Merge pull request #412 from recp/sse_only

separate SSE and SSE2

docs/source/conf.py

@@ -91,6 +91,7 @@ todo_include_todos = False
 # a list of builtin themes.
 #
 html_theme = 'sphinx_rtd_theme'
+pygments_style = 'monokai'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -111,8 +112,11 @@ html_theme_options = {
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-# html_static_path = ['_static']
+html_static_path = ['sphinx-static']
 
+# Add customm CSS and JS files
+html_css_files = ['theme_overrides.css']
+html_js_files = []
 
 # -- Options for HTMLHelp output ------------------------------------------
 

docs/source/mat3x4.rst

@@ -23,6 +23,17 @@ Functions:
 #. :c:func:`glm_mat3x4_transpose`
 #. :c:func:`glm_mat3x4_scale`
 
+Represented
+~~~~~~~~~~~
+
+.. csv-table:: mat3x4
+   :header: "", "column 1", "column 2", "column 3"
+
+   "row 1", "m00", "m10", "m20"
+   "row 2", "m01", "m11", "m21"
+   "row 3", "m02", "m12", "m22"
+   "row 4", "m03", "m13", "m23"
+
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -51,28 +62,74 @@ Functions documentation
       | *[in]*  **src**  pointer to an array of floats
       | *[out]* **dest** destination matrix3x4
 
-.. c:function:: void glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest)
+.. c:function:: void glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat4 dest)
 
     multiply m1 and m2 to dest
 
     .. code-block:: c
 
-       glm_mat3x4_mul(mat3x4, mat4x3, mat3);
+       glm_mat3x4_mul(mat3x4, mat4x3, mat4);
 
     Parameters:
       | *[in]*  **m1**    left matrix (mat3x4)
       | *[in]*  **m2**    right matrix (mat4x3)
-      | *[out]* **dest**  destination matrix (mat3)
+      | *[out]* **dest**  destination matrix (mat4)
 
-.. c:function:: void glm_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest)
+    .. csv-table:: mat3x4
+        :header: "", "column 1", "column 2", "column 3"
 
-    multiply mat3x4 with vec4 (column vector) and store in dest vector
+        "row 1", "a00", "a10", "a20"
+        "row 2", "a01", "a11", "a21"
+        "row 3", "a02", "a12", "a22"
+        "row 4", "a03", "a13", "a23"
+
+    .. csv-table:: mat4x3
+        :header: "", "column 1", "column 2", "column 3", "column 4"
+
+        "row 1", "b00", "b10", "b20", "b30"
+        "row 2", "b01", "b11", "b21", "b31"
+        "row 3", "b02", "b12", "b22", "b32"
+
+    .. csv-table:: mat4x4
+        :header: "", "column 1", "column 2", "column 3", "column 4"
+
+        "row 1", "a00 * b00 + a10 * b01 + a20 * b02", "a00 * b10 + a10 * b11 + a20 * b12", "a00 * b20 + a10 * b21 + a20 * b22", "a00 * b30 + a10 * b31 + a20 * b32"
+        "row 2", "a01 * b00 + a11 * b01 + a21 * b02", "a01 * b10 + a11 * b11 + a21 * b12", "a01 * b20 + a11 * b21 + a21 * b22", "a01 * b30 + a11 * b31 + a21 * b32"
+        "row 3", "a02 * b00 + a12 * b01 + a22 * b02", "a02 * b10 + a12 * b11 + a22 * b12", "a02 * b20 + a12 * b21 + a22 * b22", "a02 * b30 + a12 * b31 + a22 * b32"
+        "row 4", "a03 * b00 + a13 * b01 + a23 * b02", "a03 * b10 + a13 * b11 + a23 * b12", "a03 * b20 + a13 * b21 + a23 * b22", "a03 * b30 + a13 * b31 + a23 * b32"
+
+.. c:function:: void glm_mat3x4_mulv(mat3x4 m, vec3 v, vec4 dest)
+
+    multiply mat3x4 with vec3 (column vector) and store in dest vector
 
     Parameters:
       | *[in]*  **m**     mat3x4 (left)
-      | *[in]*  **v**     vec4 (right, column vector)
+      | *[in]*  **v**     vec3 (right, column vector)
       | *[out]* **dest**  destination (result, column vector)
 
+    .. csv-table:: mat3x4
+        :header: "", "column 1", "column 2", "column 3"
+
+        "row 1", "m00", "m10", "m20"
+        "row 2", "m01", "m11", "m21"
+        "row 3", "m02", "m12", "m22"
+        "row 4", "m03", "m13", "m23"
+
+    .. csv-table:: column vec3 (1x3)
+        :header: "", "column 1"
+
+        "row 1", "v0"
+        "row 2", "v1"
+        "row 3", "v2"
+
+    .. csv-table:: column vec4 (1x4)
+        :header: "", "column 1"
+
+        "row 1", "m00 * v0 + m10 * v1 + m20 * v2"
+        "row 2", "m01 * v0 + m11 * v1 + m21 * v2"
+        "row 3", "m02 * v0 + m12 * v1 + m22 * v2"
+        "row 4", "m03 * v0 + m13 * v1 + m23 * v2"
+
 .. c:function:: void glm_mat3x4_transpose(mat3x4 m, mat4x3 dest)
 
     transpose matrix and store in dest

docs/source/mat4x2.rst

@@ -23,6 +23,15 @@ Functions:
 #. :c:func:`glm_mat4x2_transpose`
 #. :c:func:`glm_mat4x2_scale`
 
+Represented
+~~~~~~~~~~~
+
+.. csv-table:: mat4x2
+   :header: "", "column 1", "column 2", "column 3", "column4"
+
+   "row 1", "m00", "m10", "m20", "m30"
+   "row 2", "m01", "m11", "m21", "m31"
+
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -51,28 +60,70 @@ Functions documentation
       | *[in]*  **src**  pointer to an array of floats
       | *[out]* **dest** destination matrix4x2
 
