[vulkan] Correction on unconditional/ harcoded makeview 2D array vs compute shader 3D views

src/audio_core/device/device_session.cpp

@@ -22,11 +22,9 @@ using namespace std::literals;
 constexpr auto INCREMENT_TIME{5ms};
 
 DeviceSession::DeviceSession(Core::System& system_)
-    : system{system_}
+    : system{system_}, thread_event{Core::Timing::CreateEvent(
-    , thread_event{system_.CreateTimingEvent("AudioOutSampleTick", [this](s64 time, std::chrono::nanoseconds) {
+                           "AudioOutSampleTick",
-        return ThreadFunc();
+                           [this](s64 time, std::chrono::nanoseconds) { return ThreadFunc(); })} {}
-    })}
-{}
 
 DeviceSession::~DeviceSession() {
     Finalize();

src/core/core.cpp

@@ -969,8 +969,4 @@ void System::ApplySettings() {
     }
 }
 
-std::shared_ptr<Core::Timing::EventType> System::CreateTimingEvent(std::string name, Core::Timing::TimedCallback&& callback) {
-    return std::make_shared<Core::Timing::EventType>(std::move(callback), std::move(name));
-}
-
 } // namespace Core

src/core/core.h

@@ -19,7 +19,6 @@
 #include "core/file_sys/vfs/vfs_types.h"
 #include "core/hle/service/os/event.h"
 #include "core/hle/service/kernel_helpers.h"
-#include "core/core_timing.h"
 
 namespace Core::Frontend {
 class EmuWindow;
@@ -439,9 +438,6 @@ public:
     /// Applies any changes to settings to this core instance.
     void ApplySettings();
 
-    std::shared_ptr<Core::Timing::EventType> CreateTimingEvent(std::string name, Core::Timing::TimedCallback&& callback);
-
-private:
     struct Impl;
     std::unique_ptr<Impl> impl;
 };

src/core/core_timing.cpp

@@ -23,6 +23,10 @@ namespace Core::Timing {
 
 constexpr s64 MAX_SLICE_LENGTH = 10000;
 
+std::shared_ptr<EventType> CreateEvent(std::string name, TimedCallback&& callback) {
+    return std::make_shared<EventType>(std::move(callback), std::move(name));
+}
+
 struct CoreTiming::Event {
     s64 time;
     u64 fifo_order;
@@ -32,10 +36,11 @@ struct CoreTiming::Event {
 
     // Sort by time, unless the times are the same, in which case sort by
     // the order added to the queue
-    friend bool operator>(const Event& left, const Event& right) noexcept {
+    friend bool operator>(const Event& left, const Event& right) {
         return std::tie(left.time, left.fifo_order) > std::tie(right.time, right.fifo_order);
     }
-    friend bool operator<(const Event& left, const Event& right) noexcept {
+
+    friend bool operator<(const Event& left, const Event& right) {
         return std::tie(left.time, left.fifo_order) < std::tie(right.time, right.fifo_order);
     }
 };
@@ -55,6 +60,8 @@ void CoreTiming::Initialize(std::function<void()>&& on_thread_init_) {
             Common::SetCurrentThreadName("HostTiming");
             Common::SetCurrentThreadPriority(Common::ThreadPriority::High);
             on_thread_init();
+            has_started = true;
+
             // base frequency in MHz: 1ns (10^-9) = 1GHz (10^9)
             while (!stop_token.stop_requested()) {
                 while (!paused && !stop_token.stop_requested()) {
@@ -70,8 +77,8 @@ void CoreTiming::Initialize(std::function<void()>&& on_thread_init_) {
                         // continue.
                         wait_set = true;
                         event.Wait();
-                        wait_set = false;
                     }
+                    wait_set = false;
                 }
                 paused_set = true;
                 pause_event.Wait();
@@ -137,28 +144,39 @@ void CoreTiming::ScheduleEvent(std::chrono::nanoseconds ns_into_future,
     event.Set();
 }
 
-void CoreTiming::ScheduleLoopingEvent(std::chrono::nanoseconds start_time, std::chrono::nanoseconds resched_time, const std::shared_ptr<EventType>& event_type, bool absolute_time) {
+void CoreTiming::ScheduleLoopingEvent(std::chrono::nanoseconds start_time,
+                                      std::chrono::nanoseconds resched_time,
+                                      const std::shared_ptr<EventType>& event_type,
+                                      bool absolute_time) {
     {
         std::scoped_lock scope{basic_lock};
         const auto next_time{absolute_time ? start_time : GetGlobalTimeNs() + start_time};
-        auto h = event_queue.emplace(Event{next_time.count(), event_fifo_id++, event_type, resched_time.count()});
+
+        auto h{event_queue.emplace(
+            Event{next_time.count(), event_fifo_id++, event_type, resched_time.count()})};
         (*h).handle = h;
     }
+
     event.Set();
 }
 
-void CoreTiming::UnscheduleEvent(const std::shared_ptr<EventType>& event_type, UnscheduleEventType type) {
+void CoreTiming::UnscheduleEvent(const std::shared_ptr<EventType>& event_type,
+                                 UnscheduleEventType type) {
     {
         std::scoped_lock lk{basic_lock};
+
         std::vector<heap_t::handle_type> to_remove;
-        for (auto it = event_queue.begin(); it != event_queue.end(); it++) {
+        for (auto itr = event_queue.begin(); itr != event_queue.end(); itr++) {
-            auto const& e = *it;
+            const Event& e = *itr;
             if (e.type.lock().get() == event_type.get()) {
-                to_remove.push_back(it->handle);
+                to_remove.push_back(itr->handle);
             }
         }
-        for (auto& h : to_remove)
+
+        for (auto& h : to_remove) {
             event_queue.erase(h);
+        }
+
         event_type->sequence_number++;
     }
 
@@ -169,15 +187,16 @@ void CoreTiming::UnscheduleEvent(const std::shared_ptr<EventType>& event_type, U
 }
 
 static u64 GetNextTickCount(u64 next_ticks) {
-    if (Settings::values.use_custom_cpu_ticks.GetValue())
+    if (Settings::values.use_custom_cpu_ticks.GetValue()) {
         return Settings::values.cpu_ticks.GetValue();
+    }
     return next_ticks;
 }
 
 void CoreTiming::AddTicks(u64 ticks_to_add) {
     const u64 ticks = GetNextTickCount(ticks_to_add);
     cpu_ticks += ticks;
-    downcount -= s64(ticks);
+    downcount -= static_cast<s64>(ticks);
 }
 
 void CoreTiming::Idle() {
@@ -251,14 +270,19 @@ std::optional<s64> CoreTiming::Advance() {
                     next_time = pause_end_time + next_schedule_time;
                 }
 
