private static int CountTriples256v2(int[] arr, int

sum)
{
int n = arr.Length;
int count = 0;
var vCount = Vector<int>.Count;
ref int p = ref arr[0];
var sumVector = new Vector<int>(sum);
for (int i = 0; i < n; i++)
{
for (int j = i + 1; j < n; j++)
{
var ijSum = arr[i] + arr[j];
var ijSumVector = new Vector<int>(ijSum);
var k = j + 1;
for (; k < n - vCount; k += vCount)
{
var kVector = Vector.LoadUnsafe(ref p, (nuint)k);
var ijkSumVector = kVector + ijSumVector;
var subResult = Vector.Equals(sumVector, ijkSumVector);
if (subResult != Vector<int>.Zero)
{
var sumCount = Vector.Sum(subResult);
count -= sumCount;
}
}

for (; k < n; k++)
count += ijSum + arr[k] == sum ? 1 : 0;
}
}
return count;
}

Vector.LoadUnsafe(ref p, (nuint)k) это уже на грани байтоёбства

4х хуже

Чот я потестил, 225+-

private static int CountTriples512v3(int[] arr, int sum) { int n = arr.Length; int count = 0; var vCount = Vector512<int>.Count; ref int p = ref arr[0]; var sumVector = Vector512.Create(sum); for (int i = 0; i < n; i++) { for (int j = i + 1; j < n; j++) { var ijSum = arr[i] + arr[j]; var ijSumVector = Vector512.Create(ijSum); var k = j + 1; for (; k < n - vCount; k += vCount) { var kVector = Vector512.LoadUnsafe(ref p, (nuint)k); var ijkSumVector = kVector + ijSumVector; var subResult = Vector512.Equals(sumVector, ijkSumVector); if (subResult != Vector512<int>.Zero) { var sumCount = Vector512.Sum(subResult); count -= sumCount; } } for (; k < n; k++) count += ijSum + arr[k] == sum ? 1 : 0; } } return count; } вот это хуже но не в 4x

LoadUnsafe это дотнет8?

Ага