update affine-post.h

remove redundant comments
Merge pull request #260 from recp/new-affine
2026-02-17 03:39:05 +00:00 · 2022-10-23 14:27:34 +03:00 · 2022-10-23 14:22:16 +03:00 · 2022-10-23 14:06:34 +03:00 · 2022-10-23 12:09:44 +03:00 · 2022-10-23 12:08:37 +03:00
171 changed files with 14050 additions and 1381 deletions
--- a/.github/FUNDING.yml
+++ b/.github/FUNDING.yml
@@ -1,7 +1,7 @@
 # These are supported funding model platforms

-github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
-patreon: # Replace with a single Patreon username
+github: [recp]
+patreon: recp
 open_collective: cglm
 ko_fi: # Replace with a single Ko-fi username
 tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
--- a/.gitignore
+++ b/.gitignore
@@ -76,3 +76,7 @@ build/
 conftest.dir/*
 confdefs.h
 *.xcuserdatad
+.idea
+cmake-build-debug
+*.o.tmp
+xcode/*
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1,5 +1,10 @@
 cmake_minimum_required(VERSION 3.8.2)
-project(cglm VERSION 0.7.9 LANGUAGES C)
+project(cglm
+  VERSION 0.8.6
+  HOMEPAGE_URL https://github.com/recp/cglm
+  DESCRIPTION "OpenGL Mathematics (glm) for C"
+  LANGUAGES C
+)

 set(CMAKE_C_STANDARD 11)
 set(CMAKE_C_STANDARD_REQUIRED YES)
@@ -18,7 +23,7 @@ else(CGLM_STATIC)
 endif()

 if(CGLM_USE_C99)
-  set(C_STANDARD 99)
+  set(CMAKE_C_STANDARD 99)
 endif()

 if(MSVC)
@@ -47,7 +52,10 @@ include(GNUInstallDirs)

 set(CPACK_PROJECT_NAME ${PROJECT_NAME})
 set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
-include(CPack)
+
+if(NOT CPack_CMake_INCLUDED)
+  include(CPack)
+endif()

 # Target Start
 add_library(${PROJECT_NAME}
@@ -58,8 +66,11 @@ add_library(${PROJECT_NAME}
  src/quat.c
  src/cam.c
  src/vec2.c
+  src/ivec2.c
  src/vec3.c
+  src/ivec3.c
  src/vec4.c
+  src/ivec4.c
  src/mat2.c
  src/mat3.c
  src/mat4.c
@@ -73,6 +84,20 @@ add_library(${PROJECT_NAME}
  src/bezier.c
  src/ray.c
  src/affine2d.c
+  src/clipspace/ortho_lh_no.c
+  src/clipspace/ortho_lh_zo.c
+  src/clipspace/ortho_rh_no.c
+  src/clipspace/ortho_rh_zo.c
+  src/clipspace/persp_lh_no.c
+  src/clipspace/persp_lh_zo.c
+  src/clipspace/persp_rh_no.c
+  src/clipspace/persp_rh_zo.c
+  src/clipspace/view_lh_no.c
+  src/clipspace/view_lh_zo.c
+  src/clipspace/view_rh_no.c
+  src/clipspace/view_rh_zo.c
+  src/clipspace/project_no.c
+  src/clipspace/project_zo.c
  )

 if(CGLM_SHARED)
@@ -85,6 +110,12 @@ set_target_properties(${PROJECT_NAME} PROPERTIES
                              VERSION ${PROJECT_VERSION} 
                            SOVERSION ${PROJECT_VERSION_MAJOR})

+if(WIN32)
+  # Because SOVERSION has no effect to file naming on Windows
+  set_target_properties(${PROJECT_NAME} PROPERTIES
+    RUNTIME_OUTPUT_NAME ${PROJECT_NAME}-${PROJECT_VERSION_MAJOR})
+endif()
+
 target_include_directories(${PROJECT_NAME}
    PUBLIC 
        $<INSTALL_INTERFACE:include>    
@@ -93,6 +124,11 @@ target_include_directories(${PROJECT_NAME}
        ${CMAKE_CURRENT_SOURCE_DIR}/src
 )

+# Target for header-only usage
+add_library(${PROJECT_NAME}_headers INTERFACE)
+target_include_directories(${PROJECT_NAME}_headers INTERFACE
+  ${CMAKE_CURRENT_SOURCE_DIR}/include)
+
 # Test Configuration
 if(CGLM_USE_TEST)
  include(CTest)
@@ -105,7 +141,7 @@ install(TARGETS ${PROJECT_NAME}
        EXPORT  ${PROJECT_NAME}
        LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
        ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-        RUNTIME DESTINATION ${CMAKE_INSTALL_LIBDIR})
+        RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})

 install(DIRECTORY include/${PROJECT_NAME} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
        PATTERN ".*" EXCLUDE)
@@ -117,6 +153,11 @@ export(TARGETS ${PROJECT_NAME}
 )

 install(EXPORT      ${PROJECT_NAME}
+        FILE        "${PROJECT_NAME}Config.cmake"
        NAMESPACE   ${PROJECT_NAME}::
-        DESTINATION ${CMAKE_INSTALL_LIBDIR}/${PROJECT_NAME}/cmake)
+        DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/${PROJECT_NAME})

+configure_file(cglm.pc.in cglm.pc @ONLY)
+
+install(FILES ${CMAKE_BINARY_DIR}/cglm.pc
+  DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
--- a/8
+++ b/8
@@ -74,3 +74,11 @@ Link to paper: http://webserver2.tecgraf.puc-rio.br/~mgattass/cg/trbRR/Fast%20Mi

 14. ARM NEON: Matrix Vector Multiplication
 https://stackoverflow.com/a/57793352/2676533
+
+16. ARM NEON Div
+
+http://github.com/microsoft/DirectXMath
+
+17. Pick Matrix
+
+glu project -> project.c
--- a/Makefile.am
+++ b/Makefile.am
@@ -46,16 +46,19 @@ cglm_HEADERS = include/cglm/version.h \
               include/cglm/mat3.h \
               include/cglm/mat2.h \
               include/cglm/affine.h \
+               include/cglm/affine-mat.h \
               include/cglm/vec2.h \
               include/cglm/vec2-ext.h \
+               include/cglm/ivec2.h \
               include/cglm/vec3.h \
               include/cglm/vec3-ext.h \
+               include/cglm/ivec3.h \
               include/cglm/vec4.h \
               include/cglm/vec4-ext.h \
+               include/cglm/ivec4.h \
               include/cglm/euler.h \
               include/cglm/util.h \
               include/cglm/quat.h \
-               include/cglm/affine-mat.h \
               include/cglm/plane.h \
               include/cglm/frustum.h \
               include/cglm/box.h \
@@ -69,6 +72,25 @@ cglm_HEADERS = include/cglm/version.h \
               include/cglm/ray.h \
               include/cglm/affine2d.h

+cglm_clipspacedir=$(includedir)/cglm/clipspace
+cglm_clipspace_HEADERS = include/cglm/clipspace/persp.h \
+                         include/cglm/clipspace/persp_lh_no.h \
+                         include/cglm/clipspace/persp_lh_zo.h \
+                         include/cglm/clipspace/persp_rh_no.h \
+                         include/cglm/clipspace/persp_rh_zo.h \
+                         include/cglm/clipspace/ortho_lh_no.h \
+                         include/cglm/clipspace/ortho_lh_zo.h \
+                         include/cglm/clipspace/ortho_rh_no.h \
+                         include/cglm/clipspace/ortho_rh_zo.h \
+                         include/cglm/clipspace/view_lh.h \
+                         include/cglm/clipspace/view_rh.h \
+                         include/cglm/clipspace/view_lh_no.h \
+                         include/cglm/clipspace/view_lh_zo.h \
+                         include/cglm/clipspace/view_rh_no.h \
+                         include/cglm/clipspace/view_rh_zo.h \
+                         include/cglm/clipspace/project_no.h \
+                         include/cglm/clipspace/project_zo.h
+
 cglm_calldir=$(includedir)/cglm/call
 cglm_call_HEADERS = include/cglm/call/mat4.h \
                    include/cglm/call/mat3.h \
@@ -76,7 +98,9 @@ cglm_call_HEADERS = include/cglm/call/mat4.h \
                    include/cglm/call/vec2.h \
                    include/cglm/call/vec3.h \
                    include/cglm/call/vec4.h \
-                    include/cglm/call/affine.h \
+                    include/cglm/call/ivec2.h \
+                    include/cglm/call/ivec3.h \
+                    include/cglm/call/ivec4.h \
                    include/cglm/call/io.h \
                    include/cglm/call/cam.h \
                    include/cglm/call/quat.h \
@@ -90,8 +114,25 @@ cglm_call_HEADERS = include/cglm/call/mat4.h \
                    include/cglm/call/curve.h \
                    include/cglm/call/bezier.h \
                    include/cglm/call/ray.h \
+                    include/cglm/call/affine.h \
                    include/cglm/call/affine2d.h

+cglm_call_clipspacedir=$(includedir)/cglm/call/clipspace
+cglm_call_clipspace_HEADERS = include/cglm/call/clipspace/persp_lh_no.h \
+                              include/cglm/call/clipspace/persp_lh_zo.h \
+                              include/cglm/call/clipspace/persp_rh_no.h \
+                              include/cglm/call/clipspace/persp_rh_zo.h \
+                              include/cglm/call/clipspace/ortho_lh_no.h \
+                              include/cglm/call/clipspace/ortho_lh_zo.h \
+                              include/cglm/call/clipspace/ortho_rh_no.h \
+                              include/cglm/call/clipspace/ortho_rh_zo.h \
+                              include/cglm/call/clipspace/view_lh_no.h \
+                              include/cglm/call/clipspace/view_lh_zo.h \
+                              include/cglm/call/clipspace/view_rh_no.h \
+                              include/cglm/call/clipspace/view_rh_zo.h \
+                              include/cglm/call/clipspace/project_no.h \
+                              include/cglm/call/clipspace/project_zo.h
+
 cglm_simddir=$(includedir)/cglm/simd
 cglm_simd_HEADERS = include/cglm/simd/intrin.h \
                    include/cglm/simd/x86.h \
@@ -109,19 +150,25 @@ cglm_simd_avx_HEADERS = include/cglm/simd/avx/mat4.h \
                        include/cglm/simd/avx/affine.h

 cglm_simd_neondir=$(includedir)/cglm/simd/neon
-cglm_simd_neon_HEADERS = include/cglm/simd/neon/mat4.h
+cglm_simd_neon_HEADERS = include/cglm/simd/neon/affine.h \
+                         include/cglm/simd/neon/mat2.h \
+                         include/cglm/simd/neon/mat4.h \
+                         include/cglm/simd/neon/quat.h

 cglm_structdir=$(includedir)/cglm/struct
 cglm_struct_HEADERS = include/cglm/struct/mat4.h \
                      include/cglm/struct/mat3.h \
                      include/cglm/struct/mat2.h \
+                      include/cglm/struct/affine-pre.h \
+                      include/cglm/struct/affine-post.h \
+                      include/cglm/struct/affine.h \
+                      include/cglm/struct/affine2d.h \
                      include/cglm/struct/vec2.h \
                      include/cglm/struct/vec2-ext.h \
                      include/cglm/struct/vec3.h \
                      include/cglm/struct/vec3-ext.h \
                      include/cglm/struct/vec4.h \
                      include/cglm/struct/vec4-ext.h \
-                      include/cglm/struct/affine.h \
                      include/cglm/struct/io.h \
                      include/cglm/struct/cam.h \
                      include/cglm/struct/quat.h \
@@ -132,8 +179,23 @@ cglm_struct_HEADERS = include/cglm/struct/mat4.h \
                      include/cglm/struct/project.h \
                      include/cglm/struct/sphere.h \
                      include/cglm/struct/color.h \
-                      include/cglm/struct/curve.h \
-                      include/cglm/struct/affine2d.h
+                      include/cglm/struct/curve.h
+
+cglm_struct_clipspacedir=$(includedir)/cglm/struct/clipspace
+cglm_struct_clipspace_HEADERS = include/cglm/struct/clipspace/persp_lh_no.h \
+                                include/cglm/struct/clipspace/persp_lh_zo.h \
+                                include/cglm/struct/clipspace/persp_rh_no.h \
+                                include/cglm/struct/clipspace/persp_rh_zo.h \
+                                include/cglm/struct/clipspace/ortho_lh_no.h \
+                                include/cglm/struct/clipspace/ortho_lh_zo.h \
+                                include/cglm/struct/clipspace/ortho_rh_no.h \
+                                include/cglm/struct/clipspace/ortho_rh_zo.h \
+                                include/cglm/struct/clipspace/view_lh_no.h \
+                                include/cglm/struct/clipspace/view_lh_zo.h \
+                                include/cglm/struct/clipspace/view_rh_no.h \
+                                include/cglm/struct/clipspace/view_rh_zo.h \
+                                include/cglm/struct/clipspace/project_no.h \
+                                include/cglm/struct/clipspace/project_zo.h

 libcglm_la_SOURCES=\
    src/euler.c \
@@ -142,8 +204,11 @@ libcglm_la_SOURCES=\
    src/quat.c \
    src/cam.c \
    src/vec2.c \
+    src/ivec2.c \
    src/vec3.c \
+    src/ivec3.c \
    src/vec4.c \
+    src/ivec4.c \
    src/mat2.c \
    src/mat3.c \
    src/mat4.c \
@@ -156,13 +221,31 @@ libcglm_la_SOURCES=\
    src/curve.c \
    src/bezier.c \
    src/ray.c \
-    src/affine2d.c
+    src/affine2d.c \
+    src/clipspace/ortho_lh_no.c \
+    src/clipspace/ortho_lh_zo.c \
+    src/clipspace/ortho_rh_no.c \
+    src/clipspace/ortho_rh_zo.c \
+    src/clipspace/persp_lh_no.c \
+    src/clipspace/persp_lh_zo.c \
+    src/clipspace/persp_rh_no.c \
+    src/clipspace/persp_rh_zo.c \
+    src/clipspace/view_lh_no.c \
+    src/clipspace/view_lh_zo.c \
+    src/clipspace/view_rh_no.c \
+    src/clipspace/view_rh_zo.c \
+    src/clipspace/project_no.c \
+    src/clipspace/project_zo.c
    
 test_tests_SOURCES=\
    test/runner.c \
    test/src/test_common.c \
    test/src/tests.c \
    test/src/test_cam.c \
+    test/src/test_cam_lh_zo.c \
+    test/src/test_cam_rh_zo.c \
+    test/src/test_cam_lh_no.c \
+    test/src/test_cam_rh_no.c \
    test/src/test_clamp.c \
    test/src/test_euler.c \
    test/src/test_bezier.c \
--- a/README.md
+++ b/README.md
@@ -1,19 +1,59 @@
 # 🎥 OpenGL Mathematics (glm) for `C`
-[![Build Status](https://travis-ci.org/recp/cglm.svg?branch=master)](https://travis-ci.org/recp/cglm)
- [![Build status](https://ci.appveyor.com/api/projects/status/av7l3gc0yhfex8y4/branch/master?svg=true)](https://ci.appveyor.com/project/recp/cglm/branch/master)
-[![Documentation Status](https://readthedocs.org/projects/cglm/badge/?version=latest)](http://cglm.readthedocs.io/en/latest/?badge=latest)
-[![Coverage Status](https://coveralls.io/repos/github/recp/cglm/badge.svg?branch=master)](https://coveralls.io/github/recp/cglm?branch=master)
-[![codecov](https://codecov.io/gh/recp/cglm/branch/master/graph/badge.svg)](https://codecov.io/gh/recp/cglm)
-[![Codacy Badge](https://api.codacy.com/project/badge/Grade/6a62b37d5f214f178ebef269dc4a6bf1)](https://www.codacy.com/app/recp/cglm?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=recp/cglm&amp;utm_campaign=Badge_Grade)
-[![Backers on Open Collective](https://opencollective.com/cglm/backers/badge.svg)](#backers)
-[![Sponsors on Open Collective](https://opencollective.com/cglm/sponsors/badge.svg)](#sponsors)

-#### Documentation
+<p align="center">
+   <img alt="" src="cglm.png" width="550" />
+</p>
+<br>
+<p align="center">
+    <a href="https://travis-ci.com/recp/cglm">
+        <img src="https://travis-ci.com/recp/cglm.svg?branch=master"
+             alt="Build Status">
+    </a>
+    <a href="https://ci.appveyor.com/project/recp/cglm/branch/master">
+        <img src="https://ci.appveyor.com/api/projects/status/av7l3gc0yhfex8y4/branch/master?svg=true"
+             alt="Windows Build Status">
+    </a>
+    <a href="http://cglm.readthedocs.io/en/latest/?badge=latest">
+        <img src="https://readthedocs.org/projects/cglm/badge/?version=latest"
+             alt="Documentation Status">
+    </a>
+    <a href="https://www.codacy.com/app/recp/cglm?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=recp/cglm&amp;utm_campaign=Badge_Grade">
+        <img src="https://api.codacy.com/project/badge/Grade/6a62b37d5f214f178ebef269dc4a6bf1"
+             alt="Codacy Badge"/>
+    </a>
+    <a href="https://coveralls.io/github/recp/cglm?branch=master">
+        <img src="https://coveralls.io/repos/github/recp/cglm/badge.svg?branch=master"
+             alt="Coverage Status"/>
+    </a>
+    <a href="https://codecov.io/gh/recp/cglm">
+        <img src="https://codecov.io/gh/recp/cglm/branch/master/graph/badge.svg"
+             alt="Coverage Status"/>
+    </a>
+    <br /><br />
+    <a href="#sponsors">
+        <img src="https://opencollective.com/cglm/sponsors/badge.svg"
+             alt="Sponsors on Open Collective"/>
+    </a>
+    <a href="#backers">
+        <img src="https://opencollective.com/cglm/backers/badge.svg"
+             alt="Backers on Open Collective"/>
+    </a>
+</p>
+
+<br>
+
+<p align="center">
+Highly optimized 2D|3D math library, also known as <b>OpenGL Mathematics (glm) for `C`</b>. <b>cglm</b> provides lot of utils to help math operations to be fast and quick to write. It is community friendly, feel free to bring any issues, bugs you faced. 
+</p>
+
+---
+
+#### 📚 Documentation

 Almost all functions (inline versions) and parameters are documented inside the corresponding headers. <br />
 Complete documentation: http://cglm.readthedocs.io

-#### Note for previous versions:
+#### 📌 Note for previous versions:

 - _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
@@ -26,31 +66,29 @@ you have the latest version
 - **[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
 - **[major change]** by starting v0.7.3, inline print functions are disabled in release/production mode to eliminate print costs (see options in documentation). Print output also improved. You can disable colors if you need  (see documentation)
+- **[major change]** by starting v0.8.3, **cglm** supports alternative clipspace configuations e.g. Left Handed, Zero-to-One (_zo)... `CGLM_FORCE_DEPTH_ZERO_TO_ONE` and `CGLM_FORCE_LEFT_HANDED` is provided to control clipspace. You should be able to use **cglm** with Vulkan, DirectX and Metal now... see https://cglm.readthedocs.io/en/latest/opt.html#clipspace-option-s

-#### Note for C++ developers:
+#### 📌 Note for C++ developers:
 If you are not aware of the original GLM library yet, you may also want to look at:
 https://github.com/g-truc/glm

-#### Note for new comers (Important):
+#### 📌 Note for new comers (Important):
 - `vec4` and `mat4` variables must be aligned. (There will be unaligned versions later)
 - **in** and **[in, out]** parameters must be initialized (please). But **[out]** parameters not, initializing out param is  also redundant
 - All functions are inline if you don't want to use pre-compiled versions with glmc_ prefix, you can ignore build process. Just include headers.
 - if your debugger takes you to cglm headers then make sure you are not trying to copy vec4 to vec3 or alig issues...
 - Welcome!

-#### Note for experienced developers:
+#### 📌 Note for experienced developers:
 - Since I'm testing this library in my projects, sometimes bugs occurs; finding that bug[s] and making improvements would be more easy with multiple developer/contributor and their projects or knowledge. Consider to make some tests if you suspect something is wrong and any feedbacks, contributions and bug reports are always welcome.

-#### Allocations?
+#### 📌 Allocations?
 `cglm` doesn't alloc any memory on heap. So it doesn't provide any allocator. You should alloc memory for **out** parameters too if you pass pointer of memory location. Don't forget that **vec4** (also quat/**versor**) and **mat4** must be aligned (16-bytes), because *cglm* uses SIMD instructions to optimize most operations if available.

-#### Returning vector or matrix... ?
+#### 📌 Returning vector or matrix... ?

 **cglm** supports both *ARRAY API* and *STRUCT API*, so you can return structs if you utilize struct api (`glms_`).

-#### Other APIs like Vulkan, Metal, Dx?
-Currently *cglm* uses default clip space configuration (-1, 1) for camera functions (perspective, extract corners...), in the future other clip space configurations will be supported
-
 <hr/>

 <table>
@@ -68,7 +106,9 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi
  </tbody>
 </table>

-## Features
+## 🚀 Features
+- **scalar** and **simd** (sse, avx, neon...) optimizations
+- option to use different clipspaces e.g. Left Handed, Zero-to-One... (currrently right handed negative-one is default)
 - array api and struct api, you can use arrays or structs.
 - general purpose matrix operations (mat4, mat3)
 - chain matrix multiplication (square only)
@@ -83,7 +123,7 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi
 - extract euler angles
 - inline or pre-compiled function call
 - frustum (extract view frustum planes, corners...)
- bounding box  (AABB in Frustum (culling), crop, merge...)
+- bounding box (AABB in Frustum (culling), crop, merge...)
 - bounding sphere
 - project, unproject
 - easing functions
@@ -95,9 +135,9 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi

 <hr />

-You have two option to call a function/operation: inline or library call (link)
+You have two options to call a function/operation: inline or library call (link)
 Almost all functions are marked inline (always_inline) so compiler will probably inline.
-To call pre-compiled version, just use `glmc_` (c stands for 'call') instead of `glm_`.
+To call pre-compiled versions, just use `glmc_` (c stands for 'call') instead of `glm_`.

 ```C
  #include <cglm/cglm.h>   /* for inline */
@@ -148,7 +188,7 @@ Struct functions generally take their parameters as *values* and *return* their

 The types used are actually unions that allow access to the same data multiple ways. One of those ways involves anonymous structures, available since C11. MSVC also supports it for earlier C versions out of the box and GCC/Clang do if you enable `-fms-extensions`. To explicitly enable these anonymous structures, `#define CGLM_USE_ANONYMOUS_STRUCT` to `1`, to disable them, to `0`. For backward compatibility, you can also `#define CGLM_NO_ANONYMOUS_STRUCT` (value is irrelevant) to disable them. If you don't specify explicitly, cglm will do a best guess based on your compiler and the C version you're using.

-## Build
+## 🔨 Build

 ### CMake (All platforms)
 ```bash
@@ -168,6 +208,24 @@ option(CGLM_USE_C99 "" OFF) # C11
 option(CGLM_USE_TEST "Enable Tests" OFF) # for make check - make test
 ```

+#### Use as header-only library with your CMake project
+
+This requires no building or installation of cglm.
+
+* Example:
+
+``` cmake
+cmake_minimum_required(VERSION 3.8.2)
+
+project(<Your Project Name>)
+
+add_executable(${PROJECT_NAME} src/main.c)
+target_link_libraries(${LIBRARY_NAME} PRIVATE
+  cglm_headers)
+
+add_subdirectory(external/cglm/ EXCLUDE_FROM_ALL)
+```
+
 #### Use with your CMake project
 * Example:
 ```cmake
@@ -373,7 +431,7 @@ You can pass matrices the same way to other APIs e.g. Vulkan, DX...

 ## Notes

- This library uses float types only, does not support Integers, Double... yet
+- This library does not support double type... yet
 - If headers are not working properly with your compiler, IDE please open an issue, because I'm using GCC and clang to test it maybe sometimes MSVC

 **TODO:**
@@ -382,7 +440,7 @@ You can pass matrices the same way to other APIs e.g. Vulkan, DX...
 - [x] Add version info
 - [ ] Unaligned operations (e.g. `glm_umat4_mul`)
 - [x] Extra documentation
- [ ] ARM Neon Arch (In Progress)
+- [x] ARM Neon Arch


 ## Contributors
--- a/cglm.pc.in
+++ b/cglm.pc.in
@@ -1,11 +1,11 @@
-prefix=@prefix@
-exec_prefix=@exec_prefix@
-libdir=@libdir@
-includedir=@includedir@
+prefix=@CMAKE_INSTALL_PREFIX@
+exec_prefix="${prefix}"
+libdir="${exec_prefix}/lib"
+includedir="${prefix}/include"

-Name: @PACKAGE_NAME@
-Description: OpenGL Mathematics (glm) for C
-URL: https://github.com/recp/cglm
-Version: @PACKAGE_VERSION@
+Name: @PROJECT_NAME@
+Description: @CMAKE_PROJECT_DESCRIPTION@
+URL: @CMAKE_PROJECT_HOMEPAGE_URL@
+Version: @PROJECT_VERSION@
 Cflags: -I${includedir}
 Libs: -L${libdir} -lcglm @LIBS@
--- a/cglm.png
+++ b/cglm.png
--- a/cglm.podspec
+++ b/cglm.podspec
@@ -2,10 +2,10 @@ Pod::Spec.new do |s|

  # Description
  s.name         = "cglm"
-  s.version      = "0.7.2"
-  s.summary      = "📽 Optimized OpenGL/Graphics Math (glm) for C"
+  s.version      = "0.8.4"
+  s.summary      = "📽 Highly Optimized 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.
+cglm is math library for graphics programming for C. See the documentation or README for all features.
                   DESC

  s.documentation_url = "http://cglm.readthedocs.io"
@@ -25,4 +25,13 @@ cglm is math library for graphics programming for C. It is similar to original g

  # Linking
  s.library = "m"
+
+  # Configuration
+  s.pod_target_xcconfig = {
+    'CLANG_ENABLE_MODULES' => 'NO',
+    'CLANG_ALLOW_NON_MODULAR_INCLUDES_IN_FRAMEWORK_MODULES' => 'YES',
+    'CLANG_WARN_DOCUMENTATION_COMMENTS' => 'NO',
+    'GCC_C_LANGUAGE_STANDARD' => 'gnu11',
+    'GCC_PREPROCESSOR_DEFINITIONS' => '$(inherited) GLM_TESTS_NO_COLORFUL_OUTPUT'
+  }
 end
--- a/configure.ac
+++ b/configure.ac
@@ -7,7 +7,7 @@
 #*****************************************************************************

 AC_PREREQ([2.69])
-AC_INIT([cglm], [0.7.9], [info@recp.me])
+AC_INIT([cglm], [0.8.6], [info@recp.me])
 AM_INIT_AUTOMAKE([-Wall -Werror foreign subdir-objects serial-tests])

 # Don't use the default cflags (-O2 -g), we set ours manually in Makefile.am.
--- a/docs/source/affine-common.rst
+++ b/docs/source/affine-common.rst
@@ -0,0 +1,129 @@
+.. default-domain:: C
+
+3D Affine Transforms (common)
+================================================================================
+
+Common transfrom functions.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translate_make`
+#. :c:func:`glm_scale_to`
+#. :c:func:`glm_scale_make`
+#. :c:func:`glm_scale`
+#. :c:func:`glm_scale_uni`
+#. :c:func:`glm_rotate_make`
+#. :c:func:`glm_rotate_atm`
+#. :c:func:`glm_decompose_scalev`
+#. :c:func:`glm_uniscaled`
+#. :c:func:`glm_decompose_rs`
+#. :c:func:`glm_decompose`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void  glm_translate_make(mat4 m, vec3 v)
+
+    creates NEW translate transform matrix by *v* vector.
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_scale_to(mat4 m, vec3 v, mat4 dest)
+
+    scale existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    scale vector [x, y, z]
+      | *[out]* **dest** scaled matrix
+
+.. c:function:: void  glm_scale_make(mat4 m, vec3 v)
+
+    creates NEW scale matrix by v vector
+
+    Parameters:
+      | *[out]* **m** affine transfrom
+      | *[in]*  **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale(mat4 m, vec3 v)
+
+    scales existing transform matrix by v vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale_uni(mat4 m, float s)
+
+    applies uniform scale to existing transform matrix v = [s, s, s]
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale factor
+
+.. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
+
+    creates NEW rotation matrix by angle and axis,
+    axis will be normalized so you don't need to normalize it
+
+    Parameters:
+      | *[out]* **m**    affine transfrom
+      | *[in]*  **axis** 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
+
+    Parameters:
+      | *[in]*  **m**  affine transform
+      | *[out]* **s**  scale vector (Sx, Sy, Sz)
+
+.. c:function:: bool  glm_uniscaled(mat4 m)
+
+    returns true if matrix is uniform scaled.
+    This is helpful for creating normal matrix.
+
+    Parameters:
+      | *[in]*  **m**   matrix
+
+.. c:function:: void  glm_decompose_rs(mat4 m, mat4 r, vec3 s)
+
+    decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transform
+      | *[out]* **r** rotation matrix
+      | *[out]* **s** scale matrix
+
+.. c:function:: void  glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s)
+
+    decompose affine transform, TODO: extract shear factors.
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transfrom
+      | *[out]* **t** translation vector
+      | *[out]* **r** rotation matrix (mat4)
+      | *[out]* **s** scaling vector [X, Y, Z]
--- a/docs/source/affine-post.rst
+++ b/docs/source/affine-post.rst
@@ -0,0 +1,129 @@
+.. default-domain:: C
+
+3D Affine Transforms (post)
+================================================================================
+
+Post transfrom functions are similar to pre transform functions except order of application is reversed.  
+Post transform functions are applied after the object is transformed with given (model matrix) transfrom. 
+
+Ther are named af
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translated_to`
+#. :c:func:`glm_translated`
+#. :c:func:`glm_translated_x`
+#. :c:func:`glm_translated_y`
+#. :c:func:`glm_translated_z`
+#. :c:func:`glm_rotated_x`
+#. :c:func:`glm_rotated_y`
+#. :c:func:`glm_rotated_z`
+#. :c:func:`glm_rotated`
+#. :c:func:`glm_rotated_at`
+#. :c:func:`glm_spinned`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void  glm_translated_to(mat4 m, vec3 v, mat4 dest)
+
+    translate existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    translate vector [x, y, z]
+      | *[out]* **dest** translated matrix
+
+.. c:function:: void  glm_translated(mat4 m, vec3 v)
+
+    translate existing transform matrix by *v* vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_translated_x(mat4 m, float x)
+
+    translate existing transform matrix by x factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  x factor
+
+.. c:function:: void  glm_translated_y(mat4 m, float y)
+
+    translate existing transform matrix by *y* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  y factor
+
+.. c:function:: void  glm_translated_z(mat4 m, float z)
+
+    translate existing transform matrix by *z* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  z factor
+
+.. c:function:: void  glm_rotated_x(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around X axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotated_y(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Y axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotated_z(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Z axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotated(mat4 m, float angle, vec3 axis)
+
+    rotate existing transform matrix around Z axis by angle and axis
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_rotated_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_spinned(mat4 m, float angle, vec3 axis)
+
+    | rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
--- a/docs/source/affine-pre.rst
+++ b/docs/source/affine-pre.rst
@@ -0,0 +1,240 @@
+.. default-domain:: C
+
+3D Affine Transforms (pre)
+================================================================================
+
+Pre transfrom functions which are regular transfrom functions.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translate_to`
+#. :c:func:`glm_translate`
+#. :c:func:`glm_translate_x`
+#. :c:func:`glm_translate_y`
+#. :c:func:`glm_translate_z`
+#. :c:func:`glm_translate_make`
+#. :c:func:`glm_scale_to`
+#. :c:func:`glm_scale_make`
+#. :c:func:`glm_scale`
+#. :c:func:`glm_scale_uni`
+#. :c:func:`glm_rotate_x`
+#. :c:func:`glm_rotate_y`
+#. :c:func:`glm_rotate_z`
+#. :c:func:`glm_rotate_make`
+#. :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`
+#. :c:func:`glm_decompose`
+#. :c:func:`glm_spin`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void  glm_translate_to(mat4 m, vec3 v, mat4 dest)
+
+    translate existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    translate vector [x, y, z]
+      | *[out]* **dest** translated matrix
+
+.. c:function:: void  glm_translate(mat4 m, vec3 v)
+
+    translate existing transform matrix by *v* vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_translate_x(mat4 m, float x)
+
+    translate existing transform matrix by x factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  x factor
+
+.. c:function:: void  glm_translate_y(mat4 m, float y)
+
+    translate existing transform matrix by *y* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  y factor
+
+.. c:function:: void  glm_translate_z(mat4 m, float z)
+
+    translate existing transform matrix by *z* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  z factor
+
+.. c:function:: void  glm_translate_make(mat4 m, vec3 v)
+
+    creates NEW translate transform matrix by *v* vector.
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_scale_to(mat4 m, vec3 v, mat4 dest)
+
+    scale existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    scale vector [x, y, z]
+      | *[out]* **dest** scaled matrix
+
+.. c:function:: void  glm_scale_make(mat4 m, vec3 v)
+
+    creates NEW scale matrix by v vector
+
+    Parameters:
+      | *[out]* **m** affine transfrom
+      | *[in]*  **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale(mat4 m, vec3 v)
+
+    scales existing transform matrix by v vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale_uni(mat4 m, float s)
+
+    applies uniform scale to existing transform matrix v = [s, s, s]
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale factor
+
+.. c:function:: void  glm_rotate_x(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around X axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotate_y(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Y axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotate_z(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Z axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
+
+    creates NEW rotation matrix by angle and axis,
+    axis will be normalized so you don't need to normalize it
+
+    Parameters:
+      | *[out]* **m**    affine transfrom
+      | *[in]*  **axis** angle (radians)
+      | *[in]*  **axis** axis
+
+.. c:function:: void  glm_rotate(mat4 m, float angle, vec3 axis)
+
+    rotate existing transform matrix around Z axis by angle and axis
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[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
+
+    Parameters:
+      | *[in]*  **m**  affine transform
+      | *[out]* **s**  scale vector (Sx, Sy, Sz)
+
+.. c:function:: bool  glm_uniscaled(mat4 m)
+
+    returns true if matrix is uniform scaled.
+    This is helpful for creating normal matrix.
+
+    Parameters:
+      | *[in]*  **m**   matrix
+
+.. c:function:: void  glm_decompose_rs(mat4 m, mat4 r, vec3 s)
+
+    decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transform
+      | *[out]* **r** rotation matrix
+      | *[out]* **s** scale matrix
+
+.. c:function:: void  glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s)
+
+    decompose affine transform, TODO: extract shear factors.
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transfrom
+      | *[out]* **t** translation vector
+      | *[out]* **r** rotation matrix (mat4)
+      | *[out]* **s** scaling vector [X, Y, Z]
+
+.. c:function:: void  glm_spin(mat4 m, float angle, vec3 axis)
+
+    | rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
--- a/docs/source/affine.rst
+++ b/docs/source/affine.rst
@@ -5,6 +5,18 @@

 Header: cglm/affine.h

+Before starting, **cglm** provides two kind of transform functions; pre and post. 
+
+Pre functions (`T' = Tnew * T`) are like `glm_translate`, `glm_rotate` which means it will translate the vector first and then apply the model transformation.
+Post functions (`T' = T * Tnew`) are like `glm_translated`, `glm_rotated` which means it will apply the model transformation first and then translate the vector.
+
+`glm_translate`, `glm_rotate` are pre functions and are similar to C++ **glm** which you are familiar with. 
+
+In new versions of **cglm** we added `glm_translated`, `glm_rotated`... which are post functions, 
+they are useful in some cases, e.g. append transform to existing transform (apply/append transform as last transfrom T' = T * Tnew).
+
+Post functions are named after pre functions with `ed` suffix, e.g. `glm_translate` -> `glm_translated`. So don't mix them up.
+
 Initialize Transform Matrices
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Functions with **_make** prefix expect you don't have a matrix and they create
@@ -25,6 +37,9 @@ since scale factors are stored in rotation matrix, same may also true for scalli
 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)").

