merged, no conflicts

1 files changed, 190 insertions, 284 deletions

diff --git a/linmath.h b/linmath.h
index c1c3ab5..70b15a4 100644
--- a/linmath.h
+++ b/linmath.h
@@ -1,29 +1,42 @@
 #ifndef LINMATH_H
 #define LINMATH_H
 
+#if __STDC_VERSION__ < 199901L
+# ifndef inline
+#  if defined(_MSC_VER)
+#   define inline __inline
+#  elif defined(__GNUC__)
+#   define inline __inline__
+#  else
+#   define inline
+#  endif
+# endif
+#endif
+
 #include <math.h>
+#include <string.h>
 
 #define LINMATH_H_DEFINE_VEC(n) \
 typedef float vec##n[n]; \
-static inline void vec##n##_add(vec##n r, vec##n const a, vec##n const b) \
+static inline void vec##n##_add(vec##n r, vec##n a, vec##n b) \
 { \
 	int i; \
 	for(i=0; i<n; ++i) \
 		r[i] = a[i] + b[i]; \
 } \
-static inline void vec##n##_sub(vec##n r, vec##n const a, vec##n const b) \
+static inline void vec##n##_sub(vec##n r, vec##n a, vec##n b) \
 { \
 	int i; \
 	for(i=0; i<n; ++i) \
 		r[i] = a[i] - b[i]; \
 } \
-static inline void vec##n##_scale(vec##n r, vec##n const v, float const s) \
+static inline void vec##n##_scale(vec##n r, vec##n v, float s) \
 { \
 	int i; \
 	for(i=0; i<n; ++i) \
 		r[i] = v[i] * s; \
 } \
-static inline float vec##n##_mul_inner(vec##n const a, vec##n const b) \
+static inline float vec##n##_mul_inner(vec##n a, vec##n b) \
 { \
 	float p = 0.; \
 	int i; \
@@ -31,96 +44,55 @@ static inline float vec##n##_mul_inner(vec##n const a, vec##n const b) \
 		p += b[i]*a[i]; \
 	return p; \
 } \
-static inline float vec##n##_len(vec##n const v) \
+static inline float vec##n##_len(vec##n v) \
 { \
 	return sqrtf(vec##n##_mul_inner(v,v)); \
 } \
-static inline void vec##n##_norm(vec##n r, vec##n const v) \
+static inline void vec##n##_norm(vec##n r, vec##n v) \
 { \
 	float k = 1.0 / vec##n##_len(v); \
 	vec##n##_scale(r, v, k); \
-} \
-static inline void vec##n##_min(vec##n r, vec##n a, vec##n b) \
-{ \
-	int i; \
-	for(i=0; i<n; ++i) \
-		r[i] = a[i]<b[i] ? a[i] : b[i]; \
-} \
-static inline void vec##n##_max(vec##n r, vec##n a, vec##n b) \
-{ \
-	int i; \
-	for(i=0; i<n; ++i) \
-		r[i] = a[i]>b[i] ? a[i] : b[i]; \
 }
 
-LINMATH_H_DEFINE_VEC(2)
-LINMATH_H_DEFINE_VEC(3)
-LINMATH_H_DEFINE_VEC(4)
-
-static inline void vec3_mul_cross(vec3 r, vec3 const a, vec3 const b)
-{
-	r[0] = a[1]*b[2] - a[2]*b[1];
-	r[1] = a[2]*b[0] - a[0]*b[2];
-	r[2] = a[0]*b[1] - a[1]*b[0];
-}
+LINMATH_H_DEFINE_VEC(2);
+LINMATH_H_DEFINE_VEC(3);
+LINMATH_H_DEFINE_VEC(4);
 
