Update src/shader_recompiler/backend/glsl/emit_glsl.cpp

unrelated. merely to avoid build error.

src/common/CMakeLists.txt

@@ -89,6 +89,7 @@ add_library(
     param_package.h
     parent_of_member.h
     point.h
+    quaternion.h
     range_map.h
     range_mutex.h
     range_sets.h

src/common/quaternion.h

@@ -0,0 +1,79 @@
+// SPDX-FileCopyrightText: 2016 Citra Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#include "common/vector_math.h"
+
+namespace Common {
+
+template <typename T>
+class Quaternion {
+public:
+    Vec3<T> xyz;
+    T w{};
+
+    [[nodiscard]] Quaternion<decltype(-T{})> Inverse() const {
+        return {-xyz, w};
+    }
+
+    [[nodiscard]] Quaternion<decltype(T{} + T{})> operator+(const Quaternion& other) const {
+        return {xyz + other.xyz, w + other.w};
+    }
+
+    [[nodiscard]] Quaternion<decltype(T{} - T{})> operator-(const Quaternion& other) const {
+        return {xyz - other.xyz, w - other.w};
+    }
+
+    [[nodiscard]] Quaternion<decltype(T{} * T{} - T{} * T{})> operator*(
+        const Quaternion& other) const {
+        return {xyz * other.w + other.xyz * w + Cross(xyz, other.xyz),
+                w * other.w - Dot(xyz, other.xyz)};
+    }
+
+    [[nodiscard]] Quaternion<T> Normalized() const {
+        T length = std::sqrt(xyz.Length2() + w * w);
+        return {xyz / length, w / length};
+    }
+
+    [[nodiscard]] std::array<decltype(-T{}), 16> ToMatrix() const {
+        const T x2 = xyz[0] * xyz[0];
+        const T y2 = xyz[1] * xyz[1];
+        const T z2 = xyz[2] * xyz[2];
+
+        const T xy = xyz[0] * xyz[1];
+        const T wz = w * xyz[2];
+        const T xz = xyz[0] * xyz[2];
+        const T wy = w * xyz[1];
+        const T yz = xyz[1] * xyz[2];
+        const T wx = w * xyz[0];
+
+        return {1.0f - 2.0f * (y2 + z2),
+                2.0f * (xy + wz),
+                2.0f * (xz - wy),
+                0.0f,
+                2.0f * (xy - wz),
+                1.0f - 2.0f * (x2 + z2),
+                2.0f * (yz + wx),
+                0.0f,
+                2.0f * (xz + wy),
+                2.0f * (yz - wx),
+                1.0f - 2.0f * (x2 + y2),
+                0.0f,
+                0.0f,
+                0.0f,
+                0.0f,
+                1.0f};
+    }
+};
+
+template <typename T>
+[[nodiscard]] auto QuaternionRotate(const Quaternion<T>& q, const Vec3<T>& v) {
+    return v + 2 * Cross(q.xyz, Cross(q.xyz, v) + v * q.w);
+}
+
+[[nodiscard]] inline Quaternion<float> MakeQuaternion(const Vec3<float>& axis, float angle) {
+    return {axis * std::sin(angle / 2), std::cos(angle / 2)};
+}
+
+} // namespace Common

src/common/vector_math.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: 2014 Tony Wasserka
@@ -7,128 +7,752 @@
 
 #pragma once
 
+#ifdef __ARM_NEON
+#include <arm_neon.h>
+#endif
+
 #include <cmath>
 #include <type_traits>
 
 namespace Common {
 
-template <typename T, size_t N>
-class Vec {
+template <typename T>
+class Vec2;
+template <typename T>
+class Vec3;
+template <typename T>
+class Vec4;
+
+template <typename T>
+class Vec2 {
 public:
-    std::array<T, N> elems{};
+    T x{};
+    T y{};
 
-    constexpr Vec() = default;
-    constexpr Vec(T e0) noexcept : elems{e0} {}
-    constexpr Vec(T e0, T e1) noexcept : elems{e0, e1} {}
-    constexpr Vec(T e0, T e1, T e2) noexcept : elems{e0, e1, e2} {}
-    constexpr Vec(T e0, T e1, T e2, T e4) noexcept : elems{e0, e1, e2, e4} {}
-    //explicit constexpr Vec(const std::initializer_list<T> elems_) noexcept : elems{elems_} {}
+    constexpr Vec2() = default;
+    constexpr Vec2(const T& x_, const T& y_) : x(x_), y(y_) {}
 
-    [[nodiscard]] constexpr Vec<decltype(T{} + T{}), N> operator+(const Vec o) const noexcept {
-        Vec<decltype(T{} + T{}), N> r{};
-        for (size_t i = 0; i < N; ++i)
-            r.elems[i] = elems[i] + o.elems[i];
-        return r;
+    template <typename T2>
+    [[nodiscard]] constexpr Vec2<T2> Cast() const {
+        return Vec2<T2>(static_cast<T2>(x), static_cast<T2>(y));
     }
-    constexpr Vec<T, N> operator+=(const Vec<T, N> o) noexcept { return *this = *this + o; }
 
-    [[nodiscard]] constexpr Vec<decltype(T{} - T{}), N> operator-(const Vec o) const noexcept {
-        Vec<decltype(T{} - T{}), N> r{};
-        for (size_t i = 0; i < N; ++i)
-            r.elems[i] = elems[i] - o.elems[i];
-        return r;
+    [[nodiscard]] static constexpr Vec2 AssignToAll(const T& f) {
+        return Vec2{f, f};
+    }
+
+    [[nodiscard]] constexpr Vec2<decltype(T{} + T{})> operator+(const Vec2& other) const {
+        return {x + other.x, y + other.y};
+    }
+    constexpr Vec2& operator+=(const Vec2& other) {
+        x += other.x;
+        y += other.y;
+        return *this;
+    }
+    [[nodiscard]] constexpr Vec2<decltype(T{} - T{})> operator-(const Vec2& other) const {
+        return {x - other.x, y - other.y};
+    }
+    constexpr Vec2& operator-=(const Vec2& other) {
+        x -= other.x;
+        y -= other.y;
+        return *this;
     }
-    constexpr Vec<T, N> operator-=(const Vec<T, N> o) noexcept { return *this = *this - o; }
 
     template <typename U = T>
-    [[nodiscard]] constexpr Vec<std::enable_if_t<std::is_signed_v<U>, U>, N> operator-() const noexcept {
-        Vec<U, N> r{};
-        for (size_t i = 0; i < N; ++i)
-            r.elems[i] = -elems[i];
-        return r;
+    [[nodiscard]] constexpr Vec2<std::enable_if_t<std::is_signed_v<U>, U>> operator-() const {
+        return {-x, -y};
+    }
+    [[nodiscard]] constexpr Vec2<decltype(T{} * T{})> operator*(const Vec2& other) const {
+        return {x * other.x, y * other.y};
     }
 
-    [[nodiscard]] constexpr Vec<decltype(T{} * T{}), N> operator*(const Vec o) const noexcept {
-        Vec<decltype(T{} * T{}), N> r{};
-        for (size_t i = 0; i < N; ++i)
-            r.elems[i] = elems[i] * o.elems[i];
-        return r;
-    }
     template <typename V>
-    [[nodiscard]] constexpr Vec<decltype(T{} * V{}), N> operator*(const V f) const noexcept {
+    [[nodiscard]] constexpr Vec2<decltype(T{} * V{})> operator*(const V& f) const {
         using TV = decltype(T{} * V{});
         using C = std::common_type_t<T, V>;
-        Vec<TV, N> r{};
-        for (size_t i = 0; i < N; ++i)
-            r.elems[i] = TV(C(elems[i]) * C(f));
-        return r;
+
+        return {
+            static_cast<TV>(static_cast<C>(x) * static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(y) * static_cast<C>(f)),
+        };
     }
-    template <typename V>
-    constexpr Vec<T, N> operator*=(const V f) noexcept { return *this = *this * f; }
 
     template <typename V>
-    [[nodiscard]] constexpr Vec<decltype(T{} / V{}), N> operator/(const V f) const noexcept {
+    constexpr Vec2& operator*=(const V& f) {
+        *this = *this * f;
+        return *this;
+    }
+
+    template <typename V>
+    [[nodiscard]] constexpr Vec2<decltype(T{} / V{})> operator/(const V& f) const {
         using TV = decltype(T{} / V{});
         using C = std::common_type_t<T, V>;
-        Vec<TV, N> r{};
-        for (size_t i = 0; i < N; ++i)
-            r.elems[i] = TV(C(elems[i]) / C(f));
-        return r;
-    }
-    template <typename V>
-    constexpr Vec<T, N> operator/=(const V f) noexcept { return *this = *this / f; }
 
-    [[nodiscard]] constexpr T Length2() const noexcept {
-        T r{};
-        for (size_t i = 0; i < N; ++i)
-            r += elems[i] * elems[i];
-        return r;
-    }
-    // Only implemented for T=float
-    [[nodiscard]] T Length() const { return T(std::sqrt(float(Length2()))); }
-    [[nodiscard]] Vec<T, N> Normalized() const { return *this / Length(); }
-    [[nodiscard]] constexpr T& operator[](std::size_t i) noexcept { return elems[i]; }
-    [[nodiscard]] constexpr const T& operator[](std::size_t i) const noexcept { return elems[i]; }
-
-    [[nodiscard]] std::array<decltype(-T{}), 16> ToMatrix() const {
-        const T x2 = elems[0] * elems[0];
-        const T y2 = elems[1] * elems[1];
-        const T z2 = elems[2] * elems[2];
-
-        const T xy = elems[0] * elems[1];
-        const T wz = elems[3] * elems[2];
-        const T xz = elems[0] * elems[2];
-        const T wy = elems[3] * elems[1];
-        const T yz = elems[1] * elems[2];
-        const T wx = elems[3] * elems[0];
         return {
-            1.0f - 2.0f * (y2 + z2),
-            2.0f * (xy + wz),
-            2.0f * (xz - wy),
-            0.0f,
-            2.0f * (xy - wz),
-            1.0f - 2.0f * (x2 + z2),
-            2.0f * (yz + wx),
-            0.0f,
-            2.0f * (xz + wy),
-            2.0f * (yz - wx),
-            1.0f - 2.0f * (x2 + y2),
-            0.0f,
-            0.0f,
-            0.0f,
-            0.0f,
-            1.0f
+            static_cast<TV>(static_cast<C>(x) / static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(y) / static_cast<C>(f)),
         };
     }
+
+    template <typename V>
+    constexpr Vec2& operator/=(const V& f) {
+        *this = *this / f;
+        return *this;
+    }
+
+    [[nodiscard]] constexpr T Length2() const {
+        return x * x + y * y;
+    }
+
+    // Only implemented for T=float
+    [[nodiscard]] float Length() const;
+    [[nodiscard]] float Normalize(); // returns the previous length, which is often useful
+
+    [[nodiscard]] constexpr T& operator[](std::size_t i) {
+        return *((&x) + i);
+    }
+    [[nodiscard]] constexpr const T& operator[](std::size_t i) const {
+        return *((&x) + i);
+    }
+
+    constexpr void SetZero() {
+        x = 0;
+        y = 0;
+    }
+
+    // Common aliases: UV (texel coordinates), ST (texture coordinates)
+    [[nodiscard]] constexpr T& u() {
+        return x;
+    }
+    [[nodiscard]] constexpr T& v() {
+        return y;
+    }
+    [[nodiscard]] constexpr T& s() {
+        return x;
+    }
+    [[nodiscard]] constexpr T& t() {
+        return y;
+    }
+
+    [[nodiscard]] constexpr const T& u() const {
+        return x;
+    }
+    [[nodiscard]] constexpr const T& v() const {
+        return y;
+    }
+    [[nodiscard]] constexpr const T& s() const {
+        return x;
+    }
+    [[nodiscard]] constexpr const T& t() const {
+        return y;
+    }
+
+    // swizzlers - create a subvector of specific components
+    [[nodiscard]] constexpr Vec2 yx() const {
+        return Vec2(y, x);
+    }
+    [[nodiscard]] constexpr Vec2 vu() const {
+        return Vec2(y, x);
+    }
+    [[nodiscard]] constexpr Vec2 ts() const {
+        return Vec2(y, x);
+    }
 };
 
