Merge branch 'master' into fix-simd-signmask

wasm: replace usage of -0.f to 0x80000000

.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@v11
+
+    - 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

@@ -78,3 +78,5 @@ confdefs.h
 *.xcuserdatad
 .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 0.8.3 LANGUAGES C)
+project(cglm
+  VERSION 0.9.0
+  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)
@@ -36,7 +46,9 @@ else()
   add_compile_options(-Wall -Werror -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
@@ -47,7 +59,10 @@ include(GNUInstallDirs)
 
 set(CPACK_PROJECT_NAME ${PROJECT_NAME})
 set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
-include(CPack)
+
+if(NOT CPack_CMake_INCLUDED)
+  include(CPack)
+endif()
 
 # Target Start
 add_library(${PROJECT_NAME}
@@ -58,8 +73,11 @@ add_library(${PROJECT_NAME}
   src/quat.c
   src/cam.c
   src/vec2.c
+  src/ivec2.c
   src/vec3.c
+  src/ivec3.c
   src/vec4.c
+  src/ivec4.c
   src/mat2.c
   src/mat3.c
   src/mat4.c
@@ -73,18 +91,20 @@ 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)
@@ -97,6 +117,12 @@ set_target_properties(${PROJECT_NAME} PROPERTIES
                               VERSION ${PROJECT_VERSION} 
                             SOVERSION ${PROJECT_VERSION_MAJOR})
 
+if(WIN32)
+  # Because SOVERSION has no effect to file naming on Windows
+  set_target_properties(${PROJECT_NAME} PROPERTIES
+    RUNTIME_OUTPUT_NAME ${PROJECT_NAME}-${PROJECT_VERSION_MAJOR})
+endif()
+
 target_include_directories(${PROJECT_NAME}
     PUBLIC 
         $<INSTALL_INTERFACE:include>    
@@ -122,7 +148,7 @@ install(TARGETS ${PROJECT_NAME}
         EXPORT  ${PROJECT_NAME}
         LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
         ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-        RUNTIME DESTINATION ${CMAKE_INSTALL_LIBDIR})
+        RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 
 install(DIRECTORY include/${PROJECT_NAME} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
         PATTERN ".*" EXCLUDE)
@@ -141,9 +167,18 @@ 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 "${CMAKE_INSTALL_INCLUDEDIR}")
-configure_file(${CMAKE_CURRENT_LIST_DIR}/cglm.pc.in ${CMAKE_BINARY_DIR}/cglm.pc @ONLY)
+else()
+  set(includedir "\${prefix}/${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(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)

CREDITS

@@ -78,3 +78,7 @@ https://stackoverflow.com/a/57793352/2676533
 16. ARM NEON Div
 
 http://github.com/microsoft/DirectXMath
+
+17. Pick Matrix
+
+glu project -> project.c

Makefile.am

@@ -45,17 +45,22 @@ cglm_HEADERS = include/cglm/version.h \
                include/cglm/mat4.h \
                include/cglm/mat3.h \
                include/cglm/mat2.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 \
@@ -71,20 +76,22 @@ 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_rh_no.h
+                         include/cglm/clipspace/view_lh_zo.h \
+                         include/cglm/clipspace/view_rh_no.h \
+                         include/cglm/clipspace/view_rh_zo.h \
+                         include/cglm/clipspace/project_no.h \
+                         include/cglm/clipspace/project_zo.h
 
 cglm_calldir=$(includedir)/cglm/call
 cglm_call_HEADERS = include/cglm/call/mat4.h \
@@ -93,7 +100,9 @@ cglm_call_HEADERS = include/cglm/call/mat4.h \
                     include/cglm/call/vec2.h \
                     include/cglm/call/vec3.h \
                     include/cglm/call/vec4.h \
-                    include/cglm/call/affine.h \
+                    include/cglm/call/ivec2.h \
+                    include/cglm/call/ivec3.h \
+                    include/cglm/call/ivec4.h \
                     include/cglm/call/io.h \
                     include/cglm/call/cam.h \
                     include/cglm/call/quat.h \
@@ -107,8 +116,25 @@ cglm_call_HEADERS = include/cglm/call/mat4.h \
                     include/cglm/call/curve.h \
                     include/cglm/call/bezier.h \
                     include/cglm/call/ray.h \
+                    include/cglm/call/affine.h \
                     include/cglm/call/affine2d.h
 
+cglm_call_clipspacedir=$(includedir)/cglm/call/clipspace
+cglm_call_clipspace_HEADERS = include/cglm/call/clipspace/persp_lh_no.h \
+                              include/cglm/call/clipspace/persp_lh_zo.h \
+                              include/cglm/call/clipspace/persp_rh_no.h \
+                              include/cglm/call/clipspace/persp_rh_zo.h \
+                              include/cglm/call/clipspace/ortho_lh_no.h \
+                              include/cglm/call/clipspace/ortho_lh_zo.h \
+                              include/cglm/call/clipspace/ortho_rh_no.h \
+                              include/cglm/call/clipspace/ortho_rh_zo.h \
+                              include/cglm/call/clipspace/view_lh_no.h \
+                              include/cglm/call/clipspace/view_lh_zo.h \
+                              include/cglm/call/clipspace/view_rh_no.h \
+                              include/cglm/call/clipspace/view_rh_zo.h \
+                              include/cglm/call/clipspace/project_no.h \
+                              include/cglm/call/clipspace/project_zo.h
+
 cglm_simddir=$(includedir)/cglm/simd
 cglm_simd_HEADERS = include/cglm/simd/intrin.h \
                     include/cglm/simd/x86.h \
@@ -126,22 +152,25 @@ cglm_simd_avx_HEADERS = include/cglm/simd/avx/mat4.h \
                         include/cglm/simd/avx/affine.h
 
 cglm_simd_neondir=$(includedir)/cglm/simd/neon
-cglm_simd_neon_HEADERS = include/cglm/simd/neon/mat4.h \
+cglm_simd_neon_HEADERS = include/cglm/simd/neon/affine.h \
                          include/cglm/simd/neon/mat2.h \
-                         include/cglm/simd/neon/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/mat3.h \
                       include/cglm/struct/mat2.h \
+                      include/cglm/struct/affine-pre.h \
+                      include/cglm/struct/affine-post.h \
+                      include/cglm/struct/affine.h \
+                      include/cglm/struct/affine2d.h \
                       include/cglm/struct/vec2.h \
                       include/cglm/struct/vec2-ext.h \
                       include/cglm/struct/vec3.h \
                       include/cglm/struct/vec3-ext.h \
                       include/cglm/struct/vec4.h \
                       include/cglm/struct/vec4-ext.h \
-                      include/cglm/struct/affine.h \
                       include/cglm/struct/io.h \
                       include/cglm/struct/cam.h \
                       include/cglm/struct/quat.h \
@@ -152,22 +181,23 @@ 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 \
@@ -176,8 +206,11 @@ libcglm_la_SOURCES=\
     src/quat.c \
     src/cam.c \
     src/vec2.c \
+    src/ivec2.c \
     src/vec3.c \
+    src/ivec3.c \
     src/vec4.c \
+    src/ivec4.c \
     src/mat2.c \
     src/mat3.c \
     src/mat4.c \
@@ -202,17 +235,14 @@ libcglm_la_SOURCES=\
     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/view_rh_zo.c \
+    src/clipspace/project_no.c \
+    src/clipspace/project_zo.c
     
 test_tests_SOURCES=\
     test/runner.c \
     test/src/test_common.c \
     test/src/tests.c \
-    test/src/test_cam.c \
-    test/src/test_cam_lh_zo.c \
-    test/src/test_cam_rh_zo.c \
-    test/src/test_cam_lh_no.c \
-    test/src/test_cam_rh_no.c \
     test/src/test_clamp.c \
     test/src/test_euler.c \
     test/src/test_bezier.c \

README.md

@@ -1,19 +1,59 @@
 # 🎥 OpenGL Mathematics (glm) for `C`
-[![Build Status](https://travis-ci.com/recp/cglm.svg?branch=master)](https://travis-ci.com/recp/cglm)
-[![Build status](https://ci.appveyor.com/api/projects/status/av7l3gc0yhfex8y4/branch/master?svg=true)](https://ci.appveyor.com/project/recp/cglm/branch/master)
-[![Documentation Status](https://readthedocs.org/projects/cglm/badge/?version=latest)](http://cglm.readthedocs.io/en/latest/?badge=latest)
-[![Coverage Status](https://coveralls.io/repos/github/recp/cglm/badge.svg?branch=master)](https://coveralls.io/github/recp/cglm?branch=master)
-[![codecov](https://codecov.io/gh/recp/cglm/branch/master/graph/badge.svg)](https://codecov.io/gh/recp/cglm)
-[![Codacy Badge](https://api.codacy.com/project/badge/Grade/6a62b37d5f214f178ebef269dc4a6bf1)](https://www.codacy.com/app/recp/cglm?utm_source=github.com&utm_medium=referral&utm_content=recp/cglm&utm_campaign=Badge_Grade)
-[![Backers on Open Collective](https://opencollective.com/cglm/backers/badge.svg)](#backers)
-[![Sponsors on Open Collective](https://opencollective.com/cglm/sponsors/badge.svg)](#sponsors)
 
-#### Documentation
+<p align="center">
+   <img alt="" src="cglm.png" width="550" />
+</p>
+<br>
+<p align="center">
+    <a href="https://travis-ci.com/recp/cglm">
+        <img src="https://travis-ci.com/recp/cglm.svg?branch=master"
+             alt="Build Status">
+    </a>
+    <a href="https://ci.appveyor.com/project/recp/cglm/branch/master">
+        <img src="https://ci.appveyor.com/api/projects/status/av7l3gc0yhfex8y4/branch/master?svg=true"
+             alt="Windows Build Status">
+    </a>
+    <a href="http://cglm.readthedocs.io/en/latest/?badge=latest">
+        <img src="https://readthedocs.org/projects/cglm/badge/?version=latest"
+             alt="Documentation Status">
+    </a>
+    <a href="https://www.codacy.com/app/recp/cglm?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=recp/cglm&amp;utm_campaign=Badge_Grade">
+        <img src="https://api.codacy.com/project/badge/Grade/6a62b37d5f214f178ebef269dc4a6bf1"
+             alt="Codacy Badge"/>
+    </a>
+    <a href="https://coveralls.io/github/recp/cglm?branch=master">
+        <img src="https://coveralls.io/repos/github/recp/cglm/badge.svg?branch=master"
+             alt="Coverage Status"/>
+    </a>
+    <a href="https://codecov.io/gh/recp/cglm">
+        <img src="https://codecov.io/gh/recp/cglm/branch/master/graph/badge.svg"
+             alt="Coverage Status"/>
+    </a>
+    <br /><br />
+    <a href="#sponsors">
+        <img src="https://opencollective.com/cglm/sponsors/badge.svg"
+             alt="Sponsors on Open Collective"/>
+    </a>
+    <a href="#backers">
+        <img src="https://opencollective.com/cglm/backers/badge.svg"
+             alt="Backers on Open Collective"/>
+    </a>
+</p>
+
+<br>
+
+<p align="center">
+Highly optimized 2D|3D math library, also known as <b>OpenGL Mathematics (glm) for `C`</b>. <b>cglm</b> provides lot of utils to help math operations to be fast and quick to write. It is community friendly, feel free to bring any issues, bugs you faced. 
+</p>
+
+---
+
+#### 📚 Documentation
 