-static inline void vec3_reflect(vec3 r, vec3 const v, vec3 const n)
+static inline void vec3_mul_cross(vec3 r, vec3 a, vec3 b)
 {
-	float p  = 2.f*vec3_mul_inner(v, n);
-	int i;
-	for(i=0;i<3;++i)
-		r[i] = v[i] - p*n[i];
+	vec3 c;
+	c[0] = a[1]*b[2] - a[2]*b[1];
+	c[1] = a[2]*b[0] - a[0]*b[2];
+	c[2] = a[0]*b[1] - a[1]*b[0];
+	memcpy(r, c, sizeof(c));
 }
 
 static inline void vec4_mul_cross(vec4 r, vec4 a, vec4 b)
 {
-	r[0] = a[1]*b[2] - a[2]*b[1];
-	r[1] = a[2]*b[0] - a[0]*b[2];
-	r[2] = a[0]*b[1] - a[1]*b[0];
-	r[3] = 1.f;
-}
-
-static inline void vec4_reflect(vec4 r, vec4 v, vec4 n)
-{
-	float p  = 2.f*vec4_mul_inner(v, n);
-	int i;
-	for(i=0;i<4;++i)
-		r[i] = v[i] - p*n[i];
+	vec4 c;
+	c[0] = a[1]*b[2] - a[2]*b[1];
+	c[1] = a[2]*b[0] - a[0]*b[2];
+	c[2] = a[0]*b[1] - a[1]*b[0];
+	c[3] = 1.;
+	memcpy(r, c, sizeof(c));
 }
 