-template <typename T, size_t N, typename V>
-[[nodiscard]] constexpr Vec<T, N> operator*(const V f, const Vec<T, N> v) noexcept {
+template <typename T, typename V>
+[[nodiscard]] constexpr Vec2<T> operator*(const V& f, const Vec2<T>& vec) {
     using C = std::common_type_t<T, V>;
-    Vec<T, N> r{};
-    for (size_t i = 0; i < N; ++i)
-        r.elems[i] = T(C(f) * C(v.elems[i]));
-    return r;
+
+    return Vec2<T>(static_cast<T>(static_cast<C>(f) * static_cast<C>(vec.x)),
+                   static_cast<T>(static_cast<C>(f) * static_cast<C>(vec.y)));
+}
+
+using Vec2f = Vec2<float>;
+
+template <>
+inline float Vec2<float>::Length() const {
+    return std::sqrt(x * x + y * y);
+}
+
+template <>
+inline float Vec2<float>::Normalize() {
+    float length = Length();
+    *this /= length;
+    return length;
+}
+
+template <typename T>
+class Vec3 {
+public:
+    T x{};
+    T y{};
+    T z{};
+
+    constexpr Vec3() = default;
+    constexpr Vec3(const T& x_, const T& y_, const T& z_) : x(x_), y(y_), z(z_) {}
+
+    template <typename T2>
+    [[nodiscard]] constexpr Vec3<T2> Cast() const {
+        return Vec3<T2>(static_cast<T2>(x), static_cast<T2>(y), static_cast<T2>(z));
+    }
+
+    [[nodiscard]] static constexpr Vec3 AssignToAll(const T& f) {
+        return Vec3(f, f, f);
+    }
+
+    [[nodiscard]] constexpr Vec3<decltype(T{} + T{})> operator+(const Vec3& other) const {
+        return {x + other.x, y + other.y, z + other.z};
+    }
+
+    constexpr Vec3& operator+=(const Vec3& other) {
+        x += other.x;
+        y += other.y;
+        z += other.z;
+        return *this;
+    }
+
+    [[nodiscard]] constexpr Vec3<decltype(T{} - T{})> operator-(const Vec3& other) const {
+        return {x - other.x, y - other.y, z - other.z};
+    }
+
+    constexpr Vec3& operator-=(const Vec3& other) {
+        x -= other.x;
+        y -= other.y;
+        z -= other.z;
+        return *this;
+    }
+
+    template <typename U = T>
+    [[nodiscard]] constexpr Vec3<std::enable_if_t<std::is_signed_v<U>, U>> operator-() const {
+        return {-x, -y, -z};
+    }
+
+    [[nodiscard]] constexpr Vec3<decltype(T{} * T{})> operator*(const Vec3& other) const {
+        return {x * other.x, y * other.y, z * other.z};
+    }
+
+    template <typename V>
+    [[nodiscard]] constexpr Vec3<decltype(T{} * V{})> operator*(const V& f) const {
+        using TV = decltype(T{} * V{});
+        using C = std::common_type_t<T, V>;
+
+        return {
+            static_cast<TV>(static_cast<C>(x) * static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(y) * static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(z) * static_cast<C>(f)),
+        };
+    }
+
+    template <typename V>
+    constexpr Vec3& operator*=(const V& f) {
+        *this = *this * f;
+        return *this;
+    }
+    template <typename V>
+    [[nodiscard]] constexpr Vec3<decltype(T{} / V{})> operator/(const V& f) const {
+        using TV = decltype(T{} / V{});
+        using C = std::common_type_t<T, V>;
+
+        return {
+            static_cast<TV>(static_cast<C>(x) / static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(y) / static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(z) / static_cast<C>(f)),
+        };
+    }
+
+    template <typename V>
+    constexpr Vec3& operator/=(const V& f) {
+        *this = *this / f;
+        return *this;
+    }
+
+    void RotateFromOrigin(float roll, float pitch, float yaw) {
+        float temp = y;
+        y = std::cos(roll) * y - std::sin(roll) * z;
+        z = std::sin(roll) * temp + std::cos(roll) * z;
+
+        temp = x;
+        x = std::cos(pitch) * x + std::sin(pitch) * z;
+        z = -std::sin(pitch) * temp + std::cos(pitch) * z;
+
+        temp = x;
+        x = std::cos(yaw) * x - std::sin(yaw) * y;
+        y = std::sin(yaw) * temp + std::cos(yaw) * y;
+    }
+
+    [[nodiscard]] constexpr T Length2() const {
+        return x * x + y * y + z * z;
+    }
+
+    // Only implemented for T=float
+    [[nodiscard]] float Length() const;
+    [[nodiscard]] Vec3 Normalized() const;
+    [[nodiscard]] float Normalize(); // returns the previous length, which is often useful
+
+    [[nodiscard]] constexpr T& operator[](std::size_t i) {
+        return *((&x) + i);
+    }
+
+    [[nodiscard]] constexpr const T& operator[](std::size_t i) const {
+        return *((&x) + i);
+    }
+
+    constexpr void SetZero() {
+        x = 0;
+        y = 0;
+        z = 0;
+    }
+
+    // Common aliases: UVW (texel coordinates), RGB (colors), STQ (texture coordinates)
+    [[nodiscard]] constexpr T& u() {
+        return x;
+    }
+    [[nodiscard]] constexpr T& v() {
+        return y;
+    }
+    [[nodiscard]] constexpr T& w() {
+        return z;
+    }
+
+    [[nodiscard]] constexpr T& r() {
+        return x;
+    }
+    [[nodiscard]] constexpr T& g() {
+        return y;
+    }
+    [[nodiscard]] constexpr T& b() {
+        return z;
+    }
+
+    [[nodiscard]] constexpr T& s() {
+        return x;
+    }
+    [[nodiscard]] constexpr T& t() {
+        return y;
+    }
+    [[nodiscard]] constexpr T& q() {
+        return z;
+    }
+
+    [[nodiscard]] constexpr const T& u() const {
+        return x;
+    }
+    [[nodiscard]] constexpr const T& v() const {
+        return y;
+    }
+    [[nodiscard]] constexpr const T& w() const {
+        return z;
+    }
+
+    [[nodiscard]] constexpr const T& r() const {
+        return x;
+    }
+    [[nodiscard]] constexpr const T& g() const {
+        return y;
+    }
+    [[nodiscard]] constexpr const T& b() const {
+        return z;
+    }
+
+    [[nodiscard]] constexpr const T& s() const {
+        return x;
+    }
+    [[nodiscard]] constexpr const T& t() const {
+        return y;
+    }
+    [[nodiscard]] constexpr const T& q() const {
+        return z;
+    }
+
+// swizzlers - create a subvector of specific components
+// e.g. Vec2 uv() { return Vec2(x,y); }
+// _DEFINE_SWIZZLER2 defines a single such function, DEFINE_SWIZZLER2 defines all of them for all
+// component names (x<->r) and permutations (xy<->yx)
+#define _DEFINE_SWIZZLER2(a, b, name)                                                              \
+    [[nodiscard]] constexpr Vec2<T> name() const { return Vec2<T>(a, b); }
+#define DEFINE_SWIZZLER2(a, b, a2, b2, a3, b3, a4, b4)                                             \
+    _DEFINE_SWIZZLER2(a, b, a##b);                                                                 \
+    _DEFINE_SWIZZLER2(a, b, a2##b2);                                                               \
+    _DEFINE_SWIZZLER2(a, b, a3##b3);                                                               \
+    _DEFINE_SWIZZLER2(a, b, a4##b4);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b##a);                                                                 \
+    _DEFINE_SWIZZLER2(b, a, b2##a2);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b3##a3);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b4##a4)
+
+    DEFINE_SWIZZLER2(x, y, r, g, u, v, s, t);
+    DEFINE_SWIZZLER2(x, z, r, b, u, w, s, q);
+    DEFINE_SWIZZLER2(y, z, g, b, v, w, t, q);
+#undef DEFINE_SWIZZLER2
+#undef _DEFINE_SWIZZLER2
+};
+
+template <typename T, typename V>
+[[nodiscard]] constexpr Vec3<T> operator*(const V& f, const Vec3<T>& vec) {
+    using C = std::common_type_t<T, V>;
+
+    return Vec3<T>(static_cast<T>(static_cast<C>(f) * static_cast<C>(vec.x)),
+                   static_cast<T>(static_cast<C>(f) * static_cast<C>(vec.y)),
+                   static_cast<T>(static_cast<C>(f) * static_cast<C>(vec.z)));
+}
+
+template <>
+inline float Vec3<float>::Length() const {
+    return std::sqrt(x * x + y * y + z * z);
+}
+
+template <>
+inline Vec3<float> Vec3<float>::Normalized() const {
+    return *this / Length();
+}
+
+template <>
+inline float Vec3<float>::Normalize() {
+    float length = Length();
+    *this /= length;
+    return length;
+}
+
+using Vec3f = Vec3<float>;
+
+template <typename T>
+class Vec4 {
+public:
+    T x{};
+    T y{};
+    T z{};
+    T w{};
+
+    constexpr Vec4() = default;
+    constexpr Vec4(const T& x_, const T& y_, const T& z_, const T& w_)
+        : x(x_), y(y_), z(z_), w(w_) {}
+
+    template <typename T2>
+    [[nodiscard]] constexpr Vec4<T2> Cast() const {
+        return Vec4<T2>(static_cast<T2>(x), static_cast<T2>(y), static_cast<T2>(z),
+                        static_cast<T2>(w));
+    }
+
+    [[nodiscard]] static constexpr Vec4 AssignToAll(const T& f) {
+        return Vec4(f, f, f, f);
+    }
+
+    [[nodiscard]] constexpr Vec4<decltype(T{} + T{})> operator+(const Vec4& other) const {
+        return {x + other.x, y + other.y, z + other.z, w + other.w};
+    }
+
+    constexpr Vec4& operator+=(const Vec4& other) {
+        x += other.x;
+        y += other.y;
+        z += other.z;
+        w += other.w;
+        return *this;
+    }
+
+    [[nodiscard]] constexpr Vec4<decltype(T{} - T{})> operator-(const Vec4& other) const {
+        return {x - other.x, y - other.y, z - other.z, w - other.w};
+    }
+
+    constexpr Vec4& operator-=(const Vec4& other) {
+        x -= other.x;
+        y -= other.y;
+        z -= other.z;
+        w -= other.w;
+        return *this;
+    }
+
+    template <typename U = T>
+    [[nodiscard]] constexpr Vec4<std::enable_if_t<std::is_signed_v<U>, U>> operator-() const {
+        return {-x, -y, -z, -w};
+    }
+
+    [[nodiscard]] constexpr Vec4<decltype(T{} * T{})> operator*(const Vec4& other) const {
+        return {x * other.x, y * other.y, z * other.z, w * other.w};
+    }
+
+    template <typename V>
+    [[nodiscard]] constexpr Vec4<decltype(T{} * V{})> operator*(const V& f) const {
+        using TV = decltype(T{} * V{});
+        using C = std::common_type_t<T, V>;
+
+        return {
+            static_cast<TV>(static_cast<C>(x) * static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(y) * static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(z) * static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(w) * static_cast<C>(f)),
+        };
+    }
+
+    template <typename V>
+    constexpr Vec4& operator*=(const V& f) {
+        *this = *this * f;
+        return *this;
+    }
+
+    template <typename V>
+    [[nodiscard]] constexpr Vec4<decltype(T{} / V{})> operator/(const V& f) const {
+        using TV = decltype(T{} / V{});
+        using C = std::common_type_t<T, V>;
+
+        return {
+            static_cast<TV>(static_cast<C>(x) / static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(y) / static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(z) / static_cast<C>(f)),
+            static_cast<TV>(static_cast<C>(w) / static_cast<C>(f)),
+        };
+    }
+
+    template <typename V>
+    constexpr Vec4& operator/=(const V& f) {
+        *this = *this / f;
+        return *this;
+    }
+
+    [[nodiscard]] constexpr T Length2() const {
+        return x * x + y * y + z * z + w * w;
+    }
+
+    [[nodiscard]] constexpr T& operator[](std::size_t i) {
+        return *((&x) + i);
+    }
+
+    [[nodiscard]] constexpr const T& operator[](std::size_t i) const {
+        return *((&x) + i);
+    }
+
+    constexpr void SetZero() {
+        x = 0;
+        y = 0;
+        z = 0;
+        w = 0;
+    }
+
+    // Common alias: RGBA (colors)
+    [[nodiscard]] constexpr T& r() {
+        return x;
+    }
+    [[nodiscard]] constexpr T& g() {
+        return y;
+    }
+    [[nodiscard]] constexpr T& b() {
+        return z;
+    }
+    [[nodiscard]] constexpr T& a() {
+        return w;
+    }
+
+    [[nodiscard]] constexpr const T& r() const {
+        return x;
+    }
+    [[nodiscard]] constexpr const T& g() const {
+        return y;
+    }
+    [[nodiscard]] constexpr const T& b() const {
+        return z;
+    }
+    [[nodiscard]] constexpr const T& a() const {
+        return w;
+    }
+
+// Swizzlers - Create a subvector of specific components
+// e.g. Vec2 uv() { return Vec2(x,y); }
+
+// _DEFINE_SWIZZLER2 defines a single such function
+// DEFINE_SWIZZLER2_COMP1 defines one-component functions for all component names (x<->r)
+// DEFINE_SWIZZLER2_COMP2 defines two component functions for all component names (x<->r) and
+// permutations (xy<->yx)
+#define _DEFINE_SWIZZLER2(a, b, name)                                                              \
+    [[nodiscard]] constexpr Vec2<T> name() const { return Vec2<T>(a, b); }
+#define DEFINE_SWIZZLER2_COMP1(a, a2)                                                              \
+    _DEFINE_SWIZZLER2(a, a, a##a);                                                                 \
+    _DEFINE_SWIZZLER2(a, a, a2##a2)
+#define DEFINE_SWIZZLER2_COMP2(a, b, a2, b2)                                                       \
+    _DEFINE_SWIZZLER2(a, b, a##b);                                                                 \
+    _DEFINE_SWIZZLER2(a, b, a2##b2);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b##a);                                                                 \
+    _DEFINE_SWIZZLER2(b, a, b2##a2)
+
+    DEFINE_SWIZZLER2_COMP2(x, y, r, g);
+    DEFINE_SWIZZLER2_COMP2(x, z, r, b);
+    DEFINE_SWIZZLER2_COMP2(x, w, r, a);
+    DEFINE_SWIZZLER2_COMP2(y, z, g, b);
+    DEFINE_SWIZZLER2_COMP2(y, w, g, a);
+    DEFINE_SWIZZLER2_COMP2(z, w, b, a);
+    DEFINE_SWIZZLER2_COMP1(x, r);
+    DEFINE_SWIZZLER2_COMP1(y, g);
+    DEFINE_SWIZZLER2_COMP1(z, b);
+    DEFINE_SWIZZLER2_COMP1(w, a);
+#undef DEFINE_SWIZZLER2_COMP1
+#undef DEFINE_SWIZZLER2_COMP2
+#undef _DEFINE_SWIZZLER2
+
+#define _DEFINE_SWIZZLER3(a, b, c, name)                                                           \
+    [[nodiscard]] constexpr Vec3<T> name() const { return Vec3<T>(a, b, c); }
+#define DEFINE_SWIZZLER3_COMP1(a, a2)                                                              \
+    _DEFINE_SWIZZLER3(a, a, a, a##a##a);                                                           \
+    _DEFINE_SWIZZLER3(a, a, a, a2##a2##a2)
+#define DEFINE_SWIZZLER3_COMP3(a, b, c, a2, b2, c2)                                                \
+    _DEFINE_SWIZZLER3(a, b, c, a##b##c);                                                           \
+    _DEFINE_SWIZZLER3(a, c, b, a##c##b);                                                           \
+    _DEFINE_SWIZZLER3(b, a, c, b##a##c);                                                           \
+    _DEFINE_SWIZZLER3(b, c, a, b##c##a);                                                           \
+    _DEFINE_SWIZZLER3(c, a, b, c##a##b);                                                           \
+    _DEFINE_SWIZZLER3(c, b, a, c##b##a);                                                           \
+    _DEFINE_SWIZZLER3(a, b, c, a2##b2##c2);                                                        \
+    _DEFINE_SWIZZLER3(a, c, b, a2##c2##b2);                                                        \
+    _DEFINE_SWIZZLER3(b, a, c, b2##a2##c2);                                                        \
+    _DEFINE_SWIZZLER3(b, c, a, b2##c2##a2);                                                        \
+    _DEFINE_SWIZZLER3(c, a, b, c2##a2##b2);                                                        \
+    _DEFINE_SWIZZLER3(c, b, a, c2##b2##a2)
+
+    DEFINE_SWIZZLER3_COMP3(x, y, z, r, g, b);
+    DEFINE_SWIZZLER3_COMP3(x, y, w, r, g, a);
+    DEFINE_SWIZZLER3_COMP3(x, z, w, r, b, a);
+    DEFINE_SWIZZLER3_COMP3(y, z, w, g, b, a);
+    DEFINE_SWIZZLER3_COMP1(x, r);
+    DEFINE_SWIZZLER3_COMP1(y, g);
+    DEFINE_SWIZZLER3_COMP1(z, b);
+    DEFINE_SWIZZLER3_COMP1(w, a);
+#undef DEFINE_SWIZZLER3_COMP1
+#undef DEFINE_SWIZZLER3_COMP3
+#undef _DEFINE_SWIZZLER3
+};
+
+template <typename T, typename V>
+[[nodiscard]] constexpr Vec4<decltype(V{} * T{})> operator*(const V& f, const Vec4<T>& vec) {
+    using TV = decltype(V{} * T{});
+    using C = std::common_type_t<T, V>;
+
+    return {
+        static_cast<TV>(static_cast<C>(f) * static_cast<C>(vec.x)),
+        static_cast<TV>(static_cast<C>(f) * static_cast<C>(vec.y)),
+        static_cast<TV>(static_cast<C>(f) * static_cast<C>(vec.z)),
+        static_cast<TV>(static_cast<C>(f) * static_cast<C>(vec.w)),
+    };
+}
+
+using Vec4f = Vec4<float>;
+
+template <typename T>
+constexpr decltype(T{} * T{} + T{} * T{}) Dot(const Vec2<T>& a, const Vec2<T>& b) {
+    return a.x * b.x + a.y * b.y;
+}
+
+template <typename T>
+[[nodiscard]] constexpr decltype(T{} * T{} + T{} * T{}) Dot(const Vec3<T>& a, const Vec3<T>& b) {
+    return a.x * b.x + a.y * b.y + a.z * b.z;
+}
+
+template <typename T>
+[[nodiscard]] constexpr decltype(T{} * T{} + T{} * T{}) Dot(const Vec4<T>& a, const Vec4<T>& b) {
+    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.x);
+    float32x4_t vb = vld1q_f32(&b.x);
+    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) {
+    return {a.y * b.z - a.z * b.y, a.z * b.x - a.x * b.z, a.x * b.y - a.y * b.x};
+}
+
+// linear interpolation via float: 0.0=begin, 1.0=end
+template <typename X>
+[[nodiscard]] constexpr decltype(X{} * float{} + X{} * float{}) Lerp(const X& begin, const X& end,
+                                                                     const float t) {
+    return begin * (1.f - t) + end * t;
+}
+
+// linear interpolation via int: 0=begin, base=end
+template <typename X, int base>
+[[nodiscard]] constexpr decltype((X{} * int{} + X{} * int{}) / base) LerpInt(const X& begin,
+                                                                             const X& end,
+                                                                             const int t) {
+    return (begin * (base - t) + end * t) / base;
+}
+
+// bilinear interpolation. s is for interpolating x00-x01 and x10-x11, and t is for the second
+// interpolation.
+template <typename X>
+[[nodiscard]] constexpr auto BilinearInterp(const X& x00, const X& x01, const X& x10, const X& x11,
+                                            const float s, const float t) {
+    auto y0 = Lerp(x00, x01, s);
+    auto y1 = Lerp(x10, x11, s);
+    return Lerp(y0, y1, t);
+}
+
+// Utility vector factories
+template <typename T>
+[[nodiscard]] constexpr Vec2<T> MakeVec(const T& x, const T& y) {
+    return Vec2<T>{x, y};
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec3<T> MakeVec(const T& x, const T& y, const T& z) {
+    return Vec3<T>{x, y, z};
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const T& x, const T& y, const Vec2<T>& zw) {
+    return MakeVec(x, y, zw[0], zw[1]);
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec3<T> MakeVec(const Vec2<T>& xy, const T& z) {
+    return MakeVec(xy[0], xy[1], z);
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec3<T> MakeVec(const T& x, const Vec2<T>& yz) {
+    return MakeVec(x, yz[0], yz[1]);
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const T& x, const T& y, const T& z, const T& w) {
+    return Vec4<T>{x, y, z, w};
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const Vec2<T>& xy, const T& z, const T& w) {
+    return MakeVec(xy[0], xy[1], z, w);
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const T& x, const Vec2<T>& yz, const T& w) {
+    return MakeVec(x, yz[0], yz[1], w);
+}
+
+// NOTE: This has priority over "Vec2<Vec2<T>> MakeVec(const Vec2<T>& x, const Vec2<T>& y)".
+//       Even if someone wanted to use an odd object like Vec2<Vec2<T>>, the compiler would error
+//       out soon enough due to misuse of the returned structure.
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const Vec2<T>& xy, const Vec2<T>& zw) {
+    return MakeVec(xy[0], xy[1], zw[0], zw[1]);
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const Vec3<T>& xyz, const T& w) {
+    return MakeVec(xyz[0], xyz[1], xyz[2], w);
+}
+
+template <typename T>
+[[nodiscard]] constexpr Vec4<T> MakeVec(const T& x, const Vec3<T>& yzw) {
+    return MakeVec(x, yzw[0], yzw[1], yzw[2]);
 }
 
 } // namespace Common

src/core/hle/service/set/setting_formats/device_settings.h

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -33,15 +30,15 @@ struct DeviceSettings {
     INSERT_PADDING_BYTES(0x20); // Reserved
 
     // nn::settings::system::ConsoleSixAxisSensorAccelerationBias
-    Common::Vec<f32, 3> console_six_axis_sensor_acceleration_bias;
+    Common::Vec3<f32> console_six_axis_sensor_acceleration_bias;
     // nn::settings::system::ConsoleSixAxisSensorAngularVelocityBias
-    Common::Vec<f32, 3> console_six_axis_sensor_angular_velocity_bias;
+    Common::Vec3<f32> console_six_axis_sensor_angular_velocity_bias;
     // nn::settings::system::ConsoleSixAxisSensorAccelerationGain
     std::array<u8, 0x24> console_six_axis_sensor_acceleration_gain;
     // nn::settings::system::ConsoleSixAxisSensorAngularVelocityGain
     std::array<u8, 0x24> console_six_axis_sensor_angular_velocity_gain;
     // nn::settings::system::ConsoleSixAxisSensorAngularVelocityTimeBias
-    Common::Vec<f32, 3> console_six_axis_sensor_angular_velocity_time_bias;
+    Common::Vec3<f32> console_six_axis_sensor_angular_velocity_time_bias;
     // nn::settings::system::ConsoleSixAxisSensorAngularAcceleration
     std::array<u8, 0x24> console_six_axis_sensor_angular_acceleration;
 };

src/core/hle/service/set/setting_formats/system_settings.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
@@ -153,15 +153,15 @@ struct SystemSettings {
     INSERT_PADDING_BYTES(0x7FF8); // Reserved
 
