Compare commits

..

4 Commits

Author SHA1 Message Date
lizzie d15474ded1 2026-09-05 17:42:18
Signed-off-by: lizzie <lizzie@eden-emu.dev>
2026-09-05 23:57:32 +02:00
lizzie d542dd523c 2026-09-05 17:17:08
Signed-off-by: lizzie <lizzie@eden-emu.dev>
2026-09-05 23:57:32 +02:00
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
54 changed files with 616 additions and 510 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)
{
+2 -1
View File
@@ -3,6 +3,7 @@
cmake_minimum_required(VERSION 3.31) cmake_minimum_required(VERSION 3.31)
set(CMAKE_OSX_DEPLOYMENT_TARGET "15.0" CACHE STRING "macOS deployment target")
project(yuzu) project(yuzu)
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMakeModules") list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/CMakeModules")
@@ -512,7 +513,7 @@ endfunction()
# ============================================= # =============================================
if (APPLE) 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 ${fw} REQUIRED) find_library(${fw}_LIBRARY ${fw} REQUIRED)
list(APPEND PLATFORM_LIBRARIES ${${fw}_LIBRARY}) list(APPEND PLATFORM_LIBRARIES ${${fw}_LIBRARY})
endforeach() endforeach()
+2 -2
View File
@@ -22,9 +22,9 @@ Eden is free, open-source, copyleft software, licensed under the terms of the [G
- No LLM or AI usage, *period*, for patches, pull requests, issues, comments, debugging, brainstorming, etc. - No LLM or AI usage, *period*, for patches, pull requests, issues, comments, debugging, brainstorming, etc.
- For details on why, see the [detailed AI policy](docs/policies/AI.md). - For details on why, see the [detailed AI policy](docs/policies/AI.md).
- Usage of any form of profanity or otherwise unsavory language is prohibited. - Usage of any form of profanity or otherwise unsavory language is generally discouraged.
- This is primarily because it rarely helps to actually understand what's going on. - This is primarily because it rarely helps to actually understand what's going on.
- Remember that your comments should be focused and actually address what's happening. - Remember that your comments should be focused and actually address what's happening. With very few exceptions, expletives are actively detrimental at best.
- New code must follow the same general style as the surrounding codebase. Exceptions may be granted in certain cases. - New code must follow the same general style as the surrounding codebase. Exceptions may be granted in certain cases.
- Maintainers reserve the right to change your patches and pull requests at will. We will try to avoid this. - Maintainers reserve the right to change your patches and pull requests at will. We will try to avoid this.
- You should generally respect all decisions made by the [code owners](docs/CODEOWNERS) in your particular subsystem. - You should generally respect all decisions made by the [code owners](docs/CODEOWNERS) in your particular subsystem.
+5 -10
View File
@@ -1,12 +1,4 @@
{ {
"": {
"ci": true,
"hash": "9f50d993c39529e022ad456163de91ac5934e16faf8fc348f305355fc0a643c534f87ded707e11bd03bcbc0a1760bd20852b6533a67ac0558a078385181cb184",
"name": "SDL3",
"package": "SDL3",
"repo": "crueter-ci/SDL3",
"version": "3.4.14-1788231389-147a8ee32d"
},
"biscuit": { "biscuit": {
"hash": "1229f345b014f7ca544dedb4edb3311e41ba736f9aa9a67f88b5f26f3c983288c6bb6cdedcfb0b8a02c63088a37e6a0d7ba97d9c2a4d721b213916327cffe28a", "hash": "1229f345b014f7ca544dedb4edb3311e41ba736f9aa9a67f88b5f26f3c983288c6bb6cdedcfb0b8a02c63088a37e6a0d7ba97d9c2a4d721b213916327cffe28a",
"min_version": "0.9.1", "min_version": "0.9.1",
@@ -68,10 +60,10 @@
}, },
"discord-rpc": { "discord-rpc": {
"find_args": "MODULE", "find_args": "MODULE",
"hash": "8213c43dcb0f7d479f5861091d111ed12fbdec1e62e6d729d65a4bc181d82f48a35d5fd3cd5c291f2393ac7c9681eabc6b76609755f55376284c8a8d67e148f3", "hash": "8d680b3a16d6f6bf292ad823cf8635595ff986f2a49f758e3009f505b540a9d75194a8cf44cddea75736a8c3e3b5160166e716a0939ce3f18cc463cf648753fe",
"package": "DiscordRPC", "package": "DiscordRPC",
"repo": "eden-emulator/discord-rpc", "repo": "eden-emulator/discord-rpc",
"version": "0d8b2d6a37" "version": "76616d8675"
}, },
"enet": { "enet": {
"find_args": "MODULE", "find_args": "MODULE",
@@ -311,6 +303,9 @@
"find_args": "CONFIG", "find_args": "CONFIG",
"hash": "deb5902ef8db0e329fbd5f3f4385eb0e26bdd9f14f3a2334823fb3fe18f36bc5d235d620d6e5f6fe3551ec3ea7038638899db8778c09f6d5c278f5ff95c3344b", "hash": "deb5902ef8db0e329fbd5f3f4385eb0e26bdd9f14f3a2334823fb3fe18f36bc5d235d620d6e5f6fe3551ec3ea7038638899db8778c09f6d5c278f5ff95c3344b",
"package": "VulkanMemoryAllocator", "package": "VulkanMemoryAllocator",
"patches": [
"0001-macos-clang.patch"
],
"repo": "GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator", "repo": "GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator",
"version": "v3.3.0" "version": "v3.3.0"
}, },
+2 -2
View File
@@ -239,6 +239,6 @@ find ./*/ -name "*.dll" | while read -r dll; do deps "$dll"; done
## RedoxOS ## RedoxOS
Package installs randomly hang at times, you may need to restart it about 3-5 times to complete. Always do `sudo pkg update` or it will hang. Try installing each package individually. The package install may randomly hang at times, in which case it has to be restarted. ALWAYS do a `sudo pkg update` or the chances of it hanging will be close to 90%. If "multiple" installs fail at once, try installing 1 by 1 the packages.
When CMake invokes certain file syscalls - most of the time it causes crashes, and corruptions on the address space. Reboot if there's a freeze over 5 minutes. When CMake invokes certain file syscalls - it may sometimes cause crashes or corruptions on the (kernel?) address space - so reboot the system if there is a "hang" in CMake.
+4 -4
View File
@@ -38,7 +38,7 @@ Pull requests are only to be merged by core developers when properly tested and
- The level of namespacing is generally left to the committer's choice. - The level of namespacing is generally left to the committer's choice.
- However, we never recommend going more than two levels *except* in `hle`, in which case you may go as many as four levels depending on the specificity of your changes. - However, we never recommend going more than two levels *except* in `hle`, in which case you may go as many as four levels depending on the specificity of your changes.
- Occasionally, up to two additional namespaces may be provided for more clarity. - Ocassionally, up to two additional namespaces may be provided for more clarity.
- Changes that affect the entire project (sans CMake changes) should be namespaced as `meta`. - Changes that affect the entire project (sans CMake changes) should be namespaced as `meta`.
- Maintainers are permitted to change namespaces at will. - Maintainers are permitted to change namespaces at will.
