Updated version info

HandmadeMath.h

@@ -1,5 +1,5 @@
 /*
-  HandmadeMath.h v1.9.0
+  HandmadeMath.h v1.7.1
   
   This is a single header file with a bunch of useful functions for game and
   graphics math operations.
@@ -65,6 +65,121 @@
   versions of these functions that are provided by the CRT.
   
   =============================================================================
+  
+  Version History:
+      0.2 (*) Updated documentation
+          (*) Better C compliance
+          (*) Prefix all handmade math functions 
+          (*) Better operator overloading
+      0.2a
+          (*) Prefixed Macros
+      0.2b
+          (*) Disabled warning 4201 on MSVC as it is legal is C11
+          (*) Removed the f at the end of HMM_PI to get 64bit precision
+      0.3
+          (*) Added +=, -=, *=, /= for hmm_vec2, hmm_vec3, hmm_vec4
+      0.4
+          (*) SSE Optimized HMM_SqrtF
+          (*) SSE Optimized HMM_RSqrtF
+          (*) Removed CRT
+      0.5
+          (*) Added scalar multiplication and division for vectors
+              and matrices
+          (*) Added matrix subtraction and += for hmm_mat4
+          (*) Reconciled all headers and implementations
+          (*) Tidied up, and filled in a few missing operators
+      0.5.1
+          (*) Ensured column-major order for matrices throughout
+          (*) Fixed HMM_Translate producing row-major matrices
+      0.5.2
+          (*) Fixed SSE code in HMM_SqrtF
+          (*) Fixed SSE code in HMM_RSqrtF
+      0.6
+          (*) Added Unit testing
+          (*) Made HMM_Power faster
+          (*) Fixed possible efficiency problem with HMM_Normalize 
+          (*) RENAMED HMM_LengthSquareRoot to HMM_LengthSquared
+          (*) RENAMED HMM_RSqrtF to HMM_RSquareRootF
+          (*) RENAMED HMM_SqrtF to HMM_SquareRootF
+          (*) REMOVED Inner function (user should use Dot now)
+          (*) REMOVED HMM_FastInverseSquareRoot function declaration
+      0.7 
+          (*) REMOVED HMM_LengthSquared in HANDMADE_MATH_IMPLEMENTATION (should
+              use HMM_LengthSquaredVec3, or HANDMADE_MATH_CPP_MODE for function
+              overloaded version)
+          (*) REMOVED HMM_Length in HANDMADE_MATH_IMPLEMENTATION (should use
+              HMM_LengthVec3, HANDMADE_MATH_CPP_MODE for function
+              overloaded version)
+          (*) REMOVED HMM_Normalize in HANDMADE_MATH_IMPLEMENTATION (should use
+              HMM_NormalizeVec3, or HANDMADE_MATH_CPP_MODE for function
+              overloaded version)
+          (*) Added HMM_LengthSquaredVec2
+          (*) Added HMM_LengthSquaredVec4
+          (*) Addd HMM_LengthVec2
+          (*) Added HMM_LengthVec4
+          (*) Added HMM_NormalizeVec2
+          (*) Added HMM_NormalizeVec4
+     1.0
+          (*) Lots of testing!
+     1.1
+          (*) Quaternion support
+          (*) Added type hmm_quaternion
+          (*) Added HMM_Quaternion
+          (*) Added HMM_QuaternionV4
+          (*) Added HMM_AddQuaternion
+          (*) Added HMM_SubtractQuaternion
+          (*) Added HMM_MultiplyQuaternion
+          (*) Added HMM_MultiplyQuaternionF
+          (*) Added HMM_DivideQuaternionF
+          (*) Added HMM_InverseQuaternion
+          (*) Added HMM_DotQuaternion
+          (*) Added HMM_NormalizeQuaternion
+          (*) Added HMM_Slerp
+          (*) Added HMM_QuaternionToMat4
+          (*) Added HMM_QuaternionFromAxisAngle
+     1.1.1
+          (*) Resolved compiler warnings on gcc and g++
+     1.1.2
+          (*) Fixed invalid HMMDEF's in the function definitions
+     1.1.3
+          (*) Fixed compile error in C mode
+     1.1.4
+          (*) Fixed SSE being included on platforms that don't support it
+          (*) Fixed divide-by-zero errors when normalizing zero vectors.
+     1.1.5
+          (*) Add Width and Height to HMM_Vec2
+          (*) Made it so you can supply your own SqrtF 
+     1.2.0
+          (*) Added equality functions for HMM_Vec2, HMM_Vec3, and HMM_Vec4.
+              (*) Added HMM_EqualsVec2, HMM_EqualsVec3, and HMM_EqualsVec4
+              (*) Added C++ overloaded HMM_Equals for all three
+              (*) Added C++ == and != operators for all three
+          (*) SSE'd HMM_MultiplyMat4 (this is _WAY_ faster)
+          (*) SSE'd HMM_Transpose
+     1.3.0
+          (*) Remove need to #define HANDMADE_MATH_CPP_MODE
+     1.4.0
+          (*) Fixed bug when using HandmadeMath in C mode
+          (*) SSEd all vec4 operations          
+          (*) Removed all zero-ing
+     1.5.0
+          (*) Changed internal structure for better performance and inlining.
+          (*) As a result, HANDMADE_MATH_NO_INLINE has been removed and no
+              longer has any effect.
+     1.5.1
+          (*) Fixed a bug with uninitialized elements in HMM_LookAt.
+     1.6.0
+          (*) Added array subscript operators for vector and matrix types in
+              C++. This is provided as a convenience, but be aware that it may
+              incur an extra function call in unoptimized builds.
+     1.7.0
+          (*) Renamed the 'Rows' member of hmm_mat4 to 'Columns'. Since our
+              matrices are column-major, this should have been named 'Columns'
+              from the start. 'Rows' is still present, but has been deprecated.
+     1.7.1
+          (*) Changed operator[] to take in a const ref int instead of a int. 
+              Simple dumb mistake. NOTE: The compiler still wont inline operator[]
+              for some reason 
 
