From 37a410558ee661d6fe0362b01f825bc4e68474b4 Mon Sep 17 00:00:00 2001
From: Gamer64 <76565986+Gamer64ytb@users.noreply.github.com>
Date: Fri, 1 Aug 2025 20:13:16 +0200
Subject: [PATCH] Minor updates

---
 src/common/vector_math.h | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/src/common/vector_math.h b/src/common/vector_math.h
index e16e39cbc6..829a79ce5a 100644
--- a/src/common/vector_math.h
+++ b/src/common/vector_math.h
@@ -648,24 +648,22 @@ template <typename T>
     return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
 }
 
-#ifdef __ARM_NEON__
-// NEON-accelerated overload for float Vec4 dot product
-inline float Dot(const Vec4<float>& a, const Vec4<float>& b) {
-    // Load 4 floats into NEON registers
+template <>
+[[nodiscard]] inline float Dot(const Vec4<float>& a, const Vec4<float>& b) {
+#ifdef __ARM_NEON
     float32x4_t va = vld1q_f32(&a.x);
     float32x4_t vb = vld1q_f32(&b.x);
-    // Element-wise multiply
-    float32x4_t prod = vmulq_f32(va, vb);
-
-    // Horizontal add across the vector
-    #if defined(__aarch64__)
-        return vaddvq_f32(prod);
-    #else
-        float32x2_t sum2 = vadd_f32(vget_high_f32(prod), vget_low_f32(prod));
-        return vget_lane_f32(vpadd_f32(sum2, sum2), 0);
-    #endif
-}
+    float32x4_t result = vmulq_f32(va, vb);
+#if defined(__aarch64__) // Use vaddvq_f32 in ARMv8 architectures
+    return vaddvq_f32(result);
+#else // Use manual addition for older architectures
+    float32x2_t sum2 = vadd_f32(vget_high_f32(result), vget_low_f32(result));
+    return vget_lane_f32(vpadd_f32(sum2, sum2), 0);
 #endif
+#else
+    return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
+#endif
+}
 
 template <typename T>
 [[nodiscard]] constexpr Vec3<decltype(T{} * T{} - T{} * T{})> Cross(const Vec3<T>& a,