fix enabling FMA macro for MSVC

Optimizations with FMA

.gitattributes

@@ -0,0 +1 @@
+*.h linguist-language=C

.github/FUNDING.yml

@@ -0,0 +1,8 @@
+# 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
+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
+custom: # Replace with a single custom sponsorship URL

.gitignore

@@ -51,7 +51,6 @@ cscope.*
 test/*.trs
 test/test_*
 *.log
-test-*
 test/.libs/*
 test/tests
 cglm_arm/*
@@ -69,3 +68,11 @@ win/cglm_test_*
 win/x64
 win/x85
 win/Debug
+cglm-test-ios*
+/cglm.pc
+test-driver
+Default-568h@2x.png
+build/
+conftest.dir/*
+confdefs.h
+*.xcuserdatad

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "test/lib/cmocka"]
-	path = test/lib/cmocka
-	url = git://git.cryptomilk.org/projects/cmocka.git

.travis.yml

@@ -4,6 +4,12 @@ os:
   - linux
   - osx
 
+arch:
+  - amd64
+  - ppc64le
+  - s390x
+  - arm64
+
 sudo: required
 dist: trusty
 
@@ -37,10 +43,9 @@ branches:
     - master
 
 script:
-  - sh ./build-deps.sh
   - sh ./autogen.sh
   - if [[ "$CC" == "gcc" && "$CODE_COVERAGE" == "ON" ]]; then
-      ./configure CFLAGS="-ftest-coverage -fprofile-arcs";
+      ./configure CFLAGS="-ftest-coverage -fprofile-arcs -coverage";
     else
       ./configure;
     fi
@@ -55,5 +60,9 @@ after_success:
         --exclude lib
         --exclude test
         --gcov-options '\-lp'
-        --verbose;
+        --verbose &&
+      bash <(curl -s https://codecov.io/bash);
     fi
+
+# after_failure:
+#   - cat ./test-suite.log

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+  "C_Cpp.default.configurationProvider": "vector-of-bool.cmake-tools",
+  "restructuredtext.confPath": "${workspaceFolder}/docs/source"
+}

CMakeLists.txt

@@ -0,0 +1,128 @@
+cmake_minimum_required(VERSION 3.8.2)
+project(cglm VERSION 0.8.1 LANGUAGES C)
+
+set(CMAKE_C_STANDARD 11)
+set(CMAKE_C_STANDARD_REQUIRED YES)
+set(DEFAULT_BUILD_TYPE "Release")
+
+set(CGLM_BUILD)
+option(CGLM_SHARED "Shared build" ON)
+option(CGLM_STATIC "Static build" OFF)
+option(CGLM_USE_C99 "" OFF)
+option(CGLM_USE_TEST "Enable Tests" OFF)
+
+if(NOT CGLM_STATIC AND CGLM_SHARED)
+  set(CGLM_BUILD SHARED)
+else(CGLM_STATIC)
+  set(CGLM_BUILD STATIC)
+endif()
+
+if(CGLM_USE_C99)
+  set(CMAKE_C_STANDARD 99)
+endif()
+
+if(MSVC)
+  add_definitions(-DNDEBUG -D_WINDOWS -D_USRDLL)
+  add_compile_options(/W3 /Ox /Gy /Oi /TC)
+  
+  # Ref: https://skia.googlesource.com/third_party/sdl/+/refs/heads/master/CMakeLists.txt#225
+  # Make sure /RTC1 is disabled, otherwise it will use functions from the CRT
+  foreach(flag_var
+      CMAKE_C_FLAGS CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE
+      CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO)
+    string(REGEX REPLACE "/RTC(su|[1su])" "" ${flag_var} "${${flag_var}}")
+  endforeach(flag_var)
+else()
+  add_compile_options(-Wall -Werror -O3)
+endif()
+
+if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
+  message(STATUS "Setting build type to '${DEFAULT_BUILD_TYPE}' as none was specified.")
+  set(CMAKE_BUILD_TYPE "${DEFAULT_BUILD_TYPE}" CACHE STRING "Choose the type of build." FORCE)
+  # Set the possible values of build type for cmake-gui
+  set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo")
+endif()
+
+include(GNUInstallDirs)
+
+set(CPACK_PROJECT_NAME ${PROJECT_NAME})
+set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
+include(CPack)
+
+# Target Start
+add_library(${PROJECT_NAME}
+  ${CGLM_BUILD}
+  src/euler.c
+  src/affine.c
+  src/io.c
+  src/quat.c
+  src/cam.c
+  src/vec2.c
+  src/vec3.c
+  src/vec4.c
+  src/mat2.c
+  src/mat3.c
+  src/mat4.c
+  src/plane.c
+  src/frustum.c
+  src/box.c
+  src/project.c
+  src/sphere.c
+  src/ease.c
+  src/curve.c
+  src/bezier.c
+  src/ray.c
+  src/affine2d.c
+  )
+
+if(CGLM_SHARED)
+  add_definitions(-DCGLM_EXPORTS)
+else()
+  target_compile_definitions(${PROJECT_NAME} PUBLIC -DCGLM_STATIC)
+endif()
+
+set_target_properties(${PROJECT_NAME} PROPERTIES
+                              VERSION ${PROJECT_VERSION} 
+                            SOVERSION ${PROJECT_VERSION_MAJOR})
+
+target_include_directories(${PROJECT_NAME}
+    PUBLIC 
+        $<INSTALL_INTERFACE:include>    
+        $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
+    PRIVATE
+        ${CMAKE_CURRENT_SOURCE_DIR}/src
+)
+
+# Target for header-only usage
+add_library(${PROJECT_NAME}_headers INTERFACE)
+target_include_directories(${PROJECT_NAME}_headers INTERFACE
+  ${CMAKE_CURRENT_SOURCE_DIR}/include)
+
+# Test Configuration
+if(CGLM_USE_TEST)
+  include(CTest)
+  enable_testing()
+  add_subdirectory(test)
+endif()
+
+# Install 
+install(TARGETS ${PROJECT_NAME}
+        EXPORT  ${PROJECT_NAME}
+        LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
+        ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
+        RUNTIME DESTINATION ${CMAKE_INSTALL_LIBDIR})
+
+install(DIRECTORY include/${PROJECT_NAME} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
+        PATTERN ".*" EXCLUDE)
+
+# Config
+export(TARGETS ${PROJECT_NAME}
+       NAMESPACE ${PROJECT_NAME}::
+       FILE "${CMAKE_CURRENT_BINARY_DIR}/${PROJECT_NAME}Config.cmake"
+)
+
+install(EXPORT      ${PROJECT_NAME}
+        FILE        "${PROJECT_NAME}Config.cmake"
+        NAMESPACE   ${PROJECT_NAME}::
+        DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/${PROJECT_NAME})
+

CONTRIBUTING.md

@@ -1,11 +1,11 @@
 # CONTRIBUTING
 
-Any contributions (code, documentation, ...) are welcome. This project uses [cmocka](http://cmocka.org) for testing, you may need to check their documentation 
+Any contributions (code, documentation, ...) are welcome.
 
 # New Features
 - This library may not accept all new features, it is better to create an issue and get approval before coding
 - You must add test for every new feature
-- The feature must be compiled in both UNIX/POSIX systems (e.g. macos, linux...) and Windows
+- The feature must be compiled on both UNIX/POSIX systems (e.g. macos, linux...) and Windows
 
 # Code Style
 This library is written with C99, don't try to add C++ files (yes it can compiled into lib),

CREDITS

@@ -1,7 +1,7 @@
 This library [initially] used some [piece of] implementations
 (may include codes) from these open source projects/resources:
 
-1. Affine Transforms
+1. Initial Affine Transforms
 The original glm repo (g-truc), url: https://github.com/g-truc/glm
 
 LICENSE[S]:
@@ -11,7 +11,7 @@ LICENSE[S]:
 
 FULL LICENSE: https://github.com/g-truc/glm/blob/master/copying.txt
 
-2. Quaternions
+2. Initial Quaternions
 Anton's OpenGL 4 Tutorials book source code:
 
 LICENSE:
@@ -47,6 +47,30 @@ http://old.cescg.org/CESCG-2002/DSykoraJJelinek/
 7. Quaternions
 Initial mat4_quat is borrowed from Apple's simd library
 
-
 8. Vector Rotation using Quaternion
 https://gamedev.stackexchange.com/questions/28395/rotating-vector3-by-a-quaternion
+
+9. Sphere AABB intersect
+https://github.com/erich666/GraphicsGems/blob/master/gems/BoxSphere.c
+
+10. Horizontal add
+https://stackoverflow.com/questions/6996764/fastest-way-to-do-horizontal-float-vector-sum-on-x86
+
+11. de casteljau implementation and comments
+https://forums.khronos.org/showthread.php/10264-Animations-in-1-4-1-release-notes-revision-A/page2?highlight=bezier
+https://forums.khronos.org/showthread.php/10644-Animation-Bezier-interpolation
+https://forums.khronos.org/showthread.php/10387-2D-Tangents-in-Bezier-Splines?p=34164&viewfull=1#post34164
+https://forums.khronos.org/showthread.php/10651-Animation-TCB-Spline-Interpolation-in-COLLADA?highlight=bezier
+
+12. vec2 cross product
+http://allenchou.net/2013/07/cross-product-of-2d-vectors/
+
+13. Ray triangle intersect
+Möller–Trumbore ray-triangle intersection algorithm, from "Fast, Minimum Storage Ray/Triangle Intersection"
+Authors:
+  Thomas Möller (tompa@clarus.se)
+  Ben Trumbore (wbt@graphics.cornell.edu)
+Link to paper: http://webserver2.tecgraf.puc-rio.br/~mgattass/cg/trbRR/Fast%20MinimumStorage%20RayTriangle%20Intersection.pdf
+
+14. ARM NEON: Matrix Vector Multiplication
+https://stackoverflow.com/a/57793352/2676533

Makefile.am

@@ -0,0 +1,180 @@
+#******************************************************************************
+# Copyright (c), Recep Aslantas.                                              *
+#                                                                             *
+# MIT License (MIT), http://opensource.org/licenses/MIT                       *
+# Full license can be found in the LICENSE file                               *
+#                                                                             *
+#******************************************************************************
+
+ACLOCAL_AMFLAGS = -I m4
+AM_CFLAGS = -Wall \
+            -std=gnu11 \
+            -O3 \
+            -Wstrict-aliasing=2 \
+            -fstrict-aliasing \
+            -Werror=strict-prototypes
+
+lib_LTLIBRARIES = libcglm.la
+libcglm_la_LDFLAGS = -no-undefined -version-info 0:1:0
+
+checkLDFLAGS = -L./.libs \
+               -lm \
+               -lcglm
+checkCFLAGS = $(AM_CFLAGS) \
+               -std=gnu11 \
+               -O3 \
+               -DCGLM_DEFINE_PRINTS \
+               -I./include
+
+check_PROGRAMS = test/tests
+TESTS = $(check_PROGRAMS)
+
+test_tests_LDFLAGS = $(checkLDFLAGS)
+test_tests_CFLAGS  = $(checkCFLAGS)
+
+cglmdir=$(includedir)/cglm
+cglm_HEADERS = include/cglm/version.h \
+               include/cglm/common.h \
+               include/cglm/types.h \
+               include/cglm/types-struct.h \
+               include/cglm/cglm.h \
+               include/cglm/call.h \
+               include/cglm/struct.h \
+               include/cglm/cam.h \
+               include/cglm/io.h \
+               include/cglm/mat4.h \
+               include/cglm/mat3.h \
+               include/cglm/mat2.h \
+               include/cglm/affine.h \
+               include/cglm/vec2.h \
+               include/cglm/vec2-ext.h \
+               include/cglm/vec3.h \
+               include/cglm/vec3-ext.h \
+               include/cglm/vec4.h \
+               include/cglm/vec4-ext.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 \
+               include/cglm/color.h \
+               include/cglm/project.h \
+               include/cglm/sphere.h \
+               include/cglm/ease.h \
+               include/cglm/curve.h \
+               include/cglm/bezier.h \
+               include/cglm/applesimd.h \
+               include/cglm/ray.h \
+               include/cglm/affine2d.h
+
+cglm_calldir=$(includedir)/cglm/call
+cglm_call_HEADERS = include/cglm/call/mat4.h \
+                    include/cglm/call/mat3.h \
+                    include/cglm/call/mat2.h \
+                    include/cglm/call/vec2.h \
+                    include/cglm/call/vec3.h \
+                    include/cglm/call/vec4.h \
+                    include/cglm/call/affine.h \
+                    include/cglm/call/io.h \
+                    include/cglm/call/cam.h \
+                    include/cglm/call/quat.h \
+                    include/cglm/call/euler.h \
+                    include/cglm/call/plane.h \
+                    include/cglm/call/frustum.h \
+                    include/cglm/call/box.h \
+                    include/cglm/call/project.h \
+                    include/cglm/call/sphere.h \
+                    include/cglm/call/ease.h \
+                    include/cglm/call/curve.h \
+                    include/cglm/call/bezier.h \
+                    include/cglm/call/ray.h \
+                    include/cglm/call/affine2d.h
+
+cglm_simddir=$(includedir)/cglm/simd
+cglm_simd_HEADERS = include/cglm/simd/intrin.h \
+                    include/cglm/simd/x86.h \
+                    include/cglm/simd/arm.h
+
+cglm_simd_sse2dir=$(includedir)/cglm/simd/sse2
+cglm_simd_sse2_HEADERS = include/cglm/simd/sse2/affine.h \
+                         include/cglm/simd/sse2/mat4.h \
+                         include/cglm/simd/sse2/mat3.h \
+                         include/cglm/simd/sse2/mat2.h \
+                         include/cglm/simd/sse2/quat.h
+
+cglm_simd_avxdir=$(includedir)/cglm/simd/avx
+cglm_simd_avx_HEADERS = include/cglm/simd/avx/mat4.h \
+                        include/cglm/simd/avx/affine.h
+
+cglm_simd_neondir=$(includedir)/cglm/simd/neon
+cglm_simd_neon_HEADERS = include/cglm/simd/neon/mat4.h
+
+cglm_structdir=$(includedir)/cglm/struct
+cglm_struct_HEADERS = include/cglm/struct/mat4.h \
+                      include/cglm/struct/mat3.h \
+                      include/cglm/struct/mat2.h \
+                      include/cglm/struct/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 \
+                      include/cglm/struct/euler.h \
+                      include/cglm/struct/plane.h \
+                      include/cglm/struct/frustum.h \
+                      include/cglm/struct/box.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
+                      
+libcglm_la_SOURCES=\
+    src/euler.c \
+    src/affine.c \
+    src/io.c \
+    src/quat.c \
+    src/cam.c \
+    src/vec2.c \
+    src/vec3.c \
+    src/vec4.c \
+    src/mat2.c \
+    src/mat3.c \
+    src/mat4.c \
+    src/plane.c \
+    src/frustum.c \
+    src/box.c \
+    src/project.c \
+    src/sphere.c \
+    src/ease.c \
+    src/curve.c \
+    src/bezier.c \
+    src/ray.c \
+    src/affine2d.c
+
+test_tests_SOURCES=\
+    test/runner.c \
+    test/src/test_common.c \
+    test/src/tests.c \
+    test/src/test_cam.c \
+    test/src/test_clamp.c \
+    test/src/test_euler.c \
+    test/src/test_bezier.c \
+    test/src/test_struct.c
+
+pkgconfig_DATA=cglm.pc
+
+# When running configure with --prefix, $VPATH references
+# the source directory that post-build.sh is in. When not
+# using a prefix, $VPATH will be unset, so we need to fall
+# back to using . to run the script.
+#export VPATH
+
+# all-local:
+#	sh $${VPATH:-.}/post-build.sh

Package.swift

@@ -0,0 +1,44 @@
+// swift-tools-version:5.2
+
+import PackageDescription
+
+let package = Package(
+    name: "cglm",
+    products: [
+        .library(name: "cglm", type: .static, targets: ["cglmHeader"]),
+        .library(name: "cglmc", targets: ["cglmCompiled"]),
+    ],
+    dependencies: [],
+    targets: [
+        .target(
+            name: "cglmCompiled",
+            path: "./",
+            exclude: [
+                "./docs",
+                "./src/swift",
+                "./include",
+                "./test",
+                "./win",
+            ],
+            sources: [
+                "./src",
+            ],
+            publicHeadersPath: "./include"
+        ),
+        .target(
+            name: "cglmHeader",
+            path: "./",
+            exclude: [
+                "./docs",
+                "./include",
+                "./test",
+                "./win",
+            ],
+            sources: [
+                "./src/swift",
+            ],
+            publicHeadersPath: "./include"
+        ),
+    ],
+    cLanguageStandard: .c11
+)

README.md

@@ -3,20 +3,19 @@
  [![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&utm_medium=referral&utm_content=recp/cglm&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)
 
-The original glm library is for C++ only (templates, namespaces, classes...), this library targeted to C99 but currently you can use it for C89 safely by language extensions e.g `__restrict`
-
 #### Documentation
 
-Almost all functions (inline versions) and parameters are documented inside related headers. <br />
+Almost all functions (inline versions) and parameters are documented inside the corresponding headers. <br />
 Complete documentation: http://cglm.readthedocs.io
 
 #### Note for previous versions:
 
-- _dup (duplicate) is changed to _copy. For instance `glm_vec_dup -> glm_vec_copy`
+- _dup (duplicate) is changed to _copy. For instance `glm_vec_dup -> glm_vec3_copy`
 - OpenGL related functions are dropped to make this lib platform/third-party independent
 - make sure you have latest version and feel free to report bugs, troubles
 - **[bugfix]** euler angles was implemented in reverse order (extrinsic) it was fixed, now they are intrinsic. Make sure that
@@ -24,15 +23,18 @@ you have the latest version
 - **[major change]** by starting v0.4.0, quaternions are stored as [x, y, z, w], it was [w, x, y, z] in v0.3.5 and earlier versions
 - **[api rename]** by starting v0.4.5, **glm_simd** functions are renamed to **glmm_**  
 - **[new option]** by starting v0.4.5, you can disable alignment requirement, check options in docs.  
+- **[major change]** by starting v0.5.0, vec3 functions use **glm_vec3_** namespace, it was **glm_vec_** until v0.5.0
+- **[major change]** by starting v0.5.1, built-in alignment is removed from **vec3** and **mat3** types
+- **[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)
 
 #### Note for C++ developers:
-If you don't aware about original GLM library yet, you may also want to look at:
+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):
 - `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 incliude headers.
+- 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!
 
@@ -43,7 +45,8 @@ https://github.com/g-truc/glm
 `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... ?
-Since almost all types are arrays and **C** doesn't allow returning arrays, so **cglm** doesn't support this feature. In the future *cglm* may use **struct** for some types for this purpose.
+
+**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
@@ -66,10 +69,11 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi
 </table>
 
 ## Features
+- array api and struct api, you can use arrays or structs.
 - general purpose matrix operations (mat4, mat3)
 - chain matrix multiplication (square only)
 - general purpose vector operations (cross, dot, rotate, proj, angle...)
-- affine transforms
+- affine transformations
 - matrix decomposition (extract rotation, scaling factor)
 - optimized affine transform matrices (mul, rigid-body inverse)
 - camera (lookat)
@@ -80,12 +84,19 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi
 - inline or pre-compiled function call
 - frustum (extract view frustum planes, corners...)
 - bounding box  (AABB in Frustum (culling), crop, merge...)
+- bounding sphere
 - project, unproject
+- easing functions
+- curves
+- curve interpolation helpers (S*M*C, deCasteljau...)
+- helpers to convert cglm types to Apple's simd library to pass cglm types to Metal GL without packing them on both sides
+- ray intersection helpers
+- and others...
 
 <hr />
 
 You have two option to call a function/operation: inline or library call (link)
-Almost all functions are marked inline (always_inline) so compiler probably will inline.
+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_`.
 
 ```C
@@ -112,7 +123,7 @@ You can pass matrices and vectors as array to functions rather than get address.
   glm_translate(m, (vec3){1.0f, 0.0f, 0.0f});
 ```
 
-Library contains general purpose mat4 mul and inverse functions but also contains some special form (optimized) of these functions for affine transform matrices. If you want to multiply two affine transform matrices you can use glm_mul instead of glm_mat4_mul and glm_inv_tr (ROT + TR) instead glm_mat4_inv
+Library contains general purpose mat4 mul and inverse functions, and also contains some special forms (optimized) of these functions for affine transformations' matrices. If you want to multiply two affine transformation matrices you can use glm_mul instead of glm_mat4_mul and glm_inv_tr (ROT + TR) instead glm_mat4_inv
 ```C
 /* multiplication */
 mat4 modelMat;
@@ -122,59 +133,161 @@ glm_mul(T, R, modelMat);
 glm_inv_tr(modelMat);
 ```
 
-## Contributors
+### Struct API
 
-This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
+The struct API works as follows, note the `s` suffix on types, the `glms_` prefix on functions and the `GLMS_` prefix on constants:
-<a href="graphs/contributors"><img src="https://opencollective.com/cglm/contributors.svg?width=890&button=false" /></a>
 
+```C
+#include <cglm/struct.h>
 
-## Backers
+mat4s mat = GLMS_MAT4_IDENTITY_INIT;
+mat4s inv = glms_mat4_inv(mat);
+```
 
-Thank you to all our backers! 🙏 [[Become a backer](https://opencollective.com/cglm#backer)]
+Struct functions generally take their parameters as *values* and *return* their results, rather than taking pointers and writing to out parameters. That means your parameters can usually be `const`, if you're into that.
 
-<a href="https://opencollective.com/cglm#backers" target="_blank"><img src="https://opencollective.com/cglm/backers.svg?width=890"></a>
+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.
-
-
-## Sponsors
-
-Support this project by becoming a sponsor. Your logo will show up here with a link to your website. [[Become a sponsor](https://opencollective.com/cglm#sponsor)]
-
-<a href="https://opencollective.com/cglm/sponsor/0/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/0/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/1/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/1/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/2/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/2/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/3/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/3/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/4/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/4/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/5/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/5/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/6/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/6/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/7/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/7/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/8/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/8/avatar.svg"></a>
-<a href="https://opencollective.com/cglm/sponsor/9/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/9/avatar.svg"></a>
-
-
-
-## License
-MIT. check the LICENSE file
 
 ## Build
 
+### CMake (All platforms)
+```bash
+$ mkdir build
+$ cd build
+$ cmake .. # [Optional] -DCGLM_SHARED=ON
+$ make
+$ sudo make install # [Optional]
+```
+
+##### Cmake options with Defaults:
+
+```CMake
+option(CGLM_SHARED "Shared build" ON)
+option(CGLM_STATIC "Static build" OFF)
+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
+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)
+
+add_subdirectory(external/cglm/)
+
+# or you can use find_package to configure cglm
+```
+
+### Meson (All platforms)
+
+```bash
+$ meson build # [Optional] --default-library=static
+$ cd build
+$ ninja
+$ sudo ninja install # [Optional]
+```
+
+##### Meson options with Defaults:
+
+```meson
+c_std=c11
+buildtype=release
+default_library=shared
+enable_tests=false # to run tests: ninja test
+```
+#### Use with your Meson project
+* Example:
+```meson
+# Clone cglm or create a cglm.wrap under <source_root>/subprojects
+project('name', 'c')
+
+cglm_dep = dependency('cglm', fallback : 'cglm', 'cglm_dep')
+
+executable('exe', 'src/main.c', dependencies : cglm_dep)
+```
+
+### Swift (Swift Package Manager)
+
+Currently only default build options are supported. Add **cglm** dependency to your project:
+
+```swift
+...
+Package( 
+  ...
+  dependencies: [
+    ...
+    .package(url: "https://github.com/recp/cglm", .branch("master")),
+  ]
+  ...
+)
+```
+
+Now add **cgml** as a dependency to your target. Product choices are:
+- **cglm** for inlined version of the library which can be linked only statically
+- **cglmc** for a compiled version of the library with no linking limitation
+
+```swift
+...
+.target(
+  ...
+  dependencies: [
+    ...
+    .product(name: "cglm", package: "cglm"),
+  ]
+  ...
+)
+...
+```
+
 ### Unix (Autotools)
 
 ```bash
-$ sh ./build-deps.sh # run only once (dependencies) [Optional].
-$ # You can pass this step if you don't want to run `make check` for tests.
-$ # cglm uses cmocka for tests and it may reqiure cmake for building it
-$
 $ sh autogen.sh
 $ ./configure
 $ make
-$ make check # [Optional] (if you run `sh ./build-deps.sh`)
+$ make check # [Optional]
-$ [sudo] make install
+$ [sudo] make install # [Optional]
 ```
 
+This will also install pkg-config files so you can use
+`pkg-config --cflags cglm` and `pkg-config --libs cglm` to retrieve compiler
+and linker flags.
+
+The files will be installed into the given prefix (usually `/usr/local` by
+default on Linux), but your pkg-config may not be configured to actually check
+there. You can figure out where it's looking by running `pkg-config --variable
+pc_path pkg-config` and change the path the files are installed to via
+`./configure --with-pkgconfigdir=/your/path`. Alternatively, you can add the
+prefix path to your `PKG_CONFIG_PATH` environment variable.
+
 ### Windows (MSBuild)
-Windows related build files, project files are located in `win` folder,
+Windows related build file and project files are located in `win` folder,
 make sure you are inside `cglm/win` folder.
-Code Analysis are enabled, it may take awhile to build
+Code Analysis is enabled, so it may take awhile to build.
 
 ```Powershell
 $ cd win
@@ -185,6 +298,10 @@ if `msbuild` won't work (because of multi version VS) then try to build with `de
 $ devenv cglm.sln /Build Release
 ```
 
+#### Running Tests on Windows
+
+You can see test project in same visual studio solution file. It is enough to run that project to run tests.
+
 ### Building Docs
 First you need install Sphinx: http://www.sphinx-doc.org/en/master/usage/installation.html
 then:
@@ -195,21 +312,21 @@ $ sphinx-build source build
 it will compile docs into build folder, you can run index.html inside that function.
 
 ## How to use
-If you want to use inline versions of funcstions then; include main header
+If you want to use the inline versions of functions, then include the main header
 ```C
 #include <cglm/cglm.h>
 ```
-the header will include all headers. Then call func you want e.g. rotate vector by axis:
+the header will include all headers. Then call the func you want e.g. rotate vector by axis:
 ```C
-glm_vec_rotate(v1, glm_rad(45), (vec3){1.0f, 0.0f, 0.0f});
+glm_vec3_rotate(v1, glm_rad(45), (vec3){1.0f, 0.0f, 0.0f});
 ```
 some functions are overloaded :) e.g you can normalize vector:
 ```C
-glm_vec_normalize(vec);
+glm_vec3_normalize(vec);
 ```
 this will normalize vec and store normalized vector into `vec` but if you will store normalized vector into another vector do this:
 ```C
-glm_vec_normalize_to(vec, result);
+glm_vec3_normalize_to(vec, result);
 ```
 like this function you may see `_to` postfix, this functions store results to another variables and save temp memory
 
@@ -220,7 +337,7 @@ to call pre-compiled versions include header with `c` postfix, c means call. Pre
 ```
 this header will include all headers with c postfix. You need to call functions with c posfix:
 ```C
-glmc_vec_normalize(vec);
+glmc_vec3_normalize(vec);
 ```
 
 Function usage and parameters are documented inside related headers. You may see same parameter passed twice in some examples like this:
@@ -230,7 +347,7 @@ glm_mat4_mul(m1, m2, m1);
 /* or */
 glm_mat4_mul(m1, m1, m1);
 ```
-the first two parameter are **[in]** and the last one is **[out]** parameter. After multiplied *m1* and *m2* the result is stored in *m1*. This is why we send *m1* twice. You may store result in different matrix, this just an example.
+the first two parameter are **[in]** and the last one is **[out]** parameter. After multiplying *m1* and *m2*, the result is stored in *m1*. This is why we send *m1* twice. You may store the result in a different matrix, this is just an example.
 