 Almost all functions (inline versions) and parameters are documented inside the corresponding headers. <br />
 Complete documentation: http://cglm.readthedocs.io
 
-#### Note for previous versions:
+#### 📌 Note for previous versions:
 
 - _dup (duplicate) is changed to _copy. For instance `glm_vec_dup -> glm_vec3_copy`
 - OpenGL related functions are dropped to make this lib platform/third-party independent
@@ -28,30 +68,27 @@ you have the latest version
 - **[major change]** by starting v0.7.3, inline print functions are disabled in release/production mode to eliminate print costs (see options in documentation). Print output also improved. You can disable colors if you need  (see documentation)
 - **[major change]** by starting v0.8.3, **cglm** supports alternative clipspace configuations e.g. Left Handed, Zero-to-One (_zo)... `CGLM_FORCE_DEPTH_ZERO_TO_ONE` and `CGLM_FORCE_LEFT_HANDED` is provided to control clipspace. You should be able to use **cglm** with Vulkan, DirectX and Metal now... see https://cglm.readthedocs.io/en/latest/opt.html#clipspace-option-s
 
-#### Note for C++ developers:
+#### 📌 Note for C++ developers:
 If you are not aware of the original GLM library yet, you may also want to look at:
 https://github.com/g-truc/glm
 
-#### Note for new comers (Important):
+#### 📌 Note for new comers (Important):
 - `vec4` and `mat4` variables must be aligned. (There will be unaligned versions later)
 - **in** and **[in, out]** parameters must be initialized (please). But **[out]** parameters not, initializing out param is  also redundant
 - All functions are inline if you don't want to use pre-compiled versions with glmc_ prefix, you can ignore build process. Just include headers.
 - if your debugger takes you to cglm headers then make sure you are not trying to copy vec4 to vec3 or alig issues...
 - Welcome!
 
-#### Note for experienced developers:
+#### 📌 Note for experienced developers:
 - Since I'm testing this library in my projects, sometimes bugs occurs; finding that bug[s] and making improvements would be more easy with multiple developer/contributor and their projects or knowledge. Consider to make some tests if you suspect something is wrong and any feedbacks, contributions and bug reports are always welcome.
 
-#### Allocations?
+#### 📌 Allocations?
 `cglm` doesn't alloc any memory on heap. So it doesn't provide any allocator. You should alloc memory for **out** parameters too if you pass pointer of memory location. Don't forget that **vec4** (also quat/**versor**) and **mat4** must be aligned (16-bytes), because *cglm* uses SIMD instructions to optimize most operations if available.
 
-#### Returning vector or matrix... ?
+#### 📌 Returning vector or matrix... ?
 
 **cglm** supports both *ARRAY API* and *STRUCT API*, so you can return structs if you utilize struct api (`glms_`).
 
-#### Other APIs like Vulkan, Metal, Dx?
-Currently *cglm* uses default clip space configuration (-1, 1) for camera functions (perspective, extract corners...), in the future other clip space configurations will be supported
-
 <hr/>
 
 <table>
@@ -69,7 +106,7 @@ Currently *cglm* uses default clip space configuration (-1, 1) for camera functi
   </tbody>
 </table>
 
-## Features
+## 🚀 Features
 - **scalar** and **simd** (sse, avx, neon...) optimizations
 - option to use different clipspaces e.g. Left Handed, Zero-to-One... (currrently right handed negative-one is default)
 - array api and struct api, you can use arrays or structs.
@@ -151,7 +188,7 @@ Struct functions generally take their parameters as *values* and *return* their
 
 The types used are actually unions that allow access to the same data multiple ways. One of those ways involves anonymous structures, available since C11. MSVC also supports it for earlier C versions out of the box and GCC/Clang do if you enable `-fms-extensions`. To explicitly enable these anonymous structures, `#define CGLM_USE_ANONYMOUS_STRUCT` to `1`, to disable them, to `0`. For backward compatibility, you can also `#define CGLM_NO_ANONYMOUS_STRUCT` (value is irrelevant) to disable them. If you don't specify explicitly, cglm will do a best guess based on your compiler and the C version you're using.
 
