Merge pull request #340 from recp/non-square-matrix

add some missing non-square matrix funcs

.github/FUNDING.yml

@@ -1,7 +1,7 @@
 # These are supported funding model platforms
 
-github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+github: [recp]
-patreon: # Replace with a single Patreon username
+patreon: recp
 open_collective: cglm
 ko_fi: # Replace with a single Ko-fi username
 tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel

.github/workflows/cmake-wasm.yml

@@ -0,0 +1,97 @@
+name: CMake WebAssembly
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+env:
+  wasmtime_version: v7.0.0
+  wasmer_version: v3.1.1
+
+jobs:
+  build_wasi_sdk:
+    strategy:
+      matrix:
+        BUILD_TYPE: [Release, Debug, RelWithDebInfo, MinSizeRel]
+        C_FLAGS: ['', '-msimd128']
+        wasi_sdk_version: [19, 20]
+    # The CMake configure and build commands are platform agnostic and should work equally well on Windows or Mac.
+    # You can convert this to a matrix build if you need cross-platform coverage.
+    # See: https://docs.github.com/en/free-pro-team@latest/actions/learn-github-actions/managing-complex-workflows#using-a-build-matrix
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Downloading wasi-sdk
+      run: |
+        cd ${{github.workspace}}
+        wget --no-verbose https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-${{matrix.wasi_sdk_version}}/wasi-sdk-${{matrix.wasi_sdk_version}}.0-linux.tar.gz
+        tar xf wasi-sdk-${{matrix.wasi_sdk_version}}.0-linux.tar.gz
+
+    - name: Configure CMake
+      # Configure CMake in a 'build' subdirectory. `CMAKE_BUILD_TYPE` is only required if you are using a single-configuration generator such as make.
+      # See https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html?highlight=cmake_build_type
+      run: cmake -B ${{github.workspace}}/build -DCMAKE_BUILD_TYPE=${{matrix.BUILD_TYPE}} -DCMAKE_C_FLAGS="${{matrix.C_FLAGS}}" -DCMAKE_TOOLCHAIN_FILE=${{github.workspace}}/wasi-sdk-${{matrix.wasi_sdk_version}}.0/share/cmake/wasi-sdk.cmake -DWASI_SDK_PREFIX=${{github.workspace}}/wasi-sdk-${{matrix.wasi_sdk_version}}.0 -DCGLM_USE_TEST=ON
+
+    - name: Build
+      # Build your program with the given configuration
+      run: cmake --build ${{github.workspace}}/build --config ${{matrix.BUILD_TYPE}}
+
+    - name: Test with wasmtime
+      run: |
+        cd ${{github.workspace}}
+        ls -lh ${{github.workspace}}/build/
+        wget --no-verbose https://github.com/bytecodealliance/wasmtime/releases/download/${{env.wasmtime_version}}/wasmtime-${{env.wasmtime_version}}-x86_64-linux.tar.xz
+        tar xf wasmtime-${{env.wasmtime_version}}-x86_64-linux.tar.xz
+        ./wasmtime-${{env.wasmtime_version}}-x86_64-linux/wasmtime run --wasm-features simd ${{github.workspace}}/build/tests
+
+    - name: Test with wasmer
+      run: |
+        cd ${{github.workspace}}
+        mkdir wasmer
+        cd wasmer
+        wget --no-verbose https://github.com/wasmerio/wasmer/releases/download/${{env.wasmer_version}}/wasmer-linux-amd64.tar.gz
+        tar xf wasmer-linux-amd64.tar.gz
+        ./bin/wasmer run --enable-simd ${{github.workspace}}/build/tests
+
+  build_emsdk:
+    strategy:
+      matrix:
+        BUILD_TYPE: [Release, Debug, RelWithDebInfo, MinSizeRel]
+        C_FLAGS: ['', '-msimd128', '-msse -msse2 -msimd128', '-msse -msse2 -msse3 -msse4 -msimd128']
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Setup emsdk
+      uses: mymindstorm/setup-emsdk@v12
+
+    - name: Verify emsdk
+      run: emcc -v
+
+    - name: Configure CMake
+      # Configure CMake in a 'build' subdirectory. `CMAKE_BUILD_TYPE` is only required if you are using a single-configuration generator such as make.
+      # See https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html?highlight=cmake_build_type
+      run: emcmake cmake -B ${{github.workspace}}/build -DCMAKE_BUILD_TYPE=${{matrix.BUILD_TYPE}} -DCMAKE_C_FLAGS="${{matrix.C_FLAGS}}" -DCMAKE_EXE_LINKER_FLAGS="-s STANDALONE_WASM" -DCGLM_STATIC=ON -DCGLM_USE_TEST=ON
+
+    - name: Build
+      # Build your program with the given configuration
+      run: cmake --build ${{github.workspace}}/build --config ${{matrix.BUILD_TYPE}}
+
+    - name: Test with wasmtime
+      run: |
+        cd ${{github.workspace}}
+        ls -lh ${{github.workspace}}/build/
+        wget --no-verbose https://github.com/bytecodealliance/wasmtime/releases/download/${{env.wasmtime_version}}/wasmtime-${{env.wasmtime_version}}-x86_64-linux.tar.xz
+        tar xf wasmtime-${{env.wasmtime_version}}-x86_64-linux.tar.xz
+        ./wasmtime-${{env.wasmtime_version}}-x86_64-linux/wasmtime run --wasm-features simd ${{github.workspace}}/build/tests.wasm
+    - name: Test with wasmer
+      run: |
+        cd ${{github.workspace}}
+        mkdir wasmer
+        cd wasmer
+        wget --no-verbose https://github.com/wasmerio/wasmer/releases/download/${{env.wasmer_version}}/wasmer-linux-amd64.tar.gz
+        tar xf wasmer-linux-amd64.tar.gz
+        ./bin/wasmer run --enable-simd ${{github.workspace}}/build/tests.wasm

.gitignore

@@ -79,3 +79,4 @@ confdefs.h
 .idea
 cmake-build-debug
 *.o.tmp
+xcode/*

.vscode/c_cpp_properties.json

@@ -0,0 +1,20 @@
+{
+    "configurations": [
+        {
+            "name": "Mac",
+            "includePath": [
+                "${workspaceFolder}/**"
+            ],
+            "defines": [],
+            "macFrameworkPath": [
+                "/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/System/Library/Frameworks"
+            ],
+            "compilerPath": "/usr/bin/clang",
+            "cStandard": "c23",
+            "cppStandard": "c++23",
+            "intelliSenseMode": "macos-clang-arm64",
+            "configurationProvider": "vector-of-bool.cmake-tools"
+        }
+    ],
+    "version": 4
+}

.vscode/settings.json

@@ -1,4 +1,31 @@
 {
   "C_Cpp.default.configurationProvider": "vector-of-bool.cmake-tools",
-  "restructuredtext.confPath": "${workspaceFolder}/docs/source"
+  "restructuredtext.confPath": "${workspaceFolder}/docs/source",
+  "workbench.colorTheme": "Default Light+ Experimental",
+  "editor.fontSize": 14,
+  "workbench.colorCustomizations": {
+	"[Default Light*]": {
+  	    "editor.background": "#fefefe",
+  	    "sideBar.background": "#fefefe",
+  	    "sideBar.foreground": "#343436",
+  	    "sideBarTitle.foreground": "#343436",
+  	    "sideBar.border": "#e2e2e4",
+  	    "statusBar.background": "#fefefe",
+  	    "titleBar.activeBackground": "#fefefe",
+  	    "tab.activeBackground": "#f4fff4aa",
+  	    "tab.inactiveBackground": "#fefefe",
+  	    "activityBar.background": "#fefefe",
+  	    "editorGroupHeader.tabsBackground": "#fefefe"
+	},
+	"[Default Dark*]": {
+		"editor.background": "#1D1D25",
+		"sideBar.background": "#1D1D25",
+		"statusBar.background": "#1D1D25",
+		"titleBar.activeBackground": "#1D1D25",
+		"tab.activeBackground": "#2C2C3A",
+		"tab.inactiveBackground": "#1D1D25",
+		"activityBar.background": "#1D1D25",
+		"editorGroupHeader.tabsBackground": "#1D1D25"
+    }
+  },
 }

CMakeLists.txt

@@ -1,5 +1,10 @@
 cmake_minimum_required(VERSION 3.8.2)
-project(cglm VERSION 0.8.5 LANGUAGES C)
+project(cglm
+  VERSION 0.9.1
+  HOMEPAGE_URL https://github.com/recp/cglm
+  DESCRIPTION "OpenGL Mathematics (glm) for C"
+  LANGUAGES C
+)
 
 set(CMAKE_C_STANDARD 11)
 set(CMAKE_C_STANDARD_REQUIRED YES)
@@ -11,6 +16,11 @@ option(CGLM_STATIC "Static build" OFF)
 option(CGLM_USE_C99 "" OFF)
 option(CGLM_USE_TEST "Enable Tests" OFF)
 
+if(CMAKE_SYSTEM_NAME STREQUAL WASI)
+  set(CGLM_STATIC ON CACHE BOOL "Static option" FORCE)
+  set(CGLM_SHARED OFF CACHE BOOL "Shared option" FORCE)
+endif()
+
 if(NOT CGLM_STATIC AND CGLM_SHARED)
   set(CGLM_BUILD SHARED)
 else(CGLM_STATIC)
@@ -33,10 +43,12 @@ if(MSVC)
     string(REGEX REPLACE "/RTC(su|[1su])" "" ${flag_var} "${${flag_var}}")
   endforeach(flag_var)
 else()
-  add_compile_options(-Wall -Werror -O3)
+  add_compile_options(-Wall -O3)
 endif()
 
-if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
+get_directory_property(hasParent PARENT_DIRECTORY)
+
+if(NOT hasParent AND 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
@@ -61,11 +73,20 @@ add_library(${PROJECT_NAME}
   src/quat.c
   src/cam.c
   src/vec2.c
+  src/ivec2.c
   src/vec3.c
+  src/ivec3.c
   src/vec4.c
+  src/ivec4.c
   src/mat2.c
+  src/mat2x3.c
+  src/mat2x4.c
   src/mat3.c
+  src/mat3x2.c
+  src/mat3x4.c
   src/mat4.c
+  src/mat4x2.c
+  src/mat4x3.c
   src/plane.c
   src/frustum.c
   src/box.c
@@ -76,18 +97,20 @@ add_library(${PROJECT_NAME}
   src/bezier.c
   src/ray.c
   src/affine2d.c
-  src/clipspace/persp_lh_zo.c
-  src/clipspace/persp_rh_zo.c
-  src/clipspace/persp_lh_no.c
-  src/clipspace/persp_rh_no.c
-  src/clipspace/ortho_lh_zo.c
-  src/clipspace/ortho_rh_zo.c
   src/clipspace/ortho_lh_no.c
+  src/clipspace/ortho_lh_zo.c
   src/clipspace/ortho_rh_no.c
-  src/clipspace/view_lh_zo.c
+  src/clipspace/ortho_rh_zo.c
-  src/clipspace/view_rh_zo.c
+  src/clipspace/persp_lh_no.c
+  src/clipspace/persp_lh_zo.c
+  src/clipspace/persp_rh_no.c
+  src/clipspace/persp_rh_zo.c
   src/clipspace/view_lh_no.c
+  src/clipspace/view_lh_zo.c
   src/clipspace/view_rh_no.c
+  src/clipspace/view_rh_zo.c
+  src/clipspace/project_no.c
+  src/clipspace/project_zo.c
   )
 
 if(CGLM_SHARED)
@@ -150,10 +173,18 @@ install(EXPORT      ${PROJECT_NAME}
 set(PACKAGE_NAME ${PROJECT_NAME})
 set(prefix ${CMAKE_INSTALL_PREFIX})
 set(exec_prefix ${CMAKE_INSTALL_PREFIX})
-set(includedir "\${prefix}/${CMAKE_INSTALL_INCLUDEDIR}")
+if (IS_ABSOLUTE "${CMAKE_INSTALL_INCLUDEDIR}")
-set(libdir "\${prefix}/${CMAKE_INSTALL_LIBDIR}")
+  set(includedir "${CMAKE_INSTALL_INCLUDEDIR}")
+else()
+  set(includedir "\${prefix}/${CMAKE_INSTALL_INCLUDEDIR}")
+endif()
+if (IS_ABSOLUTE "${CMAKE_INSTALL_LIBDIR}")
+  set(libdir "${CMAKE_INSTALL_LIBDIR}")
+else()
+  set(libdir "\${exec_prefix}/${CMAKE_INSTALL_LIBDIR}")
+endif()
 set(PACKAGE_VERSION "${PROJECT_VERSION}")
-configure_file(${CMAKE_CURRENT_LIST_DIR}/cglm.pc.in ${CMAKE_BINARY_DIR}/cglm.pc @ONLY)
+configure_file(cglm.pc.in cglm.pc @ONLY)
 
-install(FILES ${CMAKE_BINARY_DIR}/cglm.pc
+install(FILES ${CMAKE_CURRENT_BINARY_DIR}/cglm.pc
   DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)

Makefile.am

@@ -11,8 +11,7 @@ AM_CFLAGS = -Wall \
             -std=gnu11 \
             -O3 \
             -Wstrict-aliasing=2 \
-            -fstrict-aliasing \
+            -fstrict-aliasing
-            -Werror=strict-prototypes
 
 lib_LTLIBRARIES = libcglm.la
 libcglm_la_LDFLAGS = -no-undefined -version-info 0:1:0
@@ -43,19 +42,30 @@ cglm_HEADERS = include/cglm/version.h \
                include/cglm/cam.h \
                include/cglm/io.h \
                include/cglm/mat4.h \
+               include/cglm/mat4x2.h \
+               include/cglm/mat4x3.h \
                include/cglm/mat3.h \
+               include/cglm/mat3x2.h \
+               include/cglm/mat3x4.h \
                include/cglm/mat2.h \
+               include/cglm/mat2x3.h \
+               include/cglm/mat2x4.h \
+               include/cglm/affine-pre.h \
+               include/cglm/affine-post.h \
                include/cglm/affine.h \
+               include/cglm/affine-mat.h \
                include/cglm/vec2.h \
                include/cglm/vec2-ext.h \
+               include/cglm/ivec2.h \
                include/cglm/vec3.h \
                include/cglm/vec3-ext.h \
+               include/cglm/ivec3.h \
                include/cglm/vec4.h \
                include/cglm/vec4-ext.h \
+               include/cglm/ivec4.h \
                include/cglm/euler.h \
                include/cglm/util.h \
                include/cglm/quat.h \
-               include/cglm/affine-mat.h \
                include/cglm/plane.h \
                include/cglm/frustum.h \
                include/cglm/box.h \
@@ -71,31 +81,39 @@ cglm_HEADERS = include/cglm/version.h \
 
 cglm_clipspacedir=$(includedir)/cglm/clipspace
 cglm_clipspace_HEADERS = include/cglm/clipspace/persp.h \
-                         include/cglm/clipspace/persp_lh_zo.h \
-                         include/cglm/clipspace/persp_rh_zo.h \
                          include/cglm/clipspace/persp_lh_no.h \
+                         include/cglm/clipspace/persp_lh_zo.h \
                          include/cglm/clipspace/persp_rh_no.h \
-                         include/cglm/clipspace/ortho_lh_zo.h \
+                         include/cglm/clipspace/persp_rh_zo.h \
-                         include/cglm/clipspace/ortho_rh_zo.h \
                          include/cglm/clipspace/ortho_lh_no.h \
+                         include/cglm/clipspace/ortho_lh_zo.h \
                          include/cglm/clipspace/ortho_rh_no.h \
+                         include/cglm/clipspace/ortho_rh_zo.h \
                          include/cglm/clipspace/view_lh.h \
                          include/cglm/clipspace/view_rh.h \
-                         include/cglm/clipspace/view_lh_zo.h \
-                         include/cglm/clipspace/view_rh_zo.h \
                          include/cglm/clipspace/view_lh_no.h \
+                         include/cglm/clipspace/view_lh_zo.h \
                          include/cglm/clipspace/view_rh_no.h \
-                         include/cglm/clipspace/project_zo.h \
+                         include/cglm/clipspace/view_rh_zo.h \
-                         include/cglm/clipspace/project_no.h
+                         include/cglm/clipspace/project_no.h \
+                         include/cglm/clipspace/project_zo.h
 
 cglm_calldir=$(includedir)/cglm/call
 cglm_call_HEADERS = include/cglm/call/mat4.h \
+                    include/cglm/call/mat4x2.h \
+                    include/cglm/call/mat4x3.h \
                     include/cglm/call/mat3.h \
+                    include/cglm/call/mat3x2.h \
+                    include/cglm/call/mat3x4.h \
                     include/cglm/call/mat2.h \
+                    include/cglm/call/mat2x3.h \
+                    include/cglm/call/mat2x4.h \
                     include/cglm/call/vec2.h \
                     include/cglm/call/vec3.h \
                     include/cglm/call/vec4.h \
-                    include/cglm/call/affine.h \
+                    include/cglm/call/ivec2.h \
+                    include/cglm/call/ivec3.h \
+                    include/cglm/call/ivec4.h \
                     include/cglm/call/io.h \
                     include/cglm/call/cam.h \
                     include/cglm/call/quat.h \
@@ -109,21 +127,22 @@ cglm_call_HEADERS = include/cglm/call/mat4.h \
                     include/cglm/call/curve.h \
                     include/cglm/call/bezier.h \
                     include/cglm/call/ray.h \
+                    include/cglm/call/affine.h \
                     include/cglm/call/affine2d.h
 
 cglm_call_clipspacedir=$(includedir)/cglm/call/clipspace
-cglm_call_clipspace_HEADERS = include/cglm/call/clipspace/persp_lh_zo.h \
+cglm_call_clipspace_HEADERS = include/cglm/call/clipspace/persp_lh_no.h \
-                              include/cglm/call/clipspace/persp_rh_zo.h \
+                              include/cglm/call/clipspace/persp_lh_zo.h \
-                              include/cglm/call/clipspace/persp_lh_no.h \
                               include/cglm/call/clipspace/persp_rh_no.h \
-                              include/cglm/call/clipspace/ortho_lh_zo.h \
+                              include/cglm/call/clipspace/persp_rh_zo.h \
-                              include/cglm/call/clipspace/ortho_rh_zo.h \
                               include/cglm/call/clipspace/ortho_lh_no.h \
+                              include/cglm/call/clipspace/ortho_lh_zo.h \
                               include/cglm/call/clipspace/ortho_rh_no.h \
-                              include/cglm/call/clipspace/view_lh_zo.h \
+                              include/cglm/call/clipspace/ortho_rh_zo.h \
-                              include/cglm/call/clipspace/view_rh_zo.h \
                               include/cglm/call/clipspace/view_lh_no.h \
+                              include/cglm/call/clipspace/view_lh_zo.h \
                               include/cglm/call/clipspace/view_rh_no.h \
+                              include/cglm/call/clipspace/view_rh_zo.h \
                               include/cglm/call/clipspace/project_no.h \
                               include/cglm/call/clipspace/project_zo.h
 
@@ -144,22 +163,32 @@ cglm_simd_avx_HEADERS = include/cglm/simd/avx/mat4.h \
                         include/cglm/simd/avx/affine.h
 
 cglm_simd_neondir=$(includedir)/cglm/simd/neon
-cglm_simd_neon_HEADERS = include/cglm/simd/neon/mat4.h \
+cglm_simd_neon_HEADERS = include/cglm/simd/neon/affine.h \
                          include/cglm/simd/neon/mat2.h \
-                         include/cglm/simd/neon/affine.h \
+                         include/cglm/simd/neon/mat4.h \
                          include/cglm/simd/neon/quat.h
 
 cglm_structdir=$(includedir)/cglm/struct
 cglm_struct_HEADERS = include/cglm/struct/mat4.h \
+                      include/cglm/struct/mat4x2.h \
+                      include/cglm/struct/mat4x3.h \
                       include/cglm/struct/mat3.h \
+                      include/cglm/struct/mat3x2.h \
+                      include/cglm/struct/mat3x4.h \
                       include/cglm/struct/mat2.h \
+                      include/cglm/struct/mat2x3.h \
+                      include/cglm/struct/mat2x4.h \
+                      include/cglm/struct/affine-pre.h \
+                      include/cglm/struct/affine-post.h \
+                      include/cglm/struct/affine-mat.h \
+                      include/cglm/struct/affine.h \
+                      include/cglm/struct/affine2d.h \
                       include/cglm/struct/vec2.h \
                       include/cglm/struct/vec2-ext.h \
                       include/cglm/struct/vec3.h \
                       include/cglm/struct/vec3-ext.h \
                       include/cglm/struct/vec4.h \
                       include/cglm/struct/vec4-ext.h \
-                      include/cglm/struct/affine.h \
                       include/cglm/struct/io.h \
                       include/cglm/struct/cam.h \
                       include/cglm/struct/quat.h \
@@ -170,22 +199,23 @@ cglm_struct_HEADERS = include/cglm/struct/mat4.h \
                       include/cglm/struct/project.h \
                       include/cglm/struct/sphere.h \
                       include/cglm/struct/color.h \
-                      include/cglm/struct/curve.h \
+                      include/cglm/struct/curve.h
-                      include/cglm/struct/affine2d.h
 
 cglm_struct_clipspacedir=$(includedir)/cglm/struct/clipspace
-cglm_struct_clipspace_HEADERS = include/cglm/struct/clipspace/persp_lh_zo.h \
+cglm_struct_clipspace_HEADERS = include/cglm/struct/clipspace/persp_lh_no.h \
-                                include/cglm/struct/clipspace/persp_rh_zo.h \
+                                include/cglm/struct/clipspace/persp_lh_zo.h \
-                                include/cglm/struct/clipspace/persp_lh_no.h \
                                 include/cglm/struct/clipspace/persp_rh_no.h \
-                                include/cglm/struct/clipspace/ortho_lh_zo.h \
+                                include/cglm/struct/clipspace/persp_rh_zo.h \
-                                include/cglm/struct/clipspace/ortho_rh_zo.h \
                                 include/cglm/struct/clipspace/ortho_lh_no.h \
+                                include/cglm/struct/clipspace/ortho_lh_zo.h \
                                 include/cglm/struct/clipspace/ortho_rh_no.h \
-                                include/cglm/struct/clipspace/view_lh_zo.h \
+                                include/cglm/struct/clipspace/ortho_rh_zo.h \
-                                include/cglm/struct/clipspace/view_rh_zo.h \
                                 include/cglm/struct/clipspace/view_lh_no.h \
-                                include/cglm/struct/clipspace/view_rh_no.h
+                                include/cglm/struct/clipspace/view_lh_zo.h \
+                                include/cglm/struct/clipspace/view_rh_no.h \
+                                include/cglm/struct/clipspace/view_rh_zo.h \
+                                include/cglm/struct/clipspace/project_no.h \
+                                include/cglm/struct/clipspace/project_zo.h
 
 libcglm_la_SOURCES=\
     src/euler.c \
@@ -194,11 +224,20 @@ libcglm_la_SOURCES=\
     src/quat.c \
     src/cam.c \
     src/vec2.c \
+    src/ivec2.c \
     src/vec3.c \
+    src/ivec3.c \
     src/vec4.c \
+    src/ivec4.c \
     src/mat2.c \
+    src/mat2x3.c \
+    src/mat2x4.c \
     src/mat3.c \
+    src/mat3x2.c \
+    src/mat3x4.c \
     src/mat4.c \
+    src/mat4x2.c \
+    src/mat4x3.c \
     src/plane.c \
     src/frustum.c \
     src/box.c \
@@ -228,11 +267,6 @@ test_tests_SOURCES=\
     test/runner.c \
     test/src/test_common.c \
     test/src/tests.c \
-    test/src/test_cam.c \
-    test/src/test_cam_lh_zo.c \
-    test/src/test_cam_rh_zo.c \
-    test/src/test_cam_lh_no.c \
-    test/src/test_cam_rh_no.c \
     test/src/test_clamp.c \
     test/src/test_euler.c \
     test/src/test_bezier.c \

README.md

@@ -242,6 +242,38 @@ add_subdirectory(external/cglm/)
 # or you can use find_package to configure cglm
 ```
 
+#### Use CMake to build for WebAssembly
+
+Since math functions like `sinf` is used, this can not be targeted at `wasm32-unknown-unknown`, one of [wasi-sdk](https://github.com/WebAssembly/wasi-sdk) or [emscripten](https://github.com/emscripten-core/emsdk) should be used.
+
+Should note that shared build is not yet supported for WebAssembly.
+
+For [simd128](https://github.com/WebAssembly/simd) support, add `-msimd128` to `CMAKE_C_FLAGS`, in command line `-DCMAKE_C_FLAGS="-msimd128"`.
+
+For tests, the cmake option `CGLM_USE_TEST` would still work, you'll need a wasi runtime for running tests, see our [ci config file](.github/workflows/cmake-wasm.yml) for a detailed example.
+
+##### Use CMake and WASI SDK to build for WebAssembly
+
+```bash
+$ cmake .. \
+  -DCMAKE_TOOLCHAIN_FILE=/path/to/wasi-sdk-19.0/share/cmake/wasi-sdk.cmake \
+  -DWASI_SDK_PREFIX=/path/to/wasi-sdk-19.0
+```
+
+Where `/path/to/wasi-sdk-19.0/` is the path to extracted [wasi sdk](https://github.com/WebAssembly/wasi-sdk).
+
+In this case it would by default make a static build.
+
+##### Use CMake and Emscripten SDK to build for WebAssembly
+
+```bash
+$ emcmake cmake .. \
+  -DCMAKE_EXE_LINKER_FLAGS="-s STANDALONE_WASM" \
+  -DCGLM_STATIC=ON
+```
+
+The `emcmake` here is the cmake wrapper for Emscripten from installed [emsdk](https://github.com/emscripten-core/emsdk).
+
 ### Meson (All platforms)
 