 ### Example: Computing MVP matrix
 
@@ -270,7 +387,7 @@ Option 2: Cast matrix to pointer type (also valid for multiple dimensional array
 glUniformMatrix4fv(location, 1, GL_FALSE, (float *)matrix);
 ```
 
-You can pass same way to another APIs e.g. Vulkan, DX...
+You can pass matrices the same way to other APIs e.g. Vulkan, DX...
 
 ## Notes
 
@@ -284,3 +401,35 @@ You can pass same way to another APIs e.g. Vulkan, DX...
 - [ ] Unaligned operations (e.g. `glm_umat4_mul`)
 - [x] Extra documentation
 - [ ] ARM Neon Arch (In Progress)
+
+
+## Contributors
+
+This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
+<a href="https://github.com/recp/cglm/graphs/contributors"><img src="https://opencollective.com/cglm/contributors.svg?width=890&button=false" /></a>
+
+
+## Backers
+
+Thank you to all our backers! 🙏 [[Become a backer](https://opencollective.com/cglm#backer)]
+
+<a href="https://opencollective.com/cglm#backers" target="_blank"><img src="https://opencollective.com/cglm/backers.svg?width=890"></a>
+
+
+## Sponsors
+
+Support this project by becoming a sponsor. Your logo will show up here with a link to your website. [[Become a sponsor](https://opencollective.com/cglm#sponsor)]
+
+<a href="https://opencollective.com/cglm/sponsor/0/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/0/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/1/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/1/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/2/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/2/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/3/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/3/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/4/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/4/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/5/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/5/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/6/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/6/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/7/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/7/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/8/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/8/avatar.svg"></a>
+<a href="https://opencollective.com/cglm/sponsor/9/website" target="_blank"><img src="https://opencollective.com/cglm/sponsor/9/avatar.svg"></a>
+
+## License
+MIT. check the LICENSE file

build-deps.sh

@@ -1,23 +0,0 @@
-#! /bin/sh
-#
-# Copyright (c), Recep Aslantas.
-#
-# MIT License (MIT), http://opensource.org/licenses/MIT
-# Full license can be found in the LICENSE file
-#
-
-# check if deps are pulled
-git submodule update --init --recursive
-
-cd $(dirname "$0")
-
-# general deps: gcc make autoconf automake libtool cmake
-
-# test - cmocka
-cd ./test/lib/cmocka
-rm -rf build
-mkdir -p build
-cd build
-cmake -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_BUILD_TYPE=Debug ..
-make -j8
-cd ../../../../

cglm.pc.in

@@ -0,0 +1,11 @@
+prefix=@prefix@
+exec_prefix=@exec_prefix@
+libdir=@libdir@
+includedir=@includedir@
+
+Name: @PACKAGE_NAME@
+Description: OpenGL Mathematics (glm) for C
+URL: https://github.com/recp/cglm
+Version: @PACKAGE_VERSION@
+Cflags: -I${includedir}
+Libs: -L${libdir} -lcglm @LIBS@

cglm.podspec

@@ -2,10 +2,10 @@ Pod::Spec.new do |s|
 
   # Description
   s.name         = "cglm"
-  s.version      = "0.4.4"
+  s.version      = "0.8.0"
-  s.summary      = "📽 Optimized OpenGL/Graphics Math (glm) for C"
+  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

configure.ac

@@ -7,13 +7,30 @@
 #*****************************************************************************
 
 AC_PREREQ([2.69])
-AC_INIT([cglm], [0.4.5], [info@recp.me])
+AC_INIT([cglm], [0.8.1], [info@recp.me])
-AM_INIT_AUTOMAKE([-Wall -Werror foreign subdir-objects])
+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.
+: ${CFLAGS=""}
 
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_SRCDIR([src/])
 AC_CONFIG_HEADERS([config.h])
 
+# Dependencies for pkg-config.
+PKG_PROG_PKG_CONFIG
+# Ancient versions of pkg-config (such as the one used in Travis CI)
+# don't have this macro, so we need to do it manually.
+m4_ifdef([PKG_INSTALLDIR], [
+    PKG_INSTALLDIR
+], [
+    AC_ARG_WITH([pkgconfigdir],
+        [AS_HELP_STRING([--with-pkgconfigdir],
+                        [pkg-config installation directory ['${libdir}/pkgconfig']])],,
+        [with_pkgconfigdir=]'${libdir}/pkgconfig')
+    AC_SUBST([pkgconfigdir], [$with_pkgconfigdir])
+])
+
 # Checks for programs.
 AC_PROG_CC
 AM_PROG_CC_C_O
@@ -29,6 +46,7 @@ LT_INIT
 # Checks for libraries.
 AC_CHECK_LIB([m], [floor])
 
+m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
 AC_SYS_LARGEFILE
 
 # Checks for header files.
@@ -52,6 +70,6 @@ AC_TYPE_UINT8_T
 # Checks for library functions.
 AC_FUNC_ERROR_AT_LINE
 
-AC_CONFIG_FILES([makefile])
+AC_CONFIG_FILES([Makefile cglm.pc])
 
 AC_OUTPUT

docs/source/affine-mat.rst

@@ -1,6 +1,6 @@
 .. default-domain:: C
 
-affine transform matrix (specialized functions)
+3D Affine Transform Matrix (specialized functions)
 ================================================================================
 
 Header: cglm/affine-mat.h

docs/source/affine.rst

@@ -1,6 +1,6 @@
 .. default-domain:: C
 
-affine transforms
+3D Affine Transforms
 ================================================================================
 
 Header: cglm/affine.h
@@ -45,6 +45,8 @@ The implementation would be:
   glm_rotate(m, angle, axis);
   glm_translate(m, pivotInv); /* pivotInv = -pivot */
 
+.. _TransformsOrder:
+
 Transforms Order
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

docs/source/affine2d.rst

@@ -0,0 +1,140 @@
+.. default-domain:: C
+
+2D Affine Transforms
+================================================================================
+
+Header: cglm/affine2d.h
+
+2D Transforms uses `2d` suffix for naming. If there is no 2D suffix it is 3D function.
+
+Initialize Transform Matrices
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Functions with **_make** prefix expect you don't have a matrix and they create
+a matrix for you. You don't need to pass identity matrix.
+
+But other functions expect you have a matrix and you want to transform them. If
+you didn't have any existing matrix you have to initialize matrix to identity
+before sending to transfrom functions.
+
+Transforms Order
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+See :ref:`TransformsOrder` to read similar section.
+
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translate2d`
+#. :c:func:`glm_translate2d_to`
+#. :c:func:`glm_translate2d_x`
+#. :c:func:`glm_translate2d_y`
+#. :c:func:`glm_translate2d_make`
+#. :c:func:`glm_scale2d_to`
+#. :c:func:`glm_scale2d_make`
+#. :c:func:`glm_scale2d`
+#. :c:func:`glm_scale2d_uni`
+#. :c:func:`glm_rotate2d_make`
+#. :c:func:`glm_rotate2d`
+#. :c:func:`glm_rotate2d_to`
+
+.. c:function:: void glm_translate2d(mat3 m, vec2 v)
+
+    translate existing 2d transform matrix by *v* vector and stores result in same matrix
+
+    Parameters:
+      | *[in, out]*  **m**    2d affine transfrom
+      | *[in]*       **v**    translate vector [x, y]
+
+.. c:function:: void glm_translate2d_to(mat3 m, vec2 v, mat3 dest)
+
+    translate existing 2d transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    2d affine transfrom
+      | *[in]*  **v**    translate vector [x, y]
+      | *[out]* **dest** translated matrix
+
+.. c:function:: void glm_translate2d_x(mat3 m, float x)
+
+    translate existing 2d transform matrix by x factor
+
+    Parameters:
+      | *[in, out]*  **m**    2d affine transfrom
+      | *[in]*       **x**    x factor
+
+.. c:function:: void glm_translate2d_y(mat3 m, float y)
+
+    translate existing 2d transform matrix by y factor
+
+    Parameters:
+      | *[in, out]*  **m**    2d affine transfrom
+      | *[in]*       **y**    y factor
+
+.. c:function:: void glm_translate2d_make(mat3 m, vec2 v)
+
+    creates NEW translate 2d transform matrix by *v* vector
+
+    Parameters:
+      | *[in, out]*  **m**    affine transfrom
+      | *[in]*       **v**    translate vector [x, y]
+
+.. c:function:: void glm_scale2d_to(mat3 m, vec2 v, mat3 dest)
+
+    scale existing 2d transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    scale vector [x, y]
+      | *[out]* **dest** scaled matrix
+
+.. c:function:: void glm_scale2d_make(mat3 m, vec2 v)
+
+    creates NEW 2d scale matrix by *v* vector
+
+    Parameters:
+      | *[in, out]*  **m**    affine transfrom
+      | *[in]*       **v**    scale vector [x, y]
+
+.. c:function:: void glm_scale2d(mat3 m, vec2 v)
+
+    scales existing 2d transform matrix by *v* vector and stores result in same matrix
+
+    Parameters:
+      | *[in, out]*  **m**    affine transfrom
+      | *[in]*       **v**    translate vector [x, y]
+
+.. c:function:: void glm_scale2d_uni(mat3 m, float s)
+
+    applies uniform scale to existing 2d transform matrix v = [s, s] and stores result in same matrix
+
+    Parameters:
+      | *[in, out]*  **m**  affine transfrom
+      | *[in]*       **s**  scale factor
+
+.. c:function:: void glm_rotate2d_make(mat3 m, float angle)
+
+    creates NEW rotation matrix by angle around *Z* axis
+
+    Parameters:
+      | *[in, out]*  **m**      affine transfrom
+      | *[in]*       **angle**  angle (radians)
+
+.. c:function:: void glm_rotate2d(mat3 m, float angle)
+
+    rotate existing 2d transform matrix around *Z* axis by angle and store result in same matrix
+
+    Parameters:
+      | *[in, out]*  **m**      affine transfrom
+      | *[in]*       **angle**  angle (radians)
+
+.. c:function:: void glm_rotate2d_to(mat3 m, float angle, mat3 dest)
+
+    rotate existing 2d 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

docs/source/api.rst

@@ -5,14 +5,14 @@ Some functions may exist twice,
 once for their namespace and once for global namespace
 to make easier to write very common functions
 
-For instance, in general we use :code:`glm_vec_dot` to get dot product
+For instance, in general we use :code:`glm_vec3_dot` to get dot product
 of two **vec3**. Now we can also do this with :code:`glm_dot`,
 same for *_cross* and so on...
 
 The original function stays where it is, the function in global namespace
 of same name is just an alias, so there is no call version of those functions.
 e.g there is no func like :code:`glmc_dot` because *glm_dot* is just alias for
-:code:`glm_vec_dot`
+:code:`glm_vec3_dot`
 
 By including **cglm/cglm.h** header you will include all inline version
 of functions. Since functions in this header[s] are inline you don't need to
@@ -28,6 +28,7 @@ Follow the :doc:`build` documentation for this
 
    affine
    affine-mat
+   affine2d
    cam
    frustum
    box
@@ -35,13 +36,21 @@ Follow the :doc:`build` documentation for this
    euler
    mat4
    mat3
+   mat2
    vec3
    vec3-ext
    vec4
    vec4-ext
+   vec2
+   vec2-ext
    color
    plane
    project
    util
    io
    call
+   sphere
+   curve
+   bezier
+   version
+   ray

docs/source/bezier.rst

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

docs/source/box.rst

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

docs/source/build.rst

@@ -1,23 +1,108 @@
-Building cglm
+Build cglm
 ================================
 
-| **cglm** does not have external dependencies except for unit testing.
+| **cglm** does not have any external dependencies.
-| When you pulled cglm repo with submodules all dependencies will be pulled too.
-| `build-deps.sh` will pull all dependencies/submodules and build for you.
-
-External dependencies:
-  * cmocka - for unit testing
 
 **NOTE:**
 If you only need to inline versions, you don't need to build **cglm**, you don't need to link it to your program.
 Just import cglm to your project as dependency / external lib by copy-paste then use it as usual
 
-**Unix (Autotools):**
+CMake (All platforms):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. code-block:: bash
   :linenos:
 
-  $ sh ./build-deps.sh    # run this only once (dependencies)
+  $ mkdir build
+  $ cd build
+  $ cmake .. # [Optional] -DCGLM_SHARED=ON
+  $ make
+  $ sudo make install # [Optional]
+
+**make** will build cglm to **build** folder.
+If you don't want to install **cglm** to your system's folder you can get static and dynamic libs in this folder.
+
+**CMake Options:**
+
+.. code-block:: CMake
+  :linenos:
+
+  option(CGLM_SHARED "Shared build" ON)
+  option(CGLM_STATIC "Static build" OFF)
+  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
+  :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)
+  
+  add_subdirectory(external/cglm/)
+
+Meson (All platforms):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. code-block::
+  :linenos:
+
+  $ meson build # [Optional] --default-library=static
+  $ cd build
+  $ ninja
+  $ sudo ninja install # [Optional]
+
+**Meson Options:**
+
+.. code-block:: 
+  :linenos:
+
+  c_std=c11
+  buildtype=release
+  default_library=shared
+  enable_tests=false # to run tests: ninja test
+
+
+**Use with your Meson project**
+
+.. code-block::
+  :linenos:
+
+  # Clone cglm or create a cglm.wrap under <source_root>/subprojects
+  project('name', 'c')
+  
+  cglm_dep = dependency('cglm', fallback : 'cglm', 'cglm_dep')
+  
+  executable('exe', 'src/main.c', dependencies : cglm_dep)
+
+
+Unix (Autotools):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. code-block:: bash
+  :linenos:
 
   $ sh autogen.sh
   $ ./configure
@@ -26,11 +111,12 @@ Just import cglm to your project as dependency / external lib by copy-paste then
   $ [sudo] make install   # install to system (optional)
 
 **make** will build cglm to **.libs** sub folder in project folder.
-If you don't want to install cglm to your system's folder you can get static and dynamic libs in this folder.
+If you don't want to install **cglm** to your system's folder you can get static and dynamic libs in this folder.
 
-**Build dependencies (windows):**
+Windows (MSBuild):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Windows related build files, project files are located in win folder,
+Windows related build files, project files are located in `win` folder,
 make sure you are inside in cglm/win folder.
 
 Code Analysis are enabled, it may take awhile to build.
@@ -50,3 +136,18 @@ then try to build with *devenv*:
   $ devenv cglm.sln /Build Release
 
 Currently tests are not available on Windows.
+
+Documentation (Sphinx):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+**cglm** uses sphinx framework for documentation, it allows lot of formats for documentation. To see all options see sphinx build page:
+
+https://www.sphinx-doc.org/en/master/man/sphinx-build.html
+
+Example build:
+
+.. code-block:: bash
+  :linenos:
+
+  $ cd cglm/docs
+  $ sphinx-build source build

docs/source/cam.rst

@@ -9,7 +9,7 @@ There are many convenient functions for camera. For instance :c:func:`glm_look`
 is just wrapper for :c:func:`glm_lookat`. Sometimes you only have direction
 instead of target, so that makes easy to build view matrix using direction.
 There is also :c:func:`glm_look_anyup` function which can help build view matrix
-without providing UP axis. It uses :c:func:`glm_vec_ortho` to get a UP axis and
+without providing UP axis. It uses :c:func:`glm_vec3_ortho` to get a UP axis and
 builds view matrix.
 
 You can also *_default* versions of ortho and perspective to build projection
@@ -36,6 +36,7 @@ Functions:
 #. :c:func:`glm_ortho_default`
 #. :c:func:`glm_ortho_default_s`
 #. :c:func:`glm_perspective`
+#. :c:func:`glm_persp_move_far`
 #. :c:func:`glm_perspective_default`
 #. :c:func:`glm_perspective_resize`
 #. :c:func:`glm_lookat`
@@ -145,6 +146,16 @@ Functions documentation
       | *[in]*  **farVal**  far clipping planes
       | *[out]* **dest**    result matrix
 
+.. c:function:: void  glm_persp_move_far(mat4 proj, float deltaFar)
+
+    | extend perspective projection matrix's far distance
+
+    | this function does not guarantee far >= near, be aware of that!
+
+    Parameters:
+      | *[in, out]*  **proj**      projection matrix to extend
+      | *[in]*       **deltaFar**  distance from existing far (negative to shink)
+
 .. c:function:: void glm_perspective_default(float aspect, mat4 dest)
 
      | set up perspective projection matrix with default near/far
@@ -167,11 +178,13 @@ Functions documentation
 
     | set up view matrix
 
+    **NOTE:** The UP vector must not be parallel to the line of sight from the eye point to the reference point.
+
     Parameters:
-    | *[in]*  **eye**     eye vector
+      | *[in]*  **eye**     eye vector
-    | *[in]*  **center**  center vector
+      | *[in]*  **center**  center vector
-    | *[in]*  **up**      up vector
+      | *[in]*  **up**      up vector
-    | *[out]* **dest**    result matrix
+      | *[out]* **dest**    result matrix
 
 .. c:function:: void  glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest)
 
@@ -181,9 +194,11 @@ Functions documentation
     target self then this might be useful. Because you need to get target
     from direction.
 
+    **NOTE:** The UP vector must not be parallel to the line of sight from the eye point to the reference point.
+
     Parameters:
       | *[in]*  **eye**     eye vector
-      | *[in]*  **center**  direction vector
+      | *[in]*  **dir**     direction vector
       | *[in]*  **up**      up vector
       | *[out]* **dest**    result matrix
 
@@ -197,7 +212,7 @@ Functions documentation
 
     Parameters:
       | *[in]*  **eye**     eye vector
-      | *[in]*  **center**  direction vector
+      | *[in]*  **dir**     direction vector
       | *[out]* **dest**    result matrix
 
 .. c:function:: void  glm_persp_decomp(mat4 proj, float *nearVal, float *farVal, float *top, float *bottom, float *left, float *right)

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'0.4.5'
+version = u'0.8.1'
 # The full version, including alpha/beta/rc tags.
-release = u'0.4.5'
+release = u'0.8.1'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -90,7 +90,7 @@ todo_include_todos = False
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'alabaster'
+html_theme = 'sphinx_rtd_theme'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -99,13 +99,13 @@ html_theme = 'alabaster'
 # html_theme_options = {}
 
 html_theme_options = {
-    'github_banner': 'true',
+    # 'github_banner': 'true',
-    'github_button': 'true',
+    # 'github_button': 'true',
-    'github_user': 'recp',
+    # 'github_user': 'recp',
-    'github_repo': 'cglm',
+    # 'github_repo': 'cglm',
-    'travis_button': 'true',
+    # 'travis_button': 'true',
-    'show_related': 'true',
+    # 'show_related': 'true',
-    'fixed_sidebar': 'true'
+    # 'fixed_sidebar': 'true'
 }
 
 # Add any paths that contain custom static files (such as style sheets) here,
@@ -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']

docs/source/curve.rst

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

docs/source/features.rst

@@ -0,0 +1,26 @@
+Features
+================================================================================
+
+* array api and struct api, you can use arrays or structs.
+* general purpose matrix operations (mat4, mat3)
+* chain matrix multiplication (square only)
+* general purpose vector operations (cross, dot, rotate, proj, angle...)
+* affine transformations
+* matrix decomposition (extract rotation, scaling factor)
+* optimized affine transform matrices (mul, rigid-body inverse)
+* camera (lookat)
+* projections (ortho, perspective)
+* quaternions
+* euler angles / yaw-pitch-roll to matrix
+* extract euler angles
+* inline or pre-compiled function call
+* frustum (extract view frustum planes, corners...)
+* bounding box (AABB in Frustum (culling), crop, merge...)
+* bounding sphere
+* project, unproject
+* easing functions
+* curves
+* curve interpolation helpers (SMC, deCasteljau...)
+* helpers to convert cglm types to Apple's simd library to pass cglm types to Metal GL without packing them on both sides
+* ray intersection helpers
+* and others...

docs/source/frustum.rst

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

docs/source/getting_started.rst

@@ -9,23 +9,26 @@ Types:
 .. code-block:: c
   :linenos:
 
-   typedef float vec3[3];
+  typedef float                   vec2[2];
-   typedef int  ivec3[3];
+  typedef float                   vec3[3];
-   typedef CGLM_ALIGN(16) float vec4[4];
+  typedef int                    ivec3[3];
+  typedef CGLM_ALIGN_IF(16) float vec4[4];
+  typedef vec4                    versor;
+  typedef vec3                    mat3[3];
 
-   typedef vec3 mat3[3];
+  #ifdef __AVX__
-   typedef vec4 mat4[4];
+  typedef CGLM_ALIGN_IF(32) vec4  mat4[4];
-
+  #else
-   typedef vec4 versor;
+  typedef CGLM_ALIGN_IF(16) vec4  mat4[4];
+  #endif
 
 As you can see types don't store extra informations in favor of space.
 You can send these values e.g. matrix to OpenGL directly without casting or calling a function like *value_ptr*
 
-Alignment is Required:
+Alignment Is Required:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-**vec4** and **mat4** requires 16 byte alignment because vec4 and mat4 operations are
+**vec4** and **mat4** requires 16 (32 for **mat4** if AVX is enabled) byte alignment because **vec4** and **mat4** operations are vectorized by SIMD instructions (SSE/AVX/NEON).
-vectorized by SIMD instructions (SSE/AVX).
 
 **UPDATE:**
   By starting v0.4.5 cglm provides an option to disable alignment requirement, it is enabled as default
@@ -37,10 +40,9 @@ vectorized by SIMD instructions (SSE/AVX).
 Allocations:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *cglm* doesn't alloc any memory on heap. So it doesn't provide any allocator.
-You must allocate memory yourself. You should alloc memory for out parameters too if you pass pointer of memory location.
+You must allocate memory yourself. You should alloc memory for out parameters too if you pass pointer of memory location. When allocating memory, don't forget that **vec4** and **mat4** require alignment.
-When allocating memory don't forget that **vec4** and **mat4** requires alignment.
 
-**NOTE:** Unaligned vec4 and unaligned mat4 operations will be supported in the future. Check todo list.
+**NOTE:** Unaligned **vec4** and unaligned **mat4** operations will be supported in the future. Check todo list.
 Because you may want to multiply a CGLM matrix with external matrix.
 There is no guarantee that non-CGLM matrix is aligned. Unaligned types will have *u* prefix e.g. **umat4**
 

docs/source/index.rst

@@ -3,7 +3,7 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Welcome to cglm's documentation!
+cglm Documentation
 ================================
 
 **cglm** is optimized 3D math library written in C99 (compatible with C89).
@@ -14,33 +14,36 @@ is considered to be supported as optional.
 
 Also currently only **float** type is supported for most operations.
 
-**Features**
-
-* general purpose matrix operations (mat4, mat3)
-* chain matrix multiplication (square only)
-* general purpose vector operations (cross, dot, rotate, proj, angle...)
-* affine transforms
-* matrix decomposition (extract rotation, scaling factor)
-* optimized affine transform matrices (mul, rigid-body inverse)
-* camera (lookat)
-* projections (ortho, perspective)
-* quaternions
-* euler angles / yaw-pitch-roll to matrix
-* extract euler angles
-* inline or pre-compiled function call
-* frustum (extract view frustum planes, corners...)
-* bounding box (AABB in Frustum (culling), crop, merge...)
-
-
 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
-   :caption: Table Of Contents:
+   :caption: Getting Started:
 
+   features
    build
    getting_started
+
+.. toctree::
+   :maxdepth: 2
+   :caption: How To:
+
    opengl
+
+.. toctree::
+   :maxdepth: 2
+   :caption: API:
+
    api
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Options:
+
    opt
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Troubleshooting:
+
    troubleshooting
 
 Indices and tables

docs/source/io.rst

@@ -28,6 +28,23 @@ Example to print mat4 matrix:
 (you probably will in some cases), you can change it temporary.
 cglm may provide precision parameter in the future
 
+Changes since **v0.7.3**:
+* Now mis-alignment of columns are fixed: larger numbers are printed via %g and others are printed via %f. Column withs are calculated before print.
+* Now values are colorful ;)
+* Some print improvements
+* New options with default values:
+
+.. code-block:: c
+
+    #define CGLM_PRINT_PRECISION    5
+    #define CGLM_PRINT_MAX_TO_SHORT 1e5
+    #define CGLM_PRINT_COLOR        "\033[36m"
+    #define CGLM_PRINT_COLOR_RESET  "\033[0m"
+
+* Inline prints are only enabled in DEBUG mode and if **CGLM_DEFINE_PRINTS** is defined.
+
+Check options page.
+
 Table of contents (click to go):
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

docs/source/mat2.rst

@@ -0,0 +1,179 @@
+.. default-domain:: C
+
+mat2
+====
+
+Header: cglm/mat2.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_mat2_IDENTITY_INIT
+#. GLM_mat2_ZERO_INIT
+#. GLM_mat2_IDENTITY
+#. GLM_mat2_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat2_copy`
+#. :c:func:`glm_mat2_identity`
+#. :c:func:`glm_mat2_identity_array`
+#. :c:func:`glm_mat2_zero`
+#. :c:func:`glm_mat2_mul`
+#. :c:func:`glm_mat2_transpose_to`
+#. :c:func:`glm_mat2_transpose`
+#. :c:func:`glm_mat2_mulv`
+#. :c:func:`glm_mat2_scale`
+#. :c:func:`glm_mat2_det`
+#. :c:func:`glm_mat2_inv`
+#. :c:func:`glm_mat2_trace`
+#. :c:func:`glm_mat2_swap_col`
+#. :c:func:`glm_mat2_swap_row`
+#. :c:func:`glm_mat2_rmc`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat2_copy(mat2 mat, mat2 dest)
+
+    copy mat2 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat2_identity(mat2 mat)
+
+    copy identity mat2 to mat, or makes mat to identiy
+
+    Parameters:
+      | *[out]* **mat**  matrix
+
+.. c:function:: void glm_mat2_identity_array(mat2 * __restrict mat, size_t count)
+
+    make given matrix array's each element identity matrix
+
+    Parameters:
+      | *[in,out]* **mat**  matrix array (must be aligned (16/32) if alignment is not disabled)
+      | *[in]* **count**  count of matrices
+
+.. c:function:: void glm_mat2_zero(mat2 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix to
+
+.. c:function:: void glm_mat2_mul(mat2 m1, mat2 m2, mat2 dest)
+
+    multiply m1 and m2 to dest
+    m1, m2 and dest matrices can be same matrix, it is possible to write this:
+
+    .. code-block:: c
+
+       mat2 m = GLM_mat2_IDENTITY_INIT;
+       glm_mat2_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat2_transpose_to(mat2 m, mat2 dest)
+
+    transpose mat4 and store in dest
+    source matrix will not be transposed unless dest is m
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat2_transpose(mat2 m)
+
+    tranpose mat2 and store result in same matrix
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat2_mulv(mat2 m, vec2 v, vec2 dest)
+
+    multiply mat4 with vec4 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **mat**   mat2 (left)
+      | *[in]*  **v**     vec2 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void  glm_mat2_scale(mat2 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **mat**   matrix
+      | *[in]*      **dest**  scalar
+
+.. c:function:: float  glm_mat2_det(mat2 mat)
+
+    returns mat2 determinant
+
+    Parameters:
+      | *[in]*  **mat**   matrix
+
+    Returns:
+        mat2 determinant
+
+.. c:function:: void glm_mat2_inv(mat2 mat, mat2 dest)
+
+    inverse mat2 and store in dest
+
+    Parameters:
+      | *[in]*  **mat**  matrix
+      | *[out]* **dest** destination (inverse matrix)
+
+.. c:function:: void glm_mat2_trace(mat2 m)
+
+    | sum of the elements on the main diagonal from upper left to the lower right
+
+    Parameters:
+      | *[in]*  **m**  matrix
+
+    Returns:
+        trace of matrix
+
+.. c:function:: void glm_mat2_swap_col(mat2 mat, int col1, int col2)
+
+    swap two matrix columns
+
+    Parameters:
+      | *[in, out]*  **mat**   matrix
+      | *[in]*       **col1**  col1
+      | *[in]*       **col2**  col2
+
+.. c:function:: void glm_mat2_swap_row(mat2 mat, int row1, int row2)
+
+    swap two matrix rows
+
+    Parameters:
+      | *[in, out]*  **mat**   matrix
+      | *[in]*       **row1**  row1
+      | *[in]*       **row2**  row2
+
+.. c:function:: float glm_mat2_rmc(vec2 r, mat2 m, vec2 c)
+
+    | **rmc** stands for **Row** * **Matrix** * **Column**
+
+    | helper for  R (row vector) * M (matrix) * C (column vector)
+
+    | the result is scalar because R * M = Matrix1x2 (row vector),
+    | then Matrix1x2 * Vec2 (column vector) = Matrix1x1 (Scalar)
+
+    Parameters:
+      | *[in]*  **r**  row vector or matrix1x2
+      | *[in]*  **m**  matrix2x2
+      | *[in]*  **c**  column vector or matrix2x1
+
+    Returns:
+        scalar value e.g. Matrix1x1

docs/source/mat3.rst

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

docs/source/mat4.rst

@@ -25,6 +25,8 @@ Functions:
 1. :c:func:`glm_mat4_ucopy`
 #. :c:func:`glm_mat4_copy`
 #. :c:func:`glm_mat4_identity`
+#. :c:func:`glm_mat4_identity_array`
+#. :c:func:`glm_mat4_zero`
 #. :c:func:`glm_mat4_pick3`
 #. :c:func:`glm_mat4_pick3t`
 #. :c:func:`glm_mat4_ins3`
@@ -32,6 +34,9 @@ Functions:
 #. :c:func:`glm_mat4_mulN`
 #. :c:func:`glm_mat4_mulv`
 #. :c:func:`glm_mat4_mulv3`
+#. :c:func:`glm_mat3_trace`
+#. :c:func:`glm_mat3_trace3`
+#. :c:func:`glm_mat4_quat`
 #. :c:func:`glm_mat4_transpose_to`
 #. :c:func:`glm_mat4_transpose`
 #. :c:func:`glm_mat4_scale_p`
@@ -41,6 +46,7 @@ Functions:
 #. :c:func:`glm_mat4_inv_fast`
 #. :c:func:`glm_mat4_swap_col`
 #. :c:func:`glm_mat4_swap_row`
+#. :c:func:`glm_mat4_rmc`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -68,6 +74,21 @@ Functions documentation
     Parameters:
       | *[out]* **mat**  matrix
 
+.. c:function:: void  glm_mat4_identity_array(mat4 * __restrict mat, size_t count)
+
+    make given matrix array's each element identity matrix
+
+    Parameters:
+      | *[in,out]* **mat**  matrix array (must be aligned (16/32) if alignment is not disabled)
+      | *[in]* **count**  count of matrices
+
+.. c:function:: void  glm_mat4_zero(mat4 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix to
+
 .. c:function:: void  glm_mat4_pick3(mat4 mat, mat3 dest)
 
     copy upper-left of mat4 to mat3
@@ -135,16 +156,51 @@ Functions documentation
     Parameters:
       | *[in]*  **m**     mat4 (left)
       | *[in]*  **v**     vec4 (right, column vector)