+Also **cglm** provides :c:func:`glm_spin` and :c:func:`glm_spinned` functions to rotate around itself. No need to give pivot.
+These functions are useful for rotating around center of object. 
+
 Rotate or Scale around specific Point (Anchor Point)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

@@ -35,6 +50,7 @@ If you want to rotate model around arbibtrary point follow these steps:
 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. 
+So if you use them you don't need to do these steps manually which are done by **cglm**.

 The implementation would be:

@@ -45,6 +61,13 @@ The implementation would be:
  glm_rotate(m, angle, axis);
  glm_translate(m, pivotInv); /* pivotInv = -pivot */

+or just:
+
+.. code-block:: c
+  :linenos:
+
+  glm_rotate_at(m, pivot, angle, axis);
+
 .. _TransformsOrder:

 Transforms Order
@@ -54,7 +77,7 @@ 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):
+helpers functions works like this (cglm provides reverse order as `ed` suffix e.g `glm_translated`, `glm_rotated` see post transforms):

 .. code-block:: c
  :linenos:
@@ -147,199 +170,27 @@ Functions:
 #. :c:func:`glm_decompose_rs`
 #. :c:func:`glm_decompose`

+Post functions (**NEW**):
+
+1. :c:func:`glm_translated_to`
+#. :c:func:`glm_translated`
+#. :c:func:`glm_translated_x`
+#. :c:func:`glm_translated_y`
+#. :c:func:`glm_translated_z`
+#. :c:func:`glm_rotated_x`
+#. :c:func:`glm_rotated_y`
+#. :c:func:`glm_rotated_z`
+#. :c:func:`glm_rotated`
+#. :c:func:`glm_rotated_at`
+#. :c:func:`glm_spinned`
+
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~

-.. c:function:: void  glm_translate_to(mat4 m, vec3 v, mat4 dest)
+.. toctree::
+   :maxdepth: 1
+   :caption: Affine categories:

-    translate existing transform matrix by *v* vector and store result in dest
-
-    Parameters:
-      | *[in]*  **m**    affine transfrom
-      | *[in]*  **v**    translate vector [x, y, z]
-      | *[out]* **dest** translated matrix
-
-.. c:function:: void  glm_translate(mat4 m, vec3 v)
-
-    translate existing transform matrix by *v* vector
-    and stores result in same matrix
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  translate vector [x, y, z]
-
-.. c:function:: void  glm_translate_x(mat4 m, float x)
-
-    translate existing transform matrix by x factor
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  x factor
-
-.. c:function:: void  glm_translate_y(mat4 m, float y)
-
-    translate existing transform matrix by *y* factor
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  y factor
-
-.. c:function:: void  glm_translate_z(mat4 m, float z)
-
-    translate existing transform matrix by *z* factor
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  z factor
-
-.. c:function:: void  glm_translate_make(mat4 m, vec3 v)
-
-    creates NEW translate transform matrix by *v* vector.
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  translate vector [x, y, z]
-
-.. c:function:: void  glm_scale_to(mat4 m, vec3 v, mat4 dest)
-
-    scale existing transform matrix by *v* vector and store result in dest
-
-    Parameters:
-      | *[in]*  **m**    affine transfrom
-      | *[in]*  **v**    scale vector [x, y, z]
-      | *[out]* **dest** scaled matrix
-
-.. c:function:: void  glm_scale_make(mat4 m, vec3 v)
-
-    creates NEW scale matrix by v vector
-
-    Parameters:
-      | *[out]* **m** affine transfrom
-      | *[in]*  **v** scale vector [x, y, z]
-
-.. c:function:: void  glm_scale(mat4 m, vec3 v)
-
-    scales existing transform matrix by v vector
-    and stores result in same matrix
-
-    Parameters:
-      | *[in, out]* **m** affine transfrom
-      | *[in]*      **v** scale vector [x, y, z]
-
-.. c:function:: void  glm_scale_uni(mat4 m, float s)
-
-    applies uniform scale to existing transform matrix v = [s, s, s]
-    and stores result in same matrix
-
-    Parameters:
-      | *[in, out]* **m** affine transfrom
-      | *[in]*      **v** scale factor
-
-.. c:function:: void  glm_rotate_x(mat4 m, float angle, mat4 dest)
-
-    rotate existing transform matrix around X axis by angle
-    and store result in dest
-
-    Parameters:
-      | *[in]*  **m**     affine transfrom
-      | *[in]*  **angle** angle (radians)
-      | *[out]* **dest**  rotated matrix
-
-.. c:function:: void  glm_rotate_y(mat4 m, float angle, mat4 dest)
-
-    rotate existing transform matrix around Y axis by angle
-    and store result in dest
-
-    Parameters:
-      | *[in]*  **m**     affine transfrom
-      | *[in]*  **angle** angle (radians)
-      | *[out]* **dest**  rotated matrix
-
-.. c:function:: void  glm_rotate_z(mat4 m, float angle, mat4 dest)
-
-    rotate existing transform matrix around Z axis by angle
-    and store result in dest
-
-    Parameters:
-      | *[in]*  **m**     affine transfrom
-      | *[in]*  **angle** angle (radians)
-      | *[out]* **dest**  rotated matrix
-
-.. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
-
-    creates NEW rotation matrix by angle and axis,
-    axis will be normalized so you don't need to normalize it
-
-    Parameters:
-      | *[out]* **m**    affine transfrom
-      | *[in]*  **axis** angle (radians)
-      | *[in]*  **axis** axis
-
-.. c:function:: void  glm_rotate(mat4 m, float angle, vec3 axis)
-
-    rotate existing transform matrix around Z axis by angle and axis
-
-    Parameters:
-      | *[in, out]* **m**     affine transfrom
-      | *[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
-
-    Parameters:
-      | *[in]*  **m**  affine transform
-      | *[out]* **s**  scale vector (Sx, Sy, Sz)
-
-.. c:function:: bool  glm_uniscaled(mat4 m)
-
-    returns true if matrix is uniform scaled.
-    This is helpful for creating normal matrix.
-
-    Parameters:
-      | *[in]*  **m**   matrix
-
-.. c:function:: void  glm_decompose_rs(mat4 m, mat4 r, vec3 s)
-
-    decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
-    DON'T pass projected matrix here
-
-    Parameters:
-      | *[in]*  **m** affine transform
-      | *[out]* **r** rotation matrix
-      | *[out]* **s** scale matrix
-
-.. c:function:: void  glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s)
-
-    decompose affine transform, TODO: extract shear factors.
-    DON'T pass projected matrix here
-
-    Parameters:
-      | *[in]*  **m** affine transfrom
-      | *[out]* **t** translation vector
-      | *[out]* **r** rotation matrix (mat4)
-      | *[out]* **s** scaling vector [X, Y, Z]
+   affine-common
+   affine-pre
+   affine-post
--- a/docs/source/api.rst
+++ b/docs/source/api.rst
@@ -34,15 +34,18 @@ Follow the :doc:`build` documentation for this
   box
   quat
   euler
-   mat4
-   mat3
   mat2
+   mat3
+   mat4
+   vec2
+   vec2-ext
   vec3
   vec3-ext
   vec4
   vec4-ext
-   vec2
-   vec2-ext
+   ivec2
+   ivec3
+   ivec4
   color
   plane
   project
--- a/docs/source/build.rst
+++ b/docs/source/build.rst
@@ -32,6 +32,22 @@ If you don't want to install **cglm** to your system's folder you can get static
  option(CGLM_USE_C99 "" OFF) # C11 
  option(CGLM_USE_TEST "Enable Tests" OFF) # for make check - make test

+**Use as header-only library with your CMake project example**
+This requires no building or installation of cglm.
+
+.. code-block:: CMake
+  :linenos:
+
+  cmake_minimum_required(VERSION 3.8.2)
+  
+  project(<Your Project Name>)
+  
+  add_executable(${PROJECT_NAME} src/main.c)
+  target_link_libraries(${LIBRARY_NAME} PRIVATE
+    cglm_headers)
+  
+  add_subdirectory(external/cglm/ EXCLUDE_FROM_ALL)
+
 **Use with your CMake project example**

 .. code-block:: CMake
@@ -50,7 +66,7 @@ If you don't want to install **cglm** to your system's folder you can get static
 Meson (All platforms):
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

-.. code-block:: bash
+.. code-block::
  :linenos:

  $ meson build # [Optional] --default-library=static
@@ -60,7 +76,7 @@ Meson (All platforms):

 **Meson Options:**

-.. code-block:: CMake
+.. code-block:: 
  :linenos:

  c_std=c11
@@ -69,9 +85,9 @@ Meson (All platforms):
  enable_tests=false # to run tests: ninja test


-**Use with your CMake project example**
+**Use with your Meson project**

-.. code-block:: CMake
+.. code-block::
  :linenos:

  # Clone cglm or create a cglm.wrap under <source_root>/subprojects
--- a/docs/source/cam.rst
+++ b/docs/source/cam.rst
@@ -140,7 +140,7 @@ Functions documentation
    | set up perspective projection matrix

    Parameters:
-      | *[in]*  **fovy**    field of view angle
+      | *[in]*  **fovy**    field of view angle (in radians)
      | *[in]*  **aspect**  aspect ratio ( width / height )
      | *[in]*  **nearVal** near clipping plane
      | *[in]*  **farVal**  far clipping planes
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -25,7 +25,7 @@

 # If your documentation needs a minimal Sphinx version, state it here.
 #
-# needs_sphinx = '1.0'
+# needs_sphinx = '3.0'

 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
@@ -62,9 +62,9 @@ author = u'Recep Aslantas'
 # built documents.
 #
 # The short X.Y version.
-version = u'0.7.9'
+version = u'0.8.6'
 # The full version, including alpha/beta/rc tags.
-release = u'0.7.9'
+release = u'0.8.6'

 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -197,3 +197,7 @@ epub_exclude_files = ['search.html']

 # If true, `todo` and `todoList` produce output, else they produce nothing.
 todo_include_todos = True
+
+# -- Options for the C domain ------------------------------------------------
+
+c_id_attributes = ['__restrict']
--- a/docs/source/features.rst
+++ b/docs/source/features.rst
@@ -1,6 +1,8 @@
 Features
 ================================================================================

+* **scalar** and **simd** (sse, avx, neon...) optimizations
+* option to use different clipspaces e.g. Left Handed, Zero-to-One... (currrently right handed negative-one is default)
 * array api and struct api, you can use arrays or structs.
 * general purpose matrix operations (mat4, mat3)
 * chain matrix multiplication (square only)
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -6,13 +6,12 @@
 cglm Documentation
 ================================

-**cglm** is optimized 3D math library written in C99 (compatible with C89).
-It is similar to original **glm** library except this is mainly for **C**
+**cglm** is an optimized 3D math library written in C99 (compatible with C89).
+It is similar to the original **glm** library, except **cglm** is mainly for
+**C**.

-This library stores matrices as column-major order but in the future row-major
-is considered to be supported as optional.
-
-Also currently only **float** type is supported for most operations.
+**cglm** stores matrices as column-major order but in the future row-major is
+considered to be supported as optional.

 .. toctree::
   :maxdepth: 2
@@ -46,8 +45,8 @@ Also currently only **float** type is supported for most operations.

   troubleshooting

-Indices and tables
-==================
+Indices and Tables:
+===================

 * :ref:`genindex`
 * :ref:`modindex`
--- a/docs/source/ivec2.rst
+++ b/docs/source/ivec2.rst
@@ -0,0 +1,163 @@
+.. default-domain:: C
+
+ivec2
+=====
+
+Header: cglm/ivec2.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_ivec2`
+#. :c:func:`glm_ivec2_copy`
+#. :c:func:`glm_ivec2_zero`
+#. :c:func:`glm_ivec2_one`
+#. :c:func:`glm_ivec2_add`
+#. :c:func:`glm_ivec2_adds`
+#. :c:func:`glm_ivec2_sub`
+#. :c:func:`glm_ivec2_subs`
+#. :c:func:`glm_ivec2_mul`
+#. :c:func:`glm_ivec2_scale`
+#. :c:func:`glm_ivec2_distance2`
+#. :c:func:`glm_ivec2_distance`
+#. :c:func:`glm_ivec2_maxv`
+#. :c:func:`glm_ivec2_minv`
+#. :c:func:`glm_ivec2_clamp`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_ivec2(int * v, ivec2 dest)
+    
+    init ivec2 using vec3 or vec4
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_copy(ivec2 a, ivec2 dest)
+    
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**    source vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_zero(ivec2 v)
+
+    set all members of [v] to zero
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec2_one(ivec2 v)
+
+    set all members of [v] to one
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec2_add(ivec2 a, ivec2 b, ivec2 dest)
+
+    add vector [a] to vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_adds(ivec2 v, int s, ivec2 dest)
+
+    add scalar s to vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest)
+
+    subtract vector [b] from vector [a] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_subs(ivec2 v, int s, ivec2 dest)
+
+    subtract scalar s from vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest)
+
+    multiply vector [a] with vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_scale(ivec2 v, int s, ivec2 dest)
+
+    multiply vector [a] with scalar s and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: int glm_ivec2_distance2(ivec2 a, ivec2 b)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        squared distance (distance * distance)
+
+.. c:function:: float glm_ivec2_distance(ivec2 a, ivec2 b)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        distance
+
+.. c:function:: void glm_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest)
+
+    set each member of dest to greater of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest)
+
+    set each member of dest to lesser of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_clamp(ivec2 v, int minVal, int maxVal)
+
+    clamp each member of [v] between minVal and maxVal (inclusive)
+
+    Parameters:
+      | *[in, out]* **v**      vector
+      | *[in]*      **minVal** minimum value
+      | *[in]*      **maxVal** maximum value
--- a/docs/source/ivec3.rst
+++ b/docs/source/ivec3.rst
@@ -0,0 +1,163 @@
+.. default-domain:: C
+
+ivec3
+=====
+
+Header: cglm/ivec3.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_ivec3`
+#. :c:func:`glm_ivec3_copy`
+#. :c:func:`glm_ivec3_zero`
+#. :c:func:`glm_ivec3_one`
+#. :c:func:`glm_ivec3_add`
+#. :c:func:`glm_ivec3_adds`
+#. :c:func:`glm_ivec3_sub`
+#. :c:func:`glm_ivec3_subs`
+#. :c:func:`glm_ivec3_mul`
+#. :c:func:`glm_ivec3_scale`
+#. :c:func:`glm_ivec3_distance2`
+#. :c:func:`glm_ivec3_distance`
+#. :c:func:`glm_ivec3_maxv`
+#. :c:func:`glm_ivec3_minv`
+#. :c:func:`glm_ivec3_clamp`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_ivec3(ivec4 v4, ivec3 dest)
+    
+    init ivec3 using ivec4
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_copy(ivec3 a, ivec3 dest)
+    
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**    source vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_zero(ivec3 v)
+
+    set all members of [v] to zero
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec3_one(ivec3 v)
+
+    set all members of [v] to one
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec3_add(ivec3 a, ivec3 b, ivec3 dest)
+
+    add vector [a] to vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_adds(ivec3 v, int s, ivec3 dest)
+
+    add scalar s to vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest)
+
+    subtract vector [b] from vector [a] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_subs(ivec3 v, int s, ivec3 dest)
+
+    subtract scalar s from vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest)
+
+    multiply vector [a] with vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_scale(ivec3 v, int s, ivec3 dest)
+
+    multiply vector [a] with scalar s and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: int glm_ivec3_distance2(ivec3 a, ivec3 b)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        squared distance (distance * distance)
+
+.. c:function:: float glm_ivec3_distance(ivec3 a, ivec3 b)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        distance
+
+.. c:function:: void glm_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest)
+
+    set each member of dest to greater of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest)
+
+    set each member of dest to lesser of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_clamp(ivec3 v, int minVal, int maxVal)
+
+    clamp each member of [v] between minVal and maxVal (inclusive)
+
+    Parameters:
+      | *[in, out]* **v**      vector
+      | *[in]*      **minVal** minimum value
+      | *[in]*      **maxVal** maximum value
--- a/docs/source/ivec4.rst
+++ b/docs/source/ivec4.rst
@@ -0,0 +1,163 @@
+.. default-domain:: C
+
+ivec4
+=====
+
+Header: cglm/ivec4.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_ivec4`
+#. :c:func:`glm_ivec4_copy`
+#. :c:func:`glm_ivec4_zero`
+#. :c:func:`glm_ivec4_one`
+#. :c:func:`glm_ivec4_add`
+#. :c:func:`glm_ivec4_adds`
+#. :c:func:`glm_ivec4_sub`
+#. :c:func:`glm_ivec4_subs`
+#. :c:func:`glm_ivec4_mul`
+#. :c:func:`glm_ivec4_scale`
+#. :c:func:`glm_ivec4_distance2`
+#. :c:func:`glm_ivec4_distance`
+#. :c:func:`glm_ivec4_maxv`
+#. :c:func:`glm_ivec4_minv`
+#. :c:func:`glm_ivec4_clamp`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_ivec4(ivec3 v3, int last, ivec4 dest)
+    
+    init ivec4 using ivec3
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_copy(ivec4 a, ivec4 dest)
+    
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**    source vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_zero(ivec4 v)
+
+    set all members of [v] to zero
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec4_one(ivec4 v)
+
+    set all members of [v] to one
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec4_add(ivec4 a, ivec4 b, ivec4 dest)
+
+    add vector [a] to vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_adds(ivec4 v, int s, ivec4 dest)
+
+    add scalar s to vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest)
+
+    subtract vector [b] from vector [a] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_subs(ivec4 v, int s, ivec4 dest)
+
+    subtract scalar s from vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest)
+
+    multiply vector [a] with vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_scale(ivec4 v, int s, ivec4 dest)
+
+    multiply vector [a] with scalar s and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: int glm_ivec4_distance2(ivec4 a, ivec4 b)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        squared distance (distance * distance)
+
+.. c:function:: float glm_ivec4_distance(ivec4 a, ivec4 b)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        distance
+
+.. c:function:: void glm_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest)
+
+    set each member of dest to greater of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest)
+
+    set each member of dest to lesser of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_clamp(ivec4 v, int minVal, int maxVal)
+
+    clamp each member of [v] between minVal and maxVal (inclusive)
+
+    Parameters:
+      | *[in, out]* **v**      vector
+      | *[in]*      **minVal** minimum value
+      | *[in]*      **maxVal** maximum value
--- a/docs/source/opengl.rst
+++ b/docs/source/opengl.rst
@@ -2,7 +2,7 @@ How to send vector or matrix to OpenGL like API
 ==================================================

 *cglm*'s vector and matrix types are arrays. So you can send them directly to a
-function which accecpts pointer. But you may got warnings for matrix because it is
+function which accepts pointer. But you may got warnings for matrix because it is
 two dimensional array.

 Passing / Uniforming Matrix to OpenGL:
--- a/docs/source/opt.rst
+++ b/docs/source/opt.rst
@@ -35,6 +35,45 @@ have to compile cglm with **CGLM_ALL_UNALIGNED** macro.

 For instance if you set CGLM_ALL_UNALIGNED in a project then set it in other projects too

+Clipspace Option[s]
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By starting **v0.8.3** cglm provides options to switch between clipspace configurations.
+
+Clipspace related files are located at `include/cglm/[struct]/clipspace.h` but 
+these are included in related files like `cam.h`. If you don't want to change your existing 
+clipspace configuration and want to use different clipspace function like `glm_lookat_zo` or `glm_lookat_lh_zo`...
+then you can include individual headers or just define `CGLM_CLIPSPACE_INCLUDE_ALL` which will iclude all headers for you.
+
+1. **CGLM_CLIPSPACE_INCLUDE_ALL**
+2. **CGLM_FORCE_DEPTH_ZERO_TO_ONE**
+3. **CGLM_FORCE_LEFT_HANDED**
+
+
+1. **CGLM_CLIPSPACE_INCLUDE_ALL**:
+
+By defining this macro, **cglm** will include all clipspace functions for you by just using
+`#include cglm/cglm.h` or `#include cglm/struct.h` or `#include cglm/call.h`
+
+Otherwise you need to include header you want manually e.g. `#include cglm/clipspace/view_rh_zo.h`
+
+2. **CGLM_FORCE_DEPTH_ZERO_TO_ONE**
+
+This is similar to **GLM**'s **GLM_FORCE_DEPTH_ZERO_TO_ONE** option. 
+This will set clip space between 0 to 1 which makes **cglm** Vulkan, Metal friendly. 
+
+You can use functions like `glm_lookat_lh_zo()` individually. By setting **CGLM_FORCE_DEPTH_ZERO_TO_ONE**
+functions in cam.h for instance will use `_zo` versions.
+
+3. **CGLM_FORCE_LEFT_HANDED**
+
+Force **cglm** to use the left handed coordinate system by default, currently **cglm** uses right handed coordinate system as default,
+you can change this behavior with this option.
+
+**VERY VERY IMPORTANT:**
+
+Be careful if you include **cglm** in multiple projects.
+
 SSE and SSE2 Shuffle Option
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 **_mm_shuffle_ps** generates **shufps** instruction even if registers are same.
--- a/docs/source/project.rst
+++ b/docs/source/project.rst
@@ -21,14 +21,14 @@ Functions:
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~

-.. c:function:: void  glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest)
+.. c:function:: void glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest)

    | maps the specified viewport coordinates into specified space [1]
      the matrix should contain projection matrix.

    if you don't have ( and don't want to have ) an inverse matrix then use
-    glm_unproject version. You may use existing inverse of matrix in somewhere
-    else, this is why glm_unprojecti exists to save save inversion cost
+    :c:func:`glm_unproject` version. You may use existing inverse of matrix in somewhere
+    else, this is why **glm_unprojecti** exists to save inversion cost

    [1] space:
      - if m = invProj:     View Space
@@ -57,7 +57,7 @@ Functions documentation
    | maps the specified viewport coordinates into specified space [1]
      the matrix should contain projection matrix.

-    this is same as glm_unprojecti except this function get inverse matrix for
+    this is same as :c:func:`glm_unprojecti` except this function get inverse matrix for
    you.

    [1] space:
@@ -80,7 +80,7 @@ Functions documentation
      | *[in]*  **vp**   viewport as [x, y, width, height]
      | *[out]* **dest** unprojected coordinates

-.. c:function:: void  glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest)
+.. c:function:: void glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest)

    | map object coordinates to window coordinates

@@ -91,12 +91,29 @@ Functions documentation
       glm_mat4_mul(proj, view, viewProj);
       glm_mat4_mul(viewProj, model, MVP);

-    this could be useful for gettng a bbox which fits with view frustum and
-    object bounding boxes. In this case you crop view frustum box with objects
-    box
-
    Parameters:
      | *[in]*  **pos**      object coordinates
      | *[in]*  **m**        MVP matrix
      | *[in]*  **vp**       viewport as [x, y, width, height]
      | *[out]* **dest**     projected coordinates
+
+.. c:function:: float glm_project_z(vec3 pos, mat4 m)
+
+    | map object's z coordinate to window coordinates
+
+    this is same as :c:func:`glm_project` except this function projects only Z coordinate
+    which reduces a few calculations and parameters.
+
+    Computing MVP:
+
+    .. code-block:: c
+
+       glm_mat4_mul(proj, view, viewProj);
+       glm_mat4_mul(viewProj, model, MVP);
+
+    Parameters:
+      | *[in]*  **pos**      object coordinates
+      | *[in]*  **m**        MVP matrix
+
+    Returns:
+        projected z coordinate
--- a/docs/source/quat.rst
+++ b/docs/source/quat.rst
@@ -32,6 +32,7 @@ Functions:
 #. :c:func:`glm_quat`
 #. :c:func:`glm_quatv`
 #. :c:func:`glm_quat_copy`
+#. :c:func:`glm_quat_from_vecs`
 #. :c:func:`glm_quat_norm`
 #. :c:func:`glm_quat_normalize`
 #. :c:func:`glm_quat_normalize_to`
@@ -52,6 +53,7 @@ Functions:
 #. :c:func:`glm_quat_mat3`
 #. :c:func:`glm_quat_mat3t`
 #. :c:func:`glm_quat_lerp`
+#. :c:func:`glm_quat_nlerp`
 #. :c:func:`glm_quat_slerp`
 #. :c:func:`glm_quat_look`
 #. :c:func:`glm_quat_for`
@@ -122,6 +124,20 @@ Functions documentation
      | *[in]*  **q**     source quaternion
      | *[out]* **dest**  destination quaternion

+.. c:function:: void  glm_quat_from_vecs(vec3 a, vec3 b, versor dest)
+
+    | compute unit quaternion needed to rotate a into b
+
+    References:
+      * `Finding quaternion representing the rotation from one vector to another <https://stackoverflow.com/a/11741520/183120>`_
+      * `Quaternion from two vectors <http://lolengine.net/blog/2014/02/24/quaternion-from-two-vectors-final>`_
+      * `Angle between vectors <http://www.euclideanspace.com/maths/algebra/vectors/angleBetween/minorlogic.htm>`_
+
+    Parameters:
+      | *[in]*  **a**     unit vector
+      | *[in]*  **b**     unit vector
+      | *[in]*  **dest**  unit quaternion
+
 .. c:function:: float  glm_quat_norm(versor q)

    | returns norm (magnitude) of quaternion
@@ -304,6 +320,25 @@ Functions documentation
      | *[in]*  **t**     interpolant (amount) clamped between 0 and 1
      | *[out]* **dest**  result quaternion

+.. c:function:: void glm_quat_nlerp(versor q, versor r, float  t, versor dest)
+
+    | interpolates between two quaternions
+    | taking the shortest rotation path using
+    | normalized linear interpolation (NLERP)
+
+    | This is a cheaper alternative to slerp; most games use nlerp
+    | for animations as it visually makes little difference.
+
+    References:
+      * `Understanding Slerp, Then Not Using it <http://number-none.com/product/Understanding%20Slerp,%20Then%20Not%20Using%20It>`_
+      * `Lerp, Slerp and Nlerp <https://keithmaggio.wordpress.com/2011/02/15/math-magician-lerp-slerp-and-nlerp/>`_
+
+    Parameters:
+      | *[in]*  **from**  from
+      | *[in]*  **to**    to
+      | *[in]*  **t**     interpolant (amount) clamped between 0 and 1
+      | *[out]* **dest**  result quaternion
+
 .. c:function:: void glm_quat_slerp(versor q, versor r, float  t, versor dest)

    | interpolates between two quaternions
@@ -374,7 +409,7 @@ Functions documentation
      | *[in]*       **q**      quaternion
      | *[in]*       **pivot**  pivot

-.. c:function:: void glm_quat_rotate(mat4 m, versor q, mat4 dest)
+.. c:function:: void glm_quat_rotate_atm(mat4 m, versor q, vec3 pivot)

    | rotate NEW transform matrix using quaternion at pivot point
    | this creates rotation matrix, it assumes you don't have a matrix
--- a/docs/source/vec2.rst
+++ b/docs/source/vec2.rst
@@ -55,7 +55,7 @@ Functions:
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~

-.. c:function:: void glm_vec2(float \*v, vec2 dest)
+.. c:function:: void glm_vec2(float * v, vec2 dest)

    init vec2 using vec3 or vec4

--- a/docs/source/vec3.rst
+++ b/docs/source/vec3.rst
@@ -474,6 +474,9 @@ Functions documentation

    possible orthogonal/perpendicular vector

+    References:
+      * `On picking an orthogonal vector (and combing coconuts) <http://lolengine.net/blog/2013/09/21/picking-orthogonal-vector-combing-coconuts>`_
+
    Parameters:
      | *[in]*  **v**     vector
      | *[out]* **dest**  orthogonal/perpendicular vector
--- a/include/cglm/affine-mat.h
+++ b/include/cglm/affine-mat.h
@@ -26,6 +26,10 @@
 #  include "simd/avx/affine.h"
 #endif

+#ifdef CGLM_NEON_FP
+#  include "simd/neon/affine.h"
+#endif
+
 /*!
 * @brief this is similar to glm_mat4_mul but specialized to affine transform
 *
@@ -49,6 +53,8 @@ glm_mul(mat4 m1, mat4 m2, mat4 dest) {
  glm_mul_avx(m1, m2, dest);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
  glm_mul_sse2(m1, m2, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_mul_neon(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],
@@ -103,6 +109,8 @@ void
 glm_mul_rot(mat4 m1, mat4 m2, mat4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
  glm_mul_rot_sse2(m1, m2, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_mul_rot_neon(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],
@@ -150,6 +158,8 @@ void
 glm_inv_tr(mat4 mat) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
  glm_inv_tr_sse2(mat);
+#elif defined(CGLM_NEON_FP)
+  glm_inv_tr_neon(mat);
 #else
  CGLM_ALIGN_MAT mat3 r;
  CGLM_ALIGN(8)  vec3 t;
--- a/include/cglm/affine-post.h
+++ b/include/cglm/affine-post.h
@@ -0,0 +1,247 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_affine_post_h
+#define cglm_affine_post_h
+
+/*
+ Functions:
+   CGLM_INLINE void glm_translated_to(mat4 m, vec3 v, mat4 dest);
+   CGLM_INLINE void glm_translated(mat4 m, vec3 v);
+   CGLM_INLINE void glm_translated_x(mat4 m, float to);
+   CGLM_INLINE void glm_translated_y(mat4 m, float to);
+   CGLM_INLINE void glm_translated_z(mat4 m, float to);
+   CGLM_INLINE void glm_rotated_x(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotated_y(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotated_z(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotated(mat4 m, float angle, vec3 axis);
+   CGLM_INLINE void glm_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis);
+   CGLM_INLINE void glm_spinned(mat4 m, float angle, vec3 axis);
+ */
+
+#include "common.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 stores result in same matrix
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       v  translate vector [x, y, z]
+ */
+CGLM_INLINE
+void
+glm_translated(mat4 m, vec3 v) {
+  glm_vec3_add(m[3], v, m[3]);
+}
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and store result in dest
+ *
+ * source matrix will remain same
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]  m    affine transfrom
+ * @param[in]  v    translate vector [x, y, z]
+ * @param[out] dest translated matrix
+ */
+CGLM_INLINE
+void
+glm_translated_to(mat4 m, vec3 v, mat4 dest) {
+  glm_mat4_copy(m, dest);
+  glm_translated(dest, v);
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       x  x factor
+ */
+CGLM_INLINE
+void
+glm_translated_x(mat4 m, float x) {
+  m[3][0] += x;
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       y  y factor
+ */
+CGLM_INLINE
+void
+glm_translated_y(mat4 m, float y) {
+  m[3][1] += y;
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       z  z factor
+ */
+CGLM_INLINE
+void
+glm_translated_z(mat4 m, float z) {
+  m[3][2] += z;
+}
+
+/*!
+ * @brief rotate existing transform matrix around X axis by angle
+ *        and store result in dest
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotated_x(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[1][1] =  c;
+  t[1][2] =  s;
+  t[2][1] = -s;
+  t[2][2] =  c;
+
+  glm_mul_rot(t, m, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Y axis by angle
+ *        and store result in dest
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotated_y(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][2] = -s;
+  t[2][0] =  s;
+  t[2][2] =  c;
+
+  glm_mul_rot(t, m, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Z axis by angle
+ *        and store result in dest
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotated_z(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][1] =  s;
+  t[1][0] = -s;
+  t[1][1] =  c;
+
+  glm_mul_rot(t, m, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotated(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_make(rot, angle, axis);
+  glm_mul_rot(rot, m, m);
+}
+
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       pivot  rotation center
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translated(m, pivot);
+  glm_rotated(m, angle, axis);
+  glm_translated(m, pivotInv);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_spinned(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_atm(rot, m[3], angle, axis);
+  glm_mat4_mul(rot, m, m);
+}
+
+#endif /* cglm_affine_post_h */
--- a/include/cglm/affine-pre.h
+++ b/include/cglm/affine-pre.h
@@ -0,0 +1,285 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_affine_pre_h
+#define cglm_affine_pre_h
+
+/*
+ Functions:
+   CGLM_INLINE void glm_translate_to(mat4 m, vec3 v, mat4 dest);
+   CGLM_INLINE void glm_translate(mat4 m, vec3 v);
+   CGLM_INLINE void glm_translate_x(mat4 m, float to);
+   CGLM_INLINE void glm_translate_y(mat4 m, float to);
+   CGLM_INLINE void glm_translate_z(mat4 m, float to);
+   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(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_spin(mat4 m, float angle, vec3 axis);
+ */
+
+#include "common.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 stores result in same matrix
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       v  translate vector [x, y, z]
+ */
+CGLM_INLINE
+void
+glm_translate(mat4 m, vec3 v) {
+#if defined(CGLM_SIMD)
+  glmm_128 m0, m1, m2, m3;
+
+  m0 = glmm_load(m[0]);
+  m1 = glmm_load(m[1]);
+  m2 = glmm_load(m[2]);
+  m3 = glmm_load(m[3]);
+
+  glmm_store(m[3],
+             glmm_fmadd(m0, glmm_set1(v[0]),
+                        glmm_fmadd(m1, glmm_set1(v[1]),
+                                   glmm_fmadd(m2, glmm_set1(v[2]), m3))));
+#else
+  glm_vec4_muladds(m[0], v[0], m[3]);
+  glm_vec4_muladds(m[1], v[1], m[3]);
+  glm_vec4_muladds(m[2], v[2], m[3]);
+#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(mat4 m, vec3 v, mat4 dest) {
+  glm_mat4_copy(m, dest);
+  glm_translate(dest, v);
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       x  x factor
+ */
+CGLM_INLINE
+void
+glm_translate_x(mat4 m, float x) {
+#if defined(CGLM_SIMD)
+  glmm_store(m[3], glmm_fmadd(glmm_load(m[0]), glmm_set1(x), glmm_load(m[3])));
+#else
+  vec4 v1;
+  glm_vec4_scale(m[0], x, v1);
+  glm_vec4_add(v1, m[3], m[3]);
+#endif
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       y  y factor
+ */
+CGLM_INLINE
+void
+glm_translate_y(mat4 m, float y) {
+#if defined(CGLM_SIMD)
+  glmm_store(m[3], glmm_fmadd(glmm_load(m[1]), glmm_set1(y), glmm_load(m[3])));
+#else
+  vec4 v1;
+  glm_vec4_scale(m[1], y, v1);
+  glm_vec4_add(v1, m[3], m[3]);
+#endif
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       z  z factor
+ */
+CGLM_INLINE
+void
+glm_translate_z(mat4 m, float z) {
+#if defined(CGLM_SIMD)
+  glmm_store(m[3], glmm_fmadd(glmm_load(m[2]), glmm_set1(z), glmm_load(m[3])));
+#else
+  vec4 v1;
+  glm_vec4_scale(m[2], z, v1);
+  glm_vec4_add(v1, m[3], m[3]);
+#endif
+}
+
+/*!
+ * @brief rotate existing transform matrix around X axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotate_x(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[1][1] =  c;
+  t[1][2] =  s;
+  t[2][1] = -s;
+  t[2][2] =  c;
+
+  glm_mul_rot(m, t, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Y axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotate_y(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][2] = -s;
+  t[2][0] =  s;
+  t[2][2] =  c;
+
+  glm_mul_rot(m, t, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Z axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotate_z(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][1] =  s;
+  t[1][0] = -s;
+  t[1][1] =  c;
+
+  glm_mul_rot(m, t, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotate(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_make(rot, angle, axis);
+  glm_mul_rot(m, rot, m);
+}
+
+/*!
+ * @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, vec3 pivot, float angle, 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, vec3 pivot, float angle, 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);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_spin(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_atm(rot, m[3], angle, axis);
+  glm_mat4_mul(m, rot, m);
+}
+
+#endif /* cglm_affine_pre_h */
--- a/include/cglm/affine.h
+++ b/include/cglm/affine.h
@@ -24,6 +24,7 @@
   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_spin(mat4 m, 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);
@@ -40,122 +41,6 @@
 #include "mat4.h"
 #include "affine-mat.h"

