build: make clang-tidy checks opt-in

launcher: add game patches

.github/workflows/build-linux.yml

@@ -0,0 +1,82 @@
+name: Build KytyPS5 (Linux)
+
+on:
+  workflow_dispatch:
+  push:
+    branches: [ main, master ]
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-24.04
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Install build dependencies
+        shell: bash
+        run: |
+          sudo apt-get update
+          sudo apt-get install --no-install-recommends --yes \
+            clang \
+            glslang-tools \
+            libgl1-mesa-dev \
+            libx11-dev \
+            libxcursor-dev \
+            libxext-dev \
+            libxfixes-dev \
+            libxi-dev \
+            libxrandr-dev \
+            libxss-dev \
+            lld \
+            ninja-build
+
+      - name: Install Qt 6.10.3
+        uses: jurplel/install-qt-action@v4
+        with:
+          version: "6.10.3"
+          host: linux
+          target: desktop
+          arch: linux_gcc_64
+          cache: true
+
+      - name: Verify toolchain
+        shell: bash
+        run: |
+          git --version
+          cmake --version
+          ninja --version
+          clang++ --version
+          ld.lld --version
+          glslangValidator --version
+          echo "Qt6_DIR=$Qt6_DIR"
+
+      - name: Configure
+        shell: bash
+        run: |
+          cmake -S src -B _Build/linux \
+            -G Ninja \
+            -DCMAKE_BUILD_TYPE=Release \
+            -DCMAKE_C_COMPILER=clang \
+            -DCMAKE_CXX_COMPILER=clang++ \
+            -DCMAKE_PREFIX_PATH="$Qt6_DIR"
+
+      - name: Build
+        shell: bash
+        run: |
+          cmake --build _Build/linux --target launcher --parallel
+
+      - name: Install
+        shell: bash
+        run: |
+          cmake --install _Build/linux --prefix _Build/linux/install
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: KytyPS5-Linux
+          path: _Build/linux/install/**
+          if-no-files-found: error

3rdparty/CMakeLists.txt

@@ -44,7 +44,17 @@ set(SPDLOG_NO_EXCEPTIONS ON CACHE BOOL "" FORCE)
 add_subdirectory(spdlog EXCLUDE_FROM_ALL)
 
 if (NOT TARGET FFmpeg::ffmpeg)
-	if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64|ARM64)$")
+	# On macOS the target arch is driven by CMAKE_OSX_ARCHITECTURES, not the host
+	# CMAKE_SYSTEM_PROCESSOR (which reports arm64 even for an x86_64/Rosetta build).
+	if(APPLE AND CMAKE_OSX_ARCHITECTURES)
+		if(CMAKE_OSX_ARCHITECTURES MATCHES "^(x86_64)$")
+			set(ARCHITECTURE x86_64)
+		elseif(CMAKE_OSX_ARCHITECTURES MATCHES "^(arm64)$")
+			set(ARCHITECTURE arm64)
+		else()
+			set(ARCHITECTURE x86_64 arm64) # universal
+		endif()
+	elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64|ARM64)$")
 		set(ARCHITECTURE arm64)
 	else()
 		set(ARCHITECTURE x86_64)

3rdparty/cpuinfo/CMakeLists.txt

@@ -5,7 +5,14 @@ set(cpuinfo_src
 	deps/clog/src/clog.c
 )
 
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(i[3-6]86|AMD64|x86(_64)?)$")
+# On Apple the target arch is driven by CMAKE_OSX_ARCHITECTURES, not the host
+# CMAKE_SYSTEM_PROCESSOR (which is arm64 even for an x86_64/Rosetta build).
+set(CPUINFO_TARGET_PROC "${CMAKE_SYSTEM_PROCESSOR}")
+if(APPLE AND CMAKE_OSX_ARCHITECTURES)
+	list(GET CMAKE_OSX_ARCHITECTURES 0 CPUINFO_TARGET_PROC)
+endif()
+
+if(CPUINFO_TARGET_PROC MATCHES "^(i[3-6]86|AMD64|x86(_64)?)$")
 	list(APPEND cpuinfo_src
 		src/x86/init.c
 		src/x86/info.c
@@ -19,11 +26,13 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(i[3-6]86|AMD64|x86(_64)?)$")
 		src/x86/cache/deterministic.c)
 	if(LINUX OR ANDROID)
 		list(APPEND cpuinfo_src src/x86/linux/init.c src/x86/linux/cpuinfo.c)
+	elseif(APPLE)
+		list(APPEND cpuinfo_src src/x86/mach/init.c src/mach/topology.c)
 	else()
 		list(APPEND cpuinfo_src src/x86/windows/init.c)
 	endif()
-	
-elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv[5-8].*|aarch64|arm64)$")
+
+elseif(CPUINFO_TARGET_PROC MATCHES "^(armv[5-8].*|aarch64|arm64)$")
 	list(APPEND cpuinfo_src src/arm/uarch.c src/arm/cache.c)
 	
 	if(LINUX OR ANDROID)

README.md

@@ -1,5 +1,7 @@
 # KytyPS5
 
+[![Windows Build](https://github.com/KytyPS5/KytyPS5/actions/workflows/build.yml/badge.svg)](https://github.com/KytyPS5/KytyPS5/actions/workflows/build.yml)
+[![Linux Build](https://github.com/KytyPS5/KytyPS5/actions/workflows/build-linux.yml/badge.svg)](https://github.com/KytyPS5/KytyPS5/actions/workflows/build-linux.yml)
 [![Platform](https://img.shields.io/badge/platform-Windows%20x64-0078D4.svg)](#system-requirements)
 [![Status](https://img.shields.io/badge/status-early%20development-orange.svg)](#current-status)
 [![License](https://img.shields.io/badge/license-GPL--2.0-blue.svg)](LICENSE)

src/CMakeLists.txt

@@ -10,15 +10,19 @@ if(CMAKE_SYSTEM_NAME MATCHES ".*Linux")
 	set(LINUX TRUE)
 endif()
 
-if (NOT (WIN32 OR LINUX))
-    message(FATAL_ERROR "only Windows and Linux builds are supported")
+if (NOT (WIN32 OR LINUX OR APPLE))
+    message(FATAL_ERROR "only Windows, Linux, and macOS builds are supported")
 endif()
 
 set(CMAKE_CXX_STANDARD 20)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 set(CMAKE_CXX_EXTENSIONS OFF)
+set(CMAKE_CXX_SCAN_FOR_MODULES OFF)
 
 include(utils.cmake)
+include(CTest)
+
+option(KYTY_ENABLE_CLANG_TIDY "Run clang-tidy checks during builds" OFF)
 
 set(KYTY_THIRD_PARTY_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../3rdparty")
 
@@ -43,8 +47,9 @@ else()
 	set(KYTY_BUILD KYTY_BUILD_RELEASE)
 endif()
 
-if(LINUX)
-	set(KYTY_PLATFORM KYTY_PLATFORM_LINUX)	
+if(LINUX OR APPLE)
+	# macOS rides the POSIX/Linux code paths until it gets a dedicated platform
+	set(KYTY_PLATFORM KYTY_PLATFORM_LINUX)
 else()
 	set(KYTY_PLATFORM KYTY_PLATFORM_WINDOWS)
 endif()
@@ -61,6 +66,8 @@ if(CMAKE_CXX_COMPILER_ID MATCHES "^(Apple)?Clang$")
 	if(WIN32 AND KYTY_CXX_COMPILER_NAME STREQUAL "clang-cl")
 		set(KYTY_CLANG_CL TRUE)
 		set(KYTY_LINKER LLD_LINK)
+	elseif(APPLE)
+		set(KYTY_LINKER LD64) # Apple's default linker; lld flags don't apply
 	else()
 		set(KYTY_LINKER LLD)
 	endif()
@@ -113,6 +120,7 @@ add_custom_target( KytyGitVersion
 	-D INPUT_FILE=${CMAKE_CURRENT_SOURCE_DIR}/kytyGitVersion.h.in
     -D OUTPUT_FILE=${CMAKE_CURRENT_BINARY_DIR}/kytyGitVersion.h
 	-D GIT_EXECUTABLE=${GIT_EXECUTABLE}
+	-D GIT_WORKING_DIRECTORY=${CMAKE_CURRENT_SOURCE_DIR}
 	-P ${CMAKE_CURRENT_SOURCE_DIR}/generate_version.cmake
 	COMMENT "Generate kytyGitVersion.h"
 )
@@ -123,7 +131,7 @@ if (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 12.0.0)
 		common
 		#launcher
 	)
-	list(APPEND KYTY_CLANG_TYDY 
+	list(APPEND KYTY_CLANG_TIDY
 		kyty_emulator
 		#common
 		launcher
@@ -183,6 +191,9 @@ set(gpu_tiler_shader_names
 	prt_3d
 	render_target
 	depth
+	promote_d16
+	demote_d16
+	swap_bgra16
 )
 file(GLOB gpu_tiler_shader_includes CONFIGURE_DEPENDS "${gpu_tiler_shader_dir}/gpu_tiler_*.inc")
 foreach(shader_name IN LISTS gpu_tiler_shader_names)
@@ -204,6 +215,30 @@ foreach(shader_name IN LISTS gpu_tiler_shader_names)
 endforeach()
 list(APPEND kyty_emulator_src ${gpu_tiler_shader_headers})
 
+set(gpu_blit_generated_dir "${PROJECT_BINARY_DIR}/gpu_blit_shaders")
+set(gpu_blit_shader_sources
+	"${gpu_tiler_shader_dir}/gpu_blit_fs_triangle.vert"
+	"${gpu_tiler_shader_dir}/gpu_blit_color_to_ms_depth.frag"
+)
+foreach(shader_source IN LISTS gpu_blit_shader_sources)
+	get_filename_component(shader_name "${shader_source}" NAME_WE)
+	set(shader_spv "${gpu_blit_generated_dir}/${shader_name}.spv")
+	set(shader_header "${gpu_blit_generated_dir}/${shader_name}_spv.h")
+	string(TOUPPER "${shader_name}_SPV" shader_symbol)
+	add_custom_command(
+		OUTPUT "${shader_header}"
+		COMMAND ${CMAKE_COMMAND} -E make_directory "${gpu_blit_generated_dir}"
+		COMMAND "${KYTY_GLSLANG_VALIDATOR}" -V --target-env vulkan1.0 -Os
+		        "-I${gpu_tiler_shader_dir}" -o "${shader_spv}" "${shader_source}"
+		COMMAND ${CMAKE_COMMAND} -DINPUT=${shader_spv} -DOUTPUT=${shader_header}
+		        -DSYMBOL=${shader_symbol} -P "${CMAKE_CURRENT_SOURCE_DIR}/embed_spirv.cmake"
+		DEPENDS "${shader_source}"
+		VERBATIM
+	)
+	list(APPEND gpu_blit_shader_headers "${shader_header}")
+endforeach()
+list(APPEND kyty_emulator_src ${gpu_blit_shader_headers})
+
 list(APPEND kyty_emulator_src
 	emulator.h
 	emulator.cpp
@@ -318,17 +353,83 @@ add_executable(resource_mutex_tests EXCLUDE_FROM_ALL
 target_link_libraries(resource_mutex_tests common)
 target_include_directories(resource_mutex_tests PRIVATE ${inc_headers})
 
+add_executable(event_queue_lifetime_tests EXCLUDE_FROM_ALL
+	../tests/EventQueueLifetimeTests.cpp
+	kernel/eventQueue.cpp
+	loader/timer.cpp
+)
+target_link_libraries(event_queue_lifetime_tests common fmt::fmt)
+target_include_directories(event_queue_lifetime_tests PRIVATE ${inc_headers})
+
 add_executable(image_page_table_tests EXCLUDE_FROM_ALL
 	../tests/ImagePageTableTests.cpp
 )
+target_link_libraries(image_page_table_tests common fmt::fmt)
 target_include_directories(image_page_table_tests PRIVATE ${inc_headers})
 
 add_kyty_full_emulator_test(shader_recompiler_compute_tests ../tests/ShaderRecompilerComputeTests.cpp)
 
+set(gpu_test_generated_dir "${PROJECT_BINARY_DIR}/gpu_test_shaders")
+set(gpu_test_ms_depth_source
+	"${gpu_tiler_shader_dir}/gpu_test_ms_depth.comp")
+set(gpu_test_ms_depth_spv
+	"${gpu_test_generated_dir}/gpu_test_ms_depth.spv")
+set(gpu_test_ms_depth_header
+	"${gpu_test_generated_dir}/gpu_test_ms_depth_spv.h")
+add_custom_command(
+	OUTPUT "${gpu_test_ms_depth_header}"
+	COMMAND ${CMAKE_COMMAND} -E make_directory "${gpu_test_generated_dir}"
+	COMMAND "${KYTY_GLSLANG_VALIDATOR}" -V --target-env vulkan1.0 -Os
+	        -o "${gpu_test_ms_depth_spv}" "${gpu_test_ms_depth_source}"
+	COMMAND ${CMAKE_COMMAND} -DINPUT=${gpu_test_ms_depth_spv}
+	        -DOUTPUT=${gpu_test_ms_depth_header} -DSYMBOL=GPU_TEST_MS_DEPTH_SPV
+	        -P "${CMAKE_CURRENT_SOURCE_DIR}/embed_spirv.cmake"
+	DEPENDS "${gpu_test_ms_depth_source}"
+	VERBATIM
+)
+target_sources(shader_recompiler_compute_tests PRIVATE
+	"${gpu_test_ms_depth_header}")
+
 add_kyty_full_emulator_test(virtual_memory_allocation_tests ../tests/VirtualMemoryAllocationTests.cpp)
 target_compile_definitions(virtual_memory_allocation_tests PRIVATE
 	KYTY_VIRTUAL_MEMORY_ALLOCATION_TESTS=1)
 
+if(BUILD_TESTING)
+	add_test(NAME image_page_table COMMAND $<TARGET_FILE:image_page_table_tests>)
+	add_test(NAME memory_tracker COMMAND $<TARGET_FILE:memory_tracker_tests>)
+	add_test(NAME page_manager COMMAND $<TARGET_FILE:page_manager_tests>)
+	add_test(NAME resource_mutex COMMAND $<TARGET_FILE:resource_mutex_tests>)
+	add_test(NAME event_queue_lifetime COMMAND $<TARGET_FILE:event_queue_lifetime_tests>)
+	add_test(NAME shader_recompiler_compute COMMAND $<TARGET_FILE:shader_recompiler_compute_tests>)
+	add_test(NAME command_scheduler_timeline
+		COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --scheduler-only)
+	add_test(NAME stream_buffer_ring
+		COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --stream-buffer-only)
+	add_test(NAME gpu_command_lane
+		COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --gpu-command-lane-only)
+	add_test(NAME gpu_tiler
+		COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --gpu-tiler-only)
+
+	if(WIN32)
+		add_test(NAME texture_cache_image_overlap
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --image-overlap-only)
+		add_test(NAME texture_cache_htile_clear
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --htile-clear-only)
+		add_test(NAME texture_cache_layered_image
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --layered-image-only)
+		add_test(NAME texture_cache_image_views
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --image-view-cache-only)
+		add_test(NAME texture_cache_storage_sampled
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --storage-sampled-only)
+		add_test(NAME texture_cache_depth_readback
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --depth-readback-only)
+		add_test(NAME buffer_cache_ranges
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --buffer-cache-range-only)
+		add_test(NAME buffer_cache_dirty_gc
+			COMMAND $<TARGET_FILE:shader_recompiler_compute_tests> --buffer-cache-gc-only)
+	endif()
+endif()
+
 
 add_executable(kyty_emulator main.cpp ${kyty_emulator_src})
 
@@ -365,6 +466,18 @@ endif()
 
 add_dependencies(kyty_emulator KytyGitVersion)
 
+if(APPLE)
+	# The emulator writes x86-64 trampolines/PLT stubs into memory and executes them, and
+	# runs guest code under Rosetta. That requires the JIT / unsigned-executable-memory
+	# entitlements, so re-sign the binary after every link (an unsigned/relinked binary
+	# reverts to the hardened defaults and aborts when it first executes written code).
+	add_custom_command(TARGET kyty_emulator POST_BUILD
+		COMMAND codesign -s - --force --options runtime
+			--entitlements "${CMAKE_CURRENT_SOURCE_DIR}/macos_jit.entitlements"
+			$<TARGET_FILE:kyty_emulator>
+		COMMENT "Codesign kyty_emulator with JIT entitlements (macOS)")
+endif()
+
 install(TARGETS kyty_emulator DESTINATION .)
 if(KYTY_BUILD_LAUNCHER)
 	add_subdirectory(launcher)

src/common/byteBuffer.h

@@ -6,6 +6,7 @@
 
 #include <algorithm>
 #include <cstddef> // IWYU pragma: export
+#include <cstring>
 #include <utility>
 #include <vector>
 

src/common/debug.h

@@ -5,6 +5,7 @@
 #include "common/stringUtils.h"
 
 #include <array>
+#include <cstring>
 
 namespace Common {
 

src/common/emulatorConfig.cpp

@@ -93,4 +93,8 @@ bool NggRectlistDrawEnabled() {
 	return g_config->ngg_rectlist_draw_enabled;
 }
 
+bool ReadbackLinearImagesEnabled() {
+	return g_config->readback_linear_images;
+}
+
 } // namespace Config

src/common/emulatorConfig.h

@@ -36,6 +36,7 @@ struct ConfigOptions {
 	bool                   spirv_debug_printf_enabled  = false;
 	bool                   renderdoc_enabled           = false;
 	bool                   ngg_rectlist_draw_enabled   = true;
+	bool                   readback_linear_images      = false;
 };
 
 void Load(const ConfigOptions& cfg);
@@ -64,6 +65,7 @@ bool SpirvDebugPrintfEnabled();
 
 bool RenderDocEnabled();
 bool NggRectlistDrawEnabled();
+bool ReadbackLinearImagesEnabled();
 
 } // namespace Config
 

src/common/logging/log.cpp

@@ -178,6 +178,11 @@ Direction GetDirection() {
 	return g_direction;
 }
 
+bool IsSilent() {
+	// Before init LOGF must keep writing to stdout, so report non-silent.
+	return g_initialized && g_direction == Direction::Silent;
+}
+
 void Write(std::string_view text) {
 	WriteImpl(text);
 }

src/common/logging/log.h

@@ -15,6 +15,7 @@ KYTY_SUBSYSTEM_DEFINE(Log);
 enum class Direction { Silent, Console, File };
 
 Direction GetDirection();
+bool      IsSilent();
 void      Write(std::string_view text);
 void      Write(fmt::text_style style, std::string_view text);
 void      WriteFatal(std::string_view text);
@@ -41,8 +42,18 @@ inline constexpr auto BrightWhite   = fmt::fg(fmt::terminal_color::bright_white)
 } // namespace Log
 
 // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
-#define LOGF(...) ::Log::Write(::fmt::sprintf(__VA_ARGS__))
+#define LOGF(...)                                                                                  \
+	do {                                                                                           \
+		if (!::Log::IsSilent()) {                                                                  \
+			::Log::Write(::fmt::sprintf(__VA_ARGS__));                                             \
+		}                                                                                          \
+	} while (false)
 // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
-#define LOGF_COLOR(style, ...) ::Log::Write((style), ::fmt::sprintf(__VA_ARGS__))
+#define LOGF_COLOR(style, ...)                                                                     \
+	do {                                                                                           \
+		if (!::Log::IsSilent()) {                                                                  \
+			::Log::Write((style), ::fmt::sprintf(__VA_ARGS__));                                    \
+		}                                                                                          \
+	} while (false)
 
 #endif /* KYTY_COMMON_LOGGING_LOG_H_ */

src/common/lruCache.h

@@ -0,0 +1,119 @@
+#ifndef EMULATOR_SRC_COMMON_LRUCACHE_H_
+#define EMULATOR_SRC_COMMON_LRUCACHE_H_
+
+#include <cstddef>
+#include <deque>
+#include <type_traits>
+#include <utility>
+
+namespace Common {
+
+template <typename Object, typename Tick>
+class LeastRecentlyUsedCache {
+	struct Item {
+		Object object {};
+		Tick   tick {};
+		Item*  next = nullptr;
+		Item*  prev = nullptr;
+	};
+
+public:
+	[[nodiscard]] size_t Insert(Object object, Tick tick) {
+		const auto id = Build();
+		auto&      item = m_items[id];
+		item.object = std::move(object);
+		item.tick   = tick;
+		Attach(item);
+		return id;
+	}
+
+	void Touch(size_t id, Tick tick) {
+		auto& item = m_items[id];
+		if (item.tick >= tick) {
+			return;
+		}
+		item.tick = tick;
+		if (&item != m_last) {
+			Detach(item);
+			Attach(item);
+		}
+	}
+
+	void Free(size_t id) {
+		auto& item = m_items[id];
+		Detach(item);
+		item.next = nullptr;
+		item.prev = nullptr;
+		m_free.push_back(id);
+	}
+
+	template <typename Function>
+	void ForEachItemBelow(Tick tick, Function&& function) {
+		constexpr bool ReturnsBool =
+		    std::is_same_v<std::invoke_result_t<Function, Object>, bool>;
+		for (auto* item = m_first; item != nullptr;) {
+			if (item->tick > tick) {
+				return;
+			}
+			auto* next = item->next;
+			if constexpr (ReturnsBool) {
+				if (function(item->object)) {
+					return;
+				}
+			} else {
+				function(item->object);
+			}
+			item = next;
+		}
+	}
+
+private:
+	[[nodiscard]] size_t Build() {
+		if (m_free.empty()) {
+			const auto id = m_items.size();
+			m_items.emplace_back();
+			return id;
+		}
+		const auto id = m_free.front();
+		m_free.pop_front();
+		return id;
+	}
+
+	void Attach(Item& item) {
+		if (m_first == nullptr) {
+			m_first = &item;
+		}
+		if (m_last == nullptr) {
+			m_last = &item;
+			return;
+		}
+		item.prev   = m_last;
+		m_last->next = &item;
+		item.next   = nullptr;
+		m_last      = &item;
+	}
+
+	void Detach(Item& item) {
+		if (item.prev != nullptr) {
+			item.prev->next = item.next;
+		}
+		if (item.next != nullptr) {
+			item.next->prev = item.prev;
+		}
+		if (m_first == &item) {
+			m_first = item.next;
+		}
+		if (m_last == &item) {
+			m_last = item.prev;
+		}
+	}
+
+	std::deque<Item>   m_items;
+	std::deque<size_t> m_free;
+	Item*              m_first = nullptr;
+	Item*              m_last  = nullptr;
+};
+
+} // namespace Common
+
+#endif // EMULATOR_SRC_COMMON_LRUCACHE_H_

src/common/uniqueFunction.h

@@ -0,0 +1,56 @@
+#ifndef KYTY_COMMON_UNIQUEFUNCTION_H_
+#define KYTY_COMMON_UNIQUEFUNCTION_H_
+
+#include <memory>
+#include <type_traits>
+#include <utility>
+
+namespace Common {
+
+template <typename Result, typename... Args>
+class UniqueFunction {
+	class CallableBase {
+	public:
+		virtual ~CallableBase() = default;
+		virtual Result Invoke(Args&&... args) = 0;
+	};
+
+	template <typename Function>
+	class Callable final: public CallableBase {
+	public:
+		explicit Callable(Function function): m_function(std::move(function)) {}
+
+		Result Invoke(Args&&... args) override {
+			return m_function(std::forward<Args>(args)...);
+		}
+
+	private:
+		Function m_function;
+	};
+
+public:
+	UniqueFunction() = default;
+
+	template <typename Function>
+	UniqueFunction(Function&& function)
+	    : m_callable(std::make_unique<Callable<std::decay_t<Function>>>(
+	          std::forward<Function>(function))) {}
+
+	UniqueFunction(UniqueFunction&&) noexcept            = default;
+	UniqueFunction& operator=(UniqueFunction&&) noexcept = default;
+	UniqueFunction(const UniqueFunction&)                = delete;
+	UniqueFunction& operator=(const UniqueFunction&)     = delete;
+
+	Result operator()(Args... args) const {
+		return m_callable->Invoke(std::forward<Args>(args)...);
+	}
+
+	explicit operator bool() const noexcept { return m_callable != nullptr; }
+
+private:
+	std::unique_ptr<CallableBase> m_callable;
+};
+
+} // namespace Common
+
+#endif // KYTY_COMMON_UNIQUEFUNCTION_H_

src/emulator.cpp

@@ -159,25 +159,16 @@ static void LoadElf(const std::filesystem::path& elf, bool dbg_print_reloc = fal
 	}
 }
 
-static void Execute() {
-	int thread_model = 1;
-
-	if (thread_model == 0) {
-		Common::Thread t([](void* /*unused*/) { Libs::Graphics::WindowRun(); }, nullptr);
-		t.Detach();
-		auto* rt = Common::Singleton<Loader::RuntimeLinker>::Instance();
-		rt->Execute();
-	} else {
-		Common::Thread t(
-		    [](void* /*unused*/) {
-			    auto* rt = Common::Singleton<Loader::RuntimeLinker>::Instance();
-			    rt->Execute();
-		    },
-		    nullptr);
-		t.Detach();
-		Libs::Graphics::WindowRun();
-		t.Join();
-	}
+static void Execute(const std::filesystem::path& game_patch) {
+	auto           patch_path = game_patch;
+	Common::Thread guest_thread(
+	    [](void* param) {
+		    auto* rt = Common::Singleton<Loader::RuntimeLinker>::Instance();
+		    rt->Execute(*static_cast<const std::filesystem::path*>(param));
+	    },
+	    &patch_path);
+	Libs::Graphics::WindowRun();
+	std::quick_exit(0);
 }
 
 void Run(const RunOptions& options) {
@@ -217,7 +208,7 @@ void Run(const RunOptions& options) {
 
 	LoadElf(options.elf);
 
-	Execute();
+	Execute(options.game_patch);
 }
 
 } // namespace Emulator

src/emulator.h

@@ -12,6 +12,7 @@ struct RunOptions {
 	Config::ConfigOptions config;
 	std::filesystem::path app0_dir;
 	std::filesystem::path elf;
+	std::filesystem::path game_patch;
 };
 
 void Run(const RunOptions& options);

src/generate_version.cmake

@@ -1,8 +1,15 @@
-#message("${GIT_EXECUTABLE}")
+set(KYTY_GIT_VERSION "unknown")
 if(GIT_EXECUTABLE)
-	execute_process(COMMAND ${GIT_EXECUTABLE} describe --tags --always OUTPUT_VARIABLE KYTY_GIT_VERSION)
-else()
-	set(KYTY_GIT_VERSION "unknown")
+	execute_process(
+		COMMAND "${GIT_EXECUTABLE}" describe --tags --always
+		WORKING_DIRECTORY "${GIT_WORKING_DIRECTORY}"
+		OUTPUT_VARIABLE KYTY_GIT_VERSION
+		OUTPUT_STRIP_TRAILING_WHITESPACE
+		RESULT_VARIABLE GIT_RESULT
+		ERROR_QUIET
+	)
+	if(NOT GIT_RESULT EQUAL 0)
+		set(KYTY_GIT_VERSION "unknown")
+	endif()
 endif()
-string(STRIP ${KYTY_GIT_VERSION} KYTY_GIT_VERSION)
-configure_file(${INPUT_FILE} ${OUTPUT_FILE})
+configure_file("${INPUT_FILE}" "${OUTPUT_FILE}")

src/graphics/asyncJob.h

@@ -1,96 +0,0 @@
-#ifndef EMULATOR_INCLUDE_EMULATOR_GRAPHICS_ASYNCJOB_H_
-#define EMULATOR_INCLUDE_EMULATOR_GRAPHICS_ASYNCJOB_H_
-
-#include "common/common.h"
-#include "common/profiler.h"
-#include "common/threads.h"
-
-#include <functional>
-#include <string>
-#include <utility>
-
-namespace Libs::Graphics {
-
-class AsyncJob final {
-public:
-	using Task = std::function<void()>;
-
-	explicit AsyncJob(std::string thread_name = {})
-	    : m_thread_name(std::move(thread_name)), m_worker_thread(WorkerEntry, this) {}
-
-	~AsyncJob() {
-		{
-			Common::LockGuard lock(m_mutex);
-			m_stop_requested = true;
-			m_task_available_condition.Signal();
-		}
-
-		m_worker_thread.Join();
-	}
-
-	KYTY_CLASS_NO_COPY(AsyncJob);
-
-	void Execute(Task task) {
-		Common::LockGuard lock(m_mutex);
-		while (m_is_busy) {
-			m_idle_condition.Wait(&m_mutex);
-		}
-
-		m_task    = std::move(task);
-		m_is_busy = true;
-		m_task_available_condition.Signal();
-	}
-
-	void Wait() {
-		Common::LockGuard lock(m_mutex);
-		while (m_is_busy) {
-			m_idle_condition.Wait(&m_mutex);
-		}
-	}
-
-private:
-	static void WorkerEntry(void* data) { static_cast<AsyncJob*>(data)->WorkerLoop(); }
-
-	void WorkerLoop() {
-		if (!m_thread_name.empty()) {
-			KYTY_PROFILER_THREAD(m_thread_name.c_str());
-		}
-
-		for (;;) {
-			Task task;
-			{
-				Common::LockGuard lock(m_mutex);
-				while (!m_is_busy && !m_stop_requested) {
-					m_task_available_condition.Wait(&m_mutex);
-				}
-
-				if (!m_is_busy) {
-					return;
-				}
-
-				task = std::move(m_task);
-			}
-
-			task();
-
-			{
-				Common::LockGuard lock(m_mutex);
-				m_is_busy = false;
-				m_idle_condition.SignalAll();
-			}
-		}
-	}
-
-	std::string     m_thread_name;
-	Common::Mutex   m_mutex;
-	Common::CondVar m_task_available_condition;
-	Common::CondVar m_idle_condition;
-	Task            m_task;
-	bool            m_is_busy        = false;
-	bool            m_stop_requested = false;
-	Common::Thread  m_worker_thread;
-};
-
-} // namespace Libs::Graphics
-
-#endif /* EMULATOR_INCLUDE_EMULATOR_GRAPHICS_ASYNCJOB_H_ */

src/graphics/guest_gpu/command_processor/commandProcessor.h

@@ -2,109 +2,36 @@
 #define GRAPHICS_GUEST_GPU_COMMAND_PROCESSOR_COMMAND_PROCESSOR_H
 
 #include "common/assert.h"
-#include "common/threads.h"
 #include "graphics/guest_gpu/hardwareContext.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
 
-#include <array>
 #include <cstdint>
 #include <vector>
 
 namespace Libs::Graphics {
 
-inline constexpr uint32_t AcquireGcrGl2Writeback = 1u << 15u;
-
 bool TestWaitRegMemValue(uint64_t value, uint64_t ref, uint64_t mask, uint32_t func);
 
-class CommandScheduler {
+enum class Pm4ProcessResult { Complete, Blocked };
+
+class Pm4Execution {
 public:
-	static constexpr int BuffersNum = 8;
-
-	CommandScheduler(HW::Context& registers, HW::UserConfig& user_config, HW::Shader& shaders)
-	    : m_registers(registers), m_user_config(user_config), m_shaders(shaders) {}
-
-	bool Active() const { return m_current >= 0 && m_current < BuffersNum; }
-	void CheckActive() const { EXIT_IF(!Active()); }
-
-	RenderCommandBuffer& Current() const {
-		CheckActive();
-		EXIT_IF(m_buffers[m_current] == nullptr);
-		return *m_buffers[m_current];
-	}
-
-	void Init() {
-		if (m_current >= 0) {
-			return;
-		}
-		for (auto& buf: m_buffers) {
-			EXIT_IF(buf != nullptr);
-			buf = new RenderCommandBuffer(m_registers, m_user_config, m_shaders);
-		}
-		m_current = 0;
-		Current().Begin();
-	}
-
-	void Flush() {
-		SubmitCurrent();
-		BeginNext();
-	}
-
-	CommandBuffer& FlushAndGetSubmitted() {
-		auto& submitted = SubmitCurrent();
-		BeginNext();
-		return submitted;
-	}
-
-	void CopyBuffers(std::array<CommandBuffer*, BuffersNum>& out) const {
-		for (int i = 0; i < BuffersNum; i++) {
-			auto* buf = m_buffers[i];
-			EXIT_IF(buf == nullptr);
-			out[i] = buf;
-		}
-	}
-
-	void WaitAll() {
-		for (auto* buf: m_buffers) {
-			EXIT_IF(buf == nullptr);
-			buf->WaitForFenceAndReset();
-		}
-	}
-
-	void SubmitForReadback() {
-		if (!Active()) {
-			return;
-		}
-		SubmitCurrent();
-	}
-
-	void ResumeAfterReadback() {
-		if (!Active()) {
-			return;
-		}
-		Current().WaitForFenceAndReset();
-		Current().Begin();
-	}
+	[[nodiscard]] bool MadeProgress() const noexcept { return m_made_progress; }
 
 private:
-	CommandBuffer& SubmitCurrent() {
-		auto& submitted = Current();
-		submitted.End();
-		submitted.Execute();
-		return submitted;
-	}
+	friend class CommandProcessor;
 
-	void BeginNext() {
-		m_current = (m_current + 1) % BuffersNum;
-		Current().WaitForFenceAndReset();
-		Current().Begin();
-	}
+	struct BufferCursor {
+		uint32_t* next_packet         = nullptr;
+		uint32_t  remaining_dw        = 0;
+		uint32_t  total_dw            = 0;
+		uint32_t  deferred_advance_dw = 0;
+	};
 
-	RenderCommandBuffer* m_buffers[BuffersNum] = {};
-	int                  m_current             = -1;
-	HW::Context&         m_registers;
-	HW::UserConfig&      m_user_config;
-	HW::Shader&          m_shaders;
+	std::vector<BufferCursor> m_buffer_stack;
+	bool                      m_suspended     = false;
+	bool                      m_made_progress = false;
 };
 
 class CommandProcessor {
@@ -116,8 +43,8 @@ public:
 		int64_t flip_arg  = 0;
 	};
 
-	CommandProcessor();
-	~CommandProcessor() { KYTY_NOT_IMPLEMENTED; }
+	explicit CommandProcessor(RenderContext& renderer): m_renderer(renderer) {}
+	~CommandProcessor() = default;
 
 	KYTY_CLASS_NO_COPY(CommandProcessor);
 
@@ -128,26 +55,18 @@ public:
 	void BufferFlushAndWait();
 	void BufferWait();
 	void BeginReadbackTransaction() {
-		m_mutex.Lock();
 		if (m_readback_active) {
 			EXIT("nested command-processor readback transaction\n");
 		}
-		m_readback_active   = true;
-		m_readback_finished = false;
+		m_readback_active = true;
 	}
-	void FinishReadbackTransaction();
 	void EndReadbackTransaction() {
 		if (!m_readback_active) {
 			EXIT("command-processor readback transaction is not active\n");
 		}
-		m_readback_active   = false;
-		m_readback_finished = false;
-		m_mutex.Unlock();
+		m_readback_active = false;
 	}
 
-	void RunLock() { m_run_mutex.Lock(); }
-	void RunUnlock() { m_run_mutex.Unlock(); }
-
 	HW::Context&    GetCtx() { return m_ctx; }
 	HW::UserConfig& GetUcfg() { return m_ucfg; }
 	HW::Shader&     GetShCtx() { return m_sh_ctx; }
@@ -182,12 +101,10 @@ public:
 	void Flip(void* dst_gpu_addr, uint32_t value);
 	void FlipWithInterrupt(uint32_t eop_event_type, uint32_t cache_action, void* dst_gpu_addr,
 	                       uint32_t value);
-	void PrepareCpuFlip();
+	void PrepareCpuFlip(uint64_t request_id);
 	void SynchronizeGpu();
-	void MemoryBarrier();
+	void EmitGlobalBarrier();
 	void TriggerEopEventAtEndOfPipe(uint32_t interrupt_context_id);
-	void RenderTextureBarrier(uint64_t vaddr, uint64_t size);
-	void DepthStencilBarrier(uint64_t vaddr, uint64_t size);
 	void DispatchDirect(uint32_t thread_group_x, uint32_t thread_group_y, uint32_t thread_group_z,
 	                    uint32_t mode);
 	void DispatchIndirect(uint32_t data_offset, uint32_t mode);
@@ -196,16 +113,13 @@ public:
 
 	void SetUserDataMarker(HW::UserSgprType type) { m_user_data_marker = type; }
 	[[nodiscard]] HW::UserSgprType GetUserDataMarker() const { return m_user_data_marker; }
-	void SetEmbeddedDataMarker(const uint32_t* buffer, uint32_t num_dw, uint32_t align) {}
-	void PushMarker(const char* str) {}
-	void PopMarker() {}
 
