AQUI LLEGO TU LOBITO, MI LOBA.

This reverts commit 2ea449f71a.

src/audio_core/sink/sdl3_sink.cpp

@@ -19,23 +19,6 @@
 namespace AudioCore::Sink {
 
 namespace {
-
-[[nodiscard]] bool InitializeAudio() {
-    if (!SDL_WasInit(SDL_INIT_AUDIO)) {
-        // See https://github.com/PCSX2/pcsx2/pull/12312
-        // "SDL and cubeb backends previously resulted in different names for the output which
-        // caused them be identified as different applications by the OS."
-        //
-        // Keep in sync with cubeb_sink.cpp name.
-        SDL_SetHint("SDL_AUDIO_DEVICE_APP_NAME", "yuzu Latency Getter");
-        if (!SDL_InitSubSystem(SDL_INIT_AUDIO)) {
-            LOG_CRITICAL(Audio_Sink, "SDL_InitSubSystem audio failed: {}", SDL_GetError());
-            return false;
-        }
-    }
-    return true;
-}
-
 SDL_AudioDeviceID FindAudioDeviceByName(const std::string& device_name, bool capture) {
     int device_count = 0;
     SDL_AudioDeviceID* devices = capture ? SDL_GetAudioRecordingDevices(&device_count)
@@ -221,14 +204,20 @@ private:
 };
 
 SDLSink::SDLSink(std::string_view target_device_name) {
-    if (InitializeAudio()) {
-        if (target_device_name != auto_device_name && !target_device_name.empty()) {
-            output_device = target_device_name;
-        } else {
-            output_device.clear();
+    if (!SDL_WasInit(SDL_INIT_AUDIO)) {
+        if (!SDL_InitSubSystem(SDL_INIT_AUDIO)) {
+            LOG_CRITICAL(Audio_Sink, "SDL_InitSubSystem audio failed: {}", SDL_GetError());
+            return;
         }
-        device_channels = 2;
     }
+
+    if (target_device_name != auto_device_name && !target_device_name.empty()) {
+        output_device = target_device_name;
+    } else {
+        output_device.clear();
+    }
+
+    device_channels = 2;
 }
 
 SDLSink::~SDLSink() = default;
@@ -276,10 +265,15 @@ void SDLSink::SetSystemVolume(f32 volume) {
 }
 
 std::vector<std::string> ListSDLSinkDevices(bool capture) {
-    if (!InitializeAudio())
-        return {}; //no devices
-
     std::vector<std::string> device_list;
+
+    if (!SDL_WasInit(SDL_INIT_AUDIO)) {
+        if (!SDL_InitSubSystem(SDL_INIT_AUDIO)) {
+            LOG_CRITICAL(Audio_Sink, "SDL_InitSubSystem audio failed: {}", SDL_GetError());
+            return {};
+        }
+    }
+
     int device_count = 0;
     SDL_AudioDeviceID* devices =
         capture ? SDL_GetAudioRecordingDevices(&device_count)
@@ -310,8 +304,13 @@ bool IsSDLSuitable() {
     return false;
 #else
     // Check SDL can init
-    if (!InitializeAudio()!
-        return false;
+    if (!SDL_WasInit(SDL_INIT_AUDIO)) {
+        if (SDL_InitSubSystem(SDL_INIT_AUDIO) < 0) {
+            LOG_ERROR(Audio_Sink, "SDL failed to init, it is not suitable. Error: {}",
+                      SDL_GetError());
+            return false;
+        }
+    }
 
     // We can set any latency frequency we want with SDL, so no need to check that.
 

src/common/settings.cpp

@@ -369,7 +369,7 @@ void TranslateResolutionInfo(ResolutionSetup setup, ResolutionScalingInfo& info)
     }
     info.up_factor = static_cast<f32>(info.up_scale) / (1U << info.down_shift);
     info.down_factor = static_cast<f32>(1U << info.down_shift) / info.up_scale;
-    info.active = info.up_scale != 1 || info.down_shift != 0;
+    info.active = true;
 }
 
 void UpdateRescalingInfo() {

src/common/stb.cpp

@@ -7,4 +7,6 @@
 #define STB_IMAGE_IMPLEMENTATION 1
 #define STB_IMAGE_RESIZE_IMPLEMENTATION 1
 #define STB_IMAGE_WRITE_IMPLEMENTATION 1
+#define STBI_ONLY_JPEG 1
+
 #include "common/stb.h"

src/common/stb.h

@@ -7,7 +7,6 @@
 #pragma once
 
 #define STBI_ONLY_JPEG 1
-#define STBI_WRITE_NO_STDIO 1
 #include <stb_image.h>
 #include <stb_image_resize.h>
 #include <stb_image_write.h>

src/core/core.cpp

@@ -4,7 +4,6 @@
 #include <array>
 #include <atomic>
 #include <memory>
-#include <unordered_map>
 #include <utility>
 
 #include "game_settings.h"
@@ -249,30 +248,12 @@ struct System::Impl {
         }
     }
 
-    void NotifyNVDECChannelOpen(u64 process_id) {
-        std::scoped_lock lock{nvdec_active_mutex};
-        ++nvdec_active_channels[process_id];
-    }
-
-    void NotifyNVDECChannelClose(u64 process_id) {
-        std::scoped_lock lock{nvdec_active_mutex};
-        const auto it = nvdec_active_channels.find(process_id);
-        if (it == nvdec_active_channels.end()) {
-            return;
-        }
-        if (--it->second == 0) {
-            nvdec_active_channels.erase(it);
-        }
+    void SetNVDECActive(bool is_nvdec_active) {
+        nvdec_active = is_nvdec_active;
     }
 
     bool GetNVDECActive() {
-        std::scoped_lock lock{nvdec_active_mutex};
-        return !nvdec_active_channels.empty();
-    }
-
-    bool IsNVDECActiveForProcess(u64 process_id) {
-        std::scoped_lock lock{nvdec_active_mutex};
-        return nvdec_active_channels.contains(process_id);
+        return nvdec_active;
     }
 
     void InitializeDebugger(System& system, u16 port) {
@@ -517,8 +498,6 @@ struct System::Impl {
 
     mutable std::mutex suspend_guard;
     std::mutex general_channel_mutex;
-    std::mutex nvdec_active_mutex;
-    std::unordered_map<u64, u32> nvdec_active_channels;
     std::atomic_bool is_paused{};
     std::atomic_bool is_shutting_down{};
     std::atomic_bool is_powered_on{};
@@ -526,6 +505,7 @@ struct System::Impl {
     bool extended_memory_layout : 1 = false;
     bool exit_locked : 1 = false;
     bool exit_requested : 1 = false;
+    bool nvdec_active : 1 = false;
 
     void EnsureGeneralChannelInitialized(System& system) {
         if (!general_channel_event) {
@@ -589,22 +569,14 @@ void System::UnstallApplication() {
     impl->UnstallApplication();
 }
 
-void System::NotifyNVDECChannelOpen(u64 process_id) {
-    impl->NotifyNVDECChannelOpen(process_id);
-}
-
-void System::NotifyNVDECChannelClose(u64 process_id) {
-    impl->NotifyNVDECChannelClose(process_id);
+void System::SetNVDECActive(bool is_nvdec_active) {
+    impl->SetNVDECActive(is_nvdec_active);
 }
 
 bool System::GetNVDECActive() {
     return impl->GetNVDECActive();
 }
 
-bool System::IsNVDECActiveForProcess(u64 process_id) {
-    return impl->IsNVDECActiveForProcess(process_id);
-}
-
 void System::InitializeDebugger() {
     impl->InitializeDebugger(*this, Settings::values.gdbstub_port.GetValue());
 }

src/core/core.h

@@ -191,10 +191,8 @@ public:
     std::unique_lock<std::mutex> StallApplication();
     void UnstallApplication();
 
-    void NotifyNVDECChannelOpen(u64 process_id);
-    void NotifyNVDECChannelClose(u64 process_id);
+    void SetNVDECActive(bool is_nvdec_active);
     [[nodiscard]] bool GetNVDECActive();
-    [[nodiscard]] bool IsNVDECActiveForProcess(u64 process_id);
 
     /**
      * Initialize the debugger.

src/core/hle/service/am/service/application_functions.cpp

@@ -324,7 +324,6 @@ Result IApplicationFunctions::NotifyRunning(Out<bool> out_became_running) {
 
 Result IApplicationFunctions::GetPseudoDeviceId(Out<Common::UUID> out_pseudo_device_id) {
     LOG_WARNING(Service_AM, "(stubbed)");
-    R_UNLESS(out_pseudo_device_id, ResultUnknown);
 
