[dynarmic/backend/exception_handler] normalize EH for arches, use LOG_ERROR instead of fmt::print (#4283)

Signed-off-by: lizzie <lizzie@eden-emu.dev>

- [x] I have read and followed the [Contribution Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/CONTRIBUTING.md#code-contributions).
- [x] I have read and followed the [AI Policy](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/AI.md)
- [x] I have read and followed the [Coding Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/Coding.md) to the best of my ability.

-------------------

this should simplify a bit of code logic
akin to NetBSD's UC_CONTEXT_PC...
additionally use LOG_ERROR so the
"unhandled ..."
is logged unto a file
before sigsegv'ing

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4283
Reviewed-by: Maufeat <sahyno1996@gmail.com>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>

src/audio_core/sink/sdl3_sink.cpp

@@ -19,6 +19,23 @@
 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)
@@ -204,20 +221,14 @@ private:
 };
 
 SDLSink::SDLSink(std::string_view target_device_name) {
-    if (!SDL_WasInit(SDL_INIT_AUDIO)) {
+    if (InitializeAudio()) {
-        if (!SDL_InitSubSystem(SDL_INIT_AUDIO)) {
+        if (target_device_name != auto_device_name && !target_device_name.empty()) {
-            LOG_CRITICAL(Audio_Sink, "SDL_InitSubSystem audio failed: {}", SDL_GetError());
+            output_device = target_device_name;
-            return;
+        } else {
+            output_device.clear();
         }
+        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;
@@ -265,15 +276,10 @@ 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)
@@ -304,13 +310,8 @@ bool IsSDLSuitable() {
     return false;
 #else
     // Check SDL can init
-    if (!SDL_WasInit(SDL_INIT_AUDIO)) {
+    if (!InitializeAudio()!
-        if (SDL_InitSubSystem(SDL_INIT_AUDIO) < 0) {
+        return false;
-            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/logging.cpp

@@ -224,7 +224,7 @@ struct ColorConsoleBackend final : public Backend {
             auto const df = GetDirectFormatArgs(entry);
             // more restrictive, because take for example this simple prelude:
             // [  50.872256] Config <Info> common/settings.cpp:142:LogSettings:
-            char buffer[128];
+            char buffer[256];
             auto result = fmt::format_to_n(buffer, sizeof(buffer) - 1, "\x1b{}[{:4d}.{:06d}] {} <{}> {}:{}:{}: ", color_str, df.time_seconds, df.time_fractional, df.class_name, df.level_name, entry.filename, entry.line_num, entry.function, entry.message);
             std::fwrite(buffer, 1, (std::min)(sizeof(buffer) - 1, result.size), stdout);
             std::fwrite(entry.message, 1, entry.message_len, stdout);
@@ -425,14 +425,14 @@ void SetColorConsoleBackendEnabled(bool enabled) {
 
 void FmtLogMessageImpl(Class log_class, Level log_level, const char* filename, unsigned int line_num, const char* function, fmt::string_view format, const fmt::format_args& args) {
     if (logging_instance && logging_instance->filter.CheckMessage(log_class, log_level)) {
+        auto const flush = ::Settings::values.log_flush_line.GetValue();
         char buffer[BUFSIZ];
         auto result = fmt::vformat_to_n(buffer, sizeof(buffer) - 1, format, args);
-        buffer[result.size] = '\0';
+        buffer[(std::min)(result.size, sizeof(buffer) - 1)] = '\0';
-        auto const flush = ::Settings::values.log_flush_line.GetValue();
         logging_instance->ForEachBackend([=](Backend& backend) {
             backend.Write(Entry{
                 .message = buffer,
-                .message_len = (std::min)(sizeof(buffer) - 1, result.size),
+                .message_len = (std::min)(result.size, sizeof(buffer) - 1),
                 .timestamp = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - logging_instance->time_origin),
                 .log_class = log_class,
                 .log_level = log_level,

src/common/settings.cpp

@@ -132,11 +132,9 @@ void LogSettings() {
             }
         }
     }
-
+    LOG_INFO(Config, "Eden Configuration:");
-    std::string settings_str{};
     for (auto const& e : settings_list)
-        settings_str += e;
+        LOG_INFO(Config, "{}", e);
-    LOG_INFO(Config, "Eden Configuration:\n{}", settings_str);
 #define LOG_PATH(NAME) \
     LOG_INFO(Config, #NAME ": {}", Common::FS::PathToUTF8String(Common::FS::GetEdenPath(Common::FS::EdenPath::NAME)))
     LOG_PATH(CacheDir);

src/common/stb.cpp

@@ -7,6 +7,4 @@
 #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

@@ -7,6 +7,7 @@
 #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/hle/service/ns/read_only_application_control_data_interface.cpp

