public static void MultiplyFloat32_GetGradientA(Tensor gradienta, Tensor s, Tensor a, Tensor b)
{
if (s.Shape.TotalSize == a.Shape.TotalSize)
{
long go = s.Shape.TotalSize / b.Shape.TotalSize * b.Shape.TotalSize;
for (long i = 0; i < go; i += b.Shape.TotalSize)
{
VectorizationFloat.ElementWiseMultiplyAVX((float *)s.Base.Array + i, (float *)b.Base.Array, (float *)gradienta.Base.Array + i, b.Shape.TotalSize);
}
if (go < s.Shape.TotalSize)
{
VectorizationFloat.ElementWiseMultiplyAVX((float *)s.Base.Array + go, (float *)b.Base.Array, (float *)gradienta.Base.Array + go, s.Shape.TotalSize - go);
}
}
else if (s.Shape.TotalSize == b.Shape.TotalSize)
{
long go = s.Shape.TotalSize / a.Shape.TotalSize * a.Shape.TotalSize;
for (long i = 0; i < go; i += a.Shape.TotalSize)
{
if (i == 0)
{
VectorizationFloat.ElementWiseMultiplyAVX((float *)s.Base.Array, (float *)b.Base.Array, (float *)gradienta.Base.Array, gradienta.Shape.TotalSize);
}
else
{
VectorizationFloat.ElementWiseFMA((float *)s.Base.Array + i, (float *)b.Base.Array + i, (float *)gradienta.Base.Array, (float *)gradienta.Base.Array, gradienta.Shape.TotalSize);
}
}
if (go < s.Shape.TotalSize)
{
VectorizationFloat.ElementWiseFMA((float *)s.Base.Array + go, (float *)b.Base.Array + go, (float *)gradienta.Base.Array, (float *)gradienta.Base.Array, s.Shape.TotalSize - go);
}
}
else
{
throw new Exception("Impossible reagion MultiplyFloat32_GetGradientA!");
}
}