   LICENSE
   
@@ -83,7 +198,6 @@
    Gingerbill (@TheGingerBill)
    Ben Visness (@bvisness) 
    Trinton Bullard (@Peliex_Dev)
-   @AntonDan
    
   Fixes:
    Jeroen van Rijn (@J_vanRijn)
@@ -380,10 +494,6 @@ typedef union hmm_quaternion
     };
     
     float Elements[4];
-
-#ifdef HANDMADE_MATH__USE_SSE    
-    __m128 InternalElementsSSE;
-#endif
 } hmm_quaternion;
 
 typedef int32_t hmm_bool;
@@ -1021,21 +1131,6 @@ HMM_INLINE hmm_vec4 HMM_NormalizeVec4(hmm_vec4 A)
     return (Result);
 }
 
-HMM_INLINE hmm_vec2 HMM_FastNormalizeVec2(hmm_vec2 A)
-{
-    return HMM_MultiplyVec2f(A, HMM_RSquareRootF(HMM_DotVec2(A, A)));
-}
-
-HMM_INLINE hmm_vec3 HMM_FastNormalizeVec3(hmm_vec3 A)
-{
-    return HMM_MultiplyVec3f(A, HMM_RSquareRootF(HMM_DotVec3(A, A)));
-}
-
-HMM_INLINE hmm_vec4 HMM_FastNormalizeVec4(hmm_vec4 A)
-{
-    return HMM_MultiplyVec4f(A, HMM_RSquareRootF(HMM_DotVec4(A, A)));
-}
-
 