 ```bash
@@ -257,7 +289,7 @@ $ sudo ninja install # [Optional]
 c_std=c11
 buildtype=release
 default_library=shared
-enable_tests=false # to run tests: ninja test
+build_tests=true # to run tests: ninja test
 ```
 #### Use with your Meson project
 * Example:
@@ -431,7 +463,7 @@ You can pass matrices the same way to other APIs e.g. Vulkan, DX...
 
 ## Notes
 
-- This library uses float types only, does not support Integers, Double... yet
+- This library does not support double type... yet
 - If headers are not working properly with your compiler, IDE please open an issue, because I'm using GCC and clang to test it maybe sometimes MSVC
 
 **TODO:**

cglm.podspec

@@ -2,7 +2,7 @@ Pod::Spec.new do |s|
 
   # Description
   s.name         = "cglm"
-  s.version      = "0.8.4"
+  s.version      = "0.9.0"
   s.summary      = "📽 Highly Optimized Graphics Math (glm) for C"
   s.description  = <<-DESC
 cglm is math library for graphics programming for C. See the documentation or README for all features.

configure.ac

@@ -7,8 +7,8 @@
 #*****************************************************************************
 
 AC_PREREQ([2.69])
-AC_INIT([cglm], [0.8.5], [info@recp.me])
+AC_INIT([cglm], [0.9.1], [info@recp.me])
-AM_INIT_AUTOMAKE([-Wall -Werror foreign subdir-objects serial-tests])
+AM_INIT_AUTOMAKE([-Wall foreign subdir-objects serial-tests])
 
 # Don't use the default cflags (-O2 -g), we set ours manually in Makefile.am.
 : ${CFLAGS=""}

docs/source/affine-common.rst

@@ -0,0 +1,129 @@
+.. default-domain:: C
+
+3D Affine Transforms (common)
+================================================================================
+
+Common transfrom functions.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translate_make`
+#. :c:func:`glm_scale_to`
+#. :c:func:`glm_scale_make`
+#. :c:func:`glm_scale`
+#. :c:func:`glm_scale_uni`
+#. :c:func:`glm_rotate_make`
+#. :c:func:`glm_rotate_atm`
+#. :c:func:`glm_decompose_scalev`
+#. :c:func:`glm_uniscaled`
+#. :c:func:`glm_decompose_rs`
+#. :c:func:`glm_decompose`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void  glm_translate_make(mat4 m, vec3 v)
+
+    creates NEW translate transform matrix by *v* vector.
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_scale_to(mat4 m, vec3 v, mat4 dest)
+
+    scale existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    scale vector [x, y, z]
+      | *[out]* **dest** scaled matrix
+
+.. c:function:: void  glm_scale_make(mat4 m, vec3 v)
+
+    creates NEW scale matrix by v vector
+
+    Parameters:
+      | *[out]* **m** affine transfrom
+      | *[in]*  **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale(mat4 m, vec3 v)
+
+    scales existing transform matrix by v vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale_uni(mat4 m, float s)
+
+    applies uniform scale to existing transform matrix v = [s, s, s]
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale factor
+
+.. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
+
+    creates NEW rotation matrix by angle and axis,
+    axis will be normalized so you don't need to normalize it
+
+    Parameters:
+      | *[out]* **m**    affine transfrom
+      | *[in]*  **axis** angle (radians)
+      | *[in]*  **axis** axis
+
+.. c:function:: void  glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis)
+
+    | creates NEW rotation matrix by angle and axis at given point
+    | this creates rotation matrix, it assumes you don't have a matrix
+
+    | this should work faster than glm_rotate_at because it reduces one glm_translate.
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **pivot** pivot, anchor point, rotation center
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_decompose_scalev(mat4 m, vec3 s)
+
+    decompose scale vector
+
+    Parameters:
+      | *[in]*  **m**  affine transform
+      | *[out]* **s**  scale vector (Sx, Sy, Sz)
+
+.. c:function:: bool  glm_uniscaled(mat4 m)
+
+    returns true if matrix is uniform scaled.
+    This is helpful for creating normal matrix.
+
+    Parameters:
+      | *[in]*  **m**   matrix
+
+.. c:function:: void  glm_decompose_rs(mat4 m, mat4 r, vec3 s)
+
+    decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transform
+      | *[out]* **r** rotation matrix
+      | *[out]* **s** scale matrix
+
+.. c:function:: void  glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s)
+
+    decompose affine transform, TODO: extract shear factors.
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transfrom
+      | *[out]* **t** translation vector
+      | *[out]* **r** rotation matrix (mat4)
+      | *[out]* **s** scaling vector [X, Y, Z]

docs/source/affine-post.rst

@@ -0,0 +1,129 @@
+.. default-domain:: C
+
+3D Affine Transforms (post)
+================================================================================
+
+Post transfrom functions are similar to pre transform functions except order of application is reversed.  
+Post transform functions are applied after the object is transformed with given (model matrix) transfrom. 
+
+Ther are named af
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translated_to`
+#. :c:func:`glm_translated`
+#. :c:func:`glm_translated_x`
+#. :c:func:`glm_translated_y`
+#. :c:func:`glm_translated_z`
+#. :c:func:`glm_rotated_x`
+#. :c:func:`glm_rotated_y`
+#. :c:func:`glm_rotated_z`
+#. :c:func:`glm_rotated`
+#. :c:func:`glm_rotated_at`
+#. :c:func:`glm_spinned`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void  glm_translated_to(mat4 m, vec3 v, mat4 dest)
+
+    translate existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    translate vector [x, y, z]
+      | *[out]* **dest** translated matrix
+
+.. c:function:: void  glm_translated(mat4 m, vec3 v)
+
+    translate existing transform matrix by *v* vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_translated_x(mat4 m, float x)
+
+    translate existing transform matrix by x factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  x factor
+
+.. c:function:: void  glm_translated_y(mat4 m, float y)
+
+    translate existing transform matrix by *y* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  y factor
+
+.. c:function:: void  glm_translated_z(mat4 m, float z)
+
+    translate existing transform matrix by *z* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  z factor
+
+.. c:function:: void  glm_rotated_x(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around X axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotated_y(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Y axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotated_z(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Z axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotated(mat4 m, float angle, vec3 axis)
+
+    rotate existing transform matrix around Z axis by angle and axis
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis)
+
+    rotate existing transform around given axis by angle at given pivot point (rotation center)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **pivot** pivot, anchor point, rotation center
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_spinned(mat4 m, float angle, vec3 axis)
+
+    | rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis

docs/source/affine-pre.rst

@@ -0,0 +1,240 @@
+.. default-domain:: C
+
+3D Affine Transforms (pre)
+================================================================================
+
+Pre transfrom functions which are regular transfrom functions.
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Functions:
+
+1. :c:func:`glm_translate_to`
+#. :c:func:`glm_translate`
+#. :c:func:`glm_translate_x`
+#. :c:func:`glm_translate_y`
+#. :c:func:`glm_translate_z`
+#. :c:func:`glm_translate_make`
+#. :c:func:`glm_scale_to`
+#. :c:func:`glm_scale_make`
+#. :c:func:`glm_scale`
+#. :c:func:`glm_scale_uni`
+#. :c:func:`glm_rotate_x`
+#. :c:func:`glm_rotate_y`
+#. :c:func:`glm_rotate_z`
+#. :c:func:`glm_rotate_make`
+#. :c:func:`glm_rotate`
+#. :c:func:`glm_rotate_at`
+#. :c:func:`glm_rotate_atm`
+#. :c:func:`glm_decompose_scalev`
+#. :c:func:`glm_uniscaled`
+#. :c:func:`glm_decompose_rs`
+#. :c:func:`glm_decompose`
+#. :c:func:`glm_spin`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void  glm_translate_to(mat4 m, vec3 v, mat4 dest)
+
+    translate existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    translate vector [x, y, z]
+      | *[out]* **dest** translated matrix
+
+.. c:function:: void  glm_translate(mat4 m, vec3 v)
+
+    translate existing transform matrix by *v* vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_translate_x(mat4 m, float x)
+
+    translate existing transform matrix by x factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  x factor
+
+.. c:function:: void  glm_translate_y(mat4 m, float y)
+
+    translate existing transform matrix by *y* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  y factor
+
+.. c:function:: void  glm_translate_z(mat4 m, float z)
+
+    translate existing transform matrix by *z* factor
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  z factor
+
+.. c:function:: void  glm_translate_make(mat4 m, vec3 v)
+
+    creates NEW translate transform matrix by *v* vector.
+
+    Parameters:
+      | *[in, out]* **m**  affine transfrom
+      | *[in]*      **v**  translate vector [x, y, z]
+
+.. c:function:: void  glm_scale_to(mat4 m, vec3 v, mat4 dest)
+
+    scale existing transform matrix by *v* vector and store result in dest
+
+    Parameters:
+      | *[in]*  **m**    affine transfrom
+      | *[in]*  **v**    scale vector [x, y, z]
+      | *[out]* **dest** scaled matrix
+
+.. c:function:: void  glm_scale_make(mat4 m, vec3 v)
+
+    creates NEW scale matrix by v vector
+
+    Parameters:
+      | *[out]* **m** affine transfrom
+      | *[in]*  **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale(mat4 m, vec3 v)
+
+    scales existing transform matrix by v vector
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale vector [x, y, z]
+
+.. c:function:: void  glm_scale_uni(mat4 m, float s)
+
+    applies uniform scale to existing transform matrix v = [s, s, s]
+    and stores result in same matrix
+
+    Parameters:
+      | *[in, out]* **m** affine transfrom
+      | *[in]*      **v** scale factor
+
+.. c:function:: void  glm_rotate_x(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around X axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotate_y(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Y axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotate_z(mat4 m, float angle, mat4 dest)
+
+    rotate existing transform matrix around Z axis by angle
+    and store result in dest
+
+    Parameters:
+      | *[in]*  **m**     affine transfrom
+      | *[in]*  **angle** angle (radians)
+      | *[out]* **dest**  rotated matrix
+
+.. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
+
+    creates NEW rotation matrix by angle and axis,
+    axis will be normalized so you don't need to normalize it
+
+    Parameters:
+      | *[out]* **m**    affine transfrom
+      | *[in]*  **axis** angle (radians)
+      | *[in]*  **axis** axis
+
+.. c:function:: void  glm_rotate(mat4 m, float angle, vec3 axis)
+
+    rotate existing transform matrix around Z axis by angle and axis
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis)
+
+    rotate existing transform around given axis by angle at given pivot point (rotation center)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **pivot** pivot, anchor point, rotation center
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis)
+
+    | creates NEW rotation matrix by angle and axis at given point
+    | this creates rotation matrix, it assumes you don't have a matrix
+
+    | this should work faster than glm_rotate_at because it reduces one glm_translate.
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **pivot** pivot, anchor point, rotation center
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis
+
+.. c:function:: void  glm_decompose_scalev(mat4 m, vec3 s)
+
+    decompose scale vector
+
+    Parameters:
+      | *[in]*  **m**  affine transform
+      | *[out]* **s**  scale vector (Sx, Sy, Sz)
+
+.. c:function:: bool  glm_uniscaled(mat4 m)
+
+    returns true if matrix is uniform scaled.
+    This is helpful for creating normal matrix.
+
+    Parameters:
+      | *[in]*  **m**   matrix
+
+.. c:function:: void  glm_decompose_rs(mat4 m, mat4 r, vec3 s)
+
+    decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transform
+      | *[out]* **r** rotation matrix
+      | *[out]* **s** scale matrix
+
+.. c:function:: void  glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s)
+
+    decompose affine transform, TODO: extract shear factors.
+    DON'T pass projected matrix here
+
+    Parameters:
+      | *[in]*  **m** affine transfrom
+      | *[out]* **t** translation vector
+      | *[out]* **r** rotation matrix (mat4)
+      | *[out]* **s** scaling vector [X, Y, Z]
+
+.. c:function:: void  glm_spin(mat4 m, float angle, vec3 axis)
+
+    | rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+
+    Parameters:
+      | *[in, out]* **m**     affine transfrom
+      | *[in]*      **angle** angle (radians)
+      | *[in]*      **axis**  axis

docs/source/affine.rst

@@ -5,6 +5,18 @@
 
 Header: cglm/affine.h
 
+Before starting, **cglm** provides two kind of transform functions; pre and post. 
+
+Pre functions (`T' = Tnew * T`) are like `glm_translate`, `glm_rotate` which means it will translate the vector first and then apply the model transformation.
+Post functions (`T' = T * Tnew`) are like `glm_translated`, `glm_rotated` which means it will apply the model transformation first and then translate the vector.
+
+`glm_translate`, `glm_rotate` are pre functions and are similar to C++ **glm** which you are familiar with. 
+
+In new versions of **cglm** we added `glm_translated`, `glm_rotated`... which are post functions, 
+they are useful in some cases, e.g. append transform to existing transform (apply/append transform as last transfrom T' = T * Tnew).
+
+Post functions are named after pre functions with `ed` suffix, e.g. `glm_translate` -> `glm_translated`. So don't mix them up.
+
 Initialize Transform Matrices
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Functions with **_make** prefix expect you don't have a matrix and they create
@@ -25,6 +37,9 @@ since scale factors are stored in rotation matrix, same may also true for scalli
 cglm provides some functions for rotating around at given point e.g.
 **glm_rotate_at**, **glm_quat_rotate_at**. Use them or follow next section for algorihm ("Rotate or Scale around specific Point (Pivot Point / Anchor Point)").
 
+Also **cglm** provides :c:func:`glm_spin` and :c:func:`glm_spinned` functions to rotate around itself. No need to give pivot.
+These functions are useful for rotating around center of object. 
+
 Rotate or Scale around specific Point (Anchor Point)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -35,6 +50,7 @@ If you want to rotate model around arbibtrary point follow these steps:
 3. Move model back from origin to pivot (reverse of step-1): **translate(pivot.x, pivot.y, pivot.z)**
 
 **glm_rotate_at**, **glm_quat_rotate_at** and their helper functions works that way. 
+So if you use them you don't need to do these steps manually which are done by **cglm**.
 
 The implementation would be:
 
@@ -45,6 +61,13 @@ The implementation would be:
   glm_rotate(m, angle, axis);
   glm_translate(m, pivotInv); /* pivotInv = -pivot */
 
+or just:
+
+.. code-block:: c
+  :linenos:
+
+  glm_rotate_at(m, pivot, angle, axis);
+
 .. _TransformsOrder:
 
 Transforms Order
@@ -54,7 +77,7 @@ It is important to understand this part especially if you call transform
 functions multiple times
 
 `glm_translate`, `glm_rotate`, `glm_scale` and `glm_quat_rotate` and their
-helpers functions works like this (cglm may provide reverse order too as alternative in the future):
+helpers functions works like this (cglm provides reverse order as `ed` suffix e.g `glm_translated`, `glm_rotated` see post transforms):
 
 .. code-block:: c
   :linenos:
@@ -147,199 +170,27 @@ Functions:
 #. :c:func:`glm_decompose_rs`
 #. :c:func:`glm_decompose`
 
+Post functions (**NEW**):
+
+1. :c:func:`glm_translated_to`
+#. :c:func:`glm_translated`
+#. :c:func:`glm_translated_x`
+#. :c:func:`glm_translated_y`
+#. :c:func:`glm_translated_z`
+#. :c:func:`glm_rotated_x`
+#. :c:func:`glm_rotated_y`
+#. :c:func:`glm_rotated_z`
+#. :c:func:`glm_rotated`
+#. :c:func:`glm_rotated_at`
+#. :c:func:`glm_spinned`
+
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
 
-.. c:function:: void  glm_translate_to(mat4 m, vec3 v, mat4 dest)
+.. toctree::
+   :maxdepth: 1
+   :caption: Affine categories:
 
-    translate existing transform matrix by *v* vector and store result in dest
+   affine-common
-
+   affine-pre
-    Parameters:
+   affine-post
-      | *[in]*  **m**    affine transfrom
-      | *[in]*  **v**    translate vector [x, y, z]
-      | *[out]* **dest** translated matrix
-
-.. c:function:: void  glm_translate(mat4 m, vec3 v)
-
-    translate existing transform matrix by *v* vector
-    and stores result in same matrix
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  translate vector [x, y, z]
-
-.. c:function:: void  glm_translate_x(mat4 m, float x)
-
-    translate existing transform matrix by x factor
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  x factor
-
-.. c:function:: void  glm_translate_y(mat4 m, float y)
-
-    translate existing transform matrix by *y* factor
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  y factor
-
-.. c:function:: void  glm_translate_z(mat4 m, float z)
-
-    translate existing transform matrix by *z* factor
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  z factor
-
-.. c:function:: void  glm_translate_make(mat4 m, vec3 v)
-
-    creates NEW translate transform matrix by *v* vector.
-
-    Parameters:
-      | *[in, out]* **m**  affine transfrom
-      | *[in]*      **v**  translate vector [x, y, z]
-
-.. c:function:: void  glm_scale_to(mat4 m, vec3 v, mat4 dest)
-
-    scale existing transform matrix by *v* vector and store result in dest
-
-    Parameters:
-      | *[in]*  **m**    affine transfrom
-      | *[in]*  **v**    scale vector [x, y, z]
-      | *[out]* **dest** scaled matrix
-
-.. c:function:: void  glm_scale_make(mat4 m, vec3 v)
-
-    creates NEW scale matrix by v vector
-
-    Parameters:
-      | *[out]* **m** affine transfrom
-      | *[in]*  **v** scale vector [x, y, z]
-
-.. c:function:: void  glm_scale(mat4 m, vec3 v)
-
-    scales existing transform matrix by v vector
-    and stores result in same matrix
-
-    Parameters:
-      | *[in, out]* **m** affine transfrom
-      | *[in]*      **v** scale vector [x, y, z]
-
-.. c:function:: void  glm_scale_uni(mat4 m, float s)
-
-    applies uniform scale to existing transform matrix v = [s, s, s]
-    and stores result in same matrix
-
-    Parameters:
-      | *[in, out]* **m** affine transfrom
-      | *[in]*      **v** scale factor
-
-.. c:function:: void  glm_rotate_x(mat4 m, float angle, mat4 dest)
-
-    rotate existing transform matrix around X axis by angle
-    and store result in dest
-
-    Parameters:
-      | *[in]*  **m**     affine transfrom
-      | *[in]*  **angle** angle (radians)
-      | *[out]* **dest**  rotated matrix
-
-.. c:function:: void  glm_rotate_y(mat4 m, float angle, mat4 dest)
-
-    rotate existing transform matrix around Y axis by angle
-    and store result in dest
-
-    Parameters:
-      | *[in]*  **m**     affine transfrom
-      | *[in]*  **angle** angle (radians)
-      | *[out]* **dest**  rotated matrix
-
-.. c:function:: void  glm_rotate_z(mat4 m, float angle, mat4 dest)
-
-    rotate existing transform matrix around Z axis by angle
-    and store result in dest
-
-    Parameters:
-      | *[in]*  **m**     affine transfrom
-      | *[in]*  **angle** angle (radians)
-      | *[out]* **dest**  rotated matrix
-
-.. c:function:: void  glm_rotate_make(mat4 m, float angle, vec3 axis)
-
-    creates NEW rotation matrix by angle and axis,
-    axis will be normalized so you don't need to normalize it
-
-    Parameters:
-      | *[out]* **m**    affine transfrom
-      | *[in]*  **axis** angle (radians)
-      | *[in]*  **axis** axis
-
-.. c:function:: void  glm_rotate(mat4 m, float angle, vec3 axis)
-
-    rotate existing transform matrix around Z axis by angle and axis
-
-    Parameters:
-      | *[in, out]* **m**     affine transfrom
-      | *[in]*      **angle** angle (radians)
-      | *[in]*      **axis**  axis
-
-.. c:function:: void  glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis)
-
-    rotate existing transform around given axis by angle at given pivot point (rotation center)
-
-    Parameters:
-      | *[in, out]* **m**     affine transfrom
-      | *[in]*      **pivot** pivot, anchor point, rotation center
-      | *[in]*      **angle** angle (radians)
-      | *[in]*      **axis**  axis
-
-.. c:function:: void  glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis)
-
-    | creates NEW rotation matrix by angle and axis at given point
-    | this creates rotation matrix, it assumes you don't have a matrix
-
-    | this should work faster than glm_rotate_at because it reduces one glm_translate.
-
-    Parameters:
-      | *[in, out]* **m**     affine transfrom
-      | *[in]*      **pivot** pivot, anchor point, rotation center
-      | *[in]*      **angle** angle (radians)
-      | *[in]*      **axis**  axis
-
-.. c:function:: void  glm_decompose_scalev(mat4 m, vec3 s)
-
-    decompose scale vector
-
-    Parameters:
-      | *[in]*  **m**  affine transform
-      | *[out]* **s**  scale vector (Sx, Sy, Sz)
-
-.. c:function:: bool  glm_uniscaled(mat4 m)
-
-    returns true if matrix is uniform scaled.
-    This is helpful for creating normal matrix.
-
-    Parameters:
-      | *[in]*  **m**   matrix
-
-.. c:function:: void  glm_decompose_rs(mat4 m, mat4 r, vec3 s)
-
-    decompose rotation matrix (mat4) and scale vector [Sx, Sy, Sz]
-    DON'T pass projected matrix here
-
-    Parameters:
-      | *[in]*  **m** affine transform
-      | *[out]* **r** rotation matrix
-      | *[out]* **s** scale matrix
-
-.. c:function:: void  glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s)
-
-    decompose affine transform, TODO: extract shear factors.
-    DON'T pass projected matrix here
-
-    Parameters:
-      | *[in]*  **m** affine transfrom
-      | *[out]* **t** translation vector
-      | *[out]* **r** rotation matrix (mat4)
-      | *[out]* **s** scaling vector [X, Y, Z]

docs/source/api.rst

@@ -1,56 +1,28 @@
-API documentation
+📚 API documentation
 ================================
 
-Some functions may exist twice,
+**cglm** provides a few APIs for similar functions.
-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_vec3_dot` to get dot product
+* 📦 **Inline API**: All functions are inline. You can include **cglm/cglm.h** header
-of two **vec3**. Now we can also do this with :code:`glm_dot`,
+  to use this API. This is the default API. `glm_` is namespace/prefix for this API. 
-same for *_cross* and so on...
+* 📦 **Call API**: All functions are not inline. You need to build *cglm* and link it
+  to your project. You can include **cglm/call.h** header to use this API. `glmc_` is namespace/prefix for this API. 
 
-The original function stays where it is, the function in global namespace
+And also there are also sub categories:
-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_vec3_dot`
 
-By including **cglm/cglm.h** header you will include all inline version
+* 📦 **Array API**: Types are raw arrays and functions takes array as argument. You can include **cglm/cglm.h** header
-of functions. Since functions in this header[s] are inline you don't need to
+  to use this API. This is the default API. `glm_` is namespace/prefix for this API. 
