diff --git a/CMakeLists.txt b/CMakeLists.txt
index 9579aeba..07e3e428 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -6,7 +6,7 @@ project(glm)
 add_definitions(-D_CRT_SECURE_NO_WARNINGS)
 #add_definitions(-S)
 #add_definitions(-s)
-add_definitions(-msse2)
+#add_definitions(-msse2)
 #add_definitions(-m32)
 #add_definitions(-mfpmath=387)
 #add_definitions(-ffast-math)
diff --git a/doc/CMakeLists.txt b/doc/CMakeLists.txt
index 6d9f918b..da40c39e 100644
--- a/doc/CMakeLists.txt
+++ b/doc/CMakeLists.txt
@@ -1,10 +1,12 @@
 set(NAME glm-doc)
 
+file(GLOB ROOT_TXT doxyfile ../*.txt)
 file(GLOB ROOT_CPP src/*.cpp)
 file(GLOB ROOT_XML src/*.xml)
 file(GLOB ROOT_XSL src/*.xsl)
 
+source_group("TXT Files" FILES ${ROOT_TXT})
 source_group("XML Files" FILES ${ROOT_XML})
 source_group("XSL Files" FILES ${ROOT_XSL})
 
-add_executable(${NAME} ${ROOT_CPP} ${ROOT_XML} ${ROOT_XSL})
+add_executable(${NAME} ${ROOT_CPP} ${ROOT_XML} ${ROOT_XSL} ${ROOT_TXT})
diff --git a/glm/core/_detail.hpp b/glm/core/_detail.hpp
index 9c826409..7cdc2ed0 100644
--- a/glm/core/_detail.hpp
+++ b/glm/core/_detail.hpp
@@ -327,7 +327,7 @@ namespace detail
 #	define GLM_RESTRICT_VAR __restrict
 #elif((GLM_COMPILER & GLM_COMPILER_GCC) && (GLM_COMPILER >= GLM_COMPILER_GCC31))
 #	define GLM_DEPRECATED __attribute__((__deprecated__))
-#	define GLM_ALIGN(x) __attribute__(aligned(x)) 
+#	define GLM_ALIGN(x) __attribute__((aligned(x))) 
 #	if(GLM_COMPILER >= GLM_COMPILER_GCC33)
 #		define GLM_RESTRICT __restrict__
 #		define GLM_RESTRICT_VAR __restrict__
diff --git a/glm/core/intrinsic_common.inl b/glm/core/intrinsic_common.inl
index b11f000d..fd031ef8 100644
--- a/glm/core/intrinsic_common.inl
+++ b/glm/core/intrinsic_common.inl
@@ -258,7 +258,7 @@ inline __m128 sse_inf_ps(__m128 x)
 }
 
 // SSE scalar reciprocal sqrt using rsqrt op, plus one Newton-Rhaphson iteration
-// By Elan Ruskin, 
+// By Elan Ruskin, http://assemblyrequired.crashworks.org/
 inline __m128 sse_sqrt_wip_ss(__m128 const & x)
 {
 	__m128 recip = _mm_rsqrt_ss(x);  // "estimate" opcode
diff --git a/glm/gtc/matrix_transform.hpp b/glm/gtc/matrix_transform.hpp
index 477dc2eb..f7d466f8 100644
--- a/glm/gtc/matrix_transform.hpp
+++ b/glm/gtc/matrix_transform.hpp
@@ -133,6 +133,14 @@ namespace glm
 			detail::tmat4x4<T> const & proj, 
 			detail::tvec4<U> const & viewport);
 
+		//! Define a picking region
+		//! From GLM_GTC_matrix_transform extension.
+		template <typename T, typename U> 
+		detail::tmat4x4<T> pickMatrix(
+			detail::tvec2<T> const & center, 
+			detail::tvec2<T> const & delta, 
+			detail::tvec4<U> const & viewport);
+
 		//! Build a look at view matrix.
 		//! From GLM_GTC_matrix_transform extension.
 		template <typename T> 
diff --git a/glm/gtc/matrix_transform.inl b/glm/gtc/matrix_transform.inl
index 858fa68c..b8e79ca2 100644
--- a/glm/gtc/matrix_transform.inl
+++ b/glm/gtc/matrix_transform.inl
@@ -324,6 +324,25 @@ namespace matrix_transform
 		return detail::tvec3<T>(obj);
 	}
 