-.. c:function:: void glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest)
+.. c:function:: void glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat2 dest)
 
     multiply m1 and m2 to dest
 
     .. code-block:: c
 
-       glm_mat4x2_mul(mat4x2, mat2x4, mat4);
+       glm_mat4x2_mul(mat4x2, mat2x4, mat2);
 
     Parameters:
       | *[in]*  **m1**    left matrix (mat4x2)
       | *[in]*  **m2**    right matrix (mat2x4)
-      | *[out]* **dest**  destination matrix (mat4)
+      | *[out]* **dest**  destination matrix (mat2)
 
-.. c:function:: void glm_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest)
+    .. csv-table:: mat4x2
+        :header: "", "column 1", "column 2", "column 3", "column 4"
 
-    multiply mat4x2 with vec2 (column vector) and store in dest vector
+        "row 1", "a00", "a10", "a20", "a30"
+        "row 2", "a01", "a11", "a21", "a31"
+
+    .. csv-table:: mat2x4
+        :header: "", "column 1", "column 2"
+
+        "row 1", "b00", "b10"
+        "row 2", "b01", "b11"
+        "row 3", "b02", "b12"
+        "row 4", "b03", "b13"
+
+    .. csv-table:: mat2x2
+        :header: "", "column 1", "column 2"
+
+        "row 1", "a00 * b00 + a10 * b01 + a20 * b02 + a30 * b03", "a00 * b10 + a10 * b11 + a20 * b12 + a30 * b13"
+        "row 2", "a01 * b00 + a11 * b01 + a21 * b02 + a31 * b03", "a01 * b10 + a11 * b11 + a21 * b12 + a31 * b13"
+
+.. c:function:: void glm_mat4x2_mulv(mat4x2 m, vec4 v, vec2 dest)
+
+    multiply mat4x2 with vec4 (column vector) and store in dest vector
 
     Parameters:
       | *[in]*  **m**     mat4x2 (left)
-      | *[in]*  **v**     vec2 (right, column vector)
+      | *[in]*  **v**     vec4 (right, column vector)
       | *[out]* **dest**  destination (result, column vector)
 
+    .. csv-table:: mat4x2
+        :header: "", "column 1", "column 2", "column 3"
+
+        "row 1", "m00", "m10", "m20"
+        "row 2", "m01", "m11", "m21"
+        "row 3", "m02", "m12", "m22"
+        "row 4", "m03", "m13", "m23"
+
+    .. csv-table:: column vec4 (1x4)
+        :header: "", "column 1"
+
+        "row 1", "v0"
+        "row 2", "v1"
+        "row 3", "v2"
+        "row 4", "v3"
+
+    .. csv-table:: column vec2 (1x2)
+        :header: "", "column 1"
+
+        "row 1", "m00 * v0 + m10 * v1 + m20 * v2 + m30 * v3"
+        "row 2", "m01 * v0 + m11 * v1 + m21 * v2 + m31 * v3"
+
 .. c:function:: void glm_mat4x2_transpose(mat4x2 m, mat2x4 dest)
 
     transpose matrix and store in dest

docs/source/mat4x3.rst

@@ -23,6 +23,16 @@ Functions:
 #. :c:func:`glm_mat4x3_transpose`
 #. :c:func:`glm_mat4x3_scale`
 
+Represented
+~~~~~~~~~~~
+
+.. csv-table:: mat4x3
+   :header: "", "column 1", "column 2", "column 3", "column4"
+
+   "row 1", "m00", "m10", "m20", "m30"
+   "row 2", "m01", "m11", "m21", "m31"
+   "row 3", "m02", "m12", "m22", "m32"
+
 Functions documentation
 ~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -51,28 +61,72 @@ Functions documentation
       | *[in]*  **src**  pointer to an array of floats
       | *[out]* **dest** destination matrix4x3
 
-.. c:function:: void glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest)
+.. c:function:: void glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat3 dest)
 
     multiply m1 and m2 to dest
 
     .. code-block:: c
 
-       glm_mat4x3_mul(mat4x3, mat3x4, mat4);
+       glm_mat4x3_mul(mat4x3, mat3x4, mat3);
 
     Parameters:
       | *[in]*  **m1**    left matrix (mat4x3)
       | *[in]*  **m2**    right matrix (mat3x4)
-      | *[out]* **dest**  destination matrix (mat4)
+      | *[out]* **dest**  destination matrix (mat3)
 
-.. c:function:: void glm_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest)
+    .. csv-table:: mat4x3
+        :header: "", "column 1", "column 2", "column 3", "column 4"
 
-    multiply mat4x3 with vec3 (column vector) and store in dest vector
+        "row 1", "a00", "a10", "a20", "a30"
+        "row 2", "a01", "a11", "a21", "a31"
+        "row 3", "a02", "a12", "a22", "a32"
+
+    .. csv-table:: mat3x4
+        :header: "", "column 1", "column 2", "column 3"
+
+        "row 1", "b00", "b10", "b20"
+        "row 2", "b01", "b11", "b21"
+        "row 3", "b02", "b12", "b22"
+        "row 4", "b03", "b13", "b23"
+
+    .. csv-table:: mat3x3
+        :header: "", "column 1", "column 2", "column 3"
+
+        "row 1", "a00 * b00 + a10 * b01 + a20 * b02 + a30 * b03", "a00 * b10 + a10 * b11 + a20 * b12 + a30 * b13", "a00 * b20 + a10 * b21 + a20 * b22 + a30 * b23"
+        "row 2", "a01 * b00 + a11 * b01 + a21 * b02 + a31 * b03", "a01 * b10 + a11 * b11 + a21 * b12 + a31 * b13", "a01 * b20 + a11 * b21 + a21 * b22 + a31 * b23"
+        "row 3", "a02 * b00 + a12 * b01 + a22 * b02 + a32 * b03", "a02 * b10 + a12 * b11 + a22 * b12 + a32 * b13", "a02 * b20 + a12 * b21 + a22 * b22 + a32 * b23"
+
+.. c:function:: void glm_mat4x3_mulv(mat4x3 m, vec4 v, vec3 dest)
+
+    multiply mat4x3 with vec4 (column vector) and store in dest column vector
 