-## Build
+## 🔨 Build
 
 ### CMake (All platforms)
 ```bash
@@ -394,7 +431,7 @@ You can pass matrices the same way to other APIs e.g. Vulkan, DX...
 
 ## Notes
 
-- This library uses float types only, does not support Integers, Double... yet
+- This library does not support double type... yet
 - If headers are not working properly with your compiler, IDE please open an issue, because I'm using GCC and clang to test it maybe sometimes MSVC
 
 **TODO:**
@@ -403,7 +440,7 @@ You can pass matrices the same way to other APIs e.g. Vulkan, DX...
 - [x] Add version info
 - [ ] Unaligned operations (e.g. `glm_umat4_mul`)
 - [x] Extra documentation
-- [ ] ARM Neon Arch (In Progress)
+- [x] ARM Neon Arch
 
 
 ## Contributors

cglm.podspec

@@ -2,7 +2,7 @@ Pod::Spec.new do |s|
 
   # Description
   s.name         = "cglm"
-  s.version      = "0.8.2"
+  s.version      = "0.8.9"
   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

@@ -7,7 +7,7 @@
 #*****************************************************************************
 
 AC_PREREQ([2.69])
-AC_INIT([cglm], [0.8.3], [info@recp.me])
+AC_INIT([cglm], [0.9.0], [info@recp.me])
 AM_INIT_AUTOMAKE([-Wall -Werror foreign subdir-objects serial-tests])
 
 # Don't use the default cflags (-O2 -g), we set ours manually in Makefile.am.

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

@@ -34,15 +34,18 @@ Follow the :doc:`build` documentation for this
    box
    quat
    euler
-   mat4
-   mat3
    mat2
+   mat3
+   mat4
+   vec2
+   vec2-ext
    vec3
    vec3-ext
    vec4
    vec4-ext
-   vec2
+   ivec2
-   vec2-ext
+   ivec3
+   ivec4
    color
    plane
    project

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
@@ -140,7 +140,7 @@ Functions documentation
     | set up perspective projection matrix
 
     Parameters:
-      | *[in]*  **fovy**    field of view angle
+      | *[in]*  **fovy**    field of view angle (in radians)
       | *[in]*  **aspect**  aspect ratio ( width / height )
       | *[in]*  **nearVal** near clipping plane
       | *[in]*  **farVal**  far clipping planes

docs/source/conf.py

@@ -62,9 +62,9 @@ author = u'Recep Aslantas'
 # built documents.
 #
 # The short X.Y version.
-version = u'0.8.3'
+version = u'0.9.0'
 # The full version, including alpha/beta/rc tags.
-release = u'0.8.3'
+release = u'0.9.0'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

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
@@ -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/project.rst

@@ -21,14 +21,14 @@ Functions:
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
 
-.. c:function:: void  glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest)
+.. c:function:: void glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest)
 
     | maps the specified viewport coordinates into specified space [1]
       the matrix should contain projection matrix.
 
     if you don't have ( and don't want to have ) an inverse matrix then use
-    glm_unproject version. You may use existing inverse of matrix in somewhere
+    :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:
@@ -80,7 +80,7 @@ Functions documentation
       | *[in]*  **vp**   viewport as [x, y, width, height]
       | *[out]* **dest** unprojected coordinates
 
-.. c:function:: void  glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest)
+.. c:function:: void glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest)
 
     | map object coordinates to window coordinates
 
@@ -91,12 +91,29 @@ Functions documentation
        glm_mat4_mul(proj, view, viewProj);
        glm_mat4_mul(viewProj, model, MVP);
 
-    this could be useful for gettng a bbox which fits with view frustum and
-    object bounding boxes. In this case you crop view frustum box with objects
-    box
-
     Parameters:
       | *[in]*  **pos**      object coordinates
       | *[in]*  **m**        MVP matrix
       | *[in]*  **vp**       viewport as [x, y, width, height]
       | *[out]* **dest**     projected coordinates
+
+.. c:function:: float glm_project_z(vec3 pos, mat4 m)
+
+    | map object's z coordinate to window coordinates
+
+    this is same as :c:func:`glm_project` except this function projects only Z coordinate
+    which reduces a few calculations and parameters.
+
+    Computing MVP:
+
+    .. code-block:: c
+
+       glm_mat4_mul(proj, view, viewProj);
+       glm_mat4_mul(viewProj, model, MVP);
+
+    Parameters:
+      | *[in]*  **pos**      object coordinates
+      | *[in]*  **m**        MVP matrix
+
+    Returns:
+        projected z coordinate

docs/source/quat.rst

@@ -32,6 +32,7 @@ Functions:
 #. :c:func:`glm_quat`
 #. :c:func:`glm_quatv`
 #. :c:func:`glm_quat_copy`
+#. :c:func:`glm_quat_from_vecs`
 #. :c:func:`glm_quat_norm`
 #. :c:func:`glm_quat_normalize`
 #. :c:func:`glm_quat_normalize_to`
@@ -123,6 +124,20 @@ Functions documentation
       | *[in]*  **q**     source quaternion
       | *[out]* **dest**  destination quaternion
 
+.. c:function:: void  glm_quat_from_vecs(vec3 a, vec3 b, versor dest)
+
+    | compute unit quaternion needed to rotate a into b
+
+    References:
+      * `Finding quaternion representing the rotation from one vector to another <https://stackoverflow.com/a/11741520/183120>`_
+      * `Quaternion from two vectors <http://lolengine.net/blog/2014/02/24/quaternion-from-two-vectors-final>`_
+      * `Angle between vectors <http://www.euclideanspace.com/maths/algebra/vectors/angleBetween/minorlogic.htm>`_
+
+    Parameters:
+      | *[in]*  **a**     unit vector
+      | *[in]*  **b**     unit vector
+      | *[in]*  **dest**  unit quaternion
+
 .. c:function:: float  glm_quat_norm(versor q)
 
     | returns norm (magnitude) of quaternion

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:
 

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

@@ -474,6 +474,9 @@ Functions documentation
 
     possible orthogonal/perpendicular vector
 
+    References:
+      * `On picking an orthogonal vector (and combing coconuts) <http://lolengine.net/blog/2013/09/21/picking-orthogonal-vector-combing-coconuts>`_
+
     Parameters:
       | *[in]*  **v**     vector
       | *[out]* **dest**  orthogonal/perpendicular vector

include/cglm/affine-mat.h

@@ -30,6 +30,10 @@
 #  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 +53,9 @@
 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 +113,9 @@ 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 +164,9 @@ 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/call.h

@@ -15,6 +15,9 @@ extern "C" {
 #include "call/vec2.h"
 #include "call/vec3.h"
 #include "call/vec4.h"
+#include "call/ivec2.h"
+#include "call/ivec3.h"
+#include "call/ivec4.h"
 #include "call/mat2.h"
 #include "call/mat3.h"
 #include "call/mat4.h"

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/ortho_lh_no.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/ortho_lh_zo.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/ortho_rh_no.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/ortho_rh_zo.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/persp_lh_no.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/persp_lh_zo.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/persp_rh_no.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/persp_rh_zo.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/project_no.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_project_no_h
+#define cglmc_project_no_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_unprojecti_no(vec3 pos, mat4 invMat, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_project_no(vec3 pos, mat4 m, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_project_z_no(vec3 pos, mat4 m);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_project_no_h */

include/cglm/call/clipspace/project_zo.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglmc_project_zo_h
+#define cglmc_project_zo_h
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "../../cglm.h"
+
+CGLM_EXPORT
+void
+glmc_unprojecti_zo(vec3 pos, mat4 invMat, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+void
+glmc_project_zo(vec3 pos, mat4 m, vec4 vp, vec3 dest);
+
+CGLM_EXPORT
+float
+glmc_project_z_zo(vec3 pos, mat4 m);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* cglmc_project_zo_h */

include/cglm/call/clipspace/view_lh_no.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/view_lh_zo.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/view_rh_no.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

include/cglm/call/clipspace/view_rh_zo.h

@@ -11,7 +11,7 @@
 extern "C" {
 #endif
 
-#include "../cglm.h"
+#include "../../cglm.h"
 
 CGLM_EXPORT
 void

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/project.h

@@ -25,6 +25,14 @@ CGLM_EXPORT
 void
 glmc_project(vec3 pos, mat4 m, vec4 vp, vec3 dest);
 
+CGLM_EXPORT
+float
+glmc_project_z(vec3 pos, mat4 m);
+
+CGLM_EXPORT
+void
+glmc_pickmatrix(vec2 center, vec2 size, vec4 vp, mat4 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/call/quat.h

@@ -37,6 +37,10 @@ CGLM_EXPORT
 void
 glmc_quat_copy(versor q, versor dest);
 
+CGLM_EXPORT
+void
+glmc_quat_from_vecs(vec3 a, vec3 b, versor dest);
+
 CGLM_EXPORT
 float
 glmc_quat_norm(versor q);

include/cglm/call/vec2.h

@@ -145,10 +145,26 @@ 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);
 
+CGLM_EXPORT
+void
+glmc_vec2_complex_mul(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_complex_div(vec2 a, vec2 b, vec2 dest);
+
+CGLM_EXPORT
+void
+glmc_vec2_complex_conjugate(vec2 a, vec2 dest);
+
 #ifdef __cplusplus
 }
 #endif

include/cglm/cglm.h

@@ -12,6 +12,9 @@
 #include "vec2.h"
 #include "vec3.h"
 #include "vec4.h"
+#include "ivec2.h"
+#include "ivec3.h"
+#include "ivec4.h"
 #include "mat4.h"
 #include "mat3.h"
 #include "mat2.h"

include/cglm/clipspace/ortho_lh_no.h

@@ -30,6 +30,7 @@
 
 #include "../common.h"