     // nn::settings::system::ConsoleSixAxisSensorAccelerationBias
-    Common::Vec<f32, 3> console_six_axis_sensor_acceleration_bias;
+    Common::Vec3<f32> console_six_axis_sensor_acceleration_bias;
     // nn::settings::system::ConsoleSixAxisSensorAngularVelocityBias
-    Common::Vec<f32, 3> console_six_axis_sensor_angular_velocity_bias;
+    Common::Vec3<f32> console_six_axis_sensor_angular_velocity_bias;
     // nn::settings::system::ConsoleSixAxisSensorAccelerationGain
     std::array<u8, 0x24> console_six_axis_sensor_acceleration_gain;
     // nn::settings::system::ConsoleSixAxisSensorAngularVelocityGain
     std::array<u8, 0x24> console_six_axis_sensor_angular_velocity_gain;
     // nn::settings::system::ConsoleSixAxisSensorAngularVelocityTimeBias
-    Common::Vec<f32, 3> console_six_axis_sensor_angular_velocity_time_bias;
+    Common::Vec3<f32> console_six_axis_sensor_angular_velocity_time_bias;
     // nn::settings::system::ConsoleSixAxisSensorAngularAcceleration
     std::array<u8, 0x24> console_six_axis_sensor_angular_velocity_acceleration;
     INSERT_PADDING_BYTES(0x70); // Reserved

src/hid_core/frontend/emulated_console.cpp

@@ -170,12 +170,12 @@ void EmulatedConsole::SetMotion(const Common::Input::CallbackStatus& callback) {
     auto& emulated = console.motion_values.emulated;
 
     raw_status = TransformToMotion(callback);
-    emulated.SetAcceleration(Common::Vec<f32, 3>{
+    emulated.SetAcceleration(Common::Vec3f{
         raw_status.accel.x.value,
         raw_status.accel.y.value,
         raw_status.accel.z.value,
     });
-    emulated.SetGyroscope(Common::Vec<f32, 3>{
+    emulated.SetGyroscope(Common::Vec3f{
         raw_status.gyro.x.value,
         raw_status.gyro.y.value,
         raw_status.gyro.z.value,

src/hid_core/frontend/emulated_console.h

@@ -18,6 +18,7 @@
 #include "common/input.h"
 #include "common/param_package.h"
 #include "common/point.h"
+#include "common/quaternion.h"
 #include "common/vector_math.h"
 #include "hid_core/frontend/motion_input.h"
 #include "hid_core/hid_types.h"
@@ -42,12 +43,12 @@ using TouchValues = std::array<Common::Input::TouchStatus, MaxTouchDevices>;
 
 // Contains all motion related data that is used on the services
 struct ConsoleMotion {
-    Common::Vec<f32, 3> accel{};
-    Common::Vec<f32, 3> gyro{};
-    Common::Vec<f32, 3> rotation{};
-    std::array<Common::Vec<f32, 3>, 3> orientation{};
-    Common::Vec<f32, 4> quaternion{};
-    Common::Vec<f32, 3> gyro_bias{};
+    Common::Vec3f accel{};
+    Common::Vec3f gyro{};
+    Common::Vec3f rotation{};
+    std::array<Common::Vec3f, 3> orientation{};
+    Common::Quaternion<f32> quaternion{};
+    Common::Vec3f gyro_bias{};
     f32 verticalization_error{};
     bool is_at_rest{};
 };

src/hid_core/frontend/emulated_controller.cpp

@@ -1051,12 +1051,12 @@ void EmulatedController::SetMotion(const Common::Input::CallbackStatus& callback
     auto& emulated = controller.motion_values[index].emulated;
 
     raw_status = TransformToMotion(callback);
-    emulated.SetAcceleration(Common::Vec<f32, 3>{
+    emulated.SetAcceleration(Common::Vec3f{
         raw_status.accel.x.value,
         raw_status.accel.y.value,
         raw_status.accel.z.value,
     });
-    emulated.SetGyroscope(Common::Vec<f32, 3>{
+    emulated.SetGyroscope(Common::Vec3f{
         raw_status.gyro.x.value,
         raw_status.gyro.y.value,
         raw_status.gyro.z.value,

src/hid_core/frontend/emulated_controller.h

@@ -107,11 +107,11 @@ struct RingSensorForce {
 using NfcState = Common::Input::NfcStatus;
 
 struct ControllerMotion {
-    Common::Vec<f32, 3> accel{};
-    Common::Vec<f32, 3> gyro{};
-    Common::Vec<f32, 3> rotation{};
-    Common::Vec<f32, 3> euler{};
-    std::array<Common::Vec<f32, 3>, 3> orientation{};
+    Common::Vec3f accel{};
+    Common::Vec3f gyro{};
+    Common::Vec3f rotation{};
+    Common::Vec3f euler{};
+    std::array<Common::Vec3f, 3> orientation{};
     bool is_at_rest{};
 };
 

src/hid_core/frontend/motion_input.cpp

@@ -26,19 +26,20 @@ void MotionInput::SetPID(f32 new_kp, f32 new_ki, f32 new_kd) {
     kd = new_kd;
 }
 
-void MotionInput::SetAcceleration(const Common::Vec<f32, 3>& acceleration) {
+void MotionInput::SetAcceleration(const Common::Vec3f& acceleration) {
     accel = acceleration;
-    accel[0] = std::clamp(accel[0], -AccelMaxValue, AccelMaxValue);
-    accel[1] = std::clamp(accel[1], -AccelMaxValue, AccelMaxValue);
-    accel[2] = std::clamp(accel[2], -AccelMaxValue, AccelMaxValue);
+
+    accel.x = std::clamp(accel.x, -AccelMaxValue, AccelMaxValue);
+    accel.y = std::clamp(accel.y, -AccelMaxValue, AccelMaxValue);
+    accel.z = std::clamp(accel.z, -AccelMaxValue, AccelMaxValue);
 }
 
-void MotionInput::SetGyroscope(const Common::Vec<f32, 3>& gyroscope) {
+void MotionInput::SetGyroscope(const Common::Vec3f& gyroscope) {
     gyro = gyroscope - gyro_bias;
 
-    gyro[0] = std::clamp(gyro[0], -GyroMaxValue, GyroMaxValue);
-    gyro[1] = std::clamp(gyro[1], -GyroMaxValue, GyroMaxValue);
-    gyro[2] = std::clamp(gyro[2], -GyroMaxValue, GyroMaxValue);
+    gyro.x = std::clamp(gyro.x, -GyroMaxValue, GyroMaxValue);
+    gyro.y = std::clamp(gyro.y, -GyroMaxValue, GyroMaxValue);
+    gyro.z = std::clamp(gyro.z, -GyroMaxValue, GyroMaxValue);
 
     // Auto adjust gyro_bias to minimize drift
     if (!IsMoving(IsAtRestRelaxed)) {
@@ -58,25 +59,25 @@ void MotionInput::SetGyroscope(const Common::Vec<f32, 3>& gyroscope) {
     }
 }
 
-void MotionInput::SetQuaternion(const Common::Vec<f32, 4>& quaternion) {
+void MotionInput::SetQuaternion(const Common::Quaternion<f32>& quaternion) {
     quat = quaternion;
 }
 
-void MotionInput::SetEulerAngles(const Common::Vec<f32, 3>& euler_angles) {
-    const float cr = std::cos(euler_angles[0] * 0.5f);
-    const float sr = std::sin(euler_angles[0] * 0.5f);
-    const float cp = std::cos(euler_angles[1] * 0.5f);
-    const float sp = std::sin(euler_angles[1] * 0.5f);
-    const float cy = std::cos(euler_angles[2] * 0.5f);
-    const float sy = std::sin(euler_angles[2] * 0.5f);
+void MotionInput::SetEulerAngles(const Common::Vec3f& euler_angles) {
+    const float cr = std::cos(euler_angles.x * 0.5f);
+    const float sr = std::sin(euler_angles.x * 0.5f);
+    const float cp = std::cos(euler_angles.y * 0.5f);
+    const float sp = std::sin(euler_angles.y * 0.5f);
+    const float cy = std::cos(euler_angles.z * 0.5f);
+    const float sy = std::sin(euler_angles.z * 0.5f);
 
-    quat[3] = cr * cp * cy + sr * sp * sy;
-    quat[0] = sr * cp * cy - cr * sp * sy;
-    quat[1] = cr * sp * cy + sr * cp * sy;
-    quat[2] = cr * cp * sy - sr * sp * cy;
+    quat.w = cr * cp * cy + sr * sp * sy;
+    quat.xyz.x = sr * cp * cy - cr * sp * sy;
+    quat.xyz.y = cr * sp * cy + sr * cp * sy;
+    quat.xyz.z = cr * cp * sy - sr * sp * cy;
 }
 
-void MotionInput::SetGyroBias(const Common::Vec<f32, 3>& bias) {
+void MotionInput::SetGyroBias(const Common::Vec3f& bias) {
     gyro_bias = bias;
 }
 
@@ -97,7 +98,7 @@ void MotionInput::ResetRotations() {
 }
 
 void MotionInput::ResetQuaternion() {
-    quat = Common::Vec<f32, 4>{0.0f, 0.0f, -1.0f, 0.0f};
+    quat = {{0.0f, 0.0f, -1.0f}, 0.0f};
 }
 
 bool MotionInput::IsMoving(f32 sensitivity) const {
@@ -136,10 +137,10 @@ void MotionInput::UpdateOrientation(u64 elapsed_time) {
         ResetOrientation();
     }
     // Short name local variable for readability
-    f32 q1 = quat[3];
-    f32 q2 = quat[0];
-    f32 q3 = quat[1];
-    f32 q4 = quat[2];
+    f32 q1 = quat.w;
+    f32 q2 = quat.xyz[0];
+    f32 q3 = quat.xyz[1];
+    f32 q4 = quat.xyz[2];
     const auto sample_period = static_cast<f32>(elapsed_time) / 1000000.0f;
 
     // Ignore invalid elapsed time
@@ -149,23 +150,23 @@ void MotionInput::UpdateOrientation(u64 elapsed_time) {
 
     const auto normal_accel = accel.Normalized();
     auto rad_gyro = gyro * std::numbers::pi_v<float> * 2.f;
-    const f32 swap = rad_gyro[0];
-    rad_gyro[0] = rad_gyro[1];
-    rad_gyro[1] = -swap;
-    rad_gyro[2] = -rad_gyro[2];
+    const f32 swap = rad_gyro.x;
+    rad_gyro.x = rad_gyro.y;
+    rad_gyro.y = -swap;
+    rad_gyro.z = -rad_gyro.z;
 
     // Clear gyro values if there is no gyro present
     if (only_accelerometer) {
-        rad_gyro[0] = 0;
-        rad_gyro[1] = 0;
-        rad_gyro[2] = 0;
+        rad_gyro.x = 0;
+        rad_gyro.y = 0;
+        rad_gyro.z = 0;
     }
 
     // Ignore drift correction if acceleration is not reliable
     if (accel.Length() >= 0.75f && accel.Length() <= 1.25f) {
-        const f32 ax = -normal_accel[0];
-        const f32 ay = normal_accel[1];
-        const f32 az = -normal_accel[2];
+        const f32 ax = -normal_accel.x;
+        const f32 ay = normal_accel.y;
+        const f32 az = -normal_accel.z;
 
         // Estimated direction of gravity
         const f32 vx = 2.0f * (q2 * q4 - q1 * q3);
@@ -173,7 +174,7 @@ void MotionInput::UpdateOrientation(u64 elapsed_time) {
         const f32 vz = q1 * q1 - q2 * q2 - q3 * q3 + q4 * q4;
 
         // Error is cross product between estimated direction and measured direction of gravity
-        const Common::Vec<f32, 3> new_real_error{
+        const Common::Vec3f new_real_error = {
             az * vx - ax * vz,
             ay * vz - az * vy,
             ax * vy - ay * vx,
@@ -201,16 +202,16 @@ void MotionInput::UpdateOrientation(u64 elapsed_time) {
             rad_gyro += 10.0f * kd * derivative_error;
 
             // Emulate gyro values for games that need them
-            gyro[0] = -rad_gyro[1];
-            gyro[1] = rad_gyro[0];
-            gyro[2] = -rad_gyro[2];
+            gyro.x = -rad_gyro.y;
+            gyro.y = rad_gyro.x;
+            gyro.z = -rad_gyro.z;
             UpdateRotation(elapsed_time);
         }
     }
 
-    const f32 gx = rad_gyro[1];
-    const f32 gy = rad_gyro[0];
-    const f32 gz = rad_gyro[2];
+    const f32 gx = rad_gyro.y;
+    const f32 gy = rad_gyro.x;
+    const f32 gz = rad_gyro.z;
 
     // Integrate rate of change of quaternion
     const f32 pa = q2;
@@ -221,58 +222,57 @@ void MotionInput::UpdateOrientation(u64 elapsed_time) {
     q3 = pb + (q1 * gy - pa * gz + pc * gx) * (0.5f * sample_period);
     q4 = pc + (q1 * gz + pa * gy - pb * gx) * (0.5f * sample_period);
 
-    quat[3] = q1;
-    quat[0] = q2;
-    quat[1] = q3;
-    quat[2] = q4;
+    quat.w = q1;
+    quat.xyz[0] = q2;
+    quat.xyz[1] = q3;
+    quat.xyz[2] = q4;
     quat = quat.Normalized();
 }
 
-std::array<Common::Vec<f32, 3>, 3> MotionInput::GetOrientation() const {
-    const Common::Vec<f32, 4> quad{
-        -quat[1],
-        -quat[0],
-        -quat[3],
-        -quat[2],
+std::array<Common::Vec3f, 3> MotionInput::GetOrientation() const {
+    const Common::Quaternion<float> quad{
+        .xyz = {-quat.xyz[1], -quat.xyz[0], -quat.w},
+        .w = -quat.xyz[2],
     };
-    const std::array<f32, 16> matrix4x4 = quad.ToMatrix();
-    return {Common::Vec<f32, 3>(matrix4x4[0], matrix4x4[1], -matrix4x4[2]),
-            Common::Vec<f32, 3>(matrix4x4[4], matrix4x4[5], -matrix4x4[6]),
-            Common::Vec<f32, 3>(-matrix4x4[8], -matrix4x4[9], matrix4x4[10])};
+    const std::array<float, 16> matrix4x4 = quad.ToMatrix();
+
+    return {Common::Vec3f(matrix4x4[0], matrix4x4[1], -matrix4x4[2]),
+            Common::Vec3f(matrix4x4[4], matrix4x4[5], -matrix4x4[6]),
+            Common::Vec3f(-matrix4x4[8], -matrix4x4[9], matrix4x4[10])};
 }
 
-Common::Vec<f32, 3> MotionInput::GetAcceleration() const {
+Common::Vec3f MotionInput::GetAcceleration() const {
     return accel;
 }
 
-Common::Vec<f32, 3> MotionInput::GetGyroscope() const {
+Common::Vec3f MotionInput::GetGyroscope() const {
     return gyro;
 }
 
-Common::Vec<f32, 3> MotionInput::GetGyroBias() const {
+Common::Vec3f MotionInput::GetGyroBias() const {
     return gyro_bias;
 }
 
-Common::Vec<f32, 4> MotionInput::GetQuaternion() const {
+Common::Quaternion<f32> MotionInput::GetQuaternion() const {
     return quat;
 }
 
-Common::Vec<f32, 3> MotionInput::GetRotations() const {
+Common::Vec3f MotionInput::GetRotations() const {
     return rotations;
 }
 
-Common::Vec<f32, 3> MotionInput::GetEulerAngles() const {
+Common::Vec3f MotionInput::GetEulerAngles() const {
     // roll (x-axis rotation)
-    const float sinr_cosp = 2 * (quat[3] * quat[0] + quat[1] * quat[2]);
-    const float cosr_cosp = 1 - 2 * (quat[0] * quat[0] + quat[1] * quat[1]);
+    const float sinr_cosp = 2 * (quat.w * quat.xyz.x + quat.xyz.y * quat.xyz.z);
+    const float cosr_cosp = 1 - 2 * (quat.xyz.x * quat.xyz.x + quat.xyz.y * quat.xyz.y);
 
     // pitch (y-axis rotation)
-    const float sinp = std::sqrt(1 + 2 * (quat[3] * quat[1] - quat[0] * quat[2]));
-    const float cosp = std::sqrt(1 - 2 * (quat[3] * quat[1] - quat[0] * quat[2]));
+    const float sinp = std::sqrt(1 + 2 * (quat.w * quat.xyz.y - quat.xyz.x * quat.xyz.z));
+    const float cosp = std::sqrt(1 - 2 * (quat.w * quat.xyz.y - quat.xyz.x * quat.xyz.z));
 
     // yaw (z-axis rotation)
-    const float siny_cosp = 2 * (quat[3] * quat[2] + quat[0] * quat[1]);
-    const float cosy_cosp = 1 - 2 * (quat[1] * quat[1] + quat[2] * quat[2]);
+    const float siny_cosp = 2 * (quat.w * quat.xyz.z + quat.xyz.x * quat.xyz.y);
+    const float cosy_cosp = 1 - 2 * (quat.xyz.y * quat.xyz.y + quat.xyz.z * quat.xyz.z);
 
     return {
         std::atan2(sinr_cosp, cosr_cosp),
@@ -285,13 +285,13 @@ void MotionInput::ResetOrientation() {
     if (!reset_enabled || only_accelerometer) {
         return;
     }
-    if (!IsMoving(IsAtRestRelaxed) && accel[2] <= -0.9f) {
+    if (!IsMoving(IsAtRestRelaxed) && accel.z <= -0.9f) {
         ++reset_counter;
         if (reset_counter > 900) {
-            quat[3] = 0;
-            quat[0] = 0;
-            quat[1] = 0;
-            quat[2] = -1;
+            quat.w = 0;
+            quat.xyz[0] = 0;
+            quat.xyz[1] = 0;
+            quat.xyz[2] = -1;
             SetOrientationFromAccelerometer();
             integral_error = {};
             reset_counter = 0;
@@ -309,15 +309,15 @@ void MotionInput::SetOrientationFromAccelerometer() {
 
     while (!IsCalibrated(0.01f) && ++iterations < 100) {
         // Short name local variable for readability
-        f32 q1 = quat[3];
-        f32 q2 = quat[0];
-        f32 q3 = quat[1];
-        f32 q4 = quat[2];
+        f32 q1 = quat.w;
+        f32 q2 = quat.xyz[0];
+        f32 q3 = quat.xyz[1];
+        f32 q4 = quat.xyz[2];
 
-        Common::Vec<f32, 3> rad_gyro;
-        const f32 ax = -normal_accel[0];
-        const f32 ay = normal_accel[1];
-        const f32 az = -normal_accel[2];
+        Common::Vec3f rad_gyro;
+        const f32 ax = -normal_accel.x;
+        const f32 ay = normal_accel.y;
+        const f32 az = -normal_accel.z;
 
         // Estimated direction of gravity
         const f32 vx = 2.0f * (q2 * q4 - q1 * q3);
@@ -325,7 +325,7 @@ void MotionInput::SetOrientationFromAccelerometer() {
         const f32 vz = q1 * q1 - q2 * q2 - q3 * q3 + q4 * q4;
 
         // Error is cross product between estimated direction and measured direction of gravity
-        const Common::Vec<f32, 3> new_real_error = {
+        const Common::Vec3f new_real_error = {
             az * vx - ax * vz,
             ay * vz - az * vy,
             ax * vy - ay * vx,
@@ -338,9 +338,9 @@ void MotionInput::SetOrientationFromAccelerometer() {
         rad_gyro += 5.0f * ki * integral_error;
         rad_gyro += 10.0f * kd * derivative_error;
 