- Commits within PRs are not required to be namespaced, but it is highly recommended. - Commits within PRs are not required to be namespaced, but it is highly recommended.
@@ -51,8 +51,8 @@ When adding new settings, use `tr("Setting:")` if the setting is meant to be a f
- Debug settings must never be turned on by default. - Debug settings must never be turned on by default.
- Provide reasonable bounds (for example, a setting controlling the amount of VRAM should never be 0). - Provide reasonable bounds (for example, a setting controlling the amount of VRAM should never be 0).
- The description of the setting must be short and concise, if the setting "does a lot of things" consider splitting the setting into multiple if possible. - The description of the setting must be short and concise, if the setting "does a lot of things" consider splitting the setting into multiple if possible.
- Try to avoid excessive/redundant explanations "recommended for most users and games" can just be "(recommended)". - Try to avoid excessive/redundant explainations "recommended for most users and games" can just be "(recommended)".
- Try to not write "slow/fast" options unless it clearly degrades/increases performance for a given case, as most options may modify behavior that result in different metrics across different systems. If for example the option is an "accuracy" option, writing "High" is sufficient to imply "Slow". No need to write "High (Slow)". - Try to not write "slow/fast" options unless it clearly degrades/increases performance for a given case, as most options may modify behaviour that result in different metrics accross different systems. If for example the option is an "accuracy" option, writing "High" is sufficient to imply "Slow". No need to write "High (Slow)".
Some examples: Some examples:
@@ -91,7 +91,7 @@ You may additionally need the `Qt Extension Pack` extension if building Qt.
# Build speedup # Build speedup
If you have an HDD, use ramdisk (build in RAM); you need about 4GB for a `RelWithDebInfo` build: If you have an HDD, use ramdisk (build in RAM), approximately you need 4GB for a full build with debug symbols:
```sh ```sh
mkdir /tmp/ramdisk mkdir /tmp/ramdisk
+2 -2
View File
@@ -3,9 +3,9 @@
> [!WARNING] > [!WARNING]
> This guide is intended for developers ONLY. If you're looking for configuring the emulator itself, read **[the user handbook](./user/README.md)**. > This guide is intended for developers ONLY. If you're looking for configuring the emulator itself, read **[the user handbook](./user/README.md)**.
Settings have their own dedicated subsystem. Toggles can be added to gate features and fixes, as not all of them apply to every game. Settings on the emulator are very important, toggles and such can be used to guard and/or add branches to paths where some games may crash while others won't, and viceversa.
However, this process can be tedious for those unfamiliar; this document serves as an outline for the settings subsystem. However, this process can be tedious for those unfamiliar; this document serves as an outline/documentation for the settings subsystem.
## Index ## Index
+5 -5
View File
@@ -12,7 +12,7 @@ AMD64, aka x86_64, is the most tested and supported architecture for desktop tar
### Caveats ### Caveats
AMD64 systems are almost always limited by the CPU. For example, a Zen 5/RX 6600 system will often hit max CPU usage before the GPU ever reaches 70% usage, with minimal exceptions (that tend to pop up only at >200fps). JIT is slow. AMD64 systems are almost always limited by the CPU. For example, a Zen 5/RX 6600 system will often hit max CPU usage before the GPU ever reaches 70% usage, with minimal exceptions (that tend to pop up only at >200fps). JIT is slow!
Computers on Linux will almost always run Eden strictly better than an equivalent machine on Windows. This is largely due to the way the Linux kernel handles memory management (and the lack of Microsoft spyware). Computers on Linux will almost always run Eden strictly better than an equivalent machine on Windows. This is largely due to the way the Linux kernel handles memory management (and the lack of Microsoft spyware).
@@ -24,7 +24,7 @@ ARM64, aka aarch64, is the only supported architecture for Android, with limited
### Caveats ### Caveats
NCE (Native Code Execution) is currently only available on Android and (experimentally) Linux. Support for macOS is in the works, but Windows is extremely unlikely to ever happen (if you want it -- submit patches). Generally, if NCE is available, you should pretty much always use it due to the massive performance hit JIT has. NCE (Native Code Execution) is currently only available on Android and (experimentally) Linux. Support for macOS is in the works, but Windows is extremely unlikely to ever happen (if you want it--submit patches!). Generally, if NCE is available, you should pretty much always use it due to the massive performance hit JIT has.
When NCE is enabled, do note that the GPU will almost always be the limiting factor. This is especially the case for Android, as well as desktops that lack dedicated GPUs; Adreno, Mali, PowerVR, etc. GPUs are generally significantly weaker relative to their respective CPUs. When NCE is enabled, do note that the GPU will almost always be the limiting factor. This is especially the case for Android, as well as desktops that lack dedicated GPUs; Adreno, Mali, PowerVR, etc. GPUs are generally significantly weaker relative to their respective CPUs.
@@ -44,7 +44,7 @@ Only Fedora/riscv64 has been tested, but in theory, every riscv64 distribution t
## Other ## Other
Other architectures, such as SPARC, MIPS, PowerPC, Loong, and all 32-bit architectures are completely unsupported, as there is no JIT backend or emitter thereof. If you want support for it -- submit patches. Other architectures, such as SPARC, MIPS, PowerPC, Loong, and all 32-bit architectures are completely unsupported, as there is no JIT backend or emitter thereof. If you want support for it -- submit patches!
IA-64 (Itanium) support is completely unknown. Existing amd64 packages will not run on IA-64 (assuming you can even find a supported Windows/Linux distribution) IA-64 (Itanium) support is completely unknown. Existing amd64 packages will not run on IA-64 (assuming you can even find a supported Windows/Linux distribution)
@@ -106,14 +106,14 @@ Qualcomm Snapdragon SoCs are generally the most well supported.
* A good base to compare to is the Snapdragon 865--e.g. [Tensor vs SD865](https://archive.is/M1P58) * A good base to compare to is the Snapdragon 865--e.g. [Tensor vs SD865](https://archive.is/M1P58)
* Some benchmarks may be misleading due to thermal throttling OR RAM requirements. * Some benchmarks may be misleading due to thermal throttling OR RAM requirements.
- For example, a Pixel 6a (Tensor G1) performs about 1/3 as well as an 865 due to its lack of RAM and poor thermals. - For example, a Pixel 6a (Tensor G1) performs about 1/3 as well as an 865 due to its lack of RAM and poor thermals.
* Remember--always use a cooler if you can, and you MUST have *at least* 8GB of RAM. * Remember--always use a cooler if you can, and you MUST have *at least* 8GB of RAM!
- If you're not sure what SoC you have, check [GSMArena](https://www.gsmarena.com) - e.g. [Pixel 9 Pro](https://archive.ph/91VhA) - If you're not sure what SoC you have, check [GSMArena](https://www.gsmarena.com) - e.g. [Pixel 9 Pro](https://archive.ph/91VhA)
Custom ROMs are recommended, *as long as* you know what you're doing. Custom ROMs are recommended, *as long as* you know what you're doing.
- For most devices, [LineageOS](https://lineageos.org/) is preferred. - For most devices, [LineageOS](https://lineageos.org/) is preferred.