     Parameters:
       | *[in]*  **m**     mat4x3 (left)
-      | *[in]*  **v**     vec3 (right, column vector)
+      | *[in]*  **v**     vec4 (right, column vector)
       | *[out]* **dest**  destination (result, column vector)
 
+    .. csv-table:: mat4x3
+        :header: "", "column 1", "column 2", "column 3", "column 4"
+
+        "row 1", "m00", "m10", "m20", "m30"
+        "row 2", "m01", "m11", "m21", "m31"
+        "row 3", "m02", "m12", "m22", "m32"
+
+    .. csv-table:: column vec4 (1x4)
+        :header: "", "column 1"
+
+        "row 1", "v0"
+        "row 2", "v1"
+        "row 3", "v2"
+        "row 4", "v3"
+
+    .. csv-table:: column vec3 (1x3)
+        :header: "", "column 1"
+
+        "row 1", "m00 * v0 + m10 * v1 + m20 * v2 + m30 * v3"
+        "row 2", "m01 * v0 + m11 * v1 + m21 * v2 + m31 * v3"
+        "row 3", "m02 * v0 + m12 * v1 + m22 * v2 + m32 * v3"
+
 .. c:function:: void glm_mat4x3_transpose(mat4x3 m, mat3x4 dest)
 
     transpose matrix and store in dest

docs/source/sphinx-static/theme_overrides.css

@@ -0,0 +1,12 @@
+@media screen {
+  /* content column
+   *
+   * RTD theme's default is 800px as max width for the content, but we have
+   * tables with tons of columns, which need the full width of the view-port.
+   *
+   * Comment from yocto project theme_overrides.css
+   */
+
+  .wy-nav-content{ max-width: none; }
+
+}

include/cglm/call/mat3x4.h

@@ -27,11 +27,11 @@ glmc_mat3x4_make(const float * __restrict src, mat3x4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest);
+glmc_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat4 dest);
 
 CGLM_EXPORT
 void
-glmc_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest);
+glmc_mat3x4_mulv(mat3x4 m, vec3 v, vec4 dest);
 
 CGLM_EXPORT
 void

include/cglm/call/mat4x2.h

@@ -27,11 +27,11 @@ glmc_mat4x2_make(const float * __restrict src, mat4x2 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest);
+glmc_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat2 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest);
+glmc_mat4x2_mulv(mat4x2 m, vec4 v, vec2 dest);
 
 CGLM_EXPORT
 void

include/cglm/call/mat4x3.h

@@ -27,11 +27,11 @@ glmc_mat4x3_make(const float * __restrict src, mat4x3 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest);
+glmc_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat3 dest);
 
 CGLM_EXPORT
 void
-glmc_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest);
+glmc_mat4x3_mulv(mat4x3 m, vec4 v, vec3 dest);
 
 CGLM_EXPORT
 void

include/cglm/mat3x4.h

@@ -14,8 +14,8 @@
    CGLM_INLINE void glm_mat3x4_copy(mat3x4 mat, mat3x4 dest);
    CGLM_INLINE void glm_mat3x4_zero(mat3x4 mat);
    CGLM_INLINE void glm_mat3x4_make(const float * __restrict src, mat3x4 dest);
-   CGLM_INLINE void glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest);
-   CGLM_INLINE void glm_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest);
+   CGLM_INLINE void glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat4 dest);
+   CGLM_INLINE void glm_mat3x4_mulv(mat3x4 m, vec3 v, vec4 dest);
    CGLM_INLINE void glm_mat3x4_transpose(mat3x4 m, mat4x3 dest);
    CGLM_INLINE void glm_mat3x4_scale(mat3x4 m, float s);
  */
@@ -87,16 +87,16 @@ glm_mat3x4_make(const float * __restrict src, mat3x4 dest) {
  * @brief multiply m1 and m2 to dest
  *
  * @code
- * glm_mat3x4_mul(mat3x4, mat4x3, mat3);
+ * glm_mat3x4_mul(mat3x4, mat4x3, mat4);
  * @endcode
  *
  * @param[in]  m1   left matrix (mat3x4)
  * @param[in]  m2   right matrix (mat4x3)
- * @param[out] dest destination matrix (mat3)
+ * @param[out] dest destination matrix (mat4)
  */
 CGLM_INLINE
 void
-glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest) {
+glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat4 dest) {
   float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2], a03 = m1[0][3],
         a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2], a13 = m1[1][3],
         a20 = m1[2][0], a21 = m1[2][1], a22 = m1[2][2], a23 = m1[2][3],
@@ -106,21 +106,29 @@ glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest) {
         b20 = m2[2][0], b21 = m2[2][1], b22 = m2[2][2],
         b30 = m2[3][0], b31 = m2[3][1], b32 = m2[3][2];
 
-  dest[0][0] = a00 * b00 + a01 * b10 + a02 * b20 + a03 * b30;
-  dest[0][1] = a00 * b01 + a01 * b11 + a02 * b21 + a03 * b31;
-  dest[0][2] = a00 * b02 + a01 * b12 + a02 * b22 + a03 * b32;
+  dest[0][0] = a00 * b00 + a10 * b01 + a20 * b02;
+  dest[0][1] = a01 * b00 + a11 * b01 + a21 * b02;
+  dest[0][2] = a02 * b00 + a12 * b01 + a22 * b02;
+  dest[0][3] = a03 * b00 + a13 * b01 + a23 * b02;
 