-                event_queue.update(evt.handle, Event{next_time, event_fifo_id++, evt.type, next_schedule_time, evt.handle});
+                event_queue.update(evt.handle, Event{next_time, event_fifo_id++, evt.type,
+                                                     next_schedule_time, evt.handle});
             }
         }
 
         global_timer = GetGlobalTimeNs().count();
     }
 
-    return event_queue.empty() ? std::optional<s64>{} : event_queue.top().time;
+    if (!event_queue.empty()) {
+        return event_queue.top().time;
+    } else {
+        return std::nullopt;
+    }
 }
 
 void CoreTiming::Reset() {
@@ -269,6 +293,7 @@ void CoreTiming::Reset() {
         timer_thread.request_stop();
         timer_thread.join();
     }
+    has_started = false;
 }
 
 /// @brief Returns current time in nanoseconds.
@@ -285,4 +310,10 @@ std::chrono::microseconds CoreTiming::GetGlobalTimeUs() const noexcept {
         : std::chrono::microseconds{Common::WallClock::CPUTickToUS(cpu_ticks)};
 }
 
+#ifdef _WIN32
+void CoreTiming::SetTimerResolutionNs(std::chrono::nanoseconds ns) {
+    timer_resolution_ns = ns.count();
+}
+#endif
+
 } // namespace Core::Timing

src/core/core_timing.h

@@ -29,7 +29,8 @@ using TimedCallback = std::function<std::optional<std::chrono::nanoseconds>(
 
 /// Contains the characteristics of a particular event.
 struct EventType {
-    explicit EventType(TimedCallback&& callback_, std::string&& name_) : callback{std::move(callback_)}, name{std::move(name_)}, sequence_number{0} {}
+    explicit EventType(TimedCallback&& callback_, std::string&& name_)
+        : callback{std::move(callback_)}, name{std::move(name_)}, sequence_number{0} {}
 
     /// The event's callback function.
     TimedCallback callback;
@@ -89,6 +90,11 @@ public:
     /// Checks if core timing is running.
     bool IsRunning() const;
 
+    /// Checks if the timer thread has started.
+    bool HasStarted() const {
+        return has_started;
+    }
+
     /// Checks if there are any pending time events.
     bool HasPendingEvents() const;
 
@@ -128,29 +134,45 @@ public:
     /// Checks for events manually and returns time in nanoseconds for next event, threadsafe.
     std::optional<s64> Advance();
 
+#ifdef _WIN32
+    void SetTimerResolutionNs(std::chrono::nanoseconds ns);
+#endif
+
     struct Event;
 
     void Reset();
 
     using heap_t = boost::heap::fibonacci_heap<CoreTiming::Event, boost::heap::compare<std::greater<>>>;
-    Common::Event event{};
-    Common::Event pause_event{};
-
-    alignas(64) mutable std::mutex basic_lock;
-    alignas(64) std::mutex advance_lock;
-    alignas(64) std::atomic<bool> paused{};
-    alignas(64) std::atomic<bool> paused_set{};
-    alignas(64) std::atomic<bool> wait_set{};
-    std::function<void()> on_thread_init{};
     heap_t event_queue;
-    std::jthread timer_thread;
     s64 global_timer = 0;
+#ifdef _WIN32
+    s64 timer_resolution_ns;
+#endif
     u64 event_fifo_id = 0;
     s64 pause_end_time{};
     /// Cycle timing
     u64 cpu_ticks{};
     s64 downcount{};
+    Common::Event event{};
+    Common::Event pause_event{};
+    std::function<void()> on_thread_init{};
+    std::jthread timer_thread;
+    mutable std::mutex basic_lock;
+    std::mutex advance_lock;
+    std::atomic<bool> paused{};
+    std::atomic<bool> paused_set{};
+    std::atomic<bool> wait_set{};
+    std::atomic<bool> has_started{};
     bool is_multicore{};
 };
 
+/// Creates a core timing event with the given name and callback.
+///
+/// @param name     The name of the core timing event to create.
+/// @param callback The callback to execute for the event.
+///
+/// @returns An EventType instance representing the created event.
+///
+std::shared_ptr<EventType> CreateEvent(std::string name, TimedCallback&& callback);
+
 } // namespace Core::Timing

src/core/hle/kernel/k_hardware_timer.cpp

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
@@ -13,10 +13,11 @@ namespace Kernel {
 
 void KHardwareTimer::Initialize() {
     // Create the timing callback to register with CoreTiming.
-    m_event_type = m_kernel.System().CreateTimingEvent("KHardwareTimer::Callback", [this](s64, std::chrono::nanoseconds) {
+    m_event_type = Core::Timing::CreateEvent("KHardwareTimer::Callback",
-        this->DoTask();
+                                             [this](s64, std::chrono::nanoseconds) {
-        return std::nullopt;
+                                                 this->DoTask();
-    });
+                                                 return std::nullopt;
+                                             });
 }
 
 void KHardwareTimer::Finalize() {

src/core/hle/kernel/kernel.cpp

@@ -255,7 +255,7 @@ struct KernelCore::Impl {
     }
 
     void InitializePreemption(KernelCore& kernel) {
-        preemption_event = system.CreateTimingEvent("PreemptionCallback", [this, &kernel](s64 time, std::chrono::nanoseconds) -> std::optional<std::chrono::nanoseconds> {
+        preemption_event = Core::Timing::CreateEvent("PreemptionCallback", [this, &kernel](s64 time, std::chrono::nanoseconds) -> std::optional<std::chrono::nanoseconds> {
             {
                 KScopedSchedulerLock lock(kernel);
                 global_scheduler_context->PreemptThreads(kernel);

src/core/hle/service/glue/time/alarm_worker.cpp

@@ -25,11 +25,16 @@ AlarmWorker::~AlarmWorker() {
 
 void AlarmWorker::Initialize(std::shared_ptr<Service::PSC::Time::ServiceManager> time_m) {
     m_time_m = std::move(time_m);
+
     m_timer_event = m_ctx.CreateEvent("Glue:AlarmWorker:TimerEvent");
-    m_timer_timing_event = m_system.CreateTimingEvent("Glue:AlarmWorker::AlarmTimer", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    m_timer_timing_event = Core::Timing::CreateEvent(
-        m_timer_event->Signal(m_system.Kernel());
+        "Glue:AlarmWorker::AlarmTimer",
-        return std::nullopt;
+        [this](s64 time,
-    });
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+            m_timer_event->Signal(m_system.Kernel());
+            return std::nullopt;
+        });
+
     AttachToClosestAlarmEvent();
 }
 