- [CalyxOS](https://calyxos.org/) is available as well. - [CalyxOS](https://calyxos.org/) is available as well.
- For Google Pixel devices ONLY... and [soon another OEM](https://archive.ph/cPpMd)... [GrapheneOS](https://grapheneos.org/) is highly recommended. - For Google Pixel devices ONLY... and [soon another OEM](https://archive.ph/cPpMd)... [GrapheneOS](https://grapheneos.org/) is highly recommended.
* As of October 5, 2025, the Pixel 10 line is unsupported, however, [it will be](https://archive.is/viAUl) in the very near future. * As of October 5, 2025, the Pixel 10 line is unsupported, however, [it will be](https://archive.is/viAUl) in the very near future!
* Keep checking the [FAQ page](https://grapheneos.org/faq#supported-devices) for news. * Keep checking the [FAQ page](https://grapheneos.org/faq#supported-devices) for news.
- Custom ROMs will likely be exclusively recommended in the future due to Google's upcoming [draconian](https://archive.is/hGIjZ), [anti-privacy, anti-user](https://archive.is/mc1CJ) verification requirements. - Custom ROMs will likely be exclusively recommended in the future due to Google's upcoming [draconian](https://archive.is/hGIjZ), [anti-privacy, anti-user](https://archive.is/mc1CJ) verification requirements.
+1
View File
@@ -11,6 +11,7 @@
#include <limits> #include <limits>
#include <span> #include <span>
#include <array> #include <array>
#include <algorithm>
#include <time.h> #include <time.h>
namespace Tz { namespace Tz {
+1
View File
@@ -5,6 +5,7 @@
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#include <string> #include <string>
#include <cstdlib>
#include <string_view> #include <string_view>
#ifdef _WIN32 #ifdef _WIN32
#include <llvm/Demangle/Demangle.h> #include <llvm/Demangle/Demangle.h>
+5 -1
View File
@@ -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-FileCopyrightText: Copyright 2022 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <iterator> #include <iterator>
#include <cstring>
#include "common/make_unique_for_overwrite.h" #include "common/make_unique_for_overwrite.h"
@@ -61,7 +65,7 @@ public:
void resize(size_type size) { void resize(size_type size) {
if (size > buffer_capacity) { if (size > buffer_capacity) {
auto new_buffer = Common::make_unique_for_overwrite<T[]>(size); 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 = std::move(new_buffer);
buffer_capacity = size; buffer_capacity = size;
} }
+1
View File
@@ -10,6 +10,7 @@
#include <functional> #include <functional>
#include <span> #include <span>
#include <string> #include <string>
#include <type_traits>
#include "common/common_types.h" #include "common/common_types.h"
+2 -2
View File
@@ -6,13 +6,13 @@
#include <mutex> #include <mutex>
#include <utility> #include <utility>
#include <type_traits>
#include <boost/asio.hpp> #include <boost/asio.hpp>
#include <boost/version.hpp> #include <boost/version.hpp>
#if BOOST_VERSION > 108400 && (!defined(_WINDOWS) && !defined(__ANDROID__)) || defined(YUZU_BOOST_v1) #if BOOST_VERSION > 108400 && (!defined(_WINDOWS) && !defined(__ANDROID__)) || defined(YUZU_BOOST_v1)
#define USE_BOOST_v1 #define USE_BOOST_v1
#endif #endif
#ifdef USE_BOOST_v1 #ifdef USE_BOOST_v1
#include <boost/process/v1/async_pipe.hpp> #include <boost/process/v1/async_pipe.hpp>
#else #else
+2 -1
View File
@@ -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-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -6,6 +6,7 @@
#pragma once #pragma once
#include <type_traits>
#include "common/common_funcs.h" #include "common/common_funcs.h"
namespace FileSys { namespace FileSys {
@@ -7,6 +7,7 @@
#pragma once #pragma once
#include <optional> #include <optional>
#include <type_traits>
#include "common/literals.h" #include "common/literals.h"
#include "core/file_sys/fssystem/fs_i_storage.h" #include "core/file_sys/fssystem/fs_i_storage.h"
@@ -4,6 +4,7 @@
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#include <type_traits>
#include "core/file_sys/errors.h" #include "core/file_sys/errors.h"
#include "core/file_sys/fssystem/fssystem_bucket_tree.h" #include "core/file_sys/fssystem/fssystem_bucket_tree.h"
#include "core/file_sys/fssystem/fssystem_bucket_tree_utils.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-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <mutex> #include <mutex>
#include <type_traits>
#include "common/alignment.h" #include "common/alignment.h"
#include "common/common_funcs.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-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -6,6 +6,7 @@
#pragma once #pragma once
#include <type_traits>
#include "core/file_sys/errors.h" #include "core/file_sys/errors.h"
#include "core/file_sys/fssystem/fssystem_bucket_tree.h" #include "core/file_sys/fssystem/fssystem_bucket_tree.h"
#include "core/file_sys/fssystem/fssystem_bucket_tree_utils.h" #include "core/file_sys/fssystem/fssystem_bucket_tree_utils.h"
@@ -6,6 +6,8 @@
#pragma once #pragma once
#include <type_traits>
#include <cstddef>
#include "common/literals.h" #include "common/literals.h"
#include "core/file_sys/errors.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-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <type_traits>
#include "common/alignment.h" #include "common/alignment.h"
#include "core/file_sys/fssystem/fs_i_storage.h" #include "core/file_sys/fssystem/fs_i_storage.h"
#include "core/file_sys/fssystem/fs_types.h" #include "core/file_sys/fssystem/fs_types.h"
@@ -6,6 +6,9 @@
#pragma once #pragma once
#include <type_traits>
#include <array>
#include <cstddef>
#include "core/file_sys/errors.h" #include "core/file_sys/errors.h"
#include "core/file_sys/fssystem/fs_i_storage.h" #include "core/file_sys/fssystem/fs_i_storage.h"
#include "core/file_sys/fssystem/fssystem_bucket_tree.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-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <optional> #include <optional>
#include <array>
#include <cstddef>
#include <type_traits>
#include "core/file_sys/fssystem/fs_i_storage.h" #include "core/file_sys/fssystem/fs_i_storage.h"
#include "core/file_sys/fssystem/fs_types.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-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@@ -6,6 +6,8 @@
#pragma once #pragma once
#include <type_traits>
#include <cstddef>
#include "core/file_sys/fssystem/fssystem_compression_common.h" #include "core/file_sys/fssystem/fssystem_compression_common.h"
#include "core/file_sys/fssystem/fssystem_nca_header.h" #include "core/file_sys/fssystem/fssystem_nca_header.h"
#include "core/file_sys/vfs/vfs.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-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <type_traits>
#include <array>
#include <cstddef>
#include "common/common_funcs.h" #include "common/common_funcs.h"
#include "common/common_types.h" #include "common/common_types.h"
#include "common/literals.h" #include "common/literals.h"
+1
View File
@@ -7,6 +7,7 @@
#pragma once #pragma once
#include <memory> #include <memory>
#include <type_traits>
#include "common/common_funcs.h" #include "common/common_funcs.h"
#include "common/page_table.h" #include "common/page_table.h"
+1
View File
@@ -6,6 +6,7 @@
