WIP: [cmake] Use a debloated boost distribution

Should speed up fetch time

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

.patch/boost/0001-clang-cl.patch

@@ -1,13 +0,0 @@
-diff --git a/libs/cobalt/include/boost/cobalt/concepts.hpp b/libs/cobalt/include/boost/cobalt/concepts.hpp
-index d49f2ec..a9bdb80 100644
---- a/libs/cobalt/include/boost/cobalt/concepts.hpp
-+++ b/libs/cobalt/include/boost/cobalt/concepts.hpp
-@@ -62,7 +62,7 @@ struct enable_awaitables
- template <typename T>
- concept with_get_executor = requires (T& t)
- {
--  {t.get_executor()} -> asio::execution::executor;
-+  t.get_executor();
- };
- 
- 

.patch/vulkan-memory-allocator/0001-macos-clang.patch

@@ -1,112 +0,0 @@
-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)
-     {

CMakeLists.txt

@@ -3,7 +3,6 @@
 
 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")
@@ -415,12 +414,9 @@ AddJsonPackage(boost)
 set(BOOST_NO_HEADERS ${Boost_ADDED})
 
 if (Boost_ADDED)
-    if (MSVC OR ANDROID)
-        add_compile_definitions(YUZU_BOOST_v1)
-    endif()
-
+    add_compile_definitions(YUZU_BOOST_v1)
     if (NOT MSVC OR CXX_CLANG)
-        # boost sucks
+        # solaris sucks
         if (SOLARIS)
             add_compile_options($<$<COMPILE_LANGUAGE:C,CXX>:-pthreads>)
         endif()
@@ -429,8 +425,7 @@ if (Boost_ADDED)
         target_compile_options(boost_icl INTERFACE $<$<COMPILE_LANGUAGE:C,CXX>:-Wno-shadow>)
         target_compile_options(boost_asio INTERFACE
             $<$<COMPILE_LANGUAGE:C,CXX>:-Wno-conversion>
-            $<$<COMPILE_LANGUAGE:C,CXX>:-Wno-implicit-fallthrough>
-        )
+            $<$<COMPILE_LANGUAGE:C,CXX>:-Wno-implicit-fallthrough>)
     endif()
 endif()
 
@@ -513,7 +508,7 @@ endfunction()
 # =============================================
 
 if (APPLE)
-    foreach(fw Carbon Metal Cocoa IOKit CoreVideo CoreMedia Security UniformTypeIdentifiers Foundation)
+    foreach(fw Carbon Metal Cocoa IOKit CoreVideo CoreMedia Security UniformTypeIdentifiers)
         find_library(${fw}_LIBRARY ${fw} REQUIRED)
         list(APPEND PLATFORM_LIBRARIES ${${fw}_LIBRARY})
     endforeach()