-/*!
- * @brief translate existing transform matrix by v vector
- *        and stores result in same matrix
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       v  translate vector [x, y, z]
- */
-CGLM_INLINE
-void
-glm_translate(mat4 m, vec3 v) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  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(glmm_load(m[1]),
-                                              _mm_set1_ps(v[1]))),
-                        _mm_add_ps(_mm_mul_ps(glmm_load(m[2]),
-                                              _mm_set1_ps(v[2])),
-                                   glmm_load(m[3]))))
-  ;
-#else
-  vec4 v1, v2, v3;
-
-  glm_vec4_scale(m[0], v[0], v1);
-  glm_vec4_scale(m[1], v[1], v2);
-  glm_vec4_scale(m[2], v[2], v3);
-
-  glm_vec4_add(v1, m[3], m[3]);
-  glm_vec4_add(v2, m[3], m[3]);
-  glm_vec4_add(v3, m[3], m[3]);
-#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(mat4 m, vec3 v, mat4 dest) {
-  glm_mat4_copy(m, dest);
-  glm_translate(dest, v);
-}
-
-/*!
- * @brief translate existing transform matrix by x factor
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       x  x factor
- */
-CGLM_INLINE
-void
-glm_translate_x(mat4 m, float x) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  glmm_store(m[3],
-             _mm_add_ps(_mm_mul_ps(glmm_load(m[0]),
-                                   _mm_set1_ps(x)),
-                        glmm_load(m[3])))
-  ;
-#else
-  vec4 v1;
-  glm_vec4_scale(m[0], x, v1);
-  glm_vec4_add(v1, m[3], m[3]);
-#endif
-}
-
-/*!
- * @brief translate existing transform matrix by y factor
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       y  y factor
- */
-CGLM_INLINE
-void
-glm_translate_y(mat4 m, float y) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  glmm_store(m[3],
-             _mm_add_ps(_mm_mul_ps(glmm_load(m[1]),
-                                   _mm_set1_ps(y)),
-                        glmm_load(m[3])))
-  ;
-#else
-  vec4 v1;
-  glm_vec4_scale(m[1], y, v1);
-  glm_vec4_add(v1, m[3], m[3]);
-#endif
-}
-
-/*!
- * @brief translate existing transform matrix by z factor
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       z  z factor
- */
-CGLM_INLINE
-void
-glm_translate_z(mat4 m, float z) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  glmm_store(m[3],
-             _mm_add_ps(_mm_mul_ps(glmm_load(m[2]),
-                                   _mm_set1_ps(z)),
-                        glmm_load(m[3])))
-  ;
-#else
-  vec4 v1;
-  glm_vec4_scale(m[2], z, v1);
-  glm_vec4_add(v1, m[3], m[3]);
-#endif
-}
-
 /*!
 * @brief creates NEW translate transform matrix by v vector
 *
@@ -229,81 +114,6 @@ glm_scale_uni(mat4 m, float s) {
  glm_scale_to(m, v, m);
 }

-/*!
- * @brief rotate existing transform matrix around X axis by angle
- *        and store result in dest
- *
- * @param[in]   m      affine transfrom
- * @param[in]   angle  angle (radians)
- * @param[out]  dest   rotated matrix
- */
-CGLM_INLINE
-void
-glm_rotate_x(mat4 m, float angle, mat4 dest) {
-  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
-  float c, s;
-
-  c = cosf(angle);
-  s = sinf(angle);
-
-  t[1][1] =  c;
-  t[1][2] =  s;
-  t[2][1] = -s;
-  t[2][2] =  c;
-
-  glm_mul_rot(m, t, dest);
-}
-
-/*!
- * @brief rotate existing transform matrix around Y axis by angle
- *        and store result in dest
- *
- * @param[in]   m      affine transfrom
- * @param[in]   angle  angle (radians)
- * @param[out]  dest   rotated matrix
- */
-CGLM_INLINE
-void
-glm_rotate_y(mat4 m, float angle, mat4 dest) {
-  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
-  float c, s;
-
-  c = cosf(angle);
-  s = sinf(angle);
-
-  t[0][0] =  c;
-  t[0][2] = -s;
-  t[2][0] =  s;
-  t[2][2] =  c;
-
-  glm_mul_rot(m, t, dest);
-}
-
-/*!
- * @brief rotate existing transform matrix around Z axis by angle
- *        and store result in dest
- *
- * @param[in]   m      affine transfrom
- * @param[in]   angle  angle (radians)
- * @param[out]  dest   rotated matrix
- */
-CGLM_INLINE
-void
-glm_rotate_z(mat4 m, float angle, mat4 dest) {
-  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
-  float c, s;
-
-  c = cosf(angle);
-  s = sinf(angle);
-
-  t[0][0] =  c;
-  t[0][1] =  s;
-  t[1][0] = -s;
-  t[1][1] =  c;
-
-  glm_mul_rot(m, t, dest);
-}
-
 /*!
 * @brief creates NEW rotation matrix by angle and axis
 *
@@ -337,67 +147,6 @@ glm_rotate_make(mat4 m, float angle, vec3 axis) {
  m[3][3] = 1.0f;
 }

-/*!
- * @brief rotate existing transform matrix around given axis by angle
- *
- * @param[in, out]  m      affine transfrom
- * @param[in]       angle  angle (radians)
- * @param[in]       axis   axis
- */
-CGLM_INLINE
-void
-glm_rotate(mat4 m, float angle, vec3 axis) {
-  CGLM_ALIGN_MAT mat4 rot;
-  glm_rotate_make(rot, angle, axis);
-  glm_mul_rot(m, rot, m);
-}
-
-/*!
- * @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, vec3 pivot, float angle, 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, vec3 pivot, float angle, 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);
-}
-
 /*!
 * @brief decompose scale vector
 *
@@ -455,7 +204,7 @@ glm_decompose_rs(mat4 m, mat4 r, vec3 s) {
  glm_vec4_scale(r[1], 1.0f/s[1], r[1]);
  glm_vec4_scale(r[2], 1.0f/s[2], r[2]);

-  /* Note from Apple Open Source (asume that the matrix is orthonormal):
+  /* Note from Apple Open Source (assume 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_vec3_cross(m[0], m[1], v);
@@ -483,4 +232,7 @@ glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s) {
  glm_decompose_rs(m, r, s);
 }

+#include "affine-pre.h"
+#include "affine-post.h"
+
 #endif /* cglm_affine_h */
--- a/include/cglm/box.h
+++ b/include/cglm/box.h
@@ -228,6 +228,8 @@ glm_aabb_aabb(vec3 box[2], vec3 other[2]) {
 * https://github.com/erich666/GraphicsGems/blob/master/gems/BoxSphere.c
 * Solid Box - Solid Sphere test.
 *
+ * Sphere Representation in cglm: [center.x, center.y, center.z, radii]
+ *
 * @param[in]   box    solid bounding box
 * @param[in]   s      solid sphere
 */
@@ -237,13 +239,13 @@ glm_aabb_sphere(vec3 box[2], 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];
+  a = (s[0] < box[0][0]) + (s[0] > box[1][0]);
+  b = (s[1] < box[0][1]) + (s[1] > box[1][1]);
+  c = (s[2] < box[0][2]) + (s[2] > box[1][2]);

-  dmin  = glm_pow2(s[0] - box[a][0])
-        + glm_pow2(s[1] - box[b][1])
-        + glm_pow2(s[2] - box[c][2]);
+  dmin  = glm_pow2((s[0] - box[!(a - 1)][0]) * (a != 0))
+        + glm_pow2((s[1] - box[!(b - 1)][1]) * (b != 0))
+        + glm_pow2((s[2] - box[!(c - 1)][2]) * (c != 0));

  return dmin <= glm_pow2(s[3]);
 }
--- a/include/cglm/call.h
+++ b/include/cglm/call.h
@@ -15,6 +15,9 @@ extern "C" {
 #include "call/vec2.h"
 #include "call/vec3.h"
 #include "call/vec4.h"
+#include "call/ivec2.h"
+#include "call/ivec3.h"
+#include "call/ivec4.h"
 #include "call/mat2.h"
 #include "call/mat3.h"
 #include "call/mat4.h"
--- a/include/cglm/call/affine.h
+++ b/include/cglm/call/affine.h
@@ -81,6 +81,10 @@ CGLM_EXPORT
 void
 glmc_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis);

+CGLM_EXPORT
+void
+glmc_spin(mat4 m, float angle, vec3 axis);
+
 CGLM_EXPORT
 void
 glmc_decompose_scalev(mat4 m, vec3 s);
@@ -97,6 +101,52 @@ CGLM_EXPORT
 void
 glmc_decompose(mat4 m, vec4 t, mat4 r, vec3 s);

+/* affine-post */
+
+CGLM_EXPORT
+void
+glmc_translated(mat4 m, vec3 v);
+
+CGLM_EXPORT
+void
+glmc_translated_to(mat4 m, vec3 v, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_translated_x(mat4 m, float x);
+
+CGLM_EXPORT
+void
+glmc_translated_y(mat4 m, float y);
+
+CGLM_EXPORT
+void
+glmc_translated_z(mat4 m, float z);
+
+CGLM_EXPORT
+void
+glmc_rotated_x(mat4 m, float angle, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_rotated_y(mat4 m, float angle, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_rotated_z(mat4 m, float angle, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_rotated(mat4 m, float angle, vec3 axis);
+
+CGLM_EXPORT
+void
+glmc_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis);
+
+CGLM_EXPORT
+void
+glmc_spinned(mat4 m, float angle, vec3 axis);
+
 /* affine-mat */

 CGLM_EXPORT
--- a/include/cglm/call/cam.h
+++ b/include/cglm/call/cam.h
@@ -15,23 +15,17 @@ extern "C" {

 CGLM_EXPORT
 void
-glmc_frustum(float left,
-             float right,
-             float bottom,
-             float top,
-             float nearVal,
-             float farVal,
-             mat4 dest);
+glmc_frustum(float left,   float right,
+             float bottom, float top,
+             float nearZ,  float farZ,
+             mat4  dest);

 CGLM_EXPORT
 void
-glmc_ortho(float left,
-           float right,
-           float bottom,
-           float top,
-           float nearVal,
-           float farVal,
-           mat4 dest);
+glmc_ortho(float left,   float right,
+           float bottom, float top,
+           float nearZ,  float farZ,
+           mat4  dest);

 CGLM_EXPORT
 void
@@ -55,11 +49,7 @@ glmc_ortho_default_s(float aspect, float size, mat4 dest);

 CGLM_EXPORT
 void
-glmc_perspective(float fovy,
-                 float aspect,
-                 float nearVal,
-                 float farVal,
-                 mat4 dest);
+glmc_perspective(float fovy, float aspect, float nearZ, float farZ, mat4 dest);

 CGLM_EXPORT
 void
@@ -88,8 +78,8 @@ glmc_look_anyup(vec3 eye, vec3 dir, mat4 dest);
 CGLM_EXPORT
 void
 glmc_persp_decomp(mat4 proj,
-                  float * __restrict nearVal,
-                  float * __restrict farVal,
+                  float * __restrict nearZ,
+                  float * __restrict farZ,
                  float * __restrict top,
                  float * __restrict bottom,
                  float * __restrict left,
@@ -114,16 +104,16 @@ glmc_persp_decomp_y(mat4 proj,
 CGLM_EXPORT
 void
 glmc_persp_decomp_z(mat4 proj,
-                    float * __restrict nearVal,
-                    float * __restrict farVal);
+                    float * __restrict nearZ,
+                    float * __restrict farZ);

 CGLM_EXPORT
 void
-glmc_persp_decomp_far(mat4 proj, float * __restrict farVal);
+glmc_persp_decomp_far(mat4 proj, float * __restrict farZ);

 CGLM_EXPORT
 void
-glmc_persp_decomp_near(mat4 proj, float * __restrict nearVal);
+glmc_persp_decomp_near(mat4 proj, float * __restrict nearZ);

 CGLM_EXPORT
 float
--- a/include/cglm/call/clipspace/ortho_lh_no.h
+++ b/include/cglm/call/clipspace/ortho_lh_no.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ortho_lh_no_h
+#define cglmc_ortho_lh_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ortho_lh_no(float left,    float right,
+                 float bottom,  float top,
+                 float nearZ,   float farZ,
+                 mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_lh_no(vec3 box[2], mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p_lh_no(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz_lh_no(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_lh_no(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s_lh_no(float aspect, float size, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ortho_lh_no_h */
--- a/include/cglm/call/clipspace/ortho_lh_zo.h
+++ b/include/cglm/call/clipspace/ortho_lh_zo.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ortho_lh_zo_h
+#define cglmc_ortho_lh_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ortho_lh_zo(float left,    float right,
+                 float bottom,  float top,
+                 float nearZ,   float farZ,
+                 mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_lh_zo(vec3 box[2], mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p_lh_zo(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz_lh_zo(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_lh_zo(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s_lh_zo(float aspect, float size, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ortho_lh_zo_h */
--- a/include/cglm/call/clipspace/ortho_rh_no.h
+++ b/include/cglm/call/clipspace/ortho_rh_no.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ortho_rh_no_h
+#define cglmc_ortho_rh_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ortho_rh_no(float left,    float right,
+                 float bottom,  float top,
+                 float nearZ,   float farZ,
+                 mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_rh_no(vec3 box[2], mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p_rh_no(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz_rh_no(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_rh_no(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s_rh_no(float aspect, float size, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ortho_rh_no_h */
--- a/include/cglm/call/clipspace/ortho_rh_zo.h
+++ b/include/cglm/call/clipspace/ortho_rh_zo.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ortho_rh_zo_h
+#define cglmc_ortho_rh_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ortho_rh_zo(float left,    float right,
+                 float bottom,  float top,
+                 float nearZ,   float farZ,
+                 mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_rh_zo(vec3 box[2], mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p_rh_zo(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz_rh_zo(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_rh_zo(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s_rh_zo(float aspect, float size, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ortho_rh_zo_h */
--- a/include/cglm/call/clipspace/persp_lh_no.h
+++ b/include/cglm/call/clipspace/persp_lh_no.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_persp_lh_no_h
+#define cglmc_persp_lh_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_frustum_lh_no(float left,    float right,
+                   float bottom,  float top,
+                   float nearZ,   float farZ,
+                   mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_perspective_lh_no(float fovy,
+                       float aspect,
+                       float nearVal,
+                       float farVal,
+                       mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_persp_move_far_lh_no(mat4 proj, float deltaFar);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_lh_no(mat4 proj,
+                        float * __restrict nearZ, float * __restrict farZ,
+                        float * __restrict top,   float * __restrict bottom,
+                        float * __restrict left,  float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decompv_lh_no(mat4 proj, float dest[6]);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x_lh_no(mat4 proj,
+                          float * __restrict left,
+                          float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y_lh_no(mat4 proj,
+                          float * __restrict top,
+                          float * __restrict bottom);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z_lh_no(mat4 proj,
+                          float * __restrict nearZ,
+                          float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far_lh_no(mat4 proj, float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near_lh_no(mat4 proj, float * __restrict nearZ);
+
+CGLM_EXPORT
+void
+glmc_persp_sizes_lh_no(mat4 proj, float fovy, vec4 dest);
+
+CGLM_EXPORT
+float
+glmc_persp_fovy_lh_no(mat4 proj);
+
+CGLM_EXPORT
+float
+glmc_persp_aspect_lh_no(mat4 proj);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_persp_lh_no_h */
--- a/include/cglm/call/clipspace/persp_lh_zo.h
+++ b/include/cglm/call/clipspace/persp_lh_zo.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_persp_lh_zo_h
+#define cglmc_persp_lh_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_frustum_lh_zo(float left,    float right,
+                   float bottom,  float top,
+                   float nearZ,   float farZ,
+                   mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_perspective_lh_zo(float fovy,
+                       float aspect,
+                       float nearVal,
+                       float farVal,
+                       mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_persp_move_far_lh_zo(mat4 proj, float deltaFar);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_lh_zo(mat4 proj,
+                        float * __restrict nearZ, float * __restrict farZ,
+                        float * __restrict top,   float * __restrict bottom,
+                        float * __restrict left,  float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decompv_lh_zo(mat4 proj, float dest[6]);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x_lh_zo(mat4 proj,
+                          float * __restrict left,
+                          float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y_lh_zo(mat4 proj,
+                          float * __restrict top,
+                          float * __restrict bottom);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z_lh_zo(mat4 proj,
+                          float * __restrict nearZ,
+                          float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far_lh_zo(mat4 proj, float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near_lh_zo(mat4 proj, float * __restrict nearZ);
+
+CGLM_EXPORT
+void
+glmc_persp_sizes_lh_zo(mat4 proj, float fovy, vec4 dest);
+
+CGLM_EXPORT
+float
+glmc_persp_fovy_lh_zo(mat4 proj);
+
+CGLM_EXPORT
+float
+glmc_persp_aspect_lh_zo(mat4 proj);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_persp_lh_zo_h */
--- a/include/cglm/call/clipspace/persp_rh_no.h
+++ b/include/cglm/call/clipspace/persp_rh_no.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_persp_rh_no_h
+#define cglmc_persp_rh_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_frustum_rh_no(float left,    float right,
+                   float bottom,  float top,
+                   float nearZ,   float farZ,
+                   mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_perspective_rh_no(float fovy,
+                       float aspect,
+                       float nearVal,
+                       float farVal,
+                       mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_persp_move_far_rh_no(mat4 proj, float deltaFar);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_rh_no(mat4 proj,
+                        float * __restrict nearZ, float * __restrict farZ,
+                        float * __restrict top,   float * __restrict bottom,
+                        float * __restrict left,  float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decompv_rh_no(mat4 proj, float dest[6]);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x_rh_no(mat4 proj,
+                          float * __restrict left,
+                          float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y_rh_no(mat4 proj,
+                          float * __restrict top,
+                          float * __restrict bottom);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z_rh_no(mat4 proj,
+                          float * __restrict nearZ,
+                          float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far_rh_no(mat4 proj, float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near_rh_no(mat4 proj, float * __restrict nearZ);
+
+CGLM_EXPORT
+void
+glmc_persp_sizes_rh_no(mat4 proj, float fovy, vec4 dest);
+
+CGLM_EXPORT
+float
+glmc_persp_fovy_rh_no(mat4 proj);
+
+CGLM_EXPORT
+float
+glmc_persp_aspect_rh_no(mat4 proj);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_persp_rh_no_h */
--- a/include/cglm/call/clipspace/persp_rh_zo.h
+++ b/include/cglm/call/clipspace/persp_rh_zo.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_persp_rh_zo_h
+#define cglmc_persp_rh_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_frustum_rh_zo(float left,    float right,
+                   float bottom,  float top,
+                   float nearZ,   float farZ,
+                   mat4  dest);
+
+CGLM_EXPORT
+void
+glmc_perspective_rh_zo(float fovy,
+                       float aspect,
+                       float nearVal,
+                       float farVal,
+                       mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_persp_move_far_rh_zo(mat4 proj, float deltaFar);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_rh_zo(mat4 proj,
+                        float * __restrict nearZ, float * __restrict farZ,
+                        float * __restrict top,   float * __restrict bottom,
+                        float * __restrict left,  float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decompv_rh_zo(mat4 proj, float dest[6]);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x_rh_zo(mat4 proj,
+                          float * __restrict left,
+                          float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y_rh_zo(mat4 proj,
+                          float * __restrict top,
+                          float * __restrict bottom);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z_rh_zo(mat4 proj,
+                          float * __restrict nearZ,
+                          float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far_rh_zo(mat4 proj, float * __restrict farZ);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near_rh_zo(mat4 proj, float * __restrict nearZ);
+
+CGLM_EXPORT
+void
+glmc_persp_sizes_rh_zo(mat4 proj, float fovy, vec4 dest);
+
+CGLM_EXPORT
+float
+glmc_persp_fovy_rh_zo(mat4 proj);
+
+CGLM_EXPORT
+float
+glmc_persp_aspect_rh_zo(mat4 proj);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_persp_rh_zo_h */
--- a/include/cglm/call/clipspace/project_no.h
+++ b/include/cglm/call/clipspace/project_no.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_project_no_h
+#define cglmc_project_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_unprojecti_no(vec3 pos, mat4 invMat, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_project_no(vec3 pos, mat4 m, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_project_z_no(vec3 pos, mat4 m);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_project_no_h */
--- a/include/cglm/call/clipspace/project_zo.h
+++ b/include/cglm/call/clipspace/project_zo.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_project_zo_h
+#define cglmc_project_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_unprojecti_zo(vec3 pos, mat4 invMat, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_project_zo(vec3 pos, mat4 m, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_project_z_zo(vec3 pos, mat4 m);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_project_zo_h */
--- a/include/cglm/call/clipspace/view_lh_no.h
+++ b/include/cglm/call/clipspace/view_lh_no.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_view_lh_no_h
+#define cglmc_view_lh_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_lookat_lh_no(vec3 eye, vec3 center, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_lh_no(vec3 eye, vec3 dir, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_anyup_lh_no(vec3 eye, vec3 dir, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_view_lh_no_h */
--- a/include/cglm/call/clipspace/view_lh_zo.h
+++ b/include/cglm/call/clipspace/view_lh_zo.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_view_lh_zo_h
+#define cglmc_view_lh_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_lookat_lh_zo(vec3 eye, vec3 center, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_lh_zo(vec3 eye, vec3 dir, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_anyup_lh_zo(vec3 eye, vec3 dir, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_view_lh_zo_h */
--- a/include/cglm/call/clipspace/view_rh_no.h
+++ b/include/cglm/call/clipspace/view_rh_no.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_view_rh_no_h
+#define cglmc_view_rh_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_lookat_rh_no(vec3 eye, vec3 center, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_rh_no(vec3 eye, vec3 dir, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_anyup_rh_no(vec3 eye, vec3 dir, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_view_rh_no_h */
--- a/include/cglm/call/clipspace/view_rh_zo.h
+++ b/include/cglm/call/clipspace/view_rh_zo.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_view_rh_zo_h
+#define cglmc_view_rh_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_lookat_rh_zo(vec3 eye, vec3 center, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_rh_zo(vec3 eye, vec3 dir, vec3 up, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_look_anyup_rh_zo(vec3 eye, vec3 dir, mat4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_view_rh_zo_h */
--- a/include/cglm/call/ivec2.h
+++ b/include/cglm/call/ivec2.h
@@ -0,0 +1,79 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ivec2_h
+#define cglmc_ivec2_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ivec2(int * __restrict v, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_copy(ivec2 a, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_zero(ivec2 v);
+
+CGLM_EXPORT
+void
+glmc_ivec2_one(ivec2 v);
+
+CGLM_EXPORT
+void
+glmc_ivec2_add(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_adds(ivec2 v, int s, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_subs(ivec2 v, int s, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_scale(ivec2 v, int s, ivec2 dest);
+
+CGLM_EXPORT
+int
+glmc_ivec2_distance2(ivec2 a, ivec2 b);
+
+CGLM_EXPORT
+float
+glmc_ivec2_distance(ivec2 a, ivec2 b);
+
+CGLM_EXPORT
+void
+glmc_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_clamp(ivec2 v, int minVal, int maxVal);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ivec2_h */
--- a/include/cglm/call/ivec3.h
+++ b/include/cglm/call/ivec3.h
@@ -0,0 +1,79 @@
+/*
+ * Copyright (c);, Recep Aslantas.
+ *
+ * MIT License (MIT);, http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ivec3_h
+#define cglmc_ivec3_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ivec3(ivec4 v4, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_copy(ivec3 a, ivec3 dest);
+
+CGLM_EXPORT
+void 
+glmc_ivec3_zero(ivec3 v);
+
+CGLM_EXPORT
+void
+glmc_ivec3_one(ivec3 v);
+
+CGLM_EXPORT
+void
+glmc_ivec3_add(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_adds(ivec3 v, int s, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_subs(ivec3 v, int s, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_scale(ivec3 v, int s, ivec3 dest);
+
+CGLM_EXPORT
+int
+glmc_ivec3_distance2(ivec3 a, ivec3 b);
+
+CGLM_EXPORT
+float
+glmc_ivec3_distance(ivec3 a, ivec3 b);
+
+CGLM_EXPORT
+void
+glmc_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_clamp(ivec3 v, int minVal, int maxVal);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ivec3_h */
--- a/include/cglm/call/ivec4.h
+++ b/include/cglm/call/ivec4.h
@@ -0,0 +1,79 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ivec4_h
+#define cglmc_ivec4_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ivec4(ivec3 v3, int last, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_copy(ivec4 a, ivec4 dest);
+
+CGLM_EXPORT
+void 
+glmc_ivec4_zero(ivec4 v);
+
+CGLM_EXPORT
+void
+glmc_ivec4_one(ivec4 v);
+
+CGLM_EXPORT
+void
+glmc_ivec4_add(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_adds(ivec4 v, int s, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_subs(ivec4 v, int s, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_scale(ivec4 v, int s, ivec4 dest);
+
+CGLM_EXPORT
+int
+glmc_ivec4_distance2(ivec4 a, ivec4 b);
+
+CGLM_EXPORT
+float
+glmc_ivec4_distance(ivec4 a, ivec4 b);
+
+CGLM_EXPORT
+void
+glmc_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_clamp(ivec4 v, int minVal, int maxVal);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ivec4_h */
--- a/include/cglm/call/project.h
+++ b/include/cglm/call/project.h
@@ -25,6 +25,14 @@ CGLM_EXPORT
 void
 glmc_project(vec3 pos, mat4 m, vec4 vp, vec3 dest);

+CGLM_EXPORT
+float
+glmc_project_z(vec3 pos, mat4 m);
+
+CGLM_EXPORT
+void
+glmc_pickmatrix(vec2 center, vec2 size, vec4 vp, mat4 dest);
+
 #ifdef __cplusplus
 }
 #endif
--- a/include/cglm/call/quat.h
+++ b/include/cglm/call/quat.h
@@ -37,6 +37,10 @@ CGLM_EXPORT
 void
 glmc_quat_copy(versor q, versor dest);

+CGLM_EXPORT
+void
+glmc_quat_from_vecs(vec3 a, vec3 b, versor dest);
+
 CGLM_EXPORT
 float
 glmc_quat_norm(versor q);
@@ -121,6 +125,10 @@ CGLM_EXPORT
 void
 glmc_quat_lerpc(versor from, versor to, float t, versor dest);

+CGLM_EXPORT
+void
+glmc_quat_nlerp(versor q, versor r, float t, versor dest);
+
 CGLM_EXPORT
 void
 glmc_quat_slerp(versor q, versor r, float t, versor dest);
--- a/include/cglm/call/vec2.h
+++ b/include/cglm/call/vec2.h
@@ -149,6 +149,18 @@ CGLM_EXPORT
 void
 glmc_vec2_lerp(vec2 from, vec2 to, float t, vec2 dest);

+CGLM_EXPORT
+void
+glmc_vec2_complex_mul(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_complex_div(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_complex_conjugate(vec2 a, vec2 dest);
+
 #ifdef __cplusplus
 }
 #endif
--- a/include/cglm/call/vec4.h
+++ b/include/cglm/call/vec4.h
@@ -99,7 +99,7 @@ glmc_vec4_scale(vec4 v, float s, vec4 dest);

 CGLM_EXPORT
 void
-glmc_vec4_scale_as(vec3 v, float s, vec3 dest);
+glmc_vec4_scale_as(vec4 v, float s, vec4 dest);

 CGLM_EXPORT
 void
--- a/include/cglm/cam.h
+++ b/include/cglm/cam.h
@@ -7,13 +7,13 @@

 /*
 Functions:
-   CGLM_INLINE void  glm_frustum(float left,    float right,
-                                 float bottom,  float top,
-                                 float nearVal, float farVal,
+   CGLM_INLINE void  glm_frustum(float left,   float right,
+                                 float bottom, float top,
+                                 float nearZ,  float farZ,
                                 mat4  dest)
-   CGLM_INLINE void  glm_ortho(float left,    float right,
-                               float bottom,  float top,
-                               float nearVal, float farVal,
+   CGLM_INLINE void  glm_ortho(float left,   float right,
+                               float bottom, float top,
+                               float nearZ,  float farZ,
                               mat4  dest)
   CGLM_INLINE void  glm_ortho_aabb(vec3 box[2], mat4 dest)
   CGLM_INLINE void  glm_ortho_aabb_p(vec3 box[2],  float padding, mat4 dest)
@@ -22,8 +22,8 @@
   CGLM_INLINE void  glm_ortho_default_s(float aspect, float size, mat4 dest)
   CGLM_INLINE void  glm_perspective(float fovy,
                                     float aspect,
-                                     float nearVal,
-                                     float farVal,
+                                     float nearZ,
+                                     float farZ,
                                     mat4  dest)
   CGLM_INLINE void  glm_perspective_default(float aspect, mat4 dest)
   CGLM_INLINE void  glm_perspective_resize(float aspect, mat4 proj)
@@ -31,26 +31,61 @@
   CGLM_INLINE void  glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest)
   CGLM_INLINE void  glm_look_anyup(vec3 eye, vec3 dir, mat4 dest)
   CGLM_INLINE void  glm_persp_decomp(mat4   proj,
-                                      float *nearVal, float *farVal,
-                                      float *top,     float *bottom,
-                                      float *left,    float *right)
+                                      float *nearZ, float *farZ,
+                                      float *top,   float *bottom,
+                                      float *left,  float *right)
   CGLM_INLINE void  glm_persp_decompv(mat4 proj, float dest[6])
   CGLM_INLINE void  glm_persp_decomp_x(mat4 proj, float *left, float *right)
   CGLM_INLINE void  glm_persp_decomp_y(mat4 proj, float *top,  float *bottom)
   CGLM_INLINE void  glm_persp_decomp_z(mat4 proj, float *nearv, float *farv)
-   CGLM_INLINE void  glm_persp_decomp_far(mat4 proj, float *farVal)
-   CGLM_INLINE void  glm_persp_decomp_near(mat4 proj, float *nearVal)
+   CGLM_INLINE void  glm_persp_decomp_far(mat4 proj, float *farZ)
+   CGLM_INLINE void  glm_persp_decomp_near(mat4 proj, float *nearZ)
   CGLM_INLINE float glm_persp_fovy(mat4 proj)
   CGLM_INLINE float glm_persp_aspect(mat4 proj)
   CGLM_INLINE void  glm_persp_sizes(mat4 proj, float fovy, vec4 dest)
 */

-#ifndef cglm_vcam_h
-#define cglm_vcam_h
+#ifndef cglm_cam_h
+#define cglm_cam_h

 #include "common.h"
 #include "plane.h"

+#include "clipspace/persp.h"
+
+#ifndef CGLM_CLIPSPACE_INCLUDE_ALL
+#  if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+#    include "clipspace/ortho_lh_zo.h"
+#    include "clipspace/persp_lh_zo.h"
+#    include "clipspace/view_lh_zo.h"
+#  elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+#    include "clipspace/ortho_lh_no.h"
+#    include "clipspace/persp_lh_no.h"
+#    include "clipspace/view_lh_no.h"
+#  elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+#    include "clipspace/ortho_rh_zo.h"
+#    include "clipspace/persp_rh_zo.h"
+#    include "clipspace/view_rh_zo.h"
+#  elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+#    include "clipspace/ortho_rh_no.h"
+#    include "clipspace/persp_rh_no.h"
+#    include "clipspace/view_rh_no.h"
+#  endif
+#else
+#  include "clipspace/ortho_lh_zo.h"
+#  include "clipspace/persp_lh_zo.h"
+#  include "clipspace/ortho_lh_no.h"
+#  include "clipspace/persp_lh_no.h"
+#  include "clipspace/ortho_rh_zo.h"
+#  include "clipspace/persp_rh_zo.h"
+#  include "clipspace/ortho_rh_no.h"
+#  include "clipspace/persp_rh_no.h"
+#  include "clipspace/view_lh_zo.h"
+#  include "clipspace/view_lh_no.h"
+#  include "clipspace/view_rh_zo.h"
+#  include "clipspace/view_rh_no.h"
+#endif
+
 /*!
 * @brief set up perspective peprojection matrix
 *
@@ -58,32 +93,25 @@
 * @param[in]  right   viewport.right
 * @param[in]  bottom  viewport.bottom
 * @param[in]  top     viewport.top
- * @param[in]  nearVal near clipping plane
- * @param[in]  farVal  far clipping plane
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
 * @param[out] dest    result matrix
 */
 CGLM_INLINE
 void
 glm_frustum(float left,    float right,
            float bottom,  float top,
-            float nearVal, float farVal,
+            float nearZ,   float farZ,
            mat4  dest) {
-  float rl, tb, fn, nv;
-
-  glm_mat4_zero(dest);
-
-  rl = 1.0f / (right  - left);
-  tb = 1.0f / (top    - bottom);
-  fn =-1.0f / (farVal - nearVal);
-  nv = 2.0f * nearVal;
-
-  dest[0][0] = nv * rl;
-  dest[1][1] = nv * tb;
-  dest[2][0] = (right  + left)    * rl;
-  dest[2][1] = (top    + bottom)  * tb;
-  dest[2][2] = (farVal + nearVal) * fn;
-  dest[2][3] =-1.0f;
-  dest[3][2] = farVal * nv * fn;
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_frustum_lh_zo(left, right, bottom, top, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_frustum_lh_no(left, right, bottom, top, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_frustum_rh_zo(left, right, bottom, top, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_frustum_rh_no(left, right, bottom, top, nearZ, farZ, dest);
+#endif
 }

