0501;
+
+# --- ':hireswallclock' special handling
+
+my $hirestime;
+
+sub mytime () { time }
&init;
+sub BEGIN {
+ if (eval 'require Time::HiRes') {
+ import Time::HiRes qw(time);
+ $hirestime = \&Time::HiRes::time;
+ }
+}
+
+sub import {
+ my $class = shift;
+ if (grep { $_ eq ":hireswallclock" } @_) {
+ @_ = grep { $_ ne ":hireswallclock" } @_;
+ *mytime = $hirestime if defined $hirestime;
+ }
+ Benchmark->export_to_level(1, $class, @_);
+}
+
sub init {
$debug = 0;
$min_count = 4;
# --- Functions to process the 'time' data type
-sub new { my @t = (time, times, @_ == 2 ? $_[1] : 0);
- print "new=@t\n" if $debug;
+sub new { my @t = (mytime, times, @_ == 2 ? $_[1] : 0);
+ print STDERR "new=@t\n" if $debug;
bless \@t; }
sub cpu_p { my($r,$pu,$ps,$cu,$cs) = @{$_[0]}; $pu+$ps ; }
sub cpu_c { my($r,$pu,$ps,$cu,$cs) = @{$_[0]}; $cu+$cs ; }
sub cpu_a { my($r,$pu,$ps,$cu,$cs) = @{$_[0]}; $pu+$ps+$cu+$cs ; }
sub real { my($r,$pu,$ps,$cu,$cs) = @{$_[0]}; $r ; }
+sub iters { $_[0]->[5] ; }
sub timediff {
my($a, $b) = @_;
my @t = @$tr;
warn "bad time value (@t)" unless @t==6;
my($r, $pu, $ps, $cu, $cs, $n) = @t;
- my($pt, $ct, $t) = ($tr->cpu_p, $tr->cpu_c, $tr->cpu_a);
+ my($pt, $ct, $tt) = ($tr->cpu_p, $tr->cpu_c, $tr->cpu_a);
$f = $defaultfmt unless defined $f;
# format a time in the required style, other formats may be added here
$style ||= $defaultstyle;
+ return '' if $style eq 'none';
$style = ($ct>0) ? 'all' : 'noc' if $style eq 'auto';
my $s = "@t $style"; # default for unknown style
- $s=sprintf("%2d wallclock secs (%$f usr %$f sys + %$f cusr %$f csys = %$f CPU)",
- @t,$t) if $style eq 'all';
- $s=sprintf("%2d wallclock secs (%$f usr + %$f sys = %$f CPU)",
+ my $w = $hirestime ? "%2g" : "%2d";
+ $s=sprintf("$w wallclock secs (%$f usr %$f sys + %$f cusr %$f csys = %$f CPU)",
+ $r,$pu,$ps,$cu,$cs,$tt) if $style eq 'all';
+ $s=sprintf("$w wallclock secs (%$f usr + %$f sys = %$f CPU)",
$r,$pu,$ps,$pt) if $style eq 'noc';
- $s=sprintf("%2d wallclock secs (%$f cusr + %$f csys = %$f CPU)",
+ $s=sprintf("$w wallclock secs (%$f cusr + %$f csys = %$f CPU)",
$r,$cu,$cs,$ct) if $style eq 'nop';
- $s .= sprintf(" @ %$f/s (n=$n)", $n / ( $pu + $ps )) if $n;
+ $s .= sprintf(" @ %$f/s (n=$n)", $n / ( $pu + $ps )) if $n && $pu+$ps;
$s;
}
# -0.01, +0. If we don't wait, then it's more like -0.01, +0.01. This
# may not seem important, but it significantly reduces the chances of
# getting a too low initial $n in the initial, 'find the minimum' loop
- # in &runfor. This, in turn, can reduce the number of calls to
+ # in &countit. This, in turn, can reduce the number of calls to
# &runloop a lot, and thus reduce additive errors.
my $tbase = Benchmark->new(0)->[1];
- do {
- $t0 = Benchmark->new(0);
- } while ( $t0->[1] == $tbase );
+ while ( ( $t0 = Benchmark->new(0) )->[1] == $tbase ) {} ;
&$subref;
$t1 = Benchmark->new($n);
$td = &timediff($t1, $t0);
if ($cache && exists $cache{$cache_key} ) {
$wn = $cache{$cache_key};
} else {
- $wn = &runloop($n, ref( $code ) ? sub { undef } : '' );
+ $wn = &runloop($n, ref( $code ) ? sub { } : '' );
# Can't let our baseline have any iterations, or they get subtracted
# out of the result.
$wn->[5] = 0;
my $min_for = 0.1;
-sub runfor {
- my ($code, $tmax) = @_;
+sub countit {
+ my ( $tmax, $code ) = @_;
if ( not defined $tmax or $tmax == 0 ) {
$tmax = $default_for;
$tmax = -$tmax;
}
- die "runfor(..., $tmax): timelimit cannot be less than $min_for.\n"
+ die "countit($tmax, ...): timelimit cannot be less than $min_for.\n"
if $tmax < $min_for;
my ($n, $tc);
# accuracy since we're not couting these times.
$n = int( $tpra * 1.05 * $n / $tc ); # Linear approximation.
my $td = timeit($n, $code);
- $tc = $td->[1] + $td->[2];
+ my $new_tc = $td->[1] + $td->[2];
+ # Make sure we are making progress.
+ $tc = $new_tc > 1.2 * $tc ? $new_tc : 1.2 * $tc;
}
# Now, do the 'for real' timing(s), repeating until we exceed
$ttot = $utot + $stot;
last if $ttot >= $tmax;
+ $ttot = 0.01 if $ttot < 0.01;
my $r = $tmax / $ttot - 1; # Linear approximation.
$n = int( $r * $ntot );
$n = $nmin if $n < $nmin;
$title = "timethis $n" unless defined $title;
} else {
$fort = n_to_for( $n );
- $t = runfor($code, $fort);
+ $t = countit( $fort, $code );
$title = "timethis for $fort" unless defined $title;
$forn = $t->[-1];
}
print " ", join(', ',@names) unless $style eq 'none';
unless ( $n > 0 ) {
my $for = n_to_for( $n );
- print ", each for at least $for CPU seconds" unless $style eq 'none';
+ print ", each" if $n > 1 && $style ne 'none';
+ print " for at least $for CPU seconds" unless $style eq 'none';
}
print "...\n" unless $style eq 'none';
}
sub cmpthese{
- my $results = ref $_[0] ? $_[0] : timethese( @_ );
+ my ($results, $style) =
+ ref $_ [0] ? @_
+ : (timethese (@_ [0, 1], @_ > 2 ? $_ [2] : "none"), $_ [2]);
- return $results
- if defined $_[2] && $_[2] eq 'none';
+ $style = "" unless defined $style;
# Flatten in to an array of arrays with the name as the first field
my @vals = map{ [ $_, @{$results->{$_}} ] } keys %$results;
push @rows, \@row;
}
+ return \@rows if $style eq "none";
+
# Equalize column widths in the chart as much as possible without
# exceeding 80 characters. This does not use or affect cols 0 or 1.
my @sorted_width_refs =
sort { $$a <=> $$b } map { \$_ } @col_widths[2..$#col_widths];
my $max_width = ${$sorted_width_refs[-1]};
- my $total = 0;
+ my $total = @col_widths - 1 ;
for ( @col_widths ) { $total += $_ }
STRETCHER:
printf $format, @$_;
}
- return $results;
+ return \@rows ;
}