2026-09-06 04:05:29

Signed-off-by: lizzie <lizzie@eden-emu.dev>
[cmake] Fix some macOS compilation errors (#4350 )
2026-09-06 12:13:57 +00:00 · 2026-09-06 04:05:29 +00:00 · 2026-09-05 23:43:46 +02:00 · 2026-09-04 13:32:36 +02:00 · 2026-09-02 14:04:35 +02:00 · 2026-09-02 04:07:24 +02:00
66 changed files with 755 additions and 1258 deletions
@@ -0,0 +1,112 @@
+diff --git a/include/vk_mem_alloc.h b/include/vk_mem_alloc.h
+index 8df0364..4856064 100644
+--- a/include/vk_mem_alloc.h
+++ b/include/vk_mem_alloc.h
+@@ -3017,7 +3017,7 @@ remove them if not needed.
+ 
+ #if defined(__ANDROID_API__) && (__ANDROID_API__ < 16)
+ #include <cstdlib>
+-static void* vma_aligned_alloc(size_t alignment, size_t size)
+static inline void* vma_aligned_alloc(size_t alignment, size_t size)
+ {
+     // alignment must be >= sizeof(void*)
+     if(alignment < sizeof(void*))
+@@ -3860,7 +3860,7 @@ Returned value is the found element, if present in the collection or place where
+ new element with value (key) should be inserted.
+ */
+ template <typename CmpLess, typename IterT, typename KeyT>
+-static IterT VmaBinaryFindFirstNotLess(IterT beg, IterT end, const KeyT& key, const CmpLess& cmp)
+static inline IterT VmaBinaryFindFirstNotLess(IterT beg, IterT end, const KeyT& key, const CmpLess& cmp)
+ {
+     size_t down = 0;
+     size_t up = size_t(end - beg);
+@@ -3898,7 +3898,7 @@ Warning! O(n^2) complexity. Use only inside VMA_HEAVY_ASSERT.
+ T must be pointer type, e.g. VmaAllocation, VmaPool.
+ */
+ template<typename T>
+-static bool VmaValidatePointerArray(uint32_t count, const T* arr)
+static inline bool VmaValidatePointerArray(uint32_t count, const T* arr)
+ {
+     for (uint32_t i = 0; i < count; ++i)
+     {
+@@ -4188,13 +4188,13 @@ static void VmaFree(const VkAllocationCallbacks* pAllocationCallbacks, void* ptr
+ }
+ 
+ template<typename T>
+-static T* VmaAllocate(const VkAllocationCallbacks* pAllocationCallbacks)
+static inline T* VmaAllocate(const VkAllocationCallbacks* pAllocationCallbacks)
+ {
+     return (T*)VmaMalloc(pAllocationCallbacks, sizeof(T), VMA_ALIGN_OF(T));
+ }
+ 
+ template<typename T>
+-static T* VmaAllocateArray(const VkAllocationCallbacks* pAllocationCallbacks, size_t count)
+static inline T* VmaAllocateArray(const VkAllocationCallbacks* pAllocationCallbacks, size_t count)
+ {
+     return (T*)VmaMalloc(pAllocationCallbacks, sizeof(T) * count, VMA_ALIGN_OF(T));
+ }
+@@ -4204,14 +4204,14 @@ static T* VmaAllocateArray(const VkAllocationCallbacks* pAllocationCallbacks, si
+ #define vma_new_array(allocator, type, count)   new(VmaAllocateArray<type>((allocator), (count)))(type)
+ 
+ template<typename T>
+-static void vma_delete(const VkAllocationCallbacks* pAllocationCallbacks, T* ptr)
+static inline void vma_delete(const VkAllocationCallbacks* pAllocationCallbacks, T* ptr)
+ {
+     ptr->~T();
+     VmaFree(pAllocationCallbacks, ptr);
+ }
+ 
+ template<typename T>
+-static void vma_delete_array(const VkAllocationCallbacks* pAllocationCallbacks, T* ptr, size_t count)
+static inline void vma_delete_array(const VkAllocationCallbacks* pAllocationCallbacks, T* ptr, size_t count)
+ {
+     if (ptr != VMA_NULL)
+     {
+@@ -4658,13 +4658,13 @@ void VmaVector<T, AllocatorT>::remove(size_t index)
+ #endif // _VMA_VECTOR_FUNCTIONS
+ 
+ template<typename T, typename allocatorT>
+-static void VmaVectorInsert(VmaVector<T, allocatorT>& vec, size_t index, const T& item)
+static inline void VmaVectorInsert(VmaVector<T, allocatorT>& vec, size_t index, const T& item)
+ {
+     vec.insert(index, item);
+ }
+ 
+ template<typename T, typename allocatorT>
+-static void VmaVectorRemove(VmaVector<T, allocatorT>& vec, size_t index)
+static inline void VmaVectorRemove(VmaVector<T, allocatorT>& vec, size_t index)
+ {
+     vec.remove(index);
+ }
+@@ -10620,19 +10620,19 @@ static void VmaFree(VmaAllocator hAllocator, void* ptr)
+ }
+ 
+ template<typename T>
+-static T* VmaAllocate(VmaAllocator hAllocator)
+static inline T* VmaAllocate(VmaAllocator hAllocator)
+ {
+     return (T*)VmaMalloc(hAllocator, sizeof(T), VMA_ALIGN_OF(T));
+ }
+ 
+ template<typename T>
+-static T* VmaAllocateArray(VmaAllocator hAllocator, size_t count)
+static inline T* VmaAllocateArray(VmaAllocator hAllocator, size_t count)
+ {
+     return (T*)VmaMalloc(hAllocator, sizeof(T) * count, VMA_ALIGN_OF(T));
+ }
+ 
+ template<typename T>
+-static void vma_delete(VmaAllocator hAllocator, T* ptr)
+static inline void vma_delete(VmaAllocator hAllocator, T* ptr)
+ {
+     if(ptr != VMA_NULL)
+     {
+@@ -10642,7 +10642,7 @@ static void vma_delete(VmaAllocator hAllocator, T* ptr)
+ }
+ 
+ template<typename T>
+-static void vma_delete_array(VmaAllocator hAllocator, T* ptr, size_t count)
+static inline void vma_delete_array(VmaAllocator hAllocator, T* ptr, size_t count)
+ {
+     if(ptr != VMA_NULL)
+     {
@@ -3,6 +3,7 @@

 cmake_minimum_required(VERSION 3.31)

+set(CMAKE_OSX_DEPLOYMENT_TARGET "15.0" CACHE STRING "macOS deployment target")
 project(yuzu)

 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMakeModules")
@@ -238,7 +239,7 @@ option(YUZU_USE_BUNDLED_SIRIT "Download bundled sirit" ${BUNDLED_SIRIT_DEFAULT})
 # FreeBSD 15+ has libusb, versions below should disable it
 cmake_dependent_option(ENABLE_LIBUSB "Enable the use of LibUSB" ON "WIN32 OR LINUX OR FREEBSD OR APPLE" OFF)

-cmake_dependent_option(ENABLE_OPENGL "Enable OpenGL" ON "NOT (WIN32 AND ARCHITECTURE_arm64) AND NOT APPLE" OFF)
+cmake_dependent_option(ENABLE_OPENGL "Enable OpenGL" ON "NOT (WIN32 AND ARCHITECTURE_arm64) AND NOT APPLE AND NOT ANDROID" OFF)
 mark_as_advanced(FORCE ENABLE_OPENGL)

 option(ENABLE_WEB_SERVICE "Enable web services (telemetry, etc.)" ON)
@@ -512,7 +513,7 @@ endfunction()
 # =============================================

 if (APPLE)
-    foreach(fw Carbon Metal Cocoa IOKit CoreVideo CoreMedia Security UniformTypeIdentifiers)
+    foreach(fw Carbon Metal Cocoa IOKit CoreVideo CoreMedia Security UniformTypeIdentifiers Foundation)
        find_library(${fw}_LIBRARY ${fw} REQUIRED)
        list(APPEND PLATFORM_LIBRARIES ${${fw}_LIBRARY})
    endforeach()
@@ -83,3 +83,16 @@ Once your request is processed, you will receive a confirmation email with your
 Alongside the other contribution methods listed up top, you can also choose to contribute through documentation, organization, or community guides. These can be done either through the code contribution methods described above, or created externally and shared via our Discord community.

 If you have an external tool/page that you believe would be handy to integrate/link into Eden, please additionally email our developers at [`developers@eden-emu.dev`](mailto:developers@eden-emu.dev). **Do not submit vibe-coded or AI generated tools or applications**.
+
+### Non-English Contributions
+
+If you can't speak English or find more comfortable speaking in your native tongue, you may submit PR, commits, comments, and reviews in other languages. There is no restriction what languages are allowed, but maintainers will use translators if they're unable to understand.
+
+Triage can speak:
+
+- Chinese
+- Portuguese
+- Russian
+- Spanish
+
+Documentation must be in American English, we don't have the capacity to support multilingual manuals. Code comments must remain in English for future referral.
@@ -1,12 +1,4 @@
 {
-    "": {
-        "ci": true,
-        "hash": "9f50d993c39529e022ad456163de91ac5934e16faf8fc348f305355fc0a643c534f87ded707e11bd03bcbc0a1760bd20852b6533a67ac0558a078385181cb184",
-        "name": "SDL3",
-        "package": "SDL3",
-        "repo": "crueter-ci/SDL3",
-        "version": "3.4.14-1788231389-147a8ee32d"
-    },
    "biscuit": {
        "hash": "1229f345b014f7ca544dedb4edb3311e41ba736f9aa9a67f88b5f26f3c983288c6bb6cdedcfb0b8a02c63088a37e6a0d7ba97d9c2a4d721b213916327cffe28a",
        "min_version": "0.9.1",
@@ -68,10 +60,10 @@
    },
    "discord-rpc": {
        "find_args": "MODULE",
-        "hash": "8213c43dcb0f7d479f5861091d111ed12fbdec1e62e6d729d65a4bc181d82f48a35d5fd3cd5c291f2393ac7c9681eabc6b76609755f55376284c8a8d67e148f3",
+        "hash": "8d680b3a16d6f6bf292ad823cf8635595ff986f2a49f758e3009f505b540a9d75194a8cf44cddea75736a8c3e3b5160166e716a0939ce3f18cc463cf648753fe",
        "package": "DiscordRPC",
        "repo": "eden-emulator/discord-rpc",
-        "version": "0d8b2d6a37"
+        "version": "76616d8675"
    },
    "enet": {
        "find_args": "MODULE",
@@ -311,6 +303,9 @@
        "find_args": "CONFIG",
        "hash": "deb5902ef8db0e329fbd5f3f4385eb0e26bdd9f14f3a2334823fb3fe18f36bc5d235d620d6e5f6fe3551ec3ea7038638899db8778c09f6d5c278f5ff95c3344b",
        "package": "VulkanMemoryAllocator",
+        "patches": [
+            "0001-macos-clang.patch"
+        ],
        "repo": "GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator",
        "version": "v3.3.0"
    },
@@ -76,7 +76,7 @@ The following options are desktop only.

 - `ENABLE_LIBUSB` (ON) Enable the use of the libusb input backend (HIGHLY RECOMMENDED)
 - `ENABLE_OPENGL` (ON) Enable the OpenGL graphics backend
-  - Unavailable on Windows/ARM64
+  - Unavailable on Windows/ARM64 and on Android
  - You probably shouldn't turn this off.

 ### Qt
@@ -11,6 +11,7 @@
 #include <limits>
 #include <span>
 #include <array>
+#include <algorithm>
 #include <time.h>

 namespace Tz {
@@ -5,6 +5,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later

 #include <string>
+#include <cstdlib>
 #include <string_view>
 #ifdef _WIN32
 #include <llvm/Demangle/Demangle.h>
@@ -1,9 +1,13 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

 #include <iterator>
+#include <cstring>

 #include "common/make_unique_for_overwrite.h"

@@ -61,7 +65,7 @@ public:
    void resize(size_type size) {
        if (size > buffer_capacity) {
            auto new_buffer = Common::make_unique_for_overwrite<T[]>(size);
-            std::move(buffer.get(), buffer.get() + buffer_capacity, new_buffer.get());
+            std::memcpy(new_buffer.get(), buffer.get(), buffer_capacity * sizeof(T));
            buffer = std::move(new_buffer);
            buffer_capacity = size;
        }
@@ -10,6 +10,7 @@
 #include <functional>
 #include <span>
 #include <string>
+#include <type_traits>

 #include "common/common_types.h"

@@ -6,13 +6,13 @@

 #include <mutex>
 #include <utility>
+#include <type_traits>
+
 #include <boost/asio.hpp>
 #include <boost/version.hpp>
-
 #if BOOST_VERSION > 108400 && (!defined(_WINDOWS) && !defined(__ANDROID__)) || defined(YUZU_BOOST_v1)
 #define USE_BOOST_v1
 #endif
-
 #ifdef USE_BOOST_v1
 #include <boost/process/v1/async_pipe.hpp>
 #else
@@ -358,7 +358,7 @@ private:

        ConnectionState(boost::asio::ip::tcp::socket&& client_socket_, async_pipe signal_pipe_, Kernel::KernelCore& kernel)
            : client_socket{std::move(client_socket_)}
-            , signal_pipe{signal_pipe_}
+            , signal_pipe{std::move(signal_pipe_)}
            , active_thread{kernel, nullptr}
        {}

