=head1 NOTHING is faster in 5.10

E<AElig>var ArnfjE<ouml>rE<eth> Bjarmason <avar@cpan.org>

=head1 split optimizations

Handled by custom C code in C<pp_split>. Will never reach the regex
engine (see B<perlreapi.pod>)

=begin perl

    my @line = split /^/, $text;

    my @word = split /\s+/, $text;

    my @char = split //, $text; # NEW!

    # Hands in the air if you know what this does
    my @what = split ' ', $text;

=end perl

=head1 The benchmark

=begin perl

use Benchmark ':all';

my $str = ("hlagh" x 666);

cmpthese(-1, {
    old  => sub { split / /x, $str },
    new  => sub { split //, $str },
    pack => sub { unpack "(a)*", $str },
});

=end perl

=head1 Benchmark results

The new C<split //> is around 3x faster than it was in 5.8.8

=begin perl

    old  => sub { split / /x, $str },
    new  => sub { split //, $str },
    pack => sub { unpack "(a)*", $str },

=end perl

=begin text

          Rate  old pack  new
    old  182/s   -- -61% -72%
    pack 473/s 160%   -- -28%
    new  661/s 262%  40%   --

=end text

=cut

=head1 The benchmark lies...

...unless you compiled with C<-DSTUPID_PATTERN_CHECKS>

./Configure -A ccflags=-DSTUPID_PATTERN_CHECKS

=begin text

$ perl5.9.5 -Mre=Debug,DUMP -e '//; /(?#I CAN HAS OPTIMIZE?!)/'
Compiling REx ""
Final program:
   1: NOTHING (2)
   2: END (0)
minlen 0
Compiling REx "(?#I CAN HAS OPTIMIZE?!)"
Final program:
   1: NOTHING (2)
   2: END (0)
minlen 0

=end text

=head1 split is rarely the bottleneck

=begin perl

    old  => sub { () = map { chr } split /(?:)/x, $str },
    new  => sub { () = map { chr } split //, $str },
    pack => sub { () = unpack "(C)*", $str },

=end perl

=begin text

           Rate  old  new pack
    old  80.7/s   -- -31% -89%
    new   117/s  45%   -- -84%
    pack  725/s 798% 518%   --

=end text

=cut