     // This should be hashed with the device specific hash
     // for now this will do

src/core/hle/service/ns/read_only_application_control_data_interface.cpp

@@ -9,7 +9,11 @@
 #include <optional>
 #include <string>
 
-#include "common/stb.h"
+#define STBI_ONLY_JPEG 1
+#include <stb_image.h>
+#include <stb_image_resize.h>
+#include <stb_image_write.h>
+
 #include "common/settings.h"
 #include "core/file_sys/control_metadata.h"
 #include "core/file_sys/patch_manager.h"

src/core/hle/service/nvdrv/devices/nvhost_nvdec.cpp

@@ -8,7 +8,6 @@
 #include "common/assert.h"
 #include "common/logging.h"
 #include "core/core.h"
-#include "core/hle/kernel/k_process.h"
 #include "core/hle/service/nvdrv/core/container.h"
 #include "core/hle/service/nvdrv/devices/ioctl_serialization.h"
 #include "core/hle/service/nvdrv/devices/nvhost_nvdec.h"
@@ -72,23 +71,17 @@ NvResult nvhost_nvdec::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> in
 
 void nvhost_nvdec::OnOpen(NvCore::SessionId session_id, DeviceFD fd) {
     LOG_INFO(Service_NVDRV, "NVDEC video stream started");
+    system.SetNVDECActive(true);
     sessions[fd] = session_id;
-    if (const auto* session = core.GetSession(session_id);
-        session != nullptr && session->process != nullptr) {
-        system.NotifyNVDECChannelOpen(session->process->GetId());
-    }
     host1x.StartDevice(fd, Tegra::Host1x::ChannelType::NvDec, channel_syncpoint);
 }
 
 void nvhost_nvdec::OnClose(DeviceFD fd) {
     LOG_INFO(Service_NVDRV, "NVDEC video stream ended");
     host1x.StopDevice(fd, Tegra::Host1x::ChannelType::NvDec);
+    system.SetNVDECActive(false);
     auto it = sessions.find(fd);
     if (it != sessions.end()) {
-        if (const auto* session = core.GetSession(it->second);
-            session != nullptr && session->process != nullptr) {
-            system.NotifyNVDECChannelClose(session->process->GetId());
-        }
         sessions.erase(it);
     }
 }

src/core/hle/service/service.cpp

@@ -4,16 +4,12 @@
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <chrono>
 #include <fmt/ranges.h>
-#include <string_view>
-#include <thread>
 #include "common/assert.h"
 #include "common/logging.h"
 #include "common/settings.h"
 #include "core/core.h"
 #include "core/hle/ipc.h"
-#include "core/hle/kernel/k_process.h"
 #include "core/hle/kernel/kernel.h"
 #include "core/hle/service/ipc_helpers.h"
 #include "core/hle/service/service.h"
@@ -37,7 +33,6 @@ ServiceFrameworkBase::ServiceFrameworkBase(Core::System& system_, const char* se
     : SessionRequestHandler(system_.Kernel(), service_name_)
     , system{system_}
     , service_name{service_name_}
-    , is_i_storage{std::string_view{service_name_} == "IStorage"}
     , handler_invoker{handler_invoker_}
     , max_sessions{max_sessions_}
 {}
@@ -82,22 +77,13 @@ void ServiceFrameworkBase::ReportUnimplementedFunction(HLERequestContext& ctx,
 }
 
 void ServiceFrameworkBase::InvokeRequest(HLERequestContext& ctx) {
-    const auto command = ctx.GetCommand();
-    auto it = handlers.find(command);
-    const bool is_cmd_read = command == 0;
+    auto it = handlers.find(ctx.GetCommand());
     FunctionInfoBase const* info = it == handlers.end() ? nullptr : &it->second;
     if (info == nullptr || info->handler_callback == nullptr)
         return ReportUnimplementedFunction(ctx, info);
 
     LOG_TRACE(Service, "{}", MakeFunctionString(info->name, GetServiceName(), ctx.CommandBuffer()));
     handler_invoker(this, info->handler_callback, ctx);
-
-    if (is_i_storage && is_cmd_read) {
-        const auto* const process = ctx.GetThread().GetOwnerProcess();
-        if (process != nullptr && system.IsNVDECActiveForProcess(process->GetId())) {
-            std::this_thread::sleep_for(std::chrono::microseconds{600});
-        }
-    }
 }
 
 void ServiceFrameworkBase::InvokeRequestTipc(HLERequestContext& ctx) {

src/core/hle/service/service.h

@@ -107,8 +107,6 @@ protected:
     Core::System& system;
     /// Identifier string used to connect to the service.
     const char* service_name;
-    /// Whether this is the IStorage service.
-    const bool is_i_storage;
     /// Function used to safely up-cast pointers to the derived class before invoking a handler.
     InvokerFn* handler_invoker;
     /// Maximum number of concurrent sessions that this service can handle.

src/dynarmic/src/dynarmic/backend/exception_handler_posix.cpp

@@ -22,7 +22,6 @@
 #include <sys/mman.h>
 
 #include "common/assert.h"
-#include "common/logging.h"
 #include "common/common_types.h"
 #include "dynarmic/backend/exception_handler.h"
 #include "dynarmic/common/context.h"
@@ -54,21 +53,23 @@ class SigHandler {
             return e.first <= offset && e.first + e.second.size > offset;
         });
     }
+    static void SigAction(int sig, siginfo_t* info, void* raw_context);
 
+    bool supports_fast_mem = true;
+    void* signal_stack_memory = nullptr;
     ankerl::unordered_dense::map<u64, CodeBlockInfo> code_block_infos;
     std::shared_mutex code_block_infos_mutex;
     struct sigaction old_sa_segv;
     struct sigaction old_sa_bus;
-    std::unique_ptr<uint8_t[]> signal_stack_memory;
-    bool supports_fast_mem = true;
+    std::size_t signal_stack_size;
 public:
     SigHandler() noexcept {
-        auto const stack_size = std::max<size_t>(SIGSTKSZ, 2 * 1024 * 1024);
-        signal_stack_memory = std::make_unique<uint8_t[]>(stack_size);
+        signal_stack_size = std::max<size_t>(SIGSTKSZ, 2 * 1024 * 1024);
+        signal_stack_memory = mmap(nullptr, signal_stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 
         stack_t signal_stack{};
-        signal_stack.ss_sp = signal_stack_memory.get();
-        signal_stack.ss_size = stack_size;
+        signal_stack.ss_sp = signal_stack_memory;
+        signal_stack.ss_size = signal_stack_size;
         signal_stack.ss_flags = 0;
         if (sigaltstack(&signal_stack, nullptr) != 0) {
             fmt::print(stderr, "dynarmic: POSIX SigHandler: init failure at sigaltstack\n");
@@ -86,7 +87,7 @@ public:
             supports_fast_mem = false;
             return;
         }
-#if defined(__APPLE__)
+#ifdef __APPLE__
         if (sigaction(SIGBUS, &sa, &old_sa_bus) != 0) {
             fmt::print(stderr, "dynarmic: POSIX SigHandler: could not set SIGBUS handler\n");
             supports_fast_mem = false;
@@ -95,6 +96,10 @@ public:
 #endif
     }
 
+    ~SigHandler() noexcept {
+        munmap(signal_stack_memory, signal_stack_size);
+    }
+
     void AddCodeBlock(u64 offset, CodeBlockInfo cbi) noexcept {
         std::unique_lock guard(code_block_infos_mutex);
         code_block_infos.insert_or_assign(offset, cbi);
@@ -104,17 +109,14 @@ public:
         code_block_infos.erase(offset);
     }
 
-    [[nodiscard]] inline bool SupportsFastmem() const noexcept {
-        return supports_fast_mem;
-    }
-
-    static void RegisterHandler();
-    static void SigAction(int sig, siginfo_t* info, void* raw_context);
+    bool SupportsFastmem() const noexcept { return supports_fast_mem; }
 };
 
+std::mutex handler_lock;
 std::optional<SigHandler> sig_handler;
 