+      | *[in]*  **last**  4th item to make it vec4
       | *[out]* **dest**  vec4 (result, column vector)
 
-.. c:function:: void  glm_mat4_mulv3(mat4 m, vec3 v, vec3 dest)
+.. c:function:: void  glm_mat4_mulv3(mat4 m, vec3 v, float last, vec3 dest)
 
-    multiply vector with mat4's mat3 part(rotation)
+    | multiply **vec3** with **mat4** and get **vec3** as result
+    |
+    | actually the result is **vec4**, after multiplication, 
+      the last component is trimmed, if you need the result's last component 
+      then don't use this function and consider to use **glm_mat4_mulv()**
 
     Parameters:
-    | *[in]*  **m**     mat4 (left)
+      | *[in]*  **m**     mat4(affine transform)
-    | *[in]*  **v**     vec3 (right, column vector)
+      | *[in]*  **v**     vec3
-    | *[out]* **dest**  vec3 (result, column vector)
+      | *[in]*  **last**  4th item to make it vec4
+      | *[out]* **dest**  result vector (vec3)
+
+.. c:function:: void  glm_mat4_trace(mat4 m)
+
+    | sum of the elements on the main diagonal from upper left to the lower right
+
+    Parameters:
+      | *[in]*  **m**  matrix
+
+    Returns:
+        trace of matrix
+
+.. c:function:: void  glm_mat4_trace3(mat4 m)
+
+    | trace of matrix (rotation part)
+    | sum of the elements on the main diagonal from upper left to the lower right
+
+    Parameters:
+      | *[in]*  **m**  matrix
+
+    Returns:
+        trace of matrix
+
+.. c:function:: void  glm_mat4_quat(mat4 m, versor dest)
+
+    convert mat4's rotation part to quaternion
+
+    Parameters:
+    | *[in]*  **m**     affine matrix
+    | *[out]* **dest**  destination quaternion
 
 .. c:function:: void  glm_mat4_transpose_to(mat4 m, mat4 dest)
 
@@ -229,3 +285,20 @@ Functions documentation
       | *[in, out]*  **mat**   matrix
       | *[in]*       **row1**  row1
       | *[in]*       **row2**  row2
+
+.. c:function:: float  glm_mat4_rmc(vec4 r, mat4 m, vec4 c)
+
+    | **rmc** stands for **Row** * **Matrix** * **Column**
+
+    | helper for  R (row vector) * M (matrix) * C (column vector)
+
+    | the result is scalar because R * M = Matrix1x4 (row vector),
+    | then Matrix1x4 * Vec4 (column vector) = Matrix1x1 (Scalar)
+
+    Parameters:
+      | *[in]*  **r**  row vector or matrix1x4
+      | *[in]*  **m**  matrix4x4
+      | *[in]*  **c**  column vector or matrix4x1
+
+    Returns:
+        scalar value e.g. Matrix1x1

docs/source/opengl.rst

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

docs/source/opt.rst

@@ -18,7 +18,7 @@ versor: 16 byte
 By starting **v0.4.5** cglm provides an option to disable alignment requirement.
 To enable this option define **CGLM_ALL_UNALIGNED** macro before all headers.
 You can define it in Xcode, Visual Studio (or other IDEs) or you can also prefer
-to define it in build system. If you use pre-compiled verisons then you
+to define it in build system. If you use pre-compiled versions then you
 have to compile cglm with **CGLM_ALL_UNALIGNED** macro.
 
 **VERY VERY IMPORTANT:** If you use cglm in multiple projects and
@@ -40,3 +40,46 @@ SSE and SSE2 Shuffle Option
 **_mm_shuffle_ps** generates **shufps** instruction even if registers are same.
 You can force it to generate **pshufd** instruction by defining
 **CGLM_USE_INT_DOMAIN** macro. As default it is not defined.
+
+SSE3 and SSE4 Dot Product Options
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+You have to extra options for dot product: **CGLM_SSE4_DOT** and **CGLM_SSE3_DOT**.
+
+- If **SSE4** is enabled then you can define **CGLM_SSE4_DOT** to force cglm to use **_mm_dp_ps** instruction.
+- If **SSE3** is enabled then you can define **CGLM_SSE3_DOT** to force cglm to use **_mm_hadd_ps** instructions.
+
+otherwise cglm will use custom cglm's hadd functions which are optimized too.
+
+Print Options
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+1. **CGLM_DEFINE_PRINTS**
+2. **CGLM_NO_PRINTS_NOOP** (use CGLM_DEFINE_PRINTS)
+
+Inline prints are only enabled in **DEBUG** mode or if **CGLM_DEFINE_PRINTS** is defined.
+**glmc_** versions will always print too.
+
+Because **cglm** tried to enable print functions in debug mode and disable them in
+release/production mode to eliminate printing costs when we do not need them.
+
+**cglm** checks **DEBUG** or **_DEBUG** macros to test debug mode, if these are not working for you then you can use 
+**CGLM_DEFINE_PRINTS** to force enable, or create a PR to introduce new macro to test against debugging mode.
+
+If DEBUG mode is not enabled then print functions will be emptied to eliminate print function calls.
+You can disable this feature too by defining **CGLM_DEFINE_PRINTS** macro top of cglm header 
+or in project/build settings...
+
+3. **CGLM_PRINT_PRECISION**    5
+
+precision.
+
+4. **CGLM_PRINT_MAX_TO_SHORT** 1e5
+
+if a number is greater than this value then %g will be used, since this is shorten print you won't be able to see high precision.
+
+5. **CGLM_PRINT_COLOR**        "\033[36m"
+6. **CGLM_PRINT_COLOR_RESET**  "\033[0m"
+
+You can disable colorful print output by defining **CGLM_PRINT_COLOR** and **CGLM_PRINT_COLOR_RESET** as empty macro.
+Because some terminals may not support colors.

docs/source/quat.rst

@@ -27,6 +27,7 @@ Macros:
 Functions:
 
 1. :c:func:`glm_quat_identity`
+#. :c:func:`glm_quat_identity_array`
 #. :c:func:`glm_quat_init`
 #. :c:func:`glm_quat`
 #. :c:func:`glm_quatv`
@@ -70,6 +71,14 @@ Functions documentation
     Parameters:
       | *[in, out]*  **q**    quaternion
 
+.. c:function:: void  glm_quat_identity_array(versor * __restrict q, size_t count)
+
+    | make given quaternion array's each element identity quaternion
+
+    Parameters:
+      | *[in, out]*  **q**   quat array (must be aligned (16) if alignment is not disabled)
+      | *[in]*  **count**    count of quaternions
+
 .. c:function:: void  glm_quat_init(versor q, float x, float y, float z, float w)
 
     | inits quaternion with given values
@@ -315,26 +324,24 @@ Functions documentation
       | *[in]*  **ori**   orientation in world space as quaternion
       | *[out]* **dest**  result matrix
 
-.. c:function:: void  glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest)
+.. c:function:: void  glm_quat_for(vec3 dir, vec3 up, versor dest)
 
     | creates look rotation quaternion
 
     Parameters:
       | *[in]*  **dir**   direction to look
-      | *[in]*  **fwd**   forward vector
       | *[in]*  **up**    up vector
       | *[out]* **dest**  result matrix
 
-.. c:function:: void  glm_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest)
+.. c:function:: void  glm_quat_forp(vec3 from, vec3 to, vec3 up, versor dest)
 
-    | creates look rotation quaternion using source and  destination positions p suffix stands for position
+    | creates look rotation quaternion using source and destination positions p suffix stands for position
 
     | this is similar to glm_quat_for except this computes direction for glm_quat_for for you.
 
     Parameters:
       | *[in]*  **from**  source point
       | *[in]*  **to**    destination point
-      | *[in]*  **fwd**   forward vector
       | *[in]*  **up**    up vector
       | *[out]* **dest**  result matrix
 
@@ -367,7 +374,7 @@ 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

docs/source/ray.rst

@@ -0,0 +1,31 @@
+.. default-domain:: C
+
+ray
+====
+
+Header: cglm/ray.h
+
+This is for collision-checks used by ray-tracers and the like.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_ray_triangle`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: bool  glm_ray_triangle(vec3 origin, vec3 direction, vec3 v0, vec3 v1, vec3 v2, float *d)
+
+    Möller–Trumbore ray-triangle intersection algorithm
+
+    Parameters:
+      | *[in]*       **origin**        origin of ray
+      | *[in]*       **direction**     direction of ray
+      | *[in]*       **v0**            first vertex of triangle
+      | *[in]*       **v1**            second vertex of triangle
+      | *[in]*       **v2**            third vertex of triangle
+      | *[in, out]*  **d**             float pointer to save distance to intersection
+      | *[out]*      **intersection**  whether there is intersection

docs/source/sphere.rst

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

docs/source/troubleshooting.rst

@@ -57,12 +57,19 @@ For instance you may called **glm_vec4_** functions for **vec3** data type.
 It will try to write 32 byte but since **vec3** is 24 byte it should throw
 memory access error or exit the app without saying anything.
 
+**UPDATE - IMPORTANT:** 
+
+  | On MSVC or some other compilers, if alignment is enabled (default) then double check alignment requirements if you got a crash.
+
+  | If you send GLM_VEC4_ONE or similar macros directly to a function, it may be crashed.
+  | Because compiler may not apply alignment as defined on **typedef** to that macro while passing it (on stack) to a function.
+
 Wrong Results:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Again, you may used wrong function.
 
-For instance if you use **glm_normalize()** or **glm_vec_normalize()** for **vec4**,
+For instance if you use **glm_normalize()** or **glm_vec3_normalize()** for **vec4**,
 it will assume that passed param is **vec3** and will normalize it for **vec3**.
 Since you need to **vec4** to be normalized in your case, you will get wrong results.
 
@@ -73,6 +80,19 @@ So be carefull, when your IDE (Xcode, Visual Studio ...) tried to autocomplete f
 
 **Also implementation may be wrong please let us know by creating an issue on Github.**
 
+BAD_ACCESS : Thread 1: EXC_BAD_ACCESS (code=EXC_I386_GPFLT) or Similar Errors/Crashes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This is similar issue with alignment. For instance if you compiled **cglm** with 
+AVX (**-mavx**, intentionally or not) and if you use **cglm** in an environment that doesn't 
+support AVX (or if AVX is disabled intentionally) e.g. environment that max support SSE2/3/4, 
+then you probably get **BAD ACCESS** or similar...
+
+Because if you compile **cglm** with AVX it aligns **mat4** with 32 byte boundary, 
+and your project aligns that as 16 byte boundary...
+
+Check alignment, supported vector extension or simd in **cglm** and linked projects...
+
 Other Issues?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

docs/source/util.rst

@@ -23,6 +23,7 @@ Functions:
 #. :c:func:`glm_max`
 #. :c:func:`glm_clamp`
 #. :c:func:`glm_lerp`
+#. :c:func:`glm_swapf`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -136,3 +137,46 @@ Functions documentation
 
     Returns:
        interpolated value
+
+.. c:function:: bool glm_eq(float a, float b)
+
+    check if two float equal with using EPSILON
+
+    Parameters:
+      | *[in]*  **a**   a
+      | *[in]*  **b**   b
+
+    Returns:
+       true if a and b are equal
+
+.. c:function:: float glm_percent(float from, float to, float current)
+
+    percentage of current value between start and end value
+
+    Parameters:
+      | *[in]*  **from**   from value
+      | *[in]*  **to**     to value
+      | *[in]*  **current**   value between from and to values
+
+    Returns:
+       percentage of current value
+
+.. c:function:: float glm_percentc(float from, float to, float current)
+
+    clamped percentage of current value between start and end value
+
+    Parameters:
+      | *[in]*  **from**      from value
+      | *[in]*  **to**        to value
+      | *[in]*  **current**   value between from and to values
+
+    Returns:
+       clamped normalized percent (0-100 in 0-1)
+
+.. c:function:: void glm_swapf(float *a, float *b) 
+
+    swap two float values
+
+    Parameters:
+      | *[in]*  **a**      float 1
+      | *[in]*  **b**      float 2

docs/source/vec2-ext.rst

@@ -0,0 +1,134 @@
+.. default-domain:: C
+
+vec2 extra
+==========
+
+Header: cglm/vec2-ext.h
+
+There are some functions are in called in extra header. These are called extra
+because they are not used like other functions in vec2.h in the future some of
+these functions ma be moved to vec2 header.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_vec2_fill`
+#. :c:func:`glm_vec2_eq`
+#. :c:func:`glm_vec2_eq_eps`
+#. :c:func:`glm_vec2_eq_all`
+#. :c:func:`glm_vec2_eqv`
+#. :c:func:`glm_vec2_eqv_eps`
+#. :c:func:`glm_vec2_max`
+#. :c:func:`glm_vec2_min`
+#. :c:func:`glm_vec2_isnan`
+#. :c:func:`glm_vec2_isinf`
+#. :c:func:`glm_vec2_isvalid`
+#. :c:func:`glm_vec2_sign`
+#. :c:func:`glm_vec2_sqrt`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_vec2_fill(vec2 v, float val)
+
+    fill a vector with specified value
+
+    Parameters:
+      | *[in,out]* **dest**  destination
+      | *[in]*     **val**   value
+      
+
+.. c:function:: bool glm_vec2_eq(vec2 v, float val)
+
+    check if vector is equal to value (without epsilon)
+
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **val**  value
+
+.. c:function:: bool glm_vec2_eq_eps(vec2 v, float val)
+
+    check if vector is equal to value (with epsilon)
+
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **val**  value
+
+.. c:function:: bool glm_vec2_eq_all(vec2 v)
+
+    check if vectors members are equal (without epsilon)
+
+    Parameters:
+      | *[in]*  **v**   vector
+
+.. c:function:: bool glm_vec2_eqv(vec2 v1, vec2 v2)
+
+    check if vector is equal to another (without epsilon) vector
+
+    Parameters:
+      | *[in]*  **vec**   vector 1
+      | *[in]*  **vec**   vector 2
+
+.. c:function:: bool glm_vec2_eqv_eps(vec2 v1, vec2 v2)
+
+    check if vector is equal to another (with epsilon)
+
+    Parameters:
+      | *[in]*  **v1**    vector1
+      | *[in]*  **v2**    vector2
+
+.. c:function:: float glm_vec2_max(vec2 v)
+
+    max value of vector
+
+    Parameters:
+      | *[in]*  **v**    vector
+
+.. c:function:: float glm_vec2_min(vec2 v)
+
+     min value of vector
+
+    Parameters:
+      | *[in]*  **v**  vector
+
+.. c:function:: bool glm_vec2_isnan(vec2 v)
+
+    | check if one of items is NaN (not a number)
+    | you should only use this in DEBUG mode or very critical asserts
+
+    Parameters:
+      | *[in]*  **v**  vector
+
+.. c:function:: bool glm_vec2_isinf(vec2 v)
+
+    | check if one of items is INFINITY
+    | you should only use this in DEBUG mode or very critical asserts
+
+    Parameters:
+      | *[in]*  **v**  vector
+
+.. c:function:: bool glm_vec2_isvalid(vec2 v)
+
+    | check if all items are valid number
+    | you should only use this in DEBUG mode or very critical asserts
+
+    Parameters:
+      | *[in]*  **v**  vector
+
+.. c:function:: void glm_vec2_sign(vec2 v, vec2 dest)
+
+    get sign of 32 bit float as +1, -1, 0
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  sign vector (only keeps signs as -1, 0, -1)
+
+.. c:function:: void glm_vec2_sqrt(vec2 v, vec2 dest)
+
+    square root of each vector item
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  destination vector (sqrt(v))

docs/source/vec2.rst

@@ -0,0 +1,375 @@
+.. default-domain:: C
+
+vec2
+====
+
+Header: cglm/vec2.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_vec2_ONE_INIT
+#. GLM_vec2_ZERO_INIT
+#. GLM_vec2_ONE
+#. GLM_vec2_ZERO
+
+Functions:
+
+1. :c:func:`glm_vec2`
+#. :c:func:`glm_vec2_copy`
+#. :c:func:`glm_vec2_zero`
+#. :c:func:`glm_vec2_one`
+#. :c:func:`glm_vec2_dot`
+#. :c:func:`glm_vec2_cross`
+#. :c:func:`glm_vec2_norm2`
+#. :c:func:`glm_vec2_norm`
+#. :c:func:`glm_vec2_add`
+#. :c:func:`glm_vec2_adds`
+#. :c:func:`glm_vec2_sub`
+#. :c:func:`glm_vec2_subs`
+#. :c:func:`glm_vec2_mul`
+#. :c:func:`glm_vec2_scale`
+#. :c:func:`glm_vec2_scale_as`
+#. :c:func:`glm_vec2_div`
+#. :c:func:`glm_vec2_divs`
+#. :c:func:`glm_vec2_addadd`
+#. :c:func:`glm_vec2_subadd`
+#. :c:func:`glm_vec2_muladd`
+#. :c:func:`glm_vec2_muladds`
+#. :c:func:`glm_vec2_maxadd`
+#. :c:func:`glm_vec2_minadd`
+#. :c:func:`glm_vec2_negate`
+#. :c:func:`glm_vec2_negate_to`
+#. :c:func:`glm_vec2_normalize`
+#. :c:func:`glm_vec2_normalize_to`
+#. :c:func:`glm_vec2_rotate`
+#. :c:func:`glm_vec2_distance2`
+#. :c:func:`glm_vec2_distance`
+#. :c:func:`glm_vec2_maxv`
+#. :c:func:`glm_vec2_minv`
+#. :c:func:`glm_vec2_clamp`
+#. :c:func:`glm_vec2_lerp`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_vec2(float * v, vec2 dest)
+
+    init vec2 using vec3 or vec4
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_vec2_copy(vec2 a, vec2 dest)
+
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**     source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_vec2_zero(vec2 v)
+
+    makes all members 0.0f (zero)
+
+    Parameters:
+      | *[in, out]*  **v**     vector
+
+.. c:function:: void  glm_vec2_one(vec2 v)
+
+    makes all members 1.0f (one)
+
+    Parameters:
+      | *[in, out]*  **v**     vector
+
+.. c:function:: float glm_vec2_dot(vec2 a, vec2 b)
+
+    dot product of vec2
+
+    Parameters:
+      | *[in]*  **a**  vector1
+      | *[in]*  **b**  vector2
+
+    Returns:
+      dot product
+
+.. c:function:: void glm_vec2_cross(vec2 a, vec2 b, vec2 d)
+
+    cross product of two vector (RH)
+
+    | ref: http://allenchou.net/2013/07/cross-product-of-2d-vectors/
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  destination
+
+    Returns:
+      Z component of cross product
+
+.. c:function:: float glm_vec2_norm2(vec2 v)
+
+    norm * norm (magnitude) of vector
+
+    we can use this func instead of calling norm * norm, because it would call
+    sqrtf fuction twice but with this func we can avoid func call, maybe this is
+    not good name for this func
+
+    Parameters:
+      | *[in]*  **v**   vector
+
+    Returns:
+      square of norm / magnitude
+
+.. c:function:: float glm_vec2_norm(vec2 vec)
+
+    | euclidean norm (magnitude), also called L2 norm
+    | this will give magnitude of vector in euclidean space
+
+    Parameters:
+      | *[in]*  **vec**   vector
+
+.. c:function:: void glm_vec2_add(vec2 a, vec2 b, vec2 dest)
+
+    add a vector to b vector store result in dest
+
+    Parameters:
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void glm_vec2_adds(vec2 a, float s, vec2 dest)
+
+    add scalar to v vector store result in dest (d = v + vec(s))
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void glm_vec2_sub(vec2 v1, vec2 v2, vec2 dest)
+
+    subtract b vector from a vector store result in dest (d = v1 - v2)
+
+    Parameters:
+      | *[in]*  **a**     vector1
+      | *[in]*  **b**     vector2
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void glm_vec2_subs(vec2 v, float s, vec2 dest)
+
+    subtract scalar from v vector store result in dest (d = v - vec(s))
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void glm_vec2_mul(vec2 a, vec2 b, vec2 d)
+
+    multiply two vector (component-wise multiplication)
+
+    Parameters:
+      | *[in]*  **a**     vector
+      | *[in]*  **b**     scalar
+      | *[out]* **d**     result = (a[0] * b[0], a[1] * b[1], a[2] * b[2])
+
+.. c:function:: void glm_vec2_scale(vec2 v, float s, vec2 dest)
+
+     multiply/scale vec2 vector with scalar: result = v * s
+
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void glm_vec2_scale_as(vec2 v, float s, vec2 dest)
+
+    make vec2 vector scale as specified: result = unit(v) * s
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  destination vector
+
+.. c:function:: void glm_vec2_div(vec2 a, vec2 b, vec2 dest)
+
+    div vector with another component-wise division: d = a / b
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  result = (a[0] / b[0], a[1] / b[1], a[2] / b[2])
+
+.. c:function:: void glm_vec2_divs(vec2 v, float s, vec2 dest)
+
+    div vector with scalar: d = v / s
+
+    Parameters:
+      | *[in]*  **v**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  result = (a[0] / s, a[1] / s, a[2] / s])
+
+.. c:function:: void glm_vec2_addadd(vec2 a, vec2 b, vec2 dest)
+
+    | add two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a + b)
+
+.. c:function:: void glm_vec2_subadd(vec2 a, vec2 b, vec2 dest)
+
+    | sub two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a - b)
+
+.. c:function:: void glm_vec2_muladd(vec2 a, vec2 b, vec2 dest)
+
+    | mul two vectors and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void glm_vec2_muladds(vec2 a, float s, vec2 dest)
+
+    | mul vector with scalar and add result to sum
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector
+      | *[in]*  **s**     scalar
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void glm_vec2_maxadd(vec2 a, vec2 b, vec2 dest)
+
+    | add max of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void glm_vec2_minadd(vec2 a, vec2 b, vec2 dest)
+
+    | add min of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void glm_vec2_negate(vec2 v)
+
+    negate vector components
+
+    Parameters:
+      | *[in, out]*  **v**    vector
+
+.. c:function:: void glm_vec2_negate_to(vec2 v, vec2 dest)
+
+    negate vector components and store result in dest
+
+    Parameters:
+      | *[in]*  **v**       vector
+      | *[out]* **dest**    negated vector
+
+.. c:function:: void glm_vec2_normalize(vec2 v)
+
+    normalize vec2 and store result in same vec
+
+    Parameters:
+      | *[in, out]*  **v**    vector
+
+.. c:function:: void glm_vec2_normalize_to(vec2 vec, vec2 dest)
+
+     normalize vec2 to dest
+
+    Parameters:
+      | *[in]*   **vec**   source
+      | *[out]*  **dest**  destination
+
+.. c:function:: void glm_vec2_rotate(vec2 v, float angle, vec2 dest)
+
+     rotate vec2 around axis by angle using Rodrigues' rotation formula
+
+    Parameters:
+      | *[in]*  **v**      vector
+      | *[in]*  **axis**   axis vector
+      | *[out]* **dest**   destination
+
+.. c:function:: float glm_vec2_distance2(vec2 v1, vec2 v2)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **mat**   vector1
+      | *[in]*  **row1**  vector2
+
+    Returns:
+      | squared distance (distance * distance)
+
+.. c:function:: float glm_vec2_distance(vec2 v1, vec2 v2)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **mat**   vector1
+      | *[in]*  **row1**  vector2
+
+    Returns:
+      | distance
+
+.. c:function:: void glm_vec2_maxv(vec2 v1, vec2 v2, vec2 dest)
+
+    max values of vectors
+
+    Parameters:
+      | *[in]*  **v1**    vector1
+      | *[in]*  **v2**    vector2
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_vec2_minv(vec2 v1, vec2 v2, vec2 dest)
+
+    min values of vectors
+
+    Parameters:
+      | *[in]*  **v1**    vector1
+      | *[in]*  **v2**    vector2
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_vec2_clamp(vec2 v, float minVal, float maxVal)
+
+    constrain a value to lie between two further values
+
+    Parameters:
+      | *[in, out]*  **v**       vector
+      | *[in]*       **minVal**  minimum value
+      | *[in]*       **maxVal**  maximum value
+
+.. c:function:: void glm_vec2_lerp(vec2 from, vec2 to, float t, vec2 dest)
+
+    linear interpolation between two vector
+
+    | formula:  from + s * (to - from)
+
+    Parameters:
+      | *[in]*  **from**   from value
+      | *[in]*  **to**     to value
+      | *[in]*  **t**      interpolant (amount) clamped between 0 and 1
+      | *[out]* **dest**   destination

docs/source/vec3-ext.rst

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

docs/source/vec3.rst

@@ -5,9 +5,14 @@ vec3
 
 Header: cglm/vec3.h
 
+ **Important:** *cglm* was used **glm_vec_** namespace for vec3 functions until
+ **v0.5.0**, since **v0.5.0** cglm uses **glm_vec3_** namespace for vec3.
+
+ Also `glm_vec3_flipsign` has been renamed to `glm_vec3_negate`
+
 We mostly use vectors in graphics math, to make writing code faster
 and easy to read, some *vec3* functions are aliased in global namespace.
-For instance :c:func:`glm_dot` is alias of :c:func:`glm_vec_dot`,
+For instance :c:func:`glm_dot` is alias of :c:func:`glm_vec3_dot`,
 alias means inline wrapper here. There is no call verison of alias functions
 
 There are also functions for rotating *vec3* vector. **_m4**, **_m3** prefixes
@@ -18,7 +23,7 @@ Table of contents (click to go):
 
 Macros:
 
-1. glm_vec_dup(v, dest)
+1. glm_vec3_dup(v, dest)
 #. GLM_VEC3_ONE_INIT
 #. GLM_VEC3_ZERO_INIT
 #. GLM_VEC3_ONE
@@ -30,44 +35,50 @@ Macros:
 Functions:
 
 1. :c:func:`glm_vec3`
-#. :c:func:`glm_vec_copy`
+#. :c:func:`glm_vec3_copy`
-#. :c:func:`glm_vec_zero`
+#. :c:func:`glm_vec3_zero`
-#. :c:func:`glm_vec_one`
+#. :c:func:`glm_vec3_one`
-#. :c:func:`glm_vec_dot`
+#. :c:func:`glm_vec3_dot`
-#. :c:func:`glm_vec_cross`
+#. :c:func:`glm_vec3_norm2`
-#. :c:func:`glm_vec_norm2`
+#. :c:func:`glm_vec3_norm`
-#. :c:func:`glm_vec_norm`
+#. :c:func:`glm_vec3_add`
-#. :c:func:`glm_vec_add`
+#. :c:func:`glm_vec3_adds`
-#. :c:func:`glm_vec_adds`
+#. :c:func:`glm_vec3_sub`
-#. :c:func:`glm_vec_sub`
+#. :c:func:`glm_vec3_subs`
-#. :c:func:`glm_vec_subs`
+#. :c:func:`glm_vec3_mul`
-#. :c:func:`glm_vec_mul`
+#. :c:func:`glm_vec3_scale`
-#. :c:func:`glm_vec_scale`
+#. :c:func:`glm_vec3_scale_as`
-#. :c:func:`glm_vec_scale_as`
+#. :c:func:`glm_vec3_div`
-#. :c:func:`glm_vec_div`
+#. :c:func:`glm_vec3_divs`
-#. :c:func:`glm_vec_divs`
+#. :c:func:`glm_vec3_addadd`
-#. :c:func:`glm_vec_addadd`
+#. :c:func:`glm_vec3_subadd`
-#. :c:func:`glm_vec_subadd`
+#. :c:func:`glm_vec3_muladd`
-#. :c:func:`glm_vec_muladd`
+#. :c:func:`glm_vec3_muladds`
-#. :c:func:`glm_vec_muladds`
+#. :c:func:`glm_vec3_maxadd`
-#. :c:func:`glm_vec_flipsign`
+#. :c:func:`glm_vec3_minadd`
-#. :c:func:`glm_vec_flipsign_to`
+#. :c:func:`glm_vec3_flipsign`
-#. :c:func:`glm_vec_inv`
+#. :c:func:`glm_vec3_flipsign_to`
-#. :c:func:`glm_vec_inv_to`
+#. :c:func:`glm_vec3_inv`
-#. :c:func:`glm_vec_normalize`
+#. :c:func:`glm_vec3_inv_to`
-#. :c:func:`glm_vec_normalize_to`
+#. :c:func:`glm_vec3_negate`
-#. :c:func:`glm_vec_distance`
+#. :c:func:`glm_vec3_negate_to`
-#. :c:func:`glm_vec_angle`
+#. :c:func:`glm_vec3_normalize`
-#. :c:func:`glm_vec_rotate`
+#. :c:func:`glm_vec3_normalize_to`
-#. :c:func:`glm_vec_rotate_m4`
+#. :c:func:`glm_vec3_cross`
-#. :c:func:`glm_vec_rotate_m3`
+#. :c:func:`glm_vec3_crossn`
-#. :c:func:`glm_vec_proj`
+#. :c:func:`glm_vec3_distance2`
-#. :c:func:`glm_vec_center`
+#. :c:func:`glm_vec3_distance`
-#. :c:func:`glm_vec_maxv`
+#. :c:func:`glm_vec3_angle`
-#. :c:func:`glm_vec_minv`
+#. :c:func:`glm_vec3_rotate`
-#. :c:func:`glm_vec_ortho`
+#. :c:func:`glm_vec3_rotate_m4`
-#. :c:func:`glm_vec_clamp`
+#. :c:func:`glm_vec3_rotate_m3`
-#. :c:func:`glm_vec_lerp`
+#. :c:func:`glm_vec3_proj`
+#. :c:func:`glm_vec3_center`
+#. :c:func:`glm_vec3_maxv`
+#. :c:func:`glm_vec3_minv`
+#. :c:func:`glm_vec3_ortho`
+#. :c:func:`glm_vec3_clamp`
+#. :c:func:`glm_vec3_lerp`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -80,7 +91,7 @@ Functions documentation
       | *[in]*  **v4**    vector4
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_copy(vec3 a, vec3 dest)
+.. c:function:: void  glm_vec3_copy(vec3 a, vec3 dest)
 
     copy all members of [a] to [dest]
 
@@ -88,21 +99,21 @@ Functions documentation
       | *[in]*  **a**     source
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_zero(vec3 v)
+.. c:function:: void  glm_vec3_zero(vec3 v)
 
     makes all members 0.0f (zero)
 
     Parameters:
       | *[in, out]*  **v**     vector
 
-.. c:function:: void  glm_vec_one(vec3 v)
+.. c:function:: void  glm_vec3_one(vec3 v)
 
     makes all members 1.0f (one)
 
     Parameters:
       | *[in, out]*  **v**     vector
 
-.. c:function:: float  glm_vec_dot(vec3 a, vec3 b)
+.. c:function:: float  glm_vec3_dot(vec3 a, vec3 b)
 
     dot product of vec3
 
@@ -113,16 +124,25 @@ Functions documentation
     Returns:
       dot product
 
-.. c:function:: void  glm_vec_cross(vec3 a, vec3 b, vec3 d)
+.. c:function:: void  glm_vec3_cross(vec3 a, vec3 b, vec3 d)
 
-    cross product
+    cross product of two vector (RH)
 
     Parameters:
-      | *[in]*  **a**  source 1
+      | *[in]*  **a**     vector 1
-      | *[in]*  **b**  source 2
+      | *[in]*  **b**     vector 2
-      | *[out]* **d**  destination
+      | *[out]* **dest**  destination
 
-.. c:function:: float  glm_vec_norm2(vec3 v)
+.. c:function:: void  glm_vec3_crossn(vec3 a, vec3 b, vec3 dest)
+
+    cross product of two vector (RH) and normalize the result
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  destination
+
+.. c:function:: float  glm_vec3_norm2(vec3 v)
 
     norm * norm (magnitude) of vector
 
@@ -136,14 +156,15 @@ Functions documentation
     Returns:
       square of norm / magnitude
 
-.. c:function:: float  glm_vec_norm(vec3 vec)
+.. c:function:: float  glm_vec3_norm(vec3 vec)
 
-    norm (magnitude) of vec3
+    | euclidean norm (magnitude), also called L2 norm
+    | this will give magnitude of vector in euclidean space
 
     Parameters:
       | *[in]*  **vec**   vector
 
-.. c:function:: void  glm_vec_add(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_add(vec3 a, vec3 b, vec3 dest)
 
     add a vector to b vector store result in dest
 
@@ -152,7 +173,7 @@ Functions documentation
       | *[in]*  **b**     vector2
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_adds(vec3 a, float s, vec3 dest)
+.. c:function:: void  glm_vec3_adds(vec3 a, float s, vec3 dest)
 
     add scalar to v vector store result in dest (d = v + vec(s))
 
@@ -161,7 +182,7 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_sub(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_sub(vec3 v1, vec3 v2, vec3 dest)
 
     subtract b vector from a vector store result in dest (d = v1 - v2)
 
@@ -170,7 +191,7 @@ Functions documentation
       | *[in]*  **b**     vector2
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_subs(vec3 v, float s, vec3 dest)
+.. c:function:: void  glm_vec3_subs(vec3 v, float s, vec3 dest)
 
     subtract scalar from v vector store result in dest (d = v - vec(s))
 
@@ -179,7 +200,7 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_mul(vec3 a, vec3 b, vec3 d)
+.. c:function:: void  glm_vec3_mul(vec3 a, vec3 b, vec3 d)
 
     multiply two vector (component-wise multiplication)
 
@@ -188,7 +209,7 @@ Functions documentation
       | *[in]*  **b**     scalar
       | *[out]* **d**     result = (a[0] * b[0], a[1] * b[1], a[2] * b[2])
 
-.. c:function:: void glm_vec_scale(vec3 v, float s, vec3 dest)
+.. c:function:: void glm_vec3_scale(vec3 v, float s, vec3 dest)
 
      multiply/scale vec3 vector with scalar: result = v * s
 
@@ -198,7 +219,7 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_scale_as(vec3 v, float s, vec3 dest)
+.. c:function:: void  glm_vec3_scale_as(vec3 v, float s, vec3 dest)
 
     make vec3 vector scale as specified: result = unit(v) * s
 
@@ -207,7 +228,7 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  destination vector
 