#pragma once #pragma once
#include <type_traits>
#include "common/assert.h" #include "common/assert.h"
#include "common/bit_field.h" #include "common/bit_field.h"
#include "common/common_funcs.h" #include "common/common_funcs.h"
+4
View File
@@ -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-FileCopyrightText: Copyright 2024 yuzu Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later // SPDX-License-Identifier: GPL-3.0-or-later
#pragma once #pragma once
#include <array> #include <array>
#include <type_traits>
#include <functional> #include <functional>
#include "common/common_funcs.h" #include "common/common_funcs.h"
+8 -26
View File
@@ -175,19 +175,10 @@ Result AlbumManager::LoadAlbumScreenShotImage(LoadAlbumScreenShotImageOutput& ou
return ResultIsNotMounted; return ResultIsNotMounted;
} }
out_image_output = { out_image_output = {};
.width = 1280, out_image_output.width = 1280;
.height = 720, out_image_output.height = 720;
.attribute = out_image_output.attribute.orientation = AlbumImageOrientation::None;
{
.unknown_0{},
.orientation = AlbumImageOrientation::None,
.unknown_1{},
.unknown_2{},
.pad163{},
},
.pad179{},
};
std::filesystem::path path; std::filesystem::path path;
const auto result = GetFile(path, file_id); const auto result = GetFile(path, file_id);
@@ -211,19 +202,10 @@ Result AlbumManager::LoadAlbumScreenShotThumbnail(
return ResultIsNotMounted; return ResultIsNotMounted;
} }
out_image_output = { out_image_output = {};
.width = 320, out_image_output.width = 320;
.height = 180, out_image_output.height = 180;
.attribute = out_image_output.attribute.orientation = AlbumImageOrientation::None;
{
.unknown_0{},
.orientation = AlbumImageOrientation::None,
.unknown_1{},
.unknown_2{},
.pad163{},
},
.pad179{},
};
std::filesystem::path path; std::filesystem::path path;
const auto result = GetFile(path, file_id); const auto result = GetFile(path, file_id);
+2 -7
View File
@@ -73,13 +73,8 @@ void IScreenShotApplicationService::CaptureAndSaveScreenshot(AlbumReportOption r
Layout::FramebufferLayout layout = Layout::FramebufferLayout layout =
Layout::DefaultFrameLayout(screenshot_width, screenshot_height); Layout::DefaultFrameLayout(screenshot_width, screenshot_height);
const Capture::ScreenShotAttribute attribute{ Capture::ScreenShotAttribute attribute{};
.unknown_0{}, attribute.orientation = Capture::AlbumImageOrientation::None;
.orientation = Capture::AlbumImageOrientation::None,
.unknown_1{},
.unknown_2{},
.pad163{},
};
renderer.RequestScreenshot( renderer.RequestScreenshot(
image_data.data(), image_data.data(),
+4
View File
@@ -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-FileCopyrightText: Copyright 2018 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <type_traits>
#include "common/common_funcs.h" #include "common/common_funcs.h"
#include "common/common_types.h" #include "common/common_types.h"
+2 -1
View File
@@ -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-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
@@ -6,6 +6,7 @@
#pragma once #pragma once
#include <type_traits>
#include <fmt/ranges.h> #include <fmt/ranges.h>
#include "common/common_funcs.h" #include "common/common_funcs.h"
+1
View File
@@ -8,6 +8,7 @@
#include <array> #include <array>
#include <chrono> #include <chrono>
#include <type_traits>
#include <fmt/ranges.h> #include <fmt/ranges.h>
#include "common/common_types.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-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <array> #include <array>
#include <type_traits>
#include "common/common_types.h" #include "common/common_types.h"
#include "core/hle/service/psc/time/common.h" #include "core/hle/service/psc/time/common.h"
@@ -7,6 +7,7 @@
#pragma once #pragma once
#include <array> #include <array>
#include <type_traits>
#include "common/bit_field.h" #include "common/bit_field.h"
#include "common/common_funcs.h" #include "common/common_funcs.h"
+7
View File
@@ -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-FileCopyrightText: Copyright 2021 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <cstddef>
#include <array>
#include <type_traits>
#include "common/bit_field.h" #include "common/bit_field.h"
#include "common/common_funcs.h" #include "common/common_funcs.h"
#include "common/common_types.h" #include "common/common_types.h"
+53 -51
View File
@@ -6,55 +6,6 @@
add_library(shader_recompiler STATIC add_library(shader_recompiler STATIC
backend/bindings.h 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.cpp
backend/spirv/emit_spirv.h backend/spirv/emit_spirv.h
backend/spirv/emit_spirv_atomic.cpp backend/spirv/emit_spirv_atomic.cpp
@@ -239,9 +190,60 @@ add_library(shader_recompiler STATIC
program_header.h program_header.h
runtime_info.h runtime_info.h
shader_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) 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) { void JoinStorageInfo(Info& base, Info& source) {
auto& descriptors = base.storage_buffers_descriptors; auto& descriptors = base.storage_buffers_descriptors;
for (auto& desc : source.storage_buffers_descriptors) { for (auto& desc : source.storage_buffers_descriptors) {
+1
View File
@@ -8,6 +8,7 @@
#include <array> #include <array>
#include <vector> #include <vector>
#include <type_traits>
#include "common/bit_field.h" #include "common/bit_field.h"
#include "common/common_funcs.h" #include "common/common_funcs.h"
+7
View File
@@ -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-FileCopyrightText: Copyright 2020 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <array>
#include <cstddef>
#include <type_traits>
#include "common/bit_field.h" #include "common/bit_field.h"
#include "common/common_funcs.h" #include "common/common_funcs.h"
#include "common/common_types.h" #include "common/common_types.h"
+1
View File
@@ -7,6 +7,7 @@
#pragma once #pragma once
#include <memory> #include <memory>
#include <type_traits>
#include "common/common_types.h" #include "common/common_types.h"
#include "common/scratch_buffer.h" #include "common/scratch_buffer.h"
@@ -148,11 +148,11 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_,
} }
StagingBufferMap BufferCacheRuntime::UploadStagingBuffer(size_t size) { StagingBufferMap BufferCacheRuntime::UploadStagingBuffer(size_t size) {
return staging_buffer_pool.RequestUploadBuffer(size); return staging_buffer_pool.RequestUploadBuffer(device, size);
} }
StagingBufferMap BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) { StagingBufferMap BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
return staging_buffer_pool.RequestDownloadBuffer(size, deferred); return staging_buffer_pool.RequestDownloadBuffer(device, size, deferred);
} }
void BufferCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) { void BufferCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) {
@@ -557,11 +557,11 @@ void TextureCacheRuntime::Finish() {
} }
StagingBufferMap TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) { StagingBufferMap TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) {
return staging_buffer_pool.RequestUploadBuffer(size); return staging_buffer_pool.RequestUploadBuffer(device, size);
} }