-void SigHandler::RegisterHandler() {
+void RegisterHandler() {
+    std::lock_guard<std::mutex> guard(handler_lock);
     if (!sig_handler) {
         sig_handler.emplace();
     }
@@ -123,27 +125,51 @@ void SigHandler::RegisterHandler() {
 void SigHandler::SigAction(int sig, siginfo_t* info, void* raw_context) {
     DEBUG_ASSERT(sig == SIGSEGV || sig == SIGBUS);
     CTX_DECLARE(raw_context);
+#if defined(ARCHITECTURE_x86_64)
     {
         std::shared_lock guard(sig_handler->code_block_infos_mutex);
         if (auto const iter = sig_handler->FindCodeBlockInfo(CTX_PC); iter != sig_handler->code_block_infos.end()) {
             FakeCall fc = iter->second.cb(CTX_PC);
-#if defined(ARCHITECTURE_x86_64)
             CTX_SP -= sizeof(u64);
             *std::bit_cast<u64*>(CTX_SP) = fc.ret_rip;
             CTX_PC = fc.call_rip;
-#elif defined(ARCHITECTURE_arm64)
-            CTX_PC = fc.call_pc;
-#elif defined(ARCHITECTURE_riscv64)
-            CTX_PC = fc.call_sepc;
-#elif defined(ARCHITECTURE_loongarch64)
-            CTX_PC = fc.call_pc;
-#else
-            ASSERT(false);
-#endif
             return;
         }
     }
-    LOG_ERROR(Core, "Unhandled {} at {:#018x}\n", sig == SIGSEGV ? "SIGSEGV" : "SIGBUS", CTX_PC);
+    fmt::print(stderr, "Unhandled {} at rip {:#018x}\n", sig == SIGSEGV ? "SIGSEGV" : "SIGBUS", CTX_PC);
+#elif defined(ARCHITECTURE_arm64)
+    {
+        std::shared_lock guard(sig_handler->code_block_infos_mutex);
+        if (const auto iter = sig_handler->FindCodeBlockInfo(CTX_PC); iter != sig_handler->code_block_infos.end()) {
+            FakeCall fc = iter->second.cb(CTX_PC);
+            CTX_PC = fc.call_pc;
+            return;
+        }
+    }
+    fmt::print(stderr, "Unhandled {} at pc {:#018x}\n", sig == SIGSEGV ? "SIGSEGV" : "SIGBUS", CTX_PC);
+#elif defined(ARCHITECTURE_riscv64)
+    {
+        std::shared_lock guard(sig_handler->code_block_infos_mutex);
+        if (const auto iter = sig_handler->FindCodeBlockInfo(CTX_SEPC); iter != sig_handler->code_block_infos.end()) {
+            FakeCall fc = iter->second.cb(CTX_SEPC);
+            CTX_SEPC = fc.call_sepc;
+            return;
+        }
+    }
+    fmt::print(stderr, "Unhandled {} at pc {:#018x}\n", sig == SIGSEGV ? "SIGSEGV" : "SIGBUS", CTX_SEPC);
+#elif defined(ARCHITECTURE_loongarch64)
+    {
+        std::shared_lock guard(sig_handler->code_block_infos_mutex);
+        if (const auto iter = sig_handler->FindCodeBlockInfo(CTX_PC); iter != sig_handler->code_block_infos.end()) {
+            FakeCall fc = iter->second.cb(CTX_PC);
+            CTX_PC = fc.call_pc;
+            return;
+        }
+    }
+    fmt::print(stderr, "Unhandled {} at pc {:#018x}\n", sig == SIGSEGV ? "SIGSEGV" : "SIGBUS", CTX_PC);
+#else
+#    error "Invalid architecture"
+#endif
 
     struct sigaction* retry_sa = sig == SIGSEGV ? &sig_handler->old_sa_segv : &sig_handler->old_sa_bus;
     if (retry_sa->sa_flags & SA_SIGINFO) {
@@ -164,10 +190,9 @@ void SigHandler::SigAction(int sig, siginfo_t* info, void* raw_context) {
 
 struct ExceptionHandler::Impl final {
     Impl(u64 offset_, u64 size_)
-        : offset(offset_)
-        , size(size_)
-    {
-        SigHandler::RegisterHandler();
+            : offset(offset_)
+            , size(size_) {
+        RegisterHandler();
     }
 
     void SetCallback(std::function<FakeCall(u64)> cb) {

src/dynarmic/src/dynarmic/backend/loongarch64/emit_loongarch64.cpp

@@ -1,7 +1,6 @@
 // SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
-#include <variant>
 #include "dynarmic/backend/loongarch64/emit_loongarch64.h"
 
 #include "dynarmic/backend/loongarch64/a32_jitstate.h"
@@ -96,8 +95,7 @@ EmittedBlockInfo EmitLoongArch64(lagoon_assembler_t& as, IR::Block block, const
 
     // TODO: Emit Terminal
     const auto term = block.GetTerminal();
-    const IR::Term::LeafTerminal* leaft_term = std::get_if<IR::Term::LeafTerminal>(&term);
-    const IR::Term::LinkBlock* link_block_term = std::get_if<IR::Term::LinkBlock>(leaft_term);
+    const IR::Term::LinkBlock* link_block_term = boost::get<IR::Term::LinkBlock>(&term);
     ASSERT(link_block_term);
     la_load_immediate64(&as, Xscratch0, link_block_term->next.Value());
     la_st_w(&as, Xscratch0, Xstate, static_cast<int32_t>(offsetof(A32JitState, regs) + sizeof(u32) * 15));

src/dynarmic/src/dynarmic/common/context.h

@@ -136,14 +136,14 @@
 #    endif
 #elif defined(ARCHITECTURE_riscv64)
 #   if defined(__FreeBSD__)
-#       define CTX_PC (mctx.mc_gpregs.gp_sepc)
+#       define CTX_SEPC (mctx.mc_gpregs.gp_sepc)
 #       define CTX_SP (mctx.mc_gpregs.gp_sp)
 #   elif defined(__linux__)
-#       define CTX_PC (mctx.__gregs[REG_PC])
+#       define CTX_SEPC (mctx.__gregs[REG_PC])
 #       define CTX_SP (mctx.__gregs[REG_SP])
 #   elif defined(__OpenBSD__)
 // https://github.com/openbsd/src/blob/master/sys/arch/riscv64/include/signal.h
-#        define CTX_PC (ucontext->sc_sepc)
+#        define CTX_SEPC (ucontext->sc_sepc)
 #        define CTX_SP (ucontext->sc_sp)
 #    else
 #        error "unknown platform"

src/qt_common/discord/discord_impl.cpp

@@ -74,8 +74,8 @@ static constexpr char DEFAULT_DISCORD_IMAGE[] =
     "https://git.eden-emu.dev/eden-emu/eden/raw/branch/master/dist/qt_themes/default/icons/256x256/"
     "eden.png";
 
-void DiscordImpl::UpdateGameStatus(std::string_view game_url, bool has_boxart) {
-    const std::string url = std::string{has_boxart ? game_url : DEFAULT_DISCORD_IMAGE};
+void DiscordImpl::UpdateGameStatus(bool use_default) {
+    const std::string url = use_default ? std::string{DEFAULT_DISCORD_IMAGE} : game_url;
     s64 start_time = std::chrono::duration_cast<std::chrono::seconds>(
                          std::chrono::system_clock::now().time_since_epoch())
                          .count();
@@ -98,7 +98,7 @@ void DiscordImpl::Update() {
 
         // Used to format Icon URL for yuzu website game compatibility page
         std::string icon_name = GetGameString(game_title);
-        auto const game_url = fmt::format(
+        game_url = fmt::format(
             "https://raw.githubusercontent.com/eden-emulator/boxart/refs/heads/master/img/{}.png",
             icon_name);
 
@@ -117,7 +117,7 @@ void DiscordImpl::Update() {
         };
 
         auto res = client.send(request);
-        UpdateGameStatus(game_url, res && res->status == 200);
+        UpdateGameStatus(res && res->status == 200);
 
         return;
     }

src/qt_common/discord/discord_impl.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: 2018 Citra Emulator Project
@@ -26,9 +26,11 @@ public:
 
 private:
     std::string GetGameString(const std::string& title);
-    void UpdateGameStatus(std::string_view game_url, bool use_default);
+    void UpdateGameStatus(bool use_default);
 
+    std::string game_url{};
     std::string game_title{};
+
     Core::System& system;
 };
 

src/shader_recompiler/backend/glasm/emit_glasm_instructions.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -665,8 +665,6 @@ void EmitShuffleDown(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU3
                      const IR::Value& clamp, const IR::Value& segmentation_mask);
 void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 index,
                           const IR::Value& clamp, const IR::Value& segmentation_mask);
-void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 lane);
-void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 direction);
 void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, ScalarF32 op_a, ScalarF32 op_b,
                      ScalarU32 swizzle);
 void EmitDPdxFine(EmitContext& ctx, IR::Inst& inst, ScalarF32 op_a);

src/shader_recompiler/backend/glasm/emit_glasm_warp.cpp

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -100,24 +97,6 @@ void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, Sca
     Shuffle(ctx, inst, value, index, clamp, segmentation_mask, "XOR");
 }
 