-        const f32 gx = rad_gyro[1];
-        const f32 gy = rad_gyro[0];
-        const f32 gz = rad_gyro[2];
+        const f32 gx = rad_gyro.y;
+        const f32 gy = rad_gyro.x;
+        const f32 gz = rad_gyro.z;
 
         // Integrate rate of change of quaternion
         const f32 pa = q2;
@@ -351,10 +351,10 @@ void MotionInput::SetOrientationFromAccelerometer() {
         q3 = pb + (q1 * gy - pa * gz + pc * gx) * (0.5f * sample_period);
         q4 = pc + (q1 * gz + pa * gy - pb * gx) * (0.5f * sample_period);
 
-        quat[3] = q1;
-        quat[0] = q2;
-        quat[1] = q3;
-        quat[2] = q4;
+        quat.w = q1;
+        quat.xyz[0] = q2;
+        quat.xyz[1] = q3;
+        quat.xyz[2] = q4;
         quat = quat.Normalized();
     }
 }

src/hid_core/frontend/motion_input.h

@@ -1,12 +1,10 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #pragma once
 
 #include "common/common_types.h"
+#include "common/quaternion.h"
 #include "common/vector_math.h"
 
 namespace Core::HID {
@@ -36,11 +34,11 @@ public:
     MotionInput& operator=(MotionInput&&) = default;
 
     void SetPID(f32 new_kp, f32 new_ki, f32 new_kd);
-    void SetAcceleration(const Common::Vec<f32, 3>& acceleration);
-    void SetGyroscope(const Common::Vec<f32, 3>& gyroscope);
-    void SetQuaternion(const Common::Vec<f32, 4>& quaternion);
-    void SetEulerAngles(const Common::Vec<f32, 3>& euler_angles);
-    void SetGyroBias(const Common::Vec<f32, 3>& bias);
+    void SetAcceleration(const Common::Vec3f& acceleration);
+    void SetGyroscope(const Common::Vec3f& gyroscope);
+    void SetQuaternion(const Common::Quaternion<f32>& quaternion);
+    void SetEulerAngles(const Common::Vec3f& euler_angles);
+    void SetGyroBias(const Common::Vec3f& bias);
     void SetGyroThreshold(f32 threshold);
 
     /// Applies a modifier on top of the normal gyro threshold
@@ -55,13 +53,13 @@ public:
 
     void Calibrate();
 
-    [[nodiscard]] std::array<Common::Vec<f32, 3>, 3> GetOrientation() const;
-    [[nodiscard]] Common::Vec<f32, 3> GetAcceleration() const;
-    [[nodiscard]] Common::Vec<f32, 3> GetGyroscope() const;
-    [[nodiscard]] Common::Vec<f32, 3> GetGyroBias() const;
-    [[nodiscard]] Common::Vec<f32, 3> GetRotations() const;
-    [[nodiscard]] Common::Vec<f32, 4> GetQuaternion() const;
-    [[nodiscard]] Common::Vec<f32, 3> GetEulerAngles() const;
+    [[nodiscard]] std::array<Common::Vec3f, 3> GetOrientation() const;
+    [[nodiscard]] Common::Vec3f GetAcceleration() const;
+    [[nodiscard]] Common::Vec3f GetGyroscope() const;
+    [[nodiscard]] Common::Vec3f GetGyroBias() const;
+    [[nodiscard]] Common::Vec3f GetRotations() const;
+    [[nodiscard]] Common::Quaternion<f32> GetQuaternion() const;
+    [[nodiscard]] Common::Vec3f GetEulerAngles() const;
 
     [[nodiscard]] bool IsMoving(f32 sensitivity) const;
     [[nodiscard]] bool IsCalibrated(f32 sensitivity) const;
@@ -77,24 +75,24 @@ private:
     f32 kd;
 
     // PID errors
-    Common::Vec<f32, 3> real_error;
-    Common::Vec<f32, 3> integral_error;
-    Common::Vec<f32, 3> derivative_error;
+    Common::Vec3f real_error;
+    Common::Vec3f integral_error;
+    Common::Vec3f derivative_error;
 
     // Quaternion containing the device orientation
-    Common::Vec<f32, 4> quat;
+    Common::Quaternion<f32> quat;
 
     // Number of full rotations in each axis
-    Common::Vec<f32, 3> rotations;
+    Common::Vec3f rotations;
 
     // Acceleration vector measurement in G force
-    Common::Vec<f32, 3> accel;
+    Common::Vec3f accel;
 
     // Gyroscope vector measurement in radians/s.
-    Common::Vec<f32, 3> gyro;
+    Common::Vec3f gyro;
 
     // Vector to be subtracted from gyro measurements
-    Common::Vec<f32, 3> gyro_bias;
+    Common::Vec3f gyro_bias;
 
     // Minimum gyro amplitude to detect if the device is moving
     f32 gyro_threshold = 0.0f;

src/hid_core/hid_types.h

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -605,10 +602,10 @@ static_assert(sizeof(SixAxisSensorAttribute) == 4, "SixAxisSensorAttribute is an
 struct SixAxisSensorState {
     s64 delta_time{};
     s64 sampling_number{};
-    Common::Vec<f32, 3> accel{};
-    Common::Vec<f32, 3> gyro{};
-    Common::Vec<f32, 3> rotation{};
-    std::array<Common::Vec<f32, 3>, 3> orientation{};
+    Common::Vec3f accel{};
+    Common::Vec3f gyro{};
+    Common::Vec3f rotation{};
+    std::array<Common::Vec3f, 3> orientation{};
     SixAxisSensorAttribute attribute{};
     INSERT_PADDING_BYTES(4); // Reserved
 };

src/hid_core/resources/shared_memory_format.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -196,7 +196,7 @@ struct ConsoleSixAxisSensorSharedMemoryFormat {
     bool is_seven_six_axis_sensor_at_rest{};
     INSERT_PADDING_BYTES(3); // padding
     f32 verticalization_error{};
-    Common::Vec<f32, 3> gyro_bias{};
+    Common::Vec3f gyro_bias{};
     INSERT_PADDING_BYTES(4); // padding
 };
 static_assert(sizeof(ConsoleSixAxisSensorSharedMemoryFormat) == 0x20,

src/hid_core/resources/six_axis/seven_six_axis.cpp

@@ -46,11 +46,14 @@ void SevenSixAxis::OnUpdate(const Core::Timing::CoreTiming& core_timing) {
     next_seven_sixaxis_state.accel = motion_status.accel;
     next_seven_sixaxis_state.gyro = motion_status.gyro;
     next_seven_sixaxis_state.quaternion = {
-        motion_status.quaternion[1],
-        motion_status.quaternion[0],
-        -motion_status.quaternion[3],
-        -motion_status.quaternion[2],
+        {
+            motion_status.quaternion.xyz.y,
+            motion_status.quaternion.xyz.x,
+            -motion_status.quaternion.w,
+        },
+        -motion_status.quaternion.xyz.z,
     };
+
     seven_sixaxis_lifo.WriteNextEntry(next_seven_sixaxis_state);
     transfer_memory_owner->GetMemory().WriteBlock(transfer_memory, &seven_sixaxis_lifo,
                                                   sizeof(seven_sixaxis_lifo));

src/hid_core/resources/six_axis/seven_six_axis.h

@@ -7,7 +7,7 @@
 #pragma once
 
 #include "common/common_types.h"
-#include "common/vector_math.h"
+#include "common/quaternion.h"
 #include "common/typed_address.h"
 #include "hid_core/resources/controller_base.h"
 #include "hid_core/resources/ring_lifo.h"
@@ -51,9 +51,9 @@ private:
         u64 timestamp{};
         u64 sampling_number{};
         u64 unknown{};
-        Common::Vec<f32, 3> accel{};
-        Common::Vec<f32, 3> gyro{};
-        Common::Vec<f32, 4> quaternion{};
+        Common::Vec3f accel{};
+        Common::Vec3f gyro{};
+        Common::Quaternion<f32> quaternion{};
     };
     static_assert(sizeof(SevenSixAxisState) == 0x48, "SevenSixAxisState is an invalid size");
 

src/hid_core/resources/six_axis/six_axis.cpp

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
@@ -96,9 +93,9 @@ void SixAxis::OnUpdate(const Core::Timing::CoreTiming& core_timing) {
                     .accel = {0, 0, -1.0f},
                     .orientation =
                         {
-                            Common::Vec<f32, 3>{1.0f, 0, 0},
-                            Common::Vec<f32, 3>{0, 1.0f, 0},
-                            Common::Vec<f32, 3>{0, 0, 1.0f},
+                            Common::Vec3f{1.0f, 0, 0},
+                            Common::Vec3f{0, 1.0f, 0},
+                            Common::Vec3f{0, 0, 1.0f},
                         },
                     .attribute = {1},
                 };

src/input_common/drivers/mouse.cpp

@@ -88,8 +88,8 @@ void Mouse::UpdateStickInput() {
         last_mouse_change *= maximum_stick_range;
     }
 
-    SetAxis(identifier, mouse_axis_x, last_mouse_change[0]);
-    SetAxis(identifier, mouse_axis_y, -last_mouse_change[1]);
+    SetAxis(identifier, mouse_axis_x, last_mouse_change.x);
+    SetAxis(identifier, mouse_axis_y, -last_mouse_change.y);
 
     // Decay input over time
     const float clamped_length = (std::min)(1.0f, length);
@@ -104,20 +104,20 @@ void Mouse::UpdateMotionInput() {
     const float sensitivity =
         IsMousePanningEnabled() ? default_motion_panning_sensitivity : default_motion_sensitivity;
 
-    const float rotation_velocity = std::sqrt(last_motion_change[0] * last_motion_change[0] +
-                                              last_motion_change[1] * last_motion_change[1]);
+    const float rotation_velocity = std::sqrt(last_motion_change.x * last_motion_change.x +
+                                              last_motion_change.y * last_motion_change.y);
 
     // Clamp rotation speed
     if (rotation_velocity > maximum_rotation_speed / sensitivity) {
         const float multiplier = maximum_rotation_speed / rotation_velocity / sensitivity;
-        last_motion_change[0] = last_motion_change[0] * multiplier;
-        last_motion_change[1] = last_motion_change[1] * multiplier;
+        last_motion_change.x = last_motion_change.x * multiplier;
+        last_motion_change.y = last_motion_change.y * multiplier;
     }
 
     const BasicMotion motion_data{
-        .gyro_x = last_motion_change[0] * sensitivity,
-        .gyro_y = last_motion_change[1] * sensitivity,
-        .gyro_z = last_motion_change[2] * sensitivity,
+        .gyro_x = last_motion_change.x * sensitivity,
+        .gyro_y = last_motion_change.y * sensitivity,
+        .gyro_z = last_motion_change.z * sensitivity,
         .accel_x = 0,
         .accel_y = 0,
         .accel_z = 0,
@@ -125,46 +125,53 @@ void Mouse::UpdateMotionInput() {
     };
 
     if (IsMousePanningEnabled()) {
-        last_motion_change[0] = 0;
-        last_motion_change[1] = 0;
+        last_motion_change.x = 0;
+        last_motion_change.y = 0;
     }
-    last_motion_change[2] = 0;
+    last_motion_change.z = 0;
 
     SetMotion(motion_identifier, 0, motion_data);
 }
 
 void Mouse::Move(int x, int y, int center_x, int center_y) {
     if (IsMousePanningEnabled()) {
-        auto const mouse_change_int = Common::Vec<int, 2>(x, y) - Common::Vec<int, 2>(center_x, center_y);
-        auto const mouse_change = Common::Vec<float, 2>(float(mouse_change_int[0]), float(mouse_change_int[1]));
-        auto const x_sensitivity = Settings::values.mouse_panning_x_sensitivity.GetValue() * default_panning_sensitivity;
-        auto const y_sensitivity = Settings::values.mouse_panning_y_sensitivity.GetValue() * default_panning_sensitivity;
-        auto const deadzone_cw = Settings::values.mouse_panning_deadzone_counterweight.GetValue() * default_deadzone_counterweight;
-        last_motion_change += {-mouse_change[1] * x_sensitivity, -mouse_change[0] * y_sensitivity, 0};
-        last_mouse_change[0] += mouse_change[0] * x_sensitivity;
-        last_mouse_change[1] += mouse_change[1] * y_sensitivity;
-        // Bind the mouse change to [0 <= deadzone_cw <= 1.0]
+        const auto mouse_change =
+            (Common::MakeVec(x, y) - Common::MakeVec(center_x, center_y)).Cast<float>();
+        const float x_sensitivity =
+            Settings::values.mouse_panning_x_sensitivity.GetValue() * default_panning_sensitivity;
+        const float y_sensitivity =
+            Settings::values.mouse_panning_y_sensitivity.GetValue() * default_panning_sensitivity;
+        const float deadzone_counterweight =
+            Settings::values.mouse_panning_deadzone_counterweight.GetValue() *
+            default_deadzone_counterweight;
+
+        last_motion_change += {-mouse_change.y * x_sensitivity, -mouse_change.x * y_sensitivity, 0};
+        last_mouse_change.x += mouse_change.x * x_sensitivity;
+        last_mouse_change.y += mouse_change.y * y_sensitivity;
+
+        // Bind the mouse change to [0 <= deadzone_counterweight <= 1.0]
         const float length = last_mouse_change.Length();
-        if (length < deadzone_cw && length != 0.0f) {
+        if (length < deadzone_counterweight && length != 0.0f) {
             last_mouse_change /= length;
-            last_mouse_change *= deadzone_cw;
+            last_mouse_change *= deadzone_counterweight;
         }
+
         return;
     }
 
     if (button_pressed) {
-        const auto mouse_move = Common::Vec<int, 2>(x, y) - mouse_origin;
+        const auto mouse_move = Common::MakeVec<int>(x, y) - mouse_origin;
         const float x_sensitivity =
             Settings::values.mouse_panning_x_sensitivity.GetValue() * default_stick_sensitivity;
         const float y_sensitivity =
             Settings::values.mouse_panning_y_sensitivity.GetValue() * default_stick_sensitivity;
-        SetAxis(identifier, mouse_axis_x, float(mouse_move[0]) * x_sensitivity);
-        SetAxis(identifier, mouse_axis_y, float(-mouse_move[1]) * y_sensitivity);
+        SetAxis(identifier, mouse_axis_x, static_cast<float>(mouse_move.x) * x_sensitivity);
+        SetAxis(identifier, mouse_axis_y, static_cast<float>(-mouse_move.y) * y_sensitivity);
 
         last_motion_change = {
-            float(-mouse_move[1]) * x_sensitivity,
-            float(-mouse_move[0]) * y_sensitivity,
-            last_motion_change[2],
+            static_cast<float>(-mouse_move.y) * x_sensitivity,
+            static_cast<float>(-mouse_move.x) * y_sensitivity,
+            last_motion_change.z,
         };
     }
 }
@@ -213,18 +220,18 @@ void Mouse::ReleaseButton(MouseButton button) {
         SetAxis(identifier, mouse_axis_y, 0);
     }
 
-    last_motion_change[0] = 0;
-    last_motion_change[1] = 0;
+    last_motion_change.x = 0;
+    last_motion_change.y = 0;
 
     button_pressed = false;
 }
 
 void Mouse::MouseWheelChange(int x, int y) {
-    wheel_position[0] += x;
-    wheel_position[1] += y;
-    last_motion_change[2] += static_cast<f32>(y);
-    SetAxis(identifier, wheel_axis_x, static_cast<f32>(wheel_position[0]));
-    SetAxis(identifier, wheel_axis_y, static_cast<f32>(wheel_position[1]));
+    wheel_position.x += x;
+    wheel_position.y += y;
+    last_motion_change.z += static_cast<f32>(y);
+    SetAxis(identifier, wheel_axis_x, static_cast<f32>(wheel_position.x));
+    SetAxis(identifier, wheel_axis_y, static_cast<f32>(wheel_position.y));
 }
 
 void Mouse::ReleaseAllButtons() {

src/input_common/drivers/mouse.h

@@ -107,11 +107,11 @@ private:
 
     Common::Input::ButtonNames GetUIButtonName(const Common::ParamPackage& params) const;
 
-    Common::Vec<int, 2> mouse_origin;
-    Common::Vec<int, 2> last_mouse_position;
-    Common::Vec<float, 2> last_mouse_change;
-    Common::Vec<float, 3> last_motion_change;
-    Common::Vec<int, 2> wheel_position;
+    Common::Vec2<int> mouse_origin;
+    Common::Vec2<int> last_mouse_position;
+    Common::Vec2<float> last_mouse_change;
+    Common::Vec3<float> last_motion_change;
+    Common::Vec2<int> wheel_position;
     bool button_pressed = false;
 };
 

src/shader_recompiler/backend/glsl/emit_glsl.cpp

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -29,7 +32,7 @@ struct FuncTraits<ReturnType_ (*)(Args...)> {
 };
 
 template <auto func, typename... Args>
-void SetDefinition(EmitContext& ctx, IR::Inst* inst, Args... args) {
+[[maybe_unused]] void SetDefinition(EmitContext& ctx, IR::Inst* inst, Args... args) {
     inst->SetDefinition<Id>(func(ctx, std::forward<Args>(args)...));
 }
 

src/shader_recompiler/backend/spirv/emit_spirv.cpp

@@ -492,6 +492,9 @@ void SetupCapabilities(const Profile& profile, const Info& info, EmitContext& ct
         if (ctx.uses_nonuniform_storage_texel_buffer) {
             ctx.AddCapability(spv::Capability::StorageTexelBufferArrayNonUniformIndexing);
         }
+        if (ctx.uses_nonuniform_storage_buffer) {
+            ctx.AddCapability(spv::Capability::StorageBufferArrayNonUniformIndexing);
+        }
     }
 }
 

src/shader_recompiler/backend/spirv/emit_spirv_atomic.cpp

@@ -4,8 +4,6 @@
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <bit>
-
 #include "shader_recompiler/backend/spirv/emit_spirv.h"
 #include "shader_recompiler/backend/spirv/emit_spirv_instructions.h"
 #include "shader_recompiler/backend/spirv/spirv_emit_context.h"
@@ -23,29 +21,13 @@ Id SharedPointer(EmitContext& ctx, Id offset, u32 index_offset = 0) {
                : ctx.OpAccessChain(ctx.shared_u32, ctx.shared_memory_u32, index);
 }
 