-.. c:function:: void  glm_vec_div(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_div(vec3 a, vec3 b, vec3 dest)
 
     div vector with another component-wise division: d = a / b
 
@@ -216,7 +237,7 @@ Functions documentation
       | *[in]*  **b**     vector 2
       | *[out]* **dest**  result = (a[0] / b[0], a[1] / b[1], a[2] / b[2])
 
-.. c:function:: void  glm_vec_divs(vec3 v, float s, vec3 dest)
+.. c:function:: void  glm_vec3_divs(vec3 v, float s, vec3 dest)
 
     div vector with scalar: d = v / s
 
@@ -225,7 +246,7 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  result = (a[0] / s, a[1] / s, a[2] / s])
 
-.. c:function:: void  glm_vec_addadd(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_addadd(vec3 a, vec3 b, vec3 dest)
 
     | add two vectors and add result to sum
     | it applies += operator so dest must be initialized
@@ -235,7 +256,7 @@ Functions documentation
       | *[in]*  **b**     vector 2
       | *[out]* **dest**  dest += (a + b)
 
-.. c:function:: void  glm_vec_subadd(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_subadd(vec3 a, vec3 b, vec3 dest)
 
     | sub two vectors and add result to sum
     | it applies += operator so dest must be initialized
@@ -245,7 +266,7 @@ Functions documentation
       | *[in]*  **b**     vector 2
       | *[out]* **dest**  dest += (a - b)
 
-.. c:function:: void  glm_vec_muladd(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_muladd(vec3 a, vec3 b, vec3 dest)
 
     | mul two vectors and add result to sum
     | it applies += operator so dest must be initialized
@@ -255,7 +276,7 @@ Functions documentation
       | *[in]*  **b**     vector 2
       | *[out]* **dest**  dest += (a * b)
 
-.. c:function:: void  glm_vec_muladds(vec3 a, float s, vec3 dest)
+.. c:function:: void  glm_vec3_muladds(vec3 a, float s, vec3 dest)
 
     | mul vector with scalar and add result to sum
     | it applies += operator so dest must be initialized
@@ -265,44 +286,87 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  dest += (a * b)
 
-.. c:function:: void  glm_vec_flipsign(vec3 v)
+.. c:function:: void  glm_vec3_maxadd(vec3 a, vec3 b, vec3 dest)
 
-    flip sign of all vec3 members
+    | add max of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec3_minadd(vec3 a, vec3 b, vec3 dest)
+
+    | add min of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec3_flipsign(vec3 v)
+
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate`
 
     Parameters:
       | *[in, out]*  **v**    vector
 
-.. c:function:: void  glm_vec_flipsign_to(vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_flipsign_to(vec3 v, vec3 dest)
 
-    flip sign of all vec3 members and store result in dest
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate_to`
 
     Parameters:
       | *[in]*  **v**       vector
       | *[out]* **dest**    negated vector
 
-.. c:function:: void  glm_vec_inv(vec3 v)
+.. c:function:: void  glm_vec3_inv(vec3 v)
 
-    make vector as inverse/opposite of itself
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate`
 
     Parameters:
       | *[in, out]*  **v**    vector
 
-.. c:function:: void  glm_vec_inv_to(vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_inv_to(vec3 v, vec3 dest)
 
-    inverse/opposite vector
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec3_negate_to`
 
     Parameters:
       | *[in]*  **v**     source
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_normalize(vec3 v)
+.. c:function:: void  glm_vec3_negate(vec3 v)
+
+    negate vector components
+
+    Parameters:
+      | *[in, out]*  **v**    vector
+
+.. c:function:: void  glm_vec3_negate_to(vec3 v, vec3 dest)
+
+    negate vector components and store result in dest
+
+    Parameters:
+      | *[in]*  **v**       vector
+      | *[out]* **dest**    negated vector
+
+.. c:function:: void  glm_vec3_normalize(vec3 v)
 
     normalize vec3 and store result in same vec
 
     Parameters:
       | *[in, out]*  **v**    vector
 
-.. c:function:: void  glm_vec_normalize_to(vec3 vec, vec3 dest)
+.. c:function:: void  glm_vec3_normalize_to(vec3 vec, vec3 dest)
 
      normalize vec3 to dest
 
@@ -310,7 +374,7 @@ Functions documentation
       | *[in]*   **vec**   source
       | *[out]*  **dest**  destination
 
-.. c:function:: float  glm_vec_angle(vec3 v1, vec3 v2)
+.. c:function:: float  glm_vec3_angle(vec3 v1, vec3 v2)
 
     angle betwen two vector
 
@@ -321,16 +385,16 @@ Functions documentation
     Return:
       | angle as radians
 
-.. c:function:: void  glm_vec_rotate(vec3 v, float angle, vec3 axis)
+.. c:function:: void  glm_vec3_rotate(vec3 v, float angle, vec3 axis)
 
      rotate vec3 around axis by angle using Rodrigues' rotation formula
 
     Parameters:
       | *[in, out]*  **v**      vector
       | *[in]*       **axis**   axis vector (will be normalized)
-      | *[out]*      **angle**  angle (radians)
+      | *[in]*       **angle**  angle (radians)
 
-.. c:function:: void  glm_vec_rotate_m4(mat4 m, vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_rotate_m4(mat4 m, vec3 v, vec3 dest)
 
     apply rotation matrix to vector
 
@@ -339,7 +403,7 @@ Functions documentation
       | *[in]*  **v**     vector
       | *[out]* **dest**  rotated vector
 
-.. c:function:: void  glm_vec_rotate_m3(mat3 m, vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_rotate_m3(mat3 m, vec3 v, vec3 dest)
 
     apply rotation matrix to vector
 
@@ -348,7 +412,7 @@ Functions documentation
       | *[in]*  **v**     vector
       | *[out]* **dest**  rotated vector
 
-.. c:function:: void  glm_vec_proj(vec3 a, vec3 b, vec3 dest)
+.. c:function:: void  glm_vec3_proj(vec3 a, vec3 b, vec3 dest)
 
     project a vector onto b vector
 
@@ -357,7 +421,7 @@ Functions documentation
       | *[in]*  **b**     vector2
       | *[out]* **dest**  projected vector
 
-.. c:function:: void  glm_vec_center(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_center(vec3 v1, vec3 v2, vec3 dest)
 
     find center point of two vector
 
@@ -366,18 +430,29 @@ Functions documentation
       | *[in]*  **v2**    vector2
       | *[out]* **dest**  center point
 
-.. c:function:: float  glm_vec_distance(vec3 v1, vec3 v2)
+.. c:function:: float  glm_vec3_distance2(vec3 v1, vec3 v2)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **v1**  vector1
+      | *[in]*  **v2**  vector2
+
+    Returns:
+      | squared distance (distance * distance)
+
+.. c:function:: float  glm_vec3_distance(vec3 v1, vec3 v2)
 
     distance between two vectors
 
     Parameters:
-      | *[in]*  **mat**   vector1
+      | *[in]*  **v1**  vector1
-      | *[in]*  **row1**  vector2
+      | *[in]*  **v2**  vector2
 
     Returns:
       | distance
 
-.. c:function:: void  glm_vec_maxv(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_maxv(vec3 v1, vec3 v2, vec3 dest)
 
     max values of vectors
 
@@ -386,7 +461,7 @@ Functions documentation
       | *[in]*  **v2**    vector2
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_minv(vec3 v1, vec3 v2, vec3 dest)
+.. c:function:: void  glm_vec3_minv(vec3 v1, vec3 v2, vec3 dest)
 
     min values of vectors
 
@@ -395,15 +470,15 @@ Functions documentation
       | *[in]*  **v2**    vector2
       | *[out]* **dest**  destination
 
-.. c:function:: void  glm_vec_ortho(vec3 v, vec3 dest)
+.. c:function:: void  glm_vec3_ortho(vec3 v, vec3 dest)
 
     possible orthogonal/perpendicular vector
 
     Parameters:
-      | *[in]*  **mat**   vector
+      | *[in]*  **v**     vector
       | *[out]* **dest**  orthogonal/perpendicular vector
 
-.. c:function:: void  glm_vec_clamp(vec3 v, float minVal, float maxVal)
+.. c:function:: void  glm_vec3_clamp(vec3 v, float minVal, float maxVal)
 
     constrain a value to lie between two further values
 
@@ -412,7 +487,7 @@ Functions documentation
       | *[in]*       **minVal**  minimum value
       | *[in]*       **maxVal**  maximum value
 
-.. c:function:: void  glm_vec_lerp(vec3 from, vec3 to, float t, vec3 dest)
+.. c:function:: void  glm_vec3_lerp(vec3 from, vec3 to, float t, vec3 dest)
 
     linear interpolation between two vector
 

docs/source/vec4.rst

@@ -24,6 +24,7 @@ Functions:
 1. :c:func:`glm_vec4`
 #. :c:func:`glm_vec4_copy3`
 #. :c:func:`glm_vec4_copy`
+#. :c:func:`glm_vec4_ucopy`
 #. :c:func:`glm_vec4_zero`
 #. :c:func:`glm_vec4_one`
 #. :c:func:`glm_vec4_dot`
@@ -42,10 +43,14 @@ Functions:
 #. :c:func:`glm_vec4_subadd`
 #. :c:func:`glm_vec4_muladd`
 #. :c:func:`glm_vec4_muladds`
+#. :c:func:`glm_vec4_maxadd`
+#. :c:func:`glm_vec4_minadd`
 #. :c:func:`glm_vec4_flipsign`
-#. :c:func:`glm_vec_flipsign_to`
+#. :c:func:`glm_vec4_flipsign_to`
 #. :c:func:`glm_vec4_inv`
 #. :c:func:`glm_vec4_inv_to`
+#. :c:func:`glm_vec4_negate`
+#. :c:func:`glm_vec4_negate_to`
 #. :c:func:`glm_vec4_normalize`
 #. :c:func:`glm_vec4_normalize_to`
 #. :c:func:`glm_vec4_distance`
@@ -53,11 +58,7 @@ Functions:
 #. :c:func:`glm_vec4_minv`
 #. :c:func:`glm_vec4_clamp`
 #. :c:func:`glm_vec4_lerp`
-#. :c:func:`glm_vec4_isnan`
+#. :c:func:`glm_vec4_cubic`
-#. :c:func:`glm_vec4_isinf`
-#. :c:func:`glm_vec4_isvalid`
-#. :c:func:`glm_vec4_sign`
-#. :c:func:`glm_vec4_sqrt`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -89,6 +90,16 @@ Functions documentation
       | *[in]*  **v**     source
       | *[in]*  **dest**  destination
 
+.. c:function:: void  glm_vec4_ucopy(vec4 v, vec4 dest)
+
+    copy all members of [a] to [dest]
+
+    | alignment is not required
+
+    Parameters:
+      | *[in]*  **v**     source
+      | *[in]*  **dest**  destination
+
 .. c:function:: void  glm_vec4_zero(vec4 v)
 
     makes all members zero
@@ -123,7 +134,8 @@ Functions documentation
 
 .. c:function:: float  glm_vec4_norm(vec4 vec)
 
-    norm (magnitude) of vec4
+    | euclidean norm (magnitude), also called L2 norm
+    | this will give magnitude of vector in euclidean space
 
     Parameters:
       | *[in]*  **vec**   vector
@@ -249,16 +261,40 @@ Functions documentation
       | *[in]*  **s**     scalar
       | *[out]* **dest**  dest += (a * b)
 
+.. c:function:: void  glm_vec4_maxadd(vec4 a, vec4 b, vec4 dest)
+
+    | add max of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
+.. c:function:: void  glm_vec4_minadd(vec4 a, vec4 b, vec4 dest)
+
+    | add min of two vector to result/dest
+    | it applies += operator so dest must be initialized
+
+    Parameters:
+      | *[in]*  **a**     vector 1
+      | *[in]*  **b**     vector 2
+      | *[out]* **dest**  dest += (a * b)
+
 .. c:function:: void  glm_vec4_flipsign(vec4 v)
 
-    flip sign of all vec4 members
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate`
 
     Parameters:
     | *[in, out]*  **v**    vector
 
 .. c:function:: void  glm_vec4_flipsign_to(vec4 v, vec4 dest)
 
-    flip sign of all vec4 members and store result in dest
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate_to`
 
     Parameters:
       | *[in]*  **v**       vector
@@ -266,19 +302,38 @@ Functions documentation
 
 .. c:function:: void  glm_vec4_inv(vec4 v)
 
-    make vector as inverse/opposite of itself
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate`
 
     Parameters:
       | *[in, out]*  **v**    vector
 
 .. c:function:: void  glm_vec4_inv_to(vec4 v, vec4 dest)
 
-    inverse/opposite vector
+    **DEPRACATED!**
+
+    use :c:func:`glm_vec4_negate_to`
 
     Parameters:
       | *[in]*  **v**     source
       | *[out]* **dest**  destination
 
+.. c:function:: void  glm_vec4_negate(vec4 v)
+
+    negate vector components
+
+    Parameters:
+    | *[in, out]*  **v**    vector
+
+.. c:function:: void  glm_vec4_negate_to(vec4 v, vec4 dest)
+
+    negate vector components and store result in dest
+
+    Parameters:
+      | *[in]*  **v**       vector
+      | *[out]* **dest**    negated vector
+
 .. c:function:: void  glm_vec4_normalize(vec4 v)
 
     normalize vec4 and store result in same vec
@@ -343,3 +398,11 @@ Functions documentation
       | *[in]*  **to**     to value
       | *[in]*  **t**      interpolant (amount) clamped between 0 and 1
       | *[out]* **dest**   destination
+
+.. c:function:: void  glm_vec4_cubic(float s, vec4 dest)
+
+    helper to fill vec4 as [S^3, S^2, S, 1]
+
+    Parameters:
+      | *[in]*  **s**      parameter
+      | *[out]* **dest**   destination

docs/source/version.rst

@@ -0,0 +1,15 @@
+.. default-domain:: C
+
+version
+================================================================================
+
+Header: cglm/version.h
+
+**cglm** uses semantic versioning (http://semver.org) which is MAJOR.MINOR.PATCH 
+
+| **CGLM_VERSION_MAJOR** is major number of the version.
+| **CGLM_VERSION_MINOR** is minor number of the version.
+| **CGLM_VERSION_PATCH** is patch number of the version.
+
+every release increases these numbers. You can check existing version by 
+including `cglm/version.h`

include/cglm/affine-mat.h

@@ -151,8 +151,8 @@ glm_inv_tr(mat4 mat) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_inv_tr_sse2(mat);
 #else
-  CGLM_ALIGN(16) mat3 r;
+  CGLM_ALIGN_MAT mat3 r;
-  CGLM_ALIGN(16) vec3 t;
+  CGLM_ALIGN(8)  vec3 t;
 
   /* rotate */
   glm_mat4_pick3t(mat, r);
@@ -160,8 +160,8 @@ glm_inv_tr(mat4 mat) {
 
   /* translate */
   glm_mat3_mulv(r, mat[3], t);
-  glm_vec_flipsign(t);
+  glm_vec3_negate(t);
-  glm_vec_copy(t, mat[3]);
+  glm_vec3_copy(t, mat[3]);
 #endif
 }
 

include/cglm/affine.h

@@ -40,52 +40,6 @@
 #include "mat4.h"
 #include "affine-mat.h"
 
-CGLM_INLINE
-void
-glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest);
-
-/*!
- * @brief translate existing transform matrix by v vector
- *        and store result in dest
- *
- * @param[in]  m    affine transfrom
- * @param[in]  v    translate vector [x, y, z]
- * @param[out] dest translated matrix
- */
-CGLM_INLINE
-void
-glm_translate_to(mat4 m, vec3 v, mat4 dest) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
-
-#if defined( __SSE__ ) || defined( __SSE2__ )
-  glmm_store(dest[3],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_load(t[0]),
-                                              _mm_set1_ps(v[0])),
-                                   _mm_mul_ps(glmm_load(t[1]),
-                                              _mm_set1_ps(v[1]))),
-                        _mm_add_ps(_mm_mul_ps(glmm_load(t[2]),
-                                              _mm_set1_ps(v[2])),
-                                   glmm_load(t[3]))))
-  ;
-
-  glmm_store(dest[0], glmm_load(m[0]));
-  glmm_store(dest[1], glmm_load(m[1]));
-  glmm_store(dest[2], glmm_load(m[2]));
-#else
-  vec4 v1, v2, v3;
-
-  glm_vec4_scale(t[0], v[0], v1);
-  glm_vec4_scale(t[1], v[1], v2);
-  glm_vec4_scale(t[2], v[2], v3);
-
-  glm_vec4_add(v1, t[3], t[3]);
-  glm_vec4_add(v2, t[3], t[3]);
-  glm_vec4_add(v3, t[3], t[3]);
-
-  glm__memcpy(float, dest, t, sizeof(mat4));
-#endif
-}
-
 /*!
  * @brief translate existing transform matrix by v vector
  *        and stores result in same matrix
@@ -119,6 +73,23 @@ glm_translate(mat4 m, vec3 v) {
 #endif
 }
 
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and store result in dest
+ *
+ * source matrix will remain same
+ *
+ * @param[in]  m    affine transfrom
+ * @param[in]  v    translate vector [x, y, z]
+ * @param[out] dest translated matrix
+ */
+CGLM_INLINE
+void
+glm_translate_to(mat4 m, vec3 v, mat4 dest) {
+  glm_mat4_copy(m, dest);
+  glm_translate(dest, v);
+}
+
 /*!
  * @brief translate existing transform matrix by x factor
  *
@@ -194,8 +165,8 @@ glm_translate_z(mat4 m, float z) {
 CGLM_INLINE
 void
 glm_translate_make(mat4 m, vec3 v) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
+  glm_mat4_identity(m);
-  glm_translate_to(t, v, m);
+  glm_vec3_copy(v, m[3]);
 }
 
 /*!
@@ -225,8 +196,10 @@ glm_scale_to(mat4 m, vec3 v, mat4 dest) {
 CGLM_INLINE
 void
 glm_scale_make(mat4 m, vec3 v) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
+  glm_mat4_identity(m);
-  glm_scale_to(t, v, m);
+  m[0][0] = v[0];
+  m[1][1] = v[1];
+  m[2][2] = v[2];
 }
 
 /*!
@@ -252,7 +225,7 @@ glm_scale(mat4 m, vec3 v) {
 CGLM_INLINE
 void
 glm_scale_uni(mat4 m, float s) {
-  vec3 v = { s, s, s };
+  CGLM_ALIGN(8) vec3 v = { s, s, s };
   glm_scale_to(m, v, m);
 }
 
@@ -267,7 +240,7 @@ glm_scale_uni(mat4 m, float s) {
 CGLM_INLINE
 void
 glm_rotate_x(mat4 m, float angle, mat4 dest) {
-  mat4  t = GLM_MAT4_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
   float c, s;
 
   c = cosf(angle);
@@ -292,7 +265,7 @@ glm_rotate_x(mat4 m, float angle, mat4 dest) {
 CGLM_INLINE
 void
 glm_rotate_y(mat4 m, float angle, mat4 dest) {
-  mat4  t = GLM_MAT4_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
   float c, s;
 
   c = cosf(angle);
@@ -317,7 +290,7 @@ glm_rotate_y(mat4 m, float angle, mat4 dest) {
 CGLM_INLINE
 void
 glm_rotate_z(mat4 m, float angle, mat4 dest) {
-  mat4  t = GLM_MAT4_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
   float c, s;
 
   c = cosf(angle);
@@ -343,18 +316,18 @@ glm_rotate_z(mat4 m, float angle, mat4 dest) {
 CGLM_INLINE
 void
 glm_rotate_make(mat4 m, float angle, vec3 axis) {
-  vec3  axisn, v, vs;
+  CGLM_ALIGN(8) vec3 axisn, v, vs;
   float c;
 
   c = cosf(angle);
 
-  glm_vec_normalize_to(axis, axisn);
+  glm_vec3_normalize_to(axis, axisn);
-  glm_vec_scale(axisn, 1.0f - c, v);
+  glm_vec3_scale(axisn, 1.0f - c, v);
-  glm_vec_scale(axisn, sinf(angle), vs);
+  glm_vec3_scale(axisn, sinf(angle), vs);
 
-  glm_vec_scale(axisn, v[0], m[0]);
+  glm_vec3_scale(axisn, v[0], m[0]);
-  glm_vec_scale(axisn, v[1], m[1]);
+  glm_vec3_scale(axisn, v[1], m[1]);
-  glm_vec_scale(axisn, v[2], m[2]);
+  glm_vec3_scale(axisn, v[2], m[2]);
 
   m[0][0] += c;       m[1][0] -= vs[2];   m[2][0] += vs[1];
   m[0][1] += vs[2];   m[1][1] += c;       m[2][1] -= vs[0];
@@ -374,7 +347,7 @@ glm_rotate_make(mat4 m, float angle, vec3 axis) {
 CGLM_INLINE
 void
 glm_rotate(mat4 m, float angle, vec3 axis) {
-  mat4 rot;
+  CGLM_ALIGN_MAT mat4 rot;
   glm_rotate_make(rot, angle, axis);
   glm_mul_rot(m, rot, m);
 }
@@ -391,9 +364,9 @@ glm_rotate(mat4 m, float angle, vec3 axis) {
 CGLM_INLINE
 void
 glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis) {
-  vec3 pivotInv;
+  CGLM_ALIGN(8) vec3 pivotInv;
 
-  glm_vec_inv_to(pivot, pivotInv);
+  glm_vec3_negate_to(pivot, pivotInv);
 
   glm_translate(m, pivot);
   glm_rotate(m, angle, axis);
@@ -416,12 +389,11 @@ 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) {
-  vec3 pivotInv;
+  CGLM_ALIGN(8) vec3 pivotInv;
 
-  glm_vec_inv_to(pivot, pivotInv);
+  glm_vec3_negate_to(pivot, pivotInv);
 
-  glm_mat4_identity(m);
+  glm_translate_make(m, pivot);
-  glm_vec_copy(pivot, m[3]);
   glm_rotate(m, angle, axis);
   glm_translate(m, pivotInv);
 }
@@ -435,9 +407,9 @@ glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis) {
 CGLM_INLINE
 void
 glm_decompose_scalev(mat4 m, vec3 s) {
-  s[0] = glm_vec_norm(m[0]);
+  s[0] = glm_vec3_norm(m[0]);
-  s[1] = glm_vec_norm(m[1]);
+  s[1] = glm_vec3_norm(m[1]);
-  s[2] = glm_vec_norm(m[2]);
+  s[2] = glm_vec3_norm(m[2]);
 }
 
 /*!
@@ -451,10 +423,9 @@ glm_decompose_scalev(mat4 m, vec3 s) {
 CGLM_INLINE
 bool
 glm_uniscaled(mat4 m) {
-  vec3 s;
+  CGLM_ALIGN(8) vec3 s;
   glm_decompose_scalev(m, s);
-
+  return glm_vec3_eq_all(s);
-  return glm_vec_eq_all(s);
 }
 
 /*!
@@ -468,31 +439,31 @@ glm_uniscaled(mat4 m) {
 CGLM_INLINE
 void
 glm_decompose_rs(mat4 m, mat4 r, vec3 s) {
-  vec4 t = {0.0f, 0.0f, 0.0f, 1.0f};
+  CGLM_ALIGN(16) vec4 t = {0.0f, 0.0f, 0.0f, 1.0f};
-  vec3 v;
+  CGLM_ALIGN(8)  vec3 v;
 
   glm_vec4_copy(m[0], r[0]);
   glm_vec4_copy(m[1], r[1]);
   glm_vec4_copy(m[2], r[2]);
   glm_vec4_copy(t,    r[3]);
 
-  s[0] = glm_vec_norm(m[0]);
+  s[0] = glm_vec3_norm(m[0]);
-  s[1] = glm_vec_norm(m[1]);
+  s[1] = glm_vec3_norm(m[1]);
-  s[2] = glm_vec_norm(m[2]);
+  s[2] = glm_vec3_norm(m[2]);
 
   glm_vec4_scale(r[0], 1.0f/s[0], r[0]);
   glm_vec4_scale(r[1], 1.0f/s[1], r[1]);
   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_vec_cross(m[0], m[1], v);
+  glm_vec3_cross(m[0], m[1], v);
-  if (glm_vec_dot(v, m[2]) < 0.0f) {
+  if (glm_vec3_dot(v, m[2]) < 0.0f) {
-    glm_vec4_flipsign(r[0]);
+    glm_vec4_negate(r[0]);
-    glm_vec4_flipsign(r[1]);
+    glm_vec4_negate(r[1]);
-    glm_vec4_flipsign(r[2]);
+    glm_vec4_negate(r[2]);
-    glm_vec_flipsign(s);
+    glm_vec3_negate(s);
   }
 }
 

include/cglm/affine2d.h

@@ -0,0 +1,268 @@
+/*
+ * 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_translate2d(mat3 m, vec2 v)
+   CGLM_INLINE void glm_translate2d_to(mat3 m, vec2 v, mat3 dest)
+   CGLM_INLINE void glm_translate2d_x(mat3 m, float x)
+   CGLM_INLINE void glm_translate2d_y(mat3 m, float y)
+   CGLM_INLINE void glm_translate2d_make(mat3 m, vec2 v)
+   CGLM_INLINE void glm_scale2d_to(mat3 m, vec2 v, mat3 dest)
+   CGLM_INLINE void glm_scale2d_make(mat3 m, vec2 v)
+   CGLM_INLINE void glm_scale2d(mat3 m, vec2 v)
+   CGLM_INLINE void glm_scale2d_uni(mat3 m, float s)
+   CGLM_INLINE void glm_rotate2d_make(mat3 m, float angle)
+   CGLM_INLINE void glm_rotate2d(mat3 m, float angle)
+   CGLM_INLINE void glm_rotate2d_to(mat3 m, float angle, mat3 dest)
+ */
+
+#ifndef cglm_affine2d_h
+#define cglm_affine2d_h
+
+#include "common.h"
+#include "util.h"
+#include "vec2.h"
+#include "mat3.h"
+
+/*!
+ * @brief translate existing 2d transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       v  translate vector [x, y]
+ */
+CGLM_INLINE
+void
+glm_translate2d(mat3 m, vec2 v) {
+  m[2][0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0];
+  m[2][1] = m[0][1] * v[0] + m[1][1] * v[1] + m[2][1];
+  m[2][2] = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2];
+}
+
+/*!
+ * @brief translate existing 2d 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]
+ * @param[out] dest translated matrix
+ */
+CGLM_INLINE
+void
+glm_translate2d_to(mat3 m, vec2 v, mat3 dest) {
+  glm_mat3_copy(m, dest);
+  glm_translate2d(dest, v);
+}
+
+/*!
+ * @brief translate existing 2d transform matrix by x factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       x  x factor
+ */
+CGLM_INLINE
+void
+glm_translate2d_x(mat3 m, float x) {
+  m[2][0] = m[0][0] * x + m[2][0];
+  m[2][1] = m[0][1] * x + m[2][1];
+  m[2][2] = m[0][2] * x + m[2][2];
+}
+
+/*!
+ * @brief translate existing 2d transform matrix by y factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       y  y factor
+ */
+CGLM_INLINE
+void
+glm_translate2d_y(mat3 m, float y) {
+  m[2][0] = m[1][0] * y + m[2][0];
+  m[2][1] = m[1][1] * y + m[2][1];
+  m[2][2] = m[1][2] * y + m[2][2];
+}
+
+/*!
+ * @brief creates NEW translate 2d transform matrix by v vector
+ *
+ * @param[out]  m  affine transfrom
+ * @param[in]   v  translate vector [x, y]
+ */
+CGLM_INLINE
+void
+glm_translate2d_make(mat3 m, vec2 v) {
+  glm_mat3_identity(m);
+  m[2][0] = v[0];
+  m[2][1] = v[1];
+}
+
+/*!
+ * @brief scale existing 2d transform matrix by v vector
+ *        and store result in dest
+ *
+ * @param[in]  m    affine transfrom
+ * @param[in]  v    scale vector [x, y]
+ * @param[out] dest scaled matrix
+ */
+CGLM_INLINE
+void
+glm_scale2d_to(mat3 m, vec2 v, mat3 dest) {
+  dest[0][0] = m[0][0] * v[0];
+  dest[0][1] = m[0][1] * v[0];
+  dest[0][2] = m[0][2] * v[0];
+  
+  dest[1][0] = m[1][0] * v[1];
+  dest[1][1] = m[1][1] * v[1];
+  dest[1][2] = m[1][2] * v[1];
+  
+  dest[2][0] = m[2][0];
+  dest[2][1] = m[2][1];
+  dest[2][2] = m[2][2];
+}
+
+/*!
+ * @brief creates NEW 2d scale matrix by v vector
+ *
+ * @param[out]  m  affine transfrom
+ * @param[in]   v  scale vector [x, y]
+ */
+CGLM_INLINE
+void
+glm_scale2d_make(mat3 m, vec2 v) {
+  glm_mat3_identity(m);
+  m[0][0] = v[0];
+  m[1][1] = v[1];
+}
+
+/*!
+ * @brief scales existing 2d transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       v  scale vector [x, y]
+ */
+CGLM_INLINE
+void
+glm_scale2d(mat3 m, vec2 v) {
+  m[0][0] = m[0][0] * v[0];
+  m[0][1] = m[0][1] * v[0];
+  m[0][2] = m[0][2] * v[0];
+
+  m[1][0] = m[1][0] * v[1];
+  m[1][1] = m[1][1] * v[1];
+  m[1][2] = m[1][2] * v[1];
+}
+
+/*!
+ * @brief applies uniform scale to existing 2d transform matrix v = [s, s]
+ *        and stores result in same matrix
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       s  scale factor
+ */
+CGLM_INLINE
+void
+glm_scale2d_uni(mat3 m, float s) {
+  m[0][0] = m[0][0] * s;
+  m[0][1] = m[0][1] * s;
+  m[0][2] = m[0][2] * s;
+
+  m[1][0] = m[1][0] * s;
+  m[1][1] = m[1][1] * s;
+  m[1][2] = m[1][2] * s;
+}
+
+/*!
+ * @brief creates NEW rotation matrix by angle around Z axis
+ *
+ * @param[out] m     affine transfrom
+ * @param[in]  angle angle (radians)
+ */
+CGLM_INLINE
+void
+glm_rotate2d_make(mat3 m, float angle) {
+  float c, s;
+
+  s = sinf(angle);
+  c = cosf(angle);
+  
+  m[0][0] = c;
+  m[0][1] = s;
+  m[0][2] = 0;
+
+  m[1][0] = -s;
+  m[1][1] = c;
+  m[1][2] = 0;
+  
+  m[2][0] = 0.0f;
+  m[2][1] = 0.0f;
+  m[2][2] = 1.0f;
+}
+
+/*!
+ * @brief rotate existing 2d transform matrix around Z axis by angle
+ *         and store result in same matrix
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ */
+CGLM_INLINE
+void
+glm_rotate2d(mat3 m, float angle) {
+  float m00 = m[0][0],  m10 = m[1][0],
+        m01 = m[0][1],  m11 = m[1][1],
+        m02 = m[0][2],  m12 = m[1][2];
+  float c, s;
+
+  s = sinf(angle);
+  c = cosf(angle);
+  
+  m[0][0] = m00 * c + m10 * s;
+  m[0][1] = m01 * c + m11 * s;
+  m[0][2] = m02 * c + m12 * s;
+
+  m[1][0] = m00 * -s + m10 * c;
+  m[1][1] = m01 * -s + m11 * c;
+  m[1][2] = m02 * -s + m12 * c;
+}
+
+/*!
+ * @brief rotate existing 2d 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   destination
+ */
+CGLM_INLINE
+void
+glm_rotate2d_to(mat3 m, float angle, mat3 dest) {
+  float m00 = m[0][0],  m10 = m[1][0],
+        m01 = m[0][1],  m11 = m[1][1],
+        m02 = m[0][2],  m12 = m[1][2];
+  float c, s;
+
+  s = sinf(angle);
+  c = cosf(angle);
+  
+  dest[0][0] = m00 * c + m10 * s;
+  dest[0][1] = m01 * c + m11 * s;
+  dest[0][2] = m02 * c + m12 * s;
+
+  dest[1][0] = m00 * -s + m10 * c;
+  dest[1][1] = m01 * -s + m11 * c;
+  dest[1][2] = m02 * -s + m12 * c;
+  
+  dest[2][0] = m[2][0];
+  dest[2][1] = m[2][1];
+  dest[2][2] = m[2][2];
+}
+
+#endif /* cglm_affine2d_h */

include/cglm/applesimd.h

@@ -0,0 +1,95 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_applesimd_h
+#define cglm_applesimd_h
+#if defined(__APPLE__)                                                        \
+    && defined(SIMD_COMPILER_HAS_REQUIRED_FEATURES)                           \
+    && defined(SIMD_BASE)                                                     \
+    && defined(SIMD_TYPES)                                                    \
+    && defined(SIMD_VECTOR_TYPES)
+
+#include "common.h"
+
+/*!
+* @brief converts mat4 to Apple's simd type simd_float4x4
+* @return simd_float4x4
+*/
+CGLM_INLINE
+simd_float4x4
+glm_mat4_applesimd(mat4 m) {
+  simd_float4x4 t;
+  
+  t.columns[0][0] = m[0][0];
+  t.columns[0][1] = m[0][1];
+  t.columns[0][2] = m[0][2];
+  t.columns[0][3] = m[0][3];
+
+  t.columns[1][0] = m[1][0];
+  t.columns[1][1] = m[1][1];
+  t.columns[1][2] = m[1][2];
+  t.columns[1][3] = m[1][3];
+
+  t.columns[2][0] = m[2][0];
+  t.columns[2][1] = m[2][1];
+  t.columns[2][2] = m[2][2];
+  t.columns[2][3] = m[2][3];
+
+  t.columns[3][0] = m[3][0];
+  t.columns[3][1] = m[3][1];
+  t.columns[3][2] = m[3][2];
+  t.columns[3][3] = m[3][3];
+
+  return t;
+}
+
+/*!
+* @brief converts mat3 to Apple's simd type simd_float3x3
+* @return simd_float3x3
+*/
+CGLM_INLINE
+simd_float3x3
+glm_mat3_applesimd(mat3 m) {
+  simd_float3x3 t;
+  
+  t.columns[0][0] = m[0][0];
+  t.columns[0][1] = m[0][1];
+  t.columns[0][2] = m[0][2];
+
+  t.columns[1][0] = m[1][0];
+  t.columns[1][1] = m[1][1];
+  t.columns[1][2] = m[1][2];
+
+  t.columns[2][0] = m[2][0];
+  t.columns[2][1] = m[2][1];
+  t.columns[2][2] = m[2][2];
+
+  return t;
+}
+
+/*!
+* @brief converts vec4 to Apple's simd type simd_float4
+* @return simd_float4
+*/
+CGLM_INLINE
+simd_float4
+glm_vec4_applesimd(vec4 v) {
+  return (simd_float4){v[0], v[1], v[2], v[3]};
+}
+
+/*!
+* @brief converts vec3 to Apple's simd type simd_float3
+* @return v
+*/
+CGLM_INLINE
+simd_float3
+glm_vec3_applesimd(vec3 v) {
+  return (simd_float3){v[0], v[1], v[2]};
+}
+
+#endif
+#endif /* cglm_applesimd_h */

include/cglm/bezier.h

@@ -0,0 +1,154 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_bezier_h
+#define cglm_bezier_h
+
+#include "common.h"
+
+#define GLM_BEZIER_MAT_INIT  {{-1.0f,  3.0f, -3.0f,  1.0f},                   \
+                              { 3.0f, -6.0f,  3.0f,  0.0f},                   \
+                              {-3.0f,  3.0f,  0.0f,  0.0f},                   \
+                              { 1.0f,  0.0f,  0.0f,  0.0f}}
+#define GLM_HERMITE_MAT_INIT {{ 2.0f, -3.0f,  0.0f,  1.0f},                   \
+                              {-2.0f,  3.0f,  0.0f,  0.0f},                   \
+                              { 1.0f, -2.0f,  1.0f,  0.0f},                   \
+                              { 1.0f, -1.0f,  0.0f,  0.0f}}
+/* for C only */
+#define GLM_BEZIER_MAT  ((mat4)GLM_BEZIER_MAT_INIT)
+#define GLM_HERMITE_MAT ((mat4)GLM_HERMITE_MAT_INIT)
+
+#define CGLM_DECASTEL_EPS   1e-9f
+#define CGLM_DECASTEL_MAX   1000.0f
+#define CGLM_DECASTEL_SMALL 1e-20f
+
+/*!
+ * @brief cubic bezier interpolation
+ *
+ * Formula:
+ *  B(s) = P0*(1-s)^3 + 3*C0*s*(1-s)^2 + 3*C1*s^2*(1-s) + P1*s^3
+ *
+ * similar result using matrix:
+ *  B(s) = glm_smc(t, GLM_BEZIER_MAT, (vec4){p0, c0, c1, p1})
+ *
+ * glm_eq(glm_smc(...), glm_bezier(...)) should return TRUE
+ *
+ * @param[in]  s    parameter between 0 and 1
+ * @param[in]  p0   begin point
+ * @param[in]  c0   control point 1
+ * @param[in]  c1   control point 2
+ * @param[in]  p1   end point
+ *
+ * @return B(s)
+ */
+CGLM_INLINE
+float
+glm_bezier(float s, float p0, float c0, float c1, float p1) {
+  float x, xx, ss, xs3, a;
+
+  x   = 1.0f - s;
+  xx  = x * x;
+  ss  = s * s;
+  xs3 = (s - ss) * 3.0f;
+  a   = p0 * xx + c0 * xs3;
+
+  return a + s * (c1 * xs3 + p1 * ss - a);
+}
+
+/*!
+ * @brief cubic hermite interpolation
+ *
+ * Formula:
+ *  H(s) = P0*(2*s^3 - 3*s^2 + 1) + T0*(s^3 - 2*s^2 + s)
+ *            + P1*(-2*s^3 + 3*s^2) + T1*(s^3 - s^2)
+ *
+ * similar result using matrix:
+ *  H(s) = glm_smc(t, GLM_HERMITE_MAT, (vec4){p0, p1, c0, c1})
+ *
+ * glm_eq(glm_smc(...), glm_hermite(...)) should return TRUE
+ *
+ * @param[in]  s    parameter between 0 and 1
+ * @param[in]  p0   begin point
+ * @param[in]  t0   tangent 1
+ * @param[in]  t1   tangent 2
+ * @param[in]  p1   end point
+ *
+ * @return H(s)
+ */
+CGLM_INLINE
+float