-void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 lane) {
-    const Register ret{ctx.reg_alloc.Define(inst)};
-    ctx.Add("AND.U RC.x,{}.threadid,~3;"
-            "AND.U RC.y,{},3;"
-            "OR.U RC.x,RC.x,RC.y;"
-            "SHFIDX.U {},{},RC.x,0x1C03;"
-            "MOV.U {}.x,{}.y;",
-            ctx.stage_name, lane, ret, value, ret, ret);
-}
-
-void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 direction) {
-    const Register ret{ctx.reg_alloc.Define(inst)};
-    ctx.Add("ADD.U RC.x,{},1;"
-            "SHFXOR.U {},{},RC.x,0x1C03;"
-            "MOV.U {}.x,{}.y;",
-            direction, ret, value, ret, ret);
-}
-
 void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, ScalarF32 op_a, ScalarF32 op_b,
                      ScalarU32 swizzle) {
     const auto ret{ctx.reg_alloc.Define(inst)};

src/shader_recompiler/backend/glsl/emit_glsl_instructions.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -743,10 +743,6 @@ void EmitShuffleDown(EmitContext& ctx, IR::Inst& inst, std::string_view value,
 void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, std::string_view value,
                           std::string_view index, std::string_view clamp,
                           std::string_view segmentation_mask);
-void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, std::string_view value,
-                       std::string_view lane);
-void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, std::string_view value,
-                  std::string_view direction);
 void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, std::string_view op_a, std::string_view op_b,
                      std::string_view swizzle);
 void EmitDPdxFine(EmitContext& ctx, IR::Inst& inst, std::string_view op_a);

src/shader_recompiler/backend/glsl/emit_glsl_warp.cpp

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -203,18 +200,6 @@ void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, std::string_view val
     ctx.AddU32("{}=shfl_in_bounds?shfl_result:{};", inst, value);
 }
 
-void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, std::string_view value,
-                       std::string_view lane) {
-    const auto src_thread_id{fmt::format("(({}&~3)|({}& 3))", THREAD_ID, lane)};
-    ctx.AddU32("{}=readInvocationARB({},{});", inst, value, src_thread_id);
-}
-
-void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, std::string_view value,
-                  std::string_view direction) {
-    const auto src_thread_id{fmt::format("({}^({}+1))", THREAD_ID, direction)};
-    ctx.AddU32("{}=readInvocationARB({},{});", inst, value, src_thread_id);
-}
-
 void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, std::string_view op_a, std::string_view op_b,
                      std::string_view swizzle) {
     const auto mask{fmt::format("({}>>((gl_SubGroupInvocationARB&3)<<1))&3", swizzle)};

src/shader_recompiler/backend/spirv/emit_spirv.cpp

@@ -322,11 +322,6 @@ void DefineEntryPoint(const IR::Program& program, EmitContext& ctx, Id main) {
         if (ctx.runtime_info.force_early_z) {
             ctx.AddExecutionMode(main, spv::ExecutionMode::EarlyFragmentTests);
         }
-        if (ctx.profile.support_shader_quad_control && program.info.uses_quad_shuffles) {
-            ctx.AddExtension("SPV_KHR_quad_control");
-            ctx.AddCapability(spv::Capability::QuadControlKHR);
-            ctx.AddExecutionMode(main, spv::ExecutionMode::RequireFullQuadsKHR);
-        }
         break;
     default:
         throw NotImplementedException("Stage {}", program.stage);
@@ -448,12 +443,6 @@ void SetupCapabilities(const Profile& profile, const Info& info, EmitContext& ct
             ctx.AddCapability(spv::Capability::GroupNonUniformVote);
         }
     }
-    if (info.uses_quad_shuffles) {
-        if (profile.support_quad_shuffles) {
-            ctx.AddCapability(spv::Capability::GroupNonUniformQuad);
-        }
-        ctx.AddCapability(spv::Capability::GroupNonUniformShuffle);
-    }
     if (info.uses_int64_bit_atomics && profile.support_int64_atomics) {
         ctx.AddCapability(spv::Capability::Int64Atomics);
     }

src/shader_recompiler/backend/spirv/emit_spirv_instructions.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -622,8 +622,6 @@ Id EmitShuffleDown(EmitContext& ctx, IR::Inst* inst, Id value, Id index, Id clam
                    Id segmentation_mask);
 Id EmitShuffleButterfly(EmitContext& ctx, IR::Inst* inst, Id value, Id index, Id clamp,
                         Id segmentation_mask);
-Id EmitQuadBroadcast(EmitContext& ctx, Id value, Id lane);
-Id EmitQuadSwap(EmitContext& ctx, Id value, Id direction);
 Id EmitFSwizzleAdd(EmitContext& ctx, Id op_a, Id op_b, Id swizzle);
 Id EmitDPdxFine(EmitContext& ctx, Id op_a);
 Id EmitDPdyFine(EmitContext& ctx, Id op_a);

src/shader_recompiler/backend/spirv/emit_spirv_warp.cpp

@@ -260,21 +260,6 @@ Id EmitShuffleButterfly(EmitContext& ctx, IR::Inst* inst, Id value, Id index, Id
     return SelectValue(ctx, in_range, value, src_thread_id);
 }
 
-Id EmitQuadBroadcast(EmitContext& ctx, Id value, Id lane) {
-    if (ctx.profile.support_quad_shuffles) {
-        return ctx.OpGroupNonUniformQuadBroadcast(ctx.U32[1], SubgroupScope(ctx), value, lane);
-    }
-    const Id base{ctx.OpBitwiseAnd(ctx.U32[1], GetThreadId(ctx), ctx.Const(~3u))};
-    const Id local_lane{ctx.OpBitwiseAnd(ctx.U32[1], lane, ctx.Const(3u))};
-    const Id src_thread_id{ctx.OpBitwiseOr(ctx.U32[1], base, local_lane)};
-    return ctx.OpGroupNonUniformShuffle(ctx.U32[1], SubgroupScope(ctx), value, src_thread_id);
-}
-
-Id EmitQuadSwap(EmitContext& ctx, Id value, Id direction) {
-    const Id xor_mask{ctx.OpIAdd(ctx.U32[1], direction, ctx.Const(1u))};
-    return ctx.OpGroupNonUniformShuffleXor(ctx.U32[1], SubgroupScope(ctx), value, xor_mask);
-}
-
 Id EmitFSwizzleAdd(EmitContext& ctx, Id op_a, Id op_b, Id swizzle) {
     const Id three{ctx.Const(3U)};
     Id mask{GetThreadId(ctx)};

src/shader_recompiler/frontend/ir/ir_emitter.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 2021 yuzu Emulator Project
@@ -2100,14 +2100,6 @@ U32 IREmitter::ShuffleButterfly(const IR::U32& value, const IR::U32& index, cons
     return Inst<U32>(Opcode::ShuffleButterfly, value, index, clamp, seg_mask);
 }
 
-U32 IREmitter::QuadBroadcast(const IR::U32& value, const IR::U32& lane) {
-    return Inst<U32>(Opcode::QuadBroadcast, value, lane);
-}
-
-U32 IREmitter::QuadSwap(const IR::U32& value, const IR::U32& direction) {
-    return Inst<U32>(Opcode::QuadSwap, value, direction);
-}
-
 F32 IREmitter::FSwizzleAdd(const F32& a, const F32& b, const U32& swizzle, FpControl control) {
     return Inst<F32>(Opcode::FSwizzleAdd, Flags{control}, a, b, swizzle);
 }

src/shader_recompiler/frontend/ir/ir_emitter.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -394,8 +394,6 @@ public:
                                   const IR::U32& seg_mask);
     [[nodiscard]] U32 ShuffleButterfly(const IR::U32& value, const IR::U32& index,
                                        const IR::U32& clamp, const IR::U32& seg_mask);
-    [[nodiscard]] U32 QuadBroadcast(const IR::U32& value, const IR::U32& lane);
-    [[nodiscard]] U32 QuadSwap(const IR::U32& value, const IR::U32& direction);
     [[nodiscard]] F32 FSwizzleAdd(const F32& a, const F32& b, const U32& swizzle,
                                   FpControl control = {});
 

src/shader_recompiler/frontend/ir/opcodes.cpp

@@ -10,7 +10,7 @@ namespace Shader::IR {
 
 namespace Detail {
 
-OpcodeMeta META_TABLE[534] = {
+OpcodeMeta META_TABLE[532] = {
 #define OPCODE(name_token, type_token, ...)                                                        \
     {                                                                                              \
         .name{#name_token},                                                                        \
@@ -21,7 +21,7 @@ OpcodeMeta META_TABLE[534] = {
 #undef OPCODE
 };
 
-u8 NUM_ARGS[534] = {
+u8 NUM_ARGS[532] = {
 #define OPCODE(name_token, type_token, ...) u8(CalculateNumArgsOf(Opcode::name_token)),
 #include "opcodes.inc"
 #undef OPCODE

src/shader_recompiler/frontend/ir/opcodes.h

@@ -57,12 +57,12 @@ static constexpr Type F64x2{Type::F64x2};
 static constexpr Type F64x3{Type::F64x3};
 static constexpr Type F64x4{Type::F64x4};
 