 #include "../plane.h"
+#include "../mat4.h"
 
 /*!
  * @brief set up orthographic projection matrix

include/cglm/clipspace/ortho_lh_zo.h

@@ -30,6 +30,7 @@
 
 #include "../common.h"
 #include "../plane.h"
+#include "../mat4.h"
 
 /*!
  * @brief set up orthographic projection matrix with a left-hand coordinate

include/cglm/clipspace/ortho_rh_no.h

@@ -30,6 +30,7 @@
 
 #include "../common.h"
 #include "../plane.h"
+#include "../mat4.h"
 
 /*!
  * @brief set up orthographic projection matrix

include/cglm/clipspace/ortho_rh_zo.h

@@ -30,6 +30,7 @@
 
 #include "../common.h"
 #include "../plane.h"
+#include "../mat4.h"
 
 /*!
  * @brief set up orthographic projection matrix with a right-hand coordinate

include/cglm/clipspace/persp_lh_no.h

@@ -47,7 +47,6 @@
 #define cglm_persp_lh_no_h
 
 #include "../common.h"
-#include "../plane.h"
 #include "persp.h"
 
 /*!

include/cglm/clipspace/persp_lh_zo.h

@@ -47,7 +47,6 @@
 #define cglm_persp_lh_zo_h
 
 #include "../common.h"
-#include "../plane.h"
 #include "persp.h"
 
 /*!

include/cglm/clipspace/persp_rh_no.h

@@ -47,7 +47,6 @@
 #define cglm_persp_rh_no_h
 
 #include "../common.h"
-#include "../plane.h"
 #include "persp.h"
 
 /*!

include/cglm/clipspace/persp_rh_zo.h

@@ -47,7 +47,6 @@
 #define cglm_persp_rh_zo_h
 
 #include "../common.h"
-#include "../plane.h"
 #include "persp.h"
 
 /*!

include/cglm/clipspace/project_no.h

@@ -0,0 +1,109 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_project_no_h
+#define cglm_project_no_h
+
+#include "../common.h"
+#include "../vec3.h"
+#include "../vec4.h"
+#include "../mat4.h"
+
+/*!
+ * @brief maps the specified viewport coordinates into specified space [1]
+ *        the matrix should contain projection matrix.
+ *
+ * if you don't have ( and don't want to have ) an inverse matrix then use
+ * glm_unproject version. You may use existing inverse of matrix in somewhere
+ * else, this is why glm_unprojecti exists to save save inversion cost
+ *
+ * [1] space:
+ *  1- if m = invProj:     View Space
+ *  2- if m = invViewProj: World Space
+ *  3- if m = invMVP:      Object Space
+ *
+ * You probably want to map the coordinates into object space
+ * so use invMVP as m
+ *
+ * Computing viewProj:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *   glm_mat4_inv(viewProj, invMVP);
+ *
+ * @param[in]  pos      point/position in viewport coordinates
+ * @param[in]  invMat   matrix (see brief)
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     unprojected coordinates
+ */
+CGLM_INLINE
+void
+glm_unprojecti_no(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
+  vec4 v;
+
+  v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
+  v[1] = 2.0f * (pos[1] - vp[1]) / vp[3] - 1.0f;
+  v[2] = 2.0f *  pos[2]                  - 1.0f;
+  v[3] = 1.0f;
+
+  glm_mat4_mulv(invMat, v, v);
+  glm_vec4_scale(v, 1.0f / v[3], v);
+  glm_vec3(v, dest);
+}
+
+/*!
+ * @brief map object coordinates to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  pos      object coordinates
+ * @param[in]  m        MVP matrix
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     projected coordinates
+ */
+CGLM_INLINE
+void
+glm_project_no(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+  CGLM_ALIGN(16) vec4 pos4;
+
+  glm_vec4(pos, 1.0f, pos4);
+
+  glm_mat4_mulv(m, pos4, pos4);
+  glm_vec4_scale(pos4, 1.0f / pos4[3], pos4); /* pos = pos / pos.w */
+  glm_vec4_scale(pos4, 0.5f, pos4);
+  glm_vec4_adds(pos4,  0.5f, pos4);
+
+  dest[0] = pos4[0] * vp[2] + vp[0];
+  dest[1] = pos4[1] * vp[3] + vp[1];
+  dest[2] = pos4[2];
+}
+
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z_no(vec3 v, mat4 m) {
+  float z, w;
+
+  z = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2] + m[3][2];
+  w = m[0][3] * v[0] + m[1][3] * v[1] + m[2][3] * v[2] + m[3][3];
+
+  return 0.5f * (z / w) + 0.5f;
+}
+
+#endif /* cglm_project_no_h */

include/cglm/clipspace/project_zo.h

@@ -0,0 +1,111 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_project_zo_h
+#define cglm_project_zo_h
+
+#include "../common.h"
+#include "../vec3.h"
+#include "../vec4.h"
+#include "../mat4.h"
+
+/*!
+ * @brief maps the specified viewport coordinates into specified space [1]
+ *        the matrix should contain projection matrix.
+ *
+ * if you don't have ( and don't want to have ) an inverse matrix then use
+ * glm_unproject version. You may use existing inverse of matrix in somewhere
+ * else, this is why glm_unprojecti exists to save save inversion cost
+ *
+ * [1] space:
+ *  1- if m = invProj:     View Space
+ *  2- if m = invViewProj: World Space
+ *  3- if m = invMVP:      Object Space
+ *
+ * You probably want to map the coordinates into object space
+ * so use invMVP as m
+ *
+ * Computing viewProj:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *   glm_mat4_inv(viewProj, invMVP);
+ *
+ * @param[in]  pos      point/position in viewport coordinates
+ * @param[in]  invMat   matrix (see brief)
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     unprojected coordinates
+ */
+CGLM_INLINE
+void
+glm_unprojecti_zo(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
+  vec4 v;
+
+  v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
+  v[1] = 2.0f * (pos[1] - vp[1]) / vp[3] - 1.0f;
+  v[2] = pos[2];
+  v[3] = 1.0f;
+
+  glm_mat4_mulv(invMat, v, v);
+  glm_vec4_scale(v, 1.0f / v[3], v);
+  glm_vec3(v, dest);
+}
+
+/*!
+ * @brief map object coordinates to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  pos      object coordinates
+ * @param[in]  m        MVP matrix
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     projected coordinates
+ */
+CGLM_INLINE
+void
+glm_project_zo(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
+  CGLM_ALIGN(16) vec4 pos4;
+
+  glm_vec4(pos, 1.0f, pos4);
+
+  glm_mat4_mulv(m, pos4, pos4);
+  glm_vec4_scale(pos4, 1.0f / pos4[3], pos4); /* pos = pos / pos.w */
+
+  dest[2] = pos4[2];
+  
+  glm_vec4_scale(pos4, 0.5f, pos4);
+  glm_vec4_adds(pos4,  0.5f, pos4);
+
+  dest[0] = pos4[0] * vp[2] + vp[0];
+  dest[1] = pos4[1] * vp[3] + vp[1];
+}
+
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z_zo(vec3 v, mat4 m) {
+  float z, w;
+
+  z = m[0][2] * v[0] + m[1][2] * v[1] + m[2][2] * v[2] + m[3][2];
+  w = m[0][3] * v[0] + m[1][3] * v[1] + m[2][3] * v[2] + m[3][3];
+
+  return z / w;
+}
+
+#endif /* cglm_project_zo_h */

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/clipspace/view_lh_no.h

@@ -15,6 +15,7 @@
 #ifndef cglm_view_lh_no_h
 #define cglm_view_lh_no_h
 
+#include "../common.h"
 #include "view_lh.h"
 
 /*!

include/cglm/clipspace/view_lh_zo.h

@@ -15,6 +15,7 @@
 #ifndef cglm_view_lh_zo_h
 #define cglm_view_lh_zo_h
 
+#include "../common.h"
 #include "view_lh.h"
 
 /*!

include/cglm/clipspace/view_rh_no.h

@@ -15,6 +15,7 @@
 #ifndef cglm_view_rh_no_h
 #define cglm_view_rh_no_h
 
+#include "../common.h"
 #include "view_rh.h"
 
 /*!

include/cglm/clipspace/view_rh_zo.h

@@ -15,6 +15,7 @@
 #ifndef cglm_view_rh_zo_h
 #define cglm_view_rh_zo_h
 
+#include "../common.h"
 #include "view_rh.h"
 
 /*!

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-6
+#    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

@@ -39,6 +39,7 @@
    || defined(CGLM_NO_PRINTS_NOOP)
 
 #include "common.h"
+#include "util.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -48,7 +49,7 @@
 #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
@@ -59,6 +60,35 @@
 #  define CGLM_PRINT_COLOR_RESET  "\033[0m"
 #endif
 
+/*!
+ * @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) {
+#if defined(CGLM_SIMD_WASM)
+  fprintf(ostream, CGLM_PRINT_COLOR "\ncglm arch: wasm SIMD128"
+    "\n\n" CGLM_PRINT_COLOR_RESET);
+#elif defined(CGLM_SIMD_x86)
+  fprintf(ostream, CGLM_PRINT_COLOR "\ncglm arch: x86 SSE*" 
+#ifdef __AVX__
+    " AVX"
+#endif
+    "\n\n" CGLM_PRINT_COLOR_RESET);
+#elif defined(CGLM_SIMD_ARM) 
+  fprintf(ostream, CGLM_PRINT_COLOR "\ncglm arch: arm"
+#ifndef __ARM_NEON_FP
+    " NEON_FP"
+#endif
+#ifdef CGLM_ARM64
+    " ARM64"
+#endif
+    "\n\n" CGLM_PRINT_COLOR_RESET);
+#endif
+}
+
 CGLM_INLINE
 void
 glm_mat4_print(mat4              matrix,
@@ -76,9 +106,9 @@ 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 +118,9 @@ 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 +149,9 @@ 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 +161,9 @@ 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 +191,9 @@ 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 +203,9 @@ 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 +228,9 @@ 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 +250,9 @@ 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 +290,9 @@ 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 +312,9 @@ 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 +339,9 @@ 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");

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

@@ -44,6 +44,10 @@
 #  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 +136,9 @@ 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 +166,9 @@ 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 +230,10 @@ 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)));

include/cglm/mat3.h

@@ -42,6 +42,10 @@
 #  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 +152,9 @@ 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],

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) ;
@@ -64,6 +64,10 @@
 #  include "simd/neon/mat4.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/mat4.h"
+#endif
+
 #ifdef DEBUG
 # include <assert.h>
 #endif
@@ -121,7 +125,12 @@ 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 +196,14 @@ 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 +313,9 @@ 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 +395,9 @@ 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 +517,9 @@ 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 +543,9 @@ 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 +584,9 @@ 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 +607,9 @@ 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 +707,9 @@ 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);