src/core/hle/service/glue/time/worker.cpp

@@ -22,19 +22,28 @@ namespace Service::Glue::Time {
 
 TimeWorker::TimeWorker(Core::System& system, StandardSteadyClockResource& steady_clock_resource,
                        FileTimestampWorker& file_timestamp_worker)
-    : m_system{system}, m_ctx{m_system, "Glue:TimeWorker"}, m_event{m_ctx.CreateEvent("Glue:TimeWorker:Event")},
+    : m_system{system}, m_ctx{m_system, "Glue:TimeWorker"}, m_event{m_ctx.CreateEvent(
+                                                                "Glue:TimeWorker:Event")},
       m_steady_clock_resource{steady_clock_resource},
-      m_file_timestamp_worker{file_timestamp_worker}, m_timer_steady_clock{m_ctx.CreateEvent("Glue:TimeWorker:SteadyClockTimerEvent")},
+      m_file_timestamp_worker{file_timestamp_worker}, m_timer_steady_clock{m_ctx.CreateEvent(
+                                                          "Glue:TimeWorker:SteadyClockTimerEvent")},
       m_timer_file_system{m_ctx.CreateEvent("Glue:TimeWorker:FileTimeTimerEvent")},
       m_alarm_worker{m_system, m_steady_clock_resource}, m_pm_state_change_handler{m_alarm_worker} {
-    m_timer_steady_clock_timing_event = m_system.CreateTimingEvent("Time::SteadyClockEvent", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    m_timer_steady_clock_timing_event = Core::Timing::CreateEvent(
-        m_timer_steady_clock->Signal(m_system.Kernel());
+        "Time::SteadyClockEvent",
-        return std::nullopt;
+        [this](s64 time,
-    });
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
-    m_timer_file_system_timing_event = m_system.CreateTimingEvent("Time::SteadyClockEvent", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+            m_timer_steady_clock->Signal(m_system.Kernel());
-        m_timer_file_system->Signal(m_system.Kernel());
+            return std::nullopt;
-        return std::nullopt;
+        });
-    });
+
+    m_timer_file_system_timing_event = Core::Timing::CreateEvent(
+        "Time::SteadyClockEvent",
+        [this](s64 time,
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+            m_timer_file_system->Signal(m_system.Kernel());
+            return std::nullopt;
+        });
 }
 
 TimeWorker::~TimeWorker() {

src/core/hle/service/hid/hidbus.cpp

@@ -51,12 +51,17 @@ Hidbus::Hidbus(Core::System& system_)
     RegisterHandlers(functions);
 
     // Register update callbacks
-    hidbus_update_event = system_.CreateTimingEvent("Hidbus::UpdateCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    hidbus_update_event = Core::Timing::CreateEvent(
-        const auto guard = LockService();
+        "Hidbus::UpdateCallback",
-        UpdateHidbus(ns_late);
+        [this](s64 time,
-        return std::nullopt;
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
-    });
+            const auto guard = LockService();
-    system_.CoreTiming().ScheduleLoopingEvent(hidbus_update_ns, hidbus_update_ns, hidbus_update_event);
+            UpdateHidbus(ns_late);
+            return std::nullopt;
+        });
+
+    system_.CoreTiming().ScheduleLoopingEvent(hidbus_update_ns, hidbus_update_ns,
+                                              hidbus_update_event);
 }
 
 Hidbus::~Hidbus() {

src/core/hle/service/vi/conductor.cpp

@@ -23,17 +23,25 @@ Conductor::Conductor(Core::System& system, Container& container, DisplayList& di
     });
 
     if (system.IsMulticore()) {
-        m_event = system.CreateTimingEvent("ScreenComposition", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+        m_event = Core::Timing::CreateEvent(
-            m_signal.Set();
+            "ScreenComposition",
-            return std::chrono::nanoseconds(this->GetNextTicks());
+            [this](s64 time,
-        });
+                   std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+                m_signal.Set();
+                return std::chrono::nanoseconds(this->GetNextTicks());
+            });
+
         system.CoreTiming().ScheduleLoopingEvent(FrameNs, FrameNs, m_event);
         m_thread = std::jthread([this](std::stop_token token) { this->VsyncThread(token); });
     } else {
-        m_event = system.CreateTimingEvent("ScreenComposition", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+        m_event = Core::Timing::CreateEvent(
-            this->ProcessVsync();
+            "ScreenComposition",
-            return std::chrono::nanoseconds(this->GetNextTicks());
+            [this](s64 time,
-        });
+                   std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+                this->ProcessVsync();
+                return std::chrono::nanoseconds(this->GetNextTicks());
+            });
+
         system.CoreTiming().ScheduleLoopingEvent(FrameNs, FrameNs, m_event);
     }
 }

src/core/memory/cheat_engine.cpp

@@ -231,10 +231,12 @@ CheatEngine::~CheatEngine() {
 }
 
 void CheatEngine::Initialize() {
-    event = system.CreateTimingEvent("CheatEngine::FrameCallback::" + Common::HexToString(metadata.main_nso_build_id), [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    event = Core::Timing::CreateEvent(
-        FrameCallback(ns_late);
+        "CheatEngine::FrameCallback::" + Common::HexToString(metadata.main_nso_build_id),
-        return std::nullopt;
+        [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
-    });
+            FrameCallback(ns_late);
+            return std::nullopt;
+        });
     core_timing.ScheduleLoopingEvent(CHEAT_ENGINE_NS, CHEAT_ENGINE_NS, event);
 
     metadata.process_id = system.ApplicationProcess()->GetProcessId();

src/core/tools/freezer.cpp

@@ -52,12 +52,14 @@ void MemoryWriteWidth(Core::Memory::Memory& memory, u32 width, VAddr addr, u64 v
 
 } // Anonymous namespace
 
-Freezer::Freezer(Core::System& system_, Core::Timing::CoreTiming& core_timing_, Core::Memory::Memory& memory_)
+Freezer::Freezer(Core::Timing::CoreTiming& core_timing_, Core::Memory::Memory& memory_)
     : core_timing{core_timing_}, memory{memory_} {
-    event = system_.CreateTimingEvent("MemoryFreezer::FrameCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    event = Core::Timing::CreateEvent("MemoryFreezer::FrameCallback",
-        FrameCallback(ns_late);
+                                      [this](s64 time, std::chrono::nanoseconds ns_late)
-        return std::nullopt;
+                                          -> std::optional<std::chrono::nanoseconds> {
-    });
+                                          FrameCallback(ns_late);
+                                          return std::nullopt;
+                                      });
     core_timing.ScheduleEvent(memory_freezer_ns, event);
 }
 

src/core/tools/freezer.h

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2019 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -14,16 +11,14 @@
 #include <vector>
 #include "common/common_types.h"
 