-build or link *cglm* against your project.
+* 📦 **Struct API**: Types are union/struct and functions takes struct as argument and return structs if needed. You can include **cglm/struct.h** header
+  to use this API. This also includes **cglm/cglm.h** header.`glms_` is namespace/prefix for this API but your can omit or change it, see struct api docs.
+* 📦 **SIMD API**: SIMD functions and helpers. `glmm_` is namespace/prefix for this API. 
 
-But by including **cglm/call.h** header you will include all *non-inline*
+📌 Since struct api and call api are built top of inline array api, follow inline array api docs for individual functions. 
-version of functions. You need to build *cglm* and link it.
-Follow the :doc:`build` documentation for this
 
 .. toctree::
    :maxdepth: 1
-   :caption: API categories:
+   :caption: API documentations:
 
-   affine
+   api_inline_array
-   affine-mat
+   api_struct
-   affine2d
+   api_call
-   cam
+   api_simd
-   frustum
-   box
-   quat
-   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/api_call.rst

@@ -0,0 +1,11 @@
+Call API
+================================
+
+Call API is pre-built API for making calls from library. It is built on top of the array api. **glmc_** is the namespace for the call api. 
+**c** stands for call. 
+
+You need to built cglm to use call api. See build instructions (:doc:`build`) for more details.
+
+The functions except namespace **glmc_** are same as inline api. See ( :doc:`api_inline_array` ) for more details.
+
+📌 In the future we can define option to forward inline functions or struct api to call api.

docs/source/api_inline_array.rst

@@ -0,0 +1,76 @@
+Array API - Inline (Default)
+========================================
+
+This is the default API of *cglm*. All functions are forced to be inlined 
+and struct api, call api uses this inline api to share implementation.
+
+📌 Call api is also array api but it is not inlined. 
+In the future there may be option to forward struct api to call api instead of inline api to reduce binary size if needed.
+
+📌 **USE this API docs for similar functions in struct and call api** 
+
+📌 In struct api you can omit namespace e.g :code:`glms_vec3_dot` can be called as :code:`vec3_dot` in struct api, see :doc:`struct-api` to configure struct api for more details. 
+📌 In struct api functions can return struct/union
+📌 In struct api you can access items like **.x**, **.y**, **.z**, **.w**, **.r**, **.g**, **.b**, **.a**, **.m00**, **m01**... 
+
+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_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_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
+build or link *cglm* against your project.
+
+But by including **cglm/call.h** header you will include all *non-inline*
+version of functions. You need to build *cglm* and link it.
+Follow the :doc:`build` documentation for this
+
+.. toctree::
+   :maxdepth: 1
+   :caption: API categories:
+
+   affine
+   affine-mat
+   affine2d
+   cam
+   frustum
+   box
+   quat
+   euler
+   mat2
+   mat2x3
+   mat2x4
+   mat3
+   mat3x2
+   mat3x4
+   mat4
+   mat4x2
+   mat4x3
+   vec2
+   vec2-ext
+   vec3
+   vec3-ext
+   vec4
+   vec4-ext
+   ivec2
+   ivec3
+   ivec4
+   color
+   plane
+   project
+   util
+   io
+   call
+   sphere
+   curve
+   bezier
+   version
+   ray

docs/source/api_simd.rst

@@ -0,0 +1,12 @@
+SIMD API
+================================
+
+SIMD api is special api for SIMD operations. **glmm_** prefix is used for SIMD operations in cglm. It is used in many places in cglm.
+You can use it for your own SIMD operations too. In the future the api may be extended by time.
+
+Supported SIMD architectures ( may vary by time )
+
+* SSE / SSE2
+* AVX
+* NEON
+* WASM 128

docs/source/api_struct.rst

@@ -0,0 +1,98 @@
+Struct API 
+================================
+
+Struct API is alternative API to array api to use **cglm** with improved type safety and easy to use. 
+Since struct api is built top of array api, every struct API is not documented here. 
+See array api documentation for more information for individual functions.
+
+By default struct api adds `s` suffix to every type name e.g. vec3s, mat4s, versors etc. 
+Also struct api `s` suffix to namespace e.g. `glms_vec3_add`, `glms_mat4_mul` etc.
+
+By starting v0.9.0, struct api namespace is configurable. We can omit **glms_** namespace or 
+even change it with custom name to move existing api integrations to **cglm** more easliy...
+We can also add **s** to functin names if we want e.g. `glms_vec3_add()` -> `vec3_add()` or `vec3s_add()`.
+
+By including **cglm/struct.h** header you will include all struct api. It will also include **cglm/cglm.h** too. 
+Since struct apis are inline you don't need to build or link *cglm* against 
+your project unless if you want to use pre-built call-api too.
+
+Struct API is built top of array api. So you can mix them. 
+Use **.raw** union member to access raw array data to use it with array api. 
+
+Unlike array api ([0], [1], [0][0] ...), it is also possible to use struct api 
+with **.x**, **.y**, **.z**, **.w**, **.r**, **.g**, **.b**, **.a**, **.m00**, **m01**... 
+accessors to access individual elements/properties of vectors and matrices.
+
+Struct API usage:
+-----------------
+
+.. code-block:: c
+
+   #include <cglm/struct.h>
+   
+   mat4s m1  = glms_mat4_identity(); /* init...  */
+   mat4s m2  = glms_mat4_identity(); /* init...  */
+   mat4s m3  = glms_mat4_mul(glms_mat4_mul(m1, m2), glms_mat4_mul(m3, m4));
+   
+   vec3s v1  = { 1.0f, 0.0f, 0.0f };
+   vec3s v2  = { 0.0f, 1.0f, 0.0f };
+   vec4s v4  = { 0.0f, 1.0f, 0.0f, 0.0f };
+   vec4  v5a = { 0.0f, 1.0f, 0.0f, 0.0f };
+   
+   mat4s m4 = glms_rotate(m3, M_PI_2, 
+                          glms_vec3_cross(glms_vec3_add(v1, v6) 
+                                          glms_vec3_add(v1, v7)));
+
+   v1.x = 1.0f; v1.y = 0.0f; v1.z = 0.0f;
+   // or
+   v1.raw[0] = 1.0f; v1.raw[1] = 0.0f; v1.raw[2] = 0.0f;
+
+   /* use struct api with array api (mix them). */
+   /* use .raw to access array and use it with array api */
+
+   glm_vec4_add(m4.col[0].raw, v5a, m4.col[0].raw);
+   glm_mat4_mulv(m4.raw, v4.raw, v5a);
+
+or omit `glms_` namespace completely (see options below):
+
+.. code-block:: c
+
+   #define CGLM_OMIT_NS_FROM_STRUCT_API
+
+   #include <cglm/struct.h>
+
+   mat4s m1  = mat4_identity(); /* init...  */
+   mat4s m2  = mat4_identity(); /* init...  */
+   mat4s m3  = mat4_mul(mat4_mul(m1, m2), mat4_mul(m3, m4));
+   
+   vec3s v1  = { 1.0f, 0.0f, 0.0f };
+   vec3s v2  = { 0.0f, 1.0f, 0.0f };
+   vec4s v4  = { 0.0f, 1.0f, 0.0f, 0.0f };
+   vec4  v5a = { 0.0f, 1.0f, 0.0f, 0.0f };
+   
+   mat4s m4 = glms_rotate(m3, M_PI_2, 
+                          vec3_cross(vec3_add(v1, v6) 
+                                     vec3_add(v1, v7)));
+   
+   v1.x = 1.0f; v1.y = 0.0f; v1.z = 0.0f;
+   // or
+   v1.raw[0] = 1.0f; v1.raw[1] = 0.0f; v1.raw[2] = 0.0f;
+
+   /* use struct api with array api (mix them) */
+   glm_vec4_add(m4.col[0].raw, v5a, m4.col[0].raw);
+   glm_mat4_mulv(m4.raw, v4.raw, v5a);
+   
+Configuring the Struct API:
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To configure the Struct API namespace, you can define the following macros before including the cglm/struct.h header:
+
+- **CGLM_OMIT_NS_FROM_STRUCT_API**: omits CGLM_STRUCT_API_NS (`glms_`) namespace completely if there is sub namespace e.g `mat4_`, `vec4_` ... DEFAULT is not defined
+- **CGLM_STRUCT_API_NS**:           define name space for struct api, DEFAULT is **glms**
+- **CGLM_STRUCT_API_NAME_SUFFIX**:  define name suffix, DEFAULT is **empty** e.g defining it as #define CGLM_STRUCT_API_NAME_SUFFIX  s will add s suffix to mat4_mul -> mat4s_mul
+
+
+Detailed documentation for Struct API:
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Since struct api if built top of array api, see array api functions for more information about individual functions.

docs/source/cam.rst

@@ -101,7 +101,7 @@ Functions documentation
     Parameters:
       | *[in]*  **box**      AABB
       | *[in]*  **padding**  padding
-      | *[out]* **d**        result matrix
+      | *[out]* **dest**        result matrix
 
 .. c:function:: void  glm_ortho_aabb_pz(vec3 box[2], float padding, mat4 dest)
 
@@ -113,7 +113,7 @@ Functions documentation
     Parameters:
       | *[in]*  **box**      AABB
       | *[in]*  **padding**  padding for near and far
-      | *[out]* **d**        result matrix
+      | *[out]* **dest**        result matrix
 
     Returns:
       square of norm / magnitude

docs/source/conf.py

@@ -62,16 +62,16 @@ author = u'Recep Aslantas'
 # built documents.
 #
 # The short X.Y version.
-version = u'0.8.5'
+version = u'0.9.1'
 # The full version, including alpha/beta/rc tags.
-release = u'0.8.5'
+release = u'0.9.1'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en'
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -111,7 +111,7 @@ html_theme_options = {
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+# html_static_path = ['_static']
 
 
 # -- Options for HTMLHelp output ------------------------------------------

docs/source/features.rst

@@ -1,7 +1,7 @@
 Features
 ================================================================================
 
-* **scalar** and **simd** (sse, avx, neon...) optimizations
+* **scalar** and **simd** (sse, avx, neon, wasm...) optimizations
 * option to use different clipspaces e.g. Left Handed, Zero-to-One... (currrently right handed negative-one is default)
 * array api and struct api, you can use arrays or structs.
 * general purpose matrix operations (mat4, mat3)

docs/source/index.rst

@@ -6,13 +6,12 @@
 cglm Documentation
 ================================
 
-**cglm** is optimized 3D math library written in C99 (compatible with C89).
+**cglm** is an optimized 3D math library written in C99 (compatible with C89).
-It is similar to original **glm** library except this is mainly for **C**
+It is similar to the original **glm** library, except **cglm** is mainly for
+**C**.
 
-This library stores matrices as column-major order but in the future row-major
+**cglm** stores matrices as column-major order but in the future row-major is
-is considered to be supported as optional.
+considered to be supported as optional.
-
-Also currently only **float** type is supported for most operations.
 
 .. toctree::
    :maxdepth: 2
@@ -29,7 +28,7 @@ Also currently only **float** type is supported for most operations.
    opengl
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 3
    :caption: API:
 
    api
@@ -46,8 +45,8 @@ Also currently only **float** type is supported for most operations.
 
    troubleshooting
 
-Indices and tables
+Indices and Tables:
-==================
+===================
 
 * :ref:`genindex`
 * :ref:`modindex`

docs/source/ivec2.rst

@@ -0,0 +1,179 @@
+.. default-domain:: C
+
+ivec2
+=====
+
+Header: cglm/ivec2.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_IVEC2_ONE_INIT
+#. GLM_IVEC2_ZERO_INIT
+#. GLM_IVEC2_ONE
+#. GLM_IVEC2_ZERO
+
+Functions:
+
+1. :c:func:`glm_ivec2`
+#. :c:func:`glm_ivec2_copy`
+#. :c:func:`glm_ivec2_zero`
+#. :c:func:`glm_ivec2_one`
+#. :c:func:`glm_ivec2_add`
+#. :c:func:`glm_ivec2_adds`
+#. :c:func:`glm_ivec2_sub`
+#. :c:func:`glm_ivec2_subs`
+#. :c:func:`glm_ivec2_mul`
+#. :c:func:`glm_ivec2_scale`
+#. :c:func:`glm_ivec2_distance2`
+#. :c:func:`glm_ivec2_distance`
+#. :c:func:`glm_ivec2_maxv`
+#. :c:func:`glm_ivec2_minv`
+#. :c:func:`glm_ivec2_clamp`
+#. :c:func:`glm_ivec2_abs`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_ivec2(int * v, ivec2 dest)
+    
+    init ivec2 using vec3 or vec4
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_copy(ivec2 a, ivec2 dest)
+    
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**    source vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_zero(ivec2 v)
+
+    set all members of [v] to zero
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec2_one(ivec2 v)
+
+    set all members of [v] to one
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec2_add(ivec2 a, ivec2 b, ivec2 dest)
+
+    add vector [a] to vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_adds(ivec2 v, int s, ivec2 dest)
+
+    add scalar s to vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest)
+
+    subtract vector [b] from vector [a] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_subs(ivec2 v, int s, ivec2 dest)
+
+    subtract scalar s from vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest)
+
+    multiply vector [a] with vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_scale(ivec2 v, int s, ivec2 dest)
+
+    multiply vector [a] with scalar s and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: int glm_ivec2_distance2(ivec2 a, ivec2 b)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        squared distance (distance * distance)
+
+.. c:function:: float glm_ivec2_distance(ivec2 a, ivec2 b)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        distance
+
+.. c:function:: void glm_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest)
+
+    set each member of dest to greater of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest)
+
+    set each member of dest to lesser of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec2_clamp(ivec2 v, int minVal, int maxVal)
+
+    clamp each member of [v] between minVal and maxVal (inclusive)
+
+    Parameters:
+      | *[in, out]* **v**      vector
+      | *[in]*      **minVal** minimum value
+      | *[in]*      **maxVal** maximum value
+
+.. c:function:: void glm_ivec2_abs(ivec2 v, ivec2 dest)
+
+    absolute value of each vector item
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  destination vector

docs/source/ivec3.rst

@@ -0,0 +1,179 @@
+.. default-domain:: C
+
+ivec3
+=====
+
+Header: cglm/ivec3.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_IVEC3_ONE_INIT
+#. GLM_IVEC3_ZERO_INIT
+#. GLM_IVEC3_ONE
+#. GLM_IVEC3_ZERO
+
+Functions:
+
+1. :c:func:`glm_ivec3`
+#. :c:func:`glm_ivec3_copy`
+#. :c:func:`glm_ivec3_zero`
+#. :c:func:`glm_ivec3_one`
+#. :c:func:`glm_ivec3_add`
+#. :c:func:`glm_ivec3_adds`
+#. :c:func:`glm_ivec3_sub`
+#. :c:func:`glm_ivec3_subs`
+#. :c:func:`glm_ivec3_mul`
+#. :c:func:`glm_ivec3_scale`
+#. :c:func:`glm_ivec3_distance2`
+#. :c:func:`glm_ivec3_distance`
+#. :c:func:`glm_ivec3_maxv`
+#. :c:func:`glm_ivec3_minv`
+#. :c:func:`glm_ivec3_clamp`
+#. :c:func:`glm_ivec2_abs`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_ivec3(ivec4 v4, ivec3 dest)
+    
+    init ivec3 using ivec4
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_copy(ivec3 a, ivec3 dest)
+    
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**    source vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_zero(ivec3 v)
+
+    set all members of [v] to zero
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec3_one(ivec3 v)
+
+    set all members of [v] to one
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec3_add(ivec3 a, ivec3 b, ivec3 dest)
+
+    add vector [a] to vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_adds(ivec3 v, int s, ivec3 dest)
+
+    add scalar s to vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest)
+
+    subtract vector [b] from vector [a] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_subs(ivec3 v, int s, ivec3 dest)
+
+    subtract scalar s from vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest)
+
+    multiply vector [a] with vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_scale(ivec3 v, int s, ivec3 dest)
+
+    multiply vector [a] with scalar s and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: int glm_ivec3_distance2(ivec3 a, ivec3 b)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        squared distance (distance * distance)
+
+.. c:function:: float glm_ivec3_distance(ivec3 a, ivec3 b)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        distance
+
+.. c:function:: void glm_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest)
+
+    set each member of dest to greater of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest)
+
+    set each member of dest to lesser of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec3_clamp(ivec3 v, int minVal, int maxVal)
+
+    clamp each member of [v] between minVal and maxVal (inclusive)
+
+    Parameters:
+      | *[in, out]* **v**      vector
+      | *[in]*      **minVal** minimum value
+      | *[in]*      **maxVal** maximum value
+
+.. c:function:: void glm_ivec3_abs(ivec3 v, ivec3 dest)
+
+    absolute value of each vector item
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  destination vector

docs/source/ivec4.rst

@@ -0,0 +1,179 @@
+.. default-domain:: C
+
+ivec4
+=====
+
+Header: cglm/ivec4.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_IVEC4_ONE_INIT
+#. GLM_IVEC4_ZERO_INIT
+#. GLM_IVEC4_ONE
+#. GLM_IVEC4_ZERO
+
+Functions:
+
+1. :c:func:`glm_ivec4`
+#. :c:func:`glm_ivec4_copy`
+#. :c:func:`glm_ivec4_zero`
+#. :c:func:`glm_ivec4_one`
+#. :c:func:`glm_ivec4_add`
+#. :c:func:`glm_ivec4_adds`
+#. :c:func:`glm_ivec4_sub`
+#. :c:func:`glm_ivec4_subs`
+#. :c:func:`glm_ivec4_mul`
+#. :c:func:`glm_ivec4_scale`
+#. :c:func:`glm_ivec4_distance2`
+#. :c:func:`glm_ivec4_distance`
+#. :c:func:`glm_ivec4_maxv`
+#. :c:func:`glm_ivec4_minv`
+#. :c:func:`glm_ivec4_clamp`
+#. :c:func:`glm_ivec4_abs`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_ivec4(ivec3 v3, int last, ivec4 dest)
+    
+    init ivec4 using ivec3
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_copy(ivec4 a, ivec4 dest)
+    
+    copy all members of [a] to [dest]
+
+    Parameters:
+      | *[in]*  **a**    source vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_zero(ivec4 v)
+
+    set all members of [v] to zero
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec4_one(ivec4 v)
+
+    set all members of [v] to one
+
+    Parameters:
+      | *[out]* **v** vector
+
+.. c:function:: void glm_ivec4_add(ivec4 a, ivec4 b, ivec4 dest)
+
+    add vector [a] to vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_adds(ivec4 v, int s, ivec4 dest)
+
+    add scalar s to vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest)
+
+    subtract vector [b] from vector [a] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_subs(ivec4 v, int s, ivec4 dest)
+
+    subtract scalar s from vector [v] and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest)
+
+    multiply vector [a] with vector [b] and store result in [dest]
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_scale(ivec4 v, int s, ivec4 dest)
+
+    multiply vector [a] with scalar s and store result in [dest]
+    
+    Parameters:
+      | *[in]*  **v**    vector
+      | *[in]*  **s**    scalar
+      | *[out]* **dest** destination
+
+.. c:function:: int glm_ivec4_distance2(ivec4 a, ivec4 b)
+
+    squared distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        squared distance (distance * distance)
+
+.. c:function:: float glm_ivec4_distance(ivec4 a, ivec4 b)
+
+    distance between two vectors
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+    
+    Returns:
+        distance
+
+.. c:function:: void glm_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest)
+
+    set each member of dest to greater of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest)
+
+    set each member of dest to lesser of vector a and b
+
+    Parameters:
+      | *[in]*  **a**    first vector
+      | *[in]*  **b**    second vector
+      | *[out]* **dest** destination
+
+.. c:function:: void glm_ivec4_clamp(ivec4 v, int minVal, int maxVal)
+
+    clamp each member of [v] between minVal and maxVal (inclusive)
+
+    Parameters:
+      | *[in, out]* **v**      vector
+      | *[in]*      **minVal** minimum value
+      | *[in]*      **maxVal** maximum value
+
+.. c:function:: void glm_ivec4_abs(ivec4 v, ivec4 dest)
+
+    absolute value of each vector item
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  destination vector

docs/source/mat2.rst

@@ -32,6 +32,7 @@ Functions:
 #. :c:func:`glm_mat2_swap_col`
 #. :c:func:`glm_mat2_swap_row`
 #. :c:func:`glm_mat2_rmc`
+#. :c:func:`glm_mat2_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -64,11 +65,12 @@ Functions documentation
     make given matrix zero
 
     Parameters:
-      | *[in,out]* **mat**  matrix to
+      | *[in,out]* **mat**  matrix
 
 .. 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
@@ -100,7 +102,7 @@ Functions documentation
 
 .. c:function:: void glm_mat2_mulv(mat2 m, vec2 v, vec2 dest)
 
-    multiply mat4 with vec4 (column vector) and store in dest vector
+    multiply mat2 with vec2 (column vector) and store in dest vector
 
     Parameters:
       | *[in]*  **mat**   mat2 (left)
@@ -112,8 +114,8 @@ Functions documentation
     multiply matrix with scalar
 
     Parameters:
-      | *[in, out]* **mat**   matrix
+      | *[in, out]* **m**  matrix
-      | *[in]*      **dest**  scalar
+      | *[in]*      **s**  scalar
 
 .. c:function:: float  glm_mat2_det(mat2 mat)
 
@@ -177,3 +179,13 @@ Functions documentation
 
     Returns:
         scalar value e.g. Matrix1x1
+
+.. c:function:: void glm_mat2_make(float * __restrict src, mat2 dest)
+
+    Create mat2 matrix from pointer
+
+    | NOTE: **@src** must contain at least 4 elements.
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix2x2

docs/source/mat2x3.rst

@@ -0,0 +1,92 @@
+.. default-domain:: C
+
+mat2x3
+======
+
+Header: cglm/mat2x3.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_MAT2X3_ZERO_INIT
+#. GLM_MAT2X3_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat2x3_copy`
+#. :c:func:`glm_mat2x3_zero`
+#. :c:func:`glm_mat2x3_make`
+#. :c:func:`glm_mat2x3_mul`
+#. :c:func:`glm_mat2x3_mulv`
+#. :c:func:`glm_mat2x3_transpose`
+#. :c:func:`glm_mat2x3_scale`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat2x3_copy(mat2x3 mat, mat2x3 dest)
+
+    copy mat2x3 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat2x3_zero(mat2x3 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix
+
+.. c:function:: void glm_mat2x3_make(float * __restrict src, mat2x3 dest)
+
+    Create mat2x3 matrix from pointer
+
+    | NOTE: **@src** must contain at least 6 elements.
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix2x3
+
+.. c:function:: void glm_mat2x3_mul(mat2x3 m1, mat3x2 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
+
+       glm_mat2x3_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat2x3_mulv(mat2x3 m, vec3 v, vec2 dest)
+
+    multiply mat2x3 with vec3 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **m**     mat2x3 (left)
+      | *[in]*  **v**     vec3 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void glm_mat2x3_transpose(mat2x3 m, mat3x2 dest)
+
+    transpose matrix and store in dest
+
+    Parameters:
+      | *[in]*  **m**     matrix
+      | *[out]* **dest**  destination
+
+.. c:function:: void  glm_mat2x3_scale(mat2x3 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **m** matrix
+      | *[in]*      **s** scalar

docs/source/mat2x4.rst

@@ -0,0 +1,92 @@
+.. default-domain:: C
+
+mat2x4
+======
+
+Header: cglm/mat2x4.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_MAT2X4_ZERO_INIT
+#. GLM_MAT2X4_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat2x4_copy`
+#. :c:func:`glm_mat2x4_zero`
+#. :c:func:`glm_mat2x4_make`
+#. :c:func:`glm_mat2x4_mul`
+#. :c:func:`glm_mat2x4_mulv`
+#. :c:func:`glm_mat2x4_transpose`
+#. :c:func:`glm_mat2x4_scale`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat2x4_copy(mat2x4 mat, mat2x4 dest)
+
+    copy mat2x4 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat2x4_zero(mat2x4 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix
+
+.. c:function:: void glm_mat2x4_make(float * __restrict src, mat2x4 dest)
+
+    Create mat2x4 matrix from pointer
+
+    | NOTE: **@src** must contain at least 8 elements.
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix2x4
+
