Merge branch 'master' into const

Resolve vec4 : glm_vec4_distance() to satisfy compiling on armv7

.gitignore

@@ -61,3 +61,12 @@ docs/build/*
 win/cglm_test_*
 * copy.*
 *.o
+*.obj
+*codeanalysis.*.xml
+*codeanalysis.xml
+*.lib
+*.tlog
+win/x64
+win/x85
+win/Debug
+cglm-test-ios*

.travis.yml

@@ -49,7 +49,7 @@ script:
 
 after_success:
   - if [[ "$CC" == "gcc" && "$CODE_COVERAGE" == "ON" ]]; then
-      pip install --user cpp-coveralls
+      pip install --user cpp-coveralls && 
       coveralls
         --build-root .
         --exclude lib
@@ -57,3 +57,6 @@ after_success:
         --gcov-options '\-lp'
         --verbose;
     fi
+
+after_failure:
+  - cat ./test-suite.log

CREDITS

@@ -1,7 +1,7 @@
 This library [initially] used some [piece of] implementations
 (may include codes) from these open source projects/resources:
 
-1. Affine Transforms
+1. Initial Affine Transforms
 The original glm repo (g-truc), url: https://github.com/g-truc/glm
 
 LICENSE[S]:
@@ -11,7 +11,7 @@ LICENSE[S]:
 
 FULL LICENSE: https://github.com/g-truc/glm/blob/master/copying.txt
 
-2. Quaternions
+2. Initial Quaternions
 Anton's OpenGL 4 Tutorials book source code:
 
 LICENSE:
@@ -47,6 +47,17 @@ http://old.cescg.org/CESCG-2002/DSykoraJJelinek/
 7. Quaternions
 Initial mat4_quat is borrowed from Apple's simd library
 
-
 8. Vector Rotation using Quaternion
 https://gamedev.stackexchange.com/questions/28395/rotating-vector3-by-a-quaternion
+
+9. Sphere AABB intersect
+https://github.com/erich666/GraphicsGems/blob/master/gems/BoxSphere.c
+
+10. Horizontal add
+https://stackoverflow.com/questions/6996764/fastest-way-to-do-horizontal-float-vector-sum-on-x86
+
+11. de casteljau implementation and comments
+https://forums.khronos.org/showthread.php/10264-Animations-in-1-4-1-release-notes-revision-A/page2?highlight=bezier
+https://forums.khronos.org/showthread.php/10644-Animation-Bezier-interpolation
+https://forums.khronos.org/showthread.php/10387-2D-Tangents-in-Bezier-Splines?p=34164&viewfull=1#post34164
+https://forums.khronos.org/showthread.php/10651-Animation-TCB-Spline-Interpolation-in-COLLADA?highlight=bezier

README.md

@@ -16,10 +16,16 @@ Complete documentation: http://cglm.readthedocs.io
 
 #### Note for previous versions:
 
-- _dup (duplicate) is changed to _copy. For instance `glm_vec_dup -> glm_vec_copy`
+- _dup (duplicate) is changed to _copy. For instance `glm_vec_dup -> glm_vec3_copy`
 - OpenGL related functions are dropped to make this lib platform/third-party independent
 - make sure you have latest version and feel free to report bugs, troubles
-- **[bugfix]** euler angles was implemented in reverse order (extrinsic) it was fixed, now they are intrinsic. Make sure that you have the latest version
+- **[bugfix]** euler angles was implemented in reverse order (extrinsic) it was fixed, now they are intrinsic. Make sure that
+you have the latest version
+- **[major change]** by starting v0.4.0, quaternions are stored as [x, y, z, w], it was [w, x, y, z] in v0.3.5 and earlier versions
+- **[api rename]** by starting v0.4.5, **glm_simd** functions are renamed to **glmm_**  
+- **[new option]** by starting v0.4.5, you can disable alignment requirement, check options in docs.  
+- **[major change]** by starting v0.5.0, vec3 functions use **glm_vec3_** namespace, it was **glm_vec_** until v0.5.0
+- **[major change]** by starting v0.5.1, built-in alignment is removed from **vec3** and **mat3** types
 
 #### Note for C++ developers:
 If you don't aware about original GLM library yet, you may also want to look at:
@@ -76,7 +82,12 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi
 - inline or pre-compiled function call
 - frustum (extract view frustum planes, corners...)
 - bounding box  (AABB in Frustum (culling), crop, merge...)
+- bounding sphere
 - project, unproject
+- easing functions
+- curves
+- curve interpolation helpers (S*M*C, deCasteljau...)
+- and other...
 
 <hr />
 
@@ -118,39 +129,6 @@ glm_mul(T, R, modelMat);
 glm_inv_tr(modelMat);
 ```
 
-## Contributors
-
-This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
-<a href="graphs/contributors"><img src="https://opencollective.com/cglm/contributors.svg?width=890&button=false" /></a>
-
-
-## Backers
-
-Thank you to all our backers! 🙏 [[Become a backer](https://opencollective.com/cglm#backer)]
-
-<a href="https://opencollective.com/cglm#backers" target="_blank"><img src="https://opencollective.com/cglm/backers.svg?width=890"></a>
-
-
-## Sponsors
-
-Support this project by becoming a sponsor. Your logo will show up here with a link to your website. [[Become a sponsor](https://opencollective.com/cglm#sponsor)]
-
-<a href="https://opencollective.com/cglm/sponsor/0/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/0/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/1/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/1/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/2/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/2/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/3/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/3/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/4/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/4/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/5/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/5/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/6/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/6/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/7/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/7/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/8/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/8/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/9/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/9/avatar.svg"></a>
-
-
-
-## License
-MIT. check the LICENSE file
-
 ## Build
 
 ### Unix (Autotools)
@@ -197,15 +175,15 @@ If you want to use inline versions of funcstions then; include main header
 ```
 the header will include all headers. Then call func you want e.g. rotate vector by axis:
 ```C
-glm_vec_rotate(v1, glm_rad(45), (vec3){1.0f, 0.0f, 0.0f});
+glm_vec3_rotate(v1, glm_rad(45), (vec3){1.0f, 0.0f, 0.0f});
 ```
 some functions are overloaded :) e.g you can normalize vector:
 ```C
-glm_vec_normalize(vec);
+glm_vec3_normalize(vec);
 ```
 this will normalize vec and store normalized vector into `vec` but if you will store normalized vector into another vector do this:
 ```C
-glm_vec_normalize_to(vec, result);
+glm_vec3_normalize_to(vec, result);
 ```
 like this function you may see `_to` postfix, this functions store results to another variables and save temp memory
 