+	template <typename T, typename U> 
+	detail::tmat4x4<T> pickMatrix
+	(
+		detail::tvec2<T> const & center, 
+		detail::tvec2<T> const & delta, 
+		detail::tvec4<U> const & viewport
+	)
+	{
+		assert(delta.x > 0.0f && delta.y > 0.0f)
+		detail::tmat4x4<T> Result(1.0f);
+
+		if(!(delta.x > 0.0f && delta.y > 0.0f)) 
+			return Result; // Error
+
+		// Translate and scale the picked region to the entire window
+		Result = translate(Result, (T(viewport[2]) - T(2) * (x - T(viewport[0]))) / delta.x, (T(viewport[3]) - T(2) * (y - T(viewport[1]))) / delta.y, T(0));
+		return scale(Result, T(viewport[2]) / delta.x, T(viewport[3]) / delta.y, T(1));
+	}
+
     template <typename T> 
     inline detail::tmat4x4<T> lookAt(
 		const detail::tvec3<T>& eye, 
diff --git a/glm/gtc/quaternion.hpp b/glm/gtc/quaternion.hpp
index 34da0401..df475421 100644
--- a/glm/gtc/quaternion.hpp
+++ b/glm/gtc/quaternion.hpp
@@ -150,7 +150,7 @@ namespace glm
 			detail::tquat<T> const & q1, 
 			detail::tquat<T> const & q2);
 		
-		//! Returns a LERP interpolated quaternion of x and y according a. 
+		//! Returns a SLERP interpolated quaternion of x and y according a. 
 		//! From GLM_GTC_quaternion extension.
 		template <typename T> 
 		detail::tquat<T> mix(
diff --git a/glm/gtc/quaternion.inl b/glm/gtc/quaternion.inl
index df9d65d4..ee1e804a 100644
--- a/glm/gtc/quaternion.inl
+++ b/glm/gtc/quaternion.inl
@@ -370,6 +370,43 @@ namespace quaternion{
             k0 * x.z + k1 * y2.z);
     }
 
+    template <typename T>
+    inline detail::tquat<T> mix2
+	(
+		detail::tquat<T> const & x, 
+		detail::tquat<T> const & y, 
+		T const & a
+	)
+    {
+        bool flip = false;
+		if(a <= T(0)) return x;
+        if(a >= T(1)) return y;
+
+        T cos_t = dot(x, y);
+		if(cos_t < T(0))
+		{
+			cos_t = -cos_t;
+			flip = true;
+		}
+
+		T alpha(0), beta(0);
+
+		if(T(1) - cos_t < 1e-7)
+			beta = T(1) - alpha;
+		else
+		{
+			T theta = acos(cos_t);
+			T sin_t = sin(theta);
+			beta = sin(theta * (T(1) - alpha)) / sin_t;
+			alpha = sin(alpha * theta) / sin_t;
+		}
+
+		if(flip)
+			alpha = -alpha;
+		
+        return normalize(beta * x + alpha * y2);
+    }
+
     template <typename T> 
     inline detail::tquat<T> conjugate
 	(
diff --git a/glm/gtx/simd_mat4.hpp b/glm/gtx/simd_mat4.hpp
index f48df975..95923aaa 100644
--- a/glm/gtx/simd_mat4.hpp
+++ b/glm/gtx/simd_mat4.hpp
@@ -142,7 +142,7 @@ namespace glm
 		//! Multiply matrix x by matrix y component-wise, i.e.,
 		//! result[i][j] is the scalar product of x[i][j] and y[i][j].
 		//! (From GLM_GTX_simd_mat4 extension).
-		detail::fmat4x4SIMD simdMatrixCompMult(
+		detail::fmat4x4SIMD matrixCompMult(
 			detail::fmat4x4SIMD const & x,
 			detail::fmat4x4SIMD const & y);
 
@@ -150,23 +150,23 @@ namespace glm
 		//! and the second parameter r as a row vector
 		//! and does a linear algebraic matrix multiply c * r.
 		//! (From GLM_GTX_simd_mat4 extension).
-		detail::fmat4x4SIMD simdOuterProduct(
+		detail::fmat4x4SIMD outerProduct(
 			detail::fvec4SIMD const & c,
 			detail::fvec4SIMD const & r);
 
 		//! Returns the transposed matrix of x
 		//! (From GLM_GTX_simd_mat4 extension).
-		detail::fmat4x4SIMD simdTranspose(
+		detail::fmat4x4SIMD transpose(
 			detail::fmat4x4SIMD const & x);
 
 		//! Return the determinant of a mat4 matrix.
 		//! (From GLM_GTX_simd_mat4 extension).
-		float simdDeterminant(
+		float determinant(
 			detail::fmat4x4SIMD const & m);
 
 		//! Return the inverse of a mat4 matrix.
 		//! (From GLM_GTX_simd_mat4 extension).
-		detail::fmat4x4SIMD simdInverse(
+		detail::fmat4x4SIMD inverse(
 			detail::fmat4x4SIMD const & m);
 
 	}//namespace simd_mat4
diff --git a/glm/gtx/simd_mat4.inl b/glm/gtx/simd_mat4.inl
index 59d1065e..c9b6f450 100644
--- a/glm/gtx/simd_mat4.inl
+++ b/glm/gtx/simd_mat4.inl
@@ -242,7 +242,7 @@ namespace simd_mat4
 		detail::fmat4x4SIMD const & x
 	)
 	{
-		detail::tmat4x4<float> Result;
+		GLM_ALIGN(16) detail::tmat4x4<float> Result;
 		_mm_store_ps(&Result[0][0], x.Data[0].Data);
 		_mm_store_ps(&Result[1][0], x.Data[1].Data);
 		_mm_store_ps(&Result[2][0], x.Data[2].Data);
@@ -250,7 +250,7 @@ namespace simd_mat4
 		return Result;
 	}
 
