The Computer Language
Benchmarks Game

k-nucleotide Perl program

source code

#  The Computer Language Benchmarks Game
#  http://benchmarksgame.alioth.debian.org/

#  contributed by Karl FORNER
# (borrowed fasta loading routine from Kjetil Skotheim, 2005-11-29)
# Corrected again by Jesse Millikan
# revised by Kuang-che Wu
# Multi-threaded by Andrew Rodland

use strict;
use threads;

my $threads = num_cpus() || 1;

my ($sequence, $begin, $end);
$/ = ">";
/^THREE/ and $sequence = uc(join "", grep !/^THREE/, split /\n+/) while <STDIN>;

my ($l,%h,$sum) = (length $sequence);

foreach my $frame (1,2) {
  %h = ();
  update_hash_for_frame($frame);
  $sum = $l - $frame + 1;
  printf "$_ %.3f\n", $h{$_}*100/$sum for sort { $h{$b} <=> $h{$a} || $a cmp $b } keys %h;
  print "\n";
}

foreach my $s (qw(GGT GGTA GGTATT GGTATTTTAATT GGTATTTTAATTTATAGT)) {
  update_hash_for_frame(length($s));
  printf "%d\t$s\n", $h{$s};
}

sub update_hash_for_frame {
  my $frame = $_[0];
  my @threads;
  for my $i (0 .. $threads - 1) {
    use integer;
    my $begin = $l * $i / $threads;
    my $end = $l * ($i + 1) / $threads - 1;
    no integer;
    if ($end > $l - $frame) {
      $end = $l - $frame;
    }
    push @threads, threads->create(\&update_hash_slice, $frame, $begin, $end);
  }
  for my $thread (@threads) {
    my $count = $thread->join;
    $h{$_} += $count->{$_} for keys %$count;
  }
}

sub update_hash_slice {
  my ($frame, $begin, $end) = @_;
  my %local;
  $local{substr($sequence,$_,$frame)}++ for $begin .. $end;
  return \%local;
}

sub num_cpus {
  open my $fh, '</proc/cpuinfo' or return;
  my $cpus;
  while (<$fh>) {
    $cpus ++ if /^processor\s+:/;
  }
  return $cpus;
}
    

notes, command-line, and program output

NOTES:
64-bit Ubuntu quad core
This is perl 5, version 24, subversion 0 (v5.24.0) built for x86_64-linux-thread-multi



Tue, 10 May 2016 23:57:36 GMT

COMMAND LINE:
/usr/local/src/perl-5.24.0/bin/perl knucleotide.perl 0 < knucleotide-input25000000.txt

PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754

AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902

1471758	GGT
446535	GGTA
47336	GGTATT
893	GGTATTTTAATT
893	GGTATTTTAATTTATAGT