@@ -216,7 +194,7 @@ to call pre-compiled versions include header with `c` postfix, c means call. Pre
 ```
 this header will include all headers with c postfix. You need to call functions with c posfix:
 ```C
-glmc_vec_normalize(vec);
+glmc_vec3_normalize(vec);
 ```
 
 Function usage and parameters are documented inside related headers. You may see same parameter passed twice in some examples like this:
@@ -280,3 +258,35 @@ You can pass same way to another APIs e.g. Vulkan, DX...
 - [ ] Unaligned operations (e.g. `glm_umat4_mul`)
 - [x] Extra documentation
 - [ ] ARM Neon Arch (In Progress)
+
+
+## Contributors
+
+This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
+<a href="graphs/contributors"><img src="https://opencollective.com/cglm/contributors.svg?width=890&button=false" /></a>
+
+
+## Backers
+
+Thank you to all our backers! 🙏 [[Become a backer](https://opencollective.com/cglm#backer)]
+
+<a href="https://opencollective.com/cglm#backers" target="_blank"><img src="https://opencollective.com/cglm/backers.svg?width=890"></a>
+
+
+## Sponsors
+
+Support this project by becoming a sponsor. Your logo will show up here with a link to your website. [[Become a sponsor](https://opencollective.com/cglm#sponsor)]
+
+<a href="https://opencollective.com/cglm/sponsor/0/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/0/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/1/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/1/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/2/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/2/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/3/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/3/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/4/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/4/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/5/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/5/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/6/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/6/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/7/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/7/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/8/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/8/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/9/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/9/avatar.svg"></a>
+
+## License
+MIT. check the LICENSE file

autogen.sh

@@ -8,17 +8,14 @@
 
 cd $(dirname "$0")
 
-if [ "$(uname)" = "Darwin" ]; then
-libtoolBin=$(which glibtoolize)
-libtoolBinDir=$(dirname "${libtoolBin}")
-
-if [ ! -f "${libtoolBinDir}/libtoolize" ]; then
-ln -s $libtoolBin "${libtoolBinDir}/libtoolize"
-fi
-fi
-
 autoheader
-libtoolize
+
+if [ "$(uname)" = "Darwin" ]; then
+  glibtoolize
+else
+  libtoolize
+fi
+
 aclocal -I m4
 autoconf
 automake --add-missing --copy

build-deps.sh

@@ -9,19 +9,8 @@
 # check if deps are pulled
 git submodule update --init --recursive
 
-# fix glibtoolize
-
 cd $(dirname "$0")
 
-if [ "$(uname)" = "Darwin" ]; then
-  libtoolBin=$(which glibtoolize)
-  libtoolBinDir=$(dirname "${libtoolBin}")
-
-  if [ ! -f "${libtoolBinDir}/libtoolize" ]; then
-    ln -s $libtoolBin "${libtoolBinDir}/libtoolize"
-  fi
-fi
-
 # general deps: gcc make autoconf automake libtool cmake
 
 # test - cmocka

cglm.podspec

@@ -0,0 +1,28 @@
+Pod::Spec.new do |s|
+
+  # Description
+  s.name         = "cglm"
+  s.version      = "0.5.1"
+  s.summary      = "📽 Optimized OpenGL/Graphics Math (glm) for C"
+  s.description  = <<-DESC
+cglm is math library for graphics programming for C. It is similar to original glm but it is written for C instead of C++ (you can use here too). See the documentation or README for all features.
+                   DESC
+
+  s.documentation_url = "http://cglm.readthedocs.io"
+
+  # Home
+  s.homepage     = "https://github.com/recp/cglm"
+  s.license      = { :type => "MIT", :file => "LICENSE" }
+  s.author       = { "Recep Aslantas" => "recp@acm.org" }
+
+  # Sources
+  s.source               = { :git => "https://github.com/recp/cglm.git", :tag => "v#{s.version}" }
+  s.source_files         = "src", "include/cglm/**/*.h"
+  s.public_header_files  = "include", "include/cglm/**/*.h"
+  s.exclude_files        = "src/win/*", "src/dllmain.c", "src/**/*.h"
+  s.preserve_paths       = "include", "src"
+  s.header_mappings_dir  = "include"
+
+  # Linking
+  s.library = "m"
+end

configure.ac

@@ -7,7 +7,7 @@
 #*****************************************************************************
 
 AC_PREREQ([2.69])
-AC_INIT([cglm], [0.4.0], [info@recp.me])
+AC_INIT([cglm], [0.5.4], [info@recp.me])
 AM_INIT_AUTOMAKE([-Wall -Werror foreign subdir-objects])
 
 AC_CONFIG_MACRO_DIR([m4])
@@ -29,6 +29,7 @@ LT_INIT
 # Checks for libraries.
 AC_CHECK_LIB([m], [floor])
 
+m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
 AC_SYS_LARGEFILE
 
 # Checks for header files.

docs/source/affine-mat.rst

@@ -33,6 +33,7 @@ Table of contents (click func go):
 Functions:
 
 1. :c:func:`glm_mul`
+#. :c:func:`glm_mul_rot`
 #. :c:func:`glm_inv_tr`
 
 Functions documentation
@@ -59,6 +60,27 @@ Functions documentation
       | *[in]*  **m2**    affine matrix 2
       | *[out]* **dest**  result matrix
 
+.. c:function:: void  glm_mul_rot(mat4 m1, mat4 m2, mat4 dest)
+
+    | this is similar to glm_mat4_mul but specialized to rotation matrix
+
+    Right Matrix format should be (left is free):
+
+    .. code-block:: text
+
+       R  R  R  0
+       R  R  R  0
+       R  R  R  0
+       0  0  0  1
+
+    this reduces some multiplications. It should be faster than mat4_mul.
+    if you are not sure about matrix format then DON'T use this! use mat4_mul
+
+    Parameters:
+      | *[in]*  **m1**    affine matrix 1
+      | *[in]*  **m2**    affine matrix 2
+      | *[out]* **dest**  result matrix
+
 .. c:function:: void  glm_inv_tr(mat4 mat)
 
     | inverse orthonormal rotation + translation matrix (ridig-body)

docs/source/affine.rst

@@ -5,6 +5,8 @@ affine transforms
 
 Header: cglm/affine.h
 
+Initialize Transform Matrices
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Functions with **_make** prefix expect you don't have a matrix and they create
 a matrix for you. You don't need to pass identity matrix.
 
@@ -15,6 +17,107 @@ before sending to transfrom functions.
 There are also functions to decompose transform matrix. These functions can't
 decompose matrix after projected.
 
+Rotation Center
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Rotating functions uses origin as rotation center (pivot/anchor point),
+since scale factors are stored in rotation matrix, same may also true for scalling.
+cglm provides some functions for rotating around at given point e.g.
+**glm_rotate_at**, **glm_quat_rotate_at**. Use them or follow next section for algorihm ("Rotate or Scale around specific Point (Pivot Point / Anchor Point)").
+
+Rotate or Scale around specific Point (Anchor Point)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If you want to rotate model around arbibtrary point follow these steps:
+
+1. Move model from pivot point to origin: **translate(-pivot.x, -pivot.y, -pivot.z)**
+2. Apply rotation (or scaling maybe)
+3. Move model back from origin to pivot (reverse of step-1): **translate(pivot.x, pivot.y, pivot.z)**
+
+**glm_rotate_at**, **glm_quat_rotate_at** and their helper functions works that way.
+
+The implementation would be:
+
+.. code-block:: c
+  :linenos:
+
+  glm_translate(m, pivot);
+  glm_rotate(m, angle, axis);
+  glm_translate(m, pivotInv); /* pivotInv = -pivot */
+
+Transforms Order
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is important to understand this part especially if you call transform
+functions multiple times
+
+`glm_translate`, `glm_rotate`, `glm_scale` and `glm_quat_rotate` and their
+helpers functions works like this (cglm may provide reverse order too as alternative in the future):
+
+.. code-block:: c
+  :linenos:
+
+  TransformMatrix = TransformMatrix * TraslateMatrix; // glm_translate()
+  TransformMatrix = TransformMatrix * RotateMatrix;   // glm_rotate(), glm_quat_rotate()
+  TransformMatrix = TransformMatrix * ScaleMatrix;    // glm_scale()
+
+As you can see it is multipled as right matrix. For instance what will happen if you call `glm_translate` twice?
+
+.. code-block:: c
+  :linenos:
+
+  glm_translate(transform, translate1); /* transform = transform * translate1 */
+  glm_translate(transform, translate2); /* transform = transform * translate2 */
+  glm_rotate(transform, angle, axis)    /* transform = transform * rotation   */
+
+Now lets try to understand this:
+
+1. You call translate using `translate1` and you expect it will be first transform
+because you call it first, do you?
+
+Result will be **`transform = transform * translate1`**
+
+2. Then you call translate using `translate2` and you expect it will be second transform?
+
+Result will be **`transform = transform * translate2`**. Now lets expand transform,
+it was `transform * translate1` before second call.
+
+Now it is **`transform = transform * translate1 * translate2`**, now do you understand what I say?
+
+3. After last call transform will be:
+
+**`transform = transform * translate1 * translate2 * rotation`**
+
+The order will be; **rotation will be applied first**, then **translate2** then **translate1**
+
+It is all about matrix multiplication order. It is similar to MVP matrix:
+`MVP = Projection * View * Model`, model will be applied first, then view then projection.
+
+**Confused?**
+
+In the end the last function call applied first in shaders.
+
+As alternative way, you can create transform matrices individually then combine manually,
+but don't forget that `glm_translate`, `glm_rotate`, `glm_scale`... are optimized and should be faster (an smaller assembly output) than manual multiplication
+
+.. code-block:: c
+  :linenos:
+
+  mat4 transform1, transform2, transform3, finalTransform;
+
+  glm_translate_make(transform1, translate1);
+  glm_translate_make(transform2, translate2);
+  glm_rotate_make(transform3, angle, axis);
+
+  /* first apply transform1, then transform2, thentransform3 */
+  glm_mat4_mulN((mat4 *[]){&transform3, &transform2, &transform1}, 3, finalTransform);
+
+  /* if you don't want to use mulN, same as above */
+  glm_mat4_mul(transform3, transform2, finalTransform);
+  glm_mat4_mul(finalTransform, transform1, finalTransform);
+
+Now transform1 will be applied first, then transform2 then transform3
+
 Table of contents (click to go):
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -29,15 +132,14 @@ Functions:
 #. :c:func:`glm_scale_to`
 #. :c:func:`glm_scale_make`
 #. :c:func:`glm_scale`
-#. :c:func:`glm_scale1`
 #. :c:func:`glm_scale_uni`
 #. :c:func:`glm_rotate_x`
 #. :c:func:`glm_rotate_y`
 #. :c:func:`glm_rotate_z`
-#. :c:func:`glm_rotate_ndc_make`
 #. :c:func:`glm_rotate_make`
-#. :c:func:`glm_rotate_ndc`
 #. :c:func:`glm_rotate`
+#. :c:func:`glm_rotate_at`
+#. :c:func:`glm_rotate_atm`
 #. :c:func:`glm_decompose_scalev`
 #. :c:func:`glm_uniscaled`
 #. :c:func:`glm_decompose_rs`
@@ -122,10 +224,6 @@ Functions documentation
       | *[in, out]* **m** affine transfrom
       | *[in]*      **v** scale vector [x, y, z]
 
-.. c:function:: void  glm_scale1(mat4 m, float s)
-
-    DEPRECATED! Use glm_scale_uni
-
 .. c:function:: void  glm_scale_uni(mat4 m, float s)
 
     applies uniform scale to existing transform matrix v = [s, s, s]
@@ -165,16 +263,6 @@ Functions documentation
       | *[in]*  **angle** angle (radians)
       | *[out]* **dest**  rotated matrix
 
-.. c:function:: void  glm_rotate_ndc_make(mat4 m, float angle, vec3 axis_ndc)
-
-    creates NEW rotation matrix by angle and axis
-    this name may change in the future. axis must be is normalized
-
-    Parameters:
-      | *[out]* **m**        affine transfrom
-      | *[in]*  **angle**    angle (radians)
-      | *[in]*  **axis_ndc** normalized axis
-
 .. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
 
     creates NEW rotation matrix by angle and axis,
@@ -185,16 +273,6 @@ Functions documentation
       | *[in]*  **axis** angle (radians)
       | *[in]*  **axis** axis
 
-.. c:function:: void  glm_rotate_ndc(mat4 m, float angle, vec3 axis_ndc)
-
-    rotate existing transform matrix around Z axis by angle and axis
-    this name may change in the future, axis must be normalized.
-
-    Parameters:
-      | *[out]* **m**        affine transfrom
-      | *[in]*  **angle**    angle (radians)
-      | *[in]*  **axis_ndc** normalized axis
-
 .. c:function:: void  glm_rotate(mat4 m, float angle, vec3 axis)
 
     rotate existing transform matrix around Z axis by angle and axis
@@ -204,6 +282,29 @@ Functions documentation
       | *[in]*      **angle** angle (radians)
       | *[in]*      **axis**  axis
 
+.. c:function:: void  glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis)
+
+    rotate existing transform around given axis by angle at given pivot point (rotation center)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **pivot** pivot, anchor point, rotation center
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis)
+
+    | creates NEW rotation matrix by angle and axis at given point
+    | this creates rotation matrix, it assumes you don't have a matrix
+
+    | this should work faster than glm_rotate_at because it reduces one glm_translate.
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **pivot** pivot, anchor point, rotation center
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
 .. c:function:: void  glm_decompose_scalev(mat4 m, vec3 s)
 
     decompose scale vector

docs/source/api.rst

@@ -5,14 +5,14 @@ Some functions may exist twice,
 once for their namespace and once for global namespace
 to make easier to write very common functions
 
-For instance, in general we use :code:`glm_vec_dot` to get dot product
+For instance, in general we use :code:`glm_vec3_dot` to get dot product
 of two **vec3**. Now we can also do this with :code:`glm_dot`,
 same for *_cross* and so on...
 
 The original function stays where it is, the function in global namespace
 of same name is just an alias, so there is no call version of those functions.
 e.g there is no func like :code:`glmc_dot` because *glm_dot* is just alias for
-:code:`glm_vec_dot`
+:code:`glm_vec3_dot`
 
 By including **cglm/cglm.h** header you will include all inline version
 of functions. Since functions in this header[s] are inline you don't need to
@@ -45,3 +45,6 @@ Follow the :doc:`build` documentation for this
    util
    io
    call
+   sphere
+   curve
+   bezier

docs/source/bezier.rst

@@ -0,0 +1,89 @@
+.. default-domain:: C
+
+Bezier
+================================================================================
+
+Header: cglm/bezier.h
+
+Common helpers for cubic bezier and similar curves.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_bezier`
+2. :c:func:`glm_hermite`
+3. :c:func:`glm_decasteljau`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: float glm_bezier(float s, float p0, float c0, float c1, float p1)
+
+    | cubic bezier interpolation
+    | formula:
+
+    .. code-block:: text
+
+      B(s) = P0*(1-s)^3 + 3*C0*s*(1-s)^2 + 3*C1*s^2*(1-s) + P1*s^3
+
+    | similar result using matrix:
+
+    .. code-block:: text
+
+      B(s) = glm_smc(t, GLM_BEZIER_MAT, (vec4){p0, c0, c1, p1})
+
+    | glm_eq(glm_smc(...), glm_bezier(...)) should return TRUE
+
+    Parameters:
+      | *[in]*  **s**   parameter between 0 and 1
+      | *[in]*  **p0**  begin point
+      | *[in]*  **c0**  control point 1
+      | *[in]*  **c1**  control point 2
+      | *[in]*  **p1**  end point
+
+    Returns:
+        B(s)
+
+.. c:function:: float glm_hermite(float s, float p0, float t0, float t1, float p1)
+
+    | cubic hermite interpolation
+    | formula:
+
+    .. code-block:: text
+
+      H(s) = P0*(2*s^3 - 3*s^2 + 1) + T0*(s^3 - 2*s^2 + s) + P1*(-2*s^3 + 3*s^2) + T1*(s^3 - s^2)
+
+    | similar result using matrix:
+
+    .. code-block:: text
+
+      H(s) = glm_smc(t, GLM_HERMITE_MAT, (vec4){p0, p1, c0, c1})
+
+    | glm_eq(glm_smc(...), glm_hermite(...)) should return TRUE
+
+
+    Parameters:
+      | *[in]*  **s**   parameter between 0 and 1
+      | *[in]*  **p0**  begin point
+      | *[in]*  **t0**  tangent 1
+      | *[in]*  **t1**  tangent 2
+      | *[in]*  **p1**  end point
+
+    Returns:
+        B(s)
+
+.. c:function:: float glm_decasteljau(float prm, float p0, float c0, float c1, float p1)
+
+    | iterative way to solve cubic equation
+
+    Parameters:
+      | *[in]*  **prm** parameter between 0 and 1
+      | *[in]*  **p0**  begin point
+      | *[in]*  **c0**  control point 1
+      | *[in]*  **c1**  control point 2
+      | *[in]*  **p1**  end point
+
+    Returns:
+        parameter to use in cubic equation

docs/source/box.rst

@@ -28,6 +28,11 @@ Functions:
 #. :c:func:`glm_aabb_isvalid`
 #. :c:func:`glm_aabb_size`
 #. :c:func:`glm_aabb_radius`
+#. :c:func:`glm_aabb_center`
+#. :c:func:`glm_aabb_aabb`
+#. :c:func:`glm_aabb_sphere`
+#. :c:func:`glm_aabb_point`
+#. :c:func:`glm_aabb_contains`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -131,3 +136,46 @@ Functions documentation
 
     Parameters:
       | *[in]*   **box**     bounding box
+
+.. c:function:: void  glm_aabb_center(vec3 box[2], vec3 dest)
+
+    | computes center point of AABB
+
+    Parameters:
+      | *[in]*    **box**      bounding box
+      | *[out]*   **dest**     center of bounding box
+
+.. c:function:: bool  glm_aabb_aabb(vec3 box[2], vec3 other[2])
+
+    | check if two AABB intersects
+
+    Parameters:
+      | *[in]*    **box**     bounding box
+      | *[out]*   **other**   other bounding box
+
+.. c:function:: bool  glm_aabb_sphere(vec3 box[2], vec4 s)
+
+    | check if AABB intersects with sphere
+
+    | https://github.com/erich666/GraphicsGems/blob/master/gems/BoxSphere.c
+    | Solid Box - Solid Sphere test.
+
+    Parameters:
+      | *[in]*    **box**     solid bounding box
+      | *[out]*   **s**       solid sphere
+
+.. c:function:: bool  glm_aabb_point(vec3 box[2], vec3 point)
+
+    | check if point is inside of AABB
+
+    Parameters:
+      | *[in]*    **box**     bounding box
+      | *[out]*   **point**   point
+
+.. c:function:: bool  glm_aabb_contains(vec3 box[2], vec3 other[2])
+
+    | check if AABB contains other AABB
+
+    Parameters:
+      | *[in]*    **box**     bounding box
+      | *[out]*   **other**   other bounding box

docs/source/build.rst

@@ -1,9 +1,7 @@
-Building cglm
+Build cglm
 ================================
 
-| **cglm** does not have external dependencies except for unit testing.
-| When you pulled cglm repo with submodules all dependencies will be pulled too.
-| `build-deps.sh` will pull all dependencies/submodules and build for you.
+| **cglm** does not have external dependencies except for unit testing. When you pulled **cglm** repo with submodules all dependencies will be pulled too. `build-deps.sh` will pull all dependencies/submodules and build for you.
 
 External dependencies:
   * cmocka - for unit testing
@@ -12,7 +10,8 @@ External dependencies:
 If you only need to inline versions, you don't need to build **cglm**, you don't need to link it to your program.
 Just import cglm to your project as dependency / external lib by copy-paste then use it as usual
 
-**Unix (Autotools):**
+Unix (Autotools):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. code-block:: bash
   :linenos:
@@ -26,11 +25,12 @@ Just import cglm to your project as dependency / external lib by copy-paste then
   $ [sudo] make install   # install to system (optional)
 
 **make** will build cglm to **.libs** sub folder in project folder.
-If you don't want to install cglm to your system's folder you can get static and dynamic libs in this folder.
+If you don't want to install **cglm** to your system's folder you can get static and dynamic libs in this folder.
 
-**Build dependencies (windows):**
+Windows (MSBuild):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Windows related build files, project files are located in win folder,
+Windows related build files, project files are located in `win` folder,
 make sure you are inside in cglm/win folder.
 
 Code Analysis are enabled, it may take awhile to build.
@@ -50,3 +50,19 @@ then try to build with *devenv*:
   $ devenv cglm.sln /Build Release
 
 Currently tests are not available on Windows.
+
+Documentation (Sphinx):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+**cglm** uses sphinx framework for documentation, it allows lot of formats for documentation. To see all options see sphinx build page:
+
+https://www.sphinx-doc.org/en/master/man/sphinx-build.html
+
+Example build:
+
+.. code-block:: bash
+  :linenos:
+
+  $ cd cglm/docs
+  $ sphinx-build source build
+

docs/source/cam.rst

@@ -9,7 +9,7 @@ There are many convenient functions for camera. For instance :c:func:`glm_look`
 is just wrapper for :c:func:`glm_lookat`. Sometimes you only have direction
 instead of target, so that makes easy to build view matrix using direction.
 There is also :c:func:`glm_look_anyup` function which can help build view matrix
-without providing UP axis. It uses :c:func:`glm_vec_ortho` to get a UP axis and
+without providing UP axis. It uses :c:func:`glm_vec3_ortho` to get a UP axis and
 builds view matrix.
 
 You can also *_default* versions of ortho and perspective to build projection
@@ -36,6 +36,7 @@ Functions:
 #. :c:func:`glm_ortho_default`
 #. :c:func:`glm_ortho_default_s`
 #. :c:func:`glm_perspective`
+#. :c:func:`glm_persp_move_far`
 #. :c:func:`glm_perspective_default`
 #. :c:func:`glm_perspective_resize`
 #. :c:func:`glm_lookat`
@@ -145,6 +146,16 @@ Functions documentation
       | *[in]*  **farVal**  far clipping planes
       | *[out]* **dest**    result matrix
 
+.. c:function:: void  glm_persp_move_far(mat4 proj, float deltaFar)
+
+    | extend perspective projection matrix's far distance
+
+    | this function does not guarantee far >= near, be aware of that!
+
+    Parameters:
+      | *[in, out]*  **proj**      projection matrix to extend
+      | *[in]*       **deltaFar**  distance from existing far (negative to shink)
+
 .. c:function:: void glm_perspective_default(float aspect, mat4 dest)
 
      | set up perspective projection matrix with default near/far
@@ -167,6 +178,8 @@ Functions documentation
 
     | set up view matrix
 
+    **NOTE:** The UP vector must not be parallel to the line of sight from the eye point to the reference point.
+
     Parameters:
       | *[in]*  **eye**     eye vector
       | *[in]*  **center**  center vector
@@ -181,6 +194,8 @@ Functions documentation
     target self then this might be useful. Because you need to get target
     from direction.
 
+    **NOTE:** The UP vector must not be parallel to the line of sight from the eye point to the reference point.
+
     Parameters:
       | *[in]*  **eye**     eye vector
       | *[in]*  **center**  direction vector

docs/source/conf.py

@@ -62,9 +62,9 @@ author = u'Recep Aslantas'
 # built documents.
 #
 # The short X.Y version.
-version = u'0.3.4'
+version = u'0.5.4'
 # The full version, including alpha/beta/rc tags.
-release = u'0.3.4'
+release = u'0.5.4'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -90,7 +90,7 @@ todo_include_todos = False
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'alabaster'
+html_theme = 'sphinx_rtd_theme'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -99,13 +99,13 @@ html_theme = 'alabaster'
 # html_theme_options = {}
 
 html_theme_options = {
-    'github_banner': 'true',
-    'github_button': 'true',
-    'github_user': 'recp',
-    'github_repo': 'cglm',
-    'travis_button': 'true',
-    'show_related': 'true',
-    'fixed_sidebar': 'true'
+    # 'github_banner': 'true',
+    # 'github_button': 'true',
+    # 'github_user': 'recp',
+    # 'github_repo': 'cglm',
+    # 'travis_button': 'true',
+    # 'show_related': 'true',
+    # 'fixed_sidebar': 'true'
 }
 
 # Add any paths that contain custom static files (such as style sheets) here,

docs/source/curve.rst

@@ -0,0 +1,41 @@
+.. default-domain:: C
+
+Curve
+================================================================================
+
+Header: cglm/curve.h
+
+Common helpers for common curves. For specific curve see its header/doc
+e.g bezier
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_smc`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: float  glm_smc(float s, mat4 m, vec4 c)
+
+    | helper function to calculate **S** * **M** * **C** multiplication for curves
+
+    | this function does not encourage you to use SMC, instead it is a helper if you use SMC.
+
+    | if you want to specify S as vector then use more generic glm_mat4_rmc() func.
+
+    | Example usage:
+
+    .. code-block:: c
+
+       Bs = glm_smc(s, GLM_BEZIER_MAT, (vec4){p0, c0, c1, p1})
+
+    Parameters:
+      | *[in]*  **s**  parameter between 0 and 1 (this will be [s3, s2, s, 1])
+      | *[in]*  **m**  basis matrix
+      | *[out]* **c**  position/control vector
+
+    Returns:
+        scalar value e.g. Bs

docs/source/features.rst

@@ -0,0 +1,23 @@
+Features
+================================================================================
+
+* general purpose matrix operations (mat4, mat3)
+* chain matrix multiplication (square only)
+* general purpose vector operations (cross, dot, rotate, proj, angle...)
+* affine transforms
+* matrix decomposition (extract rotation, scaling factor)
+* optimized affine transform matrices (mul, rigid-body inverse)
+* camera (lookat)
+* projections (ortho, perspective)
+* quaternions
+* euler angles / yaw-pitch-roll to matrix
+* extract euler angles
+* inline or pre-compiled function call
+* frustum (extract view frustum planes, corners...)
+* bounding box (AABB in Frustum (culling), crop, merge...)
+* bounding sphere
+* project, unproject
+* easing functions
+* curves
+* curve interpolation helpers (SMC, deCasteljau...)
+* and other...

docs/source/frustum.rst

@@ -127,7 +127,7 @@ Functions documentation
     .. code-block:: c
 
        for (j = 0; j < 4; j++) {
-         glm_vec_center(corners[i], corners[i + 4], centerCorners[i]);
+         glm_vec3_center(corners[i], corners[i + 4], centerCorners[i]);
        }
 
     corners[i + 4] is far of corners[i] point.

docs/source/getting_started.rst

@@ -9,31 +9,40 @@ Types:
 .. code-block:: c
   :linenos:
 
+  typedef float                   vec2[2];
   typedef float                   vec3[3];
   typedef int                    ivec3[3];
-   typedef CGLM_ALIGN(16) float vec4[4];
-
-   typedef vec3 mat3[3];
-   typedef vec4 mat4[4];
-
+  typedef CGLM_ALIGN_IF(16) float vec4[4];
   typedef vec4                    versor;
+  typedef vec3                    mat3[3];
+
+  #ifdef __AVX__
+  typedef CGLM_ALIGN_IF(32) vec4  mat4[4];
+  #else
+  typedef CGLM_ALIGN_IF(16) vec4  mat4[4];
+  #endif
 
 As you can see types don't store extra informations in favor of space.
 You can send these values e.g. matrix to OpenGL directly without casting or calling a function like *value_ptr*
 
-Aligment is Required:
+Alignment Is Required:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-**vec4** and **mat4** requires 16 byte aligment because vec4 and mat4 operations are
-vectorized by SIMD instructions (SSE/AVX).
+**vec4** and **mat4** requires 16 (32 for **mat4** if AVX is enabled) byte alignment because **vec4** and **mat4** operations are vectorized by SIMD instructions (SSE/AVX/NEON).
+
+**UPDATE:**
+  By starting v0.4.5 cglm provides an option to disable alignment requirement, it is enabled as default
+
+  | Check :doc:`opt` page for more details
+
+  Also alignment is disabled for older msvc verisons as default. Now alignment is only required in Visual Studio 2017 version 15.6+ if CGLM_ALL_UNALIGNED macro is not defined.
 
 Allocations:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *cglm* doesn't alloc any memory on heap. So it doesn't provide any allocator.
-You must allocate memory yourself. You should alloc memory for out parameters too if you pass pointer of memory location.
-When allocating memory don't forget that **vec4** and **mat4** requires aligment.
+You must allocate memory yourself. You should alloc memory for out parameters too if you pass pointer of memory location. When allocating memory, don't forget that **vec4** and **mat4** require alignment.
 
-**NOTE:** Unaligned vec4 and unaligned mat4 operations will be supported in the future. Check todo list.
+**NOTE:** Unaligned **vec4** and unaligned **mat4** operations will be supported in the future. Check todo list.
 Because you may want to multiply a CGLM matrix with external matrix.
 There is no guarantee that non-CGLM matrix is aligned. Unaligned types will have *u* prefix e.g. **umat4**
 

docs/source/index.rst

@@ -3,7 +3,7 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Welcome to cglm's documentation!
+cglm Documentation
 ================================
 
 **cglm** is optimized 3D math library written in C99 (compatible with C89).
@@ -14,33 +14,38 @@ is considered to be supported as optional.
 
 Also currently only **float** type is supported for most operations.
 
-**Features**
-
-* general purpose matrix operations (mat4, mat3)
-* chain matrix multiplication (square only)
-* general purpose vector operations (cross, dot, rotate, proj, angle...)
-* affine transforms
-* matrix decomposition (extract rotation, scaling factor)
-* optimized affine transform matrices (mul, rigid-body inverse)
-* camera (lookat)
-* projections (ortho, perspective)
-* quaternions
-* euler angles / yaw-pitch-roll to matrix
-* extract euler angles
-* inline or pre-compiled function call
-* frustum (extract view frustum planes, corners...)
-* bounding box (AABB in Frustum (culling), crop, merge...)
-
-
 .. toctree::
-   :maxdepth: 1
-   :caption: Table Of Contents:
+   :maxdepth: 2
+   :caption: Getting Started:
 
+   features
    build
    getting_started
+
+.. toctree::
+   :maxdepth: 2
+   :caption: How To:
+
    opengl
+
+.. toctree::
+   :maxdepth: 2
+   :caption: API:
+
    api
 
+.. toctree::
+   :maxdepth: 2
+   :caption: Options:
+
+   opt
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Troubleshooting:
+
+   troubleshooting
+
 Indices and tables
 ==================
 

docs/source/mat3.rst

@@ -20,15 +20,20 @@ Functions:
 
 1. :c:func:`glm_mat3_copy`
 #. :c:func:`glm_mat3_identity`
+#. :c:func:`glm_mat3_identity_array`
+#. :c:func:`glm_mat3_zero`
 #. :c:func:`glm_mat3_mul`
 #. :c:func:`glm_mat3_transpose_to`
 #. :c:func:`glm_mat3_transpose`
 #. :c:func:`glm_mat3_mulv`
+#. :c:func:`glm_mat3_quat`
 #. :c:func:`glm_mat3_scale`
 #. :c:func:`glm_mat3_det`
 #. :c:func:`glm_mat3_inv`
+#. :c:func:`glm_mat3_trace`
 #. :c:func:`glm_mat3_swap_col`
 #. :c:func:`glm_mat3_swap_row`
+#. :c:func:`glm_mat3_rmc`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -48,6 +53,21 @@ Functions documentation
     Parameters:
       | *[out]* **mat**  matrix
 
+.. c:function:: void  glm_mat3_identity_array(mat3 * __restrict mat, size_t count)
+
+    make given matrix array's each element identity matrix
+
+    Parameters:
+      | *[in,out]* **mat**  matrix array (must be aligned (16/32) if alignment is not disabled)
+      | *[in]* **count**  count of matrices
+
+.. c:function:: void  glm_mat3_zero(mat3 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix to
+
 .. c:function:: void  glm_mat3_mul(mat3 m1, mat3 m2, mat3 dest)
 
     multiply m1 and m2 to dest
@@ -89,6 +109,14 @@ Functions documentation
       | *[in]*  **v**     vec3 (right, column vector)
       | *[out]* **dest**  destination (result, column vector)
 
+.. c:function:: void  glm_mat3_quat(mat3 m, versor dest)
+
+    convert mat3 to quaternion
+
+    Parameters:
+      | *[in]*  **m**     rotation matrix
+      | *[out]* **dest**  destination quaternion
+
 .. c:function:: void  glm_mat3_scale(mat3 m, float s)
 
     multiply matrix with scalar
@@ -115,6 +143,16 @@ Functions documentation
       | *[in]*  **mat**  matrix
       | *[out]* **dest** destination (inverse matrix)
 
+.. c:function:: void glm_mat3_trace(mat3 m)
+
+    | sum of the elements on the main diagonal from upper left to the lower right
+
+    Parameters:
+      | *[in]*  **m**  matrix
+
+    Returns:
+        trace of matrix
+
 .. c:function:: void  glm_mat3_swap_col(mat3 mat, int col1, int col2)
 
     swap two matrix columns
@@ -132,3 +170,20 @@ Functions documentation
       | *[in, out]*  **mat**   matrix
       | *[in]*       **row1**  row1
       | *[in]*       **row2**  row2
+
+.. c:function:: float  glm_mat3_rmc(vec3 r, mat3 m, vec3 c)
+
+    | **rmc** stands for **Row** * **Matrix** * **Column**
+
+    | helper for  R (row vector) * M (matrix) * C (column vector)
+
+    | the result is scalar because R * M = Matrix1x3 (row vector),
+    | then Matrix1x3 * Vec3 (column vector) = Matrix1x1 (Scalar)
+
+    Parameters:
+      | *[in]*  **r**  row vector or matrix1x3
+      | *[in]*  **m**  matrix3x3
+      | *[in]*  **c**  column vector or matrix3x1
+
+    Returns:
+        scalar value e.g. Matrix1x1

docs/source/mat4.rst

@@ -25,6 +25,8 @@ Functions:
 1. :c:func:`glm_mat4_ucopy`
 #. :c:func:`glm_mat4_copy`
 #. :c:func:`glm_mat4_identity`
+#. :c:func:`glm_mat4_identity_array`
+#. :c:func:`glm_mat4_zero`
 #. :c:func:`glm_mat4_pick3`
 #. :c:func:`glm_mat4_pick3t`
 #. :c:func:`glm_mat4_ins3`
@@ -32,6 +34,9 @@ Functions:
 #. :c:func:`glm_mat4_mulN`
 #. :c:func:`glm_mat4_mulv`
 #. :c:func:`glm_mat4_mulv3`
+#. :c:func:`glm_mat3_trace`
+#. :c:func:`glm_mat3_trace3`
+#. :c:func:`glm_mat4_quat`
 #. :c:func:`glm_mat4_transpose_to`
 #. :c:func:`glm_mat4_transpose`
 #. :c:func:`glm_mat4_scale_p`
@@ -41,6 +46,7 @@ Functions:
 #. :c:func:`glm_mat4_inv_fast`
 #. :c:func:`glm_mat4_swap_col`
 #. :c:func:`glm_mat4_swap_row`
+#. :c:func:`glm_mat4_rmc`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -68,6 +74,21 @@ Functions documentation
     Parameters:
       | *[out]* **mat**  matrix
 
+.. c:function:: void  glm_mat4_identity_array(mat4 * __restrict mat, size_t count)
+
+    make given matrix array's each element identity matrix
+
+    Parameters:
+      | *[in,out]* **mat**  matrix array (must be aligned (16/32) if alignment is not disabled)
+      | *[in]* **count**  count of matrices
+
+.. c:function:: void  glm_mat4_zero(mat4 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix to
+
 .. c:function:: void  glm_mat4_pick3(mat4 mat, mat3 dest)
 
     copy upper-left of mat4 to mat3
@@ -146,6 +167,35 @@ Functions documentation
     | *[in]*  **v**     vec3 (right, column vector)
     | *[out]* **dest**  vec3 (result, column vector)
 
+.. c:function:: void  glm_mat4_trace(mat4 m)
+
+    | sum of the elements on the main diagonal from upper left to the lower right
+
+    Parameters:
+      | *[in]*  **m**  matrix
+
+    Returns:
+        trace of matrix
+
+.. c:function:: void  glm_mat4_trace3(mat4 m)
+
+    | trace of matrix (rotation part)
+    | sum of the elements on the main diagonal from upper left to the lower right
+
+    Parameters:
+      | *[in]*  **m**  matrix
+
+    Returns:
+        trace of matrix
+
+.. c:function:: void  glm_mat4_quat(mat4 m, versor dest)
+
+    convert mat4's rotation part to quaternion
+
+    Parameters:
+    | *[in]*  **m**     affine matrix
+    | *[out]* **dest**  destination quaternion
+
 .. c:function:: void  glm_mat4_transpose_to(mat4 m, mat4 dest)
 
     transpose mat4 and store in dest
@@ -229,3 +279,20 @@ Functions documentation
       | *[in, out]*  **mat**   matrix
       | *[in]*       **row1**  row1
       | *[in]*       **row2**  row2
+
+.. c:function:: float  glm_mat4_rmc(vec4 r, mat4 m, vec4 c)
+
+    | **rmc** stands for **Row** * **Matrix** * **Column**
+
+    | helper for  R (row vector) * M (matrix) * C (column vector)
+
+    | the result is scalar because R * M = Matrix1x4 (row vector),
+    | then Matrix1x4 * Vec4 (column vector) = Matrix1x1 (Scalar)
+
+    Parameters:
+      | *[in]*  **r**  row vector or matrix1x4
+      | *[in]*  **m**  matrix4x4
+      | *[in]*  **c**  column vector or matrix4x1
+
+    Returns:
+        scalar value e.g. Matrix1x1

docs/source/opengl.rst

@@ -45,7 +45,7 @@ array of matrices:
 
 in this way, passing aray of matrices is same
 
-Passing / Uniforming Vectors to OpenGL:¶
+Passing / Uniforming Vectors to OpenGL:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 You don't need to do extra thing when passing cglm vectors to OpengL or other APIs.

docs/source/opt.rst

@@ -0,0 +1,52 @@
+.. default-domain:: C
+
+Options
+===============================================================================
+
+A few options are provided via macros.
+
+Alignment Option
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As default, cglm requires types to be aligned. Alignment requirements:
+
+vec3:   8 byte
+vec4:   16 byte
+mat4:   16 byte
+versor: 16 byte
+
+By starting **v0.4.5** cglm provides an option to disable alignment requirement.
+To enable this option define **CGLM_ALL_UNALIGNED** macro before all headers.
+You can define it in Xcode, Visual Studio (or other IDEs) or you can also prefer
+to define it in build system. If you use pre-compiled verisons then you
+have to compile cglm with **CGLM_ALL_UNALIGNED** macro.
+
+**VERY VERY IMPORTANT:** If you use cglm in multiple projects and
+ those projects are depends on each other, then
+
+ | *ALWAYS* or *NEVER USE* **CGLM_ALL_UNALIGNED** macro in linked projects
+
+ if you do not know what you are doing. Because a cglm header included
+ via 'project A' may force types to be aligned and another cglm header
+ included via 'project B' may not require alignment. In this case
+ cglm functions will read from and write to **INVALID MEMORY LOCATIONs**.
+
+ ALWAYS USE SAME CONFIGURATION / OPTION for **cglm** if you have multiple projects.
+
+ For instance if you set CGLM_ALL_UNALIGNED in a project then set it in other projects too
+
+SSE and SSE2 Shuffle Option
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+**_mm_shuffle_ps** generates **shufps** instruction even if registers are same.
+You can force it to generate **pshufd** instruction by defining
+**CGLM_USE_INT_DOMAIN** macro. As default it is not defined.
+
+SSE3 and SSE4 Dot Product Options
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+You have to extra options for dot product: **CGLM_SSE4_DOT** and **CGLM_SSE3_DOT**.
+
+- If **SSE4** is enabled then you can define **CGLM_SSE4_DOT** to force cglm to use **_mm_dp_ps** instruction.
+- If **SSE3** is enabled then you can define **CGLM_SSE3_DOT** to force cglm to use **_mm_hadd_ps** instructions.
+
+otherwise cglm will use custom cglm's hadd functions which are optimized too.

docs/source/quat.rst

@@ -27,6 +27,7 @@ Macros:
 Functions:
 
 1. :c:func:`glm_quat_identity`
+#. :c:func:`glm_quat_identity_array`
 #. :c:func:`glm_quat_init`
 #. :c:func:`glm_quat`
 #. :c:func:`glm_quatv`
@@ -56,6 +57,9 @@ Functions:
 #. :c:func:`glm_quat_for`
 #. :c:func:`glm_quat_forp`
 #. :c:func:`glm_quat_rotatev`
+#. :c:func:`glm_quat_rotate`
+#. :c:func:`glm_quat_rotate_at`
+#. :c:func:`glm_quat_rotate_atm`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -67,6 +71,14 @@ Functions documentation
     Parameters:
       | *[in, out]*  **q**    quaternion
 
+.. c:function:: void  glm_quat_identity_array(versor * __restrict q, size_t count)
+
+    | make given quaternion array's each element identity quaternion
+
+    Parameters:
+      | *[in, out]*  **q**   quat array (must be aligned (16) if alignment is not disabled)
+      | *[in]*  **count**    count of quaternions
+
 .. c:function:: void  glm_quat_init(versor q, float x, float y, float z, float w)
 
     | inits quaternion with given values
@@ -354,3 +366,24 @@ Functions documentation
       | *[in]*  **m**     existing transform matrix to rotate
       | *[in]*  **q**     quaternion
       | *[out]* **dest**  rotated matrix/transform
+
+.. c:function:: void glm_quat_rotate_at(mat4 m, versor q, vec3 pivot)
+
+    | rotate existing transform matrix using quaternion at pivot point
+
+    Parameters:
+      | *[in, out]*  **m**      existing transform matrix to rotate
+      | *[in]*       **q**      quaternion
+      | *[in]*       **pivot**  pivot
+
+.. c:function:: void glm_quat_rotate(mat4 m, versor q, mat4 dest)
+
+    | rotate NEW transform matrix using quaternion at pivot point
+    | this creates rotation matrix, it assumes you don't have a matrix
+
+    | this should work faster than glm_quat_rotate_at because it reduces one glm_translate.
+
+    Parameters:
+      | *[in, out]*  **m**      existing transform matrix to rotate
+      | *[in]*       **q**      quaternion
+      | *[in]*       **pivot**  pivot

docs/source/sphere.rst

@@ -0,0 +1,74 @@
+.. default-domain:: C
+
+Sphere
+================================================================================
+
+Header: cglm/sphere.h
+
+**Definition of sphere:**
+
+Sphere Representation in cglm is *vec4*: **[center.x, center.y, center.z, radii]**
+
+You can call any vec3 function by pasing sphere. Because first three elements
+defines center of sphere.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_sphere_radii`
+#. :c:func:`glm_sphere_transform`
+#. :c:func:`glm_sphere_merge`
+#. :c:func:`glm_sphere_sphere`
+#. :c:func:`glm_sphere_point`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: float  glm_sphere_radii(vec4 s)
+
+    | helper for getting sphere radius
+
+    Parameters:
+      | *[in]*  **s**   sphere
+
+    Returns:
+       returns radii
+
+.. c:function:: void  glm_sphere_transform(vec4 s, mat4 m, vec4 dest)
+
+    | apply transform to sphere, it is just wrapper for glm_mat4_mulv3
+
+    Parameters:
+      | *[in]*  **s**    sphere
+      | *[in]*  **m**    transform matrix
+      | *[out]* **dest** transformed sphere
+
+.. c:function:: void  glm_sphere_merge(vec4 s1, vec4 s2, vec4 dest)
+
+    | merges two spheres and creates a new one
+
+    two sphere must be in same space, for instance if one in world space then
+    the other must be in world space too, not in local space.
+
+    Parameters:
+      | *[in]*  **s1**      sphere 1
+      | *[in]*  **s2**      sphere 2
+      | *[out]* **dest**    merged/extended sphere
+
+.. c:function:: bool  glm_sphere_sphere(vec4 s1, vec4 s2)
+
+    | check if two sphere intersects
+
+    Parameters:
+      | *[in]*  **s1**      sphere
+      | *[in]*  **s2**      other sphere
+
+.. c:function:: bool  glm_sphere_point(vec4 s, vec3 point)
+
+    | check if sphere intersects with point
+
+    Parameters:
+      | *[in]*  **s**       sphere
+      | *[in]*  **point**   point

docs/source/troubleshooting.rst

@@ -0,0 +1,79 @@
+.. default-domain:: C
+
+Troubleshooting
+================================================================================
+
+It is possible that sometimes you may get crashes or wrong results.
+Follow these topics
+
+Memory Allocation:
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Again, **cglm** doesn't alloc any memory on heap.
+cglm functions works like memcpy; it copies data from src,
+makes calculations then copy the result to dest.
+
+You are responsible for allocation of **src** and **dest** parameters.
+
+Alignment:
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+**vec4** and **mat4** types requires 16 byte alignment.
+These types are marked with align attribute to let compiler know about this
+requirement.
+
+But since MSVC (Windows) throws the error:
+
+**"formal parameter with requested alignment of 16 won't be aligned"**
+
+The alignment attribute has been commented for MSVC
+
+.. code-block:: c
+
+   #if defined(_MSC_VER)
+   #  define CGLM_ALIGN(X) /* __declspec(align(X)) */
+   #else
+   #  define CGLM_ALIGN(X) __attribute((aligned(X)))
+   #endif.
+
+So MSVC may not know about alignment requirements when creating variables.
+The interesting thing is that, if I remember correctly Visual Studio 2017
+doesn't throw the above error. So we may uncomment that line for Visual Studio 2017,
+you may do it yourself.
+
+**This MSVC issue is still in TODOs.**
+
+**UPDATE:** By starting v0.4.5 cglm provides an option to disable alignment requirement.
+Also alignment is disabled for older msvc verisons as default. Now alignment is only required in Visual Studio 2017 version 15.6+ if CGLM_ALL_UNALIGNED macro is not defined.
+
+Crashes, Invalid Memory Access:
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Probably you are trying to write to invalid memory location.
+
+You may used wrong function for what you want to do.
+
+For instance you may called **glm_vec4_** functions for **vec3** data type.
+It will try to write 32 byte but since **vec3** is 24 byte it should throw
+memory access error or exit the app without saying anything.
+
+Wrong Results:
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Again, you may used wrong function.