-extern OpcodeMeta META_TABLE[534];
+extern OpcodeMeta META_TABLE[532];
 constexpr size_t CalculateNumArgsOf(Opcode op) noexcept {
     const auto& arg_types = META_TABLE[size_t(op)].arg_types;
     return size_t(std::distance(arg_types.begin(), std::ranges::find(arg_types, Type::Void)));
 }
-extern u8 NUM_ARGS[534];
+extern u8 NUM_ARGS[532];
 } // namespace Detail
 
 /// Get return type of an opcode

src/shader_recompiler/frontend/ir/opcodes.inc

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -582,8 +579,6 @@ OPCODE(ShuffleIndex,                                        U32,            U32,
 OPCODE(ShuffleUp,                                           U32,            U32,            U32,            U32,            U32,                            )
 OPCODE(ShuffleDown,                                         U32,            U32,            U32,            U32,            U32,                            )
 OPCODE(ShuffleButterfly,                                    U32,            U32,            U32,            U32,            U32,                            )
-OPCODE(QuadBroadcast,                                       U32,            U32,            U32,                                                                    )
-OPCODE(QuadSwap,                                            U32,            U32,            U32,                                                                    )
 OPCODE(FSwizzleAdd,                                         F32,            F32,            F32,            U32,                                            )
 OPCODE(DPdxFine,                                            F32,            F32,                                                                            )
 OPCODE(DPdyFine,                                            F32,            F32,                                                                            )

src/shader_recompiler/frontend/maxwell/translate/impl/warp_shuffle.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 2021 yuzu Emulator Project
@@ -36,10 +36,7 @@ enum class ShuffleMode : u64 {
     }
 }
 
-constexpr u32 QUAD_MASK = (28u << 8) | 3u;
-
-void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32& mask,
-             bool index_is_imm, u32 index_imm, bool mask_is_imm, u32 mask_imm) {
+void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32& mask) {
     union {
         u64 insn;
         BitField<0, 8, IR::Reg> dest_reg;
@@ -48,21 +45,6 @@ void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32
         BitField<48, 3, IR::Pred> pred;
     } const shfl{insn};
 
-    const bool is_quad_candidate{mask_is_imm && mask_imm == QUAD_MASK && index_is_imm &&
-                                  v.env.ShaderStage() == Stage::Fragment};
-    if (is_quad_candidate) {
-        if (shfl.mode == ShuffleMode::IDX && index_imm <= 3) {
-            v.X(shfl.dest_reg, v.ir.QuadBroadcast(v.X(shfl.src_reg), v.ir.Imm32(index_imm)));
-            v.ir.SetPred(shfl.pred, v.ir.Imm1(true));
-            return;
-        }
-        if (shfl.mode == ShuffleMode::BFLY && index_imm >= 1 && index_imm <= 3) {
-            v.X(shfl.dest_reg, v.ir.QuadSwap(v.X(shfl.src_reg), v.ir.Imm32(index_imm - 1)));
-            v.ir.SetPred(shfl.pred, v.ir.Imm1(true));
-            return;
-        }
-    }
-
     const IR::U32 result{ShuffleOperation(v.ir, v.X(shfl.src_reg), index, mask, shfl.mode)};
     v.ir.SetPred(shfl.pred, v.ir.GetInBoundsFromOp(result));
     v.X(shfl.dest_reg, result);
@@ -77,14 +59,11 @@ void TranslatorVisitor::SHFL(u64 insn) {
         BitField<29, 1, u64> src_b_flag;
         BitField<34, 13, u64> src_b_imm;
     } const flags{insn};
-    const bool index_is_imm{flags.src_a_flag != 0};
-    const bool mask_is_imm{flags.src_b_flag != 0};
-    const IR::U32 src_a{index_is_imm ? ir.Imm32(static_cast<u32>(flags.src_a_imm))
-                                     : GetReg20(insn)};
-    const IR::U32 src_b{mask_is_imm ? ir.Imm32(static_cast<u32>(flags.src_b_imm))
-                                    : GetReg39(insn)};
-    Shuffle(*this, insn, src_a, src_b, index_is_imm, static_cast<u32>(flags.src_a_imm),
-            mask_is_imm, static_cast<u32>(flags.src_b_imm));
+    const IR::U32 src_a{flags.src_a_flag != 0 ? ir.Imm32(static_cast<u32>(flags.src_a_imm))
+                                              : GetReg20(insn)};
+    const IR::U32 src_b{flags.src_b_flag != 0 ? ir.Imm32(static_cast<u32>(flags.src_b_imm))
+                                              : GetReg39(insn)};
+    Shuffle(*this, insn, src_a, src_b);
 }
 
 } // namespace Shader::Maxwell

src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp

@@ -498,10 +498,6 @@ void VisitUsages(Info& info, IR::Inst& inst) {
     case IR::Opcode::ShuffleButterfly:
         info.uses_subgroup_shuffles = true;
         break;
-    case IR::Opcode::QuadBroadcast:
-    case IR::Opcode::QuadSwap:
-        info.uses_quad_shuffles = true;
-        break;
     case IR::Opcode::GetCbufU8:
     case IR::Opcode::GetCbufS8:
     case IR::Opcode::GetCbufU16:

src/shader_recompiler/profile.h

@@ -37,8 +37,6 @@ struct Profile {
     bool support_explicit_workgroup_layout{};
     bool support_workgroup_layout_8bit_access{};
     bool support_workgroup_layout_16bit_access{};
-    bool support_shader_quad_control{};
-    bool support_quad_shuffles{};
     bool support_vote{};
     u32 supported_subgroup_stages{0x7F};
     bool support_viewport_index_layer_non_geometry{};

src/shader_recompiler/shader_info.h

@@ -252,7 +252,6 @@ struct Info {
     bool uses_is_helper_invocation{};
     bool uses_subgroup_invocation_id{};
     bool uses_subgroup_shuffles{};
-    bool uses_quad_shuffles{};
     std::array<bool, 30> uses_patches{};
 
     std::array<Interpolation, 32> interpolation{};

src/video_core/host_shaders/CMakeLists.txt

@@ -206,6 +206,40 @@ foreach(VARIANT IN ITEMS ${SHADER_TYPE_VARIANTS})
     set(SHADER_HEADERS ${SHADER_HEADERS} ${VARIANT_HEADER_FILE})
 endforeach()
 
+set(SHADER_DEFINE_VARIANTS
+    "block_linear_unswizzle_2d.comp|nonarrow|HAS_EXTENDED_TYPES=0"
+    "pitch_unswizzle.comp|nonarrow|HAS_EXTENDED_TYPES=0"
+    "block_linear_unswizzle_3d.comp|nonarrow|HAS_EXTENDED_TYPES=0"
+)
+
+foreach(VARIANT IN ITEMS ${SHADER_DEFINE_VARIANTS})
+    string(REPLACE "|" ";" VARIANT_PARTS ${VARIANT})
+    list(GET VARIANT_PARTS 0 VARIANT_FILENAME)
+    list(GET VARIANT_PARTS 1 VARIANT_SUFFIX)
+    list(GET VARIANT_PARTS 2 VARIANT_DEFINE)
+
+    set(VARIANT_SOURCE ${CMAKE_CURRENT_SOURCE_DIR}/${VARIANT_FILENAME})
+    get_filename_component(VARIANT_STEM ${VARIANT_FILENAME} NAME_WE)
+    get_filename_component(VARIANT_EXT ${VARIANT_FILENAME} EXT)
+    string(REPLACE "." "" VARIANT_EXT ${VARIANT_EXT})
+    set(VARIANT_NAME ${VARIANT_STEM}_${VARIANT_SUFFIX}_${VARIANT_EXT})
+
+    string(TOUPPER ${VARIANT_NAME}_SPV VARIANT_VARIABLE_NAME)
+    set(VARIANT_HEADER_FILE ${SHADER_DIR}/${VARIANT_NAME}_spv.h)
+    add_custom_command(
+        OUTPUT
+            ${VARIANT_HEADER_FILE}
+        COMMAND
+            ${GLSLANGVALIDATOR} -V ${QUIET_FLAG} -I"${FIDELITYFX_INCLUDE_DIR}" ${GLSL_FLAGS}
+            -D${VARIANT_DEFINE}
+            --variable-name ${VARIANT_VARIABLE_NAME} -o ${VARIANT_HEADER_FILE} ${VARIANT_SOURCE}
+            --target-env ${SPIR_V_VERSION}
+        MAIN_DEPENDENCY
+            ${VARIANT_SOURCE}
+    )
+    set(SHADER_HEADERS ${SHADER_HEADERS} ${VARIANT_HEADER_FILE})
+endforeach()
+
 foreach(FILEPATH IN ITEMS ${FIDELITYFX_FILES})
     get_filename_component(FILENAME ${FILEPATH} NAME)
     string(REPLACE "." "_" HEADER_NAME ${FILENAME})