StagingBufferMap TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) { StagingBufferMap TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
return staging_buffer_pool.RequestDownloadBuffer(size, deferred); return staging_buffer_pool.RequestDownloadBuffer(device, size, deferred);
} }
void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) { void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferMap& buffer) {
@@ -192,7 +192,7 @@ public:
if (host_visible) { if (host_visible) {
return StagingBufferRef{}; return StagingBufferRef{};
} }
return staging_pool.Request(size_bytes, MemoryUsage::Upload); return staging_pool.Request(device, size_bytes, MemoryUsage::Upload);
}(); }();
u8* staging_data = host_visible ? buffer.Mapped().data() : staging.mapped_span.data(); 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) { StagingBufferRef BufferCacheRuntime::UploadStagingBuffer(size_t size) {
return staging_pool.Request(size, MemoryUsage::Upload); return staging_pool.Request(device, size, MemoryUsage::Upload);
} }
StagingBufferRef BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) { StagingBufferRef BufferCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
return staging_pool.Request(size, MemoryUsage::Download, deferred); return staging_pool.Request(device, size, MemoryUsage::Download, deferred);
} }
VkFormat BufferCacheRuntime::TexelBufferFormat(VideoCore::Surface::PixelFormat format) const { VkFormat BufferCacheRuntime::TexelBufferFormat(VideoCore::Surface::PixelFormat format) const {
@@ -149,7 +149,7 @@ public:
std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t stage, std::span<u8> BindMappedUniformBuffer([[maybe_unused]] size_t stage,
[[maybe_unused]] u32 binding_index, [[maybe_unused]] u32 binding_index,
u32 size) { u32 size) {
const StagingBufferRef ref = staging_pool.Request(size, MemoryUsage::Upload); const StagingBufferRef ref = staging_pool.Request(device, size, MemoryUsage::Upload);
guest_descriptor_queue.AddBuffer(ref.buffer, ref.device_address, guest_descriptor_queue.AddBuffer(ref.buffer, ref.device_address,
static_cast<u32>(ref.offset), size); static_cast<u32>(ref.offset), size);
return ref.mapped_span; return ref.mapped_span;
@@ -287,7 +287,7 @@ Uint8Pass::~Uint8Pass() = default;
std::pair<VkBuffer, VkDeviceSize> Uint8Pass::Assemble(u32 num_vertices, VkBuffer src_buffer, std::pair<VkBuffer, VkDeviceSize> Uint8Pass::Assemble(u32 num_vertices, VkBuffer src_buffer,
u32 src_offset) { u32 src_offset) {
const u32 staging_size = static_cast<u32>(num_vertices * sizeof(u16)); const u32 staging_size = static_cast<u32>(num_vertices * sizeof(u16));
const auto staging = staging_buffer_pool.Request(staging_size, MemoryUsage::DeviceLocal); const auto staging = staging_buffer_pool.Request(device, staging_size, MemoryUsage::DeviceLocal);
compute_pass_descriptor_queue.Acquire(scheduler, 2); compute_pass_descriptor_queue.Acquire(scheduler, 2);
compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, num_vertices); 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 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 std::size_t staging_size = num_tri_vertices * sizeof(u32);
const auto staging = staging_buffer_pool.Request(staging_size, MemoryUsage::DeviceLocal); const auto staging = staging_buffer_pool.Request(device, staging_size, MemoryUsage::DeviceLocal);
compute_pass_descriptor_queue.Acquire(scheduler, 2); compute_pass_descriptor_queue.Acquire(scheduler, 2);
compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, input_size); compute_pass_descriptor_queue.AddBuffer(src_buffer, src_offset, input_size);
@@ -338,7 +338,7 @@ void PresentManager::PresentThread(std::stop_token token) {
// By exchanging the lock ownership we take the swapchain lock // By exchanging the lock ownership we take the swapchain lock
// before the queue lock goes out of scope. This way the swapchain // before the queue lock goes out of scope. This way the swapchain
// lock in WaitPresent is guaranteed to occur after here. // 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); CopyToSwapchain(frame);
// Free the frame for reuse // Free the frame for reuse
@@ -852,7 +852,7 @@ public:
void PushUnsyncedQueries() override { void PushUnsyncedQueries() override {
CloseCounter(); CloseCounter();
auto staging_ref = staging_pool.Request( auto staging_ref = staging_pool.Request(device,
pending_flush_queries.size() * TFBQueryBank::QUERY_SIZE, MemoryUsage::Download, true); pending_flush_queries.size() * TFBQueryBank::QUERY_SIZE, MemoryUsage::Download, true);
size_t offset_base = staging_ref.offset; size_t offset_base = staging_ref.offset;
for (auto q : pending_flush_queries) { 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.clear();
impl->copies_setup.resize(impl->little_cache.size()); impl->copies_setup.resize(impl->little_cache.size());
if constexpr (SyncValuesType::GeneratesBaseBuffer) { if constexpr (SyncValuesType::GeneratesBaseBuffer) {
ref = impl->staging_pool.Request(total_size, MemoryUsage::Upload); ref = impl->staging_pool.Request(impl->device, total_size, MemoryUsage::Upload);
size_t current_offset = ref.offset; size_t current_offset = ref.offset;
size_t accumulated_size = 0; size_t accumulated_size = 0;
for (size_t i = 0; i < values.size(); i++) { for (size_t i = 0; i < values.size(); i++) {
@@ -300,7 +300,7 @@ void Scheduler::WorkerThread(std::stop_token stop_token) {
// Exchange lock ownership so that we take the execution lock before // Exchange lock ownership so that we take the execution lock before
// the queue lock goes out of scope. This allows us to force execution // the queue lock goes out of scope. This allows us to force execution
// to complete in the next step. // 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 // Perform the work, tracking whether the chunk was a submission
// before executing. // before executing.
@@ -25,29 +25,14 @@ namespace {
using namespace Common::Literals; using namespace Common::Literals;
// Maximum potential alignment of a Vulkan buffer size_t GetStreamBufferSize(const Device& device, size_t max_stream_buffer_size, size_t max_alignment) {
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()) { if (!device.HasDebuggingToolAttached()) {
return MAX_STREAM_BUFFER_SIZE; return max_stream_buffer_size;
} }
VkDeviceSize size{0}; VkDeviceSize size{0};
bool has_device_local_host_visible_heap{}; bool has_device_local_host_visible_heap{};
ForEachDeviceLocalHostVisibleHeap(device, [&size, &has_device_local_host_visible_heap]( ForEachDeviceLocalHostVisibleHeap(device, [&size, &has_device_local_host_visible_heap](size_t index, VkMemoryHeap& heap) {
size_t index, VkMemoryHeap& heap) {
has_device_local_host_visible_heap = true; has_device_local_host_visible_heap = true;
size = (std::max)(size, heap.size); size = (std::max)(size, heap.size);
}); });
@@ -55,28 +40,27 @@ size_t GetStreamBufferSize(const Device& device) {
// If rebar is not supported, cut the max heap size to 40%. This will allow 2 captures to be // 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 // loaded at the same time in RenderDoc. If rebar is supported, this shouldn't be an issue
// as the heap will be much larger. // as the heap will be much larger.