+
+For instance if you use **glm_normalize()** or **glm_vec3_normalize()** for **vec4**,
+it will assume that passed param is **vec3** and will normalize it for **vec3**.
+Since you need to **vec4** to be normalized in your case, you will get wrong results.
+
+Accessing vec4 type with vec3 functions is valid, you will not get any error, exception or crash.
+You only get wrong results if you don't know what you are doing!
+
+So be carefull, when your IDE (Xcode, Visual Studio ...) tried to autocomplete function names, READ IT :)
+
+**Also implementation may be wrong please let us know by creating an issue on Github.**
+
+Other Issues?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+**Please let us know by creating an issue on Github.**

docs/source/util.rst

@@ -136,3 +136,38 @@ Functions documentation
 
     Returns:
        interpolated value
+
+.. c:function:: bool glm_eq(float a, float b)
+
+    check if two float equal with using EPSILON
+
+    Parameters:
+      | *[in]*  **a**   a
+      | *[in]*  **b**   b
+
+    Returns:
+       true if a and b equals
+
+.. c:function:: float glm_percent(float from, float to, float current)
+
+    percentage of current value between start and end value
+
+    Parameters:
+      | *[in]*  **from**   from value
+      | *[in]*  **to**     to value
+      | *[in]*  **current**   value between from and to values
+
+    Returns:
+       clamped normalized percent (0-100 in 0-1)
+
+.. c:function:: float glm_percentc(float from, float to, float current)
+
+    clamped percentage of current value between start and end value
+
+    Parameters:
+      | *[in]*  **from**      from value
+      | *[in]*  **to**        to value
+      | *[in]*  **current**   value between from and to values
+
+    Returns:
+       clamped normalized percent (0-100 in 0-1)

docs/source/vec3-ext.rst

@@ -14,25 +14,25 @@ Table of contents (click to go):
 
 Functions:
 
-1. :c:func:`glm_vec_mulv`
-#. :c:func:`glm_vec_broadcast`
-#. :c:func:`glm_vec_eq`
-#. :c:func:`glm_vec_eq_eps`
-#. :c:func:`glm_vec_eq_all`
-#. :c:func:`glm_vec_eqv`
-#. :c:func:`glm_vec_eqv_eps`
-#. :c:func:`glm_vec_max`
-#. :c:func:`glm_vec_min`
-#. :c:func:`glm_vec_isnan`
-#. :c:func:`glm_vec_isinf`
-#. :c:func:`glm_vec_isvalid`
-#. :c:func:`glm_vec_sign`
-#. :c:func:`glm_vec_sqrt`
+1. :c:func:`glm_vec3_mulv`
+#. :c:func:`glm_vec3_broadcast`
+#. :c:func:`glm_vec3_eq`
+#. :c:func:`glm_vec3_eq_eps`
+#. :c:func:`glm_vec3_eq_all`
+#. :c:func:`glm_vec3_eqv`
+#. :c:func:`glm_vec3_eqv_eps`
+#. :c:func:`glm_vec3_max`
+#. :c:func:`glm_vec3_min`
+#. :c:func:`glm_vec3_isnan`
+#. :c:func:`glm_vec3_isinf`
+#. :c:func:`glm_vec3_isvalid`
+#. :c:func:`glm_vec3_sign`
+#. :c:func:`glm_vec3_sqrt`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
 
-.. c:function:: void  glm_vec_mulv(vec3 a, vec3 b, vec3 d)
+.. c:function:: void  glm_vec3_mulv(vec3 a, vec3 b, vec3 d)
 
     multiplies individual items
 
@@ -41,7 +41,7 @@ Functions documentation
       | *[in]*  **b**  vec2
       | *[out]* **d**  destination (v1[0] * v2[0], v1[1] * v2[1], v1[2] * v2[2])
 
-.. c:function:: void  glm_vec_broadcast(float val, vec3 d)
+.. c:function:: void  glm_vec3_broadcast(float val, vec3 d)
 
     fill a vector with specified value
 
@@ -49,7 +49,7 @@ Functions documentation
       | *[in]*  **val**   value
       | *[out]* **dest**  destination
 
-.. c:function:: bool  glm_vec_eq(vec3 v, float val)
+.. c:function:: bool  glm_vec3_eq(vec3 v, float val)
 
     check if vector is equal to value (without epsilon)
 
@@ -57,7 +57,7 @@ Functions documentation
       | *[in]*  **v**    vector
       | *[in]*  **val**  value
 
-.. c:function:: bool  glm_vec_eq_eps(vec3 v, float val)
+.. c:function:: bool  glm_vec3_eq_eps(vec3 v, float val)
 
     check if vector is equal to value (with epsilon)
 
@@ -65,14 +65,14 @@ Functions documentation
       | *[in]*  **v**    vector
       | *[in]*  **val**  value
 
-.. c:function:: bool  glm_vec_eq_all(vec3 v)
+.. c:function:: bool  glm_vec3_eq_all(vec3 v)
 
     check if vectors members are equal (without epsilon)
 
     Parameters:
       | *[in]*  **v**   vector
 
-.. c:function:: bool  glm_vec_eqv(vec3 v1, vec3 v2)
+.. c:function:: bool  glm_vec3_eqv(vec3 v1, vec3 v2)
 
     check if vector is equal to another (without epsilon) vector
 
@@ -80,7 +80,7 @@ Functions documentation
       | *[in]*  **vec**   vector 1
       | *[in]*  **vec**   vector 2
 
-.. c:function:: bool  glm_vec_eqv_eps(vec3 v1, vec3 v2)
+.. c:function:: bool  glm_vec3_eqv_eps(vec3 v1, vec3 v2)
 
     check if vector is equal to another (with epsilon)
 
@@ -88,21 +88,21 @@ Functions documentation
       | *[in]*  **v1**    vector1
       | *[in]*  **v2**    vector2
 
-.. c:function:: float  glm_vec_max(vec3 v)
+.. c:function:: float  glm_vec3_max(vec3 v)
 
     max value of vector
 
     Parameters:
       | *[in]*  **v**    vector
 
-.. c:function:: float glm_vec_min(vec3 v)
+.. c:function:: float glm_vec3_min(vec3 v)
 
      min value of vector
 
     Parameters:
       | *[in]*  **v**  vector
 
-.. c:function:: bool glm_vec_isnan(vec3 v)
+.. c:function:: bool glm_vec3_isnan(vec3 v)
 
     | check if one of items is NaN (not a number)
     | you should only use this in DEBUG mode or very critical asserts
@@ -110,7 +110,7 @@ Functions documentation
     Parameters:
       | *[in]*  **v**  vector
 
-.. c:function:: bool glm_vec_isinf(vec3 v)
+.. c:function:: bool glm_vec3_isinf(vec3 v)
 
     | check if one of items is INFINITY
     | you should only use this in DEBUG mode or very critical asserts
@@ -118,7 +118,7 @@ Functions documentation
     Parameters:
       | *[in]*  **v**  vector
 
-.. c:function:: bool glm_vec_isvalid(vec3 v)
+.. c:function:: bool glm_vec3_isvalid(vec3 v)
 
     | check if all items are valid number
     | you should only use this in DEBUG mode or very critical asserts
@@ -126,7 +126,7 @@ Functions documentation
     Parameters:
       | *[in]*  **v**  vector
 
-.. c:function:: void glm_vec_sign(vec3 v, vec3 dest)
+.. c:function:: void glm_vec3_sign(vec3 v, vec3 dest)
 
     get sign of 32 bit float as +1, -1, 0
 
@@ -134,7 +134,7 @@ Functions documentation
       | *[in]*   **v**     vector
       | *[out]*  **dest**  sign vector (only keeps signs as -1, 0, -1)
 
-.. c:function:: void glm_vec_sqrt(vec3 v, vec3 dest)
+.. c:function:: void glm_vec3_sqrt(vec3 v, vec3 dest)
 
     square root of each vector item
 

docs/source/vec3.rst

@@ -5,9 +5,14 @@ vec3
 
 Header: cglm/vec3.h
 
+ **Important:** *cglm* was used **glm_vec_** namespace for vec3 functions until
+ **v0.5.0**, since **v0.5.0** cglm uses **glm_vec3_** namespace for vec3.
+
+ Also `glm_vec3_flipsign` has been renamed to `glm_vec3_negate`
+
 We mostly use vectors in graphics math, to make writing code faster
 and easy to read, some *vec3* functions are aliased in global namespace.
-For instance :c:func:`glm_dot` is alias of :c:func:`glm_vec_dot`,
+For instance :c:func:`glm_dot` is alias of :c:func:`glm_vec3_dot`,
 alias means inline wrapper here. There is no call verison of alias functions
 
 There are also functions for rotating *vec3* vector. **_m4**, **_m3** prefixes
@@ -18,7 +23,7 @@ Table of contents (click to go):
 
 Macros:
 
-1. glm_vec_dup(v, dest)
+1. glm_vec3_dup(v, dest)
 #. GLM_VEC3_ONE_INIT
 #. GLM_VEC3_ZERO_INIT
 #. GLM_VEC3_ONE
@@ -30,32 +35,50 @@ Macros:
 Functions:
 
 1. :c:func:`glm_vec3`
-#. :c:func:`glm_vec_copy`
-#. :c:func:`glm_vec_dot`
-#. :c:func:`glm_vec_cross`
-#. :c:func:`glm_vec_norm2`
-#. :c:func:`glm_vec_norm`
-#. :c:func:`glm_vec_add`
-#. :c:func:`glm_vec_sub`
-#. :c:func:`glm_vec_scale`
-#. :c:func:`glm_vec_scale_as`
-#. :c:func:`glm_vec_flipsign`
-#. :c:func:`glm_vec_flipsign_to`
-#. :c:func:`glm_vec_inv`
-#. :c:func:`glm_vec_inv_to`
-#. :c:func:`glm_vec_normalize`
-#. :c:func:`glm_vec_normalize_to`
-#. :c:func:`glm_vec_distance`
-#. :c:func:`glm_vec_angle`
-#. :c:func:`glm_vec_rotate`
-#. :c:func:`glm_vec_rotate_m4`
-#. :c:func:`glm_vec_proj`
-#. :c:func:`glm_vec_center`
-#. :c:func:`glm_vec_maxv`
-#. :c:func:`glm_vec_minv`
-#. :c:func:`glm_vec_ortho`
-#. :c:func:`glm_vec_clamp`
-#. :c:func:`glm_vec_lerp`
+#. :c:func:`glm_vec3_copy`
+#. :c:func:`glm_vec3_zero`
+#. :c:func:`glm_vec3_one`
+#. :c:func:`glm_vec3_dot`
+#. :c:func:`glm_vec3_norm2`
+#. :c:func:`glm_vec3_norm`
+#. :c:func:`glm_vec3_add`
+#. :c:func:`glm_vec3_adds`
+#. :c:func:`glm_vec3_sub`
+#. :c:func:`glm_vec3_subs`
+#. :c:func:`glm_vec3_mul`
+#. :c:func:`glm_vec3_scale`
+#. :c:func:`glm_vec3_scale_as`
+#. :c:func:`glm_vec3_div`
+#. :c:func:`glm_vec3_divs`
+#. :c:func:`glm_vec3_addadd`
+#. :c:func:`glm_vec3_subadd`
+#. :c:func:`glm_vec3_muladd`
+#. :c:func:`glm_vec3_muladds`
+#. :c:func:`glm_vec3_maxadd`
+#. :c:func:`glm_vec3_minadd`
+#. :c:func:`glm_vec3_flipsign`
+#. :c:func:`glm_vec3_flipsign_to`
+#. :c:func:`glm_vec3_inv`
+#. :c:func:`glm_vec3_inv_to`
+#. :c:func:`glm_vec3_negate`
+#. :c:func:`glm_vec3_negate_to`
+#. :c:func:`glm_vec3_normalize`
+#. :c:func:`glm_vec3_normalize_to`
+#. :c:func:`glm_vec3_cross`
+#. :c:func:`glm_vec3_crossn`
+#. :c:func:`glm_vec3_distance2`
+#. :c:func:`glm_vec3_distance`
+#. :c:func:`glm_vec3_angle`
+#. :c:func:`glm_vec3_rotate`
+#. :c:func:`glm_vec3_rotate_m4`
+#. :c:func:`glm_vec3_rotate_m3`
+#. :c:func:`glm_vec3_proj`
+#. :c:func:`glm_vec3_center`
+#. :c:func:`glm_vec3_maxv`
+#. :c:func:`glm_vec3_minv`
+#. :c:func:`glm_vec3_ortho`
+#. :c:func:`glm_vec3_clamp`
+#. :c:func:`glm_vec3_lerp`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -68,7 +91,7 @@ Functions documentation
       | *[in]*  **v4**    vector4
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_copy(vec3 a, vec3 dest)
+.. c:function:: void  glm_vec3_copy(vec3 a, vec3 dest)
 
     copy all members of [a] to [dest]
 
@@ -76,7 +99,21 @@ Functions documentation
       | *[in]*  **a**     source
       | *[out]* **dest**  destination
 
-.. c:function:: float  glm_vec_dot(vec3 a, vec3 b)
+.. c:function:: void  glm_vec3_zero(vec3 v)
+
+    makes all members 0.0f (zero)
+
+    Parameters:
+      | *[in, out]*  **v**     vector
+
+.. c:function:: void  glm_vec3_one(vec3 v)
+
+    makes all members 1.0f (one)
+
+    Parameters:
+      | *[in, out]*  **v**     vector
+
+.. c:function:: float  glm_vec3_dot(vec3 a, vec3 b)
 
     dot product of vec3
 
@@ -87,16 +124,25 @@ Functions documentation
     Returns:
       dot product
 
-.. c:function:: void  glm_vec_cross(vec3 a, vec3 b, vec3 d)
+.. c:function:: void  glm_vec3_cross(vec3 a, vec3 b, vec3 d)
 
-    cross product
+    cross product of two vector (RH)
 
     Parameters:
-      | *[in]*  **a**  source 1
-      | *[in]*  **b**  source 2
-      | *[out]* **d**  destination
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  destination
 
-.. c:function:: float  glm_vec_norm2(vec3 v)
+.. c:function:: void  glm_vec3_crossn(vec3 a, vec3 b, vec3 dest)
+
+    cross product of two vector (RH) and normalize the result
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  destination
+
+.. c:function:: float  glm_vec3_norm2(vec3 v)
 
     norm * norm (magnitude) of vector
 
@@ -110,32 +156,59 @@ Functions documentation
     Returns:
       square of norm / magnitude
 
-.. c:function:: float  glm_vec_norm(vec3 vec)
+.. c:function:: float  glm_vec3_norm(vec3 vec)
 
     norm (magnitude) of vec3
 
     Parameters:
       | *[in]*  **vec**   vector
 
-.. c:function:: void  glm_vec_add(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_add(vec3 a, vec3 b, vec3 dest)
 
-    add v2 vector to v1 vector store result in dest
+    add a vector to b vector store result in dest
 
     Parameters:
-      | *[in]*  **v1**    vector1
-      | *[in]*  **v2**    vector2
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_sub(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_adds(vec3 a, float s, vec3 dest)
 
-    subtract v2 vector from v1 vector store result in dest
+    add scalar to v vector store result in dest (d = v + vec(s))
 
     Parameters:
-      | *[in]*  **v1**    vector1
-      | *[in]*  **v2**    vector2
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void glm_vec_scale(vec3 v, float s, vec3 dest)
+.. c:function:: void  glm_vec3_sub(vec3 v1, vec3 v2, vec3 dest)
+
+    subtract b vector from a vector store result in dest (d = v1 - v2)
+
+    Parameters:
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void  glm_vec3_subs(vec3 v, float s, vec3 dest)
+
+    subtract scalar from v vector store result in dest (d = v - vec(s))
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void  glm_vec3_mul(vec3 a, vec3 b, vec3 d)
+
+    multiply two vector (component-wise multiplication)
+
+    Parameters:
+      | *[in]*  **a**     vector
+      | *[in]*  **b**     scalar
+      | *[out]* **d**     result = (a[0] * b[0], a[1] * b[1], a[2] * b[2])
+
+.. c:function:: void glm_vec3_scale(vec3 v, float s, vec3 dest)
 
      multiply/scale vec3 vector with scalar: result = v * s
 
@@ -145,7 +218,7 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_scale_as(vec3 v, float s, vec3 dest)
+.. c:function:: void  glm_vec3_scale_as(vec3 v, float s, vec3 dest)
 
     make vec3 vector scale as specified: result = unit(v) * s
 
@@ -154,44 +227,145 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_flipsign(vec3 v)
+.. c:function:: void  glm_vec3_div(vec3 a, vec3 b, vec3 dest)
 
-    flip sign of all vec3 members
+    div vector with another component-wise division: d = a / b
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  result = (a[0] / b[0], a[1] / b[1], a[2] / b[2])
+
+.. c:function:: void  glm_vec3_divs(vec3 v, float s, vec3 dest)
+
+    div vector with scalar: d = v / s
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  result = (a[0] / s, a[1] / s, a[2] / s])
+
+.. c:function:: void  glm_vec3_addadd(vec3 a, vec3 b, vec3 dest)
+
+    | add two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a + b)
+
+.. c:function:: void  glm_vec3_subadd(vec3 a, vec3 b, vec3 dest)
+
+    | sub two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a - b)
+
+.. c:function:: void  glm_vec3_muladd(vec3 a, vec3 b, vec3 dest)
+
+    | mul two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec3_muladds(vec3 a, float s, vec3 dest)
+
+    | mul vector with scalar and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec3_maxadd(vec3 a, vec3 b, vec3 dest)
+
+    | add max of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec3_minadd(vec3 a, vec3 b, vec3 dest)
+
+    | add min of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec3_flipsign(vec3 v)
+
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate`
 
     Parameters:
       | *[in, out]*  **v**    vector
 
-.. c:function:: void  glm_vec_flipsign_to(vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_flipsign_to(vec3 v, vec3 dest)
 
-    flip sign of all vec3 members and store result in dest
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate_to`
 
     Parameters:
       | *[in]*  **v**       vector
       | *[out]* **dest**    negated vector
 
-.. c:function:: void  glm_vec_inv(vec3 v)
+.. c:function:: void  glm_vec3_inv(vec3 v)
 
-    make vector as inverse/opposite of itself
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate`
 
     Parameters:
       | *[in, out]*  **v**    vector
 
-.. c:function:: void  glm_vec_inv_to(vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_inv_to(vec3 v, vec3 dest)
 
-    inverse/opposite vector
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate_to`
 
     Parameters:
       | *[in]*  **v**     source
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_normalize(vec3 v)
+.. c:function:: void  glm_vec3_negate(vec3 v)
+
+    negate vector components
+
+    Parameters:
+      | *[in, out]*  **v**    vector
+
+.. c:function:: void  glm_vec3_negate_to(vec3 v, vec3 dest)
+
+    negate vector components and store result in dest
+
+    Parameters:
+      | *[in]*  **v**       vector
+      | *[out]* **dest**    negated vector
+
+.. c:function:: void  glm_vec3_normalize(vec3 v)
 
     normalize vec3 and store result in same vec
 
     Parameters:
       | *[in, out]*  **v**    vector
 
-.. c:function:: void  glm_vec_normalize_to(vec3 vec, vec3 dest)
+.. c:function:: void  glm_vec3_normalize_to(vec3 vec, vec3 dest)
 
      normalize vec3 to dest
 
@@ -199,7 +373,7 @@ Functions documentation
       | *[in]*   **vec**   source
       | *[out]*  **dest**  destination
 
-.. c:function:: float  glm_vec_angle(vec3 v1, vec3 v2)
+.. c:function:: float  glm_vec3_angle(vec3 v1, vec3 v2)
 
     angle betwen two vector
 
@@ -210,7 +384,7 @@ Functions documentation
     Return:
       | angle as radians
 
-.. c:function:: void  glm_vec_rotate(vec3 v, float angle, vec3 axis)
+.. c:function:: void  glm_vec3_rotate(vec3 v, float angle, vec3 axis)
 
      rotate vec3 around axis by angle using Rodrigues' rotation formula
 
@@ -219,7 +393,7 @@ Functions documentation
       | *[in]*       **axis**   axis vector (will be normalized)
       | *[out]*      **angle**  angle (radians)
 
-.. c:function:: void  glm_vec_rotate_m4(mat4 m, vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_rotate_m4(mat4 m, vec3 v, vec3 dest)
 
     apply rotation matrix to vector
 
@@ -228,7 +402,16 @@ Functions documentation
       | *[in]*  **v**     vector
       | *[out]* **dest**  rotated vector
 
-.. c:function:: void  glm_vec_proj(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_rotate_m3(mat3 m, vec3 v, vec3 dest)
+
+    apply rotation matrix to vector
+
+    Parameters:
+      | *[in]*  **m**     affine matrix or rot matrix
+      | *[in]*  **v**     vector
+      | *[out]* **dest**  rotated vector
+
+.. c:function:: void  glm_vec3_proj(vec3 a, vec3 b, vec3 dest)
 
     project a vector onto b vector
 
@@ -237,7 +420,7 @@ Functions documentation
       | *[in]*  **b**     vector2
       | *[out]* **dest**  projected vector
 
-.. c:function:: void  glm_vec_center(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_center(vec3 v1, vec3 v2, vec3 dest)
 
     find center point of two vector
 
@@ -246,7 +429,18 @@ Functions documentation
       | *[in]*  **v2**    vector2
       | *[out]* **dest**  center point
 
-.. c:function:: float  glm_vec_distance(vec3 v1, vec3 v2)
+.. c:function:: float  glm_vec3_distance2(vec3 v1, vec3 v2)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **mat**   vector1
+      | *[in]*  **row1**  vector2
+
+    Returns:
+      | squared distance (distance * distance)
+
+.. c:function:: float  glm_vec3_distance(vec3 v1, vec3 v2)
 
     distance between two vectors
 
@@ -257,7 +451,7 @@ Functions documentation
     Returns:
       | distance
 
-.. c:function:: void  glm_vec_maxv(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_maxv(vec3 v1, vec3 v2, vec3 dest)
 
     max values of vectors
 
@@ -266,7 +460,7 @@ Functions documentation
       | *[in]*  **v2**    vector2
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_minv(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_minv(vec3 v1, vec3 v2, vec3 dest)
 
     min values of vectors
 
@@ -275,7 +469,7 @@ Functions documentation
       | *[in]*  **v2**    vector2
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_ortho(vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_ortho(vec3 v, vec3 dest)
 
     possible orthogonal/perpendicular vector
 
@@ -283,7 +477,7 @@ Functions documentation
       | *[in]*  **mat**   vector
       | *[out]* **dest**  orthogonal/perpendicular vector
 
-.. c:function:: void  glm_vec_clamp(vec3 v, float minVal, float maxVal)
+.. c:function:: void  glm_vec3_clamp(vec3 v, float minVal, float maxVal)
 
     constrain a value to lie between two further values
 
@@ -292,7 +486,7 @@ Functions documentation
       | *[in]*       **minVal**  minimum value
       | *[in]*       **maxVal**  maximum value
 
-.. c:function:: void  glm_vec_lerp(vec3 from, vec3 to, float t, vec3 dest)
+.. c:function:: void  glm_vec3_lerp(vec3 from, vec3 to, float t, vec3 dest)
 
     linear interpolation between two vector
 

docs/source/vec4.rst

@@ -24,17 +24,33 @@ Functions:
 1. :c:func:`glm_vec4`
 #. :c:func:`glm_vec4_copy3`
 #. :c:func:`glm_vec4_copy`
+#. :c:func:`glm_vec4_ucopy`
+#. :c:func:`glm_vec4_zero`
+#. :c:func:`glm_vec4_one`
 #. :c:func:`glm_vec4_dot`
 #. :c:func:`glm_vec4_norm2`
 #. :c:func:`glm_vec4_norm`
 #. :c:func:`glm_vec4_add`
+#. :c:func:`glm_vec4_adds`
 #. :c:func:`glm_vec4_sub`
+#. :c:func:`glm_vec4_subs`
+#. :c:func:`glm_vec4_mul`
 #. :c:func:`glm_vec4_scale`
 #. :c:func:`glm_vec4_scale_as`
+#. :c:func:`glm_vec4_div`
+#. :c:func:`glm_vec4_divs`
+#. :c:func:`glm_vec4_addadd`
+#. :c:func:`glm_vec4_subadd`
+#. :c:func:`glm_vec4_muladd`
+#. :c:func:`glm_vec4_muladds`
+#. :c:func:`glm_vec4_maxadd`
+#. :c:func:`glm_vec4_minadd`
 #. :c:func:`glm_vec4_flipsign`
-#. :c:func:`glm_vec_flipsign_to`
+#. :c:func:`glm_vec4_flipsign_to`
 #. :c:func:`glm_vec4_inv`
 #. :c:func:`glm_vec4_inv_to`
+#. :c:func:`glm_vec4_negate`
+#. :c:func:`glm_vec4_negate_to`
 #. :c:func:`glm_vec4_normalize`
 #. :c:func:`glm_vec4_normalize_to`
 #. :c:func:`glm_vec4_distance`
@@ -42,11 +58,7 @@ Functions:
 #. :c:func:`glm_vec4_minv`
 #. :c:func:`glm_vec4_clamp`
 #. :c:func:`glm_vec4_lerp`
-#. :c:func:`glm_vec4_isnan`
-#. :c:func:`glm_vec4_isinf`
-#. :c:func:`glm_vec4_isvalid`
-#. :c:func:`glm_vec4_sign`
-#. :c:func:`glm_vec4_sqrt`
+#. :c:func:`glm_vec4_cubic`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -78,6 +90,23 @@ Functions documentation
       | *[in]*  **v**     source
       | *[in]*  **dest**  destination
 
+.. c:function:: void  glm_vec4_ucopy(vec4 v, vec4 dest)
+
+    copy all members of [a] to [dest]
+
+    | alignment is not required
+
+    Parameters:
+      | *[in]*  **v**     source
+      | *[in]*  **dest**  destination
+
+.. c:function:: void  glm_vec4_zero(vec4 v)
+
+    makes all members zero
+
+    Parameters:
+      | *[in, out]*  **v**     vector
+
 .. c:function:: float  glm_vec4_dot(vec4 a, vec4 b)
 
     dot product of vec4
@@ -110,24 +139,51 @@ Functions documentation
     Parameters:
       | *[in]*  **vec**   vector
 
-.. c:function:: void  glm_vec4_add(vec4 v1, vec4 v2, vec4 dest)
+.. c:function:: void  glm_vec4_add(vec4 a, vec4 b, vec4 dest)
 
-    add v2 vector to v1 vector store result in dest
+    add a vector to b vector store result in dest
 
     Parameters:
-      | *[in]*  **v1**    vector1
-      | *[in]*  **v2**    vector2
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec4_sub(vec4 v1, vec4 v2, vec4 dest)
+.. c:function:: void  glm_vec4_adds(vec4 v, float s, vec4 dest)
 
-    subtract v2 vector from v1 vector store result in dest
+    add scalar to v vector store result in dest (d = v + vec(s))
 
     Parameters:
-      | *[in]*  **v1**    vector1
-      | *[in]*  **v2**    vector2
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
+.. c:function:: void  glm_vec4_sub(vec4 a, vec4 b, vec4 dest)
+
+    subtract b vector from a vector store result in dest (d = v1 - v2)
+
+    Parameters:
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void  glm_vec4_subs(vec4 v, float s, vec4 dest)
+
+    subtract scalar from v vector store result in dest (d = v - vec(s))
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void  glm_vec4_mul(vec4 a, vec4 b, vec4 d)
+
+    multiply two vector (component-wise multiplication)
+
+    Parameters:
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
+      | *[out]* **dest**  result = (a[0] * b[0], a[1] * b[1], a[2] * b[2], a[3] * b[3])
+
 .. c:function:: void glm_vec4_scale(vec4 v, float s, vec4 dest)
 
      multiply/scale vec4 vector with scalar: result = v * s
@@ -146,16 +202,98 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
+.. c:function:: void  glm_vec4_div(vec4 a, vec4 b, vec4 dest)
+
+    div vector with another component-wise division: d = v1 / v2
+
+    Parameters:
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
+      | *[out]* **dest**  result = (a[0] / b[0], a[1] / b[1], a[2] / b[2], a[3] / b[3])
+
+.. c:function:: void  glm_vec4_divs(vec4 v, float s, vec4 dest)
+
+    div vector with scalar: d = v / s
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  result = (a[0] / s, a[1] / s, a[2] / s, a[3] / s)
+
+.. c:function:: void  glm_vec4_addadd(vec4 a, vec4 b, vec4 dest)
+
+    | add two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a + b)
+
+.. c:function:: void  glm_vec4_subadd(vec4 a, vec4 b, vec4 dest)
+
+    | sub two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a - b)
+
+.. c:function:: void  glm_vec4_muladd(vec4 a, vec4 b, vec4 dest)
+
+    | mul two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec4_muladds(vec4 a, float s, vec4 dest)
+
+    | mul vector with scalar and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec4_maxadd(vec4 a, vec4 b, vec4 dest)
+
+    | add max of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec4_minadd(vec4 a, vec4 b, vec4 dest)
+
+    | add min of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
 .. c:function:: void  glm_vec4_flipsign(vec4 v)
 
-    flip sign of all vec4 members
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate`
 
     Parameters:
     | *[in, out]*  **v**    vector
 
 .. c:function:: void  glm_vec4_flipsign_to(vec4 v, vec4 dest)
 
-    flip sign of all vec4 members and store result in dest
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate_to`
 
     Parameters:
       | *[in]*  **v**       vector
@@ -163,19 +301,38 @@ Functions documentation
 
 .. c:function:: void  glm_vec4_inv(vec4 v)
 
-    make vector as inverse/opposite of itself
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate`
 
     Parameters:
       | *[in, out]*  **v**    vector
 
 .. c:function:: void  glm_vec4_inv_to(vec4 v, vec4 dest)
 
-    inverse/opposite vector
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate_to`
 
     Parameters:
       | *[in]*  **v**     source
       | *[out]* **dest**  destination
 
+.. c:function:: void  glm_vec4_negate(vec4 v)
+
+    negate vector components
+
+    Parameters:
+    | *[in, out]*  **v**    vector
+
+.. c:function:: void  glm_vec4_negate_to(vec4 v, vec4 dest)
+
+    negate vector components and store result in dest
+
+    Parameters:
+      | *[in]*  **v**       vector
+      | *[out]* **dest**    negated vector
+
 .. c:function:: void  glm_vec4_normalize(vec4 v)
 
     normalize vec4 and store result in same vec
@@ -240,3 +397,11 @@ Functions documentation
       | *[in]*  **to**     to value
       | *[in]*  **t**      interpolant (amount) clamped between 0 and 1
       | *[out]* **dest**   destination
+
+.. c:function:: void  glm_vec4_cubic(float s, vec4 dest)
+
+    helper to fill vec4 as [S^3, S^2, S, 1]
+
+    Parameters:
+      | *[in]*  **s**      parameter
+      | *[out]* **dest**   destination

include/cglm/affine-mat.h

@@ -16,6 +16,7 @@
 
 #include "common.h"
 #include "mat4.h"
+#include "mat3.h"
 
 #ifdef CGLM_SSE_FP
 #  include "simd/sse2/affine.h"
@@ -43,7 +44,7 @@
  */
 CGLM_INLINE
 void
-glm_mul(mat4 m1, mat4 m2, mat4 dest) {
+glm_mul(const mat4 m1, const mat4 m2, mat4 dest) {
 #ifdef __AVX__
   glm_mul_avx(m1, m2, dest);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
@@ -81,6 +82,59 @@ glm_mul(mat4 m1, mat4 m2, mat4 dest) {
 #endif
 }
 
+/*!
+ * @brief this is similar to glm_mat4_mul but specialized to affine transform
+ *
+ * Right Matrix format should be:
+ *   R  R  R  0
+ *   R  R  R  0
+ *   R  R  R  0
+ *   0  0  0  1
+ *
+ * this reduces some multiplications. It should be faster than mat4_mul.
+ * if you are not sure about matrix format then DON'T use this! use mat4_mul
+ *
+ * @param[in]   m1    affine matrix 1
+ * @param[in]   m2    affine matrix 2
+ * @param[out]  dest  result matrix
+ */
+CGLM_INLINE
+void
+glm_mul_rot(const mat4 m1, const mat4 m2, mat4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glm_mul_rot_sse2(m1, m2, dest);
+#else
+  float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2], a03 = m1[0][3],
+        a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2], a13 = m1[1][3],
+        a20 = m1[2][0], a21 = m1[2][1], a22 = m1[2][2], a23 = m1[2][3],
+        a30 = m1[3][0], a31 = m1[3][1], a32 = m1[3][2], a33 = m1[3][3],
+
+        b00 = m2[0][0], b01 = m2[0][1], b02 = m2[0][2],
+        b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2],
+        b20 = m2[2][0], b21 = m2[2][1], b22 = m2[2][2];
+
+  dest[0][0] = a00 * b00 + a10 * b01 + a20 * b02;
+  dest[0][1] = a01 * b00 + a11 * b01 + a21 * b02;
+  dest[0][2] = a02 * b00 + a12 * b01 + a22 * b02;
+  dest[0][3] = a03 * b00 + a13 * b01 + a23 * b02;
+
+  dest[1][0] = a00 * b10 + a10 * b11 + a20 * b12;
+  dest[1][1] = a01 * b10 + a11 * b11 + a21 * b12;
+  dest[1][2] = a02 * b10 + a12 * b11 + a22 * b12;
+  dest[1][3] = a03 * b10 + a13 * b11 + a23 * b12;
+
+  dest[2][0] = a00 * b20 + a10 * b21 + a20 * b22;
+  dest[2][1] = a01 * b20 + a11 * b21 + a21 * b22;
+  dest[2][2] = a02 * b20 + a12 * b21 + a22 * b22;
+  dest[2][3] = a03 * b20 + a13 * b21 + a23 * b22;
+
+  dest[3][0] = a30;
+  dest[3][1] = a31;
+  dest[3][2] = a32;
+  dest[3][3] = a33;
+#endif
+}
+
 /*!
  * @brief inverse orthonormal rotation + translation matrix (ridig-body)
  *
@@ -97,8 +151,8 @@ glm_inv_tr(mat4 mat) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_inv_tr_sse2(mat);
 #else
-  CGLM_ALIGN(16) mat3 r;
-  CGLM_ALIGN(16) vec3 t;
+  CGLM_ALIGN_MAT mat3 r;
+  CGLM_ALIGN(8)  vec3 t;
 
   /* rotate */
   glm_mat4_pick3t(mat, r);
@@ -106,8 +160,8 @@ glm_inv_tr(mat4 mat) {
 
   /* translate */
   glm_mat3_mulv(r, mat[3], t);
-  glm_vec_flipsign(t);
-  glm_vec_copy(t, mat[3]);
+  glm_vec3_negate(t);
+  glm_vec3_copy(t, mat[3]);
 #endif
 }
 

include/cglm/affine.h

@@ -16,15 +16,14 @@
    CGLM_INLINE void glm_scale_to(mat4 m, vec3 v, mat4 dest);
    CGLM_INLINE void glm_scale_make(mat4 m, vec3 v);
    CGLM_INLINE void glm_scale(mat4 m, vec3 v);
-   CGLM_INLINE void glm_scale1(mat4 m, float s);
    CGLM_INLINE void glm_scale_uni(mat4 m, float s);
    CGLM_INLINE void glm_rotate_x(mat4 m, float angle, mat4 dest);
    CGLM_INLINE void glm_rotate_y(mat4 m, float angle, mat4 dest);
    CGLM_INLINE void glm_rotate_z(mat4 m, float angle, mat4 dest);
-   CGLM_INLINE void glm_rotate_ndc_make(mat4 m, float angle, vec3 axis_ndc);
    CGLM_INLINE void glm_rotate_make(mat4 m, float angle, vec3 axis);
-   CGLM_INLINE void glm_rotate_ndc(mat4 m, float angle, vec3 axis);
    CGLM_INLINE void glm_rotate(mat4 m, float angle, vec3 axis);
+   CGLM_INLINE void glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis);
+   CGLM_INLINE void glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis);
    CGLM_INLINE void glm_decompose_scalev(mat4 m, vec3 s);
    CGLM_INLINE bool glm_uniscaled(mat4 m);
    CGLM_INLINE void glm_decompose_rs(mat4 m, mat4 r, vec3 s);
@@ -35,51 +34,15 @@
 #define cglm_affine_h
 
 #include "common.h"
-#include "vec4.h"
-#include "affine-mat.h"
 #include "util.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
+#include "affine-mat.h"
 
-/*!
- * @brief translate existing transform matrix by v vector
- *        and store result in dest
- *
- * @param[in]  m    affine transfrom
- * @param[in]  v    translate vector [x, y, z]
- * @param[out] dest translated matrix
- */
 CGLM_INLINE
 void
-glm_translate_to(mat4 m, vec3 v, mat4 dest) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
-
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest[3],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_load_ps(t[0]),
-                                                _mm_set1_ps(v[0])),
-                                     _mm_mul_ps(_mm_load_ps(t[1]),
-                                                _mm_set1_ps(v[1]))),
-                          _mm_add_ps(_mm_mul_ps(_mm_load_ps(t[2]),
-                                                _mm_set1_ps(v[2])),
-                                     _mm_load_ps(t[3]))))
-  ;
-
-  _mm_store_ps(dest[0], _mm_load_ps(m[0]));
-  _mm_store_ps(dest[1], _mm_load_ps(m[1]));
-  _mm_store_ps(dest[2], _mm_load_ps(m[2]));
-#else
-  vec4 v1, v2, v3;
-
-  glm_vec4_scale(t[0], v[0], v1);
-  glm_vec4_scale(t[1], v[1], v2);
-  glm_vec4_scale(t[2], v[2], v3);
-
-  glm_vec4_add(v1, t[3], t[3]);
-  glm_vec4_add(v2, t[3], t[3]);
-  glm_vec4_add(v3, t[3], t[3]);
-
-  glm__memcpy(float, dest, t, sizeof(mat4));
-#endif
-}
+glm_mat4_mul(const mat4 m1, const mat4 m2, mat4 dest);
 
 /*!
  * @brief translate existing transform matrix by v vector
@@ -90,16 +53,16 @@ glm_translate_to(mat4 m, vec3 v, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_translate(mat4 m, vec3 v) {
+glm_translate(mat4 m, const vec3 v) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(m[3],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_load_ps(m[0]),
+  glmm_store(m[3],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_load(m[0]),
                                               _mm_set1_ps(v[0])),
-                                     _mm_mul_ps(_mm_load_ps(m[1]),
+                                   _mm_mul_ps(glmm_load(m[1]),
                                               _mm_set1_ps(v[1]))),
-                          _mm_add_ps(_mm_mul_ps(_mm_load_ps(m[2]),
+                        _mm_add_ps(_mm_mul_ps(glmm_load(m[2]),
                                               _mm_set1_ps(v[2])),
-                                     _mm_load_ps(m[3]))))
+                                   glmm_load(m[3]))))
   ;
 #else
   vec4 v1, v2, v3;
@@ -114,6 +77,23 @@ glm_translate(mat4 m, vec3 v) {
 #endif
 }
 
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and store result in dest
+ *
+ * source matrix will remain same
+ *
+ * @param[in]  m    affine transfrom
+ * @param[in]  v    translate vector [x, y, z]
+ * @param[out] dest translated matrix
+ */
+CGLM_INLINE
+void
+glm_translate_to(const mat4 m, const vec3 v, mat4 dest) {
+  glm_mat4_copy(m, dest);
+  glm_translate(dest, v);
+}
+
 /*!
  * @brief translate existing transform matrix by x factor
  *
@@ -124,10 +104,10 @@ CGLM_INLINE
 void
 glm_translate_x(mat4 m, float x) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(m[3],
-               _mm_add_ps(_mm_mul_ps(_mm_load_ps(m[0]),
+  glmm_store(m[3],
+             _mm_add_ps(_mm_mul_ps(glmm_load(m[0]),
                                    _mm_set1_ps(x)),
-                          _mm_load_ps(m[3])))
+                        glmm_load(m[3])))
   ;
 #else
   vec4 v1;
@@ -146,10 +126,10 @@ CGLM_INLINE
 void
 glm_translate_y(mat4 m, float y) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(m[3],
-               _mm_add_ps(_mm_mul_ps(_mm_load_ps(m[1]),
+  glmm_store(m[3],
+             _mm_add_ps(_mm_mul_ps(glmm_load(m[1]),
                                    _mm_set1_ps(y)),
-                          _mm_load_ps(m[3])))
+                        glmm_load(m[3])))
   ;
 #else
   vec4 v1;
@@ -168,10 +148,10 @@ CGLM_INLINE
 void
 glm_translate_z(mat4 m, float z) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(m[3],
-               _mm_add_ps(_mm_mul_ps(_mm_load_ps(m[2]),
+  glmm_store(m[3],
+             _mm_add_ps(_mm_mul_ps(glmm_load(m[2]),
                                    _mm_set1_ps(z)),
-                          _mm_load_ps(m[3])))
+                        glmm_load(m[3])))
   ;
 #else
   vec4 v1;
@@ -188,9 +168,9 @@ glm_translate_z(mat4 m, float z) {
  */
 CGLM_INLINE
 void
-glm_translate_make(mat4 m, vec3 v) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
-  glm_translate_to(t, v, m);
+glm_translate_make(mat4 m, const vec3 v) {
+  glm_mat4_identity(m);
+  glm_vec3_copy(v, m[3]);
 }
 
 /*!
@@ -203,7 +183,7 @@ glm_translate_make(mat4 m, vec3 v) {
  */
 CGLM_INLINE
 void
-glm_scale_to(mat4 m, vec3 v, mat4 dest) {
+glm_scale_to(const mat4 m, const vec3 v, mat4 dest) {
   glm_vec4_scale(m[0], v[0], dest[0]);
   glm_vec4_scale(m[1], v[1], dest[1]);
   glm_vec4_scale(m[2], v[2], dest[2]);
@@ -219,9 +199,11 @@ glm_scale_to(mat4 m, vec3 v, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_scale_make(mat4 m, vec3 v) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
-  glm_scale_to(t, v, m);
+glm_scale_make(mat4 m, const vec3 v) {
+  glm_mat4_identity(m);
+  m[0][0] = v[0];
+  m[1][1] = v[1];
+  m[2][2] = v[2];
 }
 
 /*!
@@ -233,17 +215,7 @@ glm_scale_make(mat4 m, vec3 v) {
  */
 CGLM_INLINE
 void
-glm_scale(mat4 m, vec3 v) {
-  glm_scale_to(m, v, m);
-}
-
-/*!
- * @brief DEPRECATED! Use glm_scale_uni
- */
-CGLM_INLINE
-void
-glm_scale1(mat4 m, float s) {
-  vec3 v = { s, s, s };
+glm_scale(mat4 m, const vec3 v) {
   glm_scale_to(m, v, m);
 }
 
@@ -257,7 +229,7 @@ glm_scale1(mat4 m, float s) {
 CGLM_INLINE
 void
 glm_scale_uni(mat4 m, float s) {
-  vec3 v = { s, s, s };
+  CGLM_ALIGN(8) vec3 v = { s, s, s };
   glm_scale_to(m, v, m);
 }
 
@@ -271,20 +243,19 @@ glm_scale_uni(mat4 m, float s) {
  */
 CGLM_INLINE
 void
-glm_rotate_x(mat4 m, float angle, mat4 dest) {
-  float cosVal;
-  float sinVal;
-  mat4  t = GLM_MAT4_IDENTITY_INIT;
+glm_rotate_x(const mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
 
-  cosVal = cosf(angle);
-  sinVal = sinf(angle);
+  c = cosf(angle);
+  s = sinf(angle);
 
-  t[1][1] =  cosVal;
-  t[1][2] =  sinVal;
-  t[2][1] = -sinVal;
-  t[2][2] =  cosVal;
+  t[1][1] =  c;
+  t[1][2] =  s;
+  t[2][1] = -s;
+  t[2][2] =  c;
 
-  glm_mat4_mul(m, t, dest);
+  glm_mul_rot(m, t, dest);
 }
 
 /*!
@@ -297,20 +268,19 @@ glm_rotate_x(mat4 m, float angle, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_rotate_y(mat4 m, float angle, mat4 dest) {
-  float cosVal;
-  float sinVal;
-  mat4  t = GLM_MAT4_IDENTITY_INIT;
+glm_rotate_y(const mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
 
-  cosVal = cosf(angle);
-  sinVal = sinf(angle);
+  c = cosf(angle);
+  s = sinf(angle);
 
-  t[0][0] =  cosVal;
-  t[0][2] = -sinVal;
-  t[2][0] =  sinVal;
-  t[2][2] =  cosVal;
+  t[0][0] =  c;
+  t[0][2] = -s;
+  t[2][0] =  s;
+  t[2][2] =  c;
 
-  glm_mat4_mul(m, t, dest);
+  glm_mul_rot(m, t, dest);
 }
 
 /*!
@@ -323,62 +293,19 @@ glm_rotate_y(mat4 m, float angle, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_rotate_z(mat4 m, float angle, mat4 dest) {
-  float cosVal;
-  float sinVal;
-  mat4  t = GLM_MAT4_IDENTITY_INIT;
-
-  cosVal = cosf(angle);
-  sinVal = sinf(angle);
-
-  t[0][0] =  cosVal;
-  t[0][1] =  sinVal;
-  t[1][0] = -sinVal;
-  t[1][1] =  cosVal;
-
-  glm_mat4_mul(m, t, dest);
-}
-
-/*!
- * @brief creates NEW rotation matrix by angle and axis
- *
- * this name may change in the future. axis must be is normalized
- *
- * @param[out] m        affine transfrom
- * @param[in]  angle    angle (radians)
- * @param[in]  axis_ndc normalized axis
- */
-CGLM_INLINE
-void
-glm_rotate_ndc_make(mat4 m, float angle, vec3 axis_ndc) {
-  /* https://www.opengl.org/sdk/docs/man2/xhtml/glRotate.xml */
-
-  vec3 v, vs;
-  float c;
+glm_rotate_z(const mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
 
   c = cosf(angle);
+  s = sinf(angle);
 
-  glm_vec_scale(axis_ndc, 1.0f - c, v);
-  glm_vec_scale(axis_ndc, sinf(angle), vs);
+  t[0][0] =  c;
+  t[0][1] =  s;
+  t[1][0] = -s;
+  t[1][1] =  c;
 
-  glm_vec_scale(axis_ndc, v[0], m[0]);
-  glm_vec_scale(axis_ndc, v[1], m[1]);
-  glm_vec_scale(axis_ndc, v[2], m[2]);
-
-  m[0][0] += c;
-  m[0][1] += vs[2];
-  m[0][2] -= vs[1];
-
-  m[1][0] -= vs[2];
-  m[1][1] += c;
-  m[1][2] += vs[0];
-
-  m[2][0] += vs[1];
-  m[2][1] -= vs[0];
-  m[2][2] += c;
-
-  m[0][3] = m[1][3] = m[2][3] = m[3][0] = m[3][1] = m[3][2] = 0.0f;
-  m[3][3] = 1.0f;
+  glm_mul_rot(m, t, dest);
 }
 
 /*!
@@ -392,54 +319,30 @@ glm_rotate_ndc_make(mat4 m, float angle, vec3 axis_ndc) {
  */
 CGLM_INLINE
 void
-glm_rotate_make(mat4 m, float angle, vec3 axis) {
-  vec3 axis_ndc;
+glm_rotate_make(mat4 m, float angle, const vec3 axis) {
+  CGLM_ALIGN(8) vec3 axisn, v, vs;
+  float c;
 
-  glm_vec_normalize_to(axis, axis_ndc);
-  glm_rotate_ndc_make(m, angle, axis_ndc);
+  c = cosf(angle);
+
+  glm_vec3_normalize_to(axis, axisn);
+  glm_vec3_scale(axisn, 1.0f - c, v);
+  glm_vec3_scale(axisn, sinf(angle), vs);
+
+  glm_vec3_scale(axisn, v[0], m[0]);
+  glm_vec3_scale(axisn, v[1], m[1]);
+  glm_vec3_scale(axisn, v[2], m[2]);
+
+  m[0][0] += c;       m[1][0] -= vs[2];   m[2][0] += vs[1];
+  m[0][1] += vs[2];   m[1][1] += c;       m[2][1] -= vs[0];
+  m[0][2] -= vs[1];   m[1][2] += vs[0];   m[2][2] += c;
+
+  m[0][3] = m[1][3] = m[2][3] = m[3][0] = m[3][1] = m[3][2] = 0.0f;
+  m[3][3] = 1.0f;
 }
 
 /*!
- * @brief rotate existing transform matrix around Z axis by angle and axis
- *
- * this name may change in the future, axis must be normalized.
- *
- * @param[in, out]  m         affine transfrom
- * @param[in]       angle     angle (radians)
- * @param[in]       axis_ndc  normalized axis
- */
-CGLM_INLINE
-void
-glm_rotate_ndc(mat4 m, float angle, vec3 axis_ndc) {
-  mat4 rot, tmp;
-
-  glm_rotate_ndc_make(rot, angle, axis_ndc);
-
-  glm_vec4_scale(m[0], rot[0][0], tmp[1]);
-  glm_vec4_scale(m[1], rot[0][1], tmp[0]);
-  glm_vec4_add(tmp[1], tmp[0],    tmp[1]);
-  glm_vec4_scale(m[2], rot[0][2], tmp[0]);
-  glm_vec4_add(tmp[1], tmp[0],    tmp[1]);
-
-  glm_vec4_scale(m[0], rot[1][0], tmp[2]);
-  glm_vec4_scale(m[1], rot[1][1], tmp[0]);
-  glm_vec4_add(tmp[2], tmp[0],    tmp[2]);
-  glm_vec4_scale(m[2], rot[1][2], tmp[0]);
-  glm_vec4_add(tmp[2], tmp[0],    tmp[2]);
-
-  glm_vec4_scale(m[0], rot[2][0], tmp[3]);
-  glm_vec4_scale(m[1], rot[2][1], tmp[0]);
-  glm_vec4_add(tmp[3], tmp[0],    tmp[3]);
-  glm_vec4_scale(m[2], rot[2][2], tmp[0]);
-  glm_vec4_add(tmp[3], tmp[0],    tmp[3]);
-
-  glm_vec4_copy(tmp[1], m[0]);
-  glm_vec4_copy(tmp[2], m[1]);
-  glm_vec4_copy(tmp[3], m[2]);
-}
-
-/*!
- * @brief rotate existing transform matrix around Z axis by angle and axis
+ * @brief rotate existing transform matrix around given axis by angle
  *
  * @param[in, out]  m      affine transfrom
  * @param[in]       angle  angle (radians)
@@ -447,11 +350,56 @@ glm_rotate_ndc(mat4 m, float angle, vec3 axis_ndc) {
  */
 CGLM_INLINE
 void
-glm_rotate(mat4 m, float angle, vec3 axis) {
-  vec3 axis_ndc;
+glm_rotate(mat4 m, float angle, const vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_make(rot, angle, axis);
+  glm_mul_rot(m, rot, m);
+}
 
-  glm_vec_normalize_to(axis, axis_ndc);
-  glm_rotate_ndc(m, angle, axis_ndc);
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       pivot  rotation center
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotate_at(mat4 m, const vec3 pivot, float angle, const vec3 axis) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translate(m, pivot);
+  glm_rotate(m, angle, axis);
+  glm_translate(m, pivotInv);
+}
+
+/*!
+ * @brief creates NEW rotation matrix by angle and axis at given point
+ *
+ * this creates rotation matrix, it assumes you don't have a matrix
+ *
+ * this should work faster than glm_rotate_at because it reduces
+ * one glm_translate.
+ *
+ * @param[out] m      affine transfrom
+ * @param[in]  pivot  rotation center
+ * @param[in]  angle  angle (radians)
+ * @param[in]  axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotate_atm(mat4 m, const vec3 pivot, float angle, const vec3 axis) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translate_make(m, pivot);
+  glm_rotate(m, angle, axis);
+  glm_translate(m, pivotInv);
 }
 
 /*!
@@ -462,10 +410,10 @@ glm_rotate(mat4 m, float angle, vec3 axis) {
  */
 CGLM_INLINE
 void
-glm_decompose_scalev(mat4 m, vec3 s) {
-  s[0] = glm_vec_norm(m[0]);
-  s[1] = glm_vec_norm(m[1]);
-  s[2] = glm_vec_norm(m[2]);
+glm_decompose_scalev(const mat4 m, vec3 s) {
+  s[0] = glm_vec3_norm(m[0]);
+  s[1] = glm_vec3_norm(m[1]);
+  s[2] = glm_vec3_norm(m[2]);
 }
 
 /*!
@@ -478,11 +426,10 @@ glm_decompose_scalev(mat4 m, vec3 s) {
  */
 CGLM_INLINE
 bool
-glm_uniscaled(mat4 m) {
-  vec3 s;
+glm_uniscaled(const mat4 m) {
+  CGLM_ALIGN(8) vec3 s;
   glm_decompose_scalev(m, s);
-
-  return glm_vec_eq_all(s);
+  return glm_vec3_eq_all(s);
 }
 
 /*!
@@ -495,18 +442,18 @@ glm_uniscaled(mat4 m) {
  */
 CGLM_INLINE
 void
-glm_decompose_rs(mat4 m, mat4 r, vec3 s) {
-  vec4 t = {0.0f, 0.0f, 0.0f, 1.0f};
-  vec3 v;
+glm_decompose_rs(const mat4 m, mat4 r, vec3 s) {
+  CGLM_ALIGN(16) vec4 t = {0.0f, 0.0f, 0.0f, 1.0f};
+  CGLM_ALIGN(8)  vec3 v;
 
   glm_vec4_copy(m[0], r[0]);
   glm_vec4_copy(m[1], r[1]);
   glm_vec4_copy(m[2], r[2]);
   glm_vec4_copy(t,    r[3]);
 
-  s[0] = glm_vec_norm(m[0]);
-  s[1] = glm_vec_norm(m[1]);
-  s[2] = glm_vec_norm(m[2]);
+  s[0] = glm_vec3_norm(m[0]);
+  s[1] = glm_vec3_norm(m[1]);
+  s[2] = glm_vec3_norm(m[2]);
 
   glm_vec4_scale(r[0], 1.0f/s[0], r[0]);
   glm_vec4_scale(r[1], 1.0f/s[1], r[1]);
@@ -515,12 +462,12 @@ glm_decompose_rs(mat4 m, mat4 r, vec3 s) {
   /* Note from Apple Open Source (asume that the matrix is orthonormal):
      check for a coordinate system flip.  If the determinant
      is -1, then negate the matrix and the scaling factors. */
-  glm_vec_cross(m[0], m[1], v);
-  if (glm_vec_dot(v, m[2]) < 0.0f) {
-    glm_vec4_flipsign(r[0]);
-    glm_vec4_flipsign(r[1]);