src/video_core/host_shaders/block_linear_unswizzle_2d.comp

@@ -5,9 +5,13 @@
 
 #ifdef VULKAN
 
+#ifndef HAS_EXTENDED_TYPES
+#define HAS_EXTENDED_TYPES 1
+#endif
+#if HAS_EXTENDED_TYPES
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_shader_8bit_storage : require
-#define HAS_EXTENDED_TYPES 1
+#endif
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)

src/video_core/host_shaders/block_linear_unswizzle_3d.comp

@@ -5,9 +5,13 @@
 
 #ifdef VULKAN
 
+#ifndef HAS_EXTENDED_TYPES
+#define HAS_EXTENDED_TYPES 1
+#endif
+#if HAS_EXTENDED_TYPES
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_shader_8bit_storage : require
-#define HAS_EXTENDED_TYPES 1
+#endif
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)

src/video_core/host_shaders/pitch_unswizzle.comp

@@ -5,9 +5,13 @@
 
 #ifdef VULKAN
 
+#ifndef HAS_EXTENDED_TYPES
+#define HAS_EXTENDED_TYPES 1
+#endif
+#if HAS_EXTENDED_TYPES
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_shader_8bit_storage : require
-#define HAS_EXTENDED_TYPES 1
+#endif
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)

src/video_core/renderer_vulkan/vk_compute_pass.cpp

@@ -22,7 +22,13 @@
 #include "video_core/host_shaders/resolve_conditional_render_comp_spv.h"
 #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_2d_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_2d_nonarrow_comp_spv.h"
 #include "video_core/host_shaders/block_linear_unswizzle_3d_bcn_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_3d_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_3d_nonarrow_comp_spv.h"
+#include "video_core/host_shaders/pitch_unswizzle_comp_spv.h"
+#include "video_core/host_shaders/pitch_unswizzle_nonarrow_comp_spv.h"
 #include "video_core/renderer_vulkan/vk_compute_pass.h"
 #include "video_core/surface.h"
 #include "video_core/renderer_vulkan/vk_descriptor_pool.h"
@@ -872,4 +878,291 @@ void BlockLinearUnswizzle3DPass::UnswizzleChunk(
     });
 }
 
+namespace {
+
+constexpr u32 UNSWIZZLE_BINDING_INPUT_BUFFER = 0;
+constexpr u32 UNSWIZZLE_BINDING_OUTPUT_IMAGE = 1;
+constexpr size_t UNSWIZZLE_NUM_BINDINGS = 2;
+
+constexpr std::array<VkDescriptorSetLayoutBinding, UNSWIZZLE_NUM_BINDINGS>
+    UNSWIZZLE_DESCRIPTOR_SET_BINDINGS{{
+        {
+            .binding = UNSWIZZLE_BINDING_INPUT_BUFFER,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
+            .descriptorCount = 1,
+            .stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
+            .pImmutableSamplers = nullptr,
+        },
+        {
+            .binding = UNSWIZZLE_BINDING_OUTPUT_IMAGE,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_IMAGE,
+            .descriptorCount = 1,
+            .stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
+            .pImmutableSamplers = nullptr,
+        },
+    }};
+
+constexpr std::array<VkDescriptorUpdateTemplateEntry, UNSWIZZLE_NUM_BINDINGS>
+    UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE{{
+        {
+            .dstBinding = UNSWIZZLE_BINDING_INPUT_BUFFER,
+            .dstArrayElement = 0,
+            .descriptorCount = 1,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
+            .offset = UNSWIZZLE_BINDING_INPUT_BUFFER * sizeof(DescriptorUpdateEntry),
+            .stride = sizeof(DescriptorUpdateEntry),
+        },
+        {
+            .dstBinding = UNSWIZZLE_BINDING_OUTPUT_IMAGE,
+            .dstArrayElement = 0,
+            .descriptorCount = 1,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_IMAGE,
+            .offset = UNSWIZZLE_BINDING_OUTPUT_IMAGE * sizeof(DescriptorUpdateEntry),
+            .stride = sizeof(DescriptorUpdateEntry),
+        },
+    }};
+
+constexpr DescriptorBankInfo UNSWIZZLE_BANK_INFO{
+    .uniform_buffers = 0,
+    .storage_buffers = 1,
+    .texture_buffers = 0,
+    .image_buffers = 0,
+    .textures = 0,
+    .images = 1,
+    .score = 2,
+};
+
+[[nodiscard]] std::span<const u32> UnswizzleSpv(const Device& device,
+                                                std::span<const u32> extended,
+                                                std::span<const u32> narrow) {
+    if (device.IsStorageBuffer8BitAccessSupported() &&
+        device.IsStorageBuffer16BitAccessSupported()) {
+        return extended;
+    }
+    return narrow;
+}
+
+struct PitchUnswizzlePushConstants {
+    alignas(8) std::array<u32, 2> origin;
+    alignas(8) std::array<s32, 2> destination;
+    u32 bytes_per_block;
+    u32 pitch;
+};
+
+void RecordUnswizzleEntryBarrier(Scheduler& scheduler, VkPipeline vk_pipeline, VkImage vk_image,
+                                 VkImageAspectFlags aspect_mask, bool is_initialized) {
+    scheduler.Record([vk_pipeline, vk_image, aspect_mask,
+                      is_initialized](vk::CommandBuffer cmdbuf) {
+        VkAccessFlags src_access = VK_ACCESS_NONE;
+        VkImageLayout old_layout = VK_IMAGE_LAYOUT_UNDEFINED;
+        if (is_initialized) {
+            src_access = VK_ACCESS_SHADER_WRITE_BIT | VK_ACCESS_TRANSFER_WRITE_BIT |
+                         VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;
+            old_layout = VK_IMAGE_LAYOUT_GENERAL;
+        }
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = src_access,
+            .dstAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .oldLayout = old_layout,
+            .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,
+            },
+        };
+        VkPipelineStageFlags src_stage = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
+        if (is_initialized) {
+            src_stage = vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER;
+        }
+        cmdbuf.PipelineBarrier(src_stage, VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, image_barrier);
+        cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, vk_pipeline);
+    });
+}
+
+void RecordUnswizzleExitBarrier(Scheduler& scheduler, VkImage vk_image,
+                                VkImageAspectFlags aspect_mask) {
+    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_TRANSFER_READ_BIT |
+                             VK_ACCESS_COLOR_ATTACHMENT_READ_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);
+    });
+}
+
+} // Anonymous namespace
+
+BlockLinearUnswizzle2DPass::BlockLinearUnswizzle2DPass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, UNSWIZZLE_DESCRIPTOR_SET_BINDINGS,
+                  UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE, UNSWIZZLE_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(
+                      VideoCommon::Accelerated::BlockLinearSwizzle2DParams)>,
+                  UnswizzleSpv(device_, BLOCK_LINEAR_UNSWIZZLE_2D_COMP_SPV,
+                               BLOCK_LINEAR_UNSWIZZLE_2D_NONARROW_COMP_SPV)),
+      scheduler{scheduler_}, compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+BlockLinearUnswizzle2DPass::~BlockLinearUnswizzle2DPass() = default;
+
+void BlockLinearUnswizzle2DPass::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();
+    RecordUnswizzleEntryBarrier(scheduler, vk_pipeline, vk_image, aspect_mask, is_initialized);
+
+    const u32 num_layers = static_cast<u32>(image.info.resources.layers);
+    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 auto params = MakeBlockLinearSwizzle2DParams(swizzle, image.info);
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, num_layers, 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_layers);
+        });
+    }
+    RecordUnswizzleExitBarrier(scheduler, vk_image, aspect_mask);
+}
+
+BlockLinearUnswizzleImage3DPass::BlockLinearUnswizzleImage3DPass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, UNSWIZZLE_DESCRIPTOR_SET_BINDINGS,
+                  UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE, UNSWIZZLE_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(BlockLinearSwizzle3DParams)>,
+                  UnswizzleSpv(device_, BLOCK_LINEAR_UNSWIZZLE_3D_COMP_SPV,
+                               BLOCK_LINEAR_UNSWIZZLE_3D_NONARROW_COMP_SPV)),
+      scheduler{scheduler_}, 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();
+    RecordUnswizzleEntryBarrier(scheduler, vk_pipeline, vk_image, aspect_mask, is_initialized);
+
+    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 params = MakeBlockLinearSwizzle3DParams(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);
+        });
+    }
+    RecordUnswizzleExitBarrier(scheduler, vk_image, aspect_mask);
+}
+
+PitchUnswizzlePass::PitchUnswizzlePass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, UNSWIZZLE_DESCRIPTOR_SET_BINDINGS,
+                  UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE, UNSWIZZLE_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(PitchUnswizzlePushConstants)>,
+                  UnswizzleSpv(device_, PITCH_UNSWIZZLE_COMP_SPV,
+                               PITCH_UNSWIZZLE_NONARROW_COMP_SPV)),
+      scheduler{scheduler_}, 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();
+    RecordUnswizzleEntryBarrier(scheduler, vk_pipeline, vk_image, aspect_mask, is_initialized);
+
+    const u32 bytes_per_block = VideoCore::Surface::BytesPerBlock(image.info.format);
+    const u32 pitch = image.info.pitch;
+    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 = 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);
+        });
+    }
+    RecordUnswizzleExitBarrier(scheduler, vk_image, aspect_mask);
+}
+
 } // namespace Vulkan

src/video_core/renderer_vulkan/vk_compute_pass.h

@@ -164,4 +164,49 @@ private:
     ComputePassDescriptorQueue& compute_pass_descriptor_queue;
 };
 