@@ -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 2023 yuzu Emulator Project
@@ -6,6 +6,7 @@

 #pragma once

+#include <type_traits>
 #include "common/common_funcs.h"

 namespace FileSys {
@@ -7,6 +7,7 @@
 #pragma once

 #include <optional>
+#include <type_traits>

 #include "common/literals.h"
 #include "core/file_sys/fssystem/fs_i_storage.h"
@@ -4,6 +4,7 @@
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

+#include <type_traits>
 #include "core/file_sys/errors.h"
 #include "core/file_sys/fssystem/fssystem_bucket_tree.h"
 #include "core/file_sys/fssystem/fssystem_bucket_tree_utils.h"
@@ -1,9 +1,13 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

 #include <mutex>
+#include <type_traits>

 #include "common/alignment.h"
 #include "common/common_funcs.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 2023 yuzu Emulator Project
@@ -6,6 +6,7 @@

 #pragma once

+#include <type_traits>
 #include "core/file_sys/errors.h"
 #include "core/file_sys/fssystem/fssystem_bucket_tree.h"
 #include "core/file_sys/fssystem/fssystem_bucket_tree_utils.h"
@@ -6,6 +6,8 @@

 #pragma once

+#include <type_traits>
+#include <cstddef>
 #include "common/literals.h"

 #include "core/file_sys/errors.h"
@@ -1,8 +1,12 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

+#include <type_traits>
 #include "common/alignment.h"
 #include "core/file_sys/fssystem/fs_i_storage.h"
 #include "core/file_sys/fssystem/fs_types.h"
@@ -6,6 +6,9 @@

 #pragma once

+#include <type_traits>
+#include <array>
+#include <cstddef>
 #include "core/file_sys/errors.h"
 #include "core/file_sys/fssystem/fs_i_storage.h"
 #include "core/file_sys/fssystem/fssystem_bucket_tree.h"
@@ -1,9 +1,15 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

 #include <optional>
+#include <array>
+#include <cstddef>
+#include <type_traits>

 #include "core/file_sys/fssystem/fs_i_storage.h"
 #include "core/file_sys/fssystem/fs_types.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 2023 yuzu Emulator Project
@@ -6,6 +6,8 @@

 #pragma once

+#include <type_traits>
+#include <cstddef>
 #include "core/file_sys/fssystem/fssystem_compression_common.h"
 #include "core/file_sys/fssystem/fssystem_nca_header.h"
 #include "core/file_sys/vfs/vfs.h"
@@ -1,8 +1,14 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

+#include <type_traits>
+#include <array>
+#include <cstddef>
 #include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "common/literals.h"
@@ -7,6 +7,7 @@
 #pragma once

 #include <memory>
+#include <type_traits>

 #include "common/common_funcs.h"
 #include "common/page_table.h"
@@ -1021,6 +1021,9 @@ Result KProcess::Run(KernelCore& kernel, s32 priority, size_t stack_size) {

    // Suspend for debug, if we should.
    if (kernel.System().DebuggerEnabled()) {
+        LOG_INFO(Debug_GDBStub,
+                 "GDB stub enabled; suspending guest process until a debugger continues execution on port {}",
+                 Settings::values.gdbstub_port.GetValue());
        main_thread->RequestSuspend(kernel, SuspendType::Debug);
    }

@@ -6,6 +6,7 @@

 #pragma once

+#include <type_traits>
 #include "common/assert.h"
 #include "common/bit_field.h"
 #include "common/common_funcs.h"
@@ -1,9 +1,13 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2024 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later

 #pragma once

 #include <array>
+#include <type_traits>
 #include <functional>

 #include "common/common_funcs.h"
@@ -175,19 +175,10 @@ Result AlbumManager::LoadAlbumScreenShotImage(LoadAlbumScreenShotImageOutput& ou
        return ResultIsNotMounted;
    }

-    out_image_output = {
-        .width = 1280,
-        .height = 720,
-        .attribute =
-            {
-                .unknown_0{},
-                .orientation = AlbumImageOrientation::None,
-                .unknown_1{},
-                .unknown_2{},
-                .pad163{},
-            },
-        .pad179{},
-    };
+    out_image_output = {};
+    out_image_output.width = 1280;
+    out_image_output.height = 720;
+    out_image_output.attribute.orientation = AlbumImageOrientation::None;

    std::filesystem::path path;
    const auto result = GetFile(path, file_id);
@@ -211,19 +202,10 @@ Result AlbumManager::LoadAlbumScreenShotThumbnail(
        return ResultIsNotMounted;
    }

-    out_image_output = {
-        .width = 320,
-        .height = 180,
-        .attribute =
-            {
-                .unknown_0{},
-                .orientation = AlbumImageOrientation::None,
-                .unknown_1{},
-                .unknown_2{},
-                .pad163{},
-            },
-        .pad179{},
-    };
+    out_image_output = {};
+    out_image_output.width = 320;
+    out_image_output.height = 180;
+    out_image_output.attribute.orientation = AlbumImageOrientation::None;

    std::filesystem::path path;
    const auto result = GetFile(path, file_id);
@@ -73,13 +73,8 @@ void IScreenShotApplicationService::CaptureAndSaveScreenshot(AlbumReportOption r
    Layout::FramebufferLayout layout =
        Layout::DefaultFrameLayout(screenshot_width, screenshot_height);

-    const Capture::ScreenShotAttribute attribute{
-        .unknown_0{},
-        .orientation = Capture::AlbumImageOrientation::None,
-        .unknown_1{},
-        .unknown_2{},
-        .pad163{},
-    };
+    Capture::ScreenShotAttribute attribute{};
+    attribute.orientation = Capture::AlbumImageOrientation::None;

    renderer.RequestScreenshot(
        image_data.data(),
@@ -1,8 +1,12 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

+#include <type_traits>
 #include "common/common_funcs.h"
 #include "common/common_types.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 2022 yuzu Emulator Project
@@ -6,6 +6,7 @@

 #pragma once

+#include <type_traits>
 #include <fmt/ranges.h>

 #include "common/common_funcs.h"
@@ -8,6 +8,7 @@

 #include <array>
 #include <chrono>
+#include <type_traits>
 #include <fmt/ranges.h>

 #include "common/common_types.h"
@@ -1,10 +1,13 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

 #include <array>
-
+#include <type_traits>
 #include "common/common_types.h"
 #include "core/hle/service/psc/time/common.h"

@@ -7,6 +7,7 @@
 #pragma once

 #include <array>
+#include <type_traits>

 #include "common/bit_field.h"
 #include "common/common_funcs.h"
@@ -1,8 +1,15 @@
+// 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

 #pragma once

+#include <cstddef>
+#include <array>
+#include <type_traits>
+
 #include "common/bit_field.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
@@ -6,55 +6,6 @@

 add_library(shader_recompiler STATIC
    backend/bindings.h
-    backend/glasm/emit_glasm.cpp
-    backend/glasm/emit_glasm.h
-    backend/glasm/emit_glasm_barriers.cpp
-    backend/glasm/emit_glasm_bitwise_conversion.cpp
-    backend/glasm/emit_glasm_composite.cpp
-    backend/glasm/emit_glasm_context_get_set.cpp
-    backend/glasm/emit_glasm_control_flow.cpp
-    backend/glasm/emit_glasm_convert.cpp
-    backend/glasm/emit_glasm_floating_point.cpp
-    backend/glasm/emit_glasm_image.cpp
-    backend/glasm/emit_glasm_instructions.h
-    backend/glasm/emit_glasm_integer.cpp
-    backend/glasm/emit_glasm_logical.cpp
-    backend/glasm/emit_glasm_memory.cpp
-    backend/glasm/emit_glasm_not_implemented.cpp
-    backend/glasm/emit_glasm_select.cpp
-    backend/glasm/emit_glasm_shared_memory.cpp
-    backend/glasm/emit_glasm_special.cpp
-    backend/glasm/emit_glasm_undefined.cpp
-    backend/glasm/emit_glasm_warp.cpp
-    backend/glasm/glasm_emit_context.cpp
-    backend/glasm/glasm_emit_context.h
-    backend/glasm/reg_alloc.cpp
-    backend/glasm/reg_alloc.h
-    backend/glsl/emit_glsl.cpp
-    backend/glsl/emit_glsl.h
-    backend/glsl/emit_glsl_atomic.cpp
-    backend/glsl/emit_glsl_barriers.cpp
-    backend/glsl/emit_glsl_bitwise_conversion.cpp
-    backend/glsl/emit_glsl_composite.cpp
-    backend/glsl/emit_glsl_context_get_set.cpp
-    backend/glsl/emit_glsl_control_flow.cpp
-    backend/glsl/emit_glsl_convert.cpp
-    backend/glsl/emit_glsl_floating_point.cpp
-    backend/glsl/emit_glsl_image.cpp
-    backend/glsl/emit_glsl_instructions.h
-    backend/glsl/emit_glsl_integer.cpp
-    backend/glsl/emit_glsl_logical.cpp
-    backend/glsl/emit_glsl_memory.cpp
-    backend/glsl/emit_glsl_not_implemented.cpp
-    backend/glsl/emit_glsl_select.cpp
-    backend/glsl/emit_glsl_shared_memory.cpp
-    backend/glsl/emit_glsl_special.cpp
-    backend/glsl/emit_glsl_undefined.cpp
-    backend/glsl/emit_glsl_warp.cpp
-    backend/glsl/glsl_emit_context.cpp
-    backend/glsl/glsl_emit_context.h
-    backend/glsl/var_alloc.cpp
-    backend/glsl/var_alloc.h
    backend/spirv/emit_spirv.cpp
    backend/spirv/emit_spirv.h
    backend/spirv/emit_spirv_atomic.cpp
@@ -239,9 +190,60 @@ add_library(shader_recompiler STATIC
    program_header.h
    runtime_info.h
    shader_info.h
-    varying_state.h
+    varying_state.h)

-)
+if (ENABLE_OPENGL)
+    target_sources(shader_recompiler PRIVATE
+        backend/glasm/emit_glasm.cpp
+        backend/glasm/emit_glasm.h
+        backend/glasm/emit_glasm_barriers.cpp
+        backend/glasm/emit_glasm_bitwise_conversion.cpp
+        backend/glasm/emit_glasm_composite.cpp
+        backend/glasm/emit_glasm_context_get_set.cpp
+        backend/glasm/emit_glasm_control_flow.cpp
+        backend/glasm/emit_glasm_convert.cpp
+        backend/glasm/emit_glasm_floating_point.cpp
+        backend/glasm/emit_glasm_image.cpp
+        backend/glasm/emit_glasm_instructions.h
+        backend/glasm/emit_glasm_integer.cpp
+        backend/glasm/emit_glasm_logical.cpp
+        backend/glasm/emit_glasm_memory.cpp
+        backend/glasm/emit_glasm_not_implemented.cpp
+        backend/glasm/emit_glasm_select.cpp
+        backend/glasm/emit_glasm_shared_memory.cpp
+        backend/glasm/emit_glasm_special.cpp
+        backend/glasm/emit_glasm_undefined.cpp
+        backend/glasm/emit_glasm_warp.cpp
+        backend/glasm/glasm_emit_context.cpp
+        backend/glasm/glasm_emit_context.h
+        backend/glasm/reg_alloc.cpp
+        backend/glasm/reg_alloc.h
+        backend/glsl/emit_glsl.cpp
+        backend/glsl/emit_glsl.h
+        backend/glsl/emit_glsl_atomic.cpp
+        backend/glsl/emit_glsl_barriers.cpp
+        backend/glsl/emit_glsl_bitwise_conversion.cpp
+        backend/glsl/emit_glsl_composite.cpp
+        backend/glsl/emit_glsl_context_get_set.cpp
+        backend/glsl/emit_glsl_control_flow.cpp
+        backend/glsl/emit_glsl_convert.cpp
+        backend/glsl/emit_glsl_floating_point.cpp
+        backend/glsl/emit_glsl_image.cpp
+        backend/glsl/emit_glsl_instructions.h
+        backend/glsl/emit_glsl_integer.cpp
+        backend/glsl/emit_glsl_logical.cpp
+        backend/glsl/emit_glsl_memory.cpp
+        backend/glsl/emit_glsl_not_implemented.cpp
+        backend/glsl/emit_glsl_select.cpp
+        backend/glsl/emit_glsl_shared_memory.cpp
+        backend/glsl/emit_glsl_special.cpp
+        backend/glsl/emit_glsl_undefined.cpp
+        backend/glsl/emit_glsl_warp.cpp
+        backend/glsl/glsl_emit_context.cpp
+        backend/glsl/glsl_emit_context.h
+        backend/glsl/var_alloc.cpp
+        backend/glsl/var_alloc.h)
+endif()

 target_link_libraries(shader_recompiler PUBLIC common fmt::fmt sirit::sirit)

@@ -553,17 +553,6 @@ void GlobalMemoryToStorageBufferPass(IR::Program& program, const HostTranslateIn
    }
 }

-template <typename Descriptors, typename Descriptor, typename Func>
-static u32 Add(Descriptors& descriptors, const Descriptor& desc, Func&& pred) {
-    // TODO: Handle arrays
-    const auto it{std::ranges::find_if(descriptors, pred)};
-    if (it != descriptors.end()) {
-        return static_cast<u32>(std::distance(descriptors.begin(), it));
-    }
-    descriptors.push_back(desc);
-    return static_cast<u32>(descriptors.size()) - 1;
-}
-
 void JoinStorageInfo(Info& base, Info& source) {
    auto& descriptors = base.storage_buffers_descriptors;
    for (auto& desc : source.storage_buffers_descriptors) {
@@ -20,6 +20,8 @@ namespace VideoCommon {

 enum class BufferFlagBits {
    Picked = 1 << 0,
+    CachedWrites = 1 << 1,
+    PreemtiveDownload = 1 << 2,
 };
 DECLARE_ENUM_FLAG_OPERATORS(BufferFlagBits)