cpmfile.json

@@ -1,4 +1,12 @@
 {
+    "": {
+        "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",
@@ -6,22 +14,19 @@
         "version": "v0.19.0"
     },
     "boost": {
-        "artifact": "%VERSION%-cmake.tar.xz",
+        "artifact": "boost-%VERSION%.tar.zst",
         "find_args": "CONFIG OPTIONAL_COMPONENTS headers context system fiber filesystem",
-        "hash": "6ae6e94664fe7f2fb01976b59b276ac5df8085c7503fa829d810fbfe495960cfec44fa2c36e2cb23480bc19c956ed199d4952b02639a00a6c07625d4e7130c2d",
+        "hash": "077ad58b3d336041c05ad5f2b1de7db9fe1d35af3da85cd99496c35ddeca080ecd0ae5c8058319077bda892361b38624d89f70bc9bfec6713aae2aabc17f2a43",
         "min_version": "1.57",
         "package": "Boost",
-        "patches": [
-            "0001-clang-cl.patch"
-        ],
-        "repo": "boostorg/boost",
-        "version": "boost-1.90.0"
+        "repo": "eden-emulator/ext-boost",
+        "version": "1.91.0-1"
     },
     "boost_headers": {
         "bundled": true,
-        "hash": "4ef845775e2277a8104ded6ddf749aa262ce52cf8438042869a048f9a0156dd772fbbcfa74efa1378fecef339b7286f6fe4b4feb5c45d49966b35d08e3e83507",
+        "hash": "c5fa2cd72f6e6666b7963b97bc359c75284b8fb540c30f3629a028b85270c9bc66c8a051383964f2bd4c1e005a4691593d15696e7ef39ea87cf6cff9e5691fb2",
         "repo": "boostorg/headers",
-        "version": "boost-1.90.0"
+        "version": "boost-1.91.0"
     },
     "catch2": {
         "hash": "7eea385d79d88a5690cde131fe7ccda97d5c54ea09d6f515000d7bf07c828809d61c1ac99912c1ee507cf933f61c1c47ecdcc45df7850ffa82714034b0fccf35",
@@ -60,10 +65,10 @@
     },
     "discord-rpc": {
         "find_args": "MODULE",
-        "hash": "8d680b3a16d6f6bf292ad823cf8635595ff986f2a49f758e3009f505b540a9d75194a8cf44cddea75736a8c3e3b5160166e716a0939ce3f18cc463cf648753fe",
+        "hash": "8213c43dcb0f7d479f5861091d111ed12fbdec1e62e6d729d65a4bc181d82f48a35d5fd3cd5c291f2393ac7c9681eabc6b76609755f55376284c8a8d67e148f3",
         "package": "DiscordRPC",
         "repo": "eden-emulator/discord-rpc",
-        "version": "76616d8675"
+        "version": "0d8b2d6a37"
     },
     "enet": {
         "find_args": "MODULE",
@@ -303,9 +308,6 @@
         "find_args": "CONFIG",
         "hash": "deb5902ef8db0e329fbd5f3f4385eb0e26bdd9f14f3a2334823fb3fe18f36bc5d235d620d6e5f6fe3551ec3ea7038638899db8778c09f6d5c278f5ff95c3344b",
         "package": "VulkanMemoryAllocator",
-        "patches": [
-            "0001-macos-clang.patch"
-        ],
         "repo": "GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator",
         "version": "v3.3.0"
     },

src/common/scratch_buffer.h

@@ -1,13 +1,9 @@
-// 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"
 
@@ -65,7 +61,7 @@ public:
     void resize(size_type size) {
         if (size > buffer_capacity) {
             auto new_buffer = Common::make_unique_for_overwrite<T[]>(size);
-            std::memcpy(new_buffer.get(), buffer.get(), buffer_capacity * sizeof(T));
+            std::move(buffer.get(), buffer.get() + buffer_capacity, new_buffer.get());
             buffer = std::move(new_buffer);
             buffer_capacity = size;
         }

src/common/uuid.h

@@ -10,7 +10,6 @@
 #include <functional>
 #include <span>
 #include <string>
-#include <type_traits>
 
 #include "common/common_types.h"
 

src/core/debugger/debugger.cpp

@@ -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

src/core/file_sys/fssystem/fs_types.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -6,7 +6,6 @@
 
 #pragma once
 
-#include <type_traits>
 #include "common/common_funcs.h"
 
 namespace FileSys {

src/core/file_sys/fssystem/fssystem_aes_ctr_counter_extended_storage.h

@@ -7,7 +7,6 @@
 #pragma once
 
 #include <optional>
-#include <type_traits>
 
 #include "common/literals.h"
 #include "core/file_sys/fssystem/fs_i_storage.h"

src/core/file_sys/fssystem/fssystem_bucket_tree.cpp

@@ -4,7 +4,6 @@
 // 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"

src/core/file_sys/fssystem/fssystem_bucket_tree.h

@@ -1,13 +1,9 @@
-// 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"

src/core/file_sys/fssystem/fssystem_bucket_tree_template_impl.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -6,7 +6,6 @@
 
 #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"

src/core/file_sys/fssystem/fssystem_compressed_storage.h

@@ -6,8 +6,6 @@
 
 #pragma once
 
-#include <type_traits>
-#include <cstddef>
 #include "common/literals.h"
 
 #include "core/file_sys/errors.h"

src/core/file_sys/fssystem/fssystem_hierarchical_integrity_verification_storage.h