-namespace Core {
+namespace Core::Timing {
-class System;
-namespace Timing {
 class CoreTiming;
 struct EventType;
 } // namespace Core::Timing
-namespace Memory {
+
+namespace Core::Memory {
 class Memory;
-} //namespace Core::Memory
+}
-} //namespace Core
 
 namespace Tools {
 
@@ -43,7 +38,7 @@ public:
         u64 value;
     };
 
-    explicit Freezer(Core::System& system_, Core::Timing::CoreTiming& core_timing_, Core::Memory::Memory& memory_);
+    explicit Freezer(Core::Timing::CoreTiming& core_timing_, Core::Memory::Memory& memory_);
     ~Freezer();
 
     // Enables or disables the entire memory freezer.

src/hid_core/resource_manager.cpp

@@ -56,22 +56,33 @@ ResourceManager::ResourceManager(Core::System& system_,
     applet_resource = std::make_shared<AppletResource>(system);
 
     // Register update callbacks
-    npad_update_event = system.CreateTimingEvent("HID::UpdatePadCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    npad_update_event = Core::Timing::CreateEvent("HID::UpdatePadCallback",
-        UpdateNpad(ns_late);
+                                                  [this](s64 time, std::chrono::nanoseconds ns_late)
-        return std::nullopt;
+                                                      -> std::optional<std::chrono::nanoseconds> {
-    });
+                                                      UpdateNpad(ns_late);
-    default_update_event = system.CreateTimingEvent("HID::UpdateDefaultCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+                                                      return std::nullopt;
-        UpdateControllers(ns_late);
+                                                  });
-        return std::nullopt;
+    default_update_event = Core::Timing::CreateEvent(
-    });
+        "HID::UpdateDefaultCallback",
-    mouse_keyboard_update_event = system.CreateTimingEvent("HID::UpdateMouseKeyboardCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+        [this](s64 time,
-        UpdateMouseKeyboard(ns_late);
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
-        return std::nullopt;
+            UpdateControllers(ns_late);
-    });
+            return std::nullopt;
-    motion_update_event = system.CreateTimingEvent("HID::UpdateMotionCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+        });
-        UpdateMotion(ns_late);
+    mouse_keyboard_update_event = Core::Timing::CreateEvent(
-        return std::nullopt;
+        "HID::UpdateMouseKeyboardCallback",
-    });
+        [this](s64 time,
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+            UpdateMouseKeyboard(ns_late);
+            return std::nullopt;
+        });
+    motion_update_event = Core::Timing::CreateEvent(
+        "HID::UpdateMotionCallback",
+        [this](s64 time,
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+            UpdateMotion(ns_late);
+            return std::nullopt;
+        });
 }
 
 ResourceManager::~ResourceManager() {
@@ -256,10 +267,13 @@ void ResourceManager::InitializeTouchScreenSampler() {
     touch_screen = std::make_shared<TouchScreen>(touch_resource);
     gesture = std::make_shared<Gesture>(touch_resource);
 
-    touch_update_event = system.CreateTimingEvent("HID::TouchUpdateCallback", [this](s64 time, std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+    touch_update_event = Core::Timing::CreateEvent(
-        touch_resource->OnTouchUpdate(time);
+        "HID::TouchUpdateCallback",
-        return std::nullopt;
+        [this](s64 time,
-    });
+               std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+            touch_resource->OnTouchUpdate(time);
+            return std::nullopt;
+        });
 
     touch_resource->SetTouchDriver(touch_driver);
     touch_resource->SetAppletResource(applet_resource, &shared_mutex);

src/qt_common/qt_common.cpp

@@ -266,7 +266,12 @@ void Init(QWidget* root) {
              Common::GetMemInfo().TotalPhysicalMemory / f64{1_GiB});
     LOG_INFO(Frontend, "Host Swap: {:.2f} GiB", Common::GetMemInfo().TotalSwapMemory / f64{1_GiB});
 #ifdef _WIN32
-    LOG_INFO(Frontend, "Host Timer Resolution: {:.4f} ms", std::chrono::duration_cast<std::chrono::duration<f64, std::milli>>(Common::Windows::SetCurrentTimerResolutionToMaximum()).count());
+    LOG_INFO(Frontend, "Host Timer Resolution: {:.4f} ms",
+             std::chrono::duration_cast<std::chrono::duration<f64, std::milli>>(
+                 Common::Windows::SetCurrentTimerResolutionToMaximum())
+                 .count());
+    QtCommon::system->CoreTiming().SetTimerResolutionNs(
+        Common::Windows::GetCurrentTimerResolution());
 #endif
 
     // Remove cached contents generated during the previous session

src/tests/core/core_timing.cpp

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: 2016 Dolphin Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -56,15 +53,14 @@ u64 TestTimerSpeed(Core::Timing::CoreTiming& core_timing) {
 } // Anonymous namespace
 
 TEST_CASE("CoreTiming[BasicOrder]", "[core]") {
-    Core::System system{};
     ScopeInit guard;
     auto& core_timing = guard.core_timing;
     std::vector<std::shared_ptr<Core::Timing::EventType>> events{
-        system.CreateTimingEvent("callbackA", HostCallbackTemplate<0>),
+        Core::Timing::CreateEvent("callbackA", HostCallbackTemplate<0>),
-        system.CreateTimingEvent("callbackB", HostCallbackTemplate<1>),
+        Core::Timing::CreateEvent("callbackB", HostCallbackTemplate<1>),
-        system.CreateTimingEvent("callbackC", HostCallbackTemplate<2>),
+        Core::Timing::CreateEvent("callbackC", HostCallbackTemplate<2>),
-        system.CreateTimingEvent("callbackD", HostCallbackTemplate<3>),
+        Core::Timing::CreateEvent("callbackD", HostCallbackTemplate<3>),
-        system.CreateTimingEvent("callbackE", HostCallbackTemplate<4>),
+        Core::Timing::CreateEvent("callbackE", HostCallbackTemplate<4>),
     };
 
     expected_callback = 0;
@@ -97,15 +93,14 @@ TEST_CASE("CoreTiming[BasicOrder]", "[core]") {
 }
 
