my @arr = unpack('A8A8A8A8A8A8A8A8A8A8A8A8A8A8A8A8A8A8A8A8', $str);

##</code><code>##

# No longer wins but is still faster than '(A8)*'
my @arr = unpack((join '', ('A8' x ($strlen / 8))), $str);

##</code><code>##

#!/usr/bin/perl
use strict;
use warnings;
use Benchmark 'cmpthese';

my $str = "abcdefgh12345678" x 2000;
my $strlen = length $str;
my $end = $strlen / 8 - 1;
my $fmt = join '', ('A8' x ($strlen / 8));
my @pos = map {$_ * 8} 0 .. $end;

cmpthese(-3, {
    'regex'      => sub { my @arr = $str =~ /(........)/g;},
    'split_grep' => sub { my @arr = grep $_, split /(.{8})/, $str;},
    'split_pos'  => sub { my @arr = split /(?(?{pos() % 8})(?!))/, $str;},
    'substr_map' => sub { my @arr = map substr($str, $_, 8), @pos;},
    'substr_for' => sub { my @arr; push @arr, substr($str, $_, 8) for @pos;},
    'unpack'     => sub { my @arr = unpack($fmt, $str);}
});
__DATA__
             Rate  split_pos split_grep substr_map     unpack substr_for
split_pos  38.2/s         --       -28%       -54%       -57%       -74%
split_grep 53.1/s        39%         --       -36%       -41%       -64%
regex      77.4/s      110%        52%        --        -3%      -12%       -46%
substr_map 82.3/s       115%        55%         --        -8%       -45%
unpack     89.5/s       134%        69%         9%         --       -40%
substr_for  149/s       291%       182%        81%        67%         --