use Benchmark 'cmpthese';

$iterations = 1000000;     

%re = (
    foo => 'foo1',
    bar => 'bar1',
);

$re = join '|', keys %re;
$re = qr/($re)/;

$name1 = "RE";
$code1 = << 'END_CODE1';
    $_ = 'foo bar';
    s/$re/$re{$1}/g;
END_CODE1

$name2 = "Loop";
$code2 = << 'END_CODE2';
    $_ = 'foo bar';
    for my $sub( keys %re ) {
        s/$sub/$re{$sub}/g;
    }
END_CODE2


cmpthese( $iterations, {$name1 => $code1, $name2 => $code2} );

__END__
Benchmark: timing 1000000 iterations of Loop, RE...
      Loop: 24 wallclock secs (24.77 usr +  0.00 sys = 24.77 CPU) @ 40377.94/s (n=1000000)
        RE:  8 wallclock secs ( 7.27 usr +  0.00 sys =  7.27 CPU) @ 137551.58/s (n=1000000)
         Rate Loop   RE
Loop  40378/s   -- -71%
RE   137552/s 241%   --

##</code><code>##

$_ = 'foo bar' x 2000;

Benchmark: timing 10000 iterations of Loop, RE...
      Loop: 20 wallclock secs (19.90 usr +  0.00 sys = 19.90 CPU) @ 502.56/s (n=10000)
        RE: 30 wallclock secs (29.44 usr +  0.00 sys = 29.44 CPU) @ 339.64/s (n=10000)
      Rate   RE Loop
RE   340/s   -- -32%
Loop 503/s  48%   -

##</code><code>##

$_ = 'fo ba' x 1000 . 'foo bar';

Benchmark: timing 10000 iterations of Loop, RE...
      Loop:  1 wallclock secs ( 0.71 usr +  0.00 sys =  0.71 CPU) @ 14064.70/s (n=10000)
        RE: 12 wallclock secs (11.10 usr +  0.00 sys = 11.10 CPU) @ 901.23/s (n=10000)
        Rate    RE  Loop
RE     901/s    --  -94%
Loop 14065/s 1461%    --