@@ -1,12 +1,8 @@
-// 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"

src/core/file_sys/fssystem/fssystem_indirect_storage.h

@@ -6,9 +6,6 @@
 
 #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"

src/core/file_sys/fssystem/fssystem_integrity_verification_storage.h

@@ -1,15 +1,9 @@
-// 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"

src/core/file_sys/fssystem/fssystem_nca_file_system_driver.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -6,8 +6,6 @@
 
 #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"

src/core/file_sys/fssystem/fssystem_nca_header.h

@@ -1,14 +1,8 @@
-// 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"

src/core/hle/kernel/k_page_table_base.h

@@ -7,7 +7,6 @@
 #pragma once
 
 #include <memory>
-#include <type_traits>
 
 #include "common/common_funcs.h"
 #include "common/page_table.h"

src/core/hle/result.h

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

src/core/hle/service/bcat/bcat_types.h

@@ -1,13 +1,9 @@
-// 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"

src/core/hle/service/caps/caps_manager.cpp

@@ -175,10 +175,19 @@ Result AlbumManager::LoadAlbumScreenShotImage(LoadAlbumScreenShotImageOutput& ou
         return ResultIsNotMounted;
     }
 
-    out_image_output = {};
-    out_image_output.width = 1280;
-    out_image_output.height = 720;
-    out_image_output.attribute.orientation = AlbumImageOrientation::None;
+    out_image_output = {
+        .width = 1280,
+        .height = 720,
+        .attribute =
+            {
+                .unknown_0{},
+                .orientation = AlbumImageOrientation::None,
+                .unknown_1{},
+                .unknown_2{},
+                .pad163{},
+            },
+        .pad179{},
+    };
 
     std::filesystem::path path;
     const auto result = GetFile(path, file_id);
@@ -202,10 +211,19 @@ Result AlbumManager::LoadAlbumScreenShotThumbnail(
         return ResultIsNotMounted;
     }
 
-    out_image_output = {};
-    out_image_output.width = 320;
-    out_image_output.height = 180;
-    out_image_output.attribute.orientation = AlbumImageOrientation::None;
+    out_image_output = {
+        .width = 320,
+        .height = 180,
+        .attribute =
+            {
+                .unknown_0{},
+                .orientation = AlbumImageOrientation::None,
+                .unknown_1{},
+                .unknown_2{},
+                .pad163{},
+            },
+        .pad179{},
+    };
 
     std::filesystem::path path;
     const auto result = GetFile(path, file_id);

src/core/hle/service/caps/caps_su.cpp

@@ -73,8 +73,13 @@ void IScreenShotApplicationService::CaptureAndSaveScreenshot(AlbumReportOption r
     Layout::FramebufferLayout layout =
         Layout::DefaultFrameLayout(screenshot_width, screenshot_height);
 
-    Capture::ScreenShotAttribute attribute{};
-    attribute.orientation = Capture::AlbumImageOrientation::None;
+    const Capture::ScreenShotAttribute attribute{
+        .unknown_0{},
+        .orientation = Capture::AlbumImageOrientation::None,
+        .unknown_1{},
+        .unknown_2{},
+        .pad163{},
+    };
 
     renderer.RequestScreenshot(
         image_data.data(),

src/core/hle/service/caps/caps_types.h

@@ -1,12 +1,8 @@
-// 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"
 

src/core/hle/service/ldn/ldn_types.h

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
@@ -6,7 +6,6 @@
 
 #pragma once
 
-#include <type_traits>
 #include <fmt/ranges.h>
 
 #include "common/common_funcs.h"

src/core/hle/service/psc/time/common.h

@@ -8,7 +8,6 @@
 
 #include <array>
 #include <chrono>
-#include <type_traits>
 #include <fmt/ranges.h>
 