-	inline detail::fmat4x4SIMD simdMatrixCompMult
+	inline detail::fmat4x4SIMD matrixCompMult
 	(
 		detail::fmat4x4SIMD const & x,
 		detail::fmat4x4SIMD const & y
@@ -264,30 +264,40 @@ namespace simd_mat4
 		return result;
 	}
 
-	inline detail::fmat4x4SIMD simdOuterProduct
+	inline detail::fmat4x4SIMD outerProduct
 	(
 		detail::fvec4SIMD const & c,
 		detail::fvec4SIMD const & r
 	)
 	{
+		__m128 Shu0 = _mm_shuffle_ps(r.Data, r.Data, _MM_SHUFFLE(0, 0, 0, 0));
+		__m128 Shu1 = _mm_shuffle_ps(r.Data, r.Data, _MM_SHUFFLE(1, 1, 1, 1));
+		__m128 Shu2 = _mm_shuffle_ps(r.Data, r.Data, _MM_SHUFFLE(2, 2, 2, 2));
+		__m128 Shu3 = _mm_shuffle_ps(r.Data, r.Data, _MM_SHUFFLE(3, 3, 3, 3));
 
+		detail::fmat4x4SIMD result(detail::fmat4x4SIMD::null);
+		result[0].Data = _mm_mul_ps(c.Data, Shu0);
+		result[1].Data = _mm_mul_ps(c.Data, Shu1);
+		result[2].Data = _mm_mul_ps(c.Data, Shu2);
+		result[3].Data = _mm_mul_ps(c.Data, Shu3);
+		return result;
 	}
 
-	inline detail::fmat4x4SIMD simdTranspose(detail::fmat4x4SIMD const & m)
+	inline detail::fmat4x4SIMD transpose(detail::fmat4x4SIMD const & m)
 	{
 		detail::fmat4x4SIMD result;
 		detail::sse_transpose_ps(&m[0].Data, &result[0].Data);
 		return result;
 	}
 
-	inline float simdDeterminant(detail::fmat4x4SIMD const & m)
+	inline float determinant(detail::fmat4x4SIMD const & m)
 	{
 		float Result;
 		_mm_store_ss(&Result, detail::sse_det_ps(&m[0].Data));
 		return Result;
 	}
 
-	inline detail::fmat4x4SIMD simdInverse(detail::fmat4x4SIMD const & m)
+	inline detail::fmat4x4SIMD inverse(detail::fmat4x4SIMD const & m)
 	{
 		detail::fmat4x4SIMD result;
 		detail::sse_inverse_ps(&m[0].Data, &result[0].Data);
diff --git a/glm/gtx/simd_vec4.hpp b/glm/gtx/simd_vec4.hpp
index 186fd045..83691a80 100644
--- a/glm/gtx/simd_vec4.hpp
+++ b/glm/gtx/simd_vec4.hpp
@@ -336,23 +336,47 @@ namespace glm
 
 		//! Returns the length of x, i.e., sqrt(x * x).
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		float simdLength(
+		float length(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the length of x, i.e., sqrt(x * x).
+		//! Less accurate but much faster than simdLength.
+		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
+		float fastLength(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the length of x, i.e., sqrt(x * x).
+		//! Slightly more accurate but much slower than simdLength.
+		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
+		float niceLength(
 			detail::fvec4SIMD const & x);
 
 		//! Returns the length of x, i.e., sqrt(x * x).
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdLength4(
+		detail::fvec4SIMD length4(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the length of x, i.e., sqrt(x * x).
+		//! Less accurate but much faster than simdLength4.
+		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
+		detail::fvec4SIMD fastLength4(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the length of x, i.e., sqrt(x * x).
+		//! Slightly more accurate but much slower than simdLength4.
+		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
+		detail::fvec4SIMD niceLength4(
 			detail::fvec4SIMD const & x);
 
 		//! Returns the distance betwwen p0 and p1, i.e., length(p0 - p1).
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		float simdDistance(
+		float distance(
 			detail::fvec4SIMD const & p0,
 			detail::fvec4SIMD const & p1);
 
 		//! Returns the distance betwwen p0 and p1, i.e., length(p0 - p1).
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdDistance4(
+		detail::fvec4SIMD distance4(
 			detail::fvec4SIMD const & p0,
 			detail::fvec4SIMD const & p1);
 
@@ -364,19 +388,25 @@ namespace glm
 
 		//! Returns the dot product of x and y, i.e., result = x * y.
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdDot4(
+		detail::fvec4SIMD dot4(
 			detail::fvec4SIMD const & x,
 			detail::fvec4SIMD const & y);
 
 		//! Returns the cross product of x and y.
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdCross(
+		detail::fvec4SIMD cross(
 			detail::fvec4SIMD const & x,
 			detail::fvec4SIMD const & y);
 