-  dest[1][0] = a10 * b00 + a11 * b10 + a12 * b20 + a13 * b30;
-  dest[1][1] = a10 * b01 + a11 * b11 + a12 * b21 + a13 * b31;
-  dest[1][2] = a10 * b02 + a11 * b12 + a12 * b22 + a13 * b32;
+  dest[1][0] = a00 * b10 + a10 * b11 + a20 * b12;
+  dest[1][1] = a01 * b10 + a11 * b11 + a21 * b12;
+  dest[1][2] = a02 * b10 + a12 * b11 + a22 * b12;
+  dest[1][3] = a03 * b10 + a13 * b11 + a23 * b12;
 
-  dest[2][0] = a20 * b00 + a21 * b10 + a22 * b20 + a23 * b30;
-  dest[2][1] = a20 * b01 + a21 * b11 + a22 * b21 + a23 * b31;
-  dest[2][2] = a20 * b02 + a21 * b12 + a22 * b22 + a23 * b32;
+  dest[2][0] = a00 * b20 + a10 * b21 + a20 * b22;
+  dest[2][1] = a01 * b20 + a11 * b21 + a21 * b22;
+  dest[2][2] = a02 * b20 + a12 * b21 + a22 * b22;
+  dest[2][3] = a03 * b20 + a13 * b21 + a23 * b22;
+
+  dest[3][0] = a00 * b30 + a10 * b31 + a20 * b32;
+  dest[3][1] = a01 * b30 + a11 * b31 + a21 * b32;
+  dest[3][2] = a02 * b30 + a12 * b31 + a22 * b32;
+  dest[3][3] = a03 * b30 + a13 * b31 + a23 * b32;
 }
 
 /*!
- * @brief multiply matrix with column vector and store in dest vector
+ * @brief multiply matrix with column vector and store in dest column vector
  *
  * @param[in]  m    matrix (left)
  * @param[in]  v    vector (right, column vector)
@@ -128,12 +136,13 @@ glm_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest) {
  */
 CGLM_INLINE
 void
-glm_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest) {
-  float v0 = v[0], v1 = v[1], v2 = v[2], v3 = v[3];
+glm_mat3x4_mulv(mat3x4 m, vec3 v, vec4 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2];
 
-  dest[0] = m[0][0] * v0 + m[0][1] * v1 + m[0][2] * v2 + m[0][3] * v3;
-  dest[1] = m[1][0] * v0 + m[1][1] * v1 + m[1][2] * v2 + m[1][3] * v3;
-  dest[2] = m[2][0] * v0 + m[2][1] * v1 + m[2][2] * v2 + m[2][3] * v3;
+  dest[0] = m[0][0] * v0 + m[1][0] * v1 + m[2][0] * v2;
+  dest[1] = m[0][1] * v0 + m[1][1] * v1 + m[2][1] * v2;
+  dest[2] = m[0][2] * v0 + m[1][2] * v1 + m[2][2] * v2;
+  dest[3] = m[0][3] * v0 + m[1][3] * v1 + m[2][3] * v2;
 }
 
 /*!
@@ -162,10 +171,9 @@ glm_mat3x4_transpose(mat3x4 m, mat4x3 dest) {
 CGLM_INLINE
 void
 glm_mat3x4_scale(mat3x4 m, float s) {
-  m[0][0] *= s;  m[1][0] *= s;   m[2][0] *= s;
-  m[0][1] *= s;  m[1][1] *= s;   m[2][1] *= s;
-  m[0][2] *= s;  m[1][2] *= s;   m[2][2] *= s;
-  m[0][3] *= s;  m[1][3] *= s;   m[2][3] *= s;
+  m[0][0] *= s; m[0][1] *= s; m[0][2] *= s; m[0][3] *= s;
+  m[1][0] *= s; m[1][1] *= s; m[1][2] *= s; m[1][3] *= s;
+  m[2][0] *= s; m[2][1] *= s; m[2][2] *= s; m[2][3] *= s;
 }
 
 #endif

include/cglm/mat4x2.h

@@ -14,8 +14,8 @@
    CGLM_INLINE void glm_mat4x2_copy(mat4x2 mat, mat4x2 dest);
    CGLM_INLINE void glm_mat4x2_zero(mat4x2 mat);
    CGLM_INLINE void glm_mat4x2_make(const float * __restrict src, mat4x2 dest);
-   CGLM_INLINE void glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest);
-   CGLM_INLINE void glm_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest);
+   CGLM_INLINE void glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat2 dest);
+   CGLM_INLINE void glm_mat4x2_mulv(mat4x2 m, vec4 v, vec2 dest);
    CGLM_INLINE void glm_mat4x2_transpose(mat4x2 m, mat2x4 dest);
    CGLM_INLINE void glm_mat4x2_scale(mat4x2 m, float s);
  */
@@ -90,16 +90,16 @@ glm_mat4x2_make(const float * __restrict src, mat4x2 dest) {
  * @brief multiply m1 and m2 to dest
  *
  * @code
- * glm_mat4x2_mul(mat4x2, mat2x4, mat4);
+ * glm_mat4x2_mul(mat4x2, mat2x4, mat2);
  * @endcode
  *
  * @param[in]  m1   left matrix (mat4x2)
  * @param[in]  m2   right matrix (mat2x4)
- * @param[out] dest destination matrix (mat4)
+ * @param[out] dest destination matrix (mat2)
  */
 CGLM_INLINE
 void
-glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest) {
+glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat2 dest) {
   float a00 = m1[0][0], a01 = m1[0][1],
         a10 = m1[1][0], a11 = m1[1][1],
         a20 = m1[2][0], a21 = m1[2][1],
@@ -108,29 +108,15 @@ glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest) {
         b00 = m2[0][0], b01 = m2[0][1], b02 = m2[0][2], b03 = m2[0][3],
         b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2], b13 = m2[1][3];
 