-	void PrefetchL2(void* addr, uint32_t size) {}
 	void ResetDeCe();
+	void SetCeComplete(bool complete) { m_ce_complete = complete; }
 	void WaitCe();
 	void WaitDeDiff(uint32_t diff);
-	void IncremenetDe();
-	void IncremenetCe();
+	void IncrementDe();
+	void IncrementCe();
 
 	void WriteConstRam(uint32_t offset, const uint32_t* src, uint32_t dw_num);
 	void DumpConstRam(uint32_t* dst, uint32_t offset, uint32_t dw_num);
@@ -222,32 +136,29 @@ public:
 	                    const volatile void* address, uint32_t count_in_dwords);
 	[[nodiscard]] bool ShouldSkipPredicatedPackets() const { return m_predicate_skip; }
 
-	void Run(uint32_t* data, uint32_t num_dw);
+	Pm4ProcessResult Process(Pm4Execution& execution, uint32_t* buffer, uint32_t size_dw);
+	void             ProcessIndirectBuffer(uint32_t* buffer, uint32_t size_dw);
 
-	[[nodiscard]] const FlipInfo& GetFlip() const { return m_flip; }
-	void                          SetFlip(const FlipInfo& flip) { m_flip = flip; }
+	void SetFlip(const FlipInfo& flip) { m_flip = flip; }
 
 	[[nodiscard]] uint64_t GetSubmitId() const { return m_submit_id; }
 	void                   SetSubmitId(uint64_t submit_id) { m_submit_id = submit_id; }
 
 private:
-	struct Counter {
-		Common::Mutex   mutex;
-		Common::CondVar cond_var;
-		uint32_t        value = 0;
-	};
-
 	template <typename T>
 	void WriteAtEndOfPipe(uint32_t cache_policy, uint32_t event_write_dest, uint32_t eop_event_type,
 	                      uint32_t cache_action, uint32_t event_index, uint32_t event_write_source,
 	                      void* dst_gpu_addr, T value, uint32_t interrupt_selector,
 	                      uint32_t interrupt_context_id);
-	void FinishCommandProcessors();
+	void ProcessPm4(Pm4Execution& execution, size_t stop_depth);
+	void SuspendPm4();
 
-	RenderCommandBuffer& CurrentBuffer() { return m_scheduler.Current(); }
-	void                 CheckBuffer() const { m_scheduler.CheckActive(); }
-	GpuResourceManager&  GetGpuResources() const { return GetRenderContext().GetGpuResources(); }
+	CommandScheduler&    GetScheduler() const { return m_renderer.GetCommandScheduler(); }
+	RenderCommandBuffer& CurrentBuffer() { return GetScheduler().Current(); }
+	void                 CheckBuffer() const { GetScheduler().CheckActive(); }
+	GpuResourceManager&  GetGpuResources() const { return m_renderer.GetGpuResources(); }
 
+	RenderContext&    m_renderer;
 	HW::Context      m_ctx;
 	HW::UserConfig   m_ucfg;
 	HW::Shader       m_sh_ctx;
@@ -259,16 +170,10 @@ private:
 	uint64_t         m_dispatch_indirect_args_base_addr = 0;
 	uint32_t         m_num_instances                    = 1;
 
-	inline static Common::Mutex                  m_mutex;
-	inline static std::vector<CommandProcessor*> m_processors;
-	inline static bool                           m_readback_active   = false;
-	inline static bool                           m_readback_finished = false;
-	Common::Mutex                                m_run_mutex;
-
-	CommandScheduler m_scheduler;
-
-	Counter m_de_counter;
-	Counter m_ce_counter;
+	uint32_t m_de_count          = 0;
+	uint32_t m_ce_count          = 0;
+	bool     m_ce_complete       = false;
+	bool     m_readback_active = false;
 
 	uint32_t m_const_ram[0x3000] = {0};
 

src/graphics/guest_gpu/command_processor/pm4Handlers.cpp

@@ -6,7 +6,6 @@
 #include "graphics/guest_gpu/command_processor/pm4Dispatch.h"
 #include "graphics/guest_gpu/graphicsRun.h"
 #include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/objects/label.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
 #include "graphics/presentation/videoOut.h"
@@ -598,30 +597,7 @@ KYTY_HW_CTX_PARSER(HwCtxSetDepthRenderTarget) {
 	uint32_t count = 1;
 
 	if (cmd_id == 0xC0016900) {
-		HW::DepthZInfo r;
-
-		//	r.expclear_enabled = (buffer[0] & 0x08000000u) != 0;
-		//	r.format              = (buffer[0] >> Pm4::DB_Z_INFO_FORMAT_SHIFT) &
-		// Pm4::DB_Z_INFO_FORMAT_MASK; 	r.num_samples         = (buffer[0] >>
-		// Pm4::DB_Z_INFO_NUM_SAMPLES_SHIFT) & Pm4::DB_Z_INFO_NUM_SAMPLES_MASK; r.tile_mode_index =
-		//(buffer[0] >> Pm4::DB_Z_INFO_TILE_MODE_INDEX_SHIFT) & Pm4::DB_Z_INFO_TILE_MODE_INDEX_MASK;
-		//	r.tile_surface_enable = ((buffer[0] >> Pm4::DB_Z_INFO_TILE_SURFACE_ENABLE_SHIFT) &
-		// Pm4::DB_Z_INFO_TILE_SURFACE_ENABLE_MASK) !=0
-		// 	r.zrange_precision    = (buffer[0] >> Pm4::DB_Z_INFO_ZRANGE_PRECISION_SHIFT) &
-		// Pm4::DB_Z_INFO_ZRANGE_PRECISION_MASK;
-
-		r.format                    = KYTY_PM4_GET(buffer[0], DB_Z_INFO, FORMAT);
-		r.num_samples               = KYTY_PM4_GET(buffer[0], DB_Z_INFO, NUM_SAMPLES);
-		r.embedded_sample_locations = KYTY_PM4_GET(buffer[0], DB_Z_INFO, ITERATE_FLUSH) != 0;
-		r.partially_resident        = KYTY_PM4_GET(buffer[0], DB_Z_INFO, PARTIALLY_RESIDENT) != 0;
-		r.num_mip_levels            = KYTY_PM4_GET(buffer[0], DB_Z_INFO, MAXMIP);
-		r.tile_mode_index           = KYTY_PM4_GET(buffer[0], DB_Z_INFO, TILE_MODE_INDEX);
-		r.plane_compression         = KYTY_PM4_GET(buffer[0], DB_Z_INFO, DECOMPRESS_ON_N_ZPLANES);
-		r.expclear_enabled          = KYTY_PM4_GET(buffer[0], DB_Z_INFO, ALLOW_EXPCLEAR) != 0;
-		r.tile_surface_enable       = KYTY_PM4_GET(buffer[0], DB_Z_INFO, TILE_SURFACE_ENABLE) != 0;
-		r.zrange_precision          = KYTY_PM4_GET(buffer[0], DB_Z_INFO, ZRANGE_PRECISION);
-
-		cp.GetCtx().SetDepthZInfo(r);
+		cp.GetCtx().SetDepthZInfo(HW::DepthZInfo::Decode(buffer[0]));
 	} else if (cmd_id == 0xC0086900) {
 		if (dw >= 22 && buffer[8] == 0xC0016900 && buffer[9] == Pm4::DB_DEPTH_INFO &&
 		    buffer[11] == 0xC0016900 && buffer[12] == Pm4::DB_DEPTH_VIEW &&
@@ -632,51 +608,8 @@ KYTY_HW_CTX_PARSER(HwCtxSetDepthRenderTarget) {
 
 			HW::DepthRenderTarget z;
 
-			//			z.z_info.expclear_enabled    = (buffer[0] & 0x08000000u) != 0;
-			//			z.z_info.format              = (buffer[0] >> Pm4::DB_Z_INFO_FORMAT_SHIFT) &
-			// Pm4::DB_Z_INFO_FORMAT_MASK; 			z.z_info.num_samples         = (buffer[0] >>
-			// Pm4::DB_Z_INFO_NUM_SAMPLES_SHIFT) & Pm4::DB_Z_INFO_NUM_SAMPLES_MASK;
-			//			z.z_info.tile_mode_index     = (buffer[0] >>
-			// Pm4::DB_Z_INFO_TILE_MODE_INDEX_SHIFT) &
-			// Pm4::DB_Z_INFO_TILE_MODE_INDEX_MASK; 			z.z_info.tile_surface_enable =
-			// KYTY_PM4_GET(buffer[0], DB_Z_INFO, TILE_SURFACE_ENABLE) != 0;
-			// z.z_info.zrange_precision    = (buffer[0] >> Pm4::DB_Z_INFO_ZRANGE_PRECISION_SHIFT) &
-			// Pm4::DB_Z_INFO_ZRANGE_PRECISION_MASK;
-
-			z.z_info.format      = KYTY_PM4_GET(buffer[0], DB_Z_INFO, FORMAT);
-			z.z_info.num_samples = KYTY_PM4_GET(buffer[0], DB_Z_INFO, NUM_SAMPLES);
-			z.z_info.embedded_sample_locations =
-			    KYTY_PM4_GET(buffer[0], DB_Z_INFO, ITERATE_FLUSH) != 0;
-			z.z_info.partially_resident =
-			    KYTY_PM4_GET(buffer[0], DB_Z_INFO, PARTIALLY_RESIDENT) != 0;
-			z.z_info.num_mip_levels  = KYTY_PM4_GET(buffer[0], DB_Z_INFO, MAXMIP);
-			z.z_info.tile_mode_index = KYTY_PM4_GET(buffer[0], DB_Z_INFO, TILE_MODE_INDEX);
-			z.z_info.plane_compression =
-			    KYTY_PM4_GET(buffer[0], DB_Z_INFO, DECOMPRESS_ON_N_ZPLANES);
-			z.z_info.expclear_enabled = KYTY_PM4_GET(buffer[0], DB_Z_INFO, ALLOW_EXPCLEAR) != 0;
-			z.z_info.tile_surface_enable =
-			    KYTY_PM4_GET(buffer[0], DB_Z_INFO, TILE_SURFACE_ENABLE) != 0;
-			z.z_info.zrange_precision = KYTY_PM4_GET(buffer[0], DB_Z_INFO, ZRANGE_PRECISION);
-
-			//			z.stencil_info.expclear_enabled     = (buffer[1] & 0x08000000u) != 0;
-			//			z.stencil_info.tile_split           = (buffer[1] >> 13u) & 0x7u;
-			//			z.stencil_info.format               = KYTY_PM4_GET(buffer[1],
-			// DB_STENCIL_INFO, FORMAT); 			z.stencil_info.tile_mode_index      =
-			// KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, TILE_MODE_INDEX);
-			//			z.stencil_info.tile_stencil_disable = KYTY_PM4_GET(buffer[1],
-			// DB_STENCIL_INFO, TILE_STENCIL_DISABLE);
-			z.stencil_info.format = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, FORMAT);
-			z.stencil_info.texture_compatible_stencil =
-			    KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, ITERATE_FLUSH) != 0;
-			z.stencil_info.partially_resident =
-			    KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, PARTIALLY_RESIDENT) != 0;
-			z.stencil_info.tile_split = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, RESERVED_FIELD_1);
-			z.stencil_info.tile_mode_index =
-			    KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, TILE_MODE_INDEX);
-			z.stencil_info.expclear_enabled =
-			    KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, ALLOW_EXPCLEAR) != 0;
-			z.stencil_info.tile_stencil_disable =
-			    KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, TILE_STENCIL_DISABLE) != 0;
+			z.z_info       = HW::DepthZInfo::Decode(buffer[0]);
+			z.stencil_info = HW::DepthStencilInfo::Decode(buffer[1]);
 
 			z.z_read_base_addr        = static_cast<uint64_t>(buffer[2]) << 8u;
 			z.stencil_read_base_addr  = static_cast<uint64_t>(buffer[3]) << 8u;
@@ -1253,26 +1186,7 @@ KYTY_HW_CTX_PARSER(HwCtxSetStencilInfo) {
 	EXIT_NOT_IMPLEMENTED(cmd_id != 0xC0016900);
 	EXIT_NOT_IMPLEMENTED(cmd_offset != Pm4::DB_STENCIL_INFO);
 
-	HW::DepthStencilInfo r;
-
-	//	r.expclear_enabled = (buffer[0] & 0x08000000u) != 0;
-	//	r.tile_split       = (buffer[0] >> 13u) & 0x7u;
-	//	r.format          = (buffer[0] >> Pm4::DB_STENCIL_INFO_FORMAT_SHIFT) &
-	// Pm4::DB_STENCIL_INFO_FORMAT_MASK; 	r.tile_mode_index = (buffer[0] >>
-	// Pm4::DB_STENCIL_INFO_TILE_MODE_INDEX_SHIFT) & Pm4::DB_STENCIL_INFO_TILE_MODE_INDEX_MASK;
-	//	r.tile_stencil_disable =
-	//	    ((buffer[0] >> Pm4::DB_STENCIL_INFO_TILE_STENCIL_DISABLE_SHIFT) &
-	// Pm4::DB_STENCIL_INFO_TILE_STENCIL_DISABLE_MASK) != 0;
-
-	r.format                     = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, FORMAT);
-	r.texture_compatible_stencil = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, ITERATE_FLUSH) != 0;
-	r.partially_resident   = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, PARTIALLY_RESIDENT) != 0;
-	r.tile_split           = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, RESERVED_FIELD_1);
-	r.tile_mode_index      = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, TILE_MODE_INDEX);
-	r.expclear_enabled     = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, ALLOW_EXPCLEAR) != 0;
-	r.tile_stencil_disable = KYTY_PM4_GET(buffer[1], DB_STENCIL_INFO, TILE_STENCIL_DISABLE) != 0;
-
-	cp.GetCtx().SetDepthStencilInfo(r);
+	cp.GetCtx().SetDepthStencilInfo(HW::DepthStencilInfo::Decode(buffer[0]));
 
 	return 1;
 }
@@ -1764,231 +1678,11 @@ static bool HwUcTrySetFakeRegisterRange(uint32_t cmd_offset, const uint32_t* buf
 	return true;
 }
 
-// NOLINTNEXTLINE(readability-function-cognitive-complexity)
 KYTY_CP_OP_PARSER(CpOpAcquireMem) {
 	KYTY_PROFILER_FUNCTION();
 
 	EXIT_NOT_IMPLEMENTED(cmd_id != 0xC0055800 && cmd_id != 0xc0061050);
-
-	bool custom = (cmd_id == 0xc0061050);
-
-	uint32_t                  engine       = buffer[0] >> 31u;
-	uint32_t                  stall_mode   = (custom ? 1u : engine);
-	uint32_t                  cache_action = buffer[0] & 0x7fffffffu;
-	uint64_t                  size_lo      = buffer[1];
-	uint32_t                  size_hi      = buffer[2];
-	uint64_t                  base_lo      = buffer[3];
-	uint32_t                  base_hi      = buffer[4];
-	uint32_t                  poll         = buffer[5];
-	[[maybe_unused]] uint32_t gcr_cntl     = (custom ? buffer[6] : 0);
-
-	uint32_t target_mask     = cache_action & 0x00007FC0u;
-	uint32_t extended_action = cache_action & 0x2E000000u;
-	uint32_t action =
-	    ((cache_action & 0x00C00000u) >> 0x12u) | ((cache_action & 0x00058000u) >> 0xfu);
-
-	if (custom && engine > 1) {
-		LOGF("\t warning: custom acquire_mem unsupported engine: %" PRIu32 "\n", engine);
-	}
-
-	// EXIT_NOT_IMPLEMENTED(stall_mode != 1);
-	EXIT_NOT_IMPLEMENTED(size_hi != 0);
-	EXIT_NOT_IMPLEMENTED(base_hi != 0);
-	if (poll != 10) {
-		LOGF("\t warning: acquire_mem unexpected poll interval: %" PRIu32 "\n", poll);
-	}
-
-	switch (cache_action) {
-		case 0x00000000: {
-			if (custom && gcr_cntl != 0) {
-				LOGF("\t custom acquire_mem GCR-only barrier, gcr_cntl = 0x%08" PRIx32
-				     ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
-				     gcr_cntl, base_lo << 8u, size_lo << 8u);
-
-				cp.MemoryBarrier();
-				if ((gcr_cntl & AcquireGcrGl2Writeback) != 0) {
-					cp.SynchronizeGpu();
-				}
-			}
-		} break;
-		case 0x00000040:
-		case 0x00003fc0:
-		case 0x00004000:
-		case 0x00007fc0: {
-			// target_mask set, no CB/DB action bits. Treat as an ordering barrier.
-			EXIT_IF(target_mask != cache_action);
-			EXIT_IF(extended_action != 0x00000000);
-			EXIT_IF(action != 0x00);
-
-			LOGF("\t temporary: acquire_mem target-mask-only barrier, target_mask = 0x%08" PRIx32
-			     ", gcr_cntl = 0x%08" PRIx32 ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
-			     target_mask, gcr_cntl, base_lo << 8u, size_lo << 8u);
-
-			cp.MemoryBarrier();
-		} break;
-		case 0x02000000: {
-			// target_mask:     0x00000000 (none)
-			// extended_action: 0x02000000 (FlushAndInvalidateCbCache)
-			// action:          0x00 (none)
-			EXIT_IF(target_mask != 0x00000000);
-			EXIT_IF(extended_action != 0x02000000);
-			EXIT_IF(action != 0x00);
-
-			LOGF("\t temporary: acquire_mem CB-cache-only barrier, gcr_cntl = 0x%08" PRIx32
-			     ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
-			     gcr_cntl, base_lo << 8u, size_lo << 8u);
-
-			cp.MemoryBarrier();
-		} break;
-		case 0x04000000: {
-			// target_mask:     0x00000000 (none)
-			// extended_action: 0x04000000 (FlushAndInvalidateDbCache)
-			// action:          0x00 (none)
-			EXIT_IF(target_mask != 0x00000000);
-			EXIT_IF(extended_action != 0x04000000);
-			EXIT_IF(action != 0x00);
-
-			LOGF("\t temporary: acquire_mem DB-cache-only barrier, gcr_cntl = 0x%08" PRIx32
-			     ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
-			     gcr_cntl, base_lo << 8u, size_lo << 8u);
-
-			cp.MemoryBarrier();
-		} break;
-		case 0x04004000:
-		case 0x04007fc0: {
-			// target_mask:     0x00004000 (Depth Target), 0x00007fc0 (all rt and depth)
-			// extended_action: 0x04000000 (FlushAndInvalidateDbCache)
-			// action:          0x00 (none)
-			EXIT_IF(target_mask != 0x00004000 && target_mask != 0x00007FC0);
-			EXIT_IF(extended_action != 0x04000000);
-			EXIT_IF(action != 0x00);
-
-			LOGF("\t temporary: acquire_mem DB target barrier, target_mask = 0x%08" PRIx32
-			     ", gcr_cntl = 0x%08" PRIx32 ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
-			     target_mask, gcr_cntl, base_lo << 8u, size_lo << 8u);
-
-			if (size_lo != 0) {
-				cp.DepthStencilBarrier(base_lo << 8u, size_lo << 8u);
-			} else {
-				cp.MemoryBarrier();
-			}
-		} break;
-		case 0x02c40040:
-		case 0x02c43fc0:
-		case 0x02c47fc0: {
-			// target_mask:     0x00000040 (rt0), 0x00003fc0 (all rt), 0x00007fc0 (all rt and depth)
-			// extended_action: 0x02000000 (FlushAndInvalidateCbCache)
-			// action:          0x38 (WriteBackAndInvalidateL1andL2)
-			EXIT_IF(target_mask != 0x00000040 && target_mask != 0x00003FC0 &&
-			        target_mask != 0x00007FC0);
-			EXIT_IF(extended_action != 0x02000000);
-			EXIT_IF(action != 0x38);
-			EXIT_NOT_IMPLEMENTED(size_lo == 0);
-			EXIT_NOT_IMPLEMENTED(base_lo == 0);
-
-			cp.RenderTextureBarrier(base_lo << 8u, size_lo << 8u);
-			cp.SynchronizeGpu();
-		} break;
-		case 0x02003fc0:
-		case 0x02007fc0: {
-			// target_mask:     0x00003FC0 (all rt), 0x00007fc0 (all rt and depth)
-			// extended_action: 0x02000000 (FlushAndInvalidateCbCache)
-			// action:          0x00 (none)
-			EXIT_IF(target_mask != 0x00003FC0 && target_mask != 0x00007fc0);
-			EXIT_IF(extended_action != 0x02000000);
-			EXIT_IF(action != 0x00);
-
-			if (size_lo == 0) {
-				if (base_lo != 0) {
-					LOGF("\t warning: acquire_mem CB-cache barrier with non-zero base");
-				}
-
-				cp.MemoryBarrier();
-			} else {
-				EXIT_NOT_IMPLEMENTED(base_lo == 0);
-
-				cp.RenderTextureBarrier(base_lo << 8u, size_lo << 8u);
-			}
-		} break;
-		case 0x00C40000: {
-			// target_mask:     0x00000000 (none)
-			// extended_action: 0x00000000 (none)
-			// action:          0x38 (WriteBackAndInvalidateL1andL2)
-			EXIT_IF(target_mask != 0x00000000);
-			EXIT_IF(extended_action != 0x00000000);
-			EXIT_IF(action != 0x38);
-			EXIT_NOT_IMPLEMENTED(size_lo != 1);
-			EXIT_NOT_IMPLEMENTED(base_lo != 0);
-
-			cp.MemoryBarrier();
-			cp.SynchronizeGpu();
-		} break;
-		case 0x00400000: {
-			// target_mask:     0x00000000 (none)
-			// extended_action: 0x00000000 (none)
-			// action:          0x10 (InvalidateL1)
-			EXIT_IF(target_mask != 0x00000000);
-			EXIT_IF(extended_action != 0x00000000);
-			EXIT_IF(action != 0x10);
-			EXIT_NOT_IMPLEMENTED(size_lo != 1);
-			EXIT_NOT_IMPLEMENTED(base_lo != 0);
-
-			cp.MemoryBarrier();
-		} break;
-		case 0x04c44000: {
-			// target_mask:     0x00004000 (Depth Target)
-			// extended_action: 0x04000000 (FlushAndInvalidateDbCache)
-			// action:          0x38 (WriteBackAndInvalidateL1andL2)
-			EXIT_IF(target_mask != 0x00004000);
-			EXIT_IF(extended_action != 0x04000000);
-			EXIT_IF(action != 0x38);
-
-			cp.DepthStencilBarrier(base_lo << 8u, size_lo << 8u);
-			cp.SynchronizeGpu();
-		} break;
-
-		case 0x06000040:
-		case 0x06000080:
-		case 0x06003fc0:
-		case 0x06007fc0: {
-			// target_mask:     0x00000040 (rt0), 0x00000080 (rt1), 0x00003fc0 (all rt), 0x00007fc0
-			// (all rt and depth) extended_action: 0x06000000 (Flush Cb & Db) action:          0x00
-			// (none)
-			if (gcr_cntl != 0 && gcr_cntl != 0x280 && gcr_cntl != 0x300) {
-				LOGF("\t temporary: acquire_mem CB+DB barrier with unhandled GCR control "
-				     "0x%08" PRIx32 "\n",
-				     gcr_cntl);
-			}
-
-			EXIT_IF(target_mask != 0x00000040 && target_mask != 0x00000080 &&
-			        target_mask != 0x00003fc0 && target_mask != 0x00007fc0);
-			EXIT_IF(extended_action != 0x06000000);
-			EXIT_IF(action != 0x00);
-
-			if (size_lo != 0) {
-				if ((target_mask & 0x00003fc0) != 0) {
-					cp.RenderTextureBarrier(base_lo << 8u, size_lo << 8u);
-				}
-				if ((target_mask & 0x00004000) != 0) {
-					cp.DepthStencilBarrier(base_lo << 8u, size_lo << 8u);
-				}
-			} else {
-				cp.MemoryBarrier();
-			}
-		} break;
-
-		default:
-			EXIT("unknown barrier: 0x%08" PRIx32 ", 0x%08" PRIx32 ", 0x%08" PRIx32 ", 0x%08" PRIx32
-			     "\n",
-			     cache_action, target_mask, extended_action, action);
-	}
-
-	if (stall_mode == 0) {
-		cp.BufferFlush();
-		cp.BufferWait();
-	}
-
-	return (custom ? 7 : 6);
+	return (cmd_id == 0xc0061050 ? 7 : 6);
 }
 
 KYTY_CP_OP_PARSER(CpOpDispatchDirect) {
@@ -2166,10 +1860,10 @@ KYTY_CP_OP_PARSER(CpOpBranch) {
 	     reinterpret_cast<uint64_t>(else_buffer), else_num_dw);
 
 	if (take_then) {
-		cp.Run(then_buffer, then_num_dw);
+		cp.ProcessIndirectBuffer(then_buffer, then_num_dw);
 	} else if (mode == 2 && else_num_dw != 0) {
 		EXIT_NOT_IMPLEMENTED(else_buffer == nullptr);
-		cp.Run(else_buffer, else_num_dw);
+		cp.ProcessIndirectBuffer(else_buffer, else_num_dw);
 	}
 
 	return payload_dw;
@@ -2250,9 +1944,6 @@ KYTY_CP_OP_PARSER(CpOpDmaData) {
 	const uint64_t dst      = buffer[3] | (static_cast<uint64_t>(buffer[4]) << 32u);
 
 	if (control == 0x60000000 && dst == 0x0003022c && (control2 >> 21u) == 0x141u) {
-		auto* addr = reinterpret_cast<void*>(src);
-
-		cp.PrefetchL2(addr, control2 & 0x1fffffu);
 		return 6;
 	}
 
@@ -2496,7 +2187,7 @@ KYTY_CP_OP_PARSER(CpOpIncrementCeCounter) {
 	EXIT_NOT_IMPLEMENTED(cmd_id != 0xC0008400);
 	EXIT_NOT_IMPLEMENTED(buffer[0] != 1);
 
-	cp.IncremenetCe();
+	cp.IncrementCe();
 
 	return 1;
 }
@@ -2507,7 +2198,7 @@ KYTY_CP_OP_PARSER(CpOpIncrementDeCounter) {
 	EXIT_NOT_IMPLEMENTED(cmd_id != 0xC0008500);
 	EXIT_NOT_IMPLEMENTED(buffer[0] != 0);
 
-	cp.IncremenetDe();
+	cp.IncrementDe();
 
 	return 1;
 }
@@ -2607,7 +2298,7 @@ KYTY_CP_OP_PARSER(CpOpIndirectBuffer) {
 
 	GraphicsDbgDumpDcb("ci", indirect_num_dw, indirect_buffer);
 
-	cp.Run(indirect_buffer, indirect_num_dw);
+	cp.ProcessIndirectBuffer(indirect_buffer, indirect_num_dw);
 
 	return 3;
 }
@@ -2800,11 +2491,10 @@ KYTY_CP_OP_PARSER(CpOpMarker) {
 	// EXIT_NOT_IMPLEMENTED(cmd_id != 0xC0001000);
 
 	uint32_t id     = buffer[0] & 0xfffu;
-	uint32_t align  = (buffer[0] >> 12u) & 0xfu;
 	uint32_t len_dw = ((cmd_id >> 16u) & 0x3fffu);
 
 	switch (id) {
-		case 0x0: cp.SetEmbeddedDataMarker(buffer + 1, len_dw, align); break;
+		case 0x0: break;
 		case 0x4: cp.SetUserDataMarker(HW::UserSgprType::Vsharp); break;
 		case 0xd: cp.SetUserDataMarker(HW::UserSgprType::Region); break;
 		case 0x777: {
@@ -2876,8 +2566,6 @@ KYTY_CP_OP_PARSER(CpOpPopMarker) {
 		LOGF("Pop marker\n");
 	}
 
-	cp.PopMarker();
-
 	return dw_num + 1;
 }
 
@@ -2893,8 +2581,6 @@ KYTY_CP_OP_PARSER(CpOpPushMarker) {
 		LOGF("Push marker: %s\n", str);
 	}
 
-	cp.PushMarker(str);
-
 	return dw_num + 1;
 }
 
@@ -2939,7 +2625,7 @@ KYTY_CP_OP_PARSER(CpOpReleaseMem) {
 
 	if (data_sel == 0 || interrupt_selector == 4) {
 		if (eop_event_type != 0x28 || gcr_cntl != 0) {
-			cp.MemoryBarrier();
+			cp.EmitGlobalBarrier();
 		}
 
 		if (gl2_writeback) {
@@ -2953,7 +2639,7 @@ KYTY_CP_OP_PARSER(CpOpReleaseMem) {
 
 	if (release_dst == ReleaseMemDstMemory && dst_gpu_addr == nullptr) {
 		if (eop_event_type != 0x28 || gcr_cntl != 0) {
-			cp.MemoryBarrier();
+			cp.EmitGlobalBarrier();
 		}
 
 		if (gl2_writeback) {
@@ -2966,7 +2652,7 @@ KYTY_CP_OP_PARSER(CpOpReleaseMem) {
 	}
 
 	if (ReleaseMemGcrNeedsBarrier(eop_event_type, gcr_cntl)) {
-		cp.MemoryBarrier();
+		cp.EmitGlobalBarrier();
 	}
 
 	auto cache_action = ReleaseMemCacheActionFromGcr(gcr_cntl);
@@ -3986,18 +3672,7 @@ void GraphicsInitJmpTablesCxIndirect() {
 	};
 
 	g_hw_ctx_indirect_func[Pm4::DB_Z_INFO] = [](KYTY_HW_CTX_INDIRECT_ARGS) {
-		HW::DepthZInfo r;
-		r.format                    = KYTY_PM4_GET(value, DB_Z_INFO, FORMAT);
-		r.num_samples               = KYTY_PM4_GET(value, DB_Z_INFO, NUM_SAMPLES);
-		r.embedded_sample_locations = KYTY_PM4_GET(value, DB_Z_INFO, ITERATE_FLUSH) != 0;
-		r.partially_resident        = KYTY_PM4_GET(value, DB_Z_INFO, PARTIALLY_RESIDENT) != 0;
-		r.num_mip_levels            = KYTY_PM4_GET(value, DB_Z_INFO, MAXMIP);
-		r.tile_mode_index           = KYTY_PM4_GET(value, DB_Z_INFO, TILE_MODE_INDEX);
-		r.plane_compression         = KYTY_PM4_GET(value, DB_Z_INFO, DECOMPRESS_ON_N_ZPLANES);
-		r.expclear_enabled          = KYTY_PM4_GET(value, DB_Z_INFO, ALLOW_EXPCLEAR) != 0;
-		r.tile_surface_enable       = KYTY_PM4_GET(value, DB_Z_INFO, TILE_SURFACE_ENABLE) != 0;
-		r.zrange_precision          = KYTY_PM4_GET(value, DB_Z_INFO, ZRANGE_PRECISION);
-		cp.GetCtx().SetDepthZInfo(r);
+		cp.GetCtx().SetDepthZInfo(HW::DepthZInfo::Decode(value));
 	};
 
 	g_hw_ctx_indirect_func[Pm4::DB_DEPTH_INFO] = [](KYTY_HW_CTX_INDIRECT_ARGS) {
@@ -4025,15 +3700,7 @@ void GraphicsInitJmpTablesCxIndirect() {
 	};
 
 	g_hw_ctx_indirect_func[Pm4::DB_STENCIL_INFO] = [](KYTY_HW_CTX_INDIRECT_ARGS) {
-		HW::DepthStencilInfo r;
-		r.format                     = KYTY_PM4_GET(value, DB_STENCIL_INFO, FORMAT);
-		r.texture_compatible_stencil = KYTY_PM4_GET(value, DB_STENCIL_INFO, ITERATE_FLUSH) != 0;
-		r.partially_resident   = KYTY_PM4_GET(value, DB_STENCIL_INFO, PARTIALLY_RESIDENT) != 0;
-		r.tile_split           = KYTY_PM4_GET(value, DB_STENCIL_INFO, RESERVED_FIELD_1);
-		r.tile_mode_index      = KYTY_PM4_GET(value, DB_STENCIL_INFO, TILE_MODE_INDEX);
-		r.expclear_enabled     = KYTY_PM4_GET(value, DB_STENCIL_INFO, ALLOW_EXPCLEAR) != 0;
-		r.tile_stencil_disable = KYTY_PM4_GET(value, DB_STENCIL_INFO, TILE_STENCIL_DISABLE) != 0;
-		cp.GetCtx().SetDepthStencilInfo(r);
+		cp.GetCtx().SetDepthStencilInfo(HW::DepthStencilInfo::Decode(value));
 	};
 
 	g_hw_ctx_indirect_func[Pm4::DB_Z_READ_BASE] = [](KYTY_HW_CTX_INDIRECT_ARGS) {

src/graphics/guest_gpu/gpu_defs.h

@@ -142,6 +142,24 @@ enum class StencilFormat : uint32_t {
 	k8UInt   = 1,
 };
 
+enum class TextureCompatiblePlaneCompression : uint32_t {
+	kDisable = 0x00000000,
+	kEnable  = 0x02900800,
+	kBitMask = 0x02900800,
+};
+
+enum class TextureCompatibleStencil : uint32_t {
+	kDisable = 0x00000000,
+	kEnable  = 0x00100800,
+	kBitMask = 0x00100800,
+};
+
+enum class ZCompareBase : uint32_t {
+	kZMin    = 0x00000000,
+	kZMax    = 0x80000000,
+	kBitMask = 0x80000000,
+};
+
 enum class TileMode : uint32_t {
 	kLinear       = 0x00,
 	kStandard256B = 0x01,

src/graphics/guest_gpu/graphicsRun.h

@@ -3,33 +3,59 @@
 
 #include "common/abi.h"
 #include "common/common.h"
+#include "common/uniqueFunction.h"
+
+#include <memory>
 
 namespace Libs::Graphics {
 
 class CommandProcessor;
+class GpuState;
+class RenderContext;
 
-class GraphicsRunSubmissionLock final {
+class Gpu final {
 public:
-	GraphicsRunSubmissionLock();
-	~GraphicsRunSubmissionLock();
-	KYTY_CLASS_NO_COPY(GraphicsRunSubmissionLock);
+	explicit Gpu(RenderContext& renderer);
+	~Gpu();
+	KYTY_CLASS_NO_COPY(Gpu);
+
+	void               Shutdown();
+	[[nodiscard]] bool IsStopping();
+	void               SendCommand(Common::UniqueFunction<void>&& command);
+	void               SendCommandSync(Common::UniqueFunction<void>&& command);
+	void SendCommandSyncWithProcessor(Common::UniqueFunction<void, CommandProcessor&>&& command);
+
+	void Submit(uint32_t* draw_commands, uint32_t draw_size_dw, uint32_t* constant_commands,
+	            uint32_t constant_size_dw, bool trigger_agc_interrupt_on_done = false);
+	void SubmitCompute(uint32_t queue, uint32_t* commands, uint32_t size_dw,
+	                   bool trigger_agc_interrupt_on_done = false);
+	void SubmitFlipPreparation(uint64_t request_id);
+	void Done();
+	[[nodiscard]] int GetFrameNum() const;
+
+	[[nodiscard]] static bool              IsCommandProcessorThread() noexcept;
+	[[nodiscard]] static CommandProcessor* CurrentCommandProcessor() noexcept;
+	[[nodiscard]] static bool              SubmissionLockHeld() noexcept;
+	[[nodiscard]] static bool              MutexHeld() noexcept;
+
+	class SubmissionLock final {
+	public:
+		explicit SubmissionLock(Gpu& gpu);
+		~SubmissionLock();
+		KYTY_CLASS_NO_COPY(SubmissionLock);
+
+	private:
+		Gpu& m_gpu;
+	};
+
+private:
+	friend class SubmissionLock;
+
+	void PauseSubmissions();
+	void ResumeSubmissions();
+
+	std::unique_ptr<GpuState> m_state;
 };
-
-void GraphicsRunInit();
-
-void GraphicsRunSubmit(uint32_t* cmd_draw_buffer, uint32_t num_draw_dw, uint32_t* cmd_const_buffer,
-                       uint32_t num_const_dw, bool trigger_agc_interrupt_on_done = false);
-void GraphicsRunSubmitCompute(uint32_t queue, uint32_t* cmd_buffer, uint32_t num_dw,
-                              bool trigger_agc_interrupt_on_done = false);
-void GraphicsRunSubmitFlipPreparation();
-void GraphicsRunWait();
-void GraphicsRunDone();
-int  GraphicsRunGetFrameNum();
-[[nodiscard]] bool              GraphicsRunIsCommandProcessorThread() noexcept;
-[[nodiscard]] CommandProcessor* GraphicsRunCurrentCommandProcessor() noexcept;
-void                            GraphicsRunFinishCommandProcessors();
-[[nodiscard]] bool              GraphicsRunSubmissionLockHeld() noexcept;
-[[nodiscard]] bool              GraphicsRunGpuLockHeld() noexcept;
 } // namespace Libs::Graphics
 