 		//! Returns a vector in the same direction as x but with length of 1.
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdNormalize(
+		detail::fvec4SIMD normalize(
+			detail::fvec4SIMD const & x);
+
+		//! Returns a vector in the same direction as x but with length of 1.
+		//! Less accurate but much faster than simdNormalize.
+		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
+		detail::fvec4SIMD fastNormalize(
 			detail::fvec4SIMD const & x);
 
 		//! If dot(Nref, I) < 0.0, return N, otherwise, return -N.
@@ -389,7 +419,7 @@ namespace glm
 		//! For the incident vector I and surface orientation N,
 		//! returns the reflection direction : result = I - 2.0 * dot(N, I) * N.
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdReflect(
+		detail::fvec4SIMD reflect(
 			detail::fvec4SIMD const & I,
 			detail::fvec4SIMD const & N);
 
@@ -397,10 +427,39 @@ namespace glm
 		//! and the ratio of indices of refraction eta,
 		//! return the refraction vector.
 		//! (From GLM_GTX_simd_vec4 extension, geometry functions)
-		detail::fvec4SIMD simdRefract(
+		detail::fvec4SIMD refract(
 			detail::fvec4SIMD const & I,
 			detail::fvec4SIMD const & N,
 			float const & eta);
+
+		//! Returns the positive square root of x.
+		//! (From GLM_GTX_simd_vec4 extension, exponential function)
+		detail::fvec4SIMD sqrt(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the positive square root of x with the nicest quality but very slow.
+		//! Slightly more accurate but much slower than simdSqrt.
+		//! (From GLM_GTX_simd_vec4 extension, exponential function)
+		detail::fvec4SIMD niceSqrt(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the positive square root of x
+		//! Less accurate but much faster than sqrt.
+		//! (From GLM_GTX_simd_vec4 extension, exponential function)
+		detail::fvec4SIMD fastSqrt(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the reciprocal of the positive square root of x.
+		//! (From GLM_GTX_simd_vec4 extension, exponential function)
+		detail::fvec4SIMD inversesqrt(
+			detail::fvec4SIMD const & x);
+
+		//! Returns the reciprocal of the positive square root of x.
+		//! Faster than inversesqrt but less accurate.
+		//! (From GLM_GTX_simd_vec4 extension, exponential function)
+		detail::fvec4SIMD fastInversesqrt(
+			detail::fvec4SIMD const & x);
+
 	}//namespace simd_vec4
 	}//namespace gtx
 }//namespace glm
diff --git a/glm/gtx/simd_vec4.inl b/glm/gtx/simd_vec4.inl
index 28b44eb0..ae5a250f 100644
--- a/glm/gtx/simd_vec4.inl
+++ b/glm/gtx/simd_vec4.inl
@@ -275,7 +275,7 @@ namespace glm
 			detail::fvec4SIMD const & x
 		)
 		{
-			detail::tvec4<float> Result;
+			GLM_ALIGN(4) detail::tvec4<float> Result;
 			_mm_store_ps(&Result[0], x.Data);
 			return Result;
 		}
@@ -530,25 +530,67 @@ namespace glm
 			return _mm_add_ps(_mm_mul_ps(a.Data, b.Data), c.Data);
 		}
 
-		inline float simdLength
+		inline float length
 		(
 			detail::fvec4SIMD const & x
 		)
 		{
+			detail::fvec4SIMD dot0 = detail::sse_dot_ss(x.Data, x.Data);
+			detail::fvec4SIMD sqt0 = sqrt(dot0);
 			float Result = 0;
-			_mm_store_ss(&Result, detail::sse_len_ps(x.Data));
+			_mm_store_ss(&Result, sqt0.Data);
 			return Result;
 		}
 
-		inline detail::fvec4SIMD simdLength4
+		inline float fastLength
 		(
 			detail::fvec4SIMD const & x
 		)
 		{
-			return detail::sse_len_ps(x.Data);
+			detail::fvec4SIMD dot0 = detail::sse_dot_ss(x.Data, x.Data);
+			detail::fvec4SIMD sqt0 = fastSqrt(dot0);
+			float Result = 0;
+			_mm_store_ss(&Result, sqt0.Data);
+			return Result;
 		}
 
-		inline float simdDistance
+		inline float niceLength
+		(
+			detail::fvec4SIMD const & x
+		)
+		{
+			detail::fvec4SIMD dot0 = detail::sse_dot_ss(x.Data, x.Data);
+			detail::fvec4SIMD sqt0 = niceSqrt(dot0);
+			float Result = 0;
+			_mm_store_ss(&Result, sqt0.Data);
+			return Result;
+		}
+
+		inline detail::fvec4SIMD length4
+		(
+			detail::fvec4SIMD const & x
+		)
+		{
+			return sqrt(dot4(x, x));
+		}
+
+		inline detail::fvec4SIMD fastLength4
+		(
+			detail::fvec4SIMD const & x
+		)
+		{
+			return fastSqrt(dot4(x, x));
+		}
+
+		inline detail::fvec4SIMD niceLength4
+		(
+			detail::fvec4SIMD const & x
+		)
+		{
+			return niceSqrt(dot4(x, x));
+		}
+
+		inline float distance
 		(
 			detail::fvec4SIMD const & p0,
 			detail::fvec4SIMD const & p1
@@ -559,7 +601,7 @@ namespace glm
 			return Result;
 		}
 
