use Algorithm::Loops      qw( NestedLoops );
use Parallel::ForkManager qw( );

my $num_jobs_log6 = 4;   # 6*6*6*6 jobs.
my $num_workers = 64;    # 20.25 jobs/worker (on average).

my $pm = Parallel::ForkManager->new($num_workers);

my @param_arr;
$pm->run_on_finish(sub{
   my ($pid, $exit_code, $ident, $exit_signal, undef, $data) = @_;
   die("Child killed by signal $exit_signal\n") if $exit_signal;
   die("Child return error $exit_code\n") if $exit_code;

   push @param_arr, @$data;
});

my @ps = map { $_ * 0.2 } 0..5;
my $outer_iter = NestedLoops([ (\@ps) * $num_jobs_log6 ]);
while (my @p_outer = $outer_iter->()) {
   my $p_outer = join("\t", @p_outer);
   $pm->start() and next;

   my @child_output;
   my $inner_iter = NestedLoops([
      (\@ps) * ( 11 - $num_jobs_log6 ),
      [ 1 ], 
      [ 1 ],
   ]);
   while (my @p_inner = $inner_iter->()) {
      push @child_output, $p_outer . join("\t", @p_inner) . "\n";
   }

   $pm_finish(0, \@output);
}

$pm->wait_all_children();