 #include "common/common_types.h"

src/core/hle/service/psc/time/shared_memory.h

@@ -1,13 +1,10 @@
-// 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"
 

src/core/hle/service/set/settings_types.h

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

src/hid_core/hid_types.h

@@ -1,15 +1,8 @@
-// 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"

src/shader_recompiler/CMakeLists.txt

@@ -6,6 +6,55 @@
 
 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
@@ -190,60 +239,9 @@ 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)
 

src/shader_recompiler/ir_opt/global_memory_to_storage_buffer_pass.cpp

@@ -553,6 +553,17 @@ 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) {

src/video_core/host1x/codec_types.h

@@ -8,7 +8,6 @@
 
 #include <array>
 #include <vector>
-#include <type_traits>
 
 #include "common/bit_field.h"
 #include "common/common_funcs.h"

src/video_core/host1x/nvdec_common.h

@@ -1,15 +1,8 @@
-// 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"

src/video_core/host1x/vic.h

@@ -7,7 +7,6 @@
 #pragma once
 
 #include <memory>
-#include <type_traits>
 
 #include "common/common_types.h"
 #include "common/scratch_buffer.h"

src/video_core/renderer_opengl/gl_buffer_cache.cpp

@@ -148,11 +148,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_,
 }
 
 StagingBufferMap BufferCacheRuntime::UploadStagingBuffer(size_t size) {
-    return staging_buffer_pool.RequestUploadBuffer(device, size);
+    return staging_buffer_pool.RequestUploadBuffer(size);
 }
 
 StagingBufferMap BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.RequestDownloadBuffer(device, size, deferred);
+    return staging_buffer_pool.RequestDownloadBuffer(size, deferred);
 }
 
 void BufferCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) {

src/video_core/renderer_opengl/gl_texture_cache.cpp

@@ -557,11 +557,11 @@ void TextureCacheRuntime::Finish() {
 }
 
 StagingBufferMap TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.RequestUploadBuffer(device, size);
+    return staging_buffer_pool.RequestUploadBuffer(size);
 }
 
 StagingBufferMap TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.RequestDownloadBuffer(device, size, deferred);
+    return staging_buffer_pool.RequestDownloadBuffer(size, deferred);
 }
 
 void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) {

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -192,7 +192,7 @@ public:
             if (host_visible) {
                 return StagingBufferRef{};
             }
-            return staging_pool.Request(device, size_bytes, MemoryUsage::Upload);
+            return staging_pool.Request(size_bytes, MemoryUsage::Upload);
         }();
 
         u8* staging_data = host_visible ? buffer.Mapped().data() : staging.mapped_span.data();
@@ -366,11 +366,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_, MemoryAllocator& m
 }
 
 StagingBufferRef BufferCacheRuntime::UploadStagingBuffer(size_t size) {
-    return staging_pool.Request(device, size, MemoryUsage::Upload);
+    return staging_pool.Request(size, MemoryUsage::Upload);
 }
 
 StagingBufferRef BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_pool.Request(device, size, MemoryUsage::Download, deferred);
+    return staging_pool.Request(size, MemoryUsage::Download, deferred);
 }
 
 VkFormat BufferCacheRuntime::TexelBufferFormat(VideoCore::Surface::PixelFormat format) const {

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -149,7 +149,7 @@ public:
     std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t stage,
                                           [[maybe_unused]] u32 binding_index,
                                           u32 size) {
-        const StagingBufferRef ref = staging_pool.Request(device, size, MemoryUsage::Upload);
+        const StagingBufferRef ref = staging_pool.Request(size, MemoryUsage::Upload);
         guest_descriptor_queue.AddBuffer(ref.buffer, ref.device_address,
                                          static_cast<u32>(ref.offset), size);
         return ref.mapped_span;

src/video_core/renderer_vulkan/vk_compute_pass.cpp

@@ -287,7 +287,7 @@ Uint8Pass::~Uint8Pass() = default;
 std::pair<VkBuffer, VkDeviceSize> Uint8Pass::Assemble(u32 num_vertices, VkBuffer src_buffer,
                                                       u32 src_offset) {
     const u32 staging_size = static_cast<u32>(num_vertices * sizeof(u16));
-    const auto staging = staging_buffer_pool.Request(device, staging_size, MemoryUsage::DeviceLocal);
+    const auto staging = staging_buffer_pool.Request(staging_size, MemoryUsage::DeviceLocal);
 
     compute_pass_descriptor_queue.Acquire(scheduler, 2);
     compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, num_vertices);
@@ -345,7 +345,7 @@ std::pair<VkBuffer, VkDeviceSize> QuadIndexedPass::Assemble(
     const u32 num_tri_vertices = (is_strip ? (num_vertices - 2) / 2 : num_vertices / 4) * 6;
 