@@ -56,6 +58,15 @@ public:
        flags |= BufferFlagBits::Picked;
    }

+    void MarkPreemtiveDownload() noexcept {
+        flags |= BufferFlagBits::PreemtiveDownload;
+    }
+
+    /// Unmark buffer as picked
+    void Unpick() noexcept {
+        flags &= ~BufferFlagBits::Picked;
+    }
+
    /// Increases the likeliness of this being a stream buffer
    void IncreaseStreamScore(int score) noexcept {
        stream_score += score;
@@ -76,6 +87,15 @@ public:
        return True(flags & BufferFlagBits::Picked);
    }

+    /// Returns true when the buffer has pending cached writes
+    [[nodiscard]] bool HasCachedWrites() const noexcept {
+        return True(flags & BufferFlagBits::CachedWrites);
+    }
+
+    bool IsPreemtiveDownload() const noexcept {
+        return True(flags & BufferFlagBits::PreemtiveDownload);
+    }
+
    /// Returns the base CPU address of the buffer
    [[nodiscard]] VAddr CpuAddr() const noexcept {
        return cpu_addr;
@@ -7,7 +7,6 @@
 #pragma once

 #include <algorithm>
-#include <limits>
 #include <memory>
 #include <numeric>

@@ -122,6 +121,25 @@ void BufferCache<P>::WriteMemory(DAddr device_addr, u64 size) {
    memory_tracker.MarkRegionAsCpuModified(device_addr, size);
 }

+template <class P>
+void BufferCache<P>::CachedWriteMemory(DAddr device_addr, u64 size) {
+    const bool is_dirty = IsRegionRegistered(device_addr, size);
+    if (!is_dirty) {
+        return;
+    }
+    DAddr aligned_start = Common::AlignDown(device_addr, DEVICE_PAGESIZE);
+    DAddr aligned_end = Common::AlignUp(device_addr + size, DEVICE_PAGESIZE);
+    if (!IsRegionGpuModified(aligned_start, aligned_end - aligned_start)) {
+        WriteMemory(device_addr, size);
+        return;
+    }
+
+    tmp_buffer.resize_destructive(size);
+    device_memory.ReadBlockUnsafe(device_addr, tmp_buffer.data(), size);
+
+    InlineMemoryImplementation(device_addr, size, tmp_buffer);
+}
+
 template <class P>
 bool BufferCache<P>::OnCPUWrite(DAddr device_addr, u64 size) {
    const bool is_dirty = IsRegionRegistered(device_addr, size);
@@ -404,7 +422,7 @@ void BufferCache<P>::UnbindGraphicsStorageBuffers(size_t stage) {
 }

 template <class P>
-void BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index,
+bool BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index,
                                               u32 cbuf_offset, bool is_written) {
    const bool already_enabled =
        ((channel_state->enabled_storage_buffers[stage] >> ssbo_index) & 1U) != 0;
@@ -415,7 +433,7 @@ void BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index,
                LOG_WARNING(HW_GPU,
                            "Skipping graphics storage buffer {} due to driver limit {}",
                            ssbo_index, max_bindings);
-                return;
+                return false;
            }
        }
    }
@@ -431,6 +449,7 @@ void BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index,
    const GPUVAddr ssbo_addr = cbufs.const_buffers[cbuf_index].address + cbuf_offset;
    channel_state->storage_buffers[stage][ssbo_index] =
        StorageBufferBinding(ssbo_addr, cbuf_index, is_written);
+    return (channel_state->storage_buffers[stage][ssbo_index].buffer_id != NULL_BUFFER_ID);
 }

 template <class P>
@@ -743,6 +762,16 @@ void BufferCache<P>::BindHostIndexBuffer() {
    }
 }

+template <class P>
+void BufferCache<P>::BindHostVertexBuffer(u32 index, Buffer& buffer, u32 offset, u32 size,
+                                          u32 stride) {
+    if constexpr (IS_OPENGL) {
+        runtime.BindVertexBuffer(index, buffer, offset, size, stride);
+    } else {
+        runtime.BindVertexBuffer(index, buffer.Handle(), offset, size, stride);
+    }
+}
+
 template <class P>
 Binding& BufferCache<P>::VertexBufferSlot(u32 index) {
    ASSERT(index < NUM_VERTEX_BUFFERS);
@@ -1168,7 +1197,7 @@ void BufferCache<P>::DoUpdateGraphicsBuffers(bool is_indexed) {
        if (is_indexed) {
            UpdateIndexBuffer();
        }
-        UpdateVertexBuffers(is_indexed);
+        UpdateVertexBuffers();
        UpdateTransformFeedbackBuffers();
        for (size_t stage = 0; stage < NUM_STAGES; ++stage) {
            UpdateUniformBuffers(stage);
@@ -1222,14 +1251,9 @@ void BufferCache<P>::UpdateIndexBuffer() {
    const GPUVAddr gpu_addr_begin = index_buffer_ref.StartAddress();
    const GPUVAddr gpu_addr_end = index_buffer_ref.EndAddress();
    const std::optional<DAddr> device_addr = gpu_memory->GpuToCpuAddress(gpu_addr_begin);
-    u64 address_size = 0;
-    if (gpu_addr_end > gpu_addr_begin) {
-        address_size = (std::min)(gpu_addr_end - gpu_addr_begin,
-                                  u64{(std::numeric_limits<u32>::max)()});
-    }
-    const u64 draw_size = (u64{index_buffer_ref.count} + u64{index_buffer_ref.first}) *
-                          u64{index_buffer_ref.FormatSizeInBytes()};
-    const u32 size = static_cast<u32>((std::min)(address_size, draw_size));
+    const u32 address_size = static_cast<u32>(gpu_addr_end - gpu_addr_begin);
+    const u32 draw_size = (index_buffer_ref.count + index_buffer_ref.first) * u32(index_buffer_ref.FormatSizeInBytes());
+    const u32 size = (std::min)(address_size, draw_size);
    if (size == 0 || !device_addr) {
        channel_state->index_buffer = NULL_BINDING;
        return;
@@ -1242,142 +1266,20 @@ void BufferCache<P>::UpdateIndexBuffer() {
 }

 template <class P>
-u64 BufferCache<P>::DrawMaxIndex() {
-    if (max_index_scanned) {
-        return cached_max_index;
-    }
-    max_index_scanned = true;
-    cached_max_index = 0;
-    const auto& index_buffer_ref = maxwell3d->draw_manager.draw_state.index_buffer;
-    const u32 count = index_buffer_ref.count;
-    if (count == 0) {
-        return 0;
-    }
-    index_scan_buffer.resize_destructive(count);
-    gpu_memory->ReadBlockUnsafe(index_buffer_ref.IndexStart(), index_scan_buffer.data(),
-                                size_t{count} * sizeof(u32));
-    u32 restart_index = (std::numeric_limits<u32>::max)();
-    if (maxwell3d->regs.primitive_restart.enabled != 0) {
-        restart_index = maxwell3d->regs.primitive_restart.index;
-    }
-    u32 max_index = 0;
-    for (u32 i = 0; i < count; ++i) {
-        const u32 value = index_scan_buffer[i];
-        if (value == restart_index) {
-            continue;
-        }
-        max_index = (std::max)(max_index, value);
-    }
-    cached_max_index = max_index;
-    return cached_max_index;
-}
-
-template <class P>
-u64 BufferCache<P>::StreamAttributeExtent(u32 index) {
-    using VertexAttribute = typename Maxwell::VertexAttribute;
-    if (stream_extents_valid) {
-        return stream_extents[index];
-    }
-    stream_extents_valid = true;
-    stream_extents.fill(0);
-    for (size_t i = 0; i < Maxwell::NumVertexAttributes; ++i) {
-        const auto& attribute = maxwell3d->regs.vertex_attrib_format[i];
-        if (attribute.constant != 0 || attribute.size == VertexAttribute::Size::Invalid) {
-            continue;
-        }
-        const u32 buffer = attribute.buffer.Value();
-        if (buffer >= NUM_VERTEX_BUFFERS) {
-            continue;
-        }
-        const u64 end = static_cast<u64>(attribute.offset.Value()) +
-                        static_cast<u64>(attribute.SizeInBytes());
-        stream_extents[buffer] = (std::max)(stream_extents[buffer], end);
-    }
-    return stream_extents[index];
-}
-
-template <class P>
-u64 BufferCache<P>::DrawVertexBound(u32 index, bool is_indexed) {
-    const auto& array = maxwell3d->regs.vertex_streams[index];
-    if (array.enable == 0) {
-        return 0;
-    }
-    const u64 extent = StreamAttributeExtent(index);
-    if (extent == 0) {
-        return 0;
-    }
-    const u64 stride = static_cast<u64>(array.stride);
-    if (stride == 0) {
-        return extent;
-    }
-    const auto& draw_state = maxwell3d->draw_manager.draw_state;
-    u64 elements = 0;
-    if (maxwell3d->regs.vertex_stream_instances.IsInstancingEnabled(index)) {
-        if (draw_instance_count == 0) {
-            return 0;
-        }
-        const u64 base_instance = static_cast<u64>(draw_state.base_instance);
-        elements = base_instance + 1;
-        if (array.frequency != 0) {
-            elements = (base_instance + static_cast<u64>(draw_instance_count) - 1) /
-                           static_cast<u64>(array.frequency) +
-                       1;
-        }
-    } else if (!is_indexed) {
-        elements = static_cast<u64>(draw_state.vertex_buffer.first) +
-                   static_cast<u64>(draw_state.vertex_buffer.count);
-    } else {
-        const auto format = draw_state.index_buffer.format;
-        u64 max_index = 0xFF;
-        if (format == Maxwell::IndexFormat::UnsignedShort) {
-            max_index = 0xFFFF;
-        } else if (format != Maxwell::IndexFormat::UnsignedByte) {
-            const auto& limit = maxwell3d->regs.vertex_stream_limits[index];
-            const GPUVAddr gpu_addr_begin = array.Address();
-            const GPUVAddr gpu_addr_end = limit.Address() + 1;
-            if (gpu_addr_end <= gpu_addr_begin) {
-                return 0;
-            }
-            const bool walks = gpu_addr_end - gpu_addr_begin >= IMPLAUSIBLE_VERTEX_SIZE ||
-                               !gpu_memory->IsWithinGPUAddressRange(gpu_addr_end);
-            if (!walks) {
-                return 0;
-            }
-            max_index = DrawMaxIndex();
-        }
-        elements = static_cast<u64>(draw_state.base_index) + max_index + 1;
-    }
-    if (elements == 0) {
-        return extent;
-    }
-    return (elements - 1) * stride + extent;
-}
-
-template <class P>
-void BufferCache<P>::UpdateVertexBuffers(bool is_indexed) {
+void BufferCache<P>::UpdateVertexBuffers() {
    auto& flags = maxwell3d->dirty.flags;
-    max_index_scanned = false;
-    stream_extents_valid = false;
-    for (u32 index = 0; index < NUM_VERTEX_BUFFERS; ++index) {
-        const u64 bound = DrawVertexBound(index, is_indexed);
-        if (bound <= last_draw_bounds[index]) {
-            continue;
-        }
-        flags[Dirty::VertexBuffer0 + index] = true;
-        flags[Dirty::VertexBuffers] = true;
-    }
    if (!maxwell3d->dirty.flags[Dirty::VertexBuffers]) {
        return;
    }
    flags[Dirty::VertexBuffers] = false;

    for (u32 index = 0; index < NUM_VERTEX_BUFFERS; ++index) {
-        UpdateVertexBuffer(index, is_indexed);
+        UpdateVertexBuffer(index);
    }
 }

