public static void MatrixMultiplyFloat32_GetGradient_1(Tensor combinedright, Tensor s, Tensor A, Shape thisShape, Shape term0, Shape term1)
{
float *ptr_right = (float *)combinedright.Base.Array, ptr_a = (float *)A.Base.Array, ptr_s = (float *)s.Base.Array;
VectorizationFloat.TransposeAandMatrixMultiply(ptr_a, A.Shape[0], A.Shape[1], ptr_s, thisShape[0], thisShape[1], ptr_right);
//Derivative of B = Transpose(A)*s
//A -> m,k
//B -> k,n
//s -> m,n
}