-Id StorageIndex(EmitContext& ctx, const IR::Value& offset, size_t element_size) {
-    if (offset.IsImmediate()) {
-        const u32 imm_offset{static_cast<u32>(offset.U32() / element_size)};
-        return ctx.Const(imm_offset);
-    }
-    const u32 shift{static_cast<u32>(std::countr_zero(element_size))};
-    const Id index{ctx.Def(offset)};
-    if (shift == 0) {
-        return index;
-    }
-    const Id shift_id{ctx.Const(shift)};
-    return ctx.OpShiftRightLogical(ctx.U32[1], index, shift_id);
-}
-
 Id StoragePointer(EmitContext& ctx, const StorageTypeDefinition& type_def,
                   Id StorageDefinitions::*member_ptr, const IR::Value& binding,
                   const IR::Value& offset, size_t element_size) {
     if (!binding.IsImmediate()) {
         throw NotImplementedException("Dynamic storage buffer indexing");
     }
-    const Id ssbo{ctx.ssbos[binding.U32()].*member_ptr};
-    const Id index{StorageIndex(ctx, offset, element_size)};
-    return ctx.OpAccessChain(type_def.element, ssbo, ctx.u32_zero_value, index);
+    return ctx.StoragePointer(binding.U32(), ctx.Def(offset), type_def, static_cast<u32>(element_size), member_ptr);
 }
 
 std::pair<Id, Id> AtomicArgs(EmitContext& ctx) {
@@ -216,16 +198,14 @@ Id EmitStorageAtomicUMax32(EmitContext& ctx, const IR::Value& binding, const IR:
 
 Id EmitStorageAtomicInc32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                           Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    return ctx.OpFunctionCall(ctx.U32[1], ctx.increment_cas_ssbo, base_index, value, ssbo);
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    return ctx.OpFunctionCall(ctx.U32[1], ctx.increment_cas_ssbo, pointer, value);
 }
 
 Id EmitStorageAtomicDec32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                           Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    return ctx.OpFunctionCall(ctx.U32[1], ctx.decrement_cas_ssbo, base_index, value, ssbo);
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    return ctx.OpFunctionCall(ctx.U32[1], ctx.decrement_cas_ssbo, pointer, value);
 }
 
 Id EmitStorageAtomicAnd32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
@@ -364,56 +344,49 @@ Id EmitStorageAtomicExchange32x2(EmitContext& ctx, const IR::Value& binding,
 
 Id EmitStorageAtomicAddF32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                            Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    return ctx.OpFunctionCall(ctx.F32[1], ctx.f32_add_cas, base_index, value, ssbo);
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    return ctx.OpFunctionCall(ctx.F32[1], ctx.f32_add_cas, pointer, value);
 }
 
 Id EmitStorageAtomicAddF16x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                              Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    const Id result{ctx.OpFunctionCall(ctx.F16[2], ctx.f16x2_add_cas, base_index, value, ssbo)};
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    const Id result{ctx.OpFunctionCall(ctx.F16[2], ctx.f16x2_add_cas, pointer, value)};
     return ctx.OpBitcast(ctx.U32[1], result);
 }
 
 Id EmitStorageAtomicAddF32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                              Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    const Id result{ctx.OpFunctionCall(ctx.F32[2], ctx.f32x2_add_cas, base_index, value, ssbo)};
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    const Id result{ctx.OpFunctionCall(ctx.F32[2], ctx.f32x2_add_cas, pointer, value)};
     return ctx.OpPackHalf2x16(ctx.U32[1], result);
 }
 
 Id EmitStorageAtomicMinF16x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                              Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    const Id result{ctx.OpFunctionCall(ctx.F16[2], ctx.f16x2_min_cas, base_index, value, ssbo)};
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    const Id result{ctx.OpFunctionCall(ctx.F16[2], ctx.f16x2_min_cas, pointer, value)};
     return ctx.OpBitcast(ctx.U32[1], result);
 }
 
 Id EmitStorageAtomicMinF32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                              Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    const Id result{ctx.OpFunctionCall(ctx.F32[2], ctx.f32x2_min_cas, base_index, value, ssbo)};
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    const Id result{ctx.OpFunctionCall(ctx.F32[2], ctx.f32x2_min_cas, pointer, value)};
     return ctx.OpPackHalf2x16(ctx.U32[1], result);
 }
 
 Id EmitStorageAtomicMaxF16x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                              Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    const Id result{ctx.OpFunctionCall(ctx.F16[2], ctx.f16x2_max_cas, base_index, value, ssbo)};
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    const Id result{ctx.OpFunctionCall(ctx.F16[2], ctx.f16x2_max_cas, pointer, value)};
     return ctx.OpBitcast(ctx.U32[1], result);
 }
 
 Id EmitStorageAtomicMaxF32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                              Id value) {
-    const Id ssbo{ctx.ssbos[binding.U32()].U32};
-    const Id base_index{StorageIndex(ctx, offset, sizeof(u32))};
-    const Id result{ctx.OpFunctionCall(ctx.F32[2], ctx.f32x2_max_cas, base_index, value, ssbo)};
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32, &StorageDefinitions::U32, binding, offset, sizeof(u32))};
+    const Id result{ctx.OpFunctionCall(ctx.F32[2], ctx.f32x2_max_cas, pointer, value)};
     return ctx.OpPackHalf2x16(ctx.U32[1], result);
 }
 

src/shader_recompiler/backend/spirv/emit_spirv_memory.cpp

@@ -4,46 +4,33 @@
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <bit>
-
 #include "shader_recompiler/backend/spirv/emit_spirv.h"
 #include "shader_recompiler/backend/spirv/emit_spirv_instructions.h"
 #include "shader_recompiler/backend/spirv/spirv_emit_context.h"
 
 namespace Shader::Backend::SPIRV {
 namespace {
-Id StorageIndex(EmitContext& ctx, const IR::Value& offset, size_t element_size,
-                u32 index_offset = 0) {
-    if (offset.IsImmediate()) {
-        const u32 imm_offset{static_cast<u32>(offset.U32() / element_size) + index_offset};
-        return ctx.Const(imm_offset);
-    }
-    const u32 shift{static_cast<u32>(std::countr_zero(element_size))};
-    Id index{ctx.Def(offset)};
-    if (shift != 0) {
-        const Id shift_id{ctx.Const(shift)};
-        index = ctx.OpShiftRightLogical(ctx.U32[1], index, shift_id);
-    }
+Id StorageByteOffset(EmitContext& ctx, const IR::Value& offset, size_t element_size, u32 index_offset) {
+    Id byte_offset{ctx.Def(offset)};
     if (index_offset != 0) {
-        index = ctx.OpIAdd(ctx.U32[1], index, ctx.Const(index_offset));
+        byte_offset = ctx.OpIAdd(ctx.U32[1], byte_offset, ctx.Const(static_cast<u32>(index_offset * element_size)));
     }
-    return index;
+    return byte_offset;
 }
 
 Id StoragePointer(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                   const StorageTypeDefinition& type_def, size_t element_size,
-                  Id StorageDefinitions::*member_ptr, u32 index_offset = 0) {
+                  Id StorageDefinitions::* member_ptr, u32 index_offset = 0) {
     if (!binding.IsImmediate()) {
         throw NotImplementedException("Dynamic storage buffer indexing");
     }
-    const Id ssbo{ctx.ssbos[binding.U32()].*member_ptr};
-    const Id index{StorageIndex(ctx, offset, element_size, index_offset)};
-    return ctx.OpAccessChain(type_def.element, ssbo, ctx.u32_zero_value, index);
+    const Id byte_offset{StorageByteOffset(ctx, offset, element_size, index_offset)};
+    return ctx.StoragePointer(binding.U32(), byte_offset, type_def, static_cast<u32>(element_size), member_ptr);
 }
 
 Id LoadStorage(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset, Id result_type,
                const StorageTypeDefinition& type_def, size_t element_size,
-               Id StorageDefinitions::*member_ptr, u32 index_offset = 0) {
+               Id StorageDefinitions::* member_ptr, u32 index_offset = 0) {
     const Id pointer{
         StoragePointer(ctx, binding, offset, type_def, element_size, member_ptr, index_offset)};
     return ctx.OpLoad(result_type, pointer);
@@ -57,7 +44,7 @@ Id LoadStorage32(EmitContext& ctx, const IR::Value& binding, const IR::Value& of
 
 void WriteStorage(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset, Id value,
                   const StorageTypeDefinition& type_def, size_t element_size,
-                  Id StorageDefinitions::*member_ptr, u32 index_offset = 0) {
+                  Id StorageDefinitions::* member_ptr, u32 index_offset = 0) {
     const Id pointer{
         StoragePointer(ctx, binding, offset, type_def, element_size, member_ptr, index_offset)};
     ctx.OpStore(pointer, value);

src/shader_recompiler/backend/spirv/spirv_emit_context.cpp

@@ -299,7 +299,7 @@ void DefineConstBuffers(EmitContext& ctx, const Info& info, Id UniformDefinition
 }
 
 void DefineSsbos(EmitContext& ctx, StorageTypeDefinition& type_def,
-                 Id StorageDefinitions::*member_type, const Info& info, u32 binding, Id type,
+                 Id StorageDefinitions::* member_type, const Info& info, u32 binding, Id type,
                  u32 stride) {
     const Id array_type{ctx.TypeRuntimeArray(type)};
     ctx.Decorate(array_type, spv::Decoration::ArrayStride, stride);
@@ -309,23 +309,27 @@ void DefineSsbos(EmitContext& ctx, StorageTypeDefinition& type_def,
     ctx.MemberDecorate(struct_type, 0, spv::Decoration::Offset, 0U);
 
     const Id struct_pointer{ctx.TypePointer(spv::StorageClass::StorageBuffer, struct_type)};
-    type_def.array = struct_pointer;
     type_def.element = ctx.TypePointer(spv::StorageClass::StorageBuffer, type);
 
     u32 index{};
     for (const StorageBufferDescriptor& desc : info.storage_buffers_descriptors) {
-        const Id id{ctx.AddGlobalVariable(struct_pointer, spv::StorageClass::StorageBuffer)};
+        const Id variable_type{[&] {
+            if (desc.count == 1) {
+                return struct_pointer;
+            }
+            const Id descriptor_array{ctx.TypeArray(struct_type, ctx.Const(desc.count))};
+            return ctx.TypePointer(spv::StorageClass::StorageBuffer, descriptor_array);
+        }()};
+        const Id id{ctx.AddGlobalVariable(variable_type, spv::StorageClass::StorageBuffer)};
         ctx.Decorate(id, spv::Decoration::Binding, binding);
         ctx.Decorate(id, spv::Decoration::DescriptorSet, 0U);
         ctx.Name(id, fmt::format("ssbo{}", index));
         if (ctx.profile.supported_spirv >= 0x00010400) {
             ctx.interfaces.push_back(id);
         }
-        for (size_t i = 0; i < desc.count; ++i) {
-            ctx.ssbos[index + i].*member_type = id;
-        }
-        index += desc.count;
-        binding += desc.count;
+        ctx.ssbos[index].*member_type = id;
+        ++index;
+        ++binding;
     }
 }
 
@@ -368,8 +372,7 @@ Id CasFunction(EmitContext& ctx, Operation operation, Id value_type) {
     return func;
 }
 
-Id CasLoop(EmitContext& ctx, Operation operation, Id array_pointer, Id element_pointer,
-           Id value_type, Id memory_type, spv::Scope scope) {
+Id CasLoop(EmitContext& ctx, Operation operation, Id element_pointer, Id value_type, Id memory_type, spv::Scope scope) {
     const bool is_shared{scope == spv::Scope::Workgroup};
     const bool is_struct{!is_shared || ctx.uses_explicit_workgroup_layout};
     const Id cas_func{CasFunction(ctx, operation, value_type)};
@@ -379,14 +382,12 @@ Id CasLoop(EmitContext& ctx, Operation operation, Id array_pointer, Id element_p
     const Id loop_header{ctx.OpLabel()};
     const Id continue_block{ctx.OpLabel()};
     const Id merge_block{ctx.OpLabel()};
-    const Id func_type{is_shared
-                           ? ctx.TypeFunction(value_type, ctx.U32[1], value_type)
-                           : ctx.TypeFunction(value_type, ctx.U32[1], value_type, array_pointer)};
+    const Id func_type{is_shared ? ctx.TypeFunction(value_type, ctx.U32[1], value_type)
+                                 : ctx.TypeFunction(value_type, element_pointer, value_type)};
 
     const Id func{ctx.OpFunction(value_type, spv::FunctionControlMask::MaskNone, func_type)};
-    const Id index{ctx.OpFunctionParameter(ctx.U32[1])};
+    const Id address{ctx.OpFunctionParameter(is_shared ? ctx.U32[1] : element_pointer)};
     const Id op_b{ctx.OpFunctionParameter(value_type)};
-    const Id base{is_shared ? ctx.shared_memory_u32 : ctx.OpFunctionParameter(array_pointer)};
     ctx.AddLabel();
     ctx.OpBranch(loop_header);
     ctx.AddLabel(loop_header);
@@ -395,8 +396,13 @@ Id CasLoop(EmitContext& ctx, Operation operation, Id array_pointer, Id element_p
     ctx.OpBranch(continue_block);
 
     ctx.AddLabel(continue_block);
-    const Id word_pointer{is_struct ? ctx.OpAccessChain(element_pointer, base, zero, index)
-                                    : ctx.OpAccessChain(element_pointer, base, index)};
+    const Id word_pointer{[&] {
+        if (!is_shared) {
+            return address;
+        }
+        return is_struct ? ctx.OpAccessChain(element_pointer, ctx.shared_memory_u32, zero, address)
+                         : ctx.OpAccessChain(element_pointer, ctx.shared_memory_u32, address);
+    }()};
     if (value_type.value == ctx.F32[2].value) {
         const Id u32_value{ctx.OpLoad(ctx.U32[1], word_pointer)};
         const Id value{ctx.OpUnpackHalf2x16(ctx.F32[2], u32_value)};
@@ -480,6 +486,7 @@ EmitContext::EmitContext(const Profile& profile_, const RuntimeInfo& runtime_inf
     DefineSharedMemoryFunctions(program);
     DefineConstantBuffers(program.info, uniform_binding);
     DefineConstantBufferIndirectFunctions(program.info);
+    DefineStorageBufferMappings(program.info, storage_binding);
     DefineStorageBuffers(program.info, storage_binding);
     DefineTextureBuffers(program.info, texture_binding);
     DefineImageBuffers(program.info, image_binding);
@@ -532,6 +539,36 @@ Id EmitContext::BitOffset16(const IR::Value& offset) {
     return OpBitwiseAnd(U32[1], OpShiftLeftLogical(U32[1], Def(offset), Const(3u)), Const(16u));
 }
 
+Id EmitContext::StoragePointer(u32 binding, Id byte_offset, const StorageTypeDefinition& type_def,
+                               u32 element_size, Id StorageDefinitions::* member_ptr) {
+    const Id ssbo{ssbos[binding].*member_ptr};
+    const u32 segment_count{storage_buffer_mapping_counts[binding]};
+    if (segment_count <= 1) {
+        const Id index{
+            element_size == 1
+                ? byte_offset
+                : OpShiftRightLogical(U32[1], byte_offset, Const(static_cast<u32>(std::countr_zero(element_size))))};
+        return OpAccessChain(type_def.element, ssbo, u32_zero_value, index);
+    }
+
+    const Id mapped{OpFunctionCall(U32[2], storage_buffer_map_func,
+                                   Const(storage_buffer_mapping_bases[binding]),
+                                   Const(segment_count), byte_offset)};
+    const Id segment{OpCompositeExtract(U32[1], mapped, 0U)};
+    const Id local_offset{OpCompositeExtract(U32[1], mapped, 1U)};
+    const Id index{
+        element_size == 1
+            ? local_offset
+            : OpShiftRightLogical(U32[1], local_offset, Const(static_cast<u32>(std::countr_zero(element_size))))};
+    Decorate(segment, spv::Decoration::NonUniform);
+    non_uniform_ids.insert(segment.value);
+    const Id pointer{OpAccessChain(type_def.element, ssbo, segment, u32_zero_value, index)};
+    Decorate(pointer, spv::Decoration::NonUniform);
+    non_uniform_ids.insert(pointer.value);
+    uses_nonuniform_storage_buffer = true;
+    return pointer;
+}
+
 void EmitContext::DefineCommonTypes(const Info& info) {
     void_id = TypeVoid();
 
@@ -696,12 +733,10 @@ void EmitContext::DefineSharedMemory(const IR::Program& program) {
 
 void EmitContext::DefineSharedMemoryFunctions(const IR::Program& program) {
     if (program.info.uses_shared_increment) {
-        increment_cas_shared = CasLoop(*this, Operation::Increment, shared_memory_u32_type,
-                                       shared_u32, U32[1], U32[1], spv::Scope::Workgroup);
+        increment_cas_shared = CasLoop(*this, Operation::Increment, shared_u32, U32[1], U32[1], spv::Scope::Workgroup);
     }
     if (program.info.uses_shared_decrement) {
-        decrement_cas_shared = CasLoop(*this, Operation::Decrement, shared_memory_u32_type,
-                                       shared_u32, U32[1], U32[1], spv::Scope::Workgroup);
+        decrement_cas_shared = CasLoop(*this, Operation::Decrement, shared_u32, U32[1], U32[1], spv::Scope::Workgroup);
     }
 }
 
