40 files changed, 911 insertions, 199 deletions

diff --git a/src/common/common_types.h b/src/common/common_types.h
index 4cec89fbd..99bffc460 100644
--- a/src/common/common_types.h
+++ b/src/common/common_types.h
@@ -46,13 +46,3 @@ using GPUVAddr = u64; ///< Represents a pointer in the GPU virtual address space
 
 using u128 = std::array<std::uint64_t, 2>;
 static_assert(sizeof(u128) == 16, "u128 must be 128 bits wide");
-
-// An inheritable class to disallow the copy constructor and operator= functions
-class NonCopyable {
-protected:
-    constexpr NonCopyable() = default;
-    ~NonCopyable() = default;
-
-    NonCopyable(const NonCopyable&) = delete;
-    NonCopyable& operator=(const NonCopyable&) = delete;
-};
diff --git a/src/common/input.h b/src/common/input.h
index f4f9eb30a..54fcb24b0 100644
--- a/src/common/input.h
+++ b/src/common/input.h
@@ -209,6 +209,8 @@ enum class ButtonNames {
     Triangle,
     Share,
     Options,
+    Home,
+    Touch,
 
     // Mouse buttons
     ButtonMouseWheel,
diff --git a/src/common/telemetry.h b/src/common/telemetry.h
index 49186e848..d38aeac99 100644
--- a/src/common/telemetry.h
+++ b/src/common/telemetry.h
@@ -8,6 +8,7 @@
 #include <map>
 #include <memory>
 #include <string>
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 
 namespace Common::Telemetry {
@@ -28,7 +29,7 @@ struct VisitorInterface;
 /**
  * Interface class for telemetry data fields.
  */
-class FieldInterface : NonCopyable {
+class FieldInterface {
 public:
     virtual ~FieldInterface() = default;
 
@@ -52,14 +53,15 @@ public:
 template <typename T>
 class Field : public FieldInterface {
 public:
+    YUZU_NON_COPYABLE(Field);
+
     Field(FieldType type_, std::string name_, T value_)
         : name(std::move(name_)), type(type_), value(std::move(value_)) {}
 
-    Field(const Field&) = default;
-    Field& operator=(const Field&) = default;
+    ~Field() override = default;
 
-    Field(Field&&) = default;
-    Field& operator=(Field&& other) = default;
+    Field(Field&&) noexcept = default;
+    Field& operator=(Field&& other) noexcept = default;
 
     void Accept(VisitorInterface& visitor) const override;
 
@@ -98,9 +100,15 @@ private:
 /**
  * Collection of data fields that have been logged.
  */
-class FieldCollection final : NonCopyable {
+class FieldCollection final {
 public:
+    YUZU_NON_COPYABLE(FieldCollection);
+
     FieldCollection() = default;
+    ~FieldCollection() = default;
+
+    FieldCollection(FieldCollection&&) noexcept = default;
+    FieldCollection& operator=(FieldCollection&&) noexcept = default;
 
     /**
      * Accept method for the visitor pattern, visits each field in the collection.
@@ -133,7 +141,7 @@ private:
  * Telemetry fields visitor interface class. A backend to log to a web service should implement
  * this interface.
  */
-struct VisitorInterface : NonCopyable {
+struct VisitorInterface {
     virtual ~VisitorInterface() = default;
 
     virtual void Visit(const Field<bool>& field) = 0;
@@ -160,8 +168,8 @@ struct VisitorInterface : NonCopyable {
  * Empty implementation of VisitorInterface that drops all fields. Used when a functional
  * backend implementation is not available.
  */
-struct NullVisitor : public VisitorInterface {
-    ~NullVisitor() = default;
+struct NullVisitor final : public VisitorInterface {
+    YUZU_NON_COPYABLE(NullVisitor);
 
     void Visit(const Field<bool>& /*field*/) override {}
     void Visit(const Field<double>& /*field*/) override {}
diff --git a/src/core/arm/arm_interface.h b/src/core/arm/arm_interface.h
index 689e3ceb5..c60322442 100644
--- a/src/core/arm/arm_interface.h
+++ b/src/core/arm/arm_interface.h
@@ -6,6 +6,7 @@
 
 #include <array>
 #include <vector>
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/hardware_properties.h"
 
@@ -24,8 +25,11 @@ class CPUInterruptHandler;
 using CPUInterrupts = std::array<CPUInterruptHandler, Core::Hardware::NUM_CPU_CORES>;
 
 /// Generic ARMv8 CPU interface
-class ARM_Interface : NonCopyable {
+class ARM_Interface {
 public:
+    YUZU_NON_COPYABLE(ARM_Interface);
+    YUZU_NON_MOVEABLE(ARM_Interface);
+
     explicit ARM_Interface(System& system_, CPUInterrupts& interrupt_handlers_,
                            bool uses_wall_clock_)
         : system{system_}, interrupt_handlers{interrupt_handlers_}, uses_wall_clock{
diff --git a/src/core/file_sys/vfs.h b/src/core/file_sys/vfs.h
index 3e625fad6..1b9365853 100644
--- a/src/core/file_sys/vfs.h
+++ b/src/core/file_sys/vfs.h
@@ -12,6 +12,7 @@
 #include <type_traits>
 #include <vector>
 
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/file_sys/vfs_types.h"
 
@@ -29,8 +30,11 @@ enum class VfsEntryType {
 // A class representing an abstract filesystem. A default implementation given the root VirtualDir
 // is provided for convenience, but if the Vfs implementation has any additional state or
 // functionality, they will need to override.
-class VfsFilesystem : NonCopyable {
+class VfsFilesystem {
 public:
+    YUZU_NON_COPYABLE(VfsFilesystem);
+    YUZU_NON_MOVEABLE(VfsFilesystem);
+
     explicit VfsFilesystem(VirtualDir root);
     virtual ~VfsFilesystem();
 
@@ -77,8 +81,12 @@ protected:
 };
 
 // A class representing a file in an abstract filesystem.
-class VfsFile : NonCopyable {
+class VfsFile {
 public:
+    YUZU_NON_COPYABLE(VfsFile);
+    YUZU_NON_MOVEABLE(VfsFile);
+
+    VfsFile() = default;
     virtual ~VfsFile();
 
     // Retrieves the file name.
@@ -176,8 +184,12 @@ public:
 };
 
 // A class representing a directory in an abstract filesystem.
-class VfsDirectory : NonCopyable {
+class VfsDirectory {
 public:
+    YUZU_NON_COPYABLE(VfsDirectory);
+    YUZU_NON_MOVEABLE(VfsDirectory);
+
+    VfsDirectory() = default;
     virtual ~VfsDirectory();
 
     // Retrives the file located at path as if the current directory was root. Returns nullptr if
diff --git a/src/core/hid/emulated_console.h b/src/core/hid/emulated_console.h
index 707419102..5eb170823 100644
--- a/src/core/hid/emulated_console.h
+++ b/src/core/hid/emulated_console.h
@@ -10,6 +10,7 @@
 #include <mutex>
 #include <unordered_map>
 
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "common/input.h"
 #include "common/param_package.h"
diff --git a/src/core/hid/emulated_controller.h b/src/core/hid/emulated_controller.h
index a63a83cce..d8642c5b3 100644
--- a/src/core/hid/emulated_controller.h
+++ b/src/core/hid/emulated_controller.h
@@ -13,8 +13,6 @@
 #include "common/common_types.h"
 #include "common/input.h"
 #include "common/param_package.h"
-#include "common/point.h"
-#include "common/quaternion.h"
 #include "common/settings.h"
 #include "common/vector_math.h"
 #include "core/hid/hid_types.h"
diff --git a/src/core/hid/hid_core.h b/src/core/hid/hid_core.h
index 837f7de49..717f605e7 100644
--- a/src/core/hid/hid_core.h
+++ b/src/core/hid/hid_core.h
@@ -6,6 +6,7 @@
 
 #include <memory>
 
+#include "common/common_funcs.h"
 #include "core/hid/hid_types.h"
 
 namespace Core::HID {
diff --git a/src/core/hle/kernel/k_auto_object.h b/src/core/hle/kernel/k_auto_object.h
index 165b76747..05779f2d5 100644
--- a/src/core/hle/kernel/k_auto_object.h
+++ b/src/core/hle/kernel/k_auto_object.h
@@ -20,8 +20,6 @@ class KernelCore;
 class KProcess;
 
 #define KERNEL_AUTOOBJECT_TRAITS(CLASS, BASE_CLASS)                                                \
-    YUZU_NON_COPYABLE(CLASS);                                                                      \
-    YUZU_NON_MOVEABLE(CLASS);                                                                      \
                                                                                                    \
 private:                                                                                           \
     friend class ::Kernel::KClassTokenGenerator;                                                   \
@@ -32,6 +30,9 @@ private:
     }                                                                                              \
                                                                                                    \
 public:                                                                                            \
+    YUZU_NON_COPYABLE(CLASS);                                                                      \
+    YUZU_NON_MOVEABLE(CLASS);                                                                      \
+                                                                                                   \
     using BaseClass = BASE_CLASS;                                                                  \
     static constexpr TypeObj GetStaticTypeObj() {                                                  \
         constexpr ClassTokenType Token = ClassToken();                                             \
@@ -224,9 +225,9 @@ private:
 
 template <typename T>
 class KScopedAutoObject {
+public:
     YUZU_NON_COPYABLE(KScopedAutoObject);
 
-public:
     constexpr KScopedAutoObject() = default;
 
     constexpr KScopedAutoObject(T* o) : m_obj(o) {
diff --git a/src/core/hle/kernel/k_auto_object_container.h b/src/core/hle/kernel/k_auto_object_container.h
index 4eadfe99d..697cc4289 100644
--- a/src/core/hle/kernel/k_auto_object_container.h
+++ b/src/core/hle/kernel/k_auto_object_container.h
@@ -16,13 +16,12 @@ class KernelCore;
 class KProcess;
 
 class KAutoObjectWithListContainer {
+public:
     YUZU_NON_COPYABLE(KAutoObjectWithListContainer);
     YUZU_NON_MOVEABLE(KAutoObjectWithListContainer);
 
-public:
     using ListType = boost::intrusive::rbtree<KAutoObjectWithList>;
 
-public:
     class ListAccessor : public KScopedLightLock {
     public:
         explicit ListAccessor(KAutoObjectWithListContainer* container)
@@ -48,7 +47,6 @@ public:
 
     friend class ListAccessor;
 
-public:
     KAutoObjectWithListContainer(KernelCore& kernel) : m_lock(kernel), m_object_list() {}
 
     void Initialize() {}
diff --git a/src/core/hle/kernel/k_handle_table.h b/src/core/hle/kernel/k_handle_table.h
index 4b114ec2f..87004a0f9 100644
--- a/src/core/hle/kernel/k_handle_table.h
+++ b/src/core/hle/kernel/k_handle_table.h
@@ -22,13 +22,12 @@ namespace Kernel {
 class KernelCore;
 
 class KHandleTable {
+public:
     YUZU_NON_COPYABLE(KHandleTable);
     YUZU_NON_MOVEABLE(KHandleTable);
 
-public:
     static constexpr size_t MaxTableSize = 1024;
 
-public:
     explicit KHandleTable(KernelCore& kernel_);
     ~KHandleTable();
 
diff --git a/src/core/hle/kernel/k_memory_manager.h b/src/core/hle/kernel/k_memory_manager.h
index abd6c8ace..17c7690f1 100644
--- a/src/core/hle/kernel/k_memory_manager.h
+++ b/src/core/hle/kernel/k_memory_manager.h
@@ -8,6 +8,7 @@
 #include <mutex>
 #include <tuple>
 
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/hle/kernel/k_page_heap.h"
 #include "core/hle/result.h"
@@ -20,8 +21,11 @@ namespace Kernel {
 
 class KPageLinkedList;
 