 TEST_CASE("CoreTiming[BasicOrderNoPausing]", "[core]") {
-    Core::System system{};
     ScopeInit guard;
     auto& core_timing = guard.core_timing;
     std::vector<std::shared_ptr<Core::Timing::EventType>> events{
-        system.CreateTimingEvent("callbackA", HostCallbackTemplate<0>),
+        Core::Timing::CreateEvent("callbackA", HostCallbackTemplate<0>),
-        system.CreateTimingEvent("callbackB", HostCallbackTemplate<1>),
+        Core::Timing::CreateEvent("callbackB", HostCallbackTemplate<1>),
-        system.CreateTimingEvent("callbackC", HostCallbackTemplate<2>),
+        Core::Timing::CreateEvent("callbackC", HostCallbackTemplate<2>),
-        system.CreateTimingEvent("callbackD", HostCallbackTemplate<3>),
+        Core::Timing::CreateEvent("callbackD", HostCallbackTemplate<3>),
-        system.CreateTimingEvent("callbackE", HostCallbackTemplate<4>),
+        Core::Timing::CreateEvent("callbackE", HostCallbackTemplate<4>),
     };
 
     core_timing.SyncPause(true);

src/video_core/renderer_vulkan/renderer_vulkan.cpp

@@ -169,6 +169,7 @@ try
 }
 
 RendererVulkan::~RendererVulkan() {
+    scheduler.WaitWorker();
     scheduler.RegisterOnSubmit([] {});
     void(device.GetLogical().WaitIdle());
 }

src/video_core/renderer_vulkan/vk_compute_pass.cpp

@@ -25,6 +25,9 @@
 #include "video_core/host_shaders/vulkan_quad_indexed_comp_spv.h"
 #include "video_core/host_shaders/vulkan_uint8_comp_spv.h"
 #include "video_core/host_shaders/block_linear_unswizzle_3d_bcn_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_2d_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_3d_comp_spv.h"
+#include "video_core/host_shaders/pitch_unswizzle_comp_spv.h"
 #include "video_core/renderer_vulkan/vk_compute_pass.h"
 #include "video_core/renderer_vulkan/vk_descriptor_pool.h"
 #include "video_core/renderer_vulkan/vk_scheduler.h"
@@ -232,6 +235,26 @@ struct QueriesPrefixScanPushConstants {
 struct ConditionalRenderingResolvePushConstants {
     u32 compare_to_zero;
 };
+
+struct BlockLinear3DImagePushConstants {
+    alignas(16) std::array<u32, 3> origin;
+    alignas(16) std::array<s32, 3> destination;
+    u32 bytes_per_block_log2;
+    u32 slice_size;
+    u32 block_size;
+    u32 x_shift;
+    u32 block_height;
+    u32 block_height_mask;
+    u32 block_depth;
+    u32 block_depth_mask;
+};
+
+struct PitchUnswizzlePushConstants {
+    std::array<u32, 2> origin;
+    std::array<s32, 2> destination;
+    u32 bytes_per_block;
+    u32 pitch;
+};
 } // Anonymous namespace
 
 ComputePass::ComputePass(const Device& device_, Scheduler& scheduler, DescriptorPool& descriptor_pool,
@@ -653,6 +676,309 @@ void ASTCDecoderPass::Assemble(Image& image, const StagingBufferRef& map,
     scheduler.Finish();
 }
 