-    glm_vec4_flipsign(r[2]);
-    glm_vec_flipsign(s);
+  glm_vec3_cross(m[0], m[1], v);
+  if (glm_vec3_dot(v, m[2]) < 0.0f) {
+    glm_vec4_negate(r[0]);
+    glm_vec4_negate(r[1]);
+    glm_vec4_negate(r[2]);
+    glm_vec3_negate(s);
   }
 }
 
@@ -535,7 +482,7 @@ glm_decompose_rs(mat4 m, mat4 r, vec3 s) {
  */
 CGLM_INLINE
 void
-glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s) {
+glm_decompose(const mat4 m, vec4 t, mat4 r, vec3 s) {
   glm_vec4_copy(m[3], t);
   glm_decompose_rs(m, r, s);
 }

include/cglm/bezier.h

@@ -0,0 +1,154 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_bezier_h
+#define cglm_bezier_h
+
+#include "common.h"
+
+#define GLM_BEZIER_MAT_INIT  {{-1.0f,  3.0f, -3.0f,  1.0f},                   \
+                              { 3.0f, -6.0f,  3.0f,  0.0f},                   \
+                              {-3.0f,  3.0f,  0.0f,  0.0f},                   \
+                              { 1.0f,  0.0f,  0.0f,  0.0f}}
+#define GLM_HERMITE_MAT_INIT {{ 2.0f, -3.0f,  0.0f,  1.0f},                   \
+                              {-2.0f,  3.0f,  0.0f,  0.0f},                   \
+                              { 1.0f, -2.0f,  1.0f,  0.0f},                   \
+                              { 1.0f, -1.0f,  0.0f,  0.0f}}
+/* for C only */
+#define GLM_BEZIER_MAT  ((mat4)GLM_BEZIER_MAT_INIT)
+#define GLM_HERMITE_MAT ((mat4)GLM_HERMITE_MAT_INIT)
+
+#define CGLM_DECASTEL_EPS   1e-9
+#define CGLM_DECASTEL_MAX   1000
+#define CGLM_DECASTEL_SMALL 1e-20
+
+/*!
+ * @brief cubic bezier interpolation
+ *
+ * Formula:
+ *  B(s) = P0*(1-s)^3 + 3*C0*s*(1-s)^2 + 3*C1*s^2*(1-s) + P1*s^3
+ *
+ * similar result using matrix:
+ *  B(s) = glm_smc(t, GLM_BEZIER_MAT, (vec4){p0, c0, c1, p1})
+ *
+ * glm_eq(glm_smc(...), glm_bezier(...)) should return TRUE
+ *
+ * @param[in]  s    parameter between 0 and 1
+ * @param[in]  p0   begin point
+ * @param[in]  c0   control point 1
+ * @param[in]  c1   control point 2
+ * @param[in]  p1   end point
+ *
+ * @return B(s)
+ */
+CGLM_INLINE
+float
+glm_bezier(float s, float p0, float c0, float c1, float p1) {
+  float x, xx, ss, xs3, a;
+
+  x   = 1.0f - s;
+  xx  = x * x;
+  ss  = s * s;
+  xs3 = (s - ss) * 3.0f;
+  a   = p0 * xx + c0 * xs3;
+
+  return a + s * (c1 * xs3 + p1 * ss - a);
+}
+
+/*!
+ * @brief cubic hermite interpolation
+ *
+ * Formula:
+ *  H(s) = P0*(2*s^3 - 3*s^2 + 1) + T0*(s^3 - 2*s^2 + s)
+ *            + P1*(-2*s^3 + 3*s^2) + T1*(s^3 - s^2)
+ *
+ * similar result using matrix:
+ *  H(s) = glm_smc(t, GLM_HERMITE_MAT, (vec4){p0, p1, c0, c1})
+ *
+ * glm_eq(glm_smc(...), glm_hermite(...)) should return TRUE
+ *
+ * @param[in]  s    parameter between 0 and 1
+ * @param[in]  p0   begin point
+ * @param[in]  t0   tangent 1
+ * @param[in]  t1   tangent 2
+ * @param[in]  p1   end point
+ *
+ * @return H(s)
+ */
+CGLM_INLINE
+float
+glm_hermite(float s, float p0, float t0, float t1, float p1) {
+  float ss, d, a, b, c, e, f;
+
+  ss = s  * s;
+  a  = ss + ss;
+  c  = a  + ss;
+  b  = a  * s;
+  d  = s  * ss;
+  f  = d  - ss;
+  e  = b  - c;
+
+  return p0 * (e + 1.0f) + t0 * (f - ss + s) + t1 * f - p1 * e;
+}
+
+/*!
+ * @brief iterative way to solve cubic equation
+ *
+ * @param[in]  prm  parameter between 0 and 1
+ * @param[in]  p0   begin point
+ * @param[in]  c0   control point 1
+ * @param[in]  c1   control point 2
+ * @param[in]  p1   end point
+ *
+ * @return parameter to use in cubic equation
+ */
+CGLM_INLINE
+float
+glm_decasteljau(float prm, float p0, float c0, float c1, float p1) {
+  float u, v, a, b, c, d, e, f;
+  int   i;
+
+  if (prm - p0 < CGLM_DECASTEL_SMALL)
+    return 0.0f;
+
+  if (p1 - prm < CGLM_DECASTEL_SMALL)
+    return 1.0f;
+
+  u  = 0.0f;
+  v  = 1.0f;
+
+  for (i = 0; i < CGLM_DECASTEL_MAX; i++) {
+    /* de Casteljau Subdivision */
+    a  = (p0 + c0) * 0.5f;
+    b  = (c0 + c1) * 0.5f;
+    c  = (c1 + p1) * 0.5f;
+    d  = (a  + b)  * 0.5f;
+    e  = (b  + c)  * 0.5f;
+    f  = (d  + e)  * 0.5f; /* this one is on the curve! */
+
+    /* The curve point is close enough to our wanted t */
+    if (fabsf(f - prm) < CGLM_DECASTEL_EPS)
+      return glm_clamp_zo((u  + v) * 0.5f);
+
+    /* dichotomy */
+    if (f < prm) {
+      p0 = f;
+      c0 = e;
+      c1 = c;
+      u  = (u  + v) * 0.5f;
+    } else {
+      c0 = a;
+      c1 = d;
+      p1 = f;
+      v  = (u  + v) * 0.5f;
+    }
+  }
+
+  return glm_clamp_zo((u  + v) * 0.5f);
+}
+
+#endif /* cglm_bezier_h */

include/cglm/box.h

@@ -11,6 +11,7 @@
 #include "common.h"
 #include "vec3.h"
 #include "vec4.h"
+#include "util.h"
 
 /*!
  * @brief apply transform to Axis-Aligned Bounding Box
@@ -21,36 +22,32 @@
  */
 CGLM_INLINE
 void
-glm_aabb_transform(vec3 box[2], mat4 m, vec3 dest[2]) {
-  vec3 v[2], xa, xb, ya, yb, za, zb, tmp;
+glm_aabb_transform(const vec3 box[2], const mat4 m, vec3 dest[2]) {
+  vec3 v[2], xa, xb, ya, yb, za, zb;
 
-  glm_vec_scale(m[0], box[0][0], xa);
-  glm_vec_scale(m[0], box[1][0], xb);
+  glm_vec3_scale(m[0], box[0][0], xa);
+  glm_vec3_scale(m[0], box[1][0], xb);
 
-  glm_vec_scale(m[1], box[0][1], ya);
-  glm_vec_scale(m[1], box[1][1], yb);
+  glm_vec3_scale(m[1], box[0][1], ya);
+  glm_vec3_scale(m[1], box[1][1], yb);
 
-  glm_vec_scale(m[2], box[0][2], za);
-  glm_vec_scale(m[2], box[1][2], zb);
+  glm_vec3_scale(m[2], box[0][2], za);
+  glm_vec3_scale(m[2], box[1][2], zb);
 
-  /* min(xa, xb) + min(ya, yb) + min(za, zb) + translation */
-  glm_vec_minv(xa, xb, v[0]);
-  glm_vec_minv(ya, yb, tmp);
-  glm_vec_add(v[0], tmp, v[0]);
-  glm_vec_minv(za, zb, tmp);
-  glm_vec_add(v[0], tmp, v[0]);
-  glm_vec_add(v[0], m[3], v[0]);
+  /* translation + min(xa, xb) + min(ya, yb) + min(za, zb) */
+  glm_vec3(m[3], v[0]);
+  glm_vec3_minadd(xa, xb, v[0]);
+  glm_vec3_minadd(ya, yb, v[0]);
+  glm_vec3_minadd(za, zb, v[0]);
 
-  /* max(xa, xb) + max(ya, yb) + max(za, zb) + translation */
-  glm_vec_maxv(xa, xb, v[1]);
-  glm_vec_maxv(ya, yb, tmp);
-  glm_vec_add(v[1], tmp, v[1]);
-  glm_vec_maxv(za, zb, tmp);
-  glm_vec_add(v[1], tmp, v[1]);
-  glm_vec_add(v[1], m[3], v[1]);
+  /* translation + max(xa, xb) + max(ya, yb) + max(za, zb) */
+  glm_vec3(m[3], v[1]);
+  glm_vec3_maxadd(xa, xb, v[1]);
+  glm_vec3_maxadd(ya, yb, v[1]);
+  glm_vec3_maxadd(za, zb, v[1]);
 
-  glm_vec_copy(v[0], dest[0]);
-  glm_vec_copy(v[1], dest[1]);
+  glm_vec3_copy(v[0], dest[0]);
+  glm_vec3_copy(v[1], dest[1]);
 }
 
 /*!
@@ -65,7 +62,7 @@ glm_aabb_transform(vec3 box[2], mat4 m, vec3 dest[2]) {
  */
 CGLM_INLINE
 void
-glm_aabb_merge(vec3 box1[2], vec3 box2[2], vec3 dest[2]) {
+glm_aabb_merge(const vec3 box1[2], const vec3 box2[2], vec3 dest[2]) {
   dest[0][0] = glm_min(box1[0][0], box2[0][0]);
   dest[0][1] = glm_min(box1[0][1], box2[0][1]);
   dest[0][2] = glm_min(box1[0][2], box2[0][2]);
@@ -88,7 +85,7 @@ glm_aabb_merge(vec3 box1[2], vec3 box2[2], vec3 dest[2]) {
  */
 CGLM_INLINE
 void
-glm_aabb_crop(vec3 box[2], vec3 cropBox[2], vec3 dest[2]) {
+glm_aabb_crop(const vec3 box[2], const vec3 cropBox[2], vec3 dest[2]) {
   dest[0][0] = glm_max(box[0][0], cropBox[0][0]);
   dest[0][1] = glm_max(box[0][1], cropBox[0][1]);
   dest[0][2] = glm_max(box[0][2], cropBox[0][2]);
@@ -112,9 +109,9 @@ glm_aabb_crop(vec3 box[2], vec3 cropBox[2], vec3 dest[2]) {
  */
 CGLM_INLINE
 void
-glm_aabb_crop_until(vec3 box[2],
-                    vec3 cropBox[2],
-                    vec3 clampBox[2],
+glm_aabb_crop_until(const vec3 box[2],
+                    const vec3 cropBox[2],
+                    const vec3 clampBox[2],
                     vec3       dest[2]) {
   glm_aabb_crop(box, cropBox, dest);
   glm_aabb_merge(clampBox, dest, dest);
@@ -136,8 +133,9 @@ glm_aabb_crop_until(vec3 box[2],
  */
 CGLM_INLINE
 bool
-glm_aabb_frustum(vec3 box[2], vec4 planes[6]) {
-  float *p, dp;
+glm_aabb_frustum(const vec3 box[2], const vec4 planes[6]) {
+  const float *p;
+  float       dp;
   int         i;
 
   for (i = 0; i < 6; i++) {
@@ -161,8 +159,8 @@ glm_aabb_frustum(vec3 box[2], vec4 planes[6]) {
 CGLM_INLINE
 void
 glm_aabb_invalidate(vec3 box[2]) {
-  glm_vec_broadcast(FLT_MAX,  box[0]);
-  glm_vec_broadcast(-FLT_MAX, box[1]);
+  glm_vec3_broadcast(FLT_MAX,  box[0]);
+  glm_vec3_broadcast(-FLT_MAX, box[1]);
 }
 
 /*!
@@ -172,9 +170,9 @@ glm_aabb_invalidate(vec3 box[2]) {
  */
 CGLM_INLINE
 bool
-glm_aabb_isvalid(vec3 box[2]) {
-  return glm_vec_max(box[0]) != FLT_MAX
-         && glm_vec_min(box[1]) != -FLT_MAX;
+glm_aabb_isvalid(const vec3 box[2]) {
+  return glm_vec3_max(box[0]) != FLT_MAX
+         && glm_vec3_min(box[1]) != -FLT_MAX;
 }
 
 /*!
@@ -184,8 +182,8 @@ glm_aabb_isvalid(vec3 box[2]) {
  */
 CGLM_INLINE
 float
-glm_aabb_size(vec3 box[2]) {
-  return glm_vec_distance(box[0], box[1]);
+glm_aabb_size(const vec3 box[2]) {
+  return glm_vec3_distance(box[0], box[1]);
 }
 
 /*!
@@ -195,8 +193,88 @@ glm_aabb_size(vec3 box[2]) {
  */
 CGLM_INLINE
 float
-glm_aabb_radius(vec3 box[2]) {
+glm_aabb_radius(const vec3 box[2]) {
   return glm_aabb_size(box) * 0.5f;
 }
 
+/*!
+ * @brief computes center point of AABB
+ *
+ * @param[in]   box  bounding box
+ * @param[out]  dest center of bounding box
+ */
+CGLM_INLINE
+void
+glm_aabb_center(const vec3 box[2], vec3 dest) {
+  glm_vec3_center(box[0], box[1], dest);
+}
+
+/*!
+ * @brief check if two AABB intersects
+ *
+ * @param[in]   box    bounding box
+ * @param[in]   other  other bounding box
+ */
+CGLM_INLINE
+bool
+glm_aabb_aabb(const vec3 box[2], const vec3 other[2]) {
+  return (box[0][0] <= other[1][0] && box[1][0] >= other[0][0])
+      && (box[0][1] <= other[1][1] && box[1][1] >= other[0][1])
+      && (box[0][2] <= other[1][2] && box[1][2] >= other[0][2]);
+}
+
+/*!
+ * @brief check if AABB intersects with sphere
+ *
+ * https://github.com/erich666/GraphicsGems/blob/master/gems/BoxSphere.c
+ * Solid Box - Solid Sphere test.
+ *
+ * @param[in]   box    solid bounding box
+ * @param[in]   s      solid sphere
+ */
+CGLM_INLINE
+bool
+glm_aabb_sphere(const vec3 box[2], const vec4 s) {
+  float dmin;
+  int   a, b, c;
+
+  a = s[0] >= box[0][0];
+  b = s[1] >= box[0][1];
+  c = s[2] >= box[0][2];
+
+  dmin  = glm_pow2(s[0] - box[a][0])
+        + glm_pow2(s[1] - box[b][1])
+        + glm_pow2(s[2] - box[c][2]);
+
+  return dmin <= glm_pow2(s[3]);
+}
+
+/*!
+ * @brief check if point is inside of AABB
+ *
+ * @param[in]   box    bounding box
+ * @param[in]   point  point
+ */
+CGLM_INLINE
+bool
+glm_aabb_point(const vec3 box[2], const vec3 point) {
+  return (point[0] >= box[0][0] && point[0] <= box[1][0])
+      && (point[1] >= box[0][1] && point[1] <= box[1][1])
+      && (point[2] >= box[0][2] && point[2] <= box[1][2]);
+}
+
+/*!
+ * @brief check if AABB contains other AABB
+ *
+ * @param[in]   box    bounding box
+ * @param[in]   other  other bounding box
+ */
+CGLM_INLINE
+bool
+glm_aabb_contains(const vec3 box[2], const vec3 other[2]) {
+  return (box[0][0] <= other[0][0] && box[1][0] >= other[1][0])
+      && (box[0][1] <= other[0][1] && box[1][1] >= other[1][1])
+      && (box[0][2] <= other[0][2] && box[1][2] >= other[1][2]);
+}
+
 #endif /* cglm_box_h */

include/cglm/call.h

@@ -25,6 +25,10 @@ extern "C" {
 #include "call/box.h"
 #include "call/io.h"
 #include "call/project.h"
+#include "call/sphere.h"
+#include "call/ease.h"
+#include "call/curve.h"
+#include "call/bezier.h"
 
 #ifdef __cplusplus
 }

include/cglm/call/affine.h

@@ -15,11 +15,15 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_translate_to(mat4 m, vec3 v, mat4 dest);
+glmc_translate_make(mat4 m, const vec3 v);
 
 CGLM_EXPORT
 void
-glmc_translate(mat4 m, vec3 v);
+glmc_translate_to(const mat4 m, const vec3 v, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_translate(mat4 m, const vec3 v);
 
 CGLM_EXPORT
 void
@@ -35,55 +39,77 @@ glmc_translate_z(mat4 m, float to);
 
 CGLM_EXPORT
 void
-glmc_scale_to(mat4 m, vec3 v, mat4 dest);
+glmc_scale_make(mat4 m, const vec3 v);
 
 CGLM_EXPORT
 void
-glmc_scale(mat4 m, vec3 v);
+glmc_scale_to(const mat4 m, const vec3 v, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_scale1(mat4 m, float s);
+glmc_scale(mat4 m, const vec3 v);
 
 CGLM_EXPORT
 void
-glmc_rotate_x(mat4 m, float rad, mat4 dest);
+glmc_scale_uni(mat4 m, float s);
 
 CGLM_EXPORT
 void
-glmc_rotate_y(mat4 m, float rad, mat4 dest);
+glmc_rotate_x(const mat4 m, float rad, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_rotate_z(mat4 m, float rad, mat4 dest);
+glmc_rotate_y(const mat4 m, float rad, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_rotate_ndc_make(mat4 m, float angle, vec3 axis_ndc);
+glmc_rotate_z(const mat4 m, float rad, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_rotate_make(mat4 m, float angle, vec3 axis);
+glmc_rotate_make(mat4 m, float angle, const vec3 axis);
 
 CGLM_EXPORT
 void
-glmc_rotate_ndc(mat4 m, float angle, vec3 axis_ndc);
+glmc_rotate(mat4 m, float angle, const vec3 axis);
 
 CGLM_EXPORT
 void
-glmc_rotate(mat4 m, float angle, vec3 axis);
+glmc_rotate_at(mat4 m, const vec3 pivot, float angle, const vec3 axis);
 
 CGLM_EXPORT
 void
-glmc_decompose_scalev(mat4 m, vec3 s);
+glmc_rotate_atm(mat4 m, const vec3 pivot, float angle, const vec3 axis);
 
 CGLM_EXPORT
 void
-glmc_decompose_rs(mat4 m, mat4 r, vec3 s);
+glmc_decompose_scalev(const mat4 m, vec3 s);
+
+CGLM_EXPORT
+bool
+glmc_uniscaled(const mat4 m);
 
 CGLM_EXPORT
 void
-glmc_decompose(mat4 m, vec4 t, mat4 r, vec3 s);
+glmc_decompose_rs(const mat4 m, mat4 r, vec3 s);
+
+CGLM_EXPORT
+void
+glmc_decompose(const mat4 m, vec4 t, mat4 r, vec3 s);
+
+/* affine-mat */
+
+CGLM_EXPORT
+void
+glmc_mul(const mat4 m1, const mat4 m2, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_mul_rot(const mat4 m1, const mat4 m2, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_inv_tr(mat4 mat);
 
 #ifdef __cplusplus
 }

include/cglm/call/bezier.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_bezier_h
+#define cglmc_bezier_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+float
+glmc_bezier(float s, float p0, float c0, float c1, float p1);
+
+CGLM_EXPORT
+float
+glmc_hermite(float s, float p0, float t0, float t1, float p1);
+
+CGLM_EXPORT
+float
+glmc_decasteljau(float prm, float p0, float c0, float c1, float p1);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_bezier_h */

include/cglm/call/box.h

@@ -15,23 +15,63 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_aabb_transform(vec3 box[2], mat4 m, vec3 dest[2]);
+glmc_aabb_transform(const vec3 box[2], const mat4 m, vec3 dest[2]);
 
 CGLM_EXPORT
 void
-glmc_aabb_merge(vec3 box1[2], vec3 box2[2], vec3 dest[2]);
+glmc_aabb_merge(const vec3 box1[2], const vec3 box2[2], vec3 dest[2]);
 
 CGLM_EXPORT
 void
-glmc_aabb_crop(vec3 box[2], vec3 cropBox[2], vec3 dest[2]);
+glmc_aabb_crop(const vec3 box[2], const vec3 cropBox[2], vec3 dest[2]);
 
 CGLM_EXPORT
 void
-glmc_aabb_crop_until(vec3 box[2],
-                     vec3 cropBox[2],
-                     vec3 clampBox[2],
+glmc_aabb_crop_until(const vec3 box[2],
+                     const vec3 cropBox[2],
+                     const vec3 clampBox[2],
                      vec3       dest[2]);
 
+CGLM_EXPORT
+bool
+glmc_aabb_frustum(const vec3 box[2], vec4 planes[6]);
+
+CGLM_EXPORT
+void
+glmc_aabb_invalidate(vec3 box[2]);
+
+CGLM_EXPORT
+bool
+glmc_aabb_isvalid(const vec3 box[2]);
+
+CGLM_EXPORT
+float
+glmc_aabb_size(const vec3 box[2]);
+
+CGLM_EXPORT
+float
+glmc_aabb_radius(const vec3 box[2]);
+
+CGLM_EXPORT
+void
+glmc_aabb_center(const vec3 box[2], vec3 dest);
+
+CGLM_EXPORT
+bool
+glmc_aabb_aabb(const vec3 box[2], const vec3 other[2]);
+
+CGLM_EXPORT
+bool
+glmc_aabb_point(const vec3 box[2], const vec3 point);
+
+CGLM_EXPORT
+bool
+glmc_aabb_contains(const vec3 box[2], const vec3 other[2]);
+
+CGLM_EXPORT
+bool
+glmc_aabb_sphere(const vec3 box[2], const vec4 s);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/cam.h

@@ -33,6 +33,26 @@ glmc_ortho(float left,
            float farVal,
            mat4  dest);
 
+CGLM_EXPORT
+void
+glmc_ortho_aabb(const vec3 box[2], mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p(const vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz(const vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s(float aspect, float size, mat4 dest);
+
 CGLM_EXPORT
 void
 glmc_perspective(float fovy,
@@ -43,15 +63,79 @@ glmc_perspective(float fovy,
 
 CGLM_EXPORT
 void
-glmc_lookat(vec3 eye, vec3 center, vec3 up, mat4 dest);
+glmc_persp_move_far(mat4 proj, float deltaFar);
 
 CGLM_EXPORT
 void
-glmc_look(vec3 eye, vec3 dir, vec3 up, mat4 dest);
+glmc_perspective_default(float aspect, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_look_anyup(vec3 eye, vec3 dir, mat4 dest);
+glmc_perspective_resize(float aspect, mat4 proj);
+
+CGLM_EXPORT
+void
+glmc_lookat(const vec3 eye, const vec3 center, const vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look(const vec3 eye, const vec3 dir, const vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_anyup(const vec3 eye, const vec3 dir, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp(const mat4 proj,
+                  float * __restrict nearVal,
+                  float * __restrict farVal,
+                  float * __restrict top,
+                  float * __restrict bottom,
+                  float * __restrict left,
+                  float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decompv(const mat4 proj, float dest[6]);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x(const mat4 proj,
+                    float * __restrict left,
+                    float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y(const mat4 proj,
+                    float * __restrict top,
+                    float * __restrict bottom);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z(const mat4 proj,
+                    float * __restrict nearVal,
+                    float * __restrict farVal);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far(const mat4 proj, float * __restrict farVal);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near(const mat4 proj, float * __restrict nearVal);
+
+CGLM_EXPORT
+float
+glmc_persp_fovy(const mat4 proj);
+
+CGLM_EXPORT
+float
+glmc_persp_aspect(const mat4 proj);
+
+CGLM_EXPORT
+void
+glmc_persp_sizes(const mat4 proj, float fovy, vec4 dest);
 
 #ifdef __cplusplus
 }

include/cglm/call/curve.h

@@ -0,0 +1,23 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_curve_h
+#define cglmc_curve_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+float
+glmc_smc(float s, const mat4 m, const vec4 c);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_curve_h */

include/cglm/call/ease.h

@@ -0,0 +1,143 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ease_h
+#define cglmc_ease_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+float
+glmc_ease_linear(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_sine_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_sine_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_sine_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quad_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quad_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quad_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_cubic_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_cubic_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_cubic_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quart_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quart_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quart_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quint_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quint_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_quint_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_exp_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_exp_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_exp_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_circ_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_circ_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_circ_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_back_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_back_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_back_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_elast_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_elast_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_elast_inout(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_bounce_out(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_bounce_in(float t);
+
+CGLM_EXPORT
+float
+glmc_ease_bounce_inout(float t);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ease_h */

include/cglm/call/euler.h

@@ -15,39 +15,39 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_euler_angles(mat4 m, vec3 dest);
+glmc_euler_angles(const mat4 m, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_euler(vec3 angles, mat4 dest);
+glmc_euler(const vec3 angles, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_xyz(vec3 angles,  mat4 dest);
+glmc_euler_xyz(const vec3 angles,  mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_zyx(vec3 angles,  mat4 dest);
+glmc_euler_zyx(const vec3 angles,  mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_zxy(vec3 angles, mat4 dest);
+glmc_euler_zxy(const vec3 angles, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_xzy(vec3 angles, mat4 dest);
+glmc_euler_xzy(const vec3 angles, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_yzx(vec3 angles, mat4 dest);
+glmc_euler_yzx(const vec3 angles, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_yxz(vec3 angles, mat4 dest);
+glmc_euler_yxz(const vec3 angles, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_by_order(vec3 angles, glm_euler_sq axis, mat4 dest);
+glmc_euler_by_order(const vec3 angles, glm_euler_sq axis, mat4 dest);
 
 #ifdef __cplusplus
 }

include/cglm/call/frustum.h

@@ -15,23 +15,23 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_frustum_planes(mat4 m, vec4 dest[6]);
+glmc_frustum_planes(const mat4 m, vec4 dest[6]);
 
 CGLM_EXPORT
 void
-glmc_frustum_corners(mat4 invMat, vec4 dest[8]);
+glmc_frustum_corners(const mat4 invMat, vec4 dest[8]);
 
 CGLM_EXPORT
 void
-glmc_frustum_center(vec4 corners[8], vec4 dest);
+glmc_frustum_center(const vec4 corners[8], vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]);
+glmc_frustum_box(const vec4 corners[8], const mat4 m, vec3 box[2]);
 
 CGLM_EXPORT
 void
-glmc_frustum_corners_at(vec4  corners[8],
+glmc_frustum_corners_at(const vec4 corners[8],
                         float      splitDist,
                         float      farDist,
                         vec4       planeCorners[4]);

include/cglm/call/io.h

@@ -15,28 +15,28 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_mat4_print(mat4   matrix,
-                FILE * __restrict ostream);
+glmc_mat4_print(const mat4   matrix,
+                FILE * const __restrict ostream);
 
 CGLM_EXPORT
 void
-glmc_mat3_print(mat3 matrix,
-                FILE * __restrict ostream);
+glmc_mat3_print(const mat3 matrix,
+                FILE * const __restrict ostream);
 
 CGLM_EXPORT
 void
-glmc_vec4_print(vec4 vec,
-                FILE * __restrict ostream);
+glmc_vec4_print(const vec4 vec,
+                FILE * const __restrict ostream);
 
 CGLM_EXPORT
 void
-glmc_vec3_print(vec3 vec,
-                FILE * __restrict ostream);
+glmc_vec3_print(const vec3 vec,
+                FILE * const __restrict ostream);
 
 CGLM_EXPORT
 void
-glmc_versor_print(versor vec,
-                  FILE * __restrict ostream);
+glmc_versor_print(const versor vec,
+                  FILE * const __restrict ostream);
 
 #ifdef __cplusplus
 }

include/cglm/call/mat3.h

@@ -18,7 +18,7 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_mat3_copy(mat3 mat, mat3 dest);
+glmc_mat3_copy(const mat3 mat, mat3 dest);
 
 CGLM_EXPORT
 void
@@ -26,11 +26,15 @@ glmc_mat3_identity(mat3 mat);
 
 CGLM_EXPORT
 void
-glmc_mat3_mul(mat3 m1, mat3 m2, mat3 dest);
+glmc_mat3_identity_array(mat3 * const __restrict mat, size_t count);
 
 CGLM_EXPORT
 void
-glmc_mat3_transpose_to(mat3 m, mat3 dest);
+glmc_mat3_mul(const mat3 m1, const mat3 m2, mat3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3_transpose_to(const mat3 m, mat3 dest);
 
 CGLM_EXPORT
 void
@@ -38,7 +42,15 @@ glmc_mat3_transpose(mat3 m);
 
 CGLM_EXPORT
 void
-glmc_mat3_mulv(mat3 m, vec3 v, vec3 dest);
+glmc_mat3_mulv(const mat3 m, const vec3 v, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_mat3_trace(const mat3 m);
+
+CGLM_EXPORT
+void
+glmc_mat3_quat(const mat3 m, versor dest);
 
 CGLM_EXPORT
 void
@@ -46,11 +58,11 @@ glmc_mat3_scale(mat3 m, float s);
 
 CGLM_EXPORT
 float
-glmc_mat3_det(mat3 mat);
+glmc_mat3_det(const mat3 mat);
 
 CGLM_EXPORT
 void
-glmc_mat3_inv(mat3 mat, mat3 dest);
+glmc_mat3_inv(const mat3 mat, mat3 dest);
 
 CGLM_EXPORT
 void
@@ -60,6 +72,10 @@ CGLM_EXPORT
 void
 glmc_mat3_swap_row(mat3 mat, int row1, int row2);
 
+CGLM_EXPORT
+float
+glmc_mat3_rmc(const vec3 r, const mat3 m, const vec3 c);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/mat4.h

@@ -19,11 +19,11 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_mat4_ucopy(mat4 mat, mat4 dest);
+glmc_mat4_ucopy(const mat4 mat, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_copy(mat4 mat, mat4 dest);
+glmc_mat4_copy(const mat4 mat, mat4 dest);
 
 CGLM_EXPORT
 void
@@ -31,35 +31,51 @@ glmc_mat4_identity(mat4 mat);
 
 CGLM_EXPORT
 void
-glmc_mat4_pick3(mat4 mat, mat3 dest);
+glmc_mat4_identity_array(mat4 * const __restrict mat, size_t count);
 
 CGLM_EXPORT
 void
-glmc_mat4_pick3t(mat4 mat, mat3 dest);
+glmc_mat4_pick3(const mat4 mat, mat3 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_ins3(mat3 mat, mat4 dest);
+glmc_mat4_pick3t(const mat4 mat, mat3 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_mul(mat4 m1, mat4 m2, mat4 dest);
+glmc_mat4_ins3(const mat3 mat, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_mulN(mat4 * __restrict matrices[], uint32_t len, mat4 dest);
+glmc_mat4_mul(const mat4 m1, const mat4 m2, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_mulv(mat4 m, vec4 v, vec4 dest);
+glmc_mat4_mulN(mat4 * const __restrict matrices[], uint32_t len, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_quat(mat4 m, versor dest);
+glmc_mat4_mulv(const mat4 m, const vec4 v, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_transpose_to(mat4 m, mat4 dest);
+glmc_mat4_mulv3(const mat4 m, const vec3 v, float last, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_mat4_trace(const mat4 m);
+
+CGLM_EXPORT
+float
+glmc_mat4_trace3(const mat4 m);
+
+CGLM_EXPORT
+void
+glmc_mat4_quat(const mat4 m, versor dest);
+
+CGLM_EXPORT
+void
+glmc_mat4_transpose_to(const mat4 m, mat4 dest);
 
 CGLM_EXPORT
 void
@@ -75,15 +91,19 @@ glmc_mat4_scale(mat4 m, float s);
 
 CGLM_EXPORT
 float
-glmc_mat4_det(mat4 mat);
+glmc_mat4_det(const mat4 mat);
 
 CGLM_EXPORT
 void
-glmc_mat4_inv(mat4 mat, mat4 dest);
+glmc_mat4_inv(const mat4 mat, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4_inv_precise(mat4 mat, mat4 dest);
+glmc_mat4_inv_precise(const mat4 mat, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4_inv_fast(const mat4 mat, mat4 dest);
 
 CGLM_EXPORT
 void
@@ -93,6 +113,10 @@ CGLM_EXPORT
 void
 glmc_mat4_swap_row(mat4 mat, int row1, int row2);
 
+CGLM_EXPORT
+float
+glmc_mat4_rmc(const vec4 r, const mat4 m, const vec4 c);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/project.h

@@ -15,15 +15,15 @@ extern "C" {
 
 CGLM_EXPORT
 void
-glmc_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest);
+glmc_unprojecti(const vec3 pos, const mat4 invMat, const vec4 vp, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest);
+glmc_unproject(const vec3 pos, const mat4 m, const vec4 vp, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_project(vec3 pos, mat4 m, vec4 vp, vec3 dest);
+glmc_project(const vec3 pos, const mat4 m, const vec4 vp, vec3 dest);
 
 #ifdef __cplusplus
 }

include/cglm/call/quat.h

@@ -17,6 +17,10 @@ CGLM_EXPORT
 void
 glmc_quat_identity(versor q);
 
+CGLM_EXPORT
+void
+glmc_quat_identity_array(versor * const __restrict q, size_t count);
+
 CGLM_EXPORT
 void
 glmc_quat_init(versor q, float x, float y, float z, float w);
@@ -27,19 +31,19 @@ glmc_quat(versor q, float angle, float x, float y, float z);
 
 CGLM_EXPORT
 void
-glmc_quatv(versor q, float angle, vec3 axis);
+glmc_quatv(versor q, float angle, const vec3 axis);
 
 CGLM_EXPORT
 void
-glmc_quat_copy(versor q, versor dest);
+glmc_quat_copy(const versor q, versor dest);
 
 CGLM_EXPORT
 float
-glmc_quat_norm(versor q);
+glmc_quat_norm(const versor q);
 
 CGLM_EXPORT
 void
-glmc_quat_normalize_to(versor q, versor dest);
+glmc_quat_normalize_to(const versor q, versor dest);
 
 CGLM_EXPORT
 void
@@ -47,95 +51,107 @@ glmc_quat_normalize(versor q);
 
 CGLM_EXPORT
 float
-glmc_quat_dot(versor p, versor q);
+glmc_quat_dot(const versor p, const versor q);
 
 CGLM_EXPORT
 void
-glmc_quat_conjugate(versor q, versor dest);
+glmc_quat_conjugate(const versor q, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_inv(versor q, versor dest);
+glmc_quat_inv(const versor q, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_add(versor p, versor q, versor dest);
+glmc_quat_add(const versor p, const versor q, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_sub(versor p, versor q, versor dest);
+glmc_quat_sub(const versor p, const versor q, versor dest);
 
 CGLM_EXPORT
 float
-glmc_quat_real(versor q);
+glmc_quat_real(const versor q);
 
 CGLM_EXPORT
 void
-glmc_quat_imag(versor q, vec3 dest);
+glmc_quat_imag(const versor q, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_imagn(versor q, vec3 dest);
+glmc_quat_imagn(const versor q, vec3 dest);
 
 CGLM_EXPORT
 float
-glmc_quat_imaglen(versor q);
+glmc_quat_imaglen(const versor q);
 
 CGLM_EXPORT
 float
-glmc_quat_angle(versor q);
+glmc_quat_angle(const versor q);
 
 CGLM_EXPORT
 void
-glmc_quat_axis(versor q, versor dest);
+glmc_quat_axis(const versor q, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_mul(versor p, versor q, versor dest);
+glmc_quat_mul(const versor p, const versor q, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_mat4(versor q, mat4 dest);
+glmc_quat_mat4(const versor q, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_mat4t(versor q, mat4 dest);
+glmc_quat_mat4t(const versor q, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_mat3(versor q, mat3 dest);
+glmc_quat_mat3(const versor q, mat3 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_mat3t(versor q, mat3 dest);
+glmc_quat_mat3t(const versor q, mat3 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_lerp(versor from, versor to, float t, versor dest);
+glmc_quat_lerp(const versor from, const versor to, float t, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_slerp(versor q, versor r, float t, versor dest);
+glmc_quat_slerp(const versor q, const versor r, float t, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_look(vec3 eye, versor ori, mat4 dest);
+glmc_quat_look(const vec3 eye, const versor ori, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest);
+glmc_quat_for(const vec3 dir, const vec3 fwd, const vec3 up, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest);
+glmc_quat_forp(const vec3 from,
+               const vec3 to,
+               const vec3 fwd,
+               const vec3 up,
+               versor     dest);
 
 CGLM_EXPORT
 void
-glmc_quat_rotatev(versor from, vec3 to, vec3 dest);
+glmc_quat_rotatev(const versor from, const vec3 to, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_rotate(mat4 m, versor q, mat4 dest);
+glmc_quat_rotate(const mat4 m, const versor q, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_quat_rotate_at(mat4 model, const versor q, const vec3 pivot);
+
+CGLM_EXPORT
+void
+glmc_quat_rotate_atm(mat4 m, const versor q, const vec3 pivot);
 
 #ifdef __cplusplus
 }

include/cglm/call/sphere.h

@@ -0,0 +1,39 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_sphere_h
+#define cglmc_sphere_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+float
+glmc_sphere_radii(const vec4 s);
+
+CGLM_EXPORT
+void
+glmc_sphere_transform(const vec4 s, const mat4 m, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_sphere_merge(const vec4 s1, const vec4 s2, vec4 dest);
+
+CGLM_EXPORT
+bool
+glmc_sphere_sphere(const vec4 s1, const vec4 s2);
+
+CGLM_EXPORT
+bool
+glmc_sphere_point(const vec4 s, const vec3 point);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_sphere_h */

include/cglm/call/vec3.h

@@ -14,173 +14,233 @@ extern "C" {
 #include "../cglm.h"
 
 /* DEPRECATED! use _copy, _ucopy versions */
-#define glmc_vec_dup(v, dest) glmc_vec_copy(v, dest)
+#define glmc_vec_dup(v, dest)          glmc_vec3_copy(v, dest)
+#define glmc_vec3_flipsign(v)          glmc_vec3_negate(v)
+#define glmc_vec3_flipsign_to(v, dest) glmc_vec3_negate_to(v, dest)
+#define glmc_vec3_inv(v)               glmc_vec3_negate(v)
+#define glmc_vec3_inv_to(v, dest)      glmc_vec3_negate_to(v, dest)
 
 CGLM_EXPORT
 void
-glmc_vec3(vec4 v4, vec3 dest);
+glmc_vec3(const vec4 v4, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_copy(vec3 a, vec3 dest);
+glmc_vec3_copy(const vec3 a, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_zero(vec3 v);
+
+CGLM_EXPORT
+void
+glmc_vec3_one(vec3 v);
 
 CGLM_EXPORT
 float
-glmc_vec_dot(vec3 a, vec3 b);
+glmc_vec3_dot(const vec3 a, const vec3 b);
 
 CGLM_EXPORT
 void
-glmc_vec_cross(vec3 a, vec3 b, vec3 d);
+glmc_vec3_cross(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_crossn(const vec3 a, const vec3 b, vec3 dest);
 
 CGLM_EXPORT
 float
-glmc_vec_norm(vec3 vec);
+glmc_vec3_norm(const vec3 v);
 
 CGLM_EXPORT
 float
-glmc_vec_norm2(vec3 vec);
+glmc_vec3_norm2(const vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_normalize_to(vec3 vec, vec3 dest);
+glmc_vec3_normalize_to(const vec3 v, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_normalize(vec3 v);
+glmc_vec3_normalize(vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_add(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_add(const vec3 a, const vec3 b, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_sub(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_adds(const vec3 v, float s, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_scale(vec3 v, float s, vec3 dest);
+glmc_vec3_sub(const vec3 a, const vec3 b, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_scale_as(vec3 v, float s, vec3 dest);
+glmc_vec3_subs(const vec3 v, float s, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_flipsign(vec3 v);
+glmc_vec3_mul(const vec3 a, const vec3 b, vec3 d);
 
 CGLM_EXPORT
 void
-glmc_vec_flipsign_to(vec3 v, vec3 dest);
+glmc_vec3_scale(const vec3 v, float s, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_inv(vec3 v);
+glmc_vec3_scale_as(const vec3 v, float s, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_inv_to(vec3 v, vec3 dest);
+glmc_vec3_div(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_divs(const vec3 a, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_addadd(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_subadd(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_muladd(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_muladds(const vec3 a, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_maxadd(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_minadd(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_negate(vec3 v);
+
+CGLM_EXPORT
+void
+glmc_vec3_negate_to(const vec3 v, vec3 dest);
 
 CGLM_EXPORT
 float
-glmc_vec_angle(vec3 v1, vec3 v2);
+glmc_vec3_angle(const vec3 a, const vec3 b);
 
 CGLM_EXPORT
 void
-glmc_vec_rotate(vec3 v, float angle, vec3 axis);
+glmc_vec3_rotate(vec3 v, float angle, const vec3 axis);
 
 CGLM_EXPORT
 void
-glmc_vec_rotate_m4(mat4 m, vec3 v, vec3 dest);
+glmc_vec3_rotate_m4(const mat4 m, const vec3 v, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_proj(vec3 a, vec3 b, vec3 dest);
+glmc_vec3_rotate_m3(const mat3 m, const vec3 v, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_center(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_proj(const vec3 a, const vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_center(const vec3 a, const vec3 b, vec3 dest);
 
 CGLM_EXPORT
 float
-glmc_vec_distance(vec3 v1, vec3 v2);
+glmc_vec3_distance2(const vec3 a, const vec3 b);
+
+CGLM_EXPORT
+float
+glmc_vec3_distance(const vec3 a, const vec3 b);
 
 CGLM_EXPORT
 void
-glmc_vec_maxv(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_maxv(const vec3 a, const vec3 b, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_minv(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_minv(const vec3 a, const vec3 b, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_clamp(vec3 v, float minVal, float maxVal);
+glmc_vec3_clamp(vec3 v, float minVal, float maxVal);
 
 CGLM_EXPORT
 void
-glmc_vec_ortho(vec3 v, vec3 dest);
+glmc_vec3_ortho(const vec3 v, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_lerp(vec3 from, vec3 to, float t, vec3 dest);
+glmc_vec3_lerp(const vec3 from, const vec3 to, float t, vec3 dest);
 
 /* ext */
 
 CGLM_EXPORT
 void
-glmc_vec_mulv(vec3 a, vec3 b, vec3 d);
+glmc_vec3_mulv(const vec3 a, const vec3 b, vec3 d);
 
 CGLM_EXPORT
 void
-glmc_vec_broadcast(float val, vec3 d);
+glmc_vec3_broadcast(float val, vec3 d);
 
 CGLM_EXPORT
 bool
-glmc_vec_eq(vec3 v, float val);
+glmc_vec3_eq(const vec3 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec_eq_eps(vec3 v, float val);
+glmc_vec3_eq_eps(const vec3 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec_eq_all(vec3 v);
+glmc_vec3_eq_all(const vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_eqv(vec3 v1, vec3 v2);
+glmc_vec3_eqv(const vec3 a, const vec3 b);
 
 CGLM_EXPORT
 bool
-glmc_vec_eqv_eps(vec3 v1, vec3 v2);
+glmc_vec3_eqv_eps(const vec3 a, const vec3 b);
 
 CGLM_EXPORT
 float
-glmc_vec_max(vec3 v);
+glmc_vec3_max(const vec3 v);
 
 CGLM_EXPORT
 float
-glmc_vec_min(vec3 v);
+glmc_vec3_min(const vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_isnan(vec3 v);
+glmc_vec3_isnan(const vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_isinf(vec3 v);
+glmc_vec3_isinf(const vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_isvalid(vec3 v);
+glmc_vec3_isvalid(const vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_sign(vec3 v, vec3 dest);
+glmc_vec3_sign(const vec3 v, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_sqrt(vec3 v, vec3 dest);
+glmc_vec3_sqrt(const vec3 v, vec3 dest);
 
 #ifdef __cplusplus
 }

include/cglm/call/vec4.h

@@ -16,34 +16,50 @@ extern "C" {
 /* DEPRECATED! use _copy, _ucopy versions */
 #define glmc_vec4_dup3(v, dest)         glmc_vec4_copy3(v, dest)
 #define glmc_vec4_dup(v, dest)          glmc_vec4_copy(v, dest)
+#define glmc_vec4_flipsign(v)           glmc_vec4_negate(v)
+#define glmc_vec4_flipsign_to(v, dest)  glmc_vec4_negate_to(v, dest)
+#define glmc_vec4_inv(v)                glmc_vec4_negate(v)
+#define glmc_vec4_inv_to(v, dest)       glmc_vec4_negate_to(v, dest)
 
 CGLM_EXPORT
 void
-glmc_vec4(vec3 v3, float last, vec4 dest);
+glmc_vec4(const vec3 v3, float last, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_copy3(vec4 a, vec3 dest);
+glmc_vec4_zero(vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_copy(vec4 v, vec4 dest);
+glmc_vec4_one(vec4 v);
+
+CGLM_EXPORT
+void
+glmc_vec4_copy3(const vec4 v, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_copy(const vec4 v, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_ucopy(const vec4 v, vec4 dest);
 
 CGLM_EXPORT
 float
-glmc_vec4_dot(vec4 a, vec4 b);
+glmc_vec4_dot(const vec4 a, const vec4 b);
 
 CGLM_EXPORT
 float
-glmc_vec4_norm(vec4 vec);
+glmc_vec4_norm(const vec4 v);
 
 CGLM_EXPORT
 float
-glmc_vec4_norm2(vec4 vec);
+glmc_vec4_norm2(const vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_normalize_to(vec4 vec, vec4 dest);
+glmc_vec4_normalize_to(const vec4 v, vec4 dest);
 
 CGLM_EXPORT
 void
@@ -51,47 +67,83 @@ glmc_vec4_normalize(vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_add(vec4 v1, vec4 v2, vec4 dest);
+glmc_vec4_add(const vec4 a, const vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_sub(vec4 v1, vec4 v2, vec4 dest);
+glmc_vec4_adds(const vec4 v, float s, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_scale(vec4 v, float s, vec4 dest);
+glmc_vec4_sub(const vec4 a, const vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_scale_as(vec3 v, float s, vec3 dest);
+glmc_vec4_subs(const vec4 v, float s, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_flipsign(vec4 v);
+glmc_vec4_mul(const vec4 a, const vec4 b, vec4 d);
 
 CGLM_EXPORT
 void
-glmc_vec4_flipsign_to(vec4 v, vec4 dest);
+glmc_vec4_scale(const vec4 v, float s, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_inv(vec4 v);
+glmc_vec4_scale_as(const vec3 v, float s, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_inv_to(vec4 v, vec4 dest);
+glmc_vec4_div(const vec4 a, const vec4 b, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_divs(const vec4 v, float s, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_addadd(const vec4 a, const vec4 b, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_subadd(const vec4 a, const vec4 b, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_muladd(const vec4 a, const vec4 b, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_muladds(const vec4 a, float s, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_maxadd(const vec4 a, const vec4 b, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_minadd(const vec4 a, const vec4 b, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_negate(vec4 v);
+
+CGLM_EXPORT
+void
+glmc_vec4_negate_to(const vec4 v, vec4 dest);
 
 CGLM_EXPORT
 float
-glmc_vec4_distance(vec4 v1, vec4 v2);
+glmc_vec4_distance(const vec4 a, const vec4 b);
 
 CGLM_EXPORT
 void
-glmc_vec4_maxv(vec4 v1, vec4 v2, vec4 dest);
+glmc_vec4_maxv(const vec4 a, const vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_minv(vec4 v1, vec4 v2, vec4 dest);
+glmc_vec4_minv(const vec4 a, const vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
@@ -99,13 +151,17 @@ glmc_vec4_clamp(vec4 v, float minVal, float maxVal);
 
 CGLM_EXPORT
 void
-glmc_vec4_lerp(vec4 from, vec4 to, float t, vec4 dest);
+glmc_vec4_lerp(const vec4 from, const vec4 to, float t, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_cubic(float s, vec4 dest);
 
 /* ext */
 
 CGLM_EXPORT
 void
-glmc_vec4_mulv(vec4 a, vec4 b, vec4 d);
+glmc_vec4_mulv(const vec4 a, const vec4 b, vec4 d);
 
 CGLM_EXPORT
 void
@@ -113,51 +169,51 @@ glmc_vec4_broadcast(float val, vec4 d);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eq(vec4 v, float val);
+glmc_vec4_eq(const vec4 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eq_eps(vec4 v, float val);
+glmc_vec4_eq_eps(const vec4 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eq_all(vec4 v);
+glmc_vec4_eq_all(const vec4 v);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eqv(vec4 v1, vec4 v2);
+glmc_vec4_eqv(const vec4 a, const vec4 b);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eqv_eps(vec4 v1, vec4 v2);
+glmc_vec4_eqv_eps(const vec4 a, const vec4 b);
 
 CGLM_EXPORT
 float
-glmc_vec4_max(vec4 v);
+glmc_vec4_max(const vec4 v);
 
 CGLM_EXPORT
 float
-glmc_vec4_min(vec4 v);
+glmc_vec4_min(const vec4 v);
 
 CGLM_EXPORT
 bool
-glmc_vec4_isnan(vec4 v);
+glmc_vec4_isnan(const vec4 v);
 
 CGLM_EXPORT
 bool
-glmc_vec4_isinf(vec4 v);
+glmc_vec4_isinf(const vec4 v);
 
 CGLM_EXPORT
 bool
-glmc_vec4_isvalid(vec4 v);
+glmc_vec4_isvalid(const vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_sign(vec4 v, vec4 dest);
+glmc_vec4_sign(const vec4 v, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_sqrt(vec4 v, vec4 dest);
+glmc_vec4_sqrt(const vec4 v, vec4 dest);
 
 #ifdef __cplusplus
 }

include/cglm/cam.h

@@ -84,7 +84,7 @@ glm_frustum(float left,
             mat4  dest) {
   float rl, tb, fn, nv;
 
-  glm__memzero(float, dest, sizeof(mat4));
+  glm_mat4_zero(dest);
 
   rl = 1.0f / (right  - left);
   tb = 1.0f / (top    - bottom);
@@ -122,7 +122,7 @@ glm_ortho(float left,
           mat4  dest) {
   float rl, tb, fn;
 
-  glm__memzero(float, dest, sizeof(mat4));
+  glm_mat4_zero(dest);
 
   rl = 1.0f / (right  - left);
   tb = 1.0f / (top    - bottom);
@@ -147,7 +147,7 @@ glm_ortho(float left,
  */
 CGLM_INLINE
 void
-glm_ortho_aabb(vec3 box[2], mat4 dest) {
+glm_ortho_aabb(const vec3 box[2], mat4 dest) {
   glm_ortho(box[0][0],  box[1][0],
             box[0][1],  box[1][1],
            -box[1][2], -box[0][2],
@@ -165,7 +165,7 @@ glm_ortho_aabb(vec3 box[2], mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_ortho_aabb_p(vec3 box[2], float padding, mat4 dest) {
+glm_ortho_aabb_p(const vec3 box[2], float padding, mat4 dest) {
   glm_ortho(box[0][0] - padding,    box[1][0] + padding,
             box[0][1] - padding,    box[1][1] + padding,
           -(box[1][2] + padding), -(box[0][2] - padding),