 /*!
@@ -93,31 +121,25 @@ glm_frustum(float left,    float right,
 * @param[in]  right   viewport.right
 * @param[in]  bottom  viewport.bottom
 * @param[in]  top     viewport.top
- * @param[in]  nearVal near clipping plane
- * @param[in]  farVal  far clipping plane
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
 * @param[out] dest    result matrix
 */
 CGLM_INLINE
 void
 glm_ortho(float left,    float right,
          float bottom,  float top,
-          float nearVal, float farVal,
+          float nearZ,   float farZ,
          mat4  dest) {
-  float rl, tb, fn;
-
-  glm_mat4_zero(dest);
-
-  rl = 1.0f / (right  - left);
-  tb = 1.0f / (top    - bottom);
-  fn =-1.0f / (farVal - nearVal);
-
-  dest[0][0] = 2.0f * rl;
-  dest[1][1] = 2.0f * tb;
-  dest[2][2] = 2.0f * fn;
-  dest[3][0] =-(right  + left)    * rl;
-  dest[3][1] =-(top    + bottom)  * tb;
-  dest[3][2] = (farVal + nearVal) * fn;
-  dest[3][3] = 1.0f;
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_ortho_lh_zo(left, right, bottom, top, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_ortho_lh_no(left, right, bottom, top, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_ortho_rh_zo(left, right, bottom, top, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_ortho_rh_no(left, right, bottom, top, nearZ, farZ, dest);
+#endif
 }

 /*!
@@ -131,10 +153,15 @@ glm_ortho(float left,    float right,
 CGLM_INLINE
 void
 glm_ortho_aabb(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],
-            dest);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_ortho_aabb_lh_zo(box, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_ortho_aabb_lh_no(box, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_ortho_aabb_rh_zo(box, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_ortho_aabb_rh_no(box, dest);
+#endif
 }

 /*!
@@ -149,10 +176,15 @@ glm_ortho_aabb(vec3 box[2], mat4 dest) {
 CGLM_INLINE
 void
 glm_ortho_aabb_p(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),
-            dest);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_ortho_aabb_p_lh_zo(box, padding, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_ortho_aabb_p_lh_no(box, padding, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_ortho_aabb_p_rh_zo(box, padding, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_ortho_aabb_p_rh_no(box, padding, dest);
+#endif
 }

 /*!
@@ -167,10 +199,15 @@ 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(box[0][0],              box[1][0],
-            box[0][1],              box[1][1],
-          -(box[1][2] + padding), -(box[0][2] - padding),
-            dest);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_ortho_aabb_pz_lh_zo(box, padding, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_ortho_aabb_pz_lh_no(box, padding, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_ortho_aabb_pz_rh_zo(box, padding, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_ortho_aabb_pz_rh_no(box, padding, dest);
+#endif
 }

 /*!
@@ -182,14 +219,15 @@ glm_ortho_aabb_pz(vec3 box[2], float padding, mat4 dest) {
 CGLM_INLINE
 void
 glm_ortho_default(float aspect, mat4 dest) {
-  if (aspect >= 1.0f) {
-    glm_ortho(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
-    return;
-  }
-
-  aspect = 1.0f / aspect;
-
-  glm_ortho(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_ortho_default_lh_zo(aspect, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_ortho_default_lh_no(aspect, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_ortho_default_rh_zo(aspect, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_ortho_default_rh_no(aspect, dest);
+#endif
 }

 /*!
@@ -202,24 +240,15 @@ glm_ortho_default(float aspect, mat4 dest) {
 CGLM_INLINE
 void
 glm_ortho_default_s(float aspect, float size, mat4 dest) {
-  if (aspect >= 1.0f) {
-    glm_ortho(-size * aspect,
-               size * aspect,
-              -size,
-               size,
-              -size - 100.0f,
-               size + 100.0f,
-               dest);
-    return;
-  }
-
-  glm_ortho(-size,
-             size,
-            -size / aspect,
-             size / aspect,
-            -size - 100.0f,
-             size + 100.0f,
-             dest);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_ortho_default_s_lh_zo(aspect, size, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_ortho_default_s_lh_no(aspect, size, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_ortho_default_s_rh_zo(aspect, size, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_ortho_default_s_rh_no(aspect, size, dest);
+#endif
 }

 /*!
@@ -227,29 +256,22 @@ glm_ortho_default_s(float aspect, float size, mat4 dest) {
 *
 * @param[in]  fovy    field of view angle
 * @param[in]  aspect  aspect ratio ( width / height )
- * @param[in]  nearVal near clipping plane
- * @param[in]  farVal  far clipping planes
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping planes
 * @param[out] dest    result matrix
 */
 CGLM_INLINE
 void
-glm_perspective(float fovy,
-                float aspect,
-                float nearVal,
-                float farVal,
-                mat4  dest) {
-  float f, fn;
-
-  glm_mat4_zero(dest);
-
-  f  = 1.0f / tanf(fovy * 0.5f);
-  fn = 1.0f / (nearVal - farVal);
-
-  dest[0][0] = f / aspect;
-  dest[1][1] = f;
-  dest[2][2] = (nearVal + farVal) * fn;
-  dest[2][3] =-1.0f;
-  dest[3][2] = 2.0f * nearVal * farVal * fn;
+glm_perspective(float fovy, float aspect, float nearZ, float farZ, mat4 dest) {
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_perspective_lh_zo(fovy, aspect, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_perspective_lh_no(fovy, aspect, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_perspective_rh_zo(fovy, aspect, nearZ, farZ, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_perspective_rh_no(fovy, aspect, nearZ, farZ, dest);
+#endif
 }

 /*!
@@ -263,17 +285,15 @@ glm_perspective(float fovy,
 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;
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_move_far_lh_zo(proj, deltaFar);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_move_far_lh_no(proj, deltaFar);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_move_far_rh_zo(proj, deltaFar);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_move_far_rh_no(proj, deltaFar);
+#endif
 }

 /*!
@@ -286,7 +306,15 @@ glm_persp_move_far(mat4 proj, float deltaFar) {
 CGLM_INLINE
 void
 glm_perspective_default(float aspect, mat4 dest) {
-  glm_perspective(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_perspective_default_lh_zo(aspect, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_perspective_default_lh_no(aspect, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_perspective_default_rh_zo(aspect, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_perspective_default_rh_no(aspect, dest);
+#endif
 }

 /*!
@@ -320,28 +348,11 @@ glm_perspective_resize(float aspect, mat4 proj) {
 CGLM_INLINE
 void
 glm_lookat(vec3 eye, vec3 center, vec3 up, mat4 dest) {
-  CGLM_ALIGN(8) vec3 f, u, s;
-
-  glm_vec3_sub(center, eye, f);
-  glm_vec3_normalize(f);
-
-  glm_vec3_crossn(f, up, s);
-  glm_vec3_cross(s, f, u);
-
-  dest[0][0] = s[0];
-  dest[0][1] = u[0];
-  dest[0][2] =-f[0];
-  dest[1][0] = s[1];
-  dest[1][1] = u[1];
-  dest[1][2] =-f[1];
-  dest[2][0] = s[2];
-  dest[2][1] = u[2];
-  dest[2][2] =-f[2];
-  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;
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_LH_BIT
+  glm_lookat_lh(eye, center, up, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_RH_BIT
+  glm_lookat_rh(eye, center, up, dest);
+#endif
 }

 /*!
@@ -361,9 +372,11 @@ glm_lookat(vec3 eye, vec3 center, vec3 up, mat4 dest) {
 CGLM_INLINE
 void
 glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
-  CGLM_ALIGN(8) vec3 target;
-  glm_vec3_add(eye, dir, target);
-  glm_lookat(eye, target, up, dest);
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_LH_BIT
+  glm_look_lh(eye, dir, up, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_RH_BIT
+  glm_look_rh(eye, dir, up, dest);
+#endif
 }

 /*!
@@ -379,17 +392,19 @@ glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
 CGLM_INLINE
 void
 glm_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
-  CGLM_ALIGN(8) vec3 up;
-  glm_vec3_ortho(dir, up);
-  glm_look(eye, dir, up, dest);
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_LH_BIT
+  glm_look_anyup_lh(eye, dir, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_RH_BIT
+  glm_look_anyup_rh(eye, dir, dest);
+#endif
 }

 /*!
 * @brief decomposes frustum values of perspective projection.
 *
 * @param[in]  proj    perspective projection matrix
- * @param[out] nearVal near
- * @param[out] farVal  far
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
 * @param[out] top     top
 * @param[out] bottom  bottom
 * @param[out] left    left
@@ -398,31 +413,18 @@ glm_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
 CGLM_INLINE
 void
 glm_persp_decomp(mat4 proj,
-                 float * __restrict nearVal, float * __restrict farVal,
-                 float * __restrict top,     float * __restrict bottom,
-                 float * __restrict left,    float * __restrict right) {
-  float m00, m11, m20, m21, m22, m32, n, f;
-  float n_m11, n_m00;
-
-  m00 = proj[0][0];
-  m11 = proj[1][1];
-  m20 = proj[2][0];
-  m21 = proj[2][1];
-  m22 = proj[2][2];
-  m32 = proj[3][2];
-
-  n = m32 / (m22 - 1.0f);
-  f = m32 / (m22 + 1.0f);
-
-  n_m11 = n / m11;
-  n_m00 = n / m00;
-
-  *nearVal = n;
-  *farVal  = f;
-  *bottom  = n_m11 * (m21 - 1.0f);
-  *top     = n_m11 * (m21 + 1.0f);
-  *left    = n_m00 * (m20 - 1.0f);
-  *right   = n_m00 * (m20 + 1.0f);
+                 float * __restrict nearZ, float * __restrict farZ,
+                 float * __restrict top,   float * __restrict bottom,
+                 float * __restrict left,  float * __restrict right) {
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decomp_lh_zo(proj, nearZ, farZ, top, bottom, left, right);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decomp_lh_no(proj, nearZ, farZ, top, bottom, left, right);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decomp_rh_zo(proj, nearZ, farZ, top, bottom, left, right);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decomp_rh_no(proj, nearZ, farZ, top, bottom, left, right);
+#endif
 }

 /*!
@@ -435,8 +437,15 @@ glm_persp_decomp(mat4 proj,
 CGLM_INLINE
 void
 glm_persp_decompv(mat4 proj, float dest[6]) {
-  glm_persp_decomp(proj, &dest[0], &dest[1], &dest[2],
-                         &dest[3], &dest[4], &dest[5]);
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decompv_lh_zo(proj, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decompv_lh_no(proj, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decompv_rh_zo(proj, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decompv_rh_no(proj, dest);
+#endif
 }

 /*!
@@ -452,14 +461,15 @@ void
 glm_persp_decomp_x(mat4 proj,
                   float * __restrict left,
                   float * __restrict right) {
-  float nearVal, m20, m00;
-
-  m00 = proj[0][0];
-  m20 = proj[2][0];
-
-  nearVal = proj[3][2] / (proj[3][3] - 1.0f);
-  *left   = nearVal * (m20 - 1.0f) / m00;
-  *right  = nearVal * (m20 + 1.0f) / m00;
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decomp_x_lh_zo(proj, left, right);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decomp_x_lh_no(proj, left, right);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decomp_x_rh_zo(proj, left, right);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decomp_x_rh_no(proj, left, right);
+#endif
 }

 /*!
@@ -475,14 +485,15 @@ void
 glm_persp_decomp_y(mat4 proj,
                   float * __restrict top,
                   float * __restrict bottom) {
-  float nearVal, m21, m11;
-
-  m21 = proj[2][1];
-  m11 = proj[1][1];
-
-  nearVal = proj[3][2] / (proj[3][3] - 1.0f);
-  *bottom = nearVal * (m21 - 1) / m11;
-  *top    = nearVal * (m21 + 1) / m11;
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decomp_y_lh_zo(proj, top, bottom);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decomp_y_lh_no(proj, top, bottom);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decomp_y_rh_zo(proj, top, bottom);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decomp_y_rh_no(proj, top, bottom);
+#endif
 }

 /*!
@@ -490,70 +501,61 @@ glm_persp_decomp_y(mat4 proj,
 *        z stands for z axis (near / far axis)
 *
 * @param[in]  proj    perspective projection matrix
- * @param[out] nearVal near
- * @param[out] farVal  far
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
 */
 CGLM_INLINE
 void
-glm_persp_decomp_z(mat4 proj,
-                   float * __restrict nearVal,
-                   float * __restrict farVal) {
-  float m32, m22;
-
-  m32 = proj[3][2];
-  m22 = proj[2][2];
-
-  *nearVal = m32 / (m22 - 1.0f);
-  *farVal  = m32 / (m22 + 1.0f);
+glm_persp_decomp_z(mat4 proj, float * __restrict nearZ, float * __restrict farZ) {
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decomp_z_lh_zo(proj, nearZ, farZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decomp_z_lh_no(proj, nearZ, farZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decomp_z_rh_zo(proj, nearZ, farZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decomp_z_rh_no(proj, nearZ, farZ);
+#endif
 }

 /*!
 * @brief decomposes far value of perspective projection.
 *
 * @param[in]  proj   perspective projection matrix
- * @param[out] farVal far
+ * @param[out] farZ   far
 */
 CGLM_INLINE
 void
-glm_persp_decomp_far(mat4 proj, float * __restrict farVal) {
-  *farVal = proj[3][2] / (proj[2][2] + 1.0f);
+glm_persp_decomp_far(mat4 proj, float * __restrict farZ) {
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decomp_far_lh_zo(proj, farZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decomp_far_lh_no(proj, farZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decomp_far_rh_zo(proj, farZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decomp_far_rh_no(proj, farZ);
+#endif
 }

 /*!
 * @brief decomposes near value of perspective projection.
 *
- * @param[in]  proj    perspective projection matrix
- * @param[out] nearVal near
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] nearZ  near
 */
 CGLM_INLINE
 void
-glm_persp_decomp_near(mat4 proj, float * __restrict nearVal) {
-  *nearVal = proj[3][2] / (proj[2][2] - 1.0f);
-}
-
-/*!
- * @brief returns field of view angle along the Y-axis (in radians)
- *
- * if you need to degrees, use glm_deg to convert it or use this:
- * fovy_deg = glm_deg(glm_persp_fovy(projMatrix))
- *
- * @param[in] proj perspective projection matrix
- */
-CGLM_INLINE
-float
-glm_persp_fovy(mat4 proj) {
-  return 2.0f * atanf(1.0f / proj[1][1]);
-}
-
-/*!
- * @brief returns aspect ratio of perspective projection
- *
- * @param[in] proj perspective projection matrix
- */
-CGLM_INLINE
-float
-glm_persp_aspect(mat4 proj) {
-  return proj[1][1] / proj[0][0];
+glm_persp_decomp_near(mat4 proj, float * __restrict nearZ) {
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_decomp_near_lh_zo(proj, nearZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_decomp_near_lh_no(proj, nearZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_decomp_near_rh_zo(proj, nearZ);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_decomp_near_rh_no(proj, nearZ);
+#endif
 }

 /*!
@@ -566,17 +568,15 @@ glm_persp_aspect(mat4 proj) {
 CGLM_INLINE
 void
 glm_persp_sizes(mat4 proj, float fovy, vec4 dest) {
-  float t, a, nearVal, farVal;
-
-  t = 2.0f * tanf(fovy * 0.5f);
-  a = glm_persp_aspect(proj);
-
-  glm_persp_decomp_z(proj, &nearVal, &farVal);
-
-  dest[1]  = t * nearVal;
-  dest[3]  = t * farVal;
-  dest[0]  = a * dest[1];
-  dest[2]  = a * dest[3];
+#if CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_ZO
+  glm_persp_sizes_lh_zo(proj, fovy, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_LH_NO
+  glm_persp_sizes_lh_no(proj, fovy, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_ZO
+  glm_persp_sizes_rh_zo(proj, fovy, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL == CGLM_CLIP_CONTROL_RH_NO
+  glm_persp_sizes_rh_no(proj, fovy, dest);
+#endif
 }