if (size <= MAX_STREAM_BUFFER_SIZE) { if (size <= max_stream_buffer_size) {
size = size * 40 / 100; size = size * 40 / 100;
} }
} else { } 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 } // Anonymous namespace
StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& memory_allocator_, StagingBufferPool::StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator_, Scheduler& scheduler_)
Scheduler& scheduler_) : memory_allocator{memory_allocator_}, scheduler{scheduler_}
: device{device_}, memory_allocator{memory_allocator_}, scheduler{scheduler_}, , stream_buffer_size{GetStreamBufferSize(device, 256_MiB, 256)}
stream_buffer_size{GetStreamBufferSize(device)}, region_size{stream_buffer_size / {
StagingBufferPool::NUM_SYNCS} {
VkBufferCreateInfo stream_ci = { VkBufferCreateInfo stream_ci = {
.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
.pNext = nullptr, .pNext = nullptr,
.flags = 0, .flags = 0,
.size = stream_buffer_size, .size = stream_buffer_size,
.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_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, | VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
.sharingMode = VK_SHARING_MODE_EXCLUSIVE, .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
.queueFamilyIndexCount = 0, .queueFamilyIndexCount = 0,
.pQueueFamilyIndices = nullptr, .pQueueFamilyIndices = nullptr,
@@ -87,7 +71,20 @@ StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& mem
if (device.IsBufferDeviceAddressSupported()) { if (device.IsBufferDeviceAddressSupported()) {
stream_ci.usage |= VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT; stream_ci.usage |= VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT;
} }
stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream); // *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;
if (device.HasDebuggingToolAttached()) { if (device.HasDebuggingToolAttached()) {
stream_buffer.SetObjectNameEXT("Stream Buffer"); stream_buffer.SetObjectNameEXT("Stream Buffer");
} }
@@ -100,11 +97,10 @@ StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& mem
StagingBufferPool::~StagingBufferPool() = default; StagingBufferPool::~StagingBufferPool() = default;
StagingBufferRef StagingBufferPool::Request(size_t size, MemoryUsage usage, bool deferred) { StagingBufferRef StagingBufferPool::Request(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
if (!deferred && usage == MemoryUsage::Upload && size <= region_size) { return (!deferred && usage == MemoryUsage::Upload && size <= region_size)
return GetStreamBuffer(size); ? GetStreamBuffer(device, size)
} : GetStagingBuffer(device, size, usage, deferred);
return GetStagingBuffer(size, usage, deferred);
} }
void StagingBufferPool::FreeDeferred(StagingBufferRef& ref) { void StagingBufferPool::FreeDeferred(StagingBufferRef& ref) {
@@ -127,11 +123,10 @@ void StagingBufferPool::TickFrame() {
ReleaseCache(MemoryUsage::Download); ReleaseCache(MemoryUsage::Download);
} }
StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) { StagingBufferRef StagingBufferPool::GetStreamBuffer(const Device& device, size_t size) {
if (AreRegionsActive(Region(free_iterator) + 1, if (AreRegionsActive(Region(free_iterator) + 1, (std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
(std::min)(Region(iterator + size) + 1, NUM_SYNCS))) {
// Avoid waiting for the previous usages to be free // Avoid waiting for the previous usages to be free
return GetStagingBuffer(size, MemoryUsage::Upload); return GetStagingBuffer(device, size, MemoryUsage::Upload);
} }
const u64 current_tick = scheduler.CurrentTick(); const u64 current_tick = scheduler.CurrentTick();
std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + Region(iterator), std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + Region(iterator),
@@ -140,15 +135,14 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
free_iterator = (std::max)(free_iterator, iterator + size); free_iterator = (std::max)(free_iterator, iterator + size);
if (iterator + size >= stream_buffer_size) { if (iterator + size >= stream_buffer_size) {
std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + NUM_SYNCS, std::fill(sync_ticks.begin() + Region(used_iterator), sync_ticks.begin() + NUM_SYNCS, current_tick);
current_tick);
used_iterator = 0; used_iterator = 0;
iterator = 0; iterator = 0;
free_iterator = size; free_iterator = size;
if (AreRegionsActive(0, Region(size) + 1)) { if (AreRegionsActive(0, Region(size) + 1)) {
// Avoid waiting for the previous usages to be free // Avoid waiting for the previous usages to be free
return GetStagingBuffer(size, MemoryUsage::Upload); return GetStagingBuffer(device, size, MemoryUsage::Upload);
} }
} }
const size_t offset = iterator; const size_t offset = iterator;
@@ -156,7 +150,7 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
return StagingBufferRef{ return StagingBufferRef{
.buffer = *stream_buffer, .buffer = *stream_buffer,
.device_address = stream_buffer_address, .device_address = stream_buffer_address,
.offset = static_cast<VkDeviceSize>(offset), .offset = VkDeviceSize(offset),
.mapped_span = stream_pointer.subspan(offset, size), .mapped_span = stream_pointer.subspan(offset, size),
.usage{}, .usage{},
.log2_level{}, .log2_level{},
@@ -166,21 +160,18 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
bool StagingBufferPool::AreRegionsActive(size_t region_begin, size_t region_end) const { bool StagingBufferPool::AreRegionsActive(size_t region_begin, size_t region_end) const {
const u64 gpu_tick = scheduler.GetMasterSemaphore().KnownGpuTick(); const u64 gpu_tick = scheduler.GetMasterSemaphore().KnownGpuTick();
return std::any_of(sync_ticks.begin() + region_begin, sync_ticks.begin() + region_end, return std::any_of(sync_ticks.begin() + region_begin, sync_ticks.begin() + region_end, [gpu_tick](u64 sync_tick) {
[gpu_tick](u64 sync_tick) { return gpu_tick < sync_tick; }); return gpu_tick < sync_tick;
});
}; };
StagingBufferRef StagingBufferPool::GetStagingBuffer(size_t size, MemoryUsage usage, StagingBufferRef StagingBufferPool::GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
bool deferred) { if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred))
if (const std::optional<StagingBufferRef> ref = TryGetReservedBuffer(size, usage, deferred)) {
return *ref; return *ref;
} return CreateStagingBuffer(device, size, usage, deferred);
return CreateStagingBuffer(size, usage, deferred);
} }
std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t size, std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t size, MemoryUsage usage, bool deferred) {
MemoryUsage usage,
bool deferred) {
StagingBuffers& cache_level = GetCache(usage)[Common::Log2Ceil(size)]; StagingBuffers& cache_level = GetCache(usage)[Common::Log2Ceil(size)];
const auto is_free = [this](const StagingBuffer& entry) { const auto is_free = [this](const StagingBuffer& entry) {
@@ -202,7 +193,7 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s
return it->Ref(); return it->Ref();
} }
StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred) { StagingBufferRef StagingBufferPool::CreateStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred) {
auto const log2_size = Common::Log2Ceil<u32>(u32(size)); auto const log2_size = Common::Log2Ceil<u32>(u32(size));
VkBufferCreateInfo buffer_ci = { VkBufferCreateInfo buffer_ci = {