include/cglm/project.h

@@ -13,6 +13,17 @@
 #include "vec4.h"
 #include "mat4.h"
 
+#ifndef CGLM_CLIPSPACE_INCLUDE_ALL
+#  if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+#    include "clipspace/project_zo.h"
+#  elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+#    include "clipspace/project_no.h"
+#  endif
+#else
+#  include "clipspace/project_zo.h"
+#  include "clipspace/project_no.h"
+#endif
+
 /*!
  * @brief maps the specified viewport coordinates into specified space [1]
  *        the matrix should contain projection matrix.
@@ -42,16 +53,11 @@
 CGLM_INLINE
 void
 glm_unprojecti(vec3 pos, mat4 invMat, vec4 vp, vec3 dest) {
-  vec4 v;
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
-
+  glm_unprojecti_zo(pos, invMat, vp, dest);
-  v[0] = 2.0f * (pos[0] - vp[0]) / vp[2] - 1.0f;
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
-  v[1] = 2.0f * (pos[1] - vp[1]) / vp[3] - 1.0f;
+  glm_unprojecti_no(pos, invMat, vp, dest);
-  v[2] = 2.0f *  pos[2]                  - 1.0f;
+#endif
-  v[3] = 1.0f;
-
-  glm_mat4_mulv(invMat, v, v);
-  glm_vec4_scale(v, 1.0f / v[3], v);
-  glm_vec3(v, dest);
 }
 
 /*!
@@ -101,18 +107,66 @@ glm_unproject(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
 CGLM_INLINE
 void
 glm_project(vec3 pos, mat4 m, vec4 vp, vec3 dest) {
-  CGLM_ALIGN(16) vec4 pos4, vone = GLM_VEC4_ONE_INIT;
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+  glm_project_zo(pos, m, vp, dest);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+  glm_project_no(pos, m, vp, dest);
+#endif
+}
 
-  glm_vec4(pos, 1.0f, pos4);
+/*!
+ * @brief map object's z coordinate to window coordinates
+ *
+ * Computing MVP:
+ *   glm_mat4_mul(proj, view, viewProj);
+ *   glm_mat4_mul(viewProj, model, MVP);
+ *
+ * @param[in]  v  object coordinates
+ * @param[in]  m  MVP matrix
+ *
+ * @returns projected z coordinate
+ */
+CGLM_INLINE
+float
+glm_project_z(vec3 v, mat4 m) {
+#if CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_ZO_BIT
+  return glm_project_z_zo(v, m);
+#elif CGLM_CONFIG_CLIP_CONTROL & CGLM_CLIP_CONTROL_NO_BIT
+  return glm_project_z_no(v, m);
+#endif
+}
 
-  glm_mat4_mulv(m, pos4, pos4);
+/*!
-  glm_vec4_scale(pos4, 1.0f / pos4[3], pos4); /* pos = pos / pos.w */
+ * @brief define a picking region
-  glm_vec4_add(pos4, vone, pos4);
+ *
-  glm_vec4_scale(pos4, 0.5f, pos4);
+ * @param[in]  center   center [x, y] of a picking region in window coordinates
+ * @param[in]  size     size [width, height] of the picking region in window coordinates
+ * @param[in]  vp       viewport as [x, y, width, height]
+ * @param[out] dest     projected coordinates
+ */
+CGLM_INLINE
+void
+glm_pickmatrix(vec2 center, vec2 size, vec4 vp, mat4 dest) {
+  mat4 res;
+  vec3 v;
 
-  dest[0] = pos4[0] * vp[2] + vp[0];
+  if (size[0] <= 0.0f || size[1] <= 0.0f)
-  dest[1] = pos4[1] * vp[3] + vp[1];
+    return;
-  dest[2] = pos4[2];
+  
+  /* Translate and scale the picked region to the entire window */
+  v[0] = (vp[2] - 2.0f * (center[0] - vp[0])) / size[0];
+  v[1] = (vp[3] - 2.0f * (center[1] - vp[1])) / size[1];
+  v[2] = 0.0f;
+
+  glm_translate_make(res, v);
+  
+  v[0] = vp[2] / size[0];
+  v[1] = vp[3] / size[1];
+  v[2] = 1.0f;
+
+  glm_scale(res, v);
+
+  glm_mat4_copy(res, dest);
 }
 
 #endif /* cglm_project_h */

include/cglm/quat.h

@@ -16,6 +16,7 @@
    CGLM_INLINE void glm_quat(versor q, float angle, float x, float y, float z);
    CGLM_INLINE void glm_quatv(versor q, float angle, vec3 axis);
    CGLM_INLINE void glm_quat_copy(versor q, versor dest);
+   CGLM_INLINE void glm_quat_from_vecs(vec3 a, vec3 b, versor dest);
    CGLM_INLINE float glm_quat_norm(versor q);
    CGLM_INLINE void glm_quat_normalize(versor q);
    CGLM_INLINE void glm_quat_normalize_to(versor q, versor dest);
@@ -59,6 +60,7 @@
 #include "mat4.h"
 #include "mat3.h"
 #include "affine-mat.h"
+#include "affine.h"
 
 #ifdef CGLM_SSE_FP
 #  include "simd/sse2/quat.h"
@@ -68,17 +70,11 @@
 #  include "simd/neon/quat.h"
 #endif
 
-CGLM_INLINE
+#ifdef CGLM_SIMD_WASM
-void
+#  include "simd/wasm/quat.h"
-glm_mat4_mulv(mat4 m, vec4 v, vec4 dest);
+#endif
 
-CGLM_INLINE
+CGLM_INLINE void glm_quat_normalize(versor q);
-void
-glm_mul_rot(mat4 m1, mat4 m2, mat4 dest);
-
-CGLM_INLINE
-void
-glm_translate(mat4 m, vec3 v);
 
 /*
  * IMPORTANT:
@@ -195,10 +191,41 @@ glm_quat_copy(versor q, versor dest) {
   glm_vec4_copy(q, dest);
 }
 
+/*!
+ * @brief compute quaternion rotating vector A to vector B
+ *
+ * @param[in]   a     vec3 (must have unit length)
+ * @param[in]   b     vec3 (must have unit length)
+ * @param[out]  dest  quaternion (of unit length)
+ */
+CGLM_INLINE
+void
+glm_quat_from_vecs(vec3 a, vec3 b, versor dest) {
+  CGLM_ALIGN(8) vec3 axis;
+  float cos_theta;
+  float cos_half_theta;
+
+  cos_theta = glm_vec3_dot(a, b);
+  if (cos_theta >= 1.f - GLM_FLT_EPSILON) {  /*  a ∥ b  */
+    glm_quat_identity(dest);
+    return;
+  }
+  if (cos_theta < -1.f + GLM_FLT_EPSILON) {  /*  angle(a, b) = π  */
+    glm_vec3_ortho(a, axis);
+    cos_half_theta = 0.f;                    /*  cos π/2 */
+  } else {
+    glm_vec3_cross(a, b, axis);
+    cos_half_theta = 1.0f + cos_theta;       /*  cos 0 + cos θ  */
+  }
+
+  glm_quat_init(dest, axis[0], axis[1], axis[2], cos_half_theta);
+  glm_quat_normalize(dest);
+}
+
 /*!
  * @brief returns norm (magnitude) of quaternion
  *
- * @param[out]  q  quaternion
+ * @param[in]  q  quaternion
  */
 CGLM_INLINE
 float
@@ -215,7 +242,22 @@ 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;
 
@@ -415,7 +457,9 @@ 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);

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
@@ -34,7 +34,7 @@
 #endif
 
 #if defined(__SSE3__)
-#  include <x86intrin.h>
+#  include <pmmintrin.h>
 #  ifndef CGLM_SIMD_x86
 #    define CGLM_SIMD_x86
 #  endif
@@ -63,23 +63,56 @@
 #endif
 
 /* ARM Neon */
-#if defined(__ARM_NEON)
+#if defined(_WIN32)
-#  include <arm_neon.h>
+/* TODO: non-ARM stuff already inported, will this be better option */
-#  if defined(__ARM_NEON_FP)
+/* #  include <intrin.h> */
-#    define CGLM_NEON_FP 1
+
+#  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 */

include/cglm/simd/wasm/mat2.h

@@ -0,0 +1,50 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_mat2_wasm_h
+#define cglm_mat2_wasm_h
+#if defined(__wasm__) && defined(__wasm_simd128__)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_mat2_mul_wasm(mat2 m1, mat2 m2, mat2 dest) {
+  glmm_128 x0, x1, x2, x3, x4;
+
+  x1 = glmm_load(m1[0]); /* d c b a */
+  x2 = glmm_load(m2[0]); /* h g f e */
+
+  x3 = glmm_shuff1(x2, 2, 2, 0, 0);
+  x4 = glmm_shuff1(x2, 3, 3, 1, 1);
+  /* x0 = _mm_movelh_ps(x1, x1); */
+  x0 = wasm_i32x4_shuffle(x1, x1, 0, 1, 4, 5);
+  /* x2 = _mm_movehl_ps(x1, x1); */
+  x2 = wasm_i32x4_shuffle(x1, x1, 6, 7, 2, 3);
+
+  /*
+   dest[0][0] = a * e + c * f;
+   dest[0][1] = b * e + d * f;
+   dest[1][0] = a * g + c * h;
+   dest[1][1] = b * g + d * h;
+   */
+  x0 = glmm_fmadd(x0, x3, wasm_f32x4_mul(x2, x4));
+
+  glmm_store(dest[0], x0);
+}
+
+CGLM_INLINE
+void
+glm_mat2_transp_wasm(mat2 m, mat2 dest) {
+  /* d c b a */
+  /* d b c a */
+  glmm_store(dest[0], glmm_shuff1(glmm_load(m[0]), 3, 1, 2, 0));
+}
+
+#endif
+#endif /* cglm_mat2_wasm_h */

include/cglm/simd/wasm/mat3.h

@@ -0,0 +1,85 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_mat3_wasm_h
+#define cglm_mat3_wasm_h
+#if defined(__wasm__) && defined(__wasm_simd128__)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_mat3_mul_wasm(mat3 m1, mat3 m2, mat3 dest) {
+  glmm_128 l0, l1, l2, r0, r1, r2, x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
+  
+  l0 = wasm_v128_load(m1[0]);
+  l1 = wasm_v128_load(&m1[1][1]);
+
+  r0 = wasm_v128_load(m2[0]);
+  r1 = wasm_v128_load(&m2[1][1]);
+
+  x8 = glmm_shuff1(l0, 0, 2, 1, 0);                     /* a00 a02 a01 a00 */
+  x1 = glmm_shuff1(r0, 3, 0, 0, 0);                     /* b10 b00 b00 b00 */
+  x2 = wasm_i32x4_shuffle(l0, l1, 3, 3, 4, 5);          /* a12 a11 a10 a10 */
+  x3 = wasm_i32x4_shuffle(r0, r1, 1, 3, 4, 6);          /* b20 b11 b10 b01 */
+  x0 = wasm_f32x4_mul(x8, x1);
+
+  x6 = glmm_shuff1(l0, 1, 0, 2, 1);                     /* a01 a00 a02 a01 */
+  x7 = glmm_shuff1(x3, 3, 3, 1, 1);                     /* b20 b20 b10 b10 */
+  l2 = wasm_v128_load32_zero(&m1[2][2]);
+  r2 = wasm_v128_load32_zero(&m2[2][2]);
+  x1 = wasm_f32x4_mul(x6, x7);
+  l2 = glmm_shuff1(l2, 0, 0, 1, 0);                     /* a22 a22 0.f a22 */
+  r2 = glmm_shuff1(r2, 0, 0, 1, 0);                     /* b22 b22 0.f b22 */
+
+  x4 = glmm_shuff1(x2, 0, 3, 2, 0);                     /* a10 a12 a11 a10 */
+  x5 = glmm_shuff1(x2, 2, 0, 3, 2);                     /* a11 a10 a12 a11 */
+  x6 = glmm_shuff1(x3, 2, 0, 0, 0);                     /* b11 b01 b01 b01 */
+  x2 = glmm_shuff1(r1, 3, 3, 0, 0);                     /* b21 b21 b11 b11 */
+
+  /* x8 = _mm_unpackhi_ps(x8, x4); */
+  /* x9 = _mm_unpackhi_ps(x7, x2); */
+  x8 = wasm_i32x4_shuffle(x8, x4, 2, 6, 3, 7);          /* a10 a00 a12 a02 */
+  x9 = wasm_i32x4_shuffle(x7, x2, 2, 6, 3, 7);          /* b21 b20 b21 b20 */
+
+  x0 = glmm_fmadd(x4, x6, x0);
+  x1 = glmm_fmadd(x5, x2, x1);
+
+  /* x2 = _mm_movehl_ps(l2, l1); */
+  x2 = wasm_i32x4_shuffle(l2, l1, 6, 7, 2, 3);          /* a22 a22 a21 a20 */
+  x3 = glmm_shuff1(x2, 0, 2, 1, 0);                     /* a20 a22 a21 a20 */
+  x2 = glmm_shuff1(x2, 1, 0, 2, 1);                     /* a21 a20 a22 a21 */
+  x4 = wasm_i32x4_shuffle(r0, r1, 2, 2, 5, 5);          /* b12 b12 b02 b02 */
+  
+  x5 = glmm_shuff1(x4, 3, 0, 0, 0);                     /* b12 b02 b02 b02 */
