X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/c5d572932fd269096c2a3545999d11f5ab9563b7..b05fd80e8a75b8bba137db6cd6688f7aa8a0ec39:/lib/Benchmark.pm diff --git a/lib/Benchmark.pm b/lib/Benchmark.pm index b557be3..1f31986 100644 --- a/lib/Benchmark.pm +++ b/lib/Benchmark.pm @@ -1,11 +1,16 @@ package Benchmark; +use strict; + + =head1 NAME Benchmark - benchmark running times of Perl code =head1 SYNOPSIS + use Benchmark qw(:all) ; + timethis ($count, "code"); # Use Perl code in strings... @@ -32,7 +37,7 @@ Benchmark - benchmark running times of Perl code }); # ...or in two stages - $results = timethese($count, + $results = timethese($count, { 'Name1' => sub { ...code1... }, 'Name2' => sub { ...code2... }, @@ -48,6 +53,9 @@ Benchmark - benchmark running times of Perl 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 @@ -73,9 +81,9 @@ countit - see how many times a chunk of code runs in a given time Returns the current time. Example: use Benchmark; - $t0 = new Benchmark; + $t0 = Benchmark->new; # ... your code here ... - $t1 = new Benchmark; + $t1 = Benchmark->new; $td = timediff($t1, $t0); print "the code took:",timestr($td),"\n"; @@ -83,9 +91,9 @@ Returns the current time. Example: Enables or disable debugging by setting the C<$Benchmark::Debug> flag: - debug Benchmark 1; + Benchmark->debug(1); $t = timeit(10, ' 5 ** $Global '); - debug Benchmark 0; + Benchmark->debug(0); =item iters @@ -153,7 +161,7 @@ The routines are called in string comparison order of KEY. The COUNT can be zero or negative, see timethis(). -Returns a hash of Benchmark objects, keyed by name. +Returns a hash reference of Benchmark objects, keyed by name. =item timediff ( T1, T2 ) @@ -194,19 +202,54 @@ Clear the cached time for COUNT rounds of the null loop. 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 fastest, 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 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() (or passed in). +in case you want to see both sets of results. +If the first argument is an unblessed hash reference, +that is RESULTSHASHREF; otherwise that is COUNT. + +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: This result value differs from previous versions, which returned +the C result structure. If you want that, just use the two +statement C...C idiom shown above. + +Incidentally, 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) @@ -240,6 +283,55 @@ 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 Benchmark Object + +Many of the functions in this module return a Benchmark object, +or in the case of C, a reference to a hash, the values of +which are Benchmark objects. This is useful if you want to store or +further process results from Benchmark functions. + +Internally the Benchmark object holds timing values, +described in L below. +The following methods can be used to access them: + +=over 4 + +=item cpu_p + +Total CPU (User + System) of the main (parent) process. + +=item cpu_c + +Total CPU (User + System) of any children processes. + +=item cpu_a + +Total CPU of parent and any children processes. + +=item real + +Real elapsed time "wallclock seconds". + +=item iters + +Number of iterations run. + +=back + +The following illustrates use of the Benchmark object: + + $result = timethis(100000, sub { ... }); + print "total CPU = ", $result->cpu_a, "\n"; + =head1 NOTES The data is stored as a list of values from the time and times @@ -268,35 +360,45 @@ calls like these: enablecache(); Caching is off by default, as it can (usually slightly) decrease -accuracy and does not usually noticably affect runtimes. +accuracy and does not usually noticeably affect runtimes. =head1 EXAMPLES For example, - use Benchmark;$x=3;cmpthese(-5,{a=>sub{$x*$x},b=>sub{$x**2}}) + 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... - 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% -- + Rate b a + b 1559428/s -- -62% + a 4152037/s 166% -- + -while +while - use Benchmark; - $x=3; - $r=timethese(-5,{a=>sub{$x*$x},b=>sub{$x**2}},'none'); - cmpthese($r); + use Benchmark qw( timethese cmpthese ) ; + $x = 3; + $r = timethese( -5, { + a => sub{$x*$x}, + b => sub{$x**2}, + } ); + cmpthese $r; outputs something like this: - Rate b a - b 1559428/s -- -62% - a 4152037/s 166% -- + 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 @@ -325,7 +427,7 @@ code and therefore the difference might end up being E 0. =head1 SEE ALSO -L - a Perl code profiler +L - a Perl code profiler =head1 AUTHORS @@ -342,14 +444,28 @@ documentation. April 04-07th, 1997: by Jarkko Hietaniemi, added the run-for-some-time functionality. -September, 1999; by Barrie Slaymaker: math fixes and accuracy and -efficiency tweaks. Added cmpthese(). A result is now returned from +September, 1999; by Barrie Slaymaker: math fixes and accuracy and +efficiency tweaks. Added cmpthese(). A result is now returned from 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. + +February, 2004; by Chia-liang Kao: make cmpthese and timestr use time +statistics for children instead of parent when the style is 'nop'. + +November, 2007; by Christophe Grosjean: make cmpthese and timestr compute +time consistently with style argument, default is 'all' not 'noc' any more. + =cut # evaluate something in a clean lexical environment -sub _doeval { eval shift } +sub _doeval { no strict; eval shift } # # put any lexicals at file scope AFTER here @@ -357,41 +473,110 @@ sub _doeval { eval shift } use Carp; use Exporter; -@ISA=(Exporter); + +our(@ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS, $VERSION); + +@ISA=qw(Exporter); @EXPORT=qw(timeit timethis timethese timediff timestr); @EXPORT_OK=qw(timesum cmpthese countit clearcache clearallcache disablecache enablecache); +%EXPORT_TAGS=( all => [ @EXPORT, @EXPORT_OK ] ) ; + +$VERSION = 1.19; + +# --- ':hireswallclock' special handling + +my $hirestime; -$VERSION = 1.00; +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" } @_; + local $^W=0; + *mytime = $hirestime if defined $hirestime; + } + Benchmark->export_to_level(1, $class, @_); +} -&init; +our($Debug, $Min_Count, $Min_CPU, $Default_Format, $Default_Style, + %_Usage, %Cache, $Do_Cache); sub init { - $debug = 0; - $min_count = 4; - $min_cpu = 0.4; - $defaultfmt = '5.2f'; - $defaultstyle = 'auto'; + $Debug = 0; + $Min_Count = 4; + $Min_CPU = 0.4; + $Default_Format = '5.2f'; + $Default_Style = 'auto'; # The cache can cause a slight loss of sys time accuracy. If a # user does many tests (>10) with *very* large counts (>10000) # or works on a very slow machine the cache may be useful. - &disablecache; - &clearallcache; + disablecache(); + clearallcache(); } -sub debug { $debug = ($_[1] != 0); } +sub debug { $Debug = ($_[1] != 0); } + +sub usage { + my $calling_sub = (caller(1))[3]; + $calling_sub =~ s/^Benchmark:://; + return $_Usage{$calling_sub} || ''; +} # The cache needs two branches: 's' for strings and 'c' for code. The -# emtpy loop is different in these two cases. -sub clearcache { delete $cache{"$_[0]c"}; delete $cache{"$_[0]s"}; } -sub clearallcache { %cache = (); } -sub enablecache { $cache = 1; } -sub disablecache { $cache = 0; } +# empty loop is different in these two cases. + +$_Usage{clearcache} = <<'USAGE'; +usage: clearcache($count); +USAGE + +sub clearcache { + die usage unless @_ == 1; + delete $Cache{"$_[0]c"}; delete $Cache{"$_[0]s"}; +} + +$_Usage{clearallcache} = <<'USAGE'; +usage: clearallcache(); +USAGE + +sub clearallcache { + die usage if @_; + %Cache = (); +} + +$_Usage{enablecache} = <<'USAGE'; +usage: enablecache(); +USAGE + +sub enablecache { + die usage if @_; + $Do_Cache = 1; +} + +$_Usage{disablecache} = <<'USAGE'; +usage: disablecache(); +USAGE + +sub disablecache { + die usage if @_; + $Do_Cache = 0; +} + # --- 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 ; } @@ -400,58 +585,94 @@ 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 { $_[0]->[5] ; } + +$_Usage{timediff} = <<'USAGE'; +usage: $result_diff = timediff($result1, $result2); +USAGE + sub timediff { my($a, $b) = @_; + + die usage unless ref $a and ref $b; + my @r; for (my $i=0; $i < @$a; ++$i) { push(@r, $a->[$i] - $b->[$i]); } + #die "Bad timediff(): ($r[1] + $r[2]) <= 0 (@$a[1,2]|@$b[1,2])\n" + # if ($r[1] + $r[2]) < 0; bless \@r; } +$_Usage{timesum} = <<'USAGE'; +usage: $sum = timesum($result1, $result2); +USAGE + sub timesum { - my($a, $b) = @_; - my @r; - for (my $i=0; $i < @$a; ++$i) { + my($a, $b) = @_; + + die usage unless ref $a and ref $b; + + my @r; + for (my $i=0; $i < @$a; ++$i) { push(@r, $a->[$i] + $b->[$i]); - } - bless \@r; + } + bless \@r; } + +$_Usage{timestr} = <<'USAGE'; +usage: $formatted_result = timestr($result1); +USAGE + sub timestr { my($tr, $style, $f) = @_; + + die usage unless ref $tr; + my @t = @$tr; warn "bad time value (@t)" unless @t==6; my($r, $pu, $ps, $cu, $cs, $n) = @t; my($pt, $ct, $tt) = ($tr->cpu_p, $tr->cpu_c, $tr->cpu_a); - $f = $defaultfmt unless defined $f; + $f = $Default_Format unless defined $f; # format a time in the required style, other formats may be added here - $style ||= $defaultstyle; + $style ||= $Default_Style; + 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)", + 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'; - $s=sprintf("%2d wallclock secs (%$f usr + %$f sys = %$f CPU)", + $s = sprintf("$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 && $pu+$ps; + my $elapsed = do { + if ($style eq 'nop') {$cu+$cs} + elsif ($style eq 'noc') {$pu+$ps} + else {$cu+$cs+$pu+$ps} + }; + $s .= sprintf(" @ %$f/s (n=$n)",$n/($elapsed)) if $n && $elapsed; $s; } sub timedebug { my($msg, $t) = @_; - print STDERR "$msg",timestr($t),"\n" if $debug; + print STDERR "$msg",timestr($t),"\n" if $Debug; } # --- Functions implementing low-level support for timing loops +$_Usage{runloop} = <<'USAGE'; +usage: runloop($number, [$string | $coderef]) +USAGE + sub runloop { my($n, $c) = @_; $n+=0; # force numeric now, so garbage won't creep into the eval croak "negative loopcount $n" if $n<0; - confess "Usage: runloop(number, [string | coderef])" unless defined $c; + confess usage unless defined $c; my($t0, $t1, $td); # before, after, difference # find package of caller so we can execute code there @@ -471,38 +692,55 @@ sub runloop { $subref = _doeval($subcode); } croak "runloop unable to compile '$c': $@\ncode: $subcode\n" if $@; - print STDERR "runloop $n '$subcode'\n" if $debug; + print STDERR "runloop $n '$subcode'\n" if $Debug; - # Wait for the user timer to tick. This makes the error range more like + # Wait for the user timer to tick. This makes the error range more like # -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 &countit. This, in turn, can reduce the number of calls to # &runloop a lot, and thus reduce additive errors. + # + # Note that its possible for the act of reading the system clock to + # burn lots of system CPU while we burn very little user clock in the + # busy loop, which can cause the loop to run for a very long wall time. + # So gradually ramp up the duration of the loop. See RT #122003 + # my $tbase = Benchmark->new(0)->[1]; - while ( ( $t0 = Benchmark->new(0) )->[1] == $tbase ) {} ; - &$subref; + my $limit = 1; + while ( ( $t0 = Benchmark->new(0) )->[1] == $tbase ) { + for (my $i=0; $i < $limit; $i++) { my $x = $i / 1.5 } # burn user CPU + $limit *= 1.1; + } + $subref->(); $t1 = Benchmark->new($n); $td = &timediff($t1, $t0); timedebug("runloop:",$td); $td; } +$_Usage{timeit} = <<'USAGE'; +usage: $result = timeit($count, 'code' ); or + $result = timeit($count, sub { code } ); +USAGE sub timeit { my($n, $code) = @_; my($wn, $wc, $wd); - printf STDERR "timeit $n $code\n" if $debug; + die usage unless defined $code and + (!ref $code or ref $code eq 'CODE'); + + printf STDERR "timeit $n $code\n" if $Debug; my $cache_key = $n . ( ref( $code ) ? 