 template <class P>
-void BufferCache<P>::UpdateVertexBuffer(u32 index, bool is_indexed) {
+void BufferCache<P>::UpdateVertexBuffer(u32 index) {
    if (!maxwell3d->dirty.flags[Dirty::VertexBuffer0 + index]) {
        return;
    }
@@ -1386,31 +1288,15 @@ void BufferCache<P>::UpdateVertexBuffer(u32 index, bool is_indexed) {
    const GPUVAddr gpu_addr_begin = array.Address();
    const GPUVAddr gpu_addr_end = limit.Address() + 1;
    const std::optional<DAddr> device_addr = gpu_memory->GpuToCpuAddress(gpu_addr_begin);
-    if (array.enable == 0 || !device_addr || gpu_addr_end <= gpu_addr_begin) {
+    const u32 address_size = static_cast<u32>(gpu_addr_end - gpu_addr_begin);
+    u32 size = address_size; // TODO: Analyze stride and number of vertices
+    if (array.enable == 0 || size == 0 || !device_addr) {
        channel_state->vertex_buffers[index] = NULL_BINDING;
        UpdateVertexBufferSlot(index, NULL_BINDING);
        return;
    }
-    // TODO: Analyze stride and number of vertices
-    constexpr u64 implausible_size = IMPLAUSIBLE_VERTEX_SIZE;
-    u64 address_size = gpu_addr_end - gpu_addr_begin;
-    if (address_size > u64{(std::numeric_limits<u32>::max)()}) {
-        address_size = implausible_size;
-    }
-    const u64 draw_bound = DrawVertexBound(index, is_indexed);
-    last_draw_bounds[index] = (std::numeric_limits<u64>::max)();
-    if (draw_bound != 0) {
-        last_draw_bounds[index] = draw_bound;
-        address_size = (std::min)(address_size, draw_bound);
-    }
-    if (!gpu_memory->IsWithinGPUAddressRange(gpu_addr_end) || address_size >= implausible_size) {
-        address_size = gpu_memory->MaxContinuousRange(gpu_addr_begin, address_size);
-    }
-    const u32 size = static_cast<u32>(address_size);
-    if (size == 0) {
-        channel_state->vertex_buffers[index] = NULL_BINDING;
-        UpdateVertexBufferSlot(index, NULL_BINDING);
-        return;
+    if (!gpu_memory->IsWithinGPUAddressRange(gpu_addr_end) || size >= 64_MiB) {
+        size = static_cast<u32>(gpu_memory->MaxContinuousRange(gpu_addr_begin, size));
    }
    const BufferId buffer_id = FindBuffer(*device_addr, size);
    const Binding binding{
@@ -1692,10 +1578,9 @@ template <class P>
 BufferId BufferCache<P>::CreateBuffer(DAddr device_addr, u32 wanted_size) {
    DAddr device_addr_end = Common::AlignUp(device_addr + wanted_size, CACHING_PAGESIZE);
    device_addr = Common::AlignDown(device_addr, CACHING_PAGESIZE);
-    constexpr u64 max_buffer_size = u64{(std::numeric_limits<u32>::max)()};
-    wanted_size = static_cast<u32>((std::min)(device_addr_end - device_addr, max_buffer_size));
+    wanted_size = static_cast<u32>(device_addr_end - device_addr);
    const OverlapResult overlap = ResolveOverlaps(device_addr, wanted_size);
-    const u32 size = static_cast<u32>((std::min)(overlap.end - overlap.begin, max_buffer_size));
+    const u32 size = static_cast<u32>(overlap.end - overlap.begin);
    const BufferId new_buffer_id = slot_buffers.insert(runtime, overlap.begin, size);
    auto& new_buffer = slot_buffers[new_buffer_id];
    const size_t size_bytes = new_buffer.SizeBytes();
@@ -51,7 +51,6 @@ constexpr u32 NUM_VERTEX_BUFFERS = 16;
 #else
 constexpr u32 NUM_VERTEX_BUFFERS = 32;
 #endif
-constexpr u64 IMPLAUSIBLE_VERTEX_SIZE = 64_MiB;
 constexpr u32 NUM_TRANSFORM_FEEDBACK_BUFFERS = 4;
 constexpr u32 NUM_GRAPHICS_UNIFORM_BUFFERS = 18;
 constexpr u32 NUM_COMPUTE_UNIFORM_BUFFERS = 8;
@@ -218,6 +217,8 @@ public:

    void WriteMemory(DAddr device_addr, u64 size);

+    void CachedWriteMemory(DAddr device_addr, u64 size);
+
    bool OnCPUWrite(DAddr device_addr, u64 size);

    void DownloadMemory(DAddr device_addr, u64 size);
@@ -247,7 +248,7 @@ public:

    void UnbindGraphicsStorageBuffers(size_t stage);

-    void BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index, u32 cbuf_offset,
+    bool BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index, u32 cbuf_offset,
                                   bool is_written);

    void UnbindGraphicsTextureBuffers(size_t stage);
@@ -308,10 +309,6 @@ public:
        current_draw_indirect = current_draw_indirect_;
    }

-    void SetDrawInstanceCount(u32 draw_instance_count_) {
-        draw_instance_count = draw_instance_count_;
-    }
-
    [[nodiscard]] std::pair<Buffer*, u32> GetDrawIndirectCount();

    [[nodiscard]] std::pair<Buffer*, u32> GetDrawIndirectBuffer();
@@ -379,6 +376,8 @@ private:

    void BindHostTransformFeedbackBuffers();

+    void BindHostVertexBuffer(u32 index, Buffer& buffer, u32 offset, u32 size, u32 stride);
+
    void BindHostComputeUniformBuffers();

    void BindHostComputeStorageBuffers();
@@ -391,15 +390,9 @@ private:

    void UpdateIndexBuffer();

-    void UpdateVertexBuffers(bool is_indexed);
+    void UpdateVertexBuffers();

-    void UpdateVertexBuffer(u32 index, bool is_indexed);
-
-    [[nodiscard]] u64 DrawVertexBound(u32 index, bool is_indexed);
-
-    [[nodiscard]] u64 DrawMaxIndex();
-
-    [[nodiscard]] u64 StreamAttributeExtent(u32 index);
+    void UpdateVertexBuffer(u32 index);

    void UpdateDrawIndirect();

@@ -491,14 +484,6 @@ private:

    const Tegra::Engines::Maxwell3D::DrawManager::IndirectParams* current_draw_indirect{};

-    u32 draw_instance_count = 0;
-    std::array<u64, NUM_VERTEX_BUFFERS> last_draw_bounds{};
-    Common::ScratchBuffer<u32> index_scan_buffer;
-    u64 cached_max_index = 0;
-    bool max_index_scanned = false;
-    std::array<u64, NUM_VERTEX_BUFFERS> stream_extents{};
-    bool stream_extents_valid = false;
-
    u32 last_index_count = 0;

    u32 enabled_vertex_buffers_mask = 0;
@@ -8,6 +8,7 @@

 #include <array>
 #include <vector>
+#include <type_traits>

 #include "common/bit_field.h"
 #include "common/common_funcs.h"
@@ -1,8 +1,15 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later

 #pragma once

+#include <array>
+#include <cstddef>
+#include <type_traits>
+
 #include "common/bit_field.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
@@ -7,6 +7,7 @@
 #pragma once

 #include <memory>
+#include <type_traits>

 #include "common/common_types.h"
 #include "common/scratch_buffer.h"
@@ -206,40 +206,6 @@ 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})
@@ -5,13 +5,9 @@

 #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
-#endif
+#define HAS_EXTENDED_TYPES 1
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)
@@ -5,13 +5,9 @@

 #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
-#endif
+#define HAS_EXTENDED_TYPES 1
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)
@@ -5,13 +5,9 @@

 #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
-#endif
+#define HAS_EXTENDED_TYPES 1
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)
@@ -226,6 +226,22 @@ void BufferCacheRuntime::BindIndexBuffer(Buffer& buffer, u32 offset, u32 size) {
    }
 }

+void BufferCacheRuntime::BindVertexBuffer(u32 index, Buffer& buffer, u32 offset, u32 size,
+                                          u32 stride) {
+    if (index >= max_attributes) {
+        return;
+    }
+    if (has_unified_vertex_buffers) {
+        buffer.MakeResident(GL_READ_ONLY);
+        glBindVertexBuffer(index, 0, 0, static_cast<GLsizei>(stride));
+        glBufferAddressRangeNV(GL_VERTEX_ATTRIB_ARRAY_ADDRESS_NV, index,
+                               buffer.HostGpuAddr() + offset, static_cast<GLsizeiptr>(size));
+    } else {
+        glBindVertexBuffer(index, buffer.Handle(), static_cast<GLintptr>(offset),
+                           static_cast<GLsizei>(stride));
+    }
+}
+
 void BufferCacheRuntime::BindVertexBuffers(VideoCommon::HostBindings<Buffer>& bindings) {
    // TODO: Should HostBindings provide the correct runtime types to avoid these transforms?
    std::array<GLuint, 32> buffer_handles;
@@ -99,6 +99,8 @@ public:

    void BindIndexBuffer(Buffer& buffer, u32 offset, u32 size);

+    void BindVertexBuffer(u32 index, Buffer& buffer, u32 offset, u32 size, u32 stride);
+
    void BindVertexBuffers(VideoCommon::HostBindings<Buffer>& bindings);

    void BindUniformBuffer(size_t stage, u32 binding_index, Buffer& buffer, u32 offset, u32 size);
@@ -259,7 +259,6 @@ void RasterizerOpenGL::PrepareDraw(bool is_indexed, Func&& draw_func) {
 }

 void RasterizerOpenGL::Draw(bool is_indexed, u32 instance_count) {
-    buffer_cache.SetDrawInstanceCount(instance_count);
    PrepareDraw(is_indexed, [this, is_indexed, instance_count](GLenum primitive_mode) {
        const auto& draw_state = maxwell3d->draw_manager.draw_state;
        const GLuint base_instance = GLuint(draw_state.base_instance);
@@ -305,7 +304,6 @@ void RasterizerOpenGL::Draw(bool is_indexed, u32 instance_count) {
 void RasterizerOpenGL::DrawIndirect() {
    const auto& params = maxwell3d->draw_manager.indirect_state;
    buffer_cache.SetDrawIndirect(&params);
-    buffer_cache.SetDrawInstanceCount(0);
    PrepareDraw(params.is_indexed, [this, &params](GLenum primitive_mode) {
        if (params.is_byte_count) {
            const GPUVAddr tfb_object_base_addr = params.indirect_start_address - 4U;
@@ -585,6 +585,29 @@ void BufferCacheRuntime::BindQuadIndexBuffer(PrimitiveTopology topology, u32 fir
    }
 }

+void BufferCacheRuntime::BindVertexBuffer(u32 index, VkBuffer buffer, u32 offset, u32 size, u32 stride) {
+    if (index >= device.GetMaxVertexInputBindings()) {
+        return;
+    }
+    if (device.IsExtExtendedDynamicStateSupported()) {
+        scheduler.Record([index, buffer, offset, size, stride](vk::CommandBuffer cmdbuf) {
+            const VkDeviceSize vk_offset = buffer != VK_NULL_HANDLE ? offset : 0;
+            const VkDeviceSize vk_size = buffer != VK_NULL_HANDLE ? size : VK_WHOLE_SIZE;
+            const VkDeviceSize vk_stride = stride;
+            cmdbuf.BindVertexBuffers2EXT(index, 1, &buffer, &vk_offset, &vk_size, &vk_stride);
+        });
+    } else {
+        if (!device.HasNullDescriptor() && buffer == VK_NULL_HANDLE) {
+            ReserveNullBuffer();
+            buffer = *null_buffer;
+            offset = 0;
+        }
+        scheduler.Record([index, buffer, offset](vk::CommandBuffer cmdbuf) {
+            cmdbuf.BindVertexBuffer(index, buffer, offset);
+        });
+    }
+}
+
 void BufferCacheRuntime::BindVertexBuffers(VideoCommon::HostBindings<Buffer>& bindings) {
    boost::container::static_vector<VkBuffer, VideoCommon::NUM_VERTEX_BUFFERS> buffer_handles(bindings.buffers.size());
    for (u32 i = 0; i < bindings.buffers.size(); ++i) {
@@ -138,6 +138,8 @@ public:

    void BindQuadIndexBuffer(PrimitiveTopology topology, u32 first, u32 count);

+    void BindVertexBuffer(u32 index, VkBuffer buffer, u32 offset, u32 size, u32 stride);
+
    void BindVertexBuffers(VideoCommon::HostBindings<Buffer>& bindings);

    void BindTransformFeedbackBuffer(u32 index, VkBuffer buffer, u32 offset, u32 size);
@@ -22,13 +22,7 @@
 #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"
@@ -878,291 +872,4 @@ 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
@@ -164,49 +164,4 @@ 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
@@ -694,11 +694,9 @@ void GraphicsPipeline::MakePipeline(VkRenderPass render_pass) {
        const size_t num_vertex_arrays = (std::min)(
            Maxwell::NumVertexArrays, static_cast<size_t>(device.GetMaxVertexInputBindings()));
        for (size_t index = 0; index < num_vertex_arrays; ++index) {
-            const bool instanced = ((key.state.enabled_divisors >> index) & 1) != 0;
-            auto rate = VK_VERTEX_INPUT_RATE_VERTEX;
-            if (instanced) {
-                rate = VK_VERTEX_INPUT_RATE_INSTANCE;
-            }
+            const bool instanced = key.state.binding_divisors[index] != 0;
+            const auto rate =
+                instanced ? VK_VERTEX_INPUT_RATE_INSTANCE : VK_VERTEX_INPUT_RATE_VERTEX;
            vertex_bindings.push_back({
                .binding = static_cast<u32>(index),
                .stride = key.state.vertex_strides[index],
@@ -707,7 +705,7 @@ void GraphicsPipeline::MakePipeline(VkRenderPass render_pass) {
            if (instanced) {
                vertex_binding_divisors.push_back({
                    .binding = static_cast<u32>(index),
-                    .divisor = device.GetVertexAttribDivisor(key.state.binding_divisors[index]),
+                    .divisor = key.state.binding_divisors[index],
                });
            }
        }
@@ -338,7 +338,7 @@ void PresentManager::PresentThread(std::stop_token token) {
            // By exchanging the lock ownership we take the swapchain lock
            // before the queue lock goes out of scope. This way the swapchain
            // lock in WaitPresent is guaranteed to occur after here.
-            std::exchange(lock, std::unique_lock{swapchain_mutex});
+            void(std::exchange(lock, std::unique_lock{swapchain_mutex}));
            CopyToSwapchain(frame);

