__host__ __device__ cuvec4(); 
	__host__ __device__ ~cuvec4(); 
	__host__ __device__ cuvec4(const double &_x, const double &_y, const double &_z, const double &_w); 
	__host__ __device__ double& operator[](const int &I);
	__host__ __device__ const double& operator[](const int &I) const;
	__host__ __device__ cuvec4 operator+(const cuvec4& rhs) const;
	__host__ __device__ cuvec4 operator-(const cuvec4& rhs) const;
	__host__ __device__ cuvec4 operator*(const cuvec4& rhs) const; 	 //elementwise product
	__host__ __device__ cuvec4 operator/(const cuvec4& rhs) const; 	 //elementwise division
	__host__ __device__ friend cuvec4 operator*(const cuvec4& lhs, const double& rhs);
	__host__ __device__ friend cuvec4 operator*(const double& lhs, const cuvec4& rhs);
	__host__ __device__ friend cuvec4 operator/(const cuvec4& lhs, const double& rhs);
	__host__ __device__ friend cuvec4 operator/(const double& lhs, const cuvec4& rhs);
	__host__ __device__ friend cuvec4 operator-(const cuvec4& other);
	__host__ __device__ cuvec4& operator+=(const cuvec4& rhs);
	__host__ __device__ cuvec4& operator-=(const cuvec4& rhs);
	__host__ __device__ cuvec4& operator*=(const double& rhs);
	__host__ __device__ cuvec4& operator/=(const double& rhs);
//
//Matrix Header Stuff
//
double m00,m10,m20,m30;
double m01,m11,m21,m31;
double m02,m12,m22,m32;
double m03,m13,m23,m33;

	__host__ __device__ cumat4(); 
	__host__ __device__ ~cumat4(); 
	__host__ __device__ cumat4(
		const double& _m00, const double& _m01, const double& _m02, const double& _m03, 
		const double& _m10, const double& _m11, const double& _m12, const double& _m13, 
		const double& _m20, const double& _m21, const double& _m22, const double& _m23, 
		const double& _m30, const double& _m31, const double& _m32, const double& _m33
	);
	__host__ __device__ cumat4(const double* data16);
	__host__ __device__ double& operator[](const int &I);
	__host__ __device__ const double& operator[](const int &I) const;
	__host__ __device__ double& operator()(const int &I, const int &J);
	__host__ __device__ const double& operator()(const int &I, const int &J) const;
	__host__ __device__ double& at(const int &I, const int &J);
	__host__ __device__ const double& at(const int &I, const int &J) const;
__host__ __device__ double* data(); //pointer to double16 representation of matrix
__host__ __device__ const double* data() const; //pointer to double16 representation of matrix
__host__ __device__ cumat4 operator+(const cumat4& rhs) const;
__host__ __device__ cumat4 operator-(const cumat4& rhs) const;
__host__ __device__ cumat4 operator*(const cumat4& rhs) const;
__host__ __device__ friend cumat4 operator*(const cumat4& lhs, const double& rhs);
__host__ __device__ friend cumat4 operator/(const cumat4& lhs, const double& rhs);
__host__ __device__ friend cumat4 operator*(const double& lhs, const cumat4& rhs);
__host__ __device__ friend cuvec4 operator*(const cumat4& lhs, const cuvec4& rhs);
__host__ __device__ friend cuvec4 operator*(const cuvec4& lhs, const cumat4& rhs);
__host__ __device__ friend cumat4 operator-(const cumat4& rhs);
__host__ __device__ cumat4& operator+=(const cumat4& rhs);
__host__ __device__ cumat4& operator-=(const cumat4& rhs);
__host__ __device__ cumat4& operator*=(const double& rhs);
__host__ __device__ cumat4& operator/=(const double& rhs);
__host__ __device__ cumat4& operator*=(const cumat4& rhs);
__host__ __device__ cumat4 transpose() const;