.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
@@ -33,11 +33,10 @@ class StagingBufferPool {
public: public:
static constexpr size_t NUM_SYNCS = 16; static constexpr size_t NUM_SYNCS = 16;
explicit StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator, explicit StagingBufferPool(const Device& device, MemoryAllocator& memory_allocator, Scheduler& scheduler);
Scheduler& scheduler);
~StagingBufferPool(); ~StagingBufferPool();
StagingBufferRef Request(size_t size, MemoryUsage usage, bool deferred = false); StagingBufferRef Request(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
void FreeDeferred(StagingBufferRef& ref); void FreeDeferred(StagingBufferRef& ref);
[[nodiscard]] VkBuffer StreamBuf() const noexcept { [[nodiscard]] VkBuffer StreamBuf() const noexcept {
@@ -84,27 +83,18 @@ private:
static constexpr size_t NUM_LEVELS = sizeof(size_t) * CHAR_BIT; static constexpr size_t NUM_LEVELS = sizeof(size_t) * CHAR_BIT;
using StagingBuffersCache = std::array<StagingBuffers, NUM_LEVELS>; using StagingBuffersCache = std::array<StagingBuffers, NUM_LEVELS>;
StagingBufferRef GetStreamBuffer(size_t size); StagingBufferRef GetStreamBuffer(const Device& device, size_t size);
bool AreRegionsActive(size_t region_begin, size_t region_end) const; bool AreRegionsActive(size_t region_begin, size_t region_end) const;
StagingBufferRef GetStagingBuffer(const Device& device, size_t size, MemoryUsage usage, bool deferred = false);
StagingBufferRef GetStagingBuffer(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);
std::optional<StagingBufferRef> TryGetReservedBuffer(size_t size, MemoryUsage usage,
bool deferred);
StagingBufferRef CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred);
StagingBuffersCache& GetCache(MemoryUsage usage); StagingBuffersCache& GetCache(MemoryUsage usage);
void ReleaseCache(MemoryUsage usage); void ReleaseCache(MemoryUsage usage);
void ReleaseLevel(StagingBuffersCache& cache, size_t log2); void ReleaseLevel(StagingBuffersCache& cache, size_t log2);
size_t Region(size_t iter) const noexcept { size_t Region(size_t iter) const noexcept {
return iter / region_size; return iter / region_size;
} }
const Device& device;
MemoryAllocator& memory_allocator; MemoryAllocator& memory_allocator;
Scheduler& scheduler; Scheduler& scheduler;
@@ -975,11 +975,11 @@ void TextureCacheRuntime::Finish() {
} }
StagingBufferRef TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) { StagingBufferRef TextureCacheRuntime::UploadStagingBuffer(size_t size, bool deferred) {
return staging_buffer_pool.Request(size, MemoryUsage::Upload, deferred); return staging_buffer_pool.Request(device, size, MemoryUsage::Upload, deferred);
} }
StagingBufferRef TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) { StagingBufferRef TextureCacheRuntime::DownloadStagingBuffer(size_t size, bool deferred) {
return staging_buffer_pool.Request(size, MemoryUsage::Download, deferred); return staging_buffer_pool.Request(device, size, MemoryUsage::Download, deferred);
} }
void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferRef& ref) { void TextureCacheRuntime::FreeDeferredStagingBuffer(StagingBufferRef& ref) {
@@ -26,350 +26,329 @@
#include "common/settings.h" #include "common/settings.h"
namespace Vulkan { namespace Vulkan {
namespace { namespace {
// Helpers translating MemoryUsage to flags/usage // Helpers translating MemoryUsage to flags/usage
[[maybe_unused]] VkMemoryPropertyFlags MemoryUsagePropertyFlags(MemoryUsage usage) { [[maybe_unused]] VkMemoryPropertyFlags MemoryUsagePropertyFlags(MemoryUsage usage) {
switch (usage) { switch (usage) {
case MemoryUsage::DeviceLocal: case MemoryUsage::DeviceLocal:
return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT; return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
case MemoryUsage::Upload: case MemoryUsage::Upload:
return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
VK_MEMORY_PROPERTY_HOST_COHERENT_BIT; VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
case MemoryUsage::Download: case MemoryUsage::Download:
return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
VK_MEMORY_PROPERTY_HOST_COHERENT_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
VK_MEMORY_PROPERTY_HOST_CACHED_BIT; VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
case MemoryUsage::Stream: case MemoryUsage::Stream:
return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT | return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT |
VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
VK_MEMORY_PROPERTY_HOST_COHERENT_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) { [[nodiscard]] VkMemoryPropertyFlags MemoryUsagePreferredVmaFlags(MemoryUsage usage) {
if (usage == MemoryUsage::Download) { if (usage == MemoryUsage::Download) {
return VK_MEMORY_PROPERTY_HOST_CACHED_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT; 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) { [[nodiscard]] VmaAllocationCreateFlags MemoryUsageVmaFlags(MemoryUsage usage) {
switch (usage) { switch (usage) {
case MemoryUsage::Upload: case MemoryUsage::Upload:
case MemoryUsage::Stream: case MemoryUsage::Stream:
return VMA_ALLOCATION_CREATE_MAPPED_BIT | return VMA_ALLOCATION_CREATE_MAPPED_BIT |
VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT; VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
case MemoryUsage::Download: case MemoryUsage::Download:
return VMA_ALLOCATION_CREATE_MAPPED_BIT | return VMA_ALLOCATION_CREATE_MAPPED_BIT |
VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT; VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
case MemoryUsage::DeviceLocal: case MemoryUsage::DeviceLocal:
return {}; return {};
}
return {};
} }
return {};
}
[[nodiscard]] VmaMemoryUsage MemoryUsageVma(MemoryUsage usage) { [[nodiscard]] VmaMemoryUsage MemoryUsageVma(MemoryUsage usage) {
switch (usage) { switch (usage) {
case MemoryUsage::DeviceLocal: case MemoryUsage::DeviceLocal:
case MemoryUsage::Stream: case MemoryUsage::Stream:
return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE; return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
case MemoryUsage::Upload: case MemoryUsage::Upload:
case MemoryUsage::Download: case MemoryUsage::Download:
return VMA_MEMORY_USAGE_AUTO_PREFER_HOST; return VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
}
return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
} }
return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
}
// This avoids calling vkGetBufferMemoryRequirements* directly. } // namespace
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 is now VMA-backed
MemoryCommit::MemoryCommit(VmaAllocator alloc, VmaAllocation a, MemoryCommit::MemoryCommit(VmaAllocator alloc, VmaAllocation a,
const VmaAllocationInfo &info) noexcept const VmaAllocationInfo &info) noexcept
: allocator{alloc}, allocation{a}, memory{info.deviceMemory}, : allocator{alloc}, allocation{a}, memory{info.deviceMemory},
offset{info.offset}, size{info.size}, mapped_ptr{info.pMappedData} { offset{info.offset}, size{info.size}, mapped_ptr{info.pMappedData} {
// Log GPU memory allocation // 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() && if (GPU::Logging::IsActive() &&
Settings::values.gpu_log_memory_tracking.GetValue()) { Settings::values.gpu_log_memory_tracking.GetValue() &&
GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation( memory != VK_NULL_HANDLE) {
reinterpret_cast<uintptr_t>(memory), GPU::Logging::GPULogger::GetInstance().LogMemoryDeallocation(
static_cast<u64>(size), reinterpret_cast<uintptr_t>(memory)
0 // Memory property flags (not easily available from VMA)
); );
} }
}
MemoryCommit::~MemoryCommit() { Release(); } if (mapped_ptr) {
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); vmaUnmapMemory(allocator, allocation);
mapped_ptr = nullptr; mapped_ptr = nullptr;
} }
vmaFreeMemory(allocator, allocation);
} }
allocation = nullptr;
allocator = nullptr;
memory = VK_NULL_HANDLE;
offset = 0;
size = 0;
}
void MemoryCommit::Release() { MemoryAllocator::MemoryAllocator(const Device &device_)
if (allocation && allocator) { : device{device_}, allocator{device.GetAllocator()},
// Log GPU memory deallocation properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
if (GPU::Logging::IsActive() && buffer_image_granularity{
Settings::values.gpu_log_memory_tracking.GetValue() && device_.GetPhysical().GetProperties().limits.bufferImageGranularity} {
memory != VK_NULL_HANDLE) {
GPU::Logging::GPULogger::GetInstance().LogMemoryDeallocation(
reinterpret_cast<uintptr_t>(memory)
);
}
if (mapped_ptr) { // Preserve the previous "RenderDoc small heap" trimming behavior that we had in original vma minus the heap bug
vmaUnmapMemory(allocator, allocation); if (device.HasDebuggingToolAttached())
mapped_ptr = nullptr; {
} using namespace Common::Literals;
vmaFreeMemory(allocator, allocation); ForEachDeviceLocalHostVisibleHeap(device, [this](size_t heap_idx, VkMemoryHeap &heap) {
} if (heap.size <= 256_MiB) {
allocation = nullptr; for (u32 t = 0; t < properties.memoryTypeCount; ++t) {
allocator = nullptr; if (properties.memoryTypes[t].heapIndex == heap_idx) {
memory = VK_NULL_HANDLE; valid_memory_types &= ~(1u << t);
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 vk::Image MemoryAllocator::CreateImage(const VkImageCreateInfo &ci) const
{ {
const VmaAllocationCreateInfo alloc_ci = { const VmaAllocationCreateInfo alloc_ci = {
.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT, .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT,
.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE, .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, .requiredFlags = 0,
.preferredFlags = MemoryUsagePreferredVmaFlags(usage) | anv_flags, .preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
.memoryTypeBits = usage == MemoryUsage::Stream ? 0u : valid_memory_types, .memoryTypeBits = 0,
.pool = VK_NULL_HANDLE, .pool = VK_NULL_HANDLE,
.pUserData = nullptr, .pUserData = nullptr,
.priority = 0.f, .priority = 0.f,
}; };
VkBuffer handle{}; VkImage handle{};
VmaAllocationInfo alloc_info{}; VmaAllocation allocation{};
VmaAllocation allocation{}; VmaAllocationInfo alloc_info{};
VkMemoryPropertyFlags property_flags{}; vk::Check(vmaCreateImage(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info)); // Log GPU memory allocation for images
vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags); if (GPU::Logging::IsActive() &&
Settings::values.gpu_log_memory_tracking.GetValue()) {
// Log GPU memory allocation for buffers GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
if (GPU::Logging::IsActive() && reinterpret_cast<uintptr_t>(alloc_info.deviceMemory),
Settings::values.gpu_log_memory_tracking.GetValue()) { static_cast<u64>(alloc_info.size),
GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation( VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT
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) return vk::Image(handle, ci.usage, *device.GetLogical(), allocator, allocation,
{ device.GetDispatchLoader());
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{}; vk::Buffer MemoryAllocator::CreateBuffer(const VkBufferCreateInfo &ci, MemoryUsage usage) const {
VmaAllocationInfo info{}; // 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) { vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
// Relax 1: drop budget constraint vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags);
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 // Log GPU memory allocation for buffers
if (res != VK_SUCCESS && (ci.preferredFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT)) { if (GPU::Logging::IsActive() &&
auto ci3 = ci2; Settings::values.gpu_log_memory_tracking.GetValue()) {
ci3.preferredFlags &= ~VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT; GPU::Logging::GPULogger::GetInstance().LogMemoryAllocation(
res = vmaAllocateMemory(allocator, &reqs, &ci3, &a, &info); reinterpret_cast<uintptr_t>(alloc_info.deviceMemory),
} static_cast<u64>(alloc_info.size),
} property_flags
);
vk::Check(res);
return MemoryCommit(allocator, a, info);
} }
MemoryCommit MemoryAllocator::Commit(const vk::Buffer &buffer, MemoryUsage usage) { u8 *data = reinterpret_cast<u8 *>(alloc_info.pMappedData);
// Allocate memory appropriate for this buffer automatically const std::span<u8> mapped_data = data ? std::span<u8>{data, ci.size} : std::span<u8>{};
const auto vma_usage = MemoryUsageVma(usage); const bool is_coherent = (property_flags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) != 0;
VmaAllocationCreateInfo ci{}; return vk::Buffer(handle, *device.GetLogical(), allocator, allocation, mapped_data,
ci.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | MemoryUsageVmaFlags(usage); is_coherent,
ci.usage = vma_usage; device.GetDispatchLoader());
ci.requiredFlags = 0; }
ci.preferredFlags = MemoryUsagePreferredVmaFlags(usage);
ci.pool = VK_NULL_HANDLE;
ci.pUserData = nullptr;
ci.priority = 0.0f;
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{}; VmaAllocation a{};
VmaAllocationInfo info{}; VmaAllocationInfo info{};
// Let VMA infer memory requirements from the buffer VkResult res = vmaAllocateMemory(allocator, &reqs, &ci, &a, &info);
VkResult res = vmaAllocateMemoryForBuffer(allocator, raw, &ci, &a, &info);
if (res != VK_SUCCESS) { if (res != VK_SUCCESS) {
auto ci2 = ci; // Relax 1: drop budget constraint
ci2.flags &= ~VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT; auto ci2 = ci;
res = vmaAllocateMemoryForBuffer(allocator, raw, &ci2, &a, &info); 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)) { // Relax 2: if we preferred DEVICE_LOCAL, drop that preference
auto ci3 = ci2; if (res != VK_SUCCESS && (ci.preferredFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT)) {
ci3.preferredFlags &= ~VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT; auto ci3 = ci2;
res = vmaAllocateMemoryForBuffer(allocator, raw, &ci3, &a, &info); 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 } // namespace Vulkan
+1 -1
View File
@@ -4796,6 +4796,6 @@ void VolumeButton::ResetMultiplier() {
#endif #endif
#if !defined(QT_STATICPLUGIN) || defined(__APPLE__) #if !defined(QT_STATICPLUGIN) || defined(__APPLE__)
#define VMA_IMPLEMENTATION #define VMA_IMPLEMENTATION 1
#include "video_core/vulkan_common/vma.h" #include "video_core/vulkan_common/vma.h"
#endif #endif
+1 -1
View File
@@ -65,7 +65,7 @@ else()
endif() endif()
# update cached cpmfile content # update cached cpmfile content
string(JSON cpmfile SET "${cpmfile}" "${key}" "${new_object}") string(JSON cpmfile SET "${cpmfile}" "${KEY}" "${new_object}")
# write cached cpmfile # write cached cpmfile
get_cpmfile_path(file) get_cpmfile_path(file)