 typedef vec4 mat4x4[4];
 static inline void mat4x4_identity(mat4x4 M)
 {
 	int i, j;
-	for(i=0; i<4; ++i)
-		for(j=0; j<4; ++j)
-			M[i][j] = i==j ? 1.f : 0.f;
+	for(j=0; j<4; ++j) for(i=0; i<4; ++i) {
+		M[i][j] = i==j ? 1 : 0;
+	}
 }
 static inline void mat4x4_dup(mat4x4 M, mat4x4 N)
 {
 	int i, j;
-	for(i=0; i<4; ++i)
-		for(j=0; j<4; ++j)
+	for(j=0; j<4; ++j) {
+		for(i=0; i<4; ++i) {
 			M[i][j] = N[i][j];
-}
-static inline void mat4x4_row(vec4 r, mat4x4 M, int i)
-{
-	int k;
-	for(k=0; k<4; ++k)
-		r[k] = M[k][i];
-}
-static inline void mat4x4_col(vec4 r, mat4x4 M, int i)
-{
-	int k;
-	for(k=0; k<4; ++k)
-		r[k] = M[i][k];
-}
-static inline void mat4x4_transpose(mat4x4 M, mat4x4 N)
-{
-	int i, j;
-	for(j=0; j<4; ++j)
-		for(i=0; i<4; ++i)
-			M[i][j] = N[j][i];
+		}
+	}
 }
 static inline void mat4x4_add(mat4x4 M, mat4x4 a, mat4x4 b)
 {
@@ -142,33 +114,33 @@ static inline void mat4x4_scale(mat4x4 M, mat4x4 a, float k)
 }
 static inline void mat4x4_scale_aniso(mat4x4 M, mat4x4 a, float x, float y, float z)
 {
-	int i;
 	vec4_scale(M[0], a[0], x);
 	vec4_scale(M[1], a[1], y);
 	vec4_scale(M[2], a[2], z);
-	for(i = 0; i < 4; ++i) {
-		M[3][i] = a[3][i];
-	}
 }
 static inline void mat4x4_mul(mat4x4 M, mat4x4 a, mat4x4 b)
 {
-	mat4x4 temp;
 	int k, r, c;
-	for(c=0; c<4; ++c) for(r=0; r<4; ++r) {
-		temp[c][r] = 0.f;
-		for(k=0; k<4; ++k)
-			temp[c][r] += a[k][r] * b[c][k];
+	mat4x4 R;
+	for(r=0; r<4; ++r) for(c=0; c<4; ++c) {
+		R[c][r] = 0;
+		for(k=0; k<4; ++k) {
+			R[c][r] += a[k][r] * b[c][k];
+		}
 	}
-	mat4x4_dup(M, temp);
+	memcpy(M, R, sizeof(R));
 }
 static inline void mat4x4_mul_vec4(vec4 r, mat4x4 M, vec4 v)
 {
+	vec4 r_;
 	int i, j;
 	for(j=0; j<4; ++j) {
-		r[j] = 0.f;
-		for(i=0; i<4; ++i)
-			r[j] += M[i][j] * v[i];
+		r_[j] = 0.;
+		for(i=0; i<4; ++i) {
+			r_[j] += M[i][j] * v[i];
+		}
 	}
+	memcpy(r, r_, sizeof(r_));
 }
 static inline void mat4x4_translate(mat4x4 T, float x, float y, float z)
 {
@@ -177,21 +149,12 @@ static inline void mat4x4_translate(mat4x4 T, float x, float y, float z)
 	T[3][1] = y;
 	T[3][2] = z;
 }
-static inline void mat4x4_translate_in_place(mat4x4 M, float x, float y, float z)
-{
-	vec4 t = {x, y, z, 0};
-	vec4 r;
-	int i;
-	for (i = 0; i < 4; ++i) {
-		mat4x4_row(r, M, i);
-		M[3][i] += vec4_mul_inner(r, t);
-	}
-}
 static inline void mat4x4_from_vec3_mul_outer(mat4x4 M, vec3 a, vec3 b)
 {
 	int i, j;
-	for(i=0; i<4; ++i) for(j=0; j<4; ++j)
-		M[i][j] = i<3 && j<3 ? a[i] * b[j] : 0.f;
+	for(i=0; i<4; ++i) for(j=0; j<4; ++j) {
+		M[i][j] = i<3 && j<3 ? a[i] * b[j] : 0.;
+	}
 }
 static inline void mat4x4_rotate(mat4x4 R, mat4x4 M, float x, float y, float z, float angle)
 {
@@ -232,10 +195,10 @@ static inline void mat4x4_rotate_X(mat4x4 Q, mat4x4 M, float angle)
 	float s = sinf(angle);
 	float c = cosf(angle);
 	mat4x4 R = {
-		{1.f, 0.f, 0.f, 0.f},
-		{0.f,   c,   s, 0.f},
