Just be careful to create your data as bitstrings in the first place. If you create arrays and then turn them into bitstrings to do the comparison, then it is not that fast:
use strict;
use warnings;
use Benchmark 'cmpthese';
sub create { map {rand() < $_[1] ? 1 : 0} 1..$_[0] }
sub compare2a { # first find 1s in x, then check in ys
my $x = shift;
my $n = shift;
my @nxs = grep { $x->[$_] } 0..$n-1;
return map { scalar grep {$_} @{$_}[@nxs] } @_;
}
sub compare4 { # bitstrings
my $x = shift;
$x = pack 'b*', join '', @$x;
return map { unpack '%32b*', ( $x & pack 'b*', join'',@$_ ) } @_;
}
my $n = 15000;
my $p = 0.005;
my $ny = 10;
my @x = create $n, $p;
my @ys = map { [ create $n, $p ] } 1..$ny;
my @r2a = compare2a \@x, $n, @ys;
my @r4 = compare4 \@x, @ys;
print "compare2a: @r2a\n";
print "compare4: @r4\n";
cmpthese( -5, {
compare2a => sub{ compare2a \@x, $n, @ys },
compare4 => sub{ compare4 \@x, @ys },
}
);
Result:
Rate compare4 compare2a
compare4 246/s -- -55%
compare2a 543/s 120% --
|