-class KMemoryManager final : NonCopyable {
+class KMemoryManager final {
 public:
+    YUZU_NON_COPYABLE(KMemoryManager);
+    YUZU_NON_MOVEABLE(KMemoryManager);
+
     enum class Pool : u32 {
         Application = 0,
         Applet = 1,
@@ -88,26 +92,13 @@ public:
     }
 
 private:
-    class Impl final : NonCopyable {
-    private:
-        using RefCount = u16;
-
-    private:
-        KPageHeap heap;
-        Pool pool{};
-
+    class Impl final {
     public:
-        static std::size_t CalculateManagementOverheadSize(std::size_t region_size);
-
-        static constexpr std::size_t CalculateOptimizedProcessOverheadSize(
-            std::size_t region_size) {
-            return (Common::AlignUp((region_size / PageSize), Common::BitSize<u64>()) /
-                    Common::BitSize<u64>()) *
-                   sizeof(u64);
-        }
+        YUZU_NON_COPYABLE(Impl);
+        YUZU_NON_MOVEABLE(Impl);
 
-    public:
         Impl() = default;
+        ~Impl() = default;
 
         std::size_t Initialize(Pool new_pool, u64 start_address, u64 end_address);
 
@@ -130,6 +121,21 @@ private:
         constexpr VAddr GetEndAddress() const {
             return heap.GetEndAddress();
         }
+
+        static std::size_t CalculateManagementOverheadSize(std::size_t region_size);
+
+        static constexpr std::size_t CalculateOptimizedProcessOverheadSize(
+            std::size_t region_size) {
+            return (Common::AlignUp((region_size / PageSize), Common::BitSize<u64>()) /
+                    Common::BitSize<u64>()) *
+                   sizeof(u64);
+        }
+
+    private:
+        using RefCount = u16;
+
+        KPageHeap heap;
+        Pool pool{};
     };
 
 private:
diff --git a/src/core/hle/kernel/k_memory_region.h b/src/core/hle/kernel/k_memory_region.h
index 90ab8fd62..e9bdf4e59 100644
--- a/src/core/hle/kernel/k_memory_region.h
+++ b/src/core/hle/kernel/k_memory_region.h
@@ -5,6 +5,7 @@
 #pragma once
 
 #include "common/assert.h"
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "common/intrusive_red_black_tree.h"
 #include "core/hle/kernel/k_memory_region_type.h"
@@ -13,11 +14,13 @@ namespace Kernel {
 
 class KMemoryRegionAllocator;
 
-class KMemoryRegion final : public Common::IntrusiveRedBlackTreeBaseNode<KMemoryRegion>,
-                            NonCopyable {
+class KMemoryRegion final : public Common::IntrusiveRedBlackTreeBaseNode<KMemoryRegion> {
     friend class KMemoryRegionTree;
 
 public:
+    YUZU_NON_COPYABLE(KMemoryRegion);
+    YUZU_NON_MOVEABLE(KMemoryRegion);
+
     constexpr KMemoryRegion() = default;
     constexpr KMemoryRegion(u64 address_, u64 last_address_)
         : address{address_}, last_address{last_address_} {}
@@ -29,6 +32,8 @@ public:
         : KMemoryRegion(address_, last_address_, std::numeric_limits<u64>::max(), attributes_,
                         type_id_) {}
 
+    ~KMemoryRegion() = default;
+
     static constexpr int Compare(const KMemoryRegion& lhs, const KMemoryRegion& rhs) {
         if (lhs.GetAddress() < rhs.GetAddress()) {
             return -1;
@@ -39,16 +44,6 @@ public:
         }
     }
 
-private:
-    constexpr void Reset(u64 a, u64 la, u64 p, u32 r, u32 t) {
-        address = a;
-        pair_address = p;
-        last_address = la;
-        attributes = r;
-        type_id = t;
-    }
-
-public:
     constexpr u64 GetAddress() const {
         return address;
     }
@@ -108,6 +103,14 @@ public:
     }
 
 private:
+    constexpr void Reset(u64 a, u64 la, u64 p, u32 r, u32 t) {
+        address = a;
+        pair_address = p;
+        last_address = la;
+        attributes = r;
+        type_id = t;
+    }
+
     u64 address{};
     u64 last_address{};
     u64 pair_address{};
@@ -115,8 +118,25 @@ private:
     u32 type_id{};
 };
 
-class KMemoryRegionTree final : NonCopyable {
+class KMemoryRegionTree final {
+private:
+    using TreeType =
+        Common::IntrusiveRedBlackTreeBaseTraits<KMemoryRegion>::TreeType<KMemoryRegion>;
+
 public:
+    YUZU_NON_COPYABLE(KMemoryRegionTree);
+    YUZU_NON_MOVEABLE(KMemoryRegionTree);
+
+    using value_type = TreeType::value_type;
+    using size_type = TreeType::size_type;
+    using difference_type = TreeType::difference_type;
+    using pointer = TreeType::pointer;
+    using const_pointer = TreeType::const_pointer;
+    using reference = TreeType::reference;
+    using const_reference = TreeType::const_reference;
+    using iterator = TreeType::iterator;
+    using const_iterator = TreeType::const_iterator;
+
     struct DerivedRegionExtents {
         const KMemoryRegion* first_region{};
         const KMemoryRegion* last_region{};
@@ -140,29 +160,9 @@ public:
         }
     };
 
-private:
-    using TreeType =
-        Common::IntrusiveRedBlackTreeBaseTraits<KMemoryRegion>::TreeType<KMemoryRegion>;
-
-public:
-    using value_type = TreeType::value_type;
-    using size_type = TreeType::size_type;
-    using difference_type = TreeType::difference_type;
-    using pointer = TreeType::pointer;
-    using const_pointer = TreeType::const_pointer;
-    using reference = TreeType::reference;
-    using const_reference = TreeType::const_reference;
-    using iterator = TreeType::iterator;
-    using const_iterator = TreeType::const_iterator;
-
-private:
-    TreeType m_tree{};
-    KMemoryRegionAllocator& memory_region_allocator;
-
-public:
     explicit KMemoryRegionTree(KMemoryRegionAllocator& memory_region_allocator_);
+    ~KMemoryRegionTree() = default;
 
-public:
     KMemoryRegion* FindModifiable(u64 address) {
         if (auto it = this->find(KMemoryRegion(address, address, 0, 0)); it != this->end()) {
             return std::addressof(*it);
@@ -241,7 +241,6 @@ public:
         return GetDerivedRegionExtents(static_cast<KMemoryRegionType>(type_id));
     }
 
-public:
     void InsertDirectly(u64 address, u64 last_address, u32 attr = 0, u32 type_id = 0);
     bool Insert(u64 address, size_t size, u32 type_id, u32 new_attr = 0, u32 old_attr = 0);
 
@@ -252,7 +251,6 @@ public:
         return this->GetRandomAlignedRegion(size + 2 * guard_size, alignment, type_id) + guard_size;
     }
 
-public:
     // Iterator accessors.
     iterator begin() {
         return m_tree.begin();
@@ -322,13 +320,21 @@ public:
     iterator nfind(const_reference ref) const {
         return m_tree.nfind(ref);
     }
+
+private:
+    TreeType m_tree{};
+    KMemoryRegionAllocator& memory_region_allocator;
 };
 
-class KMemoryRegionAllocator final : NonCopyable {
+class KMemoryRegionAllocator final {
 public:
+    YUZU_NON_COPYABLE(KMemoryRegionAllocator);
+    YUZU_NON_MOVEABLE(KMemoryRegionAllocator);
+
     static constexpr size_t MaxMemoryRegions = 200;
 
     constexpr KMemoryRegionAllocator() = default;
+    constexpr ~KMemoryRegionAllocator() = default;
 
     template <typename... Args>
     KMemoryRegion* Allocate(Args&&... args) {
diff --git a/src/core/hle/kernel/k_page_heap.h b/src/core/hle/kernel/k_page_heap.h
index 8d9f30523..a65aa28a0 100644
--- a/src/core/hle/kernel/k_page_heap.h
+++ b/src/core/hle/kernel/k_page_heap.h
@@ -8,14 +8,44 @@
 #include <vector>
 
 #include "common/alignment.h"
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/hle/kernel/k_page_bitmap.h"
 #include "core/hle/kernel/memory_types.h"
 
 namespace Kernel {
 
-class KPageHeap final : NonCopyable {
+class KPageHeap final {
 public:
+    YUZU_NON_COPYABLE(KPageHeap);
+    YUZU_NON_MOVEABLE(KPageHeap);
+
+    KPageHeap() = default;
+    ~KPageHeap() = default;
+
+    constexpr VAddr GetAddress() const {
+        return heap_address;
+    }
+    constexpr std::size_t GetSize() const {
+        return heap_size;
+    }
+    constexpr VAddr GetEndAddress() const {
+        return GetAddress() + GetSize();
+    }
+    constexpr std::size_t GetPageOffset(VAddr block) const {
+        return (block - GetAddress()) / PageSize;
+    }
+
+    void Initialize(VAddr heap_address, std::size_t heap_size, std::size_t metadata_size);
+    VAddr AllocateBlock(s32 index, bool random);
+    void Free(VAddr addr, std::size_t num_pages);
+
+    void UpdateUsedSize() {
+        used_size = heap_size - (GetNumFreePages() * PageSize);
+    }
+
+    static std::size_t CalculateManagementOverheadSize(std::size_t region_size);
+
     static constexpr s32 GetAlignedBlockIndex(std::size_t num_pages, std::size_t align_pages) {
         const auto target_pages{std::max(num_pages, align_pages)};
         for (std::size_t i = 0; i < NumMemoryBlockPageShifts; i++) {
@@ -45,21 +75,13 @@ public:
     }
 
 private:
-    static constexpr std::size_t NumMemoryBlockPageShifts{7};
-    static constexpr std::array<std::size_t, NumMemoryBlockPageShifts> MemoryBlockPageShifts{
-        0xC, 0x10, 0x15, 0x16, 0x19, 0x1D, 0x1E,
-    };
-
-    class Block final : NonCopyable {
-    private:
-        KPageBitmap bitmap;
-        VAddr heap_address{};
-        uintptr_t end_offset{};
-        std::size_t block_shift{};
-        std::size_t next_block_shift{};
-
+    class Block final {
     public:
+        YUZU_NON_COPYABLE(Block);
+        YUZU_NON_MOVEABLE(Block);
+
         Block() = default;
+        ~Block() = default;
 
         constexpr std::size_t GetShift() const {
             return block_shift;
@@ -129,7 +151,6 @@ private:
             return heap_address + (offset << GetShift());
         }
 
-    public:
         static constexpr std::size_t CalculateManagementOverheadSize(std::size_t region_size,
                                                                      std::size_t cur_block_shift,
                                                                      std::size_t next_block_shift) {
@@ -139,35 +160,15 @@ private:
             return KPageBitmap::CalculateManagementOverheadSize(
                 (align * 2 + Common::AlignUp(region_size, align)) / cur_block_size);
         }
-    };
-
-public:
-    KPageHeap() = default;
-
-    constexpr VAddr GetAddress() const {
-        return heap_address;
-    }
-    constexpr std::size_t GetSize() const {
-        return heap_size;
-    }
-    constexpr VAddr GetEndAddress() const {
-        return GetAddress() + GetSize();
-    }
-    constexpr std::size_t GetPageOffset(VAddr block) const {
-        return (block - GetAddress()) / PageSize;
-    }
 
-    void Initialize(VAddr heap_address, std::size_t heap_size, std::size_t metadata_size);
-    VAddr AllocateBlock(s32 index, bool random);
-    void Free(VAddr addr, std::size_t num_pages);
-
-    void UpdateUsedSize() {
-        used_size = heap_size - (GetNumFreePages() * PageSize);
-    }
-
-    static std::size_t CalculateManagementOverheadSize(std::size_t region_size);
+    private:
+        KPageBitmap bitmap;
+        VAddr heap_address{};
+        uintptr_t end_offset{};
+        std::size_t block_shift{};
+        std::size_t next_block_shift{};
+    };
 
-private:
     constexpr std::size_t GetNumFreePages() const {
         std::size_t num_free{};
 
@@ -180,6 +181,11 @@ private:
 
     void FreeBlock(VAddr block, s32 index);
 