+BlockLinearUnswizzleImage2DPass::BlockLinearUnswizzleImage2DPass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    StagingBufferPool& staging_buffer_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, ASTC_DESCRIPTOR_SET_BINDINGS,
+                  ASTC_PASS_DESCRIPTOR_UPDATE_TEMPLATE_ENTRY, ASTC_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(BlockLinearSwizzle2DParams)>,
+                  BLOCK_LINEAR_UNSWIZZLE_2D_COMP_SPV),
+      scheduler{scheduler_}, staging_buffer_pool{staging_buffer_pool_},
+      compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+BlockLinearUnswizzleImage2DPass::~BlockLinearUnswizzleImage2DPass() = default;
+
+void BlockLinearUnswizzleImage2DPass::Unswizzle(
+    Image& image, const StagingBufferRef& map,
+    std::span<const VideoCommon::SwizzleParameters> swizzles) {
+    using namespace VideoCommon::Accelerated;
+    scheduler.RequestOutsideRenderPassOperationContext();
+    const VkPipeline vk_pipeline = *pipeline;
+    const VkImageAspectFlags aspect_mask = image.AspectMask();
+    const VkImage vk_image = image.Handle();
+    const bool is_initialized = image.ExchangeInitialization();
+    scheduler.Record([vk_pipeline, vk_image, aspect_mask,
+                      is_initialized](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = static_cast<VkAccessFlags>(is_initialized ? VK_ACCESS_SHADER_WRITE_BIT
+                                                                       : VK_ACCESS_NONE),
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT,
+            .oldLayout = is_initialized ? VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_UNDEFINED,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(is_initialized ? vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER
+                              : VkPipelineStageFlags(VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT),
+                       VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, image_barrier);
+        cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, vk_pipeline);
+    });
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        const size_t input_offset = swizzle.buffer_offset + map.offset;
+        const u32 num_dispatches_x = Common::DivCeil(swizzle.num_tiles.width, 32U);
+        const u32 num_dispatches_y = Common::DivCeil(swizzle.num_tiles.height, 32U);
+        const u32 num_dispatches_z = image.info.resources.layers;
+
+        compute_pass_descriptor_queue.Acquire(scheduler, 2);
+        compute_pass_descriptor_queue.AddBuffer(map.buffer, input_offset,
+                                                image.guest_size_bytes - swizzle.buffer_offset);
+        compute_pass_descriptor_queue.AddImage(image.StorageImageView(swizzle.level));
+        const void* const descriptor_data{compute_pass_descriptor_queue.UpdateData()};
+
+        const auto params = MakeBlockLinearSwizzle2DParams(swizzle, image.info);
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, num_dispatches_z, params,
+                          descriptor_data](vk::CommandBuffer cmdbuf) {
+            const VkDescriptorSet set = descriptor_allocator.Commit();
+            device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
+            cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});
+            cmdbuf.PushConstants(*layout, VK_SHADER_STAGE_COMPUTE_BIT, params);
+            cmdbuf.Dispatch(num_dispatches_x, num_dispatches_y, num_dispatches_z);
+        });
+    }
+    scheduler.Record([vk_image, aspect_mask](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT |
+                             VK_ACCESS_TRANSFER_READ_BIT | VK_ACCESS_TRANSFER_WRITE_BIT,
+            .oldLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
+                       vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER, 0, image_barrier);
+    });
+    scheduler.Finish();
+}
+
+BlockLinearUnswizzleImage3DPass::BlockLinearUnswizzleImage3DPass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    StagingBufferPool& staging_buffer_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, ASTC_DESCRIPTOR_SET_BINDINGS,
+                  ASTC_PASS_DESCRIPTOR_UPDATE_TEMPLATE_ENTRY, ASTC_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(BlockLinear3DImagePushConstants)>,
+                  BLOCK_LINEAR_UNSWIZZLE_3D_COMP_SPV),
+      scheduler{scheduler_}, staging_buffer_pool{staging_buffer_pool_},
+      compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+BlockLinearUnswizzleImage3DPass::~BlockLinearUnswizzleImage3DPass() = default;
+
+void BlockLinearUnswizzleImage3DPass::Unswizzle(
+    Image& image, const StagingBufferRef& map,
+    std::span<const VideoCommon::SwizzleParameters> swizzles) {
+    using namespace VideoCommon::Accelerated;
+    scheduler.RequestOutsideRenderPassOperationContext();
+    const VkPipeline vk_pipeline = *pipeline;
+    const VkImageAspectFlags aspect_mask = image.AspectMask();
+    const VkImage vk_image = image.Handle();
+    const bool is_initialized = image.ExchangeInitialization();
+    scheduler.Record([vk_pipeline, vk_image, aspect_mask,
+                      is_initialized](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = static_cast<VkAccessFlags>(is_initialized ? VK_ACCESS_SHADER_WRITE_BIT
+                                                                       : VK_ACCESS_NONE),
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT,
+            .oldLayout = is_initialized ? VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_UNDEFINED,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(is_initialized ? vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER
+                              : VkPipelineStageFlags(VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT),
+                       VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, image_barrier);
+        cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, vk_pipeline);
+    });
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        const size_t input_offset = swizzle.buffer_offset + map.offset;
+        const u32 num_dispatches_x = Common::DivCeil(swizzle.num_tiles.width, 16U);
+        const u32 num_dispatches_y = Common::DivCeil(swizzle.num_tiles.height, 8U);
+        const u32 num_dispatches_z = Common::DivCeil(swizzle.num_tiles.depth, 8U);
+
+        compute_pass_descriptor_queue.Acquire(scheduler, 2);
+        compute_pass_descriptor_queue.AddBuffer(map.buffer, input_offset,
+                                                image.guest_size_bytes - swizzle.buffer_offset);
+        compute_pass_descriptor_queue.AddImage(image.StorageImageView(swizzle.level));
+        const void* const descriptor_data{compute_pass_descriptor_queue.UpdateData()};
+
+        const auto p = MakeBlockLinearSwizzle3DParams(swizzle, image.info);
+        const BlockLinear3DImagePushConstants params{
+            .origin = p.origin,
+            .destination = p.destination,
+            .bytes_per_block_log2 = p.bytes_per_block_log2,
+            .slice_size = p.slice_size,
+            .block_size = p.block_size,
+            .x_shift = p.x_shift,
+            .block_height = p.block_height,
+            .block_height_mask = p.block_height_mask,
+            .block_depth = p.block_depth,
+            .block_depth_mask = p.block_depth_mask,
+        };
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, num_dispatches_z, params,
+                          descriptor_data](vk::CommandBuffer cmdbuf) {
+            const VkDescriptorSet set = descriptor_allocator.Commit();
+            device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
+            cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});
+            cmdbuf.PushConstants(*layout, VK_SHADER_STAGE_COMPUTE_BIT, params);
+            cmdbuf.Dispatch(num_dispatches_x, num_dispatches_y, num_dispatches_z);
+        });
+    }
+    scheduler.Record([vk_image, aspect_mask](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT |
+                             VK_ACCESS_TRANSFER_READ_BIT | VK_ACCESS_TRANSFER_WRITE_BIT,
+            .oldLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
+                       vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER, 0, image_barrier);
+    });
+    scheduler.Finish();
+}
+
+PitchUnswizzlePass::PitchUnswizzlePass(const Device& device_, Scheduler& scheduler_,
+                                       DescriptorPool& descriptor_pool_,
+                                       StagingBufferPool& staging_buffer_pool_,
+                                       ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, ASTC_DESCRIPTOR_SET_BINDINGS,
+                  ASTC_PASS_DESCRIPTOR_UPDATE_TEMPLATE_ENTRY, ASTC_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(PitchUnswizzlePushConstants)>,
+                  PITCH_UNSWIZZLE_COMP_SPV),
+      scheduler{scheduler_}, staging_buffer_pool{staging_buffer_pool_},
+      compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+PitchUnswizzlePass::~PitchUnswizzlePass() = default;
+
+void PitchUnswizzlePass::Unswizzle(Image& image, const StagingBufferRef& map,
+                                   std::span<const VideoCommon::SwizzleParameters> swizzles) {
+    scheduler.RequestOutsideRenderPassOperationContext();
+    const VkPipeline vk_pipeline = *pipeline;
+    const VkImageAspectFlags aspect_mask = image.AspectMask();
+    const VkImage vk_image = image.Handle();
+    const bool is_initialized = image.ExchangeInitialization();
+    scheduler.Record([vk_pipeline, vk_image, aspect_mask,
+                      is_initialized](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = static_cast<VkAccessFlags>(is_initialized ? VK_ACCESS_SHADER_WRITE_BIT
+                                                                       : VK_ACCESS_NONE),
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT,
+            .oldLayout = is_initialized ? VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_UNDEFINED,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(is_initialized ? vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER
+                              : VkPipelineStageFlags(VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT),
+                       VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, image_barrier);
+        cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, vk_pipeline);
+    });
+    const u32 bytes_per_block = VideoCore::Surface::BytesPerBlock(image.info.format);
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        const size_t input_offset = swizzle.buffer_offset + map.offset;
+        const u32 num_dispatches_x = Common::DivCeil(swizzle.num_tiles.width, 32U);
+        const u32 num_dispatches_y = Common::DivCeil(swizzle.num_tiles.height, 32U);
+
+        compute_pass_descriptor_queue.Acquire(scheduler, 2);
+        compute_pass_descriptor_queue.AddBuffer(map.buffer, input_offset,
+                                                image.guest_size_bytes - swizzle.buffer_offset);
+        compute_pass_descriptor_queue.AddImage(image.StorageImageView(swizzle.level));
+        const void* const descriptor_data{compute_pass_descriptor_queue.UpdateData()};
+
+        const PitchUnswizzlePushConstants params{
+            .origin = {0, 0},
+            .destination = {0, 0},
+            .bytes_per_block = bytes_per_block,
+            .pitch = image.info.pitch,
+        };
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, params,
+                          descriptor_data](vk::CommandBuffer cmdbuf) {
+            const VkDescriptorSet set = descriptor_allocator.Commit();
+            device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
+            cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});
+            cmdbuf.PushConstants(*layout, VK_SHADER_STAGE_COMPUTE_BIT, params);
+            cmdbuf.Dispatch(num_dispatches_x, num_dispatches_y, 1);
+        });
+    }
+    scheduler.Record([vk_image, aspect_mask](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT |
+                             VK_ACCESS_TRANSFER_READ_BIT | VK_ACCESS_TRANSFER_WRITE_BIT,
+            .oldLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
+                       vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER, 0, image_barrier);
+    });
+    scheduler.Finish();
+}
+
 constexpr u32 BL3D_BINDING_INPUT_BUFFER  = 0;
 constexpr u32 BL3D_BINDING_OUTPUT_BUFFER = 1;
 