+  /* x4 = _mm_movehl_ps(r2, x4); */
+  x4 = wasm_i32x4_shuffle(r2, x4, 6, 7, 2, 3);          /* b22 b22 b12 b12 */
+  x0 = glmm_fmadd(x3, x5, x0);
+  x1 = glmm_fmadd(x2, x4, x1);
+
+  /*
+   Dot Product : dest[2][2] =  a02 * b20 +
+                               a12 * b21 +
+                               a22 * b22 +
+                               0   * 00                                    */
+  /* x2 = _mm_movelh_ps(x8, l2); */
+  /* x3 = _mm_movelh_ps(x9, r2); */
+  x2 = wasm_i32x4_shuffle(x8, l2, 0, 1, 4, 5);           /* 0.f a22 a12 a02 */
+  x3 = wasm_i32x4_shuffle(x9, r2, 0, 1, 4, 5);           /* 0.f b22 b21 b20 */
+  x2 = glmm_vdots(x2, x3);
+
+  /* _mm_storeu_ps(&dest[0][0], x0); */
+  wasm_v128_store(&dest[0][0], x0);
+  /* _mm_storeu_ps(&dest[1][1], x1); */
+  wasm_v128_store(&dest[1][1], x1);
+  /* _mm_store_ss (&dest[2][2], x2); */
+  wasm_v128_store32_lane(&dest[2][2], x2, 0);
+}
+
+#endif
+#endif /* cglm_mat3_wasm_h */

include/cglm/simd/wasm/mat4.h

@@ -0,0 +1,454 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_mat_wasm_h
+#define cglm_mat_wasm_h
+#if defined(__wasm__) && defined(__wasm_simd128__)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+#define glm_mat4_inv_precise_wasm(mat, dest) glm_mat4_inv_wasm(mat, dest)
+
+CGLM_INLINE
+void
+glm_mat4_scale_wasm(mat4 m, float s) {
+  glmm_128 x0;
+  x0 = wasm_f32x4_splat(s);
+
+  glmm_store(m[0], wasm_f32x4_mul(glmm_load(m[0]), x0));
+  glmm_store(m[1], wasm_f32x4_mul(glmm_load(m[1]), x0));
+  glmm_store(m[2], wasm_f32x4_mul(glmm_load(m[2]), x0));
+  glmm_store(m[3], wasm_f32x4_mul(glmm_load(m[3]), x0));
+}
+
+CGLM_INLINE
+void
+glm_mat4_transp_wasm(mat4 m, mat4 dest) {
+  glmm_128 r0, r1, r2, r3, tmp0, tmp1, tmp2, tmp3;
+
+  r0 = glmm_load(m[0]);
+  r1 = glmm_load(m[1]);
+  r2 = glmm_load(m[2]);
+  r3 = glmm_load(m[3]);
+
+  /* _MM_TRANSPOSE4_PS(r0, r1, r2, r3); */
+  tmp0 = wasm_i32x4_shuffle(r0, r1, 0, 4, 1, 5);
+  tmp1 = wasm_i32x4_shuffle(r0, r1, 2, 6, 3, 7);
+  tmp2 = wasm_i32x4_shuffle(r2, r3, 0, 4, 1, 5);
+  tmp3 = wasm_i32x4_shuffle(r2, r3, 2, 6, 3, 7);
+  /* r0 = _mm_movelh_ps(tmp0, tmp2); */
+  r0 = wasm_i32x4_shuffle(tmp0, tmp2, 0, 1, 4, 5);
+  /* r1 = _mm_movehl_ps(tmp2, tmp0); */
+  r1 = wasm_i32x4_shuffle(tmp2, tmp0, 6, 7, 2, 3);
+  /* r2 = _mm_movelh_ps(tmp1, tmp3); */
+  r2 = wasm_i32x4_shuffle(tmp1, tmp3, 0, 1, 4, 5);
+  /* r3 = _mm_movehl_ps(tmp3, tmp1); */
+  r3 = wasm_i32x4_shuffle(tmp3, tmp1, 6, 7, 2, 3);
+
+  glmm_store(dest[0], r0);
+  glmm_store(dest[1], r1);
+  glmm_store(dest[2], r2);
+  glmm_store(dest[3], r3);
+}
+
+CGLM_INLINE
+void
+glm_mat4_mul_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]);
+  v0 = glmm_fmadd(glmm_splat_w(r0), l, v0);
+  v1 = glmm_fmadd(glmm_splat_w(r1), l, v1);
+  v2 = glmm_fmadd(glmm_splat_w(r2), l, v2);
+  v3 = glmm_fmadd(glmm_splat_w(r3), l, v3);
+
+  glmm_store(dest[0], v0);
+  glmm_store(dest[1], v1);
+  glmm_store(dest[2], v2);
+  glmm_store(dest[3], v3);
+}
+
+CGLM_INLINE
+void
+glm_mat4_mulv_wasm(mat4 m, vec4 v, vec4 dest) {
+  glmm_128 x0, x1, m0, m1, m2, m3, v0, v1, v2, v3;
+
+  m0 = glmm_load(m[0]);
+  m1 = glmm_load(m[1]);
+  m2 = glmm_load(m[2]);
+  m3 = glmm_load(m[3]);
+
+  x0 = glmm_load(v);
+  v0 = glmm_splat_x(x0);
+  v1 = glmm_splat_y(x0);
+  v2 = glmm_splat_z(x0);
+  v3 = glmm_splat_w(x0);
+
+  x1 = wasm_f32x4_mul(m3, v3);
+  x1 = glmm_fmadd(m2, v2, x1);
+  x1 = glmm_fmadd(m1, v1, x1);
+  x1 = glmm_fmadd(m0, v0, x1);
+
+  glmm_store(dest, x1);
+}
+
+CGLM_INLINE
+float
+glm_mat4_det_wasm(mat4 mat) {
+  glmm_128 r0, r1, r2, r3, x0, x1, x2;
+
+  /* 127 <- 0, [square] det(A) = det(At) */
+  r0 = glmm_load(mat[0]); /* d c b a */
+  r1 = glmm_load(mat[1]); /* h g f e */
+  r2 = glmm_load(mat[2]); /* l k j i */
+  r3 = glmm_load(mat[3]); /* p o n m */
+
+  /*
+   t[1] = j * p - n * l;
+   t[2] = j * o - n * k;
+   t[3] = i * p - m * l;
+   t[4] = i * o - m * k;
+   */
+  x0 = glmm_fnmadd(glmm_shuff1(r3, 0, 0, 1, 1), glmm_shuff1(r2, 2, 3, 2, 3),
+                   wasm_f32x4_mul(glmm_shuff1(r2, 0, 0, 1, 1),
+                              glmm_shuff1(r3, 2, 3, 2, 3)));
+  /*
+   t[0] = k * p - o * l;
+   t[0] = k * p - o * l;
+   t[5] = i * n - m * j;
+   t[5] = i * n - m * j;
+   */
+  x1 = glmm_fnmadd(glmm_shuff1(r3, 0, 0, 2, 2), glmm_shuff1(r2, 1, 1, 3, 3),
+                   wasm_f32x4_mul(glmm_shuff1(r2, 0, 0, 2, 2),
+                              glmm_shuff1(r3, 1, 1, 3, 3)));
+
+  /*
+     a * (f * t[0] - g * t[1] + h * t[2])
+   - b * (e * t[0] - g * t[3] + h * t[4])
+   + c * (e * t[1] - f * t[3] + h * t[5])
+   - d * (e * t[2] - f * t[4] + g * t[5])
+   */
+  x2 = glmm_fnmadd(glmm_shuff1(r1, 1, 1, 2, 2), glmm_shuff1(x0, 3, 2, 2, 0),
+                   wasm_f32x4_mul(glmm_shuff1(r1, 0, 0, 0, 1),
+                              wasm_i32x4_shuffle(x1, x0, 0, 0, 4, 5)));
+  x2 = glmm_fmadd(glmm_shuff1(r1, 2, 3, 3, 3),
+                  wasm_i32x4_shuffle(x0, x1, 1, 3, 6, 6),
+                  x2);
+  /* x2 = wasm_v128_xor(x2, wasm_f32x4_const(0.f, -0.f, 0.f, -0.f)); */
+  x2 = wasm_v128_xor(x2, glmm_float32x4_SIGNMASK_PNPN);
+  
+  return glmm_hadd(wasm_f32x4_mul(x2, r0));
+}
+
+CGLM_INLINE
+void
+glm_mat4_inv_fast_wasm(mat4 mat, mat4 dest) {
+  glmm_128 r0, r1, r2, r3,
+         v0, v1, v2, v3,
+         t0, t1, t2, t3, t4, t5,
+         x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
+
+  /* x8 = wasm_f32x4_const(0.f, -0.f, 0.f, -0.f); */
+  x8 = glmm_float32x4_SIGNMASK_PNPN;
+  x9 = glmm_shuff1(x8, 2, 1, 2, 1);
+
+  /* 127 <- 0 */
+  r0 = glmm_load(mat[0]); /* d c b a */
+  r1 = glmm_load(mat[1]); /* h g f e */
+  r2 = glmm_load(mat[2]); /* l k j i */
+  r3 = glmm_load(mat[3]); /* p o n m */
+  /* x0 = _mm_movehl_ps(r3, r2); */
+  x0 = wasm_i32x4_shuffle(r3, r2, 6, 7, 2, 3);           /* p o l k */
+  /* x3 = _mm_movelh_ps(r2, r3); */
+  x3 = wasm_i32x4_shuffle(r2, r3, 0, 1, 4, 5);           /* n m j i */
+  x1 = glmm_shuff1(x0, 1, 3, 3 ,3);                      /* l p p p */
+  x2 = glmm_shuff1(x0, 0, 2, 2, 2);                      /* k o o o */
+  x4 = glmm_shuff1(x3, 1, 3, 3, 3);                      /* j n n n */
+  x7 = glmm_shuff1(x3, 0, 2, 2, 2);                      /* i m m m */
+
+  x6 = wasm_i32x4_shuffle(r2, r1, 0, 0, 4, 4);           /* e e i i */
+  x5 = wasm_i32x4_shuffle(r2, r1, 1, 1, 5, 5);           /* f f j j */
+  x3 = wasm_i32x4_shuffle(r2, r1, 2, 2, 6, 6);           /* g g k k */
+  x0 = wasm_i32x4_shuffle(r2, r1, 3, 3, 7, 7);           /* h h l l */
+  
+  t0 = wasm_f32x4_mul(x3, x1);
+  t1 = wasm_f32x4_mul(x5, x1);
+  t2 = wasm_f32x4_mul(x5, x2);
+  t3 = wasm_f32x4_mul(x6, x1);
+  t4 = wasm_f32x4_mul(x6, x2);
+  t5 = wasm_f32x4_mul(x6, x4);
+  
+  /* t1[0] = k * p - o * l;
+     t1[0] = k * p - o * l;
+     t2[0] = g * p - o * h;
+     t3[0] = g * l - k * h; */
+  t0 = glmm_fnmadd(x2, x0, t0);
+  
+  /* t1[1] = j * p - n * l;
+     t1[1] = j * p - n * l;
+     t2[1] = f * p - n * h;
+     t3[1] = f * l - j * h; */
+   t1 = glmm_fnmadd(x4, x0, t1);
+  
+  /* t1[2] = j * o - n * k
+     t1[2] = j * o - n * k;
+     t2[2] = f * o - n * g;
+     t3[2] = f * k - j * g; */
+  t2 = glmm_fnmadd(x4, x3, t2);
+  
+  /* t1[3] = i * p - m * l;
+     t1[3] = i * p - m * l;
+     t2[3] = e * p - m * h;
+     t3[3] = e * l - i * h; */
+  t3 = glmm_fnmadd(x7, x0, t3);
+  
+  /* t1[4] = i * o - m * k;
+     t1[4] = i * o - m * k;
+     t2[4] = e * o - m * g;
+     t3[4] = e * k - i * g; */
+  t4 = glmm_fnmadd(x7, x3, t4);
+  
+  /* t1[5] = i * n - m * j;
+     t1[5] = i * n - m * j;
+     t2[5] = e * n - m * f;
+     t3[5] = e * j - i * f; */
+  t5 = glmm_fnmadd(x7, x5, t5);
+  /* x4 = _mm_movelh_ps(r0, r1); */
+  x4 = wasm_i32x4_shuffle(r0, r1, 0, 1, 4, 5);           /* f e b a */
+  /* x5 = _mm_movehl_ps(r1, r0); */
+  x5 = wasm_i32x4_shuffle(r1, r0, 6, 7, 2, 3);           /* h g d c */
+  
+  x0 = glmm_shuff1(x4, 0, 0, 0, 2);                      /* a a a e */
+  x1 = glmm_shuff1(x4, 1, 1, 1, 3);                      /* b b b f */
+  x2 = glmm_shuff1(x5, 0, 0, 0, 2);                      /* c c c g */
+  x3 = glmm_shuff1(x5, 1, 1, 1, 3);                      /* d d d h */
+  
+  v2 = wasm_f32x4_mul(x0, t1);
+  v1 = wasm_f32x4_mul(x0, t0);
+  v3 = wasm_f32x4_mul(x0, t2);
+  v0 = wasm_f32x4_mul(x1, t0);
+  
+  v2 = glmm_fnmadd(x1, t3, v2);
+  v3 = glmm_fnmadd(x1, t4, v3);
+  v0 = glmm_fnmadd(x2, t1, v0);
+  v1 = glmm_fnmadd(x2, t3, v1);
+  
+  v3 = glmm_fmadd(x2, t5, v3);
+  v0 = glmm_fmadd(x3, t2, v0);
+  v2 = glmm_fmadd(x3, t5, v2);
+  v1 = glmm_fmadd(x3, t4, v1);
+
+  /*
+   dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
+   dest[0][1] =-(b * t1[0] - c * t1[1] + d * t1[2]);
+   dest[0][2] =  b * t2[0] - c * t2[1] + d * t2[2];
+   dest[0][3] =-(b * t3[0] - c * t3[1] + d * t3[2]); */
+  v0 = wasm_v128_xor(v0, x8);
+  
+  /*
+   dest[2][0] =  e * t1[1] - f * t1[3] + h * t1[5];
+   dest[2][1] =-(a * t1[1] - b * t1[3] + d * t1[5]);
+   dest[2][2] =  a * t2[1] - b * t2[3] + d * t2[5];
+   dest[2][3] =-(a * t3[1] - b * t3[3] + d * t3[5]);*/
+  v2 = wasm_v128_xor(v2, x8);
+
+  /*
+   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
+   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
+   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
+   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
+  v1 = wasm_v128_xor(v1, x9);
+
+  /*
+   dest[3][0] =-(e * t1[2] - f * t1[4] + g * t1[5]);
+   dest[3][1] =  a * t1[2] - b * t1[4] + c * t1[5];
+   dest[3][2] =-(a * t2[2] - b * t2[4] + c * t2[5]);
+   dest[3][3] =  a * t3[2] - b * t3[4] + c * t3[5]; */
+  v3 = wasm_v128_xor(v3, x9);
+
+  /* determinant */
+  x0 = wasm_i32x4_shuffle(v0, v1, 0, 0, 4, 4);
+  x1 = wasm_i32x4_shuffle(v2, v3, 0, 0, 4, 4);
+  x0 = wasm_i32x4_shuffle(x0, x1, 0, 2, 4, 6);
+
+  /* x0 = _mm_rcp_ps(glmm_vhadd(wasm_f32x4_mul(x0, r0))); */