 /*
  * SSE stuff
@@ -1233,14 +1328,10 @@ HMM_INLINE hmm_quaternion HMM_Quaternion(float X, float Y, float Z, float W)
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    Result.InternalElementsSSE = _mm_setr_ps(X, Y, Z, W);
-#else
     Result.X = X;
     Result.Y = Y;
     Result.Z = Z;
     Result.W = W;
-#endif
 
     return (Result);
 }
@@ -1249,14 +1340,10 @@ HMM_INLINE hmm_quaternion HMM_QuaternionV4(hmm_vec4 Vector)
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    Result.InternalElementsSSE = Vector.InternalElementsSSE;
-#else
     Result.X = Vector.X;
     Result.Y = Vector.Y;
     Result.Z = Vector.Z;
     Result.W = Vector.W;
-#endif
 
     return (Result);
 }
@@ -1265,15 +1352,10 @@ HMM_INLINE hmm_quaternion HMM_AddQuaternion(hmm_quaternion Left, hmm_quaternion
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    Result.InternalElementsSSE = _mm_add_ps(Left.InternalElementsSSE, Right.InternalElementsSSE);
-#else
-
     Result.X = Left.X + Right.X;
     Result.Y = Left.Y + Right.Y;
     Result.Z = Left.Z + Right.Z;
     Result.W = Left.W + Right.W;
-#endif
 
     return (Result);
 }
@@ -1282,15 +1364,10 @@ HMM_INLINE hmm_quaternion HMM_SubtractQuaternion(hmm_quaternion Left, hmm_quater
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    Result.InternalElementsSSE = _mm_sub_ps(Left.InternalElementsSSE, Right.InternalElementsSSE);
-#else
-
     Result.X = Left.X - Right.X;
     Result.Y = Left.Y - Right.Y;
     Result.Z = Left.Z - Right.Z;
     Result.W = Left.W - Right.W;
-#endif
 
     return (Result);
 }
@@ -1299,28 +1376,10 @@ HMM_INLINE hmm_quaternion HMM_MultiplyQuaternion(hmm_quaternion Left, hmm_quater
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-        __m128 SSEResultOne = _mm_xor_ps(_mm_shuffle_ps(Left.InternalElementsSSE, Left.InternalElementsSSE, _MM_SHUFFLE(0, 0, 0, 0)), _mm_setr_ps(0.f, -0.f, 0.f, -0.f));
-        __m128 SSEResultTwo = _mm_shuffle_ps(Right.InternalElementsSSE, Right.InternalElementsSSE, _MM_SHUFFLE(0, 1, 2, 3));
-        __m128 SSEResultThree = _mm_mul_ps(SSEResultTwo, SSEResultOne);
-
-        SSEResultOne = _mm_xor_ps(_mm_shuffle_ps(Left.InternalElementsSSE, Left.InternalElementsSSE, _MM_SHUFFLE(1, 1, 1, 1)) , _mm_setr_ps(0.f, 0.f, -0.f, -0.f));
-        SSEResultTwo = _mm_shuffle_ps(Right.InternalElementsSSE, Right.InternalElementsSSE, _MM_SHUFFLE(1, 0, 3, 2));
-        SSEResultThree = _mm_add_ps(SSEResultThree, _mm_mul_ps(SSEResultTwo, SSEResultOne));
-
-        SSEResultOne = _mm_xor_ps(_mm_shuffle_ps(Left.InternalElementsSSE, Left.InternalElementsSSE, _MM_SHUFFLE(2, 2, 2, 2)), _mm_setr_ps(-0.f, 0.f, 0.f, -0.f));
-        SSEResultTwo = _mm_shuffle_ps(Right.InternalElementsSSE, Right.InternalElementsSSE, _MM_SHUFFLE(2, 3, 0, 1));
-        SSEResultThree = _mm_add_ps(SSEResultThree, _mm_mul_ps(SSEResultTwo, SSEResultOne));
-
-        SSEResultOne = _mm_shuffle_ps(Left.InternalElementsSSE, Left.InternalElementsSSE, _MM_SHUFFLE(3, 3, 3, 3));
-        SSEResultTwo = _mm_shuffle_ps(Right.InternalElementsSSE, Right.InternalElementsSSE, _MM_SHUFFLE(3, 2, 1, 0));
-        Result.InternalElementsSSE = _mm_add_ps(SSEResultThree, _mm_mul_ps(SSEResultTwo, SSEResultOne));
-#else
     Result.X = (Left.X * Right.W) + (Left.Y * Right.Z) - (Left.Z * Right.Y) + (Left.W * Right.X);
     Result.Y = (-Left.X * Right.Z) + (Left.Y * Right.W) + (Left.Z * Right.X) + (Left.W * Right.Y);
     Result.Z = (Left.X * Right.Y) - (Left.Y * Right.X) + (Left.Z * Right.W) + (Left.W * Right.Z);
     Result.W = (-Left.X * Right.X) - (Left.Y * Right.Y) - (Left.Z * Right.Z) + (Left.W * Right.W);
-#endif
 