@@ -833,6 +1159,23 @@ void BlockLinearUnswizzle3DPass::UnswizzleChunk(
             return;
         }
 
+        if (!is_first_chunk) {
+            const VkBufferMemoryBarrier reuse_barrier{
+                .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
+                .pNext = nullptr,
+                .srcAccessMask = VK_ACCESS_TRANSFER_READ_BIT,
+                .dstAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+                .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+                .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+                .buffer = out_buffer,
+                .offset = 0,
+                .size = VK_WHOLE_SIZE,
+            };
+            cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT,
+                                   VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, nullptr,
+                                   reuse_barrier, nullptr);
+        }
+
         device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
         cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, *pipeline);
         cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});

src/video_core/renderer_vulkan/vk_compute_pass.h

@@ -25,6 +25,7 @@ struct SwizzleParameters;
 
 namespace Vulkan {
 
+using VideoCommon::Accelerated::BlockLinearSwizzle2DParams;
 using VideoCommon::Accelerated::BlockLinearSwizzle3DParams;
 
 class Device;
@@ -164,6 +165,56 @@ private:
     ComputePassDescriptorQueue& compute_pass_descriptor_queue;
 };
 
+class BlockLinearUnswizzleImage2DPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzleImage2DPass(const Device& device_, Scheduler& scheduler_,
+                                             DescriptorPool& descriptor_pool_,
+                                             StagingBufferPool& staging_buffer_pool_,
+                                             ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzleImage2DPass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    StagingBufferPool& staging_buffer_pool;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
+class BlockLinearUnswizzleImage3DPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzleImage3DPass(const Device& device_, Scheduler& scheduler_,
+                                             DescriptorPool& descriptor_pool_,
+                                             StagingBufferPool& staging_buffer_pool_,
+                                             ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzleImage3DPass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    StagingBufferPool& staging_buffer_pool;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
+class PitchUnswizzlePass final : public ComputePass {
+public:
+    explicit PitchUnswizzlePass(const Device& device_, Scheduler& scheduler_,
+                                DescriptorPool& descriptor_pool_,
+                                StagingBufferPool& staging_buffer_pool_,
+                                ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~PitchUnswizzlePass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    StagingBufferPool& staging_buffer_pool;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
 
 class MSAACopyPass final : public ComputePass {
 public:

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -195,8 +195,42 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
     return allocator.CreateImage(image_ci);
 }
 
+[[nodiscard]] VkFormat UnswizzleStorageFormat(u32 bytes_per_block) {
+    switch (bytes_per_block) {
+    case 1:
+        return VK_FORMAT_R8_UINT;
+    case 2:
+        return VK_FORMAT_R16_UINT;
+    case 4:
+        return VK_FORMAT_R32_UINT;
+    case 8:
+        return VK_FORMAT_R32G32_UINT;
+    case 16:
+        return VK_FORMAT_R32G32B32A32_UINT;
+    default:
+        ASSERT_MSG(false, "Invalid bytes_per_block={} for accelerated unswizzle", bytes_per_block);
+        return VK_FORMAT_R32_UINT;
+    }
+}
+
+[[nodiscard]] bool IsUnswizzleStorageFormatSupported(const Device& device, u32 bytes_per_block) {
+    switch (bytes_per_block) {
+    case 1:
+        return device.IsStorageBuffer8BitAccessSupported();
+    case 2:
+        return device.IsStorageBuffer16BitAccessSupported();
+    case 4:
+    case 8:
+    case 16:
+        return true;
+    default:
+        return false;
+    }
+}
+
 [[nodiscard]] vk::ImageView MakeStorageView(const vk::Device& device, u32 level, VkImage image,
-                                            VkFormat format) {
+                                            VkFormat format,
+                                            VkImageViewType view_type = VK_IMAGE_VIEW_TYPE_2D_ARRAY) {
     static constexpr VkImageViewUsageCreateInfo storage_image_view_usage_create_info{
         .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_USAGE_CREATE_INFO,
         .pNext = nullptr,
@@ -207,7 +241,7 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
         .pNext = &storage_image_view_usage_create_info,
         .flags = 0,
         .image = image,
-        .viewType = VK_IMAGE_VIEW_TYPE_2D_ARRAY,
+        .viewType = view_type,
         .format = format,
         .components{
             .r = VK_COMPONENT_SWIZZLE_IDENTITY,
@@ -887,6 +921,12 @@ TextureCacheRuntime::TextureCacheRuntime(const Device& device_, Scheduler& sched
     if (device.IsStorageImageMultisampleSupported()) {
         msaa_copy_pass.emplace(device, scheduler, descriptor_pool, staging_buffer_pool, compute_pass_descriptor_queue);
     }
+    bl_unswizzle_2d_pass.emplace(device, scheduler, descriptor_pool, staging_buffer_pool,
+                                 compute_pass_descriptor_queue);
+    bl_unswizzle_3d_pass.emplace(device, scheduler, descriptor_pool, staging_buffer_pool,
+                                 compute_pass_descriptor_queue);
+    pitch_unswizzle_pass.emplace(device, scheduler, descriptor_pool, staging_buffer_pool,
+                                 compute_pass_descriptor_queue);
     if (!device.IsKhrImageFormatListSupported()) {
         return;
     }
@@ -894,6 +934,11 @@ TextureCacheRuntime::TextureCacheRuntime(const Device& device_, Scheduler& sched
         const auto image_format = static_cast<PixelFormat>(index_a);
         if (IsPixelFormatASTC(image_format) && !device.IsOptimalAstcSupported()) {
             view_formats[index_a].push_back(VK_FORMAT_A8B8G8R8_UNORM_PACK32);
+        } else if (!IsPixelFormatASTC(image_format) && !IsPixelFormatBCn(image_format)) {
+            const u32 bpp = VideoCore::Surface::BytesPerBlock(image_format);
+            if (IsUnswizzleStorageFormatSupported(device, bpp)) {
+                view_formats[index_a].push_back(UnswizzleStorageFormat(bpp));
+            }
         }
         for (size_t index_b = 0; index_b < VideoCore::Surface::MaxPixelFormat; index_b++) {
             const auto view_format = static_cast<PixelFormat>(index_b);
@@ -1580,6 +1625,16 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
         flags |= VideoCommon::ImageFlagBits::Converted;
         flags |= VideoCommon::ImageFlagBits::CostlyLoad;
     }
+    if (!IsPixelFormatASTC(info.format) && !IsPixelFormatBCn(info.format) &&
+        VideoCore::Surface::GetFormatType(info.format) ==
+            VideoCore::Surface::SurfaceType::ColorTexture &&
+        (info.type == ImageType::e2D || info.type == ImageType::e3D ||
+         info.type == ImageType::Linear)) {
+        if (IsUnswizzleStorageFormatSupported(runtime->device,
+                                              VideoCore::Surface::BytesPerBlock(info.format))) {
+            flags |= VideoCommon::ImageFlagBits::AcceleratedUpload;
+        }
+    }
     if (runtime->device.HasDebuggingToolAttached()) {
         original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str());
     }
@@ -1593,6 +1648,19 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
             storage_image_views[level] =
                 MakeStorageView(device, level, *original_image, VK_FORMAT_A8B8G8R8_UNORM_PACK32);
         }
+    } else if (True(flags & VideoCommon::ImageFlagBits::AcceleratedUpload)) {
+        const auto& device = runtime->device.GetLogical();
+        const VkFormat storage_format =
+            UnswizzleStorageFormat(VideoCore::Surface::BytesPerBlock(info.format));
+        const VkImageViewType storage_view_type = info.type == ImageType::e3D
+                                                       ? VK_IMAGE_VIEW_TYPE_3D
+                                                   : info.type == ImageType::Linear
+                                                       ? VK_IMAGE_VIEW_TYPE_2D
+                                                       : VK_IMAGE_VIEW_TYPE_2D_ARRAY;
+        for (s32 level = 0; level < info.resources.levels; ++level) {
+            storage_image_views[level] =
+                MakeStorageView(device, level, *original_image, storage_format, storage_view_type);
+        }
     }
 }
 