'c' : 's' ); - if ($cache && exists $cache{$cache_key} ) { - $wn = $cache{$cache_key}; + if ($Do_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; - $cache{$cache_key} = $wn; + $Cache{$cache_key} = $wn; } $wc = &runloop($n, $code); @@ -520,9 +758,16 @@ my $default_for = 3; my $min_for = 0.1; +$_Usage{countit} = <<'USAGE'; +usage: $result = countit($time, 'code' ); or + $result = countit($time, sub { code } ); +USAGE + sub countit { my ( $tmax, $code ) = @_; + die usage unless @_; + if ( not defined $tmax or $tmax == 0 ) { $tmax = $default_for; } elsif ( $tmax < 0 ) { @@ -535,9 +780,28 @@ sub countit { my ($n, $tc); # First find the minimum $n that gives a significant timing. + my $zeros=0; for ($n = 1; ; $n *= 2 ) { + my $t0 = Benchmark->new(0); my $td = timeit($n, $code); + my $t1 = Benchmark->new(0); $tc = $td->[1] + $td->[2]; + if ( $tc <= 0 and $n > 1024 ) { + my $d = timediff($t1, $t0); + # note that $d is the total CPU time taken to call timeit(), + # while $tc is is difference in CPU secs between the empty run + # and the code run. If the code is trivial, its possible + # for $d to get large while $tc is still zero (or slightly + # negative). Bail out once timeit() starts taking more than a + # few seconds without noticeable difference. + if ($d->[1] + $d->[2] > 8 + || ++$zeros > 16) + { + die "Timing is consistently zero in estimation loop, cannot benchmark. N=$n\n"; + } + } else { + $zeros = 0; + } last if $tc > 0.1; } @@ -548,8 +812,8 @@ sub countit { while ( $tc < $tpra ) { # The 5% fudge is to keep us from iterating again all # that often (this speeds overall responsiveness when $tmax is big - # and we guess a little low). This does not noticably affect - # accuracy since we're not couting these times. + # and we guess a little low). This does not noticeably affect + # accuracy since we're not counting these times. $n = int( $tpra * 1.05 * $n / $tc ); # Linear approximation. my $td = timeit($n, $code); my $new_tc = $td->[1] + $td->[2]; @@ -571,7 +835,7 @@ sub countit { # with stable times and avoiding extra timeit()s is nice for # accuracy's sake. $n = int( $n * ( 1.05 * $tmax / $tc ) ); - + $zeros=0; while () { my $td = timeit($n, $code); $ntot += $n; @@ -582,7 +846,12 @@ sub countit { $cstot += $td->[4]; $ttot = $utot + $stot; last if $ttot >= $tmax; - + if ( $ttot <= 0 ) { + ++$zeros > 16 + and die "Timing is consistently zero, cannot benchmark. N=$n\n"; + } else { + $zeros = 0; + } $ttot = 0.01 if $ttot < 0.01; my $r = $tmax / $ttot - 1; # Linear approximation. $n = int( $r * $ntot ); @@ -599,16 +868,24 @@ sub n_to_for { return $n == 0 ? $default_for : $n < 0 ? -$n : undef; } +$_Usage{timethis} = <<'USAGE'; +usage: $result = timethis($time, 'code' ); or + $result = timethis($time, sub { code } ); +USAGE + sub timethis{ my($n, $code, $title, $style) = @_; - my($t, $for, $forn); + my($t, $forn); + + die usage unless defined $code and + (!ref $code or ref $code eq 'CODE'); if ( $n > 0 ) { croak "non-integer loopcount $n, stopped" if int($n)<$n; $t = timeit($n, $code); $title = "timethis $n" unless defined $title; } else { - $fort = n_to_for( $n ); + my $fort = n_to_for( $n ); $t = countit( $fort, $code ); $title = "timethis for $fort" unless defined $title; $forn = $t->[-1]; @@ -616,7 +893,7 @@ sub timethis{ local $| = 1; $style = "" unless defined $style; printf("%10s: ", $title) unless $style eq 'none'; - print timestr($t, $style, $defaultfmt),"\n" unless $style eq 'none'; + print timestr($t, $style, $Default_Format),"\n" unless $style eq 'none'; $n = $forn if defined $forn; @@ -624,16 +901,22 @@ sub timethis{ # Don't assume that your benchmark is ok simply because # you don't get this warning! print " (warning: too few iterations for a reliable count)\n" - if $n < $min_count + if $n < $Min_Count || ($t->real < 1 && $n < 1000) - || $t->cpu_a < $min_cpu; + || $t->cpu_a < $Min_CPU; $t; } + +$_Usage{timethese} = <<'USAGE'; +usage: timethese($count, { Name1 => 'code1', ... }); or + timethese($count, { Name1 => sub { code1 }, ... }); +USAGE + sub timethese{ my($n, $alt, $style) = @_; - die "usage: timethese(count, { 'Name1'=>'code1', ... }\n" - unless ref $alt eq HASH; + die usage unless ref $alt eq 'HASH'; + my @names = sort keys %$alt; $style = "" unless defined $style; print "Benchmark: " unless $style eq 'none'; @@ -646,7 +929,8 @@ sub timethese{ 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 $style eq 'none'; @@ -660,11 +944,30 @@ sub timethese{ return \%results; } + +$_Usage{cmpthese} = <<'USAGE'; +usage: cmpthese($count, { Name1 => 'code1', ... }); or + cmpthese($count, { Name1 => sub { code1 }, ... }); or + cmpthese($result, $style); +USAGE + sub cmpthese{ - my $results = ref $_[0] ? $_[0] : timethese( @_ ); + my ($results, $style); + + # $count can be a blessed object. + if ( ref $_[0] eq 'HASH' ) { + ($results, $style) = @_; + } + else { + my($count, $code) = @_[0,1]; + $style = $_[2] if defined $_[2]; + + die usage unless ref $code eq 'HASH'; - return $results - if defined $_[2] && $_[2] eq 'none'; + $results = timethese($count, $code, ($style || "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; @@ -672,7 +975,12 @@ sub cmpthese{ for (@vals) { # The epsilon fudge here is to prevent div by 0. Since clock # resolutions are much larger, it's below the noise floor. - my $rate = $_->[6] / ( $_->[2] + $_->[3] + 0.000000000000001 ); + my $elapsed = do { + if ($style eq 'nop') {$_->[4]+$_->[5]} + elsif ($style eq 'noc') {$_->[2]+$_->[3]} + else {$_->[2]+$_->[3]+$_->[4]+$_->[5]} + }; + my $rate = $_->[6]/(($elapsed)+0.000000000000001); $_->[7] = $rate; } @@ -680,15 +988,15 @@ sub cmpthese{ @vals = sort { $a->[7] <=> $b->[7] } @vals; # If more than half of the rates are greater than one... - my $display_as_rate = $vals[$#vals>>1]->[7] > 1; + my $display_as_rate = @vals ? ($vals[$#vals>>1]->[7] > 1) : 0; my @rows; my @col_widths; - my @top_row = ( - '', - $display_as_rate ? 'Rate' : 's/iter', - map { $_->[0] } @vals + my @top_row = ( + '', + $display_as_rate ? 'Rate' : 's/iter', + map { $_->[0] } @vals ); push @rows, \@top_row; @@ -710,28 +1018,28 @@ sub cmpthese{ my $row_rate = $row_val->[7]; # We assume that we'll never get a 0 rate. - my $a = $display_as_rate ? $row_rate : 1 / $row_rate; + my $rate = $display_as_rate ? $row_rate : 1 / $row_rate; # Only give a few decimal places before switching to sci. notation, # since the results aren't usually that accurate anyway. - my $format = - $a >= 100 ? - "%0.0f" : - $a >= 10 ? + my $format = + $rate >= 100 ? + "%0.0f" : + $rate >= 10 ? "%0.1f" : - $a >= 1 ? + $rate >= 1 ? "%0.2f" : - $a >= 0.1 ? + $rate >= 0.1 ? "%0.3f" : "%0.2e"; $format .= "/s" if $display_as_rate; - # Using $b here due to optimizing bug in _58 through _61 - my $b = sprintf( $format, $a ); - push @row, $b; - $col_widths[1] = length( $b ) - if length( $b ) > $col_widths[1]; + + my $formatted_rate = sprintf( $format, $rate ); + push @row, $formatted_rate; + $col_widths[1] = length( $formatted_rate ) + if length( $formatted_rate ) > $col_widths[1]; # Columns 2..N = performance ratios my $skip_rest = 0; @@ -753,16 +1061,18 @@ sub cmpthese{ $col_widths[$col_num+2] = length( $out ) if length( $out ) > $col_widths[$col_num+2]; - # A little wierdness to set the first column width properly + # A little weirdness to set the first column width properly $col_widths[$col_num+2] = length( $col_val->[0] ) if length( $col_val->[0] ) > $col_widths[$col_num+2]; } 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 = + my @sorted_width_refs = sort { $$a <=> $$b } map { \$_ } @col_widths[2..$#col_widths]; my $max_width = ${$sorted_width_refs[-1]}; @@ -775,7 +1085,7 @@ sub cmpthese{ last if $min_width == $max_width; for ( @sorted_width_refs ) { - last + last if $$_ > $min_width; ++$$_; ++$total; @@ -791,7 +1101,7 @@ sub cmpthese{ printf $format, @$_; } - return $results; + return \@rows ; }