+.. c:function:: void glm_mat2x4_mul(mat2x4 m1, mat4x2 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
+
+       glm_mat2x4_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat2x4_mulv(mat2x4 m, vec4 v, vec2 dest)
+
+    multiply mat2x4 with vec4 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **m**     mat2x4 (left)
+      | *[in]*  **v**     vec4 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void glm_mat2x4_transpose(mat2x4 m, mat4x2 dest)
+
+    transpose matrix and store in dest
+
+    Parameters:
+      | *[in]*  **m**     matrix
+      | *[out]* **dest**  destination
+
+.. c:function:: void  glm_mat2x4_scale(mat2x4 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **m** matrix
+      | *[in]*      **s** scalar

docs/source/mat3.rst

@@ -34,6 +34,7 @@ Functions:
 #. :c:func:`glm_mat3_swap_col`
 #. :c:func:`glm_mat3_swap_row`
 #. :c:func:`glm_mat3_rmc`
+#. :c:func:`glm_mat3_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -71,6 +72,7 @@ Functions documentation
 .. c:function:: void  glm_mat3_mul(mat3 m1, mat3 m2, mat3 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
@@ -102,10 +104,10 @@ Functions documentation
 
 .. c:function:: void  glm_mat3_mulv(mat3 m, vec3 v, vec3 dest)
 
-    multiply mat4 with vec4 (column vector) and store in dest vector
+    multiply mat3 with vec3 (column vector) and store in dest vector
 
     Parameters:
-      | *[in]*  **mat**   mat3 (left)
+      | *[in]*  **m**     mat3 (left)
       | *[in]*  **v**     vec3 (right, column vector)
       | *[out]* **dest**  destination (result, column vector)
 
@@ -122,8 +124,8 @@ Functions documentation
     multiply matrix with scalar
 
     Parameters:
-      | *[in, out]* **mat**   matrix
+      | *[in, out]* **m** matrix
-      | *[in]*      **dest**  scalar
+      | *[in]*      **s** scalar
 
 .. c:function:: float  glm_mat3_det(mat3 mat)
 
@@ -187,3 +189,13 @@ Functions documentation
 
     Returns:
         scalar value e.g. Matrix1x1
+
+.. c:function:: void glm_mat3_make(float * __restrict src, mat3 dest)
+
+    Create mat3 matrix from pointer
+
+    | NOTE: **@src** must contain at least 9 elements.
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix3x3

docs/source/mat3x2.rst

@@ -0,0 +1,91 @@
+.. default-domain:: C
+
+mat3x2
+======
+
+Header: cglm/mat3x2.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_MAT3X2_ZERO_INIT
+#. GLM_MAT3X2_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat3x2_copy`
+#. :c:func:`glm_mat3x2_zero`
+#. :c:func:`glm_mat3x2_make`
+#. :c:func:`glm_mat3x2_mul`
+#. :c:func:`glm_mat3x2_mulv`
+#. :c:func:`glm_mat3x2_transpose`
+#. :c:func:`glm_mat3x2_scale`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat3x2_copy(mat3x2 mat, mat3x2 dest)
+
+    copy mat3x2 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat3x2_zero(mat3x2 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix
+
+.. c:function:: void glm_mat3x2_make(float * __restrict src, mat3x2 dest)
+
+    Create mat3x2 matrix from pointer
+
+    | NOTE: **@src** must contain at least 6 elements.
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix3x2
+
+.. c:function:: void glm_mat3x2_mul(mat3x2 m1, mat2x3 m2, mat3 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
+
+       glm_mat3x2_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat3x2_mulv(mat3x2 m, vec2 v, vec3 dest)
+
+    multiply mat3x2 with vec2 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **m**     mat3x2 (left)
+      | *[in]*  **v**     vec3 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void glm_mat3x2_transpose(mat3x2 m, mat2x3 dest)
+
+    transpose matrix and store in dest
+
+    Parameters:
+      | *[in]*  **m**     matrix
+      | *[out]* **dest**  destination
+
+.. c:function:: void  glm_mat3x2_scale(mat3x2 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **m** matrix
+      | *[in]*      **s** scalar

docs/source/mat3x4.rst

@@ -0,0 +1,91 @@
+.. default-domain:: C
+
+mat3x4
+======
+
+Header: cglm/mat3x4.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_MAT3X4_ZERO_INIT
+#. GLM_MAT3X4_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat3x4_copy`
+#. :c:func:`glm_mat3x4_zero`
+#. :c:func:`glm_mat3x4_make`
+#. :c:func:`glm_mat3x4_mul`
+#. :c:func:`glm_mat3x4_mulv`
+#. :c:func:`glm_mat3x4_transpose`
+#. :c:func:`glm_mat3x4_scale`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat3x4_copy(mat3x4 mat, mat3x4 dest)
+
+    copy mat3x4 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat3x4_zero(mat3x4 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix
+
+.. c:function:: void glm_mat3x4_make(float * __restrict src, mat3x4 dest)
+
+    Create mat3x4 matrix from pointer
+
+    | NOTE: **@src** must contain at least 12 elements.
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix3x4
+
+.. c:function:: void glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 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
+
+       glm_mat3x4_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest)
+
+    multiply mat3x4 with vec4 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **m**     mat3x4 (left)
+      | *[in]*  **v**     vec4 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void glm_mat3x4_transpose(mat3x4 m, mat4x3 dest)
+
+    transpose matrix and store in dest
+
+    Parameters:
+      | *[in]*  **m**     matrix
+      | *[out]* **dest**  destination
+
+.. c:function:: void  glm_mat3x4_scale(mat3x4 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **m** matrix
+      | *[in]*      **s** scalar

docs/source/mat4.rst

@@ -47,6 +47,7 @@ Functions:
 #. :c:func:`glm_mat4_swap_col`
 #. :c:func:`glm_mat4_swap_row`
 #. :c:func:`glm_mat4_rmc`
+#. :c:func:`glm_mat4_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -118,6 +119,7 @@ Functions documentation
 .. c:function:: void  glm_mat4_mul(mat4 m1, mat4 m2, mat4 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
@@ -156,7 +158,6 @@ 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, float last, vec3 dest)
@@ -302,3 +303,13 @@ Functions documentation
 
     Returns:
         scalar value e.g. Matrix1x1
+
+.. c:function:: void glm_mat4_make(float * __restrict src, mat4 dest)
+
+    Create mat4 matrix from pointer
+
+    | NOTE: **@src** must contain at least 16 elements.
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix4x4

docs/source/mat4x2.rst

@@ -0,0 +1,91 @@
+.. default-domain:: C
+
+mat4x2
+======
+
+Header: cglm/mat4x2.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_MAT4X2_ZERO_INIT
+#. GLM_MAT4X2_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat4x2_copy`
+#. :c:func:`glm_mat4x2_zero`
+#. :c:func:`glm_mat4x2_make`
+#. :c:func:`glm_mat4x2_mul`
+#. :c:func:`glm_mat4x2_mulv`
+#. :c:func:`glm_mat4x2_transpose`
+#. :c:func:`glm_mat4x2_scale`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat4x2_copy(mat4x2 mat, mat4x2 dest)
+
+    copy mat4x2 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat4x2_zero(mat4x2 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix
+
+.. c:function:: void glm_mat4x2_make(float * __restrict src, mat4x2 dest)
+
+    Create mat4x2 matrix from pointer
+
+    | NOTE: **@src** must contain at least 8 elements.
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix4x2
+
+.. c:function:: void glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 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
+
+       glm_mat4x2_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest)
+
+    multiply mat4x2 with vec2 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **m**     mat4x2 (left)
+      | *[in]*  **v**     vec2 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void glm_mat4x2_transpose(mat4x2 m, mat2x4 dest)
+
+    transpose matrix and store in dest
+
+    Parameters:
+      | *[in]*  **m**     matrix
+      | *[out]* **dest**  destination
+
+.. c:function:: void  glm_mat4x2_scale(mat4x2 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **m** matrix
+      | *[in]*      **s** scalar

docs/source/mat4x3.rst

@@ -0,0 +1,91 @@
+.. default-domain:: C
+
+mat4x3
+======
+
+Header: cglm/mat4x3.h
+
+Table of contents (click to go):
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Macros:
+
+1. GLM_MAT4X3_ZERO_INIT
+#. GLM_MAT4X3_ZERO
+
+Functions:
+
+1. :c:func:`glm_mat4x3_copy`
+#. :c:func:`glm_mat4x3_zero`
+#. :c:func:`glm_mat4x3_make`
+#. :c:func:`glm_mat4x3_mul`
+#. :c:func:`glm_mat4x3_mulv`
+#. :c:func:`glm_mat4x3_transpose`
+#. :c:func:`glm_mat4x3_scale`
+
+Functions documentation
+~~~~~~~~~~~~~~~~~~~~~~~
+
+.. c:function:: void glm_mat4x3_copy(mat4x3 mat, mat4x3 dest)
+
+    copy mat4x3 to another one (dest).
+
+    Parameters:
+      | *[in]*  **mat**   source
+      | *[out]* **dest**  destination
+
+.. c:function:: void glm_mat4x3_zero(mat4x3 mat)
+
+    make given matrix zero
+
+    Parameters:
+      | *[in,out]* **mat**  matrix
+
+.. c:function:: void glm_mat4x3_make(float * __restrict src, mat4x3 dest)
+
+    Create mat4x3 matrix from pointer
+
+    | NOTE: **@src** must contain at least 12 elements.
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination matrix4x3
+
+.. c:function:: void glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 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
+
+       glm_mat4x3_mul(m, m, m);
+
+    Parameters:
+      | *[in]*  **m1**    left matrix
+      | *[in]*  **m2**    right matrix
+      | *[out]* **dest**  destination matrix
+
+.. c:function:: void glm_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest)
+
+    multiply mat4x3 with vec3 (column vector) and store in dest vector
+
+    Parameters:
+      | *[in]*  **m**     mat4x3 (left)
+      | *[in]*  **v**     vec3 (right, column vector)
+      | *[out]* **dest**  destination (result, column vector)
+
+.. c:function:: void glm_mat4x3_transpose(mat4x3 m, mat3x4 dest)
+
+    transpose matrix and store in dest
+
+    Parameters:
+      | *[in]*  **m**     matrix
+      | *[out]* **dest**  destination
+
+.. c:function:: void  glm_mat4x3_scale(mat4x3 m, float s)
+
+    multiply matrix with scalar
+
+    Parameters:
+      | *[in, out]* **m** matrix
+      | *[in]*      **s** scalar

docs/source/opt.rst

@@ -1,6 +1,6 @@
 .. default-domain:: C
 
-Options
+🛠️ Options
 ===============================================================================
 
 A few options are provided via macros.
@@ -90,6 +90,16 @@ You have to extra options for dot product: **CGLM_SSE4_DOT** and **CGLM_SSE3_DOT
 
 otherwise cglm will use custom cglm's hadd functions which are optimized too.
 
+Struct API Options
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+To configure the Struct API namespace, you can define the following macros before including the cglm/struct.h header:
+
+- **CGLM_OMIT_NS_FROM_STRUCT_API**: omits CGLM_STRUCT_API_NS (`glms_`) namespace completely if there is sub namespace e.g `mat4_`, `vec4_` ... DEFAULT is not defined
+- **CGLM_STRUCT_API_NS**:           define name space for struct api, DEFAULT is **glms**
+- **CGLM_STRUCT_API_NAME_SUFFIX**:  define name suffix, DEFAULT is **empty** e.g defining it as #define CGLM_STRUCT_API_NAME_SUFFIX  s will add s suffix to mat4_mul -> mat4s_mul
+
+
 Print Options
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

docs/source/project.rst

@@ -27,8 +27,8 @@ Functions documentation
       the matrix should contain projection matrix.
 
     if you don't have ( and don't want to have ) an inverse matrix then use
-    glm_unproject version. You may use existing inverse of matrix in somewhere
+    :c:func:`glm_unproject` version. You may use existing inverse of matrix in somewhere
-    else, this is why glm_unprojecti exists to save save inversion cost
+    else, this is why **glm_unprojecti** exists to save inversion cost
 
     [1] space:
       - if m = invProj:     View Space
@@ -57,7 +57,7 @@ Functions documentation
     | maps the specified viewport coordinates into specified space [1]
       the matrix should contain projection matrix.
 
-    this is same as glm_unprojecti except this function get inverse matrix for
+    this is same as :c:func:`glm_unprojecti` except this function get inverse matrix for
     you.
 
     [1] space:
@@ -91,12 +91,29 @@ Functions documentation
        glm_mat4_mul(proj, view, viewProj);
        glm_mat4_mul(viewProj, model, MVP);
 
-    this could be useful for gettng a bbox which fits with view frustum and
-    object bounding boxes. In this case you crop view frustum box with objects
-    box
-
     Parameters:
       | *[in]*  **pos**      object coordinates
       | *[in]*  **m**        MVP matrix
       | *[in]*  **vp**       viewport as [x, y, width, height]
       | *[out]* **dest**     projected coordinates
+
+.. c:function:: float glm_project_z(vec3 pos, mat4 m)
+
+    | map object's z coordinate to window coordinates
+
+    this is same as :c:func:`glm_project` except this function projects only Z coordinate
+    which reduces a few calculations and parameters.
+
+    Computing MVP:
+
+    .. code-block:: c
+
+       glm_mat4_mul(proj, view, viewProj);
+       glm_mat4_mul(viewProj, model, MVP);
+
+    Parameters:
+      | *[in]*  **pos**      object coordinates
+      | *[in]*  **m**        MVP matrix
+
+    Returns:
+        projected z coordinate

docs/source/quat.rst

@@ -62,6 +62,7 @@ Functions:
 #. :c:func:`glm_quat_rotate`
 #. :c:func:`glm_quat_rotate_at`
 #. :c:func:`glm_quat_rotate_atm`
+#. :c:func:`glm_quat_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -420,3 +421,13 @@ Functions documentation
       | *[in, out]*  **m**      existing transform matrix to rotate
       | *[in]*       **q**      quaternion
       | *[in]*       **pivot**  pivot
+
+.. c:function:: void glm_quat_make(float * __restrict src, versor dest)
+
+    Create quaternion from pointer
+
+    | NOTE: **@src** must contain at least 4 elements. cglm store quaternions as [x, y, z, w].
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination quaternion

docs/source/vec2-ext.rst

@@ -26,6 +26,7 @@ Functions:
 #. :c:func:`glm_vec2_isinf`
 #. :c:func:`glm_vec2_isvalid`
 #. :c:func:`glm_vec2_sign`
+#. :c:func:`glm_vec2_abs`
 #. :c:func:`glm_vec2_sqrt`
 
 Functions documentation
@@ -125,6 +126,14 @@ Functions documentation
       | *[in]*   **v**     vector
       | *[out]*  **dest**  sign vector (only keeps signs as -1, 0, -1)
 
+.. c:function:: void glm_vec2_abs(vec2 v, vec2 dest)
+
+    absolute value of each vector item
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  destination vector
+
 .. c:function:: void glm_vec2_sqrt(vec2 v, vec2 dest)
 
     square root of each vector item

docs/source/vec2.rst

@@ -10,10 +10,10 @@ Table of contents (click to go):
 
 Macros:
 
-1. GLM_vec2_ONE_INIT
+1. GLM_VEC2_ONE_INIT
-#. GLM_vec2_ZERO_INIT
+#. GLM_VEC2_ZERO_INIT
-#. GLM_vec2_ONE
+#. GLM_VEC2_ONE
-#. GLM_vec2_ZERO
+#. GLM_VEC2_ZERO
 
 Functions:
 
@@ -51,6 +51,7 @@ Functions:
 #. :c:func:`glm_vec2_minv`
 #. :c:func:`glm_vec2_clamp`
 #. :c:func:`glm_vec2_lerp`
+#. :c:func:`glm_vec2_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -373,3 +374,12 @@ Functions documentation
       | *[in]*  **to**     to value
       | *[in]*  **t**      interpolant (amount) clamped between 0 and 1
       | *[out]* **dest**   destination
+
+.. c:function:: void glm_vec2_make(float * __restrict src, vec2 dest)
+
+    Create two dimensional vector from pointer
+
+    | NOTE: **@src** must contain at least 2 elements.
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination vector

docs/source/vec3-ext.rst

@@ -27,6 +27,7 @@ Functions:
 #. :c:func:`glm_vec3_isinf`
 #. :c:func:`glm_vec3_isvalid`
 #. :c:func:`glm_vec3_sign`
+#. :c:func:`glm_vec3_abs`
 #. :c:func:`glm_vec3_sqrt`
 
 Functions documentation
@@ -134,6 +135,14 @@ Functions documentation
       | *[in]*   **v**     vector
       | *[out]*  **dest**  sign vector (only keeps signs as -1, 0, -1)
 
+.. c:function:: void glm_vec3_abs(vec3 v, vec3 dest)
+
+    absolute value of each vector item
+
+    Parameters:
+      | *[in]*   **v**     vector
+      | *[out]*  **dest**  destination vector
+
 .. c:function:: void glm_vec3_sqrt(vec3 v, vec3 dest)
 
     square root of each vector item

docs/source/vec3.rst

@@ -79,6 +79,7 @@ Functions:
 #. :c:func:`glm_vec3_ortho`
 #. :c:func:`glm_vec3_clamp`
 #. :c:func:`glm_vec3_lerp`
+#. :c:func:`glm_vec3_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -501,3 +502,13 @@ Functions documentation
       | *[in]*  **to**     to value
       | *[in]*  **t**      interpolant (amount) clamped between 0 and 1
       | *[out]* **dest**   destination
+
+.. c:function:: void glm_vec3_make(float * __restrict src, vec3 dest)
+
+    Create three dimensional vector from pointer
+
+    | NOTE: **@src** must contain at least 3 elements.
+
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination vector

docs/source/vec4.rst

@@ -59,6 +59,7 @@ Functions:
 #. :c:func:`glm_vec4_clamp`
 #. :c:func:`glm_vec4_lerp`
 #. :c:func:`glm_vec4_cubic`
+#. :c:func:`glm_vec4_make`
 
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
@@ -406,3 +407,12 @@ Functions documentation
     Parameters:
       | *[in]*  **s**      parameter
       | *[out]* **dest**   destination
+
+.. c:function:: void glm_vec4_make(float * __restrict src, vec4 dest)
+
+    Create four dimensional vector from pointer
+
+    | NOTE: **@src** must contain at least 4 elements.
+    Parameters:
+      | *[in]*  **src**  pointer to an array of floats
+      | *[out]* **dest** destination vector

include/cglm/affine-mat.h

@@ -8,6 +8,7 @@
 /*
  Functions:
    CGLM_INLINE void glm_mul(mat4 m1, mat4 m2, mat4 dest);
+   CGLM_INLINE void glm_mul_rot(mat4 m1, mat4 m2, mat4 dest);
    CGLM_INLINE void glm_inv_tr(mat4 mat);
  */
 
@@ -30,6 +31,10 @@
 #  include "simd/neon/affine.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/affine.h"
+#endif
+
 /*!
  * @brief this is similar to glm_mat4_mul but specialized to affine transform
  *
@@ -49,7 +54,9 @@
 CGLM_INLINE
 void
 glm_mul(mat4 m1, mat4 m2, mat4 dest) {
-#ifdef __AVX__
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mul_wasm(m1, m2, dest);
+#elif defined(__AVX__)
   glm_mul_avx(m1, m2, dest);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mul_sse2(m1, m2, dest);
@@ -107,7 +114,9 @@ glm_mul(mat4 m1, mat4 m2, mat4 dest) {
 CGLM_INLINE
 void
 glm_mul_rot(mat4 m1, mat4 m2, mat4 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mul_rot_wasm(m1, m2, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mul_rot_sse2(m1, m2, dest);
 #elif defined(CGLM_NEON_FP)
   glm_mul_rot_neon(m1, m2, dest);
@@ -156,7 +165,9 @@ glm_mul_rot(mat4 m1, mat4 m2, mat4 dest) {
 CGLM_INLINE
 void
 glm_inv_tr(mat4 mat) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_inv_tr_wasm(mat);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_inv_tr_sse2(mat);
 #elif defined(CGLM_NEON_FP)
   glm_inv_tr_neon(mat);

include/cglm/affine-post.h

@@ -0,0 +1,247 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_affine_post_h
+#define cglm_affine_post_h
+
+/*
+ Functions:
+   CGLM_INLINE void glm_translated_to(mat4 m, vec3 v, mat4 dest);
+   CGLM_INLINE void glm_translated(mat4 m, vec3 v);
+   CGLM_INLINE void glm_translated_x(mat4 m, float to);
+   CGLM_INLINE void glm_translated_y(mat4 m, float to);
+   CGLM_INLINE void glm_translated_z(mat4 m, float to);
+   CGLM_INLINE void glm_rotated_x(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotated_y(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotated_z(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotated(mat4 m, float angle, vec3 axis);
+   CGLM_INLINE void glm_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis);
+   CGLM_INLINE void glm_spinned(mat4 m, float angle, vec3 axis);
+ */
+
+#include "common.h"
+#include "util.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
+#include "affine-mat.h"
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       v  translate vector [x, y, z]
+ */
+CGLM_INLINE
+void
+glm_translated(mat4 m, vec3 v) {
+  glm_vec3_add(m[3], v, m[3]);
+}
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and store result in dest
+ *
+ * source matrix will remain same
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]  m    affine transfrom
+ * @param[in]  v    translate vector [x, y, z]
+ * @param[out] dest translated matrix
+ */
+CGLM_INLINE
+void
+glm_translated_to(mat4 m, vec3 v, mat4 dest) {
+  glm_mat4_copy(m, dest);
+  glm_translated(dest, v);
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       x  x factor
+ */
+CGLM_INLINE
+void
+glm_translated_x(mat4 m, float x) {
+  m[3][0] += x;
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       y  y factor
+ */
+CGLM_INLINE
+void
+glm_translated_y(mat4 m, float y) {
+  m[3][1] += y;
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       z  z factor
+ */
+CGLM_INLINE
+void
+glm_translated_z(mat4 m, float z) {
+  m[3][2] += z;
+}
+
+/*!
+ * @brief rotate existing transform matrix around X axis by angle
+ *        and store result in dest
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotated_x(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[1][1] =  c;
+  t[1][2] =  s;
+  t[2][1] = -s;
+  t[2][2] =  c;
+
+  glm_mul_rot(t, m, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Y axis by angle
+ *        and store result in dest
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotated_y(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][2] = -s;
+  t[2][0] =  s;
+  t[2][2] =  c;
+
+  glm_mul_rot(t, m, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Z axis by angle
+ *        and store result in dest
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotated_z(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][1] =  s;
+  t[1][0] = -s;
+  t[1][1] =  c;
+
+  glm_mul_rot(t, m, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotated(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_make(rot, angle, axis);
+  glm_mul_rot(rot, m, m);
+}
+
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       pivot  rotation center
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translated(m, pivot);
+  glm_rotated(m, angle, axis);
+  glm_translated(m, pivotInv);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+ *
+ *  this is POST transform, applies to existing transform as last transfrom
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_spinned(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_atm(rot, m[3], angle, axis);
+  glm_mat4_mul(rot, m, m);
+}
+
+#endif /* cglm_affine_post_h */

include/cglm/affine-pre.h

@@ -0,0 +1,285 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_affine_pre_h
+#define cglm_affine_pre_h
+
+/*
+ Functions:
+   CGLM_INLINE void glm_translate_to(mat4 m, vec3 v, mat4 dest);
+   CGLM_INLINE void glm_translate(mat4 m, vec3 v);
+   CGLM_INLINE void glm_translate_x(mat4 m, float to);
+   CGLM_INLINE void glm_translate_y(mat4 m, float to);
+   CGLM_INLINE void glm_translate_z(mat4 m, float to);
+   CGLM_INLINE void glm_rotate_x(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotate_y(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotate_z(mat4 m, float angle, mat4 dest);
+   CGLM_INLINE void glm_rotate(mat4 m, float angle, vec3 axis);
+   CGLM_INLINE void glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis);
+   CGLM_INLINE void glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis);
+   CGLM_INLINE void glm_spin(mat4 m, float angle, vec3 axis);
+ */
+
+#include "common.h"
+#include "util.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
+#include "affine-mat.h"
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       v  translate vector [x, y, z]
+ */
+CGLM_INLINE
+void
+glm_translate(mat4 m, vec3 v) {
+#if defined(CGLM_SIMD)
+  glmm_128 m0, m1, m2, m3;
+
+  m0 = glmm_load(m[0]);
+  m1 = glmm_load(m[1]);
+  m2 = glmm_load(m[2]);
+  m3 = glmm_load(m[3]);
+
+  glmm_store(m[3],
+             glmm_fmadd(m0, glmm_set1(v[0]),
+                        glmm_fmadd(m1, glmm_set1(v[1]),