+  x0 = wasm_f32x4_div(wasm_f32x4_const_splat(1.0f),
+                      glmm_vhadd(wasm_f32x4_mul(x0, r0)));
+
+  glmm_store(dest[0], wasm_f32x4_mul(v0, x0));
+  glmm_store(dest[1], wasm_f32x4_mul(v1, x0));
+  glmm_store(dest[2], wasm_f32x4_mul(v2, x0));
+  glmm_store(dest[3], wasm_f32x4_mul(v3, x0));
+}
+
+CGLM_INLINE
+void
+glm_mat4_inv_wasm(mat4 mat, mat4 dest) {
+  glmm_128 r0, r1, r2, r3,
+         v0, v1, v2, v3,
+         t0, t1, t2, t3, t4, t5,
+         x0, x1, x2, x3, x4, x5, x6, x7, x8, x9;
+
+  /* x8 = wasm_f32x4_const(0.f, -0.f, 0.f, -0.f); */
+  x8 = glmm_float32x4_SIGNMASK_PNPN;
+  x9 = glmm_shuff1(x8, 2, 1, 2, 1);
+
+  /* 127 <- 0 */
+  r0 = glmm_load(mat[0]); /* d c b a */
+  r1 = glmm_load(mat[1]); /* h g f e */
+  r2 = glmm_load(mat[2]); /* l k j i */
+  r3 = glmm_load(mat[3]); /* p o n m */
+  /* x0 = _mm_movehl_ps(r3, r2); */
+  x0 = wasm_i32x4_shuffle(r3, r2, 6, 7, 2, 3);           /* p o l k */
+  /* x3 = _mm_movelh_ps(r2, r3); */
+  x3 = wasm_i32x4_shuffle(r2, r3, 0, 1, 4, 5);           /* n m j i */
+  x1 = glmm_shuff1(x0, 1, 3, 3 ,3);                      /* l p p p */
+  x2 = glmm_shuff1(x0, 0, 2, 2, 2);                      /* k o o o */
+  x4 = glmm_shuff1(x3, 1, 3, 3, 3);                      /* j n n n */
+  x7 = glmm_shuff1(x3, 0, 2, 2, 2);                      /* i m m m */
+
+  x6 = wasm_i32x4_shuffle(r2, r1, 0, 0, 4, 4);           /* e e i i */
+  x5 = wasm_i32x4_shuffle(r2, r1, 1, 1, 5, 5);           /* f f j j */
+  x3 = wasm_i32x4_shuffle(r2, r1, 2, 2, 6, 6);           /* g g k k */
+  x0 = wasm_i32x4_shuffle(r2, r1, 3, 3, 7, 7);           /* h h l l */
+  
+  t0 = wasm_f32x4_mul(x3, x1);
+  t1 = wasm_f32x4_mul(x5, x1);
+  t2 = wasm_f32x4_mul(x5, x2);
+  t3 = wasm_f32x4_mul(x6, x1);
+  t4 = wasm_f32x4_mul(x6, x2);
+  t5 = wasm_f32x4_mul(x6, x4);
+  
+  /* t1[0] = k * p - o * l;
+     t1[0] = k * p - o * l;
+     t2[0] = g * p - o * h;
+     t3[0] = g * l - k * h; */
+  t0 = glmm_fnmadd(x2, x0, t0);
+  
+  /* t1[1] = j * p - n * l;
+     t1[1] = j * p - n * l;
+     t2[1] = f * p - n * h;
+     t3[1] = f * l - j * h; */
+   t1 = glmm_fnmadd(x4, x0, t1);
+  
+  /* t1[2] = j * o - n * k
+     t1[2] = j * o - n * k;
+     t2[2] = f * o - n * g;
+     t3[2] = f * k - j * g; */
+  t2 = glmm_fnmadd(x4, x3, t2);
+  
+  /* t1[3] = i * p - m * l;
+     t1[3] = i * p - m * l;
+     t2[3] = e * p - m * h;
+     t3[3] = e * l - i * h; */
+  t3 = glmm_fnmadd(x7, x0, t3);
+  
+  /* t1[4] = i * o - m * k;
+     t1[4] = i * o - m * k;
+     t2[4] = e * o - m * g;
+     t3[4] = e * k - i * g; */
+  t4 = glmm_fnmadd(x7, x3, t4);
+  
+  /* t1[5] = i * n - m * j;
+     t1[5] = i * n - m * j;
+     t2[5] = e * n - m * f;
+     t3[5] = e * j - i * f; */
+  t5 = glmm_fnmadd(x7, x5, t5);
+  /* x4 = _mm_movelh_ps(r0, r1); */
+  x4 = wasm_i32x4_shuffle(r0, r1, 0, 1, 4, 5);           /* f e b a */
+  /* x5 = _mm_movehl_ps(r1, r0); */
+  x5 = wasm_i32x4_shuffle(r1, r0, 6, 7, 2, 3);           /* h g d c */
+  
+  x0 = glmm_shuff1(x4, 0, 0, 0, 2);                      /* a a a e */
+  x1 = glmm_shuff1(x4, 1, 1, 1, 3);                      /* b b b f */
+  x2 = glmm_shuff1(x5, 0, 0, 0, 2);                      /* c c c g */
+  x3 = glmm_shuff1(x5, 1, 1, 1, 3);                      /* d d d h */
+  
+  v2 = wasm_f32x4_mul(x0, t1);
+  v1 = wasm_f32x4_mul(x0, t0);
+  v3 = wasm_f32x4_mul(x0, t2);
+  v0 = wasm_f32x4_mul(x1, t0);
+  
+  v2 = glmm_fnmadd(x1, t3, v2);
+  v3 = glmm_fnmadd(x1, t4, v3);
+  v0 = glmm_fnmadd(x2, t1, v0);
+  v1 = glmm_fnmadd(x2, t3, v1);
+  
+  v3 = glmm_fmadd(x2, t5, v3);
+  v0 = glmm_fmadd(x3, t2, v0);
+  v2 = glmm_fmadd(x3, t5, v2);
+  v1 = glmm_fmadd(x3, t4, v1);
+
+  /*
+   dest[0][0] =  f * t1[0] - g * t1[1] + h * t1[2];
+   dest[0][1] =-(b * t1[0] - c * t1[1] + d * t1[2]);
+   dest[0][2] =  b * t2[0] - c * t2[1] + d * t2[2];
+   dest[0][3] =-(b * t3[0] - c * t3[1] + d * t3[2]); */
+  v0 = wasm_v128_xor(v0, x8);
+  
+  /*
+   dest[2][0] =  e * t1[1] - f * t1[3] + h * t1[5];
+   dest[2][1] =-(a * t1[1] - b * t1[3] + d * t1[5]);
+   dest[2][2] =  a * t2[1] - b * t2[3] + d * t2[5];
+   dest[2][3] =-(a * t3[1] - b * t3[3] + d * t3[5]);*/
+  v2 = wasm_v128_xor(v2, x8);
+
+  /*
+   dest[1][0] =-(e * t1[0] - g * t1[3] + h * t1[4]);
+   dest[1][1] =  a * t1[0] - c * t1[3] + d * t1[4];
+   dest[1][2] =-(a * t2[0] - c * t2[3] + d * t2[4]);
+   dest[1][3] =  a * t3[0] - c * t3[3] + d * t3[4]; */
+  v1 = wasm_v128_xor(v1, x9);
+
+  /*
+   dest[3][0] =-(e * t1[2] - f * t1[4] + g * t1[5]);
+   dest[3][1] =  a * t1[2] - b * t1[4] + c * t1[5];
+   dest[3][2] =-(a * t2[2] - b * t2[4] + c * t2[5]);
+   dest[3][3] =  a * t3[2] - b * t3[4] + c * t3[5]; */
+  v3 = wasm_v128_xor(v3, x9);
+
+  /* determinant */
+  x0 = wasm_i32x4_shuffle(v0, v1, 0, 0, 4, 4);
+  x1 = wasm_i32x4_shuffle(v2, v3, 0, 0, 4, 4);
+  x0 = wasm_i32x4_shuffle(x0, x1, 0, 2, 4, 6);
+
+  x0 = wasm_f32x4_div(wasm_f32x4_splat(1.0f), glmm_vhadd(wasm_f32x4_mul(x0, r0)));
+
+  glmm_store(dest[0], wasm_f32x4_mul(v0, x0));
+  glmm_store(dest[1], wasm_f32x4_mul(v1, x0));
+  glmm_store(dest[2], wasm_f32x4_mul(v2, x0));
+  glmm_store(dest[3], wasm_f32x4_mul(v3, x0));
+}
+
+#endif
+#endif /* cglm_mat_wasm_h */

include/cglm/simd/wasm/quat.h

@@ -0,0 +1,55 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+#ifndef cglm_quat_wasm_h
+#define cglm_quat_wasm_h
+#if defined(__wasm__) && defined(__wasm_simd128__)
+
+#include "../../common.h"
+#include "../intrin.h"
+
+CGLM_INLINE
+void
+glm_quat_mul_wasm(versor p, versor q, versor dest) {
+  /*
+   + (a1 b2 + b1 a2 + c1 d2 − d1 c2)i
+   + (a1 c2 − b1 d2 + c1 a2 + d1 b2)j
+   + (a1 d2 + b1 c2 − c1 b2 + d1 a2)k
+     a1 a2 − b1 b2 − c1 c2 − d1 d2
+   */
+
+  glmm_128 xp, xq, x1, x2, x3, r, x, y, z;
+
+  xp = glmm_load(p); /* 3 2 1 0 */
+  xq = glmm_load(q);
+  /* x1 = wasm_f32x4_const(0.f, -0.f, 0.f, -0.f); */
+  x1 = glmm_float32x4_SIGNMASK_PNPN; /* TODO: _mm_set1_ss() + shuff ? */
+  r  = wasm_f32x4_mul(glmm_splat_w(xp), xq);
+  /* x2 = _mm_unpackhi_ps(x1, x1); */
+  x2 = wasm_i32x4_shuffle(x1, x1, 2, 6, 3, 7);
+  x3 = glmm_shuff1(x1, 3, 2, 0, 1);
+  x  = glmm_splat_x(xp);
+  y  = glmm_splat_y(xp);
+  z  = glmm_splat_z(xp);
+
+  x  = wasm_v128_xor(x, x1);
+  y  = wasm_v128_xor(y, x2);
+  z  = wasm_v128_xor(z, x3);
+  
+  x1 = glmm_shuff1(xq, 0, 1, 2, 3);
+  x2 = glmm_shuff1(xq, 1, 0, 3, 2);
+  x3 = glmm_shuff1(xq, 2, 3, 0, 1);
+  
+  r  = glmm_fmadd(x, x1, r);
+  r  = glmm_fmadd(y, x2, r);
+  r  = glmm_fmadd(z, x3, r);
+
+  glmm_store(dest, r);
+}
+
+#endif
+#endif /* cglm_quat_wasm_h */

include/cglm/simd/x86.h

@@ -54,10 +54,23 @@
 #  endif
 #endif
 
+#define GLMM_NEGZEROf 0x80000000 /*  0x80000000 ---> -0.0f  */
+
+#define GLMM__SIGNMASKf(X, Y, Z, W)                                           \
+   _mm_castsi128_ps(_mm_set_epi32(X, Y, Z, W))
+  /* _mm_set_ps(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 _mm_castsi128_ps(_mm_set1_epi32(0x80000000)) /* _mm_set1_ps(-0.0f) */
+#define glmm_float32x8_SIGNMASK_NEG _mm256_castsi256_ps(_mm256_set1_epi32(GLMM_NEGZEROf))
+
 static inline
 __m128
 glmm_abs(__m128 x) {
-  return _mm_andnot_ps(_mm_set1_ps(-0.0f), x);
+  return _mm_andnot_ps(glmm_float32x4_SIGNMASK_NEG, x);
 }
 
 static inline
@@ -256,7 +269,8 @@ glmm_fnmsub(__m128 a, __m128 b, __m128 c) {
 #ifdef __FMA__
   return _mm_fnmsub_ps(a, b, c);
 #else
-  return _mm_xor_ps(_mm_add_ps(_mm_mul_ps(a, b), c), _mm_set1_ps(-0.0f));
+  return _mm_xor_ps(_mm_add_ps(_mm_mul_ps(a, b), c),
+                    glmm_float32x4_SIGNMASK_NEG);
 #endif
 }
 
@@ -298,7 +312,7 @@ glmm256_fnmsub(__m256 a, __m256 b, __m256 c) {
   return _mm256_fmsub_ps(a, b, c);
 #else
   return _mm256_xor_ps(_mm256_sub_ps(_mm256_mul_ps(a, b), c),
-                       _mm256_set1_ps(-0.0f));
+                       glmm_float32x8_SIGNMASK_NEG);
 #endif
 }
 #endif

include/cglm/struct/affine-post.h

@@ -0,0 +1,184 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE mat4s glms_translated(mat4s m, vec3s v);
+   CGLM_INLINE mat4s glms_translated_x(mat4s m, float x);
+   CGLM_INLINE mat4s glms_translated_y(mat4s m, float y);
+   CGLM_INLINE mat4s glms_translated_z(mat4s m, float z);
+   CGLM_INLINE mat4s glms_rotated_x(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotated_y(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotated_z(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotated(mat4s m, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_rotated_at(mat4s m, vec3s pivot, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_spinned(mat4s m, float angle, vec3s axis);
+ */
+
+#ifndef cglms_affines_post_h
+#define cglms_affines_post_h
+
+#include "../common.h"
+#include "../types-struct.h"
+#include "../affine.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       v   translate vector [x, y, z]
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translated(mat4s m, vec3s v) {
+  glm_translated(m.raw, v.raw);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       x   x factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translated_x(mat4s m, float x) {
+  glm_translated_x(m.raw, x);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       y   y factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translated_y(mat4s m, float y) {
+  glm_translated_y(m.raw, y);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       z   z factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translated_z(mat4s m, float z) {
+  glm_translated_z(m.raw, z);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform matrix around X axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m       affine transfrom
+ * @param[in]   angle   angle (radians)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotated_x(mat4s m, float angle) {
+  mat4s r;
+  glm_rotated_x(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief rotate existing transform matrix around Y axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m       affine transfrom