-		{0.f,  -s,   c, 0.f},
-		{0.f, 0.f, 0.f, 1.f}
+		{1, 0, 0, 0},
+		{0, c, s, 0},
+		{0,-s, c, 0},
+		{0, 0, 0, 1}
 	};
 	mat4x4_mul(Q, M, R);
 }
@@ -244,10 +207,10 @@ static inline void mat4x4_rotate_Y(mat4x4 Q, mat4x4 M, float angle)
 	float s = sinf(angle);
 	float c = cosf(angle);
 	mat4x4 R = {
-		{   c, 0.f,   s, 0.f},
-		{ 0.f, 1.f, 0.f, 0.f},
-		{  -s, 0.f,   c, 0.f},
-		{ 0.f, 0.f, 0.f, 1.f}
+		{ c, 0, s, 0},
+		{ 0, 1, 0, 0},
+		{-s, 0, c, 0},
+		{ 0, 0, 0, 1}
 	};
 	mat4x4_mul(Q, M, R);
 }
@@ -256,53 +219,59 @@ static inline void mat4x4_rotate_Z(mat4x4 Q, mat4x4 M, float angle)
 	float s = sinf(angle);
 	float c = cosf(angle);
 	mat4x4 R = {
-		{   c,   s, 0.f, 0.f},
-		{  -s,   c, 0.f, 0.f},
-		{ 0.f, 0.f, 1.f, 0.f},
-		{ 0.f, 0.f, 0.f, 1.f}
+		{ c, s, 0, 0},
+		{-s, c, 0, 0},
+		{ 0, 0, 1, 0},
+		{ 0, 0, 0, 1}
 	};
 	mat4x4_mul(Q, M, R);
 }
+static inline void mat4x4_row(vec4 r, mat4x4 M, int i)
+{
+	int k;
+	for(k=0; k<4; ++k)
+		r[k] = M[k][i];
+}
+static inline void mat4x4_col(vec4 r, mat4x4 M, int i)
+{
+	int k;
+	for(k=0; k<4; ++k)
+		r[k] = M[i][k];
+}
+static inline void mat4x4_transpose(mat4x4 M, mat4x4 N)
+{
+	int i, j;
+	mat4x4 R;
+	for(j=0; j<4; ++j) {
+		for(i=0; i<4; ++i) {
+			R[i][j] = N[j][i];
+		}
+	}
+	memcpy(M, R, sizeof(R));
+}
 static inline void mat4x4_invert(mat4x4 T, mat4x4 M)
 {
-	float s[6];
-	float c[6];
-	s[0] = M[0][0]*M[1][1] - M[1][0]*M[0][1];
-	s[1] = M[0][0]*M[1][2] - M[1][0]*M[0][2];
-	s[2] = M[0][0]*M[1][3] - M[1][0]*M[0][3];
-	s[3] = M[0][1]*M[1][2] - M[1][1]*M[0][2];
-	s[4] = M[0][1]*M[1][3] - M[1][1]*M[0][3];
-	s[5] = M[0][2]*M[1][3] - M[1][2]*M[0][3];
-
-	c[0] = M[2][0]*M[3][1] - M[3][0]*M[2][1];
-	c[1] = M[2][0]*M[3][2] - M[3][0]*M[2][2];
-	c[2] = M[2][0]*M[3][3] - M[3][0]*M[2][3];
-	c[3] = M[2][1]*M[3][2] - M[3][1]*M[2][2];
-	c[4] = M[2][1]*M[3][3] - M[3][1]*M[2][3];
-	c[5] = M[2][2]*M[3][3] - M[3][2]*M[2][3];
-	
-	/* Assumes it is invertible */
-	float idet = 1.0f/( s[0]*c[5]-s[1]*c[4]+s[2]*c[3]+s[3]*c[2]-s[4]*c[1]+s[5]*c[0] );
-	
-	T[0][0] = ( M[1][1] * c[5] - M[1][2] * c[4] + M[1][3] * c[3]) * idet;
-	T[0][1] = (-M[0][1] * c[5] + M[0][2] * c[4] - M[0][3] * c[3]) * idet;
-	T[0][2] = ( M[3][1] * s[5] - M[3][2] * s[4] + M[3][3] * s[3]) * idet;
-	T[0][3] = (-M[2][1] * s[5] + M[2][2] * s[4] - M[2][3] * s[3]) * idet;
-
-	T[1][0] = (-M[1][0] * c[5] + M[1][2] * c[2] - M[1][3] * c[1]) * idet;
-	T[1][1] = ( M[0][0] * c[5] - M[0][2] * c[2] + M[0][3] * c[1]) * idet;
-	T[1][2] = (-M[3][0] * s[5] + M[3][2] * s[2] - M[3][3] * s[1]) * idet;
-	T[1][3] = ( M[2][0] * s[5] - M[2][2] * s[2] + M[2][3] * s[1]) * idet;
-
-	T[2][0] = ( M[1][0] * c[4] - M[1][1] * c[2] + M[1][3] * c[0]) * idet;
-	T[2][1] = (-M[0][0] * c[4] + M[0][1] * c[2] - M[0][3] * c[0]) * idet;
-	T[2][2] = ( M[3][0] * s[4] - M[3][1] * s[2] + M[3][3] * s[0]) * idet;
-	T[2][3] = (-M[2][0] * s[4] + M[2][1] * s[2] - M[2][3] * s[0]) * idet;
-