+                                   glmm_fmadd(m2, glmm_set1(v[2]), m3))));
+#else
+  glm_vec4_muladds(m[0], v[0], m[3]);
+  glm_vec4_muladds(m[1], v[1], m[3]);
+  glm_vec4_muladds(m[2], v[2], m[3]);
+#endif
+}
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and store result in dest
+ *
+ * source matrix will remain same
+ *
+ * @param[in]  m    affine transfrom
+ * @param[in]  v    translate vector [x, y, z]
+ * @param[out] dest translated matrix
+ */
+CGLM_INLINE
+void
+glm_translate_to(mat4 m, vec3 v, mat4 dest) {
+  glm_mat4_copy(m, dest);
+  glm_translate(dest, v);
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       x  x factor
+ */
+CGLM_INLINE
+void
+glm_translate_x(mat4 m, float x) {
+#if defined(CGLM_SIMD)
+  glmm_store(m[3], glmm_fmadd(glmm_load(m[0]), glmm_set1(x), glmm_load(m[3])));
+#else
+  vec4 v1;
+  glm_vec4_scale(m[0], x, v1);
+  glm_vec4_add(v1, m[3], m[3]);
+#endif
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       y  y factor
+ */
+CGLM_INLINE
+void
+glm_translate_y(mat4 m, float y) {
+#if defined(CGLM_SIMD)
+  glmm_store(m[3], glmm_fmadd(glmm_load(m[1]), glmm_set1(y), glmm_load(m[3])));
+#else
+  vec4 v1;
+  glm_vec4_scale(m[1], y, v1);
+  glm_vec4_add(v1, m[3], m[3]);
+#endif
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ * @param[in, out]  m  affine transfrom
+ * @param[in]       z  z factor
+ */
+CGLM_INLINE
+void
+glm_translate_z(mat4 m, float z) {
+#if defined(CGLM_SIMD)
+  glmm_store(m[3], glmm_fmadd(glmm_load(m[2]), glmm_set1(z), glmm_load(m[3])));
+#else
+  vec4 v1;
+  glm_vec4_scale(m[2], z, v1);
+  glm_vec4_add(v1, m[3], m[3]);
+#endif
+}
+
+/*!
+ * @brief rotate existing transform matrix around X axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotate_x(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[1][1] =  c;
+  t[1][2] =  s;
+  t[2][1] = -s;
+  t[2][2] =  c;
+
+  glm_mul_rot(m, t, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Y axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotate_y(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][2] = -s;
+  t[2][0] =  s;
+  t[2][2] =  c;
+
+  glm_mul_rot(m, t, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around Z axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m      affine transfrom
+ * @param[in]   angle  angle (radians)
+ * @param[out]  dest   rotated matrix
+ */
+CGLM_INLINE
+void
+glm_rotate_z(mat4 m, float angle, mat4 dest) {
+  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
+  float c, s;
+
+  c = cosf(angle);
+  s = sinf(angle);
+
+  t[0][0] =  c;
+  t[0][1] =  s;
+  t[1][0] = -s;
+  t[1][1] =  c;
+
+  glm_mul_rot(m, t, dest);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotate(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_make(rot, angle, axis);
+  glm_mul_rot(m, rot, m);
+}
+
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       pivot  rotation center
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translate(m, pivot);
+  glm_rotate(m, angle, axis);
+  glm_translate(m, pivotInv);
+}
+
+/*!
+ * @brief creates NEW rotation matrix by angle and axis at given point
+ *
+ * this creates rotation matrix, it assumes you don't have a matrix
+ *
+ * this should work faster than glm_rotate_at because it reduces
+ * one glm_translate.
+ *
+ * @param[out] m      affine transfrom
+ * @param[in]  pivot  rotation center
+ * @param[in]  angle  angle (radians)
+ * @param[in]  axis   axis
+ */
+CGLM_INLINE
+void
+glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis) {
+  CGLM_ALIGN(8) vec3 pivotInv;
+
+  glm_vec3_negate_to(pivot, pivotInv);
+
+  glm_translate_make(m, pivot);
+  glm_rotate(m, angle, axis);
+  glm_translate(m, pivotInv);
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+ *
+ * @param[in, out]  m      affine transfrom
+ * @param[in]       angle  angle (radians)
+ * @param[in]       axis   axis
+ */
+CGLM_INLINE
+void
+glm_spin(mat4 m, float angle, vec3 axis) {
+  CGLM_ALIGN_MAT mat4 rot;
+  glm_rotate_atm(rot, m[3], angle, axis);
+  glm_mat4_mul(m, rot, m);
+}
+
+#endif /* cglm_affine_pre_h */

include/cglm/affine.h

@@ -24,6 +24,7 @@
    CGLM_INLINE void glm_rotate(mat4 m, float angle, vec3 axis);
    CGLM_INLINE void glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis);
    CGLM_INLINE void glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis);
+   CGLM_INLINE void glm_spin(mat4 m, float angle, vec3 axis);
    CGLM_INLINE void glm_decompose_scalev(mat4 m, vec3 s);
    CGLM_INLINE bool glm_uniscaled(mat4 m);
    CGLM_INLINE void glm_decompose_rs(mat4 m, mat4 r, vec3 s);
@@ -40,106 +41,6 @@
 #include "mat4.h"
 #include "affine-mat.h"
 
-/*!
- * @brief translate existing transform matrix by v vector
- *        and stores result in same matrix
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       v  translate vector [x, y, z]
- */
-CGLM_INLINE
-void
-glm_translate(mat4 m, vec3 v) {
-#if defined(CGLM_SIMD)
-  glmm_128 m0, m1, m2, m3;
-
-  m0 = glmm_load(m[0]);
-  m1 = glmm_load(m[1]);
-  m2 = glmm_load(m[2]);
-  m3 = glmm_load(m[3]);
-
-  glmm_store(m[3],
-             glmm_fmadd(m0, glmm_set1(v[0]),
-                        glmm_fmadd(m1, glmm_set1(v[1]),
-                                   glmm_fmadd(m2, glmm_set1(v[2]), m3))));
-#else
-  glm_vec4_muladds(m[0], v[0], m[3]);
-  glm_vec4_muladds(m[1], v[1], m[3]);
-  glm_vec4_muladds(m[2], v[2], m[3]);
-#endif
-}
-
-/*!
- * @brief translate existing transform matrix by v vector
- *        and store result in dest
- *
- * source matrix will remain same
- *
- * @param[in]  m    affine transfrom
- * @param[in]  v    translate vector [x, y, z]
- * @param[out] dest translated matrix
- */
-CGLM_INLINE
-void
-glm_translate_to(mat4 m, vec3 v, mat4 dest) {
-  glm_mat4_copy(m, dest);
-  glm_translate(dest, v);
-}
-
-/*!
- * @brief translate existing transform matrix by x factor
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       x  x factor
- */
-CGLM_INLINE
-void
-glm_translate_x(mat4 m, float x) {
-#if defined(CGLM_SIMD)
-  glmm_store(m[3], glmm_fmadd(glmm_load(m[0]), glmm_set1(x), glmm_load(m[3])));
-#else
-  vec4 v1;
-  glm_vec4_scale(m[0], x, v1);
-  glm_vec4_add(v1, m[3], m[3]);
-#endif
-}
-
-/*!
- * @brief translate existing transform matrix by y factor
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       y  y factor
- */
-CGLM_INLINE
-void
-glm_translate_y(mat4 m, float y) {
-#if defined(CGLM_SIMD)
-  glmm_store(m[3], glmm_fmadd(glmm_load(m[1]), glmm_set1(y), glmm_load(m[3])));
-#else
-  vec4 v1;
-  glm_vec4_scale(m[1], y, v1);
-  glm_vec4_add(v1, m[3], m[3]);
-#endif
-}
-
-/*!
- * @brief translate existing transform matrix by z factor
- *
- * @param[in, out]  m  affine transfrom
- * @param[in]       z  z factor
- */
-CGLM_INLINE
-void
-glm_translate_z(mat4 m, float z) {
-#if defined(CGLM_SIMD)
-  glmm_store(m[3], glmm_fmadd(glmm_load(m[2]), glmm_set1(z), glmm_load(m[3])));
-#else
-  vec4 v1;
-  glm_vec4_scale(m[2], z, v1);
-  glm_vec4_add(v1, m[3], m[3]);
-#endif
-}
-
 /*!
  * @brief creates NEW translate transform matrix by v vector
  *
@@ -213,81 +114,6 @@ glm_scale_uni(mat4 m, float s) {
   glm_scale_to(m, v, m);
 }
 
-/*!
- * @brief rotate existing transform matrix around X axis by angle
- *        and store result in dest
- *
- * @param[in]   m      affine transfrom
- * @param[in]   angle  angle (radians)
- * @param[out]  dest   rotated matrix
- */
-CGLM_INLINE
-void
-glm_rotate_x(mat4 m, float angle, mat4 dest) {
-  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
-  float c, s;
-
-  c = cosf(angle);
-  s = sinf(angle);
-
-  t[1][1] =  c;
-  t[1][2] =  s;
-  t[2][1] = -s;
-  t[2][2] =  c;
-
-  glm_mul_rot(m, t, dest);
-}
-
-/*!
- * @brief rotate existing transform matrix around Y axis by angle
- *        and store result in dest
- *
- * @param[in]   m      affine transfrom
- * @param[in]   angle  angle (radians)
- * @param[out]  dest   rotated matrix
- */
-CGLM_INLINE
-void
-glm_rotate_y(mat4 m, float angle, mat4 dest) {
-  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
-  float c, s;
-
-  c = cosf(angle);
-  s = sinf(angle);
-
-  t[0][0] =  c;
-  t[0][2] = -s;
-  t[2][0] =  s;
-  t[2][2] =  c;
-
-  glm_mul_rot(m, t, dest);
-}
-
-/*!
- * @brief rotate existing transform matrix around Z axis by angle
- *        and store result in dest
- *
- * @param[in]   m      affine transfrom
- * @param[in]   angle  angle (radians)
- * @param[out]  dest   rotated matrix
- */
-CGLM_INLINE
-void
-glm_rotate_z(mat4 m, float angle, mat4 dest) {
-  CGLM_ALIGN_MAT mat4 t = GLM_MAT4_IDENTITY_INIT;
-  float c, s;
-
-  c = cosf(angle);
-  s = sinf(angle);
-
-  t[0][0] =  c;
-  t[0][1] =  s;
-  t[1][0] = -s;
-  t[1][1] =  c;
-
-  glm_mul_rot(m, t, dest);
-}
-
 /*!
  * @brief creates NEW rotation matrix by angle and axis
  *
@@ -321,67 +147,6 @@ glm_rotate_make(mat4 m, float angle, vec3 axis) {
   m[3][3] = 1.0f;
 }
 
-/*!
- * @brief rotate existing transform matrix around given axis by angle
- *
- * @param[in, out]  m      affine transfrom
- * @param[in]       angle  angle (radians)
- * @param[in]       axis   axis
- */
-CGLM_INLINE
-void
-glm_rotate(mat4 m, float angle, vec3 axis) {
-  CGLM_ALIGN_MAT mat4 rot;
-  glm_rotate_make(rot, angle, axis);
-  glm_mul_rot(m, rot, m);
-}
-
-/*!
- * @brief rotate existing transform
- *        around given axis by angle at given pivot point (rotation center)
- *
- * @param[in, out]  m      affine transfrom
- * @param[in]       pivot  rotation center
- * @param[in]       angle  angle (radians)
- * @param[in]       axis   axis
- */
-CGLM_INLINE
-void
-glm_rotate_at(mat4 m, vec3 pivot, float angle, vec3 axis) {
-  CGLM_ALIGN(8) vec3 pivotInv;
-
-  glm_vec3_negate_to(pivot, pivotInv);
-
-  glm_translate(m, pivot);
-  glm_rotate(m, angle, axis);
-  glm_translate(m, pivotInv);
-}
-
-/*!
- * @brief creates NEW rotation matrix by angle and axis at given point
- *
- * this creates rotation matrix, it assumes you don't have a matrix
- *
- * this should work faster than glm_rotate_at because it reduces
- * one glm_translate.
- *
- * @param[out] m      affine transfrom
- * @param[in]  pivot  rotation center
- * @param[in]  angle  angle (radians)
- * @param[in]  axis   axis
- */
-CGLM_INLINE
-void
-glm_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis) {
-  CGLM_ALIGN(8) vec3 pivotInv;
-
-  glm_vec3_negate_to(pivot, pivotInv);
-
-  glm_translate_make(m, pivot);
-  glm_rotate(m, angle, axis);
-  glm_translate(m, pivotInv);
-}
-
 /*!
  * @brief decompose scale vector
  *
@@ -467,4 +232,7 @@ glm_decompose(mat4 m, vec4 t, mat4 r, vec3 s) {
   glm_decompose_rs(m, r, s);
 }
 
+#include "affine-pre.h"
+#include "affine-post.h"
+
 #endif /* cglm_affine_h */

include/cglm/bezier.h

@@ -23,7 +23,7 @@
 #define GLM_HERMITE_MAT ((mat4)GLM_HERMITE_MAT_INIT)
 
 #define CGLM_DECASTEL_EPS   1e-9f
-#define CGLM_DECASTEL_MAX   1000.0f
+#define CGLM_DECASTEL_MAX   1000
 #define CGLM_DECASTEL_SMALL 1e-20f
 
 /*!

include/cglm/call.h

@@ -15,9 +15,18 @@ extern "C" {
 #include "call/vec2.h"
 #include "call/vec3.h"
 #include "call/vec4.h"
+#include "call/ivec2.h"
+#include "call/ivec3.h"
+#include "call/ivec4.h"
 #include "call/mat2.h"
+#include "call/mat2x3.h"
+#include "call/mat2x4.h"
 #include "call/mat3.h"
+#include "call/mat3x2.h"
+#include "call/mat3x4.h"
 #include "call/mat4.h"
+#include "call/mat4x2.h"
+#include "call/mat4x3.h"
 #include "call/affine.h"
 #include "call/cam.h"
 #include "call/quat.h"

include/cglm/call/affine.h

@@ -81,6 +81,10 @@ CGLM_EXPORT
 void
 glmc_rotate_atm(mat4 m, vec3 pivot, float angle, vec3 axis);
 
+CGLM_EXPORT
+void
+glmc_spin(mat4 m, float angle, vec3 axis);
+
 CGLM_EXPORT
 void
 glmc_decompose_scalev(mat4 m, vec3 s);
@@ -97,6 +101,52 @@ CGLM_EXPORT
 void
 glmc_decompose(mat4 m, vec4 t, mat4 r, vec3 s);
 
+/* affine-post */
+
+CGLM_EXPORT
+void
+glmc_translated(mat4 m, vec3 v);
+
+CGLM_EXPORT
+void
+glmc_translated_to(mat4 m, vec3 v, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_translated_x(mat4 m, float x);
+
+CGLM_EXPORT
+void
+glmc_translated_y(mat4 m, float y);
+
+CGLM_EXPORT
+void
+glmc_translated_z(mat4 m, float z);
+
+CGLM_EXPORT
+void
+glmc_rotated_x(mat4 m, float angle, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_rotated_y(mat4 m, float angle, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_rotated_z(mat4 m, float angle, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_rotated(mat4 m, float angle, vec3 axis);
+
+CGLM_EXPORT
+void
+glmc_rotated_at(mat4 m, vec3 pivot, float angle, vec3 axis);
+
+CGLM_EXPORT
+void
+glmc_spinned(mat4 m, float angle, vec3 axis);
+
 /* affine-mat */
 
 CGLM_EXPORT

include/cglm/call/clipspace/project_no.h

@@ -21,6 +21,10 @@ CGLM_EXPORT
 void
 glmc_project_no(vec3 pos, mat4 m, vec4 vp, vec3 dest);
 
+CGLM_EXPORT
+float
+glmc_project_z_no(vec3 pos, mat4 m);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/clipspace/project_zo.h

@@ -21,6 +21,10 @@ CGLM_EXPORT
 void
 glmc_project_zo(vec3 pos, mat4 m, vec4 vp, vec3 dest);
 
+CGLM_EXPORT
+float
+glmc_project_z_zo(vec3 pos, mat4 m);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/ivec2.h

@@ -0,0 +1,83 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ivec2_h
+#define cglmc_ivec2_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ivec2(int * __restrict v, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_copy(ivec2 a, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_zero(ivec2 v);
+
+CGLM_EXPORT
+void
+glmc_ivec2_one(ivec2 v);
+
+CGLM_EXPORT
+void
+glmc_ivec2_add(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_adds(ivec2 v, int s, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_subs(ivec2 v, int s, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_scale(ivec2 v, int s, ivec2 dest);
+
+CGLM_EXPORT
+int
+glmc_ivec2_distance2(ivec2 a, ivec2 b);
+
+CGLM_EXPORT
+float
+glmc_ivec2_distance(ivec2 a, ivec2 b);
+
+CGLM_EXPORT
+void
+glmc_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec2_clamp(ivec2 v, int minVal, int maxVal);
+
+CGLM_EXPORT
+void
+glmc_ivec2_abs(ivec2 v, ivec2 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ivec2_h */

include/cglm/call/ivec3.h

@@ -0,0 +1,83 @@
+/*
+ * Copyright (c);, Recep Aslantas.
+ *
+ * MIT License (MIT);, http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ivec3_h
+#define cglmc_ivec3_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ivec3(ivec4 v4, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_copy(ivec3 a, ivec3 dest);
+
+CGLM_EXPORT
+void 
+glmc_ivec3_zero(ivec3 v);
+
+CGLM_EXPORT
+void
+glmc_ivec3_one(ivec3 v);
+
+CGLM_EXPORT
+void
+glmc_ivec3_add(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_adds(ivec3 v, int s, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_subs(ivec3 v, int s, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_scale(ivec3 v, int s, ivec3 dest);
+
+CGLM_EXPORT
+int
+glmc_ivec3_distance2(ivec3 a, ivec3 b);
+
+CGLM_EXPORT
+float
+glmc_ivec3_distance(ivec3 a, ivec3 b);
+
+CGLM_EXPORT
+void
+glmc_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec3_clamp(ivec3 v, int minVal, int maxVal);
+
+CGLM_EXPORT
+void
+glmc_ivec3_abs(ivec3 v, ivec3 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ivec3_h */

include/cglm/call/ivec4.h

@@ -0,0 +1,83 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_ivec4_h
+#define cglmc_ivec4_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_ivec4(ivec3 v3, int last, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_copy(ivec4 a, ivec4 dest);
+
+CGLM_EXPORT
+void 
+glmc_ivec4_zero(ivec4 v);
+
+CGLM_EXPORT
+void
+glmc_ivec4_one(ivec4 v);
+
+CGLM_EXPORT
+void
+glmc_ivec4_add(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_adds(ivec4 v, int s, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_subs(ivec4 v, int s, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_scale(ivec4 v, int s, ivec4 dest);
+
+CGLM_EXPORT
+int
+glmc_ivec4_distance2(ivec4 a, ivec4 b);
+
+CGLM_EXPORT
+float
+glmc_ivec4_distance(ivec4 a, ivec4 b);
+
+CGLM_EXPORT
+void
+glmc_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest);
+
+CGLM_EXPORT
+void
+glmc_ivec4_clamp(ivec4 v, int minVal, int maxVal);
+
+CGLM_EXPORT
+void
+glmc_ivec4_abs(ivec4 v, ivec4 dest);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_ivec4_h */

include/cglm/call/mat2.h

@@ -73,6 +73,10 @@ CGLM_EXPORT
 float
 glmc_mat2_rmc(vec2 r, mat2 m, vec2 c);
 
+CGLM_EXPORT
+void
+glmc_mat2_make(float * __restrict src, mat2 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/mat2x3.h

@@ -0,0 +1,47 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_mat2x3_h
+#define cglmc_mat2x3_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat2x3_copy(mat2x3 mat, mat2x3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x3_zero(mat2x3 mat);
+
+CGLM_EXPORT
+void
+glmc_mat2x3_make(float * __restrict src, mat2x3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x3_mul(mat2x3 m1, mat3x2 m2, mat2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x3_mulv(mat2x3 m, vec3 v, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x3_transpose(mat2x3 m, mat3x2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x3_scale(mat2x3 m, float s);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat2x3_h */

include/cglm/call/mat2x4.h

@@ -0,0 +1,47 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_mat2x4_h
+#define cglmc_mat2x4_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat2x4_copy(mat2x4 mat, mat2x4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x4_zero(mat2x4 mat);
+
+CGLM_EXPORT
+void
+glmc_mat2x4_make(float * __restrict src, mat2x4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x4_mul(mat2x4 m1, mat4x2 m2, mat2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x4_mulv(mat2x4 m, vec4 v, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x4_transpose(mat2x4 m, mat4x2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat2x4_scale(mat2x4 m, float s);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat2x4_h */

include/cglm/call/mat3.h

@@ -80,6 +80,10 @@ CGLM_EXPORT
 float
 glmc_mat3_rmc(vec3 r, mat3 m, vec3 c);
 
+CGLM_EXPORT
+void
+glmc_mat3_make(float * __restrict src, mat3 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/mat3x2.h

@@ -0,0 +1,47 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_mat3x2_h
+#define cglmc_mat3x2_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat3x2_copy(mat3x2 mat, mat3x2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x2_zero(mat3x2 mat);
+
+CGLM_EXPORT
+void
+glmc_mat3x2_make(float * __restrict src, mat3x2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x2_mul(mat3x2 m1, mat2x3 m2, mat3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x2_mulv(mat3x2 m, vec2 v, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x2_transpose(mat3x2 m, mat2x3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x2_scale(mat3x2 m, float s);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat3x2_h */

include/cglm/call/mat3x4.h

@@ -0,0 +1,47 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_mat3x4_h
+#define cglmc_mat3x4_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat3x4_copy(mat3x4 mat, mat3x4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x4_zero(mat3x4 mat);
+
+CGLM_EXPORT
+void
+glmc_mat3x4_make(float * __restrict src, mat3x4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x4_transpose(mat3x4 m, mat4x3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat3x4_scale(mat3x4 m, float s);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat3x4_h */

include/cglm/call/mat4.h

@@ -121,6 +121,10 @@ CGLM_EXPORT
 float
 glmc_mat4_rmc(vec4 r, mat4 m, vec4 c);
 
+CGLM_EXPORT
+void
+glmc_mat4_make(float * __restrict src, mat4 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/mat4x2.h

@@ -0,0 +1,47 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_mat4x2_h
+#define cglmc_mat4x2_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat4x2_copy(mat4x2 mat, mat4x2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x2_zero(mat4x2 mat);
+
+CGLM_EXPORT
+void
+glmc_mat4x2_make(float * __restrict src, mat4x2 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x2_transpose(mat4x2 m, mat2x4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x2_scale(mat4x2 m, float s);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat4x2_h */

include/cglm/call/mat4x3.h

@@ -0,0 +1,47 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_mat4x3_h
+#define cglmc_mat4x3_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_mat4x3_copy(mat4x3 mat, mat4x3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x3_zero(mat4x3 mat);
+
+CGLM_EXPORT
+void
+glmc_mat4x3_make(float * __restrict src, mat4x3 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x3_transpose(mat4x3 m, mat3x4 dest);
+
+CGLM_EXPORT
+void
+glmc_mat4x3_scale(mat4x3 m, float s);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_mat4x3_h */

include/cglm/call/project.h

@@ -25,6 +25,10 @@ CGLM_EXPORT
 void
 glmc_project(vec3 pos, mat4 m, vec4 vp, vec3 dest);
 
+CGLM_EXPORT
+float
+glmc_project_z(vec3 pos, mat4 m);
+
 CGLM_EXPORT
 void
 glmc_pickmatrix(vec2 center, vec2 size, vec4 vp, mat4 dest);

include/cglm/call/quat.h

@@ -161,6 +161,10 @@ CGLM_EXPORT
 void
 glmc_quat_rotate_atm(mat4 m, versor q, vec3 pivot);
 
+CGLM_EXPORT
+void
+glmc_quat_make(float * __restrict src, versor dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/vec2.h

@@ -145,6 +145,10 @@ CGLM_EXPORT
 void
 glmc_vec2_clamp(vec2 v, float minval, float maxval);
 
+CGLM_EXPORT
+void
+glmc_vec2_abs(vec2 v, vec2 dest);
+
 CGLM_EXPORT
 void
 glmc_vec2_lerp(vec2 from, vec2 to, float t, vec2 dest);
@@ -161,6 +165,10 @@ CGLM_EXPORT
 void
 glmc_vec2_complex_conjugate(vec2 a, vec2 dest);
 
+CGLM_EXPORT
+void
+glmc_vec2_make(float * __restrict src, vec2 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/vec3.h

@@ -306,6 +306,10 @@ CGLM_EXPORT
 void
 glmc_vec3_sqrt(vec3 v, vec3 dest);
 
+CGLM_EXPORT
+void
+glmc_vec3_make(float * __restrict src, vec3 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/vec4.h

@@ -283,6 +283,10 @@ CGLM_EXPORT
 void
 glmc_vec4_sqrt(vec4 v, vec4 dest);
 
+CGLM_EXPORT
+void
+glmc_vec4_make(float * __restrict src, vec4 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/cglm.h

@@ -12,9 +12,18 @@
 #include "vec2.h"
 #include "vec3.h"
 #include "vec4.h"
+#include "ivec2.h"
+#include "ivec3.h"
+#include "ivec4.h"
 #include "mat4.h"
+#include "mat4x2.h"
+#include "mat4x3.h"
 #include "mat3.h"
+#include "mat3x2.h"
+#include "mat3x4.h"
 #include "mat2.h"
+#include "mat2x3.h"
+#include "mat2x4.h"
 #include "affine.h"
 #include "cam.h"
 #include "frustum.h"

include/cglm/clipspace/project_no.h

@@ -83,4 +83,27 @@ glm_project_no(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
   dest[2] = pos4[2];
 }
 
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z_no(vec3 v, mat4 m) {
+  float z, w;
+
+  z = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2] + m[3][2];
+  w = m[0][3] * v[0] + m[1][3] * v[1] + m[2][3] * v[2] + m[3][3];
+
+  return 0.5f * (z / w) + 0.5f;
+}
+
 #endif /* cglm_project_no_h */

include/cglm/clipspace/project_zo.h

@@ -85,4 +85,27 @@ glm_project_zo(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
   dest[1] = pos4[1] * vp[3] + vp[1];
 }
 
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z_zo(vec3 v, mat4 m) {
+  float z, w;
+
+  z = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2] + m[3][2];
+  w = m[0][3] * v[0] + m[1][3] * v[1] + m[2][3] * v[2] + m[3][3];
+
+  return z / w;
+}
+
 #endif /* cglm_project_zo_h */

include/cglm/clipspace/view_lh.h

@@ -37,8 +37,8 @@ glm_lookat_lh(vec3 eye, vec3 center, vec3 up, mat4 dest) {
   glm_vec3_sub(center, eye, f);
   glm_vec3_normalize(f);
 
-  glm_vec3_crossn(f, up, s);
+  glm_vec3_crossn(up, f, s);
-  glm_vec3_cross(s, f, u);
+  glm_vec3_cross(f, s, u);
 
   dest[0][0] = s[0];
   dest[0][1] = u[0];

include/cglm/common.h

@@ -18,6 +18,7 @@
 
 #include <stdint.h>
 #include <stddef.h>
+#include <stdlib.h>
 #include <math.h>
 #include <float.h>
 #include <stdbool.h>
@@ -44,16 +45,16 @@
 
