my $MSB       = 1<<31;

my $tests = 250_000;
my $DEBUG =1;
print "Doing $tests tests\n";
my $pack = time();

my $str = '';
for my $doc_id( 1 .. $tests ) {
    #printf "Doc id: %d\n", $doc_id if $DEBUG;
    $str .= pack "w", $doc_id+$MSB;
    for my $pos ( 0 .. 2 ) {
        $str .= pack "w", $pos;
    }
}
printf "pack time %d\n", time()-$pack;
printf "length %d\n", length $str;
my $unpack = time();

my $dat = {};
my $doc_id = undef;
for my $int (unpack "w*", $str) {
    if ( $int > $MSB ) 
    {
        $doc_id = $int - $MSB;
        #printf "\nDoc id: %d\t", $doc_id if $DEBUG;
    }
    else 
    {
        push @{$dat->{$doc_id}}, $int;
        #print "$int\t" if $DEBUG;
    }
}

printf "\n\nunpack time %d\n",time()-$unpack;

__DATA__
C:\>serialize.pl
Doing 250000 tests
pack time 2
length 2000000
unpack time 2

C:\>