     const std::size_t staging_size = num_tri_vertices * sizeof(u32);
-    const auto staging = staging_buffer_pool.Request(device, staging_size, MemoryUsage::DeviceLocal);
+    const auto staging = staging_buffer_pool.Request(staging_size, MemoryUsage::DeviceLocal);
 
     compute_pass_descriptor_queue.Acquire(scheduler, 2);
     compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, input_size);

src/video_core/renderer_vulkan/vk_present_manager.cpp

@@ -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.
-            void(std::exchange(lock, std::unique_lock{swapchain_mutex}));
+            std::exchange(lock, std::unique_lock{swapchain_mutex});
             CopyToSwapchain(frame);
 
             // Free the frame for reuse

src/video_core/renderer_vulkan/vk_query_cache.cpp

@@ -852,7 +852,7 @@ public:
 
     void PushUnsyncedQueries() override {
         CloseCounter();
-        auto staging_ref = staging_pool.Request(device,
+        auto staging_ref = staging_pool.Request(
             pending_flush_queries.size() * TFBQueryBank::QUERY_SIZE, MemoryUsage::Download, true);
         size_t offset_base = staging_ref.offset;
         for (auto q : pending_flush_queries) {
@@ -1657,7 +1657,7 @@ void QueryCacheRuntime::SyncValues(std::span<SyncValuesType> values, VkBuffer ba
     impl->copies_setup.clear();
     impl->copies_setup.resize(impl->little_cache.size());
     if constexpr (SyncValuesType::GeneratesBaseBuffer) {
-        ref = impl->staging_pool.Request(impl->device, total_size, MemoryUsage::Upload);
+        ref = impl->staging_pool.Request(total_size, MemoryUsage::Upload);
         size_t current_offset = ref.offset;
         size_t accumulated_size = 0;
         for (size_t i = 0; i < values.size(); i++) {

src/video_core/renderer_vulkan/vk_scheduler.cpp

@@ -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.
-            void(std::exchange(lk, std::unique_lock{execution_mutex}));
+            std::exchange(lk, std::unique_lock{execution_mutex});
 
             // Perform the work, tracking whether the chunk was a submission
             // before executing.

src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp

@@ -25,14 +25,29 @@ namespace {
 
 using namespace Common::Literals;
 
-size_t GetStreamBufferSize(const Device& device, size_t max_stream_buffer_size, size_t max_alignment) {
+// Maximum potential alignment of a Vulkan buffer
+constexpr VkDeviceSize MAX_ALIGNMENT = 256;
+
+// Stream buffer size in bytes
+// *NIX drivers are more sensitive to increased buffers for streaming.
+// Windows ones however, can intake bigger buffers and generally do not OOM.
+// - GTX 960 on Windows will not OOM with 256mib
+// - GT 1030 on ^NIX will OOM with 256mib
+#if defined(__FreeBSD__)
+constexpr VkDeviceSize MAX_STREAM_BUFFER_SIZE = 128_MiB;
+#else
+constexpr VkDeviceSize MAX_STREAM_BUFFER_SIZE = 256_MiB;
+#endif
+
+size_t GetStreamBufferSize(const Device& device) {
     if (!device.HasDebuggingToolAttached()) {
-        return max_stream_buffer_size;
+        return MAX_STREAM_BUFFER_SIZE;
     }
 
