use Benchmark qw(:all) ;
use PDL;

my @runs = (
	[1, 10_000_000],
	[10_000, 1000],
	[1000, 10_000],
	[10_000_000, 1]
);

for my $run (@runs) {
	my $count = $run->[0]; my $loops = $run->[1];
	print "Test with count: $count, loops: $loops\n" . "-" x 50 . "\n";
	timethese($count, {
		'for' => sub { my @out = (); for (1 .. $loops) { push @out, $_ * $_;} },
		'map' => sub { my @out = map { $_ * $_ } (1 .. $loops); },
		'pdl' => sub { my $in = pdl(1 .. $loops); my $out = $in * $in; }
	});
}

##</code><code>##

Test with count: 1, loops: 10000000
--------------------------------------------------
Benchmark: timing 1 iterations of for, map, pdl...
       for:  2 wallclock secs ( 2.12 usr +  0.29 sys =  2.41 CPU) @  0.41/s (n=1)
            (warning: too few iterations for a reliable count)
       map:  5 wallclock secs ( 3.86 usr +  1.15 sys =  5.01 CPU) @  0.20/s (n=1)
            (warning: too few iterations for a reliable count)
       pdl: 17 wallclock secs ( 2.83 usr +  0.70 sys =  3.53 CPU) @  0.28/s (n=1)
            (warning: too few iterations for a reliable count)

Test with count: 10000, loops: 1000
--------------------------------------------------
Benchmark: timing 10000 iterations of for, map, pdl...
       for:  2 wallclock secs ( 1.86 usr +  0.00 sys =  1.86 CPU) @ 5376.34/s (n=10000)
       map:  3 wallclock secs ( 3.37 usr +  0.00 sys =  3.37 CPU) @ 2967.36/s (n=10000)
       pdl:  3 wallclock secs ( 2.15 usr +  0.01 sys =  2.16 CPU) @ 4629.63/s (n=10000)

Test with count: 1000, loops: 10000
--------------------------------------------------
Benchmark: timing 1000 iterations of for, map, pdl...
       for:  1 wallclock secs ( 1.84 usr +  0.00 sys =  1.84 CPU) @ 543.48/s (n=1000)
       map:  4 wallclock secs ( 3.39 usr +  0.00 sys =  3.39 CPU) @ 294.99/s (n=1000)
       pdl:  2 wallclock secs ( 1.98 usr +  0.01 sys =  1.99 CPU) @ 502.51/s (n=1000)

Test with count: 10000000, loops: 1
--------------------------------------------------
Benchmark: timing 10000000 iterations of for, map, pdl...
       for: 10 wallclock secs ( 8.82 usr +  0.01 sys =  8.83 CPU) @ 1132502.83/s (n=10000000)
       map:  7 wallclock secs ( 6.40 usr + -0.01 sys =  6.39 CPU) @ 1564945.23/s (n=10000000)
       pdl: 201 wallclock secs (198.35 usr +  0.28 sys = 198.63 CPU) @ 50344.86/s (n=10000000)