-#endif /* cglm_vcam_h */
+#endif /* cglm_cam_h */
--- a/include/cglm/cglm.h
+++ b/include/cglm/cglm.h
@@ -12,6 +12,9 @@
 #include "vec2.h"
 #include "vec3.h"
 #include "vec4.h"
+#include "ivec2.h"
+#include "ivec3.h"
+#include "ivec4.h"
 #include "mat4.h"
 #include "mat3.h"
 #include "mat2.h"
--- a/include/cglm/clipspace/ortho_lh_no.h
+++ b/include/cglm/clipspace/ortho_lh_no.h
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_ortho_lh_no(float left,    float right,
+                                    float bottom,  float top,
+                                    float nearZ, float farZ,
+                                    mat4  dest)
+   CGLM_INLINE void glm_ortho_aabb_lh_no(vec3 box[2], mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_p_lh_no(vec3 box[2],
+                                           float padding,
+                                           mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_pz_lh_no(vec3 box[2],
+                                            float padding,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_lh_no(float aspect,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_s_lh_no(float aspect,
+                                              float size,
+                                              mat4 dest)
+ */
+
+#ifndef cglm_ortho_lh_no_h
+#define cglm_ortho_lh_no_h
+
+#include "../common.h"
+#include "../plane.h"
+#include "../mat4.h"
+
+/*!
+ * @brief set up orthographic projection matrix
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_lh_no(float left,    float right,
+                float bottom,  float top,
+                float nearZ, float farZ,
+                mat4  dest) {
+  float rl, tb, fn;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+
+  dest[0][0] = 2.0f * rl;
+  dest[1][1] = 2.0f * tb;
+  dest[2][2] =-2.0f * fn;
+  dest[3][0] =-(right  + left)    * rl;
+  dest[3][1] =-(top    + bottom)  * tb;
+  dest[3][2] = (farZ + nearZ) * fn;
+  dest[3][3] = 1.0f;
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box   AABB
+ * @param[out] dest  result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_lh_no(vec3 box[2], mat4 dest) {
+  glm_ortho_lh_no(box[0][0],  box[1][0],
+                  box[0][1],  box[1][1],
+                 -box[1][2], -box[0][2],
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_p_lh_no(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_lh_no(box[0][0] - padding,    box[1][0] + padding,
+                  box[0][1] - padding,    box[1][1] + padding,
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding for near and far
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_pz_lh_no(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_lh_no(box[0][0],              box[1][0],
+                  box[0][1],              box[1][1],
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up unit orthographic projection matrix
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  aspect aspect ration ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_lh_no(float aspect, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_lh_no(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
+    return;
+  }
+
+  aspect = 1.0f / aspect;
+
+  glm_ortho_lh_no(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix with given CUBE size
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[in]  size   cube size
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_s_lh_no(float aspect, float size, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_lh_no(-size * aspect,
+                     size * aspect,
+                    -size,
+                     size,
+                    -size - 100.0f,
+                     size + 100.0f,
+                     dest);
+    return;
+  }
+
+  glm_ortho_lh_no(-size,
+                   size,
+                  -size / aspect,
+                   size / aspect,
+                  -size - 100.0f,
+                   size + 100.0f,
+                   dest);
+}
+
+#endif /*cglm_ortho_lh_no_h*/
--- a/include/cglm/clipspace/ortho_lh_zo.h
+++ b/include/cglm/clipspace/ortho_lh_zo.h
@@ -0,0 +1,177 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_ortho_lh_zo(float left,    float right,
+                                    float bottom,  float top,
+                                    float nearZ, float farZ,
+                                    mat4  dest)
+   CGLM_INLINE void glm_ortho_aabb_lh_zo(vec3 box[2], mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_p_lh_zo(vec3 box[2],
+                                           float padding,
+                                           mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_pz_lh_zo(vec3 box[2],
+                                            float padding,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_lh_zo(float aspect,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_s_lh_zo(float aspect,
+                                              float size,
+                                              mat4 dest)
+ */
+
+#ifndef cglm_ortho_lh_zo_h
+#define cglm_ortho_lh_zo_h
+
+#include "../common.h"
+#include "../plane.h"
+#include "../mat4.h"
+
+/*!
+ * @brief set up orthographic projection matrix with a left-hand coordinate
+ *        system and a clip-space of [0, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_lh_zo(float left,    float right,
+                float bottom,  float top,
+                float nearZ, float farZ,
+                mat4  dest) {
+  float rl, tb, fn;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+
+  dest[0][0] = 2.0f * rl;
+  dest[1][1] = 2.0f * tb;
+  dest[2][2] =-fn;
+  dest[3][0] =-(right  + left)    * rl;
+  dest[3][1] =-(top    + bottom)  * tb;
+  dest[3][2] = nearZ * fn;
+  dest[3][3] = 1.0f;
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box   AABB
+ * @param[out] dest  result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_lh_zo(vec3 box[2], mat4 dest) {
+  glm_ortho_lh_zo(box[0][0],  box[1][0],
+                  box[0][1],  box[1][1],
+                 -box[1][2], -box[0][2],
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_p_lh_zo(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_lh_zo(box[0][0] - padding,    box[1][0] + padding,
+                  box[0][1] - padding,    box[1][1] + padding,
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding for near and far
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_pz_lh_zo(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_lh_zo(box[0][0],              box[1][0],
+                  box[0][1],              box[1][1],
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up unit orthographic projection matrix
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * @param[in]  aspect aspect ration ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_lh_zo(float aspect, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_lh_zo(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
+    return;
+  }
+
+  aspect = 1.0f / aspect;
+
+  glm_ortho_lh_zo(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix with given CUBE size
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[in]  size   cube size
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_s_lh_zo(float aspect, float size, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_lh_zo(-size * aspect,
+                     size * aspect,
+                    -size,
+                     size,
+                    -size - 100.0f,
+                     size + 100.0f,
+                     dest);
+    return;
+  }
+
+  glm_ortho_lh_zo(-size,
+                   size,
+                  -size / aspect,
+                   size / aspect,
+                  -size - 100.0f,
+                   size + 100.0f,
+                   dest);
+}
+
+#endif /*cglm_ortho_lh_zo_h*/
--- a/include/cglm/clipspace/ortho_rh_no.h
+++ b/include/cglm/clipspace/ortho_rh_no.h
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_ortho_rh_no(float left,    float right,
+                                    float bottom,  float top,
+                                    float nearZ, float farZ,
+                                    mat4  dest)
+   CGLM_INLINE void glm_ortho_aabb_rh_no(vec3 box[2], mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_p_rh_no(vec3 box[2],
+                                           float padding,
+                                           mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_pz_rh_no(vec3 box[2],
+                                            float padding,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_rh_no(float aspect,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_s_rh_no(float aspect,
+                                              float size,
+                                              mat4 dest)
+ */
+
+#ifndef cglm_ortho_rh_no_h
+#define cglm_ortho_rh_no_h
+
+#include "../common.h"
+#include "../plane.h"
+#include "../mat4.h"
+
+/*!
+ * @brief set up orthographic projection matrix
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_rh_no(float left,    float right,
+                float bottom,  float top,
+                float nearZ, float farZ,
+                mat4  dest) {
+  float rl, tb, fn;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+
+  dest[0][0] = 2.0f * rl;
+  dest[1][1] = 2.0f * tb;
+  dest[2][2] = 2.0f * fn;
+  dest[3][0] =-(right  + left)    * rl;
+  dest[3][1] =-(top    + bottom)  * tb;
+  dest[3][2] = (farZ + nearZ) * fn;
+  dest[3][3] = 1.0f;
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box   AABB
+ * @param[out] dest  result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_rh_no(vec3 box[2], mat4 dest) {
+  glm_ortho_rh_no(box[0][0],  box[1][0],
+                  box[0][1],  box[1][1],
+                 -box[1][2], -box[0][2],
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_p_rh_no(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_rh_no(box[0][0] - padding,    box[1][0] + padding,
+                  box[0][1] - padding,    box[1][1] + padding,
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding for near and far
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_pz_rh_no(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_rh_no(box[0][0],              box[1][0],
+                  box[0][1],              box[1][1],
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up unit orthographic projection matrix
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  aspect aspect ration ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_rh_no(float aspect, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_rh_no(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
+    return;
+  }
+
+  aspect = 1.0f / aspect;
+
+  glm_ortho_rh_no(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix with given CUBE size
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[in]  size   cube size
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_s_rh_no(float aspect, float size, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_rh_no(-size * aspect,
+                     size * aspect,
+                    -size,
+                     size,
+                    -size - 100.0f,
+                     size + 100.0f,
+                     dest);
+    return;
+  }
+
+  glm_ortho_rh_no(-size,
+                   size,
+                  -size / aspect,
+                   size / aspect,
+                  -size - 100.0f,
+                   size + 100.0f,
+                   dest);
+}
+
+#endif /*cglm_ortho_rh_no_h*/
--- a/include/cglm/clipspace/ortho_rh_zo.h
+++ b/include/cglm/clipspace/ortho_rh_zo.h
@@ -0,0 +1,181 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_ortho_rh_zo(float left,    float right,
+                                    float bottom,  float top,
+                                    float nearZ, float farZ,
+                                    mat4  dest)
+   CGLM_INLINE void glm_ortho_aabb_rh_zo(vec3 box[2], mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_p_rh_zo(vec3 box[2],
+                                           float padding,
+                                           mat4 dest)
+   CGLM_INLINE void glm_ortho_aabb_pz_rh_zo(vec3 box[2],
+                                            float padding,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_rh_zo(float aspect,
+                                            mat4 dest)
+   CGLM_INLINE void glm_ortho_default_s_rh_zo(float aspect,
+                                              float size,
+                                              mat4 dest)
+ */
+
+#ifndef cglm_ortho_rh_zo_h
+#define cglm_ortho_rh_zo_h
+
+#include "../common.h"
+#include "../plane.h"
+#include "../mat4.h"
+
+/*!
+ * @brief set up orthographic projection matrix with a right-hand coordinate
+ *        system and a clip-space of [0, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_rh_zo(float left,    float right,
+                float bottom,  float top,
+                float nearZ, float farZ,
+                mat4  dest) {
+  float rl, tb, fn;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+
+  dest[0][0] = 2.0f * rl;
+  dest[1][1] = 2.0f * tb;
+  dest[2][2] = fn;
+  dest[3][0] =-(right  + left)    * rl;
+  dest[3][1] =-(top    + bottom)  * tb;
+  dest[3][2] = nearZ * fn;
+  dest[3][3] = 1.0f;
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a right-hand coordinate system and a clip-space with depth
+ *        values from zero to one.
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box   AABB
+ * @param[out] dest  result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_rh_zo(vec3 box[2], mat4 dest) {
+  glm_ortho_rh_zo(box[0][0],  box[1][0],
+                  box[0][1],  box[1][1],
+                 -box[1][2], -box[0][2],
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a right-hand coordinate system and a clip-space with depth
+ *        values from zero to one.
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_p_rh_zo(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_rh_zo(box[0][0] - padding,    box[1][0] + padding,
+                  box[0][1] - padding,    box[1][1] + padding,
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix using bounding box
+ *        with a right-hand coordinate system and a clip-space with depth
+ *        values from zero to one.
+ *
+ * bounding box (AABB) must be in view space
+ *
+ * @param[in]  box     AABB
+ * @param[in]  padding padding for near and far
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_aabb_pz_rh_zo(vec3 box[2], float padding, mat4 dest) {
+  glm_ortho_rh_zo(box[0][0],              box[1][0],
+                  box[0][1],              box[1][1],
+                -(box[1][2] + padding), -(box[0][2] - padding),
+                  dest);
+}
+
+/*!
+ * @brief set up unit orthographic projection matrix with a right-hand
+ *        coordinate system and a clip-space of [0, 1].
+ *
+ * @param[in]  aspect aspect ration ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_rh_zo(float aspect, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_rh_zo(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
+    return;
+  }
+
+  aspect = 1.0f / aspect;
+
+  glm_ortho_rh_zo(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
+}
+
+/*!
+ * @brief set up orthographic projection matrix with given CUBE size
+ *        with a right-hand coordinate system and a clip-space with depth
+ *        values from zero to one.
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[in]  size   cube size
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_ortho_default_s_rh_zo(float aspect, float size, mat4 dest) {
+  if (aspect >= 1.0f) {
+    glm_ortho_rh_zo(-size * aspect,
+                     size * aspect,
+                    -size,
+                     size,
+                    -size - 100.0f,
+                     size + 100.0f,
+                     dest);
+    return;
+  }
+
+  glm_ortho_rh_zo(-size,
+                   size,
+                  -size / aspect,
+                   size / aspect,
+                  -size - 100.0f,
+                   size + 100.0f,
+                   dest);
+}
+
+#endif /*cglm_ortho_rh_zo_h*/
--- a/include/cglm/clipspace/persp.h
+++ b/include/cglm/clipspace/persp.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void  glm_persp_decomp_far(mat4 proj, float *farZ)
+   CGLM_INLINE float glm_persp_fovy(mat4 proj)
+   CGLM_INLINE float glm_persp_aspect(mat4 proj)
+   CGLM_INLINE void  glm_persp_sizes(mat4 proj, float fovy, vec4 dest)
+ */
+
+#ifndef cglm_persp_h
+#define cglm_persp_h
+
+#include "../common.h"
+#include "../plane.h"
+#include "../mat4.h"
+
+/*!
+ * @brief returns field of view angle along the Y-axis (in radians)
+ *
+ * if you need to degrees, use glm_deg to convert it or use this:
+ * fovy_deg = glm_deg(glm_persp_fovy(projMatrix))
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_fovy(mat4 proj) {
+  return 2.0f * atanf(1.0f / proj[1][1]);
+}
+
+/*!
+ * @brief returns aspect ratio of perspective projection
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_aspect(mat4 proj) {
+  return proj[1][1] / proj[0][0];
+}
+
+#endif /* cglm_persp_h */
--- a/include/cglm/clipspace/persp_lh_no.h
+++ b/include/cglm/clipspace/persp_lh_no.h
@@ -0,0 +1,395 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_frustum_lh_no(float left,    float right,
+                                       float bottom,  float top,
+                                       float nearZ, float farZ,
+                                       mat4  dest)
+   CGLM_INLINE void glm_perspective_lh_no(float fovy,
+                                          float aspect,
+                                          float nearZ,
+                                          float farZ,
+                                          mat4  dest)
+   CGLM_INLINE void glm_perspective_default_lh_no(float aspect, mat4 dest)
+   CGLM_INLINE void glm_perspective_resize_lh_no(float aspect, mat4 proj)
+   CGLM_INLINE void glm_persp_move_far_lh_no(mat4 proj,
+                                             float deltaFar)
+   CGLM_INLINE void glm_persp_decomp_lh_no(mat4 proj,
+                                           float * __restrict nearZ,
+                                           float * __restrict farZ,
+                                           float * __restrict top,
+                                           float * __restrict bottom,
+                                           float * __restrict left,
+                                           float * __restrict right)
+  CGLM_INLINE void glm_persp_decompv_lh_no(mat4 proj,
+                                           float dest[6])
+  CGLM_INLINE void glm_persp_decomp_x_lh_no(mat4 proj,
+                                            float * __restrict left,
+                                            float * __restrict right)
+  CGLM_INLINE void glm_persp_decomp_y_lh_no(mat4 proj,
+                                            float * __restrict top,
+                                            float * __restrict bottom)
+  CGLM_INLINE void glm_persp_decomp_z_lh_no(mat4 proj,
+                                            float * __restrict nearZ,
+                                            float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_far_lh_no(mat4 proj, float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_near_lh_no(mat4 proj, float * __restrict nearZ)
+  CGLM_INLINE void glm_persp_sizes_lh_no(mat4 proj, float fovy, vec4 dest)
+ */
+
+#ifndef cglm_persp_lh_no_h
+#define cglm_persp_lh_no_h
+
+#include "../common.h"
+#include "persp.h"
+
+/*!
+ * @brief set up perspective peprojection matrix
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_frustum_lh_no(float left,    float right,
+                  float bottom,  float top,
+                  float nearZ, float farZ,
+                  mat4  dest) {
+  float rl, tb, fn, nv;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+  nv = 2.0f * nearZ;
+
+  dest[0][0] = nv * rl;
+  dest[1][1] = nv * tb;
+  dest[2][0] = (right  + left)    * rl;
+  dest[2][1] = (top    + bottom)  * tb;
+  dest[2][2] =-(farZ + nearZ) * fn;
+  dest[2][3] = 1.0f;
+  dest[3][2] = farZ * nv * fn;
+}
+
+/*!
+ * @brief set up perspective projection matrix
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  fovy    field of view angle
+ * @param[in]  aspect  aspect ratio ( width / height )
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping planes
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_lh_no(float fovy,
+                      float aspect,
+                      float nearZ,
+                      float farZ,
+                      mat4  dest) {
+  float f, fn;
+
+  glm_mat4_zero(dest);
+
+  f  = 1.0f / tanf(fovy * 0.5f);
+  fn = 1.0f / (nearZ - farZ);
+
+  dest[0][0] = f / aspect;
+  dest[1][1] = f;
+  dest[2][2] =-(nearZ + farZ) * fn;
+  dest[2][3] = 1.0f;
+  dest[3][2] = 2.0f * nearZ * farZ * fn;
+
+}
+
+/*!
+ * @brief set up perspective projection matrix with default near/far
+ *        and angle values with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_default_lh_no(float aspect, mat4 dest) {
+  glm_perspective_lh_no(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
+}
+
+/*!
+ * @brief resize perspective matrix by aspect ratio ( width / height )
+ *        this makes very easy to resize proj matrix when window /viewport
+ *        resized with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]      aspect aspect ratio ( width / height )
+ * @param[in, out] proj   perspective projection matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_resize_lh_no(float aspect, mat4 proj) {
+  if (proj[0][0] == 0.0f)
+    return;
+
+  proj[0][0] = proj[1][1] / aspect;
+}
+
+/*!
+ * @brief extend perspective projection matrix's far distance
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * 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_lh_no(mat4 proj, float deltaFar) {
+  float fn, farZ, nearZ, p22, p32;
+
+  p22        = -proj[2][2];
+  p32        = proj[3][2];
+
+  nearZ    = p32 / (p22 - 1.0f);
+  farZ     = p32 / (p22 + 1.0f) + deltaFar;
+  fn         = 1.0f / (nearZ - farZ);
+
+  proj[2][2] = -(farZ + nearZ) * fn;
+  proj[3][2] = 2.0f * nearZ * farZ * fn;
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ * @param[out] top     top
+ * @param[out] bottom  bottom
+ * @param[out] left    left
+ * @param[out] right   right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_lh_no(mat4 proj,
+                       float * __restrict nearZ, float * __restrict farZ,
+                       float * __restrict top,   float * __restrict bottom,
+                       float * __restrict left,  float * __restrict right) {
+  float m00, m11, m20, m21, m22, m32, n, f;
+  float n_m11, n_m00;
+
+  m00 = proj[0][0];
+  m11 = proj[1][1];
+  m20 = proj[2][0];
+  m21 = proj[2][1];
+  m22 =-proj[2][2];
+  m32 = proj[3][2];
+
+  n = m32 / (m22 - 1.0f);
+  f = m32 / (m22 + 1.0f);
+
+  n_m11 = n / m11;
+  n_m00 = n / m00;
+
+  *nearZ = n;
+  *farZ  = f;
+  *bottom  = n_m11 * (m21 - 1.0f);
+  *top     = n_m11 * (m21 + 1.0f);
+  *left    = n_m00 * (m20 - 1.0f);
+  *right   = n_m00 * (m20 + 1.0f);
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        this makes easy to get all values at once
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] dest   array
+ */
+CGLM_INLINE
+void
+glm_persp_decompv_lh_no(mat4 proj, float dest[6]) {
+  glm_persp_decomp_lh_no(proj, &dest[0], &dest[1], &dest[2],
+                               &dest[3], &dest[4], &dest[5]);
+}
+
+/*!
+ * @brief decomposes left and right values of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        x stands for x axis (left / right axis)
+ *
+ * @param[in]  proj  perspective projection matrix
+ * @param[out] left  left
+ * @param[out] right right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_x_lh_no(mat4 proj,
+                         float * __restrict left,
+                         float * __restrict right) {
+  float nearZ, m20, m00, m22;
+
+  m00 = proj[0][0];
+  m20 = proj[2][0];
+  m22 =-proj[2][2];
+
+  nearZ = proj[3][2] / (m22 - 1.0f);
+  *left   = nearZ * (m20 - 1.0f) / m00;
+  *right  = nearZ * (m20 + 1.0f) / m00;
+}
+
+/*!
+ * @brief decomposes top and bottom values of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        y stands for y axis (top / botom axis)
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] top    top
+ * @param[out] bottom bottom
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_y_lh_no(mat4 proj,
+                         float * __restrict top,
+                         float * __restrict bottom) {
+  float nearZ, m21, m11, m22;
+
+  m21 = proj[2][1];
+  m11 = proj[1][1];
+  m22 =-proj[2][2];
+
+  nearZ = proj[3][2] / (m22 - 1.0f);
+  *bottom = nearZ * (m21 - 1.0f) / m11;
+  *top    = nearZ * (m21 + 1.0f) / m11;
+}
+
+/*!
+ * @brief decomposes near and far values of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        z stands for z axis (near / far axis)
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_z_lh_no(mat4 proj,
+                         float * __restrict nearZ,
+                         float * __restrict farZ) {
+  float m32, m22;
+
+  m32 = proj[3][2];
+  m22 =-proj[2][2];
+
+  *nearZ = m32 / (m22 - 1.0f);
+  *farZ  = m32 / (m22 + 1.0f);
+}
+
+/*!
+ * @brief decomposes far value of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] farZ   far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_far_lh_no(mat4 proj, float * __restrict farZ) {
+  *farZ = proj[3][2] / (-proj[2][2] + 1.0f);
+}
+
+/*!
+ * @brief decomposes near value of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_near_lh_no(mat4 proj, float * __restrict nearZ) {
+  *nearZ = proj[3][2] / (-proj[2][2] - 1.0f);
+}
+
+/*!
+ * @brief returns sizes of near and far planes of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj perspective projection matrix
+ * @param[in]  fovy fovy (see brief)
+ * @param[out] dest sizes order: [Wnear, Hnear, Wfar, Hfar]
+ */
+CGLM_INLINE
+void
+glm_persp_sizes_lh_no(mat4 proj, float fovy, vec4 dest) {
+  float t, a, nearZ, farZ;
+
+  t = 2.0f * tanf(fovy * 0.5f);
+  a = glm_persp_aspect(proj);
+
+  glm_persp_decomp_z_lh_no(proj, &nearZ, &farZ);
+
+  dest[1]  = t * nearZ;
+  dest[3]  = t * farZ;
+  dest[0]  = a * dest[1];
+  dest[2]  = a * dest[3];
+}
+
+/*!
+ * @brief returns field of view angle along the Y-axis (in radians)
+ *        with a left-hand coordinate system and a clip-space of [-1, 1].
+ *
+ * if you need to degrees, use glm_deg to convert it or use this:
+ * fovy_deg = glm_deg(glm_persp_fovy(projMatrix))
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_fovy_lh_no(mat4 proj) {
+  return glm_persp_fovy(proj);
+}
+
+/*!
+ * @brief returns aspect ratio of perspective projection
+ *        with a left-hand coordinate system and a clip-space of [-1, 1].
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_aspect_lh_no(mat4 proj) {
+  return glm_persp_aspect(proj);
+}
+
+#endif /*cglm_cam_lh_no_h*/
--- a/include/cglm/clipspace/persp_lh_zo.h
+++ b/include/cglm/clipspace/persp_lh_zo.h
@@ -0,0 +1,387 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_frustum_lh_zo(float left,    float right,
+                                      float bottom,  float top,
+                                      float nearZ, float farZ,
+                                      mat4  dest)
+   CGLM_INLINE void glm_perspective_lh_zo(float fovy,
+                                          float aspect,
+                                          float nearZ,
+                                          float farZ,
+                                          mat4  dest)
+   CGLM_INLINE void glm_perspective_default_lh_zo(float aspect, mat4 dest)
+   CGLM_INLINE void glm_perspective_resize_lh_zo(float aspect, mat4 proj)
+   CGLM_INLINE void glm_persp_move_far_lh_zo(mat4 proj,
+                                             float deltaFar)
+   CGLM_INLINE void glm_persp_decomp_lh_zo(mat4 proj,
+                                           float * __restrict nearZ,
+                                           float * __restrict farZ,
+                                           float * __restrict top,
+                                           float * __restrict bottom,
+                                           float * __restrict left,
+                                           float * __restrict right)
+  CGLM_INLINE void glm_persp_decompv_lh_zo(mat4 proj,
+                                           float dest[6])
+  CGLM_INLINE void glm_persp_decomp_x_lh_zo(mat4 proj,
+                                            float * __restrict left,
+                                            float * __restrict right)
+  CGLM_INLINE void glm_persp_decomp_y_lh_zo(mat4 proj,
+                                            float * __restrict top,
+                                            float * __restrict bottom)
+  CGLM_INLINE void glm_persp_decomp_z_lh_zo(mat4 proj,
+                                            float * __restrict nearZ,
+                                            float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_far_lh_zo(mat4 proj, float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_near_lh_zo(mat4 proj, float * __restrict nearZ)
+  CGLM_INLINE void glm_persp_sizes_lh_zo(mat4 proj, float fovy, vec4 dest)
+ */
+
+#ifndef cglm_persp_lh_zo_h
+#define cglm_persp_lh_zo_h
+
+#include "../common.h"
+#include "persp.h"
+
+/*!
+ * @brief set up perspective peprojection matrix with a left-hand coordinate
+ *        system and a clip-space of [0, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_frustum_lh_zo(float left,    float right,
+                  float bottom,  float top,
+                  float nearZ, float farZ,
+                  mat4  dest) {
+  float rl, tb, fn, nv;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+  nv = 2.0f * nearZ;
+
+  dest[0][0] = nv * rl;
+  dest[1][1] = nv * tb;
+  dest[2][0] = (right  + left)    * rl;
+  dest[2][1] = (top    + bottom)  * tb;
+  dest[2][2] =-farZ * fn;
+  dest[2][3] = 1.0f;
+  dest[3][2] = farZ * nearZ * fn;
+}
+
+/*!
+ * @brief set up perspective projection matrix with a left-hand coordinate
+ * system and a clip-space of [0, 1].
+ *
+ * @param[in]  fovy    field of view angle
+ * @param[in]  aspect  aspect ratio ( width / height )
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping planes
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_lh_zo(float fovy,
+                      float aspect,
+                      float nearZ,
+                      float farZ,
+                      mat4  dest) {
+  float f, fn;
+
+  glm_mat4_zero(dest);
+
+  f  = 1.0f / tanf(fovy * 0.5f);
+  fn = 1.0f / (nearZ - farZ);
+
+  dest[0][0] = f / aspect;
+  dest[1][1] = f;
+  dest[2][2] =-farZ * fn;
+  dest[2][3] = 1.0f;
+  dest[3][2] = nearZ * farZ * fn;
+}
+
+/*!
+ * @brief extend perspective projection matrix's far distance with a
+ *        left-hand coordinate system and a clip-space with depth values
+ *        from zero to one.
+ *
+ * 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_lh_zo(mat4 proj, float deltaFar) {
+  float fn, farZ, nearZ, p22, p32;
+
+  p22        = -proj[2][2];
+  p32        = proj[3][2];
+
+  nearZ    = p32 / p22;
+  farZ     = p32 / (p22 + 1.0f) + deltaFar;
+  fn         = 1.0f / (nearZ - farZ);
+
+  proj[2][2] = -farZ * fn;
+  proj[3][2] = nearZ * farZ * fn;
+}
+
+/*!
+ * @brief set up perspective projection matrix with default near/far
+ *        and angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_default_lh_zo(float aspect, mat4 dest) {
+  glm_perspective_lh_zo(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
+}
+
+/*!
+ * @brief resize perspective matrix by aspect ratio ( width / height )
+ *        this makes very easy to resize proj matrix when window /viewport
+ *        reized
+ *
+ * @param[in]      aspect aspect ratio ( width / height )
+ * @param[in, out] proj   perspective projection matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_resize_lh_zo(float aspect, mat4 proj) {
+  if (proj[0][0] == 0.0f)
+    return;
+
+  proj[0][0] = proj[1][1] / aspect;
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ * @param[out] top     top
+ * @param[out] bottom  bottom
+ * @param[out] left    left
+ * @param[out] right   right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_lh_zo(mat4 proj,
+                    float * __restrict nearZ, float * __restrict farZ,
+                    float * __restrict top,     float * __restrict bottom,
+                    float * __restrict left,    float * __restrict right) {
+  float m00, m11, m20, m21, m22, m32, n, f;
+  float n_m11, n_m00;
+
+  m00 = proj[0][0];
+  m11 = proj[1][1];
+  m20 = proj[2][0];
+  m21 = proj[2][1];
+  m22 =-proj[2][2];
+  m32 = proj[3][2];
+
+  n = m32 / m22;
+  f = m32 / (m22 + 1.0f);
+
+  n_m11 = n / m11;
+  n_m00 = n / m00;
+
+  *nearZ = n;
+  *farZ  = f;
+  *bottom  = n_m11 * (m21 - 1.0f);
+  *top     = n_m11 * (m21 + 1.0f);
+  *left    = n_m00 * (m20 - 1.0f);
+  *right   = n_m00 * (m20 + 1.0f);
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *        this makes easy to get all values at once
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] dest   array
+ */
+CGLM_INLINE
+void
+glm_persp_decompv_lh_zo(mat4 proj, float dest[6]) {
+  glm_persp_decomp_lh_zo(proj, &dest[0], &dest[1], &dest[2],
+                               &dest[3], &dest[4], &dest[5]);
+}
+
+/*!
+ * @brief decomposes left and right values of perspective projection (ZO).
+ *        x stands for x axis (left / right axis)
+ *
+ * @param[in]  proj  perspective projection matrix
+ * @param[out] left  left
+ * @param[out] right right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_x_lh_zo(mat4 proj,
+                         float * __restrict left,
+                         float * __restrict right) {
+  float nearZ, m20, m00;
+
+  m00 = proj[0][0];
+  m20 = proj[2][0];
+
+  nearZ = proj[3][2] / (proj[3][3]);
+  *left   = nearZ * (m20 - 1.0f) / m00;
+  *right  = nearZ * (m20 + 1.0f) / m00;
+}
+
+/*!
+ * @brief decomposes top and bottom values of perspective projection
+ *        with angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *        y stands for y axis (top / bottom axis)
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] top    top
+ * @param[out] bottom bottom
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_y_lh_zo(mat4 proj,
+                         float * __restrict top,
+                         float * __restrict bottom) {
+  float nearZ, m21, m11;
+
+  m21 = proj[2][1];
+  m11 = proj[1][1];
+
+  nearZ = proj[3][2] / (proj[3][3]);
+  *bottom = nearZ * (m21 - 1) / m11;
+  *top    = nearZ * (m21 + 1) / m11;
+}
+
+/*!
+ * @brief decomposes near and far values of perspective projection
+ *        with angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *        z stands for z axis (near / far axis)
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_z_lh_zo(mat4 proj,
+                         float * __restrict nearZ,
+                         float * __restrict farZ) {
+  float m32, m22;
+
+  m32 = proj[3][2];
+  m22 = -proj[2][2];
+
+  *nearZ = m32 / m22;
+  *farZ  = m32 / (m22 + 1.0f);
+}
+
+/*!
+ * @brief decomposes far value of perspective projection
+ *        with angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] farZ   far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_far_lh_zo(mat4 proj, float * __restrict farZ) {
+  *farZ = proj[3][2] / (-proj[2][2] + 1.0f);
+}
+
+/*!
+ * @brief decomposes near value of perspective projection
+ *        with angle values with a left-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_near_lh_zo(mat4 proj, float * __restrict nearZ) {
+  *nearZ = proj[3][2] / -proj[2][2];
+}
+
+/*!
+ * @brief returns sizes of near and far planes of perspective projection
+ *        with a left-hand coordinate system and a
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj perspective projection matrix
+ * @param[in]  fovy fovy (see brief)
+ * @param[out] dest sizes order: [Wnear, Hnear, Wfar, Hfar]
+ */
+CGLM_INLINE
+void
+glm_persp_sizes_lh_zo(mat4 proj, float fovy, vec4 dest) {
+  float t, a, nearZ, farZ;
+
+  t = 2.0f * tanf(fovy * 0.5f);
+  a = glm_persp_aspect(proj);
+
+  glm_persp_decomp_z_lh_zo(proj, &nearZ, &farZ);
+
+  dest[1]  = t * nearZ;
+  dest[3]  = t * farZ;
+  dest[0]  = a * dest[1];
+  dest[2]  = a * dest[3];
+}
+
+/*!
+ * @brief returns field of view angle along the Y-axis (in radians)
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * if you need to degrees, use glm_deg to convert it or use this:
+ * fovy_deg = glm_deg(glm_persp_fovy(projMatrix))
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_fovy_lh_zo(mat4 proj) {
+  return glm_persp_fovy(proj);
+}
+
+/*!
+ * @brief returns aspect ratio of perspective projection
+ *        with a left-hand coordinate system and a clip-space of [0, 1].
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_aspect_lh_zo(mat4 proj) {
+  return glm_persp_aspect(proj);
+}
+
+#endif /*cglm_persp_lh_zo_h*/
--- a/include/cglm/clipspace/persp_rh_no.h
+++ b/include/cglm/clipspace/persp_rh_no.h
@@ -0,0 +1,395 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_frustum_rh_no(float left,    float right,
+                                      float bottom,  float top,
+                                      float nearZ, float farZ,
+                                      mat4  dest)
+   CGLM_INLINE void glm_perspective_rh_no(float fovy,
+                                          float aspect,
+                                          float nearZ,
+                                          float farZ,
+                                          mat4  dest)
+   CGLM_INLINE void glm_perspective_default_rh_no(float aspect, mat4 dest)
+   CGLM_INLINE void glm_perspective_resize_rh_no(float aspect, mat4 proj)
+   CGLM_INLINE void glm_persp_move_far_rh_no(mat4 proj,
+                                             float deltaFar)
+   CGLM_INLINE void glm_persp_decomp_rh_no(mat4 proj,
+                                           float * __restrict nearZ,
+                                           float * __restrict farZ,
+                                           float * __restrict top,
+                                           float * __restrict bottom,
+                                           float * __restrict left,
+                                           float * __restrict right)
+  CGLM_INLINE void glm_persp_decompv_rh_no(mat4 proj,
+                                           float dest[6])
+  CGLM_INLINE void glm_persp_decomp_x_rh_no(mat4 proj,
+                                            float * __restrict left,
+                                            float * __restrict right)
+  CGLM_INLINE void glm_persp_decomp_y_rh_no(mat4 proj,
+                                            float * __restrict top,
+                                            float * __restrict bottom)
+  CGLM_INLINE void glm_persp_decomp_z_rh_no(mat4 proj,
+                                            float * __restrict nearZ,
+                                            float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_far_rh_no(mat4 proj, float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_near_rh_no(mat4 proj, float * __restrict nearZ)
+  CGLM_INLINE void glm_persp_sizes_rh_no(mat4 proj, float fovy, vec4 dest)
+ */
+
+#ifndef cglm_persp_rh_no_h
+#define cglm_persp_rh_no_h
+
+#include "../common.h"
+#include "persp.h"
+
+/*!
+ * @brief set up perspective peprojection matrix
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_frustum_rh_no(float left,    float right,
+                  float bottom,  float top,
+                  float nearZ, float farZ,
+                  mat4  dest) {
+  float rl, tb, fn, nv;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+  nv = 2.0f * nearZ;
+
+  dest[0][0] = nv * rl;
+  dest[1][1] = nv * tb;
+  dest[2][0] = (right  + left)    * rl;
+  dest[2][1] = (top    + bottom)  * tb;
+  dest[2][2] = (farZ + nearZ) * fn;
+  dest[2][3] =-1.0f;
+  dest[3][2] = farZ * nv * fn;
+}
+
+/*!
+ * @brief set up perspective projection matrix
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  fovy    field of view angle
+ * @param[in]  aspect  aspect ratio ( width / height )
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping planes
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_rh_no(float fovy,
+                      float aspect,
+                      float nearZ,
+                      float farZ,
+                      mat4  dest) {
+  float f, fn;
+
+  glm_mat4_zero(dest);
+
+  f  = 1.0f / tanf(fovy * 0.5f);
+  fn = 1.0f / (nearZ - farZ);
+
+  dest[0][0] = f / aspect;
+  dest[1][1] = f;
+  dest[2][2] = (nearZ + farZ) * fn;
+  dest[2][3] =-1.0f;
+  dest[3][2] = 2.0f * nearZ * farZ * fn;
+
+}
+
+/*!
+ * @brief set up perspective projection matrix with default near/far
+ *        and angle values with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_default_rh_no(float aspect, mat4 dest) {
+  glm_perspective_rh_no(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
+}
+
+/*!
+ * @brief resize perspective matrix by aspect ratio ( width / height )
+ *        this makes very easy to resize proj matrix when window /viewport
+ *        resized with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]      aspect aspect ratio ( width / height )
+ * @param[in, out] proj   perspective projection matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_resize_rh_no(float aspect, mat4 proj) {
+  if (proj[0][0] == 0.0f)
+    return;
+
+  proj[0][0] = proj[1][1] / aspect;
+}
+
+/*!
+ * @brief extend perspective projection matrix's far distance
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * 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_rh_no(mat4 proj, float deltaFar) {
+  float fn, farZ, nearZ, p22, p32;
+
+  p22        = proj[2][2];
+  p32        = proj[3][2];
+
+  nearZ    = p32 / (p22 - 1.0f);
+  farZ     = p32 / (p22 + 1.0f) + deltaFar;
+  fn         = 1.0f / (nearZ - farZ);
+
+  proj[2][2] = (farZ + nearZ) * fn;
+  proj[3][2] = 2.0f * nearZ * farZ * fn;
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ * @param[out] top     top
+ * @param[out] bottom  bottom
+ * @param[out] left    left
+ * @param[out] right   right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_rh_no(mat4 proj,
+                       float * __restrict nearZ, float * __restrict farZ,
+                       float * __restrict top,     float * __restrict bottom,
+                       float * __restrict left,    float * __restrict right) {
+  float m00, m11, m20, m21, m22, m32, n, f;
+  float n_m11, n_m00;
+
+  m00 = proj[0][0];
+  m11 = proj[1][1];
+  m20 = proj[2][0];
+  m21 = proj[2][1];
+  m22 = proj[2][2];
+  m32 = proj[3][2];
+
+  n = m32 / (m22 - 1.0f);
+  f = m32 / (m22 + 1.0f);
+
+  n_m11 = n / m11;
+  n_m00 = n / m00;
+
+  *nearZ = n;
+  *farZ  = f;
+  *bottom  = n_m11 * (m21 - 1.0f);
+  *top     = n_m11 * (m21 + 1.0f);
+  *left    = n_m00 * (m20 - 1.0f);
+  *right   = n_m00 * (m20 + 1.0f);
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        this makes easy to get all values at once
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] dest   array
+ */
+CGLM_INLINE
+void
+glm_persp_decompv_rh_no(mat4 proj, float dest[6]) {
+  glm_persp_decomp_rh_no(proj, &dest[0], &dest[1], &dest[2],
+                               &dest[3], &dest[4], &dest[5]);
+}
+
+/*!
+ * @brief decomposes left and right values of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        x stands for x axis (left / right axis)
+ *
+ * @param[in]  proj  perspective projection matrix
+ * @param[out] left  left
+ * @param[out] right right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_x_rh_no(mat4 proj,
+                         float * __restrict left,
+                         float * __restrict right) {
+  float nearZ, m20, m00, m22;
+
+  m00 = proj[0][0];
+  m20 = proj[2][0];
+  m22 = proj[2][2];
+
+  nearZ = proj[3][2] / (m22 - 1.0f);
+  *left   = nearZ * (m20 - 1.0f) / m00;
+  *right  = nearZ * (m20 + 1.0f) / m00;
+}
+
+/*!
+ * @brief decomposes top and bottom values of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        y stands for y axis (top / botom axis)
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] top    top
+ * @param[out] bottom bottom
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_y_rh_no(mat4 proj,
+                         float * __restrict top,
+                         float * __restrict bottom) {
+  float nearZ, m21, m11, m22;
+
+  m21 = proj[2][1];
+  m11 = proj[1][1];
+  m22 = proj[2][2];
+
+  nearZ = proj[3][2] / (m22 - 1.0f);
+  *bottom = nearZ * (m21 - 1.0f) / m11;
+  *top    = nearZ * (m21 + 1.0f) / m11;
+}
+
+/*!
+ * @brief decomposes near and far values of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *        z stands for z axis (near / far axis)
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_z_rh_no(mat4 proj,
+                      float * __restrict nearZ,
+                      float * __restrict farZ) {
+  float m32, m22;
+
+  m32 = proj[3][2];
+  m22 = proj[2][2];
+
+  *nearZ = m32 / (m22 - 1.0f);
+  *farZ  = m32 / (m22 + 1.0f);
+}
+
+/*!
+ * @brief decomposes far value of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] farZ   far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_far_rh_no(mat4 proj, float * __restrict farZ) {
+  *farZ = proj[3][2] / (proj[2][2] + 1.0f);
+}
+
+/*!
+ * @brief decomposes near value of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ near
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_near_rh_no(mat4 proj, float * __restrict nearZ) {
+  *nearZ = proj[3][2] / (proj[2][2] - 1.0f);
+}
+
+/*!
+ * @brief returns sizes of near and far planes of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [-1, 1].
+ *
+ * @param[in]  proj perspective projection matrix
+ * @param[in]  fovy fovy (see brief)
+ * @param[out] dest sizes order: [Wnear, Hnear, Wfar, Hfar]
+ */
+CGLM_INLINE
+void
+glm_persp_sizes_rh_no(mat4 proj, float fovy, vec4 dest) {
+  float t, a, nearZ, farZ;
+
+  t = 2.0f * tanf(fovy * 0.5f);
+  a = glm_persp_aspect(proj);
+
+  glm_persp_decomp_z_rh_no(proj, &nearZ, &farZ);
+
+  dest[1]  = t * nearZ;
+  dest[3]  = t * farZ;
+  dest[0]  = a * dest[1];
+  dest[2]  = a * dest[3];
+}
+
+/*!
+ * @brief returns field of view angle along the Y-axis (in radians)
+ *        with a right-hand coordinate system and a clip-space of [-1, 1].
+ *
+ * if you need to degrees, use glm_deg to convert it or use this:
+ * fovy_deg = glm_deg(glm_persp_fovy(projMatrix))
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_fovy_rh_no(mat4 proj) {
+  return glm_persp_fovy(proj);
+}
+
+/*!
+ * @brief returns aspect ratio of perspective projection
+ *        with a right-hand coordinate system and a clip-space of [-1, 1].
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_aspect_rh_no(mat4 proj) {
+  return glm_persp_aspect(proj);
+}
+
+#endif /*cglm_cam_rh_no_h*/
--- a/include/cglm/clipspace/persp_rh_zo.h
+++ b/include/cglm/clipspace/persp_rh_zo.h
@@ -0,0 +1,389 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_frustum_rh_zo(float left,    float right,
+                                      float bottom,  float top,
+                                      float nearZ, float farZ,
+                                      mat4  dest)
+   CGLM_INLINE void glm_perspective_rh_zo(float fovy,
+                                          float aspect,
+                                          float nearZ,
+                                          float farZ,
+                                          mat4  dest)
+   CGLM_INLINE void glm_perspective_default_rh_zo(float aspect, mat4 dest)
+   CGLM_INLINE void glm_perspective_resize_rh_zo(float aspect, mat4 proj)
+   CGLM_INLINE void glm_persp_move_far_rh_zo(mat4 proj,
+                                             float deltaFar)
+   CGLM_INLINE void glm_persp_decomp_rh_zo(mat4 proj,
+                                           float * __restrict nearZ,
+                                           float * __restrict farZ,
+                                           float * __restrict top,
+                                           float * __restrict bottom,
+                                           float * __restrict left,
+                                           float * __restrict right)
+  CGLM_INLINE void glm_persp_decompv_rh_zo(mat4 proj,
+                                           float dest[6])
+  CGLM_INLINE void glm_persp_decomp_x_rh_zo(mat4 proj,
+                                            float * __restrict left,
+                                            float * __restrict right)
+  CGLM_INLINE void glm_persp_decomp_y_rh_zo(mat4 proj,
+                                            float * __restrict top,
+                                            float * __restrict bottom)
+  CGLM_INLINE void glm_persp_decomp_z_rh_zo(mat4 proj,
+                                            float * __restrict nearZ,
+                                            float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_far_rh_zo(mat4 proj, float * __restrict farZ)
+  CGLM_INLINE void glm_persp_decomp_near_rh_zo(mat4 proj, float * __restrict nearZ)
+  CGLM_INLINE void glm_persp_sizes_rh_zo(mat4 proj, float fovy, vec4 dest)
+ */
+
+#ifndef cglm_persp_rh_zo_h
+#define cglm_persp_rh_zo_h
+
+#include "../common.h"
+#include "persp.h"
+
+/*!
+ * @brief set up perspective peprojection matrix with a right-hand coordinate
+ *        system and a clip-space of [0, 1].
+ *
+ * @param[in]  left    viewport.left
+ * @param[in]  right   viewport.right
+ * @param[in]  bottom  viewport.bottom
+ * @param[in]  top     viewport.top
+ * @param[in]  nearZ   near clipping plane
+ * @param[in]  farZ    far clipping plane
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_frustum_rh_zo(float left,    float right,
+                  float bottom,  float top,
+                  float nearZ, float farZ,
+                  mat4  dest) {
+  float rl, tb, fn, nv;
+
+  glm_mat4_zero(dest);
+
+  rl = 1.0f / (right  - left);
+  tb = 1.0f / (top    - bottom);
+  fn =-1.0f / (farZ - nearZ);
+  nv = 2.0f * nearZ;
+
+  dest[0][0] = nv * rl;
+  dest[1][1] = nv * tb;
+  dest[2][0] = (right  + left)    * rl;
+  dest[2][1] = (top    + bottom)  * tb;
+  dest[2][2] = farZ * fn;
+  dest[2][3] =-1.0f;
+  dest[3][2] = farZ * nearZ * fn;
+}
+
+/*!
+ * @brief set up perspective projection matrix with a right-hand coordinate
+ *        system and a clip-space of [0, 1].
+ *
+ * @param[in]  fovy    field of view angle
+ * @param[in]  aspect  aspect ratio ( width / height )
+ * @param[in]  nearZ near clipping plane
+ * @param[in]  farZ  far clipping planes
+ * @param[out] dest    result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_rh_zo(float fovy,
+                      float aspect,
+                      float nearZ,
+                      float farZ,
+                      mat4  dest) {
+  float f, fn;
+
+  glm_mat4_zero(dest);
+
+  f  = 1.0f / tanf(fovy * 0.5f);
+  fn = 1.0f / (nearZ - farZ);
+
+  dest[0][0] = f / aspect;
+  dest[1][1] = f;
+  dest[2][2] = farZ * fn;
+  dest[2][3] =-1.0f;
+  dest[3][2] = nearZ * farZ * fn;
+}
+
+/*!
+ * @brief set up perspective projection matrix with default near/far
+ *        and angle values with a right-hand coordinate system and a
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  aspect aspect ratio ( width / height )
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_default_rh_zo(float aspect, mat4 dest) {
+  glm_perspective_rh_zo(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
+}
+
+/*!
+ * @brief resize perspective matrix by aspect ratio ( width / height )
+ *        this makes very easy to resize proj matrix when window /viewport
+ *        resized with a right-hand coordinate system and a clip-space of
+ *        [0, 1].
+ *
+ * @param[in]      aspect aspect ratio ( width / height )
+ * @param[in, out] proj   perspective projection matrix
+ */
+CGLM_INLINE
+void
+glm_perspective_resize_rh_zo(float aspect, mat4 proj) {
+  if (proj[0][0] == 0.0f)
+    return;
+
+  proj[0][0] = proj[1][1] / aspect;
+}
+
+/*!
+ * @brief extend perspective projection matrix's far distance with a
+ *        right-hand coordinate system and a clip-space of [0, 1].
+ *
+ * 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_rh_zo(mat4 proj, float deltaFar) {
+  float fn, farZ, nearZ, p22, p32;
+
+  p22        = proj[2][2];
+  p32        = proj[3][2];
+
+  nearZ    = p32 / p22;
+  farZ     = p32 / (p22 + 1.0f) + deltaFar;
+  fn         = 1.0f / (nearZ - farZ);
+
+  proj[2][2] = farZ * fn;
+  proj[3][2] = nearZ * farZ * fn;
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with angle values with a right-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ * @param[out] top     top
+ * @param[out] bottom  bottom
+ * @param[out] left    left
+ * @param[out] right   right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_rh_zo(mat4 proj,
+                    float * __restrict nearZ, float * __restrict farZ,
+                    float * __restrict top,     float * __restrict bottom,
+                    float * __restrict left,    float * __restrict right) {
+  float m00, m11, m20, m21, m22, m32, n, f;
+  float n_m11, n_m00;
+
+  m00 = proj[0][0];
+  m11 = proj[1][1];
+  m20 = proj[2][0];
+  m21 = proj[2][1];
+  m22 = proj[2][2];
+  m32 = proj[3][2];
+
+  n = m32 / m22;
+  f = m32 / (m22 + 1.0f);
+
+  n_m11 = n / m11;
+  n_m00 = n / m00;
+
+  *nearZ = n;
+  *farZ  = f;
+  *bottom  = n_m11 * (m21 - 1.0f);
+  *top     = n_m11 * (m21 + 1.0f);
+  *left    = n_m00 * (m20 - 1.0f);
+  *right   = n_m00 * (m20 + 1.0f);
+}
+
+/*!
+ * @brief decomposes frustum values of perspective projection
+ *        with angle values with a right-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *        this makes easy to get all values at once
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] dest   array
+ */
+CGLM_INLINE
+void
+glm_persp_decompv_rh_zo(mat4 proj, float dest[6]) {
+  glm_persp_decomp_rh_zo(proj, &dest[0], &dest[1], &dest[2],
+                               &dest[3], &dest[4], &dest[5]);
+}
+
+/*!
+ * @brief decomposes left and right values of perspective projection (ZO).
+ *        x stands for x axis (left / right axis)
+ *
+ * @param[in]  proj  perspective projection matrix
+ * @param[out] left  left
+ * @param[out] right right
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_x_rh_zo(mat4 proj,
+                         float * __restrict left,
+                         float * __restrict right) {
+  float nearZ, m20, m00, m22;
+
+  m00 = proj[0][0];
+  m20 = proj[2][0];
+  m22 = proj[2][2];
+
+  nearZ = proj[3][2] / m22;
+  *left   = nearZ * (m20 - 1.0f) / m00;
+  *right  = nearZ * (m20 + 1.0f) / m00;
+}
+
+/*!
+ * @brief decomposes top and bottom values of perspective projection
+ *        with angle values with a right-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *        y stands for y axis (top / bottom axis)
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] top    top
+ * @param[out] bottom bottom
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_y_rh_zo(mat4 proj,
+                         float * __restrict top,
+                         float * __restrict bottom) {
+  float nearZ, m21, m11, m22;
+
+  m21 = proj[2][1];
+  m11 = proj[1][1];
+  m22 = proj[2][2];
+
+  nearZ = proj[3][2] / m22;
+  *bottom = nearZ * (m21 - 1) / m11;
+  *top    = nearZ * (m21 + 1) / m11;
+}
+
+/*!
+ * @brief decomposes near and far values of perspective projection
+ *        with angle values with a right-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *        z stands for z axis (near / far axis)
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ * @param[out] farZ    far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_z_rh_zo(mat4 proj,
+                         float * __restrict nearZ,
+                         float * __restrict farZ) {
+  float m32, m22;
+
+  m32 = proj[3][2];
+  m22 = proj[2][2];
+
+  *nearZ = m32 / m22;
+  *farZ  = m32 / (m22 + 1.0f);
+}
+
+/*!
+ * @brief decomposes far value of perspective projection
+ *        with angle values with a right-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj   perspective projection matrix
+ * @param[out] farZ   far
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_far_rh_zo(mat4 proj, float * __restrict farZ) {
+  *farZ = proj[3][2] / (proj[2][2] + 1.0f);
+}
+
+/*!
+ * @brief decomposes near value of perspective projection
+ *        with angle values with a right-hand coordinate system and a 
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj    perspective projection matrix
+ * @param[out] nearZ   near
+ */
+CGLM_INLINE
+void
+glm_persp_decomp_near_rh_zo(mat4 proj, float * __restrict nearZ) {
+  *nearZ = proj[3][2] / proj[2][2];
+}
+
+/*!
+ * @brief returns sizes of near and far planes of perspective projection
+ *        with a right-hand coordinate system and a
+ *        clip-space of [0, 1].
+ *
+ * @param[in]  proj perspective projection matrix
+ * @param[in]  fovy fovy (see brief)
+ * @param[out] dest sizes order: [Wnear, Hnear, Wfar, Hfar]
+ */
+CGLM_INLINE
+void
+glm_persp_sizes_rh_zo(mat4 proj, float fovy, vec4 dest) {
+  float t, a, nearZ, farZ;
+
+  t = 2.0f * tanf(fovy * 0.5f);
+  a = glm_persp_aspect(proj);
+
+  glm_persp_decomp_z_rh_zo(proj, &nearZ, &farZ);
+
+  dest[1]  = t * nearZ;
+  dest[3]  = t * farZ;
+  dest[0]  = a * dest[1];
+  dest[2]  = a * dest[3];
+}
+
+/*!
+ * @brief returns field of view angle along the Y-axis (in radians)
+ *        with a right-hand coordinate system and a clip-space of [0, 1].
+ *
+ * if you need to degrees, use glm_deg to convert it or use this:
+ * fovy_deg = glm_deg(glm_persp_fovy(projMatrix))
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_fovy_rh_zo(mat4 proj) {
+  return glm_persp_fovy(proj);
+}
+
+/*!
+ * @brief returns aspect ratio of perspective projection
+ *        with a right-hand coordinate system and a clip-space of [0, 1].
+ *
+ * @param[in] proj perspective projection matrix
+ */
+CGLM_INLINE
+float
+glm_persp_aspect_rh_zo(mat4 proj) {
+  return glm_persp_aspect(proj);
+}
+
+#endif /*cglm_persp_rh_zo_h*/
--- a/include/cglm/clipspace/project_no.h
+++ b/include/cglm/clipspace/project_no.h
@@ -0,0 +1,109 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_project_no_h
+#define cglm_project_no_h
+
+#include "../common.h"
+#include "../vec3.h"
+#include "../vec4.h"
+#include "../mat4.h"
+
+/*!
+ * @brief maps the specified viewport coordinates into specified space [1]
+ *        the matrix should contain projection matrix.
+ *
+ * if you don't have ( and don't want to have ) an inverse matrix then use
+ * glm_unproject version. You may use existing inverse of matrix in somewhere
+ * else, this is why glm_unprojecti exists to save save inversion cost
+ *
+ * [1] space:
+ *  1- if m = invProj:     View Space
+ *  2- if m = invViewProj: World Space
+ *  3- if m = invMVP:      Object Space
+ *
+ * You probably want to map the coordinates into object space
+ * so use invMVP as m
+ *
+ * Computing viewProj:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *   glm_mat4_inv(viewProj, invMVP);
+ *
+ * @param[in]  pos      point/position in viewport coordinates
+ * @param[in]  invMat   matrix (see brief)
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     unprojected coordinates
+ */
+CGLM_INLINE
+void
+glm_unprojecti_no(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
+  vec4 v;
+
+  v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
+  v[1] = 2.0f * (pos[1] - vp[1]) / vp[3] - 1.0f;
+  v[2] = 2.0f *  pos[2]                  - 1.0f;
+  v[3] = 1.0f;
+
+  glm_mat4_mulv(invMat, v, v);
+  glm_vec4_scale(v, 1.0f / v[3], v);
+  glm_vec3(v, dest);
+}
+
+/*!
+ * @brief map object coordinates to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  pos      object coordinates
+ * @param[in]  m        MVP matrix
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     projected coordinates
+ */
+CGLM_INLINE
+void
+glm_project_no(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+  CGLM_ALIGN(16) vec4 pos4;
+
+  glm_vec4(pos, 1.0f, pos4);
+
+  glm_mat4_mulv(m, pos4, pos4);
+  glm_vec4_scale(pos4, 1.0f / pos4[3], pos4); /* pos = pos / pos.w */
+  glm_vec4_scale(pos4, 0.5f, pos4);
+  glm_vec4_adds(pos4,  0.5f, pos4);
+
+  dest[0] = pos4[0] * vp[2] + vp[0];
+  dest[1] = pos4[1] * vp[3] + vp[1];
+  dest[2] = pos4[2];
+}
+
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z_no(vec3 v, mat4 m) {
+  float z, w;
+
+  z = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2] + m[3][2];
+  w = m[0][3] * v[0] + m[1][3] * v[1] + m[2][3] * v[2] + m[3][3];
+
+  return 0.5f * (z / w) + 0.5f;
+}
+
+#endif /* cglm_project_no_h */
--- a/include/cglm/clipspace/project_zo.h
+++ b/include/cglm/clipspace/project_zo.h
@@ -0,0 +1,111 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_project_zo_h
+#define cglm_project_zo_h
+
+#include "../common.h"
+#include "../vec3.h"
+#include "../vec4.h"
+#include "../mat4.h"
+
+/*!
+ * @brief maps the specified viewport coordinates into specified space [1]
+ *        the matrix should contain projection matrix.
+ *
+ * if you don't have ( and don't want to have ) an inverse matrix then use
+ * glm_unproject version. You may use existing inverse of matrix in somewhere
+ * else, this is why glm_unprojecti exists to save save inversion cost
+ *
+ * [1] space:
+ *  1- if m = invProj:     View Space
+ *  2- if m = invViewProj: World Space
+ *  3- if m = invMVP:      Object Space
+ *
+ * You probably want to map the coordinates into object space
+ * so use invMVP as m
+ *
+ * Computing viewProj:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *   glm_mat4_inv(viewProj, invMVP);
+ *
+ * @param[in]  pos      point/position in viewport coordinates
+ * @param[in]  invMat   matrix (see brief)
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     unprojected coordinates
+ */
+CGLM_INLINE
+void
+glm_unprojecti_zo(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
+  vec4 v;
+
+  v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
+  v[1] = 2.0f * (pos[1] - vp[1]) / vp[3] - 1.0f;
+  v[2] = pos[2];
+  v[3] = 1.0f;
+
+  glm_mat4_mulv(invMat, v, v);
+  glm_vec4_scale(v, 1.0f / v[3], v);
+  glm_vec3(v, dest);
+}
+
+/*!
+ * @brief map object coordinates to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  pos      object coordinates
+ * @param[in]  m        MVP matrix
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     projected coordinates
+ */
+CGLM_INLINE
+void
+glm_project_zo(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+  CGLM_ALIGN(16) vec4 pos4;
+
+  glm_vec4(pos, 1.0f, pos4);
+
+  glm_mat4_mulv(m, pos4, pos4);
+  glm_vec4_scale(pos4, 1.0f / pos4[3], pos4); /* pos = pos / pos.w */
+
+  dest[2] = pos4[2];
+  
+  glm_vec4_scale(pos4, 0.5f, pos4);
+  glm_vec4_adds(pos4,  0.5f, pos4);
+
+  dest[0] = pos4[0] * vp[2] + vp[0];
+  dest[1] = pos4[1] * vp[3] + vp[1];
+}
+
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z_zo(vec3 v, mat4 m) {
+  float z, w;
+
+  z = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2] + m[3][2];
+  w = m[0][3] * v[0] + m[1][3] * v[1] + m[2][3] * v[2] + m[3][3];
+
+  return z / w;
+}
+
+#endif /* cglm_project_zo_h */
--- a/include/cglm/clipspace/view_lh.h
+++ b/include/cglm/clipspace/view_lh.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
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_lookat_lh(vec3 eye, vec3 center, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_lh(vec3 eye, vec3 dir, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_anyup_lh(vec3 eye, vec3 dir, mat4 dest)
+ */
+
+#ifndef cglm_view_lh_h
+#define cglm_view_lh_h
+
+#include "../common.h"
+#include "../plane.h"
+
+/*!
+ * @brief set up view matrix (LH)
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_lookat_lh(vec3 eye, vec3 center, vec3 up, mat4 dest) {
+  CGLM_ALIGN(8) vec3 f, u, s;
+
+  glm_vec3_sub(center, eye, f);
+  glm_vec3_normalize(f);
+
+  glm_vec3_crossn(up, f, s);
+  glm_vec3_cross(f, s, u);
+
+  dest[0][0] = s[0];
+  dest[0][1] = u[0];
+  dest[0][2] = f[0];
+  dest[1][0] = s[1];
+  dest[1][1] = u[1];
+  dest[1][2] = f[1];
+  dest[2][0] = s[2];
+  dest[2][1] = u[2];
+  dest[2][2] = f[2];
+  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;
+}
+
+/*!
+ * @brief set up view matrix with left handed coordinate system
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_lh(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+  CGLM_ALIGN(8) vec3 target;
+  glm_vec3_add(eye, dir, target);
+  glm_lookat_lh(eye, target, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with left handed coordinate system
+ *
+ * convenient wrapper for look: if you only have direction and if you don't
+ * care what UP vector is then this might be useful to create view matrix
+ *
+ * @param[in]  eye    eye vector
+ * @param[in]  dir    direction vector
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_anyup_lh(vec3 eye, vec3 dir, mat4 dest) {
+  CGLM_ALIGN(8) vec3 up;
+  glm_vec3_ortho(dir, up);
+  glm_look_lh(eye, dir, up, dest);
+}
+
+#endif /*cglm_view_lh_h*/
--- a/include/cglm/clipspace/view_lh_no.h
+++ b/include/cglm/clipspace/view_lh_no.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_lookat_lh_no(vec3 eye, vec3 center, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_lh_no(vec3 eye, vec3 dir, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_anyup_lh_no(vec3 eye, vec3 dir, mat4 dest)
+ */
+
+#ifndef cglm_view_lh_no_h
+#define cglm_view_lh_no_h
+
+#include "../common.h"
+#include "view_lh.h"
+
+/*!
+ * @brief set up view matrix with left handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_lookat_lh_no(vec3 eye, vec3 center, vec3 up, mat4 dest) {
+  glm_lookat_lh(eye, center, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with left handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_lh_no(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+  glm_look_lh(eye, dir, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with left handed coordinate system.
+ *
+ * convenient wrapper for look: if you only have direction and if you don't
+ * care what UP vector is then this might be useful to create view matrix
+ *
+ * @param[in]  eye    eye vector
+ * @param[in]  dir    direction vector
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_anyup_lh_no(vec3 eye, vec3 dir, mat4 dest) {
+  glm_look_anyup_lh(eye, dir, dest);
+}
+
+#endif /*cglm_view_lh_no_h*/
--- a/include/cglm/clipspace/view_lh_zo.h
+++ b/include/cglm/clipspace/view_lh_zo.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_lookat_lh_zo(vec3 eye, vec3 center, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_lh_zo(vec3 eye, vec3 dir, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_anyup_lh_zo(vec3 eye, vec3 dir, mat4 dest)
+ */
+
+#ifndef cglm_view_lh_zo_h
+#define cglm_view_lh_zo_h
+
+#include "../common.h"
+#include "view_lh.h"
+
+/*!
+ * @brief set up view matrix with left handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_lookat_lh_zo(vec3 eye, vec3 center, vec3 up, mat4 dest) {
+  glm_lookat_lh(eye, center, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with left handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_lh_zo(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+  glm_look_lh(eye, dir, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with left handed coordinate system.
+ *
+ * convenient wrapper for look: if you only have direction and if you don't
+ * care what UP vector is then this might be useful to create view matrix
+ *
+ * @param[in]  eye    eye vector
+ * @param[in]  dir    direction vector
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_anyup_lh_zo(vec3 eye, vec3 dir, mat4 dest) {
+  glm_look_anyup_lh(eye, dir, dest);
+}
+
+#endif /*cglm_view_lh_zo_h*/
--- a/include/cglm/clipspace/view_rh.h
+++ b/include/cglm/clipspace/view_rh.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
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_lookat_rh(vec3 eye, vec3 center, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_rh(vec3 eye, vec3 dir, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_anyup_rh(vec3 eye, vec3 dir, mat4 dest)
+ */
+
+#ifndef cglm_view_rh_h
+#define cglm_view_rh_h
+
+#include "../common.h"
+#include "../plane.h"
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_lookat_rh(vec3 eye, vec3 center, vec3 up, mat4 dest) {
+  CGLM_ALIGN(8) vec3 f, u, s;
+
+  glm_vec3_sub(center, eye, f);
+  glm_vec3_normalize(f);
+
+  glm_vec3_crossn(f, up, s);
+  glm_vec3_cross(s, f, u);
+
+  dest[0][0] = s[0];
+  dest[0][1] = u[0];
+  dest[0][2] =-f[0];
+  dest[1][0] = s[1];
+  dest[1][1] = u[1];
+  dest[1][2] =-f[1];
+  dest[2][0] = s[2];
+  dest[2][1] = u[2];
+  dest[2][2] =-f[2];
+  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;
+}
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_rh(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+  CGLM_ALIGN(8) vec3 target;
+  glm_vec3_add(eye, dir, target);
+  glm_lookat_rh(eye, target, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * convenient wrapper for look: if you only have direction and if you don't
+ * care what UP vector is then this might be useful to create view matrix
+ *
+ * @param[in]  eye    eye vector
+ * @param[in]  dir    direction vector
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_anyup_rh(vec3 eye, vec3 dir, mat4 dest) {
+  CGLM_ALIGN(8) vec3 up;
+  glm_vec3_ortho(dir, up);
+  glm_look_rh(eye, dir, up, dest);
+}
+
+#endif /*cglm_view_rh_h*/
--- a/include/cglm/clipspace/view_rh_no.h
+++ b/include/cglm/clipspace/view_rh_no.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_lookat_rh_no(vec3 eye, vec3 center, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_rh_no(vec3 eye, vec3 dir, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_anyup_rh_no(vec3 eye, vec3 dir, mat4 dest)
+ */
+
+#ifndef cglm_view_rh_no_h
+#define cglm_view_rh_no_h
+
+#include "../common.h"
+#include "view_rh.h"
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_lookat_rh_no(vec3 eye, vec3 center, vec3 up, mat4 dest) {
+  glm_lookat_rh(eye, center, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_rh_no(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+  glm_look_rh(eye, dir, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * convenient wrapper for look: if you only have direction and if you don't
+ * care what UP vector is then this might be useful to create view matrix
+ *
+ * @param[in]  eye    eye vector
+ * @param[in]  dir    direction vector
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_anyup_rh_no(vec3 eye, vec3 dir, mat4 dest) {
+  glm_look_anyup_rh(eye, dir, dest);
+}
+
+#endif /*cglm_view_rh_no_h*/
--- a/include/cglm/clipspace/view_rh_zo.h
+++ b/include/cglm/clipspace/view_rh_zo.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE void glm_lookat_rh_zo(vec3 eye, vec3 center, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_rh_zo(vec3 eye, vec3 dir, vec3 up, mat4 dest)
+   CGLM_INLINE void glm_look_anyup_rh_zo(vec3 eye, vec3 dir, mat4 dest)
+ */
+
+#ifndef cglm_view_rh_zo_h
+#define cglm_view_rh_zo_h
+
+#include "../common.h"
+#include "view_rh.h"
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_lookat_rh_zo(vec3 eye, vec3 center, vec3 up, mat4 dest) {
+  glm_lookat_rh(eye, center, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * 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
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_rh_zo(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
+  glm_look_rh(eye, dir, up, dest);
+}
+
+/*!
+ * @brief set up view matrix with right handed coordinate system.
+ *
+ * convenient wrapper for look: if you only have direction and if you don't
+ * care what UP vector is then this might be useful to create view matrix
+ *
+ * @param[in]  eye    eye vector
+ * @param[in]  dir    direction vector
+ * @param[out] dest   result matrix
+ */
+CGLM_INLINE
+void
+glm_look_anyup_rh_zo(vec3 eye, vec3 dir, mat4 dest) {
+  glm_look_anyup_rh(eye, dir, dest);
+}
+
+#endif /*cglm_view_rh_zo_h*/
--- a/include/cglm/common.h
+++ b/include/cglm/common.h
@@ -44,10 +44,41 @@