@@ -183,7 +183,7 @@ glm_ortho_aabb_p(vec3 box[2], float padding, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_ortho_aabb_pz(vec3 box[2], float padding, mat4 dest) {
+glm_ortho_aabb_pz(const vec3 box[2], float padding, mat4 dest) {
   glm_ortho(box[0][0],              box[1][0],
             box[0][1],              box[1][1],
           -(box[1][2] + padding), -(box[0][2] - padding),
@@ -198,26 +198,15 @@ glm_ortho_aabb_pz(vec3 box[2], float padding, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_ortho_default(float aspect,
-                  mat4  dest) {
+glm_ortho_default(float aspect, mat4 dest) {
   if (aspect >= 1.0f) {
-    glm_ortho(-1.0f * aspect,
-               1.0f * aspect,
-              -1.0f,
-               1.0f,
-              -100.0f,
-               100.0f,
-               dest);
+    glm_ortho(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
     return;
   }
 
-  glm_ortho(-1.0f,
-             1.0f,
-            -1.0f / aspect,
-             1.0f / aspect,
-            -100.0f,
-             100.0f,
-             dest);
+  aspect = 1.0f / aspect;
+
+  glm_ortho(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
 }
 
 /*!
@@ -229,9 +218,7 @@ glm_ortho_default(float aspect,
  */
 CGLM_INLINE
 void
-glm_ortho_default_s(float aspect,
-                    float size,
-                    mat4  dest) {
+glm_ortho_default_s(float aspect, float size, mat4 dest) {
   if (aspect >= 1.0f) {
     glm_ortho(-size * aspect,
                size * aspect,
@@ -270,7 +257,7 @@ glm_perspective(float fovy,
                 mat4  dest) {
   float f, fn;
 
-  glm__memzero(float, dest, sizeof(mat4));
+  glm_mat4_zero(dest);
 
   f  = 1.0f / tanf(fovy * 0.5f);
   fn = 1.0f / (nearVal - farVal);
@@ -282,6 +269,30 @@ glm_perspective(float fovy,
   dest[3][2] = 2.0f * nearVal * farVal * fn;
 }
 
+/*!
+ * @brief extend perspective projection matrix's far distance
+ *
+ * this function does not guarantee far >= near, be aware of that!
+ *
+ * @param[in, out] proj      projection matrix to extend
+ * @param[in]      deltaFar  distance from existing far (negative to shink)
+ */
+CGLM_INLINE
+void
+glm_persp_move_far(mat4 proj, float deltaFar) {
+  float fn, farVal, nearVal, p22, p32;
+
+  p22        = proj[2][2];
+  p32        = proj[3][2];
+
+  nearVal    = p32 / (p22 - 1.0f);
+  farVal     = p32 / (p22 + 1.0f) + deltaFar;
+  fn         = 1.0f / (nearVal - farVal);
+
+  proj[2][2] = (nearVal + farVal) * fn;
+  proj[3][2] = 2.0f * nearVal * farVal * fn;
+}
+
 /*!
  * @brief set up perspective projection matrix with default near/far
  *        and angle values
@@ -291,13 +302,8 @@ glm_perspective(float fovy,
  */
 CGLM_INLINE
 void
-glm_perspective_default(float aspect,
-                        mat4  dest) {
-  glm_perspective((float)CGLM_PI_4,
-                  aspect,
-                  0.01f,
-                  100.0f,
-                  dest);
+glm_perspective_default(float aspect, mat4 dest) {
+  glm_perspective(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
 }
 
 /*!
@@ -310,8 +316,7 @@ glm_perspective_default(float aspect,
  */
 CGLM_INLINE
 void
-glm_perspective_resize(float aspect,
-                       mat4  proj) {
+glm_perspective_resize(float aspect, mat4 proj) {
   if (proj[0][0] == 0.0f)
     return;
 
@@ -321,6 +326,9 @@ glm_perspective_resize(float aspect,
 /*!
  * @brief set up view matrix
  *
+ * NOTE: The UP vector must not be parallel to the line of sight from
+ *       the eye point to the reference point
+ *
  * @param[in]  eye    eye vector
  * @param[in]  center center vector
  * @param[in]  up     up vector
@@ -328,19 +336,17 @@ glm_perspective_resize(float aspect,
  */
 CGLM_INLINE
 void
-glm_lookat(vec3 eye,
-           vec3 center,
-           vec3 up,
+glm_lookat(const vec3 eye,
+           const vec3 center,
+           const vec3 up,
            mat4       dest) {
-  vec3 f, u, s;
+  CGLM_ALIGN(8) vec3 f, u, s;
 
-  glm_vec_sub(center, eye, f);
-  glm_vec_normalize(f);
+  glm_vec3_sub(center, eye, f);
+  glm_vec3_normalize(f);
 
-  glm_vec_cross(f, up, s);
-  glm_vec_normalize(s);
-
-  glm_vec_cross(s, f, u);
+  glm_vec3_crossn(f, up, s);
+  glm_vec3_cross(s, f, u);
 
   dest[0][0] = s[0];
   dest[0][1] = u[0];
@@ -351,9 +357,9 @@ glm_lookat(vec3 eye,
   dest[2][0] = s[2];
   dest[2][1] = u[2];
   dest[2][2] =-f[2];
-  dest[3][0] =-glm_vec_dot(s, eye);
-  dest[3][1] =-glm_vec_dot(u, eye);
-  dest[3][2] = glm_vec_dot(f, eye);
+  dest[3][0] =-glm_vec3_dot(s, eye);
+  dest[3][1] =-glm_vec3_dot(u, eye);
+  dest[3][2] = glm_vec3_dot(f, eye);
   dest[0][3] = dest[1][3] = dest[2][3] = 0.0f;
   dest[3][3] = 1.0f;
 }
@@ -364,6 +370,9 @@ glm_lookat(vec3 eye,
  * convenient wrapper for lookat: if you only have direction not target self
  * then this might be useful. Because you need to get target from direction.
  *
+ * NOTE: The UP vector must not be parallel to the line of sight from
+ *       the eye point to the reference point
+ *
  * @param[in]  eye    eye vector
  * @param[in]  dir    direction vector
  * @param[in]  up     up vector
@@ -371,9 +380,9 @@ glm_lookat(vec3 eye,
  */
 CGLM_INLINE
 void
-glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
-  vec3 target;
-  glm_vec_add(eye, dir, target);
+glm_look(const vec3 eye, const vec3 dir, const vec3 up, mat4 dest) {
+  CGLM_ALIGN(8) vec3 target;
+  glm_vec3_add(eye, dir, target);
   glm_lookat(eye, target, up, dest);
 }
 
@@ -389,9 +398,9 @@ glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
-  vec3 up;
-  glm_vec_ortho(dir, up);
+glm_look_anyup(const vec3 eye, const vec3 dir, mat4 dest) {
+  CGLM_ALIGN(8) vec3 up;
+  glm_vec3_ortho(dir, up);
   glm_look(eye, dir, up, dest);
 }
 
@@ -408,7 +417,7 @@ glm_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_persp_decomp(mat4 proj,
+glm_persp_decomp(const mat4 proj,
                  float * __restrict nearVal,
                  float * __restrict farVal,
                  float * __restrict top,
@@ -448,7 +457,7 @@ glm_persp_decomp(mat4 proj,
  */
 CGLM_INLINE
 void
-glm_persp_decompv(mat4 proj, float dest[6]) {
+glm_persp_decompv(const mat4 proj, float dest[6]) {
   glm_persp_decomp(proj, &dest[0], &dest[1], &dest[2],
                          &dest[3], &dest[4], &dest[5]);
 }
@@ -463,7 +472,7 @@ glm_persp_decompv(mat4 proj, float dest[6]) {
  */
 CGLM_INLINE
 void
-glm_persp_decomp_x(mat4 proj,
+glm_persp_decomp_x(const mat4 proj,
                    float * __restrict left,
                    float * __restrict right) {
   float nearVal, m20, m00;
@@ -486,7 +495,7 @@ glm_persp_decomp_x(mat4 proj,
  */
 CGLM_INLINE
 void
-glm_persp_decomp_y(mat4 proj,
+glm_persp_decomp_y(const mat4 proj,
                    float * __restrict top,
                    float * __restrict bottom) {
   float nearVal, m21, m11;
@@ -509,7 +518,7 @@ glm_persp_decomp_y(mat4 proj,
  */
 CGLM_INLINE
 void
-glm_persp_decomp_z(mat4 proj,
+glm_persp_decomp_z(const mat4 proj,
                    float * __restrict nearVal,
                    float * __restrict farVal) {
   float m32, m22;
@@ -529,7 +538,7 @@ glm_persp_decomp_z(mat4 proj,
  */
 CGLM_INLINE
 void
-glm_persp_decomp_far(mat4 proj, float * __restrict farVal) {
+glm_persp_decomp_far(const mat4 proj, float * __restrict farVal) {
   *farVal = proj[3][2] / (proj[2][2] + 1.0f);
 }
 
@@ -541,7 +550,7 @@ glm_persp_decomp_far(mat4 proj, float * __restrict farVal) {
  */
 CGLM_INLINE
 void
-glm_persp_decomp_near(mat4 proj, float * __restrict nearVal) {
+glm_persp_decomp_near(const mat4 proj, float * __restrict nearVal) {
   *nearVal = proj[3][2] / (proj[2][2] - 1.0f);
 }
 
@@ -555,7 +564,7 @@ glm_persp_decomp_near(mat4 proj, float * __restrict nearVal) {
  */
 CGLM_INLINE
 float
-glm_persp_fovy(mat4 proj) {
+glm_persp_fovy(const mat4 proj) {
   return 2.0f * atanf(1.0f / proj[1][1]);
 }
 
@@ -566,7 +575,7 @@ glm_persp_fovy(mat4 proj) {
  */
 CGLM_INLINE
 float
-glm_persp_aspect(mat4 proj) {
+glm_persp_aspect(const mat4 proj) {
   return proj[1][1] / proj[0][0];
 }
 
@@ -579,7 +588,7 @@ glm_persp_aspect(mat4 proj) {
  */
 CGLM_INLINE
 void
-glm_persp_sizes(mat4 proj, float fovy, vec4 dest) {
+glm_persp_sizes(const mat4 proj, float fovy, vec4 dest) {
   float t, a, nearVal, farVal;
 
   t = 2.0f * tanf(fovy * 0.5f);

include/cglm/cglm.h

@@ -24,5 +24,9 @@
 #include "util.h"
 #include "io.h"
 #include "project.h"
+#include "sphere.h"
+#include "ease.h"
+#include "curve.h"
+#include "bezier.h"
 
 #endif /* cglm_h */

include/cglm/color.h

@@ -18,7 +18,7 @@
  */
 CGLM_INLINE
 float
-glm_luminance(vec3 rgb) {
+glm_luminance(const vec3 rgb) {
   vec3 l = {0.212671f, 0.715160f, 0.072169f};
   return glm_dot(rgb, l);
 }

include/cglm/common.h

@@ -11,10 +11,12 @@
 #define _USE_MATH_DEFINES /* for windows */
 
 #include <stdint.h>
+#include <stddef.h>
 #include <math.h>
 #include <float.h>
+#include <stdbool.h>
 
-#if defined(_WIN32)
+#if defined(_MSC_VER)
 #  ifdef CGLM_DLL
 #    define CGLM_EXPORT __declspec(dllexport)
 #  else
@@ -26,34 +28,6 @@
 #  define CGLM_INLINE static inline __attribute((always_inline))
 #endif
 
-#define glm__memcpy(type, dest, src, size)                                    \
-  do {                                                                        \
-    type *srci;                                                               \
-    type *srci_end;                                                           \
-    type *desti;                                                              \
-                                                                              \
-    srci     = (type *)src;                                                   \
-    srci_end = (type *)((char *)srci + size);                                 \
-    desti    = (type *)dest;                                                  \
-                                                                              \
-    while (srci != srci_end)                                                  \
-      *desti++ = *srci++;                                                     \
-  } while (0)
-
-#define glm__memset(type, dest, size, val)                                    \
-  do {                                                                        \
-    type *desti;                                                              \
-    type *desti_end;                                                          \
-                                                                              \
-    desti     = (type *)dest;                                                 \
-    desti_end = (type *)((char *)desti + size);                               \
-                                                                              \
-    while (desti != desti_end)                                                \
-      *desti++ = val;                                                         \
-  } while (0)
-
-#define glm__memzero(type, dest, size) glm__memset(type, dest, size, 0)
-
 #include "types.h"
 #include "simd/intrin.h"
 

include/cglm/curve.h

@@ -0,0 +1,40 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_curve_h
+#define cglm_curve_h
+
+#include "common.h"
+#include "vec4.h"
+#include "mat4.h"
+
+/*!
+ * @brief helper function to calculate S*M*C multiplication for curves
+ *
+ * This function does not encourage you to use SMC,
+ * instead it is a helper if you use SMC.
+ *
+ * if you want to specify S as vector then use more generic glm_mat4_rmc() func.
+ *
+ * Example usage:
+ *  B(s) = glm_smc(s, GLM_BEZIER_MAT, (vec4){p0, c0, c1, p1})
+ *
+ * @param[in]  s  parameter between 0 and 1 (this will be [s3, s2, s, 1])
+ * @param[in]  m  basis matrix
+ * @param[in]  c  position/control vector
+ *
+ * @return B(s)
+ */
+CGLM_INLINE
+float
+glm_smc(float s, const mat4 m, const vec4 c) {
+  vec4 vs;
+  glm_vec4_cubic(s, vs);
+  return glm_mat4_rmc(vs, m, c);
+}
+
+#endif /* cglm_curve_h */

include/cglm/ease.h

@@ -0,0 +1,317 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_ease_h
+#define cglm_ease_h
+
+#include "common.h"
+
+CGLM_INLINE
+float
+glm_ease_linear(float t) {
+  return t;
+}
+
+CGLM_INLINE
+float
+glm_ease_sine_in(float t) {
+  return sinf((t - 1.0f) * GLM_PI_2f) + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_sine_out(float t) {
+  return sinf(t * GLM_PI_2f);
+}
+
+CGLM_INLINE
+float
+glm_ease_sine_inout(float t) {
+  return 0.5f * (1.0f - cosf(t * GLM_PIf));
+}
+
+CGLM_INLINE
+float
+glm_ease_quad_in(float t) {
+  return t * t;
+}
+
+CGLM_INLINE
+float
+glm_ease_quad_out(float t) {
+  return -(t * (t - 2.0f));
+}
+
+CGLM_INLINE
+float
+glm_ease_quad_inout(float t) {
+  float tt;
+
+  tt = t * t;
+  if (t < 0.5f)
+    return 2.0f * tt;
+
+  return (-2.0f * tt) + (4.0f * t) - 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_cubic_in(float t) {
+  return t * t * t;
+}
+
+CGLM_INLINE
+float
+glm_ease_cubic_out(float t) {
+  float f;
+  f = t - 1.0f;
+  return f * f * f + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_cubic_inout(float t) {
+  float f;
+
+  if (t < 0.5f)
+    return 4.0f * t * t * t;
+
+  f = 2.0f * t - 2.0f;
+
+  return 0.5f * f * f * f + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_quart_in(float t) {
+  float f;
+  f = t * t;
+  return f * f;
+}
+
+CGLM_INLINE
+float
+glm_ease_quart_out(float t) {
+  float f;
+
+  f = t - 1.0f;
+
+  return f * f * f * (1.0f - t) + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_quart_inout(float t) {
+  float f, g;
+
+  if (t < 0.5f) {
+    f = t * t;
+    return 8.0f * f * f;
+  }
+
+  f = t - 1.0f;
+  g = f * f;
+
+  return -8.0f * g * g + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_quint_in(float t) {
+  float f;
+  f = t * t;
+  return f * f * t;
+}
+
+CGLM_INLINE
+float
+glm_ease_quint_out(float t) {
+  float f, g;
+
+  f = t - 1.0f;
+  g = f * f;
+
+  return g * g * f + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_quint_inout(float t) {
+  float f, g;
+
+  if (t < 0.5f) {
+    f = t * t;
+    return 16.0f * f * f * t;
+  }
+
+  f = 2.0f * t - 2.0f;
+  g = f * f;
+
+  return 0.5f * g * g * f + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_exp_in(float t) {
+  if (t == 0.0f)
+    return t;
+
+  return powf(2.0f,  10.0f * (t - 1.0f));
+}
+
+CGLM_INLINE
+float
+glm_ease_exp_out(float t) {
+  if (t == 1.0f)
+    return t;
+
+  return 1.0f - powf(2.0f, -10.0f * t);
+}
+
+CGLM_INLINE
+float
+glm_ease_exp_inout(float t) {
+  if (t == 0.0f || t == 1.0f)
+    return t;
+
+  if (t < 0.5f)
+    return 0.5f * powf(2.0f, (20.0f * t) - 10.0f);
+
+  return -0.5f * powf(2.0f, (-20.0f * t) + 10.0f) + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_circ_in(float t) {
+  return 1.0f - sqrtf(1.0f - (t * t));
+}
+
+CGLM_INLINE
+float
+glm_ease_circ_out(float t) {
+  return sqrtf((2.0f - t) * t);
+}
+
+CGLM_INLINE
+float
+glm_ease_circ_inout(float t) {
+  if (t < 0.5f)
+    return 0.5f * (1.0f - sqrtf(1.0f - 4.0f * (t * t)));
+
+  return 0.5f * (sqrtf(-((2.0f * t) - 3.0f) * ((2.0f * t) - 1.0f)) + 1.0f);
+}
+
+CGLM_INLINE
+float
+glm_ease_back_in(float t) {
+  float o, z;
+
+  o = 1.70158f;
+  z = ((o + 1.0f) * t) - o;
+
+  return t * t * z;
+}
+
+CGLM_INLINE
+float
+glm_ease_back_out(float t) {
+  float o, z, n;
+
+  o = 1.70158f;
+  n = t - 1.0f;
+  z = (o + 1.0f) * n + o;
+
+  return n * n * z + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_back_inout(float t) {
+  float o, z, n, m, s, x;
+
+  o = 1.70158f;
+  s = o * 1.525f;
+  x = 0.5;
+  n = t / 0.5f;
+
+  if (n < 1.0f) {
+    z = (s + 1) * n - s;
+    m = n * n * z;
+    return x * m;
+  }
+
+  n -= 2.0f;
+  z  = (s + 1.0f) * n + s;
+  m  = (n * n * z) + 2;
+
+  return x * m;
+}
+
+CGLM_INLINE
+float
+glm_ease_elast_in(float t) {
+  return sinf(13.0f * GLM_PI_2f * t) * powf(2.0f, 10.0f * (t - 1.0f));
+}
+
+CGLM_INLINE
+float
+glm_ease_elast_out(float t) {
+  return sinf(-13.0f * GLM_PI_2f * (t + 1.0f)) * powf(2.0f, -10.0f * t) + 1.0f;
+}
+
+CGLM_INLINE
+float
+glm_ease_elast_inout(float t) {
+  float a;
+
+  a = 2.0f * t;
+
+  if (t < 0.5f)
+    return 0.5f * sinf(13.0f * GLM_PI_2f * a)
+                * powf(2.0f, 10.0f * (a - 1.0f));
+
+  return 0.5f * (sinf(-13.0f * GLM_PI_2f * a)
+                 * powf(2.0f, -10.0f * (a - 1.0f)) + 2.0f);
+}
+
+CGLM_INLINE
+float
+glm_ease_bounce_out(float t) {
+  float tt;
+
+  tt = t * t;
+
+  if (t < (4.0f / 11.0f))
+    return (121.0f * tt) / 16.0f;
+
+  if (t < 8.0f / 11.0f)
+    return ((363.0f / 40.0f) * tt) - ((99.0f / 10.0f) * t) + (17.0f / 5.0f);
+
+  if (t < (9.0f / 10.0f))
+    return (4356.0f / 361.0f) * tt
+            - (35442.0f / 1805.0f) * t
+            + (16061.0f / 1805.0f);
+
+  return ((54.0f / 5.0f) * tt) - ((513.0f / 25.0f) * t) + (268.0f / 25.0f);
+}
+
+CGLM_INLINE
+float
+glm_ease_bounce_in(float t) {
+  return 1.0f - glm_ease_bounce_out(1.0f - t);
+}
+
+CGLM_INLINE
+float
+glm_ease_bounce_inout(float t) {
+  if (t < 0.5f)
+    return 0.5f * (1.0f - glm_ease_bounce_out(t * 2.0f));
+
+  return 0.5f * glm_ease_bounce_out(t * 2.0f - 1.0f) + 0.5f;
+}
+
+#endif /* cglm_ease_h */

include/cglm/euler.h

@@ -57,7 +57,7 @@ typedef enum glm_euler_sq {
 
 CGLM_INLINE
 glm_euler_sq
-glm_euler_order(int ord[3]) {
+glm_euler_order(const int ord[3]) {
   return (glm_euler_sq)(ord[0] << 0 | ord[1] << 2 | ord[2] << 4);
 }
 
@@ -69,7 +69,7 @@ glm_euler_order(int ord[3]) {
  */
 CGLM_INLINE
 void
-glm_euler_angles(mat4 m, vec3 dest) {
+glm_euler_angles(const mat4 m, vec3 dest) {
   float m00, m01, m10, m11, m20, m21, m22;
   float thetaX, thetaY, thetaZ;
 
@@ -84,12 +84,12 @@ glm_euler_angles(mat4 m, vec3 dest) {
       thetaZ = atan2f(-m10, m00);
     } else { /* m20 == -1 */
       /* Not a unique solution */
-      thetaY = -CGLM_PI_2;
+      thetaY = -GLM_PI_2f;
       thetaX = -atan2f(m01, m11);
       thetaZ =  0.0f;
     }
   } else { /* m20 == +1 */
-    thetaY = CGLM_PI_2;
+    thetaY = GLM_PI_2f;
     thetaX = atan2f(m01, m11);
     thetaZ = 0.0f;
   }
@@ -107,7 +107,7 @@ glm_euler_angles(mat4 m, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_xyz(vec3 angles, mat4 dest) {
+glm_euler_xyz(const vec3 angles, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz, czsx, cxcz, sysz;
 
@@ -145,7 +145,7 @@ glm_euler_xyz(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler(vec3 angles, mat4 dest) {
+glm_euler(const vec3 angles, mat4 dest) {
   glm_euler_xyz(angles, dest);
 }
 
@@ -157,7 +157,7 @@ glm_euler(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_xzy(vec3 angles, mat4 dest) {
+glm_euler_xzy(const vec3 angles, mat4 dest) {
   float cx, cy, cz,
   sx, sy, sz, sxsy, cysx, cxsy, cxcy;
 
@@ -197,7 +197,7 @@ glm_euler_xzy(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_yxz(vec3 angles, mat4 dest) {
+glm_euler_yxz(const vec3 angles, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz, cycz, sysz, czsy, cysz;
 
@@ -236,7 +236,7 @@ glm_euler_yxz(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_yzx(vec3 angles, mat4 dest) {
+glm_euler_yzx(const vec3 angles, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz, sxsy, cxcy, cysx, cxsy;
 
@@ -275,7 +275,7 @@ glm_euler_yzx(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_zxy(vec3 angles, mat4 dest) {
+glm_euler_zxy(const vec3 angles, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz, cycz, sxsy, cysz;
 
@@ -313,7 +313,7 @@ glm_euler_zxy(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_zyx(vec3 angles, mat4 dest) {
+glm_euler_zyx(const vec3 angles, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz, czsx, cxcz, sysz;
 
@@ -352,7 +352,7 @@ glm_euler_zyx(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_by_order(vec3 angles, glm_euler_sq ord, mat4 dest) {
+glm_euler_by_order(const vec3 angles, glm_euler_sq ord, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz;
 

include/cglm/frustum.h

@@ -10,6 +10,9 @@
 
 #include "common.h"
 #include "plane.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
 
 #define GLM_LBN 0 /* left  bottom near */
 #define GLM_LTN 1 /* left  top    near */
@@ -66,7 +69,7 @@
  */
 CGLM_INLINE
 void
-glm_frustum_planes(mat4 m, vec4 dest[6]) {
+glm_frustum_planes(const mat4 m, vec4 dest[6]) {
   mat4 t;
 
   glm_mat4_transpose_to(m, t);
@@ -103,7 +106,7 @@ glm_frustum_planes(mat4 m, vec4 dest[6]) {
  *
  * Find center coordinates:
  *   for (j = 0; j < 4; j++) {
- *     glm_vec_center(corners[i], corners[i + 4], centerCorners[i]);
+ *     glm_vec3_center(corners[i], corners[i + 4], centerCorners[i]);
  *   }
  *
  * @param[in]  invMat matrix (see brief)
@@ -111,7 +114,7 @@ glm_frustum_planes(mat4 m, vec4 dest[6]) {
  */
 CGLM_INLINE
 void
-glm_frustum_corners(mat4 invMat, vec4 dest[8]) {
+glm_frustum_corners(const mat4 invMat, vec4 dest[8]) {
   vec4 c[8];
 
   /* indexOf(nearCoord) = indexOf(farCoord) + 4 */
@@ -154,7 +157,7 @@ glm_frustum_corners(mat4 invMat, vec4 dest[8]) {
  */
 CGLM_INLINE
 void
-glm_frustum_center(vec4 corners[8], vec4 dest) {
+glm_frustum_center(const vec4 corners[8], vec4 dest) {
   vec4 center;
 
   glm_vec4_copy(corners[0], center);
@@ -179,13 +182,13 @@ glm_frustum_center(vec4 corners[8], vec4 dest) {
  */
 CGLM_INLINE
 void
-glm_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]) {
+glm_frustum_box(const vec4 corners[8], const mat4 m, vec3 box[2]) {
   vec4 v;
   vec3 min, max;
   int  i;
 
-  glm_vec_broadcast(FLT_MAX, min);
-  glm_vec_broadcast(-FLT_MAX, max);
+  glm_vec3_broadcast(FLT_MAX, min);
+  glm_vec3_broadcast(-FLT_MAX, max);
 
   for (i = 0; i < 8; i++) {
     glm_mat4_mulv(m, corners[i], v);
@@ -199,8 +202,8 @@ glm_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]) {
     max[2] = glm_max(max[2], v[2]);
   }
 
-  glm_vec_copy(min, box[0]);
-  glm_vec_copy(max, box[1]);
+  glm_vec3_copy(min, box[0]);
+  glm_vec3_copy(max, box[1]);
 }
 
 /*!
@@ -217,7 +220,7 @@ glm_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]) {
  */
 CGLM_INLINE
 void
-glm_frustum_corners_at(vec4  corners[8],
+glm_frustum_corners_at(const vec4 corners[8],
                        float      splitDist,
                        float      farDist,
                        vec4       planeCorners[4]) {
@@ -225,7 +228,7 @@ glm_frustum_corners_at(vec4  corners[8],
   float dist, sc;
 
   /* because distance and scale is same for all */
-  dist = glm_vec_distance(corners[GLM_RTF], corners[GLM_RTN]);
+  dist = glm_vec3_distance(corners[GLM_RTF], corners[GLM_RTN]);
   sc   = dist * (splitDist / farDist);
 
   /* left bottom */

include/cglm/io.h

@@ -25,8 +25,8 @@
 
 CGLM_INLINE
 void
-glm_mat4_print(mat4   matrix,
-               FILE * __restrict ostream) {
+glm_mat4_print(const mat4              matrix,
+               FILE * const __restrict ostream) {
   int i;
   int j;
 
@@ -55,8 +55,8 @@ glm_mat4_print(mat4   matrix,
 
 CGLM_INLINE
 void
-glm_mat3_print(mat3 matrix,
-               FILE * __restrict ostream) {
+glm_mat3_print(const mat3              matrix,
+               FILE * const __restrict ostream) {
   int i;
   int j;
 
@@ -85,8 +85,8 @@ glm_mat3_print(mat3 matrix,
 
 CGLM_INLINE
 void
-glm_vec4_print(vec4 vec,
-               FILE * __restrict ostream) {
+glm_vec4_print(const vec4              vec,
+               FILE * const __restrict ostream) {
   int i;
 
 #define m 4
@@ -107,8 +107,8 @@ glm_vec4_print(vec4 vec,
 
 CGLM_INLINE
 void
-glm_vec3_print(vec3 vec,
-               FILE * __restrict ostream) {
+glm_vec3_print(const vec3              vec,
+               FILE * const __restrict ostream) {
   int i;
 
 #define m 3
@@ -129,8 +129,8 @@ glm_vec3_print(vec3 vec,
 
 CGLM_INLINE
 void
-glm_ivec3_print(ivec3 vec,
-                FILE * __restrict ostream) {
+glm_ivec3_print(const ivec3             vec,
+                FILE * const __restrict ostream) {
   int i;
 
 #define m 3
@@ -151,8 +151,8 @@ glm_ivec3_print(ivec3 vec,
 
 CGLM_INLINE
 void
-glm_versor_print(versor vec,
-                 FILE * __restrict ostream) {
+glm_versor_print(const versor            vec,
+                 FILE * const __restrict ostream) {
   int i;
 
 #define m 4
@@ -173,9 +173,9 @@ glm_versor_print(versor vec,
 
 CGLM_INLINE
 void
-glm_aabb_print(vec3                    bbox[2],
+glm_aabb_print(const vec3              bbox[2],
                const char * __restrict tag,
-               FILE       * __restrict ostream) {
+               FILE * const __restrict ostream) {
   int i, j;
 
 #define m 3

include/cglm/mat3.h

@@ -16,21 +16,27 @@
  Functions:
    CGLM_INLINE void  glm_mat3_copy(mat3 mat, mat3 dest);
    CGLM_INLINE void  glm_mat3_identity(mat3 mat);
+   CGLM_INLINE void  glm_mat3_identity_array(mat3 * restrict mat, size_t count);
+   CGLM_INLINE void  glm_mat3_zero(mat3 mat);
    CGLM_INLINE void  glm_mat3_mul(mat3 m1, mat3 m2, mat3 dest);
    CGLM_INLINE void  glm_mat3_transpose_to(mat3 m, mat3 dest);
    CGLM_INLINE void  glm_mat3_transpose(mat3 m);
    CGLM_INLINE void  glm_mat3_mulv(mat3 m, vec3 v, vec3 dest);
+   CGLM_INLINE float glm_mat3_trace(mat3 m);
+   CGLM_INLINE void  glm_mat3_quat(mat3 m, versor dest);
    CGLM_INLINE void  glm_mat3_scale(mat3 m, float s);
    CGLM_INLINE float glm_mat3_det(mat3 mat);
    CGLM_INLINE void  glm_mat3_inv(mat3 mat, mat3 dest);
    CGLM_INLINE void  glm_mat3_swap_col(mat3 mat, int col1, int col2);
    CGLM_INLINE void  glm_mat3_swap_row(mat3 mat, int row1, int row2);
+   CGLM_INLINE float glm_mat3_rmc(vec3 r, mat3 m, vec3 c);
  */
 
 #ifndef cglm_mat3_h
 #define cglm_mat3_h
 
 #include "common.h"
+#include "vec3.h"
 
 #ifdef CGLM_SSE_FP
 #  include "simd/sse2/mat3.h"
@@ -59,8 +65,18 @@
  */
 CGLM_INLINE
 void
-glm_mat3_copy(mat3 mat, mat3 dest) {
-  glm__memcpy(float, dest, mat, sizeof(mat3));
+glm_mat3_copy(const mat3 mat, mat3 dest) {
+  dest[0][0] = mat[0][0];
+  dest[0][1] = mat[0][1];
+  dest[0][2] = mat[0][2];
+
+  dest[1][0] = mat[1][0];
+  dest[1][1] = mat[1][1];
+  dest[1][2] = mat[1][2];
+
+  dest[2][0] = mat[2][0];
+  dest[2][1] = mat[2][1];
+  dest[2][2] = mat[2][2];
 }
 
 /*!
@@ -80,7 +96,38 @@ glm_mat3_copy(mat3 mat, mat3 dest) {
 CGLM_INLINE
 void
 glm_mat3_identity(mat3 mat) {
-  mat3 t = GLM_MAT3_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat3 t = GLM_MAT3_IDENTITY_INIT;
+  glm_mat3_copy(t, mat);
+}
+
+/*!
+ * @brief make given matrix array's each element identity matrix
+ *
+ * @param[in, out]  mat   matrix array (must be aligned (16/32)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of matrices
+ */
+CGLM_INLINE
+void
+glm_mat3_identity_array(mat3 * const __restrict mat, size_t count) {
+  CGLM_ALIGN_MAT mat3 t = GLM_MAT3_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_mat3_copy(t, mat[i]);
+  }
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat3_zero(mat3 mat) {
+  CGLM_ALIGN_MAT mat3 t = GLM_MAT3_ZERO_INIT;
   glm_mat3_copy(t, mat);
 }
 
@@ -100,7 +147,7 @@ glm_mat3_identity(mat3 mat) {
  */
 CGLM_INLINE
 void
-glm_mat3_mul(mat3 m1, mat3 m2, mat3 dest) {
+glm_mat3_mul(const mat3 m1, const mat3 m2, mat3 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat3_mul_sse2(m1, m2, dest);
 #else
@@ -134,7 +181,7 @@ glm_mat3_mul(mat3 m1, mat3 m2, mat3 dest) {
  */
 CGLM_INLINE
 void
-glm_mat3_transpose_to(mat3 m, mat3 dest) {
+glm_mat3_transpose_to(const mat3 m, mat3 dest) {
   dest[0][0] = m[0][0];
   dest[0][1] = m[1][0];
   dest[0][2] = m[2][0];
@@ -154,7 +201,7 @@ glm_mat3_transpose_to(mat3 m, mat3 dest) {
 CGLM_INLINE
 void
 glm_mat3_transpose(mat3 m) {
-  mat3 tmp;
+  CGLM_ALIGN_MAT mat3 tmp;
 
   tmp[0][1] = m[1][0];
   tmp[0][2] = m[2][0];
@@ -180,22 +227,34 @@ glm_mat3_transpose(mat3 m) {
  */
 CGLM_INLINE
 void
-glm_mat3_mulv(mat3 m, vec3 v, vec3 dest) {
+glm_mat3_mulv(const mat3 m, const vec3 v, vec3 dest) {
   dest[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2];
   dest[1] = m[0][1] * v[0] + m[1][1] * v[1] + m[2][1] * v[2];
   dest[2] = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2];
 }
 
+/*!
+ * @brief trace of matrix
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat3_trace(const mat3 m) {
+  return m[0][0] + m[1][1] + m[2][2];
+}
 
 /*!
- * @brief convert mat4's rotation part to quaternion
+ * @brief convert mat3 to quaternion
  *
- * @param[in]  m    left matrix
+ * @param[in]  m    rotation matrix
  * @param[out] dest destination quaternion
  */
 CGLM_INLINE
 void
-glm_mat3_quat(mat3 m, versor dest) {
+glm_mat3_quat(const mat3 m, versor dest) {
   float trace, r, rinv;
 
   /* it seems using like m12 instead of m[1][2] causes extra instructions */
@@ -261,7 +320,7 @@ glm_mat3_scale(mat3 m, float s) {
  */
 CGLM_INLINE
 float
-glm_mat3_det(mat3 mat) {
+glm_mat3_det(const mat3 mat) {
   float a = mat[0][0], b = mat[0][1], c = mat[0][2],
         d = mat[1][0], e = mat[1][1], f = mat[1][2],
         g = mat[2][0], h = mat[2][1], i = mat[2][2];
@@ -277,7 +336,7 @@ glm_mat3_det(mat3 mat) {
  */
 CGLM_INLINE
 void
-glm_mat3_inv(mat3 mat, mat3 dest) {
+glm_mat3_inv(const mat3 mat, mat3 dest) {
   float det;
   float a = mat[0][0], b = mat[0][1], c = mat[0][2],
         d = mat[1][0], e = mat[1][1], f = mat[1][2],
@@ -309,9 +368,9 @@ CGLM_INLINE
 void
 glm_mat3_swap_col(mat3 mat, int col1, int col2) {
   vec3 tmp;
-  glm_vec_copy(mat[col1], tmp);
-  glm_vec_copy(mat[col2], mat[col1]);
-  glm_vec_copy(tmp, mat[col2]);
+  glm_vec3_copy(mat[col1], tmp);
+  glm_vec3_copy(mat[col2], mat[col1]);
+  glm_vec3_copy(tmp, mat[col2]);
 }
 
 /*!
@@ -338,4 +397,26 @@ glm_mat3_swap_row(mat3 mat, int row1, int row2) {
   mat[2][row2] = tmp[2];
 }
 
+/*!
+ * @brief helper for  R (row vector) * M (matrix) * C (column vector)
+ *
+ * rmc stands for Row * Matrix * Column
+ *
+ * the result is scalar because R * M = Matrix1x3 (row vector),
+ * then Matrix1x3 * Vec3 (column vector) = Matrix1x1 (Scalar)
+ *
+ * @param[in]  r   row vector or matrix1x3
+ * @param[in]  m   matrix3x3
+ * @param[in]  c   column vector or matrix3x1
+ *
+ * @return scalar value e.g. Matrix1x1
+ */
+CGLM_INLINE
+float
+glm_mat3_rmc(const vec3 r, const mat3 m, const vec3 c) {
+  vec3 tmp;
+  glm_mat3_mulv(m, c, tmp);
+  return glm_vec3_dot(r, tmp);
+}
+
 #endif /* cglm_mat3_h */

include/cglm/mat4.h

@@ -16,13 +16,13 @@
    GLM_MAT4_ZERO_INIT
    GLM_MAT4_IDENTITY
    GLM_MAT4_ZERO
-   glm_mat4_udup(mat, dest)
-   glm_mat4_dup(mat, dest)
 
  Functions:
    CGLM_INLINE void  glm_mat4_ucopy(mat4 mat, mat4 dest);
    CGLM_INLINE void  glm_mat4_copy(mat4 mat, mat4 dest);
    CGLM_INLINE void  glm_mat4_identity(mat4 mat);
+   CGLM_INLINE void  glm_mat4_identity_array(mat4 * restrict mat, size_t count);
+   CGLM_INLINE void  glm_mat4_zero(mat4 mat);
    CGLM_INLINE void  glm_mat4_pick3(mat4 mat, mat3 dest);
    CGLM_INLINE void  glm_mat4_pick3t(mat4 mat, mat3 dest);
    CGLM_INLINE void  glm_mat4_ins3(mat3 mat, mat4 dest);
@@ -30,6 +30,9 @@
    CGLM_INLINE void  glm_mat4_mulN(mat4 *matrices[], int len, mat4 dest);
    CGLM_INLINE void  glm_mat4_mulv(mat4 m, vec4 v, vec4 dest);
    CGLM_INLINE void  glm_mat4_mulv3(mat4 m, vec3 v, vec3 dest);
+   CGLM_INLINE float glm_mat4_trace(mat4 m);
+   CGLM_INLINE float glm_mat4_trace3(mat4 m);
+   CGLM_INLINE void  glm_mat4_quat(mat4 m, versor dest) ;
    CGLM_INLINE void  glm_mat4_transpose_to(mat4 m, mat4 dest);
    CGLM_INLINE void  glm_mat4_transpose(mat4 m);
    CGLM_INLINE void  glm_mat4_scale_p(mat4 m, float s);
@@ -39,13 +42,15 @@
    CGLM_INLINE void  glm_mat4_inv_fast(mat4 mat, mat4 dest);
    CGLM_INLINE void  glm_mat4_swap_col(mat4 mat, int col1, int col2);
    CGLM_INLINE void  glm_mat4_swap_row(mat4 mat, int row1, int row2);
+   CGLM_INLINE float glm_mat4_rmc(vec4 r, mat4 m, vec4 c);
  */
 
 #ifndef cglm_mat_h
 #define cglm_mat_h
 
 #include "common.h"
-#include "quat.h"
+#include "vec4.h"
+#include "vec3.h"
 
 #ifdef CGLM_SSE_FP
 #  include "simd/sse2/mat4.h"
@@ -95,8 +100,16 @@
  */
 CGLM_INLINE
 void
-glm_mat4_ucopy(mat4 mat, mat4 dest) {
-  glm__memcpy(float, dest, mat, sizeof(mat4));
+glm_mat4_ucopy(const mat4 mat, mat4 dest) {
+  dest[0][0] = mat[0][0];  dest[1][0] = mat[1][0];
+  dest[0][1] = mat[0][1];  dest[1][1] = mat[1][1];
+  dest[0][2] = mat[0][2];  dest[1][2] = mat[1][2];
+  dest[0][3] = mat[0][3];  dest[1][3] = mat[1][3];
+
+  dest[2][0] = mat[2][0];  dest[3][0] = mat[3][0];
+  dest[2][1] = mat[2][1];  dest[3][1] = mat[3][1];
+  dest[2][2] = mat[2][2];  dest[3][2] = mat[3][2];
+  dest[2][3] = mat[2][3];  dest[3][3] = mat[3][3];
 }
 
 /*!
@@ -107,15 +120,20 @@ glm_mat4_ucopy(mat4 mat, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_copy(mat4 mat, mat4 dest) {
+glm_mat4_copy(const mat4 mat, mat4 dest) {
 #ifdef __AVX__
-  _mm256_store_ps(dest[0], _mm256_load_ps(mat[0]));
-  _mm256_store_ps(dest[2], _mm256_load_ps(mat[2]));
+  glmm_store256(dest[0], glmm_load256(mat[0]));
+  glmm_store256(dest[2], glmm_load256(mat[2]));
 #elif defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest[0], _mm_load_ps(mat[0]));
-  _mm_store_ps(dest[1], _mm_load_ps(mat[1]));
-  _mm_store_ps(dest[2], _mm_load_ps(mat[2]));
-  _mm_store_ps(dest[3], _mm_load_ps(mat[3]));
+  glmm_store(dest[0], glmm_load(mat[0]));
+  glmm_store(dest[1], glmm_load(mat[1]));
+  glmm_store(dest[2], glmm_load(mat[2]));
+  glmm_store(dest[3], glmm_load(mat[3]));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest[0], vld1q_f32(mat[0]));
+  vst1q_f32(dest[1], vld1q_f32(mat[1]));
+  vst1q_f32(dest[2], vld1q_f32(mat[2]));
+  vst1q_f32(dest[3], vld1q_f32(mat[3]));
 #else
   glm_mat4_ucopy(mat, dest);
 #endif
@@ -138,7 +156,38 @@ glm_mat4_copy(mat4 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_identity(mat4 mat) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  glm_mat4_copy(t, mat);
+}
+
+/*!
+ * @brief make given matrix array's each element identity matrix
+ *
+ * @param[in, out]  mat   matrix array (must be aligned (16/32)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of matrices
+ */
+CGLM_INLINE
+void
+glm_mat4_identity_array(mat4 * const __restrict mat, size_t count) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_mat4_copy(t, mat[i]);
+  }
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat4_zero(mat4 mat) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_ZERO_INIT;
   glm_mat4_copy(t, mat);
 }
 
@@ -150,7 +199,7 @@ glm_mat4_identity(mat4 mat) {
  */
 CGLM_INLINE
 void
-glm_mat4_pick3(mat4 mat, mat3 dest) {
+glm_mat4_pick3(const mat4 mat, mat3 dest) {
   dest[0][0] = mat[0][0];
   dest[0][1] = mat[0][1];
   dest[0][2] = mat[0][2];
@@ -174,7 +223,7 @@ glm_mat4_pick3(mat4 mat, mat3 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_pick3t(mat4 mat, mat3 dest) {
+glm_mat4_pick3t(const mat4 mat, mat3 dest) {
   dest[0][0] = mat[0][0];
   dest[0][1] = mat[1][0];
   dest[0][2] = mat[2][0];
@@ -196,7 +245,7 @@ glm_mat4_pick3t(mat4 mat, mat3 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_ins3(mat3 mat, mat4 dest) {
+glm_mat4_ins3(const mat3 mat, mat4 dest) {
   dest[0][0] = mat[0][0];
   dest[0][1] = mat[0][1];
   dest[0][2] = mat[0][2];
@@ -226,12 +275,12 @@ glm_mat4_ins3(mat3 mat, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest) {
+glm_mat4_mul(const mat4 m1, const mat4 m2, mat4 dest) {
 #ifdef __AVX__
   glm_mat4_mul_avx(m1, m2, dest);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_mul_sse2(m1, m2, dest);
-#elif defined( __ARM_NEON_FP )
+#elif defined(CGLM_NEON_FP)
   glm_mat4_mul_neon(m1, m2, dest);
 #else
   float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2], a03 = m1[0][3],
@@ -284,7 +333,7 @@ glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_mulN(mat4 * __restrict matrices[], uint32_t len, mat4 dest) {
+glm_mat4_mulN(mat4 * const __restrict matrices[], uint32_t len, mat4 dest) {
   uint32_t i;
 
 #ifdef DEBUG
@@ -306,7 +355,7 @@ glm_mat4_mulN(mat4 * __restrict matrices[], uint32_t len, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
+glm_mat4_mulv(const mat4 m, const vec4 v, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_mulv_sse2(m, v, dest);
 #else
@@ -319,15 +368,41 @@ glm_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
 #endif
 }
 
+/*!
+ * @brief trace of matrix
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat4_trace(const mat4 m) {
+  return m[0][0] + m[1][1] + m[2][2] + m[3][3];
+}
+
+/*!
+ * @brief trace of matrix (rotation part)
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat4_trace3(const mat4 m) {
+  return m[0][0] + m[1][1] + m[2][2];
+}
+
 /*!
  * @brief convert mat4's rotation part to quaternion
  *
- * @param[in]  m    left matrix
+ * @param[in]  m    affine matrix
  * @param[out] dest destination quaternion
  */
 CGLM_INLINE
 void
-glm_mat4_quat(mat4 m, versor dest) {
+glm_mat4_quat(const mat4 m, versor dest) {
   float trace, r, rinv;
 
   /* it seems using like m12 instead of m[1][2] causes extra instructions */
@@ -369,20 +444,20 @@ glm_mat4_quat(mat4 m, versor dest) {
 }
 
 /*!
- * @brief multiply vector with mat4's mat3 part(rotation)
+ * @brief multiply vector with mat4
  *
  * @param[in]  m    mat4(affine transform)
  * @param[in]  v    vec3
- * @param[out] dest vec3
+ * @param[in]  last 4th item to make it vec4
+ * @param[out] dest result vector (vec3)
  */
 CGLM_INLINE
 void
-glm_mat4_mulv3(mat4 m, vec3 v, vec3 dest) {
-  vec3 res;
-  res[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2];
-  res[1] = m[0][1] * v[0] + m[1][1] * v[1] + m[2][1] * v[2];
-  res[2] = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2];
-  glm_vec_copy(res, dest);
+glm_mat4_mulv3(const mat4 m, const vec3 v, float last, vec3 dest) {
+  vec4 res;
+  glm_vec4(v, last, res);
+  glm_mat4_mulv(m, res, res);
+  glm_vec3(res, dest);
 }
 
 /*!
@@ -395,7 +470,7 @@ glm_mat4_mulv3(mat4 m, vec3 v, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_transpose_to(mat4 m, mat4 dest) {
+glm_mat4_transpose_to(const mat4 m, mat4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_transp_sse2(m, dest);
 #else
@@ -422,10 +497,8 @@ glm_mat4_transpose(mat4 m) {
   glm_mat4_transp_sse2(m, m);
 #else
   mat4 d;
-
   glm_mat4_transpose_to(m, d);
-
-  glm__memcpy(float, m, d, sizeof(mat4));
+  glm_mat4_ucopy(d, m);
 #endif
 }
 
@@ -459,6 +532,13 @@ void
 glm_mat4_scale(mat4 m, float s) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_scale_sse2(m, s);
+#elif defined(CGLM_NEON_FP)
+  float32x4_t v0;
+  v0 = vdupq_n_f32(s);
+  vst1q_f32(m[0], vmulq_f32(vld1q_f32(m[0]), v0));
+  vst1q_f32(m[1], vmulq_f32(vld1q_f32(m[1]), v0));
+  vst1q_f32(m[2], vmulq_f32(vld1q_f32(m[2]), v0));
+  vst1q_f32(m[3], vmulq_f32(vld1q_f32(m[3]), v0));
 #else
   glm_mat4_scale_p(m, s);
 #endif
@@ -473,7 +553,7 @@ glm_mat4_scale(mat4 m, float s) {
  */
 CGLM_INLINE
 float
-glm_mat4_det(mat4 mat) {
+glm_mat4_det(const mat4 mat) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   return glm_mat4_det_sse2(mat);
 #else
@@ -506,7 +586,7 @@ glm_mat4_det(mat4 mat) {
  */
 CGLM_INLINE
 void
-glm_mat4_inv(mat4 mat, mat4 dest) {
+glm_mat4_inv(const mat4 mat, mat4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_inv_sse2(mat, dest);
 #else
@@ -567,7 +647,7 @@ glm_mat4_inv(mat4 mat, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4_inv_fast(mat4 mat, mat4 dest) {
+glm_mat4_inv_fast(const mat4 mat, mat4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_inv_fast_sse2(mat, dest);
 #else
@@ -585,7 +665,7 @@ glm_mat4_inv_fast(mat4 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_swap_col(mat4 mat, int col1, int col2) {
-  vec4 tmp;
+  CGLM_ALIGN(16) vec4 tmp;
   glm_vec4_copy(mat[col1], tmp);
   glm_vec4_copy(mat[col2], mat[col1]);
   glm_vec4_copy(tmp, mat[col2]);
@@ -600,8 +680,8 @@ glm_mat4_swap_col(mat4 mat, int col1, int col2) {
  */
 CGLM_INLINE
 void
-glm_mat4_swap_row(mat4 mat, int row1, int row2) {
-  vec4 tmp;
+glm_mat4_swap_row(mat4 mat, const int row1, const int row2) {
+  CGLM_ALIGN(16) vec4 tmp;
   tmp[0] = mat[0][row1];
   tmp[1] = mat[1][row1];
   tmp[2] = mat[2][row1];
@@ -618,4 +698,26 @@ glm_mat4_swap_row(mat4 mat, int row1, int row2) {
   mat[3][row2] = tmp[3];
 }
 
+/*!
+ * @brief helper for  R (row vector) * M (matrix) * C (column vector)
+ *
+ * rmc stands for Row * Matrix * Column
+ *
+ * the result is scalar because R * M = Matrix1x4 (row vector),
+ * then Matrix1x4 * Vec4 (column vector) = Matrix1x1 (Scalar)
+ *
+ * @param[in]  r   row vector or matrix1x4
+ * @param[in]  m   matrix4x4
+ * @param[in]  c   column vector or matrix4x1
+ *
+ * @return scalar value e.g. B(s)
+ */
+CGLM_INLINE
+float
+glm_mat4_rmc(const vec4 r, const mat4 m, const vec4 c) {
+  vec4 tmp;
+  glm_mat4_mulv(m, c, tmp);
+  return glm_vec4_dot(r, tmp);
+}
+
 #endif /* cglm_mat_h */

include/cglm/plane.h

@@ -9,9 +9,7 @@
 #define cglm_plane_h
 
 #include "common.h"
-#include "mat4.h"
 #include "vec4.h"
-#include "vec3.h"
 
 /*
  Plane equation:  Ax + By + Cz + D = 0;
@@ -32,7 +30,7 @@
 CGLM_INLINE
 void
 glm_plane_normalize(vec4 plane) {
-  glm_vec4_scale(plane, 1.0f / glm_vec_norm(plane), plane);
+  glm_vec4_scale(plane, 1.0f / glm_vec3_norm(plane), plane);
 }
 
 #endif /* cglm_plane_h */

include/cglm/project.h

@@ -8,9 +8,10 @@
 #ifndef cglm_project_h
 #define cglm_project_h
 
-#include "mat4.h"
+#include "common.h"
 #include "vec3.h"
 #include "vec4.h"
+#include "mat4.h"
 
 /*!
  * @brief maps the specified viewport coordinates into specified space [1]
@@ -40,7 +41,7 @@
  */
 CGLM_INLINE
 void
-glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
+glm_unprojecti(const vec3 pos, const mat4 invMat, const vec4 vp, vec3 dest) {
   vec4 v;
 
   v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
@@ -79,7 +80,7 @@ glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+glm_unproject(const vec3 pos, const mat4 m, const vec4 vp, vec3 dest) {
   mat4 inv;
   glm_mat4_inv(m, inv);
   glm_unprojecti(pos, inv, vp, dest);
@@ -99,8 +100,8 @@ glm_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
-  vec4 pos4, vone = GLM_VEC4_ONE_INIT;
+glm_project(const vec3 pos, const mat4 m, const vec4 vp, vec3 dest) {
+  CGLM_ALIGN(16) vec4 pos4, vone = GLM_VEC4_ONE_INIT;
 
   glm_vec4(pos, 1.0f, pos4);
 

include/cglm/quat.h

@@ -19,7 +19,7 @@
    CGLM_INLINE float glm_quat_norm(versor q);
    CGLM_INLINE void glm_quat_normalize(versor q);
    CGLM_INLINE void glm_quat_normalize_to(versor q, versor dest);
-   CGLM_INLINE float glm_quat_dot(versor q1, versor q2);
+   CGLM_INLINE float glm_quat_dot(versor p, versor q);
    CGLM_INLINE void glm_quat_conjugate(versor q, versor dest);
    CGLM_INLINE void glm_quat_inv(versor q, versor dest);
    CGLM_INLINE void glm_quat_add(versor p, versor q, versor dest);
@@ -52,9 +52,11 @@
 #define cglm_quat_h
 
 #include "common.h"
+#include "vec3.h"
 #include "vec4.h"
 #include "mat4.h"
 #include "mat3.h"
+#include "affine-mat.h"
 
 #ifdef CGLM_SSE_FP
 #  include "simd/sse2/quat.h"
@@ -62,11 +64,19 @@
 
 CGLM_INLINE
 void
-glm_mat4_mulv(mat4 m, vec4 v, vec4 dest);
+glm_mat4_identity(mat4 mat);
 
 CGLM_INLINE
 void
-glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest);
+glm_mat4_mulv(const mat4 m, const vec4 v, vec4 dest);
+
+CGLM_INLINE
+void
+glm_mul_rot(const mat4 m1, const mat4 m2, mat4 dest);
+
+CGLM_INLINE
+void
+glm_translate(mat4 m, const vec3 v);
 
 /*
  * IMPORTANT:
@@ -89,10 +99,29 @@ glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest);
 CGLM_INLINE
 void
 glm_quat_identity(versor q) {
-  versor v = GLM_QUAT_IDENTITY_INIT;
+  CGLM_ALIGN(16) versor v = GLM_QUAT_IDENTITY_INIT;
   glm_vec4_copy(v, q);
 }
 
+/*!
+ * @brief make given quaternion array's each element identity quaternion
+ *
+ * @param[in, out]  q     quat array (must be aligned (16)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of quaternions
+ */
+CGLM_INLINE
+void
+glm_quat_identity_array(versor * const __restrict q, size_t count) {
+  CGLM_ALIGN(16) versor v = GLM_QUAT_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_vec4_copy(v, q[i]);
+  }
+}
+
 /*!
  * @brief inits quaterion with raw values
  *
@@ -120,8 +149,8 @@ glm_quat_init(versor q, float x, float y, float z, float w) {
  */
 CGLM_INLINE
 void
-glm_quatv(versor q, float angle, vec3 axis) {
-  vec3  k;
+glm_quatv(versor q, float angle, const vec3 axis) {
+  CGLM_ALIGN(8) vec3 k;
   float a, c, s;
 
   a = angle * 0.5f;
@@ -148,7 +177,7 @@ glm_quatv(versor q, float angle, vec3 axis) {
 CGLM_INLINE
 void
 glm_quat(versor q, float angle, float x, float y, float z) {
-  vec3 axis = {x, y, z};
+  CGLM_ALIGN(8) vec3 axis = {x, y, z};
   glm_quatv(q, angle, axis);
 }
 
@@ -160,7 +189,7 @@ glm_quat(versor q, float angle, float x, float y, float z) {
  */
 CGLM_INLINE
 void
-glm_quat_copy(versor q, versor dest) {
+glm_quat_copy(const versor q, versor dest) {
   glm_vec4_copy(q, dest);
 }
 
@@ -171,7 +200,7 @@ glm_quat_copy(versor q, versor dest) {
  */
 CGLM_INLINE
 float
-glm_quat_norm(versor q) {
+glm_quat_norm(const versor q) {
   return glm_vec4_norm(q);
 }
 
@@ -183,13 +212,13 @@ glm_quat_norm(versor q) {
  */
 CGLM_INLINE
 void
-glm_quat_normalize_to(versor q, versor dest) {
+glm_quat_normalize_to(const versor q, versor dest) {
 #if defined( __SSE2__ ) || defined( __SSE2__ )
   __m128 xdot, x0;
   float  dot;
 
-  x0   = _mm_load_ps(q);
-  xdot = glm_simd_dot(x0, x0);
