#! perl -slw
use strict;
use threads;
use threads::shared;

sub sumEm{
    my $tid = threads->tid;
    my( $AoARef, $first, $n ) = @_;
    print "$tid: $first - ", $first + $n - 1;
    my @sums = ( 0 ) x 4;
    for my $i ( $first .. $first+$n-1 ) {
        $sums[ $_ ] += $AoARef->[ $i ][ $_ ] for 0 .. 3;
    }
    return @sums;
}

our $N ||= 1e6;
our $T ||= 4;

my @AoA:shared;
$#AoA = $N;

for( 0 .. $N -1 ) {
    $AoA[ $_ ] = &share([]);
    @{ $AoA[ $_ ] } = map rand( 100 ), 1 .. $T;
}

my $perThread = int $N / $T;
my @threads = map{
   threads->create( \&sumEm, \@AoA, $_* $perThread, $perThread )
} 0 .. $T-1;

my @aves = ( 0 ) x 4;
for my $thread ( @threads ) {
    my @subtotals = $thread->join;
    $aves[ $_ ] += $subtotals[ $_ ] for 0 .. 3;
}

$_ /= $N for @aves;

print "@aves";