-  dest[0][0] = a00 * b00 + a01 * b10;
-  dest[0][1] = a00 * b01 + a01 * b11;
-  dest[0][2] = a00 * b02 + a01 * b12;
-  dest[0][3] = a00 * b03 + a01 * b13;
+  dest[0][0] = a00 * b00 + a10 * b01 + a20 * b02 + a30 * b03;
+  dest[0][1] = a01 * b00 + a11 * b01 + a21 * b02 + a31 * b03;
 
-  dest[1][0] = a10 * b00 + a11 * b10;
-  dest[1][1] = a10 * b01 + a11 * b11;
-  dest[1][2] = a10 * b02 + a11 * b12;
-  dest[1][3] = a10 * b03 + a11 * b13;
-
-  dest[2][0] = a20 * b00 + a21 * b10;
-  dest[2][1] = a20 * b01 + a21 * b11;
-  dest[2][2] = a20 * b02 + a21 * b12;
-  dest[2][3] = a20 * b03 + a21 * b13;
-
-  dest[3][0] = a30 * b00 + a31 * b10;
-  dest[3][1] = a30 * b01 + a31 * b11;
-  dest[3][2] = a30 * b02 + a31 * b12;
-  dest[3][3] = a30 * b03 + a31 * b13;
+  dest[1][0] = a00 * b10 + a10 * b11 + a20 * b12 + a30 * b13;
+  dest[1][1] = a01 * b10 + a11 * b11 + a21 * b12 + a31 * b13;
 }
 
 /*!
- * @brief multiply matrix with column vector and store in dest vector
+ * @brief multiply matrix with column vector and store in dest column vector
  *
  * @param[in]  m    matrix (left)
  * @param[in]  v    vector (right, column vector)
@@ -138,13 +124,11 @@ glm_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest) {
-  float v0 = v[0], v1 = v[1];
+glm_mat4x2_mulv(mat4x2 m, vec4 v, vec2 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2], v3 = v[3];
 
-  dest[0] = m[0][0] * v0 + m[0][1] * v1;
-  dest[1] = m[1][0] * v0 + m[1][1] * v1;
-  dest[2] = m[2][0] * v0 + m[2][1] * v1;
-  dest[3] = m[3][0] * v0 + m[3][1] * v1;
+  dest[0] = m[0][0] * v0 + m[1][0] * v1 + m[2][0] * v2 + m[3][0] * v3;
+  dest[1] = m[0][1] * v0 + m[1][1] * v1 + m[2][1] * v2 + m[3][1] * v3;
 }
 
 /*!

include/cglm/mat4x3.h

@@ -14,8 +14,8 @@
    CGLM_INLINE void glm_mat4x3_copy(mat4x3 mat, mat4x3 dest);
    CGLM_INLINE void glm_mat4x3_zero(mat4x3 mat);
    CGLM_INLINE void glm_mat4x3_make(const float * __restrict src, mat4x3 dest);
-   CGLM_INLINE void glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest);
-   CGLM_INLINE void glm_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest);
+   CGLM_INLINE void glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat3 dest);
+   CGLM_INLINE void glm_mat4x3_mulv(mat4x3 m, vec4 v, vec3 dest);
    CGLM_INLINE void glm_mat4x3_transpose(mat4x3 m, mat3x4 dest);
    CGLM_INLINE void glm_mat4x3_scale(mat4x3 m, float s);
  */
@@ -99,16 +99,16 @@ glm_mat4x3_make(const float * __restrict src, mat4x3 dest) {
  * @brief multiply m1 and m2 to dest
  *
  * @code
- * glm_mat4x3_mul(mat4x3, mat3x4, mat4);
+ * glm_mat4x3_mul(mat4x3, mat3x4, mat3);
  * @endcode
  *
  * @param[in]  m1   left matrix (mat4x3)
  * @param[in]  m2   right matrix (mat3x4)
- * @param[out] dest destination matrix (mat4)
+ * @param[out] dest destination matrix (mat3)
  */
 CGLM_INLINE
 void
-glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest) {
+glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat3 dest) {
   float a00 = m1[0][0], a01 = m1[0][1], a02 = m1[0][2],
         a10 = m1[1][0], a11 = m1[1][1], a12 = m1[1][2],
         a20 = m1[2][0], a21 = m1[2][1], a22 = m1[2][2],
@@ -118,29 +118,21 @@ glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest) {
         b10 = m2[1][0], b11 = m2[1][1], b12 = m2[1][2], b13 = m2[1][3],
         b20 = m2[2][0], b21 = m2[2][1], b22 = m2[2][2], b23 = m2[2][3];
 
-  dest[0][0] = a00 * b00 + a01 * b10 + a02 * b20;
-  dest[0][1] = a00 * b01 + a01 * b11 + a02 * b21;
-  dest[0][2] = a00 * b02 + a01 * b12 + a02 * b22;
-  dest[0][3] = a00 * b03 + a01 * b13 + a02 * b23;
+  dest[0][0] = a00 * b00 + a10 * b01 + a20 * b02 + a30 * b03;
+  dest[0][1] = a01 * b00 + a11 * b01 + a21 * b02 + a31 * b03;
+  dest[0][2] = a02 * b00 + a12 * b01 + a22 * b02 + a32 * b03;
 
-  dest[1][0] = a10 * b00 + a11 * b10 + a12 * b20;
-  dest[1][1] = a10 * b01 + a11 * b11 + a12 * b21;
-  dest[1][2] = a10 * b02 + a11 * b12 + a12 * b22;
-  dest[1][3] = a10 * b03 + a11 * b13 + a12 * b23;
+  dest[1][0] = a00 * b10 + a10 * b11 + a20 * b12 + a30 * b13;
+  dest[1][1] = a01 * b10 + a11 * b11 + a21 * b12 + a31 * b13;
+  dest[1][2] = a02 * b10 + a12 * b11 + a22 * b12 + a32 * b13;
 