 #endif /* EMULATOR_INCLUDE_EMULATOR_GRAPHICS_GRAPHICSRUN_H_ */

src/graphics/guest_gpu/hardwareContext.h

@@ -3,6 +3,7 @@
 
 #include "common/abi.h"
 #include "common/common.h"
+#include "graphics/guest_gpu/gpu_defs.h"
 
 namespace Libs::Graphics::HW {
 
@@ -131,26 +132,66 @@ struct RenderTarget {
 };
 
 struct DepthZInfo {
-	uint32_t format                    = 0;
-	uint32_t tile_mode_index           = 0;
-	uint32_t num_samples               = 0;
-	uint32_t zrange_precision          = 0;
-	bool     tile_surface_enable       = false;
-	bool     expclear_enabled          = false;
-	bool     embedded_sample_locations = false;
-	bool     partially_resident        = false;
-	uint8_t  num_mip_levels            = 0;
-	uint8_t  plane_compression         = 0;
+	uint32_t                                    format      = 0;
+	uint32_t                                    num_samples = 0;
+	Prospero::TextureCompatiblePlaneCompression texture_compatibility =
+	    Prospero::TextureCompatiblePlaneCompression::kDisable;
+	Prospero::ZCompareBase z_compare_base     = Prospero::ZCompareBase::kZMin;
+	bool                   htile_acceleration = false;
+	bool                   expclear_enabled   = false;
+	bool                   partially_resident = false;
+	uint8_t                max_mip_level      = 0;
+
+	[[nodiscard]] static DepthZInfo Decode(uint32_t value) {
+		DepthZInfo info;
+		info.format                = value & 0x3u;
+		info.num_samples           = (value >> 2u) & 0x3u;
+		info.texture_compatibility = static_cast<Prospero::TextureCompatiblePlaneCompression>(
+		    value & Prospero::GpuEnumValue(Prospero::TextureCompatiblePlaneCompression::kBitMask));
+		info.partially_resident = (value & 0x00001000u) != 0;
+		info.max_mip_level      = static_cast<uint8_t>((value >> 16u) & 0x0fu);
+		info.expclear_enabled   = (value & 0x08000000u) != 0;
+		info.htile_acceleration = (value & 0x20000000u) != 0;
+		info.z_compare_base     = static_cast<Prospero::ZCompareBase>(
+		    value & Prospero::GpuEnumValue(Prospero::ZCompareBase::kBitMask));
+		return info;
+	}
+
+	[[nodiscard]] bool HasValidTextureCompatibility() const {
+		switch (texture_compatibility) {
+			case Prospero::TextureCompatiblePlaneCompression::kDisable:
+			case Prospero::TextureCompatiblePlaneCompression::kEnable: return true;
+			default: return false;
+		}
+	}
 };
 
 struct DepthStencilInfo {
-	uint32_t format                     = 0;
-	uint32_t tile_mode_index            = 0;
-	uint32_t tile_split                 = 0;
-	bool     expclear_enabled           = false;
-	bool     tile_stencil_disable       = false;
-	bool     texture_compatible_stencil = false;
-	bool     partially_resident         = false;
+	uint32_t                           format = 0;
+	Prospero::TextureCompatibleStencil texture_compatibility =
+	    Prospero::TextureCompatibleStencil::kDisable;
+	bool expclear_enabled       = false;
+	bool htile_stencil_disabled = false;
+	bool partially_resident     = false;
+
+	[[nodiscard]] static DepthStencilInfo Decode(uint32_t value) {
+		DepthStencilInfo info;
+		info.format                = value & 0x1u;
+		info.texture_compatibility = static_cast<Prospero::TextureCompatibleStencil>(
+		    value & Prospero::GpuEnumValue(Prospero::TextureCompatibleStencil::kBitMask));
+		info.partially_resident     = (value & 0x00001000u) != 0;
+		info.expclear_enabled       = (value & 0x08000000u) != 0;
+		info.htile_stencil_disabled = (value & 0x20000000u) != 0;
+		return info;
+	}
+
+	[[nodiscard]] bool HasValidTextureCompatibility() const {
+		switch (texture_compatibility) {
+			case Prospero::TextureCompatibleStencil::kDisable:
+			case Prospero::TextureCompatibleStencil::kEnable: return true;
+			default: return false;
+		}
+	}
 };
 
 struct DepthRenderTargetDepthInfo {

src/graphics/guest_gpu/tile.cpp

@@ -406,8 +406,8 @@ struct TextureBlockLayout {
 
 static bool GetTextureBlockLayout(uint32_t format, uint32_t tile, TextureBlockLayout& out) {
 	uint32_t width_log2 = 0, height_log2 = 0;
-	if (tile == 1 && Gen5Standard256BLayout(format, &out.bytes, &out.texel_width,
-	                                        &out.texel_height, &width_log2, &height_log2)) {
+	if (tile == 1 && Gen5Standard256BLayout(format, &out.bytes, &out.texel_width, &out.texel_height,
+	                                        &width_log2, &height_log2)) {
 		out.block_size = 256;
 	} else if (tile == 5 && Gen5Standard4KBLayout(format, &out.bytes, &out.texel_width,
 	                                              &out.texel_height, &width_log2, &height_log2)) {
@@ -524,7 +524,7 @@ static void SetMacroMipLayout(const TextureBlockLayout& block, uint32_t tile, ui
 }
 
 bool TileGetTextureVolumeLayout(uint32_t format, uint32_t width, uint32_t height, uint32_t depth,
-	                            uint32_t levels, uint32_t tile, TileVolumeLayout& out) {
+                                uint32_t levels, uint32_t tile, TileVolumeLayout& out) {
 	if (width == 0 || height == 0 || depth == 0 || levels == 0 || levels > 16) {
 		return false;
 	}
@@ -543,21 +543,26 @@ bool TileGetTextureVolumeLayout(uint32_t format, uint32_t width, uint32_t height
 	TileBlockLayout block {};
 	if (!TileGetBlockLayout(family, element.bytes, block)) return false;
 
-	out                   = {};
-	out.family            = family;
-	out.bytes_per_element = element.bytes;
-	out.texel_width       = element.texel_width;
-	out.texel_height      = element.texel_height;
-	out.block_depth       = block.block_depth;
-	out.first_tail_level  = levels;
+	out                    = {};
+	out.family             = family;
+	out.bytes_per_element  = element.bytes;
+	out.texel_width        = element.texel_width;
+	out.texel_height       = element.texel_height;
+	out.block_depth        = block.block_depth;
+	out.first_tail_level   = levels;
 	const uint32_t width0  = (width + element.texel_width - 1u) / element.texel_width;
 	const uint32_t height0 = (height + element.texel_height - 1u) / element.texel_height;
 	const bool     thick4  = family == TileBlockFamily::Standard4KB3D;
 	const bool     thick64 =
 	    family == TileBlockFamily::Standard64KB3D || family == TileBlockFamily::Prt64KB3D;
-	const uint32_t max_tail    = thick4 ? 5u : (thick64 ? 10u : 12u);
-	uint32_t       tail_width  = thick4 ? block.block_width : block.block_width >> 1u;
-	uint32_t       tail_height = thick4 ? block.block_height >> 1u : block.block_height;
+	uint32_t max_tail = 12u;
+	if (thick4) {
+		max_tail = 5u;
+	} else if (thick64) {
+		max_tail = 10u;
+	}
+	uint32_t tail_width  = thick4 ? block.block_width : block.block_width >> 1u;
+	uint32_t tail_height = thick4 ? block.block_height >> 1u : block.block_height;
 	if (family == TileBlockFamily::Depth64KB && element.bytes < 4) {
 		tail_width  = 64;
 		tail_height = 128;
@@ -574,18 +579,23 @@ bool TileGetTextureVolumeLayout(uint32_t format, uint32_t width, uint32_t height
 		}
 		out.level_widths[level]  = AlignUp(mip_width, block.block_width);
 		out.level_heights[level] = AlignUp(mip_height, block.block_height);
-		out.level_sizes[level]   = static_cast<uint64_t>(block.block_depth) *
-		                            out.level_widths[level] * out.level_heights[level] *
-		                            element.bytes;
+		out.level_sizes[level] = static_cast<uint64_t>(block.block_depth) *
+		                         out.level_widths[level] * out.level_heights[level] * element.bytes;
 		out.block_slice_size += out.level_sizes[level];
 	}
 
-	const auto bytes_log2 = std::countr_zero(element.bytes);
+	const auto                 bytes_log2     = std::countr_zero(element.bytes);
+	const Gen5MipTailLocation* tail_locations = nullptr;
+	if (thick4) {
+		tail_locations = GEN5_MIP_TAIL_LOCATIONS_THICK_4KB[bytes_log2];
+	} else if (thick64) {
+		tail_locations = GEN5_MIP_TAIL_LOCATIONS_THICK_64KB[bytes_log2];
+	} else {
+		tail_locations = GEN5_MIP_TAIL_LOCATIONS_THIN_64KB[bytes_log2];
+	}
 	for (uint32_t level = out.first_tail_level; level < levels; ++level) {
-		const auto index = level - out.first_tail_level;
-		const auto tail = thick4 ? GEN5_MIP_TAIL_LOCATIONS_THICK_4KB[bytes_log2][index]
-		                         : (thick64 ? GEN5_MIP_TAIL_LOCATIONS_THICK_64KB[bytes_log2][index]
-		                                    : GEN5_MIP_TAIL_LOCATIONS_THIN_64KB[bytes_log2][index]);
+		const auto index         = level - out.first_tail_level;
+		const auto tail          = tail_locations[index];
 		out.level_sizes[level]   = block.block_size;
 		out.level_widths[level]  = block.block_width;
 		out.level_heights[level] = block.block_height;
@@ -1047,7 +1057,7 @@ static constexpr uint32_t Depth64KB64XOffsetBytes(uint32_t x);
 static constexpr uint32_t Depth64KB64YOffsetBytes(uint32_t y);
 
 bool TileGetBlockLayout(TileBlockFamily family, uint32_t bytes_per_element,
-	                    TileBlockLayout& layout) {
+                        TileBlockLayout& layout) {
 	if (!std::has_single_bit(bytes_per_element) || bytes_per_element > 16) {
 		return false;
 	}
@@ -1067,13 +1077,25 @@ bool TileGetBlockLayout(TileBlockFamily family, uint32_t bytes_per_element,
 	};
 	switch (family) {
 		case TileBlockFamily::Standard256B:
-			result.block_size   = 256;
-			result.block_width  = bytes_per_element <= 2 ? 16 : (bytes_per_element <= 8 ? 8 : 4);
+			result.block_size = 256;
+			if (bytes_per_element <= 2) {
+				result.block_width = 16;
+			} else if (bytes_per_element <= 8) {
+				result.block_width = 8;
+			} else {
+				result.block_width = 4;
+			}
 			result.block_height = result.block_size / (result.block_width * bytes_per_element);
 			break;
 		case TileBlockFamily::Standard4KB:
-			result.block_size   = 4096;
-			result.block_width  = bytes_per_element <= 2 ? 64 : (bytes_per_element <= 8 ? 32 : 16);
+			result.block_size = 4096;
+			if (bytes_per_element <= 2) {
+				result.block_width = 64;
+			} else if (bytes_per_element <= 8) {
+				result.block_width = 32;
+			} else {
+				result.block_width = 16;
+			}
 			result.block_height = result.block_size / (result.block_width * bytes_per_element);
 			break;
 		case TileBlockFamily::Standard4KB3D: {
@@ -1126,7 +1148,7 @@ bool TileGetBlockLayout(TileBlockFamily family, uint32_t bytes_per_element,
 }
 
 bool TileGetBlockOffset(const TileBlockLayout& layout, uint32_t x, uint32_t y, uint32_t z,
-	                    uint32_t& byte_offset) {
+                        uint32_t& byte_offset) {
 	TileBlockLayout expected {};
 	if (!TileGetBlockLayout(layout.family, layout.bytes_per_element, expected) ||
 	    layout.block_size != expected.block_size || layout.block_width != expected.block_width ||
@@ -1226,12 +1248,12 @@ bool TileGetBlockOffset(const TileBlockLayout& layout, uint32_t x, uint32_t y, u
 }
 
 bool TileGetBlockXor(const TileBlockLayout& layout, uint32_t block_x, uint32_t block_y,
-	                 uint32_t& byte_offset) {
+                     uint32_t& byte_offset) {
 	return TileGetBlockXor(layout, block_x, block_y, 0, byte_offset);
 }
 
 bool TileGetBlockXor(const TileBlockLayout& layout, uint32_t block_x, uint32_t block_y,
-	                 uint32_t block_z, uint32_t& byte_offset) {
+                     uint32_t block_z, uint32_t& byte_offset) {
 	TileBlockLayout expected {};
 	if (!TileGetBlockLayout(layout.family, layout.bytes_per_element, expected) ||
 	    layout.block_size != expected.block_size || layout.block_width != expected.block_width ||
@@ -1377,8 +1399,8 @@ bool TileGetHtileSize(uint32_t width, uint32_t height, TileSizeAlign& htile_size
 }
 
 bool TileGetDepthSize(uint32_t width, uint32_t height, uint32_t pitch, uint32_t z_format,
-	                  uint32_t stencil_format, bool htile, TileSizeAlign& stencil_size,
-	                  TileSizeAlign& htile_size, TileSizeAlign& depth_size,
+                      uint32_t stencil_format, bool htile, TileSizeAlign& stencil_size,
+                      TileSizeAlign& htile_size, TileSizeAlign& depth_size,
                       uint32_t num_fragments_log2) {
 	EXIT_IF(pitch != 0);
 	// Prospero derives uncompressed depth/stencil as independent 64 KiB block surfaces.
@@ -1410,8 +1432,8 @@ bool TileGetDepthSize(uint32_t width, uint32_t height, uint32_t pitch, uint32_t
 		if (depth_bytes_total <= UINT32_MAX && stencil_bytes_total <= UINT32_MAX && htile_valid) {
 			depth_size   = {static_cast<uint32_t>(depth_bytes_total), 65536};
 			stencil_size = stencil_format == 1
-			                    ? TileSizeAlign {static_cast<uint32_t>(stencil_bytes_total), 65536}
-			                    : TileSizeAlign {};
+			                   ? TileSizeAlign {static_cast<uint32_t>(stencil_bytes_total), 65536}
+			                   : TileSizeAlign {};
 			htile_size   = calculated_htile;
 			return true;
 		}
@@ -1441,7 +1463,7 @@ uint32_t TileGetDepthPitch(uint32_t width, uint32_t bytes_per_element,
 }
 
 bool TileGetRenderTargetSize(uint32_t width, uint32_t height, uint32_t pitch,
-	                         uint32_t bytes_per_element, TileSizeAlign& total_size,
+                             uint32_t bytes_per_element, TileSizeAlign& total_size,
                              uint32_t num_fragments_log2) {
 	total_size            = {};
 	uint32_t block_width  = 0;
@@ -1466,7 +1488,7 @@ bool TileGetRenderTargetSize(uint32_t width, uint32_t height, uint32_t pitch,
 
 bool TileGetRenderTargetMipLayout(uint32_t width, uint32_t height, uint32_t pitch,
                                   uint32_t bytes_per_element, uint32_t levels,
-	                              TileSizeAlign& total_size, TileSizeOffset* level_sizes,
+                                  TileSizeAlign& total_size, TileSizeOffset* level_sizes,
                                   TilePaddedSize* padded_size) {
 	total_size = {};
 	if (width == 0 || height == 0 || levels == 0 || levels > 16 ||
@@ -1578,7 +1600,7 @@ void TileGetTextureSize(uint32_t format, uint32_t width, uint32_t height, uint32
 
 void TileGetTextureTotalSize(uint32_t format, uint32_t width, uint32_t height, uint32_t depth,
                              uint32_t pitch, uint32_t levels, uint32_t tile, bool volume_texture,
-	                         TileSizeAlign& total_size) {
+                             TileSizeAlign& total_size) {
 	EXIT_NOT_IMPLEMENTED(depth == 0);
 	if (volume_texture) {
 		TileVolumeLayout volume {};

src/graphics/host_gpu/gpuTiler.cpp

@@ -1,549 +0,0 @@
-#include "graphics/host_gpu/gpuTiler.h"
-
-#include "common/assert.h"
-#include "common/threads.h"
-#include "gpu_tiler_shaders/gpu_tiler_depth_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_prt_3d_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_prt_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_render_target_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_standard256_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_standard4_3d_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_standard4_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_standard64_3d_spv.h"
-#include "gpu_tiler_shaders/gpu_tiler_standard64_spv.h"
-#include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/renderer/render.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/vma.h"
-#include "graphics/host_gpu/vulkanCommon.h"
-
-#include <algorithm>
-#include <array>
-#include <bit>
-#include <cstring>
-#include <memory>
-#include <vector>
-
-namespace Libs::Graphics {
-namespace {
-
-constexpr uint32_t GROUP_SIZE              = 64;
-constexpr uint32_t FAMILY_COUNT            = static_cast<uint32_t>(TileBlockFamily::Count);
-constexpr uint32_t BYTES_PER_ELEMENT_COUNT = 5;
-constexpr uint32_t DIRECTION_COUNT         = 2;
-constexpr uint32_t PIPELINE_COUNT = FAMILY_COUNT * BYTES_PER_ELEMENT_COUNT * DIRECTION_COUNT;
-static_assert(FAMILY_COUNT == 9);
-
-struct Push {
-	uint32_t src_base;
-	uint32_t dst_base;
-	uint32_t width;
-	uint32_t height;
-	uint32_t depth;
-	uint32_t surface_z;
-	uint32_t pitch_bytes;
-	uint32_t slice_bytes;
-	uint32_t blocks_per_row;
-	uint32_t blocks_per_slice;
-	uint32_t tail_x;
-	uint32_t tail_y;
-	uint32_t tail;
-	uint32_t first;
-	uint32_t count;
-};
-static_assert(sizeof(Push) == 60);
-
-struct Shader {
-	const uint32_t* code;
-	size_t          words;
-};
-
-constexpr std::array<Shader, FAMILY_COUNT> SHADERS {{
-    {GPU_TILER_STANDARD256_SPV, std::size(GPU_TILER_STANDARD256_SPV)},
-    {GPU_TILER_STANDARD4_SPV, std::size(GPU_TILER_STANDARD4_SPV)},
-    {GPU_TILER_STANDARD4_3D_SPV, std::size(GPU_TILER_STANDARD4_3D_SPV)},
-    {GPU_TILER_STANDARD64_SPV, std::size(GPU_TILER_STANDARD64_SPV)},
-    {GPU_TILER_STANDARD64_3D_SPV, std::size(GPU_TILER_STANDARD64_3D_SPV)},
-    {GPU_TILER_PRT_SPV, std::size(GPU_TILER_PRT_SPV)},
-    {GPU_TILER_PRT_3D_SPV, std::size(GPU_TILER_PRT_3D_SPV)},
-    {GPU_TILER_RENDER_TARGET_SPV, std::size(GPU_TILER_RENDER_TARGET_SPV)},
-    {GPU_TILER_DEPTH_SPV, std::size(GPU_TILER_DEPTH_SPV)},
-}};
-
-struct Dispatch {
-	Push     push {};
-	uint32_t pipeline_slot = 0;
-	uint32_t elements      = 0;
-};
-
-struct Resources {
-	vk::DescriptorSetLayout                  descriptor_layout = nullptr;
-	vk::PipelineLayout                       pipeline_layout   = nullptr;
-	vk::DescriptorPool                       descriptor_pool   = nullptr;
-	vk::DescriptorSet                        descriptor_set    = nullptr;
-	std::array<vk::Pipeline, PIPELINE_COUNT> pipelines {};
-	VulkanBuffer                             staging;
-	VulkanBuffer                             linear;
-	void*                                    mapped = nullptr;
-};
-
-bool CheckedAdd(uint64_t a, uint64_t b, uint64_t& result) {
-	return b <= UINT64_MAX - a && (result = a + b, true);
-}
-
-bool CheckedMultiply(uint64_t a, uint64_t b, uint64_t& result) {
-	return (a == 0 || b <= UINT64_MAX / a) && (result = a * b, true);
-}
-
-bool CheckedAddProduct(uint64_t& value, uint64_t count, uint64_t stride) {
-	uint64_t bytes = 0;
-	return CheckedMultiply(count, stride, bytes) && CheckedAdd(value, bytes, value);
-}
-
-bool IsRangeValid(uint64_t offset, uint64_t size, uint64_t capacity) {
-	return size != 0 && offset <= capacity && size <= capacity - offset;
-}
-
-uint64_t AlignToDword(uint64_t value) {
-	return (value + 3u) & ~uint64_t {3};
-}
-
-uint32_t GetPipelineSlot(bool to_tiled, TileBlockFamily family, uint32_t bytes_per_element) {
-	const uint32_t direction_index    = to_tiled ? 1u : 0u;
-	const uint32_t family_index       = static_cast<uint32_t>(family);
-	const uint32_t element_size_index = std::countr_zero(bytes_per_element);
-	return (direction_index * FAMILY_COUNT + family_index) * BYTES_PER_ELEMENT_COUNT +
-	       element_size_index;
-}
-
-void Barrier(vk::CommandBuffer command, vk::Buffer buffer, vk::AccessFlags src_access,
-             vk::AccessFlags dst_access, vk::PipelineStageFlags src_stage,
-             vk::PipelineStageFlags dst_stage) {
-	vk::BufferMemoryBarrier barrier {};
-	barrier.sType               = vk::StructureType::eBufferMemoryBarrier;
-	barrier.srcAccessMask       = src_access;
-	barrier.dstAccessMask       = dst_access;
-	barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-	barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-	barrier.buffer              = buffer;
-	barrier.size                = VK_WHOLE_SIZE;
-	command.pipelineBarrier(src_stage, dst_stage, {}, 0, nullptr, 1, &barrier, 0, nullptr);
-}
-
-class TileCompute final {
-public:
-	explicit TileCompute(GraphicContext& graphics): graphics(graphics) {}
-	void Run(bool to_tiled, const void* input, void* output, uint64_t tiled_capacity,
-	         uint64_t linear_capacity, std::span<const GpuTileInfo> infos,
-	         const GpuTileRecord& record);
-	void Release();
-
-private:
-	void Prepare(bool to_tiled, uint64_t tiled_capacity, uint64_t linear_capacity,
-	             std::span<const GpuTileInfo> infos, std::vector<Dispatch>& dispatches) const;
-	void Init();
-	void CreatePipelines(std::span<const Dispatch> dispatches);
-	void CreatePipeline(uint32_t pipeline_slot);
-	void Resize(uint64_t staging_size, uint64_t linear_size);
-	void CreateBuffer(uint64_t size, bool mapped, VulkanBuffer& buffer, void** data) const;
-	void Execute(bool to_tiled, const void* input, void* output, uint64_t tiled_capacity,
-	             uint64_t linear_capacity, std::span<const Dispatch> dispatches,
-	             const GpuTileRecord& record);
-	void Destroy(Resources& target) const;
-
-	GraphicContext& graphics;
-	Resources       resources;
-};
-
-Common::Mutex                g_tiler_mutex;
-std::unique_ptr<TileCompute> g_tiler;
-
-void TileCompute::Prepare(bool to_tiled, uint64_t tiled_capacity, uint64_t linear_capacity,
-                          std::span<const GpuTileInfo> infos,
-                          std::vector<Dispatch>&       dispatches) const {
-	EXIT_IF(infos.empty() || tiled_capacity == 0 || linear_capacity == 0);
-	const auto& limits = graphics.GetPhysicalDeviceProperties().limits;
-	EXIT_NOT_IMPLEMENTED(tiled_capacity > UINT32_MAX || linear_capacity > UINT32_MAX ||
-	                     AlignToDword(tiled_capacity) > limits.maxStorageBufferRange ||
-	                     AlignToDword(linear_capacity) > limits.maxStorageBufferRange);
-
-	dispatches.clear();
-	dispatches.reserve(infos.size());
-	for (const auto& info: infos) {
-		TileBlockLayout block {};
-		const uint32_t  tiled_width  = info.tiled_width != 0 ? info.tiled_width : info.pitch;
-		const uint32_t  tiled_height = info.tiled_height != 0 ? info.tiled_height : info.height;
-		EXIT_NOT_IMPLEMENTED(
-		    !TileGetBlockLayout(info.family, info.bytes_per_element, block) || info.width == 0 ||
-		    info.height == 0 || info.depth == 0 || info.pitch < info.width ||
-		    (!info.tail && (tiled_width < info.width || tiled_height < info.height)) ||
-		    !IsRangeValid(info.linear_offset, info.linear_size, linear_capacity) ||
-		    !IsRangeValid(info.tiled_offset, info.tiled_size, tiled_capacity) ||
-		    (block.block_depth == 1 && info.depth != 1));
-
-		uint64_t elements = 0, pitch_bytes = 0;
-		EXIT_NOT_IMPLEMENTED(!CheckedMultiply(info.width, info.height, elements) ||
-		                     !CheckedMultiply(elements, info.depth, elements) ||
-		                     !CheckedMultiply(info.pitch, info.bytes_per_element, pitch_bytes) ||
-		                     elements > UINT32_MAX || pitch_bytes > UINT32_MAX);
-		uint64_t slice_bytes = info.linear_slice_stride;
-		EXIT_NOT_IMPLEMENTED(slice_bytes == 0 &&
-		                     !CheckedMultiply(pitch_bytes, info.height, slice_bytes));
-		uint64_t linear_used = 0, minimum_slice = 0;
-		EXIT_NOT_IMPLEMENTED(!CheckedMultiply(pitch_bytes, info.height, minimum_slice) ||
-		                     (info.depth > 1 && slice_bytes < minimum_slice) ||
-		                     !CheckedAddProduct(linear_used, info.depth - 1u, slice_bytes) ||
-		                     !CheckedAddProduct(linear_used, info.height - 1u, pitch_bytes) ||
-		                     !CheckedAddProduct(linear_used, info.width, info.bytes_per_element) ||
-		                     linear_used > info.linear_size || slice_bytes > UINT32_MAX);
-
-		const uint64_t columns =
-		    (static_cast<uint64_t>(tiled_width) + block.block_width - 1u) / block.block_width;
-		const uint64_t rows =
-		    (static_cast<uint64_t>(tiled_height) + block.block_height - 1u) / block.block_height;
-		uint64_t blocks_per_slice = 0;
-		EXIT_NOT_IMPLEMENTED(!CheckedMultiply(columns, rows, blocks_per_slice) ||
-		                     columns > UINT32_MAX || blocks_per_slice > UINT32_MAX ||
-		                     rows * block.block_height > UINT32_MAX);
-		if (info.tail) {
-			const bool supported = info.family != TileBlockFamily::Standard256B;
-			EXIT_NOT_IMPLEMENTED(
-			    !supported || info.depth > block.block_depth || info.tail_x >= block.block_width ||
-			    info.width > block.block_width - info.tail_x || info.tail_y >= block.block_height ||
-			    info.height > block.block_height - info.tail_y ||
-			    info.tiled_size < block.block_size);
-		} else {
-			const uint64_t slices =
-			    (static_cast<uint64_t>(info.depth) + block.block_depth - 1u) / block.block_depth;
-			uint64_t tiled_used = 0;
-			EXIT_NOT_IMPLEMENTED(!CheckedMultiply(blocks_per_slice, slices, tiled_used) ||
-			                     !CheckedMultiply(tiled_used, block.block_size, tiled_used) ||
-			                     tiled_used > info.tiled_size);
-		}
-		const uint32_t alignment = std::min(info.bytes_per_element, 4u);
-		EXIT_NOT_IMPLEMENTED(((info.linear_offset | info.tiled_offset | pitch_bytes | slice_bytes) &
-		                      (alignment - 1u)) != 0);
-
-		Dispatch dispatch {};
-		dispatch.elements      = static_cast<uint32_t>(elements);
-		dispatch.pipeline_slot = GetPipelineSlot(to_tiled, info.family, info.bytes_per_element);
-		dispatch.push.src_base =
-		    static_cast<uint32_t>(to_tiled ? info.linear_offset : info.tiled_offset);
-		dispatch.push.dst_base =
-		    static_cast<uint32_t>(to_tiled ? info.tiled_offset : info.linear_offset);
-		dispatch.push.width            = info.width;
-		dispatch.push.height           = info.height;
-		dispatch.push.depth            = info.depth;
-		dispatch.push.surface_z        = info.surface_z;
-		dispatch.push.pitch_bytes      = static_cast<uint32_t>(pitch_bytes);
-		dispatch.push.slice_bytes      = static_cast<uint32_t>(slice_bytes);
-		dispatch.push.blocks_per_row   = static_cast<uint32_t>(columns);
-		dispatch.push.blocks_per_slice = static_cast<uint32_t>(blocks_per_slice);
-		dispatch.push.tail_x           = info.tail_x;
-		dispatch.push.tail_y           = info.tail_y;
-		dispatch.push.tail             = info.tail;
-		dispatches.push_back(dispatch);
-	}
-}
-
-void TileCompute::Destroy(Resources& target) const {
-	if (target.mapped != nullptr) {
-		graphics.UnmapMemory(target.staging.memory);
-	}
-	if (target.staging.buffer != nullptr) {
-		graphics.DeleteBuffer(target.staging);
-	}
-	if (target.linear.buffer != nullptr) {
-		graphics.DeleteBuffer(target.linear);
-	}
-	for (auto pipeline: target.pipelines) {
-		if (pipeline != nullptr) {
-			graphics.device.destroyPipeline(pipeline, nullptr);
-		}
-	}
-	if (target.descriptor_pool != nullptr) {
-		graphics.device.destroyDescriptorPool(target.descriptor_pool, nullptr);
-	}
-	if (target.pipeline_layout != nullptr) {
-		graphics.device.destroyPipelineLayout(target.pipeline_layout, nullptr);
-	}
-	if (target.descriptor_layout != nullptr) {
-		graphics.device.destroyDescriptorSetLayout(target.descriptor_layout, nullptr);
-	}
-	target = {};
-}
-
-void TileCompute::Init() {
-	if (resources.pipeline_layout != nullptr) {
-		return;
-	}
-	std::array<vk::DescriptorSetLayoutBinding, 2> bindings {};
-	for (uint32_t i = 0; i < bindings.size(); i++) {
-		bindings[i] = {i, vk::DescriptorType::eStorageBuffer, 1, vk::ShaderStageFlagBits::eCompute,
-		               nullptr};
-	}
-	vk::DescriptorSetLayoutCreateInfo descriptor_info {};
-	descriptor_info.sType        = vk::StructureType::eDescriptorSetLayoutCreateInfo;
-	descriptor_info.bindingCount = static_cast<uint32_t>(bindings.size());
-	descriptor_info.pBindings    = bindings.data();
-	RequireVulkanSuccess(graphics.device.createDescriptorSetLayout(&descriptor_info, nullptr,
-	                                                               &resources.descriptor_layout),
-	                     "create GPU tiler descriptor layout");
-
-	vk::PushConstantRange        push_range {vk::ShaderStageFlagBits::eCompute, 0, sizeof(Push)};
-	vk::PipelineLayoutCreateInfo layout_info {};
-	layout_info.sType                  = vk::StructureType::ePipelineLayoutCreateInfo;
-	layout_info.setLayoutCount         = 1;
-	layout_info.pSetLayouts            = &resources.descriptor_layout;
-	layout_info.pushConstantRangeCount = 1;
-	layout_info.pPushConstantRanges    = &push_range;
-	RequireVulkanSuccess(
-	    graphics.device.createPipelineLayout(&layout_info, nullptr, &resources.pipeline_layout),
-	    "create GPU tiler pipeline layout");
-	vk::DescriptorPoolSize       pool_size {vk::DescriptorType::eStorageBuffer, 2};
-	vk::DescriptorPoolCreateInfo pool_info {};
-	pool_info.sType         = vk::StructureType::eDescriptorPoolCreateInfo;
-	pool_info.maxSets       = 1;
-	pool_info.poolSizeCount = 1;
-	pool_info.pPoolSizes    = &pool_size;
-	RequireVulkanSuccess(
-	    graphics.device.createDescriptorPool(&pool_info, nullptr, &resources.descriptor_pool),
-	    "create GPU tiler descriptor pool");
-	vk::DescriptorSetAllocateInfo set_info {};
-	set_info.sType              = vk::StructureType::eDescriptorSetAllocateInfo;
-	set_info.descriptorPool     = resources.descriptor_pool;
-	set_info.descriptorSetCount = 1;
-	set_info.pSetLayouts        = &resources.descriptor_layout;
-	RequireVulkanSuccess(
-	    graphics.device.allocateDescriptorSets(&set_info, &resources.descriptor_set),
-	    "allocate GPU tiler descriptor set");
-}
-
-void TileCompute::CreatePipeline(uint32_t pipeline_slot) {
-	const uint32_t element_size_index     = pipeline_slot % BYTES_PER_ELEMENT_COUNT;
-	const uint32_t family_direction_index = pipeline_slot / BYTES_PER_ELEMENT_COUNT;
-	const uint32_t family_index           = family_direction_index % FAMILY_COUNT;
-	const uint32_t direction_index        = family_direction_index / FAMILY_COUNT;
-	const uint32_t specialization_values[] {1u << element_size_index, direction_index};
-	const vk::SpecializationMapEntry entries[] {{0, 0, 4}, {1, 4, 4}};
-	vk::SpecializationInfo           specialization {2, entries, sizeof(specialization_values),
-	                                                 specialization_values};
-	vk::ShaderModuleCreateInfo       module_info {};
-	module_info.sType       = vk::StructureType::eShaderModuleCreateInfo;
-	module_info.codeSize    = SHADERS[family_index].words * sizeof(uint32_t);
-	module_info.pCode       = SHADERS[family_index].code;
-	vk::ShaderModule module = nullptr;
-	RequireVulkanSuccess(graphics.device.createShaderModule(&module_info, nullptr, &module),
-	                     "create GPU tiler shader module");
-	vk::PipelineShaderStageCreateInfo stage {};
-	stage.sType               = vk::StructureType::ePipelineShaderStageCreateInfo;
-	stage.stage               = vk::ShaderStageFlagBits::eCompute;
-	stage.module              = module;
-	stage.pName               = "main";
-	stage.pSpecializationInfo = &specialization;
-	vk::ComputePipelineCreateInfo info {};
-	info.sType            = vk::StructureType::eComputePipelineCreateInfo;
-	info.stage            = stage;
-	info.layout           = resources.pipeline_layout;
-	vk::Pipeline pipeline = nullptr;
-	const auto   result =
-	    graphics.device.createComputePipelines(nullptr, 1, &info, nullptr, &pipeline);
-	graphics.device.destroyShaderModule(module, nullptr);
-	RequireVulkanSuccess(result, "create GPU tiler pipeline");
-	resources.pipelines[pipeline_slot] = pipeline;
-}
-
-void TileCompute::CreatePipelines(std::span<const Dispatch> dispatches) {
-	for (const auto& dispatch: dispatches) {
-		if (resources.pipelines[dispatch.pipeline_slot] == nullptr) {
-			CreatePipeline(dispatch.pipeline_slot);
-		}
-	}
-}
-
-void TileCompute::CreateBuffer(uint64_t size, bool mapped, VulkanBuffer& buffer,
-                               void** data) const {
-	buffer.usage = vk::BufferUsageFlagBits::eStorageBuffer | vk::BufferUsageFlagBits::eTransferSrc |
-	               vk::BufferUsageFlagBits::eTransferDst;
-	buffer.memory.property =
-	    mapped
-	        ? vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent
-	        : vk::MemoryPropertyFlags(vk::MemoryPropertyFlagBits::eDeviceLocal);
-	graphics.CreateBuffer(size, buffer);
-	if (mapped) graphics.MapMemory(buffer.memory, *data);
-}
-
-void TileCompute::Resize(uint64_t staging_size, uint64_t linear_size) {
-	if (resources.staging.buffer_size >= staging_size &&
-	    resources.linear.buffer_size >= linear_size) {
-		return;
-	}
-	staging_size = std::max(staging_size, resources.staging.buffer_size);
-	linear_size  = std::max(linear_size, resources.linear.buffer_size);
-	VulkanBuffer staging {}, linear {};
-	void*        mapped = nullptr;
-	CreateBuffer(staging_size, true, staging, &mapped);
-	CreateBuffer(linear_size, false, linear, nullptr);
-	if (resources.mapped != nullptr) graphics.UnmapMemory(resources.staging.memory);
-	if (resources.staging.buffer != nullptr) graphics.DeleteBuffer(resources.staging);
-	if (resources.linear.buffer != nullptr) graphics.DeleteBuffer(resources.linear);
-	resources.staging = staging;
-	resources.linear  = linear;
-	resources.mapped  = mapped;
-}
-
-void TileCompute::Execute(bool to_tiled, const void* input, void* output, uint64_t tiled_capacity,
-                          uint64_t linear_capacity, std::span<const Dispatch> dispatches,
-                          const GpuTileRecord& record) {
-	const uint64_t tiled_size  = AlignToDword(tiled_capacity);
-	const uint64_t linear_size = AlignToDword(linear_capacity);
-	const uint64_t input_size  = to_tiled ? linear_capacity : tiled_capacity;
-	if (input != nullptr) {
-		std::memcpy(resources.mapped, input, static_cast<size_t>(input_size));
-		std::memset(static_cast<uint8_t*>(resources.mapped) + input_size, 0,
-		            static_cast<size_t>(AlignToDword(input_size) - input_size));
-	}
-
-	std::array<vk::DescriptorBufferInfo, 2> buffer_info {{
-	    {to_tiled ? resources.linear.buffer : resources.staging.buffer, 0,
-	     to_tiled ? linear_size : tiled_size},
-	    {to_tiled ? resources.staging.buffer : resources.linear.buffer, 0,
-	     to_tiled ? tiled_size : linear_size},
-	}};
-	std::array<vk::WriteDescriptorSet, 2>   writes {};
-	for (uint32_t i = 0; i < writes.size(); i++) {
-		writes[i].sType           = vk::StructureType::eWriteDescriptorSet;
-		writes[i].dstSet          = resources.descriptor_set;
-		writes[i].dstBinding      = i;
-		writes[i].descriptorCount = 1;
-		writes[i].descriptorType  = vk::DescriptorType::eStorageBuffer;
-		writes[i].pBufferInfo     = &buffer_info[i];
-	}
-	graphics.device.updateDescriptorSets(static_cast<uint32_t>(writes.size()), writes.data(), 0,
-	                                     nullptr);
-
-	CommandBuffer command;
-	command.Begin();
-	auto vk_command = command.Handle();
-	if (input != nullptr) {
-		Barrier(vk_command, resources.staging.buffer, vk::AccessFlagBits::eHostWrite,
-		        vk::AccessFlagBits::eShaderRead | vk::AccessFlagBits::eTransferRead,
-		        vk::PipelineStageFlagBits::eHost,
-		        vk::PipelineStageFlagBits::eComputeShader | vk::PipelineStageFlagBits::eTransfer);
-	}
-	if (to_tiled && input != nullptr) {
-		const vk::BufferCopy copy {0, 0, linear_size};
-		vk_command.copyBuffer(resources.staging.buffer, resources.linear.buffer, 1, &copy);
-		Barrier(vk_command, resources.linear.buffer, vk::AccessFlagBits::eTransferWrite,
-		        vk::AccessFlagBits::eShaderRead, vk::PipelineStageFlagBits::eTransfer,
-		        vk::PipelineStageFlagBits::eComputeShader);
-		Barrier(vk_command, resources.staging.buffer, vk::AccessFlagBits::eTransferRead,
-		        vk::AccessFlagBits::eTransferWrite, vk::PipelineStageFlagBits::eTransfer,
-		        vk::PipelineStageFlagBits::eTransfer);
-	}
-	if (to_tiled && record) {
-		record(command, resources.linear);
-		Barrier(vk_command, resources.linear.buffer,
-		        vk::AccessFlagBits::eTransferWrite | vk::AccessFlagBits::eMemoryWrite,
-		        vk::AccessFlagBits::eShaderRead, vk::PipelineStageFlagBits::eAllCommands,
-		        vk::PipelineStageFlagBits::eComputeShader);
-	}
-
-	const auto output_buffer = to_tiled ? resources.staging.buffer : resources.linear.buffer;
-	const auto output_size   = to_tiled ? tiled_size : linear_size;
-	vk_command.fillBuffer(output_buffer, 0, output_size, 0);
-	Barrier(vk_command, output_buffer, vk::AccessFlagBits::eTransferWrite,
-	        vk::AccessFlagBits::eShaderRead | vk::AccessFlagBits::eShaderWrite,
-	        vk::PipelineStageFlagBits::eTransfer, vk::PipelineStageFlagBits::eComputeShader);
-	vk_command.bindDescriptorSets(vk::PipelineBindPoint::eCompute, resources.pipeline_layout, 0, 1,
-	                              &resources.descriptor_set, 0, nullptr);
-	const uint64_t limit =
-	    static_cast<uint64_t>(
-	        graphics.GetPhysicalDeviceProperties().limits.maxComputeWorkGroupCount[0]) *
-	    GROUP_SIZE;
-	for (const auto& dispatch: dispatches) {
-		vk_command.bindPipeline(vk::PipelineBindPoint::eCompute,
-		                        resources.pipelines[dispatch.pipeline_slot]);
-		for (uint32_t first = 0; first < dispatch.elements;) {
-			auto push  = dispatch.push;
-			push.first = first;
-			push.count =
-			    static_cast<uint32_t>(std::min<uint64_t>(dispatch.elements - first, limit));
-			vk_command.pushConstants(resources.pipeline_layout, vk::ShaderStageFlagBits::eCompute,
-			                         0, sizeof(push), &push);
-			vk_command.dispatch((push.count - 1u) / GROUP_SIZE + 1u, 1, 1);
-			first += push.count;
-		}
-	}
-	Barrier(vk_command, output_buffer, vk::AccessFlagBits::eShaderWrite,
-	        vk::AccessFlagBits::eTransferRead | vk::AccessFlagBits::eHostRead,
-	        vk::PipelineStageFlagBits::eComputeShader,
-	        vk::PipelineStageFlagBits::eTransfer | vk::PipelineStageFlagBits::eHost);
-	if (!to_tiled && record) {
-		record(command, resources.linear);
-	}
-	if (!to_tiled && output != nullptr) {
-		const vk::BufferCopy copy {0, 0, linear_size};
-		vk_command.copyBuffer(resources.linear.buffer, resources.staging.buffer, 1, &copy);
-		Barrier(vk_command, resources.staging.buffer, vk::AccessFlagBits::eTransferWrite,
-		        vk::AccessFlagBits::eHostRead, vk::PipelineStageFlagBits::eTransfer,
-		        vk::PipelineStageFlagBits::eHost);
-	}
-	command.End();
-	command.Execute();
-	command.WaitForFence();
-	if (output != nullptr) {
-		std::memcpy(output, resources.mapped,
-		            static_cast<size_t>(to_tiled ? tiled_capacity : linear_capacity));
-	}
-}
-
-void TileCompute::Run(bool to_tiled, const void* input, void* output, uint64_t tiled_capacity,
-                      uint64_t linear_capacity, std::span<const GpuTileInfo> infos,
-                      const GpuTileRecord& record) {
-	EXIT_IF((to_tiled && (output == nullptr || (input == nullptr && !record))) ||
-	        (!to_tiled && (input == nullptr || (output == nullptr && !record))));
-	std::vector<Dispatch> dispatches;
-	Prepare(to_tiled, tiled_capacity, linear_capacity, infos, dispatches);
-	Init();
-	CreatePipelines(dispatches);
-	const uint64_t staging_size =
-	    std::max(AlignToDword(tiled_capacity), AlignToDword(linear_capacity));
-	const uint64_t linear_size = AlignToDword(linear_capacity);
-	Resize(staging_size, linear_size);
-	Execute(to_tiled, input, output, tiled_capacity, linear_capacity, dispatches, record);
-}
-
-void TileCompute::Release() {
-	Destroy(resources);
-}
-
-} // namespace
-
-void GpuDetile(const void* tiled, void* linear, uint64_t tiled_capacity, uint64_t linear_capacity,
-               std::span<const GpuTileInfo> infos, const GpuTileRecord& after) {
-	Common::LockGuard lock(g_tiler_mutex);
-	if (!g_tiler) {
-		g_tiler = std::make_unique<TileCompute>(GetRenderContext().GetGraphics());
-	}
-	g_tiler->Run(false, tiled, linear, tiled_capacity, linear_capacity, infos, after);
-}
-
-void GpuTile(const void* linear, void* tiled, uint64_t tiled_capacity, uint64_t linear_capacity,
-             std::span<const GpuTileInfo> infos, const GpuTileRecord& before) {
-	Common::LockGuard lock(g_tiler_mutex);
-	if (!g_tiler) {
-		g_tiler = std::make_unique<TileCompute>(GetRenderContext().GetGraphics());
-	}
-	g_tiler->Run(true, linear, tiled, tiled_capacity, linear_capacity, infos, before);
-}
-
-void GpuTileRelease() {
-	Common::LockGuard lock(g_tiler_mutex);
-	if (g_tiler) {
-		g_tiler->Release();
-		g_tiler.reset();
-	}
-}
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/gpuTiler.h

