The Computer Language
Benchmarks Game

k-nucleotide C# Mono LLVM program

source code

/* The Computer Language Benchmarks Game
   http://benchmarksgame.alioth.debian.org/
 *
 * byte processing version using C# *3.0 idioms by Robert F. Tobler
 */

using System;
using System.IO;
using System.Collections.Generic;
using System.Text;

public struct ByteString : IEquatable<ByteString>
{
    public byte[] Array;
    public int Start;
    public int Length;

    public ByteString(byte[] array, int start, int length)
    {
        Array = array; Start = start; Length = length;
    }
    
    public ByteString(string text)
    {
        Start = 0; Length = text.Length;
        Array = Encoding.ASCII.GetBytes(text);
    }
    
    public override int GetHashCode()
    {
        if (Length < 1) return 0;
        int hc = Length ^ (Array[Start] << 24); if (Length < 2) return hc;
        hc ^= Array[Start+Length-1] << 20;      if (Length < 3) return hc;
        for (int c = Length-2; c > 0; c--)
            hc ^= Array[Start + c] << (c & 0xf);
        return hc;
    }

    public bool Equals(ByteString other)
    {
        if (Length != other.Length) return false;
        for (int i = 0; i < Length; i++)
            if (Array[Start+i] != other.Array[other.Start+i]) return false;
        return true;
    }
    
    public override string ToString()
    {
        return Encoding.ASCII.GetString(Array, Start, Length);
    }
}

public static class Extensions
{
    public static byte[] GetBytes(this List<string> input)
    {
        int count = 0;
        for (int i = 0; i < input.Count; i++) count += input[i].Length;        
        var byteArray = new byte[count];
        count = 0;
        for (int i = 0; i < input.Count; i++)
        {
            string line = input[i];
            Encoding.ASCII.GetBytes(line, 0, line.Length, byteArray, count);
            count += line.Length;
        }
        return byteArray;
    }
}

public class program {


    public static void Main(string[] args) {
        string line;
        StreamReader source = new StreamReader(Console.OpenStandardInput());
        var input = new List<string>();
    
        while ( (line = source.ReadLine() ) != null )
            if (line[0] == '>' && line.Substring(1, 5) == "THREE")
                break;
    
        while ( (line = source.ReadLine()) != null ) {
            char c = line[0];
            if (c == '>') break;
            if (c != ';') input.Add(line.ToUpper());
        }
    
        KNucleotide kn = new KNucleotide(input.GetBytes());
        input = null;
        for (int f = 1; f < 3; f++) kn.WriteFrequencies(f);
        foreach (var seq in
                 new[] { "GGT", "GGTA", "GGTATT", "GGTATTTTAATT",
                         "GGTATTTTAATTTATAGT"})
            kn.WriteCount(seq);

    }
}

public class KNucleotide {

    private class Count {
	   public int V;
	   public Count(int v) { V = v; }
    }

    private Dictionary<ByteString, Count> frequencies
        = new Dictionary<ByteString, Count>();
    private byte[] sequence;

    public KNucleotide(byte[] s) { sequence = s; }

    public void WriteFrequencies(int length) {
        GenerateFrequencies(length);
        var items = new List<KeyValuePair<ByteString, Count>>(frequencies);
        items.Sort(SortByFrequencyAndCode);    
        double percent = 100.0 / (sequence.Length - length + 1);
        foreach (var item in items)
            Console.WriteLine("{0} {1:f3}",
                        item.Key.ToString(), item.Value.V * percent);
        Console.WriteLine();
    }

    public void WriteCount(string fragment) {
        GenerateFrequencies(fragment.Length);
        Count count;
        if (!frequencies.TryGetValue(new ByteString(fragment), out count))
            count = new Count(0);
        Console.WriteLine("{0}\t{1}", count.V, fragment);
    }

    private void GenerateFrequencies(int length) {
        frequencies.Clear();
        for (int frame = 0; frame < length; frame++)
            KFrequency(frame, length);
    }

    private void KFrequency(int frame, int k) {
        int n = sequence.Length - k + 1;
        for (int i = frame; i < n; i += k) {
            var key = new ByteString(sequence, i, k);
            Count count;
            if (frequencies.TryGetValue(key, out count))
                count.V++;
            else
                frequencies[key] = new Count(1);
        }
    }

    int SortByFrequencyAndCode(
            KeyValuePair<ByteString, Count> i0,
            KeyValuePair<ByteString, Count> i1) {
        int order = i1.Value.V.CompareTo(i0.Value.V);
        if (order != 0) return order;
        return i0.Key.ToString().CompareTo(i1.Key.ToString());
    }
}
    

notes, command-line, and program output

NOTES:
32-bit Ubuntu one core
Mono JIT compiler version 4.5.1 (master/3e844dd Fri May  6 19:24:07 PDT 2016)
	LLVM:          yes(3.6.0svn-mono-master/9f79399)
	GC:            sgen



Tue, 28 Jun 2016 19:13:46 GMT

MAKE:
mv knucleotide.csharpllvm knucleotide.cs
/usr/local/bin/mcs -unsafe+ -optimize+ -platform:x86 -out:knucleotide.csharpllvm_run knucleotide.cs
rm knucleotide.cs
0.28s to complete and log all make actions

COMMAND LINE:
/usr/local/bin/mono --llvm --gc=sgen knucleotide.csharpllvm_run 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