     VkDeviceSize size{0};
     bool has_device_local_host_visible_heap{};
-    ForEachDeviceLocalHostVisibleHeap(device, [&size, &has_device_local_host_visible_heap](size_t index, VkMemoryHeap& heap) {
+    ForEachDeviceLocalHostVisibleHeap(device, [&size, &has_device_local_host_visible_heap](
+                                                  size_t index, VkMemoryHeap& heap) {
         has_device_local_host_visible_heap = true;
         size = (std::max)(size, heap.size);
     });
@@ -40,27 +55,28 @@ size_t GetStreamBufferSize(const Device& device, size_t max_stream_buffer_size,
         // If rebar is not supported, cut the max heap size to 40%. This will allow 2 captures to be
         // loaded at the same time in RenderDoc. If rebar is supported, this shouldn't be an issue
         // as the heap will be much larger.
-        if (size <= max_stream_buffer_size) {
+        if (size <= MAX_STREAM_BUFFER_SIZE) {
             size = size * 40 / 100;
         }
     } else {
-        size = max_stream_buffer_size;
+        size = MAX_STREAM_BUFFER_SIZE;
     }
-    return (std::min)(Common::AlignUp(size, max_alignment), max_stream_buffer_size);
+    return (std::min)(Common::AlignUp(size, MAX_ALIGNMENT), MAX_STREAM_BUFFER_SIZE);
 }
 } // Anonymous namespace
 
-StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator_, Scheduler& scheduler_)
-    : memory_allocator{memory_allocator_}, scheduler{scheduler_}
-    , stream_buffer_size{GetStreamBufferSize(device, 256_MiB, 256)}
-{
+StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& memory_allocator_,
+                                     Scheduler& scheduler_)
+    : device{device_}, memory_allocator{memory_allocator_}, scheduler{scheduler_},
+      stream_buffer_size{GetStreamBufferSize(device)}, region_size{stream_buffer_size /
+                                                                   StagingBufferPool::NUM_SYNCS} {
     VkBufferCreateInfo stream_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
         .size = stream_buffer_size,
-        .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT
-            | VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
+        .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT |
+                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
@@ -71,20 +87,7 @@ StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memo
     if (device.IsBufferDeviceAddressSupported()) {
         stream_ci.usage |= VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT;
     }
-    // *BSD drivers are more sensitive to increased buffers for streaming.
-    // Windows ones however, can intake bigger buffers and generally do not OOM.
-    // - GTX 960 on Windows will not OOM with 256mib
-    // - GT 1030 on ^BSD will OOM with 256mib
-    // This doesn't seem to be, however, universally true
-    try {
-        stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
-    } catch (vk::Exception& e) {
-        LOG_ERROR(Render_Vulkan, "Can't fit {} bytes buffer, halving", stream_ci.size);
-        stream_buffer_size = GetStreamBufferSize(device, 128_MiB, 256);
-        stream_ci.size = stream_buffer_size;
-        stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
-    }
-    region_size = stream_buffer_size / StagingBufferPool::NUM_SYNCS;
+    stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
     if (device.HasDebuggingToolAttached()) {
         stream_buffer.SetObjectNameEXT("Stream Buffer");
     }
@@ -97,10 +100,11 @@ StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memo
 
 StagingBufferPool::~StagingBufferPool() = default;
 
-StagingBufferRef StagingBufferPool::Request(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
-    return (!deferred && usage == MemoryUsage::Upload && size <= region_size)
-        ? GetStreamBuffer(device, size)
-        : GetStagingBuffer(device, size, usage, deferred);
+StagingBufferRef StagingBufferPool::Request(size_t size, MemoryUsage usage, bool deferred) {
+    if (!deferred && usage == MemoryUsage::Upload && size <= region_size) {
+        return GetStreamBuffer(size);
+    }
+    return GetStagingBuffer(size, usage, deferred);
 }
 
 void StagingBufferPool::FreeDeferred(StagingBufferRef& ref) {
@@ -123,10 +127,11 @@ void StagingBufferPool::TickFrame() {
     ReleaseCache(MemoryUsage::Download);
 }
 
-StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t size) {
-    if (AreRegionsActive(Region(free_iterator) + 1, (std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
+StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
+    if (AreRegionsActive(Region(free_iterator) + 1,
+                         (std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
         // Avoid waiting for the previous usages to be free
-        return GetStagingBuffer(device, size, MemoryUsage::Upload);
+        return GetStagingBuffer(size, MemoryUsage::Upload);
     }
     const u64 current_tick = scheduler.CurrentTick();
     std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + Region(iterator),
@@ -135,14 +140,15 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t
     free_iterator = (std::max)(free_iterator, iterator + size);
 
     if (iterator + size >= stream_buffer_size) {
-        std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + NUM_SYNCS, current_tick);
+        std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + NUM_SYNCS,
+                  current_tick);
         used_iterator = 0;
         iterator = 0;
         free_iterator = size;
 