            // Free the frame for reuse
@@ -137,12 +137,10 @@ VkRect2D GetScissorState(const Maxwell& regs, size_t index, u32 up_scale = 1, u3
    max_y = (std::max)(max_y, 0);

    if (src.enable) {
-        const s32 min_x = static_cast<s32>(src.min_x.Value());
-        const s32 max_x = static_cast<s32>(src.max_x.Value());
-        scissor.offset.x = scale_up(min_x);
+        scissor.offset.x = scale_up(src.min_x);
        scissor.offset.y = scale_up(min_y);
-        scissor.extent.width = scale_up((std::max)(max_x - min_x, 0));
-        scissor.extent.height = scale_up((std::max)(max_y - min_y, 0));
+        scissor.extent.width = scale_up(src.max_x - src.min_x);
+        scissor.extent.height = scale_up(max_y - min_y);
    } else {
        scissor.offset.x = 0;
        scissor.offset.y = 0;
@@ -262,7 +260,6 @@ void RasterizerVulkan::PrepareDraw(bool is_indexed, Func&& draw_func) {
 }

 void RasterizerVulkan::Draw(bool is_indexed, u32 instance_count) {
-    buffer_cache.SetDrawInstanceCount(instance_count);
    PrepareDraw(is_indexed, [this, is_indexed, instance_count] {
        const auto& draw_state = maxwell3d->draw_manager.draw_state;
        const u32 num_instances{instance_count};
@@ -298,7 +295,6 @@ void RasterizerVulkan::Draw(bool is_indexed, u32 instance_count) {
 void RasterizerVulkan::DrawIndirect() {
    const auto& params = maxwell3d->draw_manager.indirect_state;
    buffer_cache.SetDrawIndirect(&params);
-    buffer_cache.SetDrawInstanceCount(0);
    PrepareDraw(params.is_indexed, [this, &params] {
        const auto indirect_buffer = buffer_cache.GetDrawIndirectBuffer();
        const auto& buffer = indirect_buffer.first;
@@ -1921,19 +1917,13 @@ void RasterizerVulkan::UpdateVertexInput(Tegra::Engines::Maxwell3D::Regs& regs)
    for (u32 binding = 0; binding < max_bindings; ++binding) {
        const auto& input_binding{regs.vertex_streams[binding]};
        const bool is_instanced{regs.vertex_stream_instances.IsInstancingEnabled(binding)};
-        auto input_rate = VK_VERTEX_INPUT_RATE_VERTEX;
-        u32 divisor = 1;
-        if (is_instanced) {
-            input_rate = VK_VERTEX_INPUT_RATE_INSTANCE;
-            divisor = device.GetVertexAttribDivisor(input_binding.frequency);
-        }
        bindings.push_back({
            .sType = VK_STRUCTURE_TYPE_VERTEX_INPUT_BINDING_DESCRIPTION_2_EXT,
            .pNext = nullptr,
            .binding = binding,
            .stride = input_binding.stride,
-            .inputRate = input_rate,
-            .divisor = divisor,
+            .inputRate = is_instanced ? VK_VERTEX_INPUT_RATE_INSTANCE : VK_VERTEX_INPUT_RATE_VERTEX,
+            .divisor = is_instanced ? input_binding.frequency : 1,
        });
    }

@@ -300,7 +300,7 @@ void Scheduler::WorkerThread(std::stop_token stop_token) {
            // Exchange lock ownership so that we take the execution lock before
            // the queue lock goes out of scope. This allows us to force execution
            // to complete in the next step.
-            std::exchange(lk, std::unique_lock{execution_mutex});
+            void(std::exchange(lk, std::unique_lock{execution_mutex}));

            // Perform the work, tracking whether the chunk was a submission
            // before executing.
@@ -449,9 +449,7 @@ 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_TRANSFER_READ_BIT
-                                         | VK_ACCESS_TRANSFER_WRITE_BIT,
+                                         | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
                        .oldLayout = VK_IMAGE_LAYOUT_GENERAL,
                        .newLayout = VK_IMAGE_LAYOUT_GENERAL,
                        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
@@ -462,7 +460,7 @@ 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_TRANSFER,
+                                   VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE,
                                   0, nullptr, nullptr, vk::Span(barriers.data(), num_images));
            if (has_transform_feedback) {
                static constexpr VkMemoryBarrier XFB_OUTPUT_BARRIER{
@@ -160,55 +160,6 @@ 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 =
@@ -297,18 +248,8 @@ constexpr u32 UNSWIZZLE_WORKGROUP_INVOCATIONS = 32 * 32;
    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, VkImageViewType view_type) {
+                                            VkFormat format) {
    static constexpr VkImageViewUsageCreateInfo storage_image_view_usage_create_info{
        .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_USAGE_CREATE_INFO,
        .pNext = nullptr,
@@ -319,7 +260,7 @@ constexpr u32 UNSWIZZLE_WORKGROUP_INVOCATIONS = 32 * 32;
        .pNext = &storage_image_view_usage_create_info,
        .flags = 0,
        .image = image,
-        .viewType = view_type,
+        .viewType = VK_IMAGE_VIEW_TYPE_2D_ARRAY,
        .format = format,
        .components{
            .r = VK_COMPONENT_SWIZZLE_IDENTITY,
@@ -717,11 +658,18 @@ void CopyBufferToImage(vk::CommandBuffer cmdbuf, VkBuffer src_buffer, VkImage im
            .subresourceRange = subresource_range,
    };

-    cmdbuf.PipelineBarrier(vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, VK_PIPELINE_STAGE_TRANSFER_BIT, 0,
+    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,
                           read_barrier);
    cmdbuf.CopyBufferToImage(src_buffer, image, VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL, copies);
-    cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, 0,
-                           nullptr, nullptr, write_barrier);
+    // 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);
 }

 [[nodiscard]] VkImageBlit MakeImageBlit(const Region2D& dst_region, const Region2D& src_region,
@@ -1020,14 +968,6 @@ 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() {
@@ -1962,12 +1902,16 @@ 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} {}
@@ -2091,7 +2035,7 @@ void Image::UploadMemory(VkBuffer buffer, VkDeviceSize offset,
                                                temp_vk_image, info.format, info.num_samples,
                                                {image_copies.data(), image_copies.size()}, false);
        }
-        InitializationFor(current_image) = true;
+        initialized = true;
        runtime->ReleaseMsaaScratchImage(temp_vk_image);

        if (is_rescaled) {
@@ -2112,7 +2056,7 @@ void Image::UploadMemory(VkBuffer buffer, VkDeviceSize offset,
    const VkBuffer src_buffer = buffer;
    const VkImage vk_image = *original_image;
    const VkImageAspectFlags vk_aspect_mask = aspect_mask;
-    const bool was_initialized = std::exchange(InitializationFor(&Image::original_image), true);
+    const bool was_initialized = std::exchange(initialized, true);

    scheduler->Record([src_buffer, vk_image, vk_aspect_mask, was_initialized,
                       vk_copies](vk::CommandBuffer cmdbuf) {
@@ -2377,46 +2321,16 @@ 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;
-}
-
-bool& Image::InitializationFor(vk::Image Image::*image) noexcept {
-    if (image == &Image::scaled_image) {
-        return scaled_initialized;
-    }
-    return original_initialized;
-}
-
 VkImageView Image::StorageImageView(s32 level) noexcept {
-    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];
+    auto& view = storage_image_views[level];
    if (!view) {
        auto format_info =
            MaxwellToVK::SurfaceFormat(runtime->device, FormatType::Optimal, true, info.format);
-        if (astc_decode) {
+        if (WillUseAcceleratedAstcDecode(runtime->device, info)) {
            format_info.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
        }
-        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));
+        view = MakeStorageView(runtime->device.GetLogical(), level, *(this->*current_image),
+                               format_info.format);
    }
    return *view;
 }
@@ -2456,7 +2370,6 @@ bool Image::ScaleUp(bool ignore) {
    }
    if (NeedsScaleHelper()) {
        if (!BlitScaleHelper(true)) {
-            flags &= ~ImageFlagBits::Rescaled;
            current_image = &Image::original_image;
            return false;
        }
@@ -2646,10 +2559,6 @@ ImageView::ImageView(TextureCacheRuntime& runtime, const VideoCommon::ImageViewI
    if (device->IsExtAstcDecodeModeSupported() && IsLdrAstcFormat(format_info.format)) {
        view_next = &astc_decode_mode;
    }
-    auto subresource_range = MakeSubresourceRange(aspect_mask, info.range);
-    if (True(flags & VideoCommon::ImageViewFlagBits::Slice)) {
-        subresource_range.levelCount = 1;
-    }
    const VkImageViewCreateInfo create_info{
        .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
        .pNext = view_next,
@@ -2658,7 +2567,7 @@ ImageView::ImageView(TextureCacheRuntime& runtime, const VideoCommon::ImageViewI
        .viewType = VkImageViewType{},
        .format = format_info.format,
        .components = swizzle_mapping,
-        .subresourceRange = subresource_range,
+        .subresourceRange = MakeSubresourceRange(aspect_mask, info.range),
    };
    const auto create = [&](TextureType tex_type, std::optional<u32> num_layers) {
        VkImageViewCreateInfo ci{create_info};
@@ -3232,19 +3141,6 @@ 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");
@@ -159,9 +159,6 @@ 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;

@@ -353,7 +350,7 @@ public:

    /// Returns true when the image is already initialized and mark it as initialized
    [[nodiscard]] bool ExchangeInitialization() noexcept {
-        return std::exchange(InitializationFor(current_image), true);
+        return std::exchange(initialized, true);
    }

    VkImageView StorageImageView(s32 level) noexcept;
@@ -373,10 +370,6 @@ private:

    bool NeedsScaleHelper() const;

-    std::vector<vk::ImageView>& StorageViewsFor(vk::Image Image::*image);
-
-    bool& InitializationFor(vk::Image Image::*image) noexcept;
-
    Scheduler* scheduler{};
    TextureCacheRuntime* runtime{};

@@ -394,10 +387,8 @@ 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 original_initialized = false;
-    bool scaled_initialized = false;
+    bool initialized = false;

    std::optional<Framebuffer> scale_framebuffer;
    std::optional<Framebuffer> normal_framebuffer;
@@ -1,6 +1,3 @@
-// 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

@@ -26,8 +23,8 @@ struct BlockLinearSwizzle2DParams {
 };

 struct BlockLinearSwizzle3DParams {
-    alignas(16) std::array<u32, 3> origin;
-    alignas(16) std::array<s32, 3> destination;
+    std::array<u32, 3> origin;
+    std::array<s32, 3> destination;
    u32 bytes_per_block_log2;
    u32 slice_size;
    u32 block_size;
@@ -20,7 +20,6 @@
 #include "video_core/engines/kepler_compute.h"
 #include "video_core/guest_memory.h"
 #include "video_core/host1x/gpu_device_memory_manager.h"
-#include "video_core/texture_cache/accelerated_swizzle.h"
 #include "video_core/texture_cache/image_view_base.h"
 #include "video_core/texture_cache/samples_helper.h"
 #include "video_core/texture_cache/texture_cache_base.h"
@@ -280,11 +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_feedback = false;
+                bool is_continue = false;
                for (size_t i = 0; i < 8; ++i)
-                    is_feedback |= (rt_active_mask & (1u << i)) && view_image_id == rt_image_id[i];
-                if (is_feedback)
-                    return true;
+                    is_continue |= (rt_active_mask & (1u << i)) && view_image_id == rt_image_id[i];
+                if (is_continue)
+                    continue;
            }
            if (depth_active && view_image_id == rt_depth_image_id) {
                return true;
@@ -627,25 +626,14 @@ void TextureCache<P>::DownloadMemory(DAddr cpu_addr, size_t size) {
    std::ranges::sort(images, [this](ImageId lhs, ImageId rhs) {
        return slot_images[lhs].modification_tick < slot_images[rhs].modification_tick;
    });
-    size_t total_size_bytes = 0;
-    for (const ImageId image_id : images) {
-        total_size_bytes += slot_images[image_id].unswizzled_size_bytes;
-    }
-    auto download_map = runtime.DownloadStagingBuffer(total_size_bytes);
    for (const ImageId image_id : images) {
        Image& image = slot_images[image_id];
+        auto map = runtime.DownloadStagingBuffer(image.unswizzled_size_bytes);
        const auto copies = FixSmallVectorADL(FullDownloadCopies(image.info));
-        image.DownloadMemory(download_map, copies);
-        download_map.offset += image.unswizzled_size_bytes;
-    }
-    runtime.Finish();
-    std::span<u8> download_span = download_map.mapped_span;
-    for (const ImageId image_id : images) {
-        const ImageBase& image = slot_images[image_id];
-        const auto copies = FixSmallVectorADL(FullDownloadCopies(image.info));
-        SwizzleImage(*gpu_memory, image.gpu_addr, image.info, copies, download_span,
+        image.DownloadMemory(map, copies);
+        runtime.Finish();
+        SwizzleImage(*gpu_memory, image.gpu_addr, image.info, copies, map.mapped_span,
                     swizzle_data_buffer);
-        download_span = download_span.subspan(image.unswizzled_size_bytes);
    }
 }

@@ -1134,12 +1122,6 @@ void TextureCache<P>::RefreshContents(Image& image, ImageId image_id) {

    TrackImage(image, image_id);