 #ifndef CGLM_USE_DEFAULT_EPSILON
 #  ifndef GLM_FLT_EPSILON
-#    define GLM_FLT_EPSILON 1e-5
+#    define GLM_FLT_EPSILON 1e-5f
 #  endif
 #else
 #  define GLM_FLT_EPSILON FLT_EPSILON
 #endif
 
 /*
- * Clip control: define GLM_FORCE_DEPTH_ZERO_TO_ONE before including
+ * Clip control: define CGLM_FORCE_DEPTH_ZERO_TO_ONE before including
  * CGLM to use a clip space between 0 to 1.
- * Coordinate system: define GLM_FORCE_LEFT_HANDED before including
+ * Coordinate system: define CGLM_FORCE_LEFT_HANDED before including
  * CGLM to use the left handed coordinate system by default.
  */
 
@@ -81,4 +82,34 @@
 #  endif
 #endif
 
+/* struct API configurator */
+/* TODO: move struct/common.h? */
+/* WARN: dont use concant helpers outside cglm headers, because they may be changed */
+
+#define CGLM_MACRO_CONCAT_HELPER(A, B, C, D, E, ...) A ## B ## C ## D ## E ## __VA_ARGS__
+#define CGLM_MACRO_CONCAT(A, B, C, D, E, ...) CGLM_MACRO_CONCAT_HELPER(A, B, C, D, E,__VA_ARGS__)
+
+#ifndef CGLM_OMIT_NS_FROM_STRUCT_API
+#  ifndef CGLM_STRUCT_API_NS
+#    define CGLM_STRUCT_API_NS glms
+#  endif
+#  ifndef CGLM_STRUCT_API_NS_SEPERATOR
+#    define CGLM_STRUCT_API_NS_SEPERATOR _
+#  endif
+#else
+#  define CGLM_STRUCT_API_NS
+#  define CGLM_STRUCT_API_NS_SEPERATOR
+#endif
+
+#ifndef CGLM_STRUCT_API_NAME_SUFFIX
+#  define CGLM_STRUCT_API_NAME_SUFFIX
+#endif
+
+#define CGLM_STRUCTAPI(A, ...) CGLM_MACRO_CONCAT(CGLM_STRUCT_API_NS,             \
+                                                 CGLM_STRUCT_API_NS_SEPERATOR,   \
+                                                 A,                              \
+                                                 CGLM_STRUCT_API_NAME_SUFFIX,    \
+                                                 _,                              \
+                                                 __VA_ARGS__)
+
 #endif /* cglm_common_h */

include/cglm/io.h

@@ -13,6 +13,7 @@
    CGLM_INLINE void glm_vec3_print(vec3 vec, FILE *ostream);
    CGLM_INLINE void glm_ivec3_print(ivec3 vec, FILE *ostream);
    CGLM_INLINE void glm_versor_print(versor vec, FILE *ostream);
+   CGLM_INLINE void glm_arch_print(FILE *ostream);
  */
 
 /*
@@ -39,6 +40,7 @@
    || defined(CGLM_NO_PRINTS_NOOP)
 
 #include "common.h"
+#include "util.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -48,16 +50,67 @@
 #endif
 
 #ifndef CGLM_PRINT_MAX_TO_SHORT
-#  define CGLM_PRINT_MAX_TO_SHORT 1e5
+#  define CGLM_PRINT_MAX_TO_SHORT 1e5f
 #endif
 
-#ifndef CGLM_PRINT_COLOR
+#ifndef GLM_TESTS_NO_COLORFUL_OUTPUT
+#  ifndef CGLM_PRINT_COLOR
 #    define CGLM_PRINT_COLOR        "\033[36m"
+#  endif
+#  ifndef CGLM_PRINT_COLOR_RESET
+#    define CGLM_PRINT_COLOR_RESET  "\033[0m"
+#  endif
+#else
+#  ifndef CGLM_PRINT_COLOR
+#    define CGLM_PRINT_COLOR
+#  endif
+#  ifndef CGLM_PRINT_COLOR_RESET
+#    define CGLM_PRINT_COLOR_RESET
+#  endif
 #endif
 
-#ifndef CGLM_PRINT_COLOR_RESET
+/*!
-#  define CGLM_PRINT_COLOR_RESET  "\033[0m"
+ * @brief prints current SIMD path in general
+ *
+ * @param[in] ostream    stream to print e.g. stdout, stderr, FILE ...
+ */
+CGLM_INLINE
+void
+glm_arch_print(FILE* __restrict ostream) {
+  fprintf(ostream, CGLM_PRINT_COLOR "arch: "
+#if defined(CGLM_SIMD_WASM)
+  "wasm SIMD128"
+#elif defined(CGLM_SIMD_x86)
+  "x86 SSE* "
+#  ifdef __AVX__
+  " AVX"
+#  endif
+#elif defined(CGLM_SIMD_ARM)
+  "arm"
+#  ifndef __ARM_NEON_FP
+    " NEON_FP"
+#  endif
+#  ifdef CGLM_ARM64
+    " ARM64"
+#  endif
+#else
+  "uncommon"
 #endif
+  CGLM_PRINT_COLOR_RESET);
+}
+
+/*!
+ * @brief prints current SIMD path in general
+ *
+ * @param[in] ostream    stream to print e.g. stdout, stderr, FILE ...
+ */
+CGLM_INLINE
+void
+glm_arch_print_name(FILE* __restrict ostream) {
+  fprintf(ostream, CGLM_PRINT_COLOR "\ncglm ");
+  glm_arch_print(ostream);
+  fprintf(ostream, "\n\n" CGLM_PRINT_COLOR_RESET);
+}
 
 CGLM_INLINE
 void
@@ -76,9 +129,9 @@ glm_mat4_print(mat4              matrix,
   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]);
+        cwi = sprintf(buff, "% .*f", CGLM_PRINT_PRECISION, (double)matrix[i][j]);
       else
-        cwi = sprintf(buff, "% g", matrix[i][j]);
+        cwi = sprintf(buff, "% g", (double)matrix[i][j]);
       cw[i] = GLM_MAX(cw[i], cwi);
     }
   }
@@ -88,9 +141,9 @@ glm_mat4_print(mat4              matrix,
 
     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]);
+        fprintf(ostream, " % *.*f", cw[j], CGLM_PRINT_PRECISION, (double)matrix[j][i]);
       else
-        fprintf(ostream, " % *g", cw[j], matrix[j][i]);
+        fprintf(ostream, " % *g", cw[j], (double)matrix[j][i]);
 
     fprintf(ostream, "  |\n");
   }
@@ -119,9 +172,9 @@ glm_mat3_print(mat3              matrix,
   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]);
+        cwi = sprintf(buff, "% .*f", CGLM_PRINT_PRECISION, (double)matrix[i][j]);
       else
-        cwi = sprintf(buff, "% g", matrix[i][j]);
+        cwi = sprintf(buff, "% g", (double)matrix[i][j]);
       cw[i] = GLM_MAX(cw[i], cwi);
     }
   }
@@ -131,9 +184,9 @@ glm_mat3_print(mat3              matrix,
 
     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]);
+        fprintf(ostream, " % *.*f", cw[j], CGLM_PRINT_PRECISION, (double)matrix[j][i]);
       else
-        fprintf(ostream, " % *g", cw[j], matrix[j][i]);
+        fprintf(ostream, " % *g", cw[j], (double)matrix[j][i]);
 
     fprintf(ostream, "  |\n");
   }
@@ -161,9 +214,9 @@ glm_mat2_print(mat2              matrix,
   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]);
+        cwi = sprintf(buff, "% .*f", CGLM_PRINT_PRECISION, (double)matrix[i][j]);
       else
-        cwi = sprintf(buff, "% g", matrix[i][j]);
+        cwi = sprintf(buff, "% g", (double)matrix[i][j]);
       cw[i] = GLM_MAX(cw[i], cwi);
     }
   }
@@ -173,9 +226,9 @@ glm_mat2_print(mat2              matrix,
 
     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]);
+        fprintf(ostream, " % *.*f", cw[j], CGLM_PRINT_PRECISION, (double)matrix[j][i]);
       else
-        fprintf(ostream, " % *g", cw[j], matrix[j][i]);
+        fprintf(ostream, " % *g", cw[j], (double)matrix[j][i]);
 
     fprintf(ostream, "  |\n");
   }
@@ -198,9 +251,9 @@ glm_vec4_print(vec4              vec,
 
   for (i = 0; i < m; i++) {
     if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, (double)vec[i]);
     else
-      fprintf(ostream, " % g", vec[i]);
+      fprintf(ostream, " % g", (double)vec[i]);
   }
 
   fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
@@ -220,9 +273,9 @@ glm_vec3_print(vec3              vec,
 
   for (i = 0; i < m; i++) {
     if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, (double)vec[i]);
     else
-      fprintf(ostream, " % g", vec[i]);
+      fprintf(ostream, " % g", (double)vec[i]);
   }
 
   fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
@@ -260,9 +313,9 @@ glm_vec2_print(vec2              vec,
 
   for (i = 0; i < m; i++) {
     if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, (double)vec[i]);
     else
-      fprintf(ostream, " % g", vec[i]);
+      fprintf(ostream, " % g", (double)vec[i]);
   }
 
   fprintf(ostream, "  )" CGLM_PRINT_COLOR_RESET "\n\n");
@@ -282,9 +335,9 @@ glm_versor_print(versor            vec,
 
   for (i = 0; i < m; i++) {
     if (vec[i] < CGLM_PRINT_MAX_TO_SHORT)
-      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, vec[i]);
+      fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, (double)vec[i]);
     else
-      fprintf(ostream, " % g", vec[i]);
+      fprintf(ostream, " % g", (double)vec[i]);
   }
 
 
@@ -309,9 +362,9 @@ glm_aabb_print(vec3                    bbox[2],
 
     for (j = 0; j < m; j++) {
       if (bbox[i][j] < CGLM_PRINT_MAX_TO_SHORT)
-        fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, bbox[i][j]);
+        fprintf(ostream, " % .*f", CGLM_PRINT_PRECISION, (double)bbox[i][j]);
       else
-        fprintf(ostream, " % g", bbox[i][j]);
+        fprintf(ostream, " % g", (double)bbox[i][j]);
     }
 
     fprintf(ostream, "  )\n");
@@ -339,6 +392,8 @@ glm_aabb_print(vec3                    bbox[2],
 #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;
+#define glm_arch_print(s) (void)s;
+#define glm_arch_print_name(s) (void)s;
 
 #endif
 #endif /* cglm_io_h */

include/cglm/ivec2.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
+ */
+
+/*
+ Macros:
+   GLM_IVEC2_ONE_INIT
+   GLM_IVEC2_ZERO_INIT
+   GLM_IVEC2_ONE
+   GLM_IVEC2_ZERO
+
+ Functions:
+  CGLM_INLINE void glm_ivec2(int * __restrict v, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_copy(ivec2 a, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_zero(ivec2 v)
+  CGLM_INLINE void glm_ivec2_one(ivec2 v)
+  CGLM_INLINE void glm_ivec2_add(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_adds(ivec2 v, int s, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_subs(ivec2 v, int s, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_scale(ivec2 v, int s, ivec2 dest)
+  CGLM_INLINE int glm_ivec2_distance2(ivec2 a, ivec2 b)
+  CGLM_INLINE float glm_ivec2_distance(ivec2 a, ivec2 b)
+  CGLM_INLINE void glm_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest)
+  CGLM_INLINE void glm_ivec2_clamp(ivec2 v, int minVal, int maxVal)
+  CGLM_INLINE void glm_ivec2_abs(ivec2 v, ivec2 dest)
+ */
+
+#ifndef cglm_ivec2_h
+#define cglm_ivec2_h
+
+#include "common.h"
+
+#define GLM_IVEC2_ONE_INIT   {1, 1}
+#define GLM_IVEC2_ZERO_INIT  {0, 0}
+
+#define GLM_IVEC2_ONE  ((ivec2)GLM_IVEC2_ONE_INIT)
+#define GLM_IVEC2_ZERO ((ivec2)GLM_IVEC2_ZERO_INIT)
+
+/*!
+ * @brief init ivec2 using vec3 or vec4
+ *
+ * @param[in]  v    vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2(int * __restrict v, ivec2 dest) {
+  dest[0] = v[0];
+  dest[1] = v[1];
+}
+
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * @param[in]  a    source vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_copy(ivec2 a, ivec2 dest) {
+  dest[0] = a[0];
+  dest[1] = a[1];
+}
+
+/*!
+ * @brief set all members of [v] to zero
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void 
+glm_ivec2_zero(ivec2 v) {
+  v[0] = v[1] = 0;
+}
+
+/*!
+ * @brief set all members of [v] to one
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void
+glm_ivec2_one(ivec2 v) {
+  v[0] = v[1] = 1;
+}
+
+/*!
+ * @brief add vector [a] to vector [b] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_add(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+}
+
+/*!
+ * @brief add scalar s to vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_adds(ivec2 v, int s, ivec2 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+}
+
+/*!
+ * @brief subtract vector [b] from vector [a] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_sub(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+}
+
+/*!
+ * @brief subtract scalar s from vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_subs(ivec2 v, int s, ivec2 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+}
+
+/*!
+ * @brief multiply vector [a] with vector [b] and store result in [dest]
+ *
+ * @param[in]  a    frist vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_mul(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+}
+
+/*!
+ * @brief multiply vector [a] with scalar s and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_scale(ivec2 v, int s, ivec2 dest) {
+  dest[0] = v[0] * s;
+  dest[1] = v[1] * s;
+}
+
+/*!
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+int
+glm_ivec2_distance2(ivec2 a, ivec2 b) {
+  int xd, yd;
+  xd = a[0] - b[0];
+  yd = a[1] - b[1];
+  return xd * xd + yd * yd;
+}
+
+/*!
+ * @brief distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns distance
+ */
+CGLM_INLINE
+float
+glm_ivec2_distance(ivec2 a, ivec2 b) {
+  return sqrtf((float)glm_ivec2_distance2(a, b));
+}
+
+/*!
+ * @brief set each member of dest to greater of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_maxv(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] > b[0] ? a[0] : b[0];
+  dest[1] = a[1] > b[1] ? a[1] : b[1];
+}
+
+/*!
+ * @brief set each member of dest to lesser of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_minv(ivec2 a, ivec2 b, ivec2 dest) {
+  dest[0] = a[0] < b[0] ? a[0] : b[0];
+  dest[1] = a[1] < b[1] ? a[1] : b[1];
+}
+
+/*!
+ * @brief clamp each member of [v] between minVal and maxVal (inclusive)
+ *
+ * @param[in, out] v      vector
+ * @param[in]      minVal minimum value
+ * @param[in]      maxVal maximum value
+ */
+CGLM_INLINE
+void
+glm_ivec2_clamp(ivec2 v, int minVal, int maxVal) {
+  if (v[0] < minVal)
+    v[0] = minVal;
+  else if(v[0] > maxVal)
+    v[0] = maxVal;
+
+  if (v[1] < minVal)
+    v[1] = minVal;
+  else if(v[1] > maxVal)
+    v[1] = maxVal;
+}
+
+/*!
+ * @brief absolute value of v
+ *
+ * @param[in]	v	vector
+ * @param[out]	dest	destination
+ */
+CGLM_INLINE
+void
+glm_ivec2_abs(ivec2 v, ivec2 dest) {
+  dest[0] = abs(v[0]);
+  dest[1] = abs(v[1]);
+}
+
+#endif /* cglm_ivec2_h */

include/cglm/ivec3.h

@@ -0,0 +1,285 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_IVEC3_ONE_INIT
+   GLM_IVEC3_ZERO_INIT
+   GLM_IVEC3_ONE
+   GLM_IVEC3_ZERO
+
+ Functions:
+  CGLM_INLINE void glm_ivec3(ivec4 v4, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_copy(ivec3 a, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_zero(ivec3 v)
+  CGLM_INLINE void glm_ivec3_one(ivec3 v)
+  CGLM_INLINE void glm_ivec3_add(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_adds(ivec3 v, int s, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_subs(ivec3 v, int s, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_scale(ivec3 v, int s, ivec3 dest)
+  CGLM_INLINE int glm_ivec3_distance2(ivec3 a, ivec3 b)
+  CGLM_INLINE float glm_ivec3_distance(ivec3 a, ivec3 b)
+  CGLM_INLINE void glm_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest)
+  CGLM_INLINE void glm_ivec3_clamp(ivec3 v, int minVal, int maxVal)
+  CGLM_INLINE void glm_ivec3_abs(ivec3 v, ivec3 dest)
+ */
+
+#ifndef cglm_ivec3_h
+#define cglm_ivec3_h
+
+#include "common.h"
+
+#define GLM_IVEC3_ONE_INIT   {1, 1, 1}
+#define GLM_IVEC3_ZERO_INIT  {0, 0, 0}
+
+#define GLM_IVEC3_ONE  ((ivec3)GLM_IVEC3_ONE_INIT)
+#define GLM_IVEC3_ZERO ((ivec3)GLM_IVEC3_ZERO_INIT)
+
+/*!
+ * @brief init ivec3 using ivec4
+ *
+ * @param[in]  v4   vector4
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3(ivec4 v4, ivec3 dest) {
+  dest[0] = v4[0];
+  dest[1] = v4[1];
+  dest[2] = v4[2];
+}
+
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * @param[in]  a    source vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_copy(ivec3 a, ivec3 dest) {
+  dest[0] = a[0];
+  dest[1] = a[1];
+  dest[2] = a[2];
+}
+
+/*!
+ * @brief set all members of [v] to zero
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void 
+glm_ivec3_zero(ivec3 v) {
+  v[0] = v[1] = v[2] = 0;
+}
+
+/*!
+ * @brief set all members of [v] to one
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void
+glm_ivec3_one(ivec3 v) {
+  v[0] = v[1] = v[2] = 1;
+}
+
+/*!
+ * @brief add vector [a] to vector [b] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_add(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+  dest[2] = a[2] + b[2];
+}
+
+/*!
+ * @brief add scalar s to vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_adds(ivec3 v, int s, ivec3 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+  dest[2] = v[2] + s;
+}
+
+/*!
+ * @brief subtract vector [b] from vector [a] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_sub(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+  dest[2] = a[2] - b[2];
+}
+
+/*!
+ * @brief subtract scalar s from vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_subs(ivec3 v, int s, ivec3 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+  dest[2] = v[2] - s;
+}
+
+/*!
+ * @brief multiply vector [a] with vector [b] and store result in [dest]
+ *
+ * @param[in]  a    frist vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_mul(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+  dest[2] = a[2] * b[2];
+}
+
+/*!
+ * @brief multiply vector [a] with scalar s and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_scale(ivec3 v, int s, ivec3 dest) {
+  dest[0] = v[0] * s;
+  dest[1] = v[1] * s;
+  dest[2] = v[2] * s;
+}
+
+/*!
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+int
+glm_ivec3_distance2(ivec3 a, ivec3 b) {
+  int xd, yd, zd;
+  xd = a[0] - b[0];
+  yd = a[1] - b[1];
+  zd = a[2] - b[2];
+  return xd * xd + yd * yd + zd * zd;
+}
+
+/*!
+ * @brief distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns distance
+ */
+CGLM_INLINE
+float
+glm_ivec3_distance(ivec3 a, ivec3 b) {
+  return sqrtf((float)glm_ivec3_distance2(a, b));
+}
+
+/*!
+ * @brief set each member of dest to greater of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_maxv(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] > b[0] ? a[0] : b[0];
+  dest[1] = a[1] > b[1] ? a[1] : b[1];
+  dest[2] = a[2] > b[2] ? a[2] : b[2];
+}
+
+/*!
+ * @brief set each member of dest to lesser of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_minv(ivec3 a, ivec3 b, ivec3 dest) {
+  dest[0] = a[0] < b[0] ? a[0] : b[0];
+  dest[1] = a[1] < b[1] ? a[1] : b[1];
+  dest[2] = a[2] < b[2] ? a[2] : b[2];
+}
+
+/*!
+ * @brief clamp each member of [v] between minVal and maxVal (inclusive)
+ *
+ * @param[in, out] v      vector
+ * @param[in]      minVal minimum value
+ * @param[in]      maxVal maximum value
+ */
+CGLM_INLINE
+void
+glm_ivec3_clamp(ivec3 v, int minVal, int maxVal) {
+  if (v[0] < minVal)
+    v[0] = minVal;
+  else if(v[0] > maxVal)
+    v[0] = maxVal;
+
+  if (v[1] < minVal)
+    v[1] = minVal;
+  else if(v[1] > maxVal)
+    v[1] = maxVal;
+
+  if (v[2] < minVal)
+    v[2] = minVal;
+  else if(v[2] > maxVal)
+    v[2] = maxVal;
+}
+
+/*!
+ * @brief absolute value of v
+ *
+ * @param[in]	v	vector
+ * @param[out]	dest	destination
+ */
+CGLM_INLINE
+void
+glm_ivec3_abs(ivec3 v, ivec3 dest) {
+  dest[0] = abs(v[0]);
+  dest[1] = abs(v[1]);
+  dest[2] = abs(v[2]);
+}
+
+#endif /* cglm_ivec3_h */

include/cglm/ivec4.h

@@ -0,0 +1,303 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_IVEC4_ONE_INIT
+   GLM_IVEC4_ZERO_INIT
+   GLM_IVEC4_ONE
+   GLM_IVEC4_ZERO
+
+ Functions:
+  CGLM_INLINE void glm_ivec4(ivec3 v3, int last, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_copy(ivec4 a, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_zero(ivec4 v)
+  CGLM_INLINE void glm_ivec4_one(ivec4 v)
+  CGLM_INLINE void glm_ivec4_add(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_adds(ivec4 v, int s, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_subs(ivec4 v, int s, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_scale(ivec4 v, int s, ivec4 dest)
+  CGLM_INLINE int glm_ivec4_distance2(ivec4 a, ivec4 b)
+  CGLM_INLINE float glm_ivec4_distance(ivec4 a, ivec4 b)
+  CGLM_INLINE void glm_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest)
+  CGLM_INLINE void glm_ivec4_clamp(ivec4 v, int minVal, int maxVal)
+  CGLM_INLINE void glm_ivec4_abs(ivec4 v, ivec4 dest)
+ */
+
+#ifndef cglm_ivec4_h
+#define cglm_ivec4_h
+
+#include "common.h"
+
+#define GLM_IVEC4_ONE_INIT   {1, 1, 1, 1}
+#define GLM_IVEC4_ZERO_INIT  {0, 0, 0, 0}
+
+#define GLM_IVEC4_ONE  ((ivec4)GLM_IVEC4_ONE_INIT)
+#define GLM_IVEC4_ZERO ((ivec4)GLM_IVEC4_ZERO_INIT)
+
+/*!
+ * @brief init ivec4 using ivec3
+ *
+ * @param[in]  v3   vector3
+ * @param[in]  last last item
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4(ivec3 v3, int last, ivec4 dest) {
+  dest[0] = v3[0];
+  dest[1] = v3[1];
+  dest[2] = v3[2];
+  dest[3] = last;
+}
+
+/*!
+ * @brief copy all members of [a] to [dest]
+ *
+ * @param[in]  a    source vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_copy(ivec4 a, ivec4 dest) {
+  dest[0] = a[0];
+  dest[1] = a[1];
+  dest[2] = a[2];
+  dest[3] = a[3];
+}
+
+/*!
+ * @brief set all members of [v] to zero
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void 
+glm_ivec4_zero(ivec4 v) {
+  v[0] = v[1] = v[2] = v[3] = 0;
+}
+
+/*!
+ * @brief set all members of [v] to one
+ *
+ * @param[out] v vector
+ */
+CGLM_INLINE
+void
+glm_ivec4_one(ivec4 v) {
+  v[0] = v[1] = v[2] = v[3] = 1;
+}
+
+/*!
+ * @brief add vector [a] to vector [b] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_add(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] + b[0];
+  dest[1] = a[1] + b[1];
+  dest[2] = a[2] + b[2];
+  dest[3] = a[3] + b[3];
+}
+
+/*!
+ * @brief add scalar s to vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_adds(ivec4 v, int s, ivec4 dest) {
+  dest[0] = v[0] + s;
+  dest[1] = v[1] + s;
+  dest[2] = v[2] + s;
+  dest[3] = v[3] + s;
+}
+
+/*!
+ * @brief subtract vector [b] from vector [a] and store result in [dest]
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_sub(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] - b[0];
+  dest[1] = a[1] - b[1];
+  dest[2] = a[2] - b[2];
+  dest[3] = a[3] - b[3];
+}
+
+/*!
+ * @brief subtract scalar s from vector [v] and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_subs(ivec4 v, int s, ivec4 dest) {
+  dest[0] = v[0] - s;
+  dest[1] = v[1] - s;
+  dest[2] = v[2] - s;
+  dest[3] = v[3] - s;
+}
+
+/*!
+ * @brief multiply vector [a] with vector [b] and store result in [dest]
+ *
+ * @param[in]  a    frist vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_mul(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] * b[0];
+  dest[1] = a[1] * b[1];
+  dest[2] = a[2] * b[2];
+  dest[3] = a[3] * b[3];
+}
+
+/*!
+ * @brief multiply vector [a] with scalar s and store result in [dest]
+ *
+ * @param[in]  v    vector
+ * @param[in]  s    scalar
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_scale(ivec4 v, int s, ivec4 dest) {
+  dest[0] = v[0] * s;
+  dest[1] = v[1] * s;
+  dest[2] = v[2] * s;
+  dest[3] = v[3] * s;
+}
+
+/*!
+ * @brief squared distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns squared distance (distance * distance)
+ */
+CGLM_INLINE
+int
+glm_ivec4_distance2(ivec4 a, ivec4 b) {
+  int xd, yd, zd, wd;
+  xd = a[0] - b[0];
+  yd = a[1] - b[1];
+  zd = a[2] - b[2];
+  wd = a[3] - b[3];
+  return xd * xd + yd * yd + zd * zd + wd * wd;
+}
+
+/*!
+ * @brief distance between two vectors
+ *
+ * @param[in] a first vector
+ * @param[in] b second vector
+ * @return returns distance
+ */
+CGLM_INLINE
+float
+glm_ivec4_distance(ivec4 a, ivec4 b) {
+  return sqrtf((float)glm_ivec4_distance2(a, b));
+}
+
+/*!
+ * @brief set each member of dest to greater of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_maxv(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] > b[0] ? a[0] : b[0];
+  dest[1] = a[1] > b[1] ? a[1] : b[1];
+  dest[2] = a[2] > b[2] ? a[2] : b[2];
+  dest[3] = a[3] > b[3] ? a[3] : b[3];
+}
+
+/*!
+ * @brief set each member of dest to lesser of vector a and b
+ *
+ * @param[in]  a    first vector
+ * @param[in]  b    second vector
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_minv(ivec4 a, ivec4 b, ivec4 dest) {
+  dest[0] = a[0] < b[0] ? a[0] : b[0];
+  dest[1] = a[1] < b[1] ? a[1] : b[1];
+  dest[2] = a[2] < b[2] ? a[2] : b[2];
+  dest[3] = a[3] < b[3] ? a[3] : b[3];
+}
+
+/*!
+ * @brief clamp each member of [v] between minVal and maxVal (inclusive)
+ *
+ * @param[in, out] v      vector
+ * @param[in]      minVal minimum value
+ * @param[in]      maxVal maximum value
+ */
+CGLM_INLINE
+void
+glm_ivec4_clamp(ivec4 v, int minVal, int maxVal) {
+  if (v[0] < minVal)
+    v[0] = minVal;
+  else if(v[0] > maxVal)
+    v[0] = maxVal;
+
+  if (v[1] < minVal)
+    v[1] = minVal;
+  else if(v[1] > maxVal)
+    v[1] = maxVal;
+
+  if (v[2] < minVal)
+    v[2] = minVal;
+  else if(v[2] > maxVal)
+    v[2] = maxVal;
+
+  if (v[3] < minVal)
+    v[3] = minVal;
+  else if(v[3] > maxVal)
+    v[3] = maxVal;
+}
+
+/*!
+ * @brief absolute value of v
+ *
+ * @param[in]	v	vector
+ * @param[out]	dest	destination
+ */
+CGLM_INLINE
+void
+glm_ivec4_abs(ivec4 v, ivec4 dest) {
+  dest[0] = abs(v[0]);
+  dest[1] = abs(v[1]);
+  dest[2] = abs(v[2]);
+  dest[3] = abs(v[3]);
+}
+
+#endif /* cglm_ivec4_h */

include/cglm/mat2.h