+glm_hermite(float s, float p0, float t0, float t1, float p1) {
+  float ss, d, a, b, c, e, f;
+
+  ss = s  * s;
+  a  = ss + ss;
+  c  = a  + ss;
+  b  = a  * s;
+  d  = s  * ss;
+  f  = d  - ss;
+  e  = b  - c;
+
+  return p0 * (e + 1.0f) + t0 * (f - ss + s) + t1 * f - p1 * e;
+}
+
+/*!
+ * @brief iterative way to solve cubic equation
+ *
+ * @param[in]  prm  parameter between 0 and 1
+ * @param[in]  p0   begin point
+ * @param[in]  c0   control point 1
+ * @param[in]  c1   control point 2
+ * @param[in]  p1   end point
+ *
+ * @return parameter to use in cubic equation
+ */
+CGLM_INLINE
+float
+glm_decasteljau(float prm, float p0, float c0, float c1, float p1) {
+  float u, v, a, b, c, d, e, f;
+  int   i;
+
+  if (prm - p0 < CGLM_DECASTEL_SMALL)
+    return 0.0f;
+
+  if (p1 - prm < CGLM_DECASTEL_SMALL)
+    return 1.0f;
+
+  u  = 0.0f;
+  v  = 1.0f;
+
+  for (i = 0; i < CGLM_DECASTEL_MAX; i++) {
+    /* de Casteljau Subdivision */
+    a  = (p0 + c0) * 0.5f;
+    b  = (c0 + c1) * 0.5f;
+    c  = (c1 + p1) * 0.5f;
+    d  = (a  + b)  * 0.5f;
+    e  = (b  + c)  * 0.5f;
+    f  = (d  + e)  * 0.5f; /* this one is on the curve! */
+
+    /* The curve point is close enough to our wanted t */
+    if (fabsf(f - prm) < CGLM_DECASTEL_EPS)
+      return glm_clamp_zo((u  + v) * 0.5f);
+
+    /* dichotomy */
+    if (f < prm) {
+      p0 = f;
+      c0 = e;
+      c1 = c;
+      u  = (u  + v) * 0.5f;
+    } else {
+      c0 = a;
+      c1 = d;
+      p1 = f;
+      v  = (u  + v) * 0.5f;
+    }
+  }
+
+  return glm_clamp_zo((u  + v) * 0.5f);
+}
+
+#endif /* cglm_bezier_h */

include/cglm/box.h

@@ -23,35 +23,31 @@
 CGLM_INLINE
 void
 glm_aabb_transform(vec3 box[2], mat4 m, vec3 dest[2]) {
-  vec3 v[2], xa, xb, ya, yb, za, zb, tmp;
+  vec3 v[2], xa, xb, ya, yb, za, zb;
 
-  glm_vec_scale(m[0], box[0][0], xa);
+  glm_vec3_scale(m[0], box[0][0], xa);
-  glm_vec_scale(m[0], box[1][0], xb);
+  glm_vec3_scale(m[0], box[1][0], xb);
 
-  glm_vec_scale(m[1], box[0][1], ya);
+  glm_vec3_scale(m[1], box[0][1], ya);
-  glm_vec_scale(m[1], box[1][1], yb);
+  glm_vec3_scale(m[1], box[1][1], yb);
 
-  glm_vec_scale(m[2], box[0][2], za);
+  glm_vec3_scale(m[2], box[0][2], za);
-  glm_vec_scale(m[2], box[1][2], zb);
+  glm_vec3_scale(m[2], box[1][2], zb);
 
-  /* min(xa, xb) + min(ya, yb) + min(za, zb) + translation */
+  /* translation + min(xa, xb) + min(ya, yb) + min(za, zb) */
-  glm_vec_minv(xa, xb, v[0]);
+  glm_vec3(m[3], v[0]);
-  glm_vec_minv(ya, yb, tmp);
+  glm_vec3_minadd(xa, xb, v[0]);
-  glm_vec_add(v[0], tmp, v[0]);
+  glm_vec3_minadd(ya, yb, v[0]);
-  glm_vec_minv(za, zb, tmp);
+  glm_vec3_minadd(za, zb, v[0]);
-  glm_vec_add(v[0], tmp, v[0]);
-  glm_vec_add(v[0], m[3], v[0]);
 
-  /* max(xa, xb) + max(ya, yb) + max(za, zb) + translation */
+  /* translation + max(xa, xb) + max(ya, yb) + max(za, zb) */
-  glm_vec_maxv(xa, xb, v[1]);
+  glm_vec3(m[3], v[1]);
-  glm_vec_maxv(ya, yb, tmp);
+  glm_vec3_maxadd(xa, xb, v[1]);
-  glm_vec_add(v[1], tmp, v[1]);
+  glm_vec3_maxadd(ya, yb, v[1]);
-  glm_vec_maxv(za, zb, tmp);
+  glm_vec3_maxadd(za, zb, v[1]);
-  glm_vec_add(v[1], tmp, v[1]);
-  glm_vec_add(v[1], m[3], v[1]);
 
-  glm_vec_copy(v[0], dest[0]);
+  glm_vec3_copy(v[0], dest[0]);
-  glm_vec_copy(v[1], dest[1]);
+  glm_vec3_copy(v[1], dest[1]);
 }
 
 /*!
@@ -162,8 +158,8 @@ glm_aabb_frustum(vec3 box[2], vec4 planes[6]) {
 CGLM_INLINE
 void
 glm_aabb_invalidate(vec3 box[2]) {
-  glm_vec_broadcast(FLT_MAX,  box[0]);
+  glm_vec3_broadcast(FLT_MAX,  box[0]);
-  glm_vec_broadcast(-FLT_MAX, box[1]);
+  glm_vec3_broadcast(-FLT_MAX, box[1]);
 }
 
 /*!
@@ -174,8 +170,8 @@ glm_aabb_invalidate(vec3 box[2]) {
 CGLM_INLINE
 bool
 glm_aabb_isvalid(vec3 box[2]) {
-  return glm_vec_max(box[0]) != FLT_MAX
+  return glm_vec3_max(box[0]) != FLT_MAX
-         && glm_vec_min(box[1]) != -FLT_MAX;
+         && glm_vec3_min(box[1]) != -FLT_MAX;
 }
 
 /*!
@@ -186,7 +182,7 @@ glm_aabb_isvalid(vec3 box[2]) {
 CGLM_INLINE
 float
 glm_aabb_size(vec3 box[2]) {
-  return glm_vec_distance(box[0], box[1]);
+  return glm_vec3_distance(box[0], box[1]);
 }
 
 /*!
@@ -200,4 +196,86 @@ glm_aabb_radius(vec3 box[2]) {
   return glm_aabb_size(box) * 0.5f;
 }
 
+/*!
+ * @brief computes center point of AABB
+ *
+ * @param[in]   box  bounding box
+ * @param[out]  dest center of bounding box
+ */
+CGLM_INLINE
+void
+glm_aabb_center(vec3 box[2], vec3 dest) {
+  glm_vec3_center(box[0], box[1], dest);
+}
+
+/*!
+ * @brief check if two AABB intersects
+ *
+ * @param[in]   box    bounding box
+ * @param[in]   other  other bounding box
+ */
+CGLM_INLINE
+bool
+glm_aabb_aabb(vec3 box[2], vec3 other[2]) {
+  return (box[0][0] <= other[1][0] && box[1][0] >= other[0][0])
+      && (box[0][1] <= other[1][1] && box[1][1] >= other[0][1])
+      && (box[0][2] <= other[1][2] && box[1][2] >= other[0][2]);
+}
+
+/*!
+ * @brief check if AABB intersects with sphere
+ *
+ * https://github.com/erich666/GraphicsGems/blob/master/gems/BoxSphere.c
+ * Solid Box - Solid Sphere test.
+ *
+ * Sphere Representation in cglm: [center.x, center.y, center.z, radii]
+ *
+ * @param[in]   box    solid bounding box
+ * @param[in]   s      solid sphere
+ */
+CGLM_INLINE
+bool
+glm_aabb_sphere(vec3 box[2], vec4 s) {
+  float dmin;
+  int   a, b, c;
+
+  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 - 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]);
+}
+
+/*!
+ * @brief check if point is inside of AABB
+ *
+ * @param[in]   box    bounding box
+ * @param[in]   point  point
+ */
+CGLM_INLINE
+bool
+glm_aabb_point(vec3 box[2], vec3 point) {
+  return (point[0] >= box[0][0] && point[0] <= box[1][0])
+      && (point[1] >= box[0][1] && point[1] <= box[1][1])
+      && (point[2] >= box[0][2] && point[2] <= box[1][2]);
+}
+
+/*!
+ * @brief check if AABB contains other AABB
+ *
+ * @param[in]   box    bounding box
+ * @param[in]   other  other bounding box
+ */
+CGLM_INLINE
+bool
+glm_aabb_contains(vec3 box[2], vec3 other[2]) {
+  return (box[0][0] <= other[0][0] && box[1][0] >= other[1][0])
+      && (box[0][1] <= other[0][1] && box[1][1] >= other[1][1])
+      && (box[0][2] <= other[0][2] && box[1][2] >= other[1][2]);
+}
+
 #endif /* cglm_box_h */

include/cglm/call.h

@@ -12,10 +12,12 @@ extern "C" {
 #endif
 
 #include "cglm.h"
+#include "call/vec2.h"
 #include "call/vec3.h"
 #include "call/vec4.h"
-#include "call/mat4.h"
+#include "call/mat2.h"
 #include "call/mat3.h"
+#include "call/mat4.h"
 #include "call/affine.h"
 #include "call/cam.h"
 #include "call/quat.h"
@@ -25,6 +27,12 @@ extern "C" {
 #include "call/box.h"
 #include "call/io.h"
 #include "call/project.h"
+#include "call/sphere.h"
+#include "call/ease.h"
+#include "call/curve.h"
+#include "call/bezier.h"
+#include "call/ray.h"
+#include "call/affine2d.h"
 
 #ifdef __cplusplus
 }

include/cglm/call/affine.h

@@ -97,6 +97,20 @@ CGLM_EXPORT
 void
 glmc_decompose(mat4 m, vec4 t, mat4 r, vec3 s);
 
+/* affine-mat */
+
+CGLM_EXPORT
+void
+glmc_mul(mat4 m1, mat4 m2, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_mul_rot(mat4 m1, mat4 m2, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_inv_tr(mat4 mat);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/affine2d.h

@@ -0,0 +1,67 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_affine2d_h
+#define cglmc_affine2d_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_translate2d_make(mat3 m, vec2 v);
+
+CGLM_EXPORT
+void
+glmc_translate2d_to(mat3 m, vec2 v, mat3 dest);
+
+CGLM_EXPORT
+void
+glmc_translate2d(mat3 m, vec2 v);
+
+CGLM_EXPORT
+void
+glmc_translate2d_x(mat3 m, float to);
+
+CGLM_EXPORT
+void
+glmc_translate2d_y(mat3 m, float to);
+
+CGLM_EXPORT
+void
+glmc_scale2d_to(mat3 m, vec2 v, mat3 dest);
+
+CGLM_EXPORT
+void
+glmc_scale2d_make(mat3 m, vec2 v);
+
+CGLM_EXPORT
+void
+glmc_scale2d(mat3 m, vec2 v);
+
+CGLM_EXPORT
+void
+glmc_scale2d_uni(mat3 m, float s);
+
+CGLM_EXPORT
+void
+glmc_rotate2d_make(mat3 m, float angle);
+
+CGLM_EXPORT
+void
+glmc_rotate2d(mat3 m, float angle);
+
+CGLM_EXPORT
+void
+glmc_rotate2d_to(mat3 m, float angle, mat3 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_affine2d_h */

include/cglm/call/bezier.h

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

include/cglm/call/box.h

@@ -32,6 +32,46 @@ glmc_aabb_crop_until(vec3 box[2],
                      vec3 clampBox[2],
                      vec3 dest[2]);
 
+CGLM_EXPORT
+bool
+glmc_aabb_frustum(vec3 box[2], vec4 planes[6]);
+
+CGLM_EXPORT
+void
+glmc_aabb_invalidate(vec3 box[2]);
+
+CGLM_EXPORT
+bool
+glmc_aabb_isvalid(vec3 box[2]);
+
+CGLM_EXPORT
+float
+glmc_aabb_size(vec3 box[2]);
+
+CGLM_EXPORT
+float
+glmc_aabb_radius(vec3 box[2]);
+
+CGLM_EXPORT
+void
+glmc_aabb_center(vec3 box[2], vec3 dest);
+
+CGLM_EXPORT
+bool
+glmc_aabb_aabb(vec3 box[2], vec3 other[2]);
+
+CGLM_EXPORT
+bool
+glmc_aabb_point(vec3 box[2], vec3 point);
+
+CGLM_EXPORT
+bool
+glmc_aabb_contains(vec3 box[2], vec3 other[2]);
+
+CGLM_EXPORT
+bool
+glmc_aabb_sphere(vec3 box[2], vec4 s);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/cam.h

@@ -33,6 +33,26 @@ glmc_ortho(float left,
            float farVal,
            mat4 dest);
 
+CGLM_EXPORT
+void
+glmc_ortho_aabb(vec3 box[2], mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_p(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_aabb_pz(vec3 box[2], float padding, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_ortho_default_s(float aspect, float size, mat4 dest);
+
 CGLM_EXPORT
 void
 glmc_perspective(float fovy,
@@ -41,6 +61,18 @@ glmc_perspective(float fovy,
                  float farVal,
                  mat4 dest);
 
+CGLM_EXPORT
+void
+glmc_persp_move_far(mat4 proj, float deltaFar);
+
+CGLM_EXPORT
+void
+glmc_perspective_default(float aspect, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_perspective_resize(float aspect, mat4 proj);
+
 CGLM_EXPORT
 void
 glmc_lookat(vec3 eye, vec3 center, vec3 up, mat4 dest);
@@ -53,6 +85,58 @@ CGLM_EXPORT
 void
 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 top,
+                  float * __restrict bottom,
+                  float * __restrict left,
+                  float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decompv(mat4 proj, float dest[6]);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_x(mat4 proj,
+                    float * __restrict left,
+                    float * __restrict right);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_y(mat4 proj,
+                    float * __restrict top,
+                    float * __restrict bottom);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_z(mat4 proj,
+                    float * __restrict nearVal,
+                    float * __restrict farVal);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_far(mat4 proj, float * __restrict farVal);
+
+CGLM_EXPORT
+void
+glmc_persp_decomp_near(mat4 proj, float * __restrict nearVal);
+
+CGLM_EXPORT
+float
+glmc_persp_fovy(mat4 proj);
+
+CGLM_EXPORT
+float
+glmc_persp_aspect(mat4 proj);
+
+CGLM_EXPORT
+void
+glmc_persp_sizes(mat4 proj, float fovy, vec4 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/curve.h

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

include/cglm/call/ease.h

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

include/cglm/call/euler.h

@@ -47,7 +47,7 @@ glmc_euler_yxz(vec3 angles, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_euler_by_order(vec3 angles, glm_euler_sq axis, mat4 dest);
+glmc_euler_by_order(vec3 angles, glm_euler_seq axis, mat4 dest);
 
 #ifdef __cplusplus
 }

include/cglm/call/io.h

@@ -7,6 +7,7 @@
 
 #ifndef cglmc_io_h
 #define cglmc_io_h
+
 #ifdef __cplusplus
 extern "C" {
 #endif

include/cglm/call/mat2.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_mat2_h
+#define cglmc_mat2_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat2_copy(mat2 mat, mat2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2_identity(mat2 mat);
+
+CGLM_EXPORT
+void
+glmc_mat2_identity_array(mat2 * __restrict mat, size_t count);
+
+CGLM_EXPORT
+void
+glmc_mat2_zero(mat2 mat);
+
+CGLM_EXPORT
+void
+glmc_mat2_mul(mat2 m1, mat2 m2, mat2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2_transpose_to(mat2 m, mat2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2_transpose(mat2 m);
+
+CGLM_EXPORT
+void
+glmc_mat2_mulv(mat2 m, vec2 v, vec2 dest);
+
+CGLM_EXPORT
+float
+glmc_mat2_trace(mat2 m);
+
+CGLM_EXPORT
+void
+glmc_mat2_scale(mat2 m, float s);
+
+CGLM_EXPORT
+float
+glmc_mat2_det(mat2 mat);
+
+CGLM_EXPORT
+void
+glmc_mat2_inv(mat2 mat, mat2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2_swap_col(mat2 mat, int col1, int col2);
+
+CGLM_EXPORT
+void
+glmc_mat2_swap_row(mat2 mat, int row1, int row2);
+
+CGLM_EXPORT
+float
+glmc_mat2_rmc(vec2 r, mat2 m, vec2 c);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat2_h */

include/cglm/call/mat3.h

@@ -24,6 +24,14 @@ CGLM_EXPORT
 void
 glmc_mat3_identity(mat3 mat);
 
+CGLM_EXPORT
+void
+glmc_mat3_zero(mat3 mat);
+
+CGLM_EXPORT
+void
+glmc_mat3_identity_array(mat3 * __restrict mat, size_t count);
+
 CGLM_EXPORT
 void
 glmc_mat3_mul(mat3 m1, mat3 m2, mat3 dest);
@@ -40,6 +48,14 @@ CGLM_EXPORT
 void
 glmc_mat3_mulv(mat3 m, vec3 v, vec3 dest);
 
+CGLM_EXPORT
+float
+glmc_mat3_trace(mat3 m);
+
+CGLM_EXPORT
+void
+glmc_mat3_quat(mat3 m, versor dest);
+
 CGLM_EXPORT
 void
 glmc_mat3_scale(mat3 m, float s);
@@ -60,6 +76,10 @@ CGLM_EXPORT
 void
 glmc_mat3_swap_row(mat3 mat, int row1, int row2);
 
+CGLM_EXPORT
+float
+glmc_mat3_rmc(vec3 r, mat3 m, vec3 c);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/mat4.h

@@ -29,6 +29,14 @@ CGLM_EXPORT
 void
 glmc_mat4_identity(mat4 mat);
 
+CGLM_EXPORT
+void
+glmc_mat4_identity_array(mat4 * __restrict mat, size_t count);
+
+CGLM_EXPORT
+void
+glmc_mat4_zero(mat4 mat);
+
 CGLM_EXPORT
 void
 glmc_mat4_pick3(mat4 mat, mat3 dest);
@@ -53,6 +61,18 @@ CGLM_EXPORT
 void
 glmc_mat4_mulv(mat4 m, vec4 v, vec4 dest);
 
+CGLM_EXPORT
+void
+glmc_mat4_mulv3(mat4 m, vec3 v, float last, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_mat4_trace(mat4 m);
+
+CGLM_EXPORT
+float
+glmc_mat4_trace3(mat4 m);
+
 CGLM_EXPORT
 void
 glmc_mat4_quat(mat4 m, versor dest);
@@ -85,6 +105,10 @@ CGLM_EXPORT
 void
 glmc_mat4_inv_precise(mat4 mat, mat4 dest);
 
+CGLM_EXPORT
+void
+glmc_mat4_inv_fast(mat4 mat, mat4 dest);
+
 CGLM_EXPORT
 void
 glmc_mat4_swap_col(mat4 mat, int col1, int col2);
@@ -93,6 +117,10 @@ CGLM_EXPORT
 void
 glmc_mat4_swap_row(mat4 mat, int row1, int row2);
 
+CGLM_EXPORT
+float
+glmc_mat4_rmc(vec4 r, mat4 m, vec4 c);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/quat.h

@@ -17,6 +17,10 @@ CGLM_EXPORT
 void
 glmc_quat_identity(versor q);
 
+CGLM_EXPORT
+void
+glmc_quat_identity_array(versor * __restrict q, size_t count);
+
 CGLM_EXPORT
 void
 glmc_quat_init(versor q, float x, float y, float z, float w);
@@ -87,7 +91,7 @@ glmc_quat_angle(versor q);
 
 CGLM_EXPORT
 void
-glmc_quat_axis(versor q, versor dest);
+glmc_quat_axis(versor q, vec3 dest);
 
 CGLM_EXPORT
 void
@@ -113,6 +117,10 @@ CGLM_EXPORT
 void
 glmc_quat_lerp(versor from, versor to, float t, versor dest);
     
+CGLM_EXPORT
+void
+glmc_quat_lerpc(versor from, versor to, float t, versor dest);
+
 CGLM_EXPORT
 void
 glmc_quat_slerp(versor q, versor r, float t, versor dest);
@@ -123,11 +131,11 @@ glmc_quat_look(vec3 eye, versor ori, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest);
+glmc_quat_for(vec3 dir, vec3 up, versor dest);
 
 CGLM_EXPORT
 void
-glmc_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest);
+glmc_quat_forp(vec3 from, vec3 to, vec3 up, versor dest);
 
 CGLM_EXPORT
 void

include/cglm/call/ray.h

@@ -0,0 +1,27 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ray_h
+#define cglmc_ray_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+#include "../cglm.h"
+
+CGLM_EXPORT
+bool
+glmc_ray_triangle(vec3   origin,
+                  vec3   direction,
+                  vec3   v0,
+                  vec3   v1,
+                  vec3   v2,
+                  float *d);
+    
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ray_h */

include/cglm/call/sphere.h

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

include/cglm/call/vec2.h

@@ -0,0 +1,155 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_vec2_h
+#define cglmc_vec2_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_vec2(float * __restrict v, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_copy(vec2 a, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_zero(vec2 v);
+
+CGLM_EXPORT
+void
+glmc_vec2_one(vec2 v);
+
+CGLM_EXPORT
+float
+glmc_vec2_dot(vec2 a, vec2 b);
+
+CGLM_EXPORT
+float
+glmc_vec2_cross(vec2 a, vec2 b);
+
+CGLM_EXPORT
+float
+glmc_vec2_norm2(vec2 v);
+
+CGLM_EXPORT
+float
+glmc_vec2_norm(vec2 v);
+
+CGLM_EXPORT
+void
+glmc_vec2_add(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_adds(vec2 v, float s, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_sub(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_subs(vec2 v, float s, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_mul(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_scale(vec2 v, float s, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_scale_as(vec2 v, float s, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_div(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_divs(vec2 v, float s, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_addadd(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_subadd(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_muladd(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_muladds(vec2 a, float s, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_maxadd(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_minadd(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_negate_to(vec2 v, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_negate(vec2 v);
+
+CGLM_EXPORT
+void
+glmc_vec2_normalize(vec2 v);
+
+CGLM_EXPORT
+void
+glmc_vec2_normalize_to(vec2 v, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_rotate(vec2 v, float angle, vec2 dest);
+
+CGLM_EXPORT
+float
+glmc_vec2_distance2(vec2 a, vec2 b);
+
+CGLM_EXPORT
+float
+glmc_vec2_distance(vec2 a, vec2 b);
+
+CGLM_EXPORT
+void
+glmc_vec2_maxv(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_minv(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_clamp(vec2 v, float minval, float maxval);
+
+CGLM_EXPORT
+void
+glmc_vec2_lerp(vec2 from, vec2 to, float t, vec2 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_vec2_h */

include/cglm/call/vec3.h

@@ -14,7 +14,11 @@ extern "C" {
 #include "../cglm.h"
 
 /* DEPRECATED! use _copy, _ucopy versions */
-#define glmc_vec_dup(v, dest) glmc_vec_copy(v, dest)
+#define glmc_vec_dup(v, dest)          glmc_vec3_copy(v, dest)
+#define glmc_vec3_flipsign(v)          glmc_vec3_negate(v)
+#define glmc_vec3_flipsign_to(v, dest) glmc_vec3_negate_to(v, dest)
+#define glmc_vec3_inv(v)               glmc_vec3_negate(v)
+#define glmc_vec3_inv_to(v, dest)      glmc_vec3_negate_to(v, dest)
 
 CGLM_EXPORT
 void
@@ -22,209 +26,285 @@ glmc_vec3(vec4 v4, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_copy(vec3 a, vec3 dest);
+glmc_vec3_copy(vec3 a, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_zero(vec3 v);
+glmc_vec3_zero(vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_one(vec3 v);
+glmc_vec3_one(vec3 v);
 
 CGLM_EXPORT
 float
-glmc_vec_dot(vec3 a, vec3 b);
+glmc_vec3_dot(vec3 a, vec3 b);
 
 CGLM_EXPORT
 void
-glmc_vec_cross(vec3 a, vec3 b, vec3 d);
+glmc_vec3_cross(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_crossn(vec3 a, vec3 b, vec3 dest);
 
 CGLM_EXPORT
 float
-glmc_vec_norm(vec3 vec);
+glmc_vec3_norm(vec3 v);
 
 CGLM_EXPORT
 float
-glmc_vec_norm2(vec3 vec);
+glmc_vec3_norm2(vec3 v);
-
-CGLM_EXPORT
-void
-glmc_vec_normalize_to(vec3 vec, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_normalize(vec3 v);
-
-CGLM_EXPORT
-void
-glmc_vec_add(vec3 v1, vec3 v2, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_adds(vec3 v, float s, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_sub(vec3 a, vec3 b, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_subs(vec3 v, float s, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_mul(vec3 a, vec3 b, vec3 d);
-
-CGLM_EXPORT
-void
-glmc_vec_scale(vec3 v, float s, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_scale_as(vec3 v, float s, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_div(vec3 a, vec3 b, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_divs(vec3 a, float s, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_addadd(vec3 a, vec3 b, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_subadd(vec3 a, vec3 b, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_muladd(vec3 a, vec3 b, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_muladds(vec3 a, float s, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_flipsign(vec3 v);
-
-CGLM_EXPORT
-void
-glmc_vec_flipsign_to(vec3 v, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_inv(vec3 v);
-
-CGLM_EXPORT
-void
-glmc_vec_inv_to(vec3 v, vec3 dest);
     
 CGLM_EXPORT
 float
-glmc_vec_angle(vec3 v1, vec3 v2);
+glmc_vec3_norm_one(vec3 v);
-
-CGLM_EXPORT
-void
-glmc_vec_rotate(vec3 v, float angle, vec3 axis);
-
-CGLM_EXPORT
-void
-glmc_vec_rotate_m4(mat4 m, vec3 v, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_proj(vec3 a, vec3 b, vec3 dest);
-
-CGLM_EXPORT
-void
-glmc_vec_center(vec3 v1, vec3 v2, vec3 dest);
 
 CGLM_EXPORT
 float
-glmc_vec_distance(vec3 v1, vec3 v2);
+glmc_vec3_norm_inf(vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_maxv(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_normalize_to(vec3 v, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_minv(vec3 v1, vec3 v2, vec3 dest);
+glmc_vec3_normalize(vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_clamp(vec3 v, float minVal, float maxVal);
+glmc_vec3_add(vec3 a, vec3 b, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_ortho(vec3 v, vec3 dest);
+glmc_vec3_adds(vec3 v, float s, vec3 dest);
 
 CGLM_EXPORT
 void
-glmc_vec_lerp(vec3 from, vec3 to, float t, vec3 dest);
+glmc_vec3_sub(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_subs(vec3 v, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_mul(vec3 a, vec3 b, vec3 d);
+
+CGLM_EXPORT
+void
+glmc_vec3_scale(vec3 v, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_scale_as(vec3 v, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_div(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_divs(vec3 a, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_addadd(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_subadd(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_muladd(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_muladds(vec3 a, float s, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_maxadd(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_minadd(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_negate(vec3 v);
+
+CGLM_EXPORT
+void
+glmc_vec3_negate_to(vec3 v, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_vec3_angle(vec3 a, vec3 b);
+
+CGLM_EXPORT
+void
+glmc_vec3_rotate(vec3 v, float angle, vec3 axis);
+
+CGLM_EXPORT
+void
+glmc_vec3_rotate_m4(mat4 m, vec3 v, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_rotate_m3(mat3 m, vec3 v, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_proj(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_center(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_vec3_distance2(vec3 a, vec3 b);
+
+CGLM_EXPORT
+float
+glmc_vec3_distance(vec3 a, vec3 b);
+
+CGLM_EXPORT
+void
+glmc_vec3_maxv(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_minv(vec3 a, vec3 b, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_vec3_clamp(vec3 v, float minVal, float maxVal);
+
+CGLM_EXPORT
+void
+glmc_vec3_ortho(vec3 v, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_lerp(vec3 from, vec3 to, float t, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_lerpc(vec3 from, vec3 to, float t, vec3 dest);
+    
+CGLM_INLINE
+void
+glmc_vec3_mix(vec3 from, vec3 to, float t, vec3 dest) {
+  glmc_vec3_lerp(from, to, t, dest);
+}
+
+CGLM_INLINE
+void
+glmc_vec3_mixc(vec3 from, vec3 to, float t, vec3 dest) {
+  glmc_vec3_lerpc(from, to, t, dest);
+}
+    
+CGLM_EXPORT
+void
+glmc_vec3_step_uni(float edge, vec3 x, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_step(vec3 edge, vec3 x, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_smoothstep_uni(float edge0, float edge1, vec3 x, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_smoothstep(vec3 edge0, vec3 edge1, vec3 x, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_smoothinterp(vec3 from, vec3 to, float t, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_smoothinterpc(vec3 from, vec3 to, float t, vec3 dest);
 
 /* ext */
 
 CGLM_EXPORT
 void
-glmc_vec_mulv(vec3 a, vec3 b, vec3 d);
+glmc_vec3_mulv(vec3 a, vec3 b, vec3 d);
 
 CGLM_EXPORT
 void
-glmc_vec_broadcast(float val, vec3 d);
+glmc_vec3_broadcast(float val, vec3 d);
+    
+CGLM_EXPORT
+void
+glmc_vec3_fill(vec3 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec_eq(vec3 v, float val);
+glmc_vec3_eq(vec3 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec_eq_eps(vec3 v, float val);
+glmc_vec3_eq_eps(vec3 v, float val);
 
 CGLM_EXPORT
 bool
-glmc_vec_eq_all(vec3 v);
+glmc_vec3_eq_all(vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_eqv(vec3 v1, vec3 v2);
+glmc_vec3_eqv(vec3 a, vec3 b);
 
 CGLM_EXPORT
 bool
-glmc_vec_eqv_eps(vec3 v1, vec3 v2);
+glmc_vec3_eqv_eps(vec3 a, vec3 b);
 
 CGLM_EXPORT
 float
-glmc_vec_max(vec3 v);
+glmc_vec3_max(vec3 v);
 
 CGLM_EXPORT
 float
-glmc_vec_min(vec3 v);
+glmc_vec3_min(vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_isnan(vec3 v);
+glmc_vec3_isnan(vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_isinf(vec3 v);
+glmc_vec3_isinf(vec3 v);
 
 CGLM_EXPORT
 bool
-glmc_vec_isvalid(vec3 v);
+glmc_vec3_isvalid(vec3 v);
 
 CGLM_EXPORT
 void
-glmc_vec_sign(vec3 v, vec3 dest);
+glmc_vec3_sign(vec3 v, vec3 dest);
     
 CGLM_EXPORT
 void
-glmc_vec_sqrt(vec3 v, vec3 dest);
+glmc_vec3_abs(vec3 v, vec3 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec3_fract(vec3 v, vec3 dest);
+    
+CGLM_EXPORT
+float
+glmc_vec3_hadd(vec3 v);
+
+CGLM_EXPORT
+void
+glmc_vec3_sqrt(vec3 v, vec3 dest);
 
 #ifdef __cplusplus
 }

include/cglm/call/vec4.h

@@ -14,8 +14,12 @@ extern "C" {
 #include "../cglm.h"
 
 /* DEPRECATED! use _copy, _ucopy versions */
-#define glmc_vec4_dup3(v, dest) glmc_vec4_copy3(v, dest)
+#define glmc_vec4_dup3(v, dest)         glmc_vec4_copy3(v, dest)
-#define glmc_vec4_dup(v, dest)  glmc_vec4_copy(v, dest)
+#define glmc_vec4_dup(v, dest)          glmc_vec4_copy(v, dest)
+#define glmc_vec4_flipsign(v)           glmc_vec4_negate(v)
+#define glmc_vec4_flipsign_to(v, dest)  glmc_vec4_negate_to(v, dest)
+#define glmc_vec4_inv(v)                glmc_vec4_negate(v)
+#define glmc_vec4_inv_to(v, dest)       glmc_vec4_negate_to(v, dest)
 
 CGLM_EXPORT
 void
@@ -31,27 +35,39 @@ glmc_vec4_one(vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_copy3(vec4 a, vec3 dest);
+glmc_vec4_copy3(vec4 v, vec3 dest);
 
 CGLM_EXPORT
 void
 glmc_vec4_copy(vec4 v, vec4 dest);
 
+CGLM_EXPORT
+void
+glmc_vec4_ucopy(vec4 v, vec4 dest);
+
 CGLM_EXPORT
 float
 glmc_vec4_dot(vec4 a, vec4 b);
 
 CGLM_EXPORT
 float
-glmc_vec4_norm(vec4 vec);
+glmc_vec4_norm(vec4 v);
 
 CGLM_EXPORT
 float
-glmc_vec4_norm2(vec4 vec);
+glmc_vec4_norm2(vec4 v);
+    
+CGLM_EXPORT
+float
+glmc_vec4_norm_one(vec4 v);
+
+CGLM_EXPORT
+float
+glmc_vec4_norm_inf(vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_normalize_to(vec4 vec, vec4 dest);
+glmc_vec4_normalize_to(vec4 v, vec4 dest);
 
 CGLM_EXPORT
 void
@@ -111,31 +127,35 @@ glmc_vec4_muladds(vec4 a, float s, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_flipsign(vec4 v);
+glmc_vec4_maxadd(vec4 a, vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_flipsign_to(vec4 v, vec4 dest);
+glmc_vec4_minadd(vec4 a, vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_inv(vec4 v);
+glmc_vec4_negate(vec4 v);
 
 CGLM_EXPORT
 void
-glmc_vec4_inv_to(vec4 v, vec4 dest);
+glmc_vec4_negate_to(vec4 v, vec4 dest);
     
 CGLM_EXPORT
 float
-glmc_vec4_distance(vec4 v1, vec4 v2);
+glmc_vec4_distance(vec4 a, vec4 b);
+    
+CGLM_EXPORT
+float
+glmc_vec4_distance2(vec4 a, vec4 b);
 
 CGLM_EXPORT
 void
-glmc_vec4_maxv(vec4 v1, vec4 v2, vec4 dest);
+glmc_vec4_maxv(vec4 a, vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
-glmc_vec4_minv(vec4 v1, vec4 v2, vec4 dest);
+glmc_vec4_minv(vec4 a, vec4 b, vec4 dest);
 
 CGLM_EXPORT
 void
@@ -145,6 +165,50 @@ CGLM_EXPORT
 void
 glmc_vec4_lerp(vec4 from, vec4 to, float t, vec4 dest);
     
+CGLM_EXPORT
+void
+glmc_vec4_lerpc(vec4 from, vec4 to, float t, vec4 dest);
+    
+CGLM_INLINE
+void
+glmc_vec4_mix(vec4 from, vec4 to, float t, vec4 dest) {
+  glmc_vec4_lerp(from, to, t, dest);
+}
+
+CGLM_INLINE
+void
+glmc_vec4_mixc(vec4 from, vec4 to, float t, vec4 dest) {
+  glmc_vec4_lerpc(from, to, t, dest);
+}
+    
+CGLM_EXPORT
+void
+glmc_vec4_step_uni(float edge, vec4 x, vec4 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec4_step(vec4 edge, vec4 x, vec4 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec4_smoothstep_uni(float edge0, float edge1, vec4 x, vec4 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec4_smoothstep(vec4 edge0, vec4 edge1, vec4 x, vec4 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec4_smoothinterp(vec4 from, vec4 to, float t, vec4 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec4_smoothinterpc(vec4 from, vec4 to, float t, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_vec4_cubic(float s, vec4 dest);
+
 /* ext */
 
 CGLM_EXPORT
@@ -155,6 +219,10 @@ CGLM_EXPORT
 void
 glmc_vec4_broadcast(float val, vec4 d);
     
+CGLM_EXPORT
+void
+glmc_vec4_fill(vec4 v, float val);
+
 CGLM_EXPORT
 bool
 glmc_vec4_eq(vec4 v, float val);
@@ -169,11 +237,11 @@ glmc_vec4_eq_all(vec4 v);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eqv(vec4 v1, vec4 v2);
+glmc_vec4_eqv(vec4 a, vec4 b);
 
 CGLM_EXPORT
 bool
-glmc_vec4_eqv_eps(vec4 v1, vec4 v2);
+glmc_vec4_eqv_eps(vec4 a, vec4 b);
 
 CGLM_EXPORT
 float
@@ -199,6 +267,18 @@ CGLM_EXPORT
 void
 glmc_vec4_sign(vec4 v, vec4 dest);
     
+CGLM_EXPORT
+void
+glmc_vec4_abs(vec4 v, vec4 dest);
+    
+CGLM_EXPORT
+void
+glmc_vec4_fract(vec4 v, vec4 dest);
+    
+CGLM_EXPORT
+float
+glmc_vec4_hadd(vec4 v);
+
 CGLM_EXPORT
 void
 glmc_vec4_sqrt(vec4 v, vec4 dest);

include/cglm/cam.h

@@ -7,48 +7,37 @@
 
 /*
  Functions:
-   CGLM_INLINE void  glm_frustum(float left,
+   CGLM_INLINE void  glm_frustum(float left,    float right,
-                                 float right,
