From 814930218799068cd85829f72bf2ab134954e0f5 Mon Sep 17 00:00:00 2001
From: PabloMK7 <hackyglitch2@gmail.com>
Date: Sat, 1 Mar 2025 23:24:19 +0100
Subject: [PATCH] Use NEON intrinsics in Vec4 dot operation (#598)

---
 src/common/vector_math.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/src/common/vector_math.h b/src/common/vector_math.h
index 51f33859e..ba6a2bd79 100644
--- a/src/common/vector_math.h
+++ b/src/common/vector_math.h
@@ -1,3 +1,4 @@
+// Copyright Citra Emulator Project / Azahar Emulator Project
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
@@ -30,6 +31,10 @@
 
 #pragma once
 
+#ifdef __ARM_NEON
+#include <arm_neon.h>
+#endif
+
 #include <cmath>
 #include <cstring>
 #include <type_traits>
@@ -682,6 +687,23 @@ template <typename T>
     return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
 }
 
+template <>
+[[nodiscard]] inline float Dot(const Vec4<float>& a, const Vec4<float>& b) {
+#ifdef __ARM_NEON
+    float32x4_t va = vld1q_f32(a.AsArray());
+    float32x4_t vb = vld1q_f32(b.AsArray());
+    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,
                                                                     const Vec3<T>& b) {