-    if (image.info.rescaleable &&
-        IsRegionGpuModified(image.cpu_addr, image.guest_size_bytes)) {
-        runtime.TransitionImageLayout(image);
-        return;
-    }
-
    if (image.info.num_samples > 1 && !runtime.CanUploadMSAA()) {
        LOG_WARNING(HW_GPU, "MSAA image uploads are not implemented");
        runtime.TransitionImageLayout(image);
@@ -1175,7 +1157,8 @@ void TextureCache<P>::UploadImageContents(Image& image, StagingBuffer& staging)
    const GPUVAddr gpu_addr = image.gpu_addr;

    if (True(image.flags & ImageFlagBits::AcceleratedUpload)) {
-        gpu_memory->ReadBlockUnsafe(gpu_addr, mapped_span.data(), image.guest_size_bytes);
+        gpu_memory->ReadBlock(gpu_addr, mapped_span.data(), mapped_span.size_bytes(),
+                              VideoCommon::CacheType::NoTextureCache);
        const auto uploads = FullUploadSwizzles(image.info);
        runtime.AccelerateImageUpload(image, staging, FixSmallVectorADL(uploads), 0, 0);
        return;
@@ -1282,9 +1265,6 @@ ImageId TextureCache<P>::FindImage(const ImageInfo& info, GPUVAddr gpu_addr,

 template <class P>
 bool TextureCache<P>::ImageCanRescale(ImageBase& image) {
-    if (!Settings::values.resolution_info.active) {
-        return false;
-    }
    if (!image.info.rescaleable) {
        return false;
    }
@@ -1372,12 +1352,12 @@ void TextureCache<P>::QueueAsyncDecode(Image& image, ImageId image_id) {
    decode->image_id = image_id;
    async_decodes.push_back(std::move(decode));

-    Common::ScratchBuffer<u8> local_unswizzle_data_buffer(image.unswizzled_size_bytes);
+    std::vector<u8> local_unswizzle_data_buffer(image.unswizzled_size_bytes, 0);
    Tegra::Memory::GpuGuestMemory<u8, Tegra::Memory::GuestMemoryFlags::UnsafeRead> swizzle_data(*gpu_memory, image.gpu_addr, image.guest_size_bytes, &swizzle_data_buffer);
    auto copies = UnswizzleImage(*gpu_memory, image.gpu_addr, image.info, swizzle_data, local_unswizzle_data_buffer);
    const size_t out_size = MapSizeBytes(image);

-    auto func = [out_size, copies = std::move(copies), info = image.info,
+    auto func = [out_size, copies, info = image.info,
                 input = std::move(local_unswizzle_data_buffer),
                 async_decode = decode_ptr]() mutable {
        async_decode->decoded_data.resize_destructive(out_size);
@@ -1446,16 +1426,18 @@ void TextureCache<P>::TickAsyncUnswizzle() {
    Image& image = slot_images[task.image_id];

    if (!task.initialized) {
-        task.total_size = image.guest_size_bytes;
+        task.total_size = MapSizeBytes(image);
        task.staging_buffer = runtime.UploadStagingBuffer(task.total_size, true);

-        const auto layout = FullUploadSwizzles(task.info);
-        const auto params =
-            VideoCommon::Accelerated::MakeBlockLinearSwizzle3DParams(layout.front(), task.info);
-        task.bytes_per_slice = params.slice_size;
-        task.chunked = task.info.block.depth == 0;
+        const auto& info = image.info;
+        const u32 bytes_per_block = BytesPerBlock(info.format);
+        const u32 width_blocks = Common::DivCeil(info.size.width, 4u);
+        const u32 height_blocks = Common::DivCeil(info.size.height, 4u);
+
+        const u32 stride = width_blocks * bytes_per_block;
+        const u32 aligned_height = height_blocks;
+        task.bytes_per_slice = static_cast<size_t>(stride) * aligned_height;
        task.last_submitted_offset = 0;
-        task.slices_submitted = 0;
        task.initialized = true;
    }

@@ -1470,39 +1452,31 @@ void TextureCache<P>::TickAsyncUnswizzle() {
            if (copy_amount == 0) copy_amount = task.bytes_per_slice;
        }

-        gpu_memory->ReadBlockUnsafe(image.gpu_addr + task.current_offset,
-                                    task.staging_buffer.mapped_span.data() + task.current_offset,
-                                    copy_amount);
+        gpu_memory->ReadBlock(image.gpu_addr + task.current_offset,
+                              task.staging_buffer.mapped_span.data() + task.current_offset,
+                              copy_amount);
        task.current_offset += copy_amount;
    }

    const bool is_final_batch = task.current_offset >= task.total_size;
+    const size_t bytes_ready = task.current_offset - task.last_submitted_offset;
+    const u32 complete_slices = static_cast<u32>(bytes_ready / task.bytes_per_slice);

-    if (task.chunked) {
-        const size_t bytes_ready = task.current_offset - task.last_submitted_offset;
-        const u32 complete_slices = static_cast<u32>(bytes_ready / task.bytes_per_slice);
+    if (complete_slices >= swizzle_slices_per_batch || (is_final_batch && complete_slices > 0)) {
+        const u32 z_start = static_cast<u32>(task.last_submitted_offset / task.bytes_per_slice);
+        const u32 slices_to_process = (std::min)(complete_slices, swizzle_slices_per_batch);
+        const u32 z_count = (std::min)(slices_to_process, image.info.size.depth - z_start);

-        if (complete_slices >= swizzle_slices_per_batch || (is_final_batch && complete_slices > 0)) {
-            const u32 z_start = task.slices_submitted;
-            const u32 slices_to_process = (std::min)(complete_slices, swizzle_slices_per_batch);
-            const u32 z_count = (std::min)(slices_to_process, image.info.size.depth - z_start);
-
-            if (z_count > 0) {
-                const auto uploads = FullUploadSwizzles(task.info);
-                runtime.AccelerateImageUpload(image, task.staging_buffer,
-                                              FixSmallVectorADL(uploads), z_start, z_count);
-                task.last_submitted_offset += static_cast<size_t>(z_count) * task.bytes_per_slice;
-                task.slices_submitted += z_count;
-            }
+        if (z_count > 0) {
+            const auto uploads = FullUploadSwizzles(task.info);
+            runtime.AccelerateImageUpload(image, task.staging_buffer, FixSmallVectorADL(uploads), z_start, z_count);
+            task.last_submitted_offset += (static_cast<size_t>(z_count) * task.bytes_per_slice);
        }
-    } else if (is_final_batch && task.slices_submitted == 0) {
-        const auto uploads = FullUploadSwizzles(task.info);
-        runtime.AccelerateImageUpload(image, task.staging_buffer, FixSmallVectorADL(uploads), 0,
-                                      image.info.size.depth);
-        task.slices_submitted = image.info.size.depth;
    }

-    const bool all_slices_submitted = task.slices_submitted >= image.info.size.depth;
+    // Check if complete
+    const u32 slices_submitted = static_cast<u32>(task.last_submitted_offset / task.bytes_per_slice);
+    const bool all_slices_submitted = slices_submitted >= image.info.size.depth;

    if (is_final_batch && all_slices_submitted) {
        runtime.FreeDeferredStagingBuffer(task.staging_buffer);
@@ -139,8 +139,6 @@ class TextureCache : public VideoCommon::ChannelSetupCaches<TextureCacheChannelI
        AsyncBuffer staging_buffer;
        size_t last_submitted_offset = 0;
        size_t bytes_per_slice;
-        u32 slices_submitted = 0;
-        bool chunked = false;
        bool initialized = false;
    };

@@ -1219,11 +1219,6 @@ bool Device::GetSuitability(bool requires_swapchain) {
            VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_TRANSFORM_FEEDBACK_PROPERTIES_EXT;
        SetNext(next, properties.transform_feedback);
    }
-    if (extensions.vertex_attribute_divisor) {
-        properties.vertex_attribute_divisor.sType =
-            VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_VERTEX_ATTRIBUTE_DIVISOR_PROPERTIES_EXT;
-        SetNext(next, properties.vertex_attribute_divisor);
-    }
    if (extensions.maintenance5) {
        properties.maintenance5.sType =
            VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_MAINTENANCE_5_PROPERTIES_KHR;
@@ -70,7 +70,6 @@ VK_DEFINE_HANDLE(VmaAllocator)
    FEATURE(EXT, ProvokingVertex, PROVOKING_VERTEX, provoking_vertex)                              \
    FEATURE(EXT, Robustness2, ROBUSTNESS_2, robustness2)                                           \
    FEATURE(EXT, TransformFeedback, TRANSFORM_FEEDBACK, transform_feedback)                        \
-    FEATURE(EXT, VertexAttributeDivisor, VERTEX_ATTRIBUTE_DIVISOR, vertex_attribute_divisor)       \
    FEATURE(EXT, VertexInputDynamicState, VERTEX_INPUT_DYNAMIC_STATE, vertex_input_dynamic_state)  \
    FEATURE(KHR, Maintenance5, MAINTENANCE_5, maintenance5)                                        \
    FEATURE(KHR, Maintenance6, MAINTENANCE_6, maintenance6)                                        \
@@ -93,6 +92,7 @@ VK_DEFINE_HANDLE(VmaAllocator)
    EXTENSION(EXT, SHADER_STENCIL_EXPORT, shader_stencil_export)                                   \
    EXTENSION(EXT, SHADER_VIEWPORT_INDEX_LAYER, shader_viewport_index_layer)                       \
    EXTENSION(EXT, TOOLING_INFO, tooling_info)                                                     \
+    EXTENSION(EXT, VERTEX_ATTRIBUTE_DIVISOR, vertex_attribute_divisor)                             \
    EXTENSION(KHR, CREATE_RENDERPASS_2, create_renderpass2)                                        \
    EXTENSION(KHR, DEPTH_STENCIL_RESOLVE, depth_stencil_resolve)                                   \
    EXTENSION(KHR, DRAW_INDIRECT_COUNT, draw_indirect_count)                                       \
@@ -359,7 +359,6 @@ 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) \
@@ -690,32 +689,6 @@ FN_MAX_LIMIT_LIST
        return features.host_query_reset.hostQueryReset != VK_FALSE;
    }

-    u32 GetMaxVertexAttribDivisor() const {
-        const u32 reported = properties.vertex_attribute_divisor.maxVertexAttribDivisor;
-        if (reported == 0) {
-            return 1;
-        }
-        return reported;
-    }
-
-    bool IsVertexAttributeInstanceRateZeroDivisorSupported() const {
-        return features.vertex_attribute_divisor.vertexAttributeInstanceRateZeroDivisor == VK_TRUE;
-    }
-
-    u32 GetVertexAttribDivisor(u32 frequency) const {
-        const u32 max_divisor = GetMaxVertexAttribDivisor();
-        if (frequency == 0) {
-            if (IsVertexAttributeInstanceRateZeroDivisorSupported()) {
-                return 0;
-            }
-            return max_divisor;
-        }
-        if (frequency > max_divisor) {
-            return max_divisor;
-        }
-        return frequency;
-    }
-
    /// Returns true if the device supports VK_EXT_transform_feedback.
    bool IsExtTransformFeedbackSupported() const {
        return extensions.transform_feedback;
@@ -1216,7 +1189,6 @@ private:
        VkPhysicalDeviceDescriptorBufferPropertiesEXT descriptor_buffer{};
        VkPhysicalDeviceSubgroupSizeControlProperties subgroup_size_control{};
        VkPhysicalDeviceTransformFeedbackPropertiesEXT transform_feedback{};
-        VkPhysicalDeviceVertexAttributeDivisorPropertiesEXT vertex_attribute_divisor{};
        VkPhysicalDeviceMaintenance5PropertiesKHR maintenance5{};
        VkPhysicalDeviceDepthStencilResolveProperties depth_stencil_resolve{};
        VkPhysicalDeviceCustomBorderColorPropertiesEXT custom_border_color{};
@@ -26,350 +26,329 @@
 #include "common/settings.h"

 namespace Vulkan {
-    namespace {
+namespace {

 // Helpers translating MemoryUsage to flags/usage

-        [[maybe_unused]] VkMemoryPropertyFlags MemoryUsagePropertyFlags(MemoryUsage usage) {
-            switch (usage) {
-                case MemoryUsage::DeviceLocal:
-                    return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
-                case MemoryUsage::Upload:
-                    return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
-                           VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
-                case MemoryUsage::Download:
-                    return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
-                           VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
-                           VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
-                case MemoryUsage::Stream:
-                    return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
-                           VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
-                           VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
-            }
-            ASSERT_MSG(false, "Invalid memory usage={}", usage);
-            return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+    [[maybe_unused]] VkMemoryPropertyFlags MemoryUsagePropertyFlags(MemoryUsage usage) {
+        switch (usage) {
+            case MemoryUsage::DeviceLocal:
+                return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
+            case MemoryUsage::Upload:
+                return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
+                        VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+            case MemoryUsage::Download:
+                return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
+                        VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
+                        VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
+            case MemoryUsage::Stream:
+                return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
+                        VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
+                        VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
        }
+        ASSERT_MSG(false, "Invalid memory usage={}", usage);
+        return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+    }

-        [[nodiscard]] VkMemoryPropertyFlags MemoryUsagePreferredVmaFlags(MemoryUsage usage) {
-            if (usage == MemoryUsage::Download) {
-                return VK_MEMORY_PROPERTY_HOST_CACHED_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
-            }
-            return usage != MemoryUsage::DeviceLocal ? VK_MEMORY_PROPERTY_HOST_COHERENT_BIT
-                                                     : VkMemoryPropertyFlagBits{};
+    [[nodiscard]] VkMemoryPropertyFlags MemoryUsagePreferredVmaFlags(MemoryUsage usage) {
+        if (usage == MemoryUsage::Download) {
+            return VK_MEMORY_PROPERTY_HOST_CACHED_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
        }
+        return usage != MemoryUsage::DeviceLocal ? VK_MEMORY_PROPERTY_HOST_COHERENT_BIT
+                                                    : VkMemoryPropertyFlagBits{};
+    }