@@ -2448,16 +2516,24 @@ void TextureCacheRuntime::AccelerateImageUpload(
         return astc_decoder_pass->Assemble(image, map, swizzles);
     }
 
-    if (!Settings::values.gpu_unswizzle_enabled.GetValue() || !bl3d_unswizzle_pass) {
+    if (IsPixelFormatBCn(image.info.format)) {
-        if (IsPixelFormatBCn(image.info.format) && image.info.type == ImageType::e3D) {
+        if (Settings::values.gpu_unswizzle_enabled.GetValue() && bl3d_unswizzle_pass &&
-            ASSERT(false && "GPU unswizzle is disabled for BCn 3D texture");
+            image.info.type == ImageType::e3D && image.info.resources.levels == 1 &&
+            image.info.resources.layers == 1) {
+            return bl3d_unswizzle_pass->Unswizzle(image, map, swizzles, z_start, z_count);
         }
-        ASSERT(false);
+        ASSERT(false && "GPU unswizzle is disabled for BCn 3D texture");
         return;
     }
 
-    if (bl3d_unswizzle_pass && IsPixelFormatBCn(image.info.format) && image.info.type == ImageType::e3D && image.info.resources.levels == 1 && image.info.resources.layers == 1) {
+    if (image.info.type == ImageType::e2D) {
-        return bl3d_unswizzle_pass->Unswizzle(image, map, swizzles, z_start, z_count);
+        return bl_unswizzle_2d_pass->Unswizzle(image, map, swizzles);
+    }
+    if (image.info.type == ImageType::e3D) {
+        return bl_unswizzle_3d_pass->Unswizzle(image, map, swizzles);
+    }
+    if (image.info.type == ImageType::Linear) {
+        return pitch_unswizzle_pass->Unswizzle(image, map, swizzles);
     }
 
     ASSERT(false);

src/video_core/renderer_vulkan/vk_texture_cache.h

@@ -130,6 +130,9 @@ public:
     std::optional<ASTCDecoderPass> astc_decoder_pass;
 
     std::optional<BlockLinearUnswizzle3DPass> bl3d_unswizzle_pass;
+    std::optional<BlockLinearUnswizzleImage2DPass> bl_unswizzle_2d_pass;
+    std::optional<BlockLinearUnswizzleImage3DPass> bl_unswizzle_3d_pass;
+    std::optional<PitchUnswizzlePass> pitch_unswizzle_pass;
     std::optional<MSAACopyPass> msaa_copy_pass;
     const Settings::ResolutionScalingInfo& resolution;
     std::array<std::vector<VkFormat>, VideoCore::Surface::MaxPixelFormat> view_formats;

src/video_core/vulkan_common/vulkan_device.h

@@ -888,6 +888,16 @@ FN_MAX_LIMIT_LIST
                features.bit16_storage.storageBuffer16BitAccess;
     }
 
+    /// Returns true if the device supports reading 8-bit values from a storage buffer.
+    bool IsStorageBuffer8BitAccessSupported() const {
+        return features.bit8_storage.storageBuffer8BitAccess;
+    }
+
+    /// Returns true if the device supports reading 16-bit values from a storage buffer.
+    bool IsStorageBuffer16BitAccessSupported() const {
+        return features.bit16_storage.storageBuffer16BitAccess;
+    }
+
     [[nodiscard]] static constexpr bool CheckBrokenCompute(VkDriverId driver_id,
                                                            u32 driver_version) {
         if (driver_id == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS) {

src/yuzu_cmd/yuzu.cpp

@@ -371,6 +371,7 @@ int main(int argc, char** argv) {
 
 #ifdef _WIN32
     Common::Windows::SetCurrentTimerResolutionToMaximum();
+    system.CoreTiming().SetTimerResolutionNs(Common::Windows::GetCurrentTimerResolution());
 #endif
 
     system.SetContentProvider(std::make_unique<FileSys::ContentProviderUnion>());