using System.Runtime.InteropServices;
using System.Runtime.Intrinsics;
using BenchmarkDotNet.Attributes;

public class Bench
{
    private static int[] Testdata = new int[10000];

    [Benchmark]
    public int Sum_safe()
    {
        ReadOnlySpan<int> span = Testdata;

        Vector128<int> vSum = default;
        int i;
        for (i = 0; i < span.Length - Vector128<int>.Count; i += Vector128<int>.Count)
            vSum += Vector128.Create(span[i..]);
        int sum = Vector128.Sum(vSum);
        for (; i < span.Length; i++)
            sum += span[i];
        return sum;
    }

    [Benchmark(Baseline = true)]
    public int Sum_unsafe()
    {
        ReadOnlySpan<int> span = Testdata;

        Vector128<int> vSum = default;
        ref int r = ref MemoryMarshal.GetReference(span);
        int i;
        for (i = 0; i < span.Length - Vector128<int>.Count; i += Vector128<int>.Count)
            vSum += Vector128.LoadUnsafe(ref r, (nuint)i);
        int sum = Vector128.Sum(vSum);
        for (; i < span.Length; i++)
            sum += span[i];
        return sum;
    }
}