half done with cuvect4f

include/amsculib2/cuvect4f.hpp

@@ -14,16 +14,22 @@ namespace amscuda
 
         __host__ __device__ cuvect4f();
         __host__ __device__ ~cuvect4f();
-        __host__ __device__ cuvect4f(float _x, float _y, float _z, float _w);
+        __host__ __device__ cuvect4f(const float &_x, const float &_y, const float &_z, const float &_w);
         
-        __host__ __device__ float& operator[](const int I);
-        __host__ __device__ const float& operator[](const int I) const;
         
-        __host__ __device__ cuvect4f operator+(cuvect4f lhs);
+        __host__ __device__ float& operator[](const int &I);
-        __host__ __device__ cuvect4f operator-(cuvect4f lhs);
+        __host__ __device__ const float& operator[](const int &I) const;
-        __host__ __device__ cuvect4f operator*(float lhs);
+
-        __host__ __device__ cuvect4f operator/(float lhs);
+        __host__ __device__ cuvect4f operator+(const cuvect4f &rhs);
-        __host__ __device__ friend cuvect4f operator-(cuvect4f rhs);
+        __host__ __device__ cuvect4f operator-(const cuvect4f &rhs);
+        __host__ __device__ cuvect4f operator*(const float &rhs);
+        __host__ __device__ cuvect4f operator/(const float &rhs);
+        __host__ __device__ friend cuvect4f operator-(const cuvect4f &rhs);
+
+        __host__ __device__ cuvect4f& operator+=(const cuvect4f &rhs);
+        __host__ __device__ cuvect4f& operator-=(const cuvect4f &rhs);
+        __host__ __device__ cuvect4f& operator/=(const float &rhs);
+        __host__ __device__ cuvect4f& operator*=(const float &rhs);
     };
 
     class cumat4f
@@ -31,6 +37,11 @@ namespace amscuda
         public:
         float dat[16];
 
+        // float m00,m10,m20,m30; //named references to force register use?
+        // float m01,m11,m21,m31; //switched to column-major-order to match GLSL/lapack
+        // float m02,m12,m22,m32;
+        // float m03,m13,m23,m33;
+
         __host__ __device__ cumat4f();
         __host__ __device__ ~cumat4f();
         __host__ __device__ float& operator[](const int I);

src/amsculib2/cuvect4f.cu

@@ -9,80 +9,119 @@ namespace amscuda
 
 __host__ __device__ cuvect4f::cuvect4f()
 {
-    x = 0.0; y = 0.0; z = 0.0; w = 0.0;
+    x = 0.0f; y = 0.0f; z = 0.0f; w = 0.0f;
     return;
 }
 
 __host__ __device__ cuvect4f::~cuvect4f()
 {
-    x = 0.0; y = 0.0; z = 0.0; w = 0.0;
+    x = 0.0f; y = 0.0f; z = 0.0f; w = 0.0f;
     return;
 }
 