-  dest[2][0] = a20 * b00 + a21 * b10 + a22 * b20;
-  dest[2][1] = a20 * b01 + a21 * b11 + a22 * b21;
-  dest[2][2] = a20 * b02 + a21 * b12 + a22 * b22;
-  dest[2][3] = a20 * b03 + a21 * b13 + a22 * b23;
-
-  dest[3][0] = a30 * b00 + a31 * b10 + a32 * b20;
-  dest[3][1] = a30 * b01 + a31 * b11 + a32 * b21;
-  dest[3][2] = a30 * b02 + a31 * b12 + a32 * b22;
-  dest[3][3] = a30 * b03 + a31 * b13 + a32 * b23;
+  dest[2][0] = a00 * b20 + a10 * b21 + a20 * b22 + a30 * b23;
+  dest[2][1] = a01 * b20 + a11 * b21 + a21 * b22 + a31 * b23;
+  dest[2][2] = a02 * b20 + a12 * b21 + a22 * b22 + a32 * b23;
 }
 
 /*!
- * @brief multiply matrix with column vector and store in dest vector
+ * @brief multiply matrix with column vector and store in dest column vector
  *
  * @param[in]  m    matrix (left)
  * @param[in]  v    vector (right, column vector)
@@ -148,13 +140,12 @@ glm_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest) {
  */
 CGLM_INLINE
 void
-glm_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest) {
-  float v0 = v[0], v1 = v[1], v2 = v[2];
+glm_mat4x3_mulv(mat4x3 m, vec4 v, vec3 dest) {
+  float v0 = v[0], v1 = v[1], v2 = v[2], v3 = v[3];
 
-  dest[0] = m[0][0] * v0 + m[0][1] * v1 + m[0][2] * v2;
-  dest[1] = m[1][0] * v0 + m[1][1] * v1 + m[1][2] * v2;
-  dest[2] = m[2][0] * v0 + m[2][1] * v1 + m[2][2] * v2;
-  dest[3] = m[3][0] * v0 + m[3][1] * v1 + m[3][2] * v2;
+  dest[0] = m[0][0] * v0 + m[1][0] * v1 + m[2][0] * v2 + m[3][0] * v3;
+  dest[1] = m[0][1] * v0 + m[1][1] * v1 + m[2][1] * v2 + m[3][1] * v3;
+  dest[2] = m[0][2] * v0 + m[1][2] * v1 + m[2][2] * v2 + m[3][2] * v3;
 }
 
 /*!

include/cglm/struct/mat3x4.h

@@ -13,8 +13,8 @@
  Functions:
    CGLM_INLINE mat3x4s glms_mat3x4_zero(void);
    CGLM_INLINE mat3x4s glms_mat3x4_make(const float * __restrict src);
-   CGLM_INLINE mat3s   glms_mat3x4_mul(mat3x4s m1, mat4x3s m2);
-   CGLM_INLINE vec3s   glms_mat3x4_mulv(mat3x4s m, vec4s v);
+   CGLM_INLINE mat4s   glms_mat3x4_mul(mat3x4s m1, mat4x3s m2);
+   CGLM_INLINE vec4s   glms_mat3x4_mulv(mat3x4s m, vec3s v);
    CGLM_INLINE mat4x3s glms_mat3x4_transpose(mat3x4s m);
    CGLM_INLINE mat3x4s glms_mat3x4_scale(mat3x4s m, float s);
  */
@@ -70,27 +70,27 @@ glms_mat3x4_(make)(const float * __restrict src) {
  *
  * @param[in]  m1   left matrix (mat3x4s)
  * @param[in]  m2   right matrix (mat4x3s)
- * @returns destination matrix (mat3s)
+ * @returns destination matrix (mat4s)
  */
 CGLM_INLINE
-mat3s
+mat4s
 glms_mat3x4_(mul)(mat3x4s m1, mat4x3s m2) {
-  mat3s r;
+  mat4s r;
   glm_mat3x4_mul(m1.raw, m2.raw, r.raw);
   return r;
 }
 
 /*!
- * @brief multiply matrix with column vector and store in dest vector
+ * @brief multiply matrix with column vector and store in dest column vector
  *
  * @param[in]  m    matrix (left)
  * @param[in]  v    vector (right, column vector)
- * @param[out] dest result vector
+ * @returns destination vector (vec4s)
  */
 CGLM_INLINE
-vec3s
-glms_mat3x4_(mulv)(mat3x4s m, vec4s v) {
-  vec3s r;
+vec4s
+glms_mat3x4_(mulv)(mat3x4s m, vec3s v) {
+  vec4s r;
   glm_mat3x4_mulv(m.raw, v.raw, r.raw);
   return r;
 }

include/cglm/struct/mat4x2.h

@@ -13,8 +13,8 @@
  Functions:
    CGLM_INLINE mat4x2s glms_mat4x2_zero(void);
    CGLM_INLINE mat4x2s glms_mat4x2_make(const float * __restrict src);
-   CGLM_INLINE mat4s   glms_mat4x2_mul(mat4x2s m1, mat2x4s m2);
-   CGLM_INLINE vec4s   glms_mat4x2_mulv(mat4x2s m, vec2s v);
+   CGLM_INLINE mat2s   glms_mat4x2_mul(mat4x2s m1, mat2x4s m2);
+   CGLM_INLINE vec2s   glms_mat4x2_mulv(mat4x2s m, vec4s v);
    CGLM_INLINE mat2x4s glms_mat4x2_transpose(mat4x2s m);
    CGLM_INLINE mat4x2s glms_mat4x2_scale(mat4x2s m, float s);
  */
@@ -71,27 +71,27 @@ glms_mat4x2_(make)(const float * __restrict src) {
  *
  * @param[in]  m1   left matrix (mat4x2s)
  * @param[in]  m2   right matrix (mat2x4s)
- * @returns destination matrix (mat4s)
+ * @returns destination matrix (mat2s)
  */
 CGLM_INLINE
-mat4s
+mat2s
 glms_mat4x2_(mul)(mat4x2s m1, mat2x4s m2) {
-  mat4s r;
+  mat2s r;
   glm_mat4x2_mul(m1.raw, m2.raw, r.raw);
   return r;
 }
 