@@ -9,11 +9,7 @@
 #include <optional>
 #include <string>
 
-#define STBI_ONLY_JPEG 1
+#include "common/stb.h"
-#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/dynarmic/src/dynarmic/backend/exception_handler_posix.cpp

@@ -22,6 +22,7 @@
 #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"
@@ -53,23 +54,21 @@ 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::size_t signal_stack_size;
+    std::unique_ptr<uint8_t[]> signal_stack_memory;
+    bool supports_fast_mem = true;
 public:
     SigHandler() noexcept {
-        signal_stack_size = std::max<size_t>(SIGSTKSZ, 2 * 1024 * 1024);
+        auto const 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);
+        signal_stack_memory = std::make_unique<uint8_t[]>(stack_size);
 
         stack_t signal_stack{};
-        signal_stack.ss_sp = signal_stack_memory;
+        signal_stack.ss_sp = signal_stack_memory.get();
-        signal_stack.ss_size = signal_stack_size;
+        signal_stack.ss_size = stack_size;
         signal_stack.ss_flags = 0;
         if (sigaltstack(&signal_stack, nullptr) != 0) {
             fmt::print(stderr, "dynarmic: POSIX SigHandler: init failure at sigaltstack\n");
@@ -87,7 +86,7 @@ public:
             supports_fast_mem = false;
             return;
         }
-#ifdef __APPLE__
+#if defined(__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;
@@ -96,10 +95,6 @@ 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);
@@ -109,14 +104,17 @@ public:
         code_block_infos.erase(offset);
     }
 
-    bool SupportsFastmem() const noexcept { return supports_fast_mem; }
+    [[nodiscard]] inline bool SupportsFastmem() const noexcept {
+        return supports_fast_mem;
+    }
+
+    static void RegisterHandler();
+    static void SigAction(int sig, siginfo_t* info, void* raw_context);
 };
 
-std::mutex handler_lock;
 std::optional<SigHandler> sig_handler;
 
-void RegisterHandler() {
+void SigHandler::RegisterHandler() {
-    std::lock_guard<std::mutex> guard(handler_lock);
     if (!sig_handler) {
         sig_handler.emplace();
     }
@@ -125,51 +123,27 @@ void 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;
-            return;
-        }
-    }
-    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)
-    {
+            CTX_PC = fc.call_sepc;
-        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;
+#else
+            ASSERT(false);
+#endif
             return;
         }
     }
-    fmt::print(stderr, "Unhandled {} at pc {:#018x}\n", sig == SIGSEGV ? "SIGSEGV" : "SIGBUS", CTX_PC);
+    LOG_ERROR(Core, "Unhandled {} at {:#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) {
@@ -190,9 +164,10 @@ void SigHandler::SigAction(int sig, siginfo_t* info, void* raw_context) {
 
 struct ExceptionHandler::Impl final {
     Impl(u64 offset_, u64 size_)
-            : offset(offset_)
+        : offset(offset_)
-            , size(size_) {
+        , size(size_)
-        RegisterHandler();
+    {
+        SigHandler::RegisterHandler();
     }
 
     void SetCallback(std::function<FakeCall(u64)> cb) {

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

@@ -1,6 +1,7 @@
 // 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"
@@ -95,7 +96,8 @@ EmittedBlockInfo EmitLoongArch64(lagoon_assembler_t& as, IR::Block block, const
 