+    static constexpr std::size_t NumMemoryBlockPageShifts{7};
+    static constexpr std::array<std::size_t, NumMemoryBlockPageShifts> MemoryBlockPageShifts{
+        0xC, 0x10, 0x15, 0x16, 0x19, 0x1D, 0x1E,
+    };
+
     VAddr heap_address{};
     std::size_t heap_size{};
     std::size_t used_size{};
diff --git a/src/core/hle/kernel/k_page_table.cpp b/src/core/hle/kernel/k_page_table.cpp
index 2ebbc0819..912853e5c 100644
--- a/src/core/hle/kernel/k_page_table.cpp
+++ b/src/core/hle/kernel/k_page_table.cpp
@@ -61,7 +61,10 @@ constexpr std::size_t GetSizeInRange(const KMemoryInfo& info, VAddr start, VAddr
 
 } // namespace
 
-KPageTable::KPageTable(Core::System& system_) : system{system_} {}
+KPageTable::KPageTable(Core::System& system_)
+    : general_lock{system_.Kernel()}, map_physical_memory_lock{system_.Kernel()}, system{system_} {}
+
+KPageTable::~KPageTable() = default;
 
 ResultCode KPageTable::InitializeForProcess(FileSys::ProgramAddressSpaceType as_type,
                                             bool enable_aslr, VAddr code_addr,
@@ -282,7 +285,7 @@ ResultCode KPageTable::MapProcessCode(VAddr addr, std::size_t num_pages, KMemory
     R_UNLESS(this->CanContain(addr, size, state), ResultInvalidCurrentMemory);
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Verify that the destination memory is unmapped.
     R_TRY(this->CheckMemoryState(addr, size, KMemoryState::All, KMemoryState::Free,
@@ -300,7 +303,7 @@ ResultCode KPageTable::MapProcessCode(VAddr addr, std::size_t num_pages, KMemory
 }
 
 ResultCode KPageTable::MapCodeMemory(VAddr dst_addr, VAddr src_addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     const std::size_t num_pages{size / PageSize};
 
@@ -337,7 +340,7 @@ ResultCode KPageTable::MapCodeMemory(VAddr dst_addr, VAddr src_addr, std::size_t
 }
 
 ResultCode KPageTable::UnmapCodeMemory(VAddr dst_addr, VAddr src_addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     if (!size) {
         return ResultSuccess;
@@ -371,7 +374,7 @@ ResultCode KPageTable::UnmapCodeMemory(VAddr dst_addr, VAddr src_addr, std::size
 
 ResultCode KPageTable::UnmapProcessMemory(VAddr dst_addr, std::size_t size,
                                           KPageTable& src_page_table, VAddr src_addr) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     const std::size_t num_pages{size / PageSize};
 
@@ -399,10 +402,10 @@ ResultCode KPageTable::UnmapProcessMemory(VAddr dst_addr, std::size_t size,
 
 ResultCode KPageTable::MapPhysicalMemory(VAddr addr, std::size_t size) {
     // Lock the physical memory lock.
-    std::lock_guard phys_lk(map_physical_memory_lock);
+    KScopedLightLock map_phys_mem_lk(map_physical_memory_lock);
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     std::size_t mapped_size{};
     const VAddr end_addr{addr + size};
@@ -478,7 +481,11 @@ ResultCode KPageTable::MapPhysicalMemory(VAddr addr, std::size_t size) {
 }
 
 ResultCode KPageTable::UnmapPhysicalMemory(VAddr addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    // Lock the physical memory lock.
+    KScopedLightLock map_phys_mem_lk(map_physical_memory_lock);
+
+    // Lock the table.
+    KScopedLightLock lk(general_lock);
 
     const VAddr end_addr{addr + size};
     ResultCode result{ResultSuccess};
@@ -540,7 +547,7 @@ ResultCode KPageTable::UnmapPhysicalMemory(VAddr addr, std::size_t size) {
 }
 
 ResultCode KPageTable::MapMemory(VAddr dst_addr, VAddr src_addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryState src_state{};
     CASCADE_CODE(CheckMemoryState(
@@ -579,7 +586,7 @@ ResultCode KPageTable::MapMemory(VAddr dst_addr, VAddr src_addr, std::size_t siz
 }
 
 ResultCode KPageTable::UnmapMemory(VAddr dst_addr, VAddr src_addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryState src_state{};
     CASCADE_CODE(CheckMemoryState(
@@ -622,6 +629,8 @@ ResultCode KPageTable::UnmapMemory(VAddr dst_addr, VAddr src_addr, std::size_t s
 
 ResultCode KPageTable::MapPages(VAddr addr, const KPageLinkedList& page_linked_list,
                                 KMemoryPermission perm) {
+    ASSERT(this->IsLockedByCurrentThread());
+
     VAddr cur_addr{addr};
 
     for (const auto& node : page_linked_list.Nodes()) {
@@ -650,7 +659,7 @@ ResultCode KPageTable::MapPages(VAddr address, KPageLinkedList& page_linked_list
     R_UNLESS(this->CanContain(address, size, state), ResultInvalidCurrentMemory);
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Check the memory state.
     R_TRY(this->CheckMemoryState(address, size, KMemoryState::All, KMemoryState::Free,
@@ -667,6 +676,8 @@ ResultCode KPageTable::MapPages(VAddr address, KPageLinkedList& page_linked_list
 }
 
 ResultCode KPageTable::UnmapPages(VAddr addr, const KPageLinkedList& page_linked_list) {
+    ASSERT(this->IsLockedByCurrentThread());
+
     VAddr cur_addr{addr};
 
     for (const auto& node : page_linked_list.Nodes()) {
@@ -691,7 +702,7 @@ ResultCode KPageTable::UnmapPages(VAddr addr, KPageLinkedList& page_linked_list,
     R_UNLESS(this->Contains(addr, size), ResultInvalidCurrentMemory);
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Check the memory state.
     R_TRY(this->CheckMemoryState(addr, size, KMemoryState::All, state, KMemoryPermission::None,
@@ -712,7 +723,7 @@ ResultCode KPageTable::SetProcessMemoryPermission(VAddr addr, std::size_t size,
     const size_t num_pages = size / PageSize;
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Verify we can change the memory permission.
     KMemoryState old_state;
@@ -766,7 +777,7 @@ ResultCode KPageTable::SetProcessMemoryPermission(VAddr addr, std::size_t size,
 }
 
 KMemoryInfo KPageTable::QueryInfoImpl(VAddr addr) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     return block_manager->FindBlock(addr).GetMemoryInfo();
 }
@@ -781,7 +792,7 @@ KMemoryInfo KPageTable::QueryInfo(VAddr addr) {
 }
 
 ResultCode KPageTable::ReserveTransferMemory(VAddr addr, std::size_t size, KMemoryPermission perm) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryState state{};
     KMemoryAttribute attribute{};
@@ -799,7 +810,7 @@ ResultCode KPageTable::ReserveTransferMemory(VAddr addr, std::size_t size, KMemo
 }
 
 ResultCode KPageTable::ResetTransferMemory(VAddr addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryState state{};
 
@@ -818,7 +829,7 @@ ResultCode KPageTable::SetMemoryPermission(VAddr addr, std::size_t size,
     const size_t num_pages = size / PageSize;
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Verify we can change the memory permission.
     KMemoryState old_state;
@@ -847,7 +858,7 @@ ResultCode KPageTable::SetMemoryAttribute(VAddr addr, std::size_t size, u32 mask
            KMemoryAttribute::SetMask);
 
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Verify we can change the memory attribute.
     KMemoryState old_state;
@@ -878,7 +889,7 @@ ResultCode KPageTable::SetMemoryAttribute(VAddr addr, std::size_t size, u32 mask
 
 ResultCode KPageTable::SetMaxHeapSize(std::size_t size) {
     // Lock the table.
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     // Only process page tables are allowed to set heap size.
     ASSERT(!this->IsKernel());
@@ -889,15 +900,15 @@ ResultCode KPageTable::SetMaxHeapSize(std::size_t size) {
 }
 
 ResultCode KPageTable::SetHeapSize(VAddr* out, std::size_t size) {
-    // Lock the physical memory lock.
-    std::lock_guard phys_lk(map_physical_memory_lock);
+    // Lock the physical memory mutex.
+    KScopedLightLock map_phys_mem_lk(map_physical_memory_lock);
 
     // Try to perform a reduction in heap, instead of an extension.
     VAddr cur_address{};
     std::size_t allocation_size{};
     {
         // Lock the table.
-        std::lock_guard lk(page_table_lock);
+        KScopedLightLock lk(general_lock);
 
         // Validate that setting heap size is possible at all.
         R_UNLESS(!is_kernel, ResultOutOfMemory);
@@ -962,7 +973,7 @@ ResultCode KPageTable::SetHeapSize(VAddr* out, std::size_t size) {
     // Map the pages.
     {
         // Lock the table.
-        std::lock_guard lk(page_table_lock);
+        KScopedLightLock lk(general_lock);
 
         // Ensure that the heap hasn't changed since we began executing.
         ASSERT(cur_address == current_heap_end);
@@ -1004,7 +1015,7 @@ ResultVal<VAddr> KPageTable::AllocateAndMapMemory(std::size_t needed_num_pages,
                                                   bool is_map_only, VAddr region_start,
                                                   std::size_t region_num_pages, KMemoryState state,
                                                   KMemoryPermission perm, PAddr map_addr) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     if (!CanContain(region_start, region_num_pages * PageSize, state)) {
         return ResultInvalidCurrentMemory;
@@ -1035,7 +1046,7 @@ ResultVal<VAddr> KPageTable::AllocateAndMapMemory(std::size_t needed_num_pages,
 }
 
 ResultCode KPageTable::LockForDeviceAddressSpace(VAddr addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryPermission perm{};
     if (const ResultCode result{CheckMemoryState(
@@ -1058,7 +1069,7 @@ ResultCode KPageTable::LockForDeviceAddressSpace(VAddr addr, std::size_t size) {
 }
 
 ResultCode KPageTable::UnlockForDeviceAddressSpace(VAddr addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryPermission perm{};
     if (const ResultCode result{CheckMemoryState(
@@ -1081,7 +1092,7 @@ ResultCode KPageTable::UnlockForDeviceAddressSpace(VAddr addr, std::size_t size)
 }
 
 ResultCode KPageTable::LockForCodeMemory(VAddr addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryPermission new_perm = KMemoryPermission::NotMapped | KMemoryPermission::KernelReadWrite;
 
@@ -1108,7 +1119,7 @@ ResultCode KPageTable::LockForCodeMemory(VAddr addr, std::size_t size) {
 }
 
 ResultCode KPageTable::UnlockForCodeMemory(VAddr addr, std::size_t size) {
-    std::lock_guard lock{page_table_lock};
+    KScopedLightLock lk(general_lock);
 
     KMemoryPermission new_perm = KMemoryPermission::UserReadWrite;
 
diff --git a/src/core/hle/kernel/k_page_table.h b/src/core/hle/kernel/k_page_table.h
index 60ae9b9e8..c98887d34 100644
--- a/src/core/hle/kernel/k_page_table.h
+++ b/src/core/hle/kernel/k_page_table.h
@@ -5,11 +5,12 @@
 #pragma once
 
 #include <memory>
-#include <mutex>
 
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "common/page_table.h"
 #include "core/file_sys/program_metadata.h"
+#include "core/hle/kernel/k_light_lock.h"
 #include "core/hle/kernel/k_memory_block.h"
 #include "core/hle/kernel/k_memory_manager.h"
 #include "core/hle/result.h"
@@ -22,9 +23,13 @@ namespace Kernel {
 
 class KMemoryBlockManager;
 
-class KPageTable final : NonCopyable {
+class KPageTable final {
 public:
+    YUZU_NON_COPYABLE(KPageTable);
+    YUZU_NON_MOVEABLE(KPageTable);
+
     explicit KPageTable(Core::System& system_);
+    ~KPageTable();
 
     ResultCode InitializeForProcess(FileSys::ProgramAddressSpaceType as_type, bool enable_aslr,
                                     VAddr code_addr, std::size_t code_size,
@@ -142,11 +147,12 @@ private:
     }
 
     bool IsLockedByCurrentThread() const {
-        return true;
+        return general_lock.IsLockedByCurrentThread();
     }
 
