For larger data files and not wanting to deal with chunking manually, then there is the parallel MCE module. This is what one might construct using the MCE::Flow module. We're running 4 workers. Therefore chunking at 24 MB is plenty. Perl and CPAN are amazing allowing this.

use strict;
use warnings;
use autodie;
use MCE::Flow;

open Newfile, ">", "./Newfile.txt" or die "Cannot create Newfile.txt";

Newfile->autoflush(1);  # important, enable autoflush

my ($f1, $f2, @seq) = ('seq.txt', 'mytext.txt');

open(my $fh, $f1);
foreach (<$fh>) {
  chomp; s/^\s+|\s+$//g;
  push @seq, $_;
}
close $fh;

@seq = sort bylen @seq;  # need to sort @seq by length.

MCE::Flow::init {
  max_workers => 4, chunk_size  => '24m',
  init_relay  => 1, use_slurpio => 1,
};

# For best performance, provide MCE the path, e.g. $f2
# versus a file handle. Workers communicate among themselves
# the next offset without involving the manager process.

mce_flow_f sub {
  my ($mce, $slurp_ref, $chunk_id) = @_;

  foreach my $r (@seq) {
    my $t = $r; $t =~ s/\h+/bbb/g;
    $$slurp_ref =~ s/$r/$t/g;
  }

  # Relay capability is useful for running something orderly.
  # For this use case, we've enabled autoflush on the file above.
  # Only one worker is allowed to run when entering the block.

  MCE::relay sub { print Newfile $$slurp_ref };
},
$f2;

MCE::Flow::finish();

close Newfile;

exit 0;

sub bylen {
  length($b) <=> length($a);
}
[download]