-__host__ __device__ cuvect4f::cuvect4f(float _x, float _y, float _z, float _w)
+__host__ __device__ float& cuvect4f::operator[](const int &I)
+{
+    if(I==0) return x;
+    if(I==1) return y;
+    if(I==2) return z;
+    if(I==3) return w;
+    return x;
+}
+
+__host__ __device__ const float& cuvect4f::operator[](const int &I) const
+{
+    if(I==0) return x;
+    if(I==1) return y;
+    if(I==2) return z;
+    if(I==3) return w;
+    return x;
+}
+
+__host__ __device__ cuvect4f cuvect4f::operator+(const cuvect4f &rhs)
+{
+    cuvect4f ret;
+    ret.x = x+rhs.x;
+    ret.y = y+rhs.y;
+    ret.z = z+rhs.z;
+    ret.w = w+rhs.w;
+
+    return ret;
+}
+
+__host__ __device__ cuvect4f cuvect4f::operator-(const cuvect4f &rhs)
+{
+    cuvect4f ret;
+    ret.x = x-rhs.x;
+    ret.y = y-rhs.y;
+    ret.z = z-rhs.z;
+    ret.w = w-rhs.w;
+
+    return ret;
+}
+
+__host__ __device__ cuvect4f cuvect4f::operator*(const float &rhs)
+{
+    cuvect4f ret;
+    ret.x = x*rhs;
+    ret.y = y*rhs;
+    ret.z = z*rhs;
+    ret.w = w*rhs;
+    return ret;
+}
+
+__host__ __device__ cuvect4f cuvect4f::operator/(const float &rhs)
+{
+    cuvect4f ret;
+    ret.x = x/rhs;
+    ret.y = y/rhs;
+    ret.z = z/rhs;
+    ret.w = w/rhs;
+    return ret;
+}
+
+__host__ __device__ cuvect4f& cuvect4f::operator+=(const cuvect4f &rhs)
+{
+    x = x + rhs.x;
+    y = y + rhs.y;
+    z = z + rhs.z;
+    w = w + rhs.w;
+    return *this;
+}
+
+__host__ __device__ cuvect4f& cuvect4f::operator-=(const cuvect4f &rhs)
+{
+    x = x - rhs.x;
+    y = y - rhs.y;
+    z = z - rhs.z;
+    w = w - rhs.w;
+    return *this;
+}
+
+__host__ __device__ cuvect4f& cuvect4f::operator*=(const float &rhs)
+{
+    x = x * rhs;
+    y = y * rhs;
+    z = z * rhs;
+    w = w * rhs;
+    return *this;
+}
+
+__host__ __device__ cuvect4f& cuvect4f::operator/=(const float &rhs)
+{
+    x = x / rhs;
+    y = y / rhs;
+    z = z / rhs;
+    w = w / rhs;
+    return *this;
+}
+
+
+__host__ __device__ cuvect4f::cuvect4f(const float &_x, const float &_y, const float &_z, const float &_w)
 {
     x = _x; y = _y; z = _z; w = _w;
     return;
 }
 
-__host__ __device__ float& cuvect4f::operator[](const int I)
-{
-    if(I==0) return x;
-    else if(I==1) return y;
-    else if(I==2) return z;
-    else if(I==3) return w;
-    return x;
-}
-
-__host__ __device__ const float& cuvect4f::operator[](const int I) const
-{
-    if(I==0) return x;
-    else if(I==1) return y;
-    else if(I==2) return z;
-    else if(I==3) return w;
-    return x;
-}
-
-__host__ __device__ cuvect4f cuvect4f::operator+(cuvect4f lhs)
-{
-    cuvect4f ret;
-    ret.x = this->x + lhs.x;
-    ret.y = this->y + lhs.y;
-    ret.z = this->z + lhs.z;
-    ret.w = this->w + lhs.w;
-    return ret;
-}
-
-__host__ __device__ cuvect4f cuvect4f::operator-(cuvect4f lhs)
-{
-    cuvect4f ret;
-    ret.x = this->x - lhs.x;
-    ret.y = this->y - lhs.y;
-    ret.z = this->z - lhs.z;
-    ret.w = this->w - lhs.w;
-    return ret;
-}
-
-__host__ __device__ cuvect4f cuvect4f::operator*(float lhs)
-{
-    cuvect4f ret;
-    ret.x = this->x*lhs;
-    ret.y = this->y*lhs;
-    ret.z = this->z*lhs;
-    ret.w = this->w*lhs;
-    return ret;
-}
-
-__host__ __device__ cuvect4f cuvect4f::operator/(float lhs)
-{
-    cuvect4f ret;
-    ret.x = this->x/lhs;
-    ret.y = this->y/lhs;
-    ret.z = this->z/lhs;
-    ret.w = this->w/lhs;
-    return ret;
-}
-
 __host__ __device__ cumat4f::cumat4f()
 {
     int I;