+                                 float bottom,  float top,
-                                 float bottom,
+                                 float nearVal, float farVal,
-                                 float top,
-                                 float nearVal,
-                                 float farVal,
                                  mat4  dest)
-   CGLM_INLINE void  glm_ortho(float left,
+   CGLM_INLINE void  glm_ortho(float left,    float right,
-                               float right,
+                               float bottom,  float top,
-                               float bottom,
+                               float nearVal, float farVal,
-                               float top,
-                               float nearVal,
-                               float farVal,
                                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)
+   CGLM_INLINE void  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)
    CGLM_INLINE void  glm_ortho_default(float aspect, mat4  dest)
-   CGLM_INLINE void  glm_ortho_default_s(float aspect, float size, mat4  dest)
+   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,
                                      mat4  dest)
-   CGLM_INLINE void  glm_perspective_default(float aspect, mat4  dest)
+   CGLM_INLINE void  glm_perspective_default(float aspect, mat4 dest)
-   CGLM_INLINE void  glm_perspective_resize(float aspect, mat4  proj)
+   CGLM_INLINE void  glm_perspective_resize(float aspect, mat4 proj)
    CGLM_INLINE void  glm_lookat(vec3 eye, vec3 center, vec3 up, mat4 dest)
    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 *nearVal, float *farVal,
-                                      float *farVal,
+                                      float *top,     float *bottom,
-                                      float *top,
+                                      float *left,    float *right)
-                                      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,
+   CGLM_INLINE void  glm_persp_decomp_z(mat4 proj, float *nearv, float *farv)
-                                        float *nearVal,
-                                        float *farVal)
    CGLM_INLINE void  glm_persp_decomp_far(mat4 proj, float *farVal)
    CGLM_INLINE void  glm_persp_decomp_near(mat4 proj, float *nearVal)
    CGLM_INLINE float glm_persp_fovy(mat4 proj)
@@ -75,16 +64,13 @@
  */
 CGLM_INLINE
 void
-glm_frustum(float left,
+glm_frustum(float left,    float right,
-            float right,
+            float bottom,  float top,
-            float bottom,
+            float nearVal, float farVal,
-            float top,
-            float nearVal,
-            float farVal,
             mat4  dest) {
   float rl, tb, fn, nv;
 
-  glm__memzero(float, dest, sizeof(mat4));
+  glm_mat4_zero(dest);
 
   rl = 1.0f / (right  - left);
   tb = 1.0f / (top    - bottom);
@@ -113,16 +99,13 @@ glm_frustum(float left,
  */
 CGLM_INLINE
 void
-glm_ortho(float left,
+glm_ortho(float left,    float right,
-          float right,
+          float bottom,  float top,
-          float bottom,
+          float nearVal, float farVal,
-          float top,
-          float nearVal,
-          float farVal,
           mat4  dest) {
   float rl, tb, fn;
 
-  glm__memzero(float, dest, sizeof(mat4));
+  glm_mat4_zero(dest);
 
   rl = 1.0f / (right  - left);
   tb = 1.0f / (top    - bottom);
@@ -198,26 +181,15 @@ glm_ortho_aabb_pz(vec3 box[2], float padding, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_ortho_default(float aspect,
+glm_ortho_default(float aspect, mat4 dest) {
-                  mat4  dest) {
   if (aspect >= 1.0f) {
-    glm_ortho(-1.0f * aspect,
+    glm_ortho(-aspect, aspect, -1.0f, 1.0f, -100.0f, 100.0f, dest);
-               1.0f * aspect,
+    return;
-              -1.0f,
-               1.0f,
-              -100.0f,
-               100.0f,
-               dest);
-	  return;
   }
 
-  glm_ortho(-1.0f,
+  aspect = 1.0f / aspect;
-             1.0f,
+
-            -1.0f / aspect,
+  glm_ortho(-1.0f, 1.0f, -aspect, aspect, -100.0f, 100.0f, dest);
-             1.0f / aspect,
-            -100.0f,
-             100.0f,
-             dest);
 }
 
 /*!
@@ -229,9 +201,7 @@ glm_ortho_default(float aspect,
  */
 CGLM_INLINE
 void
-glm_ortho_default_s(float aspect,
+glm_ortho_default_s(float aspect, float size, mat4 dest) {
-                    float size,
-                    mat4  dest) {
   if (aspect >= 1.0f) {
     glm_ortho(-size * aspect,
                size * aspect,
@@ -240,7 +210,7 @@ glm_ortho_default_s(float aspect,
               -size - 100.0f,
                size + 100.0f,
                dest);
-	  return;
+    return;
   }
 
   glm_ortho(-size,
@@ -270,7 +240,7 @@ glm_perspective(float fovy,
                 mat4  dest) {
   float f, fn;
 
-  glm__memzero(float, dest, sizeof(mat4));
+  glm_mat4_zero(dest);
 
   f  = 1.0f / tanf(fovy * 0.5f);
   fn = 1.0f / (nearVal - farVal);
@@ -282,6 +252,30 @@ glm_perspective(float fovy,
   dest[3][2] = 2.0f * nearVal * farVal * fn;
 }
 
+/*!
+ * @brief extend perspective projection matrix's far distance
+ *
+ * this function does not guarantee far >= near, be aware of that!
+ *
+ * @param[in, out] proj      projection matrix to extend
+ * @param[in]      deltaFar  distance from existing far (negative to shink)
+ */
+CGLM_INLINE
+void
+glm_persp_move_far(mat4 proj, float deltaFar) {
+  float fn, farVal, nearVal, p22, p32;
+
+  p22        = proj[2][2];
+  p32        = proj[3][2];
+
+  nearVal    = p32 / (p22 - 1.0f);
+  farVal     = p32 / (p22 + 1.0f) + deltaFar;
+  fn         = 1.0f / (nearVal - farVal);
+
+  proj[2][2] = (nearVal + farVal) * fn;
+  proj[3][2] = 2.0f * nearVal * farVal * fn;
+}
+
 /*!
  * @brief set up perspective projection matrix with default near/far
  *        and angle values
@@ -291,13 +285,8 @@ glm_perspective(float fovy,
  */
 CGLM_INLINE
 void
-glm_perspective_default(float aspect,
+glm_perspective_default(float aspect, mat4 dest) {
-                        mat4  dest) {
+  glm_perspective(GLM_PI_4f, aspect, 0.01f, 100.0f, dest);
-  glm_perspective((float)CGLM_PI_4,
-                  aspect,
-                  0.01f,
-                  100.0f,
-                  dest);
 }
 
 /*!
@@ -310,8 +299,7 @@ glm_perspective_default(float aspect,
  */
 CGLM_INLINE
 void
-glm_perspective_resize(float aspect,
+glm_perspective_resize(float aspect, mat4 proj) {
-                       mat4  proj) {
   if (proj[0][0] == 0.0f)
     return;
 
@@ -321,6 +309,9 @@ glm_perspective_resize(float aspect,
 /*!
  * @brief set up view matrix
  *
+ * NOTE: The UP vector must not be parallel to the line of sight from
+ *       the eye point to the reference point
+ *
  * @param[in]  eye    eye vector
  * @param[in]  center center vector
  * @param[in]  up     up vector
@@ -328,19 +319,14 @@ glm_perspective_resize(float aspect,
  */
 CGLM_INLINE
 void
-glm_lookat(vec3 eye,
+glm_lookat(vec3 eye, vec3 center, vec3 up, mat4 dest) {
-           vec3 center,
+  CGLM_ALIGN(8) vec3 f, u, s;
-           vec3 up,
-           mat4 dest) {
-  vec3 f, u, s;
 
-  glm_vec_sub(center, eye, f);
+  glm_vec3_sub(center, eye, f);
-  glm_vec_normalize(f);
+  glm_vec3_normalize(f);
 
-  glm_vec_cross(f, up, s);
+  glm_vec3_crossn(f, up, s);
-  glm_vec_normalize(s);
+  glm_vec3_cross(s, f, u);
-
-  glm_vec_cross(s, f, u);
 
   dest[0][0] = s[0];
   dest[0][1] = u[0];
@@ -351,9 +337,9 @@ glm_lookat(vec3 eye,
   dest[2][0] = s[2];
   dest[2][1] = u[2];
   dest[2][2] =-f[2];
-  dest[3][0] =-glm_vec_dot(s, eye);
+  dest[3][0] =-glm_vec3_dot(s, eye);
-  dest[3][1] =-glm_vec_dot(u, eye);
+  dest[3][1] =-glm_vec3_dot(u, eye);
-  dest[3][2] = glm_vec_dot(f, eye);
+  dest[3][2] = glm_vec3_dot(f, eye);
   dest[0][3] = dest[1][3] = dest[2][3] = 0.0f;
   dest[3][3] = 1.0f;
 }
@@ -364,6 +350,9 @@ glm_lookat(vec3 eye,
  * convenient wrapper for lookat: if you only have direction not target self
  * then this might be useful. Because you need to get target from direction.
  *
+ * NOTE: The UP vector must not be parallel to the line of sight from
+ *       the eye point to the reference point
+ *
  * @param[in]  eye    eye vector
  * @param[in]  dir    direction vector
  * @param[in]  up     up vector
@@ -372,8 +361,8 @@ glm_lookat(vec3 eye,
 CGLM_INLINE
 void
 glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
-  vec3 target;
+  CGLM_ALIGN(8) vec3 target;
-  glm_vec_add(eye, dir, target);
+  glm_vec3_add(eye, dir, target);
   glm_lookat(eye, target, up, dest);
 }
 
@@ -390,8 +379,8 @@ glm_look(vec3 eye, vec3 dir, vec3 up, mat4 dest) {
 CGLM_INLINE
 void
 glm_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
-  vec3 up;
+  CGLM_ALIGN(8) vec3 up;
-  glm_vec_ortho(dir, up);
+  glm_vec3_ortho(dir, up);
   glm_look(eye, dir, up, dest);
 }
 
@@ -409,12 +398,9 @@ glm_look_anyup(vec3 eye, vec3 dir, mat4 dest) {
 CGLM_INLINE
 void
 glm_persp_decomp(mat4 proj,
-                 float * __restrict nearVal,
+                 float * __restrict nearVal, float * __restrict farVal,
-                 float * __restrict farVal,
+                 float * __restrict top,     float * __restrict bottom,
-                 float * __restrict top,
+                 float * __restrict left,    float * __restrict right) {
-                 float * __restrict bottom,
-                 float * __restrict left,
-                 float * __restrict right) {
   float m00, m11, m20, m21, m22, m32, n, f;
   float n_m11, n_m00;
 

include/cglm/cglm.h

@@ -9,10 +9,12 @@
 #define cglm_h
 
 #include "common.h"
+#include "vec2.h"
 #include "vec3.h"
 #include "vec4.h"
 #include "mat4.h"
 #include "mat3.h"
+#include "mat2.h"
 #include "affine.h"
 #include "cam.h"
 #include "frustum.h"
@@ -24,5 +26,11 @@
 #include "util.h"
 #include "io.h"
 #include "project.h"
+#include "sphere.h"
+#include "ease.h"
+#include "curve.h"
+#include "bezier.h"
+#include "ray.h"
+#include "affine2d.h"
 
 #endif /* cglm_h */

include/cglm/common.h

@@ -8,14 +8,24 @@
 #ifndef cglm_common_h
 #define cglm_common_h
 
-#define _USE_MATH_DEFINES /* for windows */
+#ifndef _USE_MATH_DEFINES
+#  define _USE_MATH_DEFINES       /* for windows */
+#endif
+
+#ifndef _CRT_SECURE_NO_WARNINGS
+#  define _CRT_SECURE_NO_WARNINGS /* for windows */
+#endif
 
 #include <stdint.h>
+#include <stddef.h>
 #include <math.h>
 #include <float.h>
+#include <stdbool.h>
 
 #if defined(_MSC_VER)
-#  ifdef CGLM_DLL
+#  ifdef CGLM_STATIC
+#    define CGLM_EXPORT
+#  elif defined(CGLM_EXPORTS)
 #    define CGLM_EXPORT __declspec(dllexport)
 #  else
 #    define CGLM_EXPORT __declspec(dllimport)
@@ -26,35 +36,18 @@
 #  define CGLM_INLINE static inline __attribute((always_inline))
 #endif
 
-#define glm__memcpy(type, dest, src, size)                                    \
+#define GLM_SHUFFLE4(z, y, x, w) (((z) << 6) | ((y) << 4) | ((x) << 2) | (w))
-  do {                                                                        \
+#define GLM_SHUFFLE3(z, y, x)    (((z) << 4) | ((y) << 2) | (x))
-    type *srci;                                                               \
-    type *srci_end;                                                           \
-    type *desti;                                                              \
-                                                                              \
-    srci     = (type *)src;                                                   \
-    srci_end = (type *)((char *)srci + size);                                 \
-    desti    = (type *)dest;                                                  \
-                                                                              \
-    while (srci != srci_end)                                                  \
-      *desti++ = *srci++;                                                     \
-  } while (0)
-
-#define glm__memset(type, dest, size, val)                                    \
-  do {                                                                        \
-    type *desti;                                                              \
-    type *desti_end;                                                          \
-                                                                              \
-    desti     = (type *)dest;                                                 \
-    desti_end = (type *)((char *)desti + size);                               \
-                                                                              \
-    while (desti != desti_end)                                                \
-      *desti++ = val;                                                         \
-  } while (0)
-
-#define glm__memzero(type, dest, size) glm__memset(type, dest, size, 0)
 
 #include "types.h"
 #include "simd/intrin.h"
 
+#ifndef CGLM_USE_DEFAULT_EPSILON
+#  ifndef GLM_FLT_EPSILON
+#    define GLM_FLT_EPSILON 1e-6
+#  endif
+#else
+#  define GLM_FLT_EPSILON FLT_EPSILON
+#endif
+
 #endif /* cglm_common_h */

include/cglm/curve.h

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

include/cglm/ease.h

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

include/cglm/euler.h

@@ -15,10 +15,10 @@
 
 /*
  Types:
-   enum glm_euler_sq
+   enum glm_euler_seq
 
  Functions:
-   CGLM_INLINE glm_euler_sq glm_euler_order(int newOrder[3]);
+   CGLM_INLINE glm_euler_seq glm_euler_order(int newOrder[3]);
    CGLM_INLINE void glm_euler_angles(mat4 m, vec3 dest);
    CGLM_INLINE void glm_euler(vec3 angles, mat4 dest);
    CGLM_INLINE void glm_euler_xyz(vec3 angles, mat4 dest);
@@ -28,7 +28,7 @@
    CGLM_INLINE void glm_euler_yzx(vec3 angles, mat4 dest);
    CGLM_INLINE void glm_euler_yxz(vec3 angles, mat4 dest);
    CGLM_INLINE void glm_euler_by_order(vec3         angles,
-                                       glm_euler_sq ord,
+                                       glm_euler_seq ord,
                                        mat4         dest);
  */
 
@@ -41,24 +41,24 @@
  * if you have axis order like vec3 orderVec = [0, 1, 2] or [0, 2, 1]...
  * vector then you can convert it to this enum by doing this:
  * @code
- * glm_euler_sq order;
+ * glm_euler_seq order;
  * order = orderVec[0] | orderVec[1] << 2 | orderVec[2] << 4;
  * @endcode
  * you may need to explicit cast if required
  */
-typedef enum glm_euler_sq {
+typedef enum glm_euler_seq {
   GLM_EULER_XYZ = 0 << 0 | 1 << 2 | 2 << 4,
   GLM_EULER_XZY = 0 << 0 | 2 << 2 | 1 << 4,
   GLM_EULER_YZX = 1 << 0 | 2 << 2 | 0 << 4,
   GLM_EULER_YXZ = 1 << 0 | 0 << 2 | 2 << 4,
   GLM_EULER_ZXY = 2 << 0 | 0 << 2 | 1 << 4,
   GLM_EULER_ZYX = 2 << 0 | 1 << 2 | 0 << 4
-} glm_euler_sq;
+} glm_euler_seq;
 
 CGLM_INLINE
-glm_euler_sq
+glm_euler_seq
 glm_euler_order(int ord[3]) {
-  return (glm_euler_sq)(ord[0] << 0 | ord[1] << 2 | ord[2] << 4);
+  return (glm_euler_seq)(ord[0] << 0 | ord[1] << 2 | ord[2] << 4);
 }
 
 /*!
@@ -84,12 +84,12 @@ glm_euler_angles(mat4 m, vec3 dest) {
       thetaZ = atan2f(-m10, m00);
     } else { /* m20 == -1 */
       /* Not a unique solution */
-      thetaY = -CGLM_PI_2;
+      thetaY = -GLM_PI_2f;
       thetaX = -atan2f(m01, m11);
       thetaZ =  0.0f;
     }
   } else { /* m20 == +1 */
-    thetaY = CGLM_PI_2;
+    thetaY = GLM_PI_2f;
     thetaX = atan2f(m01, m11);
     thetaZ = 0.0f;
   }
@@ -352,7 +352,7 @@ glm_euler_zyx(vec3 angles, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_euler_by_order(vec3 angles, glm_euler_sq ord, mat4 dest) {
+glm_euler_by_order(vec3 angles, glm_euler_seq ord, mat4 dest) {
   float cx, cy, cz,
         sx, sy, sz;
 

include/cglm/frustum.h

@@ -65,7 +65,7 @@
  * Exracted planes order: [left, right, bottom, top, near, far]
  *
  * @param[in]  m    matrix (see brief)
- * @param[out] dest exracted view frustum planes (see brief)
+ * @param[out] dest extracted view frustum planes (see brief)
  */
 CGLM_INLINE
 void
@@ -106,7 +106,7 @@ glm_frustum_planes(mat4 m, vec4 dest[6]) {
  *
  * Find center coordinates:
  *   for (j = 0; j < 4; j++) {
- *     glm_vec_center(corners[i], corners[i + 4], centerCorners[i]);
+ *     glm_vec3_center(corners[i], corners[i + 4], centerCorners[i]);
  *   }
  *
  * @param[in]  invMat matrix (see brief)
@@ -187,8 +187,8 @@ glm_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]) {
   vec3 min, max;
   int  i;
 
-  glm_vec_broadcast(FLT_MAX, min);
+  glm_vec3_broadcast(FLT_MAX, min);
-  glm_vec_broadcast(-FLT_MAX, max);
+  glm_vec3_broadcast(-FLT_MAX, max);
 
   for (i = 0; i < 8; i++) {
     glm_mat4_mulv(m, corners[i], v);
@@ -202,8 +202,8 @@ glm_frustum_box(vec4 corners[8], mat4 m, vec3 box[2]) {
     max[2] = glm_max(max[2], v[2]);
   }
 
-  glm_vec_copy(min, box[0]);
+  glm_vec3_copy(min, box[0]);
-  glm_vec_copy(max, box[1]);
+  glm_vec3_copy(max, box[1]);
 }
 
 /*!
@@ -228,7 +228,7 @@ glm_frustum_corners_at(vec4  corners[8],
   float dist, sc;
 
   /* because distance and scale is same for all */
-  dist = glm_vec_distance(corners[GLM_RTF], corners[GLM_RTN]);
+  dist = glm_vec3_distance(corners[GLM_RTF], corners[GLM_RTN]);
   sc   = dist * (splitDist / farDist);
 
   /* left bottom */

include/cglm/io.h

@@ -15,69 +15,130 @@
    CGLM_INLINE void glm_versor_print(versor vec, FILE *ostream);
  */
 
+/*
+ cglm tried to enable print functions in debug mode and disable them in
+ release/production mode to eliminate printing costs.
+ 
+ if you need to force enable then define CGLM_DEFINE_PRINTS macro not DEBUG one
+ 
+ Print functions are enabled if:
+ 
+ - DEBUG or _DEBUG macro is defined (mostly defined automatically in debugging)
+ - CGLM_DEFINE_PRINTS macro is defined including release/production
+   which makes enabled printing always
+ - glmc_ calls for io are always prints
+
+ */
+
+/* DEPRECATED: CGLM_NO_PRINTS_NOOP (use CGLM_DEFINE_PRINTS) */
+
 #ifndef cglm_io_h
 #define cglm_io_h
+#if defined(DEBUG) || defined(_DEBUG) \
+   || defined(CGLM_DEFINE_PRINTS) || defined(CGLM_LIB_SRC) \
+   || defined(CGLM_NO_PRINTS_NOOP)
 
 #include "common.h"
 
 #include <stdio.h>
 #include <stdlib.h>
 
+#ifndef CGLM_PRINT_PRECISION
+#  define CGLM_PRINT_PRECISION    5
+#endif
+
+#ifndef CGLM_PRINT_MAX_TO_SHORT
+#  define CGLM_PRINT_MAX_TO_SHORT 1e5
+#endif
+
+#ifndef CGLM_PRINT_COLOR
+#  define CGLM_PRINT_COLOR        "\033[36m"
+#endif
+
+#ifndef CGLM_PRINT_COLOR_RESET
+#  define CGLM_PRINT_COLOR_RESET  "\033[0m"
+#endif
+
 CGLM_INLINE
 void
-glm_mat4_print(mat4   matrix,
+glm_mat4_print(mat4              matrix,
                FILE * __restrict ostream) {
-  int i;
+  char buff[16];
-  int j;
+  int  i, j, cw[4], cwi;
 
 #define m 4
 #define n 4
 
-  fprintf(ostream, "Matrix (float%dx%d):\n", m, n);
+  fprintf(ostream, "Matrix (float%dx%d): " CGLM_PRINT_COLOR "\n" , m, n);
+
+  cw[0] = cw[1] = cw[2] = cw[3] = 0;
 
   for (i = 0; i < m; i++) {
-    fprintf(ostream, "\t|");
     for (j = 0; j < n; j++) {
-      fprintf(ostream, "%0.4f", matrix[j][i]);;
+      if (matrix[i][j] < CGLM_PRINT_MAX_TO_SHORT)
-
+        cwi = sprintf(buff, "% .*f", CGLM_PRINT_PRECISION, matrix[i][j]);
-      if (j != n - 1)
+      else
-        fprintf(ostream, "\t");
+        cwi = sprintf(buff, "% g", matrix[i][j]);
+      cw[i] = GLM_MAX(cw[i], cwi);
     }
-
-    fprintf(ostream, "|\n");
   }
 
-  fprintf(ostream, "\n");
+  for (i = 0; i < m; i++) {
+    fprintf(ostream, "  |");
+
+    for (j = 0; j < n; j++)
+      if (matrix[i][j] < CGLM_PRINT_MAX_TO_SHORT)
+        fprintf(ostream, " % *.*f", cw[j], CGLM_PRINT_PRECISION, matrix[j][i]);
+      else
+        fprintf(ostream, " % *g", cw[j], matrix[j][i]);
+
+    fprintf(ostream, "  |\n");
+  }
+
+  fprintf(ostream, CGLM_PRINT_COLOR_RESET "\n");
 
 #undef m
 #undef n
 }
 
+
 CGLM_INLINE
 void
-glm_mat3_print(mat3 matrix,
+glm_mat3_print(mat3              matrix,
                FILE * __restrict ostream) {
-  int i;
+  char buff[16];
-  int j;
+  int  i, j, cw[4], cwi;
 
 #define m 3
 #define n 3
 
-  fprintf(ostream, "Matrix (float%dx%d):\n", m, n);
+  fprintf(ostream, "Matrix (float%dx%d): " CGLM_PRINT_COLOR "\n", m, n);
+
+  cw[0] = cw[1] = cw[2] = 0;
 
   for (i = 0; i < m; i++) {
-    fprintf(ostream, "\t|");
     for (j = 0; j < n; j++) {
-      fprintf(ostream, "%0.4f", matrix[j][i]);;
+      if (matrix[i][j] < CGLM_PRINT_MAX_TO_SHORT)
-
+        cwi = sprintf(buff, "% .*f", CGLM_PRINT_PRECISION, matrix[i][j]);
-      if (j != n - 1)
+      else
-        fprintf(ostream, "\t");
+        cwi = sprintf(buff, "% g", matrix[i][j]);
+      cw[i] = GLM_MAX(cw[i], cwi);
     }
-
-    fprintf(ostream, "|\n");
   }
 
-  fprintf(ostream, "\n");
+  for (i = 0; i < m; i++) {
+    fprintf(ostream, "  |");
+    
+    for (j = 0; j < n; j++)
+      if (matrix[i][j] < CGLM_PRINT_MAX_TO_SHORT)
+        fprintf(ostream, " % *.*f", cw[j], CGLM_PRINT_PRECISION, matrix[j][i]);
+      else
+        fprintf(ostream, " % *g", cw[j], matrix[j][i]);
+    
+    fprintf(ostream, "  |\n");
+  }
+
+  fprintf(ostream, CGLM_PRINT_COLOR_RESET "\n");
 
 #undef m
 #undef n
@@ -85,88 +146,149 @@ glm_mat3_print(mat3 matrix,
 
 CGLM_INLINE
 void
-glm_vec4_print(vec4 vec,
+glm_mat2_print(mat2              matrix,
+               FILE * __restrict ostream) {
+  char buff[16];
+  int  i, j, cw[4], cwi;
+
+#define m 2
+#define n 2
+
+  fprintf(ostream, "Matrix (float%dx%d): " CGLM_PRINT_COLOR "\n", m, n);
+
+  cw[0] = cw[1] = 0;
+
+  for (i = 0; i < m; i++) {
+    for (j = 0; j < n; j++) {
+      if (matrix[i][j] < CGLM_PRINT_MAX_TO_SHORT)
+        cwi = sprintf(buff, "% .*f", CGLM_PRINT_PRECISION, matrix[i][j]);
+      else
+        cwi = sprintf(buff, "% g", matrix[i][j]);
+      cw[i] = GLM_MAX(cw[i], cwi);
+    }
+  }
+
+  for (i = 0; i < m; i++) {
+    fprintf(ostream, "  |");
+    
+    for (j = 0; j < n; j++)
+      if (matrix[i][j] < CGLM_PRINT_MAX_TO_SHORT)
+        fprintf(ostream, " % *.*f", cw[j], CGLM_PRINT_PRECISION, matrix[j][i]);
+      else
+        fprintf(ostream, " % *g", cw[j], matrix[j][i]);
+    
+    fprintf(ostream, "  |\n");
+  }
+
+  fprintf(ostream, CGLM_PRINT_COLOR_RESET "\n");
+
+#undef m
+#undef n
+}
+
+CGLM_INLINE
+void
+glm_vec4_print(vec4              vec,
                FILE * __restrict ostream) {
   int i;
 
 #define m 4
 
-  fprintf(ostream, "Vector (float%d):\n\t|", m);
+  fprintf(ostream, "Vector (float%d): " CGLM_PRINT_COLOR "\n  (", m);
 
   for (i = 0; i < m; i++) {
-    fprintf(ostream, "%0.4f", vec[i]);
+    if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
-    if (i != m - 1)
+    else
-      fprintf(ostream, "\t");
+      fprintf(ostream, " % g", vec[i]);
   }
 
-  fprintf(ostream, "|\n\n");
+  fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
 
 #undef m
 }
 
 CGLM_INLINE
 void
-glm_vec3_print(vec3 vec,
+glm_vec3_print(vec3              vec,
                FILE * __restrict ostream) {
   int i;
 
 #define m 3
 
-  fprintf(ostream, "Vector (float%d):\n\t|", m);
+  fprintf(ostream, "Vector (float%d): " CGLM_PRINT_COLOR "\n  (", m);
 
   for (i = 0; i < m; i++) {
-    fprintf(ostream, "%0.4f", vec[i]);
+    if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
-    if (i != m - 1)
+    else
-      fprintf(ostream, "\t");
+      fprintf(ostream, " % g", vec[i]);
   }
 
-  fprintf(ostream, "|\n\n");
+  fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
 
 #undef m
 }
 
 CGLM_INLINE
 void
-glm_ivec3_print(ivec3 vec,
+glm_ivec3_print(ivec3             vec,
                 FILE * __restrict ostream) {
   int i;
 
 #define m 3
 
-  fprintf(ostream, "Vector (int%d):\n\t|", m);
+  fprintf(ostream, "Vector (int%d): " CGLM_PRINT_COLOR "\n  (", m);
 
-  for (i = 0; i < m; i++) {
+  for (i = 0; i < m; i++)
-    fprintf(ostream, "%d", vec[i]);
+    fprintf(ostream, " % d", vec[i]);
 
-    if (i != m - 1)
+  fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
-      fprintf(ostream, "\t");
-  }
-
-  fprintf(ostream, "|\n\n");
   
 #undef m
 }
 
 CGLM_INLINE
 void
-glm_versor_print(versor vec,
+glm_vec2_print(vec2              vec,
+               FILE * __restrict ostream) {
+  int i;
+
+#define m 2
+
+  fprintf(ostream, "Vector (float%d): " CGLM_PRINT_COLOR "\n  (", m);
+
+  for (i = 0; i < m; i++) {
+    if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
+    else
+      fprintf(ostream, " % g", vec[i]);
+  }
+
+  fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
+
+#undef m
+}
+
+CGLM_INLINE
+void
+glm_versor_print(versor            vec,
                  FILE * __restrict ostream) {
   int i;
 
 #define m 4
 
-  fprintf(ostream, "Versor (float%d):\n\t|", m);
+  fprintf(ostream, "Quaternion (float%d): " CGLM_PRINT_COLOR "\n  (", m);
 
   for (i = 0; i < m; i++) {
-    fprintf(ostream, "%0.4f", vec[i]);
+    if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
-    if (i != m - 1)
+    else
-      fprintf(ostream, "\t");
+      fprintf(ostream, " % g", vec[i]);
   }
 
-  fprintf(ostream, "|\n\n");
+
+  fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
 
 #undef m
 }
@@ -180,24 +302,43 @@ glm_aabb_print(vec3                    bbox[2],
 
 #define m 3
 
-  fprintf(ostream, "AABB (%s):\n", tag ? tag: "float");
+  fprintf(ostream, "AABB (%s): " CGLM_PRINT_COLOR "\n", tag ? tag: "float");
 
   for (i = 0; i < 2; i++) {
-    fprintf(ostream, "\t|");
+    fprintf(ostream, "  (");
     
     for (j = 0; j < m; j++) {
-      fprintf(ostream, "%0.4f", bbox[i][j]);
+      if (bbox[i][j] < CGLM_PRINT_MAX_TO_SHORT)
-
+        fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, bbox[i][j]);
-      if (j != m - 1)
+      else
-        fprintf(ostream, "\t");
+        fprintf(ostream, " % g", bbox[i][j]);
     }
 
-    fprintf(ostream, "|\n");
+    fprintf(ostream, "  )\n");
   }
 
-  fprintf(ostream, "\n");
+  fprintf(ostream, CGLM_PRINT_COLOR_RESET "\n");
 
 #undef m
 }
 
+#else
+
+#include "common.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+
+/* NOOP: Remove print from DEBUG */
+#define glm_mat4_print(v, s) (void)v; (void)s;
+#define glm_mat3_print(v, s) (void)v; (void)s;
+#define glm_mat2_print(v, s) (void)v; (void)s;
+#define glm_vec4_print(v, s) (void)v; (void)s;
+#define glm_vec3_print(v, s) (void)v; (void)s;
+#define glm_ivec3_print(v, s) (void)v; (void)s;
+#define glm_vec2_print(v, s) (void)v; (void)s;
+#define glm_versor_print(v, s) (void)v; (void)s;
+#define glm_aabb_print(v, t, s) (void)v; (void)t; (void)s;
+
+#endif
 #endif /* cglm_io_h */

include/cglm/mat2.h

@@ -0,0 +1,331 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT2_IDENTITY_INIT
+   GLM_MAT2_ZERO_INIT
+   GLM_MAT2_IDENTITY
+   GLM_MAT2_ZERO
+
+ Functions:
+   CGLM_INLINE void  glm_mat2_copy(mat2 mat, mat2 dest)
+   CGLM_INLINE void  glm_mat2_identity(mat2 mat)
+   CGLM_INLINE void  glm_mat2_identity_array(mat2 * restrict mat, size_t count)
+   CGLM_INLINE void  glm_mat2_zero(mat2 mat)
+   CGLM_INLINE void  glm_mat2_mul(mat2 m1, mat2 m2, mat2 dest)
+   CGLM_INLINE void  glm_mat2_transpose_to(mat2 m, mat2 dest)
+   CGLM_INLINE void  glm_mat2_transpose(mat2 m)
+   CGLM_INLINE void  glm_mat2_mulv(mat2 m, vec2 v, vec2 dest)
+   CGLM_INLINE float glm_mat2_trace(mat2 m)
+   CGLM_INLINE void  glm_mat2_scale(mat2 m, float s)
+   CGLM_INLINE float glm_mat2_det(mat2 mat)
+   CGLM_INLINE void  glm_mat2_inv(mat2 mat, mat2 dest)
+   CGLM_INLINE void  glm_mat2_swap_col(mat2 mat, int col1, int col2)
+   CGLM_INLINE void  glm_mat2_swap_row(mat2 mat, int row1, int row2)
+   CGLM_INLINE float glm_mat2_rmc(vec2 r, mat2 m, vec2 c)
+ */
+
+#ifndef cglm_mat2_h
+#define cglm_mat2_h
+
+#include "common.h"
+#include "vec2.h"
+
+#ifdef CGLM_SSE_FP
+#  include "simd/sse2/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}}
+
+/* for C only */
+#define GLM_MAT2_IDENTITY ((mat2)GLM_MAT2_IDENTITY_INIT)
+#define GLM_MAT2_ZERO     ((mat2)GLM_MAT2_ZERO_INIT)
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat2_copy(mat2 mat, mat2 dest) {
+  glm_vec4_ucopy(mat[0], dest[0]);
+}
+
+/*!
+ * @brief make given matrix identity. It is identical with below,
+ *        but it is more easy to do that with this func especially for members
+ *        e.g. glm_mat2_identity(aStruct->aMatrix);
+ *
+ * @code
+ * glm_mat2_copy(GLM_MAT2_IDENTITY, mat); // C only
+ *
+ * // or
+ * mat2 mat = GLM_MAT2_IDENTITY_INIT;
+ * @endcode
+ *
+ * @param[in, out]  mat  destination
+ */
+CGLM_INLINE
+void
+glm_mat2_identity(mat2 mat) {
+  CGLM_ALIGN_MAT mat2 t = GLM_MAT2_IDENTITY_INIT;
+  glm_mat2_copy(t, mat);
+}
+
+/*!
+ * @brief make given matrix array's each element identity matrix
+ *
+ * @param[in, out]  mat   matrix array (must be aligned (16)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of matrices
+ */
+CGLM_INLINE
+void
+glm_mat2_identity_array(mat2 * __restrict mat, size_t count) {
+  CGLM_ALIGN_MAT mat2 t = GLM_MAT2_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_mat2_copy(t, mat[i]);
+  }
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat2_zero(mat2 mat) {
+  CGLM_ALIGN_MAT mat2 t = GLM_MAT2_ZERO_INIT;
+  glm_mat2_copy(t, mat);
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * mat2 m = GLM_MAT2_IDENTITY_INIT;
+ * glm_mat2_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat2_mul(mat2 m1, mat2 m2, mat2 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glm_mat2_mul_sse2(m1, m2, dest);
+#else
+  float a00 = m1[0][0], a01 = m1[0][1],
+        a10 = m1[1][0], a11 = m1[1][1],
+        b00 = m2[0][0], b01 = m2[0][1],
+        b10 = m2[1][0], b11 = m2[1][1];
+
+  dest[0][0] = a00 * b00 + a10 * b01;
+  dest[0][1] = a01 * b00 + a11 * b01;
+  dest[1][0] = a00 * b10 + a10 * b11;
+  dest[1][1] = a01 * b10 + a11 * b11;
+#endif
+}
+
+/*!
+ * @brief transpose mat2 and store in dest
+ *
+ * source matrix will not be transposed unless dest is m
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat2_transpose_to(mat2 m, mat2 dest) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glm_mat2_transp_sse2(m, dest);
+#else
+  dest[0][0] = m[0][0];
+  dest[0][1] = m[1][0];
+  dest[1][0] = m[0][1];
+  dest[1][1] = m[1][1];
+#endif
+}
+
+/*!
+ * @brief tranpose mat2 and store result in same matrix
+ *
+ * @param[in, out] m source and dest
+ */
+CGLM_INLINE
+void
+glm_mat2_transpose(mat2 m) {
+  float tmp;
+  tmp     = m[0][1];
+  m[0][1] = m[1][0];
+  m[1][0] = tmp;
+}
+
+/*!
+ * @brief multiply mat2 with vec2 (column vector) and store in dest vector
+ *
+ * @param[in]  m    mat2 (left)
+ * @param[in]  v    vec2 (right, column vector)
+ * @param[out] dest vec2 (result, column vector)
+ */
+CGLM_INLINE
+void
+glm_mat2_mulv(mat2 m, vec2 v, vec2 dest) {
+  dest[0] = m[0][0] * v[0] + m[1][0] * v[1];
+  dest[1] = m[0][1] * v[0] + m[1][1] * v[1];
+}
+
+/*!
+ * @brief trace of matrix
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat2_trace(mat2 m) {
