IO>Тут должна быть ссылка на сравнение производительности C# и Java для "обработки большех объёмов данных" на каком-нибудь иллюстративном примере.

Java

public class V3 {
    public float X;
    public float Y;
    public float Z;
    
    public V3(float x, float y, float z) {
        X = x; Y = y; Z = z;
    }
}

public class Test {
    public static void main(String[] args) {
        Random rand = new Random(0);
        
        long s = System.nanoTime();
        
        V3[] mesh = new V3[1 << 24];
        for (int i = 0; i != mesh.length; ++i)
            mesh[i] = MakeRandVector(rand);
        
        V3 dir = MakeRandVector(rand);
        
        double sum = 0.0;
        for (int i = 0; i != mesh.length; ++i)
            sum += mesh[i].X * dir.X + mesh[i].Y * dir.Y + mesh[i].Z * dir.Z;
        
        long f = System.nanoTime();
        
        long milliseconds = (f - s) / 1000000;
        
        System.out.println(milliseconds + " : " + sum);
    }
    
    private static V3 MakeRandVector(Random rand) {
        return new V3(rand.nextFloat(), rand.nextFloat(), rand.nextFloat());
    }
}

.NET

[ Record ]
public struct V3
{
    public X : float;
    public Y : float;
    public Z : float;
}

def rand = JavaRandom(0);
def MakeRandVector()
{
    V3(rand.NextFloat(), rand.NextFloat(), rand.NextFloat())
}

def stopwatch = Stopwatch.StartNew();

def mesh = array(1 << 24);
for (mutable i = 0; i != mesh.Length; ++i)
    mesh[i] = MakeRandVector();

def dir = MakeRandVector();

mutable sum = 0.0;
for (mutable i = 0; i != mesh.Length; ++i)
    sum += mesh[i].X * dir.X + mesh[i].Y * dir.Y + mesh[i].Z * dir.Z;

stopwatch.Stop();

Console.WriteLine("{0} : {1}", stopwatch.ElapsedMilliseconds, sum);