+  x0   = glmm_load(q);
+  xdot = glmm_vdot(x0, x0);
   dot  = _mm_cvtss_f32(xdot);
 
   if (dot <= 0.0f) {
@@ -197,7 +226,7 @@ glm_quat_normalize_to(versor q, versor dest) {
     return;
   }
 
-  _mm_store_ps(dest, _mm_div_ps(x0, _mm_sqrt_ps(xdot)));
+  glmm_store(dest, _mm_div_ps(x0, _mm_sqrt_ps(xdot)));
 #else
   float dot;
 
@@ -231,7 +260,7 @@ glm_quat_normalize(versor q) {
  */
 CGLM_INLINE
 float
-glm_quat_dot(versor p, versor q) {
+glm_quat_dot(const versor p, const versor q) {
   return glm_vec4_dot(p, q);
 }
 
@@ -243,8 +272,8 @@ glm_quat_dot(versor p, versor q) {
  */
 CGLM_INLINE
 void
-glm_quat_conjugate(versor q, versor dest) {
-  glm_vec4_flipsign_to(q, dest);
+glm_quat_conjugate(const versor q, versor dest) {
+  glm_vec4_negate_to(q, dest);
   dest[3] = -dest[3];
 }
 
@@ -256,8 +285,8 @@ glm_quat_conjugate(versor q, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_inv(versor q, versor dest) {
-  versor conj;
+glm_quat_inv(const versor q, versor dest) {
+  CGLM_ALIGN(16) versor conj;
   glm_quat_conjugate(q, conj);
   glm_vec4_scale(conj, 1.0f / glm_vec4_norm2(q), dest);
 }
@@ -271,7 +300,7 @@ glm_quat_inv(versor q, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_add(versor p, versor q, versor dest) {
+glm_quat_add(const versor p, const versor q, versor dest) {
   glm_vec4_add(p, q, dest);
 }
 
@@ -284,7 +313,7 @@ glm_quat_add(versor p, versor q, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_sub(versor p, versor q, versor dest) {
+glm_quat_sub(const versor p, const versor q, versor dest) {
   glm_vec4_sub(p, q, dest);
 }
 
@@ -295,7 +324,7 @@ glm_quat_sub(versor p, versor q, versor dest) {
  */
 CGLM_INLINE
 float
-glm_quat_real(versor q) {
+glm_quat_real(const versor q) {
   return q[3];
 }
 
@@ -307,7 +336,7 @@ glm_quat_real(versor q) {
  */
 CGLM_INLINE
 void
-glm_quat_imag(versor q, vec3 dest) {
+glm_quat_imag(const versor q, vec3 dest) {
   dest[0] = q[0];
   dest[1] = q[1];
   dest[2] = q[2];
@@ -320,7 +349,7 @@ glm_quat_imag(versor q, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_imagn(versor q, vec3 dest) {
+glm_quat_imagn(const versor q, vec3 dest) {
   glm_normalize_to(q, dest);
 }
 
@@ -331,8 +360,8 @@ glm_quat_imagn(versor q, vec3 dest) {
  */
 CGLM_INLINE
 float
-glm_quat_imaglen(versor q) {
-  return glm_vec_norm(q);
+glm_quat_imaglen(const versor q) {
+  return glm_vec3_norm(q);
 }
 
 /*!
@@ -342,7 +371,7 @@ glm_quat_imaglen(versor q) {
  */
 CGLM_INLINE
 float
-glm_quat_angle(versor q) {
+glm_quat_angle(const versor q) {
   /*
    sin(theta / 2) = length(x*x + y*y + z*z)
    cos(theta / 2) = w
@@ -359,7 +388,7 @@ glm_quat_angle(versor q) {
  */
 CGLM_INLINE
 void
-glm_quat_axis(versor q, versor dest) {
+glm_quat_axis(const versor q, versor dest) {
   glm_quat_imagn(q, dest);
 }
 
@@ -377,7 +406,7 @@ glm_quat_axis(versor q, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_mul(versor p, versor q, versor dest) {
+glm_quat_mul(const versor p, const versor q, versor dest) {
   /*
     + (a1 b2 + b1 a2 + c1 d2 − d1 c2)i
     + (a1 c2 − b1 d2 + c1 a2 + d1 b2)j
@@ -402,7 +431,7 @@ glm_quat_mul(versor p, versor q, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_mat4(versor q, mat4 dest) {
+glm_quat_mat4(const versor q, mat4 dest) {
   float w, x, y, z,
         xx, yy, zz,
         xy, yz, xz,
@@ -449,7 +478,7 @@ glm_quat_mat4(versor q, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_mat4t(versor q, mat4 dest) {
+glm_quat_mat4t(const versor q, mat4 dest) {
   float w, x, y, z,
         xx, yy, zz,
         xy, yz, xz,
@@ -496,7 +525,7 @@ glm_quat_mat4t(versor q, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_mat3(versor q, mat3 dest) {
+glm_quat_mat3(const versor q, mat3 dest) {
   float w, x, y, z,
         xx, yy, zz,
         xy, yz, xz,
@@ -535,7 +564,7 @@ glm_quat_mat3(versor q, mat3 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_mat3t(versor q, mat3 dest) {
+glm_quat_mat3t(const versor q, mat3 dest) {
   float w, x, y, z,
         xx, yy, zz,
         xy, yz, xz,
@@ -577,7 +606,7 @@ glm_quat_mat3t(versor q, mat3 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_lerp(versor from, versor to, float t, versor dest) {
+glm_quat_lerp(const versor from, const versor to, float t, versor dest) {
   glm_vec4_lerp(from, to, t, dest);
 }
 
@@ -592,8 +621,8 @@ glm_quat_lerp(versor from, versor to, float t, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_slerp(versor from, versor to, float t, versor dest) {
-  vec4  q1, q2;
+glm_quat_slerp(const versor from, const versor to, float t, versor dest) {
+  CGLM_ALIGN(16) vec4 q1, q2;
   float cosTheta, sinTheta, angle;
 
   cosTheta = glm_quat_dot(from, to);
@@ -605,7 +634,7 @@ glm_quat_slerp(versor from, versor to, float t, versor dest) {
   }
 
   if (cosTheta < 0.0f) {
-    glm_vec4_flipsign(q1);
+    glm_vec4_negate(q1);
     cosTheta = -cosTheta;
   }
 
@@ -635,16 +664,13 @@ glm_quat_slerp(versor from, versor to, float t, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_look(vec3 eye, versor ori, mat4 dest) {
-  vec4 t;
-
+glm_quat_look(const vec3 eye, const versor ori, mat4 dest) {
   /* orientation */
   glm_quat_mat4t(ori, dest);
 
   /* translate */
-  glm_vec4(eye, 1.0f, t);
-  glm_mat4_mulv(dest, t, t);
-  glm_vec_flipsign_to(t, dest[3]);
+  glm_mat4_mulv3(dest, eye, 1.0f, dest[3]);
+  glm_vec3_negate(dest[3]);
 }
 
 /*!
@@ -657,13 +683,13 @@ glm_quat_look(vec3 eye, versor ori, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest) {
-  vec3  axis;
+glm_quat_for(const vec3 dir, const vec3 fwd, const vec3 up, versor dest) {
+  CGLM_ALIGN(8) vec3 axis;
   float dot, angle;
 
-  dot = glm_vec_dot(dir, fwd);
+  dot = glm_vec3_dot(dir, fwd);
   if (fabsf(dot + 1.0f)  < 0.000001f) {
-    glm_quat_init(dest, up[0], up[1], up[2], CGLM_PI);
+    glm_quat_init(dest, up[0], up[1], up[2], GLM_PIf);
     return;
   }
 
@@ -691,9 +717,13 @@ glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest) {
-  vec3 dir;
-  glm_vec_sub(to, from, dir);
+glm_quat_forp(const vec3 from,
+              const vec3 to,
+              const vec3 fwd,
+              const vec3 up,
+              versor     dest) {
+  CGLM_ALIGN(8) vec3 dir;
+  glm_vec3_sub(to, from, dir);
   glm_quat_for(dir, fwd, up, dest);
 }
 
@@ -706,23 +736,23 @@ glm_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest) {
  */
 CGLM_INLINE
 void
-glm_quat_rotatev(versor q, vec3 v, vec3 dest) {
-  versor p;
-  vec3   u, v1, v2;
+glm_quat_rotatev(const versor q, const vec3 v, vec3 dest) {
+  CGLM_ALIGN(16) versor p;
+  CGLM_ALIGN(8)  vec3   u, v1, v2;
   float s;
 
   glm_quat_normalize_to(q, p);
   glm_quat_imag(p, u);
   s = glm_quat_real(p);
 
-  glm_vec_scale(u, 2.0f * glm_vec_dot(u, v), v1);
-  glm_vec_scale(v, s * s - glm_vec_dot(u, u), v2);
-  glm_vec_add(v1, v2, v1);
+  glm_vec3_scale(u, 2.0f * glm_vec3_dot(u, v), v1);
+  glm_vec3_scale(v, s * s - glm_vec3_dot(u, u), v2);
+  glm_vec3_add(v1, v2, v1);
 
-  glm_vec_cross(u, v, v2);
-  glm_vec_scale(v2, 2.0f * s, v2);
+  glm_vec3_cross(u, v, v2);
+  glm_vec3_scale(v2, 2.0f * s, v2);
 
-  glm_vec_add(v1, v2, dest);
+  glm_vec3_add(v1, v2, dest);
 }
 
 /*!
@@ -734,10 +764,53 @@ glm_quat_rotatev(versor q, vec3 v, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_quat_rotate(mat4 m, versor q, mat4 dest) {
-  mat4 rot;
+glm_quat_rotate(const mat4 m, const versor q, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 rot;
   glm_quat_mat4(q, rot);
-  glm_mat4_mul(m, rot, dest);
+  glm_mul_rot(m, rot, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix using quaternion at pivot point
+ *
+ * @param[in, out]   m     existing transform matrix
+ * @param[in]        q     quaternion
+ * @param[out]       pivot pivot
+ */
+CGLM_INLINE
+void
+glm_quat_rotate_at(mat4 m, const versor q, const vec3 pivot) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translate(m, pivot);
+  glm_quat_rotate(m, q, m);
+  glm_translate(m, pivotInv);
+}
+
+/*!
+ * @brief rotate NEW transform matrix using quaternion at pivot point
+ *
+ * this creates rotation matrix, it assumes you don't have a matrix
+ *
+ * this should work faster than glm_quat_rotate_at because it reduces
+ * one glm_translate.
+ *
+ * @param[out]  m     existing transform matrix
+ * @param[in]   q     quaternion
+ * @param[in]   pivot pivot
+ */
+CGLM_INLINE
+void
+glm_quat_rotate_atm(mat4 m, const versor q, const vec3 pivot) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translate_make(m, pivot);
+  glm_quat_rotate(m, q, m);
+  glm_translate(m, pivotInv);
 }
 
 #endif /* cglm_quat_h */

include/cglm/simd/arm.h

@@ -0,0 +1,41 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_simd_arm_h
+#define cglm_simd_arm_h
+#include "intrin.h"
+#ifdef CGLM_SIMD_ARM
+
+#define glmm_load(p)      vld1q_f32(p)
+#define glmm_store(p, a)  vst1q_f32(p, a)
+
+static inline
+float
+glmm_hadd(float32x4_t v) {
+#if defined(__aarch64__)
+  return vaddvq_f32(v);
+#else
+  v = vaddq_f32(v, vrev64q_f32(v));
+  v = vaddq_f32(v, vcombine_f32(vget_high_f32(v), vget_low_f32(v)));
+  return vgetq_lane_f32(v, 0);
+#endif
+}
+
+static inline
+float
+glmm_dot(float32x4_t a, float32x4_t b) {
+  return glmm_hadd(vmulq_f32(a, b));
+}
+
+static inline
+float
+glmm_norm(float32x4_t a) {
+  return sqrtf(glmm_dot(a, a));
+}
+
+#endif
+#endif /* cglm_simd_arm_h */

include/cglm/simd/avx/affine.h

@@ -16,32 +16,35 @@
 
 CGLM_INLINE
 void
-glm_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
+glm_mul_avx(const mat4 m1, const mat4 m2, mat4 dest) {
   /* D = R * L (Column-Major) */
 
   __m256 y0, y1, y2, y3, y4, y5, y6, y7, y8, y9;
 
-  y0 = _mm256_load_ps(m2[0]); /* h g f e d c b a */
-  y1 = _mm256_load_ps(m2[2]); /* p o n m l k j i */
+  y0 = glmm_load256(m2[0]); /* h g f e d c b a */
+  y1 = glmm_load256(m2[2]); /* p o n m l k j i */
 
-  y2 = _mm256_load_ps(m1[0]); /* h g f e d c b a */
-  y3 = _mm256_load_ps(m1[2]); /* p o n m l k j i */
+  y2 = glmm_load256(m1[0]); /* h g f e d c b a */
+  y3 = glmm_load256(m1[2]); /* p o n m l k j i */
 
-  y4 = _mm256_permute2f128_ps(y2, y2, 0b00000011); /* d c b a h g f e */
-  y5 = _mm256_permute2f128_ps(y3, y3, 0b00000000); /* l k j i l k j i */
+  /* 0x03: 0b00000011 */
+  y4 = _mm256_permute2f128_ps(y2, y2, 0x03); /* d c b a h g f e */
+  y5 = _mm256_permute2f128_ps(y3, y3, 0x03); /* l k j i p o n m */
 
   /* f f f f a a a a */
-  /* g g g g c c c c */
+  /* h h h h c c c c */
   /* e e e e b b b b */
-  y7 = _mm256_permute_ps(y0, 0b10101010);
+  /* g g g g d d d d */
   y6 = _mm256_permutevar_ps(y0, _mm256_set_epi32(1, 1, 1, 1, 0, 0, 0, 0));
+  y7 = _mm256_permutevar_ps(y0, _mm256_set_epi32(3, 3, 3, 3, 2, 2, 2, 2));
   y8 = _mm256_permutevar_ps(y0, _mm256_set_epi32(0, 0, 0, 0, 1, 1, 1, 1));
+  y9 = _mm256_permutevar_ps(y0, _mm256_set_epi32(2, 2, 2, 2, 3, 3, 3, 3));
 
-  _mm256_store_ps(dest[0],
+  glmm_store256(dest[0],
                 _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(y2, y6),
-                                              _mm256_mul_ps(y4, y8)),
-                                _mm256_mul_ps(y5, y7)));
-
+                                            _mm256_mul_ps(y3, y7)),
+                              _mm256_add_ps(_mm256_mul_ps(y4, y8),
+                                            _mm256_mul_ps(y5, y9))));
 
   /* n n n n i i i i */
   /* p p p p k k k k */
@@ -52,7 +55,7 @@ glm_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
   y8 = _mm256_permutevar_ps(y1, _mm256_set_epi32(0, 0, 0, 0, 1, 1, 1, 1));
   y9 = _mm256_permutevar_ps(y1, _mm256_set_epi32(2, 2, 2, 2, 3, 3, 3, 3));
 
-  _mm256_store_ps(dest[2],
+  glmm_store256(dest[2],
                 _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(y2, y6),
                                             _mm256_mul_ps(y3, y7)),
                               _mm256_add_ps(_mm256_mul_ps(y4, y8),

include/cglm/simd/avx/mat4.h

@@ -16,19 +16,20 @@
 
 CGLM_INLINE
 void
-glm_mat4_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
+glm_mat4_mul_avx(const mat4 m1, const mat4 m2, mat4 dest) {
   /* D = R * L (Column-Major) */
 
   __m256 y0, y1, y2, y3, y4, y5, y6, y7, y8, y9;
 
-  y0 = _mm256_load_ps(m2[0]); /* h g f e d c b a */
-  y1 = _mm256_load_ps(m2[2]); /* p o n m l k j i */
+  y0 = glmm_load256(m2[0]); /* h g f e d c b a */
+  y1 = glmm_load256(m2[2]); /* p o n m l k j i */
 
-  y2 = _mm256_load_ps(m1[0]); /* h g f e d c b a */
-  y3 = _mm256_load_ps(m1[2]); /* p o n m l k j i */
+  y2 = glmm_load256(m1[0]); /* h g f e d c b a */
+  y3 = glmm_load256(m1[2]); /* p o n m l k j i */
 
-  y4 = _mm256_permute2f128_ps(y2, y2, 0b00000011); /* d c b a h g f e */
-  y5 = _mm256_permute2f128_ps(y3, y3, 0b00000011); /* l k j i p o n m */
+  /* 0x03: 0b00000011 */
+  y4 = _mm256_permute2f128_ps(y2, y2, 0x03); /* d c b a h g f e */
+  y5 = _mm256_permute2f128_ps(y3, y3, 0x03); /* l k j i p o n m */
 
   /* f f f f a a a a */
   /* h h h h c c c c */
@@ -39,7 +40,7 @@ glm_mat4_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
   y8 = _mm256_permutevar_ps(y0, _mm256_set_epi32(0, 0, 0, 0, 1, 1, 1, 1));
   y9 = _mm256_permutevar_ps(y0, _mm256_set_epi32(2, 2, 2, 2, 3, 3, 3, 3));
 
-  _mm256_store_ps(dest[0],
+  glmm_store256(dest[0],
                 _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(y2, y6),
                                             _mm256_mul_ps(y3, y7)),
                               _mm256_add_ps(_mm256_mul_ps(y4, y8),
@@ -54,7 +55,7 @@ glm_mat4_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
   y8 = _mm256_permutevar_ps(y1, _mm256_set_epi32(0, 0, 0, 0, 1, 1, 1, 1));
   y9 = _mm256_permutevar_ps(y1, _mm256_set_epi32(2, 2, 2, 2, 3, 3, 3, 3));
 
-  _mm256_store_ps(dest[2],
+  glmm_store256(dest[2],
                 _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(y2, y6),
                                             _mm256_mul_ps(y3, y7)),
                               _mm256_add_ps(_mm256_mul_ps(y4, y8),

include/cglm/simd/intrin.h

@@ -8,55 +8,83 @@
 #ifndef cglm_intrin_h
 #define cglm_intrin_h
 
-#if defined( _WIN32 )
+#if defined( _MSC_VER )
 #  if (defined(_M_AMD64) || defined(_M_X64)) || _M_IX86_FP == 2
+#    ifndef __SSE2__
 #      define __SSE2__
+#    endif
 #  elif _M_IX86_FP == 1
+#    ifndef __SSE__
 #      define __SSE__
 #    endif
+#  endif
+/* do not use alignment for older visual studio versions */
+#  if _MSC_VER < 1913     /* Visual Studio 2017 version 15.6 */
+#    define CGLM_ALL_UNALIGNED
+#  endif
 #endif
 
 #if defined( __SSE__ ) || defined( __SSE2__ )
 #  include <xmmintrin.h>
 #  include <emmintrin.h>
-
-/* float */
-#  define _mm_shuffle1_ps(a, z, y, x, w)                                       \
-     _mm_shuffle_ps(a, a, _MM_SHUFFLE(z, y, x, w))
-
-#  define _mm_shuffle1_ps1(a, x)                                               \
-     _mm_shuffle_ps(a, a, _MM_SHUFFLE(x, x, x, x))
-
-#  define _mm_shuffle2_ps(a, b, z0, y0, x0, w0, z1, y1, x1, w1)                \
-     _mm_shuffle1_ps(_mm_shuffle_ps(a, b, _MM_SHUFFLE(z0, y0, x0, w0)),        \
-                                    z1, y1, x1, w1)
-
-CGLM_INLINE
-__m128
-glm_simd_dot(__m128 a, __m128 b) {
-  __m128 x0;
-  x0 = _mm_mul_ps(a, b);
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 1, 0, 3, 2));
-  return _mm_add_ps(x0, _mm_shuffle1_ps(x0, 0, 1, 0, 1));
-}
-
+#  define CGLM_SSE_FP 1
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
 #endif
 
-/* x86, x64 */
-#if defined( __SSE__ ) || defined( __SSE2__ )
-#  define CGLM_SSE_FP 1
+#if defined(__SSE3__)
+#  include <x86intrin.h>
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
+#endif
+
+#if defined(__SSE4_1__)
+#  include <smmintrin.h>
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
+#endif
+
+#if defined(__SSE4_2__)
+#  include <nmmintrin.h>
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
 #endif
 
 #ifdef __AVX__
+#  include <immintrin.h>
 #  define CGLM_AVX_FP 1
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
 #endif
 
 /* ARM Neon */
-#if defined(__ARM_NEON) && defined(__ARM_NEON_FP)
+#if defined(__ARM_NEON)
 #  include <arm_neon.h>
+#  if defined(__ARM_NEON_FP)
 #    define CGLM_NEON_FP 1
-#else
-#  undef  CGLM_NEON_FP
+#    ifndef CGLM_SIMD_ARM
+#      define CGLM_SIMD_ARM
+#    endif
+#  endif
+#endif
+
+#if defined(CGLM_SIMD_x86) || defined(CGLM_NEON_FP)
+#  ifndef CGLM_SIMD
+#    define CGLM_SIMD
+#  endif
+#endif
+
+#if defined(CGLM_SIMD_x86)
+#  include "x86.h"
+#endif
+
+#if defined(CGLM_SIMD_ARM)
+#  include "arm.h"
 #endif
 
 #endif /* cglm_intrin_h */

include/cglm/simd/neon/mat4.h

@@ -14,7 +14,7 @@
 
 CGLM_INLINE
 void
-glm_mat4_mul_neon(mat4 m1, mat4 m2, mat4 dest) {
+glm_mat4_mul_neon(const mat4 m1, const mat4 m2, mat4 dest) {
   /* D = R * L (Column-Major) */
   float32x4_t l0, l1, l2, l3, r, d0, d1, d2, d3;
 

include/cglm/simd/sse2/affine.h

@@ -14,39 +14,71 @@
 
 CGLM_INLINE
 void
-glm_mul_sse2(mat4 m1, mat4 m2, mat4 dest) {
+glm_mul_sse2(const mat4 m1, const mat4 m2, mat4 dest) {
   /* D = R * L (Column-Major) */
   __m128 l0, l1, l2, l3, r;
 
-  l0 = _mm_load_ps(m1[0]);
-  l1 = _mm_load_ps(m1[1]);
-  l2 = _mm_load_ps(m1[2]);
-  l3 = _mm_load_ps(m1[3]);
+  l0 = glmm_load(m1[0]);
+  l1 = glmm_load(m1[1]);
+  l2 = glmm_load(m1[2]);
+  l3 = glmm_load(m1[3]);
 
-  r = _mm_load_ps(m2[0]);
-  _mm_store_ps(dest[0],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2)));
+  r = glmm_load(m2[0]);
+  glmm_store(dest[0],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
 
-  r = _mm_load_ps(m2[1]);
-  _mm_store_ps(dest[1],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2)));
+  r = glmm_load(m2[1]);
+  glmm_store(dest[1],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
 
-  r = _mm_load_ps(m2[2]);
-  _mm_store_ps(dest[2],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2)));
+  r = glmm_load(m2[2]);
+  glmm_store(dest[2],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
 
-  r = _mm_load_ps(m2[3]);
-  _mm_store_ps(dest[3],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 3), l3))));
+  r = glmm_load(m2[3]);
+  glmm_store(dest[3],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
+}
+
+CGLM_INLINE
+void
+glm_mul_rot_sse2(const mat4 m1, const mat4 m2, mat4 dest) {
+  /* D = R * L (Column-Major) */
+  __m128 l0, l1, l2, l3, r;
+
+  l0 = glmm_load(m1[0]);
+  l1 = glmm_load(m1[1]);
+  l2 = glmm_load(m1[2]);
+  l3 = glmm_load(m1[3]);
+
+  r = glmm_load(m2[0]);
+  glmm_store(dest[0],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+
+  r = glmm_load(m2[1]);
+  glmm_store(dest[1],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+
+  r = glmm_load(m2[2]);
+  glmm_store(dest[2],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+
+  glmm_store(dest[3], l3);
 }
 
 CGLM_INLINE
@@ -54,25 +86,25 @@ void
 glm_inv_tr_sse2(mat4 mat) {
   __m128 r0, r1, r2, r3, x0, x1;
 
-  r0 = _mm_load_ps(mat[0]);
-  r1 = _mm_load_ps(mat[1]);
-  r2 = _mm_load_ps(mat[2]);
-  r3 = _mm_load_ps(mat[3]);
+  r0 = glmm_load(mat[0]);
+  r1 = glmm_load(mat[1]);
+  r2 = glmm_load(mat[2]);
+  r3 = glmm_load(mat[3]);
   x1 = _mm_set_ps(1.0f, 0.0f, 0.0f, 0.0f);
 
   _MM_TRANSPOSE4_PS(r0, r1, r2, x1);
 
-  x0 = _mm_add_ps(_mm_mul_ps(r0, _mm_shuffle1_ps(r3, 0, 0, 0, 0)),
-                  _mm_mul_ps(r1, _mm_shuffle1_ps(r3, 1, 1, 1, 1)));
-  x0 = _mm_add_ps(x0, _mm_mul_ps(r2, _mm_shuffle1_ps(r3, 2, 2, 2, 2)));
+  x0 = _mm_add_ps(_mm_mul_ps(r0, glmm_shuff1(r3, 0, 0, 0, 0)),
+                  _mm_mul_ps(r1, glmm_shuff1(r3, 1, 1, 1, 1)));
+  x0 = _mm_add_ps(x0, _mm_mul_ps(r2, glmm_shuff1(r3, 2, 2, 2, 2)));
   x0 = _mm_xor_ps(x0, _mm_set1_ps(-0.f));
 
   x0 = _mm_add_ps(x0, x1);
 
-  _mm_store_ps(mat[0], r0);
-  _mm_store_ps(mat[1], r1);
-  _mm_store_ps(mat[2], r2);
-  _mm_store_ps(mat[3], x0);
+  glmm_store(mat[0], r0);
+  glmm_store(mat[1], r1);
+  glmm_store(mat[2], r2);
+  glmm_store(mat[3], x0);
 }
 
 #endif

include/cglm/simd/sse2/mat3.h

@@ -14,7 +14,7 @@
 
 CGLM_INLINE
 void
-glm_mat3_mul_sse2(mat3 m1, mat3 m2, mat3 dest) {
+glm_mat3_mul_sse2(const mat3 m1, const mat3 m2, mat3 dest) {
   __m128 l0, l1, l2;
   __m128 r0, r1, r2;
   __m128 x0, x1, x2;
@@ -27,27 +27,25 @@ glm_mat3_mul_sse2(mat3 m1, mat3 m2, mat3 dest) {
   r1 = _mm_loadu_ps(&m2[1][1]);
   r2 = _mm_set1_ps(m2[2][2]);
 
-  x1 = _mm_shuffle2_ps(l0, l1, 1, 0, 3, 3, 0, 3, 2, 0);
-  x2 = _mm_shuffle2_ps(l1, l2, 0, 0, 3, 2, 0, 2, 1, 0);
+  x1 = glmm_shuff2(l0, l1, 1, 0, 3, 3, 0, 3, 2, 0);
+  x2 = glmm_shuff2(l1, l2, 0, 0, 3, 2, 0, 2, 1, 0);
 
-  x0 = _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps(l0, 0, 2, 1, 0),
-                             _mm_shuffle1_ps(r0, 3, 0, 0, 0)),
-                  _mm_mul_ps(x1,
-                             _mm_shuffle2_ps(r0, r1, 0, 0, 1, 1, 2, 0, 0, 0)));
+  x0 = _mm_add_ps(_mm_mul_ps(glmm_shuff1(l0, 0, 2, 1, 0),
+                             glmm_shuff1(r0, 3, 0, 0, 0)),
+                  _mm_mul_ps(x1, glmm_shuff2(r0, r1, 0, 0, 1, 1, 2, 0, 0, 0)));
 
   x0 = _mm_add_ps(x0,
-                  _mm_mul_ps(x2,
-                             _mm_shuffle2_ps(r0, r1, 1, 1, 2, 2, 2, 0, 0, 0)));
+                  _mm_mul_ps(x2, glmm_shuff2(r0, r1, 1, 1, 2, 2, 2, 0, 0, 0)));
 
   _mm_storeu_ps(dest[0], x0);
 
-  x0 = _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps(l0, 1, 0, 2, 1),
+  x0 = _mm_add_ps(_mm_mul_ps(glmm_shuff1(l0, 1, 0, 2, 1),
                              _mm_shuffle_ps(r0, r1, _MM_SHUFFLE(2, 2, 3, 3))),
-                  _mm_mul_ps(_mm_shuffle1_ps(x1, 1, 0, 2, 1),
-                             _mm_shuffle1_ps(r1, 3, 3, 0, 0)));
+                  _mm_mul_ps(glmm_shuff1(x1, 1, 0, 2, 1),
+                             glmm_shuff1(r1, 3, 3, 0, 0)));
 
   x0 = _mm_add_ps(x0,
-                  _mm_mul_ps(_mm_shuffle1_ps(x2, 1, 0, 2, 1),
+                  _mm_mul_ps(glmm_shuff1(x2, 1, 0, 2, 1),
                              _mm_shuffle_ps(r1, r2, _MM_SHUFFLE(0, 0, 1, 1))));
 
   _mm_storeu_ps(&dest[1][1], x0);

include/cglm/simd/sse2/mat4.h

@@ -16,102 +16,98 @@
 
 CGLM_INLINE
 void
-glm_mat4_scale_sse2(mat4 m, float s){
+glm_mat4_scale_sse2(mat4 m, float s) {
   __m128 x0;
   x0 = _mm_set1_ps(s);
 
-  _mm_store_ps(m[0], _mm_mul_ps(_mm_load_ps(m[0]), x0));
-  _mm_store_ps(m[1], _mm_mul_ps(_mm_load_ps(m[1]), x0));
-  _mm_store_ps(m[2], _mm_mul_ps(_mm_load_ps(m[2]), x0));
-  _mm_store_ps(m[3], _mm_mul_ps(_mm_load_ps(m[3]), x0));
+  glmm_store(m[0], _mm_mul_ps(glmm_load(m[0]), x0));
+  glmm_store(m[1], _mm_mul_ps(glmm_load(m[1]), x0));
+  glmm_store(m[2], _mm_mul_ps(glmm_load(m[2]), x0));
+  glmm_store(m[3], _mm_mul_ps(glmm_load(m[3]), x0));
 }
 
 CGLM_INLINE
 void
-glm_mat4_transp_sse2(mat4 m, mat4 dest){
+glm_mat4_transp_sse2(const mat4 m, mat4 dest) {
   __m128 r0, r1, r2, r3;
 
-  r0 = _mm_load_ps(m[0]);
-  r1 = _mm_load_ps(m[1]);
-  r2 = _mm_load_ps(m[2]);
-  r3 = _mm_load_ps(m[3]);
+  r0 = glmm_load(m[0]);
+  r1 = glmm_load(m[1]);
+  r2 = glmm_load(m[2]);
+  r3 = glmm_load(m[3]);
 
   _MM_TRANSPOSE4_PS(r0, r1, r2, r3);
 
-  _mm_store_ps(dest[0], r0);
-  _mm_store_ps(dest[1], r1);
-  _mm_store_ps(dest[2], r2);
-  _mm_store_ps(dest[3], r3);
+  glmm_store(dest[0], r0);
+  glmm_store(dest[1], r1);
+  glmm_store(dest[2], r2);
+  glmm_store(dest[3], r3);
 }
 
 CGLM_INLINE
 void
-glm_mat4_mul_sse2(mat4 m1, mat4 m2, mat4 dest) {
+glm_mat4_mul_sse2(const mat4 m1, const mat4 m2, mat4 dest) {
   /* D = R * L (Column-Major) */
 
   __m128 l0, l1, l2, l3, r;
 
-  l0 = _mm_load_ps(m1[0]);
-  l1 = _mm_load_ps(m1[1]);
-  l2 = _mm_load_ps(m1[2]);
-  l3 = _mm_load_ps(m1[3]);
+  l0 = glmm_load(m1[0]);
+  l1 = glmm_load(m1[1]);
+  l2 = glmm_load(m1[2]);
+  l3 = glmm_load(m1[3]);
 
-  r = _mm_load_ps(m2[0]);
-  _mm_store_ps(dest[0],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 3), l3))));
-  r = _mm_load_ps(m2[1]);
-  _mm_store_ps(dest[1],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 3), l3))));
-  r = _mm_load_ps(m2[2]);
-  _mm_store_ps(dest[2],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 3), l3))));
+  r = glmm_load(m2[0]);
+  glmm_store(dest[0],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
+  r = glmm_load(m2[1]);
+  glmm_store(dest[1],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
+  r = glmm_load(m2[2]);
+  glmm_store(dest[2],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
 
-  r = _mm_load_ps(m2[3]);
-  _mm_store_ps(dest[3],
-               _mm_add_ps(_mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 0), l0),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 1), l1)),
-                          _mm_add_ps(_mm_mul_ps(_mm_shuffle1_ps1(r, 2), l2),
-                                     _mm_mul_ps(_mm_shuffle1_ps1(r, 3), l3))));
+  r = glmm_load(m2[3]);
+  glmm_store(dest[3],
+             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
 }
 
 CGLM_INLINE
 void
-glm_mat4_mulv_sse2(mat4 m, vec4 v, vec4 dest) {
+glm_mat4_mulv_sse2(const mat4 m, const vec4 v, vec4 dest) {
   __m128 x0, x1, x2;
 
-  x0 = _mm_load_ps(v);
-  x1 = _mm_add_ps(_mm_mul_ps(_mm_load_ps(m[0]),
-                             _mm_shuffle1_ps1(x0, 0)),
-                  _mm_mul_ps(_mm_load_ps(m[1]),
-                             _mm_shuffle1_ps1(x0, 1)));
+  x0 = glmm_load(v);
+  x1 = _mm_add_ps(_mm_mul_ps(glmm_load(m[0]), glmm_shuff1x(x0, 0)),
+                  _mm_mul_ps(glmm_load(m[1]), glmm_shuff1x(x0, 1)));
 
-  x2 = _mm_add_ps(_mm_mul_ps(_mm_load_ps(m[2]),
-                             _mm_shuffle1_ps1(x0, 2)),
-                  _mm_mul_ps(_mm_load_ps(m[3]),
-                             _mm_shuffle1_ps1(x0, 3)));
+  x2 = _mm_add_ps(_mm_mul_ps(glmm_load(m[2]), glmm_shuff1x(x0, 2)),
+                  _mm_mul_ps(glmm_load(m[3]), glmm_shuff1x(x0, 3)));
 
-  _mm_store_ps(dest, _mm_add_ps(x1, x2));
+  glmm_store(dest, _mm_add_ps(x1, x2));
 }
 
 CGLM_INLINE
 float
-glm_mat4_det_sse2(mat4 mat) {
+glm_mat4_det_sse2(const mat4 mat) {
   __m128 r0, r1, r2, r3, x0, x1, x2;
 
   /* 127 <- 0, [square] det(A) = det(At) */
-  r0 = _mm_load_ps(mat[0]); /* d c b a */
-  r1 = _mm_load_ps(mat[1]); /* h g f e */
-  r2 = _mm_load_ps(mat[2]); /* l k j i */
-  r3 = _mm_load_ps(mat[3]); /* p o n m */
+  r0 = glmm_load(mat[0]); /* d c b a */
+  r1 = glmm_load(mat[1]); /* h g f e */
+  r2 = glmm_load(mat[2]); /* l k j i */
+  r3 = glmm_load(mat[3]); /* p o n m */
 
   /*
    t[1] = j * p - n * l;
@@ -119,20 +115,20 @@ glm_mat4_det_sse2(mat4 mat) {
    t[3] = i * p - m * l;
    t[4] = i * o - m * k;
    */
-  x0 = _mm_sub_ps(_mm_mul_ps(_mm_shuffle1_ps(r2, 0, 0, 1, 1),
-                             _mm_shuffle1_ps(r3, 2, 3, 2, 3)),
-                  _mm_mul_ps(_mm_shuffle1_ps(r3, 0, 0, 1, 1),
-                             _mm_shuffle1_ps(r2, 2, 3, 2, 3)));
+  x0 = _mm_sub_ps(_mm_mul_ps(glmm_shuff1(r2, 0, 0, 1, 1),
+                             glmm_shuff1(r3, 2, 3, 2, 3)),
+                  _mm_mul_ps(glmm_shuff1(r3, 0, 0, 1, 1),
+                             glmm_shuff1(r2, 2, 3, 2, 3)));
   /*
    t[0] = k * p - o * l;
    t[0] = k * p - o * l;
    t[5] = i * n - m * j;
    t[5] = i * n - m * j;
    */
-  x1 = _mm_sub_ps(_mm_mul_ps(_mm_shuffle1_ps(r2, 0, 0, 2, 2),
-                             _mm_shuffle1_ps(r3, 1, 1, 3, 3)),
-                  _mm_mul_ps(_mm_shuffle1_ps(r3, 0, 0, 2, 2),
-                             _mm_shuffle1_ps(r2, 1, 1, 3, 3)));
+  x1 = _mm_sub_ps(_mm_mul_ps(glmm_shuff1(r2, 0, 0, 2, 2),
+                             glmm_shuff1(r3, 1, 1, 3, 3)),
+                  _mm_mul_ps(glmm_shuff1(r3, 0, 0, 2, 2),
+                             glmm_shuff1(r2, 1, 1, 3, 3)));
 
   /*
      a * (f * t[0] - g * t[1] + h * t[2])
@@ -140,40 +136,40 @@ glm_mat4_det_sse2(mat4 mat) {
    + c * (e * t[1] - f * t[3] + h * t[5])
    - d * (e * t[2] - f * t[4] + g * t[5])
    */
-  x2 = _mm_sub_ps(_mm_mul_ps(_mm_shuffle1_ps(r1, 0, 0, 0, 1),
+  x2 = _mm_sub_ps(_mm_mul_ps(glmm_shuff1(r1, 0, 0, 0, 1),
                              _mm_shuffle_ps(x1, x0, _MM_SHUFFLE(1, 0, 0, 0))),
-                  _mm_mul_ps(_mm_shuffle1_ps(r1, 1, 1, 2, 2),
-                             _mm_shuffle1_ps(x0, 3, 2, 2, 0)));
+                  _mm_mul_ps(glmm_shuff1(r1, 1, 1, 2, 2),
+                             glmm_shuff1(x0, 3, 2, 2, 0)));
 
   x2 = _mm_add_ps(x2,
-                  _mm_mul_ps(_mm_shuffle1_ps(r1, 2, 3, 3, 3),
+                  _mm_mul_ps(glmm_shuff1(r1, 2, 3, 3, 3),
                              _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 2, 3, 1))));
   x2 = _mm_xor_ps(x2, _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
 
   x0 = _mm_mul_ps(r0, x2);
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 0, 1, 2, 3));
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 1, 3, 3, 1));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 2, 3));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 3, 3, 1));
 
   return _mm_cvtss_f32(x0);
 }
 
 CGLM_INLINE
 void
-glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
+glm_mat4_inv_fast_sse2(const mat4 mat, mat4 dest) {
   __m128 r0, r1, r2, r3,
          v0, v1, v2, v3,
          t0, t1, t2, t3, t4, t5,
          x0, x1, x2, x3, x4, x5, x6, x7;
 
   /* 127 <- 0 */
-  r0 = _mm_load_ps(mat[0]); /* d c b a */
-  r1 = _mm_load_ps(mat[1]); /* h g f e */
-  r2 = _mm_load_ps(mat[2]); /* l k j i */
-  r3 = _mm_load_ps(mat[3]); /* p o n m */
+  r0 = glmm_load(mat[0]); /* d c b a */
+  r1 = glmm_load(mat[1]); /* h g f e */
+  r2 = glmm_load(mat[2]); /* l k j i */
+  r3 = glmm_load(mat[3]); /* p o n m */
 
   x0 = _mm_shuffle_ps(r2, r3, _MM_SHUFFLE(3, 2, 3, 2));  /* p o l k */
-  x1 = _mm_shuffle1_ps(x0, 1, 3, 3, 3);                  /* l p p p */
-  x2 = _mm_shuffle1_ps(x0, 0, 2, 2, 2);                  /* k o o o */
+  x1 = glmm_shuff1(x0, 1, 3, 3, 3);                      /* l p p p */
+  x2 = glmm_shuff1(x0, 0, 2, 2, 2);                      /* k o o o */
   x0 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(3, 3, 3, 3));  /* h h l l */
   x3 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(2, 2, 2, 2));  /* g g k k */
 
@@ -184,7 +180,7 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
   t0 = _mm_sub_ps(_mm_mul_ps(x3, x1), _mm_mul_ps(x2, x0));
 
   x4 = _mm_shuffle_ps(r2, r3, _MM_SHUFFLE(2, 1, 2, 1)); /* o n k j */
-  x4 = _mm_shuffle1_ps(x4, 0, 2, 2, 2);                 /* j n n n */
+  x4 = glmm_shuff1(x4, 0, 2, 2, 2);                     /* j n n n */
   x5 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(1, 1, 1, 1)); /* f f j j */
 
   /* t1[1] = j * p - n * l;
@@ -200,7 +196,7 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
   t2 = _mm_sub_ps(_mm_mul_ps(x5, x2), _mm_mul_ps(x4, x3));
 
   x6 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(0, 0, 0, 0)); /* e e i i */
-  x7 = _mm_shuffle2_ps(r3, r2, 0, 0, 0, 0, 2, 0, 0, 0); /* i m m m */
+  x7 = glmm_shuff2(r3, r2, 0, 0, 0, 0, 2, 0, 0, 0);     /* i m m m */
 
   /* t1[3] = i * p - m * l;
      t1[3] = i * p - m * l;
@@ -220,10 +216,10 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
      t3[5] = e * j - i * f; */
   t5 = _mm_sub_ps(_mm_mul_ps(x6, x4), _mm_mul_ps(x7, x5));
 
-  x0 = _mm_shuffle2_ps(r1, r0, 0, 0, 0, 0, 2, 2, 2, 0); /* a a a e */
-  x1 = _mm_shuffle2_ps(r1, r0, 1, 1, 1, 1, 2, 2, 2, 0); /* b b b f */
-  x2 = _mm_shuffle2_ps(r1, r0, 2, 2, 2, 2, 2, 2, 2, 0); /* c c c g */
-  x3 = _mm_shuffle2_ps(r1, r0, 3, 3, 3, 3, 2, 2, 2, 0); /* d d d h */
+  x0 = glmm_shuff2(r1, r0, 0, 0, 0, 0, 2, 2, 2, 0); /* a a a e */
+  x1 = glmm_shuff2(r1, r0, 1, 1, 1, 1, 2, 2, 2, 0); /* b b b f */
+  x2 = glmm_shuff2(r1, r0, 2, 2, 2, 2, 2, 2, 2, 0); /* c c c g */
+  x3 = glmm_shuff2(r1, r0, 3, 3, 3, 3, 2, 2, 2, 0); /* d d d h */
 
   /*
    dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
@@ -271,33 +267,33 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
   x0 = _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 0, 2, 0));
 
   x0 = _mm_mul_ps(x0, r0);
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 0, 1, 2, 3));
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 1, 0, 0, 1));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 2, 3));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 0, 0, 1));
   x0 = _mm_rcp_ps(x0);
 
-  _mm_store_ps(dest[0], _mm_mul_ps(v0, x0));
-  _mm_store_ps(dest[1], _mm_mul_ps(v1, x0));
-  _mm_store_ps(dest[2], _mm_mul_ps(v2, x0));
-  _mm_store_ps(dest[3], _mm_mul_ps(v3, x0));
+  glmm_store(dest[0], _mm_mul_ps(v0, x0));
+  glmm_store(dest[1], _mm_mul_ps(v1, x0));
+  glmm_store(dest[2], _mm_mul_ps(v2, x0));
+  glmm_store(dest[3], _mm_mul_ps(v3, x0));
 }
 
 CGLM_INLINE
 void
-glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
+glm_mat4_inv_sse2(const mat4 mat, mat4 dest) {
   __m128 r0, r1, r2, r3,
          v0, v1, v2, v3,
          t0, t1, t2, t3, t4, t5,
          x0, x1, x2, x3, x4, x5, x6, x7;
 
   /* 127 <- 0 */
-  r0 = _mm_load_ps(mat[0]); /* d c b a */
-  r1 = _mm_load_ps(mat[1]); /* h g f e */
-  r2 = _mm_load_ps(mat[2]); /* l k j i */
-  r3 = _mm_load_ps(mat[3]); /* p o n m */
+  r0 = glmm_load(mat[0]); /* d c b a */
+  r1 = glmm_load(mat[1]); /* h g f e */
+  r2 = glmm_load(mat[2]); /* l k j i */
+  r3 = glmm_load(mat[3]); /* p o n m */
 
   x0 = _mm_shuffle_ps(r2, r3, _MM_SHUFFLE(3, 2, 3, 2));  /* p o l k */
-  x1 = _mm_shuffle1_ps(x0, 1, 3, 3, 3);                  /* l p p p */
-  x2 = _mm_shuffle1_ps(x0, 0, 2, 2, 2);                  /* k o o o */
+  x1 = glmm_shuff1(x0, 1, 3, 3, 3);                      /* l p p p */
+  x2 = glmm_shuff1(x0, 0, 2, 2, 2);                      /* k o o o */
   x0 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(3, 3, 3, 3));  /* h h l l */
   x3 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(2, 2, 2, 2));  /* g g k k */
 
@@ -308,7 +304,7 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
   t0 = _mm_sub_ps(_mm_mul_ps(x3, x1), _mm_mul_ps(x2, x0));
 
   x4 = _mm_shuffle_ps(r2, r3, _MM_SHUFFLE(2, 1, 2, 1)); /* o n k j */
-  x4 = _mm_shuffle1_ps(x4, 0, 2, 2, 2);                 /* j n n n */
+  x4 = glmm_shuff1(x4, 0, 2, 2, 2);                     /* j n n n */
   x5 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(1, 1, 1, 1)); /* f f j j */
 
   /* t1[1] = j * p - n * l;
@@ -324,7 +320,7 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
   t2 = _mm_sub_ps(_mm_mul_ps(x5, x2), _mm_mul_ps(x4, x3));
 
   x6 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(0, 0, 0, 0)); /* e e i i */
-  x7 = _mm_shuffle2_ps(r3, r2, 0, 0, 0, 0, 2, 0, 0, 0); /* i m m m */
+  x7 = glmm_shuff2(r3, r2, 0, 0, 0, 0, 2, 0, 0, 0);     /* i m m m */
 
   /* t1[3] = i * p - m * l;
      t1[3] = i * p - m * l;
@@ -344,10 +340,10 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
      t3[5] = e * j - i * f; */
   t5 = _mm_sub_ps(_mm_mul_ps(x6, x4), _mm_mul_ps(x7, x5));
 
-  x0 = _mm_shuffle2_ps(r1, r0, 0, 0, 0, 0, 2, 2, 2, 0); /* a a a e */
-  x1 = _mm_shuffle2_ps(r1, r0, 1, 1, 1, 1, 2, 2, 2, 0); /* b b b f */
-  x2 = _mm_shuffle2_ps(r1, r0, 2, 2, 2, 2, 2, 2, 2, 0); /* c c c g */
-  x3 = _mm_shuffle2_ps(r1, r0, 3, 3, 3, 3, 2, 2, 2, 0); /* d d d h */
+  x0 = glmm_shuff2(r1, r0, 0, 0, 0, 0, 2, 2, 2, 0); /* a a a e */
+  x1 = glmm_shuff2(r1, r0, 1, 1, 1, 1, 2, 2, 2, 0); /* b b b f */
+  x2 = glmm_shuff2(r1, r0, 2, 2, 2, 2, 2, 2, 2, 0); /* c c c g */
+  x3 = glmm_shuff2(r1, r0, 3, 3, 3, 3, 2, 2, 2, 0); /* d d d h */
 
   /*
    dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
@@ -395,14 +391,14 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
   x0 = _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 0, 2, 0));
 
   x0 = _mm_mul_ps(x0, r0);
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 0, 1, 2, 3));
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 1, 0, 0, 1));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 2, 3));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 0, 0, 1));
   x0 = _mm_div_ps(_mm_set1_ps(1.0f), x0);
 
-  _mm_store_ps(dest[0], _mm_mul_ps(v0, x0));
-  _mm_store_ps(dest[1], _mm_mul_ps(v1, x0));
-  _mm_store_ps(dest[2], _mm_mul_ps(v2, x0));
-  _mm_store_ps(dest[3], _mm_mul_ps(v3, x0));
+  glmm_store(dest[0], _mm_mul_ps(v0, x0));
+  glmm_store(dest[1], _mm_mul_ps(v1, x0));
+  glmm_store(dest[2], _mm_mul_ps(v2, x0));
+  glmm_store(dest[3], _mm_mul_ps(v3, x0));
 }
 
 #endif

include/cglm/simd/sse2/quat.h

@@ -14,7 +14,7 @@
 
 CGLM_INLINE
 void
-glm_quat_mul_sse2(versor p, versor q, versor dest) {
+glm_quat_mul_sse2(const versor p, const versor q, versor dest) {
   /*
    + (a1 b2 + b1 a2 + c1 d2 − d1 c2)i
    + (a1 c2 − b1 d2 + c1 a2 + d1 b2)j
@@ -24,21 +24,21 @@ glm_quat_mul_sse2(versor p, versor q, versor dest) {
 
   __m128 xp, xq, x0, r;
 
-  xp = _mm_load_ps(p); /* 3 2 1 0 */
-  xq = _mm_load_ps(q);
+  xp = glmm_load(p); /* 3 2 1 0 */
+  xq = glmm_load(q);
 
-  r  = _mm_mul_ps(_mm_shuffle1_ps1(xp, 3), xq);
+  r  = _mm_mul_ps(glmm_shuff1x(xp, 3), xq);
 
-  x0 = _mm_xor_ps(_mm_shuffle1_ps1(xp, 0), _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
-  r  = _mm_add_ps(r, _mm_mul_ps(x0, _mm_shuffle1_ps(xq, 0, 1, 2, 3)));
+  x0 = _mm_xor_ps(glmm_shuff1x(xp, 0), _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
+  r  = _mm_add_ps(r, _mm_mul_ps(x0, glmm_shuff1(xq, 0, 1, 2, 3)));
 
-  x0 = _mm_xor_ps(_mm_shuffle1_ps1(xp, 1), _mm_set_ps(-0.f, -0.f, 0.f, 0.f));
-  r  = _mm_add_ps(r, _mm_mul_ps(x0, _mm_shuffle1_ps(xq, 1, 0, 3, 2)));
+  x0 = _mm_xor_ps(glmm_shuff1x(xp, 1), _mm_set_ps(-0.f, -0.f, 0.f, 0.f));
+  r  = _mm_add_ps(r, _mm_mul_ps(x0, glmm_shuff1(xq, 1, 0, 3, 2)));
 
-  x0 = _mm_xor_ps(_mm_shuffle1_ps1(xp, 2), _mm_set_ps(-0.f, 0.f, 0.f, -0.f));
-  r  = _mm_add_ps(r, _mm_mul_ps(x0, _mm_shuffle1_ps(xq, 2, 3, 0, 1)));
+  x0 = _mm_xor_ps(glmm_shuff1x(xp, 2), _mm_set_ps(-0.f, 0.f, 0.f, -0.f));
+  r  = _mm_add_ps(r, _mm_mul_ps(x0, glmm_shuff1(xq, 2, 3, 0, 1)));
 
-  _mm_store_ps(dest, r);
+  glmm_store(dest, r);
 }
 
 

include/cglm/simd/x86.h

@@ -0,0 +1,136 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_simd_x86_h
+#define cglm_simd_x86_h
+#include "intrin.h"
+#ifdef CGLM_SIMD_x86
+
+#ifdef CGLM_ALL_UNALIGNED
+#  define glmm_load(p)      _mm_loadu_ps(p)
+#  define glmm_store(p, a)  _mm_storeu_ps(p, a)
+#else
+#  define glmm_load(p)      _mm_load_ps(p)
+#  define glmm_store(p, a)  _mm_store_ps(p, a)
+#endif
+
+#ifdef CGLM_USE_INT_DOMAIN
+#  define glmm_shuff1(xmm, z, y, x, w)                                        \
+     _mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(xmm),                \
+                                        _MM_SHUFFLE(z, y, x, w)))
+#else
+#  define glmm_shuff1(xmm, z, y, x, w)                                        \
+       _mm_shuffle_ps(xmm, xmm, _MM_SHUFFLE(z, y, x, w))
+#endif
+
+#define glmm_shuff1x(xmm, x) glmm_shuff1(xmm, x, x, x, x)
+#define glmm_shuff2(a, b, z0, y0, x0, w0, z1, y1, x1, w1)                     \
+     glmm_shuff1(_mm_shuffle_ps(a, b, _MM_SHUFFLE(z0, y0, x0, w0)),           \
+                 z1, y1, x1, w1)
+
+#ifdef __AVX__
+#  ifdef CGLM_ALL_UNALIGNED
+#    define glmm_load256(p)      _mm256_loadu_ps(p)
+#    define glmm_store256(p, a)  _mm256_storeu_ps(p, a)
+#  else
+#    define glmm_load256(p)      _mm256_load_ps(p)
+#    define glmm_store256(p, a)  _mm256_store_ps(p, a)
+#  endif
+#endif
+
+static inline
+__m128
+glmm_vhadds(__m128 v) {
+#if defined(__SSE3__)
+  __m128 shuf, sums;
+  shuf = _mm_movehdup_ps(v);
+  sums = _mm_add_ps(v, shuf);
+  shuf = _mm_movehl_ps(shuf, sums);
+  sums = _mm_add_ss(sums, shuf);
+  return sums;
+#else
+  __m128 shuf, sums;
+  shuf = glmm_shuff1(v, 2, 3, 0, 1);
+  sums = _mm_add_ps(v, shuf);
+  shuf = _mm_movehl_ps(shuf, sums);
+  sums = _mm_add_ss(sums, shuf);
+  return sums;
+#endif
+}
+
+static inline
+float
+glmm_hadd(__m128 v) {
+  return _mm_cvtss_f32(glmm_vhadds(v));
+}
+
+static inline
+__m128
+glmm_vdots(__m128 a, __m128 b) {
+#if (defined(__SSE4_1__) || defined(__SSE4_2__)) && defined(CGLM_SSE4_DOT)
+  return _mm_dp_ps(a, b, 0xFF);
+#elif defined(__SSE3__) && defined(CGLM_SSE3_DOT)
+  __m128 x0, x1;
+  x0 = _mm_mul_ps(a, b);
+  x1 = _mm_hadd_ps(x0, x0);
+  return _mm_hadd_ps(x1, x1);
+#else
+  return glmm_vhadds(_mm_mul_ps(a, b));
+#endif
+}
+
+static inline
+__m128
+glmm_vdot(__m128 a, __m128 b) {
+#if (defined(__SSE4_1__) || defined(__SSE4_2__)) && defined(CGLM_SSE4_DOT)
+  return _mm_dp_ps(a, b, 0xFF);
+#elif defined(__SSE3__) && defined(CGLM_SSE3_DOT)
+  __m128 x0, x1;
+  x0 = _mm_mul_ps(a, b);
+  x1 = _mm_hadd_ps(x0, x0);
+  return _mm_hadd_ps(x1, x1);
+#else
+  __m128 x0;
+  x0 = _mm_mul_ps(a, b);
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 0, 3, 2));
+  return _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 0, 1));
+#endif
+}
+
+static inline
+float
+glmm_dot(const __m128 a, const __m128 b) {
+  return _mm_cvtss_f32(glmm_vdots(a, b));
+}
+
+static inline
+float
+glmm_norm(__m128 a) {
+  return _mm_cvtss_f32(_mm_sqrt_ss(glmm_vhadds(_mm_mul_ps(a, a))));
+}
+
+static inline
+__m128
+glmm_load3(const float v[3]) {
+  __m128i xy;
+  __m128  z;
+
+  xy = _mm_loadl_epi64((const __m128i *)v);
+  z  = _mm_load_ss(&v[2]);
+
+  return _mm_movelh_ps(_mm_castsi128_ps(xy), z);
+}
+
+static inline
+void
+glmm_store3(__m128 vx, float v[3]) {
+  _mm_storel_pi((__m64 *)&v[0], vx);
+  _mm_store_ss(&v[2], glmm_shuff1(vx, 2, 2, 2, 2));
+}
+
+#endif
+#endif /* cglm_simd_x86_h */

include/cglm/sphere.h

@@ -0,0 +1,99 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_sphere_h
+#define cglm_sphere_h
+
+#include "common.h"
+#include "mat4.h"
+
+/*
+  Sphere Representation in cglm: [center.x, center.y, center.z, radii]
+
+  You could use this representation or you can convert it to vec4 before call
+  any function
+ */
+
+/*!
+ * @brief helper for getting sphere radius
+ *
+ * @param[in]   s  sphere
+ *
+ * @return returns radii
+ */
+CGLM_INLINE
+float
+glm_sphere_radii(const vec4 s) {
+  return s[3];
+}
+
+/*!
+ * @brief apply transform to sphere, it is just wrapper for glm_mat4_mulv3
+ *
+ * @param[in]  s    sphere
+ * @param[in]  m    transform matrix
+ * @param[out] dest transformed sphere
+ */
+CGLM_INLINE
+void
+glm_sphere_transform(const vec4 s, const mat4 m, vec4 dest) {
+  glm_mat4_mulv3(m, s, 1.0f, dest);
+  dest[3] = s[3];
+}
+
+/*!
+ * @brief merges two spheres and creates a new one
+ *
+ * two sphere must be in same space, for instance if one in world space then
+ * the other must be in world space too, not in local space.
+ *
+ * @param[in]  s1   sphere 1
+ * @param[in]  s2   sphere 2
+ * @param[out] dest merged/extended sphere
+ */
+CGLM_INLINE
+void
+glm_sphere_merge(const vec4 s1, const vec4 s2, vec4 dest) {
+  float dist, radii;
+
+  dist  = glm_vec3_distance(s1, s2);
+  radii = dist + s1[3] + s2[3];
+
+  radii = glm_max(radii, s1[3]);
+  radii = glm_max(radii, s2[3]);
+
+  glm_vec3_center(s1, s2, dest);
+  dest[3] = radii;
+}
+
+/*!
+ * @brief check if two sphere intersects
+ *
+ * @param[in]   s1  sphere
+ * @param[in]   s2  other sphere
+ */
+CGLM_INLINE
+bool
+glm_sphere_sphere(const vec4 s1, const vec4 s2) {
+  return glm_vec3_distance2(s1, s2) <= glm_pow2(s1[3] + s2[3]);
+}
+
+/*!
+ * @brief check if sphere intersects with point
+ *
+ * @param[in]   s      sphere
+ * @param[in]   point  point
+ */
+CGLM_INLINE
+bool
+glm_sphere_point(const vec4 s, const vec3 point) {
+  float rr;
+  rr = s[3] * s[3];
+  return glm_vec3_distance2(point, s) <= rr;
+}
+
+#endif /* cglm_sphere_h */

include/cglm/types.h

@@ -9,23 +9,73 @@
 #define cglm_types_h
 
 #if defined(_MSC_VER)
-#  define CGLM_ALIGN(X) /* __declspec(align(X)) */
+/* do not use alignment for older visual studio versions */
+#  if _MSC_VER < 1913 /*  Visual Studio 2017 version 15.6  */
+#    define CGLM_ALL_UNALIGNED
+#    define CGLM_ALIGN(X) /* no alignment */
+#  else
+#    define CGLM_ALIGN(X) __declspec(align(X))
+#  endif
 #else
 #  define CGLM_ALIGN(X) __attribute((aligned(X)))
 #endif
 
+#ifndef CGLM_ALL_UNALIGNED
+#  define CGLM_ALIGN_IF(X) CGLM_ALIGN(X)
+#else
+#  define CGLM_ALIGN_IF(X) /* no alignment */
+#endif
+
+#ifdef __AVX__
+#  define CGLM_ALIGN_MAT CGLM_ALIGN(32)
+#else
+#  define CGLM_ALIGN_MAT CGLM_ALIGN(16)
+#endif
+
 typedef float                   vec2[2];
 typedef float                   vec3[3];
 typedef int                    ivec3[3];
-typedef CGLM_ALIGN(16) float vec4[4];
-
-typedef vec3 mat3[3];
-typedef vec4 mat4[4];
-
+typedef CGLM_ALIGN_IF(16) float vec4[4];
 typedef vec4                    versor;
+typedef vec3                    mat3[3];
 
-#define CGLM_PI    (float)M_PI
-#define CGLM_PI_2  (float)M_PI_2
-#define CGLM_PI_4  (float)M_PI_4
+#ifdef __AVX__
+typedef CGLM_ALIGN_IF(32) vec4  mat4[4];
+#else
+typedef CGLM_ALIGN_IF(16) vec4  mat4[4];
+#endif
+
+#define GLM_E         2.71828182845904523536028747135266250   /* e           */
+#define GLM_LOG2E     1.44269504088896340735992468100189214   /* log2(e)     */
+#define GLM_LOG10E    0.434294481903251827651128918916605082  /* log10(e)    */
+#define GLM_LN2       0.693147180559945309417232121458176568  /* loge(2)     */
+#define GLM_LN10      2.30258509299404568401799145468436421   /* loge(10)    */
+#define GLM_PI        3.14159265358979323846264338327950288   /* pi          */