@@ -28,6 +28,7 @@
    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)
+   CGLM_INLINE void  glm_mat2_make(float * restrict src, mat2 dest)
  */
 
 #ifndef cglm_mat2_h
@@ -44,6 +45,10 @@
 #  include "simd/neon/mat2.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/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}}
 
@@ -132,7 +137,9 @@ glm_mat2_zero(mat2 mat) {
 CGLM_INLINE
 void
 glm_mat2_mul(mat2 m1, mat2 m2, mat2 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat2_mul_wasm(m1, m2, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat2_mul_sse2(m1, m2, dest);
 #elif defined(CGLM_NEON_FP)
   glm_mat2_mul_neon(m1, m2, dest);
@@ -160,7 +167,9 @@ glm_mat2_mul(mat2 m1, mat2 m2, mat2 dest) {
 CGLM_INLINE
 void
 glm_mat2_transpose_to(mat2 m, mat2 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat2_transp_wasm(m, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat2_transp_sse2(m, dest);
 #else
   dest[0][0] = m[0][0];
@@ -222,7 +231,10 @@ glm_mat2_trace(mat2 m) {
 CGLM_INLINE
 void
 glm_mat2_scale(mat2 m, float s) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glmm_store(m[0], wasm_f32x4_mul(wasm_v128_load(m[0]),
+                                  wasm_f32x4_splat(s)));
+#elif 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)));
@@ -334,4 +346,19 @@ glm_mat2_rmc(vec2 r, mat2 m, vec2 c) {
   return glm_vec2_dot(r, tmp);
 }
 
+/*!
+ * @brief Create mat2 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat2_make(float * __restrict src, mat2 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+  dest[1][0] = src[2];
+  dest[1][1] = src[3];
+}
+
 #endif /* cglm_mat2_h */

include/cglm/mat2x3.h

@@ -0,0 +1,156 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT2X3_ZERO_INIT
+   GLM_MAT2X3_ZERO
+
+ Functions:
+   CGLM_INLINE void glm_mat2x3_copy(mat2x3 mat, mat2x3 dest);
+   CGLM_INLINE void glm_mat2x3_zero(mat2x3 mat);
+   CGLM_INLINE void glm_mat2x3_make(float * __restrict src, mat2x3 dest);
+   CGLM_INLINE void glm_mat2x3_mul(mat2x3 m1, mat3x2 m2, mat2 dest);
+   CGLM_INLINE void glm_mat2x3_mulv(mat2x3 m, vec3 v, vec2 dest);
+   CGLM_INLINE void glm_mat2x3_transpose(mat2x3 m, mat3x2 dest);
+   CGLM_INLINE void glm_mat2x3_scale(mat2x3 m, float s);
+ */
+
+#ifndef cglm_mat2x3_h
+#define cglm_mat2x3_h
+
+#include "common.h"
+
+#define GLM_MAT2X3_ZERO_INIT {{0.0f, 0.0f, 0.0f}, {0.0f, 0.0f, 0.0f}}
+
+/* for C only */
+#define GLM_MAT2X3_ZERO GLM_MAT2X3_ZERO_INIT
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat2x3_copy(mat2x3 mat, mat2x3 dest) {
+  dest[0][0] = mat[0][0];
+  dest[0][1] = mat[0][1];
+  dest[0][2] = mat[0][2];
+
+  dest[1][0] = mat[1][0];
+  dest[1][1] = mat[1][1];
+  dest[1][2] = mat[1][2];
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat2x3_zero(mat2x3 mat) {
+  CGLM_ALIGN_MAT mat2x3 t = GLM_MAT2X3_ZERO_INIT;
+  glm_mat2x3_copy(t, mat);
+}
+
+/*!
+ * @brief Create mat2x3 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat2x3_make(float * __restrict src, mat2x3 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+  dest[0][2] = src[2];
+
+  dest[1][0] = src[3];
+  dest[1][1] = src[4];
+  dest[1][2] = src[5];
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * glm_mat2x3_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat2x3_mul(mat2x3 m1, mat3x2 m2, mat2 dest) {
+  float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2],
+        a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2],
+
+        b00 = m2[0][0], b01 = m2[0][1],
+        b10 = m2[1][0], b11 = m2[1][1],
+        b20 = m2[2][0], b21 = m2[2][1];
+
+  dest[0][0] = a00 * b00 + a01 * b10 + a02 * b20;
+  dest[0][1] = a00 * b01 + a01 * b11 + a02 * b21;
+
+  dest[1][0] = a10 * b00 + a11 * b10 + a12 * b20;
+  dest[1][1] = a10 * b01 + a11 * b11 + a12 * b21;
+}
+
+/*!
+ * @brief multiply matrix with column vector and store in dest vector
+ *
+ * @param[in]  m    matrix (left)
+ * @param[in]  v    vector (right, column vector)
+ * @param[out] dest result vector
+ */
+CGLM_INLINE
+void
+glm_mat2x3_mulv(mat2x3 m, vec3 v, vec2 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2];
+
+  dest[0] = m[0][0] * v0 + m[0][1] * v1 + m[0][2] * v2;
+  dest[1] = m[1][0] * v0 + m[1][1] * v1 + m[1][2] * v2;
+}
+
+/*!
+ * @brief transpose matrix and store in dest
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat2x3_transpose(mat2x3 m, mat3x2 dest) {
+  dest[0][0] = m[0][0];  dest[0][1] = m[1][0];
+  dest[1][0] = m[0][1];  dest[1][1] = m[1][1];
+  dest[2][0] = m[0][2];  dest[2][1] = m[1][2];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]    s scalar
+ */
+CGLM_INLINE
+void
+glm_mat2x3_scale(mat2x3 m, float s) {
+  m[0][0] *= s;  m[0][1] *= s;  m[0][2] *= s;
+  m[1][0] *= s;  m[1][1] *= s;  m[1][2] *= s;
+}
+
+#endif

include/cglm/mat2x4.h

@@ -0,0 +1,156 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT2X4_ZERO_INIT
+   GLM_MAT2X4_ZERO
+
+ Functions:
+   CGLM_INLINE void glm_mat2x4_copy(mat2x4 mat, mat2x4 dest);
+   CGLM_INLINE void glm_mat2x4_zero(mat2x4 mat);
+   CGLM_INLINE void glm_mat2x4_make(float * __restrict src, mat2x4 dest);
+   CGLM_INLINE void glm_mat2x4_mul(mat2x4 m1, mat4x2 m2, mat2 dest);
+   CGLM_INLINE void glm_mat2x4_mulv(mat2x4 m, vec4 v, vec2 dest);
+   CGLM_INLINE void glm_mat2x4_transpose(mat2x4 m, mat4x2 dest);
+   CGLM_INLINE void glm_mat2x4_scale(mat2x4 m, float s);
+ */
+
+#ifndef cglm_mat2x4_h
+#define cglm_mat2x4_h
+
+#include "common.h"
+#include "vec4.h"
+
+#define GLM_MAT2X4_ZERO_INIT {{0.0f, 0.0f, 0.0f, 0.0f}, {0.0f, 0.0f, 0.0f, 0.0f}}
+
+/* for C only */
+#define GLM_MAT2X4_ZERO GLM_MAT2X4_ZERO_INIT
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat2x4_copy(mat2x4 mat, mat2x4 dest) {
+  glm_vec4_ucopy(mat[0], dest[0]);
+  glm_vec4_ucopy(mat[1], dest[1]);
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat2x4_zero(mat2x4 mat) {
+  CGLM_ALIGN_MAT mat2x4 t = GLM_MAT2X4_ZERO_INIT;
+  glm_mat2x4_copy(t, mat);
+}
+
+/*!
+ * @brief Create mat2x4 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat2x4_make(float * __restrict src, mat2x4 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+  dest[0][2] = src[2];
+  dest[0][3] = src[3];
+
+  dest[1][0] = src[4];
+  dest[1][1] = src[5];
+  dest[1][2] = src[6];
+  dest[1][3] = src[7];
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * glm_mat2x4_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat2x4_mul(mat2x4 m1, mat4x2 m2, mat2 dest) {
+  float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2], a03 = m1[0][3],
+        a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2], a13 = m1[1][3],
+
+        b00 = m2[0][0], b01 = m2[0][1],
+        b10 = m2[1][0], b11 = m2[1][1],
+        b20 = m2[2][0], b21 = m2[2][1],
+        b30 = m2[3][0], b31 = m2[3][1];
+
+  dest[0][0] = a00 * b00 + a01 * b10 + a02 * b20 + a03 * b30;
+  dest[0][1] = a00 * b01 + a01 * b11 + a02 * b21 + a03 * b31;
+
+  dest[1][0] = a10 * b00 + a11 * b10 + a12 * b20 + a13 * b30;
+  dest[1][1] = a10 * b01 + a11 * b11 + a12 * b21 + a13 * b31;
+}
+
+/*!
+ * @brief multiply matrix with column vector and store in dest vector
+ *
+ * @param[in]  m    matrix (left)
+ * @param[in]  v    vector (right, column vector)
+ * @param[out] dest result vector
+ */
+CGLM_INLINE
+void
+glm_mat2x4_mulv(mat2x4 m, vec4 v, vec2 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2], v3 = v[3];
+
+  dest[0] = m[0][0] * v0 + m[0][1] * v1 + m[0][2] * v2 + m[0][3] * v3;
+  dest[1] = m[1][0] * v0 + m[1][1] * v1 + m[1][2] * v2 + m[1][3] * v3;
+}
+
+/*!
+ * @brief transpose matrix and store in dest
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat2x4_transpose(mat2x4 m, mat4x2 dest) {
+  dest[0][0] = m[0][0];  dest[0][1] = m[1][0];
+  dest[1][0] = m[0][1];  dest[1][1] = m[1][1];
+  dest[2][0] = m[0][2];  dest[2][1] = m[1][2];
+  dest[3][0] = m[0][3];  dest[3][1] = m[1][3];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]    s scalar
+ */
+CGLM_INLINE
+void
+glm_mat2x4_scale(mat2x4 m, float s) {
+  m[0][0] *= s;  m[0][1] *= s;  m[0][2] *= s;  m[0][3] *= s;
+  m[1][0] *= s;  m[1][1] *= s;  m[1][2] *= s;  m[1][3] *= s;
+}
+
+#endif

include/cglm/mat3.h

@@ -30,6 +30,7 @@
    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);
+   CGLM_INLINE void  glm_mat3_make(float * restrict src, mat3 dest);
  */
 
 #ifndef cglm_mat3_h
@@ -42,6 +43,10 @@
 #  include "simd/sse2/mat3.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/mat3.h"
+#endif
+
 #define GLM_MAT3_IDENTITY_INIT  {{1.0f, 0.0f, 0.0f},                          \
                                  {0.0f, 1.0f, 0.0f},                          \
                                  {0.0f, 0.0f, 1.0f}}
@@ -148,7 +153,9 @@ glm_mat3_zero(mat3 mat) {
 CGLM_INLINE
 void
 glm_mat3_mul(mat3 m1, mat3 m2, mat3 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat3_mul_wasm(m1, m2, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat3_mul_sse2(m1, m2, dest);
 #else
   float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2],
@@ -421,4 +428,26 @@ glm_mat3_rmc(vec3 r, mat3 m, vec3 c) {
   return glm_vec3_dot(r, tmp);
 }
 
+/*!
+ * @brief Create mat3 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat3_make(float * __restrict src, mat3 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+  dest[0][2] = src[2];
+
+  dest[1][0] = src[3];
+  dest[1][1] = src[4];
+  dest[1][2] = src[5];
+
+  dest[2][0] = src[6];
+  dest[2][1] = src[7];
+  dest[2][2] = src[8];
+}
+
 #endif /* cglm_mat3_h */

include/cglm/mat3x2.h

@@ -0,0 +1,164 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT3X2_ZERO_INIT
+   GLM_MAT3X2_ZERO
+
+ Functions:
+   CGLM_INLINE void glm_mat3x2_copy(mat3x2 mat, mat3x2 dest);
+   CGLM_INLINE void glm_mat3x2_zero(mat3x2 mat);
+   CGLM_INLINE void glm_mat3x2_make(float * __restrict src, mat3x2 dest);
+   CGLM_INLINE void glm_mat3x2_mul(mat3x2 m1, mat2x3 m2, mat3 dest);
+   CGLM_INLINE void glm_mat3x2_mulv(mat3x2 m, vec2 v, vec3 dest);
+   CGLM_INLINE void glm_mat3x2_transpose(mat3x2 m, mat2x3 dest);
+   CGLM_INLINE void glm_mat3x2_scale(mat3x2 m, float s);
+ */
+
+#ifndef cglm_mat3x2_h
+#define cglm_mat3x2_h
+
+#include "common.h"
+
+#define GLM_MAT3X2_ZERO_INIT {{0.0f, 0.0f}, {0.0f, 0.0f}, {0.0f, 0.0f}}
+
+/* for C only */
+#define GLM_MAT3X2_ZERO GLM_MAT3X2_ZERO_INIT
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat3x2_copy(mat3x2 mat, mat3x2 dest) {
+  dest[0][0] = mat[0][0];
+  dest[0][1] = mat[0][1];
+
+  dest[1][0] = mat[1][0];
+  dest[1][1] = mat[1][1];
+
+  dest[2][0] = mat[2][0];
+  dest[2][1] = mat[2][1];
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat3x2_zero(mat3x2 mat) {
+  CGLM_ALIGN_MAT mat3x2 t = GLM_MAT3X2_ZERO_INIT;
+  glm_mat3x2_copy(t, mat);
+}
+
+/*!
+ * @brief Create mat3x2 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat3x2_make(float * __restrict src, mat3x2 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+
+  dest[1][0] = src[2];
+  dest[1][1] = src[3];
+
+  dest[2][0] = src[4];
+  dest[2][1] = src[5];
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * glm_mat3x2_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat3x2_mul(mat3x2 m1, mat2x3 m2, mat3 dest) {
+  float a00 = m1[0][0], a01 = m1[0][1],
+        a10 = m1[1][0], a11 = m1[1][1],
+        a20 = m1[2][0], a21 = m1[2][1],
+
+        b00 = m2[0][0], b01 = m2[0][1], b02 = m2[0][2],
+        b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2];
+
+  dest[0][0] = a00 * b00 + a01 * b10;
+  dest[0][1] = a00 * b01 + a01 * b11;
+  dest[0][2] = a00 * b02 + a01 * b12;
+
+  dest[1][0] = a10 * b00 + a11 * b10;
+  dest[1][1] = a10 * b01 + a11 * b11;
+  dest[1][2] = a10 * b02 + a11 * b12;
+
+  dest[2][0] = a20 * b00 + a21 * b10;
+  dest[2][1] = a20 * b01 + a21 * b11;
+  dest[2][2] = a20 * b02 + a21 * b12;
+}
+
+/*!
+ * @brief multiply matrix with column vector and store in dest vector
+ *
+ * @param[in]  m    matrix (left)
+ * @param[in]  v    vector (right, column vector)
+ * @param[out] dest result vector
+ */
+CGLM_INLINE
+void
+glm_mat3x2_mulv(mat3x2 m, vec2 v, vec3 dest) {
+  float v0 = v[0], v1 = v[1];
+
+  dest[0] = m[0][0] * v0 + m[0][1] * v1;
+  dest[1] = m[1][0] * v0 + m[1][1] * v1;
+  dest[2] = m[2][0] * v0 + m[2][1] * v1;
+}
+
+/*!
+ * @brief transpose matrix and store in dest
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat3x2_transpose(mat3x2 m, mat2x3 dest) {
+  dest[0][0] = m[0][0];  dest[0][1] = m[1][0];  dest[0][2] = m[2][0];
+  dest[1][0] = m[0][1];  dest[1][1] = m[1][1];  dest[1][2] = m[2][1];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]    s scalar
+ */
+CGLM_INLINE
+void
+glm_mat3x2_scale(mat3x2 m, float s) {
+  m[0][0] *= s;  m[0][1] *= s;  m[1][0] *= s;
+  m[1][1] *= s;  m[2][0] *= s;  m[2][1] *= s;
+}
+
+#endif

include/cglm/mat3x4.h

@@ -0,0 +1,173 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT3X4_ZERO_INIT
+   GLM_MAT3X4_ZERO
+
+ Functions:
+   CGLM_INLINE void glm_mat3x4_copy(mat3x4 mat, mat3x4 dest);
+   CGLM_INLINE void glm_mat3x4_zero(mat3x4 mat);
+   CGLM_INLINE void glm_mat3x4_make(float * __restrict src, mat3x4 dest);
+   CGLM_INLINE void glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest);
+   CGLM_INLINE void glm_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest);
+   CGLM_INLINE void glm_mat3x4_transpose(mat3x4 m, mat4x3 dest);
+   CGLM_INLINE void glm_mat3x4_scale(mat3x4 m, float s);
+ */
+
+#ifndef cglm_mat3x4_h
+#define cglm_mat3x4_h
+
+#include "common.h"
+
+#define GLM_MAT3X4_ZERO_INIT {{0.0f, 0.0f, 0.0f, 0.0f}, \
+                              {0.0f, 0.0f, 0.0f, 0.0f}, \
+                              {0.0f, 0.0f, 0.0f, 0.0f}}
+
+/* for C only */
+#define GLM_MAT3X4_ZERO GLM_MAT3X4_ZERO_INIT
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat3x4_copy(mat3x4 mat, mat3x4 dest) {
+  glm_vec4_ucopy(mat[0], dest[0]);
+  glm_vec4_ucopy(mat[1], dest[1]);
+  glm_vec4_ucopy(mat[2], dest[2]);
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat3x4_zero(mat3x4 mat) {
+  CGLM_ALIGN_MAT mat3x4 t = GLM_MAT3X4_ZERO_INIT;
+  glm_mat3x4_copy(t, mat);
+}
+
+/*!
+ * @brief Create mat3x4 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat3x4_make(float * __restrict src, mat3x4 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+  dest[0][2] = src[2];
+  dest[0][3] = src[3];
+
+  dest[1][0] = src[4];
+  dest[1][1] = src[5];
+  dest[1][2] = src[6];
+  dest[1][3] = src[7];
+
+  dest[2][0] = src[8];
+  dest[2][1] = src[9];
+  dest[2][2] = src[10];
+  dest[2][3] = src[11];
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * glm_mat3x4_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest) {
+  float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2], a03 = m1[0][3],
+        a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2], a13 = m1[1][3],
+        a20 = m1[2][0], a21 = m1[2][1], a22 = m1[2][2], a23 = m1[2][3],
+
+        b00 = m2[0][0], b01 = m2[0][1], b02 = m2[0][2],
+        b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2],
+        b20 = m2[2][0], b21 = m2[2][1], b22 = m2[2][2],
+        b30 = m2[3][0], b31 = m2[3][1], b32 = m2[3][2];
+
+  dest[0][0] = a00 * b00 + a01 * b10 + a02 * b20 + a03 * b30;
+  dest[0][1] = a00 * b01 + a01 * b11 + a02 * b21 + a03 * b31;
+  dest[0][2] = a00 * b02 + a01 * b12 + a02 * b22 + a03 * b32;
+
+  dest[1][0] = a10 * b00 + a11 * b10 + a12 * b20 + a13 * b30;
+  dest[1][1] = a10 * b01 + a11 * b11 + a12 * b21 + a13 * b31;
+  dest[1][2] = a10 * b02 + a11 * b12 + a12 * b22 + a13 * b32;
+
+  dest[2][0] = a20 * b00 + a21 * b10 + a22 * b20 + a23 * b30;
+  dest[2][1] = a20 * b01 + a21 * b11 + a22 * b21 + a23 * b31;
+  dest[2][2] = a20 * b02 + a21 * b12 + a22 * b22 + a23 * b32;
+}
+
+/*!
+ * @brief multiply matrix with column vector and store in dest vector
+ *
+ * @param[in]  m    matrix (left)
+ * @param[in]  v    vector (right, column vector)
+ * @param[out] dest result vector
+ */
+CGLM_INLINE
+void
+glm_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2], v3 = v[3];
+
+  dest[0] = m[0][0] * v0 + m[0][1] * v1 + m[0][2] * v2 + m[0][3] * v3;
+  dest[1] = m[1][0] * v0 + m[1][1] * v1 + m[1][2] * v2 + m[1][3] * v3;
+  dest[2] = m[2][0] * v0 + m[2][1] * v1 + m[2][2] * v2 + m[2][3] * v3;
+}
+
+/*!
+ * @brief transpose matrix and store in dest
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat3x4_transpose(mat3x4 m, mat4x3 dest) {
+  dest[0][0] = m[0][0];  dest[0][1] = m[1][0];  dest[0][2] = m[2][0];
+  dest[1][0] = m[0][1];  dest[1][1] = m[1][1];  dest[1][2] = m[2][1];
+  dest[2][0] = m[0][2];  dest[2][1] = m[1][2];  dest[2][2] = m[2][2];
+  dest[3][0] = m[0][3];  dest[3][1] = m[1][3];  dest[3][2] = m[2][3];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]    s scalar
+ */
+CGLM_INLINE
+void
+glm_mat3x4_scale(mat3x4 m, float s) {
+  m[0][0] *= s;  m[1][0] *= s;   m[2][0] *= s;
+  m[0][1] *= s;  m[1][1] *= s;   m[2][1] *= s;
+  m[0][2] *= s;  m[1][2] *= s;   m[2][2] *= s;
+  m[0][3] *= s;  m[1][3] *= s;   m[2][3] *= s;
+}
+
+#endif

include/cglm/mat4.h

@@ -29,7 +29,7 @@
    CGLM_INLINE void  glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest);
    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 void  glm_mat4_mulv3(mat4 m, vec3 v, float last, 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) ;
@@ -43,6 +43,7 @@
    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);
+   CGLM_INLINE void  glm_mat4_make(float * restrict src, mat4 dest);
  */
 
 #ifndef cglm_mat_h
@@ -64,6 +65,10 @@
 #  include "simd/neon/mat4.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/mat4.h"
+#endif
+
 #ifdef DEBUG
 # include <assert.h>
 #endif
@@ -121,7 +126,12 @@ glm_mat4_ucopy(mat4 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_copy(mat4 mat, mat4 dest) {
-#ifdef __AVX__
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glmm_store(dest[0], glmm_load(mat[0]));
+  glmm_store(dest[1], glmm_load(mat[1]));
+  glmm_store(dest[2], glmm_load(mat[2]));
+  glmm_store(dest[3], glmm_load(mat[3]));
+#elif defined(__AVX__)
   glmm_store256(dest[0], glmm_load256(mat[0]));
   glmm_store256(dest[2], glmm_load256(mat[2]));
 #elif defined( __SSE__ ) || defined( __SSE2__ )
@@ -187,7 +197,14 @@ glm_mat4_identity_array(mat4 * __restrict mat, size_t count) {
 CGLM_INLINE
 void
 glm_mat4_zero(mat4 mat) {
-#ifdef __AVX__
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glmm_128 x0;
+  x0 = wasm_f32x4_const_splat(0.f);
+  glmm_store(mat[0], x0);
+  glmm_store(mat[1], x0);
+  glmm_store(mat[2], x0);
+  glmm_store(mat[3], x0);
+#elif defined(__AVX__)
   __m256 y0;
   y0 = _mm256_setzero_ps();
   glmm_store256(mat[0], y0);
@@ -297,7 +314,9 @@ glm_mat4_ins3(mat3 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_mul(mat4 m1, mat4 m2, mat4 dest) {
-#ifdef __AVX__
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat4_mul_wasm(m1, m2, dest);
+#elif defined(__AVX__)
   glm_mat4_mul_avx(m1, m2, dest);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_mul_sse2(m1, m2, dest);
@@ -377,7 +396,9 @@ glm_mat4_mulN(mat4 * __restrict matrices[], uint32_t len, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat4_mulv_wasm(m, v, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_mulv_sse2(m, v, dest);
 #elif defined(CGLM_NEON_FP)
   glm_mat4_mulv_neon(m, v, dest);
@@ -497,7 +518,9 @@ glm_mat4_mulv3(mat4 m, vec3 v, float last, vec3 dest) {
 CGLM_INLINE
 void
 glm_mat4_transpose_to(mat4 m, mat4 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat4_transp_wasm(m, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_transp_sse2(m, dest);
 #elif defined(CGLM_NEON_FP)
   glm_mat4_transp_neon(m, dest);
@@ -521,7 +544,9 @@ glm_mat4_transpose_to(mat4 m, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_transpose(mat4 m) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat4_transp_wasm(m, m);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_transp_sse2(m, m);
 #elif defined(CGLM_NEON_FP)
   glm_mat4_transp_neon(m, m);
@@ -560,7 +585,9 @@ glm_mat4_scale_p(mat4 m, float s) {
 CGLM_INLINE
 void
 glm_mat4_scale(mat4 m, float s) {
-#ifdef __AVX__
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat4_scale_wasm(m, s);
+#elif defined(__AVX__)
   glm_mat4_scale_avx(m, s);
 #elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_scale_sse2(m, s);
@@ -581,7 +608,9 @@ glm_mat4_scale(mat4 m, float s) {
 CGLM_INLINE
 float
 glm_mat4_det(mat4 mat) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  return glm_mat4_det_wasm(mat);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   return glm_mat4_det_sse2(mat);
 #elif defined(CGLM_NEON_FP)
   return glm_mat4_det_neon(mat);
@@ -679,7 +708,9 @@ glm_mat4_inv(mat4 mat, mat4 dest) {
 CGLM_INLINE
 void
 glm_mat4_inv_fast(mat4 mat, mat4 dest) {
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_mat4_inv_fast_wasm(mat, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_mat4_inv_fast_sse2(mat, dest);
 #else
   glm_mat4_inv(mat, dest);
@@ -751,4 +782,24 @@ glm_mat4_rmc(vec4 r, mat4 m, vec4 c) {
   return glm_vec4_dot(r, tmp);
 }
 
+/*!
+ * @brief Create mat4 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat4_make(float * __restrict src, mat4 dest) {
+  dest[0][0] = src[0];   dest[1][0] = src[4];
+  dest[0][1] = src[1];   dest[1][1] = src[5];
+  dest[0][2] = src[2];   dest[1][2] = src[6];
+  dest[0][3] = src[3];   dest[1][3] = src[7];
+
+  dest[2][0] = src[8];   dest[3][0] = src[12];
+  dest[2][1] = src[9];   dest[3][1] = src[13];
+  dest[2][2] = src[10];  dest[3][2] = src[14];
+  dest[2][3] = src[11];  dest[3][3] = src[15];
+}
+
 #endif /* cglm_mat_h */

include/cglm/mat4x2.h

@@ -0,0 +1,186 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT4X2_ZERO_INIT
+   GLM_MAT4X2_ZERO
+
+ Functions:
+   CGLM_INLINE void glm_mat4x2_copy(mat4x2 mat, mat4x2 dest);
+   CGLM_INLINE void glm_mat4x2_zero(mat4x2 mat);
+   CGLM_INLINE void glm_mat4x2_make(float * __restrict src, mat4x2 dest);
+   CGLM_INLINE void glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest);
+   CGLM_INLINE void glm_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest);
+   CGLM_INLINE void glm_mat4x2_transpose(mat4x2 m, mat2x4 dest);
+   CGLM_INLINE void glm_mat4x2_scale(mat4x2 m, float s);
+ */
+
+#ifndef cglm_mat4x2_h
+#define cglm_mat4x2_h
+
+#include "common.h"
+
+#define GLM_MAT4X2_ZERO_INIT {{0.0f, 0.0f}, {0.0f, 0.0f}, {0.0f, 0.0f}, {0.0f, 0.0f}}
+
+/* for C only */
+#define GLM_MAT4X2_ZERO GLM_MAT4X2_ZERO_INIT
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat4x2_copy(mat4x2 mat, mat4x2 dest) {
+  dest[0][0] = mat[0][0];
+  dest[0][1] = mat[0][1];
+
+  dest[1][0] = mat[1][0];
+  dest[1][1] = mat[1][1];
+
+  dest[2][0] = mat[2][0];
+  dest[2][1] = mat[2][1];
+
+  dest[3][0] = mat[3][0];
+  dest[3][1] = mat[3][1];
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat4x2_zero(mat4x2 mat) {
+  CGLM_ALIGN_MAT mat4x2 t = GLM_MAT4X2_ZERO_INIT;
+  glm_mat4x2_copy(t, mat);
+}
+
+/*!
+ * @brief Create mat4x2 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat4x2_make(float * __restrict src, mat4x2 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+
+  dest[1][0] = src[2];
+  dest[1][1] = src[3];
+
+  dest[2][0] = src[4];
+  dest[2][1] = src[5];
+
+  dest[3][0] = src[6];
+  dest[3][1] = src[7];
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * glm_mat4x2_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest) {
+  float a00 = m1[0][0], a01 = m1[0][1],
+        a10 = m1[1][0], a11 = m1[1][1],
+        a20 = m1[2][0], a21 = m1[2][1],
+        a30 = m1[3][0], a31 = m1[3][1],
+
+        b00 = m2[0][0], b01 = m2[0][1], b02 = m2[0][2], b03 = m2[0][3],
+        b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2], b13 = m2[1][3];
+
+  dest[0][0] = a00 * b00 + a01 * b10;
+  dest[0][1] = a00 * b01 + a01 * b11;
+  dest[0][2] = a00 * b02 + a01 * b12;
+  dest[0][3] = a00 * b03 + a01 * b13;
+
+  dest[1][0] = a10 * b00 + a11 * b10;
+  dest[1][1] = a10 * b01 + a11 * b11;
+  dest[1][2] = a10 * b02 + a11 * b12;
+  dest[1][3] = a10 * b03 + a11 * b13;
+
+  dest[2][0] = a20 * b00 + a21 * b10;
+  dest[2][1] = a20 * b01 + a21 * b11;
+  dest[2][2] = a20 * b02 + a21 * b12;
+  dest[2][3] = a20 * b03 + a21 * b13;
+
