public static void AddFloat32_GetGradients(Tensor[] gradients, Tensor s, Tensor[] tensors)
{
for (int j = 0; j < gradients.Length; j++)
{
Tensor gradient = gradients[j];
//gradient.SetValue(0);
long go = s.Shape.TotalSize / gradient.Shape.TotalSize * gradient.Shape.TotalSize;
for (long i = 0; i < go; i += gradient.Shape.TotalSize)
{
if (go == 0)
{
VectorizationFloat.ElementWiseAssignAVX((float *)gradient.Base.Array, (float *)s.Base.Array + i, gradient.Shape.TotalSize);
}
else
{
VectorizationFloat.ElementWiseAddAVX((float *)s.Base.Array + i, (float *)gradient.Base.Array, (float *)gradient.Base.Array, gradient.Shape.TotalSize);
}
}
if (go < s.Shape.TotalSize)
{
VectorizationFloat.ElementWiseAddAVX((float *)s.Base.Array + go, (float *)gradient.Base.Array, (float *)gradient.Base.Array, s.Shape.TotalSize - go);
}
}
}
public unsafe void Add()
{
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.ElementWiseAddAVX(a, b, y, res.Length);
float[] res2 = new float[l];
for (int i = 0; i < l; i++)
{
res2[i] = i * 2;
}
Assert.IsTrue(ArrayEqual(res, res2));
}
public unsafe void Add2()
{
float[] v1 = { 1, 2, 3 };
float v2 = 2;
float[] res = new float[v1.Length];
fixed(float *a = v1, y = res)
VectorizationFloat.ElementWiseAddAVX(a, v2, y, res.Length);
float[] res2 = { 3, 4, 5 };
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 Tensor[] AddFloat32_GetGradients(Tensor s, Tensor[] tensors, bool generateseperately = false)
{
Tensor[] gradients = new Tensor[tensors.Length];
Dictionary <long, Tensor> dict = new Dictionary <long, Tensor>();
dict[s.Shape.TotalSize] = s;
for (int j = 0; j < gradients.Length; j++)
{
Tensor a = tensors[j];
if (!generateseperately && dict.ContainsKey(a.Shape.TotalSize))
{
gradients[j] = dict[a.Shape.TotalSize];
}
else
{
Tensor gradient = new Tensor(a.Shape.Clone(), TensorConfig.Host_Float32);
//gradient.SetValue(0);
long go = s.Shape.TotalSize / gradient.Shape.TotalSize * gradient.Shape.TotalSize;
for (long i = 0; i < go; i += gradient.Shape.TotalSize)
{
if (go == 0)
{
VectorizationFloat.ElementWiseAssignAVX((float *)gradient.Base.Array, (float *)s.Base.Array + i, gradient.Shape.TotalSize);
}
else
{
VectorizationFloat.ElementWiseAddAVX((float *)s.Base.Array + i, (float *)gradient.Base.Array, (float *)gradient.Base.Array, gradient.Shape.TotalSize);
}
}
if (go < s.Shape.TotalSize)
{
VectorizationFloat.ElementWiseAddAVX((float *)s.Base.Array + go, (float *)gradient.Base.Array, (float *)gradient.Base.Array, s.Shape.TotalSize - go);
}
}
}
return(gradients);
}
public static void SubtractFloat32_GetGradientA(Tensor gradienta, Tensor s, Tensor a)
{
long go = s.Shape.TotalSize / gradienta.Shape.TotalSize * gradienta.Shape.TotalSize;
for (long i = 0; i < go; i += gradienta.Shape.TotalSize)
{
if (i == 0)
{
VectorizationFloat.ElementWiseAssignAVX((float *)gradienta.Base.Array, (float *)s.Base.Array + i, gradienta.Shape.TotalSize);
}
else
{
VectorizationFloat.ElementWiseAddAVX((float *)s.Base.Array + i, (float *)gradienta.Base.Array, (float *)gradienta.Base.Array, gradienta.Shape.TotalSize);
}
}
if (go < s.Shape.TotalSize)
{
VectorizationFloat.ElementWiseAddAVX((float *)s.Base.Array + go, (float *)gradienta.Base.Array, (float *)gradienta.Base.Array, s.Shape.TotalSize - go);
}
}
public static void AddFloat32(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.ElementWiseAddAVX((float *)a.Base.Array, (float *)b.Base.Array + i, (float *)res.Base.Array + i, a.Shape.TotalSize);
}
if (go < res.Shape.TotalSize)
{
VectorizationFloat.ElementWiseAddAVX((float *)a.Base.Array, (float *)b.Base.Array + go, (float *)res.Base.Array + go, res.Shape.TotalSize - go);
}
}
public static void ExpandFloat32_GetGradient_0(Tensor res, Tensor s, Shape thisShape, Shape term0, Shape Multiplier)
{
res.SetValue(0);
float *ptrcombined = (float *)res.Base.Array;
float *ptrs = (float *)s.Base.Array;
if (Multiplier.N == 2 && Multiplier[1] == 1)
{
for (int i = 0; i < Multiplier[0]; i++)
{
float *me = ((float *)s.Base.Array) + i * term0.TotalSize;
VectorizationFloat.ElementWiseAddAVX((float *)res.Base.Array, me, (float *)res.Base.Array, term0.TotalSize);
}
}
else
{
Index iterator = new Index(thisShape);
iterator.SetZero();
for (int h = 0; h < thisShape.TotalSize; h++)
{
long indexs = 0;
for (int i = iterator.N - 1; i >= 0; i--)
{
if (iterator.Indices[i] == thisShape[i])
{
iterator.Indices[i] = 0;
iterator.Indices[i - 1]++;
}
indexs += (iterator.Indices[i] / Multiplier[i]) * term0.Multiplied[i + 1];
}
ptrcombined[indexs] += ptrs[h];
iterator.Indices[iterator.N - 1]++;
}
}
}