+  return m[0][0] + m[1][1];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]      s scalar
+ */
+CGLM_INLINE
+void
+glm_mat2_scale(mat2 m, float s) {
+#if defined( __SSE__ ) || defined( __SSE2__ )
+  glmm_store(m[0], _mm_mul_ps(_mm_loadu_ps(m[0]), _mm_set1_ps(s)));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(m[0], vmulq_f32(vld1q_f32(m[0]), vdupq_n_f32(s)));
+#else
+  m[0][0] = m[0][0] * s;
+  m[0][1] = m[0][1] * s;
+  m[1][0] = m[1][0] * s;
+  m[1][1] = m[1][1] * s;
+#endif
+}
+
+/*!
+ * @brief mat2 determinant
+ *
+ * @param[in] mat matrix
+ *
+ * @return determinant
+ */
+CGLM_INLINE
+float
+glm_mat2_det(mat2 mat) {
+  return mat[0][0] * mat[1][1] - mat[1][0] * mat[0][1];
+}
+
+/*!
+ * @brief inverse mat2 and store in dest
+ *
+ * @param[in]  mat  matrix
+ * @param[out] dest inverse matrix
+ */
+CGLM_INLINE
+void
+glm_mat2_inv(mat2 mat, mat2 dest) {
+  float det;
+  float a = mat[0][0], b = mat[0][1],
+        c = mat[1][0], d = mat[1][1];
+
+  det = 1.0f / (a * d - b * c);
+
+  dest[0][0] =  d * det;
+  dest[0][1] = -b * det;
+  dest[1][0] = -c * det;
+  dest[1][1] =  a * det;
+}
+
+/*!
+ * @brief swap two matrix columns
+ *
+ * @param[in,out] mat  matrix
+ * @param[in]     col1 col1
+ * @param[in]     col2 col2
+ */
+CGLM_INLINE
+void
+glm_mat2_swap_col(mat2 mat, int col1, int col2) {
+  float a, b;
+
+  a = mat[col1][0];
+  b = mat[col1][1];
+
+  mat[col1][0] = mat[col2][0];
+  mat[col1][1] = mat[col2][1];
+
+  mat[col2][0] = a;
+  mat[col2][1] = b;
+}
+
+/*!
+ * @brief swap two matrix rows
+ *
+ * @param[in,out] mat  matrix
+ * @param[in]     row1 row1
+ * @param[in]     row2 row2
+ */
+CGLM_INLINE
+void
+glm_mat2_swap_row(mat2 mat, int row1, int row2) {
+  float a, b;
+
+  a = mat[0][row1];
+  b = mat[1][row1];
+
+  mat[0][row1] = mat[0][row2];
+  mat[1][row1] = mat[1][row2];
+
+  mat[0][row2] = a;
+  mat[1][row2] = b;
+}
+
+/*!
+ * @brief helper for  R (row vector) * M (matrix) * C (column vector)
+ *
+ * rmc stands for Row * Matrix * Column
+ *
+ * the result is scalar because R * M = Matrix1x2 (row vector),
+ * then Matrix1x2 * Vec2 (column vector) = Matrix1x1 (Scalar)
+ *
+ * @param[in]  r   row vector or matrix1x2
+ * @param[in]  m   matrix2x2
+ * @param[in]  c   column vector or matrix2x1
+ *
+ * @return scalar value e.g. Matrix1x1
+ */
+CGLM_INLINE
+float
+glm_mat2_rmc(vec2 r, mat2 m, vec2 c) {
+  vec2 tmp;
+  glm_mat2_mulv(m, c, tmp);
+  return glm_vec2_dot(r, tmp);
+}
+
+#endif /* cglm_mat2_h */

include/cglm/mat3.h

@@ -16,15 +16,20 @@
  Functions:
    CGLM_INLINE void  glm_mat3_copy(mat3 mat, mat3 dest);
    CGLM_INLINE void  glm_mat3_identity(mat3 mat);
+   CGLM_INLINE void  glm_mat3_identity_array(mat3 * restrict mat, size_t count);
+   CGLM_INLINE void  glm_mat3_zero(mat3 mat);
    CGLM_INLINE void  glm_mat3_mul(mat3 m1, mat3 m2, mat3 dest);
    CGLM_INLINE void  glm_mat3_transpose_to(mat3 m, mat3 dest);
    CGLM_INLINE void  glm_mat3_transpose(mat3 m);
    CGLM_INLINE void  glm_mat3_mulv(mat3 m, vec3 v, vec3 dest);
+   CGLM_INLINE float glm_mat3_trace(mat3 m);
+   CGLM_INLINE void  glm_mat3_quat(mat3 m, versor dest);
    CGLM_INLINE void  glm_mat3_scale(mat3 m, float s);
    CGLM_INLINE float glm_mat3_det(mat3 mat);
    CGLM_INLINE void  glm_mat3_inv(mat3 mat, mat3 dest);
    CGLM_INLINE void  glm_mat3_swap_col(mat3 mat, int col1, int col2);
    CGLM_INLINE void  glm_mat3_swap_row(mat3 mat, int row1, int row2);
+   CGLM_INLINE float glm_mat3_rmc(vec3 r, mat3 m, vec3 c);
  */
 
 #ifndef cglm_mat3_h
@@ -61,7 +66,17 @@
 CGLM_INLINE
 void
 glm_mat3_copy(mat3 mat, mat3 dest) {
-  glm__memcpy(float, dest, mat, sizeof(mat3));
+  dest[0][0] = mat[0][0];
+  dest[0][1] = mat[0][1];
+  dest[0][2] = mat[0][2];
+
+  dest[1][0] = mat[1][0];
+  dest[1][1] = mat[1][1];
+  dest[1][2] = mat[1][2];
+
+  dest[2][0] = mat[2][0];
+  dest[2][1] = mat[2][1];
+  dest[2][2] = mat[2][2];
 }
 
 /*!
@@ -81,7 +96,38 @@ glm_mat3_copy(mat3 mat, mat3 dest) {
 CGLM_INLINE
 void
 glm_mat3_identity(mat3 mat) {
-  mat3 t = GLM_MAT3_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat3 t = GLM_MAT3_IDENTITY_INIT;
+  glm_mat3_copy(t, mat);
+}
+
+/*!
+ * @brief make given matrix array's each element identity matrix
+ *
+ * @param[in, out]  mat   matrix array (must be aligned (16/32)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of matrices
+ */
+CGLM_INLINE
+void
+glm_mat3_identity_array(mat3 * __restrict mat, size_t count) {
+  CGLM_ALIGN_MAT mat3 t = GLM_MAT3_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_mat3_copy(t, mat[i]);
+  }
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat3_zero(mat3 mat) {
+  CGLM_ALIGN_MAT mat3 t = GLM_MAT3_ZERO_INIT;
   glm_mat3_copy(t, mat);
 }
 
@@ -155,7 +201,7 @@ glm_mat3_transpose_to(mat3 m, mat3 dest) {
 CGLM_INLINE
 void
 glm_mat3_transpose(mat3 m) {
-  mat3 tmp;
+  CGLM_ALIGN_MAT mat3 tmp;
 
   tmp[0][1] = m[1][0];
   tmp[0][2] = m[2][0];
@@ -182,16 +228,30 @@ glm_mat3_transpose(mat3 m) {
 CGLM_INLINE
 void
 glm_mat3_mulv(mat3 m, vec3 v, vec3 dest) {
-  dest[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2];
+  vec3 res;
-  dest[1] = m[0][1] * v[0] + m[1][1] * v[1] + m[2][1] * v[2];
+  res[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2];
-  dest[2] = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2];
+  res[1] = m[0][1] * v[0] + m[1][1] * v[1] + m[2][1] * v[2];
+  res[2] = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2];
+  glm_vec3_copy(res, dest);
 }
 
+/*!
+ * @brief trace of matrix
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat3_trace(mat3 m) {
+  return m[0][0] + m[1][1] + m[2][2];
+}
 
 /*!
- * @brief convert mat4's rotation part to quaternion
+ * @brief convert mat3 to quaternion
  *
- * @param[in]  m    left matrix
+ * @param[in]  m    rotation matrix
  * @param[out] dest destination quaternion
  */
 CGLM_INLINE
@@ -310,9 +370,9 @@ CGLM_INLINE
 void
 glm_mat3_swap_col(mat3 mat, int col1, int col2) {
   vec3 tmp;
-  glm_vec_copy(mat[col1], tmp);
+  glm_vec3_copy(mat[col1], tmp);
-  glm_vec_copy(mat[col2], mat[col1]);
+  glm_vec3_copy(mat[col2], mat[col1]);
-  glm_vec_copy(tmp, mat[col2]);
+  glm_vec3_copy(tmp, mat[col2]);
 }
 
 /*!
@@ -339,4 +399,26 @@ glm_mat3_swap_row(mat3 mat, int row1, int row2) {
   mat[2][row2] = tmp[2];
 }
 
+/*!
+ * @brief helper for  R (row vector) * M (matrix) * C (column vector)
+ *
+ * rmc stands for Row * Matrix * Column
+ *
+ * the result is scalar because R * M = Matrix1x3 (row vector),
+ * then Matrix1x3 * Vec3 (column vector) = Matrix1x1 (Scalar)
+ *
+ * @param[in]  r   row vector or matrix1x3
+ * @param[in]  m   matrix3x3
+ * @param[in]  c   column vector or matrix3x1
+ *
+ * @return scalar value e.g. Matrix1x1
+ */
+CGLM_INLINE
+float
+glm_mat3_rmc(vec3 r, mat3 m, vec3 c) {
+  vec3 tmp;
+  glm_mat3_mulv(m, c, tmp);
+  return glm_vec3_dot(r, tmp);
+}
+
 #endif /* cglm_mat3_h */

include/cglm/mat4.h

@@ -16,13 +16,13 @@
    GLM_MAT4_ZERO_INIT
    GLM_MAT4_IDENTITY
    GLM_MAT4_ZERO
-   glm_mat4_udup(mat, dest)
-   glm_mat4_dup(mat, dest)
 
  Functions:
    CGLM_INLINE void  glm_mat4_ucopy(mat4 mat, mat4 dest);
    CGLM_INLINE void  glm_mat4_copy(mat4 mat, mat4 dest);
    CGLM_INLINE void  glm_mat4_identity(mat4 mat);
+   CGLM_INLINE void  glm_mat4_identity_array(mat4 * restrict mat, size_t count);
+   CGLM_INLINE void  glm_mat4_zero(mat4 mat);
    CGLM_INLINE void  glm_mat4_pick3(mat4 mat, mat3 dest);
    CGLM_INLINE void  glm_mat4_pick3t(mat4 mat, mat3 dest);
    CGLM_INLINE void  glm_mat4_ins3(mat3 mat, mat4 dest);
@@ -30,6 +30,9 @@
    CGLM_INLINE void  glm_mat4_mulN(mat4 *matrices[], int len, mat4 dest);
    CGLM_INLINE void  glm_mat4_mulv(mat4 m, vec4 v, vec4 dest);
    CGLM_INLINE void  glm_mat4_mulv3(mat4 m, vec3 v, vec3 dest);
+   CGLM_INLINE float glm_mat4_trace(mat4 m);
+   CGLM_INLINE float glm_mat4_trace3(mat4 m);
+   CGLM_INLINE void  glm_mat4_quat(mat4 m, versor dest) ;
    CGLM_INLINE void  glm_mat4_transpose_to(mat4 m, mat4 dest);
    CGLM_INLINE void  glm_mat4_transpose(mat4 m);
    CGLM_INLINE void  glm_mat4_scale_p(mat4 m, float s);
@@ -39,6 +42,7 @@
    CGLM_INLINE void  glm_mat4_inv_fast(mat4 mat, mat4 dest);
    CGLM_INLINE void  glm_mat4_swap_col(mat4 mat, int col1, int col2);
    CGLM_INLINE void  glm_mat4_swap_row(mat4 mat, int row1, int row2);
+   CGLM_INLINE float glm_mat4_rmc(vec4 r, mat4 m, vec4 c);
  */
 
 #ifndef cglm_mat_h
@@ -97,7 +101,15 @@
 CGLM_INLINE
 void
 glm_mat4_ucopy(mat4 mat, mat4 dest) {
-  glm__memcpy(float, dest, mat, sizeof(mat4));
+  dest[0][0] = mat[0][0];  dest[1][0] = mat[1][0];
+  dest[0][1] = mat[0][1];  dest[1][1] = mat[1][1];
+  dest[0][2] = mat[0][2];  dest[1][2] = mat[1][2];
+  dest[0][3] = mat[0][3];  dest[1][3] = mat[1][3];
+
+  dest[2][0] = mat[2][0];  dest[3][0] = mat[3][0];
+  dest[2][1] = mat[2][1];  dest[3][1] = mat[3][1];
+  dest[2][2] = mat[2][2];  dest[3][2] = mat[3][2];
+  dest[2][3] = mat[2][3];  dest[3][3] = mat[3][3];
 }
 
 /*!
@@ -117,6 +129,11 @@ glm_mat4_copy(mat4 mat, mat4 dest) {
   glmm_store(dest[1], glmm_load(mat[1]));
   glmm_store(dest[2], glmm_load(mat[2]));
   glmm_store(dest[3], glmm_load(mat[3]));
+#elif defined(CGLM_NEON_FP)
+  vst1q_f32(dest[0], vld1q_f32(mat[0]));
+  vst1q_f32(dest[1], vld1q_f32(mat[1]));
+  vst1q_f32(dest[2], vld1q_f32(mat[2]));
+  vst1q_f32(dest[3], vld1q_f32(mat[3]));
 #else
   glm_mat4_ucopy(mat, dest);
 #endif
@@ -139,7 +156,38 @@ glm_mat4_copy(mat4 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_identity(mat4 mat) {
-  mat4 t = GLM_MAT4_IDENTITY_INIT;
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  glm_mat4_copy(t, mat);
+}
+
+/*!
+ * @brief make given matrix array's each element identity matrix
+ *
+ * @param[in, out]  mat   matrix array (must be aligned (16/32)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of matrices
+ */
+CGLM_INLINE
+void
+glm_mat4_identity_array(mat4 * __restrict mat, size_t count) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_mat4_copy(t, mat[i]);
+  }
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat4_zero(mat4 mat) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_ZERO_INIT;
   glm_mat4_copy(t, mat);
 }
 
@@ -232,7 +280,7 @@ glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest) {
   glm_mat4_mul_avx(m1, m2, dest);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_mul_sse2(m1, m2, dest);
-#elif defined( __ARM_NEON_FP )
+#elif defined(CGLM_NEON_FP)
   glm_mat4_mul_neon(m1, m2, dest);
 #else
   float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2], a03 = m1[0][3],
@@ -310,6 +358,8 @@ void
 glm_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_mulv_sse2(m, v, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_mat4_mulv_neon(m, v, dest);
 #else
   vec4 res;
   res[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2] + m[3][0] * v[3];
@@ -320,10 +370,36 @@ glm_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
 #endif
 }
 
+/*!
+ * @brief trace of matrix
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat4_trace(mat4 m) {
+  return m[0][0] + m[1][1] + m[2][2] + m[3][3];
+}
+
+/*!
+ * @brief trace of matrix (rotation part)
+ *
+ * sum of the elements on the main diagonal from upper left to the lower right
+ *
+ * @param[in]  m matrix
+ */
+CGLM_INLINE
+float
+glm_mat4_trace3(mat4 m) {
+  return m[0][0] + m[1][1] + m[2][2];
+}
+
 /*!
  * @brief convert mat4's rotation part to quaternion
  *
- * @param[in]  m    left matrix
+ * @param[in]  m    affine matrix
  * @param[out] dest destination quaternion
  */
 CGLM_INLINE
@@ -370,20 +446,23 @@ glm_mat4_quat(mat4 m, versor dest) {
 }
 
 /*!
- * @brief multiply vector with mat4's mat3 part(rotation)
+ * @brief multiply vector with mat4
+ *
+ * actually the result is vec4, after multiplication the last component
+ * is trimmed. if you need it don't use this func.
  *
  * @param[in]  m    mat4(affine transform)
  * @param[in]  v    vec3
- * @param[out] dest vec3
+ * @param[in]  last 4th item to make it vec4
+ * @param[out] dest result vector (vec3)
  */
 CGLM_INLINE
 void
-glm_mat4_mulv3(mat4 m, vec3 v, vec3 dest) {
+glm_mat4_mulv3(mat4 m, vec3 v, float last, vec3 dest) {
-  vec3 res;
+  vec4 res;
-  res[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2];
+  glm_vec4(v, last, res);
-  res[1] = m[0][1] * v[0] + m[1][1] * v[1] + m[2][1] * v[2];
+  glm_mat4_mulv(m, res, res);
-  res[2] = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2];
+  glm_vec3(res, dest);
-  glm_vec_copy(res, dest);
 }
 
 /*!
@@ -399,6 +478,8 @@ void
 glm_mat4_transpose_to(mat4 m, mat4 dest) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_transp_sse2(m, dest);
+#elif defined(CGLM_NEON_FP)
+  glm_mat4_transp_neon(m, dest);
 #else
   dest[0][0] = m[0][0]; dest[1][0] = m[0][1];
   dest[0][1] = m[1][0]; dest[1][1] = m[1][1];
@@ -421,12 +502,12 @@ void
 glm_mat4_transpose(mat4 m) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_transp_sse2(m, m);
+#elif defined(CGLM_NEON_FP)
+  glm_mat4_transp_neon(m, m);
 #else
   mat4 d;
-
   glm_mat4_transpose_to(m, d);
-
+  glm_mat4_ucopy(d, m);
-  glm__memcpy(float, m, d, sizeof(mat4));
 #endif
 }
 
@@ -458,8 +539,12 @@ 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);
 #else
   glm_mat4_scale_p(m, s);
 #endif
@@ -586,7 +671,7 @@ glm_mat4_inv_fast(mat4 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_swap_col(mat4 mat, int col1, int col2) {
-  vec4 tmp;
+  CGLM_ALIGN(16) vec4 tmp;
   glm_vec4_copy(mat[col1], tmp);
   glm_vec4_copy(mat[col2], mat[col1]);
   glm_vec4_copy(tmp, mat[col2]);
@@ -602,7 +687,7 @@ glm_mat4_swap_col(mat4 mat, int col1, int col2) {
 CGLM_INLINE
 void
 glm_mat4_swap_row(mat4 mat, int row1, int row2) {
-  vec4 tmp;
+  CGLM_ALIGN(16) vec4 tmp;
   tmp[0] = mat[0][row1];
   tmp[1] = mat[1][row1];
   tmp[2] = mat[2][row1];
@@ -619,4 +704,26 @@ glm_mat4_swap_row(mat4 mat, int row1, int row2) {
   mat[3][row2] = tmp[3];
 }
 
+/*!
+ * @brief helper for  R (row vector) * M (matrix) * C (column vector)
+ *
+ * rmc stands for Row * Matrix * Column
+ *
+ * the result is scalar because R * M = Matrix1x4 (row vector),
+ * then Matrix1x4 * Vec4 (column vector) = Matrix1x1 (Scalar)
+ *
+ * @param[in]  r   row vector or matrix1x4
+ * @param[in]  m   matrix4x4
+ * @param[in]  c   column vector or matrix4x1
+ *
+ * @return scalar value e.g. B(s)
+ */
+CGLM_INLINE
+float
+glm_mat4_rmc(vec4 r, mat4 m, vec4 c) {
+  vec4 tmp;
+  glm_mat4_mulv(m, c, tmp);
+  return glm_vec4_dot(r, tmp);
+}
+
 #endif /* cglm_mat_h */

include/cglm/plane.h

@@ -25,12 +25,19 @@
 /*!
  * @brief normalizes a plane
  *
- * @param[in, out] plane pnale to normalize
+ * @param[in, out] plane plane to normalize
  */
 CGLM_INLINE
 void
 glm_plane_normalize(vec4 plane) {
-  glm_vec4_scale(plane, 1.0f / glm_vec_norm(plane), plane);
+  float norm;
+  
+  if ((norm = glm_vec3_norm(plane)) == 0.0f) {
+    glm_vec4_zero(plane);
+    return;
+  }
+  
+  glm_vec4_scale(plane, 1.0f / norm, plane);
 }
 
 #endif /* cglm_plane_h */

include/cglm/project.h

@@ -8,6 +8,7 @@
 #ifndef cglm_project_h
 #define cglm_project_h
 
+#include "common.h"
 #include "vec3.h"
 #include "vec4.h"
 #include "mat4.h"
@@ -100,7 +101,7 @@ glm_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
 CGLM_INLINE
 void
 glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
-  vec4 pos4, vone = GLM_VEC4_ONE_INIT;
+  CGLM_ALIGN(16) vec4 pos4, vone = GLM_VEC4_ONE_INIT;
 
   glm_vec4(pos, 1.0f, pos4);
 

include/cglm/quat.h

@@ -19,7 +19,7 @@
    CGLM_INLINE float glm_quat_norm(versor q);
    CGLM_INLINE void glm_quat_normalize(versor q);
    CGLM_INLINE void glm_quat_normalize_to(versor q, versor dest);
-   CGLM_INLINE float glm_quat_dot(versor q1, versor q2);
+   CGLM_INLINE float glm_quat_dot(versor p, versor q);
    CGLM_INLINE void glm_quat_conjugate(versor q, versor dest);
    CGLM_INLINE void glm_quat_inv(versor q, versor dest);
    CGLM_INLINE void glm_quat_add(versor p, versor q, versor dest);
@@ -29,13 +29,14 @@
    CGLM_INLINE void glm_quat_imagn(versor q, vec3 dest);
    CGLM_INLINE float glm_quat_imaglen(versor q);
    CGLM_INLINE float glm_quat_angle(versor q);
-   CGLM_INLINE void glm_quat_axis(versor q, versor dest);
+   CGLM_INLINE void glm_quat_axis(versor q, vec3 dest);
    CGLM_INLINE void glm_quat_mul(versor p, versor q, versor dest);
    CGLM_INLINE void glm_quat_mat4(versor q, mat4 dest);
    CGLM_INLINE void glm_quat_mat4t(versor q, mat4 dest);
    CGLM_INLINE void glm_quat_mat3(versor q, mat3 dest);
    CGLM_INLINE void glm_quat_mat3t(versor q, mat3 dest);
    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_look(vec3 eye, versor ori, mat4 dest);
    CGLM_INLINE void glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest);
@@ -62,10 +63,6 @@
 #  include "simd/sse2/quat.h"
 #endif
 
-CGLM_INLINE
-void
-glm_mat4_identity(mat4 mat);
-
 CGLM_INLINE
 void
 glm_mat4_mulv(mat4 m, vec4 v, vec4 dest);
@@ -99,10 +96,29 @@ glm_translate(mat4 m, vec3 v);
 CGLM_INLINE
 void
 glm_quat_identity(versor q) {
-  versor v = GLM_QUAT_IDENTITY_INIT;
+  CGLM_ALIGN(16) versor v = GLM_QUAT_IDENTITY_INIT;
   glm_vec4_copy(v, q);
 }
 
+/*!
+ * @brief make given quaternion array's each element identity quaternion
+ *
+ * @param[in, out]  q     quat array (must be aligned (16)
+ *                        if alignment is not disabled)
+ *
+ * @param[in]       count count of quaternions
+ */
+CGLM_INLINE
+void
+glm_quat_identity_array(versor * __restrict q, size_t count) {
+  CGLM_ALIGN(16) versor v = GLM_QUAT_IDENTITY_INIT;
+  size_t i;
+
+  for (i = 0; i < count; i++) {
+    glm_vec4_copy(v, q[i]);
+  }
+}
+
 /*!
  * @brief inits quaterion with raw values
  *
@@ -131,7 +147,7 @@ glm_quat_init(versor q, float x, float y, float z, float w) {
 CGLM_INLINE
 void
 glm_quatv(versor q, float angle, vec3 axis) {
-  vec3  k;
+  CGLM_ALIGN(8) vec3 k;
   float a, c, s;
 
   a = angle * 0.5f;
@@ -158,7 +174,7 @@ glm_quatv(versor q, float angle, vec3 axis) {
 CGLM_INLINE
 void
 glm_quat(versor q, float angle, float x, float y, float z) {
-  vec3 axis = {x, y, z};
+  CGLM_ALIGN(8) vec3 axis = {x, y, z};
   glm_quatv(q, angle, axis);
 }
 
@@ -199,7 +215,7 @@ glm_quat_normalize_to(versor q, versor dest) {
   float  dot;
 
   x0   = glmm_load(q);
-  xdot = glmm_dot(x0, x0);
+  xdot = glmm_vdot(x0, x0);
   dot  = _mm_cvtss_f32(xdot);
 
   if (dot <= 0.0f) {
@@ -214,7 +230,7 @@ glm_quat_normalize_to(versor q, versor dest) {
   dot = glm_vec4_norm2(q);
 
   if (dot <= 0.0f) {
-    glm_quat_identity(q);
+    glm_quat_identity(dest);
     return;
   }
 
@@ -254,7 +270,7 @@ glm_quat_dot(versor p, versor q) {
 CGLM_INLINE
 void
 glm_quat_conjugate(versor q, versor dest) {
-  glm_vec4_flipsign_to(q, dest);
+  glm_vec4_negate_to(q, dest);
   dest[3] = -dest[3];
 }
 
@@ -267,7 +283,7 @@ glm_quat_conjugate(versor q, versor dest) {
 CGLM_INLINE
 void
 glm_quat_inv(versor q, versor dest) {
-  versor conj;
+  CGLM_ALIGN(16) versor conj;
   glm_quat_conjugate(q, conj);
   glm_vec4_scale(conj, 1.0f / glm_vec4_norm2(q), dest);
 }
@@ -342,7 +358,7 @@ glm_quat_imagn(versor q, vec3 dest) {
 CGLM_INLINE
 float
 glm_quat_imaglen(versor q) {
-  return glm_vec_norm(q);
+  return glm_vec3_norm(q);
 }
 
 /*!
@@ -369,7 +385,7 @@ glm_quat_angle(versor q) {
  */
 CGLM_INLINE
 void
-glm_quat_axis(versor q, versor dest) {
+glm_quat_axis(versor q, vec3 dest) {
   glm_quat_imagn(q, dest);
 }
 
@@ -582,7 +598,7 @@ glm_quat_mat3t(versor q, mat3 dest) {
  *
  * @param[in]   from  from
  * @param[in]   to    to
- * @param[in]   t     interpolant (amount) clamped between 0 and 1
+ * @param[in]   t     interpolant (amount)
  * @param[out]  dest  result quaternion
  */
 CGLM_INLINE
@@ -591,6 +607,21 @@ glm_quat_lerp(versor from, versor to, float t, versor dest) {
   glm_vec4_lerp(from, to, t, dest);
 }
 
+/*!
+ * @brief interpolates between two quaternions
+ *        using linear interpolation (LERP)
+ *
+ * @param[in]   from  from
+ * @param[in]   to    to
+ * @param[in]   t     interpolant (amount) clamped between 0 and 1
+ * @param[out]  dest  result quaternion
+ */
+CGLM_INLINE
+void
+glm_quat_lerpc(versor from, versor to, float t, versor dest) {
+  glm_vec4_lerpc(from, to, t, dest);
+}
+
 /*!
  * @brief interpolates between two quaternions
  *        using spherical linear interpolation (SLERP)
@@ -603,7 +634,7 @@ glm_quat_lerp(versor from, versor to, float t, versor dest) {
 CGLM_INLINE
 void
 glm_quat_slerp(versor from, versor to, float t, versor dest) {
-  vec4  q1, q2;
+  CGLM_ALIGN(16) vec4 q1, q2;
   float cosTheta, sinTheta, angle;
 
   cosTheta = glm_quat_dot(from, to);
@@ -615,7 +646,7 @@ glm_quat_slerp(versor from, versor to, float t, versor dest) {
   }
 
   if (cosTheta < 0.0f) {
-    glm_vec4_flipsign(q1);
+    glm_vec4_negate(q1);
     cosTheta = -cosTheta;
   }
 
@@ -646,47 +677,35 @@ glm_quat_slerp(versor from, versor to, float t, versor dest) {
 CGLM_INLINE
 void
 glm_quat_look(vec3 eye, versor ori, mat4 dest) {
-  vec4 t;
-
   /* orientation */
   glm_quat_mat4t(ori, dest);
 
   /* translate */
-  glm_vec4(eye, 1.0f, t);
+  glm_mat4_mulv3(dest, eye, 1.0f, dest[3]);
-  glm_mat4_mulv(dest, t, t);
+  glm_vec3_negate(dest[3]);
-  glm_vec_flipsign_to(t, dest[3]);
 }
 
 /*!
  * @brief creates look rotation quaternion
  *
  * @param[in]   dir   direction to look
- * @param[in]   fwd   forward vector
  * @param[in]   up    up vector
  * @param[out]  dest  destination quaternion
  */
 CGLM_INLINE
 void
-glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest) {
+glm_quat_for(vec3 dir, vec3 up, versor dest) {
-  vec3  axis;
+  CGLM_ALIGN_MAT mat3 m;
-  float dot, angle;
 
-  dot = glm_vec_dot(dir, fwd);
+  glm_vec3_normalize_to(dir, m[2]); 
-  if (fabsf(dot + 1.0f)  < 0.000001f) {
-    glm_quat_init(dest, up[0], up[1], up[2], CGLM_PI);
-    return;
-  }
 
-  if (fabsf(dot - 1.0f) < 0.000001f) {
+  /* No need to negate in LH, but we use RH here */
-    glm_quat_identity(dest);
+  glm_vec3_negate(m[2]);
-    return;
-  }
   
-  angle = acosf(dot);
+  glm_vec3_crossn(up, m[2], m[0]);
-  glm_cross(fwd, dir, axis);
+  glm_vec3_cross(m[2], m[0], m[1]);
-  glm_normalize(axis);
 
-  glm_quatv(dest, angle, axis);
+  glm_mat3_quat(m, dest);
 }
 
 /*!
@@ -695,16 +714,15 @@ glm_quat_for(vec3 dir, vec3 fwd, vec3 up, versor dest) {
  *
  * @param[in]   from  source point
  * @param[in]   to    destination point
- * @param[in]   fwd   forward vector
  * @param[in]   up    up vector
  * @param[out]  dest  destination quaternion
  */
 CGLM_INLINE
 void
-glm_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest) {
+glm_quat_forp(vec3 from, vec3 to, vec3 up, versor dest) {
-  vec3 dir;
+  CGLM_ALIGN(8) vec3 dir;
-  glm_vec_sub(to, from, dir);
+  glm_vec3_sub(to, from, dir);
-  glm_quat_for(dir, fwd, up, dest);
+  glm_quat_for(dir, up, dest);
 }
 
 /*!
@@ -717,22 +735,22 @@ glm_quat_forp(vec3 from, vec3 to, vec3 fwd, vec3 up, versor dest) {
 CGLM_INLINE
 void
 glm_quat_rotatev(versor q, vec3 v, vec3 dest) {
-  versor p;
+  CGLM_ALIGN(16) versor p;
-  vec3   u, v1, v2;
+  CGLM_ALIGN(8)  vec3   u, v1, v2;
-  float  s;
+  float s;
 
   glm_quat_normalize_to(q, p);
   glm_quat_imag(p, u);
   s = glm_quat_real(p);
 
-  glm_vec_scale(u, 2.0f * glm_vec_dot(u, v), v1);
+  glm_vec3_scale(u, 2.0f * glm_vec3_dot(u, v), v1);
-  glm_vec_scale(v, s * s - glm_vec_dot(u, u), v2);
+  glm_vec3_scale(v, s * s - glm_vec3_dot(u, u), v2);
-  glm_vec_add(v1, v2, v1);
+  glm_vec3_add(v1, v2, v1);
 
-  glm_vec_cross(u, v, v2);
+  glm_vec3_cross(u, v, v2);
-  glm_vec_scale(v2, 2.0f * s, v2);
+  glm_vec3_scale(v2, 2.0f * s, v2);
 
-  glm_vec_add(v1, v2, dest);
+  glm_vec3_add(v1, v2, dest);
 }
 
 /*!
@@ -745,7 +763,7 @@ glm_quat_rotatev(versor q, vec3 v, vec3 dest) {
 CGLM_INLINE
 void
 glm_quat_rotate(mat4 m, versor q, mat4 dest) {
-  mat4 rot;
+  CGLM_ALIGN_MAT mat4 rot;
   glm_quat_mat4(q, rot);
   glm_mul_rot(m, rot, dest);
 }
@@ -760,9 +778,9 @@ glm_quat_rotate(mat4 m, versor q, mat4 dest) {
 CGLM_INLINE
 void
 glm_quat_rotate_at(mat4 m, versor q, vec3 pivot) {
-  vec3 pivotInv;
+  CGLM_ALIGN(8) vec3 pivotInv;
 
-  glm_vec_inv_to(pivot, pivotInv);
+  glm_vec3_negate_to(pivot, pivotInv);
 
   glm_translate(m, pivot);
   glm_quat_rotate(m, q, m);
@@ -784,12 +802,11 @@ glm_quat_rotate_at(mat4 m, versor q, vec3 pivot) {
 CGLM_INLINE
 void
 glm_quat_rotate_atm(mat4 m, versor q, vec3 pivot) {
-  vec3 pivotInv;
+  CGLM_ALIGN(8) vec3 pivotInv;
 
-  glm_vec_inv_to(pivot, pivotInv);
+  glm_vec3_negate_to(pivot, pivotInv);
 
-  glm_mat4_identity(m);
+  glm_translate_make(m, pivot);
-  glm_vec_copy(pivot, m[3]);
   glm_quat_rotate(m, q, m);
   glm_translate(m, pivotInv);
 }

include/cglm/ray.h

@@ -0,0 +1,77 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE bool glm_line_triangle_intersect(vec3   origin,
+                                                vec3   direction,
+                                                vec3   v0,
+                                                vec3   v1,
+                                                vec3   v2,
+                                                float *d);
+*/
+
+#ifndef cglm_ray_h
+#define cglm_ray_h
+
+#include "vec3.h"
+
+/*!
+ * @brief Möller–Trumbore ray-triangle intersection algorithm
+ * 
+ * @param[in] origin         origin of ray
+ * @param[in] direction      direction of ray
+ * @param[in] v0             first vertex of triangle
+ * @param[in] v1             second vertex of triangle
+ * @param[in] v2             third vertex of triangle
+ * @param[in, out] d         distance to intersection
+ * @return whether there is intersection
+ */
+
+CGLM_INLINE
+bool
+glm_ray_triangle(vec3   origin,
+                 vec3   direction,
+                 vec3   v0,
+                 vec3   v1,
+                 vec3   v2,
+                 float *d) {
+  vec3        edge1, edge2, p, t, q;
+  float       det, inv_det, u, v, dist;
+  const float epsilon = 0.000001f;
+
+  glm_vec3_sub(v1, v0, edge1);
+  glm_vec3_sub(v2, v0, edge2);
+  glm_vec3_cross(direction, edge2, p);
+
+  det = glm_vec3_dot(edge1, p);
+  if (det > -epsilon && det < epsilon)
+    return false;
+
+  inv_det = 1.0f / det;
+  
+  glm_vec3_sub(origin, v0, t);
+
+  u = inv_det * glm_vec3_dot(t, p);
+  if (u < 0.0f || u > 1.0f)
+    return false;
+
+  glm_vec3_cross(t, edge1, q);
+
+  v = inv_det * glm_vec3_dot(direction, q);
+  if (v < 0.0f || u + v > 1.0f)
+    return false;
+
+  dist = inv_det * glm_vec3_dot(edge2, q);
+
+  if (d)
+    *d = dist;
+
+  return dist > epsilon;
+}
+
+#endif

include/cglm/simd/arm.h

@@ -0,0 +1,119 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_simd_arm_h
+#define cglm_simd_arm_h
+#include "intrin.h"
+#ifdef CGLM_SIMD_ARM
+
+#define glmm_load(p)      vld1q_f32(p)
+#define glmm_store(p, a)  vst1q_f32(p, a)
+
+static inline
+float32x4_t
+glmm_abs(float32x4_t v) {
+  return vabsq_f32(v);
+}
+
+static inline
+float
+glmm_hadd(float32x4_t v) {
+#if defined(__aarch64__)
+  return vaddvq_f32(v);
+#else
+  v = vaddq_f32(v, vrev64q_f32(v));
+  v = vaddq_f32(v, vcombine_f32(vget_high_f32(v), vget_low_f32(v)));
+  return vgetq_lane_f32(v, 0);
+#endif
+}
+
+static inline
+float
+glmm_hmin(float32x4_t v) {
+  float32x2_t t;
+  t = vpmin_f32(vget_low_f32(v), vget_high_f32(v));
+  t = vpmin_f32(t, t);
+  return vget_lane_f32(t, 0);
+}
+
+static inline
+float
+glmm_hmax(float32x4_t v) {
+  float32x2_t t;
+  t = vpmax_f32(vget_low_f32(v), vget_high_f32(v));
+  t = vpmax_f32(t, t);
+  return vget_lane_f32(t, 0);
+}
+
+static inline
+float
+glmm_dot(float32x4_t a, float32x4_t b) {
+  return glmm_hadd(vmulq_f32(a, b));
+}
+
+static inline
+float
+glmm_norm(float32x4_t a) {
+  return sqrtf(glmm_dot(a, a));
+}
+
+static inline
+float
+glmm_norm2(float32x4_t a) {
+  return glmm_dot(a, a);
+}
+
+static inline
+float
+glmm_norm_one(float32x4_t a) {
+  return glmm_hadd(glmm_abs(a));
+}
+
+static inline
+float
+glmm_norm_inf(float32x4_t a) {
+  return glmm_hmax(glmm_abs(a));
+}
+
+static inline
+float32x4_t
+glmm_fmadd(float32x4_t a, float32x4_t b, float32x4_t c) {
+#if defined(__aarch64__)
+  return vfmaq_f32(c, a, b);
+#else
+  return vmlaq_f32(c, a, b);
+#endif
+}
+
+static inline
+float32x4_t
+glmm_fnmadd(float32x4_t a, float32x4_t b, float32x4_t c) {
+#if defined(__aarch64__)
+  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 defined(__aarch64__)
+  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 */

include/cglm/simd/avx/affine.h

@@ -27,21 +27,24 @@ glm_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
   y2 = glmm_load256(m1[0]); /* h g f e d c b a */
   y3 = glmm_load256(m1[2]); /* p o n m l k j i */
 
-  y4 = _mm256_permute2f128_ps(y2, y2, 0b00000011); /* d c b a h g f e */
+  /* 0x03: 0b00000011 */
-  y5 = _mm256_permute2f128_ps(y3, y3, 0b00000000); /* l k j i l k j i */
+  y4 = _mm256_permute2f128_ps(y2, y2, 0x03); /* d c b a h g f e */
+  y5 = _mm256_permute2f128_ps(y3, y3, 0x03); /* l k j i p o n m */
 
   /* f f f f a a a a */
-  /* g g g g c c c c */
+  /* h h h h c c c c */
   /* e e e e b b b b */
-  y7 = _mm256_permute_ps(y0, 0b10101010);
+  /* g g g g d d d d */
   y6 = _mm256_permutevar_ps(y0, _mm256_set_epi32(1, 1, 1, 1, 0, 0, 0, 0));
+  y7 = _mm256_permutevar_ps(y0, _mm256_set_epi32(3, 3, 3, 3, 2, 2, 2, 2));
   y8 = _mm256_permutevar_ps(y0, _mm256_set_epi32(0, 0, 0, 0, 1, 1, 1, 1));
+  y9 = _mm256_permutevar_ps(y0, _mm256_set_epi32(2, 2, 2, 2, 3, 3, 3, 3));
 
   glmm_store256(dest[0],
                 _mm256_add_ps(_mm256_add_ps(_mm256_mul_ps(y2, y6),
-                                            _mm256_mul_ps(y4, y8)),
+                                            _mm256_mul_ps(y3, y7)),
-                              _mm256_mul_ps(y5, y7)));
+                              _mm256_add_ps(_mm256_mul_ps(y4, y8),
-
+                                            _mm256_mul_ps(y5, y9))));
 
   /* n n n n i i i i */
   /* p p p p k k k k */

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) {
@@ -27,8 +37,9 @@ glm_mat4_mul_avx(mat4 m1, mat4 m2, mat4 dest) {
   y2 = glmm_load256(m1[0]); /* h g f e d c b a */
   y3 = glmm_load256(m1[2]); /* p o n m l k j i */
 
-  y4 = _mm256_permute2f128_ps(y2, y2, 0b00000011); /* d c b a h g f e */
+  /* 0x03: 0b00000011 */
-  y5 = _mm256_permute2f128_ps(y3, y3, 0b00000011); /* l k j i p o n m */
+  y4 = _mm256_permute2f128_ps(y2, y2, 0x03); /* d c b a h g f e */
+  y5 = _mm256_permute2f128_ps(y3, y3, 0x03); /* l k j i p o n m */
 
   /* f f f f a a a a */
   /* h h h h c c c c */

include/cglm/simd/intrin.h

@@ -27,90 +27,64 @@
 #if defined( __SSE__ ) || defined( __SSE2__ )
 #  include <xmmintrin.h>
 #  include <emmintrin.h>
-
-/* OPTIONAL: You may save some instructions but latency (not sure) */
-#ifdef CGLM_USE_INT_DOMAIN