     return (Result);
 }
@@ -1329,15 +1388,10 @@ HMM_INLINE hmm_quaternion HMM_MultiplyQuaternionF(hmm_quaternion Left, float Mul
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    __m128 Scalar = _mm_set1_ps(Multiplicative);
-    Result.InternalElementsSSE = _mm_mul_ps(Left.InternalElementsSSE, Scalar);
-#else
     Result.X = Left.X * Multiplicative;
     Result.Y = Left.Y * Multiplicative;
     Result.Z = Left.Z * Multiplicative;
     Result.W = Left.W * Multiplicative;
-#endif
 
     return (Result);
 }
@@ -1346,15 +1400,10 @@ HMM_INLINE hmm_quaternion HMM_DivideQuaternionF(hmm_quaternion Left, float Divid
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    __m128 Scalar = _mm_set1_ps(Dividend);
-    Result.InternalElementsSSE = _mm_div_ps(Left.InternalElementsSSE, Scalar);
-#else
     Result.X = Left.X / Dividend;
     Result.Y = Left.Y / Dividend;
     Result.Z = Left.Z / Dividend;
     Result.W = Left.W / Dividend;
-#endif
 
     return (Result);
 }
@@ -1363,18 +1412,7 @@ HMM_EXTERN hmm_quaternion HMM_InverseQuaternion(hmm_quaternion Left);
 
 HMM_INLINE float HMM_DotQuaternion(hmm_quaternion Left, hmm_quaternion Right)
 {
-    float Result;
-
-#ifdef HANDMADE_MATH__USE_SSE
-    __m128 SSEResultOne = _mm_mul_ps(Left.InternalElementsSSE, Right.InternalElementsSSE);
-    __m128 SSEResultTwo = _mm_shuffle_ps(SSEResultOne, SSEResultOne, _MM_SHUFFLE(2, 3, 0, 1));
-    SSEResultOne = _mm_add_ps(SSEResultOne, SSEResultTwo);
-    SSEResultTwo = _mm_shuffle_ps(SSEResultOne, SSEResultOne, _MM_SHUFFLE(0, 1, 2, 3));
-    SSEResultOne = _mm_add_ps(SSEResultOne, SSEResultTwo);
-    _mm_store_ss(&Result, SSEResultOne);
-#else
-    Result = (Left.X * Right.X) + (Left.Y * Right.Y) + (Left.Z * Right.Z) + (Left.W * Right.W);
-#endif
+    float Result = (Left.X * Right.X) + (Left.Y * Right.Y) + (Left.Z * Right.Z) + (Left.W * Right.W);
 
     return (Result);
 }
@@ -1393,18 +1431,11 @@ HMM_INLINE hmm_quaternion HMM_NLerp(hmm_quaternion Left, float Time, hmm_quatern
 {
     hmm_quaternion Result;
 
-#ifdef HANDMADE_MATH__USE_SSE
-    __m128 ScalarLeft = _mm_set1_ps(1.0f - Time);
-    __m128 ScalarRight = _mm_set1_ps(Time);
-    __m128 SSEResultOne = _mm_mul_ps(Left.InternalElementsSSE, ScalarLeft);
-    __m128 SSEResultTwo = _mm_mul_ps(Right.InternalElementsSSE, ScalarRight);
-    Result.InternalElementsSSE = _mm_add_ps(SSEResultOne, SSEResultTwo);
-#else
     Result.X = HMM_Lerp(Left.X, Time, Right.X);
     Result.Y = HMM_Lerp(Left.Y, Time, Right.Y);
     Result.Z = HMM_Lerp(Left.Z, Time, Right.Z);
     Result.W = HMM_Lerp(Left.W, Time, Right.W);
-#endif
+
     Result = HMM_NormalizeQuaternion(Result);
 
     return (Result);
@@ -1483,27 +1514,6 @@ HMM_INLINE hmm_vec4 HMM_Normalize(hmm_vec4 A)
     return (Result);
 }
 