+class BlockLinearUnswizzle2DPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzle2DPass(
+        const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+        ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzle2DPass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
+class BlockLinearUnswizzleImage3DPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzleImage3DPass(
+        const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+        ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzleImage3DPass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
+class PitchUnswizzlePass final : public ComputePass {
+public:
+    explicit PitchUnswizzlePass(const Device& device_, Scheduler& scheduler_,
+                                DescriptorPool& descriptor_pool_,
+                                ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~PitchUnswizzlePass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
 } // namespace Vulkan

src/video_core/renderer_vulkan/vk_pipeline_cache.cpp

@@ -404,8 +404,6 @@ PipelineCache::PipelineCache(Tegra::MaxwellDeviceMemoryManager& device_memory_,
             device.IsWorkgroupMemoryExplicitLayout8BitAccessSupported(),
         .support_workgroup_layout_16bit_access =
             device.IsWorkgroupMemoryExplicitLayout16BitAccessSupported(),
-        .support_shader_quad_control = device.IsKhrShaderQuadControlSupported(),
-        .support_quad_shuffles = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_QUAD_BIT),
         .support_vote = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_VOTE_BIT),
         .supported_subgroup_stages = supported_subgroup_stages,
         .support_viewport_index_layer_non_geometry =

src/video_core/renderer_vulkan/vk_scheduler.cpp

@@ -449,7 +449,9 @@ void Scheduler::EndRenderPass()
                                          | VK_ACCESS_COLOR_ATTACHMENT_READ_BIT
                                          | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT
                                          | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_READ_BIT
-                                         | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
+                                         | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_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,
@@ -460,7 +462,7 @@ void Scheduler::EndRenderPass()
             }
             cmdbuf.EndRenderPass();
             cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
-                                   VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE,
+                                   VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER,
                                    0, nullptr, nullptr, vk::Span(barriers.data(), num_images));
             if (has_transform_feedback) {
                 static constexpr VkMemoryBarrier XFB_OUTPUT_BARRIER{

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -160,6 +160,55 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
           info.size.depth == 1;
 }
 
+[[nodiscard]] PixelFormat UnswizzleViewFormat(u32 bytes_per_block) {
+    switch (bytes_per_block) {
+    case 1:
+        return PixelFormat::R8_UINT;
+    case 2:
+        return PixelFormat::R16_UINT;
+    case 4:
+        return PixelFormat::R32_UINT;
+    case 8:
+        return PixelFormat::R32G32_UINT;
+    case 16:
+        return PixelFormat::R32G32B32A32_UINT;
+    default:
+        return PixelFormat::Invalid;
+    }
+}
+
+constexpr u32 UNSWIZZLE_WORKGROUP_INVOCATIONS = 32 * 32;
+
+[[nodiscard]] bool SupportsAcceleratedUnswizzleDevice(const Device& device) {
+    return device.IsKhrImageFormatListSupported() &&
+           device.GetMaxComputeWorkGroupInvocations() >= UNSWIZZLE_WORKGROUP_INVOCATIONS;
+}
+
+[[nodiscard]] bool SupportsAcceleratedUnswizzle(const Device& device, const ImageInfo& info) {
+    if (!SupportsAcceleratedUnswizzleDevice(device)) {
+        return false;
+    }
+    if (info.num_samples > 1) {
+        return false;
+    }
+    if (info.type != ImageType::e2D && info.type != ImageType::e3D &&
+        info.type != ImageType::Linear) {
+        return false;
+    }
+    const PixelFormat view_format =
+        UnswizzleViewFormat(VideoCore::Surface::BytesPerBlock(info.format));
+    if (view_format == PixelFormat::Invalid) {
+        return false;
+    }
+    if (!VideoCore::Surface::IsViewCompatible(info.format, view_format, false, true)) {
+        return false;
+    }
+    const auto host_format =
+        MaxwellToVK::SurfaceFormat(device, FormatType::Optimal, false, view_format);
+    return device.IsFormatSupported(host_format.format, VK_FORMAT_FEATURE_STORAGE_IMAGE_BIT,
+                                    FormatType::Optimal);
+}
+
 [[nodiscard]] VkImageCreateInfo MakeImageCreateInfo(const Device& device, const ImageInfo& info,
                                                     std::optional<VkFormat> format_override = {}) {
     auto format_info =
@@ -248,8 +297,18 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
     return allocator.CreateImage(image_ci);
 }
 
+[[nodiscard]] VkImageViewType StorageViewType(ImageType type) {
+    if (type == ImageType::e3D) {
+        return VK_IMAGE_VIEW_TYPE_3D;
+    }
+    if (type == ImageType::Linear) {
+        return VK_IMAGE_VIEW_TYPE_2D;
+    }
+    return VK_IMAGE_VIEW_TYPE_2D_ARRAY;
+}
+
 [[nodiscard]] vk::ImageView MakeStorageView(const vk::Device& device, u32 level, VkImage image,
-                                            VkFormat format) {
+                                            VkFormat format, VkImageViewType view_type) {
     static constexpr VkImageViewUsageCreateInfo storage_image_view_usage_create_info{
         .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_USAGE_CREATE_INFO,
         .pNext = nullptr,
@@ -260,7 +319,7 @@ 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,
@@ -658,18 +717,11 @@ void CopyBufferToImage(vk::CommandBuffer cmdbuf, VkBuffer src_buffer, VkImage im
             .subresourceRange = subresource_range,
     };
 
-    cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
-                           VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT |
-                           VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, VK_PIPELINE_STAGE_TRANSFER_BIT, 0,
+    cmdbuf.PipelineBarrier(vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, VK_PIPELINE_STAGE_TRANSFER_BIT, 0,
                            read_barrier);
     cmdbuf.CopyBufferToImage(src_buffer, image, VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL, copies);
-    // TODO: Move this to another API
-    cmdbuf.PipelineBarrier(
-            VK_PIPELINE_STAGE_TRANSFER_BIT,
-            VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
-            VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT |
-            VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
-            0, nullptr, nullptr, write_barrier);
+    cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, 0,
+                           nullptr, nullptr, write_barrier);
 }
 
 [[nodiscard]] VkImageBlit MakeImageBlit(const Region2D& dst_region, const Region2D& src_region,
@@ -968,6 +1020,14 @@ TextureCacheRuntime::TextureCacheRuntime(const Device& device_, Scheduler& sched
         bl3d_unswizzle_pass.emplace(device, scheduler, descriptor_pool,
                                    staging_buffer_pool, compute_pass_descriptor_queue);
     }
+    if (SupportsAcceleratedUnswizzleDevice(device)) {
+        bl_unswizzle_2d_pass.emplace(device, scheduler, descriptor_pool,
+                                     compute_pass_descriptor_queue);
+        bl_unswizzle_image_3d_pass.emplace(device, scheduler, descriptor_pool,
+                                           compute_pass_descriptor_queue);
+        pitch_unswizzle_pass.emplace(device, scheduler, descriptor_pool,
+                                     compute_pass_descriptor_queue);
+    }
 }
 
 void TextureCacheRuntime::Finish() {
@@ -1902,16 +1962,12 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
     if (runtime->device.HasDebuggingToolAttached()) {
         original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str());
     }
+    if (False(flags & VideoCommon::ImageFlagBits::Converted) &&
+        SupportsAcceleratedUnswizzle(runtime->device, info)) {
+        flags |= VideoCommon::ImageFlagBits::AcceleratedUpload;
+    }
     current_image = &Image::original_image;
     storage_image_views.resize(info.resources.levels);
-    if (WillUseAcceleratedAstcDecode(runtime->device, info)) {
-        const auto& device = runtime->device.GetLogical();
-        const VkFormat storage_format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
-        for (s32 level = 0; level < info.resources.levels; ++level) {
-            storage_image_views[level] =
-                MakeStorageView(device, level, *original_image, storage_format);
-        }
-    }
 }
 