         if (AreRegionsActive(0, Region(size) + 1)) {
             // Avoid waiting for the previous usages to be free
-            return GetStagingBuffer(device, size, MemoryUsage::Upload);
+            return GetStagingBuffer(size, MemoryUsage::Upload);
         }
     }
     const size_t offset = iterator;
@@ -150,7 +156,7 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t
     return StagingBufferRef{
         .buffer = *stream_buffer,
         .device_address = stream_buffer_address,
-        .offset = VkDeviceSize(offset),
+        .offset = static_cast<VkDeviceSize>(offset),
         .mapped_span = stream_pointer.subspan(offset, size),
         .usage{},
         .log2_level{},
@@ -160,18 +166,21 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t
 
 bool StagingBufferPool::AreRegionsActive(size_t region_begin, size_t region_end) const {
     const u64 gpu_tick = scheduler.GetMasterSemaphore().KnownGpuTick();
-    return std::any_of(sync_ticks.begin() + region_begin, sync_ticks.begin() + region_end, [gpu_tick](u64 sync_tick) {
-        return gpu_tick < sync_tick;
-    });
+    return std::any_of(sync_ticks.begin() + region_begin, sync_ticks.begin() + region_end,
+                       [gpu_tick](u64 sync_tick) { return gpu_tick < sync_tick; });
 };
 
-StagingBufferRef StagingBufferPool::GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
-    if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred))
+StagingBufferRef StagingBufferPool::GetStagingBuffer(size_t size, MemoryUsage usage,
+                                                     bool deferred) {
+    if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred)) {
         return *ref;
-    return CreateStagingBuffer(device, size, usage, deferred);
+    }
+    return CreateStagingBuffer(size, usage, deferred);
 }
 
-std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t size, MemoryUsage usage, bool deferred) {
+std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t size,
+                                                                        MemoryUsage usage,
+                                                                        bool deferred) {
     StagingBuffers& cache_level = GetCache(usage)[Common::Log2Ceil(size)];
 
     const auto is_free = [this](const StagingBuffer& entry) {
@@ -193,7 +202,7 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s
     return it->Ref();
 }
 
-StagingBufferRef StagingBufferPool::CreateStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
+StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred) {
     auto const log2_size = Common::Log2Ceil<u32>(u32(size));
     VkBufferCreateInfo buffer_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,

src/video_core/renderer_vulkan/vk_staging_buffer_pool.h

@@ -33,10 +33,11 @@ class StagingBufferPool {
 public:
     static constexpr size_t NUM_SYNCS = 16;
 
-    explicit StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator, Scheduler& scheduler);
+    explicit StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator,
+                               Scheduler& scheduler);
     ~StagingBufferPool();
 
-    StagingBufferRef Request(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
+    StagingBufferRef Request(size_t size, MemoryUsage usage, bool deferred = false);
     void FreeDeferred(StagingBufferRef& ref);
 
     [[nodiscard]] VkBuffer StreamBuf() const noexcept {
@@ -83,18 +84,27 @@ private:
     static constexpr size_t NUM_LEVELS = sizeof(size_t) * CHAR_BIT;
     using StagingBuffersCache = std::array<StagingBuffers, NUM_LEVELS>;
 
-    StagingBufferRef GetStreamBuffer(const Device& device, size_t size);
+    StagingBufferRef GetStreamBuffer(size_t size);
+
     bool AreRegionsActive(size_t region_begin, size_t region_end) const;
-    StagingBufferRef GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
-    std::optional<StagingBufferRef> TryGetReservedBuffer(size_t size, MemoryUsage usage, bool deferred);
-    StagingBufferRef CreateStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred);
+
+    StagingBufferRef GetStagingBuffer(size_t size, MemoryUsage usage, bool deferred = false);
+
+    std::optional<StagingBufferRef> TryGetReservedBuffer(size_t size, MemoryUsage usage,
+                                                         bool deferred);
+
+    StagingBufferRef CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred);
+
     StagingBuffersCache& GetCache(MemoryUsage usage);
+
     void ReleaseCache(MemoryUsage usage);
+
     void ReleaseLevel(StagingBuffersCache& cache, size_t log2);
     size_t Region(size_t iter) const noexcept {
         return iter / region_size;
     }
 