-HMM_INLINE hmm_vec2 HMM_FastNormalize(hmm_vec2 A)
-{
-    hmm_vec2 Result = HMM_FastNormalizeVec2(A);
-
-    return (Result);
-}
-
-HMM_INLINE hmm_vec3 HMM_FastNormalize(hmm_vec3 A)
-{
-    hmm_vec3 Result = HMM_FastNormalizeVec3(A);
-
-    return (Result);
-}
-
-HMM_INLINE hmm_vec4 HMM_FastNormalize(hmm_vec4 A)
-{
-    hmm_vec4 Result = HMM_FastNormalizeVec4(A);
-
-    return (Result);
-}
-
 HMM_INLINE hmm_quaternion HMM_Normalize(hmm_quaternion A)
 {
     hmm_quaternion Result = HMM_NormalizeQuaternion(A);
@@ -2412,7 +2422,10 @@ hmm_quaternion HMM_InverseQuaternion(hmm_quaternion Left)
     Norm = HMM_SquareRootF(HMM_DotQuaternion(Left, Left));
     NormSquared = Norm * Norm;
 
-    Result = HMM_DivideQuaternionF(Conjugate, NormSquared);
+    Result.X = Conjugate.X / NormSquared;
+    Result.Y = Conjugate.Y / NormSquared;
+    Result.Z = Conjugate.Z / NormSquared;
+    Result.W = Conjugate.W / NormSquared;
 
     return (Result);
 }

README.md

@@ -10,9 +10,7 @@ To get started, go download [the latest release](https://github.com/HandmadeMath
 
 Version         | Changes        |
 ----------------|----------------|
-**1.9.0** | Added SSE versions of quaternion operations. |
-**1.8.0** | Added fast vector normalization routines that use fast inverse square roots.
-**1.7.1** | Changed operator[] to take a const ref int instead of an int.
+**1.7.1** | Changed operator[] to take in a const ref int instead of a int. Simple mistake
 **1.7.0** | Renamed the 'Rows' member of hmm_mat4 to 'Columns'. Since our matrices are column-major, this should have been named 'Columns' from the start. 'Rows' is still present, but has been deprecated.
 **1.6.0** | Added array subscript operators for vector and matrix types in C++. This is provided as a convenience, but be aware that it may incur an extra function call in unoptimized builds.
 **1.5.1** | Fixed a bug with uninitialized elements in HMM_LookAt.