 /*!
- * @brief multiply matrix with column vector and store in dest vector
+ * @brief multiply matrix with column vector and store in dest column vector
  *
  * @param[in]  m    matrix (left)
  * @param[in]  v    vector (right, column vector)
- * @param[out] dest result vector
+ * @returns destination vector (vec2s)
  */
 CGLM_INLINE
-vec4s
-glms_mat4x2_(mulv)(mat4x2s m, vec2s v) {
-  vec4s r;
+vec2s
+glms_mat4x2_(mulv)(mat4x2s m, vec4s v) {
+  vec2s r;
   glm_mat4x2_mulv(m.raw, v.raw, r.raw);
   return r;
 }

include/cglm/struct/mat4x3.h

@@ -13,8 +13,8 @@
  Functions:
    CGLM_INLINE mat4x3s glms_mat4x3_zero(void);
    CGLM_INLINE mat4x3s glms_mat4x3_make(const float * __restrict src);
-   CGLM_INLINE mat4s   glms_mat4x3_mul(mat4x3s m1, mat3x4s m2);
-   CGLM_INLINE vec4s   glms_mat4x3_mulv(mat4x3s m, vec3s v);
+   CGLM_INLINE mat3s   glms_mat4x3_mul(mat4x3s m1, mat3x4s m2);
+   CGLM_INLINE vec3s   glms_mat4x3_mulv(mat4x3s m, vec4s v);
    CGLM_INLINE mat3x4s glms_mat4x3_transpose(mat4x3s m);
    CGLM_INLINE mat4x3s glms_mat4x3_scale(mat4x3s m, float s);
  */
@@ -70,12 +70,12 @@ glms_mat4x3_(make)(const float * __restrict src) {
  *
  * @param[in]  m1   left matrix (mat4x3s)
  * @param[in]  m2   right matrix (mat3x4s)
- * @returns destination matrix (mat4s)
+ * @returns destination matrix (mat3s)
  */
 CGLM_INLINE
-mat4s
+mat3s
 glms_mat4x3_(mul)(mat4x3s m1, mat3x4s m2) {
-  mat4s r;
+  mat3s r;
   glm_mat4x3_mul(m1.raw, m2.raw, r.raw);
   return r;
 }
@@ -85,12 +85,12 @@ glms_mat4x3_(mul)(mat4x3s m1, mat3x4s m2) {
  *
  * @param[in]  m    matrix (left)
  * @param[in]  v    vector (right, column vector)
- * @param[out] dest result vector
+ * @returns destination vector (vec3s)
  */
 CGLM_INLINE
-vec4s
-glms_mat4x3_(mulv)(mat4x3s m, vec3s v) {
-  vec4s r;
+vec3s
+glms_mat4x3_(mulv)(mat4x3s m, vec4s v) {
+  vec3s r;
   glm_mat4x3_mulv(m.raw, v.raw, r.raw);
   return r;
 }

src/mat3x4.c

@@ -28,13 +28,13 @@ glmc_mat3x4_make(const float * __restrict src, mat3x4 dest) {
 
 CGLM_EXPORT
 void
-glmc_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat3 dest) {
+glmc_mat3x4_mul(mat3x4 m1, mat4x3 m2, mat4 dest) {
   glm_mat3x4_mul(m1, m2, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat3x4_mulv(mat3x4 m, vec4 v, vec3 dest) {
+glmc_mat3x4_mulv(mat3x4 m, vec3 v, vec4 dest) {
   glm_mat3x4_mulv(m, v, dest);
 }
 

src/mat4x2.c

@@ -28,13 +28,13 @@ glmc_mat4x2_make(const float * __restrict src, mat4x2 dest) {
 
 CGLM_EXPORT
 void
-glmc_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat4 dest) {
+glmc_mat4x2_mul(mat4x2 m1, mat2x4 m2, mat2 dest) {
   glm_mat4x2_mul(m1, m2, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4x2_mulv(mat4x2 m, vec2 v, vec4 dest) {
+glmc_mat4x2_mulv(mat4x2 m, vec4 v, vec2 dest) {
   glm_mat4x2_mulv(m, v, dest);
 }
 

src/mat4x3.c

@@ -28,13 +28,13 @@ glmc_mat4x3_make(const float * __restrict src, mat4x3 dest) {
 
 CGLM_EXPORT
 void
-glmc_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat4 dest) {
+glmc_mat4x3_mul(mat4x3 m1, mat3x4 m2, mat3 dest) {
   glm_mat4x3_mul(m1, m2, dest);
 }
 
 CGLM_EXPORT
 void
-glmc_mat4x3_mulv(mat4x3 m, vec3 v, vec4 dest) {
+glmc_mat4x3_mulv(mat4x3 m, vec4 v, vec3 dest) {
   glm_mat4x3_mulv(m, v, dest);
 }
 

test/src/test_mat3x4.h

@@ -90,40 +90,40 @@ TEST_IMPL(GLM_PREFIX, mat3x4_mul) {
   mat3x4 m1 = GLM_MAT3X4_ZERO_INIT;
   mat4x3 m2 = GLM_MAT4X3_ZERO_INIT;
 
-  mat3 m3 = GLM_MAT3_ZERO_INIT;
-  mat3 m4 = GLM_MAT3_ZERO_INIT;
+  mat4 m3 = GLM_MAT4_ZERO_INIT;
+  mat4 m4 = GLM_MAT4_ZERO_INIT;
 
-  int i, j, k;
+  int c, r, k;
 
   test_rand_mat3x4(m1);
   test_rand_mat4x3(m2);
 