@@ -945,8 +980,7 @@ void EmitContext::DefineGlobalMemoryFunctions(const Info& info) {
     }
     using DefPtr = Id StorageDefinitions::*;
     const Id zero{u32_zero_value};
-    const auto define_body{[&](DefPtr ssbo_member, Id addr, Id element_pointer, u32 shift,
-                               auto&& callback) {
+    const auto define_body{[&](DefPtr ssbo_member, Id addr, const StorageTypeDefinition& type_def, u32 shift, auto&& callback) {
         AddLabel();
         const size_t num_buffers{info.storage_buffers_descriptors.size()};
         for (size_t index = 0; index < num_buffers; ++index) {
@@ -973,30 +1007,28 @@ void EmitContext::DefineGlobalMemoryFunctions(const Info& info) {
             OpSelectionMerge(else_label, spv::SelectionControlMask::MaskNone);
             OpBranchConditional(cond, then_label, else_label);
             AddLabel(then_label);
-            const Id ssbo_id{ssbos[index].*ssbo_member};
             const Id ssbo_offset{OpUConvert(U32[1], OpISub(U64, addr, ssbo_addr))};
-            const Id ssbo_index{OpShiftRightLogical(U32[1], ssbo_offset, Const(shift))};
-            const Id ssbo_pointer{OpAccessChain(element_pointer, ssbo_id, zero, ssbo_index)};
+            const Id ssbo_pointer{StoragePointer(static_cast<u32>(index), ssbo_offset, type_def, 1U << shift, ssbo_member)};
             callback(ssbo_pointer);
             AddLabel(else_label);
         }
     }};
-    const auto define_load{[&](DefPtr ssbo_member, Id element_pointer, Id type, u32 shift) {
-        const Id function_type{TypeFunction(type, U64)};
-        const Id func_id{OpFunction(type, spv::FunctionControlMask::MaskNone, function_type)};
-        const Id addr{OpFunctionParameter(U64)};
-        define_body(ssbo_member, addr, element_pointer, shift,
-                    [&](Id ssbo_pointer) { OpReturnValue(OpLoad(type, ssbo_pointer)); });
-        OpReturnValue(ConstantNull(type));
-        OpFunctionEnd();
-        return func_id;
-    }};
-    const auto define_write{[&](DefPtr ssbo_member, Id element_pointer, Id type, u32 shift) {
+    const auto define_load{
+        [&](DefPtr ssbo_member, const StorageTypeDefinition& type_def, Id type, u32 shift) {
+            const Id function_type{TypeFunction(type, U64)};
+            const Id func_id{OpFunction(type, spv::FunctionControlMask::MaskNone, function_type)};
+            const Id addr{OpFunctionParameter(U64)};
+            define_body(ssbo_member, addr, type_def, shift, [&](Id ssbo_pointer) { OpReturnValue(OpLoad(type, ssbo_pointer)); });
+            OpReturnValue(ConstantNull(type));
+            OpFunctionEnd();
+            return func_id;
+        }};
+    const auto define_write{[&](DefPtr ssbo_member, const StorageTypeDefinition& type_def, Id type, u32 shift) {
         const Id function_type{TypeFunction(void_id, U64, type)};
         const Id func_id{OpFunction(void_id, spv::FunctionControlMask::MaskNone, function_type)};
         const Id addr{OpFunctionParameter(U64)};
         const Id data{OpFunctionParameter(type)};
-        define_body(ssbo_member, addr, element_pointer, shift, [&](Id ssbo_pointer) {
+        define_body(ssbo_member, addr, type_def, shift, [&](Id ssbo_pointer) {
             OpStore(ssbo_pointer, data);
             OpReturn();
         });
@@ -1006,10 +1038,9 @@ void EmitContext::DefineGlobalMemoryFunctions(const Info& info) {
     }};
     const auto define{
         [&](DefPtr ssbo_member, const StorageTypeDefinition& type_def, Id type, size_t size) {
-            const Id element_type{type_def.element};
             const u32 shift{static_cast<u32>(std::countr_zero(size))};
-            const Id load_func{define_load(ssbo_member, element_type, type, shift)};
-            const Id write_func{define_write(ssbo_member, element_type, type, shift)};
+            const Id load_func{define_load(ssbo_member, type_def, type, shift)};
+            const Id write_func{define_write(ssbo_member, type_def, type, shift)};
             return std::make_pair(load_func, write_func);
         }};
     std::tie(load_global_func_u32, write_global_func_u32) =
@@ -1228,6 +1259,79 @@ void EmitContext::DefineConstantBufferIndirectFunctions(const Info& info) {
     }
 }
 
+void EmitContext::DefineStorageBufferMappings(const Info& info, u32& binding) {
+    if (!UsesStorageBufferMappings(info)) {
+        return;
+    }
+    ASSERT(profile.support_storage_buffer_array_nonuniform_indexing);
+    AddExtension("SPV_KHR_storage_buffer_storage_class");
+
+    const u32 num_entries{NumDescriptors(info.storage_buffers_descriptors)};
+    const Id array_type{TypeArray(U32[1], Const(num_entries))};
+    Decorate(array_type, spv::Decoration::ArrayStride, sizeof(u32));
+    const Id struct_type{TypeStruct(array_type)};
+    Decorate(struct_type, spv::Decoration::Block);
+    MemberName(struct_type, 0, "segment_sizes");
+    MemberDecorate(struct_type, 0, spv::Decoration::Offset, 0U);
+    const Id pointer_type{TypePointer(spv::StorageClass::StorageBuffer, struct_type)};
+    storage_buffer_mapping_u32 = TypePointer(spv::StorageClass::StorageBuffer, U32[1]);
+    storage_buffer_mapping = AddGlobalVariable(pointer_type, spv::StorageClass::StorageBuffer);
+    Decorate(storage_buffer_mapping, spv::Decoration::Binding, binding++);
+    Decorate(storage_buffer_mapping, spv::Decoration::DescriptorSet, 0U);
+    Name(storage_buffer_mapping, "storage_buffer_mapping");
+    //Starting with version 1.4... (https://registry.khronos.org/SPIR-V/specs/unified1/SPIRV.html)
+    if (profile.supported_spirv >= 0x00010400) {
+        interfaces.push_back(storage_buffer_mapping);
+    }
+
+    u32 mapping_base{};
+    for (u32 index = 0; index < info.storage_buffers_descriptors.size(); ++index) {
+        const StorageBufferDescriptor& desc = info.storage_buffers_descriptors[index];
+        storage_buffer_mapping_bases[index] = mapping_base;
+        storage_buffer_mapping_counts[index] = desc.count;
+        mapping_base += desc.count;
+    }
+
+    const Id function_type{TypeFunction(U32[2], U32[1], U32[1], U32[1])};
+    storage_buffer_map_func = OpFunction(U32[2], spv::FunctionControlMask::MaskNone, function_type);
+    const Id base{OpFunctionParameter(U32[1])};
+    const Id count{OpFunctionParameter(U32[1])};
+    const Id byte_offset{OpFunctionParameter(U32[1])};
+    const Id index_pointer_type{TypePointer(spv::StorageClass::Function, U32[1])};
+    const Id loop_header{OpLabel()};
+    const Id continue_block{OpLabel()};
+    const Id merge_block{OpLabel()};
+    AddLabel();
+    const Id segment_var{AddLocalVariable(index_pointer_type, spv::StorageClass::Function)};
+    const Id offset_var{AddLocalVariable(index_pointer_type, spv::StorageClass::Function)};
+    OpStore(segment_var, u32_zero_value);
+    OpStore(offset_var, byte_offset);
+    OpBranch(loop_header);
+
+    AddLabel(loop_header);
+    const Id segment{OpLoad(U32[1], segment_var)};
+    const Id local_offset{OpLoad(U32[1], offset_var)};
+    const Id mapping_index{OpIAdd(U32[1], base, segment)};
+    const Id size_pointer{OpAccessChain(storage_buffer_mapping_u32, storage_buffer_mapping, u32_zero_value, mapping_index)};
+    const Id segment_size{OpLoad(U32[1], size_pointer)};
+    const Id fits{OpULessThan(U1, local_offset, segment_size)};
+    const Id last_segment{OpISub(U32[1], count, Const(1U))};
+    const Id is_last{OpIEqual(U1, segment, last_segment)};
+    const Id found{OpLogicalOr(U1, fits, is_last)};
+    OpLoopMerge(merge_block, continue_block, spv::LoopControlMask::MaskNone);
+    OpBranchConditional(found, merge_block, continue_block);
+
+    AddLabel(continue_block);
+    OpStore(offset_var, OpISub(U32[1], local_offset, segment_size));
+    OpStore(segment_var, OpIAdd(U32[1], segment, Const(1U)));
+    OpBranch(loop_header);
+
+    AddLabel(merge_block);
+    OpReturnValue(OpCompositeConstruct(U32[2], segment, local_offset));
+    OpFunctionEnd();
+    Name(storage_buffer_map_func, "map_storage_buffer");
+}
+
 void EmitContext::DefineStorageBuffers(const Info& info, u32& binding) {
     if (info.storage_buffers_descriptors.empty()) {
         return;
@@ -1271,9 +1375,7 @@ void EmitContext::DefineStorageBuffers(const Info& info, u32& binding) {
         DefineSsbos(*this, storage_types.U32x4, &StorageDefinitions::U32x4, info, binding, U32[4],
                     sizeof(u32[4]));
     }
-    for (const StorageBufferDescriptor& desc : info.storage_buffers_descriptors) {
-        binding += desc.count;
-    }
+    binding += static_cast<u32>(info.storage_buffers_descriptors.size());
     const bool needs_function{
         info.uses_global_increment || info.uses_global_decrement || info.uses_atomic_f32_add ||
         info.uses_atomic_f16x2_add || info.uses_atomic_f16x2_min || info.uses_atomic_f16x2_max ||
@@ -1282,40 +1384,31 @@ void EmitContext::DefineStorageBuffers(const Info& info, u32& binding) {
         AddCapability(spv::Capability::VariablePointersStorageBuffer);
     }
     if (info.uses_global_increment) {
-        increment_cas_ssbo = CasLoop(*this, Operation::Increment, storage_types.U32.array,
-                                     storage_types.U32.element, U32[1], U32[1], spv::Scope::Device);
+        increment_cas_ssbo = CasLoop(*this, Operation::Increment, storage_types.U32.element, U32[1], U32[1], spv::Scope::Device);
     }
     if (info.uses_global_decrement) {
-        decrement_cas_ssbo = CasLoop(*this, Operation::Decrement, storage_types.U32.array,
-                                     storage_types.U32.element, U32[1], U32[1], spv::Scope::Device);
+        decrement_cas_ssbo = CasLoop(*this, Operation::Decrement, storage_types.U32.element, U32[1], U32[1], spv::Scope::Device);
     }
     if (info.uses_atomic_f32_add) {
-        f32_add_cas = CasLoop(*this, Operation::FPAdd, storage_types.U32.array,
-                              storage_types.U32.element, F32[1], U32[1], spv::Scope::Device);
+        f32_add_cas = CasLoop(*this, Operation::FPAdd, storage_types.U32.element, F32[1], U32[1], spv::Scope::Device);
     }
     if (info.uses_atomic_f16x2_add) {
-        f16x2_add_cas = CasLoop(*this, Operation::FPAdd, storage_types.U32.array,
-                                storage_types.U32.element, F16[2], F16[2], spv::Scope::Device);
+        f16x2_add_cas = CasLoop(*this, Operation::FPAdd, storage_types.U32.element, F16[2], F16[2], spv::Scope::Device);
     }
     if (info.uses_atomic_f16x2_min) {
-        f16x2_min_cas = CasLoop(*this, Operation::FPMin, storage_types.U32.array,
-                                storage_types.U32.element, F16[2], F16[2], spv::Scope::Device);
+        f16x2_min_cas = CasLoop(*this, Operation::FPMin, storage_types.U32.element, F16[2], F16[2], spv::Scope::Device);
     }
     if (info.uses_atomic_f16x2_max) {
-        f16x2_max_cas = CasLoop(*this, Operation::FPMax, storage_types.U32.array,
-                                storage_types.U32.element, F16[2], F16[2], spv::Scope::Device);
+        f16x2_max_cas = CasLoop(*this, Operation::FPMax, storage_types.U32.element, F16[2], F16[2], spv::Scope::Device);
     }
     if (info.uses_atomic_f32x2_add) {
-        f32x2_add_cas = CasLoop(*this, Operation::FPAdd, storage_types.U32.array,
-                                storage_types.U32.element, F32[2], F32[2], spv::Scope::Device);
+        f32x2_add_cas = CasLoop(*this, Operation::FPAdd, storage_types.U32.element, F32[2], F32[2], spv::Scope::Device);
     }
     if (info.uses_atomic_f32x2_min) {
-        f32x2_min_cas = CasLoop(*this, Operation::FPMin, storage_types.U32.array,
-                                storage_types.U32.element, F32[2], F32[2], spv::Scope::Device);
+        f32x2_min_cas = CasLoop(*this, Operation::FPMin, storage_types.U32.element, F32[2], F32[2], spv::Scope::Device);
     }
     if (info.uses_atomic_f32x2_max) {
-        f32x2_max_cas = CasLoop(*this, Operation::FPMax, storage_types.U32.array,
-                                storage_types.U32.element, F32[2], F32[2], spv::Scope::Device);
+        f32x2_max_cas = CasLoop(*this, Operation::FPMax, storage_types.U32.element, F32[2], F32[2], spv::Scope::Device);
     }
 }
 

src/shader_recompiler/backend/spirv/spirv_emit_context.h

@@ -114,7 +114,6 @@ struct UniformDefinitions {
 };
 
 struct StorageTypeDefinition {
-    Id array{};
     Id element{};
 };
 
@@ -173,6 +172,8 @@ public:
     [[nodiscard]] Id BitOffset8(const IR::Value& offset);
     [[nodiscard]] Id BitOffset16(const IR::Value& offset);
 
+    [[nodiscard]] Id StoragePointer(u32 binding, Id byte_offset, const StorageTypeDefinition& type_def, u32 element_size, Id StorageDefinitions::*member_ptr);
+
     Id Const(u32 value) {
         return Constant(U32[1], value);
     }
@@ -257,6 +258,11 @@ public:
 
     std::array<UniformDefinitions, Info::MAX_CBUFS> cbufs{};
     std::array<StorageDefinitions, Info::MAX_SSBOS> ssbos{};
+    std::array<u32, Info::MAX_SSBOS> storage_buffer_mapping_bases{};
+    std::array<u32, Info::MAX_SSBOS> storage_buffer_mapping_counts{};
+    Id storage_buffer_mapping{};
+    Id storage_buffer_mapping_u32{};
+    Id storage_buffer_map_func{};
     std::vector<TextureBufferDefinition> texture_buffers;
     std::vector<ImageBufferDefinition> image_buffers;
     std::vector<TextureDefinition> textures;
@@ -376,6 +382,7 @@ public:
     bool uses_nonuniform_storage_image{};
     bool uses_nonuniform_uniform_texel_buffer{};
     bool uses_nonuniform_storage_texel_buffer{};
+    bool uses_nonuniform_storage_buffer{};
 
 private:
     void DefineCommonTypes(const Info& info);
@@ -386,6 +393,7 @@ private:
     void DefineSharedMemoryFunctions(const IR::Program& program);
     void DefineConstantBuffers(const Info& info, u32& binding);
     void DefineConstantBufferIndirectFunctions(const Info& info);
+    void DefineStorageBufferMappings(const Info& info, u32& binding);
     void DefineStorageBuffers(const Info& info, u32& binding);
     void DefineTextureBuffers(const Info& info, u32& binding);
     void DefineImageBuffers(const Info& info, u32& binding);

src/shader_recompiler/frontend/maxwell/translate_program.cpp

@@ -132,6 +132,14 @@ void AddNVNStorageBuffers(IR::Program& program) {
     }
 }
 
+void ConfigureStorageBufferMappings(IR::Program& program, const HostTranslateInfo& host_info) {
+    // https://docs.vulkan.org/guide/latest/descriptor_arrays.html
+    // will be needed: descriptor array elements represent physical spans of one guest virtual buffer.
+    for (StorageBufferDescriptor& desc : program.info.storage_buffers_descriptors) {
+        desc.count = host_info.storage_buffer_segment_count;
+    }
+}
+
 using IR::IsLegacyAttribute; //rescoped to attribute.h to make it visible in load_store_attribute.cpp IPA
 
 std::map<IR::Attribute, IR::Attribute> GenerateLegacyToGenericMappings(
@@ -299,6 +307,7 @@ IR::Program TranslateProgram(ObjectPool<IR::Inst>& inst_pool, ObjectPool<IR::Blo
     Optimization::PositionPass(env, program);
 
     Optimization::GlobalMemoryToStorageBufferPass(program, normalized_host_info);
+    ConfigureStorageBufferMappings(program, normalized_host_info);
     Optimization::TexturePass(env, program, normalized_host_info);
 
     if (Settings::values.resolution_info.active || Settings::values.rescale_hack.GetValue()) {
@@ -314,6 +323,7 @@ IR::Program TranslateProgram(ObjectPool<IR::Inst>& inst_pool, ObjectPool<IR::Blo
 
     CollectInterpolationInfo(env, program);
     AddNVNStorageBuffers(program);
+    ConfigureStorageBufferMappings(program, normalized_host_info);
     return program;
 }
 

src/shader_recompiler/host_translate_info.h

@@ -6,6 +6,7 @@
 
 #pragma once
 
+#include <algorithm>
 #include "common/common_types.h"
 
 namespace Shader {
@@ -19,6 +20,7 @@ struct HostTranslateInfo {
 
     u64 min_ssbo_alignment{};            ///< Minimum alignment supported by the device for SSBOs
     u32 max_per_stage_descriptor_sampled_images{}; ///< maximum sampled descriptors per stage
+    u32 max_per_stage_descriptor_storage_buffers{}; ///< maximum storage descriptors per stage
     u32 max_per_stage_resources{};                 ///< maximum resources per stage
     u32 max_descriptor_set_samplers{};
     u32 max_descriptor_set_uniform_buffers{};
@@ -38,12 +40,14 @@ struct HostTranslateInfo {
                                                 ///< passthrough shaders
     bool support_conditional_barrier{}; ///< True when the device supports barriers in conditional
                                         ///< control flow
+    u32 storage_buffer_segment_count{1}; ///< Physical ranges available to each guest SSBO
 
     void ApplyDescriptorLimitPolicy() noexcept {
         if (min_ssbo_alignment == 0) {
             min_ssbo_alignment = 1;
         }
         ApplyDescriptorLimitFallback(max_per_stage_descriptor_sampled_images);
+        ApplyDescriptorLimitFallback(max_per_stage_descriptor_storage_buffers);
         ApplyDescriptorLimitFallback(max_per_stage_resources);
         ApplyDescriptorLimitFallback(max_descriptor_set_samplers);
         ApplyDescriptorLimitFallback(max_descriptor_set_uniform_buffers);
@@ -53,6 +57,7 @@ struct HostTranslateInfo {
         ApplyDescriptorLimitFallback(max_descriptor_set_sampled_images);
         ApplyDescriptorLimitFallback(max_descriptor_set_storage_images);
         ApplyDescriptorLimitFallback(max_descriptor_set_input_attachements);
+        storage_buffer_segment_count = (std::max)(storage_buffer_segment_count, 1U);
     }
 
 private:

src/shader_recompiler/profile.h

@@ -64,6 +64,7 @@ struct Profile {
     bool support_storage_image_array_nonuniform_indexing{};
     bool support_uniform_texel_buffer_array_nonuniform_indexing{};
     bool support_storage_texel_buffer_array_nonuniform_indexing{};
+    bool support_storage_buffer_array_nonuniform_indexing{};
 
     bool warp_size_potentially_larger_than_guest{};
 

src/shader_recompiler/shader_info.h

@@ -6,6 +6,7 @@
 
 #pragma once
 
+#include <algorithm>
 #include <array>
 #include <bitset>
 #include <map>
@@ -340,6 +341,10 @@ struct Info {
     ImageDescriptors image_descriptors;
 };
 
