public unsafe void Multiply()
{
int l = 10000;
float[] v1 = new float[l];
for (int i = 0; i < l; i++)
{
v1[i] = i;
}
float[] v2 = new float[l];
for (int i = 0; i < l; i++)
{
v2[i] = i;
}
float[] res = new float[l];
fixed(float *a = v1, b = v2, y = res)
VectorizationFloat.ElementWiseMultiplyAVX(a, b, y, res.Length);
float[] res2 = new float[l];
for (int i = 0; i < l; i++)
{
res2[i] = i * i;
}
Assert.IsTrue(ArrayEqual(res, res2));
}
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);
}
public static void MultiplyFloat32(Tensor res, Tensor a, Tensor b)
{
if (a.Shape.TotalSize > b.Shape.TotalSize)
{
Tensor temp = a;
a = b;
b = temp;
}
long go = res.Shape.TotalSize / a.Shape.TotalSize * a.Shape.TotalSize;
for (long i = 0; i < go; i += a.Shape.TotalSize)
{
VectorizationFloat.ElementWiseMultiplyAVX((float *)a.Base.Array, (float *)b.Base.Array + i, (float *)res.Base.Array + i, a.Shape.TotalSize);
}
if (go < res.Shape.TotalSize)
{
VectorizationFloat.ElementWiseMultiplyAVX((float *)a.Base.Array, (float *)b.Base.Array + go, (float *)res.Base.Array + go, res.Shape.TotalSize - go);
}
}
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!");
}
}