-        [[nodiscard]] VmaAllocationCreateFlags MemoryUsageVmaFlags(MemoryUsage usage) {
-            switch (usage) {
-                case MemoryUsage::Upload:
-                case MemoryUsage::Stream:
-                    return VMA_ALLOCATION_CREATE_MAPPED_BIT |
-                           VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
-                case MemoryUsage::Download:
-                    return VMA_ALLOCATION_CREATE_MAPPED_BIT |
-                           VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
-                case MemoryUsage::DeviceLocal:
-                    return {};
-            }
-            return {};
+    [[nodiscard]] VmaAllocationCreateFlags MemoryUsageVmaFlags(MemoryUsage usage) {
+        switch (usage) {
+            case MemoryUsage::Upload:
+            case MemoryUsage::Stream:
+                return VMA_ALLOCATION_CREATE_MAPPED_BIT |
+                        VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
+            case MemoryUsage::Download:
+                return VMA_ALLOCATION_CREATE_MAPPED_BIT |
+                        VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
+            case MemoryUsage::DeviceLocal:
+                return {};
        }
+        return {};
+    }

-        [[nodiscard]] VmaMemoryUsage MemoryUsageVma(MemoryUsage usage) {
-            switch (usage) {
-                case MemoryUsage::DeviceLocal:
-                case MemoryUsage::Stream:
-                    return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
-                case MemoryUsage::Upload:
-                case MemoryUsage::Download:
-                    return VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
-            }
-            return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+    [[nodiscard]] VmaMemoryUsage MemoryUsageVma(MemoryUsage usage) {
+        switch (usage) {
+            case MemoryUsage::DeviceLocal:
+            case MemoryUsage::Stream:
+                return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+            case MemoryUsage::Upload:
+            case MemoryUsage::Download:
+                return VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
        }
-
-
-// This avoids calling vkGetBufferMemoryRequirements* directly.
-        template<typename T>
-        static VkBuffer GetVkHandleFromBuffer(const T &buf) {
-            if constexpr (requires { static_cast<VkBuffer>(buf); }) {
-                return static_cast<VkBuffer>(buf);
-            } else if constexpr (requires {{ buf.GetHandle() } -> std::convertible_to<VkBuffer>; }) {
-                return buf.GetHandle();
-            } else if constexpr (requires {{ buf.Handle() } -> std::convertible_to<VkBuffer>; }) {
-                return buf.Handle();
-            } else if constexpr (requires {{ buf.vk_handle() } -> std::convertible_to<VkBuffer>; }) {
-                return buf.vk_handle();
-            } else {
-                static_assert(sizeof(T) == 0, "Cannot extract VkBuffer handle from vk::Buffer");
-                return VK_NULL_HANDLE;
-            }
-        }
-
-    } // namespace
+        return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+    }
+} // namespace

 //MemoryCommit is now VMA-backed
-    MemoryCommit::MemoryCommit(VmaAllocator alloc, VmaAllocation a,
-                               const VmaAllocationInfo &info) noexcept
-            : allocator{alloc}, allocation{a}, memory{info.deviceMemory},
-              offset{info.offset}, size{info.size}, mapped_ptr{info.pMappedData} {
-        // Log GPU memory allocation
+MemoryCommit::MemoryCommit(VmaAllocator alloc, VmaAllocation a,
+                            const VmaAllocationInfo &info) noexcept
+        : allocator{alloc}, allocation{a}, memory{info.deviceMemory},
+            offset{info.offset}, size{info.size}, mapped_ptr{info.pMappedData} {
+    // Log GPU memory allocation
+    if (GPU::Logging::IsActive() &&
+        Settings::values.gpu_log_memory_tracking.GetValue()) {
+        GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
+            reinterpret_cast<uintptr_t>(memory),
+            static_cast<u64>(size),
+            0  // Memory property flags (not easily available from VMA)
+        );
+    }
+}
+
+MemoryCommit::~MemoryCommit() { Release(); }
+
+MemoryCommit::MemoryCommit(MemoryCommit &&rhs) noexcept
+        : allocator{std::exchange(rhs.allocator, nullptr)},
+            allocation{std::exchange(rhs.allocation, nullptr)},
+            memory{std::exchange(rhs.memory, VK_NULL_HANDLE)},
+            offset{std::exchange(rhs.offset, 0)},
+            size{std::exchange(rhs.size, 0)},
+            mapped_ptr{std::exchange(rhs.mapped_ptr, nullptr)} {}
+
+MemoryCommit &MemoryCommit::operator=(MemoryCommit &&rhs) noexcept {
+    if (this != &rhs) {
+        Release();
+        allocator = std::exchange(rhs.allocator, nullptr);
+        allocation = std::exchange(rhs.allocation, nullptr);
+        memory = std::exchange(rhs.memory, VK_NULL_HANDLE);
+        offset = std::exchange(rhs.offset, 0);
+        size = std::exchange(rhs.size, 0);
+        mapped_ptr = std::exchange(rhs.mapped_ptr, nullptr);
+    }
+    return *this;
+}
+
+std::span<u8> MemoryCommit::Map()
+{
+    if (!allocation) return {};
+    if (!mapped_ptr) {
+        if (vmaMapMemory(allocator, allocation, &mapped_ptr) != VK_SUCCESS) return {};
+    }
+    const size_t n = static_cast<size_t>(std::min<VkDeviceSize>(size,
+                                                                (std::numeric_limits<size_t>::max)()));
+    return std::span<u8>{static_cast<u8 *>(mapped_ptr), n};
+}
+
+std::span<const u8> MemoryCommit::Map() const
+{
+    if (!allocation) return {};
+    if (!mapped_ptr) {
+        void *p = nullptr;
+        if (vmaMapMemory(allocator, allocation, &p) != VK_SUCCESS) return {};
+        const_cast<MemoryCommit *>(this)->mapped_ptr = p;
+    }
+    const size_t n = static_cast<size_t>(std::min<VkDeviceSize>(size,
+                                                                (std::numeric_limits<size_t>::max)()));
+    return std::span<const u8>{static_cast<const u8 *>(mapped_ptr), n};
+}
+
+void MemoryCommit::Unmap()
+{
+    if (allocation && mapped_ptr) {
+        vmaUnmapMemory(allocator, allocation);
+        mapped_ptr = nullptr;
+    }
+}
+
+void MemoryCommit::Release() {
+    if (allocation && allocator) {
+        // Log GPU memory deallocation
        if (GPU::Logging::IsActive() &&
-            Settings::values.gpu_log_memory_tracking.GetValue()) {
-            GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
-                reinterpret_cast<uintptr_t>(memory),
-                static_cast<u64>(size),
-                0  // Memory property flags (not easily available from VMA)
+            Settings::values.gpu_log_memory_tracking.GetValue() &&
+            memory != VK_NULL_HANDLE) {
+            GPU::Logging::GPULogger::GetInstance().LogMemoryDeallocation(
+                reinterpret_cast<uintptr_t>(memory)
            );
        }
-    }

-    MemoryCommit::~MemoryCommit() { Release(); }
-
-    MemoryCommit::MemoryCommit(MemoryCommit &&rhs) noexcept
-            : allocator{std::exchange(rhs.allocator, nullptr)},
-              allocation{std::exchange(rhs.allocation, nullptr)},
-              memory{std::exchange(rhs.memory, VK_NULL_HANDLE)},
-              offset{std::exchange(rhs.offset, 0)},
-              size{std::exchange(rhs.size, 0)},
-              mapped_ptr{std::exchange(rhs.mapped_ptr, nullptr)} {}
-
-    MemoryCommit &MemoryCommit::operator=(MemoryCommit &&rhs) noexcept {
-        if (this != &rhs) {
-            Release();
-            allocator = std::exchange(rhs.allocator, nullptr);
-            allocation = std::exchange(rhs.allocation, nullptr);
-            memory = std::exchange(rhs.memory, VK_NULL_HANDLE);
-            offset = std::exchange(rhs.offset, 0);
-            size = std::exchange(rhs.size, 0);
-            mapped_ptr = std::exchange(rhs.mapped_ptr, nullptr);
-        }
-        return *this;
-    }
-
-    std::span<u8> MemoryCommit::Map()
-    {
-        if (!allocation) return {};
-        if (!mapped_ptr) {
-            if (vmaMapMemory(allocator, allocation, &mapped_ptr) != VK_SUCCESS) return {};
-        }
-        const size_t n = static_cast<size_t>(std::min<VkDeviceSize>(size,
-                                                                    (std::numeric_limits<size_t>::max)()));
-        return std::span<u8>{static_cast<u8 *>(mapped_ptr), n};
-    }
-
-    std::span<const u8> MemoryCommit::Map() const
-    {
-        if (!allocation) return {};
-        if (!mapped_ptr) {
-            void *p = nullptr;
-            if (vmaMapMemory(allocator, allocation, &p) != VK_SUCCESS) return {};
-            const_cast<MemoryCommit *>(this)->mapped_ptr = p;
-        }
-        const size_t n = static_cast<size_t>(std::min<VkDeviceSize>(size,
-                                                                    (std::numeric_limits<size_t>::max)()));
-        return std::span<const u8>{static_cast<const u8 *>(mapped_ptr), n};
-    }
-
-    void MemoryCommit::Unmap()
-    {
-        if (allocation && mapped_ptr) {
+        if (mapped_ptr) {
            vmaUnmapMemory(allocator, allocation);
            mapped_ptr = nullptr;
        }
+        vmaFreeMemory(allocator, allocation);
    }
+    allocation = nullptr;
+    allocator = nullptr;
+    memory = VK_NULL_HANDLE;
+    offset = 0;
+    size = 0;
+}

-    void MemoryCommit::Release() {
-        if (allocation && allocator) {
-            // Log GPU memory deallocation
-            if (GPU::Logging::IsActive() &&
-                Settings::values.gpu_log_memory_tracking.GetValue() &&
-                memory != VK_NULL_HANDLE) {
-                GPU::Logging::GPULogger::GetInstance().LogMemoryDeallocation(
-                    reinterpret_cast<uintptr_t>(memory)
-                );
-            }
+MemoryAllocator::MemoryAllocator(const Device &device_)
+        : device{device_}, allocator{device.GetAllocator()},
+            properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
+            buffer_image_granularity{
+                    device_.GetPhysical().GetProperties().limits.bufferImageGranularity} {

-            if (mapped_ptr) {
-                vmaUnmapMemory(allocator, allocation);
-                mapped_ptr = nullptr;
-            }
-            vmaFreeMemory(allocator, allocation);
-        }
-        allocation = nullptr;
-        allocator = nullptr;
-        memory = VK_NULL_HANDLE;
-        offset = 0;
-        size = 0;
-    }
-
-    MemoryAllocator::MemoryAllocator(const Device &device_)
-            : device{device_}, allocator{device.GetAllocator()},
-              properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
-              buffer_image_granularity{
-                      device_.GetPhysical().GetProperties().limits.bufferImageGranularity} {
-
-        // Preserve the previous "RenderDoc small heap" trimming behavior that we had in original vma minus the heap bug
-        if (device.HasDebuggingToolAttached())
-        {
-            using namespace Common::Literals;
-            ForEachDeviceLocalHostVisibleHeap(device, [this](size_t heap_idx, VkMemoryHeap &heap) {
-                if (heap.size <= 256_MiB) {
-                    for (u32 t = 0; t < properties.memoryTypeCount; ++t) {
-                        if (properties.memoryTypes[t].heapIndex == heap_idx) {
-                            valid_memory_types &= ~(1u << t);
-                        }
+    // Preserve the previous "RenderDoc small heap" trimming behavior that we had in original vma minus the heap bug
+    if (device.HasDebuggingToolAttached())
+    {
+        using namespace Common::Literals;
+        ForEachDeviceLocalHostVisibleHeap(device, [this](size_t heap_idx, VkMemoryHeap &heap) {
+            if (heap.size <= 256_MiB) {
+                for (u32 t = 0; t < properties.memoryTypeCount; ++t) {
+                    if (properties.memoryTypes[t].heapIndex == heap_idx) {
+                        valid_memory_types &= ~(1u << t);
                    }
                }
-            });
-        }
+            }
+        });
    }
+}

-    MemoryAllocator::~MemoryAllocator() = default;
+MemoryAllocator::~MemoryAllocator() = default;