     // TODO: Emit Terminal
     const auto term = block.GetTerminal();
-    const IR::Term::LinkBlock* link_block_term = boost::get<IR::Term::LinkBlock>(&term);
+    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);
     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_SEPC (mctx.mc_gpregs.gp_sepc)
+#       define CTX_PC (mctx.mc_gpregs.gp_sepc)
 #       define CTX_SP (mctx.mc_gpregs.gp_sp)
 #   elif defined(__linux__)
-#       define CTX_SEPC (mctx.__gregs[REG_PC])
+#       define CTX_PC (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_SEPC (ucontext->sc_sepc)
+#        define CTX_PC (ucontext->sc_sepc)
 #        define CTX_SP (ucontext->sc_sp)
 #    else
 #        error "unknown platform"

src/shader_recompiler/backend/glasm/emit_glasm_instructions.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -665,6 +665,8 @@ 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

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -97,6 +100,24 @@ 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 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -743,6 +743,10 @@ 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

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -200,6 +203,18 @@ 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

@@ -322,6 +322,11 @@ 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);
@@ -443,6 +448,12 @@ 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 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -622,6 +622,8 @@ 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

@@ -260,6 +260,21 @@ 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 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -2100,6 +2100,14 @@ 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 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -394,6 +394,8 @@ 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[532] = {
+OpcodeMeta META_TABLE[534] = {
 #define OPCODE(name_token, type_token, ...)                                                        \
     {                                                                                              \
         .name{#name_token},                                                                        \
@@ -21,7 +21,7 @@ OpcodeMeta META_TABLE[532] = {
 #undef OPCODE
 };
 
-u8 NUM_ARGS[532] = {
+u8 NUM_ARGS[534] = {
 #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[532];
+extern OpcodeMeta META_TABLE[534];
 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[532];
+extern u8 NUM_ARGS[534];
 } // namespace Detail
 
 /// Get return type of an opcode

src/shader_recompiler/frontend/ir/opcodes.inc

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -579,6 +582,8 @@ 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 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -36,7 +36,10 @@ enum class ShuffleMode : u64 {
     }
 }
 
-void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32& mask) {
+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) {
     union {
         u64 insn;
         BitField<0, 8, IR::Reg> dest_reg;
@@ -45,6 +48,21 @@ 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);
@@ -59,11 +77,14 @@ void TranslatorVisitor::SHFL(u64 insn) {
         BitField<29, 1, u64> src_b_flag;
         BitField<34, 13, u64> src_b_imm;
     } const flags{insn};
-    const IR::U32 src_a{flags.src_a_flag != 0 ? ir.Imm32(static_cast<u32>(flags.src_a_imm))
+    const bool index_is_imm{flags.src_a_flag != 0};
-                                              : GetReg20(insn)};
+    const bool mask_is_imm{flags.src_b_flag != 0};
-    const IR::U32 src_b{flags.src_b_flag != 0 ? ir.Imm32(static_cast<u32>(flags.src_b_imm))
+    const IR::U32 src_a{index_is_imm ? ir.Imm32(static_cast<u32>(flags.src_a_imm))
-                                              : GetReg39(insn)};
+                                     : GetReg20(insn)};
-    Shuffle(*this, insn, src_a, src_b);
+    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));
 }
 
 } // namespace Shader::Maxwell

src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp

@@ -498,6 +498,10 @@ 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

@@ -37,6 +37,8 @@ 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

@@ -252,6 +252,7 @@ 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/renderer_vulkan/vk_pipeline_cache.cpp

@@ -404,6 +404,8 @@ 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/vulkan_common/vulkan_device.cpp

@@ -508,6 +508,9 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
         LOG_WARNING(Render_Vulkan, "Qualcomm drivers require scaled vertex format emulation.");
         has_broken_descriptor_aliasing = true;
         LOG_WARNING(Render_Vulkan, "Qualcomm drivers have broken descriptor aliasing.");
+        LOG_WARNING(Render_Vulkan, "Qualcomm drivers have broken color write enable.");
+        RemoveExtensionFeature(extensions.color_write_enable, features.color_write_enable,
+                               VK_EXT_COLOR_WRITE_ENABLE_EXTENSION_NAME);
         LOG_WARNING(Render_Vulkan, "Qualcomm drivers have broken shader atomic int64.");
         RemoveExtensionFeature(extensions.shader_atomic_int64, features.shader_atomic_int64,
                                VK_KHR_SHADER_ATOMIC_INT64_EXTENSION_NAME);
@@ -1383,6 +1386,11 @@ 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

@@ -75,6 +75,7 @@ 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)
 
@@ -586,6 +587,11 @@ 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;