+#define GLM_PI_2      1.57079632679489661923132169163975144   /* pi/2        */
+#define GLM_PI_4      0.785398163397448309615660845819875721  /* pi/4        */
+#define GLM_1_PI      0.318309886183790671537767526745028724  /* 1/pi        */
+#define GLM_2_PI      0.636619772367581343075535053490057448  /* 2/pi        */
+#define GLM_2_SQRTPI  1.12837916709551257389615890312154517   /* 2/sqrt(pi)  */
+#define GLM_SQRT2     1.41421356237309504880168872420969808   /* sqrt(2)     */
+#define GLM_SQRT1_2   0.707106781186547524400844362104849039  /* 1/sqrt(2)   */
+
+#define GLM_Ef        ((float)GLM_E)
+#define GLM_LOG2Ef    ((float)GLM_LOG2E)
+#define GLM_LOG10Ef   ((float)GLM_LOG10E)
+#define GLM_LN2f      ((float)GLM_LN2)
+#define GLM_LN10f     ((float)GLM_LN10)
+#define GLM_PIf       ((float)GLM_PI)
+#define GLM_PI_2f     ((float)GLM_PI_2)
+#define GLM_PI_4f     ((float)GLM_PI_4)
+#define GLM_1_PIf     ((float)GLM_1_PI)
+#define GLM_2_PIf     ((float)GLM_2_PI)
+#define GLM_2_SQRTPIf ((float)GLM_2_SQRTPI)
+#define GLM_SQRT2f    ((float)GLM_SQRT2)
+#define GLM_SQRT1_2f  ((float)GLM_SQRT1_2)
+
+/* DEPRECATED! use GLM_PI and friends */
+#define CGLM_PI       GLM_PIf
+#define CGLM_PI_2     GLM_PI_2f
+#define CGLM_PI_4     GLM_PI_4f
 
 #endif /* cglm_types_h */

include/cglm/util.h

@@ -20,6 +20,9 @@
 
 #include "common.h"
 
+#define GLM_MIN(X, Y) (((X) < (Y)) ? (X) : (Y))
+#define GLM_MAX(X, Y) (((X) > (Y)) ? (X) : (Y))
+
 /*!
  * @brief get sign of 32 bit integer as +1, -1, 0
  *
@@ -54,7 +57,7 @@ glm_signf(float val) {
 CGLM_INLINE
 float
 glm_rad(float deg) {
-  return deg * CGLM_PI / 180.0f;
+  return deg * GLM_PIf / 180.0f;
 }
 
 /*!
@@ -65,7 +68,7 @@ glm_rad(float deg) {
 CGLM_INLINE
 float
 glm_deg(float rad) {
-  return rad * 180.0f / CGLM_PI;
+  return rad * 180.0f / GLM_PIf;
 }
 
 /*!
@@ -76,7 +79,7 @@ glm_deg(float rad) {
 CGLM_INLINE
 void
 glm_make_rad(float *deg) {
-  *deg = *deg * CGLM_PI / 180.0f;
+  *deg = *deg * GLM_PIf / 180.0f;
 }
 
 /*!
@@ -87,7 +90,7 @@ glm_make_rad(float *deg) {
 CGLM_INLINE
 void
 glm_make_deg(float *rad) {
-  *rad = *rad * 180.0f / CGLM_PI;
+  *rad = *rad * 180.0f / GLM_PIf;
 }
 
 /*!
@@ -98,7 +101,6 @@ glm_make_deg(float *rad) {
 CGLM_INLINE
 float
 glm_pow2(float x) {
-
   return x * x;
 }
 
@@ -143,6 +145,17 @@ glm_clamp(float val, float minVal, float maxVal) {
   return glm_min(glm_max(val, minVal), maxVal);
 }
 
+/*!
+ * @brief clamp a number to zero and one
+ *
+ * @param[in] val value to clamp
+ */
+CGLM_INLINE
+float
+glm_clamp_zo(float val) {
+  return glm_clamp(val, 0.0f, 1.0f);
+}
+
 /*!
  * @brief linear interpolation between two number
  *
@@ -155,7 +168,52 @@ glm_clamp(float val, float minVal, float maxVal) {
 CGLM_INLINE
 float
 glm_lerp(float from, float to, float t) {
-  return from + glm_clamp(t, 0.0f, 1.0f) * (to - from);
+  return from + glm_clamp_zo(t) * (to - from);
+}
+
+/*!
+ * @brief check if two float equal with using EPSILON
+ *
+ * @param[in]   a   a
+ * @param[in]   b   b
+ */
+CGLM_INLINE
+bool
+glm_eq(float a, float b) {
+  return fabsf(a - b) <= FLT_EPSILON;
+}
+
+/*!
+ * @brief percentage of current value between start and end value
+ *
+ * maybe fraction could be alternative name.
+ *
+ * @param[in]   from    from value
+ * @param[in]   to      to value
+ * @param[in]   current current value
+ */
+CGLM_INLINE
+float
+glm_percent(float from, float to, float current) {
+  float t;
+
+  if ((t = to - from) == 0.0f)
+    return 1.0f;
+
+  return (current - from) / t;
+}
+
+/*!
+ * @brief clamped percentage of current value between start and end value
+ *
+ * @param[in]   from    from value
+ * @param[in]   to      to value
+ * @param[in]   current current value
+ */
+CGLM_INLINE
+float
+glm_percentc(float from, float to, float current) {
+  return glm_clamp(glm_percent(from, to, current), 0.0f, 1.0f);
 }
 
 #endif /* cglm_util_h */

include/cglm/vec3-ext.h

@@ -11,15 +11,19 @@
 
 /*
  Functions:
-   CGLM_INLINE void  glm_vec_mulv(vec3 a, vec3 b, vec3 d);
-   CGLM_INLINE void  glm_vec_broadcast(float val, vec3 d);
-   CGLM_INLINE bool  glm_vec_eq(vec3 v, float val);
-   CGLM_INLINE bool  glm_vec_eq_eps(vec3 v, float val);
-   CGLM_INLINE bool  glm_vec_eq_all(vec3 v);
-   CGLM_INLINE bool  glm_vec_eqv(vec3 v1, vec3 v2);
-   CGLM_INLINE bool  glm_vec_eqv_eps(vec3 v1, vec3 v2);
-   CGLM_INLINE float glm_vec_max(vec3 v);
-   CGLM_INLINE float glm_vec_min(vec3 v);
+   CGLM_INLINE void  glm_vec3_broadcast(float val, vec3 d);
+   CGLM_INLINE bool  glm_vec3_eq(vec3 v, float val);
+   CGLM_INLINE bool  glm_vec3_eq_eps(vec3 v, float val);
+   CGLM_INLINE bool  glm_vec3_eq_all(vec3 v);
+   CGLM_INLINE bool  glm_vec3_eqv(vec3 a, vec3 b);
+   CGLM_INLINE bool  glm_vec3_eqv_eps(vec3 a, vec3 b);
+   CGLM_INLINE float glm_vec3_max(vec3 v);
+   CGLM_INLINE float glm_vec3_min(vec3 v);
+   CGLM_INLINE bool  glm_vec3_isnan(vec3 v);
+   CGLM_INLINE bool  glm_vec3_isinf(vec3 v);
+   CGLM_INLINE bool  glm_vec3_isvalid(vec3 v);
+   CGLM_INLINE void  glm_vec3_sign(vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_sqrt(vec3 v, vec3 dest);
  */
 
 #ifndef cglm_vec3_ext_h
@@ -27,24 +31,6 @@
 
 #include "common.h"
 #include "util.h"
-#include <stdbool.h>
-#include <math.h>
-#include <float.h>
-
-/*!
- * @brief multiplies individual items, just for convenient like SIMD
- *
- * @param[in]  a vec1
- * @param[in]  b vec2
- * @param[out] d vec3 = (v1[0] * v2[0],  v1[1] * v2[1], v1[2] * v2[2])
- */
-CGLM_INLINE
-void
-glm_vec_mulv(vec3 a, vec3 b, vec3 d) {
-  d[0] = a[0] * b[0];
-  d[1] = a[1] * b[1];
-  d[2] = a[2] * b[2];
-}
 
 /*!
  * @brief fill a vector with specified value
@@ -54,7 +40,7 @@ glm_vec_mulv(vec3 a, vec3 b, vec3 d) {
  */
 CGLM_INLINE
 void
-glm_vec_broadcast(float val, vec3 d) {
+glm_vec3_broadcast(float val, vec3 d) {
   d[0] = d[1] = d[2] = val;
 }
 
@@ -66,7 +52,7 @@ glm_vec_broadcast(float val, vec3 d) {
  */
 CGLM_INLINE
 bool
-glm_vec_eq(vec3 v, float val) {
+glm_vec3_eq(const vec3 v, float val) {
   return v[0] == val && v[0] == v[1] && v[0] == v[2];
 }
 
@@ -78,7 +64,7 @@ glm_vec_eq(vec3 v, float val) {
  */
 CGLM_INLINE
 bool
-glm_vec_eq_eps(vec3 v, float val) {
+glm_vec3_eq_eps(const vec3 v, float val) {
   return fabsf(v[0] - val) <= FLT_EPSILON
          && fabsf(v[1] - val) <= FLT_EPSILON
          && fabsf(v[2] - val) <= FLT_EPSILON;
@@ -91,36 +77,36 @@ glm_vec_eq_eps(vec3 v, float val) {
  */
 CGLM_INLINE
 bool
-glm_vec_eq_all(vec3 v) {
+glm_vec3_eq_all(const vec3 v) {
   return v[0] == v[1] && v[0] == v[2];
 }
 
 /*!
  * @brief check if vector is equal to another (without epsilon)
  *
- * @param[in] v1 vector
- * @param[in] v2 vector
+ * @param[in] a vector
+ * @param[in] b vector
  */
 CGLM_INLINE
 bool
-glm_vec_eqv(vec3 v1, vec3 v2) {
-  return v1[0] == v2[0]
-        && v1[1] == v2[1]
-        && v1[2] == v2[2];
+glm_vec3_eqv(const vec3 a, const vec3 b) {
+  return a[0] == b[0]
+         && a[1] == b[1]
+         && a[2] == b[2];
 }
 
 /*!
  * @brief check if vector is equal to another (with epsilon)
  *
- * @param[in] v1 vector
- * @param[in] v2 vector
+ * @param[in] a vector
+ * @param[in] b vector
  */
 CGLM_INLINE
 bool
-glm_vec_eqv_eps(vec3 v1, vec3 v2) {
-  return fabsf(v1[0] - v2[0]) <= FLT_EPSILON
-         && fabsf(v1[1] - v2[1]) <= FLT_EPSILON
-         && fabsf(v1[2] - v2[2]) <= FLT_EPSILON;
+glm_vec3_eqv_eps(const vec3 a, const vec3 b) {
+  return fabsf(a[0] - b[0]) <= FLT_EPSILON
+         && fabsf(a[1] - b[1]) <= FLT_EPSILON
+         && fabsf(a[2] - b[2]) <= FLT_EPSILON;
 }
 
 /*!
@@ -130,7 +116,7 @@ glm_vec_eqv_eps(vec3 v1, vec3 v2) {
  */
 CGLM_INLINE
 float
-glm_vec_max(vec3 v) {
+glm_vec3_max(const vec3 v) {
   float max;
 
   max = v[0];
@@ -149,7 +135,7 @@ glm_vec_max(vec3 v) {
  */
 CGLM_INLINE
 float
-glm_vec_min(vec3 v) {
+glm_vec3_min(const vec3 v) {
   float min;
 
   min = v[0];
@@ -169,7 +155,7 @@ glm_vec_min(vec3 v) {
  */
 CGLM_INLINE
 bool
-glm_vec_isnan(vec3 v) {
+glm_vec3_isnan(const vec3 v) {
   return isnan(v[0]) || isnan(v[1]) || isnan(v[2]);
 }
 
@@ -181,7 +167,7 @@ glm_vec_isnan(vec3 v) {
  */
 CGLM_INLINE
 bool
-glm_vec_isinf(vec3 v) {
+glm_vec3_isinf(const vec3 v) {
   return isinf(v[0]) || isinf(v[1]) || isinf(v[2]);
 }
 
@@ -193,8 +179,8 @@ glm_vec_isinf(vec3 v) {
  */
 CGLM_INLINE
 bool
-glm_vec_isvalid(vec3 v) {
-  return !glm_vec_isnan(v) && !glm_vec_isinf(v);
+glm_vec3_isvalid(const vec3 v) {
+  return !glm_vec3_isnan(v) && !glm_vec3_isinf(v);
 }
 
 /*!
@@ -206,7 +192,7 @@ glm_vec_isvalid(vec3 v) {
  */
 CGLM_INLINE
 void
-glm_vec_sign(vec3 v, vec3 dest) {
+glm_vec3_sign(const vec3 v, vec3 dest) {
   dest[0] = glm_signf(v[0]);
   dest[1] = glm_signf(v[1]);
   dest[2] = glm_signf(v[2]);
@@ -220,7 +206,7 @@ glm_vec_sign(vec3 v, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_sqrt(vec3 v, vec3 dest) {
+glm_vec3_sqrt(const vec3 v, vec3 dest) {
   dest[0] = sqrtf(v[0]);
   dest[1] = sqrtf(v[1]);
   dest[2] = sqrtf(v[2]);

include/cglm/vec3.h

@@ -5,14 +5,8 @@
  * Full license can be found in the LICENSE file
  */
 
-/*!
- * vec3 functions dont have suffix e.g glm_vec_dot (not glm_vec3_dot)
- * all functions without suffix are vec3 functions
- */
-
 /*
  Macros:
-   glm_vec_dup(v, dest)
    GLM_VEC3_ONE_INIT
    GLM_VEC3_ZERO_INIT
    GLM_VEC3_ONE
@@ -23,47 +17,81 @@
 
  Functions:
    CGLM_INLINE void  glm_vec3(vec4 v4, vec3 dest);
-   CGLM_INLINE void  glm_vec_copy(vec3 a, vec3 dest);
-   CGLM_INLINE float glm_vec_dot(vec3 a, vec3 b);
-   CGLM_INLINE void  glm_vec_cross(vec3 a, vec3 b, vec3 d);
-   CGLM_INLINE float glm_vec_norm2(vec3 v);
-   CGLM_INLINE float glm_vec_norm(vec3 vec);
-   CGLM_INLINE void  glm_vec_add(vec3 v1, vec3 v2, vec3 dest);
-   CGLM_INLINE void  glm_vec_sub(vec3 v1, vec3 v2, vec3 dest);
-   CGLM_INLINE void  glm_vec_scale(vec3 v, float s, vec3 dest);
-   CGLM_INLINE void  glm_vec_scale_as(vec3 v, float s, vec3 dest);
-   CGLM_INLINE void  glm_vec_flipsign(vec3 v);
-   CGLM_INLINE void  glm_vec_inv(vec3 v);
-   CGLM_INLINE void  glm_vec_inv_to(vec3 v, vec3 dest);
-   CGLM_INLINE void  glm_vec_normalize(vec3 v);
-   CGLM_INLINE void  glm_vec_normalize_to(vec3 vec, vec3 dest);
-   CGLM_INLINE float glm_vec_distance(vec3 v1, vec3 v2);
-   CGLM_INLINE float glm_vec_angle(vec3 v1, vec3 v2);
-   CGLM_INLINE void  glm_vec_rotate(vec3 v, float angle, vec3 axis);
-   CGLM_INLINE void  glm_vec_rotate_m4(mat4 m, vec3 v, vec3 dest);
-   CGLM_INLINE void  glm_vec_proj(vec3 a, vec3 b, vec3 dest);
-   CGLM_INLINE void  glm_vec_center(vec3 v1, vec3 v2, vec3 dest);
-   CGLM_INLINE void  glm_vec_maxv(vec3 v1, vec3 v2, vec3 dest);
-   CGLM_INLINE void  glm_vec_minv(vec3 v1, vec3 v2, vec3 dest);
-   CGLM_INLINE void  glm_vec_ortho(vec3 v, vec3 dest);
-   CGLM_INLINE void  glm_vec_clamp(vec3 v, float minVal, float maxVal);
+   CGLM_INLINE void  glm_vec3_copy(vec3 a, vec3 dest);
+   CGLM_INLINE void  glm_vec3_zero(vec3 v);
+   CGLM_INLINE void  glm_vec3_one(vec3 v);
+   CGLM_INLINE float glm_vec3_dot(vec3 a, vec3 b);
+   CGLM_INLINE float glm_vec3_norm2(vec3 v);
+   CGLM_INLINE float glm_vec3_norm(vec3 v);
+   CGLM_INLINE void  glm_vec3_add(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_adds(vec3 a, float s, vec3 dest);
+   CGLM_INLINE void  glm_vec3_sub(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_subs(vec3 a, float s, vec3 dest);
+   CGLM_INLINE void  glm_vec3_mul(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_scale(vec3 v, float s, vec3 dest);
+   CGLM_INLINE void  glm_vec3_scale_as(vec3 v, float s, vec3 dest);
+   CGLM_INLINE void  glm_vec3_div(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_divs(vec3 a, float s, vec3 dest);
+   CGLM_INLINE void  glm_vec3_addadd(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_subadd(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_muladd(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_muladds(vec3 a, float s, vec3 dest);
+   CGLM_INLINE void  glm_vec3_maxadd(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_minadd(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_flipsign(vec3 v);
+   CGLM_INLINE void  glm_vec3_flipsign_to(vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_negate_to(vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_negate(vec3 v);
+   CGLM_INLINE void  glm_vec3_inv(vec3 v);
+   CGLM_INLINE void  glm_vec3_inv_to(vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_normalize(vec3 v);
+   CGLM_INLINE void  glm_vec3_normalize_to(vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_cross(vec3 a, vec3 b, vec3 d);
+   CGLM_INLINE void  glm_vec3_crossn(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE float glm_vec3_distance(vec3 a, vec3 b);
+   CGLM_INLINE float glm_vec3_angle(vec3 a, vec3 b);
+   CGLM_INLINE void  glm_vec3_rotate(vec3 v, float angle, vec3 axis);
+   CGLM_INLINE void  glm_vec3_rotate_m4(mat4 m, vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_rotate_m3(mat3 m, vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_proj(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_center(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE float glm_vec3_distance2(vec3 a, vec3 b);
+   CGLM_INLINE void  glm_vec3_maxv(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_minv(vec3 a, vec3 b, vec3 dest);
+   CGLM_INLINE void  glm_vec3_ortho(vec3 v, vec3 dest);
+   CGLM_INLINE void  glm_vec3_clamp(vec3 v, float minVal, float maxVal);
+   CGLM_INLINE void  glm_vec3_lerp(vec3 from, vec3 to, float t, vec3 dest);
 
  Convenient:
    CGLM_INLINE void  glm_cross(vec3 a, vec3 b, vec3 d);
    CGLM_INLINE float glm_dot(vec3 a, vec3 b);
    CGLM_INLINE void  glm_normalize(vec3 v);
    CGLM_INLINE void  glm_normalize_to(vec3 v, vec3 dest);
+
+ DEPRECATED:
+   glm_vec3_dup
+   glm_vec3_flipsign
+   glm_vec3_flipsign_to
+   glm_vec3_inv
+   glm_vec3_inv_to
+   glm_vec3_mulv
  */
 
 #ifndef cglm_vec3_h
 #define cglm_vec3_h
 
 #include "common.h"
+#include "vec4.h"
 #include "vec3-ext.h"
 #include "util.h"
 
 /* DEPRECATED! use _copy, _ucopy versions */
-#define glm_vec_dup(v, dest) glm_vec_copy(v, dest)
+#define glm_vec3_dup(v, dest)         glm_vec3_copy(v, dest)
+#define glm_vec3_flipsign(v)          glm_vec3_negate(v)
+#define glm_vec3_flipsign_to(v, dest) glm_vec3_negate_to(v, dest)
+#define glm_vec3_inv(v)               glm_vec3_negate(v)
+#define glm_vec3_inv_to(v, dest)      glm_vec3_negate_to(v, dest)
+#define glm_vec3_mulv(a, b, d)        glm_vec3_mul(a, b, d)
 
 #define GLM_VEC3_ONE_INIT   {1.0f, 1.0f, 1.0f}
 #define GLM_VEC3_ZERO_INIT  {0.0f, 0.0f, 0.0f}
@@ -83,7 +111,7 @@
  */
 CGLM_INLINE
 void
-glm_vec3(vec4 v4, vec3 dest) {
+glm_vec3(const vec4 v4, vec3 dest) {
   dest[0] = v4[0];
   dest[1] = v4[1];
   dest[2] = v4[2];
@@ -97,12 +125,34 @@ glm_vec3(vec4 v4, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_copy(vec3 a, vec3 dest) {
+glm_vec3_copy(const vec3 a, vec3 dest) {
   dest[0] = a[0];
   dest[1] = a[1];
   dest[2] = a[2];
 }
 
+/*!
+ * @brief make vector zero
+ *
+ * @param[in, out]  v vector
+ */
+CGLM_INLINE
+void
+glm_vec3_zero(vec3 v) {
+  v[0] = v[1] = v[2] = 0.0f;
+}
+
+/*!
+ * @brief make vector one
+ *
+ * @param[in, out]  v vector
+ */
+CGLM_INLINE
+void
+glm_vec3_one(vec3 v) {
+  v[0] = v[1] = v[2] = 1.0f;
+}
+
 /*!
  * @brief vec3 dot product
  *
@@ -113,26 +163,10 @@ glm_vec_copy(vec3 a, vec3 dest) {
  */
 CGLM_INLINE
 float
-glm_vec_dot(vec3 a, vec3 b) {
+glm_vec3_dot(const vec3 a, const vec3 b) {
   return a[0] * b[0] + a[1] * b[1] + a[2] * b[2];
 }
 
-/*!
- * @brief vec3 cross product
- *
- * @param[in]  a source 1
- * @param[in]  b source 2
- * @param[out] d destination
- */
-CGLM_INLINE
-void
-glm_vec_cross(vec3 a, vec3 b, vec3 d) {
-  /* (u2.v3 - u3.v2, u3.v1 - u1.v3, u1.v2 - u2.v1) */
-  d[0] = a[1] * b[2] - a[2] * b[1];
-  d[1] = a[2] * b[0] - a[0] * b[2];
-  d[2] = a[0] * b[1] - a[1] * b[0];
-}
-
 /*!
  * @brief norm * norm (magnitude) of vec
  *
@@ -146,51 +180,96 @@ glm_vec_cross(vec3 a, vec3 b, vec3 d) {
  */
 CGLM_INLINE
 float
-glm_vec_norm2(vec3 v) {
-  return glm_vec_dot(v, v);
+glm_vec3_norm2(const vec3 v) {
+  return glm_vec3_dot(v, v);
 }
 
 /*!
  * @brief norm (magnitude) of vec3
  *
- * @param[in] vec vector
+ * @param[in] v vector
  *
  * @return norm
  */
 CGLM_INLINE
 float
-glm_vec_norm(vec3 vec) {
-  return sqrtf(glm_vec_norm2(vec));
+glm_vec3_norm(const vec3 v) {
+  return sqrtf(glm_vec3_norm2(v));
 }
 
 /*!
- * @brief add v2 vector to v1 vector store result in dest
+ * @brief add a vector to b vector store result in dest
  *
- * @param[in]  v1 vector1
- * @param[in]  v2 vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest destination vector
  */
 CGLM_INLINE
 void
-glm_vec_add(vec3 v1, vec3 v2, vec3 dest) {
-  dest[0] = v1[0] + v2[0];
-  dest[1] = v1[1] + v2[1];
-  dest[2] = v1[2] + v2[2];
+glm_vec3_add(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+  dest[2] = a[2] + b[2];
 }
 
 /*!
- * @brief subtract v2 vector from v1 vector store result in dest
+ * @brief add scalar to v vector store result in dest (d = v + s)
  *
- * @param[in]  v1 vector1
- * @param[in]  v2 vector2
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
  * @param[out] dest destination vector
  */
 CGLM_INLINE
 void
-glm_vec_sub(vec3 v1, vec3 v2, vec3 dest) {
-  dest[0] = v1[0] - v2[0];
-  dest[1] = v1[1] - v2[1];
-  dest[2] = v1[2] - v2[2];
+glm_vec3_adds(const vec3 v, float s, vec3 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+  dest[2] = v[2] + s;
+}
+
+/*!
+ * @brief subtract b vector from a vector store result in dest
+ *
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
+ * @param[out] dest destination vector
+ */
+CGLM_INLINE
+void
+glm_vec3_sub(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+  dest[2] = a[2] - b[2];
+}
+
+/*!
+ * @brief subtract scalar from v vector store result in dest (d = v - s)
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination vector
+ */
+CGLM_INLINE
+void
+glm_vec3_subs(const vec3 v, float s, vec3 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+  dest[2] = v[2] - s;
+}
+
+/*!
+ * @brief multiply two vector (component-wise multiplication)
+ *
+ * @param a    vector1
+ * @param b    vector2
+ * @param dest v3 = (a[0] * b[0], a[1] * b[1], a[2] * b[2])
+ */
+CGLM_INLINE
+void
+glm_vec3_mul(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+  dest[2] = a[2] * b[2];
 }
 
 /*!
@@ -202,7 +281,7 @@ glm_vec_sub(vec3 v1, vec3 v2, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_scale(vec3 v, float s, vec3 dest) {
+glm_vec3_scale(const vec3 v, float s, vec3 dest) {
   dest[0] = v[0] * s;
   dest[1] = v[1] * s;
   dest[2] = v[2] * s;
@@ -217,67 +296,173 @@ glm_vec_scale(vec3 v, float s, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_scale_as(vec3 v, float s, vec3 dest) {
+glm_vec3_scale_as(const vec3 v, float s, vec3 dest) {
   float norm;
-  norm = glm_vec_norm(v);
+  norm = glm_vec3_norm(v);
 
-  if (norm == 0) {
-    glm_vec_copy(v, dest);
+  if (norm == 0.0f) {
+    glm_vec3_zero(dest);
     return;
   }
 
-  glm_vec_scale(v, s / norm, dest);
+  glm_vec3_scale(v, s / norm, dest);
 }
 
 /*!
- * @brief flip sign of all vec3 members
+ * @brief div vector with another component-wise division: d = a / b
  *
- * @param[in, out]  v  vector
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest result = (a[0]/b[0], a[1]/b[1], a[2]/b[2])
  */
 CGLM_INLINE
 void
-glm_vec_flipsign(vec3 v) {
-  v[0] = -v[0];
-  v[1] = -v[1];
-  v[2] = -v[2];
+glm_vec3_div(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] = a[0] / b[0];
+  dest[1] = a[1] / b[1];
+  dest[2] = a[2] / b[2];
 }
 
 /*!
- * @brief flip sign of all vec3 members and store result in dest
+ * @brief div vector with scalar: d = v / s
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest result = (a[0]/s, a[1]/s, a[2]/s)
+ */
+CGLM_INLINE
+void
+glm_vec3_divs(const vec3 v, float s, vec3 dest) {
+  dest[0] = v[0] / s;
+  dest[1] = v[1] / s;
+  dest[2] = v[2] / s;
+}
+
+/*!
+ * @brief add two vectors and add result to sum
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += (a + b)
+ */
+CGLM_INLINE
+void
+glm_vec3_addadd(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] += a[0] + b[0];
+  dest[1] += a[1] + b[1];
+  dest[2] += a[2] + b[2];
+}
+
+/*!
+ * @brief sub two vectors and add result to dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += (a + b)
+ */
+CGLM_INLINE
+void
+glm_vec3_subadd(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] += a[0] - b[0];
+  dest[1] += a[1] - b[1];
+  dest[2] += a[2] - b[2];
+}
+
+/*!
+ * @brief mul two vectors and add result to dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += (a * b)
+ */
+CGLM_INLINE
+void
+glm_vec3_muladd(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] += a[0] * b[0];
+  dest[1] += a[1] * b[1];
+  dest[2] += a[2] * b[2];
+}
+
+/*!
+ * @brief mul vector with scalar and add result to sum
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector
+ * @param[in]  s    scalar
+ * @param[out] dest dest += (a * b)
+ */
+CGLM_INLINE
+void
+glm_vec3_muladds(const vec3 a, float s, vec3 dest) {
+  dest[0] += a[0] * s;
+  dest[1] += a[1] * s;
+  dest[2] += a[2] * s;
+}
+
+/*!
+ * @brief add max of two vector to result/dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += max(a, b)
+ */
+CGLM_INLINE
+void
+glm_vec3_maxadd(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] += glm_max(a[0], b[0]);
+  dest[1] += glm_max(a[1], b[1]);
+  dest[2] += glm_max(a[2], b[2]);
+}
+
+/*!
+ * @brief add min of two vector to result/dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += min(a, b)
+ */
+CGLM_INLINE
+void
+glm_vec3_minadd(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] += glm_min(a[0], b[0]);
+  dest[1] += glm_min(a[1], b[1]);
+  dest[2] += glm_min(a[2], b[2]);
+}
+
+/*!
+ * @brief negate vector components and store result in dest
  *
  * @param[in]   v     vector
  * @param[out]  dest  result vector
  */
 CGLM_INLINE
 void
-glm_vec_flipsign_to(vec3 v, vec3 dest) {
+glm_vec3_negate_to(const vec3 v, vec3 dest) {
   dest[0] = -v[0];
   dest[1] = -v[1];
   dest[2] = -v[2];
 }
 
 /*!
- * @brief make vector as inverse/opposite of itself
+ * @brief negate vector components
  *
  * @param[in, out]  v  vector
  */
 CGLM_INLINE
 void
-glm_vec_inv(vec3 v) {
-  glm_vec_flipsign(v);
-}
-
-/*!
- * @brief inverse/opposite vector
- *
- * @param[in]  v    source
- * @param[out] dest destination
- */
-CGLM_INLINE
-void
-glm_vec_inv_to(vec3 v, vec3 dest) {
-  glm_vec_copy(v, dest);
-  glm_vec_flipsign(dest);
+glm_vec3_negate(vec3 v) {
+  glm_vec3_negate_to(v, v);
 }
 
 /*!
@@ -287,56 +472,93 @@ glm_vec_inv_to(vec3 v, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_normalize(vec3 v) {
+glm_vec3_normalize(vec3 v) {
   float norm;
 
-  norm = glm_vec_norm(v);
+  norm = glm_vec3_norm(v);
 
   if (norm == 0.0f) {
     v[0] = v[1] = v[2] = 0.0f;
     return;
   }
 
-  glm_vec_scale(v, 1.0f / norm, v);
+  glm_vec3_scale(v, 1.0f / norm, v);
 }
 
 /*!
  * @brief normalize vec3 to dest
  *
- * @param[in]  vec  source
+ * @param[in]  v    source
  * @param[out] dest destination
  */
 CGLM_INLINE
 void
-glm_vec_normalize_to(vec3 vec, vec3 dest) {
+glm_vec3_normalize_to(const vec3 v, vec3 dest) {
   float norm;
 
-  norm = glm_vec_norm(vec);
+  norm = glm_vec3_norm(v);
 
   if (norm == 0.0f) {
-    dest[0] = dest[1] = dest[2] = 0.0f;
+    glm_vec3_zero(dest);
     return;
   }
 
-  glm_vec_scale(vec, 1.0f / norm, dest);
+  glm_vec3_scale(v, 1.0f / norm, dest);
+}
+
+/*!
+ * @brief cross product of two vector (RH)
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_vec3_cross(const vec3 a, const vec3 b, vec3 dest) {
+  /* (u2.v3 - u3.v2, u3.v1 - u1.v3, u1.v2 - u2.v1) */
+  dest[0] = a[1] * b[2] - a[2] * b[1];
+  dest[1] = a[2] * b[0] - a[0] * b[2];
+  dest[2] = a[0] * b[1] - a[1] * b[0];
+}
+
+/*!
+ * @brief cross product of two vector (RH) and normalize the result
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_vec3_crossn(const vec3 a, const vec3 b, vec3 dest) {
+  glm_vec3_cross(a, b, dest);
+  glm_vec3_normalize(dest);
 }
 
 /*!
  * @brief angle betwen two vector
  *
- * @param[in] v1  vector1
- * @param[in] v2  vector2
+ * @param[in] a  vector1
+ * @param[in] b  vector2
  *
  * @return angle as radians
  */
 CGLM_INLINE
 float
-glm_vec_angle(vec3 v1, vec3 v2) {
-  float norm;
+glm_vec3_angle(const vec3 a, const vec3 b) {
+  float norm, dot;
 
   /* maybe compiler generate approximation instruction (rcp) */
-  norm = 1.0f / (glm_vec_norm(v1) * glm_vec_norm(v2));
-  return acosf(glm_vec_dot(v1, v2) * norm);
+  norm = 1.0f / (glm_vec3_norm(a) * glm_vec3_norm(b));
+  dot  = glm_vec3_dot(a, b) * norm;
+
+  if (dot > 1.0f)
+    return 0.0f;
+  else if (dot < -1.0f)
+    return CGLM_PI;
+
+  return acosf(dot);
 }
 
 /*!
@@ -348,27 +570,56 @@ glm_vec_angle(vec3 v1, vec3 v2) {
  */
 CGLM_INLINE
 void
-glm_vec_rotate(vec3 v, float angle, vec3 axis) {
+glm_vec3_rotate(vec3 v, float angle, const vec3 axis) {
   vec3   v1, v2, k;
   float  c, s;
 
   c = cosf(angle);
   s = sinf(angle);
 
-  glm_vec_normalize_to(axis, k);
+  glm_vec3_normalize_to(axis, k);
 
   /* Right Hand, Rodrigues' rotation formula:
         v = v*cos(t) + (kxv)sin(t) + k*(k.v)(1 - cos(t))
    */
-  glm_vec_scale(v, c, v1);
+  glm_vec3_scale(v, c, v1);
 
-  glm_vec_cross(k, v, v2);
-  glm_vec_scale(v2, s, v2);
+  glm_vec3_cross(k, v, v2);
+  glm_vec3_scale(v2, s, v2);
 
-  glm_vec_add(v1, v2, v1);
+  glm_vec3_add(v1, v2, v1);
 
-  glm_vec_scale(k, glm_vec_dot(k, v) * (1.0f - c), v2);
-  glm_vec_add(v1, v2, v);
+  glm_vec3_scale(k, glm_vec3_dot(k, v) * (1.0f - c), v2);
+  glm_vec3_add(v1, v2, v);
+}
+
+/*!
+ * @brief apply rotation matrix to vector
+ *
+ *  matrix format should be (no perspective):
+ *   a  b  c  x
+ *   e  f  g  y
+ *   i  j  k  z
+ *   0  0  0  w
+ *
+ * @param[in]  m    affine matrix or rot matrix
+ * @param[in]  v    vector
+ * @param[out] dest rotated vector
+ */
+CGLM_INLINE
+void
+glm_vec3_rotate_m4(const mat4 m, const vec3 v, vec3 dest) {
+  vec4 x, y, z, res;
+
+  glm_vec4_normalize_to(m[0], x);
+  glm_vec4_normalize_to(m[1], y);
+  glm_vec4_normalize_to(m[2], z);
+
+  glm_vec4_scale(x,   v[0], res);
+  glm_vec4_muladds(y, v[1], res);
+  glm_vec4_muladds(z, v[2], res);
+
+  glm_vec3(res, dest);
 }
 
 /*!
@@ -380,18 +631,22 @@ glm_vec_rotate(vec3 v, float angle, vec3 axis) {
  */
 CGLM_INLINE
 void
-glm_vec_rotate_m4(mat4 m, vec3 v, vec3 dest) {
-  vec3 res, x, y, z;
+glm_vec3_rotate_m3(const mat3 m, const vec3 v, vec3 dest) {
+  vec4 res, x, y, z;
 
-  glm_vec_normalize_to(m[0], x);
-  glm_vec_normalize_to(m[1], y);
-  glm_vec_normalize_to(m[2], z);
+  glm_vec4(m[0], 0.0f, x);
+  glm_vec4(m[1], 0.0f, y);
+  glm_vec4(m[2], 0.0f, z);
 
-  res[0] = x[0] * v[0] + y[0] * v[1] + z[0] * v[2];
-  res[1] = x[1] * v[0] + y[1] * v[1] + z[1] * v[2];
-  res[2] = x[2] * v[0] + y[2] * v[1] + z[2] * v[2];
+  glm_vec4_normalize(x);
+  glm_vec4_normalize(y);
+  glm_vec4_normalize(z);
 
-  glm_vec_copy(res, dest);
+  glm_vec4_scale(x,   v[0], res);
+  glm_vec4_muladds(y, v[1], res);
+  glm_vec4_muladds(z, v[2], res);
+
+  glm_vec3(res, dest);
 }
 
 /*!
@@ -403,69 +658,82 @@ glm_vec_rotate_m4(mat4 m, vec3 v, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_proj(vec3 a, vec3 b, vec3 dest) {
-  glm_vec_scale(b,
-                glm_vec_dot(a, b) / glm_vec_norm2(b),
+glm_vec3_proj(const vec3 a, const vec3 b, vec3 dest) {
+  glm_vec3_scale(b,
+                 glm_vec3_dot(a, b) / glm_vec3_norm2(b),
                  dest);
 }
 
 /**
  * @brief find center point of two vector
  *
- * @param[in]  v1 vector1
- * @param[in]  v2 vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest center point
  */
 CGLM_INLINE
 void
-glm_vec_center(vec3 v1, vec3 v2, vec3 dest) {
-  glm_vec_add(v1, v2, dest);
-  glm_vec_scale(dest, 0.5f, dest);
+glm_vec3_center(const vec3 a, const vec3 b, vec3 dest) {
+  glm_vec3_add(a, b, dest);
+  glm_vec3_scale(dest, 0.5f, dest);
+}
+
+/**
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a vector1
+ * @param[in] b vector2
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+float
+glm_vec3_distance2(const vec3 a, const vec3 b) {
+  return glm_pow2(b[0] - a[0])
+       + glm_pow2(b[1] - a[1])
+       + glm_pow2(b[2] - a[2]);
 }
 
 /**
  * @brief distance between two vectors
  *
- * @param[in] v1 vector1
- * @param[in] v2 vector2
+ * @param[in] a vector1
+ * @param[in] b vector2
  * @return returns distance
  */
 CGLM_INLINE
 float
-glm_vec_distance(vec3 v1, vec3 v2) {
-  return sqrtf(glm_pow2(v2[0] - v1[0])
-             + glm_pow2(v2[1] - v1[1])
-             + glm_pow2(v2[2] - v1[2]));
+glm_vec3_distance(const vec3 a, const vec3 b) {
+  return sqrtf(glm_vec3_distance2(a, b));
 }
 
 /*!
  * @brief max values of vectors
  *
- * @param[in]  v1   vector1
- * @param[in]  v2   vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest destination
  */
 CGLM_INLINE
 void
-glm_vec_maxv(vec3 v1, vec3 v2, vec3 dest) {
-  dest[0] = glm_max(v1[0], v2[0]);
-  dest[1] = glm_max(v1[1], v2[1]);
-  dest[2] = glm_max(v1[2], v2[2]);
+glm_vec3_maxv(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] = glm_max(a[0], b[0]);
+  dest[1] = glm_max(a[1], b[1]);
+  dest[2] = glm_max(a[2], b[2]);
 }
 
 /*!
  * @brief min values of vectors
  *
- * @param[in]  v1   vector1
- * @param[in]  v2   vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest destination
  */
 CGLM_INLINE
 void
-glm_vec_minv(vec3 v1, vec3 v2, vec3 dest) {
-  dest[0] = glm_min(v1[0], v2[0]);
-  dest[1] = glm_min(v1[1], v2[1]);
-  dest[2] = glm_min(v1[2], v2[2]);
+glm_vec3_minv(const vec3 a, const vec3 b, vec3 dest) {
+  dest[0] = glm_min(a[0], b[0]);
+  dest[1] = glm_min(a[1], b[1]);
+  dest[2] = glm_min(a[2], b[2]);
 }
 
 /*!
@@ -476,7 +744,7 @@ glm_vec_minv(vec3 v1, vec3 v2, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_ortho(vec3 v, vec3 dest) {
+glm_vec3_ortho(const vec3 v, vec3 dest) {
   dest[0] = v[1] - v[2];
   dest[1] = v[2] - v[0];
   dest[2] = v[0] - v[1];
@@ -491,7 +759,7 @@ glm_vec_ortho(vec3 v, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec_clamp(vec3 v, float minVal, float maxVal) {
+glm_vec3_clamp(vec3 v, float minVal, float maxVal) {
   v[0] = glm_clamp(v[0], minVal, maxVal);
   v[1] = glm_clamp(v[1], minVal, maxVal);
   v[2] = glm_clamp(v[2], minVal, maxVal);
@@ -509,14 +777,14 @@ glm_vec_clamp(vec3 v, float minVal, float maxVal) {
  */
 CGLM_INLINE
 void
-glm_vec_lerp(vec3 from, vec3 to, float t, vec3 dest) {
+glm_vec3_lerp(const vec3 from, const vec3 to, float t, vec3 dest) {
   vec3 s, v;
 
   /* from + s * (to - from) */
-  glm_vec_broadcast(glm_clamp(t, 0.0f, 1.0f), s);
-  glm_vec_sub(to, from, v);
-  glm_vec_mulv(s, v, v);
-  glm_vec_add(from, v, dest);
+  glm_vec3_broadcast(glm_clamp_zo(t), s);
+  glm_vec3_sub(to, from, v);
+  glm_vec3_mul(s, v, v);
+  glm_vec3_add(from, v, dest);
 }
 
 /*!
@@ -530,8 +798,8 @@ glm_vec_lerp(vec3 from, vec3 to, float t, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_cross(vec3 a, vec3 b, vec3 d) {
-  glm_vec_cross(a, b, d);
+glm_cross(const vec3 a, const vec3 b, vec3 d) {
+  glm_vec3_cross(a, b, d);
 }
 
 /*!
@@ -546,8 +814,8 @@ glm_cross(vec3 a, vec3 b, vec3 d) {
  */
 CGLM_INLINE
 float
-glm_dot(vec3 a, vec3 b) {
-  return glm_vec_dot(a, b);
+glm_dot(const vec3 a, const vec3 b) {
+  return glm_vec3_dot(a, b);
 }
 
 /*!
@@ -560,7 +828,7 @@ glm_dot(vec3 a, vec3 b) {
 CGLM_INLINE
 void
 glm_normalize(vec3 v) {
-  glm_vec_normalize(v);
+  glm_vec3_normalize(v);
 }
 
 /*!
@@ -573,8 +841,8 @@ glm_normalize(vec3 v) {
  */
 CGLM_INLINE
 void
-glm_normalize_to(vec3 v, vec3 dest) {
-  glm_vec_normalize_to(v, dest);
+glm_normalize_to(const vec3 v, vec3 dest) {
+  glm_vec3_normalize_to(v, dest);
 }
 
 #endif /* cglm_vec3_h */

include/cglm/vec4-ext.h

@@ -11,15 +11,19 @@
 
 /*
  Functions:
-   CGLM_INLINE void  glm_vec4_mulv(vec4 a, vec4 b, vec4 d);
    CGLM_INLINE void  glm_vec4_broadcast(float val, vec4 d);
    CGLM_INLINE bool  glm_vec4_eq(vec4 v, float val);
    CGLM_INLINE bool  glm_vec4_eq_eps(vec4 v, float val);
    CGLM_INLINE bool  glm_vec4_eq_all(vec4 v);
-   CGLM_INLINE bool  glm_vec4_eqv(vec4 v1, vec4 v2);
-   CGLM_INLINE bool  glm_vec4_eqv_eps(vec4 v1, vec4 v2);
+   CGLM_INLINE bool  glm_vec4_eqv(vec4 a, vec4 b);
+   CGLM_INLINE bool  glm_vec4_eqv_eps(vec4 a, vec4 b);
    CGLM_INLINE float glm_vec4_max(vec4 v);
    CGLM_INLINE float glm_vec4_min(vec4 v);
+   CGLM_INLINE bool  glm_vec4_isnan(vec4 v);
+   CGLM_INLINE bool  glm_vec4_isinf(vec4 v);
+   CGLM_INLINE bool  glm_vec4_isvalid(vec4 v);
+   CGLM_INLINE void  glm_vec4_sign(vec4 v, vec4 dest);
+   CGLM_INLINE void  glm_vec4_sqrt(vec4 v, vec4 dest);
  */
 
 #ifndef cglm_vec4_ext_h
@@ -27,29 +31,6 @@
 
 #include "common.h"
 #include "vec3-ext.h"
-#include <stdbool.h>
-#include <math.h>
-#include <float.h>
-
-/*!
- * @brief multiplies individual items, just for convenient like SIMD
- *
- * @param a v1
- * @param b v2
- * @param d v3 = (v1[0] * v2[0],  v1[1] * v2[1], v1[2] * v2[2], v1[3] * v2[3])
- */
-CGLM_INLINE
-void
-glm_vec4_mulv(vec4 a, vec4 b, vec4 d) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(d, _mm_mul_ps(_mm_load_ps(a), _mm_load_ps(b)));
-#else
-  d[0] = a[0] * b[0];
-  d[1] = a[1] * b[1];
-  d[2] = a[2] * b[2];
-  d[3] = a[3] * b[3];
-#endif
-}
 
 /*!
  * @brief fill a vector with specified value
@@ -61,7 +42,7 @@ CGLM_INLINE
 void
 glm_vec4_broadcast(float val, vec4 d) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(d, _mm_set1_ps(val));
+  glmm_store(d, _mm_set1_ps(val));
 #else
   d[0] = d[1] = d[2] = d[3] = val;
 #endif
@@ -75,7 +56,7 @@ glm_vec4_broadcast(float val, vec4 d) {
  */
 CGLM_INLINE
 bool
-glm_vec4_eq(vec4 v, float val) {
+glm_vec4_eq(const vec4 v, float val) {
   return v[0] == val
          && v[0] == v[1]
          && v[0] == v[2]
@@ -90,7 +71,7 @@ glm_vec4_eq(vec4 v, float val) {
  */
 CGLM_INLINE
 bool
-glm_vec4_eq_eps(vec4 v, float val) {
+glm_vec4_eq_eps(const vec4 v, float val) {
   return fabsf(v[0] - val) <= FLT_EPSILON
          && fabsf(v[1] - val) <= FLT_EPSILON
          && fabsf(v[2] - val) <= FLT_EPSILON
@@ -104,7 +85,7 @@ glm_vec4_eq_eps(vec4 v, float val) {
  */
 CGLM_INLINE
 bool
-glm_vec4_eq_all(vec4 v) {
+glm_vec4_eq_all(const vec4 v) {
   return v[0] == v[1]
          && v[0] == v[2]
          && v[0] == v[3];
@@ -113,31 +94,31 @@ glm_vec4_eq_all(vec4 v) {
 /*!
  * @brief check if vector is equal to another (without epsilon)
  *
- * @param v1 vector
- * @param v2 vector
+ * @param a vector
+ * @param b vector
  */
 CGLM_INLINE
 bool
-glm_vec4_eqv(vec4 v1, vec4 v2) {
-  return v1[0] == v2[0]
-         && v1[1] == v2[1]
-         && v1[2] == v2[2]
-         && v1[3] == v2[3];
+glm_vec4_eqv(const vec4 a, const vec4 b) {
+  return a[0] == b[0]
+         && a[1] == b[1]
+         && a[2] == b[2]
+         && a[3] == b[3];
 }
 
 /*!
  * @brief check if vector is equal to another (with epsilon)
  *
- * @param v1 vector
- * @param v2 vector
+ * @param a vector
+ * @param b vector
  */
 CGLM_INLINE
 bool
-glm_vec4_eqv_eps(vec4 v1, vec4 v2) {
-  return fabsf(v1[0] - v2[0]) <= FLT_EPSILON
-         && fabsf(v1[1] - v2[1]) <= FLT_EPSILON
-         && fabsf(v1[2] - v2[2]) <= FLT_EPSILON
-         && fabsf(v1[3] - v2[3]) <= FLT_EPSILON;
+glm_vec4_eqv_eps(const vec4 a, const vec4 b) {
+  return fabsf(a[0] - b[0]) <= FLT_EPSILON
+         && fabsf(a[1] - b[1]) <= FLT_EPSILON
+         && fabsf(a[2] - b[2]) <= FLT_EPSILON
+         && fabsf(a[3] - b[3]) <= FLT_EPSILON;
 }
 
 /*!
@@ -147,10 +128,10 @@ glm_vec4_eqv_eps(vec4 v1, vec4 v2) {
  */
 CGLM_INLINE
 float
-glm_vec4_max(vec4 v) {
+glm_vec4_max(const vec4 v) {
   float max;
 
-  max = glm_vec_max(v);
+  max = glm_vec3_max(v);
   if (v[3] > max)
     max = v[3];
 
@@ -164,10 +145,10 @@ glm_vec4_max(vec4 v) {
  */
 CGLM_INLINE
 float
-glm_vec4_min(vec4 v) {
+glm_vec4_min(const vec4 v) {
   float min;
 
-  min = glm_vec_min(v);
+  min = glm_vec3_min(v);
   if (v[3] < min)
     min = v[3];
 
@@ -182,7 +163,7 @@ glm_vec4_min(vec4 v) {
  */
 CGLM_INLINE
 bool
-glm_vec4_isnan(vec4 v) {
+glm_vec4_isnan(const vec4 v) {
   return isnan(v[0]) || isnan(v[1]) || isnan(v[2]) || isnan(v[3]);
 }
 
@@ -194,7 +175,7 @@ glm_vec4_isnan(vec4 v) {
  */
 CGLM_INLINE
 bool
-glm_vec4_isinf(vec4 v) {
+glm_vec4_isinf(const vec4 v) {
   return isinf(v[0]) || isinf(v[1]) || isinf(v[2]) || isinf(v[3]);
 }
 
@@ -206,7 +187,7 @@ glm_vec4_isinf(vec4 v) {
  */
 CGLM_INLINE
 bool
-glm_vec4_isvalid(vec4 v) {
+glm_vec4_isvalid(const vec4 v) {
   return !glm_vec4_isnan(v) && !glm_vec4_isinf(v);
 }
 
@@ -219,18 +200,18 @@ glm_vec4_isvalid(vec4 v) {
  */
 CGLM_INLINE
 void
-glm_vec4_sign(vec4 v, vec4 dest) {
+glm_vec4_sign(const vec4 v, vec4 dest) {
 #if defined( __SSE2__ ) || defined( __SSE2__ )
   __m128 x0, x1, x2, x3, x4;
 
-  x0 = _mm_load_ps(v);
+  x0 = glmm_load(v);
   x1 = _mm_set_ps(0.0f, 0.0f, 1.0f, -1.0f);
-  x2 = _mm_shuffle1_ps1(x1, 2);
+  x2 = glmm_shuff1x(x1, 2);
 
-  x3 = _mm_and_ps(_mm_cmpgt_ps(x0, x2), _mm_shuffle1_ps1(x1, 1));
-  x4 = _mm_and_ps(_mm_cmplt_ps(x0, x2), _mm_shuffle1_ps1(x1, 0));
+  x3 = _mm_and_ps(_mm_cmpgt_ps(x0, x2), glmm_shuff1x(x1, 1));
+  x4 = _mm_and_ps(_mm_cmplt_ps(x0, x2), glmm_shuff1x(x1, 0));
 
-  _mm_store_ps(dest, _mm_or_ps(x3, x4));
+  glmm_store(dest, _mm_or_ps(x3, x4));
 #else
   dest[0] = glm_signf(v[0]);
   dest[1] = glm_signf(v[1]);
@@ -247,9 +228,9 @@ glm_vec4_sign(vec4 v, vec4 dest) {
  */
 CGLM_INLINE
 void
-glm_vec4_sqrt(vec4 v, vec4 dest) {
+glm_vec4_sqrt(const vec4 v, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest, _mm_sqrt_ps(_mm_load_ps(v)));
+  glmm_store(dest, _mm_sqrt_ps(glmm_load(v)));
 #else
   dest[0] = sqrtf(v[0]);
   dest[1] = sqrtf(v[1]);

include/cglm/vec4.h

@@ -5,15 +5,8 @@
  * Full license can be found in the LICENSE file
  */
 
-/*!
- * vec3 functions dont have suffix e.g glm_vec_dot (not glm_vec3_dot)
- * all functions without suffix are vec3 functions
- */
-
 /*
  Macros:
-   glm_vec4_dup3(v, dest)
-   glm_vec4_dup(v, dest)
    GLM_VEC4_ONE_INIT
    GLM_VEC4_BLACK_INIT
    GLM_VEC4_ZERO_INIT
@@ -25,22 +18,43 @@
    CGLM_INLINE void  glm_vec4(vec3 v3, float last, vec4 dest);
    CGLM_INLINE void  glm_vec4_copy3(vec4 a, vec3 dest);
    CGLM_INLINE void  glm_vec4_copy(vec4 v, vec4 dest);
+   CGLM_INLINE void  glm_vec4_ucopy(vec4 v, vec4 dest);
    CGLM_INLINE float glm_vec4_dot(vec4 a, vec4 b);
    CGLM_INLINE float glm_vec4_norm2(vec4 v);
-   CGLM_INLINE float glm_vec4_norm(vec4 vec);
-   CGLM_INLINE void  glm_vec4_add(vec4 v1, vec4 v2, vec4 dest);
-   CGLM_INLINE void  glm_vec4_sub(vec4 v1, vec4 v2, vec4 dest);
+   CGLM_INLINE float glm_vec4_norm(vec4 v);
+   CGLM_INLINE void  glm_vec4_add(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_adds(vec4 v, float s, vec4 dest);
+   CGLM_INLINE void  glm_vec4_sub(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_subs(vec4 v, float s, vec4 dest);
+   CGLM_INLINE void  glm_vec4_mul(vec4 a, vec4 b, vec4 dest);
    CGLM_INLINE void  glm_vec4_scale(vec4 v, float s, vec4 dest);
    CGLM_INLINE void  glm_vec4_scale_as(vec4 v, float s, vec4 dest);
-   CGLM_INLINE void  glm_vec4_flipsign(vec4 v);
+   CGLM_INLINE void  glm_vec4_div(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_divs(vec4 v, float s, vec4 dest);
+   CGLM_INLINE void  glm_vec4_addadd(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_subadd(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_muladd(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_muladds(vec4 a, float s, vec4 dest);
+   CGLM_INLINE void  glm_vec4_maxadd(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_minadd(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_negate(vec4 v);
    CGLM_INLINE void  glm_vec4_inv(vec4 v);
    CGLM_INLINE void  glm_vec4_inv_to(vec4 v, vec4 dest);
    CGLM_INLINE void  glm_vec4_normalize(vec4 v);
    CGLM_INLINE void  glm_vec4_normalize_to(vec4 vec, vec4 dest);
-   CGLM_INLINE float glm_vec4_distance(vec4 v1, vec4 v2);
-   CGLM_INLINE void  glm_vec4_maxv(vec4 v1, vec4 v2, vec4 dest);
-   CGLM_INLINE void  glm_vec4_minv(vec4 v1, vec4 v2, vec4 dest);
+   CGLM_INLINE float glm_vec4_distance(vec4 a, vec4 b);
+   CGLM_INLINE void  glm_vec4_maxv(vec4 a, vec4 b, vec4 dest);
+   CGLM_INLINE void  glm_vec4_minv(vec4 a, vec4 b, vec4 dest);
    CGLM_INLINE void  glm_vec4_clamp(vec4 v, float minVal, float maxVal);
+   CGLM_INLINE void  glm_vec4_lerp(vec4 from, vec4 to, float t, vec4 dest)
+
+ DEPRECATED:
+   glm_vec4_dup
+   glm_vec4_flipsign
+   glm_vec4_flipsign_to
+   glm_vec4_inv
+   glm_vec4_inv_to
+   glm_vec4_mulv
  */
 
 #ifndef cglm_vec4_h
@@ -50,9 +64,14 @@
 #include "vec4-ext.h"
 #include "util.h"
 
-/* DEPRECATED! use _copy, _ucopy versions */
+/* DEPRECATED! functions */
 #define glm_vec4_dup3(v, dest)         glm_vec4_copy3(v, dest)
 #define glm_vec4_dup(v, dest)          glm_vec4_copy(v, dest)
+#define glm_vec4_flipsign(v)           glm_vec4_negate(v)
+#define glm_vec4_flipsign_to(v, dest)  glm_vec4_negate_to(v, dest)
+#define glm_vec4_inv(v)                glm_vec4_negate(v)
+#define glm_vec4_inv_to(v, dest)       glm_vec4_negate_to(v, dest)
+#define glm_vec4_mulv(a, b, d)         glm_vec4_mul(a, b, d)
 
 #define GLM_VEC4_ONE_INIT   {1.0f, 1.0f, 1.0f, 1.0f}
 #define GLM_VEC4_BLACK_INIT {0.0f, 0.0f, 0.0f, 1.0f}
@@ -71,7 +90,7 @@
  */
 CGLM_INLINE
 void
-glm_vec4(vec3 v3, float last, vec4 dest) {
+glm_vec4(const vec3 v3, float last, vec4 dest) {
   dest[0] = v3[0];
   dest[1] = v3[1];
   dest[2] = v3[2];
@@ -86,7 +105,7 @@ glm_vec4(vec3 v3, float last, vec4 dest) {
  */
 CGLM_INLINE
 void
-glm_vec4_copy3(vec4 a, vec3 dest) {
+glm_vec4_copy3(const vec4 a, vec3 dest) {
   dest[0] = a[0];
   dest[1] = a[1];
   dest[2] = a[2];
@@ -100,9 +119,11 @@ glm_vec4_copy3(vec4 a, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_vec4_copy(vec4 v, vec4 dest) {
+glm_vec4_copy(const vec4 v, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest, _mm_load_ps(v));
+  glmm_store(dest, glmm_load(v));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vld1q_f32(v));
 #else
   dest[0] = v[0];
   dest[1] = v[1];
@@ -111,6 +132,63 @@ glm_vec4_copy(vec4 v, vec4 dest) {
 #endif
 }
 
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * alignment is not required
+ *
+ * @param[in]  v    source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_vec4_ucopy(const vec4 v, vec4 dest) {
+  dest[0] = v[0];
+  dest[1] = v[1];
+  dest[2] = v[2];
+  dest[3] = v[3];
+}
+
+/*!
+ * @brief make vector zero
+ *
+ * @param[in, out]  v vector
+ */
+CGLM_INLINE
+void
+glm_vec4_zero(vec4 v) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(v, _mm_setzero_ps());
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(v, vdupq_n_f32(0.0f));
+#else
+  v[0] = 0.0f;
+  v[1] = 0.0f;
+  v[2] = 0.0f;
+  v[3] = 0.0f;
+#endif
+}
+
+/*!
+ * @brief make vector one
+ *
+ * @param[in, out]  v vector
+ */
+CGLM_INLINE
+void
+glm_vec4_one(vec4 v) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(v, _mm_set1_ps(1.0f));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(v, vdupq_n_f32(1.0f));
+#else
+  v[0] = 1.0f;
+  v[1] = 1.0f;
+  v[2] = 1.0f;
+  v[3] = 1.0f;
+#endif
+}
+
 /*!
  * @brief vec4 dot product
  *
@@ -121,12 +199,9 @@ glm_vec4_copy(vec4 v, vec4 dest) {
  */
 CGLM_INLINE
 float
-glm_vec4_dot(vec4 a, vec4 b) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  __m128 x0;
-  x0 = _mm_mul_ps(_mm_load_ps(a), _mm_load_ps(b));
-  x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 1, 0, 3, 2));
-  return _mm_cvtss_f32(_mm_add_ss(x0, _mm_shuffle1_ps(x0, 0, 1, 0, 1)));
+glm_vec4_dot(const vec4 a, const vec4 b) {
+#if defined(CGLM_SIMD)
+  return glmm_dot(glmm_load(a), glmm_load(b));
 #else
   return a[0] * b[0] + a[1] * b[1] + a[2] * b[2] + a[3] * b[3];
 #endif
@@ -145,64 +220,134 @@ glm_vec4_dot(vec4 a, vec4 b) {
  */
 CGLM_INLINE
 float
-glm_vec4_norm2(vec4 v) {
+glm_vec4_norm2(const vec4 v) {
   return glm_vec4_dot(v, v);
 }
 
 /*!
  * @brief norm (magnitude) of vec4
  *
- * @param[in] vec vector
+ * @param[in] v vector
  *
  * @return norm
  */
 CGLM_INLINE
 float
-glm_vec4_norm(vec4 vec) {
-  return sqrtf(glm_vec4_norm2(vec));
-}
-
-/*!
- * @brief add v2 vector to v1 vector store result in dest
- *
- * @param[in]  v1 vector1
- * @param[in]  v2 vector2
- * @param[out] dest destination vector
- */
-CGLM_INLINE
-void
-glm_vec4_add(vec4 v1, vec4 v2, vec4 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest,
-               _mm_add_ps(_mm_load_ps(v1),
-                          _mm_load_ps(v2)));
+glm_vec4_norm(const vec4 v) {
+#if defined(CGLM_SIMD)
+  return glmm_norm(glmm_load(v));
 #else
-  dest[0] = v1[0] + v2[0];
-  dest[1] = v1[1] + v2[1];
-  dest[2] = v1[2] + v2[2];
-  dest[3] = v1[3] + v2[3];
+  return sqrtf(glm_vec4_dot(v, v));
 #endif
 }
 
 /*!
- * @brief subtract v2 vector from v1 vector store result in dest
+ * @brief add b vector to a vector store result in dest
  *
- * @param[in]  v1 vector1
- * @param[in]  v2 vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest destination vector