 #ifndef CGLM_USE_DEFAULT_EPSILON
 #  ifndef GLM_FLT_EPSILON
-#    define GLM_FLT_EPSILON 1e-6
+#    define GLM_FLT_EPSILON 1e-5
 #  endif
 #else
 #  define GLM_FLT_EPSILON FLT_EPSILON
 #endif

+/*
+ * Clip control: define CGLM_FORCE_DEPTH_ZERO_TO_ONE before including
+ * CGLM to use a clip space between 0 to 1.
+ * Coordinate system: define CGLM_FORCE_LEFT_HANDED before including
+ * CGLM to use the left handed coordinate system by default.
+ */
+
+#define CGLM_CLIP_CONTROL_ZO_BIT (1 << 0) /* ZERO_TO_ONE */
+#define CGLM_CLIP_CONTROL_NO_BIT (1 << 1) /* NEGATIVE_ONE_TO_ONE */
+#define CGLM_CLIP_CONTROL_LH_BIT (1 << 2) /* LEFT_HANDED, For DirectX, Metal, Vulkan */
+#define CGLM_CLIP_CONTROL_RH_BIT (1 << 3) /* RIGHT_HANDED, For OpenGL, default in GLM */
+
+#define CGLM_CLIP_CONTROL_LH_ZO (CGLM_CLIP_CONTROL_LH_BIT | CGLM_CLIP_CONTROL_ZO_BIT)
+#define CGLM_CLIP_CONTROL_LH_NO (CGLM_CLIP_CONTROL_LH_BIT | CGLM_CLIP_CONTROL_NO_BIT)
+#define CGLM_CLIP_CONTROL_RH_ZO (CGLM_CLIP_CONTROL_RH_BIT | CGLM_CLIP_CONTROL_ZO_BIT)
+#define CGLM_CLIP_CONTROL_RH_NO (CGLM_CLIP_CONTROL_RH_BIT | CGLM_CLIP_CONTROL_NO_BIT)
+
+#ifdef CGLM_FORCE_DEPTH_ZERO_TO_ONE
+#  ifdef CGLM_FORCE_LEFT_HANDED
+#    define CGLM_CONFIG_CLIP_CONTROL CGLM_CLIP_CONTROL_LH_ZO
+#  else
+#    define CGLM_CONFIG_CLIP_CONTROL CGLM_CLIP_CONTROL_RH_ZO
+#  endif
+#else
+#  ifdef CGLM_FORCE_LEFT_HANDED
+#    define CGLM_CONFIG_CLIP_CONTROL CGLM_CLIP_CONTROL_LH_NO
+#  else
+#    define CGLM_CONFIG_CLIP_CONTROL CGLM_CLIP_CONTROL_RH_NO
+#  endif
+#endif
+
 #endif /* cglm_common_h */
--- a/include/cglm/io.h
+++ b/include/cglm/io.h
@@ -39,6 +39,7 @@
   || defined(CGLM_NO_PRINTS_NOOP)

 #include "common.h"
+#include "util.h"

 #include <stdio.h>
 #include <stdlib.h>
--- a/include/cglm/ivec2.h
+++ b/include/cglm/ivec2.h
@@ -0,0 +1,242 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+FUNCTIONS:
+  CGLM_INLINE void glm_ivec2(int * __restrict v, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_copy(ivec2 a, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_zero(ivec2 v)
+  CGLM_INLINE void glm_ivec2_one(ivec2 v)
+  CGLM_INLINE void glm_ivec2_add(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_adds(ivec2 v, int s, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_subs(ivec2 v, int s, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_scale(ivec2 v, int s, ivec2 dest)
+  CGLM_INLINE int glm_ivec2_distance2(ivec2 a, ivec2 b)
+  CGLM_INLINE float glm_ivec2_distance(ivec2 a, ivec2 b)
+  CGLM_INLINE void glm_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_clamp(ivec2 v, int minVal, int maxVal)
+ */
+
+#ifndef cglm_ivec2_h
+#define cglm_ivec2_h
+
+#include "common.h"
+
+/*!
+ * @brief init ivec2 using vec3 or vec4
+ *
+ * @param[in]  v    vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2(int * __restrict v, ivec2 dest) {
+  dest[0] = v[0];
+  dest[1] = v[1];
+}
+
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * @param[in]  a    source vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_copy(ivec2 a, ivec2 dest) {
+  dest[0] = a[0];
+  dest[1] = a[1];
+}
+
+/*!
+ * @brief set all members of [v] to zero
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void 
+glm_ivec2_zero(ivec2 v) {
+  v[0] = v[1] = 0;
+}
+
+/*!
+ * @brief set all members of [v] to one
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void
+glm_ivec2_one(ivec2 v) {
+  v[0] = v[1] = 1;
+}
+
+/*!
+ * @brief add vector [a] to vector [b] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_add(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+}
+
+/*!
+ * @brief add scalar s to vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_adds(ivec2 v, int s, ivec2 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+}
+
+/*!
+ * @brief subtract vector [b] from vector [a] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+}
+
+/*!
+ * @brief subtract scalar s from vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_subs(ivec2 v, int s, ivec2 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+}
+
+/*!
+ * @brief multiply vector [a] with vector [b] and store result in [dest]
+ *
+ * @param[in]  a    frist vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+}
+
+/*!
+ * @brief multiply vector [a] with scalar s and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_scale(ivec2 v, int s, ivec2 dest) {
+  dest[0] = v[0] * s;
+  dest[1] = v[1] * s;
+}
+
+/*!
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+int
+glm_ivec2_distance2(ivec2 a, ivec2 b) {
+  int xd, yd;
+  xd = a[0] - b[0];
+  yd = a[1] - b[1];
+  return xd * xd + yd * yd;
+}
+
+/*!
+ * @brief distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns distance
+ */
+CGLM_INLINE
+float
+glm_ivec2_distance(ivec2 a, ivec2 b) {
+  return sqrtf((float)glm_ivec2_distance2(a, b));
+}
+
+/*!
+ * @brief set each member of dest to greater of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] > b[0] ? a[0] : b[0];
+  dest[1] = a[1] > b[1] ? a[1] : b[1];
+}
+
+/*!
+ * @brief set each member of dest to lesser of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] < b[0] ? a[0] : b[0];
+  dest[1] = a[1] < b[1] ? a[1] : b[1];
+}
+
+/*!
+ * @brief clamp each member of [v] between minVal and maxVal (inclusive)
+ *
+ * @param[in, out] v      vector
+ * @param[in]      minVal minimum value
+ * @param[in]      maxVal maximum value
+ */
+CGLM_INLINE
+void
+glm_ivec2_clamp(ivec2 v, int minVal, int maxVal) {
+  if (v[0] < minVal)
+    v[0] = minVal;
+  else if(v[0] > maxVal)
+    v[0] = maxVal;
+
+  if (v[1] < minVal)
+    v[1] = minVal;
+  else if(v[1] > maxVal)
+    v[1] = maxVal;
+}
+
+#endif /* cglm_ivec2_h */
--- a/include/cglm/ivec3.h
+++ b/include/cglm/ivec3.h
@@ -0,0 +1,258 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+FUNCTIONS:
+  CGLM_INLINE void glm_ivec3(ivec4 v4, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_copy(ivec3 a, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_zero(ivec3 v)
+  CGLM_INLINE void glm_ivec3_one(ivec3 v)
+  CGLM_INLINE void glm_ivec3_add(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_adds(ivec3 v, int s, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_subs(ivec3 v, int s, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_scale(ivec3 v, int s, ivec3 dest)
+  CGLM_INLINE int glm_ivec3_distance2(ivec3 a, ivec3 b)
+  CGLM_INLINE float glm_ivec3_distance(ivec3 a, ivec3 b)
+  CGLM_INLINE void glm_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_clamp(ivec3 v, int minVal, int maxVal)
+ */
+
+#ifndef cglm_ivec3_h
+#define cglm_ivec3_h
+
+#include "common.h"
+
+/*!
+ * @brief init ivec3 using ivec4
+ *
+ * @param[in]  v4   vector4
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3(ivec4 v4, ivec3 dest) {
+  dest[0] = v4[0];
+  dest[1] = v4[1];
+  dest[2] = v4[2];
+}
+
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * @param[in]  a    source vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_copy(ivec3 a, ivec3 dest) {
+  dest[0] = a[0];
+  dest[1] = a[1];
+  dest[2] = a[2];
+}
+
+/*!
+ * @brief set all members of [v] to zero
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void 
+glm_ivec3_zero(ivec3 v) {
+  v[0] = v[1] = v[2] = 0;
+}
+
+/*!
+ * @brief set all members of [v] to one
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void
+glm_ivec3_one(ivec3 v) {
+  v[0] = v[1] = v[2] = 1;
+}
+
+/*!
+ * @brief add vector [a] to vector [b] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_add(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+  dest[2] = a[2] + b[2];
+}
+
+/*!
+ * @brief add scalar s to vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_adds(ivec3 v, int s, ivec3 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+  dest[2] = v[2] + s;
+}
+
+/*!
+ * @brief subtract vector [b] from vector [a] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+  dest[2] = a[2] - b[2];
+}
+
+/*!
+ * @brief subtract scalar s from vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_subs(ivec3 v, int s, ivec3 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+  dest[2] = v[2] - s;
+}
+
+/*!
+ * @brief multiply vector [a] with vector [b] and store result in [dest]
+ *
+ * @param[in]  a    frist vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+  dest[2] = a[2] * b[2];
+}
+
+/*!
+ * @brief multiply vector [a] with scalar s and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_scale(ivec3 v, int s, ivec3 dest) {
+  dest[0] = v[0] * s;
+  dest[1] = v[1] * s;
+  dest[2] = v[2] * s;
+}
+
+/*!
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+int
+glm_ivec3_distance2(ivec3 a, ivec3 b) {
+  int xd, yd, zd;
+  xd = a[0] - b[0];
+  yd = a[1] - b[1];
+  zd = a[2] - b[2];
+  return xd * xd + yd * yd + zd * zd;
+}
+
+/*!
+ * @brief distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns distance
+ */
+CGLM_INLINE
+float
+glm_ivec3_distance(ivec3 a, ivec3 b) {
+  return sqrtf((float)glm_ivec3_distance2(a, b));
+}
+
+/*!
+ * @brief set each member of dest to greater of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] > b[0] ? a[0] : b[0];
+  dest[1] = a[1] > b[1] ? a[1] : b[1];
+  dest[2] = a[2] > b[2] ? a[2] : b[2];
+}
+
+/*!
+ * @brief set each member of dest to lesser of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] < b[0] ? a[0] : b[0];
+  dest[1] = a[1] < b[1] ? a[1] : b[1];
+  dest[2] = a[2] < b[2] ? a[2] : b[2];
+}
+
+/*!
+ * @brief clamp each member of [v] between minVal and maxVal (inclusive)
+ *
+ * @param[in, out] v      vector
+ * @param[in]      minVal minimum value
+ * @param[in]      maxVal maximum value
+ */
+CGLM_INLINE
+void
+glm_ivec3_clamp(ivec3 v, int minVal, int maxVal) {
+  if (v[0] < minVal)
+    v[0] = minVal;
+  else if(v[0] > maxVal)
+    v[0] = maxVal;
+
+  if (v[1] < minVal)
+    v[1] = minVal;
+  else if(v[1] > maxVal)
+    v[1] = maxVal;
+
+  if (v[2] < minVal)
+    v[2] = minVal;
+  else if(v[2] > maxVal)
+    v[2] = maxVal;
+}
+
+#endif /* cglm_ivec3_h */
--- a/include/cglm/ivec4.h
+++ b/include/cglm/ivec4.h
@@ -0,0 +1,275 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+FUNCTIONS:
+  CGLM_INLINE void glm_ivec4(ivec3 v3, int last, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_copy(ivec4 a, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_zero(ivec4 v)
+  CGLM_INLINE void glm_ivec4_one(ivec4 v)
+  CGLM_INLINE void glm_ivec4_add(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_adds(ivec4 v, int s, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_subs(ivec4 v, int s, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_scale(ivec4 v, int s, ivec4 dest)
+  CGLM_INLINE int glm_ivec4_distance2(ivec4 a, ivec4 b)
+  CGLM_INLINE float glm_ivec4_distance(ivec4 a, ivec4 b)
+  CGLM_INLINE void glm_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_clamp(ivec4 v, int minVal, int maxVal)
+ */
+
+#ifndef cglm_ivec4_h
+#define cglm_ivec4_h
+
+#include "common.h"
+
+/*!
+ * @brief init ivec4 using ivec3
+ *
+ * @param[in]  v3   vector3
+ * @param[in]  last last item
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4(ivec3 v3, int last, ivec4 dest) {
+  dest[0] = v3[0];
+  dest[1] = v3[1];
+  dest[2] = v3[2];
+  dest[3] = last;
+}
+
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * @param[in]  a    source vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_copy(ivec4 a, ivec4 dest) {
+  dest[0] = a[0];
+  dest[1] = a[1];
+  dest[2] = a[2];
+  dest[3] = a[3];
+}
+
+/*!
+ * @brief set all members of [v] to zero
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void 
+glm_ivec4_zero(ivec4 v) {
+  v[0] = v[1] = v[2] = v[3] = 0;
+}
+
+/*!
+ * @brief set all members of [v] to one
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void
+glm_ivec4_one(ivec4 v) {
+  v[0] = v[1] = v[2] = v[3] = 1;
+}
+
+/*!
+ * @brief add vector [a] to vector [b] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_add(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+  dest[2] = a[2] + b[2];
+  dest[3] = a[3] + b[3];
+}
+
+/*!
+ * @brief add scalar s to vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_adds(ivec4 v, int s, ivec4 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+  dest[2] = v[2] + s;
+  dest[3] = v[3] + s;
+}
+
+/*!
+ * @brief subtract vector [b] from vector [a] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+  dest[2] = a[2] - b[2];
+  dest[3] = a[3] - b[3];
+}
+
+/*!
+ * @brief subtract scalar s from vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_subs(ivec4 v, int s, ivec4 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+  dest[2] = v[2] - s;
+  dest[3] = v[3] - s;
+}
+
+/*!
+ * @brief multiply vector [a] with vector [b] and store result in [dest]
+ *
+ * @param[in]  a    frist vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+  dest[2] = a[2] * b[2];
+  dest[3] = a[3] * b[3];
+}
+
+/*!
+ * @brief multiply vector [a] with scalar s and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_scale(ivec4 v, int s, ivec4 dest) {
+  dest[0] = v[0] * s;
+  dest[1] = v[1] * s;
+  dest[2] = v[2] * s;
+  dest[3] = v[3] * s;
+}
+
+/*!
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+int
+glm_ivec4_distance2(ivec4 a, ivec4 b) {
+  int xd, yd, zd, wd;
+  xd = a[0] - b[0];
+  yd = a[1] - b[1];
+  zd = a[2] - b[2];
+  wd = a[3] - b[3];
+  return xd * xd + yd * yd + zd * zd + wd * wd;
+}
+
+/*!
+ * @brief distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns distance
+ */
+CGLM_INLINE
+float
+glm_ivec4_distance(ivec4 a, ivec4 b) {
+  return sqrtf((float)glm_ivec4_distance2(a, b));
+}
+
+/*!
+ * @brief set each member of dest to greater of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] > b[0] ? a[0] : b[0];
+  dest[1] = a[1] > b[1] ? a[1] : b[1];
+  dest[2] = a[2] > b[2] ? a[2] : b[2];
+  dest[3] = a[3] > b[3] ? a[3] : b[3];
+}
+
+/*!
+ * @brief set each member of dest to lesser of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] < b[0] ? a[0] : b[0];
+  dest[1] = a[1] < b[1] ? a[1] : b[1];
+  dest[2] = a[2] < b[2] ? a[2] : b[2];
+  dest[3] = a[3] < b[3] ? a[3] : b[3];
+}
+
+/*!
+ * @brief clamp each member of [v] between minVal and maxVal (inclusive)
+ *
+ * @param[in, out] v      vector
+ * @param[in]      minVal minimum value
+ * @param[in]      maxVal maximum value
+ */
+CGLM_INLINE
+void
+glm_ivec4_clamp(ivec4 v, int minVal, int maxVal) {
+  if (v[0] < minVal)
+    v[0] = minVal;
+  else if(v[0] > maxVal)
+    v[0] = maxVal;
+
+  if (v[1] < minVal)
+    v[1] = minVal;
+  else if(v[1] > maxVal)
+    v[1] = maxVal;
+
+  if (v[2] < minVal)
+    v[2] = minVal;
+  else if(v[2] > maxVal)
+    v[2] = maxVal;
+
+  if (v[3] < minVal)
+    v[3] = minVal;
+  else if(v[3] > maxVal)
+    v[3] = maxVal;
+}
+
+#endif /* cglm_ivec4_h */
--- a/include/cglm/mat2.h
+++ b/include/cglm/mat2.h
@@ -40,6 +40,10 @@
 #  include "simd/sse2/mat2.h"
 #endif

+#ifdef CGLM_NEON_FP
+#  include "simd/neon/mat2.h"
+#endif
+
 #define GLM_MAT2_IDENTITY_INIT  {{1.0f, 0.0f}, {0.0f, 1.0f}}
 #define GLM_MAT2_ZERO_INIT      {{0.0f, 0.0f}, {0.0f, 0.0f}}

@@ -130,6 +134,8 @@ void
 glm_mat2_mul(mat2 m1, mat2 m2, mat2 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
  glm_mat2_mul_sse2(m1, m2, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_mat2_mul_neon(m1, m2, dest);
 #else
  float a00 = m1[0][0], a01 = m1[0][1],
        a10 = m1[1][0], a11 = m1[1][1],
--- a/include/cglm/mat4.h
+++ b/include/cglm/mat4.h
@@ -187,8 +187,29 @@ glm_mat4_identity_array(mat4 * __restrict mat, size_t count) {
 CGLM_INLINE
 void
 glm_mat4_zero(mat4 mat) {
+#ifdef __AVX__
+  __m256 y0;
+  y0 = _mm256_setzero_ps();
+  glmm_store256(mat[0], y0);
+  glmm_store256(mat[2], y0);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_128 x0;
+  x0 = _mm_setzero_ps();
+  glmm_store(mat[0], x0);
+  glmm_store(mat[1], x0);
+  glmm_store(mat[2], x0);
+  glmm_store(mat[3], x0);
+#elif defined(CGLM_NEON_FP)
+  glmm_128 x0;
+  x0 = vdupq_n_f32(0.0f);
+  vst1q_f32(mat[0], x0);
+  vst1q_f32(mat[1], x0);
+  vst1q_f32(mat[2], x0);
+  vst1q_f32(mat[3], x0);
+#else
  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_ZERO_INIT;
  glm_mat4_copy(t, mat);
+#endif
 }

 /*!
@@ -539,7 +560,9 @@ glm_mat4_scale_p(mat4 m, float s) {
 CGLM_INLINE
 void
 glm_mat4_scale(mat4 m, float s) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#ifdef __AVX__
+  glm_mat4_scale_avx(m, s);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
  glm_mat4_scale_sse2(m, s);
 #elif defined(CGLM_NEON_FP)
  glm_mat4_scale_neon(m, s);
@@ -560,6 +583,8 @@ float
 glm_mat4_det(mat4 mat) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
  return glm_mat4_det_sse2(mat);
+#elif defined(CGLM_NEON_FP)
+  return glm_mat4_det_neon(mat);
 #else
  /* [square] det(A) = det(At) */
  float t[6];
@@ -593,6 +618,8 @@ void
 glm_mat4_inv(mat4 mat, mat4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
  glm_mat4_inv_sse2(mat, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_mat4_inv_neon(mat, dest);
 #else
  float t[6];
  float det;
--- a/include/cglm/plane.h
+++ b/include/cglm/plane.h
@@ -9,6 +9,7 @@
 #define cglm_plane_h

 #include "common.h"
+#include "vec3.h"
 #include "vec4.h"

 /*
--- a/include/cglm/project.h
+++ b/include/cglm/project.h
@@ -13,6 +13,17 @@
 #include "vec4.h"
 #include "mat4.h"