-	T[3][0] = (-M[1][0] * c[3] + M[1][1] * c[1] - M[1][2] * c[0]) * idet;
-	T[3][1] = ( M[0][0] * c[3] - M[0][1] * c[1] + M[0][2] * c[0]) * idet;
-	T[3][2] = (-M[3][0] * s[3] + M[3][1] * s[1] - M[3][2] * s[0]) * idet;
-	T[3][3] = ( M[2][0] * s[3] - M[2][1] * s[1] + M[2][2] * s[0]) * idet;
+	mat4x4 R;
+	R[0][0] = M[1][1]*(M[2][2]*M[3][3] - M[2][3]*M[3][2]) - M[2][1]*(M[1][2]*M[3][3] - M[1][3]*M[3][2]) - M[3][1]*(M[1][3]*M[2][2] - M[1][2]*M[2][3]);
+	R[0][1] = M[0][1]*(M[2][3]*M[3][2] - M[2][2]*M[3][3]) - M[2][1]*(M[0][3]*M[3][2] - M[0][2]*M[3][3]) - M[3][1]*(M[0][2]*M[2][3] - M[0][3]*M[2][2]);
+	R[0][2] = M[0][1]*(M[1][2]*M[3][3] - M[1][3]*M[3][2]) - M[1][1]*(M[0][2]*M[3][3] - M[0][3]*M[3][2]) - M[3][1]*(M[0][3]*M[1][2] - M[0][2]*M[1][3]);
+	R[0][3] = M[0][1]*(M[1][3]*M[2][2] - M[1][2]*M[2][3]) - M[1][1]*(M[0][3]*M[2][2] - M[0][2]*M[2][3]) - M[2][1]*(M[0][2]*M[1][3] - M[0][3]*M[1][2]);
+
+	R[1][0] = M[1][0]*(M[2][3]*M[3][2] - M[2][2]*M[3][3]) - M[2][0]*(M[1][3]*M[3][2] - M[1][2]*M[3][3]) - M[3][0]*(M[1][2]*M[2][3] - M[1][3]*M[2][2]);
+	R[1][1] = M[0][0]*(M[2][2]*M[3][3] - M[2][3]*M[3][2]) - M[2][0]*(M[0][2]*M[3][3] - M[0][3]*M[3][2]) - M[3][0]*(M[0][3]*M[2][2] - M[0][2]*M[2][3]);
+	R[1][2] = M[0][0]*(M[1][3]*M[3][2] - M[1][2]*M[3][3]) - M[1][0]*(M[0][3]*M[3][2] - M[0][2]*M[3][3]) - M[3][0]*(M[0][2]*M[1][3] - M[0][3]*M[1][2]);
+	R[1][3] = M[0][0]*(M[1][2]*M[2][3] - M[1][3]*M[2][2]) - M[1][0]*(M[0][2]*M[2][3] - M[0][3]*M[2][2]) - M[2][0]*(M[0][3]*M[1][2] - M[0][2]*M[1][3]);
+
+	R[2][0]  = M[1][0]*(M[2][1]*M[3][3] - M[2][3]*M[3][1]) - M[2][0]*(M[1][1]*M[3][3] - M[1][3]*M[3][1]) - M[3][0]*(M[1][3]*M[2][1] - M[1][1]*M[2][3]);
+	R[2][1]  = M[0][0]*(M[2][3]*M[3][1] - M[2][1]*M[3][3]) - M[2][0]*(M[0][3]*M[3][1] - M[0][1]*M[3][3]) - M[3][0]*(M[0][1]*M[2][3] - M[0][3]*M[2][1]);
+	R[2][2] = M[0][0]*(M[1][1]*M[3][3] - M[1][3]*M[3][1]) - M[1][0]*(M[0][1]*M[3][3] - M[0][3]*M[3][1]) - M[3][0]*(M[0][3]*M[1][1] - M[0][1]*M[1][3]);
+	R[2][3] = M[0][0]*(M[1][3]*M[2][1] - M[1][1]*M[2][3]) - M[1][0]*(M[0][3]*M[2][1] - M[0][1]*M[2][3]) - M[2][0]*(M[0][1]*M[1][3] - M[0][3]*M[1][1]);
+
+	R[3][0] = M[1][0]*(M[2][2]*M[3][1] - M[2][1]*M[3][2]) - M[2][0]*(M[1][2]*M[3][1] - M[1][1]*M[3][2]) - M[3][0]*(M[1][1]*M[2][2] - M[1][2]*M[2][1]);
+	R[3][1] = M[0][0]*(M[2][1]*M[3][2] - M[2][2]*M[3][1]) - M[2][0]*(M[0][1]*M[3][2] - M[0][2]*M[3][1]) - M[3][0]*(M[0][2]*M[2][1] - M[0][1]*M[2][2]);
+	R[3][2] = M[0][0]*(M[1][2]*M[3][1] - M[1][1]*M[3][2]) - M[1][0]*(M[0][2]*M[3][1] - M[0][1]*M[3][2]) - M[3][0]*(M[0][1]*M[1][2] - M[0][2]*M[1][1]);
+	R[3][3] = M[0][0]*(M[1][1]*M[2][2] - M[1][2]*M[2][1]) - M[1][0]*(M[0][1]*M[2][2] - M[0][2]*M[2][1]) - M[2][0]*(M[0][2]*M[1][1] - M[0][1]*M[1][2]);
+	memcpy(T, R, 16*sizeof(float));
 }
 static inline void mat4x4_orthonormalize(mat4x4 R, mat4x4 M)
 {
@@ -330,109 +299,42 @@ static inline void mat4x4_orthonormalize(mat4x4 R, mat4x4 M)
 