@@ -1,45 +0,0 @@
-#pragma once
-
-#include "graphics/guest_gpu/tile.h"
-
-#include <cstdint>
-#include <functional>
-#include <span>
-
-namespace Libs::Graphics {
-
-struct GraphicContext;
-struct VulkanBuffer;
-class CommandBuffer;
-
-struct GpuTileInfo {
-	TileBlockFamily family              = TileBlockFamily::Count;
-	uint32_t        bytes_per_element   = 0;
-	uint64_t        linear_offset       = 0;
-	uint64_t        linear_size         = 0;
-	uint64_t        tiled_offset        = 0;
-	uint64_t        tiled_size          = 0;
-	uint64_t        linear_slice_stride = 0;
-	uint32_t        width               = 0;
-	uint32_t        height              = 0;
-	uint32_t        depth               = 1;
-	uint32_t        pitch               = 0;
-	uint32_t        tail_x              = 0;
-	uint32_t        tail_y              = 0;
-	bool            tail                = false;
-	uint32_t        tiled_width         = 0;
-	uint32_t        tiled_height        = 0;
-	uint32_t        surface_z           = 0;
-};
-
-using GpuTileRecord = std::function<void(CommandBuffer&, VulkanBuffer&)>;
-
-void GpuDetile(const void* tiled, void* linear, uint64_t tiled_capacity,
-               uint64_t linear_capacity, std::span<const GpuTileInfo> infos,
-               const GpuTileRecord& after = {});
-void GpuTile(const void* linear, void* tiled, uint64_t tiled_capacity,
-             uint64_t linear_capacity, std::span<const GpuTileInfo> infos,
-             const GpuTileRecord& before = {});
-void GpuTileRelease();
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/graphicContext.h

@@ -6,8 +6,6 @@
 #include "graphics/host_gpu/vulkanCommon.h" // IWYU pragma: export
 #include "graphics/host_gpu/vulkanInstance.h"
 
-#include <memory>
-#include <mutex>
 #include <vector>
 #include <vk_mem_alloc.h>
 
@@ -18,32 +16,20 @@ struct VulkanBuffer;
 struct VulkanImage;
 struct VulkanMemory;
 
-struct VulkanSwapchain {
-	~VulkanSwapchain();
-
-	vk::SwapchainKHR                 swapchain        = nullptr;
-	vk::Format                       swapchain_format = vk::Format::eUndefined;
-	vk::Extent2D                     swapchain_extent = {};
-	std::unique_ptr<vk::Image[]>     swapchain_images;
-	std::unique_ptr<vk::ImageView[]> swapchain_image_views;
-	uint32_t                         swapchain_images_count = 0;
-	std::unique_ptr<vk::Semaphore[]> image_acquired_semaphores;
-	std::unique_ptr<vk::Semaphore[]> render_complete_semaphores;
-	uint32_t                         current_index = 0;
-	uint32_t                         present_frame = 0;
-};
-
 struct GraphicContext: public VulkanInstance {
 	[[nodiscard]] bool CreateAllocator();
 	void               DestroyAllocator();
 	void               LogMemoryBudget() const;
-	void               CreateBuffer(uint64_t size, VulkanBuffer& buffer);
-	void               DeleteBuffer(VulkanBuffer& buffer);
-	[[nodiscard]] bool CreateImage(const vk::ImageCreateInfo& info, VulkanImage& image);
-	void               DeleteImage(VulkanImage& image);
-	void               MapMemory(VulkanMemory& memory, void*& data);
-	void               UnmapMemory(VulkanMemory& memory);
-	void               AppendHardwareRayTracingDeviceExtensions(
+	[[nodiscard]] bool CanReportMemoryUsage() const noexcept { return memory_budget_ext_enabled; }
+	[[nodiscard]] uint64_t GetDeviceMemoryUsage() const;
+	[[nodiscard]] uint64_t GetTotalMemoryBudget() const;
+	void                   CreateBuffer(uint64_t size, VulkanBuffer& buffer);
+	void                   DeleteBuffer(VulkanBuffer& buffer);
+	[[nodiscard]] bool     CreateImage(const vk::ImageCreateInfo& info, VulkanImage& image);
+	void                   DeleteImage(VulkanImage& image);
+	void                   MapMemory(VulkanMemory& memory, void*& data);
+	void                   UnmapMemory(VulkanMemory& memory);
+	void                   AppendHardwareRayTracingDeviceExtensions(
 	    const std::vector<vk::ExtensionProperties>& available_extensions,
 	    std::vector<const char*>&                   device_extensions);
 	void LoadHardwareRayTracingFunctions() const;
@@ -64,92 +50,29 @@ struct VulkanMemory {
 	uint64_t                unique_id          = 0;
 };
 
-enum class VulkanImageType {
-	Unknown,
-	VideoOut,
-	DepthStencil,
-	Texture,
-	StorageTexture,
-	RenderTexture
-};
-
-struct ImageViewInfo {
-	vk::Format           format      = vk::Format::eUndefined;
-	vk::ImageViewType    type        = vk::ImageViewType::e2D;
-	vk::ImageAspectFlags aspect      = {};
-	uint32_t             base_level  = 0;
-	uint32_t             level_count = 0;
-	uint32_t             base_layer  = 0;
-	uint32_t             layer_count = 1;
-	uint32_t             swizzle     = 0;
-	vk::ImageUsageFlags  usage       = vk::ImageUsageFlagBits::eSampled;
-
-	bool operator==(const ImageViewInfo&) const = default;
-};
-
-struct CachedImageView {
-	ImageViewInfo info;
-	vk::ImageView view = nullptr;
-};
-
-struct ImageViewCache {
-	std::mutex                   mutex;
-	std::vector<CachedImageView> views;
-
-	ImageViewCache() = default;
-	KYTY_CLASS_NO_COPY(ImageViewCache);
+struct VulkanImageState {
+	vk::PipelineStageFlags2 pl_stage    = vk::PipelineStageFlagBits2::eAllCommands;
+	vk::AccessFlags2        access_mask = vk::AccessFlagBits2::eNone;
+	vk::ImageLayout         layout      = vk::ImageLayout::eUndefined;
 };
 
 struct VulkanImage {
-	static constexpr int VIEW_MAX           = 4;
-	static constexpr int VIEW_DEFAULT       = 0;
-	static constexpr int VIEW_DEFAULT_ARRAY = 1;
-	static constexpr int VIEW_STORAGE       = 2;
-	static constexpr int VIEW_STORAGE_ARRAY = 3;
-
-	explicit VulkanImage(VulkanImageType type): type(type) {}
+	VulkanImage() = default;
 	KYTY_CLASS_NO_COPY(VulkanImage);
 
-	VulkanImageType        type                 = VulkanImageType::Unknown;
-	vk::Format             format               = vk::Format::eUndefined;
-	vk::Extent2D           extent               = {};
-	uint32_t               guest_pitch          = 0;
-	uint32_t               layers               = 1;
-	uint32_t               mip_levels           = 1;
-	uint32_t               samples              = 1;
-	vk::Image              image                = nullptr;
-	vk::ImageView          image_view[VIEW_MAX] = {};
-	vk::ImageLayout        layout               = vk::ImageLayout::eUndefined;
+	vk::Format             format      = vk::Format::eUndefined;
+	vk::ImageType          image_type  = vk::ImageType::e2D;
+	vk::Extent3D           extent      = {1, 1, 1};
+	uint32_t               guest_pitch = 0;
+	uint32_t               layers      = 1;
+	uint32_t               mip_levels  = 1;
+	uint32_t               samples     = 1;
+	vk::ImageUsageFlags    usage       = {};
+	vk::ImageCreateFlags   flags       = {};
+	vk::Image              image       = nullptr;
+	VulkanImageState       state;
+	std::vector<VulkanImageState> subresource_states;
 	Graphics::VulkanMemory memory;
-	ImageViewCache         view_cache;
-};
-
-struct VideoOutVulkanImage: public VulkanImage {
-	VideoOutVulkanImage(): VulkanImage(VulkanImageType::VideoOut) {}
-};
-
-struct DepthStencilVulkanImage: public VulkanImage {
-	DepthStencilVulkanImage(): VulkanImage(VulkanImageType::DepthStencil) {}
-	bool compressed                    = false;
-	bool initial_depth_clear_pending   = false;
-	bool initial_stencil_clear_pending = false;
-};
-
-struct GpuTextureVulkanImage: public VulkanImage {
-	explicit GpuTextureVulkanImage(VulkanImageType type): VulkanImage(type) {}
-};
-
-struct TextureVulkanImage: public GpuTextureVulkanImage {
-	TextureVulkanImage(): GpuTextureVulkanImage(VulkanImageType::Texture) {}
-};
-
-struct StorageTextureVulkanImage: public GpuTextureVulkanImage {
-	StorageTextureVulkanImage(): GpuTextureVulkanImage(VulkanImageType::StorageTexture) {}
-};
-
-struct RenderTextureVulkanImage: public VulkanImage {
-	RenderTextureVulkanImage(): VulkanImage(VulkanImageType::RenderTexture) {}
-	bool initial_clear_pending = false;
 };
 
 struct VulkanBuffer {
@@ -159,8 +82,6 @@ struct VulkanBuffer {
 	uint64_t             buffer_size = 0;
 };
 
-struct StorageVulkanBuffer: public VulkanBuffer {};
-
 } // namespace Libs::Graphics
 
 #endif /* EMULATOR_INCLUDE_EMULATOR_GRAPHICS_GRAPHICCONTEXT_H_ */

src/graphics/host_gpu/memoryTracker.cpp

@@ -31,6 +31,44 @@ MemoryTracker::MemoryTracker(PageManager& page_manager, PageWatchMode gpu_watch_
 
 MemoryTracker::~MemoryTracker() = default;
 
+void MemoryTracker::ValidateGpuDirtyPages(const RangeSet& dirty, uint64_t vaddr, uint64_t size,
+                                          const char* operation) const noexcept {
+	if (vaddr == 0 || size == 0 || size > UINT64_MAX - vaddr ||
+	    (vaddr & (TRACKER_PAGE_SIZE - 1)) != 0 || (size & (TRACKER_PAGE_SIZE - 1)) != 0) {
+		EXIT("MemoryTracker: invalid dirty-page validation range\n");
+	}
+	for (auto page = vaddr; page < vaddr + size; page += TRACKER_PAGE_SIZE) {
+		bool found = false;
+		dirty.ForEachIntersection(page, TRACKER_PAGE_SIZE,
+		                          [&found](RangeSet::Range) { found = true; });
+		if (!found) {
+			EXIT("MemoryTracker: GPU-dirty tracker page has no dirty bytes, operation=%s "
+			     "addr=0x%016" PRIx64 "\n",
+			     operation, page);
+		}
+	}
+}
+
+void MemoryTracker::ValidateGpuDirtyOwnership(const RangeSet& dirty, uint64_t vaddr, uint64_t size,
+                                              const char* operation) {
+	ValidateRange(vaddr, size);
+	if (vaddr + size > UINT64_MAX - (TRACKER_PAGE_SIZE - 1)) {
+		EXIT("MemoryTracker: dirty ownership range alignment overflow\n");
+	}
+	const auto begin = vaddr & ~(TRACKER_PAGE_SIZE - 1);
+	const auto end   = (vaddr + size + TRACKER_PAGE_SIZE - 1) & ~(TRACKER_PAGE_SIZE - 1);
+	for (auto page = begin; page < end; page += TRACKER_PAGE_SIZE) {
+		bool has_dirty_bytes = false;
+		dirty.ForEachIntersection(page, TRACKER_PAGE_SIZE,
+		                          [&has_dirty_bytes](RangeSet::Range) { has_dirty_bytes = true; });
+		if (IsRegionGpuModified(page, TRACKER_PAGE_SIZE) != has_dirty_bytes) {
+			EXIT("MemoryTracker: tracker and byte ownership disagree, operation=%s "
+			     "addr=0x%016" PRIx64 "\n",
+			     operation, page);
+		}
+	}
+}
+
 void MemoryTracker::ValidateRange(uint64_t vaddr, uint64_t size) {
 	if (vaddr == 0 || size == 0 || vaddr >= TRACKER_ADDRESS_SIZE ||
 	    size > TRACKER_ADDRESS_SIZE - vaddr) {

src/graphics/host_gpu/memoryTracker.h

@@ -3,6 +3,7 @@
 
 #include "common/assert.h"
 #include "graphics/host_gpu/pageManager.h"
+#include "graphics/host_gpu/rangeSet.h"
 #include "graphics/host_gpu/regionManager.h"
 
 #include <algorithm>
@@ -10,6 +11,7 @@
 #include <memory>
 #include <mutex>
 #include <type_traits>
+#include <utility>
 #include <vector>
 
 namespace Libs::Graphics {
@@ -38,6 +40,10 @@ public:
 	                                    PageFaultPhase phase) noexcept;
 	[[nodiscard]] bool InvalidateVirtualGpuWrite(PageFaultAccess access, uint64_t vaddr,
 	                                             uint64_t size, PageFaultPhase phase) noexcept;
+	void ValidateGpuDirtyPages(const RangeSet& dirty, uint64_t vaddr, uint64_t size,
+	                           const char* operation) const noexcept;
+	void ValidateGpuDirtyOwnership(const RangeSet& dirty, uint64_t vaddr, uint64_t size,
+	                               const char* operation);
 
 	template <bool clear, typename Preflight, typename Func>
 	void ForEachDownloadRange(uint64_t vaddr, uint64_t size, Preflight&& preflight, Func&& func) {
@@ -99,7 +105,7 @@ public:
 		std::unique_lock access(m_access_mutex);
 		RequireMapped(vaddr, size);
 		Iterate<true>(vaddr, size, [](RegionManager*, uint64_t, uint64_t) {});
-		s_upload_owner = this;
+		const auto* previous_upload_owner = std::exchange(s_upload_owner, this);
 		Iterate<false>(vaddr, size, [&](RegionManager* manager, uint64_t offset, uint64_t bytes) {
 			manager->lock.lock();
 			manager->Track(manager->GetCpuAddr() + offset, bytes);
@@ -119,15 +125,15 @@ public:
 				    manager->lock.unlock();
 			    });
 		}
-		s_upload_owner = nullptr;
+		s_upload_owner = previous_upload_owner;
 	}
 
 private:
 	static constexpr size_t REGION_COUNT = TRACKER_ADDRESS_SIZE / TRACKER_REGION_SIZE;
 	inline static thread_local const MemoryTracker* s_upload_owner = nullptr;
 
-	static void CheckNotInUploadCallback() noexcept {
-		if (s_upload_owner != nullptr) {
+	void CheckNotInUploadCallback() const noexcept {
+		if (s_upload_owner == this) {
 			EXIT("memory tracker re-entered from upload callback\n");
 		}
 	}
@@ -167,7 +173,9 @@ private:
 	void        RequireMapped(uint64_t vaddr, uint64_t size) const {
 		ValidateRange(vaddr, size);
 		if (!m_page_manager.IsMapped(vaddr, size)) {
-			EXIT("memory tracker range is not mapped\n");
+			EXIT("memory tracker range [0x%llx, 0x%llx) is not mapped\n",
+			     static_cast<unsigned long long>(vaddr),
+			     static_cast<unsigned long long>(vaddr + size));
 		}
 	}
 	RegionManager* GetOrCreateRegion(uint64_t index);

src/graphics/host_gpu/objects/label.cpp

@@ -1,348 +0,0 @@
-#include "graphics/host_gpu/objects/label.h"
-
-#include "common/assert.h"
-#include "common/threads.h"
-#include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/renderer/render.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/vulkanCommon.h"
-
-#include <algorithm>
-#include <memory>
-#include <vector>
-
-namespace Libs::Graphics {
-
-enum LabelStatus {
-	New,
-	Active,
-	ActiveDeleted,
-	NotActive,
-};
-
-struct LabelCallbacks {
-	LabelCallback callback_1           = nullptr;
-	LabelCallback callback_2           = nullptr;
-	uint64_t      args[LABEL_ARGS_MAX] = {};
-};
-
-struct LabelEvent final {
-	vk::Device device = nullptr;
-	vk::Event  event  = nullptr;
-
-	~LabelEvent() {
-		if (event != nullptr) {
-			device.destroyEvent(event, nullptr);
-		}
-	}
-};
-
-struct LabelSubmission {
-	std::shared_ptr<LabelEvent> completion;
-	LabelCallbacks              callbacks;
-};
-
-struct Label {
-	vk::Device                   device = nullptr;
-	LabelStatus                  status = LabelStatus::New;
-	LabelCallbacks               callbacks;
-	std::vector<LabelSubmission> submissions;
-};
-
-class LabelManager {
-public:
-	LabelManager() {
-		EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
-		Common::Thread t(ThreadRun, this);
-		t.Detach();
-	}
-	~LabelManager() { KYTY_NOT_IMPLEMENTED; }
-	KYTY_CLASS_NO_COPY(LabelManager);
-
-	Label* Create(LabelCallback callback_1, LabelCallback callback_2, const uint64_t* args);
-	void   Delete(Label& label);
-	void   Set(CommandBuffer& buffer, Label& label);
-	void   Drain();
-
-private:
-	static void ThreadRun(void* data);
-
-	bool        Remove(Label& label);
-	static void Destroy(Label& label);
-
-	Common::Mutex       m_mutex;
-	Common::CondVar     m_cond_var;
-	std::vector<Label*> m_labels;
-	uint64_t            m_callbacks_in_flight = 0;
-};
-
-static LabelManager*     g_label_manager     = nullptr;
-static thread_local bool g_in_label_callback = false;
-
-class LabelCallbackScope final {
-public:
-	LabelCallbackScope() {
-		if (g_in_label_callback) {
-			EXIT("recursive GPU label callback\n");
-		}
-		g_in_label_callback = true;
-	}
-	~LabelCallbackScope() {
-		if (!g_in_label_callback) {
-			EXIT("GPU label callback scope is not active\n");
-		}
-		g_in_label_callback = false;
-	}
-};
-
-void LabelManager::ThreadRun(void* data) {
-	auto* manager = static_cast<LabelManager*>(data);
-
-	for (;;) {
-		manager->m_mutex.Lock();
-
-		uint64_t active_count = 0;
-
-		std::vector<Label*>          deleted_labels;
-		std::vector<LabelCallbacks>  fired_labels;
-		std::vector<LabelSubmission> finished_submissions;
-		deleted_labels.reserve(manager->m_labels.size());
-
-		for (auto& label: manager->m_labels) {
-			for (auto it = label->submissions.begin(); it != label->submissions.end();) {
-				active_count++;
-
-				if (it->completion == nullptr || it->completion->device == nullptr ||
-				    it->completion->event == nullptr) {
-					EXIT("GPU label submission has no completion event\n");
-				}
-				const auto status = it->completion->device.getEventStatus(it->completion->event);
-				switch (status) {
-					case vk::Result::eEventSet:
-						fired_labels.push_back(it->callbacks);
-						finished_submissions.push_back(*it);
-						it = label->submissions.erase(it);
-						break;
-					case vk::Result::eEventReset: ++it; break;
-					default: EXIT("vkGetEventStatus returned an unexpected result\n");
-				}
-			}
-
-			if (label->submissions.empty()) {
-				switch (label->status) {
-					case LabelStatus::ActiveDeleted: deleted_labels.push_back(label); break;
-					case LabelStatus::Active: label->status = LabelStatus::NotActive; break;
-					default: break;
-				}
-			}
-		}
-
-		if (active_count == 0) {
-			manager->m_cond_var.Wait(&manager->m_mutex);
-		}
-		if (fired_labels.size() > UINT64_MAX - manager->m_callbacks_in_flight) {
-			EXIT("GPU label callback count overflow\n");
-		}
-		manager->m_callbacks_in_flight += fired_labels.size();
-
-		for (auto& label: deleted_labels) {
-			bool removed = manager->Remove(*label);
-			EXIT_NOT_IMPLEMENTED(!removed);
-		}
-
-		manager->m_mutex.Unlock();
-
-		// Each completion event is shared with the recording command buffer's fence retainer.
-		// The event is destroyed only after both the label thread observed it and that command
-		// buffer completed, even when either side wins the race.
-		(void)finished_submissions;
-
-		for (auto& label: deleted_labels) {
-			Destroy(*label);
-		}
-
-		for (auto& label: fired_labels) {
-			LabelCallbackScope callback_scope;
-
-			if (label.callback_1 != nullptr) {
-				(void)label.callback_1(label.args);
-			}
-
-			if (label.callback_2 != nullptr) {
-				label.callback_2(label.args);
-			}
-		}
-
-		if (!fired_labels.empty()) {
-			Common::LockGuard lock(manager->m_mutex);
-			if (manager->m_callbacks_in_flight < fired_labels.size()) {
-				EXIT("GPU label callback count underflow\n");
-			}
-			manager->m_callbacks_in_flight -= fired_labels.size();
-			manager->m_cond_var.SignalAll();
-		}
-
-		Common::Thread::SleepMicro(100);
-	}
-}
-
-Label* LabelManager::Create(LabelCallback callback_1, LabelCallback callback_2,
-                            const uint64_t* args) {
-	Common::LockGuard lock(m_mutex);
-
-	auto* label = new Label;
-
-	label->status               = LabelStatus::New;
-	label->device               = GetRenderContext().GetGraphics().device;
-	label->callbacks.callback_1 = callback_1;
-	label->callbacks.callback_2 = callback_2;
-
-	if (args != nullptr) {
-		for (int i = 0; i < LABEL_ARGS_MAX; i++) {
-			label->callbacks.args[i] = args[i];
-		}
-	}
-
-	m_labels.push_back(label);
-
-	return label;
-}
-
-bool LabelManager::Remove(Label& label) {
-	EXIT_IF(label.device == nullptr);
-
-	Common::LockGuard lock(m_mutex);
-
-	const auto it = std::find(m_labels.begin(), m_labels.end(), &label);
-	EXIT_NOT_IMPLEMENTED(it == m_labels.end());
-
-	EXIT_NOT_IMPLEMENTED(label.status != LabelStatus::NotActive &&
-	                     label.status != LabelStatus::Active &&
-	                     label.status != LabelStatus::ActiveDeleted);
-
-	if (!label.submissions.empty()) {
-		label.status = LabelStatus::ActiveDeleted;
-
-		return false;
-	}
-
-	m_labels.erase(it);
-
-	return true;
-}
-
-void LabelManager::Destroy(Label& label) {
-	EXIT_IF(label.device == nullptr);
-
-	EXIT_NOT_IMPLEMENTED(!label.submissions.empty());
-
-	delete &label;
-}
-
-void LabelManager::Delete(Label& label) {
-	if (Remove(label)) {
-		Destroy(label);
-	}
-}
-
-void LabelManager::Set(CommandBuffer& buffer, Label& label) {
-	EXIT_IF(buffer.IsInvalid());
-	EXIT_IF(label.device == nullptr);
-
-	Common::LockGuard lock(m_mutex);
-
-	const auto it = std::find(m_labels.begin(), m_labels.end(), &label);
-	EXIT_NOT_IMPLEMENTED(it == m_labels.end());
-
-	EXIT_NOT_IMPLEMENTED(label.status != LabelStatus::New &&
-	                     label.status != LabelStatus::NotActive &&
-	                     label.status != LabelStatus::Active);
-
-	label.status = LabelStatus::Active;
-
-	LabelSubmission submission {};
-	submission.callbacks          = label.callbacks;
-	submission.completion         = std::make_shared<LabelEvent>();
-	submission.completion->device = label.device;
-
-	auto vk_buffer = buffer.Handle();
-
-	EXIT_NOT_IMPLEMENTED(vk_buffer == nullptr);
-
-	vk::EventCreateInfo create_info {};
-	create_info.sType = vk::StructureType::eEventCreateInfo;
-	create_info.pNext = nullptr;
-	create_info.flags = {};
-
-	const auto create_result =
-	    label.device.createEvent(&create_info, nullptr, &submission.completion->event);
-	if (create_result != vk::Result::eSuccess || submission.completion->event == nullptr) {
-		EXIT("failed to create label event: %s (%d)\n", VulkanToString(create_result).c_str(),
-		     static_cast<int>(create_result));
-	}
-	buffer.RetainResourceUntilFence(submission.completion);
-
-	// Labels can be reused before an earlier end-of-pipe event has been
-	// observed by the polling thread. Capture a separate Vulkan event and
-	// callback snapshot for each set so older writes are not lost.
-	const auto reset_result = label.device.resetEvent(submission.completion->event);
-	if (reset_result != vk::Result::eSuccess) {
-		EXIT("failed to reset label event: %s (%d)\n", VulkanToString(reset_result).c_str(),
-		     static_cast<int>(reset_result));
-	}
-	vk_buffer.setEvent(submission.completion->event, vk::PipelineStageFlagBits::eBottomOfPipe);
-
-	label.submissions.push_back(submission);
-
-	m_cond_var.SignalAll();
-}
-
-void LabelManager::Drain() {
-	m_mutex.Lock();
-	for (;;) {
-		const bool pending = std::any_of(m_labels.begin(), m_labels.end(), [](const Label* label) {
-			return !label->submissions.empty();
-		});
-		if (!pending && m_callbacks_in_flight == 0) {
-			m_mutex.Unlock();
-			return;
-		}
-		m_cond_var.SignalAll();
-		m_cond_var.Wait(&m_mutex);
-	}
-}
-
-void LabelInit() {
-	EXIT_IF(g_label_manager != nullptr);
-
-	g_label_manager = new LabelManager;
-}
-
-Label* LabelCreate(LabelCallback callback_1, LabelCallback callback_2, const uint64_t* args) {
-	EXIT_IF(g_label_manager == nullptr);
-
-	return g_label_manager->Create(callback_1, callback_2, args);
-}
-
-void LabelDelete(Label& label) {
-	EXIT_IF(g_label_manager == nullptr);
-
-	g_label_manager->Delete(label);
-}
-
-void LabelSet(CommandBuffer& buffer, Label& label) {
-	EXIT_IF(g_label_manager == nullptr);
-
-	g_label_manager->Set(buffer, label);
-}
-
-void LabelDrain() {
-	EXIT_IF(g_label_manager == nullptr);
-	g_label_manager->Drain();
-}
-
-bool LabelInCallback() noexcept {
-	return g_in_label_callback;
-}
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/objects/label.h

@@ -1,26 +0,0 @@
-#ifndef EMULATOR_INCLUDE_EMULATOR_GRAPHICS_OBJECTS_LABEL_H_
-#define EMULATOR_INCLUDE_EMULATOR_GRAPHICS_OBJECTS_LABEL_H_
-
-#include "common/abi.h"
-#include "common/common.h"
-
-namespace Libs::Graphics {
-
-struct Label;
-class CommandBuffer;
-struct GraphicContext;
-
-void LabelInit();
-
-constexpr int LABEL_ARGS_MAX = 5;
-using LabelCallback          = bool (*)(const uint64_t* args);
-
-Label* LabelCreate(LabelCallback callback_1, LabelCallback callback_2, const uint64_t* args);
-void   LabelDelete(Label& label);
-void   LabelSet(CommandBuffer& buffer, Label& label);
-void   LabelDrain();
-[[nodiscard]] bool LabelInCallback() noexcept;
-
-} // namespace Libs::Graphics
-
-#endif /* EMULATOR_INCLUDE_EMULATOR_GRAPHICS_OBJECTS_LABEL_H_ */

src/graphics/host_gpu/objects/textureCommon.cpp

@@ -1,17 +1,12 @@
 #include "graphics/host_gpu/objects/textureCommon.h"
 
 #include "common/assert.h"
-#include "common/logging/log.h"
 #include "graphics/guest_gpu/gpu_defs.h"
 #include "graphics/guest_gpu/gpu_format.h"
-#include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/transfer.h"
-#include "graphics/host_gpu/vma.h"
+#include "graphics/host_gpu/renderer/tiler.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 
 #include <algorithm>
-#include <atomic>
 #include <bit>
 #include <cinttypes>
 #include <cstring>
@@ -159,6 +154,8 @@ RenderTargetFormatInfo TextureGetRenderTargetFormat(uint32_t raw_layout, uint32_
 	     raw_type, raw_order);
 }
 
+namespace {
+
 static uint64_t GetLevelSrcOffset(const TileSizeOffset& level_size) {
 	return (level_size.src_size != 0 ? level_size.src_offset : level_size.offset);
 }
@@ -193,28 +190,6 @@ uint64_t TextureUploadSliceSourceOffset(const TextureUploadLayout& layout, uint3
 	return level_offset + static_cast<uint64_t>(slice) * slice_stride;
 }
 
