my $MSB       = 1<<31;
my $SET_MSB   = pack "I",$MSB;
my $UNSET_MSB = pack "I",$MSB-1;

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

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

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

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

__DATA__

C:\>serialize.pl
Doing 250000 tests
pack time 4
length 4000000
unpack time 1

C:\>