Vectorize time-series indicators

[DaveSkender]

Consider implementing time-series vector method (reverted due to minor floating-point related test errors, from diff of parallel calculations)

...
double sum = 0;
int start = i - lookbackPeriods + 1;
int end = i + 1;

// SIMD optimization
int vectorSize = Vector<double>.Count;
int simdEnd = start + ((end - start) / vectorSize * vectorSize);

for (int p = start; p < simdEnd; p += vectorSize)
{
    Vector<double> vector = new(values, p);
    sum += Vector.Sum(vector);
}

for (int p = simdEnd; p < end; p++)
{
    sum += values[p];
}

sma = sum / lookbackPeriods;
...

Note

.NET blogs say this is 10x faster and more stable in the upcoming .NET 9 release (November)

Originally posted by @DaveSkender in #1230 (comment)

[DaveSkender]

Also consider FMA, but requires minimum.NET 7 targeting for better outcomes

using System.Numerics;

public static float DotProductFMA(float[] a, float[] b)
{
    var sum = new Vector<float>(0);
    int i = 0;
    
    for (; i <= a.Length - Vector<float>.Count; i += Vector<float>.Count)
    {
        sum = Vector<float>.FusedMultiplyAdd(new Vector<float>(a, i), new Vector<float>(b, i), sum);
    }

    float result = Vector.Sum(sum);

    for (; i < a.Length; i++) 
    {
        result += a[i] * b[i];
    }

    return result;
}