-  for (i = 0; i < 3; i++) {
-    for (j = 0; j < 3; j++) {
-      for (k = 0; k < 4; k++) {
-        m4[i][j] += m1[i][k] * m2[k][j];
+  for (r = 0; r < 4; r++) {
+    for (c = 0; c < 4; c++) {
+      for (k = 0; k < 3; k++) {
+        m4[c][r] += m1[k][r] * m2[c][k];
       }
     }
   }
 
   GLM(mat3x4_mul)(m1, m2, m3);
-  ASSERTIFY(test_assert_mat3_eq(m3, m4))
+  ASSERTIFY(test_assert_mat4_eq(m3, m4))
 
   TEST_SUCCESS
 }
 
 TEST_IMPL(GLM_PREFIX, mat3x4_mulv) {
   mat3x4 mat = A_MATRIX3X4;
-  vec4 v = {11.0f, 21.0f, 31.0f, 41.0f};
+  vec4 v = {11.0f, 21.0f, 31.0f};
 
   int  i;
-  vec3 dest;
+  vec4 dest;
   float res = 0.0;
 
   GLM(mat3x4_mulv)(mat, v, dest);
 
-  for (i = 0; i < 3; i++) {
-    res = mat[i][0] * v[0] + mat[i][1] * v[1] + mat[i][2] * v[2];
+  for (i = 0; i < 4; i++) {
+    res = mat[0][i] * v[0] + mat[1][i] * v[1] + mat[2][i] * v[2];
     ASSERT(test_eq(dest[i], res))
   }
 

test/src/test_mat4x2.h

@@ -87,40 +87,40 @@ TEST_IMPL(GLM_PREFIX, mat4x2_mul) {
   mat4x2 m1 = GLM_MAT4X2_ZERO_INIT;
   mat2x4 m2 = GLM_MAT2X4_ZERO_INIT;
 
-  mat4 m3 = GLM_MAT4_ZERO_INIT;
-  mat4 m4 = GLM_MAT4_ZERO_INIT;
+  mat2 m3 = GLM_MAT2_ZERO_INIT;
+  mat2 m4 = GLM_MAT2_ZERO_INIT;
 
-  int i, j, k;
+  int c, r, k;
 
   test_rand_mat4x2(m1);
   test_rand_mat2x4(m2);
 
-  for (i = 0; i < 4; i++) {
-    for (j = 0; j < 4; j++) {
-      for (k = 0; k < 2; k++) {
-        m4[i][j] += m1[i][k] * m2[k][j];
+  for (r = 0; r < 2; r++) {
+    for (c = 0; c < 2; c++) {
+      for (k = 0; k < 4; k++) {
+	m4[c][r] += m1[k][r] * m2[c][k];
       }
     }
   }
 
   GLM(mat4x2_mul)(m1, m2, m3);
-  ASSERTIFY(test_assert_mat4_eq(m3, m4))
+  ASSERTIFY(test_assert_mat2_eq(m3, m4))
 
   TEST_SUCCESS
 }
 
 TEST_IMPL(GLM_PREFIX, mat4x2_mulv) {
   mat4x2 mat = A_MATRIX4X2;
-  vec2 v = {11.0f, 21.0f};
+  vec4 v = {11.0f, 21.0f, 31.0f, 41.0f};
 
   int  i;
-  vec4 dest;
+  vec2 dest;
   float res = 0.0;
 
   GLM(mat4x2_mulv)(mat, v, dest);
 
-  for (i = 0; i < 4; i++) {
-    res = mat[i][0] * v[0] + mat[i][1] * v[1];
+  for (i = 0; i < 2; i++) {
+    res = mat[0][i] * v[0] + mat[1][i] * v[1] + mat[2][i] * v[2] + mat[3][i] * v[3];
     ASSERT(test_eq(dest[i], res))
   }
 

test/src/test_mat4x3.h

@@ -91,40 +91,40 @@ TEST_IMPL(GLM_PREFIX, mat4x3_mul) {
   mat4x3 m1 = GLM_MAT4X3_ZERO_INIT;
   mat3x4 m2 = GLM_MAT3X4_ZERO_INIT;
 
-  mat4 m3 = GLM_MAT4_ZERO_INIT;
-  mat4 m4 = GLM_MAT4_ZERO_INIT;
+  mat3 m3 = GLM_MAT3_ZERO_INIT;
+  mat3 m4 = GLM_MAT3_ZERO_INIT;
 
-  int i, j, k;
+  int c, r, k;
 
   test_rand_mat4x3(m1);
   test_rand_mat3x4(m2);
 
-  for (i = 0; i < 4; i++) {
-    for (j = 0; j < 4; j++) {
-      for (k = 0; k < 3; k++) {
-        m4[i][j] += m1[i][k] * m2[k][j];
+  for (r = 0; r < 3; r++) {
+    for (c = 0; c < 3; c++) {
+      for (k = 0; k < 4; k++) {
+        m4[c][r] += m1[k][r] * m2[c][k];
       }
     }
   }
 
   GLM(mat4x3_mul)(m1, m2, m3);
-  ASSERTIFY(test_assert_mat4_eq(m3, m4))
+  ASSERTIFY(test_assert_mat3_eq(m3, m4))
 
   TEST_SUCCESS
 }
 
 TEST_IMPL(GLM_PREFIX, mat4x3_mulv) {
   mat4x3 mat = A_MATRIX4X3;
-  vec3 v = {11.0f, 21.0f, 31.0f};
+  vec4 v = {11.0f, 21.0f, 31.0f, 41.0f};
 
   int  i;
-  vec4 dest;
+  vec3 dest;
   float res = 0.0;
 
   GLM(mat4x3_mulv)(mat, v, dest);
 
-  for (i = 0; i < 4; i++) {
-    res = mat[i][0] * v[0] + mat[i][1] * v[1] + mat[i][2] * v[2];
+  for (i = 0; i < 3; i++) {
+    res = mat[0][i] * v[0] + mat[1][i] * v[1] + mat[2][i] * v[2] + mat[3][i] * v[3];
     ASSERT(test_eq(dest[i], res))
   }