-uint64_t TextureCalcUploadSize(const TextureUploadLayout&          layout,
-                               const std::vector<BufferImageCopy>& regions, uint64_t levels,
-                               uint32_t depth) {
-	uint64_t size = 0;
-
-	for (const auto& r: regions) {
-		size = std::max<uint64_t>(size, static_cast<uint64_t>(r.offset) +
-		                                    layout.level_sizes[r.dst_level].size);
-	}
-
-	for (uint32_t level = 0; level < levels; level++) {
-		const auto src_size  = GetLevelSrcSize(layout.level_sizes[level]);
-		const auto mip_depth = GetTextureLevelDepth(depth, level, layout.volume_texture);
-		for (uint32_t z = 0; z < mip_depth; z++) {
-			size = std::max<uint64_t>(size,
-			                          TextureUploadSliceSourceOffset(layout, level, z) + src_size);
-		}
-	}
-
-	return size;
-}
-
 vk::ComponentSwizzle TextureGetComponentSwizzle(uint8_t s) {
 	switch (static_cast<Prospero::CompSwizzle>(s)) {
 		case Prospero::CompSwizzle::kZero: return vk::ComponentSwizzle::eZero;
@@ -232,6 +207,8 @@ static uint32_t TextureGetDstSel(uint32_t swizzle, uint32_t channel) {
 	return (swizzle >> (channel * 3u)) & 0x7u;
 }
 
+} // namespace
+
 vk::ComponentMapping TextureGetComponentMapping(uint32_t swizzle) {
 	vk::ComponentMapping components {};
 	components.r = TextureGetComponentSwizzle(static_cast<uint8_t>(TextureGetDstSel(swizzle, 0)));
@@ -241,94 +218,6 @@ vk::ComponentMapping TextureGetComponentMapping(uint32_t swizzle) {
 	return components;
 }
 
-bool TextureCheckFormat(vk::ImageCreateInfo& image_info) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	vk::ImageFormatProperties props {};
-	if (graphics.GetImageFormatProperties(image_info.format, image_info.imageType,
-	                                      image_info.tiling, image_info.usage, image_info.flags,
-	                                      &props) == vk::Result::eErrorFormatNotSupported) {
-		auto apply_fallback = [&](vk::Format replacement, const char* message) {
-			image_info.format = replacement;
-			const bool result = TextureCheckFormat(image_info);
-			LOGF("%s [%s]\n", message, (!result ? "FAIL" : "SUCCESS"));
-			return result;
-		};
-
-		if (image_info.format == vk::Format::eR8G8B8A8Srgb) {
-			// TODO() convert SRGB -> LINEAR in shader
-			return apply_fallback(
-			    vk::Format::eR8G8B8A8Unorm,
-			    "replace vk::Format::eR8G8B8A8Srgb => vk::Format::eR8G8B8A8Unorm");
-		}
-		if (image_info.format == vk::Format::eB8G8R8A8Srgb) {
-			// TODO() convert SRGB -> LINEAR in shader
-			return apply_fallback(
-			    vk::Format::eB8G8R8A8Unorm,
-			    "replace vk::Format::eB8G8R8A8Srgb => vk::Format::eB8G8R8A8Unorm");
-		}
-		return false;
-	}
-	return true;
-}
-
-static bool TextureCheckFormatExact(const vk::ImageCreateInfo& image_info) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	vk::ImageFormatProperties props {};
-	return graphics.GetImageFormatProperties(image_info.format, image_info.imageType,
-	                                         image_info.tiling, image_info.usage, image_info.flags,
-	                                         &props) != vk::Result::eErrorFormatNotSupported;
-}
-
-bool TextureCheckStorageSwizzle(vk::ImageCreateInfo& image_info, vk::ComponentMapping& components) {
-	if (image_info.usage & vk::ImageUsageFlagBits::eStorage) {
-		if (components.r == vk::ComponentSwizzle::eR && components.g == vk::ComponentSwizzle::eG &&
-		    components.b == vk::ComponentSwizzle::eB && components.a == vk::ComponentSwizzle::eA) {
-			return true;
-		}
-
-		if (components.r == vk::ComponentSwizzle::eB && components.g == vk::ComponentSwizzle::eG &&
-		    components.b == vk::ComponentSwizzle::eR && components.a == vk::ComponentSwizzle::eA &&
-		    image_info.format == vk::Format::eR8G8B8A8Srgb) {
-			LOGF("replace vk::Format::eR8G8B8A8Srgb => vk::Format::eB8G8R8A8Srgb\n");
-
-			components.r      = vk::ComponentSwizzle::eR;
-			components.g      = vk::ComponentSwizzle::eG;
-			components.b      = vk::ComponentSwizzle::eB;
-			components.a      = vk::ComponentSwizzle::eA;
-			image_info.format = vk::Format::eB8G8R8A8Srgb;
-			return true;
-		}
-
-		// TODO() swizzle channels in shader
-
-		return false;
-	}
-	return true;
-}
-
-vk::ImageUsageFlags TextureGetUsage(TextureFormatUsage usage) {
-	vk::ImageUsageFlags vk_usage =
-	    vk::ImageUsageFlagBits::eTransferDst | vk::ImageUsageFlagBits::eTransferSrc;
-	if (TextureHasFormatUsage(usage, TextureFormatUsage::Sampled)) {
-		vk_usage |= vk::ImageUsageFlagBits::eSampled;
-	}
-	if (TextureHasFormatUsage(usage, TextureFormatUsage::Storage)) {
-		vk_usage |= vk::ImageUsageFlagBits::eStorage;
-	}
-	return vk_usage;
-}
-
-vk::ImageUsageFlags TextureGetViewUsage(TextureFormatUsage usage) {
-	vk::ImageUsageFlags vk_usage = {};
-	if (TextureHasFormatUsage(usage, TextureFormatUsage::Sampled)) {
-		vk_usage |= vk::ImageUsageFlagBits::eSampled;
-	}
-	if (TextureHasFormatUsage(usage, TextureFormatUsage::Storage)) {
-		vk_usage |= vk::ImageUsageFlagBits::eStorage;
-	}
-	return vk_usage;
-}
-
 vk::Format TextureGetFormat(uint32_t fmt) {
 	const auto vk_format = VulkanFormat(fmt);
 	if (vk_format != vk::Format::eUndefined) {
@@ -338,261 +227,10 @@ vk::Format TextureGetFormat(uint32_t fmt) {
 	return vk::Format::eUndefined;
 }
 
-static uint32_t AlignUpU32(uint32_t value, uint32_t alignment) {
-	return (value + alignment - 1u) & ~(alignment - 1u);
-}
+namespace {
 
-uint32_t TextureGetAtlasSliceYStride(vk::Format format, uint32_t mip_height, uint32_t depth,
-                                     uint64_t levels) {
-	return (depth > 1 && levels > 1 && Transfer::IsBlockCompressedFormat(format)
-	            ? AlignUpU32(mip_height, 4u)
-	            : mip_height);
-}
-
-uint32_t TextureCalcStackedImageHeight(vk::Format format, uint32_t height, uint32_t depth,
-                                       uint64_t levels) {
-	auto image_height = height * depth;
-	if (depth <= 1 || levels <= 1 || !Transfer::IsBlockCompressedFormat(format)) {
-		return image_height;
-	}
-
-	uint32_t mip_height = height;
-	for (uint32_t level = 0; level < levels; level++) {
-		const auto mip_image_height =
-		    TextureGetAtlasSliceYStride(format, mip_height, depth, levels) * depth;
-		image_height = std::max<uint32_t>(image_height, mip_image_height << level);
-		if (mip_height > 1) {
-			mip_height /= 2;
-		}
-	}
-
-	return image_height;
-}
-
-uint32_t TextureCalcMipmapAtlasImageHeight(vk::Format format, uint32_t width, uint32_t height,
-                                           uint32_t depth, uint64_t levels) {
-	auto image_height = height * depth;
-	if (levels <= 1) {
-		return image_height;
-	}
-
-	uint32_t mip_height = height;
-	for (uint32_t level = 0; level < levels; level++) {
-		const auto mipmap_offset = Transfer::MipmapAtlasOffset(level, width, height);
-		const auto mip_bottom =
-		    static_cast<uint32_t>(mipmap_offset.second) +
-		    TextureGetAtlasSliceYStride(format, mip_height, depth, levels) * depth;
-		image_height = std::max<uint32_t>(image_height, mip_bottom);
-		if (mip_height > 1) {
-			mip_height /= 2;
-		}
-	}
-
-	return image_height;
-}
-
-bool TextureIs3DTexture(uint64_t type) {
-	return static_cast<Prospero::ImageType>(type) == Prospero::ImageType::kColor3D;
-}
-
-bool TextureIsCubeTexture(uint64_t type) {
-	return static_cast<Prospero::ImageType>(type) == Prospero::ImageType::kCube;
-}
-
-bool TextureIsLayeredTexture(uint64_t type) {
-	const auto image_type = static_cast<Prospero::ImageType>(type);
-	return image_type == Prospero::ImageType::kCube ||
-	       image_type == Prospero::ImageType::kColor1DArray ||
-	       image_type == Prospero::ImageType::kColor2DArray ||
-	       image_type == Prospero::ImageType::kColor2DMsaaArray;
-}
-
-bool TextureCanCreateCubeView(uint64_t type, uint32_t base_array, uint32_t layer_count) {
-	return TextureIsCubeTexture(type) && base_array % 6u == 0 && layer_count >= 6 &&
-	       layer_count % 6u == 0;
-}
-
-vk::ComponentMapping TextureCreateImage(VulkanImage& vk_obj,
-                                        const TextureImageCreateParams& params) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	EXIT_IF(params.owner == nullptr);
-
-	const bool array_texture  = TextureIsLayeredTexture(params.type);
-	const bool volume_texture = TextureIs3DTexture(params.type);
-
-	auto pixel_format = TextureGetFormat(params.fmt);
-	EXIT_NOT_IMPLEMENTED(pixel_format == vk::Format::eUndefined);
-	EXIT_NOT_IMPLEMENTED(params.width == 0);
-	EXIT_NOT_IMPLEMENTED(params.height == 0);
-	EXIT_NOT_IMPLEMENTED(params.depth == 0);
-	EXIT_NOT_IMPLEMENTED(params.levels == 0 || params.levels > 16);
-
-	uint32_t image_height = 0;
-	uint32_t image_mips   = 0;
-	if (params.image_layout == TextureUploadDestination::MipAtlas) {
-		EXIT_NOT_IMPLEMENTED(params.base_level != 0);
-		const auto atlas_depth = (array_texture || volume_texture ? 1u : params.depth);
-		image_height           = TextureCalcMipmapAtlasImageHeight(
-		    pixel_format, static_cast<uint32_t>(params.width), static_cast<uint32_t>(params.height),
-		    atlas_depth, params.levels);
-		image_mips = 1;
-	} else {
-		image_height =
-		    (array_texture || volume_texture
-		         ? static_cast<uint32_t>(params.height)
-		         : TextureCalcStackedImageHeight(pixel_format, static_cast<uint32_t>(params.height),
-		                                         params.depth, params.levels));
-		image_mips = static_cast<uint32_t>(params.levels);
-	}
-
-	vk::ComponentMapping components =
-	    TextureGetComponentMapping(static_cast<uint32_t>(params.swizzle));
-
-	vk::ImageCreateInfo image_info {};
-	image_info.sType = vk::StructureType::eImageCreateInfo;
-	image_info.pNext = nullptr;
-	image_info.flags =
-	    (params.allow_cube_view && TextureCanCreateCubeView(params.type, 0, params.depth)
-	         ? vk::ImageCreateFlagBits::eCubeCompatible
-	         : vk::ImageCreateFlags {}) |
-	    (volume_texture ? vk::ImageCreateFlagBits::e2DArrayCompatible : vk::ImageCreateFlags {}) |
-	    (params.compatible_format_views ? vk::ImageCreateFlagBits::eMutableFormat
-	                                    : vk::ImageCreateFlags {});
-	image_info.imageType     = (volume_texture ? vk::ImageType::e3D : vk::ImageType::e2D);
-	image_info.extent.width  = static_cast<uint32_t>(params.width);
-	image_info.extent.height = image_height;
-	image_info.extent.depth  = (volume_texture ? params.depth : 1);
-	image_info.mipLevels     = image_mips;
-	image_info.arrayLayers   = (array_texture ? params.depth : 1);
-	image_info.format        = pixel_format;
-	image_info.tiling        = vk::ImageTiling::eOptimal;
-	image_info.initialLayout = vk::ImageLayout::eUndefined;
-	image_info.usage         = TextureGetUsage(params.format_usage);
-	image_info.sharingMode   = vk::SharingMode::eExclusive;
-	image_info.samples       = vk::SampleCountFlagBits::e1;
-
-	const bool storage_view = TextureHasFormatUsage(params.view_usage, TextureFormatUsage::Storage);
-	if (storage_view && !TextureCheckStorageSwizzle(image_info, components)) {
-		if (!params.storage_swizzle_fallback) {
-			EXIT("swizzle is not supported");
-		}
-
-		static std::atomic_uint log_count {0};
-		if (log_count.fetch_add(1, std::memory_order_relaxed) < 16) {
-			LOGF("\t %s swizzle 0x%08" PRIx64 " is not supported, using identity mapping\n",
-			     params.owner, params.swizzle);
-		}
-		components.r = vk::ComponentSwizzle::eR;
-		components.g = vk::ComponentSwizzle::eG;
-		components.b = vk::ComponentSwizzle::eB;
-		components.a = vk::ComponentSwizzle::eA;
-	}
-
-	const auto view_checked_format = image_info.format;
-	const auto requested_usage     = params.format_usage;
-	const auto required_usage      = params.required_format_usage;
-	const bool has_optional_usage  = static_cast<uint32_t>(requested_usage & ~required_usage) != 0;
-	if (!TextureCheckFormatExact(image_info) && has_optional_usage) {
-		auto required_info   = image_info;
-		required_info.usage  = TextureGetUsage(required_usage);
-		required_info.format = view_checked_format;
-		if (TextureCheckFormatExact(required_info)) {
-			static std::atomic_uint log_count {0};
-			if (log_count.fetch_add(1, std::memory_order_relaxed) < 16) {
-				LOGF("\t %s usage 0x%08x is not supported for format %d, using required "
-				     "usage 0x%08x\n",
-				     params.owner, static_cast<uint32_t>(TextureGetUsage(requested_usage)),
-				     static_cast<int>(image_info.format),
-				     static_cast<uint32_t>(TextureGetUsage(required_usage)));
-			}
-			image_info = required_info;
-		}
-	}
-
-	if (!TextureCheckFormat(image_info)) {
-		if (has_optional_usage) {
-			image_info.format = view_checked_format;
-			image_info.usage  = TextureGetUsage(required_usage);
-		}
-		if (!has_optional_usage || !TextureCheckFormat(image_info)) {
-			EXIT("format is not supported");
-		}
-	}
-
-	vk_obj.extent.width  = image_info.extent.width;
-	vk_obj.extent.height = image_info.extent.height;
-	vk_obj.layers        = image_info.arrayLayers;
-	vk_obj.mip_levels    = image_info.mipLevels;
-	vk_obj.format        = image_info.format;
-	vk_obj.image         = nullptr;
-	vk_obj.layout        = image_info.initialLayout;
-
-	vk_obj.memory.property = vk::MemoryPropertyFlagBits::eDeviceLocal;
-
-	bool created = graphics.CreateImage(image_info, vk_obj);
-	EXIT_NOT_IMPLEMENTED(!created);
-
-	return components;
-}
-
-void TextureCreateImageViews(VulkanImage& vk_obj,
-                             vk::ComponentMapping components, uint64_t type, uint32_t base_array,
-                             uint32_t base_level, uint32_t level_count, uint32_t depth,
-                             bool allow_cube_view, TextureFormatUsage view_usage) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	EXIT_IF(level_count == 0 || base_level + level_count > vk_obj.mip_levels);
-
-	const bool layered_texture = TextureIsLayeredTexture(type);
-	const bool volume_texture  = TextureIs3DTexture(type);
-	const auto layer_count     = (layered_texture && base_array < depth ? depth - base_array : 1u);
-	const auto volume_slices   = std::max(depth >> base_level, 1u);
-
-	vk::ImageViewUsageCreateInfo usage_info {};
-	usage_info.sType = vk::StructureType::eImageViewUsageCreateInfo;
-	usage_info.pNext = nullptr;
-	usage_info.usage = TextureGetViewUsage(view_usage);
-
-	vk::ImageViewCreateInfo create_info {};
-	create_info.sType                           = vk::StructureType::eImageViewCreateInfo;
-	create_info.pNext                           = (usage_info.usage ? &usage_info : nullptr);
-	create_info.flags                           = {};
-	create_info.image                           = vk_obj.image;
-	create_info.viewType                        = vk::ImageViewType::e2D;
-	create_info.format                          = vk_obj.format;
-	create_info.components                      = components;
-	create_info.subresourceRange.aspectMask     = vk::ImageAspectFlagBits::eColor;
-	create_info.subresourceRange.baseArrayLayer = (layered_texture ? base_array : 0);
-	create_info.subresourceRange.baseMipLevel   = base_level;
-	create_info.subresourceRange.layerCount     = layer_count;
-	create_info.subresourceRange.levelCount     = level_count;
-	if (volume_texture) {
-		create_info.viewType                        = vk::ImageViewType::e3D;
-		create_info.subresourceRange.baseArrayLayer = 0;
-		create_info.subresourceRange.layerCount     = 1;
-	} else if (allow_cube_view && TextureCanCreateCubeView(type, base_array, layer_count)) {
-		create_info.viewType =
-		    (layer_count > 6 ? vk::ImageViewType::eCubeArray : vk::ImageViewType::eCube);
-	} else if (layered_texture) {
-		create_info.viewType = vk::ImageViewType::e2DArray;
-	}
-
-	auto create_view = [&](int index) {
-		const auto result =
-		    graphics.device.createImageView(&create_info, nullptr, &vk_obj.image_view[index]);
-		if (result != vk::Result::eSuccess || vk_obj.image_view[index] == nullptr) {
-			EXIT("failed to create texture image view: result=%d format=%d index=%d\n",
-			     static_cast<int>(result), static_cast<int>(create_info.format), index);
-		}
-	};
-	create_view(VulkanImage::VIEW_DEFAULT);
-
-	create_info.viewType                    = vk::ImageViewType::e2DArray;
-	create_info.subresourceRange.layerCount = volume_texture ? volume_slices : layer_count;
-	create_view(VulkanImage::VIEW_DEFAULT_ARRAY);
-}
-
-static uint64_t CalcTextureSliceStride(const TileSizeOffset* level_sizes, uint64_t levels,
-                                       uint64_t total_size, uint32_t depth) {
+uint64_t CalcTextureSliceStride(const TileSizeOffset* level_sizes, uint64_t levels,
+                                uint64_t total_size, uint32_t depth) {
 	uint64_t stride = 0;
 	for (uint32_t i = 0; i < levels; i++) {
 		stride =
@@ -609,7 +247,7 @@ static uint64_t CalcTextureSliceStride(const TileSizeOffset* level_sizes, uint64
 	return stride;
 }
 
-static uint64_t CalcLinearUploadLevelSize(uint32_t fmt, uint32_t pitch, uint32_t height) {
+uint64_t CalcLinearUploadLevelSize(uint32_t fmt, uint32_t pitch, uint32_t height) {
 	if (const uint32_t bytes_per_element = Prospero::NumBytesPerElement(fmt);
 	    bytes_per_element != 0) {
 		return static_cast<uint64_t>(pitch) * height * bytes_per_element;
@@ -625,8 +263,8 @@ static uint64_t CalcLinearUploadLevelSize(uint32_t fmt, uint32_t pitch, uint32_t
 	return 0;
 }
 
-static uint64_t SetLinearUploadLevels(TileSizeOffset* level_sizes, uint32_t fmt, uint64_t height,
-                                      uint64_t levels, uint32_t base_pitch) {
+uint64_t SetLinearUploadLevels(TileSizeOffset* level_sizes, uint32_t fmt, uint64_t height,
+                               uint64_t levels, uint32_t base_pitch) {
 	uint64_t offset = 0;
 	auto     pitch  = base_pitch;
 	auto     h      = static_cast<uint32_t>(height);
@@ -655,6 +293,8 @@ static uint64_t SetLinearUploadLevels(TileSizeOffset* level_sizes, uint32_t fmt,
 	return offset;
 }
 
+} // namespace
+
 TextureUploadLayout TextureCalcUploadLayout(uint32_t fmt, uint64_t width, uint64_t height,
                                             uint64_t levels, uint32_t depth, uint64_t pitch,
                                             uint64_t tile, uint64_t upload_size,
@@ -663,6 +303,7 @@ TextureUploadLayout TextureCalcUploadLayout(uint32_t fmt, uint64_t width, uint64
 	TextureUploadLayout layout {};
 	layout.tile           = static_cast<uint32_t>(tile);
 	layout.pitch          = static_cast<uint32_t>(pitch);
+	layout.texel_block    = Prospero::BlockCompressedBytesPerBlock(fmt) != 0 ? 4u : 1u;
 	layout.volume_texture = volume_texture;
 
 	if (fmt != 0) {
@@ -752,12 +393,10 @@ TextureUploadLayout TextureCalcUploadLayout(uint32_t fmt, uint64_t width, uint64
 	return layout;
 }
 
-std::vector<BufferImageCopy> TextureBuildUploadRegions(const TextureUploadLayout& layout,
-                                                       vk::Format image_format, uint32_t width,
-                                                       uint32_t height, uint32_t depth,
-                                                       uint64_t levels, bool array_texture,
-                                                       bool                     volume_texture,
-                                                       TextureUploadDestination destination) {
+std::vector<vk::BufferImageCopy>
+TextureBuildImageCopies(const TextureUploadLayout& layout, uint32_t width, uint32_t height,
+                        uint32_t depth, uint64_t levels, bool array_texture,
+                        bool volume_texture) {
 	uint32_t mip_width  = width;
 	uint32_t mip_height = height;
 	uint32_t mip_pitch  = volume_texture && static_cast<Prospero::TileMode>(layout.tile) !=
@@ -765,53 +404,34 @@ std::vector<BufferImageCopy> TextureBuildUploadRegions(const TextureUploadLayout
 	                          ? width
 	                          : layout.pitch;
 
-	std::vector<BufferImageCopy> regions;
+	std::vector<vk::BufferImageCopy> regions;
 	regions.reserve(GetTextureRegionCount(depth, levels, volume_texture));
 	for (uint32_t i = 0; i < levels; i++) {
 		EXIT_NOT_IMPLEMENTED(layout.level_sizes[i].size == 0);
 
-		const auto mipmap_offset = Transfer::MipmapAtlasOffset(i, width, height);
-		const auto mip_depth     = GetTextureLevelDepth(depth, i, volume_texture);
+		const auto mip_depth = GetTextureLevelDepth(depth, i, volume_texture);
 
 		for (uint32_t z = 0; z < mip_depth; z++) {
-			const auto      slice_offset = z * layout.slice_stride;
-			BufferImageCopy region {};
-
-			region.offset = static_cast<uint32_t>(layout.level_sizes[i].offset + slice_offset);
-			region.width  = mip_width;
-			region.height = mip_height;
-			region.copy_height =
-			    (!array_texture && !volume_texture && depth > 1 && levels > 1 &&
-			             Transfer::IsBlockCompressedFormat(image_format)
-			         ? TextureGetAtlasSliceYStride(image_format, mip_height, depth, levels)
-			         : 0);
-			region.dst_layer = (array_texture ? z : 0);
-			region.dst_z     = (volume_texture ? static_cast<int>(z) : 0);
-			if (!layout.volume_texture &&
-			    static_cast<Prospero::TileMode>(layout.tile) == Prospero::TileMode::kLinear &&
-			    layout.padded_sizes[i].width != 0) {
-				region.pitch = layout.padded_sizes[i].width;
+			const auto slice_offset = z * layout.slice_stride;
+			vk::BufferImageCopy region {};
+			region.bufferOffset =
+			    layout.level_sizes[i].offset + slice_offset;
+			region.imageSubresource = {vk::ImageAspectFlagBits::eColor, i,
+			                           array_texture ? z : 0, 1};
+			region.imageOffset.z = volume_texture ? static_cast<int>(z) : 0;
+			region.imageExtent   = {mip_width, mip_height, 1};
+			const bool linear =
+			    static_cast<Prospero::TileMode>(layout.tile) == Prospero::TileMode::kLinear;
+			if (linear) {
+				region.bufferRowLength   = layout.padded_sizes[i].width;
+				region.bufferImageHeight = layout.padded_sizes[i].height;
 			} else {
-				region.pitch = mip_pitch;
-			}
-
-			if (destination == TextureUploadDestination::MipLevels) {
-				region.dst_level = i;
-				region.dst_x     = 0;
-				region.dst_y =
-				    (array_texture || volume_texture
-				         ? 0
-				         : static_cast<int>(z * TextureGetAtlasSliceYStride(
-				                                    image_format, mip_height, depth, levels)));
-			} else {
-				region.dst_level = 0;
-				region.dst_x     = mipmap_offset.first;
-				region.dst_y =
-				    (array_texture || volume_texture
-				         ? mipmap_offset.second
-				         : mipmap_offset.second +
-				               static_cast<int>(z * TextureGetAtlasSliceYStride(
-				                                        image_format, mip_height, depth, levels)));
+				const auto align = [](uint32_t value, uint32_t block) {
+					return ((value + block - 1u) / block) * block;
+				};
+				const auto pitch = align(mip_pitch, layout.texel_block);
+				region.bufferRowLength =
+				    pitch > align(mip_width, layout.texel_block) ? pitch : 0;
 			}
 			regions.push_back(region);
 		}
@@ -830,55 +450,6 @@ std::vector<BufferImageCopy> TextureBuildUploadRegions(const TextureUploadLayout
 	return regions;
 }
 
-std::vector<ImageBufferCopy>
-TextureBuildDownloadRegions(const std::vector<BufferImageCopy>& upload_regions) {
-	std::vector<ImageBufferCopy> regions;
-	regions.reserve(upload_regions.size());
-	for (const auto& region: upload_regions) {
-		regions.push_back({region.offset, region.pitch, region.dst_level, region.width,
-		                   region.height, region.copy_height, region.dst_layer, region.dst_x,
-		                   region.dst_y, region.dst_z, region.aspect});
-	}
-	return regions;
-}
-
-static uint64_t FmaskRegionCopySize(const BufferImageCopy& region) {
-	const uint64_t row_length = (region.pitch != 0 ? region.pitch : region.width);
-	if (region.height == 0 || region.width == 0) {
-		return 0;
-	}
-	return ((static_cast<uint64_t>(region.height - 1u) * row_length) + region.width) *
-	       sizeof(uint32_t);
-}
-
-static void UploadFmaskIdentity(VulkanImage& vk_obj,
-                                const std::vector<BufferImageCopy>& regions,
-                                vk::ImageLayout dst_layout, const char* owner) {
-	constexpr uint32_t kIdentityFmaskPattern = 0x76543210u;
-
-	std::vector<BufferImageCopy> upload_regions = regions;
-	uint64_t                     upload_size    = 0;
-	for (auto& region: upload_regions) {
-		upload_size = (upload_size + 255u) & ~uint64_t {255};
-		EXIT_NOT_IMPLEMENTED(upload_size > UINT32_MAX);
-		region.offset = static_cast<uint32_t>(upload_size);
-		upload_size += FmaskRegionCopySize(region);
-	}
-
-	LOGF("%s: temporary: decoding PS5 FMASK8_S4_F4 as identity pattern 0x%08" PRIx32
-	     ", upload_size=%" PRIu64 " regions=%zu\n",
-	     owner, kIdentityFmaskPattern, upload_size, upload_regions.size());
-
-	Transfer::ScratchBuffer temp_buf(upload_size);
-	auto*                   words = static_cast<uint32_t*>(temp_buf.Data());
-	for (uint64_t i = 0; i < upload_size / sizeof(uint32_t); i++) {
-		words[i] = kIdentityFmaskPattern;
-	}
-
-	Transfer::UploadImage(vk_obj, temp_buf.Data(), upload_size, upload_regions,
-	                      dst_layout);
-}
-
 struct GpuTileElementLayout {
 	uint32_t bytes = 0;
 	uint32_t wide  = 1;
@@ -905,7 +476,8 @@ static bool SetGpuTileSize(uint64_t offset, uint64_t length, uint64_t capacity,
 	return true;
 }
 
-bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>& regions,
+bool TextureBuildGpuTileInfos(uint64_t size,
+                              const std::vector<vk::BufferImageCopy>& regions,
                               const TextureUploadLayout& layout, uint32_t fmt, uint32_t depth,
                               uint64_t levels, std::vector<GpuTileInfo>& out_infos) {
 	if (size == 0 || levels == 0 || levels > 16 || depth == 0 ||
@@ -929,7 +501,8 @@ bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>&
 	infos.reserve(regions.size());
 	if (layout.volume_texture) {
 		TileVolumeLayout volume {};
-		if (!TileGetTextureVolumeLayout(fmt, regions[0].width, regions[0].height, depth,
+		if (!TileGetTextureVolumeLayout(fmt, regions[0].imageExtent.width,
+		                                regions[0].imageExtent.height, depth,
 		                                static_cast<uint32_t>(levels), layout.tile, volume)) {
 			return false;
 		}
@@ -945,10 +518,16 @@ bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>&
 			for (uint32_t z = 0; z < mip_depth; z += block.block_depth) {
 				const uint32_t copy_depth = std::min(block.block_depth, mip_depth - z);
 				const auto&    region     = regions[region_base + z];
+				const auto     pitch = region.bufferRowLength != 0
+				                           ? region.bufferRowLength
+				                           : region.imageExtent.width;
+				const auto logical_height = region.bufferImageHeight != 0
+				                                ? region.bufferImageHeight
+				                                : region.imageExtent.height;
 				GpuTileInfo    info {};
 				info.family            = block.family;
 				info.bytes_per_element = block.bytes_per_element;
-				info.linear_offset     = region.offset;
+				info.linear_offset     = region.bufferOffset;
 				info.tiled_offset =
 				    static_cast<uint64_t>(z / block.block_depth) * volume.block_slice_size +
 				    volume.level_offsets[level];
@@ -961,11 +540,16 @@ bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>&
 					return false;
 				}
 				info.linear_slice_stride = linear_stride;
-				info.width       = std::max((region.width + element.wide - 1u) / element.wide, 1u);
-				info.height      = std::max((region.height + element.tall - 1u) / element.tall, 1u);
+				info.width = std::max(
+				    (region.imageExtent.width + element.wide - 1u) / element.wide, 1u);
+				info.height = std::max(
+				    (logical_height + element.tall - 1u) / element.tall, 1u);
 				info.depth       = copy_depth;
-				info.surface_z   = block.block_depth == 1 ? static_cast<uint32_t>(region.dst_z) : 0;
-				info.pitch       = std::max((region.pitch + element.wide - 1u) / element.wide, 1u);
+				info.surface_z = block.block_depth == 1
+				                     ? static_cast<uint32_t>(region.imageOffset.z)
+				                     : 0;
+				info.pitch =
+				    std::max((pitch + element.wide - 1u) / element.wide, 1u);
 				info.tail_x      = tail ? volume.tail_x[level] : 0;
 				info.tail_y      = tail ? volume.tail_y[level] : 0;
 				info.tail        = tail;
@@ -993,23 +577,32 @@ bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>&
 			const auto level_depth = GetTextureLevelDepth(depth, level, layout.volume_texture);
 			for (uint32_t z = 0; z < level_depth; z++) {
 				const auto& region = regions[region_index++];
+				const auto pitch = region.bufferRowLength != 0
+				                       ? region.bufferRowLength
+				                       : region.imageExtent.width;
+				const auto logical_height = region.bufferImageHeight != 0
+				                                ? region.bufferImageHeight
+				                                : region.imageExtent.height;
 				GpuTileInfo info {};
 				info.family            = block.family;
 				info.bytes_per_element = block.bytes_per_element;
-				info.linear_offset     = region.offset;
+				info.linear_offset     = region.bufferOffset;
 				info.tiled_offset      = TextureUploadSliceSourceOffset(layout, level, z);
 				if (!SetGpuTileSize(info.linear_offset, level_size.size, size, info.linear_size) ||
 				    !SetGpuTileSize(info.tiled_offset, GetLevelSrcSize(level_size), size,
 				                    info.tiled_size)) {
 					return false;
 				}
-				info.width     = std::max((region.width + element.wide - 1u) / element.wide, 1u);
-				info.height    = std::max((region.height + element.tall - 1u) / element.tall, 1u);
+				info.width = std::max(
+				    (region.imageExtent.width + element.wide - 1u) / element.wide, 1u);
+				info.height = std::max(
+				    (logical_height + element.tall - 1u) / element.tall, 1u);
 				info.surface_z = base_family == TileBlockFamily::RenderTarget64KB ||
 				                         base_family == TileBlockFamily::Depth64KB
-				                     ? region.dst_layer
+				                     ? region.imageSubresource.baseArrayLayer
 				                     : 0;
-				info.pitch     = std::max((region.pitch + element.wide - 1u) / element.wide, 1u);
+				info.pitch =
+				    std::max((pitch + element.wide - 1u) / element.wide, 1u);
 				info.tail      = tail;
 				info.tail_x    = tail ? level_size.x : 0;
 				info.tail_y    = tail ? level_size.y : 0;
@@ -1037,32 +630,4 @@ bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>&
 	return true;
 }
 
-void TextureUploadGuestImage(VulkanImage& vk_obj, const void* src_data,
-                             uint64_t size, const std::vector<BufferImageCopy>& regions,
-                             const TextureUploadLayout& layout, uint32_t fmt, uint64_t width,
-                             uint64_t height, uint32_t depth, uint64_t levels, const char* owner,
-                             vk::ImageLayout dst_layout) {
-	if (fmt == 0) {
-		EXIT("%s: texture upload format unsupported: fmt=0 tile=%u size=%" PRIu64 " extent=%" PRIu64
-		     "x%" PRIu64 " depth=%u pitch=%u levels=%" PRIu64 "\n",
-		     owner, layout.tile, size, width, height, depth, layout.pitch, levels);
-	}
-	if (static_cast<Prospero::TileMode>(layout.tile) == Prospero::TileMode::kLinear) {
-		Transfer::UploadImage(vk_obj, src_data, size, regions, dst_layout);
-		return;
-	}
-	if (layout.tile_family == TileBlockFamily::Depth64KB && Prospero::IsFmaskTextureFormat(fmt)) {
-		UploadFmaskIdentity(vk_obj, regions, dst_layout, owner);
-		return;
-	}
-
-	std::vector<GpuTileInfo> infos;
-	if (!TextureBuildGpuTileInfos(size, regions, layout, fmt, depth, levels, infos)) {
-		EXIT("%s: GPU tiled upload unsupported: fmt=%u tile=%u size=%" PRIu64 " extent=%" PRIu64
-		     "x%" PRIu64 " depth=%u pitch=%u levels=%" PRIu64 "\n",
-		     owner, fmt, layout.tile, size, width, height, depth, layout.pitch, levels);
-	}
-	Transfer::UploadTiledImage(vk_obj, src_data, size, size, infos, regions, dst_layout);
-}
-
 } // namespace Libs::Graphics

src/graphics/host_gpu/objects/textureCommon.h

@@ -5,44 +5,13 @@
 #include "common/common.h"
 #include "graphics/guest_gpu/gpu_defs.h"
 #include "graphics/guest_gpu/tile.h"
-#include "graphics/host_gpu/transfer.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 
 #include <vector>
 
 namespace Libs::Graphics {
 
-struct GraphicContext;
-struct VulkanImage;
-
-enum class TextureFormatUsage : uint32_t {
-	None    = 0,
-	Sampled = 1u << 0u,
-	Storage = 1u << 1u,
-};
-
-constexpr TextureFormatUsage operator|(TextureFormatUsage lhs, TextureFormatUsage rhs) {
-	return static_cast<TextureFormatUsage>(static_cast<uint32_t>(lhs) | static_cast<uint32_t>(rhs));
-}
-
-constexpr TextureFormatUsage operator&(TextureFormatUsage lhs, TextureFormatUsage rhs) {
-	return static_cast<TextureFormatUsage>(static_cast<uint32_t>(lhs) & static_cast<uint32_t>(rhs));
-}
-
-constexpr TextureFormatUsage operator~(TextureFormatUsage usage) {
-	return static_cast<TextureFormatUsage>(~static_cast<uint32_t>(usage));
-}
-
-constexpr TextureFormatUsage& operator|=(TextureFormatUsage& lhs, TextureFormatUsage rhs) {
-	lhs = lhs | rhs;
-	return lhs;
-}
-
-constexpr bool TextureHasFormatUsage(TextureFormatUsage usage, TextureFormatUsage flag) {
-	return (static_cast<uint32_t>(usage & flag) == static_cast<uint32_t>(flag));
-}
-
-enum class TextureUploadDestination { MipLevels, MipAtlas };
+struct GpuTileInfo;
 
 struct RenderTargetFormatInfo {
 	vk::Format                      format            = vk::Format::eUndefined;
@@ -53,6 +22,7 @@ struct RenderTargetFormatInfo {
 struct TextureUploadLayout {
 	uint32_t        tile                = 0;
 	uint32_t        pitch               = 0;
+	uint32_t        texel_block         = 1;
 	uint64_t        slice_stride        = 0;
 	uint64_t        source_slice_stride = 0;
 	uint32_t        first_tail_level    = 16;
@@ -62,75 +32,22 @@ struct TextureUploadLayout {
 	TilePaddedSize  padded_sizes[16]    = {};
 };
 
