public static void MatrixMultiplyFloat32_GetGradient_0(Tensor combinedleft, Tensor s, Tensor B, Shape thisShape, Shape term0, Shape term1)
{
float *ptr_left = (float *)combinedleft.Base.Array, ptr_s = (float *)s.Base.Array, ptr_b = (float *)B.Base.Array;
VectorizationFloat.TransposeBandMatrixMultiply(ptr_s, (int)thisShape[0], (int)thisShape[1], ptr_b, (int)B.Shape[0], (int)B.Shape[1], ptr_left);
//Derivative of A = s*Transpose(B)
//A -> m,k
//B -> k,n
//s -> m,n
}