-		inline detail::fvec4SIMD simdDistance4
+		inline detail::fvec4SIMD distance4
 		(
 			detail::fvec4SIMD const & p0,
 			detail::fvec4SIMD const & p1
@@ -568,7 +610,7 @@ namespace glm
 			return detail::sse_dst_ps(p0.Data, p1.Data);
 		}
 
-		inline float simdDot
+		inline float dot
 		(
 			detail::fvec4SIMD const & x,
 			detail::fvec4SIMD const & y
@@ -579,16 +621,16 @@ namespace glm
 			return Result;
 		}
 
-		inline detail::fvec4SIMD simdDot4
+		inline detail::fvec4SIMD dot4
 		(
 			detail::fvec4SIMD const & x,
 			detail::fvec4SIMD const & y
 		)
 		{
-			return detail::sse_dot_ss(x.Data, y.Data);
+			return detail::sse_dot_ps(x.Data, y.Data);
 		}
 
-		inline detail::fvec4SIMD simdCross
+		inline detail::fvec4SIMD cross
 		(
 			detail::fvec4SIMD const & x,
 			detail::fvec4SIMD const & y
@@ -597,15 +639,29 @@ namespace glm
 			return detail::sse_xpd_ps(x.Data, y.Data);
 		}
 
-		inline detail::fvec4SIMD simdNormalize
+		inline detail::fvec4SIMD normalize
 		(
 			detail::fvec4SIMD const & x
 		)
 		{
-			return detail::sse_nrm_ps(x.Data);
+			__m128 dot0 = detail::sse_dot_ps(x.Data, x.Data);
+			__m128 isr0 = inversesqrt(dot0).Data;
+			__m128 mul0 = _mm_mul_ps(x.Data, isr0);
+			return mul0;
 		}
 
-		inline detail::fvec4SIMD simdFaceforward
+		inline detail::fvec4SIMD fastNormalize
+		(
+			detail::fvec4SIMD const & x
+		)
+		{
+			__m128 dot0 = detail::sse_dot_ps(x.Data, x.Data);
+			__m128 isr0 = fastInversesqrt(dot0).Data;
+			__m128 mul0 = _mm_mul_ps(x.Data, isr0);
+			return mul0;
+		}
+
+		inline detail::fvec4SIMD faceforward
 		(
 			detail::fvec4SIMD const & N,
 			detail::fvec4SIMD const & I,
@@ -615,7 +671,7 @@ namespace glm
 			return detail::sse_ffd_ps(N.Data, I.Data, Nref.Data);
 		}
 
-		inline detail::fvec4SIMD simdReflect
+		inline detail::fvec4SIMD reflect
 		(
 			detail::fvec4SIMD const & I,
 			detail::fvec4SIMD const & N
@@ -624,7 +680,7 @@ namespace glm
 			return detail::sse_rfe_ps(I.Data, N.Data);
 		}
 
-		inline detail::fvec4SIMD simdRefract
+		inline detail::fvec4SIMD refract
 		(
 			detail::fvec4SIMD const & I,
 			detail::fvec4SIMD const & N,
@@ -634,6 +690,39 @@ namespace glm
 			return detail::sse_rfa_ps(I.Data, N.Data, _mm_set1_ps(eta));
 		}
 
+		inline detail::fvec4SIMD sqrt(detail::fvec4SIMD const & x)
+		{
+			return _mm_mul_ps(inversesqrt(x.Data).Data, x.Data);
+		}
+
+		inline detail::fvec4SIMD niceSqrt(detail::fvec4SIMD const & x)
+		{
+			return _mm_sqrt_ps(x.Data);
+		}
+
+		inline detail::fvec4SIMD fastSqrt(detail::fvec4SIMD const & x)
+		{
+			return _mm_mul_ps(fastInversesqrt(x.Data).Data, x.Data);
+		}
+
+		// SSE scalar reciprocal sqrt using rsqrt op, plus one Newton-Rhaphson iteration
+		// By Elan Ruskin, http://assemblyrequired.crashworks.org/
+		inline detail::fvec4SIMD inversesqrt(detail::fvec4SIMD const & x)
+		{
+			GLM_ALIGN(4) static const __m128 three = {3, 3, 3, 3}; // aligned consts for fast load
+			GLM_ALIGN(4) static const __m128 half = {0.5,0.5,0.5,0.5};
+
+			__m128 recip = _mm_rsqrt_ps(x.Data);  // "estimate" opcode
+			__m128 halfrecip = _mm_mul_ps(half, recip);
+			__m128 threeminus_xrr = _mm_sub_ps(three, _mm_mul_ps(x.Data, _mm_mul_ps(recip, recip)));
+			return _mm_mul_ps(halfrecip, threeminus_xrr);
+		}
+
+		inline detail::fvec4SIMD fastInversesqrt(detail::fvec4SIMD const & x)
+		{
+			return _mm_rsqrt_ps(x.Data);
+		}
+
 	}//namespace simd_vec4
 	}//namespace gtx
 }//namespace glm
diff --git a/readme.txt b/readme.txt
index cca9974b..f5819bc4 100644
--- a/readme.txt
+++ b/readme.txt
@@ -1,12 +1,21 @@
-=============================
+================================================================================
 G-Truc Creation
------------------------------
+--------------------------------------------------------------------------------
 www.g-truc.net
 glm@g-truc.net
 