-struct TextureImageCreateParams {
-	uint32_t                 fmt                      = 0;
-	uint64_t                 width                    = 0;
-	uint64_t                 height                   = 0;
-	uint32_t                 base_level               = 0;
-	uint64_t                 levels                   = 1;
-	uint32_t                 depth                    = 1;
-	uint64_t                 type                     = 0;
-	uint64_t                 swizzle                  = 0;
-	TextureFormatUsage       format_usage             = TextureFormatUsage::Sampled;
-	TextureFormatUsage       required_format_usage    = TextureFormatUsage::Sampled;
-	TextureFormatUsage       view_usage               = TextureFormatUsage::Sampled;
-	TextureUploadDestination image_layout             = TextureUploadDestination::MipLevels;
-	bool                     allow_cube_view          = false;
-	bool                     compatible_format_views  = false;
-	bool                     storage_swizzle_fallback = false;
-	const char*              owner                    = nullptr;
-};
-
-vk::ComponentSwizzle TextureGetComponentSwizzle(uint8_t s);
 vk::ComponentMapping TextureGetComponentMapping(uint32_t swizzle);
-bool                 TextureCheckFormat(vk::ImageCreateInfo& image_info);
-bool TextureCheckStorageSwizzle(vk::ImageCreateInfo& image_info, vk::ComponentMapping& components);
-vk::ImageUsageFlags    TextureGetUsage(TextureFormatUsage usage);
-vk::ImageUsageFlags    TextureGetViewUsage(TextureFormatUsage usage);
 vk::Format             TextureGetFormat(uint32_t fmt);
 RenderTargetFormatInfo TextureGetRenderTargetFormat(uint32_t layout, uint32_t type, uint32_t order);
-uint32_t TextureGetAtlasSliceYStride(vk::Format format, uint32_t mip_height, uint32_t depth,
-                                     uint64_t levels);
-uint32_t TextureCalcStackedImageHeight(vk::Format format, uint32_t height, uint32_t depth,
-                                       uint64_t levels);
-uint32_t TextureCalcMipmapAtlasImageHeight(vk::Format format, uint32_t width, uint32_t height,
-                                           uint32_t depth, uint64_t levels);
-bool     TextureIs3DTexture(uint64_t type);
-bool     TextureIsCubeTexture(uint64_t type);
-bool     TextureIsLayeredTexture(uint64_t type);
-bool     TextureCanCreateCubeView(uint64_t type, uint32_t base_array, uint32_t layer_count);
-vk::ComponentMapping TextureCreateImage(VulkanImage& image,
-                                        const TextureImageCreateParams& params);
-void TextureCreateImageViews(VulkanImage& vk_obj,
-                             vk::ComponentMapping components, uint64_t type, uint32_t base_array,
-                             uint32_t base_level, uint32_t level_count, uint32_t depth,
-                             bool allow_cube_view, TextureFormatUsage view_usage);
 TextureUploadLayout TextureCalcUploadLayout(uint32_t fmt, uint64_t width, uint64_t height,
                                             uint64_t levels, uint32_t depth, uint64_t pitch,
                                             uint64_t tile, uint64_t upload_size,
                                             bool allow_depth_tile, bool volume_texture,
                                             const char* owner);
-uint64_t TextureUploadSliceSourceOffset(const TextureUploadLayout& layout, uint32_t level,
-                                        uint32_t slice);
-uint64_t TextureCalcUploadSize(const TextureUploadLayout&          layout,
-                               const std::vector<BufferImageCopy>& regions, uint64_t levels,
-                               uint32_t depth);
-std::vector<BufferImageCopy> TextureBuildUploadRegions(const TextureUploadLayout& layout,
-                                                       vk::Format image_format, uint32_t width,
-                                                       uint32_t height, uint32_t depth,
-                                                       uint64_t levels, bool array_texture,
-                                                       bool                     volume_texture,
-                                                       TextureUploadDestination destination);
-std::vector<ImageBufferCopy>
-TextureBuildDownloadRegions(const std::vector<BufferImageCopy>& upload_regions);
-bool TextureBuildGpuTileInfos(uint64_t size, const std::vector<BufferImageCopy>& regions,
+std::vector<vk::BufferImageCopy>
+TextureBuildImageCopies(const TextureUploadLayout& layout, uint32_t width, uint32_t height,
+                        uint32_t depth, uint64_t levels, bool array_texture,
+                        bool volume_texture);
+bool TextureBuildGpuTileInfos(uint64_t size,
+                              const std::vector<vk::BufferImageCopy>& regions,
                               const TextureUploadLayout& layout, uint32_t fmt, uint32_t depth,
                               uint64_t levels, std::vector<GpuTileInfo>& infos);
-void TextureUploadGuestImage(VulkanImage& vk_obj, const void* src_data,
-                             uint64_t size, const std::vector<BufferImageCopy>& regions,
-                             const TextureUploadLayout& layout, uint32_t fmt, uint64_t width,
-                             uint64_t height, uint32_t depth, uint64_t levels, const char* owner,
-                             vk::ImageLayout dst_layout);
 
 } // namespace Libs::Graphics
 

src/graphics/host_gpu/pageManager.cpp

@@ -30,6 +30,16 @@ constexpr uint64_t ADDRESS_SIZE = TRACKER_ADDRESS_SIZE;
 constexpr uint64_t REGION_COUNT = ADDRESS_SIZE / REGION_SIZE;
 constexpr uint64_t REGION_PAGES = REGION_SIZE / PAGE_SIZE;
 
+#if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
+constexpr uint32_t NO_ACCESS_PROTECTION = PAGE_NOACCESS;
+constexpr uint32_t READ_ONLY_PROTECTION = PAGE_READONLY;
+constexpr uint32_t READ_WRITE_PROTECTION = PAGE_READWRITE;
+#else
+constexpr uint32_t NO_ACCESS_PROTECTION = 0;
+constexpr uint32_t READ_ONLY_PROTECTION = 1;
+constexpr uint32_t READ_WRITE_PROTECTION = 2;
+#endif
+
 thread_local bool g_in_fault_resolution = false;
 
 [[noreturn]] void FailFast(const char* reason = nullptr) noexcept {
@@ -184,21 +194,22 @@ struct PageManager::Impl {
 
 	static uint32_t WatcherProtection(const PageState& page) {
 		if (page.access_watchers != 0) {
-			return PAGE_NOACCESS;
+			return NO_ACCESS_PROTECTION;
 		}
 		if (page.write_watchers != 0) {
-			return PAGE_READONLY;
+			return READ_ONLY_PROTECTION;
 		}
 		return page.original_protection;
 	}
 
 	static void PublishDelayedFaults(PageState& page, uint32_t old_protection,
 	                                 uint32_t new_protection) {
-		if (old_protection == PAGE_NOACCESS && new_protection != PAGE_NOACCESS) {
+		if (old_protection == NO_ACCESS_PROTECTION && new_protection != NO_ACCESS_PROTECTION) {
 			page.late_read_pending = true;
 		}
-		if ((old_protection == PAGE_NOACCESS || old_protection == PAGE_READONLY) &&
-		    new_protection == PAGE_READWRITE) {
+		if ((old_protection == NO_ACCESS_PROTECTION ||
+		     old_protection == READ_ONLY_PROTECTION) &&
+		    new_protection == READ_WRITE_PROTECTION) {
 			page.late_write_pending = true;
 		}
 	}
@@ -297,8 +308,7 @@ bool PageManager::IsTracked(uint64_t vaddr) const noexcept {
 }
 
 bool PageManager::IsMapped(uint64_t vaddr, uint64_t size) const noexcept {
-	if (g_in_fault_resolution || vaddr == 0 || size == 0 || vaddr >= ADDRESS_SIZE ||
-	    size > ADDRESS_SIZE - vaddr) {
+	if (vaddr == 0 || size == 0 || vaddr >= ADDRESS_SIZE || size > ADDRESS_SIZE - vaddr) {
 		return false;
 	}
 	const auto end = PageStart(vaddr + size - 1) + PAGE_SIZE;
@@ -363,9 +373,6 @@ bool PageManager::HasGpuAccess(uint64_t vaddr, uint64_t size, GpuAccess access)
 
 void PageManager::UpdatePageWatchers(bool track, uint64_t vaddr, uint64_t size,
                                      PageWatchMode mode) {
-	if (g_in_fault_resolution) {
-		FailFast("page watchers changed during fault resolution");
-	}
 	if (mode != PageWatchMode::Write && mode != PageWatchMode::ReadWrite) {
 		Fatal("invalid watcher mode");
 	}
@@ -401,11 +408,11 @@ void PageManager::UpdatePageWatchers(bool track, uint64_t vaddr, uint64_t size,
 				Impl::Protect(page_vaddr, new_protection, old_protection, false);
 			}
 			switch (new_protection) {
-				case PAGE_NOACCESS:
+				case NO_ACCESS_PROTECTION:
 					page.late_read_pending  = false;
 					page.late_write_pending = false;
 					break;
-				case PAGE_READONLY: page.late_write_pending = false; break;
+				case READ_ONLY_PROTECTION: page.late_write_pending = false; break;
 				default: break;
 			}
 		} else {
@@ -500,6 +507,37 @@ PageManager::BackingWrite::~BackingWrite() {
 	m_manager.EndBackingWrite(m_vaddr, m_size);
 }
 
+std::vector<std::unique_ptr<PageManager::BackingWrite>>
+PageManager::ReserveBackingWrites(std::span<const RangeSet::Range> ranges) {
+	if (ranges.empty()) {
+		Fatal("cannot reserve empty backing-write ranges");
+	}
+	std::vector<std::unique_ptr<BackingWrite>> writes;
+	writes.reserve(ranges.size());
+	uint64_t begin = 0;
+	uint64_t end   = 0;
+	for (const auto& range: ranges) {
+		if (range.address == 0 || range.size == 0 || range.size > UINT64_MAX - range.address ||
+		    range.address + range.size > UINT64_MAX - (PAGE_SIZE - 1)) {
+			Fatal("invalid backing-write range");
+		}
+		const auto page_begin = PageStart(range.address);
+		const auto page_end   = PageStart(range.address + range.size + PAGE_SIZE - 1);
+		if (begin != 0 && page_begin > end) {
+			writes.push_back(std::make_unique<BackingWrite>(*this, begin, end - begin));
+			begin = 0;
+		}
+		if (begin == 0) {
+			begin = page_begin;
+			end   = page_end;
+		} else {
+			end = std::max(end, page_end);
+		}
+	}
+	writes.push_back(std::make_unique<BackingWrite>(*this, begin, end - begin));
+	return writes;
+}
+
 void PageManager::BeginBackingWrite(uint64_t vaddr, uint64_t size) noexcept {
 	if (g_in_fault_resolution) {
 		FailFast("backing write began during fault resolution");
@@ -539,7 +577,7 @@ void PageManager::EndBackingWrite(uint64_t vaddr, uint64_t size) noexcept {
 		if (!page.resolving || page.backing_writer != writer) {
 			FailFast("backing write ended without matching owner and resolving state");
 		}
-		const auto old_protection = PAGE_NOACCESS;
+		const auto old_protection = NO_ACCESS_PROTECTION;
 		const auto new_protection = Impl::WatcherProtection(page);
 		if (new_protection != old_protection) {
 			Impl::Protect(address, new_protection, old_protection, false);

src/graphics/host_gpu/pageManager.h

@@ -2,8 +2,11 @@
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_PAGEMANAGER_H_
 
 #include "common/common.h"
+#include "graphics/host_gpu/rangeSet.h"
 
 #include <memory>
+#include <span>
+#include <vector>
 
 namespace Libs::Graphics {
 
@@ -48,6 +51,8 @@ public:
 
 	[[nodiscard]] bool HandleFault(PageFaultAccess access, uint64_t fault_vaddr) noexcept;
 	[[nodiscard]] bool HandleWriteRange(uint64_t vaddr, uint64_t size) noexcept;
+	[[nodiscard]] std::vector<std::unique_ptr<BackingWrite>>
+	     ReserveBackingWrites(std::span<const RangeSet::Range> ranges);
 
 private:
 	void BeginBackingWrite(uint64_t vaddr, uint64_t size) noexcept;

src/graphics/host_gpu/renderer/blitHelper.cpp

@@ -0,0 +1,231 @@
+#include "graphics/host_gpu/renderer/blitHelper.h"
+
+#include "common/assert.h"
+#include "gpu_blit_shaders/gpu_blit_color_to_ms_depth_spv.h"
+#include "gpu_blit_shaders/gpu_blit_fs_triangle_spv.h"
+#include "graphics/host_gpu/graphicContext.h"
+#include "graphics/host_gpu/renderer/commandScheduler.h"
+#include "graphics/host_gpu/renderer/image.h"
+#include "graphics/host_gpu/renderer/renderTarget.h"
+
+#include <algorithm>
+#include <array>
+#include <iterator>
+
+namespace Libs::Graphics {
+
+BlitHelper::BlitHelper(GraphicContext& graphics, CommandScheduler& scheduler)
+    : m_graphics(graphics), m_scheduler(scheduler) {
+	vk::DescriptorSetLayoutBinding texture_binding {};
+	texture_binding.binding         = 0;
+	texture_binding.descriptorType  = vk::DescriptorType::eSampledImage;
+	texture_binding.descriptorCount = 1;
+	texture_binding.stageFlags      = vk::ShaderStageFlagBits::eFragment;
+
+	vk::DescriptorSetLayoutCreateInfo descriptor_info {};
+	descriptor_info.sType        = vk::StructureType::eDescriptorSetLayoutCreateInfo;
+	descriptor_info.flags        = vk::DescriptorSetLayoutCreateFlagBits::ePushDescriptorKHR;
+	descriptor_info.bindingCount = 1;
+	descriptor_info.pBindings    = &texture_binding;
+	RequireVulkanSuccess(m_graphics.device.createDescriptorSetLayout(&descriptor_info, nullptr,
+	                                                                 &m_descriptor_layout),
+	                     "create BlitHelper descriptor layout");
+
+	vk::PipelineLayoutCreateInfo layout_info {};
+	layout_info.sType          = vk::StructureType::ePipelineLayoutCreateInfo;
+	layout_info.setLayoutCount = 1;
+	layout_info.pSetLayouts    = &m_descriptor_layout;
+	RequireVulkanSuccess(
+	    m_graphics.device.createPipelineLayout(&layout_info, nullptr, &m_pipeline_layout),
+	    "create BlitHelper pipeline layout");
+
+	m_vertex_shader = CreateShader(GPU_BLIT_FS_TRIANGLE_SPV, std::size(GPU_BLIT_FS_TRIANGLE_SPV));
+	m_fragment_shader =
+	    CreateShader(GPU_BLIT_COLOR_TO_MS_DEPTH_SPV, std::size(GPU_BLIT_COLOR_TO_MS_DEPTH_SPV));
+}
+
+BlitHelper::~BlitHelper() {
+	for (const auto& pipeline: m_pipelines) {
+		m_graphics.device.destroyPipeline(pipeline.handle, nullptr);
+	}
+	if (m_fragment_shader != nullptr) {
+		m_graphics.device.destroyShaderModule(m_fragment_shader, nullptr);
+	}
+	if (m_vertex_shader != nullptr) {
+		m_graphics.device.destroyShaderModule(m_vertex_shader, nullptr);
+	}
+	if (m_pipeline_layout != nullptr) {
+		m_graphics.device.destroyPipelineLayout(m_pipeline_layout, nullptr);
+	}
+	if (m_descriptor_layout != nullptr) {
+		m_graphics.device.destroyDescriptorSetLayout(m_descriptor_layout, nullptr);
+	}
+}
+
+vk::ShaderModule BlitHelper::CreateShader(const uint32_t* code, size_t words) const {
+	EXIT_IF(code == nullptr || words == 0);
+	vk::ShaderModuleCreateInfo create {};
+	create.sType            = vk::StructureType::eShaderModuleCreateInfo;
+	create.codeSize         = words * sizeof(uint32_t);
+	create.pCode            = code;
+	vk::ShaderModule module = nullptr;
+	RequireVulkanSuccess(m_graphics.device.createShaderModule(&create, nullptr, &module),
+	                     "create BlitHelper shader module");
+	return module;
+}
+
+vk::Pipeline BlitHelper::GetPipeline(PipelineKey key) {
+	const auto cached = std::ranges::find(m_pipelines, key, &Pipeline::key);
+	if (cached != m_pipelines.end()) {
+		return cached->handle;
+	}
+
+	const auto samples = vulkan_sample_count(key.samples);
+	EXIT_IF(samples == vk::SampleCountFlagBits {} || key.format == vk::Format::eUndefined);
+
+	std::array<vk::PipelineShaderStageCreateInfo, 2> stages {};
+	stages[0].sType  = vk::StructureType::ePipelineShaderStageCreateInfo;
+	stages[0].stage  = vk::ShaderStageFlagBits::eVertex;
+	stages[0].module = m_vertex_shader;
+	stages[0].pName  = "main";
+	stages[1].sType  = vk::StructureType::ePipelineShaderStageCreateInfo;
+	stages[1].stage  = vk::ShaderStageFlagBits::eFragment;
+	stages[1].module = m_fragment_shader;
+	stages[1].pName  = "main";
+
+	vk::PipelineVertexInputStateCreateInfo vertex_input {};
+	vertex_input.sType = vk::StructureType::ePipelineVertexInputStateCreateInfo;
+	vk::PipelineInputAssemblyStateCreateInfo input_assembly {};
+	input_assembly.sType    = vk::StructureType::ePipelineInputAssemblyStateCreateInfo;
+	input_assembly.topology = vk::PrimitiveTopology::eTriangleList;
+	vk::PipelineViewportStateCreateInfo viewport {};
+	viewport.sType         = vk::StructureType::ePipelineViewportStateCreateInfo;
+	viewport.viewportCount = 1;
+	viewport.scissorCount  = 1;
+	vk::PipelineRasterizationStateCreateInfo rasterization {};
+	rasterization.sType       = vk::StructureType::ePipelineRasterizationStateCreateInfo;
+	rasterization.polygonMode = vk::PolygonMode::eFill;
+	rasterization.cullMode    = vk::CullModeFlagBits::eNone;
+	rasterization.lineWidth   = 1.0f;
+	vk::PipelineMultisampleStateCreateInfo multisample {};
+	multisample.sType                = vk::StructureType::ePipelineMultisampleStateCreateInfo;
+	multisample.rasterizationSamples = samples;
+	vk::PipelineDepthStencilStateCreateInfo depth {};
+	depth.sType            = vk::StructureType::ePipelineDepthStencilStateCreateInfo;
+	depth.depthTestEnable  = VK_TRUE;
+	depth.depthWriteEnable = VK_TRUE;
+	depth.depthCompareOp   = vk::CompareOp::eAlways;
+	vk::PipelineColorBlendStateCreateInfo color_blend {};
+	color_blend.sType = vk::StructureType::ePipelineColorBlendStateCreateInfo;
+	const std::array dynamic_states {vk::DynamicState::eViewport, vk::DynamicState::eScissor};
+	vk::PipelineDynamicStateCreateInfo dynamic {};
+	dynamic.sType             = vk::StructureType::ePipelineDynamicStateCreateInfo;
+	dynamic.dynamicStateCount = static_cast<uint32_t>(dynamic_states.size());
+	dynamic.pDynamicStates    = dynamic_states.data();
+
+	vk::PipelineRenderingCreateInfo rendering {};
+	rendering.sType                 = vk::StructureType::ePipelineRenderingCreateInfo;
+	rendering.depthAttachmentFormat = key.format;
+
+	vk::GraphicsPipelineCreateInfo create {};
+	create.sType               = vk::StructureType::eGraphicsPipelineCreateInfo;
+	create.pNext               = &rendering;
+	create.stageCount          = static_cast<uint32_t>(stages.size());
+	create.pStages             = stages.data();
+	create.pVertexInputState   = &vertex_input;
+	create.pInputAssemblyState = &input_assembly;
+	create.pViewportState      = &viewport;
+	create.pRasterizationState = &rasterization;
+	create.pMultisampleState   = &multisample;
+	create.pDepthStencilState  = &depth;
+	create.pColorBlendState    = &color_blend;
+	create.pDynamicState       = &dynamic;
+	create.layout              = m_pipeline_layout;
+
+	vk::Pipeline pipeline = nullptr;
+	RequireVulkanSuccess(
+	    m_graphics.device.createGraphicsPipelines(nullptr, 1, &create, nullptr, &pipeline),
+	    "create color-to-MS-depth pipeline");
+	m_pipelines.push_back({key, pipeline});
+	return pipeline;
+}
+
+void BlitHelper::ReinterpretColorAsMsDepth(Image& source, Image& destination) {
+	const auto& source_info      = source.info;
+	const auto& destination_info = destination.info;
+	EXIT_IF(DepthAspectTransferFormat(source_info.pixel_format) != vk::Format::eUndefined ||
+	        DepthAspectTransferFormat(destination_info.pixel_format) == vk::Format::eUndefined ||
+	        source_info.samples != 1 || destination_info.samples <= 1 ||
+	        destination_info.samples > 4 || source.backing.image_type != vk::ImageType::e2D ||
+	        destination.backing.image_type != vk::ImageType::e2D ||
+	        source_info.extent.width != destination_info.extent.width ||
+	        source_info.extent.height != destination_info.extent.height ||
+	        source_info.extent.depth != 1 || destination_info.extent.depth != 1 ||
+	        source.backing.image == nullptr || destination.backing.image == nullptr);
+	m_scheduler.EndRendering();
+
+	ImageViewInfo source_view_info {};
+	source_view_info.format = source_info.pixel_format;
+	source_view_info.type   = vk::ImageViewType::e2D;
+	source_view_info.aspect = vk::ImageAspectFlagBits::eColor;
+	source_view_info.usage  = vk::ImageUsageFlagBits::eSampled;
+	const auto source_view  = source.FindView(source_view_info);
+
+	ImageViewInfo destination_view_info {};
+	destination_view_info.format = destination_info.pixel_format;
+	destination_view_info.type   = vk::ImageViewType::e2D;
+	destination_view_info.aspect = vk::ImageAspectFlagBits::eDepth;
+	destination_view_info.usage  = vk::ImageUsageFlagBits::eDepthStencilAttachment;
+	const auto destination_view  = destination.FindView(destination_view_info);
+
+	auto& command_buffer = m_scheduler.Current();
+	auto  command        = command_buffer.Handle();
+	source.Transit(vk::ImageLayout::eShaderReadOnlyOptimal, vk::AccessFlagBits2::eShaderRead, {},
+	               command);
+	destination.Transit(ColorToMsDepthLayout,
+	                    vk::AccessFlagBits2::eDepthStencilAttachmentWrite, {}, command);
+
+	vk::RenderingAttachmentInfo depth_attachment {};
+	depth_attachment.sType                   = vk::StructureType::eRenderingAttachmentInfo;
+	depth_attachment.imageView               = destination_view;
+	depth_attachment.imageLayout             = ColorToMsDepthLayout;
+	depth_attachment.loadOp                  = vk::AttachmentLoadOp::eClear;
+	depth_attachment.storeOp                 = vk::AttachmentStoreOp::eStore;
+	depth_attachment.clearValue.depthStencil = {0.0f, 0};
+
+	vk::RenderingInfo rendering {};
+	rendering.sType             = vk::StructureType::eRenderingInfo;
+	rendering.renderArea.extent = {destination_info.extent.width, destination_info.extent.height};
+	rendering.layerCount        = 1;
+	rendering.pDepthAttachment  = &depth_attachment;
+	command.beginRendering(&rendering);
+
+	vk::DescriptorImageInfo descriptor_image {};
+	descriptor_image.imageView   = source_view;
+	descriptor_image.imageLayout = vk::ImageLayout::eShaderReadOnlyOptimal;
+	vk::WriteDescriptorSet descriptor_write {};
+	descriptor_write.sType           = vk::StructureType::eWriteDescriptorSet;
+	descriptor_write.dstBinding      = 0;
+	descriptor_write.descriptorCount = 1;
+	descriptor_write.descriptorType  = vk::DescriptorType::eSampledImage;
+	descriptor_write.pImageInfo      = &descriptor_image;
+	command.pushDescriptorSetKHR(vk::PipelineBindPoint::eGraphics, m_pipeline_layout, 0, 1,
+	                             &descriptor_write);
+	command.bindPipeline(vk::PipelineBindPoint::eGraphics,
+	                     GetPipeline({destination_info.samples, destination_info.pixel_format}));
+
+	const vk::Viewport viewport {0.0f,
+	                             0.0f,
+	                             static_cast<float>(destination_info.extent.width),
+	                             static_cast<float>(destination_info.extent.height),
+	                             0.0f,
+	                             1.0f};
+	const vk::Rect2D   scissor {{0, 0},
+	                            {destination_info.extent.width, destination_info.extent.height}};
+	command.setViewport(0, 1, &viewport);
+	command.setScissor(0, 1, &scissor);
+	command.draw(3, 1, 0, 0);
+	command.endRendering();
+}
+
+} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/blitHelper.h

@@ -0,0 +1,54 @@
+#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_BLITHELPER_H_
+#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_BLITHELPER_H_
+
+#include "common/common.h"
+#include "graphics/host_gpu/vulkanCommon.h"
+
+#include <compare>
+#include <vector>
+
+namespace Libs::Graphics {
+
+class CommandScheduler;
+class Image;
+struct GraphicContext;
+
+class BlitHelper final {
+public:
+	inline static constexpr auto ColorToMsDepthLayout =
+	    vk::ImageLayout::eDepthStencilAttachmentOptimal;
+
+	BlitHelper(GraphicContext& graphics, CommandScheduler& scheduler);
+	~BlitHelper();
+	KYTY_CLASS_NO_COPY(BlitHelper);
+
+	void ReinterpretColorAsMsDepth(Image& source, Image& destination);
+
+private:
+	struct PipelineKey {
+		uint32_t   samples = 1;
+		vk::Format format  = vk::Format::eUndefined;
+
+		auto operator<=>(const PipelineKey&) const = default;
+	};
+
+	struct Pipeline {
+		PipelineKey  key;
+		vk::Pipeline handle = nullptr;
+	};
+
+	[[nodiscard]] vk::ShaderModule CreateShader(const uint32_t* code, size_t words) const;
+	[[nodiscard]] vk::Pipeline     GetPipeline(PipelineKey key);
+
+	GraphicContext&         m_graphics;
+	CommandScheduler&       m_scheduler;
+	vk::DescriptorSetLayout m_descriptor_layout = nullptr;
+	vk::PipelineLayout      m_pipeline_layout   = nullptr;
+	vk::ShaderModule        m_vertex_shader     = nullptr;
+	vk::ShaderModule        m_fragment_shader   = nullptr;
+	std::vector<Pipeline>   m_pipelines;
+};
+
+} // namespace Libs::Graphics
+
+#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_BLITHELPER_H_

src/graphics/host_gpu/renderer/bufferCache.h

@@ -6,42 +6,34 @@
 #include "common/threads.h"
 #include "graphics/host_gpu/memoryTracker.h"
 #include "graphics/host_gpu/rangeSet.h"
+#include "graphics/host_gpu/renderer/streamBuffer.h"
 
 #include <map>
 #include <memory>
 #include <mutex>
+#include <span>
+#include <utility>
+#include <vector>
 
 namespace Libs::Graphics {
 
 struct GraphicContext;
-struct VulkanBuffer;
 class CommandBuffer;
+class CommandScheduler;
 class TextureCache;
 class ResourceMutex;
 
-struct BufferImageCopySource {
-	VulkanBuffer* buffer      = nullptr;
-	uint64_t      offset      = 0;
-	uint64_t      address     = 0;
-	uint64_t      size        = 0;
-	bool          cpu_current = false;
-	// True when the guest range was CPU-dirty before coherence resolution. ObtainBufferForImage
-	// may consume that tracker state while publishing the same bytes to a cached buffer.
-	bool cpu_dirty = false;
-};
-
-struct BufferCacheRange {
-	uint64_t address = 0;
-	uint64_t size    = 0;
-};
-
 struct BufferBinding {
-	VulkanBuffer& buffer;
-	uint64_t      offset;
+	std::shared_ptr<void> owner;
+	vk::Buffer            buffer = nullptr;
+	uint64_t              offset = 0;
 };
 
-[[nodiscard]] bool MergeOverlappingBufferCacheRange(BufferCacheRange& merged,
-                                                    BufferCacheRange  candidate) noexcept;
+struct ImageBufferSource {
+	Buffer*  buffer    = nullptr;
+	uint64_t offset    = 0;
+	bool     gpu_owned = false;
+};
 
 class BufferCache {
 public:
@@ -50,7 +42,8 @@ public:
 		return vaddr & (CACHING_PAGE_SIZE - 1);
 	}
 
-	BufferCache(GraphicContext& graphics, PageManager& page_manager, ResourceMutex& resource_mutex);
+	BufferCache(GraphicContext& graphics, CommandScheduler& scheduler, PageManager& page_manager,
+	            TextureCache& texture_cache, ResourceMutex& resource_mutex);
 	~BufferCache();
 	KYTY_CLASS_NO_COPY(BufferCache);
 
@@ -60,39 +53,91 @@ public:
 	[[nodiscard]] BufferBinding ObtainBuffer(CommandBuffer& command, uint64_t vaddr, uint64_t size,
 	                                         bool is_written = false, bool is_read = true,
 	                                         bool is_formatted = false);
-	// Emulator-owned, CPU-current scratch only. Guest ranges must use ObtainBuffer so page
-	// ownership is resolved before any CPU access.
-	[[nodiscard]] bool UploadHostData(CommandBuffer& command, const void* src, uint64_t size,
-	                                  uint64_t alignment, VulkanBuffer*& out_buffer,
-	                                  uint64_t& out_offset, uint64_t& out_range);
-	[[nodiscard]] VulkanBuffer&         ObtainNullBuffer(CommandBuffer& command);
-	[[nodiscard]] BufferImageCopySource ObtainBufferForImage(uint64_t vaddr, uint64_t size);
-	void FillBuffer(CommandBuffer* command, uint64_t vaddr, uint64_t size, uint32_t value);
-	void CopyBuffer(CommandBuffer* command, uint64_t dst_vaddr, uint64_t src_vaddr, uint64_t size);
+	[[nodiscard]] StreamBuffer& GetUtilityBuffer(MemoryUsage usage) noexcept;
+	[[nodiscard]] Buffer&       GetGdsBuffer() noexcept { return m_gds_buffer; }
+	[[nodiscard]] const Buffer& GetGdsBuffer() const noexcept { return m_gds_buffer; }
+	[[nodiscard]] BufferBinding UploadTransient(const void* data, uint64_t size,
+	                                            uint64_t alignment);
+	[[nodiscard]] std::shared_ptr<Buffer> ObtainNullBuffer();
+	[[nodiscard]] ImageBufferSource       ObtainBufferForImage(uint64_t vaddr, uint64_t size);
+	[[nodiscard]] std::pair<std::shared_ptr<Buffer>, uint64_t>
+	     ObtainBufferForImageWrite(uint64_t vaddr, uint64_t size);
+	void DiscardGpuDirtyBytes(uint64_t vaddr, uint64_t size);
+	void FillBuffer(uint64_t vaddr, uint64_t size, uint32_t value, bool is_gds = false);
+	void CopyBuffer(uint64_t dst_vaddr, uint64_t src_vaddr, uint64_t size, bool dst_gds = false,
+	                bool src_gds = false);
 	[[nodiscard]] bool HasPageOverlap(uint64_t vaddr, uint64_t size);
+	[[nodiscard]] bool HasGpuDirtyBytes(uint64_t vaddr, uint64_t size);
 	[[nodiscard]] bool IsRegionCpuModified(uint64_t vaddr, uint64_t size);
 	[[nodiscard]] bool IsRegionGpuModified(uint64_t vaddr, uint64_t size);
-	void               PublishImageBacking(uint64_t vaddr, uint64_t size);
+	void               InvalidateImageAliases(uint64_t vaddr, uint64_t size);
+	void BeginBackingPublication(uint64_t vaddr, uint64_t size, uint64_t tick);
+	void CompleteBackingPublication(uint64_t vaddr, uint64_t size, uint64_t tick);
+	[[nodiscard]] bool SynchronizeBacking(uint64_t vaddr, uint64_t size);
+	void               PublishImageBuffer(uint64_t vaddr, uint64_t size);
 	void ValidateGpuAccess(uint64_t vaddr, uint64_t size, bool is_read, bool is_written) const;
-	void SetTextureCache(TextureCache& texture_cache);
-
-	void ResetNullBuffer();
+	void RunGarbageCollector();
 
 private:
-	struct CachedBuffer;
-	struct ReadbackWorker;
+	friend struct BufferCacheTestAccess;
 
-	GraphicContext&               m_graphics;
-	Common::Mutex                 m_mutex;
-	std::shared_ptr<VulkanBuffer> m_null_buffer;
-	// TODO: add LRU cache
+	struct CacheRange {
+		uint64_t address = 0;
+		uint64_t size    = 0;
+	};
+	struct CachedBuffer;
+	struct DownloadCopy;
+	struct DownloadRange;
+	struct RetiredBuffer;
+	struct FaultReadback;
+	struct PendingBackingPublication;
+	static constexpr uint64_t DOWNLOAD_ALIGNMENT = 64;
+	[[nodiscard]] static uint64_t AlignDown(uint64_t value) noexcept;
+	[[nodiscard]] static uint64_t AlignUp(uint64_t value);
+	[[nodiscard]] static constexpr uint64_t AlignDownload(uint64_t size) noexcept {
+		return (size + DOWNLOAD_ALIGNMENT - 1) & ~(DOWNLOAD_ALIGNMENT - 1);
+	}
+	[[nodiscard]] static bool PageOverlaps(uint64_t left, uint64_t left_size, uint64_t right,
+	                                      uint64_t right_size) noexcept;
+	[[nodiscard]] static std::pair<uint64_t, uint64_t>
+	     DownloadEnvelope(const DownloadCopy& copy);
+	[[nodiscard]] static bool   ResolveOverlap(CacheRange& merged, CacheRange candidate) noexcept;
+	void Upload(CommandBuffer& command, Buffer& destination, uint64_t destination_offset,
+	            const void* source, uint64_t size);
+	[[nodiscard]] CachedBuffer& GetOrCreateBuffer(CommandBuffer& command, uint64_t vaddr,
+	                                              uint64_t size);
+	[[nodiscard]] std::vector<DownloadRange>
+	     RecordDownloads(std::span<const DownloadCopy> copies);
+	void PublishDownloads(std::span<const DownloadRange> downloads);
+	void QueueGarbageDownload(std::span<const DownloadCopy> copies, RetiredBuffer retire);
+	void RefreshInvalidatedRanges(CommandBuffer& command, CachedBuffer& cached, uint64_t vaddr,
+	                              uint64_t size, bool upload);
+	void DiscardGpuDirtyBytesLocked(uint64_t vaddr, uint64_t size, const char* operation);
+	void WriteHostMemory(uint64_t vaddr, std::span<const uint8_t> data);
+
+	GraphicContext&                                   m_graphics;
+	CommandScheduler&                                 m_scheduler;
+	Buffer                                            m_gds_buffer;
+	Common::Mutex                                     m_mutex;
+	std::shared_ptr<Buffer>                           m_null_buffer;
 	std::map<uint64_t, std::unique_ptr<CachedBuffer>> m_buffers;
-	std::unique_ptr<ReadbackWorker>                   m_readback;
+	std::unique_ptr<FaultReadback>                    m_fault_readback;
 	RangeSet                                          m_gpu_modified_ranges;
+	RangeSet                                          m_image_invalidated_ranges;
+	std::mutex                                        m_publication_mutex;
+	std::vector<PendingBackingPublication>            m_pending_backing_publications;
 	MemoryTracker                                     m_memory_tracker;
+	StreamBuffer                                      m_staging_buffer;
+	StreamBuffer                                      m_stream_buffer;
+	StreamBuffer                                      m_download_buffer;
+	StreamBuffer                                      m_device_buffer;
 	PageManager&                                      m_page_manager;
-	TextureCache*                                     m_texture_cache = nullptr;
+	TextureCache&                                     m_texture_cache;
 	ResourceMutex&                                    m_resource_mutex;
+	uint64_t                                          m_total_used_memory = 0;
+	uint64_t m_trigger_gc_memory  = 1ull * 1024 * 1024 * 1024;
+	uint64_t m_critical_gc_memory = 2ull * 1024 * 1024 * 1024;
+	uint64_t m_gc_tick            = 0;
 };
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/colorRenderTarget.cpp