-    std::recursive_mutex page_table_lock;
-    std::mutex map_physical_memory_lock;
+    mutable KLightLock general_lock;
+    mutable KLightLock map_physical_memory_lock;
+
     std::unique_ptr<KMemoryBlockManager> block_manager;
 
 public:
@@ -205,7 +211,7 @@ public:
         return alias_code_region_end - alias_code_region_start;
     }
     size_t GetNormalMemorySize() {
-        std::lock_guard lk(page_table_lock);
+        KScopedLightLock lk(general_lock);
         return GetHeapSize() + mapped_physical_memory_size;
     }
     constexpr std::size_t GetAddressSpaceWidth() const {
@@ -247,7 +253,9 @@ public:
     constexpr bool IsInsideASLRRegion(VAddr address, std::size_t size) const {
         return !IsOutsideASLRRegion(address, size);
     }
-    constexpr PAddr GetPhysicalAddr(VAddr addr) {
+
+    PAddr GetPhysicalAddr(VAddr addr) {
+        ASSERT(IsLockedByCurrentThread());
         const auto backing_addr = page_table_impl.backing_addr[addr >> PageBits];
         ASSERT(backing_addr);
         return backing_addr + addr;
diff --git a/src/core/hle/kernel/k_slab_heap.h b/src/core/hle/kernel/k_slab_heap.h
index 0ad74b0a0..05c0bec9c 100644
--- a/src/core/hle/kernel/k_slab_heap.h
+++ b/src/core/hle/kernel/k_slab_heap.h
@@ -7,6 +7,7 @@
 #include <atomic>
 
 #include "common/assert.h"
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 
 namespace Kernel {
@@ -15,13 +16,17 @@ class KernelCore;
 
 namespace impl {
 
-class KSlabHeapImpl final : NonCopyable {
+class KSlabHeapImpl final {
 public:
+    YUZU_NON_COPYABLE(KSlabHeapImpl);
+    YUZU_NON_MOVEABLE(KSlabHeapImpl);
+
     struct Node {
         Node* next{};
     };
 
     constexpr KSlabHeapImpl() = default;
+    constexpr ~KSlabHeapImpl() = default;
 
     void Initialize(std::size_t size) {
         ASSERT(head == nullptr);
@@ -64,9 +69,13 @@ private:
 
 } // namespace impl
 
-class KSlabHeapBase : NonCopyable {
+class KSlabHeapBase {
 public:
+    YUZU_NON_COPYABLE(KSlabHeapBase);
+    YUZU_NON_MOVEABLE(KSlabHeapBase);
+
     constexpr KSlabHeapBase() = default;
+    constexpr ~KSlabHeapBase() = default;
 
     constexpr bool Contains(uintptr_t addr) const {
         return start <= addr && addr < end;
diff --git a/src/core/hle/service/vi/display/vi_display.h b/src/core/hle/service/vi/display/vi_display.h
index 0979fc421..329f4ba86 100644
--- a/src/core/hle/service/vi/display/vi_display.h
+++ b/src/core/hle/service/vi/display/vi_display.h
@@ -28,10 +28,10 @@ class Layer;
 
 /// Represents a single display type
 class Display {
+public:
     YUZU_NON_COPYABLE(Display);
     YUZU_NON_MOVEABLE(Display);
 
-public:
     /// Constructs a display with a given unique ID and name.
     ///
     /// @param id The unique ID for this display.
diff --git a/src/core/loader/loader.h b/src/core/loader/loader.h
index 7b1bac3f7..8b6b3b68f 100644
--- a/src/core/loader/loader.h
+++ b/src/core/loader/loader.h
@@ -11,6 +11,7 @@
 #include <utility>
 #include <vector>
 
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/file_sys/control_metadata.h"
 #include "core/file_sys/vfs.h"
@@ -139,8 +140,11 @@ std::string GetResultStatusString(ResultStatus status);
 std::ostream& operator<<(std::ostream& os, ResultStatus status);
 
 /// Interface for loading an application
-class AppLoader : NonCopyable {
+class AppLoader {
 public:
+    YUZU_NON_COPYABLE(AppLoader);
+    YUZU_NON_MOVEABLE(AppLoader);
+
     struct LoadParameters {
         s32 main_thread_priority;
         u64 main_thread_stack_size;
diff --git a/src/input_common/drivers/udp_client.cpp b/src/input_common/drivers/udp_client.cpp
index d1cdb1ab2..333173e3d 100644
--- a/src/input_common/drivers/udp_client.cpp
+++ b/src/input_common/drivers/udp_client.cpp
@@ -271,7 +271,7 @@ void UDPClient::OnPadData(Response::PadData data, std::size_t client) {
         const auto touch_axis_y_id =
             static_cast<int>(id == 0 ? PadAxes::Touch1Y : PadAxes::Touch2Y);
         const auto touch_button_id =
-            static_cast<int>(id == 0 ? PadButton::Touch1 : PadButton::touch2);
+            static_cast<int>(id == 0 ? PadButton::Touch1 : PadButton::Touch2);
 
         // TODO: Use custom calibration per device
         const Common::ParamPackage touch_param(Settings::values.touch_device.GetValue());
@@ -319,6 +319,9 @@ void UDPClient::OnPadData(Response::PadData data, std::size_t client) {
         SetButton(identifier, button, button_status);
     }
 
+    SetButton(identifier, static_cast<int>(PadButton::Home), data.home != 0);
+    SetButton(identifier, static_cast<int>(PadButton::TouchHardPress), data.touch_hard_press != 0);
+
     SetBattery(identifier, GetBatteryLevel(data.info.battery));
 }
 
@@ -393,7 +396,7 @@ std::vector<Common::ParamPackage> UDPClient::GetInputDevices() const {
 
 ButtonMapping UDPClient::GetButtonMappingForDevice(const Common::ParamPackage& params) {
     // This list excludes any button that can't be really mapped
-    static constexpr std::array<std::pair<Settings::NativeButton::Values, PadButton>, 18>
+    static constexpr std::array<std::pair<Settings::NativeButton::Values, PadButton>, 20>
         switch_to_dsu_button = {
             std::pair{Settings::NativeButton::A, PadButton::Circle},
             {Settings::NativeButton::B, PadButton::Cross},
@@ -413,6 +416,8 @@ ButtonMapping UDPClient::GetButtonMappingForDevice(const Common::ParamPackage& p
             {Settings::NativeButton::SR, PadButton::R2},
             {Settings::NativeButton::LStick, PadButton::L3},
             {Settings::NativeButton::RStick, PadButton::R3},
+            {Settings::NativeButton::Home, PadButton::Home},
+            {Settings::NativeButton::Screenshot, PadButton::TouchHardPress},
         };
     if (!params.Has("guid") || !params.Has("port") || !params.Has("pad")) {
         return {};
@@ -517,6 +522,12 @@ Common::Input::ButtonNames UDPClient::GetUIButtonName(const Common::ParamPackage
         return Common::Input::ButtonNames::Share;
     case PadButton::Options:
         return Common::Input::ButtonNames::Options;
+    case PadButton::Home:
+        return Common::Input::ButtonNames::Home;
+    case PadButton::Touch1:
+    case PadButton::Touch2:
+    case PadButton::TouchHardPress:
+        return Common::Input::ButtonNames::Touch;
     default:
         return Common::Input::ButtonNames::Undefined;
     }
diff --git a/src/input_common/drivers/udp_client.h b/src/input_common/drivers/udp_client.h
index 30d7c2682..e9c178139 100644
--- a/src/input_common/drivers/udp_client.h
+++ b/src/input_common/drivers/udp_client.h
@@ -84,7 +84,9 @@ private:
         Cross = 0x4000,
         Square = 0x8000,
         Touch1 = 0x10000,
-        touch2 = 0x20000,
+        Touch2 = 0x20000,
+        Home = 0x40000,
+        TouchHardPress = 0x80000,
     };
 
     enum class PadAxes : u8 {
diff --git a/src/input_common/helpers/stick_from_buttons.cpp b/src/input_common/helpers/stick_from_buttons.cpp
index e23394f5f..31e6f62ab 100644
--- a/src/input_common/helpers/stick_from_buttons.cpp
+++ b/src/input_common/helpers/stick_from_buttons.cpp
@@ -167,12 +167,34 @@ public:
     }
 
     void UpdateModButtonStatus(const Common::Input::CallbackStatus& button_callback) {
-        modifier_status = button_callback.button_status.value;
+        const auto& new_status = button_callback.button_status;
+        const bool new_button_value = new_status.inverted ? !new_status.value : new_status.value;
+        modifier_status.toggle = new_status.toggle;
+
+        // Update button status with current
+        if (!modifier_status.toggle) {
+            modifier_status.locked = false;
+            if (modifier_status.value != new_button_value) {
+                modifier_status.value = new_button_value;
+            }
+        } else {
+            // Toggle button and lock status
+            if (new_button_value && !modifier_status.locked) {
+                modifier_status.locked = true;
+                modifier_status.value = !modifier_status.value;
+            }
+
+            // Unlock button ready for next press
+            if (!new_button_value && modifier_status.locked) {
+                modifier_status.locked = false;
+            }
+        }
+
         UpdateStatus();
     }
 
     void UpdateStatus() {
-        const float coef = modifier_status ? modifier_scale : 1.0f;
+        const float coef = modifier_status.value ? modifier_scale : 1.0f;
 
         bool r = right_status;
         bool l = left_status;
@@ -266,7 +288,7 @@ public:
         if (down_status) {
             --y;
         }
-        const float coef = modifier_status ? modifier_scale : 1.0f;
+        const float coef = modifier_status.value ? modifier_scale : 1.0f;
         status.x.raw_value = static_cast<float>(x) * coef * (y == 0 ? 1.0f : SQRT_HALF);
         status.y.raw_value = static_cast<float>(y) * coef * (x == 0 ? 1.0f : SQRT_HALF);
         return status;
@@ -287,9 +309,9 @@ private:
     bool down_status{};
     bool left_status{};
     bool right_status{};
-    bool modifier_status{};
     float last_x_axis_value{};
     float last_y_axis_value{};
+    Common::Input::ButtonStatus modifier_status{};
     const Common::Input::AnalogProperties properties{0.0f, 1.0f, 0.5f, 0.0f, false};
     std::chrono::time_point<std::chrono::steady_clock> last_update;
 };
diff --git a/src/input_common/helpers/touch_from_buttons.cpp b/src/input_common/helpers/touch_from_buttons.cpp
index ece1e3b32..f1b57d03a 100644
--- a/src/input_common/helpers/touch_from_buttons.cpp
+++ b/src/input_common/helpers/touch_from_buttons.cpp
@@ -4,7 +4,6 @@
 