-=============================
+================================================================================
+GLM Usage
+--------------------------------------------------------------------------------
+GLM is a header only library, there is nothing to build, just include it.
+#include <glm/glm.hpp>
+
+More informations in GLM manual:
+http://glm.g-truc.net/glm-manual.pdf
+
+================================================================================
 GLM 0.9.1.A: 2010-01-31
------------------------------
+--------------------------------------------------------------------------------
 - Added SIMD support
 - Added new swizzle functions
 - Improved static assert error message with C++0x static_assert
@@ -14,314 +23,315 @@ GLM 0.9.1.A: 2010-01-31
 - Reduced branching
 - Fixed trunc implementation
 
-=============================
-GLM 0.9.0.7: 2010-01-30
------------------------------
-- Added == and != operator for *mat* and *vec*
+================================================================================
+GLM 0.9.0.7: 2011-01-30
+--------------------------------------------------------------------------------
 - Added GLSL 4.10 packing functions
+- Added == and != operators for every types.
 
-=============================
+================================================================================
 GLM 0.9.0.6: 2010-12-21
------------------------------
+--------------------------------------------------------------------------------
 - Many matrices bugs fixed
 
-=============================
+================================================================================
 GLM 0.9.0.5: 2010-11-01
------------------------------
+--------------------------------------------------------------------------------
 - Improved Clang support
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.9.0.4: 2010-10-04
------------------------------
+--------------------------------------------------------------------------------
 - Added autoexp for GLM
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.9.0.3: 2010-08-26
------------------------------
+--------------------------------------------------------------------------------
 - Fixed non-squared matrix operators
 
-=============================
+================================================================================
 GLM 0.9.0.2: 2010-07-08
------------------------------
+--------------------------------------------------------------------------------
 - Added GLM_GTX_int_10_10_10_2
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.9.0.1: 2010-06-21
------------------------------
+--------------------------------------------------------------------------------
 - Fixed extensions errors
 
-=============================
+================================================================================
 GLM 0.9.0.0: 2010-05-25
------------------------------
+--------------------------------------------------------------------------------
 - Objective-C support
 - Fixed warnings
 - Updated documentation
 
-=============================
+================================================================================
 GLM 0.9.B.2: 2010-04-30
------------------------------
+--------------------------------------------------------------------------------
 - Git transition
 - Removed experimental code from releases
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.9.B.1: 2010-04-03
------------------------------
+--------------------------------------------------------------------------------
 - Based on GLSL 4.00 specification
 - Added the new core functions
 - Added some implicit conversion support
 
-=============================
+================================================================================
 GLM 0.9.A.2: 2010-02-20
------------------------------
+--------------------------------------------------------------------------------
 - Improved some possible errors messages
 - Improved declarations and definitions match
 
-=============================
+================================================================================
 GLM 0.9.A.1: 2010-02-09
------------------------------
+--------------------------------------------------------------------------------
 - Removed deprecated features
 - Internal redesign
 
-=============================
+================================================================================
 GLM 0.8.4.4 final: 2010-01-25
------------------------------
+--------------------------------------------------------------------------------
 - Fixed warnings
 
-=============================
+================================================================================
 GLM 0.8.4.3 final: 2009-11-16
------------------------------
+--------------------------------------------------------------------------------
 - Fixed Half float arithmetic
 - Fixed setup defines
 
-=============================
+================================================================================
 GLM 0.8.4.2 final: 2009-10-19
------------------------------
+--------------------------------------------------------------------------------
 - Fixed Half float adds
 
-=============================
+================================================================================
 GLM 0.8.4.1 final: 2009-10-05
------------------------------
+--------------------------------------------------------------------------------
 - Updated documentation
 - Fixed MacOS X build
 
-=============================
+================================================================================
 GLM 0.8.4.0 final: 2009-09-16
------------------------------
+--------------------------------------------------------------------------------
 - Added GCC 4.4 and VC2010 support
 - Added matrix optimizations
 
-=============================
+================================================================================
 GLM 0.8.3.5 final: 2009-08-11
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.8.3.4 final: 2009-08-10
------------------------------
+--------------------------------------------------------------------------------
 - Updated GLM according GLSL 1.5 spec
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.8.3.3 final: 2009-06-25
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs
 
-=============================
+================================================================================
 GLM 0.8.3.2 final: 2009-06-04
------------------------------
+--------------------------------------------------------------------------------
 - Added GLM_GTC_quaternion
 - Added GLM_GTC_type_precision
 
-=============================
+================================================================================
 GLM 0.8.3.1 final: 2009-05-21
------------------------------
+--------------------------------------------------------------------------------
 - Fixed old extension system.
 