+#ifndef CGLM_CLIPSPACE_INCLUDE_ALL
+#  if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+#    include "clipspace/project_zo.h"
+#  elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+#    include "clipspace/project_no.h"
+#  endif
+#else
+#  include "clipspace/project_zo.h"
+#  include "clipspace/project_no.h"
+#endif
+
 /*!
 * @brief maps the specified viewport coordinates into specified space [1]
 *        the matrix should contain projection matrix.
@@ -42,16 +53,11 @@
 CGLM_INLINE
 void
 glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
-  vec4 v;
-
-  v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
-  v[1] = 2.0f * (pos[1] - vp[1]) / vp[3] - 1.0f;
-  v[2] = 2.0f *  pos[2]                  - 1.0f;
-  v[3] = 1.0f;
-
-  glm_mat4_mulv(invMat, v, v);
-  glm_vec4_scale(v, 1.0f / v[3], v);
-  glm_vec3(v, dest);
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+  glm_unprojecti_zo(pos, invMat, vp, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+  glm_unprojecti_no(pos, invMat, vp, dest);
+#endif
 }

 /*!
@@ -101,18 +107,66 @@ glm_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
 CGLM_INLINE
 void
 glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
-  CGLM_ALIGN(16) vec4 pos4, vone = GLM_VEC4_ONE_INIT;
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+  glm_project_zo(pos, m, vp, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+  glm_project_no(pos, m, vp, dest);
+#endif
+}

-  glm_vec4(pos, 1.0f, pos4);
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z(vec3 v, mat4 m) {
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+  return glm_project_z_zo(v, m);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+  return glm_project_z_no(v, m);
+#endif
+}

-  glm_mat4_mulv(m, pos4, pos4);
-  glm_vec4_scale(pos4, 1.0f / pos4[3], pos4); /* pos = pos / pos.w */
-  glm_vec4_add(pos4, vone, pos4);
-  glm_vec4_scale(pos4, 0.5f, pos4);
+/*!
+ * @brief define a picking region
+ *
+ * @param[in]  center   center [x, y] of a picking region in window coordinates
+ * @param[in]  size     size [width, height] of the picking region in window coordinates
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     projected coordinates
+ */
+CGLM_INLINE
+void
+glm_pickmatrix(vec2 center, vec2 size, vec4 vp, mat4 dest) {
+  mat4 res;
+  vec3 v;

-  dest[0] = pos4[0] * vp[2] + vp[0];
-  dest[1] = pos4[1] * vp[3] + vp[1];
-  dest[2] = pos4[2];
+  if (size[0] <= 0.0f || size[1] <= 0.0f)
+    return;
+  
+  /* Translate and scale the picked region to the entire window */
+  v[0] = (vp[2] - 2.0f * (center[0] - vp[0])) / size[0];
+  v[1] = (vp[3] - 2.0f * (center[1] - vp[1])) / size[1];
+  v[2] = 0.0f;
+
+  glm_translate_make(res, v);
+  
+  v[0] = vp[2] / size[0];
+  v[1] = vp[3] / size[1];
+  v[2] = 1.0f;
+
+  glm_scale(res, v);
+
+  glm_mat4_copy(res, dest);
 }

 #endif /* cglm_project_h */
--- a/include/cglm/quat.h
+++ b/include/cglm/quat.h
@@ -16,6 +16,7 @@
   CGLM_INLINE void glm_quat(versor q, float angle, float x, float y, float z);
   CGLM_INLINE void glm_quatv(versor q, float angle, vec3 axis);
   CGLM_INLINE void glm_quat_copy(versor q, versor dest);
+   CGLM_INLINE void glm_quat_from_vecs(vec3 a, vec3 b, versor dest);
   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);
@@ -38,6 +39,7 @@
   CGLM_INLINE void glm_quat_lerp(versor from, versor to, float t, versor dest);
   CGLM_INLINE void glm_quat_lerpc(versor from, versor to, float t, versor dest);
   CGLM_INLINE void glm_quat_slerp(versor q, versor r, float t, versor dest);
+   CGLM_INLINE void glm_quat_nlerp(versor q, versor r, float t, versor dest);
   CGLM_INLINE void glm_quat_look(vec3 eye, versor ori, mat4 dest);
   CGLM_INLINE void glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest);
   CGLM_INLINE void glm_quat_forp(vec3 from,
@@ -58,22 +60,17 @@
 #include "mat4.h"
 #include "mat3.h"
 #include "affine-mat.h"
+#include "affine.h"

 #ifdef CGLM_SSE_FP
 #  include "simd/sse2/quat.h"
 #endif

-CGLM_INLINE
-void
-glm_mat4_mulv(mat4 m, vec4 v, vec4 dest);
+#ifdef CGLM_NEON_FP
+#  include "simd/neon/quat.h"
+#endif

-CGLM_INLINE
-void
-glm_mul_rot(mat4 m1, mat4 m2, mat4 dest);
-
-CGLM_INLINE
-void
-glm_translate(mat4 m, vec3 v);
+CGLM_INLINE void glm_quat_normalize(versor q);

 /*
 * IMPORTANT:
@@ -190,10 +187,41 @@ glm_quat_copy(versor q, versor dest) {
  glm_vec4_copy(q, dest);
 }

+/*!
+ * @brief compute quaternion rotating vector A to vector B
+ *
+ * @param[in]   a     vec3 (must have unit length)
+ * @param[in]   b     vec3 (must have unit length)
+ * @param[out]  dest  quaternion (of unit length)
+ */
+CGLM_INLINE
+void
+glm_quat_from_vecs(vec3 a, vec3 b, versor dest) {
+  CGLM_ALIGN(8) vec3 axis;
+  float cos_theta;
+  float cos_half_theta;
+
+  cos_theta = glm_vec3_dot(a, b);
+  if (cos_theta >= 1.f - GLM_FLT_EPSILON) {  /*  a ∥ b  */
+    glm_quat_identity(dest);
+    return;
+  }
+  if (cos_theta < -1.f + GLM_FLT_EPSILON) {  /*  angle(a, b) = π  */
+    glm_vec3_ortho(a, axis);
+    cos_half_theta = 0.f;                    /*  cos π/2 */
+  } else {
+    glm_vec3_cross(a, b, axis);
+    cos_half_theta = 1.0f + cos_theta;       /*  cos 0 + cos θ  */
+  }
+
+  glm_quat_init(dest, axis[0], axis[1], axis[2], cos_half_theta);
+  glm_quat_normalize(dest);
+}
+
 /*!
 * @brief returns norm (magnitude) of quaternion
 *
- * @param[out]  q  quaternion
+ * @param[in]  q  quaternion
 */
 CGLM_INLINE
 float
@@ -412,6 +440,8 @@ glm_quat_mul(versor p, versor q, versor dest) {
   */
 #if defined( __SSE__ ) || defined( __SSE2__ )
  glm_quat_mul_sse2(p, q, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_quat_mul_neon(p, q, dest);
 #else
  dest[0] = p[3] * q[0] + p[0] * q[3] + p[1] * q[2] - p[2] * q[1];
  dest[1] = p[3] * q[1] - p[0] * q[2] + p[1] * q[3] + p[2] * q[0];
@@ -622,6 +652,29 @@ glm_quat_lerpc(versor from, versor to, float t, versor dest) {
  glm_vec4_lerpc(from, to, t, dest);
 }

+/*!
+ * @brief interpolates between two quaternions
+ *        taking the shortest rotation path using
+ *        normalized linear interpolation (NLERP)
+ *
+ * @param[in]   from  from
+ * @param[in]   to    to
+ * @param[in]   t     interpolant (amount)
+ * @param[out]  dest  result quaternion
+ */
+CGLM_INLINE
+void
+glm_quat_nlerp(versor from, versor to, float t, versor dest) {
+  versor target;
+  float  dot;
+  
+  dot = glm_vec4_dot(from, to);
+  
+  glm_vec4_scale(to, (dot >= 0) ? 1.0f : -1.0f, target);
+  glm_quat_lerp(from, target, t, dest);
+  glm_quat_normalize(dest);
+}
+
 /*!
 * @brief interpolates between two quaternions
 *        using spherical linear interpolation (SLERP)
--- a/include/cglm/simd/arm.h
+++ b/include/cglm/simd/arm.h
@@ -10,19 +10,56 @@
 #include "intrin.h"
 #ifdef CGLM_SIMD_ARM

+#if defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC) || defined(__aarch64__)
+# define CGLM_ARM64 1
+#endif
+
 #define glmm_load(p)      vld1q_f32(p)
 #define glmm_store(p, a)  vst1q_f32(p, a)

+#define glmm_set1(x) vdupq_n_f32(x)
+#define glmm_128     float32x4_t
+
+#define glmm_splat_x(x) vdupq_lane_f32(vget_low_f32(x),  0)
+#define glmm_splat_y(x) vdupq_lane_f32(vget_low_f32(x),  1)
+#define glmm_splat_z(x) vdupq_lane_f32(vget_high_f32(x), 0)
+#define glmm_splat_w(x) vdupq_lane_f32(vget_high_f32(x), 1)
+
+#define glmm_xor(a, b)                                                        \
+  vreinterpretq_f32_s32(veorq_s32(vreinterpretq_s32_f32(a),                   \
+                                  vreinterpretq_s32_f32(b)))
+
+#define glmm_swplane(v) vextq_f32(v, v, 2)
+#define glmm_low(x)     vget_low_f32(x)
+#define glmm_high(x)    vget_high_f32(x)
+
+#define glmm_combine_ll(x, y) vcombine_f32(vget_low_f32(x),  vget_low_f32(y))
+#define glmm_combine_hl(x, y) vcombine_f32(vget_high_f32(x), vget_low_f32(y))
+#define glmm_combine_lh(x, y) vcombine_f32(vget_low_f32(x),  vget_high_f32(y))
+#define glmm_combine_hh(x, y) vcombine_f32(vget_high_f32(x), vget_high_f32(y))
+
 static inline
 float32x4_t
 glmm_abs(float32x4_t v) {
  return vabsq_f32(v);
 }

+static inline
+float32x4_t
+glmm_vhadd(float32x4_t v) {
+  return vaddq_f32(vaddq_f32(glmm_splat_x(v), glmm_splat_y(v)),
+                   vaddq_f32(glmm_splat_z(v), glmm_splat_w(v)));
+  /*
+   this seems slower:
+   v = vaddq_f32(v, vrev64q_f32(v));
+   return vaddq_f32(v, vcombine_f32(vget_high_f32(v), vget_low_f32(v)));
+   */
+}
+
 static inline
 float
 glmm_hadd(float32x4_t v) {
-#if defined(__aarch64__)
+#if CGLM_ARM64
  return vaddvq_f32(v);
 #else
  v = vaddq_f32(v, vrev64q_f32(v));
@@ -79,5 +116,58 @@ glmm_norm_inf(float32x4_t a) {
  return glmm_hmax(glmm_abs(a));
 }

+static inline
+float32x4_t
+glmm_div(float32x4_t a, float32x4_t b) {
+#if CGLM_ARM64
+  return vdivq_f32(a, b);
+#else
+  /* 2 iterations of Newton-Raphson refinement of reciprocal */
+  float32x4_t r0, r1;
+  r0 = vrecpeq_f32(b);
+  r1 = vrecpsq_f32(r0, b);
+  r0 = vmulq_f32(r1, r0);
+  r1 = vrecpsq_f32(r0, b);
+  r0 = vmulq_f32(r1, r0);
+  return vmulq_f32(a, r0);
+#endif
+}
+
+static inline
+float32x4_t
+glmm_fmadd(float32x4_t a, float32x4_t b, float32x4_t c) {
+#if CGLM_ARM64
+  return vfmaq_f32(c, a, b); /* why vfmaq_f32 is slower than vmlaq_f32 ??? */
+#else
+  return vmlaq_f32(c, a, b);
+#endif
+}
+
+static inline
+float32x4_t
+glmm_fnmadd(float32x4_t a, float32x4_t b, float32x4_t c) {
+#if CGLM_ARM64
+  return vfmsq_f32(c, a, b);
+#else
+  return vmlsq_f32(c, a, b);
+#endif
+}
+
+static inline
+float32x4_t
+glmm_fmsub(float32x4_t a, float32x4_t b, float32x4_t c) {
+#if CGLM_ARM64
+  return vfmsq_f32(c, a, b);
+#else
+  return vmlsq_f32(c, a, b);
+#endif
+}
+
+static inline
+float32x4_t
+glmm_fnmsub(float32x4_t a, float32x4_t b, float32x4_t c) {
+  return vsubq_f32(vdupq_n_f32(0.0f), glmm_fmadd(a, b, c));
+}
+
 #endif
 #endif /* cglm_simd_arm_h */
--- a/include/cglm/simd/avx/mat4.h
+++ b/include/cglm/simd/avx/mat4.h
@@ -14,6 +14,16 @@

 #include <immintrin.h>

+CGLM_INLINE
+void
+glm_mat4_scale_avx(mat4 m, float s) {
+  __m256 y0;
+  y0 = _mm256_set1_ps(s);
+  
+  glmm_store256(m[0], _mm256_mul_ps(y0, glmm_load256(m[0])));
+  glmm_store256(m[2], _mm256_mul_ps(y0, glmm_load256(m[2])));
+}
+
 CGLM_INLINE
 void
 glm_mat4_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
--- a/include/cglm/simd/intrin.h
+++ b/include/cglm/simd/intrin.h
@@ -34,7 +34,7 @@
 #endif

 #if defined(__SSE3__)
-#  include <x86intrin.h>
+#  include <pmmintrin.h>
 #  ifndef CGLM_SIMD_x86
 #    define CGLM_SIMD_x86
 #  endif
--- a/include/cglm/simd/neon/affine.h
+++ b/include/cglm/simd/neon/affine.h
@@ -0,0 +1,121 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_affine_neon_h
+#define cglm_affine_neon_h
+#if defined(__ARM_NEON_FP)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_mul_neon(mat4 m1, mat4 m2, mat4 dest) {
+  /* D = R * L (Column-Major) */
+
+  glmm_128 l, r0, r1, r2, r3, v0, v1, v2, v3;
+
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+  r3 = glmm_load(m2[3]);
+
+  v0 = vmulq_f32(glmm_splat_x(r0), l);
+  v1 = vmulq_f32(glmm_splat_x(r1), l);
+  v2 = vmulq_f32(glmm_splat_x(r2), l);
+  v3 = vmulq_f32(glmm_splat_x(r3), l);
+
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_y(r3), l, v3);
+
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_z(r3), l, v3);
+
+  v3 = glmm_fmadd(glmm_splat_w(r3), glmm_load(m1[3]), v3);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], v3);
+}
+
+CGLM_INLINE
+void
+glm_mul_rot_neon(mat4 m1, mat4 m2, mat4 dest) {
+  /* D = R * L (Column-Major) */
+
+  glmm_128 l, r0, r1, r2, v0, v1, v2;
+
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+
+  v0 = vmulq_f32(glmm_splat_x(r0), l);
+  v1 = vmulq_f32(glmm_splat_x(r1), l);
+  v2 = vmulq_f32(glmm_splat_x(r2), l);
+
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+  
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], glmm_load(m1[3]));
+}
+
+CGLM_INLINE
+void
+glm_inv_tr_neon(mat4 mat) {
+  float32x4x4_t vmat;
+  glmm_128      r0, r1, r2, x0;
+
+  vmat = vld4q_f32(mat[0]);
+  r0   = vmat.val[0];
+  r1   = vmat.val[1];
+  r2   = vmat.val[2];
+
+  x0 = glmm_fmadd(r0, glmm_splat_w(r0),
+                  glmm_fmadd(r1, glmm_splat_w(r1),
+                             vmulq_f32(r2, glmm_splat_w(r2))));
+  x0 = vnegq_f32(x0);
+
+  glmm_store(mat[0], r0);
+  glmm_store(mat[1], r1);
+  glmm_store(mat[2], r2);
+  glmm_store(mat[3], x0);
+  
+  mat[0][3] = 0.0f;
+  mat[1][3] = 0.0f;
+  mat[2][3] = 0.0f;
+  mat[3][3] = 1.0f;
+
+  /* TODO: ?
+  zo   = vget_high_f32(r3);
+  vst1_lane_f32(&mat[0][3], zo, 0);
+  vst1_lane_f32(&mat[1][3], zo, 0);
+  vst1_lane_f32(&mat[2][3], zo, 0);
+  vst1_lane_f32(&mat[3][3], zo, 1);
+  */
+}
+
+#endif
+#endif /* cglm_affine_neon_h */
--- a/include/cglm/simd/neon/mat2.h
+++ b/include/cglm/simd/neon/mat2.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_mat2_neon_h
+#define cglm_mat2_neon_h
+#if defined(__ARM_NEON_FP)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_mat2_mul_neon(mat2 m1, mat2 m2, mat2 dest) {
+  float32x4x2_t a1;
+  glmm_128 x0,  x1, x2;
+  float32x2_t   dc, ba;
+
+  x1 = glmm_load(m1[0]); /* d c b a */
+  x2 = glmm_load(m2[0]); /* h g f e */
+  
+  dc = vget_high_f32(x1);
+  ba = vget_low_f32(x1);
+
+  /* g g e e, h h f f */
+  a1 = vtrnq_f32(x2, x2);
+  
+  /*
+   dest[0][0] = a * e + c * f;
+   dest[0][1] = b * e + d * f;
+   dest[1][0] = a * g + c * h;
+   dest[1][1] = b * g + d * h;
+   */
+  x0 = glmm_fmadd(vcombine_f32(ba, ba), a1.val[0],
+                  vmulq_f32(vcombine_f32(dc, dc), a1.val[1]));
+
+  glmm_store(dest[0], x0);
+}
+
+#endif
+#endif /* cglm_mat2_neon_h */
--- a/include/cglm/simd/neon/mat4.h
+++ b/include/cglm/simd/neon/mat4.h
@@ -42,41 +42,42 @@ CGLM_INLINE
 void
 glm_mat4_mul_neon(mat4 m1, mat4 m2, mat4 dest) {
  /* D = R * L (Column-Major) */
-  float32x4_t l0, l1, l2, l3, r, d0, d1, d2, d3;

-  l0 = vld1q_f32(m2[0]);
-  l1 = vld1q_f32(m2[1]);
-  l2 = vld1q_f32(m2[2]);
-  l3 = vld1q_f32(m2[3]);
+  glmm_128 l, r0, r1, r2, r3, v0, v1, v2, v3;

-  r  = vld1q_f32(m1[0]);
-  d0 = vmulq_lane_f32(r, vget_low_f32(l0), 0);
-  d1 = vmulq_lane_f32(r, vget_low_f32(l1), 0);
-  d2 = vmulq_lane_f32(r, vget_low_f32(l2), 0);
-  d3 = vmulq_lane_f32(r, vget_low_f32(l3), 0);
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+  r3 = glmm_load(m2[3]);

-  r  = vld1q_f32(m1[1]);
-  d0 = vmlaq_lane_f32(d0, r, vget_low_f32(l0), 1);
-  d1 = vmlaq_lane_f32(d1, r, vget_low_f32(l1), 1);
-  d2 = vmlaq_lane_f32(d2, r, vget_low_f32(l2), 1);
-  d3 = vmlaq_lane_f32(d3, r, vget_low_f32(l3), 1);
+  v0 = vmulq_f32(glmm_splat_x(r0), l);
+  v1 = vmulq_f32(glmm_splat_x(r1), l);
+  v2 = vmulq_f32(glmm_splat_x(r2), l);
+  v3 = vmulq_f32(glmm_splat_x(r3), l);

-  r  = vld1q_f32(m1[2]);
-  d0 = vmlaq_lane_f32(d0, r, vget_high_f32(l0), 0);
-  d1 = vmlaq_lane_f32(d1, r, vget_high_f32(l1), 0);
-  d2 = vmlaq_lane_f32(d2, r, vget_high_f32(l2), 0);
-  d3 = vmlaq_lane_f32(d3, r, vget_high_f32(l3), 0);
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_y(r3), l, v3);

-  r  = vld1q_f32(m1[3]);
-  d0 = vmlaq_lane_f32(d0, r, vget_high_f32(l0), 1);
-  d1 = vmlaq_lane_f32(d1, r, vget_high_f32(l1), 1);
-  d2 = vmlaq_lane_f32(d2, r, vget_high_f32(l2), 1);
-  d3 = vmlaq_lane_f32(d3, r, vget_high_f32(l3), 1);
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_z(r3), l, v3);

-  vst1q_f32(dest[0], d0);
-  vst1q_f32(dest[1], d1);
-  vst1q_f32(dest[2], d2);
-  vst1q_f32(dest[3], d3);
+  l  = glmm_load(m1[3]);
+  v0 = glmm_fmadd(glmm_splat_w(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_w(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_w(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_w(r3), l, v3);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], v3);
 }

 CGLM_INLINE
@@ -101,5 +102,216 @@ glm_mat4_mulv_neon(mat4 m, vec4 v, vec4 dest) {
  vst1q_f32(dest, l0);
 }

+CGLM_INLINE
+float
+glm_mat4_det_neon(mat4 mat) {
+  float32x4_t   r0, r1, r2, r3, x0, x1, x2;
+  float32x2_t   ij, op, mn, kl, nn, mm, jj, ii, gh, ef, t12, t34;
+  float32x4x2_t a1;
+  float32x4_t   x3 = { 0.f, -0.f, 0.f, -0.f };
+
+  /* 127 <- 0, [square] det(A) = det(At) */
+  r0 = glmm_load(mat[0]);              /* d c b a */
+  r1 = vrev64q_f32(glmm_load(mat[1])); /* g h e f */
+  r2 = vrev64q_f32(glmm_load(mat[2])); /* l k i j */
+  r3 = vrev64q_f32(glmm_load(mat[3])); /* o p m n */
+
+  gh = vget_high_f32(r1);
+  ef = vget_low_f32(r1);
+  kl = vget_high_f32(r2);
+  ij = vget_low_f32(r2);
+  op = vget_high_f32(r3);
+  mn = vget_low_f32(r3);
+  mm = vdup_lane_f32(mn, 1);
+  nn = vdup_lane_f32(mn, 0);
+  ii = vdup_lane_f32(ij, 1);
+  jj = vdup_lane_f32(ij, 0);
+  
+  /*
+   t[1] = j * p - n * l;
+   t[2] = j * o - n * k;
+   t[3] = i * p - m * l;
+   t[4] = i * o - m * k;
+   */
+  x0 = glmm_fnmadd(vcombine_f32(kl, kl), vcombine_f32(nn, mm),
+                   vmulq_f32(vcombine_f32(op, op), vcombine_f32(jj, ii)));
+
+  t12 = vget_low_f32(x0);
+  t34 = vget_high_f32(x0);
+  
+  /* 1 3 1 3 2 4 2 4 */
+  a1 = vuzpq_f32(x0, x0);
+  
+  /*
+   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 = glmm_fnmadd(vcombine_f32(vdup_lane_f32(kl, 0), jj),
+                   vcombine_f32(vdup_lane_f32(op, 1), mm),
+                   vmulq_f32(vcombine_f32(vdup_lane_f32(op, 0), nn),
+                             vcombine_f32(vdup_lane_f32(kl, 1), ii)));
+
+  /*
+     a * (f * t[0] - g * t[1] + h * t[2])
+   - b * (e * t[0] - g * t[3] + h * t[4])
+   + c * (e * t[1] - f * t[3] + h * t[5])
+   - d * (e * t[2] - f * t[4] + g * t[5])
+   */
+  x2 = glmm_fnmadd(vcombine_f32(vdup_lane_f32(gh, 1), vdup_lane_f32(ef, 0)),
+                   vcombine_f32(vget_low_f32(a1.val[0]), t34),
+                   vmulq_f32(vcombine_f32(ef, vdup_lane_f32(ef, 1)),
+                             vcombine_f32(vget_low_f32(x1), t12)));
+
+  x2 = glmm_fmadd(vcombine_f32(vdup_lane_f32(gh, 0), gh),
+                  vcombine_f32(vget_low_f32(a1.val[1]), vget_high_f32(x1)), x2);
+
+  x2 = glmm_xor(x2, x3);
+
+  return glmm_hadd(vmulq_f32(x2, r0));
+}
+
+CGLM_INLINE
+void
+glm_mat4_inv_neon(mat4 mat, mat4 dest) {
+  float32x4_t   r0, r1, r2, r3,
+                v0, v1, v2, v3,
+                t0, t1, t2, t3, t4, t5,
+                x0, x1, x2, x3, x4, x5, x6, x7, x8;
+  float32x4x2_t a1;
+  float32x2_t   lp, ko, hg, jn, im, fe, ae, bf, cg, dh;
+  float32x4_t   x9 = { -0.f, 0.f, -0.f, 0.f };
+
+  x8 = vrev64q_f32(x9);
+
+  /* 127 <- 0 */
+  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 */
+  
+  /* l p k o, j n i m */
+  a1  = vzipq_f32(r3, r2);
+  
+  jn  = vget_high_f32(a1.val[0]);
+  im  = vget_low_f32(a1.val[0]);
+  lp  = vget_high_f32(a1.val[1]);
+  ko  = vget_low_f32(a1.val[1]);
+  hg  = vget_high_f32(r1);
+
+  x1  = vcombine_f32(vdup_lane_f32(lp, 0), lp);                   /* l p p p */
+  x2  = vcombine_f32(vdup_lane_f32(ko, 0), ko);                   /* k o o o */
+  x0  = vcombine_f32(vdup_lane_f32(lp, 1), vdup_lane_f32(hg, 1)); /* h h l l */
+  x3  = vcombine_f32(vdup_lane_f32(ko, 1), vdup_lane_f32(hg, 0)); /* g g k k */
+  
+  /* t1[0] = k * p - o * l;
+     t1[0] = k * p - o * l;
+     t2[0] = g * p - o * h;
+     t3[0] = g * l - k * h; */
+  t0 = glmm_fnmadd(x2, x0, vmulq_f32(x3, x1));
+
+  fe = vget_low_f32(r1);
+  x4 = vcombine_f32(vdup_lane_f32(jn, 0), jn);                   /* j n n n */
+  x5 = vcombine_f32(vdup_lane_f32(jn, 1), vdup_lane_f32(fe, 1)); /* f f j j */
+  
+  /* t1[1] = j * p - n * l;
+     t1[1] = j * p - n * l;
+     t2[1] = f * p - n * h;
+     t3[1] = f * l - j * h; */
+   t1 = glmm_fnmadd(x4, x0, vmulq_f32(x5, x1));
+  
+  /* t1[2] = j * o - n * k
+     t1[2] = j * o - n * k;
+     t2[2] = f * o - n * g;
+     t3[2] = f * k - j * g; */
+  t2 = glmm_fnmadd(x4, x3, vmulq_f32(x5, x2));
+  
+  x6 = vcombine_f32(vdup_lane_f32(im, 1), vdup_lane_f32(fe, 0)); /* e e i i */
+  x7 = vcombine_f32(vdup_lane_f32(im, 0), im);                   /* i m m m */
+  
+  /* t1[3] = i * p - m * l;
+     t1[3] = i * p - m * l;
+     t2[3] = e * p - m * h;
+     t3[3] = e * l - i * h; */
+  t3 = glmm_fnmadd(x7, x0, vmulq_f32(x6, x1));
+  
+  /* t1[4] = i * o - m * k;
+     t1[4] = i * o - m * k;
+     t2[4] = e * o - m * g;
+     t3[4] = e * k - i * g; */
+  t4 = glmm_fnmadd(x7, x3, vmulq_f32(x6, x2));
+  
+  /* t1[5] = i * n - m * j;
+     t1[5] = i * n - m * j;
+     t2[5] = e * n - m * f;
+     t3[5] = e * j - i * f; */
+  t5 = glmm_fnmadd(x7, x5, vmulq_f32(x6, x4));
+  
+  /* h d f b, g c e a */
+  a1 = vtrnq_f32(r0, r1);
+  
+  x4 = vrev64q_f32(a1.val[0]); /* c g a e */
+  x5 = vrev64q_f32(a1.val[1]); /* d h b f */
+
+  ae = vget_low_f32(x4);
+  cg = vget_high_f32(x4);
+  bf = vget_low_f32(x5);
+  dh = vget_high_f32(x5);
+  
+  x0 = vcombine_f32(ae, vdup_lane_f32(ae, 1)); /* a a a e */
+  x1 = vcombine_f32(bf, vdup_lane_f32(bf, 1)); /* b b b f */
+  x2 = vcombine_f32(cg, vdup_lane_f32(cg, 1)); /* c c c g */
+  x3 = vcombine_f32(dh, vdup_lane_f32(dh, 1)); /* d d d h */
+  
+  /*
+   dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
+   dest[0][1] =-(b * t1[0] - c * t1[1] + d * t1[2]);
+   dest[0][2] =  b * t2[0] - c * t2[1] + d * t2[2];
+   dest[0][3] =-(b * t3[0] - c * t3[1] + d * t3[2]); */
+  v0 = glmm_xor(glmm_fmadd(x3, t2, glmm_fnmadd(x2, t1, vmulq_f32(x1, t0))), x8);
+  
+  /*
+   dest[2][0] =  e * t1[1] - f * t1[3] + h * t1[5];
+   dest[2][1] =-(a * t1[1] - b * t1[3] + d * t1[5]);
+   dest[2][2] =  a * t2[1] - b * t2[3] + d * t2[5];
+   dest[2][3] =-(a * t3[1] - b * t3[3] + d * t3[5]);*/
+  v2 = glmm_xor(glmm_fmadd(x3, t5, glmm_fnmadd(x1, t3, vmulq_f32(x0, t1))), x8);
+
+  /*
+   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
+   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
+   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
+   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
+  v1 = glmm_xor(glmm_fmadd(x3, t4, glmm_fnmadd(x2, t3, vmulq_f32(x0, t0))), x9);
+  
+  /*
+   dest[3][0] =-(e * t1[2] - f * t1[4] + g * t1[5]);
+   dest[3][1] =  a * t1[2] - b * t1[4] + c * t1[5];
+   dest[3][2] =-(a * t2[2] - b * t2[4] + c * t2[5]);
+   dest[3][3] =  a * t3[2] - b * t3[4] + c * t3[5]; */
+  v3 = glmm_xor(glmm_fmadd(x2, t5, glmm_fnmadd(x1, t4, vmulq_f32(x0, t2))), x9);
+
+  /* determinant */
+  x0 = vcombine_f32(vget_low_f32(vzipq_f32(v0, v1).val[0]),
+                    vget_low_f32(vzipq_f32(v2, v3).val[0]));
+
+  /*
+  x0 = glmm_div(glmm_set1(1.0f), glmm_vhadd(vmulq_f32(x0, r0)));
+
+  glmm_store(dest[0], vmulq_f32(v0, x0));
+  glmm_store(dest[1], vmulq_f32(v1, x0));
+  glmm_store(dest[2], vmulq_f32(v2, x0));
+  glmm_store(dest[3], vmulq_f32(v3, x0));
+  */
+
+  x0 = glmm_vhadd(vmulq_f32(x0, r0));
+
+  glmm_store(dest[0], glmm_div(v0, x0));
+  glmm_store(dest[1], glmm_div(v1, x0));
+  glmm_store(dest[2], glmm_div(v2, x0));
+  glmm_store(dest[3], glmm_div(v3, x0));
+}
+
 #endif
 #endif /* cglm_mat4_neon_h */
--- a/include/cglm/simd/neon/quat.h
+++ b/include/cglm/simd/neon/quat.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_quat_neon_h
+#define cglm_quat_neon_h
+#if defined(__ARM_NEON_FP)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_quat_mul_neon(versor p, versor q, versor dest) {
+  /*
+   + (a1 b2 + b1 a2 + c1 d2 − d1 c2)i
+   + (a1 c2 − b1 d2 + c1 a2 + d1 b2)j
+   + (a1 d2 + b1 c2 − c1 b2 + d1 a2)k
+     a1 a2 − b1 b2 − c1 c2 − d1 d2
+   */
+
+  glmm_128 xp, xq, xqr, r, x, y, z, s2, s3;
+  glmm_128 s1 = {-0.f, 0.f, 0.f, -0.f};
+  float32x2_t   qh, ql;
+  
+  xp  = glmm_load(p); /* 3 2 1 0 */
+  xq  = glmm_load(q);
+
+  r   = vmulq_f32(glmm_splat_w(xp), xq);
+  x   = glmm_splat_x(xp);
+  y   = glmm_splat_y(xp);
+  z   = glmm_splat_z(xp);
+
+  ql  = vget_high_f32(s1);
+  s3  = vcombine_f32(ql, ql);
+  s2  = vzipq_f32(s3, s3).val[0];
+
+  xqr = vrev64q_f32(xq);
+  qh  = vget_high_f32(xqr);
+  ql  = vget_low_f32(xqr);
+
+  r = glmm_fmadd(glmm_xor(x, s3), vcombine_f32(qh, ql), r);
+  
+  r = glmm_fmadd(glmm_xor(y, s2), vcombine_f32(vget_high_f32(xq),
+                                               vget_low_f32(xq)), r);
+  
+  r = glmm_fmadd(glmm_xor(z, s1), vcombine_f32(ql, qh), r);
+
+  glmm_store(dest, r);
+}
+
+#endif
+#endif /* cglm_quat_neon_h */
--- a/include/cglm/simd/sse2/affine.h
+++ b/include/cglm/simd/sse2/affine.h
@@ -16,75 +16,76 @@ CGLM_INLINE
 void
 glm_mul_sse2(mat4 m1, mat4 m2, mat4 dest) {
  /* D = R * L (Column-Major) */
-  __m128 l0, l1, l2, l3, r;
+  glmm_128 l, r0, r1, r2, r3, v0, v1, v2, v3;

-  l0 = glmm_load(m1[0]);
-  l1 = glmm_load(m1[1]);
-  l2 = glmm_load(m1[2]);
-  l3 = glmm_load(m1[3]);
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+  r3 = glmm_load(m2[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)));
+  v0 = _mm_mul_ps(glmm_splat_x(r0), l);
+  v1 = _mm_mul_ps(glmm_splat_x(r1), l);
+  v2 = _mm_mul_ps(glmm_splat_x(r2), l);
+  v3 = _mm_mul_ps(glmm_splat_x(r3), l);

-  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)));
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_y(r3), l, v3);

-  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)));
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_z(r3), l, v3);

-  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))));
+  l  = glmm_load(m1[3]);
+  v3 = glmm_fmadd(glmm_splat_w(r3), l, v3);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], v3);
 }

 CGLM_INLINE
 void
 glm_mul_rot_sse2(mat4 m1, 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]);
+  glmm_128 l, r0, r1, r2, v0, v1, v2;

-  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)));
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);

-  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)));
+  v0 = _mm_mul_ps(glmm_splat_x(r0), l);
+  v1 = _mm_mul_ps(glmm_splat_x(r1), l);
+  v2 = _mm_mul_ps(glmm_splat_x(r2), l);

-  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)));
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);

-  glmm_store(dest[3], l3);
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], glmm_load(m1[3]));
 }