@@ -10,12 +10,9 @@
 #include "graphics/host_gpu/objects/textureCommon.h"
 #include "graphics/host_gpu/renderer/debug.h"
 #include "graphics/host_gpu/renderer/descriptorCache.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/transfer.h"
 #include "graphics/host_gpu/vulkanCommon.h"
-#include "graphics/presentation/displayBuffer.h"
 
 #include <algorithm>
 #include <atomic>
@@ -25,9 +22,11 @@ namespace Libs::Graphics {
 static std::atomic<uint32_t> g_render_color_log_count = 0;
 
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
-void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer, RenderColorInfo& r,
-                              uint32_t render_target_slice_offset, uint32_t render_target_slot,
-                              bool ignore_target_mask, bool reuse_existing_render_texture) {
+void RenderExecutor::ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer,
+                                          RenderColorInfo& r,
+                                          uint32_t render_target_slice_offset,
+                                          uint32_t render_target_slot, bool ignore_target_mask,
+                                          bool exact_format) {
 	KYTY_PROFILER_FUNCTION();
 	const auto& hw = buffer.GetRegisters();
 
@@ -57,14 +56,17 @@ void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 
 		// No color output
 		r.type               = RenderColorType::NoColorOutput;
+		r.desc               = {};
 		r.base_addr          = 0;
-		r.vulkan_buffer      = nullptr;
-		r.vulkan_view        = nullptr;
+		r.image_id           = {};
+		r.image_view         = nullptr;
 		r.format             = vk::Format::eUndefined;
 		r.extent             = {};
 		r.base_mip_level     = 0;
+		r.base_array_layer   = 0;
 		r.buffer_size        = 0;
 		r.samples            = 1;
+		r.export_mapping     = {};
 		r.color_clear_enable = false;
 		r.color_clear_value  = {};
 		return;
@@ -176,26 +178,33 @@ void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 		pitch = width;
 	}
 
+	TileSizeOffset mip_sizes[16] {};
+	TilePaddedSize mip_padded[16] {};
 	if (tile) {
 		TileSizeAlign layout {};
 		bool          valid_layout = false;
 		if (standard64) {
 			TileGetTextureSize(Prospero::GpuEnumValue(Prospero::BufferFormat::k32Float), width,
-			                   height, pitch, levels, rt.attrib3.tile_mode, &layout, nullptr,
-			                   nullptr);
+			                   height, pitch, levels, rt.attrib3.tile_mode, &layout, mip_sizes,
+			                   mip_padded);
 			valid_layout = layout.size != 0 && layout.align == 65536;
 		} else {
 			valid_layout =
 			    levels == 1 ? TileGetRenderTargetSize(width, height, pitch, bytes_per_element,
 			                                          layout, rt.attrib.num_fragments)
 			                : TileGetRenderTargetMipLayout(width, height, pitch, bytes_per_element,
-			                                               levels, layout, nullptr, nullptr);
+			                                               levels, layout, mip_sizes, mip_padded);
 		}
 		if (!valid_layout) {
 			EXIT("unsupported render-target layout: %ux%u pitch=%u bytes=%u levels=%u\n", width,
 			     height, pitch, bytes_per_element, levels);
 		}
 		size = layout.size;
+		EXIT_IF(size > UINT32_MAX);
+		if (levels == 1) {
+			mip_sizes[0]  = {static_cast<uint32_t>(size), 0, 0, 0, 0, 0};
+			mip_padded[0] = {pitch, height};
+		}
 		if (rt.slice.slice_div64_minus1 != 0 &&
 		    (static_cast<uint64_t>(rt.slice.slice_div64_minus1) + 1u) * 64u != size) {
 			EXIT("render-target slice span mismatch: encoded=0x%016" PRIx64 " derived=0x%016" PRIx64
@@ -204,6 +213,11 @@ void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 		}
 	} else {
 		size = static_cast<uint64_t>(pitch) * height * bytes_per_element * samples;
+		if (size > UINT32_MAX) {
+			EXIT("linear render-target slice exceeds the supported layout size\n");
+		}
+		mip_sizes[0]  = {static_cast<uint32_t>(size), 0, 0, 0, 0, 0};
+		mip_padded[0] = {pitch, height};
 	}
 	if (size == 0 || size > UINT64_MAX / view.image_layers) {
 		EXIT("render-target memory footprint is invalid\n");
@@ -213,119 +227,69 @@ void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 		EXIT("render-target backing range is invalid\n");
 	}
 
-	auto video_image = Presentation::DisplayBufferFind(rt.base.addr, true);
-	if (video_image.image != nullptr &&
-	    !IsSupportedDisplayRenderTargetTileMode(rt.attrib3.tile_mode)) {
-		EXIT("unsupported display render-target tile mode: tile=%u expected=%u addr=0x%010" PRIx64
-		     " backing_size=0x%016" PRIx64 " video_size=0x%016" PRIx64 "\n",
-		     rt.attrib3.tile_mode, Prospero::GpuEnumValue(Prospero::TileMode::kRenderTarget),
-		     rt.base.addr, backing_size, video_image.size);
-	}
-	bool render_to_texture = view.base_layer != 0 || video_image.image == nullptr;
-	if (!render_to_texture && (levels != 1 || rt.view.current_mip_level != 0)) {
-		EXIT("mipmapped display render targets are unsupported\n");
-	}
 	const vk::Extent2D view_extent = {std::max(width >> rt.view.current_mip_level, 1u),
 	                                  std::max(height >> rt.view.current_mip_level, 1u)};
 
 	auto decision_log_id = g_render_color_log_count.fetch_add(1);
-	if (decision_log_id < 128 || !render_to_texture) {
+	if (decision_log_id < 128) {
 		LOGF("RenderColorTarget: slot=%" PRIu32 " addr=0x%010" PRIx64 " size=0x%016" PRIx64
 		     " extent=%ux%u view_mip=%u view_extent=%ux%u levels=%u pitch=%u"
-		     " fmt=0x%08" PRIx32 " nfmt=0x%08" PRIx32 " order=0x%08" PRIx32
-		     " samples=%u tile=%s target=%s video_size=0x%016" PRIx64 " video_pitch=%" PRIu64 "\n",
+		     " fmt=0x%08" PRIx32 " nfmt=0x%08" PRIx32 " order=0x%08" PRIx32 " samples=%u tile=%s\n",
 		     rt_slot, rt.base.addr, backing_size, width, height, rt.view.current_mip_level,
 		     view_extent.width, view_extent.height, levels, pitch, rt.info.format,
-		     rt.info.channel_type, rt.info.channel_order, samples, tile ? "tiled" : "linear",
-		     render_to_texture ? "RenderTexture" : "DisplayBuffer", video_image.size,
-		     video_image.pitch);
+		     rt.info.channel_type, rt.info.channel_order, samples, tile ? "tiled" : "linear");
 	}
 
-	if (render_to_texture) {
-		(void)reuse_existing_render_texture;
-		RenderTargetInfo target {};
-		target.address           = rt.base.addr;
-		target.size              = backing_size;
-		target.format            = target_format.format;
-		target.width             = width;
-		target.height            = height;
-		target.pitch             = pitch;
-		target.bytes_per_element = target_format.bytes_per_element;
-		target.tile_mode         = rt.attrib3.tile_mode;
-		target.levels            = levels;
-		target.layers            = view.image_layers;
-		target.samples           = samples;
-		auto& texture_cache      = GetRenderContext().GetTextureCache();
-		auto& buffer_vulkan      = texture_cache.FindRenderTarget(buffer, target);
-		r.type                   = RenderColorType::RenderTexture;
-		r.base_addr              = rt.base.addr;
-		r.vulkan_buffer          = &buffer_vulkan;
-		r.vulkan_view            = texture_cache.GetRenderTargetAttachmentView(
-		    buffer_vulkan, target.format, rt.view.current_mip_level, view.base_layer,
-		    view.layer_count);
-		r.format             = target.format;
-		r.extent             = view_extent;
-		r.base_mip_level     = rt.view.current_mip_level;
-		r.buffer_size        = backing_size;
-		r.samples            = samples;
-		r.export_mapping     = target_format.export_mapping;
-		r.color_clear_enable = buffer_vulkan.initial_clear_pending;
-		r.color_clear_value  = {};
-	} else {
-		if (samples != 1) {
-			EXIT("multisampled display render targets are unsupported\n");
-		}
-		const auto layout = static_cast<Prospero::ChannelLayout>(rt.info.format);
-		const auto type   = static_cast<Prospero::ChannelType>(rt.info.channel_type);
-		const auto order  = static_cast<Prospero::ChannelOrder>(rt.info.channel_order);
-
-		bool supported_display_format =
-		    (layout == Prospero::ChannelLayout::k8_8_8_8 &&
-		     (type == Prospero::ChannelType::kSrgb || type == Prospero::ChannelType::kUNorm) &&
-		     (order == Prospero::ChannelOrder::kStandard ||
-		      order == Prospero::ChannelOrder::kAlt)) ||
-		    (layout == Prospero::ChannelLayout::k10_10_10_2 &&
-		     type == Prospero::ChannelType::kUNorm &&
-		     (order == Prospero::ChannelOrder::kStandard ||
-		      order == Prospero::ChannelOrder::kAlt)) ||
-		    (layout == Prospero::ChannelLayout::k16_16_16_16 &&
-		     type == Prospero::ChannelType::kFloat &&
-		     (order == Prospero::ChannelOrder::kStandard || order == Prospero::ChannelOrder::kAlt));
-
-		EXIT_NOT_IMPLEMENTED(!supported_display_format);
-
-		// Display buffer
-		if (video_image.size != size) {
-			LOGF("RenderColorTarget: display buffer size differs from render target span, "
-			     "video_size=0x%016" PRIx64 " render_size=0x%016" PRIx64 "\n",
-			     video_image.size, size);
-		}
-		EXIT_NOT_IMPLEMENTED(video_image.size < size);
-		EXIT_NOT_IMPLEMENTED(video_image.pitch != pitch);
-		r.type           = RenderColorType::DisplayBuffer;
-		r.base_addr      = rt.base.addr;
-		r.vulkan_buffer  = video_image.image;
-		r.vulkan_view    = video_image.image->image_view[VulkanImage::VIEW_DEFAULT];
-		r.format         = video_image.image->format;
-		r.extent         = video_image.image->extent;
-		r.base_mip_level = 0;
-		r.buffer_size    = video_image.size;
-		r.samples        = 1;
-		r.export_mapping = target_format.export_mapping;
-	}
-}
-
-void MarkRenderTargetGpuWritten(const RenderColorInfo& target) {
-	const bool with_color = target.vulkan_buffer != nullptr;
-
-	if (with_color) {
-		if (target.type == RenderColorType::RenderTexture ||
-		    target.type == RenderColorType::DisplayBuffer) {
-			GetRenderContext().GetTextureCache().MarkGpuWritten(*target.vulkan_buffer);
-		} else {
-			EXIT("unknown writable render-color resource type\n");
-		}
+	TextureCache::ImageDesc desc {};
+	desc.type              = TextureCache::BindingType::RenderTarget;
+	desc.info.data         = {rt.base.addr, backing_size};
+	desc.info.pixel_format = target_format.format;
+	desc.info.guest_format = ImageOps::RenderTargetTransferFormat(bytes_per_element);
+	desc.info.type   = Prospero::ImageType::kColor2D;
+	desc.info.extent = {width, height, 1};
+	desc.info.resources       = {levels, view.image_layers};
+	desc.info.pitch           = pitch;
+	desc.info.bytes_per_block = bytes_per_element;
+	desc.info.samples         = samples;
+	desc.info.tile_mode       = rt.attrib3.tile_mode;
+	for (uint32_t level = 0; level < levels; level++) {
+		const auto level_offset =
+		    mip_sizes[level].src_size != 0 ? mip_sizes[level].src_offset : mip_sizes[level].offset;
+		const auto level_size =
+		    static_cast<uint64_t>(mip_sizes[level].src_size != 0 ? mip_sizes[level].src_size
+		                                                         : mip_sizes[level].size) *
+		    view.image_layers;
+		desc.info.mip_layout[level] = {
+		    level_offset,
+		    level_size,
+		    mip_padded[level].width,
+		    mip_padded[level].height,
+		};
 	}
+	desc.view_info.format = target_format.format;
+	desc.view_info.type =
+	    view.layer_count == 1 ? vk::ImageViewType::e2D : vk::ImageViewType::e2DArray;
+	desc.view_info.aspect      = vk::ImageAspectFlagBits::eColor;
+	desc.view_info.base_level  = rt.view.current_mip_level;
+	desc.view_info.level_count = 1;
+	desc.view_info.base_layer  = view.base_layer;
+	desc.view_info.layer_count = view.layer_count;
+	desc.view_info.usage       = vk::ImageUsageFlagBits::eColorAttachment;
+	auto& texture_cache = m_context.GetTextureCache();
+	r.desc              = std::move(desc);
+	r.image_id          = texture_cache.FindImage(r.desc, exact_format);
+	r.type              = RenderColorType::RenderTexture;
+	r.base_addr         = rt.base.addr;
+	r.image_view        = nullptr;
+	r.format            = r.desc.view_info.format;
+	r.extent            = view_extent;
+	r.base_mip_level    = rt.view.current_mip_level;
+	r.buffer_size       = backing_size;
+	r.samples           = samples;
+	r.export_mapping    = target_format.export_mapping;
+	r.color_clear_enable = false;
+	r.color_clear_value = {};
+	BindRenderTarget(r.image_id);
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/colorRenderTarget.h

@@ -3,6 +3,7 @@
 
 #include "graphics/guest_gpu/gpu_defs.h"
 #include "graphics/host_gpu/renderer/renderTarget.h"
+#include "graphics/host_gpu/renderer/textureCache.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 
 #include <cstdint>
@@ -10,18 +11,17 @@
 namespace Libs::Graphics {
 
 class RenderCommandBuffer;
-struct VulkanImage;
 
 enum class RenderColorType {
 	NoColorOutput,
-	DisplayBuffer,
 	RenderTexture,
 };
 
 struct RenderColorInfo {
-	RenderColorType                 type             = RenderColorType::NoColorOutput;
-	VulkanImage*                    vulkan_buffer    = nullptr;
-	vk::ImageView                   vulkan_view      = nullptr;
+	RenderColorType                 type = RenderColorType::NoColorOutput;
+	TextureCache::ImageDesc         desc;
+	ImageId                         image_id;
+	vk::ImageView                   image_view       = nullptr;
 	vk::Format                      format           = vk::Format::eUndefined;
 	vk::Extent2D                    extent           = {};
 	uint32_t                        base_mip_level   = 0;
@@ -35,13 +35,6 @@ struct RenderColorInfo {
 	vk::ClearColorValue             color_clear_value {};
 };
 
-void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer, RenderColorInfo& r,
-                              uint32_t render_target_slice_offset    = 0,
-                              uint32_t render_target_slot            = UINT32_MAX,
-                              bool     ignore_target_mask            = false,
-                              bool     reuse_existing_render_texture = false);
-void MarkRenderTargetGpuWritten(const RenderColorInfo& target);
-
 } // namespace Libs::Graphics
 
 #endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_COLORRENDERTARGET_H_

src/graphics/host_gpu/renderer/commandScheduler.cpp

@@ -0,0 +1,402 @@
+#include "graphics/host_gpu/renderer/commandScheduler.h"
+
+#include "common/assert.h"
+#include "graphics/host_gpu/graphicContext.h"
+
+#include <algorithm>
+
+namespace Libs::Graphics {
+
+static thread_local CommandScheduler* g_deferred_callback_scheduler = nullptr;
+
+void CommandSlot::Reset() {
+	EXIT_IF(buffer == nullptr);
+	const auto result = buffer.reset(vk::CommandBufferResetFlagBits::eReleaseResources);
+	if (result != vk::Result::eSuccess) {
+		EXIT("failed to reset Vulkan command buffer: %s (%d)\n", VulkanToString(result).c_str(),
+		     static_cast<int>(result));
+	}
+}
+
+CommandScheduler::CommandPool::~CommandPool() {
+	Destroy();
+}
+
+void CommandScheduler::CommandPool::Create(GraphicContext& graphics) {
+	EXIT_IF(m_pool != nullptr || m_graphics != nullptr ||
+	        graphics.queue_family == static_cast<uint32_t>(-1));
+	m_graphics = &graphics;
+
+	vk::CommandPoolCreateInfo create {};
+	create.sType            = vk::StructureType::eCommandPoolCreateInfo;
+	create.queueFamilyIndex = graphics.queue_family;
+	create.flags            = vk::CommandPoolCreateFlagBits::eResetCommandBuffer;
+	const auto result       = graphics.device.createCommandPool(&create, nullptr, &m_pool);
+	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess || m_pool == nullptr);
+}
+
+CommandSlot* CommandScheduler::CommandPool::CreateSlot() {
+	EXIT_IF(m_graphics == nullptr);
+	auto& graphics = *m_graphics;
+
+	vk::CommandBufferAllocateInfo allocate {};
+	allocate.sType              = vk::StructureType::eCommandBufferAllocateInfo;
+	allocate.commandPool        = m_pool;
+	allocate.level              = vk::CommandBufferLevel::ePrimary;
+	allocate.commandBufferCount = 1;
+	vk::CommandBuffer buffer = nullptr;
+	EXIT_IF(graphics.device.allocateCommandBuffers(&allocate, &buffer) != vk::Result::eSuccess);
+
+	vk::FenceCreateInfo fence_create {};
+	fence_create.sType = vk::StructureType::eFenceCreateInfo;
+	fence_create.flags = vk::FenceCreateFlagBits::eSignaled;
+	vk::Fence fence = nullptr;
+	if (graphics.device.createFence(&fence_create, nullptr, &fence) != vk::Result::eSuccess) {
+		graphics.device.freeCommandBuffers(m_pool, 1, &buffer);
+		EXIT("failed to create command-buffer fence\n");
+	}
+
+	auto& slot      = m_slots.emplace_back();
+	slot.pool_mutex = &m_mutex;
+	slot.id         = static_cast<uint32_t>(m_slots.size() - 1);
+	slot.buffer     = buffer;
+	slot.fence      = fence;
+	return &slot;
+}
+
+CommandSlot* CommandScheduler::CommandPool::Allocate(GraphicContext& graphics) {
+	Common::LockGuard lock(m_mutex);
+	if (m_pool == nullptr) {
+		Create(graphics);
+	}
+	EXIT_IF(m_graphics != &graphics);
+	auto found = std::ranges::find_if(m_slots, [](const auto& slot) { return !slot.busy; });
+	auto* slot = found != m_slots.end() ? &*found : CreateSlot();
+	slot->busy = true;
+	slot->Reset();
+	return slot;
+}
+
+void CommandScheduler::CommandPool::Destroy() {
+	Common::LockGuard lock(m_mutex);
+	if (m_pool == nullptr) {
+		return;
+	}
+	EXIT_IF(std::ranges::any_of(m_slots, [](const auto& slot) { return slot.busy; }));
+	EXIT_IF(m_graphics == nullptr);
+	for (const auto& slot: m_slots) {
+		m_graphics->device.destroyFence(slot.fence, nullptr);
+	}
+	m_graphics->device.destroyCommandPool(m_pool, nullptr);
+	m_slots.clear();
+	m_pool     = nullptr;
+	m_graphics = nullptr;
+}
+
+bool CommandScheduler::InDeferredOperation() noexcept {
+	return g_deferred_callback_scheduler != nullptr;
+}
+
+CommandScheduler::CommandScheduler(RenderContext& context, GraphicContext& graphics)
+    : m_master(graphics), m_context(context), m_graphics(graphics),
+      m_priority_thread([this](std::stop_token stop) { PriorityOperationsThread(stop); }) {}
+
+CommandScheduler::~CommandScheduler() {
+	Shutdown();
+}
+
+void CommandScheduler::Shutdown() {
+	{
+		std::unique_lock lock(m_operation_mutex);
+		if (m_operation_state == OperationState::Closed) {
+			return;
+		}
+		if (g_deferred_callback_scheduler == this) {
+			EXIT_IF(m_operation_state == OperationState::Open);
+			// A priority callback cannot join its own runner, while a normal callback can be
+			// executing inside the shutdown owner's final PopPendingOperations. The owning
+			// thread will finish shutdown after this callback returns.
+			return;
+		}
+		if (m_operation_state == OperationState::Draining) {
+			m_operation_available.wait(
+			    lock, [this] { return m_operation_state == OperationState::Closed; });
+			return;
+		}
+		m_operation_state = OperationState::Draining;
+	}
+	if (Active() && m_recording) {
+		Finish();
+	}
+	DrainPriorityOperations();
+	m_priority_thread.request_stop();
+	m_operation_available.notify_all();
+	if (m_priority_thread.joinable()) {
+		m_priority_thread.join();
+	}
+	{
+		std::lock_guard lock(m_operation_mutex);
+		EXIT_IF(!m_pending_operations.empty() || !m_priority_operations.empty() ||
+		        m_priority_active);
+		m_operation_state = OperationState::Closed;
+	}
+	m_operation_available.notify_all();
+}
+
+void CommandScheduler::Begin(HW::Context& registers, HW::UserConfig& user_config,
+                             HW::Shader& shaders) {
+	{
+		std::lock_guard lock(m_operation_mutex);
+		EXIT_IF(m_operation_state != OperationState::Open);
+	}
+	m_registers   = &registers;
+	m_user_config = &user_config;
+	m_shaders     = &shaders;
+
+	if (!Active()) {
+		for (auto& buffer: m_buffers) {
+			buffer = std::make_unique<RenderCommandBuffer>(*this);
+		}
+		m_current = 0;
+	}
+
+	BindCurrent();
+	if (!m_recording) {
+		Current().Begin();
+		m_recording = true;
+	}
+}
+
+void CommandScheduler::BeginRendering(const RenderState& state) {
+	Current().BeginRendering(state);
+}
+
+void CommandScheduler::EndRendering() {
+	if (Active() && m_recording) {
+		Current().EndRendering();
+	}
+}
+
+void CommandScheduler::Flush() {
+	SubmitInfo submit;
+	Flush(submit);
+}
+
+void CommandScheduler::Flush(SubmitInfo& submit) {
+	SubmitCurrent(submit);
+	BeginNext();
+}
+
+CommandBuffer& CommandScheduler::FlushAndGetSubmitted() {
+	SubmitInfo submit;
+	auto&      submitted = SubmitCurrent(submit);
+	BeginNext();
+	return submitted;
+}
+
+void CommandScheduler::Finish() {
+	CheckActive();
+	const auto tick = CurrentTick();
+	if (m_recording) {
+		SubmitInfo submit;
+		SubmitCurrent(submit);
+	}
+	for (auto& buffer: m_buffers) {
+		buffer->WaitForFenceAndReset();
+	}
+	m_master.Wait(tick);
+	PopPendingOperations();
+	BindCurrent();
+	Current().Begin();
+	m_recording = true;
+}
+
+void CommandScheduler::FinishCurrent() {
+	SubmitInfo submit;
+	auto&      submitted = SubmitCurrent(submit);
+	submitted.WaitForFenceAndReset();
+	m_master.Refresh();
+	PopPendingOperations();
+	submitted.Begin();
+	m_recording = true;
+}
+
+void CommandScheduler::Wait(uint64_t tick) {
+	CheckActive();
+	EXIT_IF(tick > CurrentTick());
+	if (tick >= CurrentTick()) {
+		// A stream-buffer wrap can wait while a draw is being prepared through a reference to
+		// Current(). Recycle the same command object so that reference remains valid.
+		FinishCurrent();
+		return;
+	}
+	m_master.Wait(tick);
+	PopPendingOperations();
+}
+
+void CommandScheduler::PopPendingOperations() {
+	m_master.Refresh();
+	for (;;) {
+		Common::UniqueFunction<void> callback;
+		{
+			std::lock_guard lock(m_operation_mutex);
+			if (m_pending_operations.empty() ||
+			    !m_master.IsFree(m_pending_operations.front().tick)) {
+				return;
+			}
+			callback = std::move(m_pending_operations.front().callback);
+			m_pending_operations.pop();
+		}
+		RunOperation(std::move(callback));
+	}
+}
+
+void CommandScheduler::DeferOperation(Common::UniqueFunction<void>&& operation) {
+	CheckActive();
+	EXIT_IF(!operation);
+	std::unique_lock lock(m_operation_mutex);
+	if (m_operation_state == OperationState::Open) {
+		m_pending_operations.push({std::move(operation), CurrentTick()});
+		return;
+	}
+	if (g_deferred_callback_scheduler == this) {
+		lock.unlock();
+		operation();
+		return;
+	}
+	m_operation_available.wait(lock,
+	                           [this] { return m_operation_state == OperationState::Closed; });
+	lock.unlock();
+	operation();
+}
+
+void CommandScheduler::DeferPriorityOperation(Common::UniqueFunction<void>&& operation) {
+	CheckActive();
+	EXIT_IF(!operation);
+	std::unique_lock lock(m_operation_mutex);
+	if (m_operation_state == OperationState::Open) {
+		m_priority_operations.push({std::move(operation), CurrentTick()});
+		lock.unlock();
+		m_operation_available.notify_one();
+		return;
+	}
+	if (g_deferred_callback_scheduler == this) {
+		lock.unlock();
+		operation();
+		return;
+	}
+	m_operation_available.wait(lock,
+	                           [this] { return m_operation_state == OperationState::Closed; });
+	lock.unlock();
+	operation();
+}
+
+void CommandScheduler::PriorityOperationsThread(std::stop_token stop) {
+	while (!stop.stop_requested()) {
+		PendingOperation operation;
+		{
+			std::unique_lock lock(m_operation_mutex);
+			m_operation_available.wait(lock, [this, &stop] {
+				return stop.stop_requested() || !m_priority_operations.empty();
+			});
+			if (stop.stop_requested()) {
+				return;
+			}
+			operation = std::move(m_priority_operations.front());
+			m_priority_operations.pop();
+			m_priority_active      = true;
+			m_priority_active_tick = operation.tick;
+		}
+		m_master.Wait(operation.tick);
+		if (!stop.stop_requested()) {
+			RunOperation(std::move(operation.callback));
+		}
+		{
+			std::lock_guard lock(m_operation_mutex);
+			m_priority_active      = false;
+			m_priority_active_tick = 0;
+		}
+		m_operation_available.notify_all();
+	}
+}
+
+void CommandScheduler::DrainPriorityOperations() {
+	EXIT_IF(g_deferred_callback_scheduler == this);
+	std::unique_lock lock(m_operation_mutex);
+	m_operation_available.wait(
+	    lock, [this] { return m_priority_operations.empty() && !m_priority_active; });
+}
+
+void CommandScheduler::WaitPriorityOperations(uint64_t tick) {
+	EXIT_IF(g_deferred_callback_scheduler == this);
+	std::unique_lock lock(m_operation_mutex);
+	m_operation_available.wait(lock, [this, tick] {
+		const bool active_before_or_at =
+		    m_priority_active && m_priority_active_tick <= tick;
+		const bool queued_before_or_at =
+		    !m_priority_operations.empty() && m_priority_operations.front().tick <= tick;
+		return !active_before_or_at && !queued_before_or_at;
+	});
+}
+
+void CommandScheduler::RunOperation(Common::UniqueFunction<void>&& operation) {
+	auto* previous                = g_deferred_callback_scheduler;
+	g_deferred_callback_scheduler = this;
+	operation();
+	g_deferred_callback_scheduler = previous;
+}
+
+bool CommandScheduler::IsFree(uint64_t tick) {
+	if (m_master.IsFree(tick)) {
+		return true;
+	}
+	m_master.Refresh();
+	return m_master.IsFree(tick);
+}
+
+CommandSlot* CommandScheduler::AllocateCommandBuffer() {
+	return m_command_pool.Allocate(m_graphics);
+}
+
+uint64_t CommandScheduler::NextSubmitSequence() noexcept {
+	return m_submit_sequence.fetch_add(1, std::memory_order_relaxed) + 1;
+}
+
+void CommandScheduler::CheckActive() const {
+	EXIT_IF(!Active() || m_current >= BufferCount);
+}
+
+RenderCommandBuffer& CommandScheduler::Current() const {
+	CheckActive();
+	EXIT_IF(m_buffers[m_current] == nullptr);
+	return *m_buffers[m_current];
+}
+
+void CommandScheduler::BindCurrent() const {
+	EXIT_IF(m_registers == nullptr || m_user_config == nullptr || m_shaders == nullptr);
+	Current().Bind(*m_registers, *m_user_config, *m_shaders);
+}
+
+CommandBuffer& CommandScheduler::SubmitCurrent(SubmitInfo& submit) {
+	CheckActive();
+	EXIT_IF(!m_recording);
+	auto& submitted = Current();
+	submitted.End();
+	const auto signal_tick = m_master.NextTick();
+	submit.AddSignal(m_master.Handle(), signal_tick);
+	submitted.Execute(submit);
+	m_recording = false;
+	return submitted;
+}
+
+void CommandScheduler::BeginNext() {
+	EXIT_IF(m_recording);
+	m_current = (m_current + 1) % BufferCount;
+	Current().WaitForFenceAndReset();
+	PopPendingOperations();
+	BindCurrent();
+	Current().Begin();
+	m_recording = true;
+}
+
+} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/commandScheduler.h

@@ -0,0 +1,127 @@
+#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_COMMANDSCHEDULER_H_
+#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_COMMANDSCHEDULER_H_
+
+#include "common/common.h"
+#include "common/uniqueFunction.h"
+#include "graphics/host_gpu/renderer/masterSemaphore.h"
+#include "graphics/host_gpu/renderer/render.h"
+
+#include <array>
+#include <atomic>
+#include <condition_variable>
+#include <deque>
+#include <memory>
+#include <mutex>
+
+#include <queue>
+
+#include <thread>
+
+namespace Libs::Graphics {
+
+struct CommandSlot {
+	Common::Mutex*    pool_mutex = nullptr;
+	uint32_t          id         = 0;
+	vk::CommandBuffer buffer     = nullptr;
+	vk::Fence         fence      = nullptr;
+	bool              busy       = false;
+
+	void Reset();
+};
+
+class CommandScheduler {
+public:
+	static constexpr int BufferCount = 8;
+
+	CommandScheduler(RenderContext& context, GraphicContext& graphics);
+	~CommandScheduler();
+	KYTY_CLASS_NO_COPY(CommandScheduler);
+
+	void           Begin(HW::Context& registers, HW::UserConfig& user_config, HW::Shader& shaders);
+	void           BeginRendering(const RenderState& state);
+	void           EndRendering();
+	void           Flush();
+	void           Flush(SubmitInfo& submit);
+	CommandBuffer& FlushAndGetSubmitted();
+	void           Finish();
+	void           FinishCurrent();
+	// Deferred callbacks can observe an externally owned drain, but cannot initiate shutdown:
+	// the priority runner cannot join itself.
+	void Shutdown();
+	void Wait(uint64_t tick);
+	void PopPendingOperations();
+	void DrainPriorityOperations();
+	void WaitPriorityOperations(uint64_t tick);
+	void DeferOperation(Common::UniqueFunction<void>&& operation);
+	void DeferPriorityOperation(Common::UniqueFunction<void>&& operation);
+	[[nodiscard]] static bool InDeferredOperation() noexcept;
+
+	[[nodiscard]] bool     Active() const noexcept { return m_current >= 0; }
+	void                   CheckActive() const;
+	RenderCommandBuffer&   Current() const;
+	[[nodiscard]] uint64_t CurrentTick() const noexcept { return m_master.CurrentTick(); }
+	[[nodiscard]] bool     IsFree(uint64_t tick);
+	[[nodiscard]] RenderContext& Context() const noexcept { return m_context; }
+	[[nodiscard]] GraphicContext& Graphics() const noexcept { return m_graphics; }
+
+private:
+	class CommandPool {
+	public:
+		CommandPool() = default;
+		~CommandPool();
+		KYTY_CLASS_NO_COPY(CommandPool);
+
+		CommandSlot* Allocate(GraphicContext& graphics);
+
+	private:
+		void         Create(GraphicContext& graphics);
+		CommandSlot* CreateSlot();
+		void         Destroy();
+
+		GraphicContext*         m_graphics = nullptr;
+		Common::Mutex           m_mutex;
+		vk::CommandPool         m_pool = nullptr;
+		std::deque<CommandSlot> m_slots;
+	};
+
+	enum class OperationState { Open, Draining, Closed };
+
+	struct PendingOperation {
+		Common::UniqueFunction<void> callback;
+		uint64_t                     tick = 0;
+	};
+
+	void           BindCurrent() const;
+	CommandBuffer& SubmitCurrent(SubmitInfo& submit);
+	void           BeginNext();
+	void           PriorityOperationsThread(std::stop_token stop);
+	void           RunOperation(Common::UniqueFunction<void>&& operation);
+	[[nodiscard]] CommandSlot* AllocateCommandBuffer();
+	[[nodiscard]] uint64_t     NextSubmitSequence() noexcept;
+
+	MasterSemaphore                                               m_master;
+	RenderContext&                                                m_context;
+	GraphicContext&                                               m_graphics;
+	CommandPool                                                   m_command_pool;
+	std::array<std::unique_ptr<RenderCommandBuffer>, BufferCount> m_buffers;
+	std::queue<PendingOperation>                                  m_pending_operations;
+	std::queue<PendingOperation>                                  m_priority_operations;
+	std::mutex                                                    m_operation_mutex;
+	std::condition_variable                                       m_operation_available;
+	std::jthread                                                  m_priority_thread;
+	bool                                                          m_priority_active = false;
+	uint64_t                                                      m_priority_active_tick = 0;
+	OperationState  m_operation_state = OperationState::Open;
+	int             m_current         = -1;
+	bool            m_recording       = false;
+	HW::Context*    m_registers       = nullptr;
+	HW::UserConfig* m_user_config     = nullptr;
+	HW::Shader*     m_shaders         = nullptr;
+	std::atomic<uint64_t> m_submit_sequence = 0;
+
+	friend class CommandBuffer;
+};
+
+} // namespace Libs::Graphics
+
+#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_COMMANDSCHEDULER_H_

src/graphics/host_gpu/renderer/context.cpp

@@ -9,63 +9,17 @@
 #include "graphics/host_gpu/renderer/debug.h"
 #include "graphics/host_gpu/renderer/depthRenderTarget.h"
 #include "graphics/host_gpu/renderer/descriptorCache.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
 #include "graphics/host_gpu/renderer/imageView.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/transfer.h"
 #include "graphics/host_gpu/vma.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 
 #include <algorithm>
-#include <atomic>
+#include <bit>
 #include <cstring>
-#include <deque>
 #include <memory>
 namespace Libs::Graphics {
-static std::atomic<uint64_t> g_command_buffer_submit_seq = 0;
-
-static void ResetNativeCommandBuffer(vk::CommandBuffer buffer) {
-	EXIT_IF(buffer == nullptr);
-	const auto result = buffer.reset(vk::CommandBufferResetFlagBits::eReleaseResources);
-	if (result != vk::Result::eSuccess) {
-		EXIT("failed to reset Vulkan command buffer: %s (%d)\n", VulkanToString(result).c_str(),
-		     static_cast<int>(result));
-	}
-}
-
-struct CommandSlot {
-	Common::Mutex*    pool_mutex = nullptr;
-	uint32_t          id         = 0;
-	vk::CommandBuffer buffer     = nullptr;
-	vk::Fence         fence      = nullptr;
-	bool              busy       = false;
-};
-
-class ThreadCommandPool {
-public:
-	ThreadCommandPool() = default;
-
-	KYTY_CLASS_NO_COPY(ThreadCommandPool);
-
-	CommandSlot* Allocate();
-	void         Destroy();
-
-private:
-	void         Create();
-	CommandSlot* CreateSlot();
-
-	Common::Mutex           m_mutex;
-	vk::CommandPool         m_pool = nullptr;
-	std::deque<CommandSlot> m_slots;
-};
-
-static RenderContext*                 g_render_ctx = nullptr;
-static thread_local ThreadCommandPool g_command_pool;
-
-RenderContext& GetRenderContext() noexcept {
-	return *g_render_ctx;
-}
 
 FenceResourceRetainer::~FenceResourceRetainer() {
 	if (!m_resources.empty()) {
@@ -88,87 +42,12 @@ void FenceResourceRetainer::ReleaseAfterFence() noexcept {
 	m_resources.clear();
 }
 
-void GraphicsRenderInit(GraphicContext& graphics) {
-	g_render_ctx = new RenderContext(graphics);
-}
+CommandBuffer::CommandBuffer(CommandScheduler& scheduler)
+    : m_context(scheduler.Context()), m_scheduler(scheduler), m_graphics(scheduler.Graphics()),
+      m_slot(scheduler.AllocateCommandBuffer()) {}
 