 Image::Image(const VideoCommon::NullImageParams& params) : VideoCommon::ImageBase{params} {}
@@ -2321,16 +2377,39 @@ void Image::DownloadMemory(const StagingBufferRef& map, std::span<const BufferIm
     DownloadMemory(buffers, offsets, copies);
 }
 
+std::vector<vk::ImageView>& Image::StorageViewsFor(vk::Image Image::*image) {
+    if (image == &Image::scaled_image) {
+        if (scaled_storage_image_views.empty()) {
+            scaled_storage_image_views.resize(info.resources.levels);
+        }
+        return scaled_storage_image_views;
+    }
+    return storage_image_views;
+}
+
 VkImageView Image::StorageImageView(s32 level) noexcept {
-    auto& view = storage_image_views[level];
+    const bool astc_decode = WillUseAcceleratedAstcDecode(runtime->device, info);
+    const bool unswizzle_upload =
+        !astc_decode && True(flags & ImageFlagBits::AcceleratedUpload);
+    vk::Image Image::*target = current_image;
+    if (astc_decode || unswizzle_upload) {
+        target = &Image::original_image;
+    }
+    auto& view = StorageViewsFor(target)[level];
     if (!view) {
         auto format_info =
             MaxwellToVK::SurfaceFormat(runtime->device, FormatType::Optimal, true, info.format);
-        if (WillUseAcceleratedAstcDecode(runtime->device, info)) {
+        if (astc_decode) {
             format_info.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
         }
-        view = MakeStorageView(runtime->device.GetLogical(), level, *(this->*current_image),
-                               format_info.format);
+        if (unswizzle_upload) {
+            const PixelFormat view_format =
+                UnswizzleViewFormat(VideoCore::Surface::BytesPerBlock(info.format));
+            format_info = MaxwellToVK::SurfaceFormat(runtime->device, FormatType::Optimal, false,
+                                                     view_format);
+        }
+        view = MakeStorageView(runtime->device.GetLogical(), level, *(this->*target),
+                               format_info.format, StorageViewType(info.type));
     }
     return *view;
 }
@@ -2361,6 +2440,7 @@ bool Image::ScaleUp(bool ignore) {
                                  runtime->ViewFormats(info.format));
         ignore = false;
     }
+    ignore = true;
     current_image = &Image::scaled_image;
     if (ignore) {
         return true;
@@ -2389,6 +2469,7 @@ bool Image::ScaleDown(bool ignore) {
     }
     ASSERT(info.type != ImageType::Linear);
     flags &= ~ImageFlagBits::Rescaled;
+    ignore = true;
     current_image = &Image::original_image;
     if (ignore) {
         return true;
@@ -3141,6 +3222,19 @@ void TextureCacheRuntime::AccelerateImageUpload(
         return astc_decoder_pass->Assemble(image, map, swizzles);
     }
 
+    if (bl_unswizzle_2d_pass && image.info.type == ImageType::e2D) {
+        return bl_unswizzle_2d_pass->Unswizzle(image, map, swizzles);
+    }
+
+    if (bl_unswizzle_image_3d_pass && image.info.type == ImageType::e3D &&
+        !IsPixelFormatBCn(image.info.format)) {
+        return bl_unswizzle_image_3d_pass->Unswizzle(image, map, swizzles);
+    }
+
+    if (pitch_unswizzle_pass && image.info.type == ImageType::Linear) {
+        return pitch_unswizzle_pass->Unswizzle(image, map, swizzles);
+    }
+
     if (!Settings::values.gpu_unswizzle_enabled.GetValue() || !bl3d_unswizzle_pass) {
         if (IsPixelFormatBCn(image.info.format) && image.info.type == ImageType::e3D) {
             ASSERT(false && "GPU unswizzle is disabled for BCn 3D texture");

src/video_core/renderer_vulkan/vk_texture_cache.h

@@ -159,6 +159,9 @@ public:
     std::optional<ASTCDecoderPass> astc_decoder_pass;
 
     std::optional<BlockLinearUnswizzle3DPass> bl3d_unswizzle_pass;
+    std::optional<BlockLinearUnswizzle2DPass> bl_unswizzle_2d_pass;
+    std::optional<BlockLinearUnswizzleImage3DPass> bl_unswizzle_image_3d_pass;
+    std::optional<PitchUnswizzlePass> pitch_unswizzle_pass;
     const Settings::ResolutionScalingInfo& resolution;
     std::array<std::vector<VkFormat>, VideoCore::Surface::MaxPixelFormat> view_formats;
 
@@ -370,6 +373,8 @@ private:
 
     bool NeedsScaleHelper() const;
 
+    std::vector<vk::ImageView>& StorageViewsFor(vk::Image Image::*image);
+
     Scheduler* scheduler{};
     TextureCacheRuntime* runtime{};
 
@@ -387,6 +392,7 @@ private:
     vk::Image Image::*current_image{};
 
     std::vector<vk::ImageView> storage_image_views;
+    std::vector<vk::ImageView> scaled_storage_image_views;
     VkImageAspectFlags aspect_mask = 0;
     bool initialized = false;
 

src/video_core/texture_cache/accelerated_swizzle.h

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -23,8 +26,8 @@ struct BlockLinearSwizzle2DParams {
 };
 
 struct BlockLinearSwizzle3DParams {
-    std::array<u32, 3> origin;
-    std::array<s32, 3> destination;
+    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;

src/video_core/texture_cache/texture_cache.h

@@ -279,11 +279,11 @@ void TextureCache<P>::CheckFeedbackLoop(std::span<const ImageViewInOut> views) {
 
             const ImageId view_image_id = slot_image_views[view.id].image_id;
             {
-                bool is_continue = false;
+                bool is_feedback = false;
                 for (size_t i = 0; i < 8; ++i)
-                    is_continue |= (rt_active_mask & (1u << i)) && view_image_id == rt_image_id[i];
-                if (is_continue)
-                    continue;
+                    is_feedback |= (rt_active_mask & (1u << i)) && view_image_id == rt_image_id[i];
+                if (is_feedback)
+                    return true;
             }
             if (depth_active && view_image_id == rt_depth_image_id) {
                 return true;

src/video_core/vulkan_common/vulkan_device.cpp

@@ -1386,11 +1386,6 @@ void Device::RemoveUnsuitableExtensions() {
                                VK_KHR_PIPELINE_EXECUTABLE_PROPERTIES_EXTENSION_NAME);
     }
 
-    // VK_KHR_shader_quad_control
-    extensions.shader_quad_control = features.shader_quad_control.shaderQuadControl;
-    RemoveExtensionFeatureIfUnsuitable(extensions.shader_quad_control, features.shader_quad_control,
-                                       VK_KHR_SHADER_QUAD_CONTROL_EXTENSION_NAME);
-
     // VK_KHR_workgroup_memory_explicit_layout
     extensions.workgroup_memory_explicit_layout =
         features.workgroup_memory_explicit_layout.workgroupMemoryExplicitLayout &&

src/video_core/vulkan_common/vulkan_device.h

@@ -75,7 +75,6 @@ VK_DEFINE_HANDLE(VmaAllocator)
     FEATURE(KHR, Maintenance6, MAINTENANCE_6, maintenance6)                                        \
     FEATURE(KHR, PipelineExecutableProperties, PIPELINE_EXECUTABLE_PROPERTIES,                     \
             pipeline_executable_properties)                                                        \
-    FEATURE(KHR, ShaderQuadControl, SHADER_QUAD_CONTROL, shader_quad_control)                      \
     FEATURE(KHR, WorkgroupMemoryExplicitLayout, WORKGROUP_MEMORY_EXPLICIT_LAYOUT,                  \
             workgroup_memory_explicit_layout)
 
@@ -355,6 +354,7 @@ public:
 
 #define FN_MAX_LIMIT_LIST \
     FN_MAX_LIMIT_ELEM(ComputeSharedMemorySize) \
+    FN_MAX_LIMIT_ELEM(ComputeWorkGroupInvocations) \
     FN_MAX_LIMIT_ELEM(PerStageDescriptorSampledImages) \
     FN_MAX_LIMIT_ELEM(PerStageResources) \
     FN_MAX_LIMIT_ELEM(DescriptorSetSamplers) \
@@ -587,11 +587,6 @@ FN_MAX_LIMIT_LIST
                features.features.shaderInt16;
     }
 
-    /// Returns true if the device supports VK_KHR_shader_quad_control.
-    bool IsKhrShaderQuadControlSupported() const {
-        return extensions.shader_quad_control && features.shader_quad_control.shaderQuadControl;
-    }
-
     /// Returns true if the device supports VK_KHR_image_format_list.
     bool IsKhrImageFormatListSupported() const {
         return extensions.image_format_list || instance_version >= VK_API_VERSION_1_2;