-#  define glmm_shuff1(xmm, z, y, x, w)                                        \
-     _mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(xmm),                \
-                                        _MM_SHUFFLE(z, y, x, w)))
-#else
-#  define glmm_shuff1(xmm, z, y, x, w)                                        \
-     _mm_shuffle_ps(xmm, xmm, _MM_SHUFFLE(z, y, x, w))
-#endif
-
-#define glmm_shuff1x(xmm, x) glmm_shuff1(xmm, x, x, x, x)
-#define glmm_shuff2(a, b, z0, y0, x0, w0, z1, y1, x1, w1)                     \
-     glmm_shuff1(_mm_shuffle_ps(a, b, _MM_SHUFFLE(z0, y0, x0, w0)),           \
-                 z1, y1, x1, w1)
-
-static inline
-__m128
-glmm_dot(__m128 a, __m128 b) {
-  __m128 x0;
-  x0 = _mm_mul_ps(a, b);
-  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 0, 3, 2));
-  return _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 0, 1));
-}
-
-static inline
-__m128
-glmm_norm(__m128 a) {
-  return _mm_sqrt_ps(glmm_dot(a, a));
-}
-
-static inline
-__m128
-glmm_load3(float v[3]) {
-  __m128i xy;
-  __m128  z;
-
-  xy = _mm_loadl_epi64((const __m128i *)v);
-  z  = _mm_load_ss(&v[2]);
-
-  return _mm_movelh_ps(_mm_castsi128_ps(xy), z);
-}
-
-static inline
-void
-glmm_store3(__m128 vx, float v[3]) {
-  _mm_storel_pi((__m64 *)&v[0], vx);
-  _mm_store_ss(&v[2], glmm_shuff1(vx, 2, 2, 2, 2));
-}
-
-#ifdef CGLM_ALL_UNALIGNED
-#  define glmm_load(p)      _mm_loadu_ps(p)
-#  define glmm_store(p, a)  _mm_storeu_ps(p, a)
-#else
-#  define glmm_load(p)      _mm_load_ps(p)
-#  define glmm_store(p, a)  _mm_store_ps(p, a)
-#endif
-
-#endif
-
-/* x86, x64 */
-#if defined( __SSE__ ) || defined( __SSE2__ )
 #  define CGLM_SSE_FP 1
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
+#endif
+
+#if defined(__SSE3__)
+#  include <x86intrin.h>
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
+#endif
+
+#if defined(__SSE4_1__)
+#  include <smmintrin.h>
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
+#endif
+
+#if defined(__SSE4_2__)
+#  include <nmmintrin.h>
+#  ifndef CGLM_SIMD_x86
+#    define CGLM_SIMD_x86
+#  endif
 #endif
 
 #ifdef __AVX__
+#  include <immintrin.h>
 #  define CGLM_AVX_FP 1
-
+#  ifndef CGLM_SIMD_x86
-#ifdef CGLM_ALL_UNALIGNED
+#    define CGLM_SIMD_x86
-#  define glmm_load256(p)      _mm256_loadu_ps(p)
+#  endif
-#  define glmm_store256(p, a)  _mm256_storeu_ps(p, a)
-#else
-#  define glmm_load256(p)      _mm256_load_ps(p)
-#  define glmm_store256(p, a)  _mm256_store_ps(p, a)
-#endif
-
 #endif
 
 /* ARM Neon */
-#if defined(__ARM_NEON) && defined(__ARM_NEON_FP)
+#if defined(__ARM_NEON)
 #  include <arm_neon.h>
-#  define CGLM_NEON_FP 1
+#  if defined(__ARM_NEON_FP)
-#else
+#    define CGLM_NEON_FP 1
-#  undef  CGLM_NEON_FP
+#    ifndef CGLM_SIMD_ARM
+#      define CGLM_SIMD_ARM
+#    endif
+#  endif
+#endif
+
+#if defined(CGLM_SIMD_x86) || defined(CGLM_NEON_FP)
+#  ifndef CGLM_SIMD
+#    define CGLM_SIMD
+#  endif
+#endif
+
+#if defined(CGLM_SIMD_x86)
+#  include "x86.h"
+#endif
+
+#if defined(CGLM_SIMD_ARM)
+#  include "arm.h"
 #endif
 
 #endif /* cglm_intrin_h */

include/cglm/simd/neon/mat4.h

@@ -12,6 +12,32 @@
 #include "../../common.h"
 #include "../intrin.h"
 
+CGLM_INLINE
+void
+glm_mat4_scale_neon(mat4 m, float s) {
+  float32x4_t v0;
+  
+  v0 = vdupq_n_f32(s);
+
+  vst1q_f32(m[0], vmulq_f32(vld1q_f32(m[0]), v0));
+  vst1q_f32(m[1], vmulq_f32(vld1q_f32(m[1]), v0));
+  vst1q_f32(m[2], vmulq_f32(vld1q_f32(m[2]), v0));
+  vst1q_f32(m[3], vmulq_f32(vld1q_f32(m[3]), v0));
+}
+
+CGLM_INLINE
+void
+glm_mat4_transp_neon(mat4 m, mat4 dest) {
+  float32x4x4_t vmat;
+  
+  vmat = vld4q_f32(m[0]);
+
+  vst1q_f32(dest[0], vmat.val[0]);
+  vst1q_f32(dest[1], vmat.val[1]);
+  vst1q_f32(dest[2], vmat.val[2]);
+  vst1q_f32(dest[3], vmat.val[3]);
+}
+
 CGLM_INLINE
 void
 glm_mat4_mul_neon(mat4 m1, mat4 m2, mat4 dest) {
@@ -53,5 +79,27 @@ glm_mat4_mul_neon(mat4 m1, mat4 m2, mat4 dest) {
   vst1q_f32(dest[3], d3);
 }
 
+CGLM_INLINE
+void
+glm_mat4_mulv_neon(mat4 m, vec4 v, vec4 dest) {
+  float32x4_t l0, l1, l2, l3;
+  float32x2_t vlo, vhi;
+  
+  l0  = vld1q_f32(m[0]);
+  l1  = vld1q_f32(m[1]);
+  l2  = vld1q_f32(m[2]);
+  l3  = vld1q_f32(m[3]);
+
+  vlo = vld1_f32(&v[0]);
+  vhi = vld1_f32(&v[2]);
+
+  l0  = vmulq_lane_f32(l0, vlo, 0);
+  l0  = vmlaq_lane_f32(l0, l1, vlo, 1);
+  l0  = vmlaq_lane_f32(l0, l2, vhi, 0);
+  l0  = vmlaq_lane_f32(l0, l3, vhi, 1);
+
+  vst1q_f32(dest, l0);
+}
+
 #endif
 #endif /* cglm_mat4_neon_h */

include/cglm/simd/sse2/affine.h

@@ -25,28 +25,29 @@ glm_mul_sse2(mat4 m1, mat4 m2, mat4 dest) {
   
   r = glmm_load(m2[0]);
   glmm_store(dest[0],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+                                   _mm_mul_ps(glmm_shuff1x(r, 2), l2))));
   
   r = glmm_load(m2[1]);
   glmm_store(dest[1],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+                                   _mm_mul_ps(glmm_shuff1x(r, 2), l2))));
 
   r = glmm_load(m2[2]);
   glmm_store(dest[2],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+                                   _mm_mul_ps(glmm_shuff1x(r, 2), l2))));
 
   r = glmm_load(m2[3]);
   glmm_store(dest[3],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+                                   glmm_fmadd(glmm_shuff1x(r, 2), l2,
-                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
+                                              _mm_mul_ps(glmm_shuff1x(r, 3),
+                                                         l3)))));
 }
 
 CGLM_INLINE
@@ -62,21 +63,22 @@ glm_mul_rot_sse2(mat4 m1, mat4 m2, mat4 dest) {
 
   r = glmm_load(m2[0]);
   glmm_store(dest[0],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+                                   _mm_mul_ps(glmm_shuff1x(r, 2), l2))));
   
   r = glmm_load(m2[1]);
   glmm_store(dest[1],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+                                   _mm_mul_ps(glmm_shuff1x(r, 2), l2))));
+  
   
   r = glmm_load(m2[2]);
   glmm_store(dest[2],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,
-                        _mm_mul_ps(glmm_shuff1x(r, 2), l2)));
+                                   _mm_mul_ps(glmm_shuff1x(r, 2), l2))));
 
   glmm_store(dest[3], l3);
 }
@@ -94,9 +96,9 @@ 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)),
+  x0 = glmm_fmadd(r0, glmm_shuff1(r3, 0, 0, 0, 0),
-                  _mm_mul_ps(r1, glmm_shuff1(r3, 1, 1, 1, 1)));
+             glmm_fmadd(r1, glmm_shuff1(r3, 1, 1, 1, 1),
-  x0 = _mm_add_ps(x0, _mm_mul_ps(r2, glmm_shuff1(r3, 2, 2, 2, 2)));
+                        _mm_mul_ps(r2, glmm_shuff1(r3, 2, 2, 2, 2))));
   x0 = _mm_xor_ps(x0, _mm_set1_ps(-0.f));
 
   x0 = _mm_add_ps(x0, x1);

include/cglm/simd/sse2/mat2.h

@@ -0,0 +1,45 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_mat2_sse_h
+#define cglm_mat2_sse_h
+#if defined( __SSE__ ) || defined( __SSE2__ )
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_mat2_mul_sse2(mat2 m1, mat2 m2, mat2 dest) {
+  __m128 x0, x1, x2;
+
+  x1 = glmm_load(m1[0]); /* d c b a */
+  x2 = glmm_load(m2[0]); /* h g f e */
+
+  /*
+   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(_mm_movelh_ps(x1, x1), glmm_shuff1(x2, 2, 2, 0, 0),
+                  _mm_mul_ps(_mm_movehl_ps(x1, x1),
+                             glmm_shuff1(x2, 3, 3, 1, 1)));
+
+  glmm_store(dest[0], x0);
+}
+
+CGLM_INLINE
+void
+glm_mat2_transp_sse2(mat2 m, mat2 dest) {
+  /* d c b a */
+  /* d b c a */
+  glmm_store(dest[0], glmm_shuff1(glmm_load(m[0]), 3, 1, 2, 0));
+}
+
+#endif
+#endif /* cglm_mat2_sse_h */

include/cglm/simd/sse2/mat3.h

@@ -30,23 +30,16 @@ glm_mat3_mul_sse2(mat3 m1, mat3 m2, mat3 dest) {
   x1 = glmm_shuff2(l0, l1, 1, 0, 3, 3, 0, 3, 2, 0);
   x2 = glmm_shuff2(l1, l2, 0, 0, 3, 2, 0, 2, 1, 0);
 
-  x0 = _mm_add_ps(_mm_mul_ps(glmm_shuff1(l0, 0, 2, 1, 0),
+  x0 = glmm_fmadd(glmm_shuff1(l0, 0, 2, 1, 0), glmm_shuff1(r0, 3, 0, 0, 0),
-                             glmm_shuff1(r0, 3, 0, 0, 0)),
+                  glmm_fmadd(x1, glmm_shuff2(r0, r1, 0, 0, 1, 1, 2, 0, 0, 0),
-                  _mm_mul_ps(x1, glmm_shuff2(r0, r1, 0, 0, 1, 1, 2, 0, 0, 0)));
+                             _mm_mul_ps(x2, glmm_shuff2(r0, r1, 1, 1, 2, 2, 2, 0, 0, 0))));
-
-  x0 = _mm_add_ps(x0,
-                  _mm_mul_ps(x2, glmm_shuff2(r0, r1, 1, 1, 2, 2, 2, 0, 0, 0)));
 
   _mm_storeu_ps(dest[0], x0);
 
-  x0 = _mm_add_ps(_mm_mul_ps(glmm_shuff1(l0, 1, 0, 2, 1),
+  x0 = glmm_fmadd(glmm_shuff1(l0, 1, 0, 2, 1), _mm_shuffle_ps(r0, r1, _MM_SHUFFLE(2, 2, 3, 3)),
-                             _mm_shuffle_ps(r0, r1, _MM_SHUFFLE(2, 2, 3, 3))),
+                  glmm_fmadd(glmm_shuff1(x1, 1, 0, 2, 1), glmm_shuff1(r1, 3, 3, 0, 0),
-                  _mm_mul_ps(glmm_shuff1(x1, 1, 0, 2, 1),
+                             _mm_mul_ps(glmm_shuff1(x2, 1, 0, 2, 1),
-                             glmm_shuff1(r1, 3, 3, 0, 0)));
+                                        _mm_shuffle_ps(r1, r2, _MM_SHUFFLE(0, 0, 1, 1)))));
-
-  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))));
   
   _mm_storeu_ps(&dest[1][1], x0);
 

include/cglm/simd/sse2/mat4.h

@@ -16,7 +16,7 @@
 
 CGLM_INLINE
 void
-glm_mat4_scale_sse2(mat4 m, float s){
+glm_mat4_scale_sse2(mat4 m, float s) {
   __m128 x0;
   x0 = _mm_set1_ps(s);
 
@@ -28,7 +28,7 @@ glm_mat4_scale_sse2(mat4 m, float s){
 
 CGLM_INLINE
 void
-glm_mat4_transp_sse2(mat4 m, mat4 dest){
+glm_mat4_transp_sse2(mat4 m, mat4 dest) {
   __m128 r0, r1, r2, r3;
 
   r0 = glmm_load(m[0]);
@@ -56,46 +56,37 @@ glm_mat4_mul_sse2(mat4 m1, mat4 m2, mat4 dest) {
   l2 = glmm_load(m1[2]);
   l3 = glmm_load(m1[3]);
   
-  r = glmm_load(m2[0]);
+#define XX(C)                                                                 \
-  glmm_store(dest[0],
+                                                                              \
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+  r = glmm_load(m2[C]);                                                       \
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+  glmm_store(dest[C],                                                         \
-                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+             glmm_fmadd(glmm_shuff1x(r, 0), l0,                               \
-                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
+                        glmm_fmadd(glmm_shuff1x(r, 1), l1,                    \
-  r = glmm_load(m2[1]);
+                                   glmm_fmadd(glmm_shuff1x(r, 2), l2,         \
-  glmm_store(dest[1],
+                                              _mm_mul_ps(glmm_shuff1x(r, 3),  \
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+                                                         l3)))));
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
-                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
-                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
-  r = glmm_load(m2[2]);
-  glmm_store(dest[2],
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
-                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
-                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
 
-  r = glmm_load(m2[3]);
+  XX(0);
-  glmm_store(dest[3],
+  XX(1);
-             _mm_add_ps(_mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 0), l0),
+  XX(2);
-                                   _mm_mul_ps(glmm_shuff1x(r, 1), l1)),
+  XX(3);
-                        _mm_add_ps(_mm_mul_ps(glmm_shuff1x(r, 2), l2),
+
-                                   _mm_mul_ps(glmm_shuff1x(r, 3), l3))));
+#undef XX
 }
 
 CGLM_INLINE
 void
 glm_mat4_mulv_sse2(mat4 m, vec4 v, vec4 dest) {
-  __m128 x0, x1, x2;
+  __m128 x0, x1;
   
   x0 = glmm_load(v);
-  x1 = _mm_add_ps(_mm_mul_ps(glmm_load(m[0]), glmm_shuff1x(x0, 0)),
+  x1 = glmm_fmadd(glmm_load(m[0]), glmm_shuff1x(x0, 0),
-                  _mm_mul_ps(glmm_load(m[1]), glmm_shuff1x(x0, 1)));
+                  glmm_fmadd(glmm_load(m[1]), glmm_shuff1x(x0, 1),
+                             glmm_fmadd(glmm_load(m[2]), glmm_shuff1x(x0, 2),
+                                        _mm_mul_ps(glmm_load(m[3]),
+                                                   glmm_shuff1x(x0, 3)))));
   
-  x2 = _mm_add_ps(_mm_mul_ps(glmm_load(m[2]), glmm_shuff1x(x0, 2)),
+  glmm_store(dest, x1);
-                  _mm_mul_ps(glmm_load(m[3]), glmm_shuff1x(x0, 3)));
-
-  glmm_store(dest, _mm_add_ps(x1, x2));
 }
 
 CGLM_INLINE
@@ -115,20 +106,18 @@ 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),
+  x0 = glmm_fnmadd(glmm_shuff1(r3, 0, 0, 1, 1), glmm_shuff1(r2, 2, 3, 2, 3),
-                             glmm_shuff1(r3, 2, 3, 2, 3)),
+                   _mm_mul_ps(glmm_shuff1(r2, 0, 0, 1, 1),
-                  _mm_mul_ps(glmm_shuff1(r3, 0, 0, 1, 1),
+                              glmm_shuff1(r3, 2, 3, 2, 3)));
-                             glmm_shuff1(r2, 2, 3, 2, 3)));
   /*
    t[0] = k * p - o * l;
    t[0] = k * p - o * l;
    t[5] = i * n - m * j;
    t[5] = i * n - m * j;
    */
-  x1 = _mm_sub_ps(_mm_mul_ps(glmm_shuff1(r2, 0, 0, 2, 2),
+  x1 = glmm_fnmadd(glmm_shuff1(r3, 0, 0, 2, 2), glmm_shuff1(r2, 1, 1, 3, 3),
-                             glmm_shuff1(r3, 1, 1, 3, 3)),
+                   _mm_mul_ps(glmm_shuff1(r2, 0, 0, 2, 2),
-                  _mm_mul_ps(glmm_shuff1(r3, 0, 0, 2, 2),
+                              glmm_shuff1(r3, 1, 1, 3, 3)));
-                             glmm_shuff1(r2, 1, 1, 3, 3)));
 
   /*
      a * (f * t[0] - g * t[1] + h * t[2])
@@ -136,21 +125,16 @@ 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),
+  x2 = glmm_fnmadd(glmm_shuff1(r1, 1, 1, 2, 2), glmm_shuff1(x0, 3, 2, 2, 0),
-                             _mm_shuffle_ps(x1, x0, _MM_SHUFFLE(1, 0, 0, 0))),
+                   _mm_mul_ps(glmm_shuff1(r1, 0, 0, 0, 1),
-                  _mm_mul_ps(glmm_shuff1(r1, 1, 1, 2, 2),
+                              _mm_shuffle_ps(x1, x0, _MM_SHUFFLE(1, 0, 0, 0))));
-                             glmm_shuff1(x0, 3, 2, 2, 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);
+  return glmm_hadd(_mm_mul_ps(x2, r0));
-  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 2, 3));
-  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 3, 3, 1));
-
-  return _mm_cvtss_f32(x0);
 }
 
 CGLM_INLINE
@@ -159,7 +143,10 @@ 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 */
@@ -177,7 +164,7 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
      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));
+  t0 = glmm_fnmadd(x2, x0, _mm_mul_ps(x3, x1));
   
   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 */
@@ -187,13 +174,13 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
      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, _mm_mul_ps(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 = _mm_sub_ps(_mm_mul_ps(x5, x2), _mm_mul_ps(x4, x3));
+  t2 = glmm_fnmadd(x4, x3, _mm_mul_ps(x5, x2));
   
   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 */
@@ -202,19 +189,19 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
      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, _mm_mul_ps(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 = _mm_sub_ps(_mm_mul_ps(x6, x2), _mm_mul_ps(x7, x3));
+  t4 = glmm_fnmadd(x7, x3, _mm_mul_ps(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 = _mm_sub_ps(_mm_mul_ps(x6, x4), _mm_mul_ps(x7, x5));
+  t5 = glmm_fnmadd(x7, x5, _mm_mul_ps(x6, x4));
   
   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 */
@@ -226,50 +213,35 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
    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),
+  v0 = _mm_xor_ps(glmm_fmadd(x3, t2, glmm_fnmadd(x2, t1, _mm_mul_ps(x1, t0))), x8);
-                  _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));
   
   /*
    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),
+  v2 = _mm_xor_ps(glmm_fmadd(x3, t5, glmm_fnmadd(x1, t3, _mm_mul_ps(x0, t1))), x8);
-                  _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));
+   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(glmm_fmadd(x3, t4, glmm_fnmadd(x2, t3, _mm_mul_ps(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 = _mm_add_ps(_mm_mul_ps(x2, t5),
+  v3 = _mm_xor_ps(glmm_fmadd(x2, t5, glmm_fnmadd(x1, t4, _mm_mul_ps(x0, t2))), x9);
-                  _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));
 
   /* 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_rcp_ps(glmm_vhadd(_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);
 
   glmm_store(dest[0], _mm_mul_ps(v0, x0));
   glmm_store(dest[1], _mm_mul_ps(v1, x0));
@@ -283,7 +255,10 @@ 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 */
@@ -301,7 +276,7 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
      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));
+  t0 = glmm_fnmadd(x2, x0, _mm_mul_ps(x3, x1));
   
   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 */
@@ -311,13 +286,13 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
      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, _mm_mul_ps(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 = _mm_sub_ps(_mm_mul_ps(x5, x2), _mm_mul_ps(x4, x3));
+  t2 = glmm_fnmadd(x4, x3, _mm_mul_ps(x5, x2));
   
   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 */
@@ -326,19 +301,19 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
      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, _mm_mul_ps(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 = _mm_sub_ps(_mm_mul_ps(x6, x2), _mm_mul_ps(x7, x3));
+  t4 = glmm_fnmadd(x7, x3, _mm_mul_ps(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 = _mm_sub_ps(_mm_mul_ps(x6, x4), _mm_mul_ps(x7, x5));
+  t5 = glmm_fnmadd(x7, x5, _mm_mul_ps(x6, x4));
   
   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 */
@@ -350,50 +325,35 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
    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),
+  v0 = _mm_xor_ps(glmm_fmadd(x3, t2, glmm_fnmadd(x2, t1, _mm_mul_ps(x1, t0))), x8);
-                  _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));
   
   /*
    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),
+  v2 = _mm_xor_ps(glmm_fmadd(x3, t5, glmm_fnmadd(x1, t3, _mm_mul_ps(x0, t1))), x8);
-                  _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));
+   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(glmm_fmadd(x3, t4, glmm_fnmadd(x2, t3, _mm_mul_ps(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 = _mm_add_ps(_mm_mul_ps(x2, t5),
+  v3 = _mm_xor_ps(glmm_fmadd(x2, t5, glmm_fnmadd(x1, t4, _mm_mul_ps(x0, t2))), x9);
-                  _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));
 
   /* 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_div_ps(_mm_set1_ps(1.0f), glmm_vhadd(_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);
 
   glmm_store(dest[0], _mm_mul_ps(v0, x0));
   glmm_store(dest[1], _mm_mul_ps(v1, x0));

include/cglm/simd/x86.h

@@ -0,0 +1,289 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_simd_x86_h
+#define cglm_simd_x86_h
+#include "intrin.h"
+#ifdef CGLM_SIMD_x86
+
+#ifdef CGLM_ALL_UNALIGNED
+#  define glmm_load(p)      _mm_loadu_ps(p)
+#  define glmm_store(p, a)  _mm_storeu_ps(p, a)
+#else
+#  define glmm_load(p)      _mm_load_ps(p)
+#  define glmm_store(p, a)  _mm_store_ps(p, a)
+#endif
+
+#ifdef CGLM_USE_INT_DOMAIN
+#  define glmm_shuff1(xmm, z, y, x, w)                                        \
+     _mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(xmm),                \
+                                        _MM_SHUFFLE(z, y, x, w)))
+#else
+#  define glmm_shuff1(xmm, z, y, x, w)                                        \
+       _mm_shuffle_ps(xmm, xmm, _MM_SHUFFLE(z, y, x, w))
+#endif
+
+#define glmm_shuff1x(xmm, x) glmm_shuff1(xmm, x, x, x, x)
+#define glmm_shuff2(a, b, z0, y0, x0, w0, z1, y1, x1, w1)                     \
+     glmm_shuff1(_mm_shuffle_ps(a, b, _MM_SHUFFLE(z0, y0, x0, w0)),           \
+                 z1, y1, x1, w1)
+
+#ifdef __AVX__
+#  ifdef CGLM_ALL_UNALIGNED
+#    define glmm_load256(p)      _mm256_loadu_ps(p)
+#    define glmm_store256(p, a)  _mm256_storeu_ps(p, a)
+#  else
+#    define glmm_load256(p)      _mm256_load_ps(p)
+#    define glmm_store256(p, a)  _mm256_store_ps(p, a)
+#  endif
+#endif
+
+static inline
+__m128
+glmm_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) {
+#if defined(__SSE3__)
+  __m128 shuf, sums;
+  shuf = _mm_movehdup_ps(v);
+  sums = _mm_add_ps(v, shuf);
+  shuf = _mm_movehl_ps(shuf, sums);
+  sums = _mm_add_ss(sums, shuf);
+  return sums;
+#else
+  __m128 shuf, sums;
+  shuf = glmm_shuff1(v, 2, 3, 0, 1);
+  sums = _mm_add_ps(v, shuf);
+  shuf = _mm_movehl_ps(shuf, sums);
+  sums = _mm_add_ss(sums, shuf);
+  return sums;
+#endif
+}
+
+static inline
+float
+glmm_hadd(__m128 v) {
+  return _mm_cvtss_f32(glmm_vhadds(v));
+}
+
+static inline
+__m128
+glmm_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] */
+  return _mm_min_ss(x1, x2);
+}
+
+static inline
+float
+glmm_hmin(__m128 v) {
+  return _mm_cvtss_f32(glmm_vhmin(v));
+}
+
+static inline
+__m128
+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] */
+  return _mm_max_ss(x1, x2);
+}
+
+static inline
+float
+glmm_hmax(__m128 v) {
+  return _mm_cvtss_f32(glmm_vhmax(v));
+}
+
+static inline
+__m128
+glmm_vdots(__m128 a, __m128 b) {
+#if (defined(__SSE4_1__) || defined(__SSE4_2__)) && defined(CGLM_SSE4_DOT)
+  return _mm_dp_ps(a, b, 0xFF);
+#elif defined(__SSE3__) && defined(CGLM_SSE3_DOT)
+  __m128 x0, x1;
+  x0 = _mm_mul_ps(a, b);
+  x1 = _mm_hadd_ps(x0, x0);
+  return _mm_hadd_ps(x1, x1);
+#else
+  return glmm_vhadds(_mm_mul_ps(a, b));
+#endif
+}
+
+static inline
+__m128
+glmm_vdot(__m128 a, __m128 b) {
+#if (defined(__SSE4_1__) || defined(__SSE4_2__)) && defined(CGLM_SSE4_DOT)
+  return _mm_dp_ps(a, b, 0xFF);
+#elif defined(__SSE3__) && defined(CGLM_SSE3_DOT)
+  __m128 x0, x1;
+  x0 = _mm_mul_ps(a, b);
+  x1 = _mm_hadd_ps(x0, x0);
+  return _mm_hadd_ps(x1, x1);
+#else
+  __m128 x0;
+  x0 = _mm_mul_ps(a, b);
+  x0 = _mm_add_ps(x0, glmm_shuff1(x0, 1, 0, 3, 2));
+  return _mm_add_ps(x0, glmm_shuff1(x0, 0, 1, 0, 1));
+#endif
+}
+
+static inline
+float
+glmm_dot(__m128 a, __m128 b) {
+  return _mm_cvtss_f32(glmm_vdots(a, b));
+}
+
+static inline
+float
+glmm_norm(__m128 a) {
+  return _mm_cvtss_f32(_mm_sqrt_ss(glmm_vhadds(_mm_mul_ps(a, a))));
+}
+
+static inline
+float
+glmm_norm2(__m128 a) {
+  return _mm_cvtss_f32(glmm_vhadds(_mm_mul_ps(a, a)));
+}
+
+static inline
+float
+glmm_norm_one(__m128 a) {
+  return _mm_cvtss_f32(glmm_vhadds(glmm_abs(a)));
+}
+
+static inline
+float
+glmm_norm_inf(__m128 a) {
+  return _mm_cvtss_f32(glmm_vhmax(glmm_abs(a)));
+}
+
+static inline
+__m128
+glmm_load3(float v[3]) {
+  __m128i xy;
+  __m128  z;
+
+  xy = _mm_loadl_epi64(CGLM_CASTPTR_ASSUME_ALIGNED(v, const __m128i));
+  z  = _mm_load_ss(&v[2]);
+
+  return _mm_movelh_ps(_mm_castsi128_ps(xy), z);
+}
+
+static inline
+void
+glmm_store3(float v[3], __m128 vx) {
+  _mm_storel_pi(CGLM_CASTPTR_ASSUME_ALIGNED(v, __m64), vx);
+  _mm_store_ss(&v[2], glmm_shuff1(vx, 2, 2, 2, 2));
+}
+
+/* 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 */

include/cglm/sphere.h

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

include/cglm/struct.h

@@ -0,0 +1,39 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_structs_h
+#define cglm_structs_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "cglm.h"
+#include "types-struct.h"
+#include "struct/vec2.h"
+#include "struct/vec3.h"
+#include "struct/vec4.h"
+#include "struct/mat2.h"
+#include "struct/mat3.h"
+#include "struct/mat4.h"
+#include "struct/affine.h"
+#include "struct/frustum.h"
+#include "struct/plane.h"
+#include "struct/box.h"
+#include "struct/color.h"
+#include "struct/io.h"
+#include "struct/cam.h"
+#include "struct/quat.h"
+#include "struct/euler.h"
+#include "struct/project.h"
+#include "struct/sphere.h"
+#include "struct/curve.h"
+#include "struct/affine2d.h"
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglm_structs_h */

include/cglm/struct/affine.h

@@ -0,0 +1,333 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE mat4s glms_translate(mat4s m, vec3s v);
+   CGLM_INLINE mat4s glms_translate_x(mat4s m, float x);
+   CGLM_INLINE mat4s glms_translate_y(mat4s m, float y);
+   CGLM_INLINE mat4s glms_translate_z(mat4s m, float z);
+   CGLM_INLINE mat4s glms_translate_make(vec3s v);
+   CGLM_INLINE mat4s glms_scale_to(mat4s m, vec3s v);
+   CGLM_INLINE mat4s glms_scale_make(vec3s v);
+   CGLM_INLINE mat4s glms_scale(mat4s m, vec3s v);
+   CGLM_INLINE mat4s glms_scale_uni(mat4s m, float s);
+   CGLM_INLINE mat4s glms_rotate_x(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotate_y(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotate_z(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotate_make(float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_rotate(mat4s m, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_rotate_at(mat4s m, vec3s pivot, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_rotate_atm(mat4s m, vec3s pivot, float angle, vec3s axis);
+   CGLM_INLINE vec3s glms_decompose_scalev(mat4s m);
+   CGLM_INLINE bool  glms_uniscaled(mat4s m);
+   CGLM_INLINE void  glms_decompose_rs(mat4s m, mat4s * r, vec3s * s);
+   CGLM_INLINE void  glms_decompose(mat4s m, vec4s t, mat4s * r, vec3s * s);
+ */
+
+#ifndef cglms_affines_h
+#define cglms_affines_h
+
+#include "../common.h"
+#include "../types-struct.h"
+#include "../affine.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       v   translate vector [x, y, z]
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate(mat4s m, vec3s v) {
+  glm_translate(m.raw, v.raw);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       x   x factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_x(mat4s m, float x) {
+  glm_translate_x(m.raw, x);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       y   y factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_y(mat4s m, float y) {
+  glm_translate_y(m.raw, y);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       z   z factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_z(mat4s m, float z) {
+  glm_translate_z(m.raw, z);
+  return m;
+}
+
+/*!
+ * @brief creates NEW translate transform matrix by v vector
+ *
+ * @param[in]   v   translate vector [x, y, z]
+ * @returns         affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_make(vec3s v) {
+  mat4s m;
+  glm_translate_make(m.raw, v.raw);
+  return m;
+}
+
+/*!
+ * @brief creates NEW scale matrix by v vector
+ *
+ * @param[in]   v  scale vector [x, y, z]
+ * @returns affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_scale_make(vec3s v) {
+  mat4s m;
+  glm_scale_make(m.raw, v.raw);
+  return m;
+}
+
+/*!
+ * @brief scales existing transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in]    m   affine transfrom
+ * @param[in]    v   scale vector [x, y, z]
+ * @returns          affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_scale(mat4s m, vec3s v) {
+  mat4s r;
+  glm_scale_to(m.raw, v.raw, r.raw);
+  return r;
+}
+
+/*!
+ * @brief applies uniform scale to existing transform matrix v = [s, s, s]
+ *        and stores result in same matrix
+ *
+ * @param[in]    m   affine transfrom
+ * @param[in]    s   scale factor
+ * @returns          affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_scale_uni(mat4s m, float s) {
+  glm_scale_uni(m.raw, s);
+  return 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)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_x(mat4s m, float angle) {
+  mat4s r;
+  glm_rotate_x(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @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)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_y(mat4s m, float angle) {
+  mat4s r;
+  glm_rotate_y(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @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)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_z(mat4s m, float angle) {
+  mat4s r;
+  glm_rotate_z(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief creates NEW rotation matrix by angle and axis
+ *
+ * axis will be normalized so you don't need to normalize it
+ *
+ * @param[in]  angle  angle (radians)
+ * @param[in]  axis   axis
+ * @returns           affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_make(float angle, vec3s axis) {
+  mat4s m;
+  glm_rotate_make(m.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                 affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotate(mat4s m, float angle, vec3s axis) {
+  glm_rotate(m.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       pivot   rotation center
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                 affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_at(mat4s m, vec3s pivot, float angle, vec3s axis) {
+  glm_rotate_at(m.raw, pivot.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @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[in]  m      affine transfrom
+ * @param[in]  pivot  rotation center
+ * @param[in]  angle  angle (radians)
+ * @param[in]  axis   axis
+ * @returns           affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_atm(mat4s m, vec3s pivot, float angle, vec3s axis) {
+  glm_rotate_atm(m.raw, pivot.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief decompose scale vector
+ *
+ * @param[in]  m  affine transform
+ * @returns       scale vector (Sx, Sy, Sz)
+ */
+CGLM_INLINE
+vec3s
+glms_decompose_scalev(mat4s m) {
+  vec3s r;
+  glm_decompose_scalev(m.raw, r.raw);
+  return r;
+}
+
+/*!
+ * @brief returns true if matrix is uniform scaled. This is helpful for
+ *        creating normal matrix.
+ *
+ * @param[in] m m
+ *
+ * @return boolean
+ */
+CGLM_INLINE
+bool
+glms_uniscaled(mat4s m) {
+  return glm_uniscaled(m.raw);
+}
+
+/*!
+ * @brief decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
+ *        DON'T pass projected matrix here
+ *
+ * @param[in]  m affine transform
+ * @param[out] r rotation matrix
+ * @param[out] s scale matrix
+ */
+CGLM_INLINE
+void
+glms_decompose_rs(mat4s m, mat4s * __restrict r, vec3s * __restrict s) {
+  glm_decompose_rs(m.raw, r->raw, s->raw);
+}
+
+/*!
+ * @brief decompose affine transform, TODO: extract shear factors.
+ *        DON'T pass projected matrix here
+ *
+ * @param[in]  m affine transfrom
+ * @param[out] t translation vector
+ * @param[out] r rotation matrix (mat4)
+ * @param[out] s scaling vector [X, Y, Z]
+ */
+CGLM_INLINE
+void
+glms_decompose(mat4s m, vec4s * __restrict t, mat4s * __restrict r, vec3s * __restrict s) {
+  glm_decompose(m.raw, t->raw, r->raw, s->raw);
+}
+
+#endif /* cglms_affines_h */