 static inline void mat4x4_frustum(mat4x4 M, float l, float r, float b, float t, float n, float f)
 {
-	M[0][0] = 2.f*n/(r-l);
-	M[0][1] = M[0][2] = M[0][3] = 0.f;
+	M[0][0] = 2.*n/(r-l);
+	M[0][1] = M[0][2] = M[0][3] = 0.;
 	
 	M[1][1] = 2.*n/(t-b);
-	M[1][0] = M[1][2] = M[1][3] = 0.f;
+	M[1][0] = M[1][2] = M[1][3] = 0.;
 
 	M[2][0] = (r+l)/(r-l);
 	M[2][1] = (t+b)/(t-b);
 	M[2][2] = -(f+n)/(f-n);
-	M[2][3] = -1.f;
+	M[2][3] = -1;
 	
-	M[3][2] = -2.f*(f*n)/(f-n);
-	M[3][0] = M[3][1] = M[3][3] = 0.f;
+	M[3][2] = -2.*(f*n)/(f-n);
+	M[3][0] = M[3][1] = M[3][3] = 0.;
 }
 static inline void mat4x4_ortho(mat4x4 M, float l, float r, float b, float t, float n, float f)
 {
-	M[0][0] = 2.f/(r-l);
-	M[0][1] = M[0][2] = M[0][3] = 0.f;
+	M[0][0] = 2./(r-l);
+	M[0][1] = M[0][2] = M[0][3] = 0.;
 
-	M[1][1] = 2.f/(t-b);
-	M[1][0] = M[1][2] = M[1][3] = 0.f;
+	M[1][1] = 2./(t-b);
+	M[1][0] = M[1][2] = M[1][3] = 0.;
 
-	M[2][2] = -2.f/(f-n);
-	M[2][0] = M[2][1] = M[2][3] = 0.f;
-	
-	M[3][0] = -(r+l)/(r-l);
-	M[3][1] = -(t+b)/(t-b);
-	M[3][2] = -(f+n)/(f-n);
-	M[3][3] = 1.f;
-}
-static inline void mat4x4_perspective(mat4x4 m, float y_fov, float aspect, float n, float f)
-{
-	/* NOTE: Degrees are an unhandy unit to work with.
-	 * linmath.h uses radians for everything! */
-	float const a = 1.f / tan(y_fov / 2.f);
-
-	m[0][0] = a / aspect;
-	m[0][1] = 0.f;
-	m[0][2] = 0.f;
-	m[0][3] = 0.f;
-
-	m[1][0] = 0.f;
-	m[1][1] = a;
-	m[1][2] = 0.f;
-	m[1][3] = 0.f;
-
-	m[2][0] = 0.f;
-	m[2][1] = 0.f;
-	m[2][2] = -((f + n) / (f - n));
-	m[2][3] = -1.f;
-
-	m[3][0] = 0.f;
-	m[3][1] = 0.f;
-	m[3][2] = -((2.f * f * n) / (f - n));
-	m[3][3] = 0.f;
-}
-static inline void mat4x4_look_at(mat4x4 m, vec3 eye, vec3 center, vec3 up)
-{
-	/* Adapted from Android's OpenGL Matrix.java.                        */
-	/* See the OpenGL GLUT documentation for gluLookAt for a description */
-	/* of the algorithm. We implement it in a straightforward way:       */
-
-	/* TODO: The negation of of can be spared by swapping the order of
-	 *       operands in the following cross products in the right way. */
-	vec3 f;
-	vec3_sub(f, center, eye);	
-	vec3_norm(f, f);	
+	M[2][2] = -2./(f-n);
+	M[2][0] = M[2][1] = M[2][3] = 0.;
 	
