diff --git a/include/cglm/quat.h b/include/cglm/quat.h
index 0ba2cf6..eac853b 100644
--- a/include/cglm/quat.h
+++ b/include/cglm/quat.h
@@ -199,7 +199,7 @@ glm_quat_normalize_to(versor q, versor dest) {
   float  dot;
 
   x0   = glmm_load(q);
-  xdot = glm_simd_dot(x0, x0);
+  xdot = glmm_dot(x0, x0);
   dot  = _mm_cvtss_f32(xdot);
 
   if (dot <= 0.0f) {
diff --git a/include/cglm/simd/intrin.h b/include/cglm/simd/intrin.h
index 8fd1526..c9ab352 100644
--- a/include/cglm/simd/intrin.h
+++ b/include/cglm/simd/intrin.h
@@ -37,7 +37,7 @@
 
 static inline
 __m128
-glm_simd_dot(__m128 a, __m128 b) {
+glmm_dot(__m128 a, __m128 b) {
   __m128 x0;
   x0 = _mm_mul_ps(a, b);
   x0 = _mm_add_ps(x0, _mm_shuffle1_ps(x0, 1, 0, 3, 2));
@@ -46,13 +46,13 @@ glm_simd_dot(__m128 a, __m128 b) {
 
 static inline
 __m128
-glm_simd_norm(__m128 a) {
-  return _mm_sqrt_ps(glm_simd_dot(a, a));
+glmm_norm(__m128 a) {
+  return _mm_sqrt_ps(glmm_dot(a, a));
 }
 
 static inline
 __m128
-glm_simd_load_v3(vec3 v) {
+glmm_load3(vec3 v) {
   __m128i xy;
   __m128  z;
 
@@ -64,7 +64,7 @@ glm_simd_load_v3(vec3 v) {
 
 static inline
 void
-glm_simd_store_v3(__m128 vx, vec3 v) {
+glmm_store3(__m128 vx, vec3 v) {
   _mm_storel_pi((__m64 *)&v[0], vx);
   _mm_store_ss(&v[2], _mm_shuffle1_ps(vx, 2, 2, 2, 2));
 }
diff --git a/include/cglm/vec4.h b/include/cglm/vec4.h
index 912932f..b98190b 100644
--- a/include/cglm/vec4.h
+++ b/include/cglm/vec4.h
@@ -215,7 +215,7 @@ glm_vec4_norm(vec4 vec) {
 #if defined( __SSE__ ) || defined( __SSE2__ )
   __m128 x0;
   x0 = glmm_load(vec);
-  return _mm_cvtss_f32(_mm_sqrt_ss(glm_simd_dot(x0, x0)));
+  return _mm_cvtss_f32(_mm_sqrt_ss(glmm_dot(x0, x0)));
 #else
   return sqrtf(glm_vec4_norm2(vec));
 #endif
@@ -571,7 +571,7 @@ glm_vec4_normalize_to(vec4 vec, vec4 dest) {
   float  dot;
 
   x0   = glmm_load(vec);
-  xdot = glm_simd_dot(x0, x0);
+  xdot = glmm_dot(x0, x0);
   dot  = _mm_cvtss_f32(xdot);
 
   if (dot == 0.0f) {