 #include <algorithm>
 #include "common/settings.h"
-#include "core/frontend/framebuffer_layout.h"
 #include "input_common/helpers/touch_from_buttons.h"
 
 namespace InputCommon {
diff --git a/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h b/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h
index b48007856..5efbe4e6f 100644
--- a/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h
+++ b/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h
@@ -372,6 +372,8 @@ void EmitSharedAtomicExchange32(EmitContext& ctx, IR::Inst& inst, ScalarU32 poin
                                 ScalarU32 value);
 void EmitSharedAtomicExchange64(EmitContext& ctx, IR::Inst& inst, ScalarU32 pointer_offset,
                                 Register value);
+void EmitSharedAtomicExchange32x2(EmitContext& ctx, IR::Inst& inst, ScalarU32 pointer_offset,
+                                  Register value);
 void EmitStorageAtomicIAdd32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              ScalarU32 offset, ScalarU32 value);
 void EmitStorageAtomicSMin32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
@@ -412,6 +414,24 @@ void EmitStorageAtomicXor64(EmitContext& ctx, IR::Inst& inst, const IR::Value& b
                             ScalarU32 offset, Register value);
 void EmitStorageAtomicExchange64(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                                  ScalarU32 offset, Register value);
+void EmitStorageAtomicIAdd32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               ScalarU32 offset, Register value);
+void EmitStorageAtomicSMin32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               ScalarU32 offset, Register value);
+void EmitStorageAtomicUMin32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               ScalarU32 offset, Register value);
+void EmitStorageAtomicSMax32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               ScalarU32 offset, Register value);
+void EmitStorageAtomicUMax32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               ScalarU32 offset, Register value);
+void EmitStorageAtomicAnd32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                              ScalarU32 offset, Register value);
+void EmitStorageAtomicOr32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                             ScalarU32 offset, Register value);
+void EmitStorageAtomicXor32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                              ScalarU32 offset, Register value);
+void EmitStorageAtomicExchange32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                                   ScalarU32 offset, Register value);
 void EmitStorageAtomicAddF32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              ScalarU32 offset, ScalarF32 value);
 void EmitStorageAtomicAddF16x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
@@ -448,6 +468,17 @@ void EmitGlobalAtomicAnd64(EmitContext& ctx);
 void EmitGlobalAtomicOr64(EmitContext& ctx);
 void EmitGlobalAtomicXor64(EmitContext& ctx);
 void EmitGlobalAtomicExchange64(EmitContext& ctx);
+void EmitGlobalAtomicIAdd32x2(EmitContext& ctx);
+void EmitGlobalAtomicSMin32x2(EmitContext& ctx);
+void EmitGlobalAtomicUMin32x2(EmitContext& ctx);
+void EmitGlobalAtomicSMax32x2(EmitContext& ctx);
+void EmitGlobalAtomicUMax32x2(EmitContext& ctx);
+void EmitGlobalAtomicInc32x2(EmitContext& ctx);
+void EmitGlobalAtomicDec32x2(EmitContext& ctx);
+void EmitGlobalAtomicAnd32x2(EmitContext& ctx);
+void EmitGlobalAtomicOr32x2(EmitContext& ctx);
+void EmitGlobalAtomicXor32x2(EmitContext& ctx);
+void EmitGlobalAtomicExchange32x2(EmitContext& ctx);
 void EmitGlobalAtomicAddF32(EmitContext& ctx);
 void EmitGlobalAtomicAddF16x2(EmitContext& ctx);
 void EmitGlobalAtomicAddF32x2(EmitContext& ctx);
diff --git a/src/shader_recompiler/backend/glasm/emit_glasm_memory.cpp b/src/shader_recompiler/backend/glasm/emit_glasm_memory.cpp
index f135b67f5..f0fd94a28 100644
--- a/src/shader_recompiler/backend/glasm/emit_glasm_memory.cpp
+++ b/src/shader_recompiler/backend/glasm/emit_glasm_memory.cpp
@@ -311,6 +311,13 @@ void EmitSharedAtomicExchange64(EmitContext& ctx, IR::Inst& inst, ScalarU32 poin
     ctx.LongAdd("ATOMS.EXCH.U64 {}.x,{},shared_mem[{}];", inst, value, pointer_offset);
 }
 
+void EmitSharedAtomicExchange32x2([[maybe_unused]] EmitContext& ctx,
+                                  [[maybe_unused]] IR::Inst& inst,
+                                  [[maybe_unused]] ScalarU32 pointer_offset,
+                                  [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
 void EmitStorageAtomicIAdd32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              ScalarU32 offset, ScalarU32 value) {
     Atom(ctx, inst, binding, offset, value, "ADD", "U32");
@@ -411,6 +418,62 @@ void EmitStorageAtomicExchange64(EmitContext& ctx, IR::Inst& inst, const IR::Val
     Atom(ctx, inst, binding, offset, value, "EXCH", "U64");
 }
 
+void EmitStorageAtomicIAdd32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                               [[maybe_unused]] const IR::Value& binding,
+                               [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicSMin32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                               [[maybe_unused]] const IR::Value& binding,
+                               [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicUMin32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                               [[maybe_unused]] const IR::Value& binding,
+                               [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicSMax32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                               [[maybe_unused]] const IR::Value& binding,
+                               [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicUMax32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                               [[maybe_unused]] const IR::Value& binding,
+                               [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicAnd32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                              [[maybe_unused]] const IR::Value& binding,
+                              [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicOr32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                             [[maybe_unused]] const IR::Value& binding,
+                             [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicXor32x2([[maybe_unused]] EmitContext& ctx, [[maybe_unused]] IR::Inst& inst,
+                              [[maybe_unused]] const IR::Value& binding,
+                              [[maybe_unused]] ScalarU32 offset, [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitStorageAtomicExchange32x2([[maybe_unused]] EmitContext& ctx,
+                                   [[maybe_unused]] IR::Inst& inst,
+                                   [[maybe_unused]] const IR::Value& binding,
+                                   [[maybe_unused]] ScalarU32 offset,
+                                   [[maybe_unused]] Register value) {
+    throw NotImplementedException("GLASM instruction");
+}
+
 void EmitStorageAtomicAddF32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              ScalarU32 offset, ScalarF32 value) {
     Atom(ctx, inst, binding, offset, value, "ADD", "F32");
@@ -537,6 +600,50 @@ void EmitGlobalAtomicExchange64(EmitContext&) {
     throw NotImplementedException("GLASM instruction");
 }
 
+void EmitGlobalAtomicIAdd32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicSMin32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicUMin32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicSMax32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicUMax32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicInc32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicDec32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicAnd32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicOr32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicXor32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
+void EmitGlobalAtomicExchange32x2(EmitContext&) {
+    throw NotImplementedException("GLASM instruction");
+}
+
 void EmitGlobalAtomicAddF32(EmitContext&) {
     throw NotImplementedException("GLASM instruction");
 }
diff --git a/src/shader_recompiler/backend/glsl/emit_glsl_atomic.cpp b/src/shader_recompiler/backend/glsl/emit_glsl_atomic.cpp
index dc377b053..a409a7ab3 100644
--- a/src/shader_recompiler/backend/glsl/emit_glsl_atomic.cpp
+++ b/src/shader_recompiler/backend/glsl/emit_glsl_atomic.cpp
@@ -105,6 +105,13 @@ void EmitSharedAtomicExchange64(EmitContext& ctx, IR::Inst& inst, std::string_vi
             pointer_offset, value, pointer_offset, value);
 }
 
+void EmitSharedAtomicExchange32x2(EmitContext& ctx, IR::Inst& inst, std::string_view pointer_offset,
+                                  std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to non-atomic");
+    ctx.AddU32x2("{}=uvec2(smem[{}>>2],smem[({}+4)>>2]);", inst, pointer_offset, pointer_offset);
+    ctx.Add("smem[{}>>2]={}.x;smem[({}+4)>>2]={}.y;", pointer_offset, value, pointer_offset, value);
+}
+
 void EmitStorageAtomicIAdd32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              const IR::Value& offset, std::string_view value) {
     ctx.AddU32("{}=atomicAdd({}_ssbo{}[{}>>2],{});", inst, ctx.stage_name, binding.U32(),
@@ -265,6 +272,97 @@ void EmitStorageAtomicExchange64(EmitContext& ctx, IR::Inst& inst, const IR::Val
                ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value);
 }
 
+void EmitStorageAtomicIAdd32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to non-atomic");
+    ctx.AddU32x2("{}=uvec2({}_ssbo{}[{}>>2],{}_ssbo{}[({}>>2)+1]);", inst, ctx.stage_name,
+                 binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name, binding.U32(),
+                 ctx.var_alloc.Consume(offset));
+    ctx.Add("{}_ssbo{}[{}>>2]+={}.x;{}_ssbo{}[({}>>2)+1]+={}.y;", ctx.stage_name, binding.U32(),
+            ctx.var_alloc.Consume(offset), value, ctx.stage_name, binding.U32(),
+            ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicSMin32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to non-atomic");
+    ctx.AddU32x2("{}=ivec2({}_ssbo{}[{}>>2],{}_ssbo{}[({}>>2)+1]);", inst, ctx.stage_name,
+                 binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name, binding.U32(),
+                 ctx.var_alloc.Consume(offset));
+    ctx.Add("for(int "
+            "i=0;i<2;++i){{{}_ssbo{}[({}>>2)+i]=uint(min(int({}_ssbo{}[({}>>2)+i]),int({}[i])));}}",
+            ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name,
+            binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicUMin32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to non-atomic");
+    ctx.AddU32x2("{}=uvec2({}_ssbo{}[{}>>2],{}_ssbo{}[({}>>2)+1]);", inst, ctx.stage_name,
+                 binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name, binding.U32(),
+                 ctx.var_alloc.Consume(offset));
+    ctx.Add("for(int i=0;i<2;++i){{ "
+            "{}_ssbo{}[({}>>2)+i]=min({}_ssbo{}[({}>>2)+i],{}[i]);}}",
+            ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name,
+            binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicSMax32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to non-atomic");
+    ctx.AddU32x2("{}=ivec2({}_ssbo{}[{}>>2],{}_ssbo{}[({}>>2)+1]);", inst, ctx.stage_name,
+                 binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name, binding.U32(),
+                 ctx.var_alloc.Consume(offset));
+    ctx.Add("for(int "
+            "i=0;i<2;++i){{{}_ssbo{}[({}>>2)+i]=uint(max(int({}_ssbo{}[({}>>2)+i]),int({}[i])));}}",
+            ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name,
+            binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicUMax32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to non-atomic");
+    ctx.AddU32x2("{}=uvec2({}_ssbo{}[{}>>2],{}_ssbo{}[({}>>2)+1]);", inst, ctx.stage_name,
+                 binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name, binding.U32(),
+                 ctx.var_alloc.Consume(offset));
+    ctx.Add("for(int i=0;i<2;++i){{{}_ssbo{}[({}>>2)+i]=max({}_ssbo{}[({}>>2)+i],{}[i]);}}",
+            ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), ctx.stage_name,
+            binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicAnd32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                              const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to 32x2");
+    ctx.AddU32x2("{}=uvec2(atomicAnd({}_ssbo{}[{}>>2],{}.x),atomicAnd({}_ssbo{}[({}>>2)+1],{}.y));",
+                 inst, ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value,
+                 ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicOr32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                             const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to 32x2");
+    ctx.AddU32x2("{}=uvec2(atomicOr({}_ssbo{}[{}>>2],{}.x),atomicOr({}_ssbo{}[({}>>2)+1],{}.y));",
+                 inst, ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value,
+                 ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicXor32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                              const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to 32x2");
+    ctx.AddU32x2("{}=uvec2(atomicXor({}_ssbo{}[{}>>2],{}.x),atomicXor({}_ssbo{}[({}>>2)+1],{}.y));",
+                 inst, ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value,
+                 ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
+void EmitStorageAtomicExchange32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                                   const IR::Value& offset, std::string_view value) {
+    LOG_WARNING(Shader_GLSL, "Int64 atomics not supported, fallback to 32x2");
+    ctx.AddU32x2("{}=uvec2(atomicExchange({}_ssbo{}[{}>>2],{}.x),atomicExchange({}_ssbo{}[({}>>2)+"
+                 "1],{}.y));",
+                 inst, ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value,
+                 ctx.stage_name, binding.U32(), ctx.var_alloc.Consume(offset), value);
+}
+
 void EmitStorageAtomicAddF32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              const IR::Value& offset, std::string_view value) {
     SsboCasFunctionF32(ctx, inst, binding, offset, value, "CasFloatAdd");
@@ -388,6 +486,50 @@ void EmitGlobalAtomicExchange64(EmitContext&) {
     throw NotImplementedException("GLSL Instrucion");
 }
 