-	vec3 s;
-	vec3_mul_cross(s, f, up);
-	vec3_norm(s, s);
-
-	vec3 t;
-	vec3_mul_cross(t, s, f);
-
-	m[0][0] =  s[0];
-	m[0][1] =  t[0];
-	m[0][2] = -f[0];
-	m[0][3] =   0.f;
-
-	m[1][0] =  s[1];
-	m[1][1] =  t[1];
-	m[1][2] = -f[1];
-	m[1][3] =   0.f;
-
-	m[2][0] =  s[2];
-	m[2][1] =  t[2];
-	m[2][2] = -f[2];
-	m[2][3] =   0.f;
-
-	m[3][0] =  0.f;
-	m[3][1] =  0.f;
-	m[3][2] =  0.f;
-	m[3][3] =  1.f;
-
-	mat4x4_translate_in_place(m, -eye[0], -eye[1], -eye[2]);
+	M[3][0] = (r+l)/(r-l);
+	M[3][1] = (t+b)/(t-b);
+	M[3][2] = (f+n)/(f-n);
+	M[3][3] = 1.;
 }
 
 typedef float quat[4];
 static inline void quat_identity(quat q)
 {
-	q[0] = q[1] = q[2] = 0.f;
-	q[3] = 1.f;
+	q[0] = q[1] = q[2] = 0.;
+	q[3] = 1.;
 }
 static inline void quat_add(quat r, quat a, quat b)
 {
@@ -464,7 +366,7 @@ static inline void quat_scale(quat r, quat v, float s)
 }
 static inline float quat_inner_product(quat a, quat b)
 {
-	float p = 0.f;
+	float p = 0.;
 	int i;
 	for(i=0; i<4; ++i)
 		p += b[i]*a[i];
@@ -477,34 +379,17 @@ static inline void quat_conj(quat r, quat q)
 		r[i] = -q[i];
 	r[3] = q[3];
 }
-static inline void quat_rotate(quat r, float angle, vec3 axis) {
-	vec3 v;
-	vec3_scale(v, axis, sinf(angle / 2));
-	int i;
-	for(i=0; i<3; ++i)
-		r[i] = v[i];
-	r[3] = cosf(angle / 2);
-}
-#define quat_norm vec4_norm
+static inline void quat_norm(quat r, quat v) { vec4_norm(r, v); }
 static inline void quat_mul_vec3(vec3 r, quat q, vec3 v)
 {
-/*
- * Method by Fabian 'ryg' Giessen (of Farbrausch)
-t = 2 * cross(q.xyz, v)
-v' = v + q.w * t + cross(q.xyz, t)
- */
-	vec3 t;
-	vec3 q_xyz = {q[0], q[1], q[2]};
-	vec3 u = {q[0], q[1], q[2]};
+	quat q_;
+	quat v_ = {v[0], v[1], v[2], 0.};
 
-	vec3_mul_cross(t, q_xyz, v);
-	vec3_scale(t, t, 2);
-
-	vec3_mul_cross(u, q_xyz, t);
-	vec3_scale(t, t, q[3]);
-
-	vec3_add(r, v, t);
-	vec3_add(r, r, u);
+	quat_conj(q_, q);
+	quat_norm(q_, q_);
+	quat_mul(q_, v_, q_);
+	quat_mul(q_, q, q_);
+	memcpy(r, q_, 3*sizeof(float));
 }
 static inline void mat4x4_from_quat(mat4x4 M, quat q)
 {
@@ -518,38 +403,35 @@ static inline void mat4x4_from_quat(mat4x4 M, quat q)
 	float d2 = d*d;
 	
 	M[0][0] = a2 + b2 - c2 - d2;
-	M[0][1] = 2.f*(b*c + a*d);
-	M[0][2] = 2.f*(b*d - a*c);
-	M[0][3] = 0.f;
+	M[0][1] = 2*(b*c + a*d);
+	M[0][2] = 2*(b*d - a*c);
+	M[0][3] = 0.;
 
 	M[1][0] = 2*(b*c - a*d);
 	M[1][1] = a2 - b2 + c2 - d2;
-	M[1][2] = 2.f*(c*d + a*b);
-	M[1][3] = 0.f;
+	M[1][2] = 2*(c*d + a*b);
+	M[1][3] = 0.;
 