 CGLM_INLINE
 void
 glm_inv_tr_sse2(mat4 mat) {
-  __m128 r0, r1, r2, r3, x0, x1;
+  __m128 r0, r1, r2, r3, x0, x1, x2, x3, x4, x5;

  r0 = glmm_load(mat[0]);
  r1 = glmm_load(mat[1]);
@@ -94,10 +95,13 @@ glm_inv_tr_sse2(mat4 mat) {

  _MM_TRANSPOSE4_PS(r0, r1, r2, x1);

-  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));
+  x2 = glmm_shuff1(r3, 0, 0, 0, 0);
+  x3 = glmm_shuff1(r3, 1, 1, 1, 1);
+  x4 = glmm_shuff1(r3, 2, 2, 2, 2);
+  x5 = _mm_set1_ps(-0.f);
+
+  x0 = glmm_fmadd(r0, x2, glmm_fmadd(r1, x3, _mm_mul_ps(r2, x4)));
+  x0 = _mm_xor_ps(x0, x5);

  x0 = _mm_add_ps(x0, x1);

--- a/include/cglm/simd/sse2/mat2.h
+++ b/include/cglm/simd/sse2/mat2.h
@@ -15,22 +15,25 @@
 CGLM_INLINE
 void
 glm_mat2_mul_sse2(mat2 m1, mat2 m2, mat2 dest) {
-  __m128 x0, x1, x2;
+  __m128 x0, x1, x2, x3, x4;

  x1 = glmm_load(m1[0]); /* d c b a */
  x2 = glmm_load(m2[0]); /* h g f e */

+  x3 = glmm_shuff1(x2, 2, 2, 0, 0);
+  x4 = glmm_shuff1(x2, 3, 3, 1, 1);
+  x0 = _mm_movelh_ps(x1, x1);
+  x2 = _mm_movehl_ps(x1, x1);
+
  /*
   dest[0][0] = a * e + c * f;
   dest[0][1] = b * e + d * f;
   dest[1][0] = a * g + c * h;
   dest[1][1] = b * g + d * h;
   */
-  x0 = _mm_mul_ps(_mm_movelh_ps(x1, x1), glmm_shuff1(x2, 2, 2, 0, 0));
-  x1 = _mm_mul_ps(_mm_movehl_ps(x1, x1), glmm_shuff1(x2, 3, 3, 1, 1));
-  x1 = _mm_add_ps(x0, x1);
+  x0 = glmm_fmadd(x0, x3, _mm_mul_ps(x2, x4));

-  glmm_store(dest[0], x1);
+  glmm_store(dest[0], x0);
 }

 CGLM_INLINE
--- a/include/cglm/simd/sse2/mat3.h
+++ b/include/cglm/simd/sse2/mat3.h
@@ -15,44 +15,61 @@
 CGLM_INLINE
 void
 glm_mat3_mul_sse2(mat3 m1, mat3 m2, mat3 dest) {
-  __m128 l0, l1, l2;
-  __m128 r0, r1, r2;
-  __m128 x0, x1, x2;
+  __m128 l0, l1, l2, r0, r1, r2, x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
  
  l0 = _mm_loadu_ps(m1[0]);
  l1 = _mm_loadu_ps(&m1[1][1]);
-  l2 = _mm_set1_ps(m1[2][2]);

  r0 = _mm_loadu_ps(m2[0]);
  r1 = _mm_loadu_ps(&m2[1][1]);
-  r2 = _mm_set1_ps(m2[2][2]);

-  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);
+  x8 = glmm_shuff1(l0, 0, 2, 1, 0);                     /* a00 a02 a01 a00 */
+  x1 = glmm_shuff1(r0, 3, 0, 0, 0);                     /* b10 b00 b00 b00 */
+  x2 = _mm_shuffle_ps(l0, l1, _MM_SHUFFLE(1, 0, 3, 3)); /* a12 a11 a10 a10 */
+  x3 = _mm_shuffle_ps(r0, r1, _MM_SHUFFLE(2, 0, 3, 1)); /* b20 b11 b10 b01 */
+  x0 = _mm_mul_ps(x8, x1);

-  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)));
+  x6 = glmm_shuff1(l0, 1, 0, 2, 1);                     /* a01 a00 a02 a01 */
+  x7 = glmm_shuff1(x3, 3, 3, 1, 1);                     /* b20 b20 b10 b10 */
+  l2 = _mm_load_ss(&m1[2][2]);
+  r2 = _mm_load_ss(&m2[2][2]);
+  x1 = _mm_mul_ps(x6, x7);
+  l2 = glmm_shuff1(l2, 0, 0, 1, 0);                     /* a22 a22 0.f a22 */
+  r2 = glmm_shuff1(r2, 0, 0, 1, 0);                     /* b22 b22 0.f b22 */

-  x0 = _mm_add_ps(x0,
-                  _mm_mul_ps(x2, glmm_shuff2(r0, r1, 1, 1, 2, 2, 2, 0, 0, 0)));
+  x4 = glmm_shuff1(x2, 0, 3, 2, 0);                     /* a10 a12 a11 a10 */
+  x5 = glmm_shuff1(x2, 2, 0, 3, 2);                     /* a11 a10 a12 a11 */
+  x6 = glmm_shuff1(x3, 2, 0, 0, 0);                     /* b11 b01 b01 b01 */
+  x2 = glmm_shuff1(r1, 3, 3, 0, 0);                     /* b21 b21 b11 b11 */

-  _mm_storeu_ps(dest[0], x0);
+  x8 = _mm_unpackhi_ps(x8, x4);                         /* a10 a00 a12 a02 */
+  x9 = _mm_unpackhi_ps(x7, x2);                         /* b21 b20 b21 b20 */

-  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(glmm_shuff1(x1, 1, 0, 2, 1),
-                             glmm_shuff1(r1, 3, 3, 0, 0)));
+  x0 = glmm_fmadd(x4, x6, x0);
+  x1 = glmm_fmadd(x5, x2, x1);

-  x0 = _mm_add_ps(x0,
-                  _mm_mul_ps(glmm_shuff1(x2, 1, 0, 2, 1),
-                             _mm_shuffle_ps(r1, r2, _MM_SHUFFLE(0, 0, 1, 1))));
+  x2 = _mm_movehl_ps(l2, l1);                           /* a22 a22 a21 a20 */
+  x3 = glmm_shuff1(x2, 0, 2, 1, 0);                     /* a20 a22 a21 a20 */
+  x2 = glmm_shuff1(x2, 1, 0, 2, 1);                     /* a21 a20 a22 a21 */
+  x4 = _mm_shuffle_ps(r0, r1, _MM_SHUFFLE(1, 1, 2, 2)); /* b12 b12 b02 b02 */
  
-  _mm_storeu_ps(&dest[1][1], x0);
+  x5 = glmm_shuff1(x4, 3, 0, 0, 0);                     /* b12 b02 b02 b02 */
+  x4 = _mm_movehl_ps(r2, x4);                           /* b22 b22 b12 b12 */
+  x0 = glmm_fmadd(x3, x5, x0);
+  x1 = glmm_fmadd(x2, x4, x1);

-  dest[2][2] = m1[0][2] * m2[2][0]
-             + m1[1][2] * m2[2][1]
-             + m1[2][2] * m2[2][2];
+  /*
+   Dot Product : dest[2][2] =  a02 * b20 +
+                               a12 * b21 +
+                               a22 * b22 +
+                               0   * 00                                    */
+  x2 = _mm_movelh_ps(x8, l2);                           /* 0.f a22 a12 a02 */
+  x3 = _mm_movelh_ps(x9, r2);                           /* 0.f b22 b21 b20 */
+  x2 = glmm_vdots(x2, x3);
+
+  _mm_storeu_ps(&dest[0][0], x0);
+  _mm_storeu_ps(&dest[1][1], x1);
+  _mm_store_ss (&dest[2][2], x2);
 }

 #endif
--- a/include/cglm/simd/sse2/mat4.h
+++ b/include/cglm/simd/sse2/mat4.h
@@ -49,53 +49,65 @@ void
 glm_mat4_mul_sse2(mat4 m1, mat4 m2, mat4 dest) {
  /* D = R * L (Column-Major) */

-  __m128 l0, l1, l2, l3, r;
+  glmm_128 l, r0, r1, r2, r3, v0, v1, v2, v3;

-  l0 = glmm_load(m1[0]);
-  l1 = glmm_load(m1[1]);
-  l2 = glmm_load(m1[2]);
-  l3 = glmm_load(m1[3]);
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+  r3 = glmm_load(m2[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_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))));
+  v0 = _mm_mul_ps(glmm_splat_x(r0), l);
+  v1 = _mm_mul_ps(glmm_splat_x(r1), l);
+  v2 = _mm_mul_ps(glmm_splat_x(r2), l);
+  v3 = _mm_mul_ps(glmm_splat_x(r3), l);

-  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))));
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_y(r3), l, v3);
+
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_z(r3), l, v3);
+
+  l  = glmm_load(m1[3]);
+  v0 = glmm_fmadd(glmm_splat_w(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_w(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_w(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_w(r3), l, v3);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], v3);
 }

 CGLM_INLINE
 void
 glm_mat4_mulv_sse2(mat4 m, vec4 v, vec4 dest) {
-  __m128 x0, x1, x2;
+  __m128 x0, x1, m0, m1, m2, m3, v0, v1, v2, v3;
+
+  m0 = glmm_load(m[0]);
+  m1 = glmm_load(m[1]);
+  m2 = glmm_load(m[2]);
+  m3 = glmm_load(m[3]);

  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)));
+  v0 = glmm_splat_x(x0);
+  v1 = glmm_splat_y(x0);
+  v2 = glmm_splat_z(x0);
+  v3 = glmm_splat_w(x0);

-  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)));
+  x1 = _mm_mul_ps(m3, v3);
+  x1 = glmm_fmadd(m2, v2, x1);
+  x1 = glmm_fmadd(m1, v1, x1);
+  x1 = glmm_fmadd(m0, v0, x1);

-  glmm_store(dest, _mm_add_ps(x1, x2));
+  glmm_store(dest, x1);
 }

 CGLM_INLINE
@@ -115,20 +127,18 @@ 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(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)));
+  x0 = glmm_fnmadd(glmm_shuff1(r3, 0, 0, 1, 1), glmm_shuff1(r2, 2, 3, 2, 3),
+                   _mm_mul_ps(glmm_shuff1(r2, 0, 0, 1, 1),
+                              glmm_shuff1(r3, 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(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)));
+  x1 = glmm_fnmadd(glmm_shuff1(r3, 0, 0, 2, 2), glmm_shuff1(r2, 1, 1, 3, 3),
+                   _mm_mul_ps(glmm_shuff1(r2, 0, 0, 2, 2),
+                              glmm_shuff1(r3, 1, 1, 3, 3)));

  /*
     a * (f * t[0] - g * t[1] + h * t[2])
@@ -136,21 +146,16 @@ 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(glmm_shuff1(r1, 0, 0, 0, 1),
-                             _mm_shuffle_ps(x1, x0, _MM_SHUFFLE(1, 0, 0, 0))),
-                  _mm_mul_ps(glmm_shuff1(r1, 1, 1, 2, 2),
-                             glmm_shuff1(x0, 3, 2, 2, 0)));
+  x2 = glmm_fnmadd(glmm_shuff1(r1, 1, 1, 2, 2), glmm_shuff1(x0, 3, 2, 2, 0),
+                   _mm_mul_ps(glmm_shuff1(r1, 0, 0, 0, 1),
+                              _mm_shuffle_ps(x1, x0, _MM_SHUFFLE(1, 0, 0, 0))));
+  x2 = glmm_fmadd(glmm_shuff1(r1, 2, 3, 3, 3),
+                  _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 2, 3, 1)),
+                  x2);
  
-  x2 = _mm_add_ps(x2,
-                  _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, glmm_shuff1(x0, 0, 1, 2, 3));
-  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 3, 3, 1));
-
-  return _mm_cvtss_f32(x0);
+  return glmm_hadd(_mm_mul_ps(x2, r0));
 }

 CGLM_INLINE
@@ -159,7 +164,10 @@ glm_mat4_inv_fast_sse2(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;
+         x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
+
+  x8 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f);
+  x9 = glmm_shuff1(x8, 2, 1, 2, 1);

  /* 127 <- 0 */
  r0 = glmm_load(mat[0]); /* d c b a */
@@ -167,109 +175,118 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
  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 = glmm_shuff1(x0, 1, 3, 3, 3);                      /* l p p p */
+  x0 = _mm_movehl_ps(r3, r2);                            /* p o l k */
+  x3 = _mm_movelh_ps(r2, r3);                            /* n m j i */
+  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 */
+  x4 = glmm_shuff1(x3, 1, 3, 3, 3);                      /* j n n n */
+  x7 = glmm_shuff1(x3, 0, 2, 2, 2);                      /* i m m m */
+
+  x6 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(0, 0, 0, 0));  /* e e i i */
+  x5 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(1, 1, 1, 1));  /* f f j j */
  x3 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(2, 2, 2, 2));  /* g g k k */
+  x0 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(3, 3, 3, 3));  /* h h l l */
+  
+  t0 = _mm_mul_ps(x3, x1);
+  t1 = _mm_mul_ps(x5, x1);
+  t2 = _mm_mul_ps(x5, x2);
+  t3 = _mm_mul_ps(x6, x1);
+  t4 = _mm_mul_ps(x6, x2);
+  t5 = _mm_mul_ps(x6, x4);
  
  /* t1[0] = k * p - o * l;
     t1[0] = k * p - o * l;
     t2[0] = g * p - o * h;
     t3[0] = g * l - k * h; */
-  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 = 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 */
+  t0 = glmm_fnmadd(x2, x0, t0);
  
  /* t1[1] = j * p - n * l;
     t1[1] = j * p - n * l;
     t2[1] = f * p - n * h;
     t3[1] = f * l - j * h; */
-  t1 = _mm_sub_ps(_mm_mul_ps(x5, x1), _mm_mul_ps(x4, x0));
+   t1 = glmm_fnmadd(x4, x0, t1);
  
  /* t1[2] = j * o - n * k
     t1[2] = j * o - n * k;
     t2[2] = f * o - n * g;
     t3[2] = f * k - j * g; */
-  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 = glmm_shuff2(r3, r2, 0, 0, 0, 0, 2, 0, 0, 0);     /* i m m m */
+  t2 = glmm_fnmadd(x4, x3, t2);
  
  /* t1[3] = i * p - m * l;
     t1[3] = i * p - m * l;
     t2[3] = e * p - m * h;
     t3[3] = e * l - i * h; */
-  t3 = _mm_sub_ps(_mm_mul_ps(x6, x1), _mm_mul_ps(x7, x0));
+  t3 = glmm_fnmadd(x7, x0, t3);
  
  /* t1[4] = i * o - m * k;
     t1[4] = i * o - m * k;
     t2[4] = e * o - m * g;
     t3[4] = e * k - i * g; */
-  t4 = _mm_sub_ps(_mm_mul_ps(x6, x2), _mm_mul_ps(x7, x3));
+  t4 = glmm_fnmadd(x7, x3, t4);
  
  /* t1[5] = i * n - m * j;
     t1[5] = i * n - m * j;
     t2[5] = e * n - m * f;
     t3[5] = e * j - i * f; */
-  t5 = _mm_sub_ps(_mm_mul_ps(x6, x4), _mm_mul_ps(x7, x5));
+  t5 = glmm_fnmadd(x7, x5, t5);
  
-  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 */
+  x4 = _mm_movelh_ps(r0, r1);        /* f e b a */
+  x5 = _mm_movehl_ps(r1, r0);        /* h g d c */
+  
+  x0 = glmm_shuff1(x4, 0, 0, 0, 2);  /* a a a e */
+  x1 = glmm_shuff1(x4, 1, 1, 1, 3);  /* b b b f */
+  x2 = glmm_shuff1(x5, 0, 0, 0, 2);  /* c c c g */
+  x3 = glmm_shuff1(x5, 1, 1, 1, 3);  /* d d d h */
+  
+  v2 = _mm_mul_ps(x0, t1);
+  v1 = _mm_mul_ps(x0, t0);
+  v3 = _mm_mul_ps(x0, t2);
+  v0 = _mm_mul_ps(x1, t0);
+  
+  v2 = glmm_fnmadd(x1, t3, v2);
+  v3 = glmm_fnmadd(x1, t4, v3);
+  v0 = glmm_fnmadd(x2, t1, v0);
+  v1 = glmm_fnmadd(x2, t3, v1);
+  
+  v3 = glmm_fmadd(x2, t5, v3);
+  v0 = glmm_fmadd(x3, t2, v0);
+  v2 = glmm_fmadd(x3, t5, v2);
+  v1 = glmm_fmadd(x3, t4, v1);

  /*
   dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
   dest[0][1] =-(b * t1[0] - c * t1[1] + d * t1[2]);
   dest[0][2] =  b * t2[0] - c * t2[1] + d * t2[2];
   dest[0][3] =-(b * t3[0] - c * t3[1] + d * t3[2]); */
-  v0 = _mm_add_ps(_mm_mul_ps(x3, t2),
-                  _mm_sub_ps(_mm_mul_ps(x1, t0),
-                             _mm_mul_ps(x2, t1)));
-  v0 = _mm_xor_ps(v0, _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
-
-  /*
-   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
-   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
-   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
-   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
-  v1 = _mm_add_ps(_mm_mul_ps(x3, t4),
-                  _mm_sub_ps(_mm_mul_ps(x0, t0),
-                             _mm_mul_ps(x2, t3)));
-  v1 = _mm_xor_ps(v1, _mm_set_ps(0.f, -0.f, 0.f, -0.f));
+  v0 = _mm_xor_ps(v0, x8);
  
  /*
   dest[2][0] =  e * t1[1] - f * t1[3] + h * t1[5];
   dest[2][1] =-(a * t1[1] - b * t1[3] + d * t1[5]);
   dest[2][2] =  a * t2[1] - b * t2[3] + d * t2[5];
   dest[2][3] =-(a * t3[1] - b * t3[3] + d * t3[5]);*/
-  v2 = _mm_add_ps(_mm_mul_ps(x3, t5),
-                  _mm_sub_ps(_mm_mul_ps(x0, t1),
-                             _mm_mul_ps(x1, t3)));
-  v2 = _mm_xor_ps(v2, _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
+  v2 = _mm_xor_ps(v2, x8);
+
+  /*
+   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
+   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
+   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
+   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
+  v1 = _mm_xor_ps(v1, x9);

  /*
   dest[3][0] =-(e * t1[2] - f * t1[4] + g * t1[5]);
   dest[3][1] =  a * t1[2] - b * t1[4] + c * t1[5];
   dest[3][2] =-(a * t2[2] - b * t2[4] + c * t2[5]);
   dest[3][3] =  a * t3[2] - b * t3[4] + c * t3[5]; */
-  v3 = _mm_add_ps(_mm_mul_ps(x2, t5),
-                  _mm_sub_ps(_mm_mul_ps(x0, t2),
-                             _mm_mul_ps(x1, t4)));
-  v3 = _mm_xor_ps(v3, _mm_set_ps(0.f, -0.f, 0.f, -0.f));
+  v3 = _mm_xor_ps(v3, x9);

  /* determinant */
  x0 = _mm_shuffle_ps(v0, v1, _MM_SHUFFLE(0, 0, 0, 0));
  x1 = _mm_shuffle_ps(v2, v3, _MM_SHUFFLE(0, 0, 0, 0));
  x0 = _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 0, 2, 0));

-  x0 = _mm_mul_ps(x0, r0);
-  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);
+  x0 = _mm_rcp_ps(glmm_vhadd(_mm_mul_ps(x0, r0)));

  glmm_store(dest[0], _mm_mul_ps(v0, x0));
  glmm_store(dest[1], _mm_mul_ps(v1, x0));
@@ -283,7 +300,10 @@ glm_mat4_inv_sse2(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;
+         x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
+
+  x8 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f);
+  x9 = glmm_shuff1(x8, 2, 1, 2, 1);

  /* 127 <- 0 */
  r0 = glmm_load(mat[0]); /* d c b a */
@@ -291,109 +311,118 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
  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 = glmm_shuff1(x0, 1, 3, 3, 3);                      /* l p p p */
+  x0 = _mm_movehl_ps(r3, r2);                            /* p o l k */
+  x3 = _mm_movelh_ps(r2, r3);                            /* n m j i */
+  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 */
+  x4 = glmm_shuff1(x3, 1, 3, 3, 3);                      /* j n n n */
+  x7 = glmm_shuff1(x3, 0, 2, 2, 2);                      /* i m m m */
+
+  x6 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(0, 0, 0, 0));  /* e e i i */
+  x5 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(1, 1, 1, 1));  /* f f j j */
  x3 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(2, 2, 2, 2));  /* g g k k */
+  x0 = _mm_shuffle_ps(r2, r1, _MM_SHUFFLE(3, 3, 3, 3));  /* h h l l */
+  
+  t0 = _mm_mul_ps(x3, x1);
+  t1 = _mm_mul_ps(x5, x1);
+  t2 = _mm_mul_ps(x5, x2);
+  t3 = _mm_mul_ps(x6, x1);
+  t4 = _mm_mul_ps(x6, x2);
+  t5 = _mm_mul_ps(x6, x4);
  
  /* t1[0] = k * p - o * l;
     t1[0] = k * p - o * l;
     t2[0] = g * p - o * h;
     t3[0] = g * l - k * h; */
-  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 = 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 */
+  t0 = glmm_fnmadd(x2, x0, t0);
  
  /* t1[1] = j * p - n * l;
     t1[1] = j * p - n * l;
     t2[1] = f * p - n * h;
     t3[1] = f * l - j * h; */
-  t1 = _mm_sub_ps(_mm_mul_ps(x5, x1), _mm_mul_ps(x4, x0));
+   t1 = glmm_fnmadd(x4, x0, t1);
  
  /* t1[2] = j * o - n * k
     t1[2] = j * o - n * k;
     t2[2] = f * o - n * g;
     t3[2] = f * k - j * g; */
-  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 = glmm_shuff2(r3, r2, 0, 0, 0, 0, 2, 0, 0, 0);     /* i m m m */
+  t2 = glmm_fnmadd(x4, x3, t2);
  
  /* t1[3] = i * p - m * l;
     t1[3] = i * p - m * l;
     t2[3] = e * p - m * h;
     t3[3] = e * l - i * h; */
-  t3 = _mm_sub_ps(_mm_mul_ps(x6, x1), _mm_mul_ps(x7, x0));
+  t3 = glmm_fnmadd(x7, x0, t3);
  
  /* t1[4] = i * o - m * k;
     t1[4] = i * o - m * k;
     t2[4] = e * o - m * g;
     t3[4] = e * k - i * g; */
-  t4 = _mm_sub_ps(_mm_mul_ps(x6, x2), _mm_mul_ps(x7, x3));
+  t4 = glmm_fnmadd(x7, x3, t4);
  
  /* t1[5] = i * n - m * j;
     t1[5] = i * n - m * j;
     t2[5] = e * n - m * f;
     t3[5] = e * j - i * f; */
-  t5 = _mm_sub_ps(_mm_mul_ps(x6, x4), _mm_mul_ps(x7, x5));
+  t5 = glmm_fnmadd(x7, x5, t5);
  
-  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 */
+  x4 = _mm_movelh_ps(r0, r1);        /* f e b a */
+  x5 = _mm_movehl_ps(r1, r0);        /* h g d c */
+  
+  x0 = glmm_shuff1(x4, 0, 0, 0, 2);  /* a a a e */
+  x1 = glmm_shuff1(x4, 1, 1, 1, 3);  /* b b b f */
+  x2 = glmm_shuff1(x5, 0, 0, 0, 2);  /* c c c g */
+  x3 = glmm_shuff1(x5, 1, 1, 1, 3);  /* d d d h */
+  
+  v2 = _mm_mul_ps(x0, t1);
+  v1 = _mm_mul_ps(x0, t0);
+  v3 = _mm_mul_ps(x0, t2);
+  v0 = _mm_mul_ps(x1, t0);
+  
+  v2 = glmm_fnmadd(x1, t3, v2);
+  v3 = glmm_fnmadd(x1, t4, v3);
+  v0 = glmm_fnmadd(x2, t1, v0);
+  v1 = glmm_fnmadd(x2, t3, v1);
+  
+  v3 = glmm_fmadd(x2, t5, v3);
+  v0 = glmm_fmadd(x3, t2, v0);
+  v2 = glmm_fmadd(x3, t5, v2);
+  v1 = glmm_fmadd(x3, t4, v1);

  /*
   dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
   dest[0][1] =-(b * t1[0] - c * t1[1] + d * t1[2]);
   dest[0][2] =  b * t2[0] - c * t2[1] + d * t2[2];
   dest[0][3] =-(b * t3[0] - c * t3[1] + d * t3[2]); */
-  v0 = _mm_add_ps(_mm_mul_ps(x3, t2),
-                  _mm_sub_ps(_mm_mul_ps(x1, t0),
-                             _mm_mul_ps(x2, t1)));
-  v0 = _mm_xor_ps(v0, _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
-
-  /*
-   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
-   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
-   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
-   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
-  v1 = _mm_add_ps(_mm_mul_ps(x3, t4),
-                  _mm_sub_ps(_mm_mul_ps(x0, t0),
-                             _mm_mul_ps(x2, t3)));
-  v1 = _mm_xor_ps(v1, _mm_set_ps(0.f, -0.f, 0.f, -0.f));
+  v0 = _mm_xor_ps(v0, x8);
  
  /*
   dest[2][0] =  e * t1[1] - f * t1[3] + h * t1[5];
   dest[2][1] =-(a * t1[1] - b * t1[3] + d * t1[5]);
   dest[2][2] =  a * t2[1] - b * t2[3] + d * t2[5];
   dest[2][3] =-(a * t3[1] - b * t3[3] + d * t3[5]);*/
-  v2 = _mm_add_ps(_mm_mul_ps(x3, t5),
-                  _mm_sub_ps(_mm_mul_ps(x0, t1),
-                             _mm_mul_ps(x1, t3)));
-  v2 = _mm_xor_ps(v2, _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
+  v2 = _mm_xor_ps(v2, x8);
+
+  /*
+   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
+   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
+   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
+   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
+  v1 = _mm_xor_ps(v1, x9);

  /*
   dest[3][0] =-(e * t1[2] - f * t1[4] + g * t1[5]);
   dest[3][1] =  a * t1[2] - b * t1[4] + c * t1[5];
   dest[3][2] =-(a * t2[2] - b * t2[4] + c * t2[5]);
   dest[3][3] =  a * t3[2] - b * t3[4] + c * t3[5]; */
-  v3 = _mm_add_ps(_mm_mul_ps(x2, t5),
-                  _mm_sub_ps(_mm_mul_ps(x0, t2),
-                             _mm_mul_ps(x1, t4)));
-  v3 = _mm_xor_ps(v3, _mm_set_ps(0.f, -0.f, 0.f, -0.f));
+  v3 = _mm_xor_ps(v3, x9);

  /* determinant */
  x0 = _mm_shuffle_ps(v0, v1, _MM_SHUFFLE(0, 0, 0, 0));
  x1 = _mm_shuffle_ps(v2, v3, _MM_SHUFFLE(0, 0, 0, 0));
  x0 = _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 0, 2, 0));

-  x0 = _mm_mul_ps(x0, r0);
-  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);
+  x0 = _mm_div_ps(_mm_set1_ps(1.0f), glmm_vhadd(_mm_mul_ps(x0, r0)));

  glmm_store(dest[0], _mm_mul_ps(v0, x0));
  glmm_store(dest[1], _mm_mul_ps(v1, x0));
--- a/include/cglm/simd/sse2/quat.h
+++ b/include/cglm/simd/sse2/quat.h
@@ -22,25 +22,33 @@ glm_quat_mul_sse2(versor p, versor q, versor dest) {
     a1 a2 − b1 b2 − c1 c2 − d1 d2
   */

-  __m128 xp, xq, x0, r;
+  __m128 xp, xq, x1, x2, x3, r, x, y, z;

  xp = glmm_load(p); /* 3 2 1 0 */
  xq = glmm_load(q);
+  x1 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f); /* TODO: _mm_set1_ss() + shuff ? */
+  r  = _mm_mul_ps(glmm_splat_w(xp), xq);
  
-  r  = _mm_mul_ps(glmm_shuff1x(xp, 3), xq);
+  x2 = _mm_unpackhi_ps(x1, x1);
+  x3 = glmm_shuff1(x1, 3, 2, 0, 1);
+  x  = glmm_splat_x(xp);
+  y  = glmm_splat_y(xp);
+  z  = glmm_splat_z(xp);

-  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)));
+  x  = _mm_xor_ps(x, x1);
+  y  = _mm_xor_ps(y, x2);
+  z  = _mm_xor_ps(z, x3);
  
-  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)));
+  x1 = glmm_shuff1(xq, 0, 1, 2, 3);
+  x2 = glmm_shuff1(xq, 1, 0, 3, 2);
+  x3 = glmm_shuff1(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)));
+  r  = glmm_fmadd(x, x1, r);
+  r  = glmm_fmadd(y, x2, r);
+  r  = glmm_fmadd(z, x3, r);

  glmm_store(dest, r);
 }

-
 #endif
 #endif /* cglm_quat_simd_h */
--- a/include/cglm/simd/x86.h
+++ b/include/cglm/simd/x86.h
@@ -18,6 +18,9 @@
 #  define glmm_store(p, a)  _mm_store_ps(p, a)
 #endif

+#define glmm_set1(x) _mm_set1_ps(x)
+#define glmm_128     __m128
+
 #ifdef CGLM_USE_INT_DOMAIN
 #  define glmm_shuff1(xmm, z, y, x, w)                                        \
     _mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(xmm),                \
@@ -27,7 +30,16 @@
       _mm_shuffle_ps(xmm, xmm, _MM_SHUFFLE(z, y, x, w))
 #endif

+#define glmm_splat(x, lane) glmm_shuff1(x, lane, lane, lane, lane)
+
+#define glmm_splat_x(x) glmm_splat(x, 0)
+#define glmm_splat_y(x) glmm_splat(x, 1)
+#define glmm_splat_z(x) glmm_splat(x, 2)
+#define glmm_splat_w(x) glmm_splat(x, 3)
+
+/* glmm_shuff1x() is DEPRECATED!, use glmm_splat() */
 #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)
@@ -48,6 +60,15 @@ glmm_abs(__m128 x) {
  return _mm_andnot_ps(_mm_set1_ps(-0.0f), x);
 }

+static inline
+__m128
+glmm_vhadd(__m128 v) {
+  __m128 x0;
+  x0 = _mm_add_ps(v,  glmm_shuff1(v, 0, 1, 2, 3));
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 0, 0, 1));
+  return x0;
+}
+
 static inline
 __m128
 glmm_vhadds(__m128 v) {
@@ -80,7 +101,7 @@ glmm_vhmin(__m128 v) {
  __m128 x0, x1, x2;
  x0 = _mm_movehl_ps(v, v);     /* [2, 3, 2, 3] */
  x1 = _mm_min_ps(x0, v);       /* [0|2, 1|3, 2|2, 3|3] */
-  x2 = glmm_shuff1x(x1, 1);     /* [1|3, 1|3, 1|3, 1|3] */
+  x2 = glmm_splat(x1, 1);       /* [1|3, 1|3, 1|3, 1|3] */
  return _mm_min_ss(x1, x2);
 }

@@ -96,7 +117,7 @@ glmm_vhmax(__m128 v) {
  __m128 x0, x1, x2;
  x0 = _mm_movehl_ps(v, v);     /* [2, 3, 2, 3] */
  x1 = _mm_max_ps(x0, v);       /* [0|2, 1|3, 2|2, 3|3] */
-  x2 = glmm_shuff1x(x1, 1);     /* [1|3, 1|3, 1|3, 1|3] */
+  x2 = glmm_splat(x1, 1);       /* [1|3, 1|3, 1|3, 1|3] */
  return _mm_max_ss(x1, x2);
 }

@@ -188,5 +209,99 @@ glmm_store3(float v[3], __m128 vx) {
  _mm_store_ss(&v[2], glmm_shuff1(vx, 2, 2, 2, 2));
 }

+static inline
+__m128
+glmm_div(__m128 a, __m128 b) {
+  return _mm_div_ps(a, b);
+}
+
+/* enable FMA macro for MSVC? */
+#if defined(_MSC_VER) && !defined(__FMA__) && defined(__AVX2__)
+#  define __FMA__ 1
+#endif
+
+static inline
+__m128
+glmm_fmadd(__m128 a, __m128 b, __m128 c) {
+#ifdef __FMA__
+  return _mm_fmadd_ps(a, b, c);
+#else
+  return _mm_add_ps(c, _mm_mul_ps(a, b));
+#endif
+}
+
+static inline
+__m128
+glmm_fnmadd(__m128 a, __m128 b, __m128 c) {
+#ifdef __FMA__
+  return _mm_fnmadd_ps(a, b, c);
+#else
+  return _mm_sub_ps(c, _mm_mul_ps(a, b));
+#endif
+}
+
+static inline
+__m128
+glmm_fmsub(__m128 a, __m128 b, __m128 c) {
+#ifdef __FMA__
+  return _mm_fmsub_ps(a, b, c);
+#else
+  return _mm_sub_ps(_mm_mul_ps(a, b), c);
+#endif
+}
+
+static inline
+__m128
+glmm_fnmsub(__m128 a, __m128 b, __m128 c) {
+#ifdef __FMA__
+  return _mm_fnmsub_ps(a, b, c);
+#else
+  return _mm_xor_ps(_mm_add_ps(_mm_mul_ps(a, b), c), _mm_set1_ps(-0.0f));
+#endif
+}
+
+#if defined(__AVX__)
+static inline
+__m256
+glmm256_fmadd(__m256 a, __m256 b, __m256 c) {
+#ifdef __FMA__
+  return _mm256_fmadd_ps(a, b, c);
+#else
+  return _mm256_add_ps(c, _mm256_mul_ps(a, b));
+#endif
+}
+
+static inline
+__m256
+glmm256_fnmadd(__m256 a, __m256 b, __m256 c) {
+#ifdef __FMA__
+  return _mm256_fnmadd_ps(a, b, c);
+#else
+  return _mm256_sub_ps(c, _mm256_mul_ps(a, b));
+#endif
+}
+
+static inline
+__m256
+glmm256_fmsub(__m256 a, __m256 b, __m256 c) {
+#ifdef __FMA__
+  return _mm256_fmsub_ps(a, b, c);
+#else
+  return _mm256_sub_ps(_mm256_mul_ps(a, b), c);
+#endif
+}
+
+static inline
+__m256
+glmm256_fnmsub(__m256 a, __m256 b, __m256 c) {
+#ifdef __FMA__
+  return _mm256_fmsub_ps(a, b, c);
+#else
+  return _mm256_xor_ps(_mm256_sub_ps(_mm256_mul_ps(a, b), c),
+                       _mm256_set1_ps(-0.0f));
+#endif
+}
+#endif
+
 #endif
 #endif /* cglm_simd_x86_h */
--- a/Show More
+++ b/Show More