+  dest[3][0] = a30 * b00 + a31 * b10;
+  dest[3][1] = a30 * b01 + a31 * b11;
+  dest[3][2] = a30 * b02 + a31 * b12;
+  dest[3][3] = a30 * b03 + a31 * b13;
+}
+
+/*!
+ * @brief multiply matrix with column vector and store in dest vector
+ *
+ * @param[in]  m    matrix (left)
+ * @param[in]  v    vector (right, column vector)
+ * @param[out] dest result vector
+ */
+CGLM_INLINE
+void
+glm_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest) {
+  float v0 = v[0], v1 = v[1];
+
+  dest[0] = m[0][0] * v0 + m[0][1] * v1;
+  dest[1] = m[1][0] * v0 + m[1][1] * v1;
+  dest[2] = m[2][0] * v0 + m[2][1] * v1;
+  dest[3] = m[3][0] * v0 + m[3][1] * v1;
+}
+
+/*!
+ * @brief transpose matrix and store in dest
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat4x2_transpose(mat4x2 m, mat2x4 dest) {
+  dest[0][0] = m[0][0];
+  dest[0][1] = m[1][0];
+  dest[0][2] = m[2][0];
+  dest[0][3] = m[3][0];
+  dest[1][0] = m[0][1];
+  dest[1][1] = m[1][1];
+  dest[1][2] = m[2][1];
+  dest[1][3] = m[3][1];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]    s scalar
+ */
+CGLM_INLINE
+void
+glm_mat4x2_scale(mat4x2 m, float s) {
+  m[0][0] *= s;  m[0][1] *= s;  m[1][0] *= s;  m[1][1] *= s;
+  m[2][0] *= s;  m[2][1] *= s;  m[3][0] *= s;  m[3][1] *= s;
+}
+
+#endif

include/cglm/mat4x3.h

@@ -0,0 +1,203 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Macros:
+   GLM_MAT4X3_ZERO_INIT
+   GLM_MAT4X3_ZERO
+
+ Functions:
+   CGLM_INLINE void glm_mat4x3_copy(mat4x3 mat, mat4x3 dest);
+   CGLM_INLINE void glm_mat4x3_zero(mat4x3 mat);
+   CGLM_INLINE void glm_mat4x3_make(float * __restrict src, mat4x3 dest);
+   CGLM_INLINE void glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest);
+   CGLM_INLINE void glm_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest);
+   CGLM_INLINE void glm_mat4x3_transpose(mat4x3 m, mat3x4 dest);
+   CGLM_INLINE void glm_mat4x3_scale(mat4x3 m, float s);
+ */
+
+#ifndef cglm_mat4x3_h
+#define cglm_mat4x3_h
+
+#include "common.h"
+
+#define GLM_MAT4X3_ZERO_INIT {{0.0f, 0.0f, 0.0f}, {0.0f, 0.0f, 0.0f}, \
+                              {0.0f, 0.0f, 0.0f}, {0.0f, 0.0f, 0.0f}}
+
+/* for C only */
+#define GLM_MAT4X3_ZERO GLM_MAT4X3_ZERO_INIT
+
+/*!
+ * @brief copy all members of [mat] to [dest]
+ *
+ * @param[in]  mat  source
+ * @param[out] dest destination
+ */
+CGLM_INLINE
+void
+glm_mat4x3_copy(mat4x3 mat, mat4x3 dest) {
+  dest[0][0] = mat[0][0];
+  dest[0][1] = mat[0][1];
+  dest[0][2] = mat[0][2];
+
+  dest[1][0] = mat[1][0];
+  dest[1][1] = mat[1][1];
+  dest[1][2] = mat[1][2];
+
+  dest[2][0] = mat[2][0];
+  dest[2][1] = mat[2][1];
+  dest[2][2] = mat[2][2];
+
+  dest[3][0] = mat[3][0];
+  dest[3][1] = mat[3][1];
+  dest[3][2] = mat[3][2];
+}
+
+/*!
+ * @brief make given matrix zero.
+ *
+ * @param[in, out]  mat  matrix
+ */
+CGLM_INLINE
+void
+glm_mat4x3_zero(mat4x3 mat) {
+  CGLM_ALIGN_MAT mat4x3 t = GLM_MAT4X3_ZERO_INIT;
+  glm_mat4x3_copy(t, mat);
+}
+
+/*!
+ * @brief Create mat4x3 matrix from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest matrix
+ */
+CGLM_INLINE
+void
+glm_mat4x3_make(float * __restrict src, mat4x3 dest) {
+  dest[0][0] = src[0];
+  dest[0][1] = src[1];
+  dest[0][2] = src[2];
+
+  dest[1][0] = src[3];
+  dest[1][1] = src[4];
+  dest[1][2] = src[5];
+
+  dest[2][0] = src[6];
+  dest[2][1] = src[7];
+  dest[2][2] = src[8];
+
+  dest[3][0] = src[9];
+  dest[3][1] = src[10];
+  dest[3][2] = src[11];
+}
+
+/*!
+ * @brief multiply m1 and m2 to dest
+ *
+ * m1, m2 and dest matrices can be same matrix, it is possible to write this:
+ *
+ * @code
+ * glm_mat4x3_mul(m, m, m);
+ * @endcode
+ *
+ * @param[in]  m1   left matrix
+ * @param[in]  m2   right matrix
+ * @param[out] dest destination matrix
+ */
+CGLM_INLINE
+void
+glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest) {
+  float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2],
+        a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2],
+        a20 = m1[2][0], a21 = m1[2][1], a22 = m1[2][2],
+        a30 = m1[3][0], a31 = m1[3][1], a32 = m1[3][2],
+
+        b00 = m2[0][0], b01 = m2[0][1], b02 = m2[0][2], b03 = m2[0][3],
+        b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2], b13 = m2[1][3],
+        b20 = m2[2][0], b21 = m2[2][1], b22 = m2[2][2], b23 = m2[2][3];
+
+  dest[0][0] = a00 * b00 + a01 * b10 + a02 * b20;
+  dest[0][1] = a00 * b01 + a01 * b11 + a02 * b21;
+  dest[0][2] = a00 * b02 + a01 * b12 + a02 * b22;
+  dest[0][3] = a00 * b03 + a01 * b13 + a02 * b23;
+
+  dest[1][0] = a10 * b00 + a11 * b10 + a12 * b20;
+  dest[1][1] = a10 * b01 + a11 * b11 + a12 * b21;
+  dest[1][2] = a10 * b02 + a11 * b12 + a12 * b22;
+  dest[1][3] = a10 * b03 + a11 * b13 + a12 * b23;
+
+  dest[2][0] = a20 * b00 + a21 * b10 + a22 * b20;
+  dest[2][1] = a20 * b01 + a21 * b11 + a22 * b21;
+  dest[2][2] = a20 * b02 + a21 * b12 + a22 * b22;
+  dest[2][3] = a20 * b03 + a21 * b13 + a22 * b23;
+
+  dest[3][0] = a30 * b00 + a31 * b10 + a32 * b20;
+  dest[3][1] = a30 * b01 + a31 * b11 + a32 * b21;
+  dest[3][2] = a30 * b02 + a31 * b12 + a32 * b22;
+  dest[3][3] = a30 * b03 + a31 * b13 + a32 * b23;
+}
+
+/*!
+ * @brief multiply matrix with column vector and store in dest vector
+ *
+ * @param[in]  m    matrix (left)
+ * @param[in]  v    vector (right, column vector)
+ * @param[out] dest result vector
+ */
+CGLM_INLINE
+void
+glm_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2];
+
+  dest[0] = m[0][0] * v0 + m[0][1] * v1 + m[0][2] * v2;
+  dest[1] = m[1][0] * v0 + m[1][1] * v1 + m[1][2] * v2;
+  dest[2] = m[2][0] * v0 + m[2][1] * v1 + m[2][2] * v2;
+  dest[3] = m[3][0] * v0 + m[3][1] * v1 + m[3][2] * v2;
+}
+
+/*!
+ * @brief transpose matrix and store in dest
+ *
+ * @param[in]  m     matrix
+ * @param[out] dest  result
+ */
+CGLM_INLINE
+void
+glm_mat4x3_transpose(mat4x3 m, mat3x4 dest) {
+  dest[0][0] = m[0][0];
+  dest[0][1] = m[1][0];
+  dest[0][2] = m[2][0];
+  dest[0][3] = m[3][0];
+
+  dest[1][0] = m[0][1];
+  dest[1][1] = m[1][1];
+  dest[1][2] = m[2][1];
+  dest[1][3] = m[3][1];
+
+  dest[2][0] = m[0][2];
+  dest[2][1] = m[1][2];
+  dest[2][2] = m[2][2];
+  dest[2][3] = m[3][2];
+}
+
+/*!
+ * @brief scale (multiply with scalar) matrix
+ *
+ * multiply matrix with scalar
+ *
+ * @param[in, out] m matrix
+ * @param[in]    s scalar
+ */
+CGLM_INLINE
+void
+glm_mat4x3_scale(mat4x3 m, float s) {
+  m[0][0] *= s;  m[0][1] *= s;  m[0][2] *= s;  m[1][0] *= s;
+  m[1][1] *= s;  m[1][2] *= s;  m[2][0] *= s;  m[2][1] *= s;
+  m[2][2] *= s;  m[3][0] *= s;  m[3][1] *= s;  m[3][2] *= s;
+}
+
+#endif

include/cglm/project.h

@@ -114,6 +114,28 @@ glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
 #endif
 }
 
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z(vec3 v, mat4 m) {
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+  return glm_project_z_zo(v, m);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+  return glm_project_z_no(v, m);
+#endif
+}
+
 /*!
  * @brief define a picking region
  *
@@ -124,7 +146,7 @@ glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
  */
 CGLM_INLINE
 void
-glm_pickmatrix(vec3 center, vec2 size, vec4 vp, mat4 dest) {
+glm_pickmatrix(vec2 center, vec2 size, vec4 vp, mat4 dest) {
   mat4 res;
   vec3 v;
 

include/cglm/quat.h

@@ -49,6 +49,7 @@
                                   versor dest);
    CGLM_INLINE void glm_quat_rotatev(versor q, vec3 v, vec3 dest);
    CGLM_INLINE void glm_quat_rotate(mat4 m, versor q, mat4 dest);
+   CGLM_INLINE void glm_quat_make(float * restrict src, versor dest);
  */
 
 #ifndef cglm_quat_h
@@ -70,6 +71,10 @@
 #  include "simd/neon/quat.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/quat.h"
+#endif
+
 CGLM_INLINE void glm_quat_normalize(versor q);
 
 /*
@@ -238,7 +243,22 @@ glm_quat_norm(versor q) {
 CGLM_INLINE
 void
 glm_quat_normalize_to(versor q, versor dest) {
-#if defined( __SSE2__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glmm_128 xdot, x0;
+  float  dot;
+
+  x0   = glmm_load(q);
+  xdot = glmm_vdot(x0, x0);
+  /* dot  = _mm_cvtss_f32(xdot); */
+  dot  = wasm_f32x4_extract_lane(xdot, 0);
+
+  if (dot <= 0.0f) {
+    glm_quat_identity(dest);
+    return;
+  }
+
+  glmm_store(dest, wasm_f32x4_div(x0, wasm_f32x4_sqrt(xdot)));
+#elif defined( __SSE2__ ) || defined( __SSE2__ )
   __m128 xdot, x0;
   float  dot;
 
@@ -438,7 +458,9 @@ glm_quat_mul(versor p, versor q, versor dest) {
     + (a1 d2 + b1 c2 − c1 b2 + d1 a2)k
        a1 a2 − b1 b2 − c1 c2 − d1 d2
    */
-#if defined( __SSE__ ) || defined( __SSE2__ )
+#if defined(__wasm__) && defined(__wasm_simd128__)
+  glm_quat_mul_wasm(p, q, dest);
+#elif defined( __SSE__ ) || defined( __SSE2__ )
   glm_quat_mul_sse2(p, q, dest);
 #elif defined(CGLM_NEON_FP)
   glm_quat_mul_neon(p, q, dest);
@@ -864,4 +886,17 @@ glm_quat_rotate_atm(mat4 m, versor q, vec3 pivot) {
   glm_translate(m, pivotInv);
 }
 
+/*!
+ * @brief Create quaternion from pointer
+ *
+ * @param[in]  src  pointer to an array of floats
+ * @param[out] dest quaternion
+ */
+CGLM_INLINE
+void
+glm_quat_make(float * __restrict src, versor dest) {
+  dest[0] = src[0]; dest[1] = src[1];
+  dest[2] = src[2]; dest[3] = src[3];
+}
+
 #endif /* cglm_quat_h */

include/cglm/simd/arm.h

@@ -12,6 +12,8 @@
 
 #if defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC) || defined(__aarch64__)
 # define CGLM_ARM64 1
+#else
+# define CGLM_ARM64 0
 #endif
 
 #define glmm_load(p)      vld1q_f32(p)
@@ -38,6 +40,22 @@
 #define glmm_combine_lh(x, y) vcombine_f32(vget_low_f32(x),  vget_high_f32(y))
 #define glmm_combine_hh(x, y) vcombine_f32(vget_high_f32(x), vget_high_f32(y))
 
+#if defined(_WIN32) && defined(_MSC_VER)
+/* #  define glmm_float32x4_init(x, y, z, w) { .n128_f32 = { x, y, z, w } } */
+CGLM_INLINE
+float32x4_t
+glmm_float32x4_init(float x, float y, float z, float w) {
+  CGLM_ALIGN(16) float v[4] = {x, y, z, w};
+  return vld1q_f32(v);
+}
+#else
+#  define glmm_float32x4_init(x, y, z, w) { x, y, z, w }
+#endif
+
+#define glmm_float32x4_SIGNMASK_PNPN glmm_float32x4_init( 0.f, -0.f,  0.f, -0.f)
+#define glmm_float32x4_SIGNMASK_NPNP glmm_float32x4_init(-0.f,  0.f, -0.f,  0.f)
+#define glmm_float32x4_SIGNMASK_NPPN glmm_float32x4_init(-0.f,  0.f,  0.f, -0.f)
+
 static inline
 float32x4_t
 glmm_abs(float32x4_t v) {

include/cglm/simd/intrin.h

@@ -17,7 +17,7 @@
 #    ifndef __SSE__
 #      define __SSE__
 #    endif
-#  endif
+#endif
 /* do not use alignment for older visual studio versions */
 #  if _MSC_VER < 1913     /* Visual Studio 2017 version 15.6 */
 #    define CGLM_ALL_UNALIGNED
@@ -63,23 +63,56 @@
 #endif
 
 /* ARM Neon */
-#if defined(__ARM_NEON)
+#if defined(_WIN32)
+/* TODO: non-ARM stuff already inported, will this be better option */
+/* #  include <intrin.h> */
+
+#  if defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC)
+#    include <arm64intr.h>
+#    include <arm64_neon.h>
+#    ifndef CGLM_NEON_FP
+#      define CGLM_NEON_FP  1
+#    endif
+#    ifndef CGLM_SIMD_ARM
+#      define CGLM_SIMD_ARM
+#    endif
+#  elif defined(_M_ARM)
+#    include <armintr.h>
+#    include <arm_neon.h>
+#    ifndef CGLM_NEON_FP
+#      define CGLM_NEON_FP 1
+#    endif
+#    ifndef CGLM_SIMD_ARM
+#      define CGLM_SIMD_ARM
+#    endif
+#  endif
+
+#else /* non-windows */
+#  if defined(__ARM_NEON) || defined(__ARM_NEON__)
 #    include <arm_neon.h>
 #    if defined(__ARM_NEON_FP)
 #      define CGLM_NEON_FP 1
+#    endif
 #    ifndef CGLM_SIMD_ARM
 #      define CGLM_SIMD_ARM
 #    endif
 #  endif
 #endif
 
-#if defined(CGLM_SIMD_x86) || defined(CGLM_NEON_FP)
+/* WebAssembly */
+#if defined(__wasm__) && defined(__wasm_simd128__)
+#  ifndef CGLM_SIMD_WASM
+#    define CGLM_SIMD_WASM
+#  endif
+#endif
+
+#if defined(CGLM_SIMD_x86) || defined(CGLM_SIMD_ARM) || defined(CGLM_SIMD_WASM)
 #  ifndef CGLM_SIMD
 #    define CGLM_SIMD
 #  endif
 #endif
 
-#if defined(CGLM_SIMD_x86)
+#if defined(CGLM_SIMD_x86) && !defined(CGLM_SIMD_WASM)
 #  include "x86.h"
 #endif
 
@@ -87,4 +120,8 @@
 #  include "arm.h"
 #endif
 
+#if defined(CGLM_SIMD_WASM)
+#  include "wasm.h"
+#endif
+
 #endif /* cglm_intrin_h */

include/cglm/simd/neon/affine.h

@@ -7,7 +7,7 @@
 
 #ifndef cglm_affine_neon_h
 #define cglm_affine_neon_h
-#if defined(__ARM_NEON_FP)
+#if defined(CGLM_NEON_FP)
 
 #include "../../common.h"
 #include "../intrin.h"
@@ -86,13 +86,12 @@ CGLM_INLINE
 void
 glm_inv_tr_neon(mat4 mat) {
   float32x4x4_t vmat;
-  glmm_128      r0, r1, r2, r3, x0;
+  glmm_128      r0, r1, r2, x0;
 
   vmat = vld4q_f32(mat[0]);
   r0   = vmat.val[0];
   r1   = vmat.val[1];
   r2   = vmat.val[2];
-  r3   = vmat.val[3];
 
   x0 = glmm_fmadd(r0, glmm_splat_w(r0),
                   glmm_fmadd(r1, glmm_splat_w(r1),

include/cglm/simd/neon/mat2.h

@@ -7,7 +7,7 @@
 
 #ifndef cglm_mat2_neon_h
 #define cglm_mat2_neon_h
-#if defined(__ARM_NEON_FP)
+#if defined(CGLM_NEON_FP)
 
 #include "../../common.h"
 #include "../intrin.h"

include/cglm/simd/neon/mat4.h

@@ -7,7 +7,7 @@
 
 #ifndef cglm_mat4_neon_h
 #define cglm_mat4_neon_h
-#if defined(__ARM_NEON_FP)
+#if defined(CGLM_NEON_FP)
 
 #include "../../common.h"
 #include "../intrin.h"
@@ -108,7 +108,7 @@ glm_mat4_det_neon(mat4 mat) {
   float32x4_t   r0, r1, r2, r3, x0, x1, x2;
   float32x2_t   ij, op, mn, kl, nn, mm, jj, ii, gh, ef, t12, t34;
   float32x4x2_t a1;
-  float32x4_t   x3 = { 0.f, -0.f, 0.f, -0.f };
+  float32x4_t   x3 = glmm_float32x4_SIGNMASK_PNPN;
 
   /* 127 <- 0, [square] det(A) = det(At) */
   r0 = glmm_load(mat[0]);              /* d c b a */
@@ -181,7 +181,7 @@ glm_mat4_inv_neon(mat4 mat, mat4 dest) {
                 x0, x1, x2, x3, x4, x5, x6, x7, x8;
   float32x4x2_t a1;
   float32x2_t   lp, ko, hg, jn, im, fe, ae, bf, cg, dh;
-  float32x4_t   x9 = { -0.f, 0.f, -0.f, 0.f };
+  float32x4_t   x9 = glmm_float32x4_SIGNMASK_NPNP;
 
   x8 = vrev64q_f32(x9);
 

include/cglm/simd/neon/quat.h

@@ -7,7 +7,7 @@
 
 #ifndef cglm_quat_neon_h
 #define cglm_quat_neon_h
-#if defined(__ARM_NEON_FP)
+#if defined(CGLM_NEON_FP)
 
 #include "../../common.h"
 #include "../intrin.h"
@@ -23,7 +23,8 @@ glm_quat_mul_neon(versor p, versor q, versor dest) {
    */
 
   glmm_128 xp, xq, xqr, r, x, y, z, s2, s3;
-  glmm_128 s1 = {-0.f, 0.f, 0.f, -0.f};
+  glmm_128 s1 = glmm_float32x4_SIGNMASK_NPPN;
+
   float32x2_t   qh, ql;
   
   xp  = glmm_load(p); /* 3 2 1 0 */

include/cglm/simd/sse2/affine.h

@@ -98,7 +98,7 @@ glm_inv_tr_sse2(mat4 mat) {
   x2 = glmm_shuff1(r3, 0, 0, 0, 0);
   x3 = glmm_shuff1(r3, 1, 1, 1, 1);
   x4 = glmm_shuff1(r3, 2, 2, 2, 2);
-  x5 = _mm_set1_ps(-0.f);
+  x5 = glmm_float32x4_SIGNMASK_NEG;
 
   x0 = glmm_fmadd(r0, x2, glmm_fmadd(r1, x3, _mm_mul_ps(r2, x4)));
   x0 = _mm_xor_ps(x0, x5);

include/cglm/simd/sse2/mat4.h

@@ -153,7 +153,7 @@ glm_mat4_det_sse2(mat4 mat) {
                   _mm_shuffle_ps(x0, x1, _MM_SHUFFLE(2, 2, 3, 1)),
                   x2);
   
-  x2 = _mm_xor_ps(x2, _mm_set_ps(-0.f, 0.f, -0.f, 0.f));
+  x2 = _mm_xor_ps(x2, glmm_float32x4_SIGNMASK_NPNP);
   
   return glmm_hadd(_mm_mul_ps(x2, r0));
 }
@@ -166,7 +166,8 @@ glm_mat4_inv_fast_sse2(mat4 mat, mat4 dest) {
          t0, t1, t2, t3, t4, t5,
          x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
 
-  x8 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f);
+  /* x8 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f); */
+  x8 = glmm_float32x4_SIGNMASK_NPNP;
   x9 = glmm_shuff1(x8, 2, 1, 2, 1);
 
   /* 127 <- 0 */
@@ -302,7 +303,8 @@ glm_mat4_inv_sse2(mat4 mat, mat4 dest) {
          t0, t1, t2, t3, t4, t5,
          x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
 
-  x8 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f);
+  /* x8 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f); */
+  x8 = glmm_float32x4_SIGNMASK_NPNP;
   x9 = glmm_shuff1(x8, 2, 1, 2, 1);
 
   /* 127 <- 0 */

include/cglm/simd/sse2/quat.h

@@ -26,7 +26,7 @@ glm_quat_mul_sse2(versor p, versor q, versor dest) {
 
   xp = glmm_load(p); /* 3 2 1 0 */
   xq = glmm_load(q);
-  x1 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f); /* TODO: _mm_set1_ss() + shuff ? */
+  x1 = glmm_float32x4_SIGNMASK_NPNP; /* TODO: _mm_set1_ss() + shuff ? */
   r  = _mm_mul_ps(glmm_splat_w(xp), xq);
 
   x2 = _mm_unpackhi_ps(x1, x1);

include/cglm/simd/wasm.h

@@ -0,0 +1,198 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_simd_wasm_h
+#define cglm_simd_wasm_h
+#include "intrin.h"
+#ifdef CGLM_SIMD_WASM
+#include <wasm_simd128.h>
+
+#define glmm_load(p)      wasm_v128_load(p)
+#define glmm_store(p, a)  wasm_v128_store(p, (a))
+
+#define glmm_set1(x) wasm_f32x4_splat(x)
+#define glmm_128     v128_t
+
+#define glmm_shuff1(xmm, z, y, x, w) wasm_i32x4_shuffle(xmm, xmm, w, x, y, z)
+
+#define glmm_splat(x, lane) glmm_shuff1(x, lane, lane, lane, lane)
+
+#define glmm_splat_x(x) glmm_splat(x, 0)
+#define glmm_splat_y(x) glmm_splat(x, 1)
+#define glmm_splat_z(x) glmm_splat(x, 2)
+#define glmm_splat_w(x) glmm_splat(x, 3)
+
+#define GLMM_NEGZEROf 0x80000000 /*  0x80000000 ---> -0.0f  */
+
+/* _mm_set_ps(X, Y, Z, W); */
+#define GLMM__SIGNMASKf(X, Y, Z, W) wasm_i32x4_const(X, Y, Z, W)
+
+#define glmm_float32x4_SIGNMASK_PNPN GLMM__SIGNMASKf(0, GLMM_NEGZEROf, 0, GLMM_NEGZEROf)
+#define glmm_float32x4_SIGNMASK_NPNP GLMM__SIGNMASKf(GLMM_NEGZEROf, 0, GLMM_NEGZEROf, 0)
+#define glmm_float32x4_SIGNMASK_NPPN GLMM__SIGNMASKf(GLMM_NEGZEROf, 0, 0, GLMM_NEGZEROf)
+#define glmm_float32x4_SIGNMASK_NEG wasm_i32x4_const_splat(GLMM_NEGZEROf)
+
+static inline
+glmm_128
+glmm_abs(glmm_128 x) {
+  return wasm_f32x4_abs(x);
+}
+
+static inline
+glmm_128
+glmm_vhadd(glmm_128 v) {
+  glmm_128 x0;
+  x0 = wasm_f32x4_add(v,  glmm_shuff1(v, 0, 1, 2, 3));
+  x0 = wasm_f32x4_add(x0, glmm_shuff1(x0, 1, 0, 0, 1));
+  return x0;
+}
+
+static inline
+glmm_128
+glmm_vhadds(glmm_128 v) {
+  glmm_128 shuf, sums;
+  shuf = glmm_shuff1(v, 2, 3, 0, 1);
+  sums = wasm_f32x4_add(v, shuf);
+  /* shuf = _mm_movehl_ps(shuf, sums); */
+  shuf = wasm_i32x4_shuffle(shuf, sums, 6, 7, 2, 3);
+  sums = wasm_i32x4_shuffle(sums, wasm_f32x4_add(sums, shuf), 4, 1, 2, 3);
+  return sums;
+}
+
+static inline
+float
+glmm_hadd(glmm_128 v) {
+  return wasm_f32x4_extract_lane(glmm_vhadds(v), 0);
+}
+
+static inline
+glmm_128
+glmm_vhmin(glmm_128 v) {
+  glmm_128 x0, x1, x2;
+  x0 = glmm_shuff1(v, 2, 3, 2, 3);     /* [2, 3, 2, 3] */
+  x1 = wasm_f32x4_pmin(x0, v);   /* [0|2, 1|3, 2|2, 3|3] */
+  x2 = glmm_splat(x1, 1);              /* [1|3, 1|3, 1|3, 1|3] */
+  return wasm_f32x4_pmin(x1, x2);
+}
+
+static inline
+float
+glmm_hmin(glmm_128 v) {
+  return wasm_f32x4_extract_lane(glmm_vhmin(v), 0);
+}
+
+static inline
+glmm_128
+glmm_vhmax(glmm_128 v) {
+  glmm_128 x0, x1, x2;
+  x0 = glmm_shuff1(v, 2, 3, 2, 3);     /* [2, 3, 2, 3] */
+  x1 = wasm_f32x4_pmax(x0, v);   /* [0|2, 1|3, 2|2, 3|3] */
+  x2 = glmm_splat(x1, 1);              /* [1|3, 1|3, 1|3, 1|3] */
+  /* _mm_max_ss */
+  return wasm_i32x4_shuffle(x1, wasm_f32x4_pmax(x1, x2), 4, 1, 2, 3);
+}
+
+static inline
+float
+glmm_hmax(glmm_128 v) {
+  return wasm_f32x4_extract_lane(glmm_vhmax(v), 0);
+}
+
+static inline
+glmm_128
+glmm_vdots(glmm_128 a, glmm_128 b) {
+  return glmm_vhadds(wasm_f32x4_mul(a, b));
+}
+
+static inline
+glmm_128
+glmm_vdot(glmm_128 a, glmm_128 b) {
+  glmm_128 x0;
+  x0 = wasm_f32x4_mul(a, b);
+  x0 = wasm_f32x4_add(x0, glmm_shuff1(x0, 1, 0, 3, 2));
+  return wasm_f32x4_add(x0, glmm_shuff1(x0, 0, 1, 0, 1));
+}
+
+static inline
+float
+glmm_dot(glmm_128 a, glmm_128 b) {
+  return wasm_f32x4_extract_lane(glmm_vdots(a, b), 0);
+}
+
+static inline
+float
+glmm_norm(glmm_128 a) {
+  glmm_128 x0;
+  x0 = glmm_vhadds(wasm_f32x4_mul(a, a));
+  return wasm_f32x4_extract_lane(
+          wasm_i32x4_shuffle(x0, wasm_f32x4_sqrt(x0),4, 1, 2, 3), 0);
+}
+
+static inline
+float
+glmm_norm2(glmm_128 a) {
+  return wasm_f32x4_extract_lane(glmm_vhadds(wasm_f32x4_mul(a, a)), 0);
+}
+
+static inline
+float
+glmm_norm_one(glmm_128 a) {
+  return wasm_f32x4_extract_lane(glmm_vhadds(glmm_abs(a)), 0);
+}
+
+static inline
+float
+glmm_norm_inf(glmm_128 a) {
+  return wasm_f32x4_extract_lane(glmm_vhmax(glmm_abs(a)), 0);
+}
+
+static inline
+glmm_128
+glmm_load3(float v[3]) {
+  glmm_128 xy = wasm_v128_load64_zero(v);
+  return wasm_f32x4_replace_lane(xy, 2, v[2]);
+}
+
+static inline
+void
+glmm_store3(float v[3], glmm_128 vx) {
+  wasm_v128_store64_lane(v, vx, 0);
+  wasm_v128_store32_lane(&v[2], vx, 2);
+}
+
+static inline
+glmm_128
+glmm_div(glmm_128 a, glmm_128 b) {
+  return wasm_f32x4_div(a, b);
+}
+
+static inline
+glmm_128
+glmm_fmadd(glmm_128 a, glmm_128 b, glmm_128 c) {
+  return wasm_f32x4_add(c, wasm_f32x4_mul(a, b));
+}
+
+static inline
+glmm_128
+glmm_fnmadd(glmm_128 a, glmm_128 b, glmm_128 c) {
+  return wasm_f32x4_sub(c, wasm_f32x4_mul(a, b));
+}
+
+static inline
+glmm_128
+glmm_fmsub(glmm_128 a, glmm_128 b, glmm_128 c) {
+  return wasm_f32x4_sub(wasm_f32x4_mul(a, b), c);
+}
+
+static inline
+glmm_128
+glmm_fnmsub(glmm_128 a, glmm_128 b, glmm_128 c) {
+  return wasm_f32x4_neg(wasm_f32x4_add(wasm_f32x4_mul(a, b), c));
+}
+
+#endif
+#endif /* cglm_simd_wasm_h */

include/cglm/simd/wasm/affine.h

@@ -0,0 +1,127 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_affine_mat_wasm_h
+#define cglm_affine_mat_wasm_h
+#if defined(__wasm__) && defined(__wasm_simd128__)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_mul_wasm(mat4 m1, mat4 m2, mat4 dest) {
+  /* D = R * L (Column-Major) */
+  glmm_128 l, r0, r1, r2, r3, v0, v1, v2, v3;
+
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+  r3 = glmm_load(m2[3]);
+
+  v0 = wasm_f32x4_mul(glmm_splat_x(r0), l);
+  v1 = wasm_f32x4_mul(glmm_splat_x(r1), l);
+  v2 = wasm_f32x4_mul(glmm_splat_x(r2), l);
+  v3 = wasm_f32x4_mul(glmm_splat_x(r3), l);
+
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_y(r3), l, v3);
+
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_z(r3), l, v3);
+
+  l  = glmm_load(m1[3]);
+  v3 = glmm_fmadd(glmm_splat_w(r3), l, v3);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], v3);
+}
+
+CGLM_INLINE
+void
+glm_mul_rot_wasm(mat4 m1, mat4 m2, mat4 dest) {
+  /* D = R * L (Column-Major) */
+
+  glmm_128 l, r0, r1, r2, v0, v1, v2;
+
+  l  = glmm_load(m1[0]);
+  r0 = glmm_load(m2[0]);
+  r1 = glmm_load(m2[1]);
+  r2 = glmm_load(m2[2]);
+
+  v0 = wasm_f32x4_mul(glmm_splat_x(r0), l);
+  v1 = wasm_f32x4_mul(glmm_splat_x(r1), l);
+  v2 = wasm_f32x4_mul(glmm_splat_x(r2), l);
+
+  l  = glmm_load(m1[1]);
+  v0 = glmm_fmadd(glmm_splat_y(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_y(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_y(r2), l, v2);
+
+  l  = glmm_load(m1[2]);
+  v0 = glmm_fmadd(glmm_splat_z(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_z(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_z(r2), l, v2);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], glmm_load(m1[3]));
+}
+
+CGLM_INLINE
+void
+glm_inv_tr_wasm(mat4 mat) {
+  glmm_128 r0, r1, r2, r3, x0, x1, x2, x3, x4, x5;
+
+  r0 = glmm_load(mat[0]);
+  r1 = glmm_load(mat[1]);
+  r2 = glmm_load(mat[2]);
+  r3 = glmm_load(mat[3]);
+  x1 = wasm_f32x4_const(0.0f, 0.0f, 0.0f, 1.0f);
+
+  /* _MM_TRANSPOSE4_PS(r0, r1, r2, x1); */
+  x2 = wasm_i32x4_shuffle(r0, r1, 0, 4, 1, 5);
+  x3 = wasm_i32x4_shuffle(r0, r1, 2, 6, 3, 7);
+  x4 = wasm_i32x4_shuffle(r2, x1, 0, 4, 1, 5);
+  x5 = wasm_i32x4_shuffle(r2, x1, 2, 6, 3, 7);
+  /* r0 = _mm_movelh_ps(x2, x4); */
+  r0 = wasm_i32x4_shuffle(x2, x4, 0, 1, 4, 5);
+  /* r1 = _mm_movehl_ps(x4, x2); */
+  r1 = wasm_i32x4_shuffle(x4, x2, 6, 7, 2, 3);
+  /* r2 = _mm_movelh_ps(x3, x5); */
+  r2 = wasm_i32x4_shuffle(x3, x5, 0, 1, 4, 5);
+  /* x1 = _mm_movehl_ps(x5, x3); */
+  x1 = wasm_i32x4_shuffle(x5, x3, 6, 7, 2, 3);
+
+  x2 = glmm_shuff1(r3, 0, 0, 0, 0);
+  x3 = glmm_shuff1(r3, 1, 1, 1, 1);
+  x4 = glmm_shuff1(r3, 2, 2, 2, 2);
+
+  x0 = glmm_fmadd(r0, x2,
+                  glmm_fmadd(r1, x3, wasm_f32x4_mul(r2, x4)));
+  x0 = wasm_f32x4_neg(x0);
+
+  x0 = wasm_f32x4_add(x0, x1);
+
+  glmm_store(mat[0], r0);
+  glmm_store(mat[1], r1);
+  glmm_store(mat[2], r2);
+  glmm_store(mat[3], x0);
+}
+
+#endif
+#endif /* cglm_affine_mat_wasm_h */