simd128: enable in quat

include/cglm/quat.h

@@ -70,6 +70,10 @@
 #  include "simd/neon/quat.h"
 #endif
 
+#ifdef CGLM_SIMD_WASM
+#  include "simd/wasm/quat.h"
+#endif
+
 CGLM_INLINE void glm_quat_normalize(versor q);
 
 /*
@@ -252,6 +256,20 @@ glm_quat_normalize_to(versor q, versor dest) {
   }
 
   glmm_store(dest, _mm_div_ps(x0, _mm_sqrt_ps(xdot)));
+#elif 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);
+
+  if (dot <= 0.0f) {
+    glm_quat_identity(dest);
+    return;
+  }
+
+  glmm_store(dest, wasm_f32x4_div(x0, wasm_f32x4_sqrt(xdot)));
 #else
   float dot;
 
@@ -440,6 +458,8 @@ glm_quat_mul(versor p, versor q, versor dest) {
    */
 #if defined( __SSE__ ) || defined( __SSE2__ )
   glm_quat_mul_sse2(p, q, dest);
+#elif defined(__wasm__) && defined(__wasm_simd128__)
+  glm_quat_mul_wasm(p, q, dest);
 #elif defined(CGLM_NEON_FP)
   glm_quat_mul_neon(p, q, dest);
 #else

include/cglm/simd/wasm/quat.h

@@ -14,7 +14,7 @@
 
 CGLM_INLINE
 void
-glm_quat_mul_sse2(versor p, versor q, versor dest) {
+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
@@ -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 = wasm_f32x4_make(-0.f, 0.f, -0.f, 0.f); /* TODO: _mm_set1_ss() + shuff ? */
+  x1 = _mm_set_ps(-0.f, 0.f, -0.f, 0.f); /* TODO: _mm_set1_ss() + shuff ? */
   r  = wasm_f32x4_mul(glmm_splat_w(xp), xq);
   
   x2 = _mm_unpackhi_ps(x1, x1);