-=============================
+================================================================================
 GLM 0.8.3.0 final: 2009-05-06
------------------------------
+--------------------------------------------------------------------------------
 - Added stable extensions.
 - Added new extension system.
 
-=============================
+================================================================================
 GLM 0.8.2.3 final: 2009-04-01
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs.
 
-=============================
+================================================================================
 GLM 0.8.2.2 final: 2009-02-24
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs.
 
-=============================
+================================================================================
 GLM 0.8.2.1 final: 2009-02-13
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs.
 
-=============================
+================================================================================
 GLM 0.8.2 final: 2009-01-21
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs.
 
-=============================
+================================================================================
 GLM 0.8.1 final: 2008-10-30
------------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs.
 
-=============================
+================================================================================
 GLM 0.8.0 final: 2008-10-23
------------------------------
+--------------------------------------------------------------------------------
 - New method to use extension.
 
-=============================
+================================================================================
 GLM 0.8.0 beta3: 2008-10-10
------------------------------
+--------------------------------------------------------------------------------
 - Added CMake support for GLM tests.
 
-=============================
+================================================================================
 GLM 0.8.0 beta2: 2008-10-04
------------------------------
+--------------------------------------------------------------------------------
 - Improved half scalars and vectors support.
 
-=============================
+================================================================================
 GLM 0.8.0 beta1: 2008-09-26
------------------------------
+--------------------------------------------------------------------------------
 - Improved GLSL conformance
 - Added GLSL 1.30 support
 - Improved API documentation
 
-=============================
+================================================================================
 GLM 0.7.6 final: 2008-08-08
----------------------------
+--------------------------------------------------------------------------------
 - Improved C++ standard comformance
 - Added Static assert for types checking
 
-===========================
+================================================================================
 GLM 0.7.5 final: 2008-07-05
----------------------------
+--------------------------------------------------------------------------------
 - Added build message system with Visual Studio
 - Pedantic build with GCC
 
-===========================
+================================================================================
 GLM 0.7.4 final: 2008-06-01
----------------------------
+--------------------------------------------------------------------------------
 - Added external dependencies system.
 
-===========================
+================================================================================
 GLM 0.7.3 final: 2008-05-24
----------------------------
+--------------------------------------------------------------------------------
 - Fixed bugs
 - Added new extension group
 
-===========================
+================================================================================
 GLM 0.7.2 final: 2008-04-27
----------------------------
+--------------------------------------------------------------------------------
 - Updated documentation
 - Added preprocessor options
 
-===========================
+================================================================================
 GLM 0.7.1 final: 2008-03-24
----------------------------
+--------------------------------------------------------------------------------
 - Disabled half on GCC
 - Fixed extensions
 
-===========================
+================================================================================
 GLM 0.7.0 final: 2008-03-22
----------------------------
+--------------------------------------------------------------------------------
 - Changed to MIT license
 - Added new documentation
 
-===========================
+================================================================================
 GLM 0.6.4 : 2007-12-10
----------------------------
+--------------------------------------------------------------------------------
 - Fixed swizzle operators
 
-===========================
+================================================================================
 GLM 0.6.3 : 2007-11-05
----------------------------
+--------------------------------------------------------------------------------
 - Fixed type data accesses
 - Fixed 3DSMax sdk conflict
 
-===========================
+================================================================================
 GLM 0.6.2 : 2007-10-08
----------------------------
+--------------------------------------------------------------------------------
 - Fixed extension
 
-===========================
+================================================================================
 GLM 0.6.1 : 2007-10-07
----------------------------
+--------------------------------------------------------------------------------
 - Fixed a namespace error
 - Added extensions
 
-===========================
+================================================================================
 GLM 0.6.0 : 2007-09-16
----------------------------
+--------------------------------------------------------------------------------
 - Added new extension namespace mecanium
 - Added Automatic compiler detection
 
-===========================
+================================================================================
 GLM 0.5.1 : 2007-02-19
----------------------------
+--------------------------------------------------------------------------------
 - Fixed swizzle operators
 
-===========================
+================================================================================
 GLM 0.5.0 : 2007-01-06
----------------------------
+--------------------------------------------------------------------------------
 - Upgrated to GLSL 1.2
 - Added swizzle operators
 - Added setup settings
 
-===========================
+================================================================================
 GLM 0.4.1 : 2006-05-22
----------------------------
+--------------------------------------------------------------------------------
 - Added OpenGL examples
 
-===========================
+================================================================================
 GLM 0.4.0 : 2006-05-17
----------------------------
+--------------------------------------------------------------------------------
 - Added missing operators to vec* and mat*
 - Added first GLSL 1.2 features
 - Fixed windows.h before glm.h when windows.h required
 
-===========================
+================================================================================
 GLM 0.3.2 : 2006-04-21
----------------------------
+--------------------------------------------------------------------------------
 - Fixed texcoord components access.
 - Fixed mat4 and imat4 division operators.
 