+[[nodiscard]] inline bool UsesStorageBufferMappings(const Info& info) noexcept {
+    return std::ranges::any_of(info.storage_buffers_descriptors, [](const auto& desc) { return desc.count > 1; });
+}
+
 template <typename Descriptors>
 u32 NumDescriptors(const Descriptors& descriptors) {
     u32 num{};

src/video_core/buffer_cache/buffer_cache.h

@@ -7,6 +7,8 @@
 #pragma once
 
 #include <algorithm>
+#include <cstring>
+#include <limits>
 #include <memory>
 #include <numeric>
 
@@ -423,7 +425,7 @@ void BufferCache<P>::UnbindGraphicsStorageBuffers(size_t stage) {
 
 template <class P>
 bool BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index,
-                                               u32 cbuf_offset, bool is_written) {
+                                               u32 cbuf_offset, bool is_written, u32 descriptor_count) {
     const bool already_enabled =
         ((channel_state->enabled_storage_buffers[stage] >> ssbo_index) & 1U) != 0;
     if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
@@ -448,8 +450,8 @@ bool BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index,
     const auto& cbufs = maxwell3d->state.shader_stages[stage];
     const GPUVAddr ssbo_addr = cbufs.const_buffers[cbuf_index].address + cbuf_offset;
     channel_state->storage_buffers[stage][ssbo_index] =
-        StorageBufferBinding(ssbo_addr, cbuf_index, is_written);
-    return (channel_state->storage_buffers[stage][ssbo_index].buffer_id != NULL_BUFFER_ID);
+        StorageBufferBinding(ssbo_addr, cbuf_index, is_written, descriptor_count);
+    return channel_state->storage_buffers[stage][ssbo_index].gpu_addr != 0;
 }
 
 template <class P>
@@ -487,7 +489,7 @@ void BufferCache<P>::UnbindComputeStorageBuffers() {
 
 template <class P>
 void BufferCache<P>::BindComputeStorageBuffer(size_t ssbo_index, u32 cbuf_index, u32 cbuf_offset,
-                                              bool is_written) {
+                                              bool is_written, u32 descriptor_count) {
     if (ssbo_index >= channel_state->compute_storage_buffers.size()) [[unlikely]] {
         LOG_ERROR(HW_GPU, "Storage buffer index {} exceeds maximum storage buffer count",
                   ssbo_index);
@@ -524,7 +526,7 @@ void BufferCache<P>::BindComputeStorageBuffer(size_t ssbo_index, u32 cbuf_index,
     const auto& cbufs = launch_desc.const_buffer_config;
     const GPUVAddr ssbo_addr = cbufs[cbuf_index].Address() + cbuf_offset;
     channel_state->compute_storage_buffers[ssbo_index] =
-        StorageBufferBinding(ssbo_addr, cbuf_index, is_written);
+        StorageBufferBinding(ssbo_addr, cbuf_index, is_written, descriptor_count);
 }
 
 template <class P>
@@ -1000,27 +1002,52 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
 
 template <class P>
 void BufferCache<P>::BindHostGraphicsStorageBuffers(size_t stage) {
+    boost::container::small_vector<u32, NUM_STORAGE_BUFFERS> segment_sizes;
+    bool uses_mapping{};
+    ForEachEnabledBit(channel_state->enabled_storage_buffers[stage], [&](u32 index) {
+        const StorageBufferBindingInfo& binding = channel_state->storage_buffers[stage][index];
+        uses_mapping |= binding.descriptor_count > 1;
+        for (u32 segment = 0; segment < binding.descriptor_count; ++segment) {
+            segment_sizes.push_back(segment < binding.segments.size() ? binding.segments[segment].size : 0);
+        }
+    });
+    if (uses_mapping) {
+        const u32 mapping_size = static_cast<u32>(segment_sizes.size() * sizeof(u32));
+        if constexpr (!IS_OPENGL) {
+            const std::span<u8> mapped = runtime.BindMappedStorageBuffer(mapping_size);
+            std::memcpy(mapped.data(), segment_sizes.data(), mapping_size);
+        }
+    }
+
     u32 binding_index = 0;
     ForEachEnabledBit(channel_state->enabled_storage_buffers[stage], [&](u32 index) {
-        const Binding& binding = channel_state->storage_buffers[stage][index];
-        Buffer& buffer = slot_buffers[binding.buffer_id];
-        TouchBuffer(buffer, binding.buffer_id);
-        const u32 size = binding.size;
-        SynchronizeBuffer(buffer, binding.device_addr, size);
-
-        const u32 offset = buffer.Offset(binding.device_addr);
-        buffer.MarkUsage(offset, size);
+        const StorageBufferBindingInfo& storage = channel_state->storage_buffers[stage][index];
         const bool is_written = ((channel_state->written_storage_buffers[stage] >> index) & 1) != 0;
-
-        if (is_written) {
-            MarkWrittenBuffer(binding.buffer_id, binding.device_addr, size);
-        }
-
-        if constexpr (NEEDS_BIND_STORAGE_INDEX) {
-            runtime.BindStorageBuffer(stage, binding_index, buffer, offset, size, is_written);
-            ++binding_index;
-        } else {
-            runtime.BindStorageBuffer(buffer, offset, size, is_written);
+        for (u32 segment = 0; segment < storage.descriptor_count; ++segment) {
+            Buffer* buffer = &slot_buffers[NULL_BUFFER_ID];
+            u32 offset{};
+            u32 size{IS_OPENGL ? 0U : static_cast<u32>(sizeof(u32))};
+            const bool is_actual_segment = segment < storage.segments.size();
+            // shall be safe enough if the segment is not actual, use the last available segment or nullptr if none exist.
+            const Binding* binding = is_actual_segment ? &storage.segments[segment] : storage.segments.empty() ? nullptr : &storage.segments.back();
+            if (binding) {
+                buffer = &slot_buffers[binding->buffer_id];
+                size = binding->size;
+                offset = buffer->Offset(binding->device_addr);
+                if (is_actual_segment) {
+                    TouchBuffer(*buffer, binding->buffer_id);
+                    SynchronizeBuffer(*buffer, binding->device_addr, size);
+                    buffer->MarkUsage(offset, size);
+                    if (is_written) {
+                        MarkWrittenBuffer(binding->buffer_id, binding->device_addr, size);
+                    }
+                }
+            }
+            if constexpr (NEEDS_BIND_STORAGE_INDEX) {
+                runtime.BindStorageBuffer(stage, binding_index++, *buffer, offset, size, is_written);
+            } else {
+                runtime.BindStorageBuffer(*buffer, offset, size, is_written);
+            }
         }
     });
 }
@@ -1136,28 +1163,53 @@ void BufferCache<P>::BindHostComputeUniformBuffers() {
 
 template <class P>
 void BufferCache<P>::BindHostComputeStorageBuffers() {
+    boost::container::small_vector<u32, NUM_STORAGE_BUFFERS> segment_sizes;
+    bool uses_mapping{};
+    ForEachEnabledBit(channel_state->enabled_compute_storage_buffers, [&](u32 index) {
+        const StorageBufferBindingInfo& binding = channel_state->compute_storage_buffers[index];
+        uses_mapping |= binding.descriptor_count > 1;
+        for (u32 segment = 0; segment < binding.descriptor_count; ++segment) {
+            segment_sizes.push_back(segment < binding.segments.size() ? binding.segments[segment].size : 0);
+        }
+    });
+    if (uses_mapping) {
+        const u32 mapping_size = static_cast<u32>(segment_sizes.size() * sizeof(u32));
+        if constexpr (!IS_OPENGL) {
+            const std::span<u8> mapped = runtime.BindMappedStorageBuffer(mapping_size);
+            std::memcpy(mapped.data(), segment_sizes.data(), mapping_size);
+        }
+    }
+
     u32 binding_index = 0;
     ForEachEnabledBit(channel_state->enabled_compute_storage_buffers, [&](u32 index) {
-        const Binding& binding = channel_state->compute_storage_buffers[index];
-        Buffer& buffer = slot_buffers[binding.buffer_id];
-        TouchBuffer(buffer, binding.buffer_id);
-        const u32 size = binding.size;
-        SynchronizeBuffer(buffer, binding.device_addr, size);
-
-        const u32 offset = buffer.Offset(binding.device_addr);
-        buffer.MarkUsage(offset, size);
+        const StorageBufferBindingInfo& storage = channel_state->compute_storage_buffers[index];
         const bool is_written =
             ((channel_state->written_compute_storage_buffers >> index) & 1) != 0;
-
-        if (is_written) {
-            MarkWrittenBuffer(binding.buffer_id, binding.device_addr, size);
-        }
-
-        if constexpr (NEEDS_BIND_STORAGE_INDEX) {
-            runtime.BindComputeStorageBuffer(binding_index, buffer, offset, size, is_written);
-            ++binding_index;
-        } else {
-            runtime.BindStorageBuffer(buffer, offset, size, is_written);
+        for (u32 segment = 0; segment < storage.descriptor_count; ++segment) {
+            Buffer* buffer = &slot_buffers[NULL_BUFFER_ID];
+            u32 offset{};
+            u32 size{IS_OPENGL ? 0U : static_cast<u32>(sizeof(u32))};
+            const bool is_actual_segment = segment < storage.segments.size();
+            //same fallback logic
+            const Binding* binding = is_actual_segment ? &storage.segments[segment] : storage.segments.empty() ? nullptr : &storage.segments.back();
+            if (binding) {
+                buffer = &slot_buffers[binding->buffer_id];
+                size = binding->size;
+                offset = buffer->Offset(binding->device_addr);
+                if (is_actual_segment) {
+                    TouchBuffer(*buffer, binding->buffer_id);
+                    SynchronizeBuffer(*buffer, binding->device_addr, size);
+                    buffer->MarkUsage(offset, size);
+                    if (is_written) {
+                        MarkWrittenBuffer(binding->buffer_id, binding->device_addr, size);
+                    }
+                }
+            }
+            if constexpr (NEEDS_BIND_STORAGE_INDEX) {
+                runtime.BindComputeStorageBuffer(binding_index++, *buffer, offset, size, is_written);
+            } else {
+                runtime.BindStorageBuffer(*buffer, offset, size, is_written);
+            }
         }
     });
 }
@@ -1350,10 +1402,7 @@ void BufferCache<P>::UpdateUniformBuffers(size_t stage) {
 template <class P>
 void BufferCache<P>::UpdateStorageBuffers(size_t stage) {
     ForEachEnabledBit(channel_state->enabled_storage_buffers[stage], [&](u32 index) {
-        // Resolve buffer
-        Binding& binding = channel_state->storage_buffers[stage][index];
-        const BufferId buffer_id = FindBuffer(binding.device_addr, binding.size);
-        binding.buffer_id = buffer_id;
+        UpdateStorageBuffer(channel_state->storage_buffers[stage][index]);
     });
 }
 
@@ -1414,12 +1463,54 @@ void BufferCache<P>::UpdateComputeUniformBuffers() {
 template <class P>
 void BufferCache<P>::UpdateComputeStorageBuffers() {
     ForEachEnabledBit(channel_state->enabled_compute_storage_buffers, [&](u32 index) {
-        // Resolve buffer
-        Binding& binding = channel_state->compute_storage_buffers[index];
-        binding.buffer_id = FindBuffer(binding.device_addr, binding.size);
+        UpdateStorageBuffer(channel_state->compute_storage_buffers[index]);
     });
 }
 
+template <class P>
+void BufferCache<P>::UpdateStorageBuffer(StorageBufferBindingInfo& binding) {
+    binding.segments.clear();
+    if (binding.gpu_addr == 0 || binding.size == 0) { return;}
+    if (binding.descriptor_count == 1) {
+        // for safety gotta preserve the legacy path on possible hosts without storage-buffer descriptor indexing.
+        const std::optional<DAddr> device_addr = gpu_memory->GpuToCpuAddress(binding.gpu_addr);
+        if (device_addr) {
+            binding.segments.push_back(Binding{
+                .device_addr = *device_addr,
+                .size = binding.size,
+                .buffer_id = FindBuffer(*device_addr, binding.size),
+            });
+        }
+        return;
+    }
+
+    const auto ranges = gpu_memory->GetSubmappedRange(binding.gpu_addr, binding.size);
+    const size_t mapped_size =
+        std::accumulate(ranges.begin(), ranges.end(), size_t{}, [](size_t total, const auto& range) { return total + range.second; });
+    if (mapped_size != binding.size) {
+        LOG_ERROR(HW_GPU, "Storage buffer range {:#x}+{:#x} is not fully mapped", binding.gpu_addr, binding.size);
+        return;
+    }
+    if (ranges.size() > binding.descriptor_count) {
+        LOG_ERROR(HW_GPU, "Storage buffer range {:#x}+{:#x} has {} physical segments, exceeding host capacity {}",
+                  binding.gpu_addr, binding.size, ranges.size(), binding.descriptor_count);
+        return;
+    }
+    for (const auto& [gpu_addr, size] : ranges) {
+        const std::optional<DAddr> device_addr = gpu_memory->GpuToCpuAddress(gpu_addr);
+        if (!device_addr || size > (std::numeric_limits<u32>::max)()) {
+            binding.segments.clear();
+            return;
+        }
+        const u32 segment_size = static_cast<u32>(size);
+        binding.segments.push_back(Binding{
+            .device_addr = *device_addr,
+            .size = segment_size,
+            .buffer_id = FindBuffer(*device_addr, segment_size),
+        });
+    }
+}
+
 template <class P>
 void BufferCache<P>::UpdateComputeTextureBuffers() {
     ForEachEnabledBit(channel_state->enabled_compute_texture_buffers, [&](u32 index) {
@@ -1841,6 +1932,11 @@ void BufferCache<P>::DeleteBuffer(BufferId buffer_id, bool do_not_mark) {
     const auto replace = [scalar_replace](std::span<Binding> bindings) {
         std::ranges::for_each(bindings, scalar_replace);
     };
+    const auto storage_replace = [scalar_replace](std::span<StorageBufferBindingInfo> bindings) {
+        for (StorageBufferBindingInfo& binding : bindings) {
+            std::ranges::for_each(binding.segments, scalar_replace);
+        }
+    };
 
     if (channel_state->index_buffer.buffer_id == buffer_id) {
         channel_state->index_buffer.buffer_id = BufferId{};
@@ -1856,10 +1952,10 @@ void BufferCache<P>::DeleteBuffer(BufferId buffer_id, bool do_not_mark) {
         }
     }
     std::ranges::for_each(channel_state->uniform_buffers, replace);
-    std::ranges::for_each(channel_state->storage_buffers, replace);
+    std::ranges::for_each(channel_state->storage_buffers, storage_replace);
     replace(channel_state->transform_feedback_buffers);
     replace(channel_state->compute_uniform_buffers);
-    replace(channel_state->compute_storage_buffers);
+    storage_replace(channel_state->compute_storage_buffers);
 
     // Mark the whole buffer as CPU written to stop tracking CPU writes
     if (!do_not_mark) {
@@ -1896,12 +1992,14 @@ void BufferCache<P>::DeleteBuffer(BufferId buffer_id, bool do_not_mark) {
 }
 
 template <class P>
-Binding BufferCache<P>::StorageBufferBinding(GPUVAddr ssbo_addr, u32 cbuf_index,
-                                             bool is_written) const {
+StorageBufferBindingInfo BufferCache<P>::StorageBufferBinding(GPUVAddr ssbo_addr, u32 cbuf_index,
+                                                              bool is_written, u32 descriptor_count) const {
+    // time to get rid of these null bindings
+    ASSERT(descriptor_count > 0); // shant happen
     const GPUVAddr gpu_addr = gpu_memory->Read<u64>(ssbo_addr);
 
     if (gpu_addr == 0) {
-        return NULL_BINDING;
+        return {.descriptor_count = descriptor_count};
     }
 
     const auto size = [&]() {
@@ -1923,21 +2021,17 @@ Binding BufferCache<P>::StorageBufferBinding(GPUVAddr ssbo_addr, u32 cbuf_index,
     const GPUVAddr aligned_gpu_addr = Common::AlignDown(gpu_addr, alignment);
     const u32 aligned_size = static_cast<u32>(gpu_addr - aligned_gpu_addr) + size;
 
-    const std::optional<DAddr> aligned_device_addr = gpu_memory->GpuToCpuAddress(aligned_gpu_addr);
-    if (!aligned_device_addr || size == 0) {
+    if (!gpu_memory->GpuToCpuAddress(aligned_gpu_addr) || size == 0) {
         LOG_DEBUG(HW_GPU, "Failed to find storage buffer for cbuf index {}", cbuf_index);
-        return NULL_BINDING;
+        return {.descriptor_count = descriptor_count};
     }
-    const std::optional<DAddr> device_addr = gpu_memory->GpuToCpuAddress(gpu_addr);
-    ASSERT_MSG(device_addr, "Unaligned storage buffer address not found for cbuf index {}",
-               cbuf_index);
     // The end address used for size calculation does not need to be aligned
-    const DAddr cpu_end = Common::AlignUp(*device_addr + size, Core::DEVICE_PAGESIZE);
+    const GPUVAddr gpu_end = Common::AlignUp(gpu_addr + size, Core::DEVICE_PAGESIZE);
 
-    const Binding binding{
-        .device_addr = *aligned_device_addr,
-        .size = is_written ? aligned_size : static_cast<u32>(cpu_end - *aligned_device_addr),
-        .buffer_id = BufferId{},
+    const StorageBufferBindingInfo binding{
+        .gpu_addr = aligned_gpu_addr,
+        .size = is_written ? aligned_size : static_cast<u32>(gpu_end - aligned_gpu_addr),
+        .descriptor_count = descriptor_count,
     };
     return binding;
 }

src/video_core/buffer_cache/buffer_cache_base.h

@@ -89,6 +89,15 @@ struct TextureBufferBinding : Binding {
     PixelFormat format;
 };
 
