Question

I am trying to learn about CPU cache performance in the world of .NET. Specifically I am working through Igor Ostovsky’s article about Processor Cache Effects.

I have gone through the first three examples in his article and have recorded results that widely differ from his. I think I must be doing something wrong because the performance on my machine is showing almost the exact opposite results of what he shows in his article. I am not seeing the large effects from cache misses that I would expect.

What am I doing wrong? (bad code, compiler setting, etc.)

Here are the performance results on my machine:

If it helps, the processor on my machine is an Intel Core i7-2630QM. Here is info on my processor’s cache:

I have compiled in x64 Release mode.

Below is my source code:

class Program
    {

        static Stopwatch watch = new Stopwatch();

        static int[] arr = new int[64 * 1024 * 1024];

        static void Main(string[] args)
        {
            Example1();
            Example2();
            Example3();


            Console.ReadLine();
        }

        static void Example1()
        {
            Console.WriteLine("Example 1:");

            // Loop 1
            watch.Restart();
            for (int i = 0; i < arr.Length; i++) arr[i] *= 3;
            watch.Stop();
            Console.WriteLine("     Loop 1: " + watch.ElapsedMilliseconds.ToString() + " ms");

            // Loop 2
            watch.Restart();
            for (int i = 0; i < arr.Length; i += 32) arr[i] *= 3;
            watch.Stop();
            Console.WriteLine("     Loop 2: " + watch.ElapsedMilliseconds.ToString() + " ms");

            Console.WriteLine();
        }

        static void Example2()
        {

            Console.WriteLine("Example 2:");

            for (int k = 1; k <= 1024; k *= 2)
            {

                watch.Restart();
                for (int i = 0; i < arr.Length; i += k) arr[i] *= 3;
                watch.Stop();
                Console.WriteLine("     K = "+ k + ": " + watch.ElapsedMilliseconds.ToString() + " ms");

            }
            Console.WriteLine();
        }

        static void Example3()
        {   

            Console.WriteLine("Example 3:");

            for (int k = 1; k <= 1024*1024; k *= 2)
            {

                //256* 4bytes per 32 bit int * k = k Kilobytes
                arr = new int[256*k];



                int steps = 64 * 1024 * 1024; // Arbitrary number of steps
                int lengthMod = arr.Length - 1;

                watch.Restart();
                for (int i = 0; i < steps; i++)
                {
                    arr[(i * 16) & lengthMod]++; // (x & lengthMod) is equal to (x % arr.Length)
                }

                watch.Stop();
                Console.WriteLine("     Array size = " + arr.Length * 4 + " bytes: " + (int)(watch.Elapsed.TotalMilliseconds * 1000000.0 / arr.Length) + " nanoseconds per element");

            }
            Console.WriteLine();
        }

    }

Answer 1

Why are you using i += 32 in the second loop. You are stepping over cache lines in this way. 32*4 = 128bytes way bigger then 64bytes needed.