#!/usr/bin/env perl
# time NUM_THREADS=3 perl pcount.pl big

use v5.36;
use autodie;
use MCE;

exit 1 if not @ARGV;

my $mul_pattern = 'mul\(\d{1,3},\d{1,3}\)';
my $filename = shift;
my $count = 0;

sub reduce_count ($worker_count) {
    $count += $worker_count;
}

my $mce = MCE->new(
    max_workers => $ENV{NUM_THREADS} // MCE::Util::get_ncpu(),
    chunk_size => 65536*16,
    use_slurpio => 1,
    gather => \&reduce_count,
    user_func => sub {
        my ($mce, $slurp_ref, $chunk_id) = @_;
        my $count = () = $$slurp_ref =~ m/$mul_pattern/g;
        $mce->gather($count);
    }
)->spawn;

$mce->process({ input_data => $filename });
$mce->shutdown;

print "Found $count matches.\n";

##</code><code>##

Found 1999533 matches.

1: 4.420s
2: 2.263s  needs 2 workers to reach Python performance
3: 1.511s
4: 1.154s
5: 0.940s
6: 0.788s
7: 0.680s
8: 0.600s
9: 0.538s

##</code><code>##

#!/usr/bin/env python
# time NUM_THREADS=3 python pcount.py big

import os, re, sys
from multiprocessing import Pool, cpu_count

if len(sys.argv) < 2: sys.exit(1)

def read_file (file, chunk_size=65536*16):
    """
    Lazy function generator to read a file in chunks,
    including to the end of line.
    """
    while True:
        chunk = file.read(chunk_size)
        if not chunk:
            break
        if not chunk.endswith('\n'):
            chunk += file.readline()
        yield chunk

def process_chunk(chunk):
    """
    Worker function to process chunks in parallel.
    """
    count = len(mul_re.findall(chunk))
    return count

mul_re = re.compile(r"mul\(\d{1,3},\d{1,3}\)")
num_processes = int(os.getenv('NUM_THREADS') or cpu_count())
p = Pool(num_processes)
file_name = sys.argv[1]

try:
    with open (file_name, "r") as file:
        results = p.map(process_chunk, read_file(file))
    p.close()
    p.join()
except Exception as e:
    print(e, file=sys.stderr)
    sys.exit(1)

print(f"Found {sum(results)} matches.")

##</code><code>##

Found 1999533 matches.

1: 3.131s
2: 1.824s
3: 1.408s
4: 1.178s
5: 1.187s
6: 1.187s
7: 1.172s
8: 1.008s
9: 0.995s