+    const Device& device;
     MemoryAllocator& memory_allocator;
     Scheduler& scheduler;
 

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -975,11 +975,11 @@ void TextureCacheRuntime::Finish() {
 }
 
 StagingBufferRef TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.Request(device, size, MemoryUsage::Upload, deferred);
+    return staging_buffer_pool.Request(size, MemoryUsage::Upload, deferred);
 }
 
 StagingBufferRef TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
-    return staging_buffer_pool.Request(device, size, MemoryUsage::Download, deferred);
+    return staging_buffer_pool.Request(size, MemoryUsage::Download, deferred);
 }
 
 void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferRef& ref) {

src/video_core/vulkan_common/vulkan_memory_allocator.cpp

@@ -26,329 +26,350 @@
 #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;
+        [[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;
         }
-        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;
+        [[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{};
         }
-        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 {};
+        [[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 {};
         }
-        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;
+        [[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;
         }
-        return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
-    }
-} // namespace
+
+
+// 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
 
 //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
-    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
+    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() &&
-            memory != VK_NULL_HANDLE) {
-            GPU::Logging::GPULogger::GetInstance().LogMemoryDeallocation(
-                reinterpret_cast<uintptr_t>(memory)
+            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)
             );
         }
+    }
 
-        if (mapped_ptr) {
+    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;
         }
-        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} {
+    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)
+                );
+            }
 
-    // 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);
+            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);
+                        }
                     }
                 }
-            }
-        });
+            });
+        }
     }
-}
 
-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,
+    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),
             .requiredFlags = 0,
-            .preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
-            .memoryTypeBits = 0,
+            .preferredFlags = MemoryUsagePreferredVmaFlags(usage) | anv_flags,
+            .memoryTypeBits = usage == MemoryUsage::Stream ? 0u : valid_memory_types,
             .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));
+        VkBuffer handle{};
+        VmaAllocationInfo alloc_info{};
+        VmaAllocation allocation{};
+        VkMemoryPropertyFlags property_flags{};
 
-    // 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
-        );
-    }
+        vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
+        vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags);
 
-    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),
-        .requiredFlags = 0,
-        .preferredFlags = MemoryUsagePreferredVmaFlags(usage) | anv_flags,
-        .memoryTypeBits = usage == MemoryUsage::Stream ? 0u : valid_memory_types,
-        .pool = VK_NULL_HANDLE,
-        .pUserData = nullptr,
-        .priority = 0.f,
-    };
-
-    VkBuffer handle{};
-    VmaAllocationInfo alloc_info{};
-    VmaAllocation allocation{};
-    VkMemoryPropertyFlags property_flags{};
-
-    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());
-}
-
-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{};
-
-    VkResult res = vmaAllocateMemory(allocator, &reqs, &ci, &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);
-
-        // 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);
+        // 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());
     }
 
-    vk::Check(res);
-    return MemoryCommit(allocator, a, info);
-}
+    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);
 
-MemoryCommit MemoryAllocator::Commit(const vk::Buffer &buffer, MemoryUsage usage) {
-    // Allocate memory appropriate for this buffer automatically
-    const auto vma_usage = MemoryUsageVma(usage);
+        VmaAllocation a{};
+        VmaAllocationInfo info{};
 
-    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;
+        VkResult res = vmaAllocateMemory(allocator, &reqs, &ci, &a, &info);
 
-    const VkBuffer raw = *buffer;
+        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);
 
-    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);
+            // 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);
     }
 
-    vk::Check(res);
-    vk::Check(vmaBindBufferMemory2(allocator, a, 0, raw, nullptr));
-    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

src/yuzu/main_window.cpp

@@ -4796,6 +4796,6 @@ void VolumeButton::ResetMultiplier() {
 #endif
 
 #if !defined(QT_STATICPLUGIN) || defined(__APPLE__)
-#define VMA_IMPLEMENTATION 1
+#define VMA_IMPLEMENTATION
 #include "video_core/vulkan_common/vma.h"
 #endif