-    vk::Image MemoryAllocator::CreateImage(const VkImageCreateInfo &ci) const
-    {
-        const VmaAllocationCreateInfo alloc_ci = {
-                .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT,
-                .usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE,
-                .requiredFlags = 0,
-                .preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
-                .memoryTypeBits = 0,
-                .pool = VK_NULL_HANDLE,
-                .pUserData = nullptr,
-                .priority = 0.f,
-        };
-
-        VkImage handle{};
-        VmaAllocation allocation{};
-        VmaAllocationInfo alloc_info{};
-        vk::Check(vmaCreateImage(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
-
-        // Log GPU memory allocation for images
-        if (GPU::Logging::IsActive() &&
-            Settings::values.gpu_log_memory_tracking.GetValue()) {
-            GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
-                reinterpret_cast<uintptr_t>(alloc_info.deviceMemory),
-                static_cast<u64>(alloc_info.size),
-                VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT
-            );
-        }
-
-        return vk::Image(handle, ci.usage, *device.GetLogical(), allocator, allocation,
-                         device.GetDispatchLoader());
-    }
-
-    vk::Buffer MemoryAllocator::CreateBuffer(const VkBufferCreateInfo &ci, MemoryUsage usage) const {
-        // MESA will do memcpy() if not marked as host cached, so just force mark it for most buffers
-        auto const anv_flags = (usage == MemoryUsage::Stream
-            && device.GetDriverID() == VK_DRIVER_ID_INTEL_OPEN_SOURCE_MESA)
-            ? VK_MEMORY_PROPERTY_HOST_CACHED_BIT : 0;
-        const VmaAllocationCreateInfo alloc_ci = {
-            .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage),
-            .usage = MemoryUsageVma(usage),
+vk::Image MemoryAllocator::CreateImage(const VkImageCreateInfo &ci) const
+{
+    const VmaAllocationCreateInfo alloc_ci = {
+            .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT,
+            .usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE,
            .requiredFlags = 0,
-            .preferredFlags = MemoryUsagePreferredVmaFlags(usage) | anv_flags,
-            .memoryTypeBits = usage == MemoryUsage::Stream ? 0u : valid_memory_types,
+            .preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
+            .memoryTypeBits = 0,
            .pool = VK_NULL_HANDLE,
            .pUserData = nullptr,
            .priority = 0.f,
-        };
+    };

-        VkBuffer handle{};
-        VmaAllocationInfo alloc_info{};
-        VmaAllocation allocation{};
-        VkMemoryPropertyFlags property_flags{};
+    VkImage handle{};
+    VmaAllocation allocation{};
+    VmaAllocationInfo alloc_info{};
+    vk::Check(vmaCreateImage(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));

-        vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
-        vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags);
-
-        // Log GPU memory allocation for buffers
-        if (GPU::Logging::IsActive() &&
-            Settings::values.gpu_log_memory_tracking.GetValue()) {
-            GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
-                reinterpret_cast<uintptr_t>(alloc_info.deviceMemory),
-                static_cast<u64>(alloc_info.size),
-                property_flags
-            );
-        }
-
-        u8 *data = reinterpret_cast<u8 *>(alloc_info.pMappedData);
-        const std::span<u8> mapped_data = data ? std::span<u8>{data, ci.size} : std::span<u8>{};
-        const bool is_coherent = (property_flags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) != 0;
-
-        return vk::Buffer(handle, *device.GetLogical(), allocator, allocation, mapped_data,
-                          is_coherent,
-                          device.GetDispatchLoader());
+    // Log GPU memory allocation for images
+    if (GPU::Logging::IsActive() &&
+        Settings::values.gpu_log_memory_tracking.GetValue()) {
+        GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
+            reinterpret_cast<uintptr_t>(alloc_info.deviceMemory),
+            static_cast<u64>(alloc_info.size),
+            VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT
+        );
    }

-    MemoryCommit MemoryAllocator::Commit(const VkMemoryRequirements &reqs, MemoryUsage usage)
-    {
-        const auto vma_usage = MemoryUsageVma(usage);
-        VmaAllocationCreateInfo ci{};
-        ci.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage);
-        ci.usage = vma_usage;
-        ci.memoryTypeBits = reqs.memoryTypeBits & valid_memory_types;
-        ci.requiredFlags = 0;
-        ci.preferredFlags = MemoryUsagePreferredVmaFlags(usage);
+    return vk::Image(handle, ci.usage, *device.GetLogical(), allocator, allocation,
+                        device.GetDispatchLoader());
+}

-        VmaAllocation a{};
-        VmaAllocationInfo info{};
+vk::Buffer MemoryAllocator::CreateBuffer(const VkBufferCreateInfo &ci, MemoryUsage usage) const {
+    // MESA will do memcpy() if not marked as host cached, so just force mark it for most buffers
+    auto const anv_flags = (usage == MemoryUsage::Stream
+        && device.GetDriverID() == VK_DRIVER_ID_INTEL_OPEN_SOURCE_MESA)
+        ? VK_MEMORY_PROPERTY_HOST_CACHED_BIT : 0;
+    const VmaAllocationCreateInfo alloc_ci = {
+        .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage),
+        .usage = MemoryUsageVma(usage),
+        .requiredFlags = 0,
+        .preferredFlags = MemoryUsagePreferredVmaFlags(usage) | anv_flags,
+        .memoryTypeBits = usage == MemoryUsage::Stream ? 0u : valid_memory_types,
+        .pool = VK_NULL_HANDLE,
+        .pUserData = nullptr,
+        .priority = 0.f,
+    };

-        VkResult res = vmaAllocateMemory(allocator, &reqs, &ci, &a, &info);
+    VkBuffer handle{};
+    VmaAllocationInfo alloc_info{};
+    VmaAllocation allocation{};
+    VkMemoryPropertyFlags property_flags{};

-        if (res != VK_SUCCESS) {
-            // Relax 1: drop budget constraint
-            auto ci2 = ci;
-            ci2.flags &= ~VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT;
-            res = vmaAllocateMemory(allocator, &reqs, &ci2, &a, &info);
+    vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
+    vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags);

-            // Relax 2: if we preferred DEVICE_LOCAL, drop that preference
-            if (res != VK_SUCCESS && (ci.preferredFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT)) {
-                auto ci3 = ci2;
-                ci3.preferredFlags &= ~VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
-                res = vmaAllocateMemory(allocator, &reqs, &ci3, &a, &info);
-            }
-        }
-
-        vk::Check(res);
-        return MemoryCommit(allocator, a, info);
+    // Log GPU memory allocation for buffers
+    if (GPU::Logging::IsActive() &&
+        Settings::values.gpu_log_memory_tracking.GetValue()) {
+        GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
+            reinterpret_cast<uintptr_t>(alloc_info.deviceMemory),
+            static_cast<u64>(alloc_info.size),
+            property_flags
+        );
    }

-    MemoryCommit MemoryAllocator::Commit(const vk::Buffer &buffer, MemoryUsage usage) {
-        // Allocate memory appropriate for this buffer automatically
-        const auto vma_usage = MemoryUsageVma(usage);
+    u8 *data = reinterpret_cast<u8 *>(alloc_info.pMappedData);
+    const std::span<u8> mapped_data = data ? std::span<u8>{data, ci.size} : std::span<u8>{};
+    const bool is_coherent = (property_flags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) != 0;

-        VmaAllocationCreateInfo ci{};
-        ci.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage);
-        ci.usage = vma_usage;
-        ci.requiredFlags = 0;
-        ci.preferredFlags = MemoryUsagePreferredVmaFlags(usage);
-        ci.pool = VK_NULL_HANDLE;
-        ci.pUserData = nullptr;
-        ci.priority = 0.0f;
+    return vk::Buffer(handle, *device.GetLogical(), allocator, allocation, mapped_data,
+                        is_coherent,
+                        device.GetDispatchLoader());
+}

-        const VkBuffer raw = *buffer;
+MemoryCommit MemoryAllocator::Commit(const VkMemoryRequirements &reqs, MemoryUsage usage)
+{
+    const auto vma_usage = MemoryUsageVma(usage);
+    VmaAllocationCreateInfo ci{};
+    ci.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage);
+    ci.usage = vma_usage;
+    ci.memoryTypeBits = reqs.memoryTypeBits & valid_memory_types;
+    ci.requiredFlags = 0;
+    ci.preferredFlags = MemoryUsagePreferredVmaFlags(usage);

-        VmaAllocation a{};
-        VmaAllocationInfo info{};
+    VmaAllocation a{};
+    VmaAllocationInfo info{};

-        // Let VMA infer memory requirements from the buffer
-        VkResult res = vmaAllocateMemoryForBuffer(allocator, raw, &ci, &a, &info);
+    VkResult res = vmaAllocateMemory(allocator, &reqs, &ci, &a, &info);

-        if (res != VK_SUCCESS) {
-            auto ci2 = ci;
-            ci2.flags &= ~VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT;
-            res = vmaAllocateMemoryForBuffer(allocator, raw, &ci2, &a, &info);
+    if (res != VK_SUCCESS) {
+        // Relax 1: drop budget constraint
+        auto ci2 = ci;
+        ci2.flags &= ~VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT;
+        res = vmaAllocateMemory(allocator, &reqs, &ci2, &a, &info);

-            if (res != VK_SUCCESS && (ci.preferredFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT)) {
-                auto ci3 = ci2;
-                ci3.preferredFlags &= ~VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
-                res = vmaAllocateMemoryForBuffer(allocator, raw, &ci3, &a, &info);
-            }
+        // Relax 2: if we preferred DEVICE_LOCAL, drop that preference
+        if (res != VK_SUCCESS && (ci.preferredFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT)) {
+            auto ci3 = ci2;
+            ci3.preferredFlags &= ~VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
+            res = vmaAllocateMemory(allocator, &reqs, &ci3, &a, &info);
        }
-
-        vk::Check(res);
-        vk::Check(vmaBindBufferMemory2(allocator, a, 0, raw, nullptr));
-        return MemoryCommit(allocator, a, info);
    }

+    vk::Check(res);
+    return MemoryCommit(allocator, a, info);
+}

+MemoryCommit MemoryAllocator::Commit(const vk::Buffer &buffer, MemoryUsage usage) {
+    // Allocate memory appropriate for this buffer automatically
+    const auto vma_usage = MemoryUsageVma(usage);
+
+    VmaAllocationCreateInfo ci{};
+    ci.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage);
+    ci.usage = vma_usage;
+    ci.requiredFlags = 0;
+    ci.preferredFlags = MemoryUsagePreferredVmaFlags(usage);
+    ci.pool = VK_NULL_HANDLE;
+    ci.pUserData = nullptr;
+    ci.priority = 0.0f;
+
+    const VkBuffer raw = *buffer;
+
+    VmaAllocation a{};
+    VmaAllocationInfo info{};
+
+    // Let VMA infer memory requirements from the buffer
+    VkResult res = vmaAllocateMemoryForBuffer(allocator, raw, &ci, &a, &info);
+
+    if (res != VK_SUCCESS) {
+        auto ci2 = ci;
+        ci2.flags &= ~VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT;
+        res = vmaAllocateMemoryForBuffer(allocator, raw, &ci2, &a, &info);
+
+        if (res != VK_SUCCESS && (ci.preferredFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT)) {
+            auto ci3 = ci2;
+            ci3.preferredFlags &= ~VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
+            res = vmaAllocateMemoryForBuffer(allocator, raw, &ci3, &a, &info);
+        }
+    }
+
+    vk::Check(res);
+    vk::Check(vmaBindBufferMemory2(allocator, a, 0, raw, nullptr));
+    return MemoryCommit(allocator, a, info);
+}

 } // namespace Vulkan
@@ -4796,6 +4796,6 @@ void VolumeButton::ResetMultiplier() {
 #endif

 #if !defined(QT_STATICPLUGIN) || defined(__APPLE__)
-#define VMA_IMPLEMENTATION
+#define VMA_IMPLEMENTATION 1
 #include "video_core/vulkan_common/vma.h"
 #endif
@@ -65,7 +65,7 @@ else()
 endif()

 # update cached cpmfile content
-string(JSON cpmfile SET "${cpmfile}" "${key}" "${new_object}")
+string(JSON cpmfile SET "${cpmfile}" "${KEY}" "${new_object}")

 # write cached cpmfile
 get_cpmfile_path(file)
Author	SHA1	Message	Date
lizzie	be67a31c93	2026-09-06 04:05:29 Signed-off-by: lizzie <lizzie@eden-emu.dev>	2026-09-06 04:05:29 +00:00
lizzie	11de264541	[cmake] Fix some macOS compilation errors (#4350 ) Don't compile GLSL/GLASM backends without OpenGL enabled. These codepaths are unused on non-OpenGL platforms. Fixes other miscellaneous errors that pop up on Clang 23 as well. Signed-off-by: Lizzie lizzie@eden-emu.dev Signed-off-by: crueter crueter@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. ------------------- Co-authored-by: crueter <crueter@eden-emu.dev> Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4350 Reviewed-by: crueter <crueter@eden-emu.dev> Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>	2026-09-05 23:43:46 +02:00
lizzie	f6e7686038	[ci] Fix macOS "no type named 'free' in namespace 'std' (#4347 ) 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. ------------------- Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4347 Reviewed-by: CamilleLaVey <camillelavey99@gmail.com> Reviewed-by: MaranBr <maranbr@eden-emu.dev>	2026-09-04 13:32:36 +02:00
xbzk	1dcc574591	[gdb] fix conn state to use same pipe (instead of a copy) (#4339 ) - [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. ------------------- I was trying to use GDB stub to investigate MHR and it was not connecting. Error was suggesting it was not available for connection although i saw it booting on logs. Debugged and noticed signal_pipe_ was not the correct one, and followed the example of client_socket_. GDB stub is now working, on windows, at least. Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4339 Reviewed-by: Lizzie and Samuel <lizzie@eden-emu.dev> Reviewed-by: MaranBr <maranbr@eden-emu.dev>	2026-09-02 14:04:35 +02:00
lizzie	5c20f244c9	[cmake] stop building OpenGL on Android (#4342 ) 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. ------------------- we don't even support OpenGL on android Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4342 Reviewed-by: crueter <crueter@eden-emu.dev> Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>	2026-09-02 04:07:24 +02:00