-	M[2][0] = 2.f*(b*d + a*c);
-	M[2][1] = 2.f*(c*d - a*b);
+	M[2][0] = 2*(b*d + a*c);
+	M[2][1] = 2*(c*d - a*b);
 	M[2][2] = a2 - b2 - c2 + d2;
-	M[2][3] = 0.f;
+	M[2][3] = 0.;
 
-	M[3][0] = M[3][1] = M[3][2] = 0.f;
-	M[3][3] = 1.f;
+	M[3][0] = M[3][1] = M[3][2] = 0.;
+	M[3][3] = 1.;
 }
-
-static inline void mat4x4o_mul_quat(mat4x4 R, mat4x4 M, quat q)
+static inline void mat4x4_mul_quat(mat4x4 R, mat4x4 M, quat q)
 {
-/*  XXX: The way this is written only works for othogonal matrices. */
-/* TODO: Take care of non-orthogonal case. */
-	quat_mul_vec3(R[0], q, M[0]);
-	quat_mul_vec3(R[1], q, M[1]);
-	quat_mul_vec3(R[2], q, M[2]);
+	quat_mul_vec3(R[0], M[0], q);
+	quat_mul_vec3(R[1], M[1], q);
+	quat_mul_vec3(R[2], M[2], q);
 
-	R[3][0] = R[3][1] = R[3][2] = 0.f;
-	R[3][3] = 1.f;
+	R[3][0] = R[3][1] = R[3][2] = 0.;
+	R[3][3] = 1.;
 }
 static inline void quat_from_mat4x4(quat q, mat4x4 M)
 {
-	float r=0.f;
+	float r=0.;
 	int i;
 
 	int perm[] = { 0, 1, 2, 0, 1 };
@@ -563,18 +445,42 @@ static inline void quat_from_mat4x4(quat q, mat4x4 M)
 		p = &perm[i];
 	}
 
-	r = sqrtf(1.f + M[p[0]][p[0]] - M[p[1]][p[1]] - M[p[2]][p[2]] );
+	r = sqrtf(1. + M[p[0]][p[0]] - M[p[1]][p[1]] - M[p[2]][p[2]] );
 
-	if(r < 1e-6) {
-		q[0] = 1.f;
-		q[1] = q[2] = q[3] = 0.f;
-		return;
+	q[0] = r/2.;
+	q[1] = (M[p[0]][p[1]] - M[p[1]][p[0]])/(2.*r);
+	q[2] = (M[p[2]][p[0]] - M[p[0]][p[2]])/(2.*r);
+	q[3] = (M[p[2]][p[1]] - M[p[1]][p[2]])/(2.*r);
+}
+
+static inline void mat4x4_arcball(mat4x4 R, mat4x4 M, vec2 _a, vec2 _b, float s)
+{
+	vec2 a; memcpy(a, _a, sizeof(a));
+	vec2 b; memcpy(b, _b, sizeof(b));
+	
+	float z_a = 0.;
+	float z_b = 0.;
+
+	if(vec2_len(a) < 1.) {
+		z_a = sqrtf(1. - vec2_mul_inner(a, a));
+	} else {
+		vec2_norm(a, a);
 	}
 
-	q[0] = r/2.f;
-	q[1] = (M[p[0]][p[1]] - M[p[1]][p[0]])/(2.f*r);
-	q[2] = (M[p[2]][p[0]] - M[p[0]][p[2]])/(2.f*r);
-	q[3] = (M[p[2]][p[1]] - M[p[1]][p[2]])/(2.f*r);
+	if(vec2_len(b) < 1.) {
+		z_b = sqrtf(1. - vec2_mul_inner(b, b));
+	} else {
+		vec2_norm(b, b);
+	}
+	
+	vec3 a_ = {a[0], a[1], z_a};
+	vec3 b_ = {b[0], b[1], z_b};
+
+	vec3 c_;
+	vec3_mul_cross(c_, a_, b_);
+
+	float const angle = acos(vec3_mul_inner(a_, b_)) * s;
+	mat4x4_rotate(R, M, c_[0], c_[1], c_[2], angle);
 }
 
 #endif