-===========================
+================================================================================
 GLM 0.3.1 : 2006-03-28
----------------------------
+--------------------------------------------------------------------------------
 - Added GCC 4.0 support under MacOS X.
 - Added GCC 4.0 and 4.1 support under Linux.
 - Added code optimisations.
 
-===========================
+================================================================================
 GLM 0.3 : 2006-02-19
----------------------------
+--------------------------------------------------------------------------------
 - Improved GLSL type conversion and construction compliance.
 - Added experimental extensions.
 - Added Doxygen Documentation.
 - Added code optimisations.
 - Fixed bugs.
 
-===========================
+================================================================================
 GLM 0.2: 2005-05-05
----------------------------
+--------------------------------------------------------------------------------
 - Improve adaptative from GLSL.
 - Add experimental extensions based on OpenGL extension process.
 - Fixe bugs.
 
-===========================
+================================================================================
 GLM 0.1: 2005-02-21
----------------------------
+--------------------------------------------------------------------------------
 - Add vec2, vec3, vec4 GLSL types
 - Add ivec2, ivec3, ivec4 GLSL types
 - Add bvec2, bvec3, bvec4 GLSL types
 - Add mat2, mat3, mat4 GLSL types
 - Add almost all functions
 
+================================================================================
diff --git a/test/gtx/gtx-simd-mat4.cpp b/test/gtx/gtx-simd-mat4.cpp
index e9a56aae..ae976be5 100644
--- a/test/gtx/gtx-simd-mat4.cpp
+++ b/test/gtx/gtx-simd-mat4.cpp
@@ -28,7 +28,7 @@ std::vector<float> test_detA(std::vector<glm::mat4> const & Data)
 		Test[i] = glm::determinant(Data[i]);
 
 	std::clock_t TimeEnd = clock();
-	printf("Det A: %d\n", TimeEnd - TimeStart);
+	printf("Det A: %ld\n", TimeEnd - TimeStart);
 
 	return Test;
 }
@@ -49,7 +49,7 @@ std::vector<float> test_detB(std::vector<glm::mat4> const & Data)
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Det B: %d\n", TimeEnd - TimeStart);
+	printf("Det B: %ld\n", TimeEnd - TimeStart);
 
 	return Test;
 }
@@ -70,7 +70,7 @@ std::vector<float> test_detC(std::vector<glm::mat4> const & Data)
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Det C: %d\n", TimeEnd - TimeStart);
+	printf("Det C: %ld\n", TimeEnd - TimeStart);
 
 	return Test;
 }
@@ -91,7 +91,7 @@ std::vector<float> test_detD(std::vector<glm::mat4> const & Data)
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Det D: %d\n", TimeEnd - TimeStart);
+	printf("Det D: %ld\n", TimeEnd - TimeStart);
 
 	return Test;
 }
@@ -109,7 +109,7 @@ void test_invA(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Inv A: %d\n", TimeEnd - TimeStart);
+	printf("Inv A: %ld\n", TimeEnd - TimeStart);
 }
 
 void test_invC(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out)
@@ -129,7 +129,7 @@ void test_invC(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Inv C: %d\n", TimeEnd - TimeStart);
+	printf("Inv C: %ld\n", TimeEnd - TimeStart);
 }
 
 void test_invD(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out)
@@ -149,7 +149,7 @@ void test_invD(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Inv D: %d\n", TimeEnd - TimeStart);
+	printf("Inv D: %ld\n", TimeEnd - TimeStart);
 }
 
 void test_mulA(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out)
@@ -165,7 +165,7 @@ void test_mulA(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Mul A: %d\n", TimeEnd - TimeStart);
+	printf("Mul A: %ld\n", TimeEnd - TimeStart);
 }
 
 void test_mulD(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out)
@@ -183,7 +183,7 @@ void test_mulD(std::vector<glm::mat4> const & Data, std::vector<glm::mat4> & Out
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("Mul D: %d\n", TimeEnd - TimeStart);
+	printf("Mul D: %ld\n", TimeEnd - TimeStart);
 }
 
 int test_compute_glm()
@@ -222,7 +222,7 @@ int test_compute_gtx()
 	}
 
 	std::clock_t TimeEnd = clock();
-	printf("test_compute_gtx: %d\n", TimeEnd - TimeStart);
+	printf("test_compute_gtx: %ld\n", TimeEnd - TimeStart);
 
 	return Output.size() != 0;
 }
@@ -280,8 +280,8 @@ int main()
 	Failed += test_compute_glm();
 	Failed += test_compute_gtx();
 	
-	float Det = glm::simdDeterminant(glm::simdMat4(1.0));
-	glm::simdMat4 D = glm::simdMatrixCompMult(glm::simdMat4(1.0), glm::simdMat4(1.0));
+	float Det = glm::determinant(glm::simdMat4(1.0));
+	glm::simdMat4 D = glm::matrixCompMult(glm::simdMat4(1.0), glm::simdMat4(1.0));
 
 	system("pause");