+struct StorageBufferBindingInfo {
+    // another good one: guest SSBO is a virtual interval and may span discontiguous device-memory ranges.
+    // exact case of missing character frames (high sample lane)
+    GPUVAddr gpu_addr{};
+    u32 size{};
+    u32 descriptor_count{1};
+    boost::container::small_vector<Binding, 1> segments;
+};
+
 static constexpr Binding NULL_BINDING{
     .device_addr = 0,
     .size = 0,
@@ -115,14 +124,15 @@ public:
     Binding index_buffer;
     std::array<Binding, NUM_VERTEX_BUFFERS> vertex_buffers;
     std::array<std::array<Binding, NUM_GRAPHICS_UNIFORM_BUFFERS>, NUM_STAGES> uniform_buffers;
-    std::array<std::array<Binding, NUM_STORAGE_BUFFERS>, NUM_STAGES> storage_buffers;
+    std::array<std::array<StorageBufferBindingInfo, NUM_STORAGE_BUFFERS>, NUM_STAGES>
+        storage_buffers;
     std::array<std::array<TextureBufferBinding, NUM_TEXTURE_BUFFERS>, NUM_STAGES> texture_buffers;
     std::array<Binding, NUM_TRANSFORM_FEEDBACK_BUFFERS> transform_feedback_buffers;
     Binding count_buffer_binding;
     Binding indirect_buffer_binding;
 
     std::array<Binding, NUM_COMPUTE_UNIFORM_BUFFERS> compute_uniform_buffers;
-    std::array<Binding, NUM_STORAGE_BUFFERS> compute_storage_buffers;
+    std::array<StorageBufferBindingInfo, NUM_STORAGE_BUFFERS> compute_storage_buffers;
     std::array<TextureBufferBinding, NUM_TEXTURE_BUFFERS> compute_texture_buffers;
 
     std::array<u32, NUM_STAGES> enabled_uniform_buffer_masks{};
@@ -249,7 +259,7 @@ public:
     void UnbindGraphicsStorageBuffers(size_t stage);
 
     bool BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index, u32 cbuf_offset,
-                                   bool is_written);
+                                   bool is_written, u32 descriptor_count = 1);
 
     void UnbindGraphicsTextureBuffers(size_t stage);
 
@@ -259,7 +269,7 @@ public:
     void UnbindComputeStorageBuffers();
 
     void BindComputeStorageBuffer(size_t ssbo_index, u32 cbuf_index, u32 cbuf_offset,
-                                  bool is_written);
+                                  bool is_written, u32 descriptor_count = 1);
 
     void UnbindComputeTextureBuffers();
 
@@ -400,6 +410,8 @@ private:
 
     void UpdateStorageBuffers(size_t stage);
 
+    void UpdateStorageBuffer(StorageBufferBindingInfo& binding);
+
     void UpdateTextureBuffers(size_t stage);
 
     void UpdateTransformFeedbackBuffers();
@@ -449,8 +461,9 @@ private:
 
     void DeleteBuffer(BufferId buffer_id, bool do_not_mark = false);
 
-    [[nodiscard]] Binding StorageBufferBinding(GPUVAddr ssbo_addr, u32 cbuf_index,
-                                               bool is_written) const;
+    [[nodiscard]] StorageBufferBindingInfo StorageBufferBinding(GPUVAddr ssbo_addr, u32 cbuf_index,
+                                                                bool is_written,
+                                                                u32 descriptor_count) const;
 
     [[nodiscard]] TextureBufferBinding GetTextureBufferBinding(GPUVAddr gpu_addr, u32 size,
                                                                PixelFormat format);

src/video_core/renderer_vulkan/pipeline_helper.h

@@ -6,6 +6,7 @@
 
 #pragma once
 
+#include <array>
 #include <cstddef>
 #include <optional>
 
@@ -136,6 +137,7 @@ inline void WriteDescriptorBuffer(const Device& device, const DescriptorBufferLa
 
 [[nodiscard]] inline u32 NumDescriptorEntries(const Shader::Info& info) {
     return Shader::NumDescriptors(info.constant_buffer_descriptors) +
+           static_cast<u32>(Shader::UsesStorageBufferMappings(info)) +
            Shader::NumDescriptors(info.storage_buffers_descriptors) +
            Shader::NumDescriptors(info.texture_buffer_descriptors) +
            Shader::NumDescriptors(info.image_buffer_descriptors) +
@@ -268,6 +270,12 @@ public:
         is_compute |= (stage & VK_SHADER_STAGE_COMPUTE_BIT) != 0;
 
         Add(VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER, stage, info.constant_buffer_descriptors);
+        // for extra implicit storage-buffer binding required by mapped-storage-buffer support
+        if (Shader::UsesStorageBufferMappings(info)) {
+            struct Descriptor { u32 count; };
+            const std::array descriptors{Descriptor{1}};
+            Add(VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, stage, descriptors);
+        }
         Add(VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, stage, info.storage_buffers_descriptors);
         Add(VK_DESCRIPTOR_TYPE_UNIFORM_TEXEL_BUFFER, stage, info.texture_buffer_descriptors);
         Add(VK_DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER, stage, info.image_buffer_descriptors);

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -695,7 +695,7 @@ vk::Buffer BufferCacheRuntime::CreateNullBuffer() {
         .flags = 0,
         .size = 4,
         .usage = VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT |
-                 VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT,
+                 VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -155,6 +155,13 @@ public:
         return ref.mapped_span;
     }
 
+    // compute/graphics new binding
+    std::span<u8> BindMappedStorageBuffer(u32 size) {
+        const StagingBufferRef ref = staging_pool.Request(size, MemoryUsage::Upload);
+        guest_descriptor_queue.AddBuffer(ref.buffer, ref.device_address, static_cast<u32>(ref.offset), size);
+        return ref.mapped_span;
+    }
+
     void BindUniformBuffer(const Buffer& buffer, u32 offset, u32 size) {
         BindBuffer(buffer, offset, size);
     }

src/video_core/renderer_vulkan/vk_compute_pipeline.cpp

@@ -157,9 +157,7 @@ bool ComputePipeline::Configure(Tegra::Engines::KeplerCompute& kepler_compute,
     buffer_cache.UnbindComputeStorageBuffers();
     size_t ssbo_index{};
     for (const auto& desc : info.storage_buffers_descriptors) {
-        ASSERT(desc.count == 1);
-        buffer_cache.BindComputeStorageBuffer(ssbo_index, desc.cbuf_index, desc.cbuf_offset,
-                                              desc.is_written);
+        buffer_cache.BindComputeStorageBuffer(ssbo_index, desc.cbuf_index, desc.cbuf_offset, desc.is_written, desc.count);
         ++ssbo_index;
     }
 

src/video_core/renderer_vulkan/vk_descriptor_pool.cpp

@@ -47,7 +47,7 @@ static DescriptorBankInfo MakeBankInfo(std::span<const Shader::Info> infos) {
     DescriptorBankInfo bank;
     for (const Shader::Info& info : infos) {
         bank.uniform_buffers += Accumulate(info.constant_buffer_descriptors);
-        bank.storage_buffers += Accumulate(info.storage_buffers_descriptors);
+        bank.storage_buffers += Accumulate(info.storage_buffers_descriptors) + static_cast<u32>(Shader::UsesStorageBufferMappings(info));
         bank.texture_buffers += Accumulate(info.texture_buffer_descriptors);
         bank.image_buffers += Accumulate(info.image_buffer_descriptors);
         bank.textures += Accumulate(info.texture_descriptors);

src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp

@@ -367,9 +367,8 @@ bool GraphicsPipeline::ConfigureImpl(bool is_indexed) {
         if constexpr (Spec::has_storage_buffers) {
             size_t ssbo_index{};
             for (const auto& desc : info.storage_buffers_descriptors) {
-                ASSERT(desc.count == 1);
                 buffer_cache.BindGraphicsStorageBuffer(stage, ssbo_index, desc.cbuf_index,
-                                                       desc.cbuf_offset, desc.is_written);
+                                                       desc.cbuf_offset, desc.is_written, desc.count);
                 ++ssbo_index;
             }
         }

src/video_core/renderer_vulkan/vk_pipeline_cache.cpp

@@ -62,7 +62,12 @@ using VideoCommon::FileEnvironment;
 using VideoCommon::GenericEnvironment;
 using VideoCommon::GraphicsEnvironment;
 
-constexpr u32 CACHE_VERSION = 18;
+// SPIR-V descriptor arrays require a fixed pipeline-layout count.
+// Exploration ceiling; buffer-cache telemetry records the actual physical-range demand.
+// Keep this modest because every mapped SSBO binds the full fixed array on each update.
+constexpr u32 MAX_MAPPED_STORAGE_BUFFER_DESCRIPTORS = 32;
+
+constexpr u32 CACHE_VERSION = 19;
 constexpr size_t VULKAN_CACHE_FLUSH_PIPELINES = 128;
 constexpr size_t VULKAN_CACHE_FLUSH_MIN_SECONDS = 30;
 constexpr std::array<char, 8> VULKAN_CACHE_MAGIC_NUMBER{'y', 'u', 'z', 'u', 'v', 'k', 'c', 'h'};
@@ -432,6 +437,8 @@ PipelineCache::PipelineCache(Tegra::MaxwellDeviceMemoryManager& device_memory_,
             device.IsUniformTexelBufferArrayNonUniformIndexingSupported(),
         .support_storage_texel_buffer_array_nonuniform_indexing =
             device.IsStorageTexelBufferArrayNonUniformIndexingSupported(),
+        .support_storage_buffer_array_nonuniform_indexing =
+            device.IsStorageBufferArrayNonUniformIndexingSupported(),
 
         .warp_size_potentially_larger_than_guest = device.IsWarpSizePotentiallyBiggerThanGuest(),
 
@@ -460,6 +467,7 @@ PipelineCache::PipelineCache(Tegra::MaxwellDeviceMemoryManager& device_memory_,
     host_info = Shader::HostTranslateInfo{
         .min_ssbo_alignment = device.GetStorageBufferAlignment(),
         .max_per_stage_descriptor_sampled_images = device.GetMaxPerStageDescriptorSampledImages(),
+        .max_per_stage_descriptor_storage_buffers = device.GetMaxPerStageDescriptorStorageBuffers(),
         .max_per_stage_resources = device.GetMaxPerStageResources(),
         .max_descriptor_set_samplers = device.GetMaxDescriptorSetSamplers(),
         .max_descriptor_set_uniform_buffers = device.GetMaxDescriptorSetUniformBuffers(),
@@ -479,6 +487,20 @@ PipelineCache::PipelineCache(Tegra::MaxwellDeviceMemoryManager& device_memory_,
         .support_viewport_index_layer = device.IsExtShaderViewportIndexLayerSupported(),
         .support_geometry_shader_passthrough = device.IsNvGeometryShaderPassthroughSupported(),
         .support_conditional_barrier = device.SupportsConditionalBarriers(),
+        .storage_buffer_segment_count = [&] {
+            if (!device.IsStorageBufferArrayNonUniformIndexingSupported()) {
+                return 1U;
+            }
+            constexpr u32 MaxGraphicsStages = static_cast<u32>(Maxwell::MaxShaderStage);
+            const auto reserve = [](u32 limit, u32 count) {
+                return limit > count ? limit - count : 0U;
+            };
+            const u32 per_stage = reserve(device.GetMaxPerStageDescriptorStorageBuffers(), 1) / static_cast<u32>(Shader::Info::MAX_SSBOS);
+            const u32 per_set = reserve(device.GetMaxDescriptorSetStorageBuffers(), MaxGraphicsStages) / (static_cast<u32>(Shader::Info::MAX_SSBOS) * MaxGraphicsStages);
+            const u32 resources = reserve(device.GetMaxPerStageResources(), 1) / (static_cast<u32>(Shader::Info::MAX_SSBOS) * 2);
+            // ensure at least one storage buffer segment is available per stage. max is still arbitrary
+            return (std::max)(1U, (std::min)({MAX_MAPPED_STORAGE_BUFFER_DESCRIPTORS, per_stage, per_set, resources}));
+        }(),
     };
     host_info.ApplyDescriptorLimitPolicy();
 

src/video_core/vulkan_common/vulkan_device.cpp

@@ -708,7 +708,6 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
         descriptor_indexing.shaderUniformTexelBufferArrayDynamicIndexing = false;
         descriptor_indexing.shaderStorageTexelBufferArrayDynamicIndexing = false;
         descriptor_indexing.shaderUniformBufferArrayNonUniformIndexing = false;
-        descriptor_indexing.shaderStorageBufferArrayNonUniformIndexing = false;
         descriptor_indexing.shaderInputAttachmentArrayNonUniformIndexing = false;
         descriptor_indexing.descriptorBindingUniformBufferUpdateAfterBind = false;
         descriptor_indexing.descriptorBindingSampledImageUpdateAfterBind = false;

src/video_core/vulkan_common/vulkan_device.h

@@ -360,6 +360,7 @@ public:
 #define FN_MAX_LIMIT_LIST \
     FN_MAX_LIMIT_ELEM(ComputeSharedMemorySize) \
     FN_MAX_LIMIT_ELEM(PerStageDescriptorSampledImages) \
+    FN_MAX_LIMIT_ELEM(PerStageDescriptorStorageBuffers) \
     FN_MAX_LIMIT_ELEM(PerStageResources) \
     FN_MAX_LIMIT_ELEM(DescriptorSetSamplers) \
     FN_MAX_LIMIT_ELEM(DescriptorSetUniformBuffers) \
@@ -415,6 +416,10 @@ FN_MAX_LIMIT_LIST
         return features.descriptor_indexing.shaderStorageTexelBufferArrayNonUniformIndexing;
     }
 
+    bool IsStorageBufferArrayNonUniformIndexingSupported() const {
+        return features.descriptor_indexing.shaderStorageBufferArrayNonUniformIndexing;
+    }
+
     /// Returns true if the device supports float64 natively.
     bool IsFloat64Supported() const {
         return features.features.shaderFloat64;

src/yuzu/configuration/configure_input_player_widget.cpp

@@ -2936,10 +2936,10 @@ void PlayerControlPreview::DrawArrow(QPainter& p, const QPointF center, const Di
 }
 
 // Draw motion functions
-void PlayerControlPreview::Draw3dCube(QPainter& p, QPointF center, const Common::Vec<f32, 3>& euler,
+void PlayerControlPreview::Draw3dCube(QPainter& p, QPointF center, const Common::Vec3f& euler,
                                       float size) {
-    std::array<Common::Vec<f32, 3>, 8> cube{
-        Common::Vec<f32, 3>{-0.7f, -1, -0.5f},
+    std::array<Common::Vec3f, 8> cube{
+        Common::Vec3f{-0.7f, -1, -0.5f},
         {-0.7f, 1, -0.5f},
         {0.7f, 1, -0.5f},
         {0.7f, -1, -0.5f},
@@ -2949,38 +2949,30 @@ void PlayerControlPreview::Draw3dCube(QPainter& p, QPointF center, const Common:
         {0.7f, -1, 0.5f},
     };
 
-    for (Common::Vec<f32, 3>& point : cube) {
-        float temp = point[1];
-        point[1] = std::cos(euler[0]) * point[1] - std::sin(euler[0]) * point[2];
-        point[2] = std::sin(euler[0]) * temp + std::cos(euler[0]) * point[2];
-        temp = point[0];
-        point[0] = std::cos(euler[1]) * point[0] + std::sin(euler[1]) * point[2];
-        point[2] = -std::sin(euler[1]) * temp + std::cos(euler[1]) * point[2];
-        temp = point[0];
-        point[0] = std::cos(euler[2]) * point[0] - std::sin(euler[2]) * point[1];
-        point[1] = std::sin(euler[2]) * temp + std::cos(euler[2]) * point[1];
+    for (Common::Vec3f& point : cube) {
+        point.RotateFromOrigin(euler.x, euler.y, euler.z);
         point *= size;
     }
 
     const std::array<QPointF, 4> front_face{
-        center + QPointF{cube[0][0], cube[0][1]},
-        center + QPointF{cube[1][0], cube[1][1]},
-        center + QPointF{cube[2][0], cube[2][1]},
-        center + QPointF{cube[3][0], cube[3][1]},
+        center + QPointF{cube[0].x, cube[0].y},
+        center + QPointF{cube[1].x, cube[1].y},
+        center + QPointF{cube[2].x, cube[2].y},
+        center + QPointF{cube[3].x, cube[3].y},
     };
     const std::array<QPointF, 4> back_face{
-        center + QPointF{cube[4][0], cube[4][1]},
-        center + QPointF{cube[5][0], cube[5][1]},
-        center + QPointF{cube[6][0], cube[6][1]},
-        center + QPointF{cube[7][0], cube[7][1]},
+        center + QPointF{cube[4].x, cube[4].y},
+        center + QPointF{cube[5].x, cube[5].y},
+        center + QPointF{cube[6].x, cube[6].y},
+        center + QPointF{cube[7].x, cube[7].y},
     };
 
     DrawPolygon(p, front_face);
     DrawPolygon(p, back_face);
-    p.drawLine(center + QPointF{cube[0][0], cube[0][1]}, center + QPointF{cube[4][0], cube[4][1]});
-    p.drawLine(center + QPointF{cube[1][0], cube[1][1]}, center + QPointF{cube[5][0], cube[5][1]});
-    p.drawLine(center + QPointF{cube[2][0], cube[2][1]}, center + QPointF{cube[6][0], cube[6][1]});
-    p.drawLine(center + QPointF{cube[3][0], cube[3][1]}, center + QPointF{cube[7][0], cube[7][1]});
+    p.drawLine(center + QPointF{cube[0].x, cube[0].y}, center + QPointF{cube[4].x, cube[4].y});
+    p.drawLine(center + QPointF{cube[1].x, cube[1].y}, center + QPointF{cube[5].x, cube[5].y});
+    p.drawLine(center + QPointF{cube[2].x, cube[2].y}, center + QPointF{cube[6].x, cube[6].y});
+    p.drawLine(center + QPointF{cube[3].x, cube[3].y}, center + QPointF{cube[7].x, cube[7].y});
 }
 
 template <size_t N>

src/yuzu/configuration/configure_input_player_widget.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
@@ -198,7 +198,7 @@ private:
     void DrawArrow(QPainter& p, QPointF center, Direction direction, float size);
 
     // Draw motion functions
-    void Draw3dCube(QPainter& p, QPointF center, const Common::Vec<f32, 3>& euler, float size);
+    void Draw3dCube(QPainter& p, QPointF center, const Common::Vec3f& euler, float size);
 
     // Draw primitive types
     template <size_t N>