+void EmitGlobalAtomicIAdd32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicSMin32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicUMin32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicSMax32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicUMax32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicInc32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicDec32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicAnd32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicOr32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicXor32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
+void EmitGlobalAtomicExchange32x2(EmitContext&) {
+    throw NotImplementedException("GLSL Instrucion");
+}
+
 void EmitGlobalAtomicAddF32(EmitContext&) {
     throw NotImplementedException("GLSL Instrucion");
 }
diff --git a/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h b/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h
index 6cabbc717..704baddc9 100644
--- a/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h
+++ b/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h
@@ -442,6 +442,8 @@ void EmitSharedAtomicExchange32(EmitContext& ctx, IR::Inst& inst, std::string_vi
                                 std::string_view value);
 void EmitSharedAtomicExchange64(EmitContext& ctx, IR::Inst& inst, std::string_view pointer_offset,
                                 std::string_view value);
+void EmitSharedAtomicExchange32x2(EmitContext& ctx, IR::Inst& inst, std::string_view pointer_offset,
+                                  std::string_view value);
 void EmitStorageAtomicIAdd32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              const IR::Value& offset, std::string_view value);
 void EmitStorageAtomicSMin32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
@@ -482,6 +484,24 @@ void EmitStorageAtomicXor64(EmitContext& ctx, IR::Inst& inst, const IR::Value& b
                             const IR::Value& offset, std::string_view value);
 void EmitStorageAtomicExchange64(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                                  const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicIAdd32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicSMin32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicUMin32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicSMax32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicUMax32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                               const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicAnd32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                              const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicOr32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                             const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicXor32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                              const IR::Value& offset, std::string_view value);
+void EmitStorageAtomicExchange32x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
+                                   const IR::Value& offset, std::string_view value);
 void EmitStorageAtomicAddF32(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
                              const IR::Value& offset, std::string_view value);
 void EmitStorageAtomicAddF16x2(EmitContext& ctx, IR::Inst& inst, const IR::Value& binding,
@@ -518,6 +538,17 @@ void EmitGlobalAtomicAnd64(EmitContext& ctx);
 void EmitGlobalAtomicOr64(EmitContext& ctx);
 void EmitGlobalAtomicXor64(EmitContext& ctx);
 void EmitGlobalAtomicExchange64(EmitContext& ctx);
+void EmitGlobalAtomicIAdd32x2(EmitContext& ctx);
+void EmitGlobalAtomicSMin32x2(EmitContext& ctx);
+void EmitGlobalAtomicUMin32x2(EmitContext& ctx);
+void EmitGlobalAtomicSMax32x2(EmitContext& ctx);
+void EmitGlobalAtomicUMax32x2(EmitContext& ctx);
+void EmitGlobalAtomicInc32x2(EmitContext& ctx);
+void EmitGlobalAtomicDec32x2(EmitContext& ctx);
+void EmitGlobalAtomicAnd32x2(EmitContext& ctx);
+void EmitGlobalAtomicOr32x2(EmitContext& ctx);
+void EmitGlobalAtomicXor32x2(EmitContext& ctx);
+void EmitGlobalAtomicExchange32x2(EmitContext& ctx);
 void EmitGlobalAtomicAddF32(EmitContext& ctx);
 void EmitGlobalAtomicAddF16x2(EmitContext& ctx);
 void EmitGlobalAtomicAddF32x2(EmitContext& ctx);
diff --git a/src/shader_recompiler/backend/spirv/emit_spirv_atomic.cpp b/src/shader_recompiler/backend/spirv/emit_spirv_atomic.cpp
index 46ba52a25..d3cbb14a9 100644
--- a/src/shader_recompiler/backend/spirv/emit_spirv_atomic.cpp
+++ b/src/shader_recompiler/backend/spirv/emit_spirv_atomic.cpp
@@ -82,6 +82,17 @@ Id StorageAtomicU64(EmitContext& ctx, const IR::Value& binding, const IR::Value&
     ctx.OpStore(pointer, ctx.OpBitcast(ctx.U32[2], result));
     return original_value;
 }
+
+Id StorageAtomicU32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset, Id value,
+                      Id (Sirit::Module::*non_atomic_func)(Id, Id, Id)) {
+    LOG_WARNING(Shader_SPIRV, "Int64 atomics not supported, fallback to non-atomic");
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32x2, &StorageDefinitions::U32x2,
+                                    binding, offset, sizeof(u32[2]))};
+    const Id original_value{ctx.OpLoad(ctx.U32[2], pointer)};
+    const Id result{(ctx.*non_atomic_func)(ctx.U32[2], value, original_value)};
+    ctx.OpStore(pointer, result);
+    return original_value;
+}
 } // Anonymous namespace
 
 Id EmitSharedAtomicIAdd32(EmitContext& ctx, Id offset, Id value) {
@@ -141,7 +152,7 @@ Id EmitSharedAtomicExchange64(EmitContext& ctx, Id offset, Id value) {
         const auto [scope, semantics]{AtomicArgs(ctx)};
         return ctx.OpAtomicExchange(ctx.U64, pointer, scope, semantics, value);
     }
-    LOG_ERROR(Shader_SPIRV, "Int64 atomics not supported, fallback to non-atomic");
+    LOG_WARNING(Shader_SPIRV, "Int64 atomics not supported, fallback to non-atomic");
     const Id pointer_1{SharedPointer(ctx, offset, 0)};
     const Id pointer_2{SharedPointer(ctx, offset, 1)};
     const Id value_1{ctx.OpLoad(ctx.U32[1], pointer_1)};
@@ -152,6 +163,18 @@ Id EmitSharedAtomicExchange64(EmitContext& ctx, Id offset, Id value) {
     return ctx.OpBitcast(ctx.U64, ctx.OpCompositeConstruct(ctx.U32[2], value_1, value_2));
 }
 
+Id EmitSharedAtomicExchange32x2(EmitContext& ctx, Id offset, Id value) {
+    LOG_WARNING(Shader_SPIRV, "Int64 atomics not supported, fallback to non-atomic");
+    const Id pointer_1{SharedPointer(ctx, offset, 0)};
+    const Id pointer_2{SharedPointer(ctx, offset, 1)};
+    const Id value_1{ctx.OpLoad(ctx.U32[1], pointer_1)};
+    const Id value_2{ctx.OpLoad(ctx.U32[1], pointer_2)};
+    const Id new_vector{ctx.OpBitcast(ctx.U32[2], value)};
+    ctx.OpStore(pointer_1, ctx.OpCompositeExtract(ctx.U32[1], new_vector, 0U));
+    ctx.OpStore(pointer_2, ctx.OpCompositeExtract(ctx.U32[1], new_vector, 1U));
+    return ctx.OpCompositeConstruct(ctx.U32[2], value_1, value_2);
+}
+
 Id EmitStorageAtomicIAdd32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                            Id value) {
     return StorageAtomicU32(ctx, binding, offset, value, &Sirit::Module::OpAtomicIAdd);
@@ -275,6 +298,56 @@ Id EmitStorageAtomicExchange64(EmitContext& ctx, const IR::Value& binding, const
     return original;
 }
 
+Id EmitStorageAtomicIAdd32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpIAdd);
+}
+
+Id EmitStorageAtomicSMin32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpSMin);
+}
+
+Id EmitStorageAtomicUMin32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpUMin);
+}
+
+Id EmitStorageAtomicSMax32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpSMax);
+}
+
+Id EmitStorageAtomicUMax32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpUMax);
+}
+
+Id EmitStorageAtomicAnd32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                            Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpBitwiseAnd);
+}
+
+Id EmitStorageAtomicOr32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                           Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpBitwiseOr);
+}
+
+Id EmitStorageAtomicXor32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                            Id value) {
+    return StorageAtomicU32x2(ctx, binding, offset, value, &Sirit::Module::OpBitwiseXor);
+}
+
+Id EmitStorageAtomicExchange32x2(EmitContext& ctx, const IR::Value& binding,
+                                 const IR::Value& offset, Id value) {
+    LOG_WARNING(Shader_SPIRV, "Int64 atomics not supported, fallback to non-atomic");
+    const Id pointer{StoragePointer(ctx, ctx.storage_types.U32x2, &StorageDefinitions::U32x2,
+                                    binding, offset, sizeof(u32[2]))};
+    const Id original{ctx.OpLoad(ctx.U32[2], pointer)};
+    ctx.OpStore(pointer, value);
+    return original;
+}
+
 Id EmitStorageAtomicAddF32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                            Id value) {
     const Id ssbo{ctx.ssbos[binding.U32()].U32};
@@ -418,6 +491,50 @@ Id EmitGlobalAtomicExchange64(EmitContext&) {
     throw NotImplementedException("SPIR-V Instruction");
 }
 
+Id EmitGlobalAtomicIAdd32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicSMin32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicUMin32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicSMax32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicUMax32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicInc32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicDec32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicAnd32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicOr32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicXor32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
+Id EmitGlobalAtomicExchange32x2(EmitContext&) {
+    throw NotImplementedException("SPIR-V Instruction");
+}
+
 Id EmitGlobalAtomicAddF32(EmitContext&) {
     throw NotImplementedException("SPIR-V Instruction");
 }
diff --git a/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h b/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h
index 887112deb..f263b41b0 100644
--- a/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h
+++ b/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h
@@ -335,6 +335,7 @@ Id EmitSharedAtomicOr32(EmitContext& ctx, Id pointer_offset, Id value);
 Id EmitSharedAtomicXor32(EmitContext& ctx, Id pointer_offset, Id value);
 Id EmitSharedAtomicExchange32(EmitContext& ctx, Id pointer_offset, Id value);
 Id EmitSharedAtomicExchange64(EmitContext& ctx, Id pointer_offset, Id value);
+Id EmitSharedAtomicExchange32x2(EmitContext& ctx, Id pointer_offset, Id value);
 Id EmitStorageAtomicIAdd32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                            Id value);
 Id EmitStorageAtomicSMin32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
@@ -375,6 +376,24 @@ Id EmitStorageAtomicXor64(EmitContext& ctx, const IR::Value& binding, const IR::
                           Id value);
 Id EmitStorageAtomicExchange64(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                                Id value);
+Id EmitStorageAtomicIAdd32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value);
+Id EmitStorageAtomicSMin32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value);
+Id EmitStorageAtomicUMin32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value);
+Id EmitStorageAtomicSMax32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value);
+Id EmitStorageAtomicUMax32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                             Id value);
+Id EmitStorageAtomicAnd32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                            Id value);
+Id EmitStorageAtomicOr32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                           Id value);
+Id EmitStorageAtomicXor32x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
+                            Id value);
+Id EmitStorageAtomicExchange32x2(EmitContext& ctx, const IR::Value& binding,
+                                 const IR::Value& offset, Id value);
 Id EmitStorageAtomicAddF32(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
                            Id value);
 Id EmitStorageAtomicAddF16x2(EmitContext& ctx, const IR::Value& binding, const IR::Value& offset,
@@ -411,6 +430,17 @@ Id EmitGlobalAtomicAnd64(EmitContext& ctx);
 Id EmitGlobalAtomicOr64(EmitContext& ctx);
 Id EmitGlobalAtomicXor64(EmitContext& ctx);
 Id EmitGlobalAtomicExchange64(EmitContext& ctx);
+Id EmitGlobalAtomicIAdd32x2(EmitContext& ctx);
+Id EmitGlobalAtomicSMin32x2(EmitContext& ctx);
+Id EmitGlobalAtomicUMin32x2(EmitContext& ctx);
+Id EmitGlobalAtomicSMax32x2(EmitContext& ctx);
+Id EmitGlobalAtomicUMax32x2(EmitContext& ctx);
+Id EmitGlobalAtomicInc32x2(EmitContext& ctx);
+Id EmitGlobalAtomicDec32x2(EmitContext& ctx);
+Id EmitGlobalAtomicAnd32x2(EmitContext& ctx);
+Id EmitGlobalAtomicOr32x2(EmitContext& ctx);
+Id EmitGlobalAtomicXor32x2(EmitContext& ctx);
+Id EmitGlobalAtomicExchange32x2(EmitContext& ctx);
 Id EmitGlobalAtomicAddF32(EmitContext& ctx);
 Id EmitGlobalAtomicAddF16x2(EmitContext& ctx);
 Id EmitGlobalAtomicAddF32x2(EmitContext& ctx);
diff --git a/src/shader_recompiler/frontend/ir/microinstruction.cpp b/src/shader_recompiler/frontend/ir/microinstruction.cpp
index 97e2bf6af..631446cf7 100644
--- a/src/shader_recompiler/frontend/ir/microinstruction.cpp
+++ b/src/shader_recompiler/frontend/ir/microinstruction.cpp
@@ -118,6 +118,7 @@ bool Inst::MayHaveSideEffects() const noexcept {
     case Opcode::SharedAtomicXor32:
     case Opcode::SharedAtomicExchange32:
     case Opcode::SharedAtomicExchange64:
+    case Opcode::SharedAtomicExchange32x2:
     case Opcode::GlobalAtomicIAdd32:
     case Opcode::GlobalAtomicSMin32:
     case Opcode::GlobalAtomicUMin32:
@@ -138,6 +139,15 @@ bool Inst::MayHaveSideEffects() const noexcept {
     case Opcode::GlobalAtomicOr64:
     case Opcode::GlobalAtomicXor64:
     case Opcode::GlobalAtomicExchange64:
+    case Opcode::GlobalAtomicIAdd32x2:
+    case Opcode::GlobalAtomicSMin32x2:
+    case Opcode::GlobalAtomicUMin32x2:
+    case Opcode::GlobalAtomicSMax32x2:
+    case Opcode::GlobalAtomicUMax32x2:
+    case Opcode::GlobalAtomicAnd32x2:
+    case Opcode::GlobalAtomicOr32x2:
+    case Opcode::GlobalAtomicXor32x2:
+    case Opcode::GlobalAtomicExchange32x2:
     case Opcode::GlobalAtomicAddF32:
     case Opcode::GlobalAtomicAddF16x2:
     case Opcode::GlobalAtomicAddF32x2:
@@ -165,6 +175,15 @@ bool Inst::MayHaveSideEffects() const noexcept {
     case Opcode::StorageAtomicOr64:
     case Opcode::StorageAtomicXor64:
     case Opcode::StorageAtomicExchange64:
+    case Opcode::StorageAtomicIAdd32x2:
+    case Opcode::StorageAtomicSMin32x2:
+    case Opcode::StorageAtomicUMin32x2:
+    case Opcode::StorageAtomicSMax32x2:
+    case Opcode::StorageAtomicUMax32x2:
+    case Opcode::StorageAtomicAnd32x2:
+    case Opcode::StorageAtomicOr32x2:
+    case Opcode::StorageAtomicXor32x2:
+    case Opcode::StorageAtomicExchange32x2:
     case Opcode::StorageAtomicAddF32:
     case Opcode::StorageAtomicAddF16x2:
     case Opcode::StorageAtomicAddF32x2:
diff --git a/src/shader_recompiler/frontend/ir/opcodes.inc b/src/shader_recompiler/frontend/ir/opcodes.inc
index b94ce7406..efb6bfac3 100644
--- a/src/shader_recompiler/frontend/ir/opcodes.inc
+++ b/src/shader_recompiler/frontend/ir/opcodes.inc
@@ -341,6 +341,7 @@ OPCODE(SharedAtomicOr32,                                    U32,            U32,
 OPCODE(SharedAtomicXor32,                                   U32,            U32,            U32,                                                            )
 OPCODE(SharedAtomicExchange32,                              U32,            U32,            U32,                                                            )
 OPCODE(SharedAtomicExchange64,                              U64,            U32,            U64,                                                            )
+OPCODE(SharedAtomicExchange32x2,                            U32x2,          U32,            U32x2,                                                          )
 