  */
 CGLM_INLINE
 void
-glm_vec4_sub(vec4 v1, vec4 v2, vec4 dest) {
+glm_vec4_add(const vec4 a, const vec4 b, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest,
-               _mm_sub_ps(_mm_load_ps(v1),
-                          _mm_load_ps(v2)));
+  glmm_store(dest, _mm_add_ps(glmm_load(a), glmm_load(b)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(a), vld1q_f32(b)));
 #else
-  dest[0] = v1[0] - v2[0];
-  dest[1] = v1[1] - v2[1];
-  dest[2] = v1[2] - v2[2];
-  dest[3] = v1[3] - v2[3];
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+  dest[2] = a[2] + b[2];
+  dest[3] = a[3] + b[3];
+#endif
+}
+
+/*!
+ * @brief add scalar to v vector store result in dest (d = v + vec(s))
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination vector
+ */
+CGLM_INLINE
+void
+glm_vec4_adds(const vec4 v, float s, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(v), _mm_set1_ps(s)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(v), vdupq_n_f32(s)));
+#else
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+  dest[2] = v[2] + s;
+  dest[3] = v[3] + s;
+#endif
+}
+
+/*!
+ * @brief subtract b vector from a vector store result in dest (d = a - b)
+ *
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
+ * @param[out] dest destination vector
+ */
+CGLM_INLINE
+void
+glm_vec4_sub(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_sub_ps(glmm_load(a), glmm_load(b)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vsubq_f32(vld1q_f32(a), vld1q_f32(b)));
+#else
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+  dest[2] = a[2] - b[2];
+  dest[3] = a[3] - b[3];
+#endif
+}
+
+/*!
+ * @brief subtract scalar from v vector store result in dest (d = v - vec(s))
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination vector
+ */
+CGLM_INLINE
+void
+glm_vec4_subs(const vec4 v, float s, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_sub_ps(glmm_load(v), _mm_set1_ps(s)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vsubq_f32(vld1q_f32(v), vdupq_n_f32(s)));
+#else
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+  dest[2] = v[2] - s;
+  dest[3] = v[3] - s;
+#endif
+}
+
+/*!
+ * @brief multiply two vector (component-wise multiplication)
+ *
+ * @param a    vector1
+ * @param b    vector2
+ * @param dest dest = (a[0] * b[0], a[1] * b[1], a[2] * b[2], a[3] * b[3])
+ */
+CGLM_INLINE
+void
+glm_vec4_mul(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_mul_ps(glmm_load(a), glmm_load(b)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vmulq_f32(vld1q_f32(a), vld1q_f32(b)));
+#else
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+  dest[2] = a[2] * b[2];
+  dest[3] = a[3] * b[3];
 #endif
 }
 
@@ -215,11 +360,11 @@ glm_vec4_sub(vec4 v1, vec4 v2, vec4 dest) {
  */
 CGLM_INLINE
 void
-glm_vec4_scale(vec4 v, float s, vec4 dest) {
+glm_vec4_scale(const vec4 v, float s, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest,
-               _mm_mul_ps(_mm_load_ps(v),
-                          _mm_set1_ps(s)));
+  glmm_store(dest, _mm_mul_ps(glmm_load(v), _mm_set1_ps(s)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vmulq_f32(vld1q_f32(v), vdupq_n_f32(s)));
 #else
   dest[0] = v[0] * s;
   dest[1] = v[1] * s;
@@ -237,12 +382,12 @@ glm_vec4_scale(vec4 v, float s, vec4 dest) {
  */
 CGLM_INLINE
 void
-glm_vec4_scale_as(vec4 v, float s, vec4 dest) {
+glm_vec4_scale_as(const vec4 v, float s, vec4 dest) {
   float norm;
   norm = glm_vec4_norm(v);
 
-  if (norm == 0) {
-    glm_vec4_copy(v, dest);
+  if (norm == 0.0f) {
+    glm_vec4_zero(dest);
     return;
   }
 
@@ -250,36 +395,223 @@ glm_vec4_scale_as(vec4 v, float s, vec4 dest) {
 }
 
 /*!
- * @brief flip sign of all vec4 members
+ * @brief div vector with another component-wise division: d = a / b
  *
- * @param[in, out]  v  vector
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest result = (a[0]/b[0], a[1]/b[1], a[2]/b[2], a[3]/b[3])
  */
 CGLM_INLINE
 void
-glm_vec4_flipsign(vec4 v) {
+glm_vec4_div(const vec4 a, const vec4 b, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(v, _mm_xor_ps(_mm_load_ps(v),
-                             _mm_set1_ps(-0.0f)));
+  glmm_store(dest, _mm_div_ps(glmm_load(a), glmm_load(b)));
 #else
-  v[0] = -v[0];
-  v[1] = -v[1];
-  v[2] = -v[2];
-  v[3] = -v[3];
+  dest[0] = a[0] / b[0];
+  dest[1] = a[1] / b[1];
+  dest[2] = a[2] / b[2];
+  dest[3] = a[3] / b[3];
 #endif
 }
 
 /*!
- * @brief flip sign of all vec4 members and store result in dest
+ * @brief div vec4 vector with scalar: d = v / s
  *
  * @param[in]  v    vector
- * @param[out] dest  vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination vector
  */
 CGLM_INLINE
 void
-glm_vec4_flipsign_to(vec4 v, vec4 dest) {
+glm_vec4_divs(const vec4 v, float s, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
-  _mm_store_ps(dest, _mm_xor_ps(_mm_load_ps(v),
-                                _mm_set1_ps(-0.0f)));
+  glmm_store(dest, _mm_div_ps(glmm_load(v), _mm_set1_ps(s)));
+#else
+  glm_vec4_scale(v, 1.0f / s, dest);
+#endif
+}
+
+/*!
+ * @brief add two vectors and add result to sum
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += (a + b)
+ */
+CGLM_INLINE
+void
+glm_vec4_addadd(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(dest),
+                              _mm_add_ps(glmm_load(a),
+                                         glmm_load(b))));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(dest),
+                            vaddq_f32(vld1q_f32(a),
+                                      vld1q_f32(b))));
+#else
+  dest[0] += a[0] + b[0];
+  dest[1] += a[1] + b[1];
+  dest[2] += a[2] + b[2];
+  dest[3] += a[3] + b[3];
+#endif
+}
+
+/*!
+ * @brief sub two vectors and add result to dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += (a - b)
+ */
+CGLM_INLINE
+void
+glm_vec4_subadd(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(dest),
+                              _mm_sub_ps(glmm_load(a),
+                                         glmm_load(b))));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(dest),
+                            vsubq_f32(vld1q_f32(a),
+                                      vld1q_f32(b))));
+#else
+  dest[0] += a[0] - b[0];
+  dest[1] += a[1] - b[1];
+  dest[2] += a[2] - b[2];
+  dest[3] += a[3] - b[3];
+#endif
+}
+
+/*!
+ * @brief mul two vectors and add result to dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += (a * b)
+ */
+CGLM_INLINE
+void
+glm_vec4_muladd(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(dest),
+                              _mm_mul_ps(glmm_load(a),
+                                         glmm_load(b))));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(dest),
+                            vmulq_f32(vld1q_f32(a),
+                                      vld1q_f32(b))));
+#else
+  dest[0] += a[0] * b[0];
+  dest[1] += a[1] * b[1];
+  dest[2] += a[2] * b[2];
+  dest[3] += a[3] * b[3];
+#endif
+}
+
+/*!
+ * @brief mul vector with scalar and add result to sum
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector
+ * @param[in]  s    scalar
+ * @param[out] dest dest += (a * b)
+ */
+CGLM_INLINE
+void
+glm_vec4_muladds(const vec4 a, float s, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(dest),
+                              _mm_mul_ps(glmm_load(a),
+                                         _mm_set1_ps(s))));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(dest),
+                            vsubq_f32(vld1q_f32(a),
+                                      vdupq_n_f32(s))));
+#else
+  dest[0] += a[0] * s;
+  dest[1] += a[1] * s;
+  dest[2] += a[2] * s;
+  dest[3] += a[3] * s;
+#endif
+}
+
+/*!
+ * @brief add max of two vector to result/dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += max(a, b)
+ */
+CGLM_INLINE
+void
+glm_vec4_maxadd(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(dest),
+                              _mm_max_ps(glmm_load(a),
+                                         glmm_load(b))));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(dest),
+                            vmaxq_f32(vld1q_f32(a),
+                                      vld1q_f32(b))));
+#else
+  dest[0] += glm_max(a[0], b[0]);
+  dest[1] += glm_max(a[1], b[1]);
+  dest[2] += glm_max(a[2], b[2]);
+  dest[3] += glm_max(a[3], b[3]);
+#endif
+}
+
+/*!
+ * @brief add min of two vector to result/dest
+ *
+ * it applies += operator so dest must be initialized
+ *
+ * @param[in]  a    vector 1
+ * @param[in]  b    vector 2
+ * @param[out] dest dest += min(a, b)
+ */
+CGLM_INLINE
+void
+glm_vec4_minadd(const vec4 a,const  vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_add_ps(glmm_load(dest),
+                              _mm_min_ps(glmm_load(a),
+                                         glmm_load(b))));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vaddq_f32(vld1q_f32(dest),
+                            vminq_f32(vld1q_f32(a),
+                                      vld1q_f32(b))));
+#else
+  dest[0] += glm_min(a[0], b[0]);
+  dest[1] += glm_min(a[1], b[1]);
+  dest[2] += glm_min(a[2], b[2]);
+  dest[3] += glm_min(a[3], b[3]);
+#endif
+}
+
+/*!
+ * @brief negate vector components and store result in dest
+ *
+ * @param[in]  v     vector
+ * @param[out] dest  result vector
+ */
+CGLM_INLINE
+void
+glm_vec4_negate_to(const vec4 v, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_xor_ps(glmm_load(v), _mm_set1_ps(-0.0f)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, veorq_s32(vld1q_f32(v), vdupq_n_f32(-0.0f)));
 #else
   dest[0] = -v[0];
   dest[1] = -v[1];
@@ -289,27 +621,51 @@ glm_vec4_flipsign_to(vec4 v, vec4 dest) {
 }
 
 /*!
- * @brief make vector as inverse/opposite of itself
+ * @brief flip sign of all vec4 members
  *
  * @param[in, out]  v  vector
  */
 CGLM_INLINE
 void
-glm_vec4_inv(vec4 v) {
-  glm_vec4_flipsign(v);
+glm_vec4_negate(vec4 v) {
+  glm_vec4_negate_to(v, v);
 }
 
 /*!
- * @brief inverse/opposite vector
+ * @brief normalize vec4 to dest
  *
  * @param[in]  v    source
  * @param[out] dest destination
  */
 CGLM_INLINE
 void
-glm_vec4_inv_to(vec4 v, vec4 dest) {
-  glm_vec4_copy(v, dest);
-  glm_vec4_flipsign(dest);
+glm_vec4_normalize_to(const vec4 v, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  __m128 xdot, x0;
+  float  dot;
+
+  x0   = glmm_load(v);
+  xdot = glmm_vdot(x0, x0);
+  dot  = _mm_cvtss_f32(xdot);
+
+  if (dot == 0.0f) {
+    glmm_store(dest, _mm_setzero_ps());
+    return;
+  }
+
+  glmm_store(dest, _mm_div_ps(x0, _mm_sqrt_ps(xdot)));
+#else
+  float norm;
+
+  norm = glm_vec4_norm(v);
+
+  if (norm == 0.0f) {
+    glm_vec4_zero(dest);
+    return;
+  }
+
+  glm_vec4_scale(v, 1.0f / norm, dest);
+#endif
 }
 
 /*!
@@ -320,85 +676,73 @@ glm_vec4_inv_to(vec4 v, vec4 dest) {
 CGLM_INLINE
 void
 glm_vec4_normalize(vec4 v) {
-  float norm;
-
-  norm = glm_vec4_norm(v);
-
-  if (norm == 0.0f) {
-    v[0] = v[1] = v[2] = v[3] = 0.0f;
-    return;
-  }
-
-  glm_vec4_scale(v, 1.0f / norm, v);
-}
-
-/*!
- * @brief normalize vec4 to dest
- *
- * @param[in]  vec  source
- * @param[out] dest destination
- */
-CGLM_INLINE
-void
-glm_vec4_normalize_to(vec4 vec, vec4 dest) {
-  float norm;
-
-  norm = glm_vec4_norm(vec);
-
-  if (norm == 0.0f) {
-    dest[0] = dest[1] = dest[2] = dest[3] = 0.0f;
-    return;
-  }
-
-  glm_vec4_scale(vec, 1.0f / norm, dest);
+  glm_vec4_normalize_to(v, v);
 }
 
 /**
  * @brief distance between two vectors
  *
- * @param[in] v1 vector1
- * @param[in] v2 vector2
+ * @param[in] a vector1
+ * @param[in] b vector2
  * @return returns distance
  */
 CGLM_INLINE
 float
-glm_vec4_distance(vec4 v1, vec4 v2) {
-  return sqrtf(glm_pow2(v2[0] - v1[0])
-             + glm_pow2(v2[1] - v1[1])
-             + glm_pow2(v2[2] - v1[2])
-             + glm_pow2(v2[3] - v1[3]));
+glm_vec4_distance(const vec4 a, const vec4 b) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  return glmm_norm(_mm_sub_ps(glmm_load(b), glmm_load(a)));
+#elif defined(CGLM_NEON_FP)
+  return glmm_norm(vsubq_f32(glmm_load(a), glmm_load(b)));
+#else
+  return sqrtf(glm_pow2(b[0] - a[0])
+             + glm_pow2(b[1] - a[1])
+             + glm_pow2(b[2] - a[2])
+             + glm_pow2(b[3] - a[3]));
+#endif
 }
 
 /*!
  * @brief max values of vectors
  *
- * @param[in]  v1   vector1
- * @param[in]  v2   vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest destination
  */
 CGLM_INLINE
 void
-glm_vec4_maxv(vec4 v1, vec4 v2, vec4 dest) {
-  dest[0] = glm_max(v1[0], v2[0]);
-  dest[1] = glm_max(v1[1], v2[1]);
-  dest[2] = glm_max(v1[2], v2[2]);
-  dest[3] = glm_max(v1[3], v2[3]);
+glm_vec4_maxv(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_max_ps(glmm_load(a), glmm_load(b)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vmaxq_f32(vld1q_f32(a), vld1q_f32(b)));
+#else
+  dest[0] = glm_max(a[0], b[0]);
+  dest[1] = glm_max(a[1], b[1]);
+  dest[2] = glm_max(a[2], b[2]);
+  dest[3] = glm_max(a[3], b[3]);
+#endif
 }
 
 /*!
  * @brief min values of vectors
  *
- * @param[in]  v1   vector1
- * @param[in]  v2   vector2
+ * @param[in]  a    vector1
+ * @param[in]  b    vector2
  * @param[out] dest destination
  */
 CGLM_INLINE
 void
-glm_vec4_minv(vec4 v1, vec4 v2, vec4 dest) {
-  dest[0] = glm_min(v1[0], v2[0]);
-  dest[1] = glm_min(v1[1], v2[1]);
-  dest[2] = glm_min(v1[2], v2[2]);
-  dest[3] = glm_min(v1[3], v2[3]);
+glm_vec4_minv(const vec4 a, const vec4 b, vec4 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(dest, _mm_min_ps(glmm_load(a), glmm_load(b)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest, vminq_f32(vld1q_f32(a), vld1q_f32(b)));
+#else
+  dest[0] = glm_min(a[0], b[0]);
+  dest[1] = glm_min(a[1], b[1]);
+  dest[2] = glm_min(a[2], b[2]);
+  dest[3] = glm_min(a[3], b[3]);
+#endif
 }
 
 /*!
@@ -411,10 +755,18 @@ glm_vec4_minv(vec4 v1, vec4 v2, vec4 dest) {
 CGLM_INLINE
 void
 glm_vec4_clamp(vec4 v, float minVal, float maxVal) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(v, _mm_min_ps(_mm_max_ps(glmm_load(v), _mm_set1_ps(minVal)),
+                           _mm_set1_ps(maxVal)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(v, vminq_f32(vmaxq_f32(vld1q_f32(v), vdupq_n_f32(minVal)),
+                         vdupq_n_f32(maxVal)));
+#else
   v[0] = glm_clamp(v[0], minVal, maxVal);
   v[1] = glm_clamp(v[1], minVal, maxVal);
   v[2] = glm_clamp(v[2], minVal, maxVal);
   v[3] = glm_clamp(v[3], minVal, maxVal);
+#endif
 }
 
 /*!
@@ -429,14 +781,33 @@ glm_vec4_clamp(vec4 v, float minVal, float maxVal) {
  */
 CGLM_INLINE
 void
-glm_vec4_lerp(vec4 from, vec4 to, float t, vec4 dest) {
+glm_vec4_lerp(const vec4 from, const vec4 to, float t, vec4 dest) {
   vec4 s, v;
 
   /* from + s * (to - from) */
-  glm_vec4_broadcast(glm_clamp(t, 0.0f, 1.0f), s);
+  glm_vec4_broadcast(glm_clamp_zo(t), s);
   glm_vec4_sub(to, from, v);
-  glm_vec4_mulv(s, v, v);
+  glm_vec4_mul(s, v, v);
   glm_vec4_add(from, v, dest);
 }
 
+/*!
+ * @brief helper to fill vec4 as [S^3, S^2, S, 1]
+ *
+ * @param[in]   s    parameter
+ * @param[out]  dest destination
+ */
+CGLM_INLINE
+void
+glm_vec4_cubic(float s, vec4 dest) {
+  float ss;
+
+  ss = s * s;
+
+  dest[0] = ss * s;
+  dest[1] = ss;
+  dest[2] = s;
+  dest[3] = 1.0f;
+}
+
 #endif /* cglm_vec4_h */

include/cglm/version.h

@@ -9,7 +9,7 @@
 #define cglm_version_h
 
 #define CGLM_VERSION_MAJOR 0
-#define CGLM_VERSION_MINOR 4
-#define CGLM_VERSION_PATCH 0
+#define CGLM_VERSION_MINOR 5
+#define CGLM_VERSION_PATCH 4
 
 #endif /* cglm_version_h */

makefile.am

@@ -54,7 +54,12 @@ cglm_HEADERS = include/cglm/version.h \
                include/cglm/plane.h \
                include/cglm/frustum.h \
                include/cglm/box.h \
-                  include/cglm/color.h
+               include/cglm/color.h \
+               include/cglm/project.h \
+               include/cglm/sphere.h \
+               include/cglm/ease.h \
+               include/cglm/curve.h \
+               include/cglm/bezier.h
 
 cglm_calldir=$(includedir)/cglm/call
 cglm_call_HEADERS = include/cglm/call/mat4.h \
@@ -68,10 +73,17 @@ cglm_call_HEADERS = include/cglm/call/mat4.h \
                     include/cglm/call/euler.h \
                     include/cglm/call/plane.h \
                     include/cglm/call/frustum.h \
-                    include/cglm/call/box.h
+                    include/cglm/call/box.h \
+                    include/cglm/call/project.h \
+                    include/cglm/call/sphere.h \
+                    include/cglm/call/ease.h \
+                    include/cglm/call/curve.h \
+                    include/cglm/call/bezier.h
 
 cglm_simddir=$(includedir)/cglm/simd
-cglm_simd_HEADERS = include/cglm/simd/intrin.h
+cglm_simd_HEADERS = include/cglm/simd/intrin.h \
+                    include/cglm/simd/x86.h \
+                    include/cglm/simd/arm.h
 
 cglm_simd_sse2dir=$(includedir)/cglm/simd/sse2
 cglm_simd_sse2_HEADERS = include/cglm/simd/sse2/affine.h \
@@ -99,7 +111,11 @@ libcglm_la_SOURCES=\
     src/plane.c \
     src/frustum.c \
     src/box.c \
-    src/project.c
+    src/project.c \
+    src/sphere.c \
+    src/ease.c \
+    src/curve.c \
+    src/bezier.c
 
 test_tests_SOURCES=\
     test/src/test_common.c \
@@ -110,7 +126,11 @@ test_tests_SOURCES=\
     test/src/test_clamp.c \
     test/src/test_euler.c \
     test/src/test_quat.c \
-    test/src/test_vec4.c
+    test/src/test_vec4.c \
+    test/src/test_vec3.c \
+    test/src/test_mat3.c \
+    test/src/test_affine.c \
+    test/src/test_bezier.c
 
 all-local:
 	sh ./post-build.sh

post-build.sh

@@ -8,12 +8,17 @@
 
 cd $(dirname "$0")
 
-mkdir -p .libs
+mkdir -p "$(pwd)/.libs"
+
+libmocka_folder=$(pwd)/test/lib/cmocka/build/src/
 
 if [ "$(uname)" = "Darwin" ]; then
-  ln -sf $(pwd)/test/lib/cmocka/build/src/libcmocka.0.dylib \
-      .libs/libcmocka.0.dylib;
+  libcmocka=libcmocka.0.dylib
 else
-  ln -sf $(pwd)/test/lib/cmocka/build/src/libcmocka.so.0 \
-      .libs/libcmocka.so.0;
+  libcmocka=libcmocka.so.0
+fi
+
+libcmocka_path="$libmocka_folder$libcmocka"
+if [ -f "$libcmocka_path" ]; then
+  ln -sf "$libcmocka_path" "$(pwd)/.libs/$libcmocka";
 fi

src/affine.c

@@ -10,13 +10,19 @@
 
 CGLM_EXPORT
 void
-glmc_translate_to(mat4 m, vec3 v, mat4 dest) {
+glmc_translate_make(mat4 m, const vec3 v) {
+  glm_translate_make(m, v);
+}
+
+CGLM_EXPORT
+void
+glmc_translate_to(const mat4 m, const vec3 v, mat4 dest) {
   glm_translate_to(m, v, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_translate(mat4 m, vec3 v) {
+glmc_translate(mat4 m, const vec3 v) {
   glm_translate(m, v);
 }
 
@@ -40,78 +46,108 @@ glmc_translate_z(mat4 m, float to) {
 
 CGLM_EXPORT
 void
-glmc_scale_to(mat4 m, vec3 v, mat4 dest) {
+glmc_scale_make(mat4 m, const vec3 v) {
+  glm_scale_make(m, v);
+}
+
+CGLM_EXPORT
+void
+glmc_scale_to(const mat4 m, const vec3 v, mat4 dest) {
   glm_scale_to(m, v, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_scale(mat4 m, vec3 v) {
+glmc_scale(mat4 m, const vec3 v) {
   glm_scale(m, v);
 }
 
 CGLM_EXPORT
 void
-glmc_scale1(mat4 m, float s) {
-  glm_scale1(m, s);
+glmc_scale_uni(mat4 m, float s) {
+  glm_scale_uni(m, s);
 }
 
 CGLM_EXPORT
 void
-glmc_rotate_x(mat4 m, float rad, mat4 dest) {
+glmc_rotate_x(const mat4 m, float rad, mat4 dest) {
   glm_rotate_x(m, rad, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_rotate_y(mat4 m, float rad, mat4 dest) {
+glmc_rotate_y(const mat4 m, float rad, mat4 dest) {
   glm_rotate_y(m, rad, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_rotate_z(mat4 m, float rad, mat4 dest) {
+glmc_rotate_z(const mat4 m, float rad, mat4 dest) {
   glm_rotate_z(m, rad, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_rotate_ndc_make(mat4 m, float angle, vec3 axis_ndc) {
-  glm_rotate_ndc_make(m, angle, axis_ndc);
-}
-
-CGLM_EXPORT
-void
-glmc_rotate_make(mat4 m, float angle, vec3 axis) {
+glmc_rotate_make(mat4 m, float angle, const vec3 axis) {
   glm_rotate_make(m, angle, axis);
 }
 
 CGLM_EXPORT
 void
-glmc_rotate_ndc(mat4 m, float angle, vec3 axis_ndc) {
-  glm_rotate_ndc(m, angle, axis_ndc);
-}
-
-CGLM_EXPORT
-void
-glmc_rotate(mat4 m, float angle, vec3 axis) {
+glmc_rotate(mat4 m, float angle, const vec3 axis) {
   glm_rotate(m, angle, axis);
 }
 
 CGLM_EXPORT
 void
-glmc_decompose_scalev(mat4 m, vec3 s) {
-  glm_decompose_scalev(m, s);
+glmc_rotate_at(mat4 m, const vec3 pivot, float angle, const vec3 axis) {
+  glm_rotate_at(m, pivot, angle, axis);
 }
 
 CGLM_EXPORT
 void
-glmc_decompose_rs(mat4 m, mat4 r, vec3 s) {
+glmc_rotate_atm(mat4 m, const vec3 pivot, float angle, const vec3 axis) {
+  glm_rotate_atm(m, pivot, angle, axis);
+}
+
+CGLM_EXPORT
+void
+glmc_decompose_scalev(const mat4 m, vec3 s) {
+  glm_decompose_scalev(m, s);
+}
+
+CGLM_EXPORT
+bool
+glmc_uniscaled(const mat4 m) {
+  return glm_uniscaled(m);
+}
+
+CGLM_EXPORT
+void
+glmc_decompose_rs(const mat4 m, mat4 r, vec3 s) {
   glm_decompose_rs(m, r, s);
 }
 
 CGLM_EXPORT
 void
-glmc_decompose(mat4 m, vec4 t, mat4 r, vec3 s) {
+glmc_decompose(const mat4 m, vec4 t, mat4 r, vec3 s) {
   glm_decompose(m, t, r, s);
 }
+
+CGLM_EXPORT
+void
+glmc_mul(const mat4 m1, const mat4 m2, mat4 dest) {
+  glm_mul(m1, m2, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_mul_rot(const mat4 m1, const mat4 m2, mat4 dest) {
+  glm_mul_rot(m1, m2, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_inv_tr(mat4 mat) {
+  glm_inv_tr(mat);
+}

src/bezier.c

@@ -0,0 +1,27 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#include "../include/cglm/cglm.h"
+#include "../include/cglm/call.h"
+
+CGLM_EXPORT
+float
+glmc_bezier(float s, float p0, float c0, float c1, float p1) {
+  return glm_bezier(s, p0, c0, c1, p1);
+}
+
+CGLM_EXPORT
+float
+glmc_hermite(float s, float p0, float t0, float t1, float p1) {
+  return glm_hermite(s, p0, t0, t1, p1);
+}
+
+CGLM_EXPORT
+float
+glmc_decasteljau(float prm, float p0, float c0, float c1, float p1) {
+  return glm_decasteljau(prm, p0, c0, c1, p1);
+}

src/box.c

@@ -10,27 +10,87 @@
 
 CGLM_EXPORT
 void
-glmc_aabb_transform(vec3 box[2], mat4 m, vec3 dest[2]) {
+glmc_aabb_transform(const vec3 box[2], const mat4 m, vec3 dest[2]) {
   glm_aabb_transform(box, m, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_aabb_merge(vec3 box1[2], vec3 box2[2], vec3 dest[2]) {
+glmc_aabb_merge(const vec3 box1[2], const vec3 box2[2], vec3 dest[2]) {
   glm_aabb_merge(box1, box2, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_aabb_crop(vec3 box[2], vec3 cropBox[2], vec3 dest[2]) {
+glmc_aabb_crop(const vec3 box[2], const vec3 cropBox[2], vec3 dest[2]) {
   glm_aabb_crop(box, cropBox, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_aabb_crop_until(vec3 box[2],
-                     vec3 cropBox[2],
-                     vec3 clampBox[2],
+glmc_aabb_crop_until(const vec3 box[2],
+                     const vec3 cropBox[2],
+                     const vec3 clampBox[2],
                      vec3       dest[2]) {
   glm_aabb_crop_until(box, cropBox, clampBox, dest);
 }
+
+CGLM_EXPORT
+bool
+glmc_aabb_frustum(const vec3 box[2], vec4 planes[6]) {
+  return glm_aabb_frustum(box, planes);
+}
+
+CGLM_EXPORT
+void
+glmc_aabb_invalidate(vec3 box[2]) {
+  glm_aabb_invalidate(box);
+}
+
+CGLM_EXPORT
+bool
+glmc_aabb_isvalid(const vec3 box[2]) {
+  return glm_aabb_isvalid(box);
+}
+
+CGLM_EXPORT
+float
+glmc_aabb_size(const vec3 box[2]) {
+  return glm_aabb_size(box);
+}
+
+CGLM_EXPORT
+float
+glmc_aabb_radius(const vec3 box[2]) {
+  return glm_aabb_radius(box);
+}
+
+CGLM_EXPORT
+void
+glmc_aabb_center(const vec3 box[2], vec3 dest) {
+  glm_aabb_center(box, dest);
+}
+
+CGLM_EXPORT
+bool
+glmc_aabb_aabb(const vec3 box[2], const vec3 other[2]) {
+  return glm_aabb_aabb(box, other);
+}
+
+CGLM_EXPORT
+bool
+glmc_aabb_point(const vec3 box[2], const vec3 point) {
+  return glm_aabb_point(box, point);
+}
+
+CGLM_EXPORT
+bool
+glmc_aabb_contains(const vec3 box[2], const vec3 other[2]) {
+  return glm_aabb_contains(box, other);
+}
+
+CGLM_EXPORT
+bool
+glmc_aabb_sphere(const vec3 box[2], const vec4 s) {
+  return glm_aabb_sphere(box, s);
+}

src/cam.c

@@ -44,6 +44,36 @@ glmc_ortho(float left,
             dest);
 }
 
+CGLM_EXPORT
+void
+glmc_ortho_aabb(const vec3 box[2], mat4 dest) {
+  glm_ortho_aabb(box, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p(const vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_aabb_p(box, padding, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz(const vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_aabb_pz(box, padding, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_ortho_default(float aspect, mat4 dest) {
+  glm_ortho_default(aspect, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s(float aspect, float size, mat4 dest) {
+  glm_ortho_default_s(aspect, size, dest);
+}
+
 CGLM_EXPORT
 void
 glmc_perspective(float fovy,
@@ -60,21 +90,111 @@ glmc_perspective(float fovy,
 
 CGLM_EXPORT
 void
-glmc_lookat(vec3 eye,
-            vec3 center,
-            vec3 up,
+glmc_persp_move_far(mat4 proj, float deltaFar) {
+  glm_persp_move_far(proj, deltaFar);
+}
+
+CGLM_EXPORT
+void
+glmc_perspective_default(float aspect, mat4 dest) {
+  glm_perspective_default(aspect, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_perspective_resize(float aspect, mat4 proj) {
+  glm_perspective_resize(aspect, proj);
+}
+
+CGLM_EXPORT
+void
+glmc_lookat(const vec3 eye,
+            const vec3 center,
+            const vec3 up,
             mat4       dest) {
   glm_lookat(eye, center, up, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+glmc_look(const vec3 eye, const vec3 dir, const vec3 up, mat4 dest) {
   glm_look(eye, dir, up, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
+glmc_look_anyup(const vec3 eye, const vec3 dir, mat4 dest) {
   glm_look_anyup(eye, dir, dest);
 }
+
+CGLM_EXPORT
+void
+glmc_persp_decomp(const mat4 proj,
+                  float * __restrict nearVal,
+                  float * __restrict farVal,
+                  float * __restrict top,
+                  float * __restrict bottom,
+                  float * __restrict left,
+                  float * __restrict right) {
+  glm_persp_decomp(proj, nearVal, farVal, top, bottom, left, right);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_decompv(const mat4 proj, float dest[6]) {
+  glm_persp_decompv(proj, dest);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x(const mat4 proj,
+                    float * __restrict left,
+                    float * __restrict right) {
+  glm_persp_decomp_x(proj, left, right);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y(const mat4 proj,
+                    float * __restrict top,
+                    float * __restrict bottom) {
+  glm_persp_decomp_y(proj, top, bottom);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z(const mat4 proj,
+                    float * __restrict nearVal,
+                    float * __restrict farVal) {
+  glm_persp_decomp_z(proj, nearVal, farVal);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far(const mat4 proj, float * __restrict farVal) {
+  glm_persp_decomp_far(proj, farVal);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near(const mat4 proj, float * __restrict nearVal) {
+  glm_persp_decomp_near(proj, nearVal);
+}
+
+CGLM_EXPORT
+float
+glmc_persp_fovy(const mat4 proj) {
+  return glm_persp_fovy(proj);
+}
+
+CGLM_EXPORT
+float
+glmc_persp_aspect(const mat4 proj) {
+  return glm_persp_aspect(proj);
+}
+
+CGLM_EXPORT
+void
+glmc_persp_sizes(const mat4 proj, float fovy, vec4 dest) {
+  glm_persp_sizes(proj, fovy, dest);
+}

src/curve.c

@@ -0,0 +1,15 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#include "../include/cglm/cglm.h"
+#include "../include/cglm/call.h"
+
+CGLM_EXPORT
+float
+glmc_smc(float s, const mat4 m, const vec4 c) {
+  return glm_smc(s, m, c);
+}

src/ease.c

@@ -0,0 +1,195 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#include "../include/cglm/cglm.h"
+#include "../include/cglm/call.h"
+
+CGLM_EXPORT
+float
+glmc_ease_linear(float t) {
+  return glm_ease_linear(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_sine_in(float t) {
+  return glm_ease_sine_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_sine_out(float t) {
+  return glm_ease_sine_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_sine_inout(float t) {
+  return glm_ease_sine_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quad_in(float t) {
+  return glm_ease_quad_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quad_out(float t) {
+  return glm_ease_quad_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quad_inout(float t) {
+  return glm_ease_quad_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_cubic_in(float t) {
+  return glm_ease_cubic_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_cubic_out(float t) {
+  return glm_ease_cubic_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_cubic_inout(float t) {
+  return glm_ease_cubic_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quart_in(float t) {
+  return glm_ease_quart_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quart_out(float t) {
+  return glm_ease_quart_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quart_inout(float t) {
+  return glm_ease_quart_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quint_in(float t) {
+  return glm_ease_quint_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quint_out(float t) {
+  return glm_ease_quint_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_quint_inout(float t) {
+  return glm_ease_quint_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_exp_in(float t) {
+  return glm_ease_exp_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_exp_out(float t) {
+  return glm_ease_exp_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_exp_inout(float t) {
+  return glm_ease_exp_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_circ_in(float t) {
+  return glm_ease_circ_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_circ_out(float t) {
+  return glm_ease_circ_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_circ_inout(float t) {
+  return glm_ease_circ_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_back_in(float t) {
+  return glm_ease_back_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_back_out(float t) {
+  return glm_ease_back_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_back_inout(float t) {
+  return glm_ease_back_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_elast_in(float t) {
+  return glm_ease_elast_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_elast_out(float t) {
+  return glm_ease_elast_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_elast_inout(float t) {
+  return glm_ease_elast_inout(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_bounce_out(float t) {
+  return glm_ease_bounce_out(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_bounce_in(float t) {
+  return glm_ease_bounce_in(t);
+}
+
+CGLM_EXPORT
+float
+glmc_ease_bounce_inout(float t) {
+  return glm_ease_bounce_inout(t);
+}

src/euler.c

@@ -10,54 +10,54 @@
 
 CGLM_EXPORT
 void
-glmc_euler_angles(mat4 m, vec3 dest) {
+glmc_euler_angles(const mat4 m, vec3 dest) {
   glm_euler_angles(m, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler(vec3 angles, mat4 dest) {
+glmc_euler(const vec3 angles, mat4 dest) {
   glm_euler(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_xyz(vec3 angles,  mat4 dest) {
+glmc_euler_xyz(const vec3 angles,  mat4 dest) {
   glm_euler_xyz(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_zyx(vec3 angles,  mat4 dest) {
+glmc_euler_zyx(const vec3 angles,  mat4 dest) {
   glm_euler_zyx(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_zxy(vec3 angles, mat4 dest) {
+glmc_euler_zxy(const vec3 angles, mat4 dest) {
   glm_euler_zxy(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_xzy(vec3 angles, mat4 dest) {
+glmc_euler_xzy(const vec3 angles, mat4 dest) {
   glm_euler_xzy(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_yzx(vec3 angles, mat4 dest) {
+glmc_euler_yzx(const vec3 angles, mat4 dest) {
   glm_euler_yzx(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_yxz(vec3 angles, mat4 dest) {
+glmc_euler_yxz(const vec3 angles, mat4 dest) {
   glm_euler_yxz(angles, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_euler_by_order(vec3 angles, glm_euler_sq axis, mat4 dest) {
+glmc_euler_by_order(const vec3 angles, glm_euler_sq axis, mat4 dest) {
   glm_euler_by_order(angles, axis, dest);
 }

src/frustum.c

@@ -10,31 +10,31 @@
 
 CGLM_EXPORT
 void
-glmc_frustum_planes(mat4 m, vec4 dest[6]) {
+glmc_frustum_planes(const mat4 m, vec4 dest[6]) {
   glm_frustum_planes(m, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_frustum_corners(mat4 invMat, vec4 dest[8]) {
+glmc_frustum_corners(const mat4 invMat, vec4 dest[8]) {
   glm_frustum_corners(invMat, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_frustum_center(vec4 corners[8], vec4 dest) {
+glmc_frustum_center(const vec4 corners[8], vec4 dest) {
   glm_frustum_center(corners, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]) {
+glmc_frustum_box(const vec4 corners[8], const mat4 m, vec3 box[2]) {
   glm_frustum_box(corners, m, box);
 }
 
 CGLM_EXPORT
 void
-glmc_frustum_corners_at(vec4  corners[8],
+glmc_frustum_corners_at(const vec4 corners[8],
                         float      splitDist,
                         float      farDist,
                         vec4       planeCorners[4]) {

src/io.c

@@ -10,35 +10,35 @@
 
 CGLM_EXPORT
 void
-glmc_mat4_print(mat4   matrix,
-                FILE * __restrict ostream) {
+glmc_mat4_print(const mat4   matrix,
+                FILE * const __restrict ostream) {
   glm_mat4_print(matrix, ostream);
 }
 
 CGLM_EXPORT
 void
-glmc_mat3_print(mat3 matrix,
-                FILE * __restrict ostream) {
+glmc_mat3_print(const mat3 matrix,
+                FILE * const __restrict ostream) {
   glm_mat3_print(matrix, ostream);
 }
 
 CGLM_EXPORT
 void
-glmc_vec4_print(vec4 vec,
-                FILE * __restrict ostream) {
+glmc_vec4_print(const vec4 vec,
+                FILE * const __restrict ostream) {
   glm_vec4_print(vec, ostream);
 }
 
 CGLM_EXPORT
 void
-glmc_vec3_print(vec3 vec,
-                FILE * __restrict ostream) {
+glmc_vec3_print(const vec3 vec,
+                FILE * const __restrict ostream) {
   glm_vec3_print(vec, ostream);
 }
 
 CGLM_EXPORT
 void
-glmc_versor_print(versor vec,
-                  FILE * __restrict ostream) {
+glmc_versor_print(const versor vec,
+                  FILE * const __restrict ostream) {
   glm_versor_print(vec, ostream);
 }

src/mat3.c

@@ -10,7 +10,7 @@
 
 CGLM_EXPORT
 void
-glmc_mat3_copy(mat3 mat, mat3 dest) {
+glmc_mat3_copy(const mat3 mat, mat3 dest) {
   glm_mat3_copy(mat, dest);
 }
 
@@ -22,13 +22,19 @@ glmc_mat3_identity(mat3 mat) {
 
 CGLM_EXPORT
 void
-glmc_mat3_mul(mat3 m1, mat3 m2, mat3 dest) {
+glmc_mat3_identity_array(mat3 * const  __restrict mat, size_t count) {
+  glm_mat3_identity_array(mat, count);
+}
+
+CGLM_EXPORT
+void
+glmc_mat3_mul(const mat3 m1, const mat3 m2, mat3 dest) {
   glm_mat3_mul(m1, m2, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat3_transpose_to(mat3 m, mat3 dest) {
+glmc_mat3_transpose_to(const mat3 m, mat3 dest) {
   glm_mat3_transpose_to(m, dest);
 }
 
@@ -40,10 +46,22 @@ glmc_mat3_transpose(mat3 m) {
 
 CGLM_EXPORT
 void
-glmc_mat3_mulv(mat3 m, vec3 v, vec3 dest) {
+glmc_mat3_mulv(const mat3 m, const vec3 v, vec3 dest) {
   glm_mat3_mulv(m, v, dest);
 }
 
+CGLM_EXPORT
+float
+glmc_mat3_trace(const mat3 m) {
+  return glm_mat3_trace(m);
+}
+
+CGLM_EXPORT
+void
+glmc_mat3_quat(const mat3 m, versor dest) {
+  glm_mat3_quat(m, dest);
+}
+
 CGLM_EXPORT
 void
 glmc_mat3_scale(mat3 m, float s) {
@@ -52,13 +70,13 @@ glmc_mat3_scale(mat3 m, float s) {
 
 CGLM_EXPORT
 float
-glmc_mat3_det(mat3 mat) {
+glmc_mat3_det(const mat3 mat) {
   return glm_mat3_det(mat);
 }
 
 CGLM_EXPORT
 void
-glmc_mat3_inv(mat3 mat, mat3 dest) {
+glmc_mat3_inv(const mat3 mat, mat3 dest) {
   glm_mat3_inv(mat, dest);
 }
 
@@ -73,3 +91,9 @@ void
 glmc_mat3_swap_row(mat3 mat, int row1, int row2) {
   glm_mat3_swap_row(mat, row1, row2);
 }
+
+CGLM_EXPORT
+float
+glmc_mat3_rmc(const vec3 r, const mat3 m, const vec3 c) {
+  return glm_mat3_rmc(r, m, c);
+}

src/mat4.c

@@ -10,13 +10,13 @@
 
 CGLM_EXPORT
 void
-glmc_mat4_ucopy(mat4 mat, mat4 dest) {
+glmc_mat4_ucopy(const mat4 mat, mat4 dest) {
   glm_mat4_copy(mat, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_copy(mat4 mat, mat4 dest) {
+glmc_mat4_copy(const mat4 mat, mat4 dest) {
   glm_mat4_copy(mat, dest);
 }
 
@@ -28,49 +28,73 @@ glmc_mat4_identity(mat4 mat) {
 
 CGLM_EXPORT
 void
-glmc_mat4_pick3(mat4 mat, mat3 dest) {
+glmc_mat4_identity_array(mat4 * const __restrict mat, size_t count) {
+  glm_mat4_identity_array(mat, count);
+}
+
+CGLM_EXPORT
+void
+glmc_mat4_pick3(const mat4 mat, mat3 dest) {
   glm_mat4_pick3(mat, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_pick3t(mat4 mat, mat3 dest) {
+glmc_mat4_pick3t(const mat4 mat, mat3 dest) {
   glm_mat4_pick3t(mat, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_ins3(mat3 mat, mat4 dest) {
+glmc_mat4_ins3(const mat3 mat, mat4 dest) {
   glm_mat4_ins3(mat, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_mul(mat4 m1, mat4 m2, mat4 dest) {
+glmc_mat4_mul(const mat4 m1, const mat4 m2, mat4 dest) {
   glm_mat4_mul(m1, m2, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_mulN(mat4 * __restrict matrices[], uint32_t len, mat4 dest) {
+glmc_mat4_mulN(mat4 * const __restrict matrices[], uint32_t len, mat4 dest) {
   glm_mat4_mulN(matrices, len, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
+glmc_mat4_mulv(const mat4 m, const vec4 v, vec4 dest) {
   glm_mat4_mulv(m, v, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_quat(mat4 m, versor dest) {
+glmc_mat4_mulv3(const mat4 m, const vec3 v, float last, vec3 dest) {
+  glm_mat4_mulv3(m, v, last, dest);
+}
+
+CGLM_EXPORT
+float
+glmc_mat4_trace(const mat4 m) {
+  return glm_mat4_trace(m);
+}
+
+CGLM_EXPORT
+float
+glmc_mat4_trace3(const mat4 m) {
+  return glm_mat4_trace3(m);
+}
+
+CGLM_EXPORT
+void
+glmc_mat4_quat(const mat4 m, versor dest) {
   glm_mat4_quat(m, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_transpose_to(mat4 m, mat4 dest) {
+glmc_mat4_transpose_to(const mat4 m, mat4 dest) {
   glm_mat4_transpose_to(m, dest);
 }
 
@@ -94,22 +118,28 @@ glmc_mat4_scale(mat4 m, float s) {
 
 CGLM_EXPORT
 float
-glmc_mat4_det(mat4 mat) {
+glmc_mat4_det(const mat4 mat) {
   return glm_mat4_det(mat);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_inv(mat4 mat, mat4 dest) {
+glmc_mat4_inv(const mat4 mat, mat4 dest) {
   glm_mat4_inv(mat, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4_inv_precise(mat4 mat, mat4 dest) {
+glmc_mat4_inv_precise(const mat4 mat, mat4 dest) {
   glm_mat4_inv_precise(mat, dest);
 }
 
+CGLM_EXPORT
+void
+glmc_mat4_inv_fast(const mat4 mat, mat4 dest) {
+  glm_mat4_inv_fast(mat, dest);
+}
+
 CGLM_EXPORT
 void
 glmc_mat4_swap_col(mat4 mat, int col1, int col2) {
@@ -121,3 +151,9 @@ void
 glmc_mat4_swap_row(mat4 mat, int row1, int row2) {
   glm_mat4_swap_row(mat, row1, row2);
 }
+
+CGLM_EXPORT
+float
+glmc_mat4_rmc(const vec4 r, const mat4 m, const vec4 c) {
+  return glm_mat4_rmc(r, m, c);
+}

src/project.c

@@ -10,18 +10,18 @@
 
 CGLM_EXPORT
 void
-glmc_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
+glmc_unprojecti(const vec3 pos, const mat4 invMat, const vec4 vp, vec3 dest) {
   glm_unprojecti(pos, invMat, vp, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+glmc_unproject(const vec3 pos, const mat4 m, const vec4 vp, vec3 dest) {
   glm_unproject(pos, m, vp, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+glmc_project(const vec3 pos, const mat4 m, const vec4 vp, vec3 dest) {
   glm_project(pos, m, vp, dest);
 }

src/quat.c

@@ -8,13 +8,18 @@
 #include "../include/cglm/cglm.h"
 #include "../include/cglm/call.h"
 
-
 CGLM_EXPORT
 void
 glmc_quat_identity(versor q) {
   glm_quat_identity(q);
 }
 
+CGLM_EXPORT
+void
+glmc_quat_identity_array(versor * const __restrict q, size_t count) {
+  glm_quat_identity_array(q, count);
+}
+
 CGLM_EXPORT
 void
 glmc_quat_init(versor q, float x, float y, float z, float w) {
@@ -29,25 +34,25 @@ glmc_quat(versor q, float angle, float x, float y, float z) {
 
 CGLM_EXPORT
 void
-glmc_quatv(versor q, float angle, vec3 axis) {
+glmc_quatv(versor q, float angle, const vec3 axis) {
   glm_quatv(q, angle, axis);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_copy(versor q, versor dest) {
+glmc_quat_copy(const versor q, versor dest) {
   glm_quat_copy(q, dest);
 }
 
 CGLM_EXPORT
 float
-glmc_quat_norm(versor q) {
+glmc_quat_norm(const versor q) {
   return glm_quat_norm(q);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_normalize_to(versor q, versor dest) {
+glmc_quat_normalize_to(const versor q, versor dest) {
   glm_quat_normalize_to(q, dest);
 }
 
@@ -59,138 +64,154 @@ glmc_quat_normalize(versor q) {
 
 CGLM_EXPORT
 float
-glmc_quat_dot(versor p, versor q) {
+glmc_quat_dot(const versor p, const versor q) {
   return glm_quat_dot(p, q);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_conjugate(versor q, versor dest) {
+glmc_quat_conjugate(const versor q, versor dest) {
   glm_quat_conjugate(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_inv(versor q, versor dest) {
+glmc_quat_inv(const versor q, versor dest) {
   glm_quat_inv(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_add(versor p, versor q, versor dest) {
+glmc_quat_add(const versor p, const versor q, versor dest) {
   glm_quat_add(p, q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_sub(versor p, versor q, versor dest) {
+glmc_quat_sub(const versor p, const versor q, versor dest) {
   glm_quat_sub(p, q, dest);
 }
 
 CGLM_EXPORT
 float
-glmc_quat_real(versor q) {
+glmc_quat_real(const versor q) {
   return glm_quat_real(q);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_imag(versor q, vec3 dest) {
+glmc_quat_imag(const versor q, vec3 dest) {
   glm_quat_imag(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_imagn(versor q, vec3 dest) {
+glmc_quat_imagn(const versor q, vec3 dest) {
   glm_quat_imagn(q, dest);
 }
 
 CGLM_EXPORT
 float
-glmc_quat_imaglen(versor q) {
+glmc_quat_imaglen(const versor q) {
   return glm_quat_imaglen(q);
 }
 
 CGLM_EXPORT
 float
-glmc_quat_angle(versor q) {
+glmc_quat_angle(const versor q) {
   return glm_quat_angle(q);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_axis(versor q, versor dest) {
+glmc_quat_axis(const versor q, versor dest) {
   glm_quat_axis(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_mul(versor p, versor q, versor dest) {
+glmc_quat_mul(const versor p, const versor q, versor dest) {
   glm_quat_mul(p, q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_mat4(versor q, mat4 dest) {
+glmc_quat_mat4(const versor q, mat4 dest) {
   glm_quat_mat4(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_mat4t(versor q, mat4 dest) {
+glmc_quat_mat4t(const versor q, mat4 dest) {
   glm_quat_mat4t(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_mat3(versor q, mat3 dest) {
+glmc_quat_mat3(const versor q, mat3 dest) {
   glm_quat_mat3(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_mat3t(versor q, mat3 dest) {
+glmc_quat_mat3t(const versor q, mat3 dest) {
   glm_quat_mat3t(q, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_lerp(versor from, versor to, float t, versor dest) {
+glmc_quat_lerp(const versor from, const versor to, float t, versor dest) {
   glm_quat_lerp(from, to, t, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_slerp(versor from, versor to, float t, versor dest) {
+glmc_quat_slerp(const versor from, const versor to, float t, versor dest) {
   glm_quat_slerp(from, to, t, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_look(vec3 eye, versor ori, mat4 dest) {
+glmc_quat_look(const vec3 eye, const versor ori, mat4 dest) {
   glm_quat_look(eye, ori, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest) {
+glmc_quat_for(const vec3 dir, const vec3 fwd, const vec3 up, versor dest) {
   glm_quat_for(dir, fwd, up, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest) {
+glmc_quat_forp(const vec3 from,
+               const vec3 to,
+               const vec3 fwd,
+               const vec3 up,
+               versor     dest) {
   glm_quat_forp(from, to, fwd, up, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_rotatev(versor q, vec3 v, vec3 dest) {
+glmc_quat_rotatev(const versor q, const vec3 v, vec3 dest) {
   glm_quat_rotatev(q, v, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_quat_rotate(mat4 m, versor q, mat4 dest) {
+glmc_quat_rotate(const mat4 m, const versor q, mat4 dest) {
   glm_quat_rotate(m, q, dest);
 }
+
+CGLM_EXPORT
+void
+glmc_quat_rotate_at(mat4 model, const versor q, const vec3 pivot) {
+  glm_quat_rotate_at(model, q, pivot);
+}
+
+CGLM_EXPORT
+void
+glmc_quat_rotate_atm(mat4 m, const versor q, const vec3 pivot) {
+  glm_quat_rotate_atm(m, q, pivot);
+}