test/categories/VectorOps.h

@@ -134,106 +134,6 @@ TEST(VectorOps, NormalizeZero)
 #endif
 }
 
-TEST(VectorOps, FastNormalize)
-{
-    hmm_vec2 v2 = HMM_Vec2(1.0f, -2.0f);
-    hmm_vec3 v3 = HMM_Vec3(1.0f, -2.0f, 3.0f);
-    hmm_vec4 v4 = HMM_Vec4(1.0f, -2.0f, 3.0f, -1.0f);
-
-    {
-        hmm_vec2 result = HMM_FastNormalizeVec2(v2);
-        EXPECT_NEAR(HMM_LengthVec2(result), 1.0f, 0.001f);
-        EXPECT_GT(result.X, 0.0f);
-        EXPECT_LT(result.Y, 0.0f);
-    }
-    {
-        hmm_vec3 result = HMM_FastNormalizeVec3(v3);
-        EXPECT_NEAR(HMM_LengthVec3(result), 1.0f, 0.001f);
-        EXPECT_GT(result.X, 0.0f);
-        EXPECT_LT(result.Y, 0.0f);
-        EXPECT_GT(result.Z, 0.0f);
-    }
-    {
-        hmm_vec4 result = HMM_FastNormalizeVec4(v4);
-        EXPECT_NEAR(HMM_LengthVec4(result), 1.0f, 0.001f);
-        EXPECT_GT(result.X, 0.0f);
-        EXPECT_LT(result.Y, 0.0f);
-        EXPECT_GT(result.Z, 0.0f);
-        EXPECT_LT(result.W, 0.0f);
-    }
-
-#ifdef __cplusplus
-    {
-        hmm_vec2 result = HMM_FastNormalize(v2);
-        EXPECT_NEAR(HMM_LengthVec2(result), 1.0f, 0.001f);
-        EXPECT_GT(result.X, 0.0f);
-        EXPECT_LT(result.Y, 0.0f);
-    }
-    {
-        hmm_vec3 result = HMM_FastNormalize(v3);
-        EXPECT_NEAR(HMM_LengthVec3(result), 1.0f, 0.001f);
-        EXPECT_GT(result.X, 0.0f);
-        EXPECT_LT(result.Y, 0.0f);
-        EXPECT_GT(result.Z, 0.0f);
-    }
-    {
-        hmm_vec4 result = HMM_FastNormalize(v4);
-        EXPECT_NEAR(HMM_LengthVec4(result), 1.0f, 0.001f);
-        EXPECT_GT(result.X, 0.0f);
-        EXPECT_LT(result.Y, 0.0f);
-        EXPECT_GT(result.Z, 0.0f);
-        EXPECT_LT(result.W, 0.0f);
-    }
-#endif
-}
-
-TEST(VectorOps, FastNormalizeZero)
-{
-    hmm_vec2 v2 = HMM_Vec2(0.0f, 0.0f);
-    hmm_vec3 v3 = HMM_Vec3(0.0f, 0.0f, 0.0f);
-    hmm_vec4 v4 = HMM_Vec4(0.0f, 0.0f, 0.0f, 0.0f);
-
-    {
-        hmm_vec2 result = HMM_FastNormalizeVec2(v2);
-        EXPECT_FLOAT_EQ(result.X, 0.0f);
-        EXPECT_FLOAT_EQ(result.Y, 0.0f);
-    }
-    {
-        hmm_vec3 result = HMM_FastNormalizeVec3(v3);
-        EXPECT_FLOAT_EQ(result.X, 0.0f);
-        EXPECT_FLOAT_EQ(result.Y, 0.0f);
-        EXPECT_FLOAT_EQ(result.Z, 0.0f);
-    }
-    {
-        hmm_vec4 result = HMM_FastNormalizeVec4(v4);
-        EXPECT_FLOAT_EQ(result.X, 0.0f);
-        EXPECT_FLOAT_EQ(result.Y, 0.0f);
-        EXPECT_FLOAT_EQ(result.Z, 0.0f);
-        EXPECT_FLOAT_EQ(result.W, 0.0f);
-    }
-
-#ifdef __cplusplus
-    {
-        hmm_vec2 result = HMM_FastNormalize(v2);
-        EXPECT_FLOAT_EQ(result.X, 0.0f);
-        EXPECT_FLOAT_EQ(result.Y, 0.0f);
-    }
-    {
-        hmm_vec3 result = HMM_FastNormalize(v3);
-        EXPECT_FLOAT_EQ(result.X, 0.0f);
-        EXPECT_FLOAT_EQ(result.Y, 0.0f);
-        EXPECT_FLOAT_EQ(result.Z, 0.0f);
-    }
-    {
-        hmm_vec4 result = HMM_FastNormalize(v4);
-        EXPECT_FLOAT_EQ(result.X, 0.0f);
-        EXPECT_FLOAT_EQ(result.Y, 0.0f);
-        EXPECT_FLOAT_EQ(result.Z, 0.0f);
-        EXPECT_FLOAT_EQ(result.W, 0.0f);
-    }
-#endif
-}
-
 TEST(VectorOps, Cross)
 {
     hmm_vec3 v1 = HMM_Vec3(1.0f, 2.0f, 3.0f);