public static Tensor SoftmaxFloat32_GetGradient_0(Tensor s, Tensor sm)
{
Tensor combined = Tensor.Clone(s);
long groupsize = sm.Shape[sm.Shape.N - 1];
for (long start = 0; start < combined.Shape.TotalSize; start += groupsize)
{
float averageK = VectorizationFloat.SumOfProduction((float *)s.Base.Array + start, (float *)sm.Base.Array + start, groupsize);
VectorizationFloat.ElementWiseAddAVX((float *)combined.Base.Array + start, -averageK, (float *)combined.Base.Array + start, groupsize);
}
VectorizationFloat.ElementWiseMultiplyAVX((float *)combined.Base.Array, (float *)sm.Base.Array, (float *)combined.Base.Array, combined.Shape.TotalSize);
return(combined);
}