+ * @param[in]   angle   angle (radians)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotated_y(mat4s m, float angle) {
+  mat4s r;
+  glm_rotated_y(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief rotate existing transform matrix around Z axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m       affine transfrom
+ * @param[in]   angle   angle (radians)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotated_z(mat4s m, float angle) {
+  mat4s r;
+  glm_rotated_z(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotated(mat4s m, float angle, vec3s axis) {
+  glm_rotated(m.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       pivot   rotation center
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                 affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotated_at(mat4s m, vec3s pivot, float angle, vec3s axis) {
+  glm_rotated_at(m.raw, pivot.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_spinned(mat4s m, float angle, vec3s axis) {
+  glm_spinned(m.raw, angle, axis.raw);
+  return m;
+}
+
+#endif /* cglms_affines_post_h */

include/cglm/struct/affine-pre.h

@@ -0,0 +1,184 @@
+/*
+ * Copyright (c), Recep Aslantas.
+ *
+ * MIT License (MIT), http://opensource.org/licenses/MIT
+ * Full license can be found in the LICENSE file
+ */
+
+/*
+ Functions:
+   CGLM_INLINE mat4s glms_translate(mat4s m, vec3s v);
+   CGLM_INLINE mat4s glms_translate_x(mat4s m, float x);
+   CGLM_INLINE mat4s glms_translate_y(mat4s m, float y);
+   CGLM_INLINE mat4s glms_translate_z(mat4s m, float z);
+   CGLM_INLINE mat4s glms_rotate_x(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotate_y(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotate_z(mat4s m, float angle);
+   CGLM_INLINE mat4s glms_rotate(mat4s m, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_rotate_at(mat4s m, vec3s pivot, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_spin(mat4s m, float angle, vec3s axis);
+ */
+
+#ifndef cglms_affines_pre_h
+#define cglms_affines_pre_h
+
+#include "../common.h"
+#include "../types-struct.h"
+#include "../affine.h"
+#include "vec3.h"
+#include "vec4.h"
+#include "mat4.h"
+
+/*!
+ * @brief translate existing transform matrix by v vector
+ *        and stores result in same matrix
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       v   translate vector [x, y, z]
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate(mat4s m, vec3s v) {
+  glm_translate(m.raw, v.raw);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by x factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       x   x factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_x(mat4s m, float x) {
+  glm_translate_x(m.raw, x);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by y factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       y   y factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_y(mat4s m, float y) {
+  glm_translate_y(m.raw, y);
+  return m;
+}
+
+/*!
+ * @brief translate existing transform matrix by z factor
+ *
+ * @param[in]       m   affine transfrom
+ * @param[in]       z   z factor
+ * @returns             affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_translate_z(mat4s m, float z) {
+  glm_translate_z(m.raw, z);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform matrix around X axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m       affine transfrom
+ * @param[in]   angle   angle (radians)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_x(mat4s m, float angle) {
+  mat4s r;
+  glm_rotate_x(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief rotate existing transform matrix around Y axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m       affine transfrom
+ * @param[in]   angle   angle (radians)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_y(mat4s m, float angle) {
+  mat4s r;
+  glm_rotate_y(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief rotate existing transform matrix around Z axis by angle
+ *        and store result in dest
+ *
+ * @param[in]   m       affine transfrom
+ * @param[in]   angle   angle (radians)
+ * @returns             rotated matrix
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_z(mat4s m, float angle) {
+  mat4s r;
+  glm_rotate_z(m.raw, angle, r.raw);
+  return r;
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotate(mat4s m, float angle, vec3s axis) {
+  glm_rotate(m.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform
+ *        around given axis by angle at given pivot point (rotation center)
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       pivot   rotation center
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                 affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_rotate_at(mat4s m, vec3s pivot, float angle, vec3s axis) {
+  glm_rotate_at(m.raw, pivot.raw, angle, axis.raw);
+  return m;
+}
+
+/*!
+ * @brief rotate existing transform matrix around given axis by angle around self (doesn't affected by position)
+ *
+ * @param[in]       m       affine transfrom
+ * @param[in]       angle   angle (radians)
+ * @param[in]       axis    axis
+ * @returns                affine transfrom
+ */
+CGLM_INLINE
+mat4s
+glms_spin(mat4s m, float angle, vec3s axis) {
+  glm_spin(m.raw, angle, axis.raw);
+  return m;
+}
+
+#endif /* cglms_affines_pre_h */

include/cglm/struct/affine.h

@@ -23,6 +23,7 @@
    CGLM_INLINE mat4s glms_rotate(mat4s m, float angle, vec3s axis);
    CGLM_INLINE mat4s glms_rotate_at(mat4s m, vec3s pivot, float angle, vec3s axis);
    CGLM_INLINE mat4s glms_rotate_atm(mat4s m, vec3s pivot, float angle, vec3s axis);
+   CGLM_INLINE mat4s glms_spin(mat4s m, float angle, vec3s axis);
    CGLM_INLINE vec3s glms_decompose_scalev(mat4s m);
    CGLM_INLINE bool  glms_uniscaled(mat4s m);
    CGLM_INLINE void  glms_decompose_rs(mat4s m, mat4s * r, vec3s * s);
@@ -39,63 +40,6 @@
 #include "vec4.h"
 #include "mat4.h"
 
-/*!
- * @brief translate existing transform matrix by v vector
- *        and stores result in same matrix
- *
- * @param[in]       m   affine transfrom
- * @param[in]       v   translate vector [x, y, z]
- * @returns             affine transfrom
- */
-CGLM_INLINE
-mat4s
-glms_translate(mat4s m, vec3s v) {
-  glm_translate(m.raw, v.raw);
-  return m;
-}
-
-/*!
- * @brief translate existing transform matrix by x factor
- *
- * @param[in]       m   affine transfrom
- * @param[in]       x   x factor
- * @returns             affine transfrom
- */
-CGLM_INLINE
-mat4s
-glms_translate_x(mat4s m, float x) {
-  glm_translate_x(m.raw, x);
-  return m;
-}
-
-/*!
- * @brief translate existing transform matrix by y factor
- *
- * @param[in]       m   affine transfrom
- * @param[in]       y   y factor
- * @returns             affine transfrom
- */
-CGLM_INLINE
-mat4s
-glms_translate_y(mat4s m, float y) {
-  glm_translate_y(m.raw, y);
-  return m;
-}
-
-/*!
- * @brief translate existing transform matrix by z factor
- *
- * @param[in]       m   affine transfrom
- * @param[in]       z   z factor
- * @returns             affine transfrom
- */
-CGLM_INLINE
-mat4s
-glms_translate_z(mat4s m, float z) {
-  glm_translate_z(m.raw, z);
-  return m;
-}
-
 /*!
  * @brief creates NEW translate transform matrix by v vector
  *
@@ -155,54 +99,6 @@ glms_scale_uni(mat4s m, float s) {
   return m;
 }
 
-/*!
- * @brief rotate existing transform matrix around X axis by angle
- *        and store result in dest
- *
- * @param[in]   m       affine transfrom
- * @param[in]   angle   angle (radians)
- * @returns             rotated matrix
- */
-CGLM_INLINE
-mat4s
-glms_rotate_x(mat4s m, float angle) {
-  mat4s r;
-  glm_rotate_x(m.raw, angle, r.raw);
-  return r;
-}
-
-/*!
- * @brief rotate existing transform matrix around Y axis by angle
- *        and store result in dest
- *
- * @param[in]   m       affine transfrom
- * @param[in]   angle   angle (radians)
- * @returns             rotated matrix
- */
-CGLM_INLINE
-mat4s
-glms_rotate_y(mat4s m, float angle) {
-  mat4s r;
-  glm_rotate_y(m.raw, angle, r.raw);
-  return r;
-}
-
-/*!
- * @brief rotate existing transform matrix around Z axis by angle
- *        and store result in dest
- *
- * @param[in]   m       affine transfrom
- * @param[in]   angle   angle (radians)
- * @returns             rotated matrix
- */
-CGLM_INLINE
-mat4s
-glms_rotate_z(mat4s m, float angle) {
-  mat4s r;
-  glm_rotate_z(m.raw, angle, r.raw);
-  return r;
-}
-
 /*!
  * @brief creates NEW rotation matrix by angle and axis
  *
@@ -220,38 +116,6 @@ glms_rotate_make(float angle, vec3s axis) {
   return m;
 }
 
-/*!
- * @brief rotate existing transform matrix around given axis by angle
- *
- * @param[in]       m       affine transfrom
- * @param[in]       angle   angle (radians)
- * @param[in]       axis    axis
- * @returns                 affine transfrom
- */
-CGLM_INLINE
-mat4s
-glms_rotate(mat4s m, float angle, vec3s axis) {
-  glm_rotate(m.raw, angle, axis.raw);
-  return m;
-}
-
-/*!
- * @brief rotate existing transform
- *        around given axis by angle at given pivot point (rotation center)
- *
- * @param[in]       m       affine transfrom
- * @param[in]       pivot   rotation center
- * @param[in]       angle   angle (radians)
- * @param[in]       axis    axis
- * @returns                 affine transfrom
- */
-CGLM_INLINE
-mat4s
-glms_rotate_at(mat4s m, vec3s pivot, float angle, vec3s axis) {
-  glm_rotate_at(m.raw, pivot.raw, angle, axis.raw);
-  return m;
-}
-
 /*!
  * @brief creates NEW rotation matrix by angle and axis at given point
  *
@@ -330,4 +194,7 @@ glms_decompose(mat4s m, vec4s * __restrict t, mat4s * __restrict r, vec3s * __re
   glm_decompose(m.raw, t->raw, r->raw, s->raw);
 }
 
+#include "affine-pre.h"
+#include "affine-post.h"
+
 #endif /* cglms_affines_h */