 OPCODE(GlobalAtomicIAdd32,                                  U32,            U64,            U32,                                                            )
 OPCODE(GlobalAtomicSMin32,                                  U32,            U64,            U32,                                                            )
@@ -362,6 +363,15 @@ OPCODE(GlobalAtomicAnd64,                                   U64,            U64,
 OPCODE(GlobalAtomicOr64,                                    U64,            U64,            U64,                                                            )
 OPCODE(GlobalAtomicXor64,                                   U64,            U64,            U64,                                                            )
 OPCODE(GlobalAtomicExchange64,                              U64,            U64,            U64,                                                            )
+OPCODE(GlobalAtomicIAdd32x2,                                U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicSMin32x2,                                U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicUMin32x2,                                U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicSMax32x2,                                U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicUMax32x2,                                U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicAnd32x2,                                 U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicOr32x2,                                  U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicXor32x2,                                 U32x2,          U32x2,          U32x2,                                                          )
+OPCODE(GlobalAtomicExchange32x2,                            U32x2,          U32x2,          U32x2,                                                          )
 OPCODE(GlobalAtomicAddF32,                                  F32,            U64,            F32,                                                            )
 OPCODE(GlobalAtomicAddF16x2,                                U32,            U64,            F16x2,                                                          )
 OPCODE(GlobalAtomicAddF32x2,                                U32,            U64,            F32x2,                                                          )
@@ -390,6 +400,15 @@ OPCODE(StorageAtomicAnd64,                                  U64,            U32,
 OPCODE(StorageAtomicOr64,                                   U64,            U32,            U32,            U64,                                            )
 OPCODE(StorageAtomicXor64,                                  U64,            U32,            U32,            U64,                                            )
 OPCODE(StorageAtomicExchange64,                             U64,            U32,            U32,            U64,                                            )
+OPCODE(StorageAtomicIAdd32x2,                               U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicSMin32x2,                               U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicUMin32x2,                               U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicSMax32x2,                               U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicUMax32x2,                               U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicAnd32x2,                                U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicOr32x2,                                 U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicXor32x2,                                U32x2,          U32,            U32,            U32x2,                                          )
+OPCODE(StorageAtomicExchange32x2,                           U32x2,          U32,            U32,            U32x2,                                          )
 OPCODE(StorageAtomicAddF32,                                 F32,            U32,            U32,            F32,                                            )
 OPCODE(StorageAtomicAddF16x2,                               U32,            U32,            U32,            F16x2,                                          )
 OPCODE(StorageAtomicAddF32x2,                               U32,            U32,            U32,            F32x2,                                          )
diff --git a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
index b6a20f904..bfd2ae650 100644
--- a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
+++ b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
@@ -360,6 +360,15 @@ void VisitUsages(Info& info, IR::Inst& inst) {
     case IR::Opcode::GlobalAtomicOr64:
     case IR::Opcode::GlobalAtomicXor64:
     case IR::Opcode::GlobalAtomicExchange64:
+    case IR::Opcode::GlobalAtomicIAdd32x2:
+    case IR::Opcode::GlobalAtomicSMin32x2:
+    case IR::Opcode::GlobalAtomicUMin32x2:
+    case IR::Opcode::GlobalAtomicSMax32x2:
+    case IR::Opcode::GlobalAtomicUMax32x2:
+    case IR::Opcode::GlobalAtomicAnd32x2:
+    case IR::Opcode::GlobalAtomicOr32x2:
+    case IR::Opcode::GlobalAtomicXor32x2:
+    case IR::Opcode::GlobalAtomicExchange32x2:
     case IR::Opcode::GlobalAtomicAddF32:
     case IR::Opcode::GlobalAtomicAddF16x2:
     case IR::Opcode::GlobalAtomicAddF32x2:
@@ -597,6 +606,15 @@ void VisitUsages(Info& info, IR::Inst& inst) {
         break;
     case IR::Opcode::LoadStorage64:
     case IR::Opcode::WriteStorage64:
+    case IR::Opcode::StorageAtomicIAdd32x2:
+    case IR::Opcode::StorageAtomicSMin32x2:
+    case IR::Opcode::StorageAtomicUMin32x2:
+    case IR::Opcode::StorageAtomicSMax32x2:
+    case IR::Opcode::StorageAtomicUMax32x2:
+    case IR::Opcode::StorageAtomicAnd32x2:
+    case IR::Opcode::StorageAtomicOr32x2:
+    case IR::Opcode::StorageAtomicXor32x2:
+    case IR::Opcode::StorageAtomicExchange32x2:
         info.used_storage_buffer_types |= IR::Type::U32x2;
         break;
     case IR::Opcode::LoadStorage128:
diff --git a/src/shader_recompiler/ir_opt/global_memory_to_storage_buffer_pass.cpp b/src/shader_recompiler/ir_opt/global_memory_to_storage_buffer_pass.cpp
index 4197b0095..38592afd0 100644
--- a/src/shader_recompiler/ir_opt/global_memory_to_storage_buffer_pass.cpp
+++ b/src/shader_recompiler/ir_opt/global_memory_to_storage_buffer_pass.cpp
@@ -92,6 +92,15 @@ bool IsGlobalMemory(const IR::Inst& inst) {
     case IR::Opcode::GlobalAtomicOr64:
     case IR::Opcode::GlobalAtomicXor64:
     case IR::Opcode::GlobalAtomicExchange64:
+    case IR::Opcode::GlobalAtomicIAdd32x2:
+    case IR::Opcode::GlobalAtomicSMin32x2:
+    case IR::Opcode::GlobalAtomicUMin32x2:
+    case IR::Opcode::GlobalAtomicSMax32x2:
+    case IR::Opcode::GlobalAtomicUMax32x2:
+    case IR::Opcode::GlobalAtomicAnd32x2:
+    case IR::Opcode::GlobalAtomicOr32x2:
+    case IR::Opcode::GlobalAtomicXor32x2:
+    case IR::Opcode::GlobalAtomicExchange32x2:
     case IR::Opcode::GlobalAtomicAddF32:
     case IR::Opcode::GlobalAtomicAddF16x2:
     case IR::Opcode::GlobalAtomicAddF32x2:
@@ -135,6 +144,15 @@ bool IsGlobalMemoryWrite(const IR::Inst& inst) {
     case IR::Opcode::GlobalAtomicOr64:
     case IR::Opcode::GlobalAtomicXor64:
     case IR::Opcode::GlobalAtomicExchange64:
+    case IR::Opcode::GlobalAtomicIAdd32x2:
+    case IR::Opcode::GlobalAtomicSMin32x2:
+    case IR::Opcode::GlobalAtomicUMin32x2:
+    case IR::Opcode::GlobalAtomicSMax32x2:
+    case IR::Opcode::GlobalAtomicUMax32x2:
+    case IR::Opcode::GlobalAtomicAnd32x2:
+    case IR::Opcode::GlobalAtomicOr32x2:
+    case IR::Opcode::GlobalAtomicXor32x2:
+    case IR::Opcode::GlobalAtomicExchange32x2:
     case IR::Opcode::GlobalAtomicAddF32:
     case IR::Opcode::GlobalAtomicAddF16x2:
     case IR::Opcode::GlobalAtomicAddF32x2:
@@ -199,6 +217,8 @@ IR::Opcode GlobalToStorage(IR::Opcode opcode) {
         return IR::Opcode::StorageAtomicOr32;
     case IR::Opcode::GlobalAtomicXor32:
         return IR::Opcode::StorageAtomicXor32;
+    case IR::Opcode::GlobalAtomicExchange32:
+        return IR::Opcode::StorageAtomicExchange32;
     case IR::Opcode::GlobalAtomicIAdd64:
         return IR::Opcode::StorageAtomicIAdd64;
     case IR::Opcode::GlobalAtomicSMin64:
@@ -215,10 +235,26 @@ IR::Opcode GlobalToStorage(IR::Opcode opcode) {
         return IR::Opcode::StorageAtomicOr64;
     case IR::Opcode::GlobalAtomicXor64:
         return IR::Opcode::StorageAtomicXor64;
-    case IR::Opcode::GlobalAtomicExchange32:
-        return IR::Opcode::StorageAtomicExchange32;
     case IR::Opcode::GlobalAtomicExchange64:
         return IR::Opcode::StorageAtomicExchange64;
+    case IR::Opcode::GlobalAtomicIAdd32x2:
+        return IR::Opcode::StorageAtomicIAdd32x2;
+    case IR::Opcode::GlobalAtomicSMin32x2:
+        return IR::Opcode::StorageAtomicSMin32x2;
+    case IR::Opcode::GlobalAtomicUMin32x2:
+        return IR::Opcode::StorageAtomicUMin32x2;
+    case IR::Opcode::GlobalAtomicSMax32x2:
+        return IR::Opcode::StorageAtomicSMax32x2;
+    case IR::Opcode::GlobalAtomicUMax32x2:
+        return IR::Opcode::StorageAtomicUMax32x2;
+    case IR::Opcode::GlobalAtomicAnd32x2:
+        return IR::Opcode::StorageAtomicAnd32x2;
+    case IR::Opcode::GlobalAtomicOr32x2:
+        return IR::Opcode::StorageAtomicOr32x2;
+    case IR::Opcode::GlobalAtomicXor32x2:
+        return IR::Opcode::StorageAtomicXor32x2;
+    case IR::Opcode::GlobalAtomicExchange32x2:
+        return IR::Opcode::StorageAtomicExchange32x2;
     case IR::Opcode::GlobalAtomicAddF32:
         return IR::Opcode::StorageAtomicAddF32;
     case IR::Opcode::GlobalAtomicAddF16x2:
@@ -454,6 +490,15 @@ void Replace(IR::Block& block, IR::Inst& inst, const IR::U32& storage_index,
     case IR::Opcode::GlobalAtomicOr64:
     case IR::Opcode::GlobalAtomicXor64:
     case IR::Opcode::GlobalAtomicExchange64:
+    case IR::Opcode::GlobalAtomicIAdd32x2:
+    case IR::Opcode::GlobalAtomicSMin32x2:
+    case IR::Opcode::GlobalAtomicUMin32x2:
+    case IR::Opcode::GlobalAtomicSMax32x2:
+    case IR::Opcode::GlobalAtomicUMax32x2:
+    case IR::Opcode::GlobalAtomicAnd32x2:
+    case IR::Opcode::GlobalAtomicOr32x2:
+    case IR::Opcode::GlobalAtomicXor32x2:
+    case IR::Opcode::GlobalAtomicExchange32x2:
     case IR::Opcode::GlobalAtomicAddF32:
     case IR::Opcode::GlobalAtomicAddF16x2:
     case IR::Opcode::GlobalAtomicAddF32x2:
diff --git a/src/shader_recompiler/ir_opt/lower_int64_to_int32.cpp b/src/shader_recompiler/ir_opt/lower_int64_to_int32.cpp
index e80d3d1d9..c2654cd9b 100644
--- a/src/shader_recompiler/ir_opt/lower_int64_to_int32.cpp
+++ b/src/shader_recompiler/ir_opt/lower_int64_to_int32.cpp
@@ -199,6 +199,26 @@ void Lower(IR::Block& block, IR::Inst& inst) {
         return ShiftRightLogical64To32(block, inst);
     case IR::Opcode::ShiftRightArithmetic64:
         return ShiftRightArithmetic64To32(block, inst);
+    case IR::Opcode::SharedAtomicExchange64:
+        return inst.ReplaceOpcode(IR::Opcode::SharedAtomicExchange32x2);
+    case IR::Opcode::GlobalAtomicIAdd64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicIAdd32x2);
+    case IR::Opcode::GlobalAtomicSMin64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicSMin32x2);
+    case IR::Opcode::GlobalAtomicUMin64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicUMin32x2);
+    case IR::Opcode::GlobalAtomicSMax64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicSMax32x2);
+    case IR::Opcode::GlobalAtomicUMax64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicUMax32x2);
+    case IR::Opcode::GlobalAtomicAnd64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicAnd32x2);
+    case IR::Opcode::GlobalAtomicOr64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicOr32x2);
+    case IR::Opcode::GlobalAtomicXor64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicXor32x2);
+    case IR::Opcode::GlobalAtomicExchange64:
+        return inst.ReplaceOpcode(IR::Opcode::GlobalAtomicExchange32x2);
     default:
         break;
     }
diff --git a/src/video_core/renderer_base.h b/src/video_core/renderer_base.h
index bb204454e..c5f974080 100644
--- a/src/video_core/renderer_base.h
+++ b/src/video_core/renderer_base.h
@@ -5,9 +5,10 @@
 #pragma once
 
 #include <atomic>
+#include <functional>
 #include <memory>
-#include <optional>
 
+#include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/frontend/emu_window.h"
 #include "video_core/gpu.h"
@@ -28,8 +29,11 @@ struct RendererSettings {
     Layout::FramebufferLayout screenshot_framebuffer_layout;
 };
 
-class RendererBase : NonCopyable {
+class RendererBase {
 public:
+    YUZU_NON_COPYABLE(RendererBase);
+    YUZU_NON_MOVEABLE(RendererBase);
+
     explicit RendererBase(Core::Frontend::EmuWindow& window,
                           std::unique_ptr<Core::Frontend::GraphicsContext> context);
     virtual ~RendererBase();
diff --git a/src/video_core/renderer_opengl/gl_resource_manager.h b/src/video_core/renderer_opengl/gl_resource_manager.h
index b2d5bfd3b..84e07f8bd 100644
--- a/src/video_core/renderer_opengl/gl_resource_manager.h
+++ b/src/video_core/renderer_opengl/gl_resource_manager.h
@@ -7,12 +7,14 @@
 #include <string_view>
 #include <utility>
 #include <glad/glad.h>
-#include "common/common_types.h"
+#include "common/common_funcs.h"
 
 namespace OpenGL {
 
-class OGLRenderbuffer : private NonCopyable {
+class OGLRenderbuffer final {
 public:
+    YUZU_NON_COPYABLE(OGLRenderbuffer);
+
     OGLRenderbuffer() = default;
 
     OGLRenderbuffer(OGLRenderbuffer&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -36,8 +38,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLTexture : private NonCopyable {
+class OGLTexture final {
 public:
+    YUZU_NON_COPYABLE(OGLTexture);
+
     OGLTexture() = default;
 
     OGLTexture(OGLTexture&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -61,8 +65,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLTextureView : private NonCopyable {
+class OGLTextureView final {
 public:
+    YUZU_NON_COPYABLE(OGLTextureView);
+
     OGLTextureView() = default;
 
     OGLTextureView(OGLTextureView&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -86,8 +92,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLSampler : private NonCopyable {
+class OGLSampler final {
 public:
+    YUZU_NON_COPYABLE(OGLSampler);
+
     OGLSampler() = default;
 
     OGLSampler(OGLSampler&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -111,8 +119,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLShader : private NonCopyable {
+class OGLShader final {
 public:
+    YUZU_NON_COPYABLE(OGLShader);
+
     OGLShader() = default;
 
     OGLShader(OGLShader&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -132,8 +142,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLProgram : private NonCopyable {
+class OGLProgram final {
 public:
+    YUZU_NON_COPYABLE(OGLProgram);
+
     OGLProgram() = default;
 
     OGLProgram(OGLProgram&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -154,8 +166,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLAssemblyProgram : private NonCopyable {
+class OGLAssemblyProgram final {
 public:
+    YUZU_NON_COPYABLE(OGLAssemblyProgram);
+
     OGLAssemblyProgram() = default;
 
     OGLAssemblyProgram(OGLAssemblyProgram&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -176,8 +190,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLPipeline : private NonCopyable {
+class OGLPipeline final {
 public:
+    YUZU_NON_COPYABLE(OGLPipeline);
+
     OGLPipeline() = default;
     OGLPipeline(OGLPipeline&& o) noexcept : handle{std::exchange<GLuint>(o.handle, 0)} {}
 
@@ -198,8 +214,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLBuffer : private NonCopyable {
+class OGLBuffer final {
 public:
+    YUZU_NON_COPYABLE(OGLBuffer);
+
     OGLBuffer() = default;
 
     OGLBuffer(OGLBuffer&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -223,8 +241,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLSync : private NonCopyable {
+class OGLSync final {
 public:
+    YUZU_NON_COPYABLE(OGLSync);
+
     OGLSync() = default;
 
     OGLSync(OGLSync&& o) noexcept : handle(std::exchange(o.handle, nullptr)) {}
@@ -247,8 +267,10 @@ public:
     GLsync handle = 0;
 };
 
-class OGLFramebuffer : private NonCopyable {
+class OGLFramebuffer final {
 public:
+    YUZU_NON_COPYABLE(OGLFramebuffer);
+
     OGLFramebuffer() = default;
 
     OGLFramebuffer(OGLFramebuffer&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
@@ -272,8 +294,10 @@ public:
     GLuint handle = 0;
 };
 
-class OGLQuery : private NonCopyable {
+class OGLQuery final {
 public:
+    YUZU_NON_COPYABLE(OGLQuery);
+
     OGLQuery() = default;
 
     OGLQuery(OGLQuery&& o) noexcept : handle(std::exchange(o.handle, 0)) {}
diff --git a/src/video_core/renderer_vulkan/vk_scheduler.cpp b/src/video_core/renderer_vulkan/vk_scheduler.cpp
index 3bfdf41ba..7d9d4f7ba 100644
--- a/src/video_core/renderer_vulkan/vk_scheduler.cpp
+++ b/src/video_core/renderer_vulkan/vk_scheduler.cpp
@@ -140,12 +140,12 @@ bool VKScheduler::UpdateRescaling(bool is_rescaling) {
 void VKScheduler::WorkerThread(std::stop_token stop_token) {
     Common::SetCurrentThreadName("yuzu:VulkanWorker");
     do {
-        if (work_queue.empty()) {
-            wait_cv.notify_all();
-        }
         std::unique_ptr<CommandChunk> work;
         {
             std::unique_lock lock{work_mutex};
+            if (work_queue.empty()) {
+                wait_cv.notify_all();
+            }
             work_cv.wait(lock, stop_token, [this] { return !work_queue.empty(); });
             if (stop_token.stop_requested()) {
                 continue;
diff --git a/src/video_core/renderer_vulkan/vk_scheduler.h b/src/video_core/renderer_vulkan/vk_scheduler.h
index 1b06c9296..e69aa136b 100644
--- a/src/video_core/renderer_vulkan/vk_scheduler.h
+++ b/src/video_core/renderer_vulkan/vk_scheduler.h
@@ -146,6 +146,7 @@ private:
             using FuncType = TypedCommand<T>;
             static_assert(sizeof(FuncType) < sizeof(data), "Lambda is too large");
 
+            recorded_counts++;
             command_offset = Common::AlignUp(command_offset, alignof(FuncType));
             if (command_offset > sizeof(data) - sizeof(FuncType)) {
                 return false;
@@ -167,7 +168,7 @@ private:
         }
 
         bool Empty() const {
-            return command_offset == 0;
+            return recorded_counts == 0;
         }
 
         bool HasSubmit() const {
@@ -178,6 +179,7 @@ private:
         Command* first = nullptr;
         Command* last = nullptr;
 
+        size_t recorded_counts = 0;
         size_t command_offset = 0;
         bool submit = false;
         alignas(std::max_align_t) std::array<u8, 0x8000> data{};
diff --git a/src/yuzu/configuration/configure_input_player.cpp b/src/yuzu/configuration/configure_input_player.cpp
index ba563b382..cc0534907 100644
--- a/src/yuzu/configuration/configure_input_player.cpp
+++ b/src/yuzu/configuration/configure_input_player.cpp
@@ -102,6 +102,10 @@ QString GetButtonName(Common::Input::ButtonNames button_name) {
         return QObject::tr("Share");
     case Common::Input::ButtonNames::Options:
         return QObject::tr("Options");
+    case Common::Input::ButtonNames::Home:
+        return QObject::tr("Home");
+    case Common::Input::ButtonNames::Touch:
+        return QObject::tr("Touch");
     case Common::Input::ButtonNames::ButtonMouseWheel:
         return QObject::tr("Wheel", "Indicates the mouse wheel");
     case Common::Input::ButtonNames::ButtonBackward:
diff --git a/src/yuzu/main.cpp b/src/yuzu/main.cpp
index d9e689d14..556d2cdb3 100644
--- a/src/yuzu/main.cpp
+++ b/src/yuzu/main.cpp
@@ -965,6 +965,7 @@ void GMainWindow::LinkActionShortcut(QAction* action, const QString& action_name
     static const QString main_window = QStringLiteral("Main Window");
     action->setShortcut(hotkey_registry.GetKeySequence(main_window, action_name));
     action->setShortcutContext(hotkey_registry.GetShortcutContext(main_window, action_name));
+    action->setAutoRepeat(false);
 
     this->addAction(action);