-void GraphicsRenderReleaseThreadCommandPool() {
-	g_command_pool.Destroy();
-}
-
-CommandBuffer::CommandBuffer()
-    : m_graphics(GetRenderContext().GetGraphics()), m_slot(g_command_pool.Allocate()),
-      m_host_stream(m_graphics) {}
-
-void ThreadCommandPool::Create() {
-	auto& graphics = GetRenderContext().GetGraphics();
-	EXIT_IF(m_pool != nullptr || graphics.queue_family == static_cast<uint32_t>(-1));
-
-	vk::CommandPoolCreateInfo pool_info {};
-	pool_info.sType            = vk::StructureType::eCommandPoolCreateInfo;
-	pool_info.pNext            = nullptr;
-	pool_info.queueFamilyIndex = graphics.queue_family;
-	pool_info.flags            = vk::CommandPoolCreateFlagBits::eResetCommandBuffer;
-
-	const auto result = graphics.device.createCommandPool(&pool_info, nullptr, &m_pool);
-	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess || m_pool == nullptr);
-}
-
-CommandSlot* ThreadCommandPool::CreateSlot() {
-	auto&                         graphics = GetRenderContext().GetGraphics();
-	vk::CommandBufferAllocateInfo alloc_info {};
-	alloc_info.sType              = vk::StructureType::eCommandBufferAllocateInfo;
-	alloc_info.commandPool        = m_pool;
-	alloc_info.level              = vk::CommandBufferLevel::ePrimary;
-	alloc_info.commandBufferCount = 1;
-
-	vk::CommandBuffer buffer = nullptr;
-	if (graphics.device.allocateCommandBuffers(&alloc_info, &buffer) != vk::Result::eSuccess) {
-		EXIT("Can't allocate command buffers");
-	}
-
-	vk::FenceCreateInfo fence_info {};
-	fence_info.sType = vk::StructureType::eFenceCreateInfo;
-	fence_info.flags = vk::FenceCreateFlagBits::eSignaled;
-
-	vk::Fence fence = nullptr;
-	if (graphics.device.createFence(&fence_info, nullptr, &fence) != vk::Result::eSuccess) {
-		graphics.device.freeCommandBuffers(m_pool, 1, &buffer);
-		EXIT("Can't create fence");
-	}
-	auto& slot      = m_slots.emplace_back();
-	slot.pool_mutex = &m_mutex;
-	slot.id         = static_cast<uint32_t>(m_slots.size() - 1);
-	slot.buffer     = buffer;
-	slot.fence      = fence;
-	return &slot;
-}
-
-CommandSlot* ThreadCommandPool::Allocate() {
-	Common::LockGuard lock(m_mutex);
-	if (m_pool == nullptr) {
-		Create();
-	}
-	auto  it   = std::ranges::find_if(m_slots, [](const auto& slot) { return !slot.busy; });
-	auto* slot = it != m_slots.end() ? &*it : CreateSlot();
-	slot->busy = true;
-	ResetNativeCommandBuffer(slot->buffer);
-	return slot;
-}
-
-void ThreadCommandPool::Destroy() {
-	Common::LockGuard lock(m_mutex);
-	if (m_pool == nullptr) {
-		return;
-	}
-	EXIT_IF(std::ranges::any_of(m_slots, [](const auto& slot) { return slot.busy; }));
-	auto& graphics = GetRenderContext().GetGraphics();
-	for (const auto& slot: m_slots) {
-		graphics.device.destroyFence(slot.fence, nullptr);
-	}
-	graphics.device.destroyCommandPool(m_pool, nullptr);
-	m_slots.clear();
-	m_pool = nullptr;
+CommandBuffer::~CommandBuffer() {
+	Release();
 }
 
 bool CommandBuffer::IsInvalid() const {
@@ -190,18 +69,19 @@ void CommandBuffer::Release() {
 
 	WaitForFence();
 
-	m_host_stream.Release();
-
 	m_slot->busy = false;
-	ResetNativeCommandBuffer(m_slot->buffer);
+	m_slot->Reset();
 	ReleaseResourcesAfterFence();
 	m_slot = nullptr;
 
 	EXIT_NOT_IMPLEMENTED(!IsInvalid());
 }
 
-void CommandBuffer::DeleteAfterFence(VulkanBuffer& buffer) {
-	m_delete_after_fence.push_back(&buffer);
+void CommandBuffer::RetireBufferAfterFence(std::unique_ptr<VulkanBuffer> buffer) {
+	if (IsInvalid() || m_execute || buffer == nullptr || buffer->buffer == nullptr) {
+		EXIT("cannot retire a buffer on an invalid or submitted command buffer\n");
+	}
+	m_retired_buffers.push_back(std::move(buffer));
 }
 
 void CommandBuffer::RetainResourceUntilFence(std::shared_ptr<void> resource) {
@@ -217,12 +97,13 @@ void CommandBuffer::RecycleDescriptorAfterFence(VulkanDescriptorSet& set) {
 
 void CommandBuffer::RecycleDescriptorsAfterFence() {
 	for (auto* set: m_descriptor_sets_after_fence) {
-		GetRenderContext().GetDescriptorCache().Recycle(*set);
+		m_context.GetDescriptorCache().Recycle(*set);
 	}
 	m_descriptor_sets_after_fence.clear();
 }
 
 void CommandBuffer::Begin() const {
+	EXIT_IF(m_rendering);
 	auto buffer = Handle();
 
 	vk::CommandBufferBeginInfo begin_info {};
@@ -237,6 +118,7 @@ void CommandBuffer::Begin() const {
 }
 
 void CommandBuffer::End() const {
+	EndRendering();
 	auto buffer = Handle();
 
 	auto result = buffer.end();
@@ -255,39 +137,34 @@ void CommandBuffer::SetDebugInfo(uint32_t op, uint64_t submit_id, uint32_t arg0,
 	m_debug_arg4      = arg4;
 }
 
-void CommandBuffer::Execute() {
-	Submit(nullptr, {}, nullptr);
-}
-
-void CommandBuffer::ExecuteWithSemaphore(vk::Semaphore          wait_semaphore,
-                                         vk::PipelineStageFlags wait_stage,
-                                         vk::Semaphore          signal_semaphore) {
-	EXIT_IF(wait_semaphore == nullptr || signal_semaphore == nullptr);
-	Submit(wait_semaphore, wait_stage, signal_semaphore);
-}
-
-void CommandBuffer::Submit(vk::Semaphore wait_semaphore, vk::PipelineStageFlags wait_stage,
-                           vk::Semaphore signal_semaphore) {
+void CommandBuffer::Execute(const SubmitInfo& submit) {
 	EXIT_IF(IsInvalid());
 	EXIT_IF(m_execute);
+	EXIT_IF(submit.num_wait_semaphores > SubmitInfo::MaxSemaphores ||
+	        submit.num_signal_semaphores > SubmitInfo::MaxSemaphores);
 
-	const bool has_wait   = wait_semaphore != nullptr;
-	const bool has_signal = signal_semaphore != nullptr;
-	auto       buffer     = Handle();
-	auto       fence      = m_slot->fence;
+	auto buffer = Handle();
+	auto fence  = m_slot->fence;
+
+	vk::TimelineSemaphoreSubmitInfo timeline_info {};
+	timeline_info.sType                     = vk::StructureType::eTimelineSemaphoreSubmitInfo;
+	timeline_info.waitSemaphoreValueCount   = submit.num_wait_semaphores;
+	timeline_info.pWaitSemaphoreValues      = submit.wait_ticks.data();
+	timeline_info.signalSemaphoreValueCount = submit.num_signal_semaphores;
+	timeline_info.pSignalSemaphoreValues    = submit.signal_ticks.data();
 
 	vk::SubmitInfo submit_info {};
 	submit_info.sType                = vk::StructureType::eSubmitInfo;
-	submit_info.pNext                = nullptr;
-	submit_info.waitSemaphoreCount   = has_wait ? 1u : 0u;
-	submit_info.pWaitSemaphores      = has_wait ? &wait_semaphore : nullptr;
-	submit_info.pWaitDstStageMask    = has_wait ? &wait_stage : nullptr;
+	submit_info.pNext                = &timeline_info;
+	submit_info.waitSemaphoreCount   = submit.num_wait_semaphores;
+	submit_info.pWaitSemaphores      = submit.wait_semaphores.data();
+	submit_info.pWaitDstStageMask    = submit.wait_stages.data();
 	submit_info.commandBufferCount   = 1;
 	submit_info.pCommandBuffers      = &buffer;
-	submit_info.signalSemaphoreCount = has_signal ? 1u : 0u;
-	submit_info.pSignalSemaphores    = has_signal ? &signal_semaphore : nullptr;
+	submit_info.signalSemaphoreCount = submit.num_signal_semaphores;
+	submit_info.pSignalSemaphores    = submit.signal_semaphores.data();
 
-	auto& graphics = GetRenderContext().GetGraphics();
+	auto& graphics = m_graphics;
 	EXIT_IF(graphics.queue == nullptr);
 
 	auto result = graphics.device.resetFences(1, &fence);
@@ -298,16 +175,16 @@ void CommandBuffer::Submit(vk::Semaphore wait_semaphore, vk::PipelineStageFlags
 	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);
 
 	if (Config::GraphicsDebugDumpEnabled()) {
-		LOGF("vkQueueSubmit begin: slot=%u wait_semaphore=%p signal_semaphore=%p"
-		     " debug_op=%u debug_submit=%" PRIu64 " args=%u,%u,%u,%u,0x%016" PRIx64 "\n",
-		     m_slot->id, static_cast<void*>(wait_semaphore), static_cast<void*>(signal_semaphore),
-		     m_debug_op, m_debug_submit_id, m_debug_arg0, m_debug_arg1, m_debug_arg2, m_debug_arg3,
+		LOGF("vkQueueSubmit begin: slot=%u waits=%u signals=%u debug_op=%u debug_submit=%" PRIu64
+		     " args=%u,%u,%u,%u,0x%016" PRIx64 "\n",
+		     m_slot->id, submit.num_wait_semaphores, submit.num_signal_semaphores, m_debug_op,
+		     m_debug_submit_id, m_debug_arg0, m_debug_arg1, m_debug_arg2, m_debug_arg3,
 		     m_debug_arg4);
 	}
 
 	{
 		Common::LockGuard lock(graphics.queue_mutex);
-		m_submit_seq = g_command_buffer_submit_seq.fetch_add(1, std::memory_order_relaxed) + 1;
+		m_submit_seq = m_scheduler.NextSubmitSequence();
 		result       = graphics.queue.submit(1, &submit_info, fence);
 	}
 
@@ -333,7 +210,7 @@ void CommandBuffer::WaitForFenceOnly() {
 	if (!m_execute || m_fence_waited) {
 		return;
 	}
-	auto device = GetRenderContext().GetGraphics().device;
+	auto device = m_graphics.device;
 	auto result = device.waitForFences(1, &m_slot->fence, VK_TRUE, UINT64_MAX);
 	if (result != vk::Result::eSuccess) {
 		LOGF("vkWaitForFences failed: %s (%d), slot=%u submit_seq=%" PRIu64
@@ -357,13 +234,10 @@ void CommandBuffer::FinalizeFence(bool reset_recording) {
 		m_execute      = false;
 		m_fence_waited = false;
 		if (reset_recording) {
-			ResetNativeCommandBuffer(m_slot->buffer);
-			m_recording_generation++;
+			Common::LockGuard lock(*m_slot->pool_mutex);
+			m_slot->Reset();
 		}
 	}
-	if (reset_recording) {
-		m_host_stream.Reset();
-	}
 	if (was_executed) {
 		ReleaseResourcesAfterFence();
 	}
@@ -376,144 +250,71 @@ void CommandBuffer::ReleaseResourcesAfterFence() {
 }
 
 void CommandBuffer::DeleteBuffersAfterFence() {
-	for (auto* buffer: m_delete_after_fence) {
-		GetRenderContext().GetGraphics().DeleteBuffer(*buffer);
-		delete buffer;
+	for (const auto& buffer: m_retired_buffers) {
+		m_graphics.DeleteBuffer(*buffer);
 	}
-	m_delete_after_fence.clear();
+	m_retired_buffers.clear();
 }
 
-void CommandBuffer::BeginRenderPass(VulkanFramebuffer& framebuffer, RenderColorInfo* colors,
-                                    uint32_t requested_color_count, RenderDepthInfo& depth) const {
-	auto buffer = Handle();
-
-	EXIT_IF(colors == nullptr);
-	EXIT_IF(requested_color_count > RENDER_COLOR_ATTACHMENTS_MAX);
-
-	bool with_depth = (depth.format != vk::Format::eUndefined && depth.vulkan_buffer != nullptr);
-	uint32_t color_count = 0;
-	for (uint32_t i = 0; i < requested_color_count; i++) {
-		if (colors[i].vulkan_buffer == nullptr) {
-			break;
-		}
-		color_count++;
+void CommandBuffer::BeginRendering(const RenderState& state) const {
+	EXIT_IF(state.width == 0 || state.height == 0 || state.num_layers == 0 ||
+	        state.num_color_attachments > RENDER_COLOR_ATTACHMENTS_MAX);
+	if (m_rendering && m_render_state == state) {
+		return;
 	}
-	bool with_color = (color_count != 0);
+	EndRendering();
 
-	EXIT_NOT_IMPLEMENTED(!with_depth && !with_color);
-
-	vk::ClearValue clears[RENDER_COLOR_ATTACHMENTS_MAX + 1] = {};
-	for (uint32_t i = 0; i < color_count; i++) {
-		clears[i].color = colors[i].color_clear_value;
-	}
-	clears[color_count].depthStencil = {depth.depth_clear_value, depth.stencil_clear_value};
-
-	vk::Extent2D extent = (with_color ? colors[0].extent : depth.vulkan_buffer->extent);
-
-	vk::RenderPassBeginInfo render_pass_info {};
-	render_pass_info.sType             = vk::StructureType::eRenderPassBeginInfo;
-	render_pass_info.pNext             = nullptr;
-	render_pass_info.renderPass        = framebuffer.render_pass;
-	render_pass_info.framebuffer       = framebuffer.framebuffer;
-	render_pass_info.renderArea.offset = {0, 0};
-	render_pass_info.renderArea.extent = extent;
-	render_pass_info.clearValueCount   = color_count + (with_depth ? 1u : 0u);
-	render_pass_info.pClearValues      = clears;
-
-	for (uint32_t i = 0; i < color_count; i++) {
-		const auto color_initial_layout = framebuffer.color_layout[i];
-		if (colors[i].vulkan_buffer->layout != color_initial_layout) {
-			if (graphics_debug_dump_enabled()) {
-				LOGF("BeginRenderPass: color%u initial barrier image=%p mem=%" PRIu64 " %s -> %s\n",
-				     i, VulkanHandleToPointer(colors[i].vulkan_buffer->image),
-				     colors[i].vulkan_buffer->memory.unique_id,
-				     VulkanToString(colors[i].vulkan_buffer->layout).c_str(),
-				     VulkanToString(color_initial_layout).c_str());
-			}
-
-			vk::ImageMemoryBarrier image_memory_barrier {};
-			image_memory_barrier.sType               = vk::StructureType::eImageMemoryBarrier;
-			image_memory_barrier.pNext               = nullptr;
-			image_memory_barrier.srcAccessMask       = {};
-			image_memory_barrier.dstAccessMask       = vk::AccessFlagBits::eColorAttachmentRead |
-			                                           vk::AccessFlagBits::eColorAttachmentWrite;
-			image_memory_barrier.oldLayout           = colors[i].vulkan_buffer->layout;
-			image_memory_barrier.newLayout           = color_initial_layout;
-			image_memory_barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-			image_memory_barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-			image_memory_barrier.image               = colors[i].vulkan_buffer->image;
-			image_memory_barrier.subresourceRange.aspectMask     = vk::ImageAspectFlagBits::eColor;
-			image_memory_barrier.subresourceRange.baseMipLevel   = 0;
-			image_memory_barrier.subresourceRange.levelCount     = VK_REMAINING_MIP_LEVELS;
-			image_memory_barrier.subresourceRange.baseArrayLayer = 0;
-			image_memory_barrier.subresourceRange.layerCount     = colors[i].vulkan_buffer->layers;
-
-			buffer.pipelineBarrier(vk::PipelineStageFlagBits::eTopOfPipe,
-			                       vk::PipelineStageFlagBits::eColorAttachmentOutput,
-			                       vk::DependencyFlags {}, 0, nullptr, 0, nullptr, 1,
-			                       &image_memory_barrier);
-
-			colors[i].vulkan_buffer->layout = image_memory_barrier.newLayout;
-		} else if (graphics_debug_dump_enabled()) {
-			LOGF("BeginRenderPass: color%u initial image=%p mem=%" PRIu64 " layout=%s\n", i,
-			     VulkanHandleToPointer(colors[i].vulkan_buffer->image),
-			     colors[i].vulkan_buffer->memory.unique_id,
-			     VulkanToString(colors[i].vulkan_buffer->layout).c_str());
-		}
+	std::array<vk::RenderingAttachmentInfo, RENDER_COLOR_ATTACHMENTS_MAX> colors {};
+	for (uint32_t i = 0; i < state.num_color_attachments; i++) {
+		const auto& attachment = state.color_attachments[i];
+		colors[i].sType        = vk::StructureType::eRenderingAttachmentInfo;
+		colors[i].imageView    = attachment.image_view;
+		colors[i].imageLayout  = attachment.image_layout;
+		colors[i].loadOp = attachment.is_clear ? vk::AttachmentLoadOp::eClear
+		                                      : vk::AttachmentLoadOp::eLoad;
+		colors[i].storeOp                  = vk::AttachmentStoreOp::eStore;
+		colors[i].clearValue.color.uint32  = attachment.clear_value;
 	}
 
-	const auto depth_layout =
-	    with_depth ? framebuffer.depth_layout : vk::ImageLayout::eDepthStencilAttachmentOptimal;
+	const auto& depth_stencil = state.depth_stencil_attachment;
+	vk::RenderingAttachmentInfo depth {};
+	depth.sType       = vk::StructureType::eRenderingAttachmentInfo;
+	depth.imageView   = depth_stencil.image_view;
+	depth.imageLayout = depth_stencil.image_layout;
+	depth.loadOp = depth_stencil.depth_clear ? vk::AttachmentLoadOp::eClear
+	                                        : vk::AttachmentLoadOp::eLoad;
+	depth.storeOp                        = vk::AttachmentStoreOp::eStore;
+	depth.clearValue.depthStencil.depth = std::bit_cast<float>(depth_stencil.clear_value[0]);
 
-	if (with_depth && depth.vulkan_buffer->layout != depth_layout) {
-		vk::ImageMemoryBarrier image_memory_barrier {};
-		image_memory_barrier.sType = vk::StructureType::eImageMemoryBarrier;
-		image_memory_barrier.pNext = nullptr;
-		image_memory_barrier.srcAccessMask =
-		    vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-		image_memory_barrier.dstAccessMask =
-		    (depth_layout == vk::ImageLayout::eDepthStencilReadOnlyOptimal
-		         ? vk::AccessFlagBits::eMemoryRead
-		         : vk::AccessFlagBits::eMemoryWrite);
-		image_memory_barrier.oldLayout           = depth.vulkan_buffer->layout;
-		image_memory_barrier.newLayout           = depth_layout;
-		image_memory_barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-		image_memory_barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-		image_memory_barrier.image               = depth.vulkan_buffer->image;
-		image_memory_barrier.subresourceRange.aspectMask =
-		    ImageViewOps::DepthAspectMask(depth.vulkan_buffer->format);
-		image_memory_barrier.subresourceRange.baseMipLevel   = 0;
-		image_memory_barrier.subresourceRange.levelCount     = 1;
-		image_memory_barrier.subresourceRange.baseArrayLayer = 0;
-		image_memory_barrier.subresourceRange.layerCount     = depth.vulkan_buffer->layers;
+	vk::RenderingAttachmentInfo stencil {};
+	stencil.sType       = vk::StructureType::eRenderingAttachmentInfo;
+	stencil.imageView   = depth_stencil.image_view;
+	stencil.imageLayout = depth_stencil.image_layout;
+	stencil.loadOp = depth_stencil.stencil_clear ? vk::AttachmentLoadOp::eClear
+	                                            : vk::AttachmentLoadOp::eLoad;
+	stencil.storeOp                            = vk::AttachmentStoreOp::eStore;
+	stencil.clearValue.depthStencil.stencil   = depth_stencil.clear_value[1];
 
-		buffer.pipelineBarrier(
-		    vk::PipelineStageFlagBits::eAllGraphics | vk::PipelineStageFlagBits::eComputeShader,
-		    vk::PipelineStageFlagBits::eAllGraphics | vk::PipelineStageFlagBits::eComputeShader,
-		    vk::DependencyFlags {}, 0, nullptr, 0, nullptr, 1, &image_memory_barrier);
-
-		depth.vulkan_buffer->layout = image_memory_barrier.newLayout;
-	}
-
-	buffer.beginRenderPass(&render_pass_info, vk::SubpassContents::eInline);
-
-	for (uint32_t i = 0; i < color_count; i++) {
-		colors[i].vulkan_buffer->layout = RENDER_COLOR_IMAGE_LAYOUT;
-		if (colors[i].vulkan_buffer->type == VulkanImageType::RenderTexture) {
-			static_cast<RenderTextureVulkanImage*>(colors[i].vulkan_buffer)->initial_clear_pending =
-			    false;
-		}
-	}
-	if (with_depth) {
-		depth.vulkan_buffer->initial_depth_clear_pending   = false;
-		depth.vulkan_buffer->initial_stencil_clear_pending = false;
-	}
+	vk::RenderingInfo rendering {};
+	rendering.sType                = vk::StructureType::eRenderingInfo;
+	rendering.renderArea.extent    = {state.width, state.height};
+	rendering.layerCount           = state.num_layers;
+	rendering.colorAttachmentCount = state.num_color_attachments;
+	rendering.pColorAttachments    = colors.data();
+	rendering.pDepthAttachment     = depth_stencil.has_depth ? &depth : nullptr;
+	rendering.pStencilAttachment   = depth_stencil.has_stencil ? &stencil : nullptr;
+	Handle().beginRendering(rendering);
+	m_render_state = state;
+	m_rendering    = true;
 }
 
-void CommandBuffer::EndRenderPass() const {
-	auto buffer = Handle();
-
-	buffer.endRenderPass();
+void CommandBuffer::EndRendering() const {
+	if (!m_rendering) {
+		return;
+	}
+	Handle().endRendering();
+	m_rendering    = false;
+	m_render_state = {};
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/debug.cpp

@@ -9,6 +9,7 @@
 #include "graphics/guest_gpu/hardwareContext.h"
 #include "graphics/host_gpu/renderer/render.h"
 
+#include <algorithm>
 #include <atomic>
 #include <cmath>
 #include <fmt/format.h>
@@ -100,8 +101,6 @@ void sh_print(const char* func, const HW::Shader& /*uc*/) {
 	LOGF("%s\n", func);
 }
 
-void sh_check(const HW::Shader& /*uc*/) {}
-
 std::vector<std::string> rt_print(const char* func, const HW::RenderTarget& rt) {
 	std::vector<std::string> dst;
 	dst.reserve(53);
@@ -431,21 +430,17 @@ static void ZPrint(const char* func, const HW::DepthRenderTarget& z) {
 	LOGF("%s\n", func);
 
 	LOGF("\t z_info.format                         = 0x%08" PRIx32 "\n"
-	     "\t z_info.tile_mode_index                = 0x%08" PRIx32 "\n"
 	     "\t z_info.num_samples                    = 0x%08" PRIx32 "\n"
-	     "\t z_info.tile_surface_enable            = %s\n"
+	     "\t z_info.texture_compatibility          = 0x%08" PRIx32 "\n"
+	     "\t z_info.htile_acceleration             = %s\n"
 	     "\t z_info.expclear_enabled               = %s\n"
-	     "\t z_info.zrange_precision               = 0x%08" PRIx32 "\n"
-	     "\t z_info.embedded_sample_locations      = %s\n"
+	     "\t z_info.z_compare_base                 = 0x%08" PRIx32 "\n"
 	     "\t z_info.partially_resident             = %s\n"
-	     "\t z_info.num_mip_levels                 = 0x%02" PRIx8 "\n"
-	     "\t z_info.plane_compression              = 0x%02" PRIx8 "\n"
+	     "\t z_info.max_mip_level                  = 0x%02" PRIx8 "\n"
 	     "\t stencil_info.format                   = 0x%08" PRIx32 "\n"
-	     "\t stencil_info.tile_stencil_disable     = %s\n"
+	     "\t stencil_info.texture_compatibility    = 0x%08" PRIx32 "\n"
+	     "\t stencil_info.htile_stencil_disabled   = %s\n"
 	     "\t stencil_info.expclear_enabled         = %s\n"
-	     "\t stencil_info.tile_mode_index          = 0x%08" PRIx32 "\n"
-	     "\t stencil_info.tile_split               = 0x%08" PRIx32 "\n"
-	     "\t stencil_info.texture_compatible_stencil = %s\n"
 	     "\t stencil_info.partially_resident       = %s\n"
 	     "\t depth_info.addr5_swizzle_mask         = 0x%08" PRIx32 "\n"
 	     "\t depth_info.array_mode                 = 0x%08" PRIx32 "\n"
@@ -478,15 +473,15 @@ static void ZPrint(const char* func, const HW::DepthRenderTarget& z) {
 	     "\t height                                = 0x%08" PRIx32 "\n"
 	     "\t size.x_max                            = 0x%04" PRIx16 "\n"
 	     "\t size.y_max                            = 0x%04" PRIx16 "\n",
-	     z.z_info.format, z.z_info.tile_mode_index, z.z_info.num_samples,
-	     z.z_info.tile_surface_enable ? "true" : "false",
-	     z.z_info.expclear_enabled ? "true" : "false", z.z_info.zrange_precision,
-	     z.z_info.embedded_sample_locations ? "true" : "false",
-	     z.z_info.partially_resident ? "true" : "false", z.z_info.num_mip_levels,
-	     z.z_info.plane_compression, z.stencil_info.format,
-	     z.stencil_info.tile_stencil_disable ? "true" : "false",
-	     z.stencil_info.expclear_enabled ? "true" : "false", z.stencil_info.tile_mode_index,
-	     z.stencil_info.tile_split, z.stencil_info.texture_compatible_stencil ? "true" : "false",
+	     z.z_info.format, z.z_info.num_samples,
+	     Prospero::GpuEnumValue(z.z_info.texture_compatibility),
+	     z.z_info.htile_acceleration ? "true" : "false",
+	     z.z_info.expclear_enabled ? "true" : "false",
+	     Prospero::GpuEnumValue(z.z_info.z_compare_base),
+	     z.z_info.partially_resident ? "true" : "false", z.z_info.max_mip_level,
+	     z.stencil_info.format, Prospero::GpuEnumValue(z.stencil_info.texture_compatibility),
+	     z.stencil_info.htile_stencil_disabled ? "true" : "false",
+	     z.stencil_info.expclear_enabled ? "true" : "false",
 	     z.stencil_info.partially_resident ? "true" : "false", z.depth_info.addr5_swizzle_mask,
 	     z.depth_info.array_mode, z.depth_info.pipe_config, z.depth_info.bank_width,
 	     z.depth_info.bank_height, z.depth_info.macro_tile_aspect, z.depth_info.num_banks,
@@ -503,36 +498,17 @@ static void ZPrint(const char* func, const HW::DepthRenderTarget& z) {
 
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
 static void ZCheck(const HW::DepthRenderTarget& z) {
+	EXIT_NOT_IMPLEMENTED(!z.z_info.HasValidTextureCompatibility());
+	EXIT_NOT_IMPLEMENTED(!z.stencil_info.HasValidTextureCompatibility());
 	if (z.z_info.format == 0) {
 		EXIT_NOT_IMPLEMENTED(z.z_info.format != 0);
-		EXIT_NOT_IMPLEMENTED(z.z_info.tile_mode_index != 0);
 		EXIT_NOT_IMPLEMENTED(z.z_info.num_samples != 0);
-		EXIT_NOT_IMPLEMENTED(z.z_info.tile_surface_enable != false);
+		EXIT_NOT_IMPLEMENTED(z.z_info.htile_acceleration != false);
 		EXIT_NOT_IMPLEMENTED(z.z_info.expclear_enabled != false);
-		if (z.z_info.zrange_precision != 0) {
-			LOGF("Warning: zrange_precision != 0\n");
-			// z.z_info.zrange_precision = 0;
-		}
-		if (z.z_info.embedded_sample_locations) {
-			static bool logged = false;
-			if (!logged) {
-				LOGF("DepthTarget: temporary: ignoring embedded sample locations\n");
-				logged = true;
-			}
-		}
 		EXIT_NOT_IMPLEMENTED(z.z_info.partially_resident != false);
-		EXIT_NOT_IMPLEMENTED(z.z_info.num_mip_levels != 0);
-		if (z.z_info.plane_compression != 0) {
-			static bool logged = false;
-			if (!logged) {
-				LOGF("DepthTarget: temporary: ignoring PS5 plane_compression=0x%02" PRIx8 "\n",
-				     z.z_info.plane_compression);
-				logged = true;
-			}
-		}
+		EXIT_NOT_IMPLEMENTED(z.z_info.max_mip_level != 0);
 	} else {
 		EXIT_NOT_IMPLEMENTED(z.z_info.format != 0x00000001 && z.z_info.format != 0x00000003);
-		// EXIT_NOT_IMPLEMENTED(z.z_info.tile_mode_index != 0x00000002);
 		if (z.z_info.num_samples != 0x00000000) {
 			static bool logged = false;
 			if (!logged) {
@@ -541,56 +517,17 @@ static void ZCheck(const HW::DepthRenderTarget& z) {
 				logged = true;
 			}
 		}
-		// EXIT_NOT_IMPLEMENTED(z.z_info.tile_surface_enable != true);
 		EXIT_NOT_IMPLEMENTED(z.z_info.expclear_enabled != false);
-		if (z.z_info.zrange_precision != 0x00000001) {
-			static bool logged = false;
-			if (!logged) {
-				LOGF("DepthTarget: temporary: ignoring zrange_precision=0x%08" PRIx32 "\n",
-				     z.z_info.zrange_precision);
-				logged = true;
-			}
-		}
-		if (z.z_info.embedded_sample_locations) {
-			static bool logged = false;
-			if (!logged) {
-				LOGF("DepthTarget: temporary: ignoring embedded sample locations\n");
-				logged = true;
-			}
-		}
 		EXIT_NOT_IMPLEMENTED(z.z_info.partially_resident != false);
-		EXIT_NOT_IMPLEMENTED(z.z_info.num_mip_levels != 0);
-		if (z.z_info.plane_compression != 0) {
-			static bool logged = false;
-			if (!logged) {
-				LOGF("DepthTarget: temporary: ignoring PS5 plane_compression=0x%02" PRIx8 "\n",
-				     z.z_info.plane_compression);
-				logged = true;
-			}
-		}
+		EXIT_NOT_IMPLEMENTED(z.z_info.max_mip_level != 0);
 	}
 
 	if (z.stencil_info.format == 0) {
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.format != 0);
-		//  EXIT_NOT_IMPLEMENTED(z.stencil_info.tile_stencil_disable != false);
 		EXIT_NOT_IMPLEMENTED(z.stencil_info.expclear_enabled != false);
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.tile_mode_index != 0);
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.tile_split != 0);
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.texture_compatible_stencil != true);
 		EXIT_NOT_IMPLEMENTED(z.stencil_info.partially_resident != false);
 	} else {
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.format != 0x00000001);
-		if (z.stencil_info.tile_stencil_disable != true) {
-
-			static std::atomic<uint32_t> log_count {0};
-			if (log_count.fetch_add(1) < 16) {
-				LOGF("DepthTarget: temporary: ignoring PS5 HTILE stencil acceleration\n");
-			}
-		}
+		EXIT_NOT_IMPLEMENTED(z.stencil_info.format != 0x00000001);
 		EXIT_NOT_IMPLEMENTED(z.stencil_info.expclear_enabled != false);
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.tile_mode_index != 0x00000002);
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.tile_split != 0x00000002);
-		// EXIT_NOT_IMPLEMENTED(z.stencil_info.texture_compatible_stencil != true);
 		EXIT_NOT_IMPLEMENTED(z.stencil_info.partially_resident != false);
 	}
 
@@ -1135,10 +1072,10 @@ static ScissorRect ScissorRectClamp(ScissorRect r, uint32_t width, uint32_t heig
 	int max_right  = static_cast<int>(width);
 	int max_bottom = static_cast<int>(height);
 
-	r.left   = (r.left < 0 ? 0 : (r.left > max_right ? max_right : r.left));
-	r.right  = (r.right < 0 ? 0 : (r.right > max_right ? max_right : r.right));
-	r.top    = (r.top < 0 ? 0 : (r.top > max_bottom ? max_bottom : r.top));
-	r.bottom = (r.bottom < 0 ? 0 : (r.bottom > max_bottom ? max_bottom : r.bottom));
+	r.left   = std::clamp(r.left, 0, max_right);
+	r.right  = std::clamp(r.right, 0, max_right);
+	r.top    = std::clamp(r.top, 0, max_bottom);
+	r.bottom = std::clamp(r.bottom, 0, max_bottom);
 
 	if (!ScissorRectValid(r)) {
 		r.right  = r.left;

src/graphics/host_gpu/renderer/debug.h

@@ -33,7 +33,6 @@ bool                     graphics_debug_dump_enabled();
 void                     uc_print(const char* func, const HW::UserConfig& uc);
 void                     uc_check(const HW::UserConfig& uc);
 void                     sh_print(const char* func, const HW::Shader& uc);
-void                     sh_check(const HW::Shader& uc);
 std::vector<std::string> rt_print(const char* func, const HW::RenderTarget& rt);
 bool                     RenderIsColorTileModeLinear(uint32_t tile_mode);
 void                     hw_print(const RenderCommandBuffer& buffer);

src/graphics/host_gpu/renderer/depthRenderTarget.cpp

@@ -13,12 +13,10 @@
 #include "graphics/host_gpu/objects/textureCommon.h"
 #include "graphics/host_gpu/renderer/debug.h"
 #include "graphics/host_gpu/renderer/descriptorCache.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
+#include "graphics/host_gpu/renderer/imageView.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/transfer.h"
 #include "graphics/host_gpu/vulkanCommon.h"
-#include "graphics/presentation/displayBuffer.h"
 
 #include <algorithm>
 #include <atomic>
@@ -88,7 +86,8 @@ static bool UsesStencilOpValue(uint8_t fail, uint8_t pass, uint8_t depth_fail) {
 }
 
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
-void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, RenderDepthInfo& r) {
+void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer,
+                                              RenderDepthInfo& r) {
 	KYTY_PROFILER_FUNCTION();
 	(void)submit_id;
 	const auto& hw = buffer.GetRegisters();
@@ -103,31 +102,34 @@ void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 	if (!depth_active && !stencil_active) {
 		return;
 	}
+	if (!z.z_info.HasValidTextureCompatibility() ||
+	    !z.stencil_info.HasValidTextureCompatibility()) {
+		DepthFatal("invalid PS5 depth texture-compatibility encoding");
+	}
 	const bool attachment_unbound =
 	    z.z_info.format == Prospero::GpuEnumValue(Prospero::DepthFormat::kInvalid) &&
 	    z.stencil_info.format == Prospero::GpuEnumValue(Prospero::StencilFormat::kInvalid) &&
-	    z.z_info.tile_mode_index == 0 && z.z_info.num_samples == 0 &&
-	    z.z_info.zrange_precision <= 1 && !z.z_info.expclear_enabled &&
-	    !z.z_info.embedded_sample_locations && !z.z_info.partially_resident &&
-	    z.z_info.num_mip_levels == 0 && z.z_info.plane_compression == 0 &&
-	    z.stencil_info.tile_mode_index == 0 && z.stencil_info.tile_split == 0 &&
-	    !z.stencil_info.expclear_enabled && !z.stencil_info.texture_compatible_stencil &&
-	    !z.stencil_info.partially_resident && z.depth_view.slice_start == 0 &&
-	    z.depth_view.slice_max == 0 && z.depth_view.current_mip_level == 0 &&
-	    !z.depth_view.depth_write_disable && !z.depth_view.stencil_write_disable &&
-	    z.depth_info.addr5_swizzle_mask == 0 && z.depth_info.array_mode == 0 &&
-	    z.depth_info.pipe_config == 0 && z.depth_info.bank_width == 0 &&
-	    z.depth_info.bank_height == 0 && z.depth_info.macro_tile_aspect == 0 &&
-	    z.depth_info.num_banks == 0 && z.htile_surface.linear == 0 &&
-	    z.htile_surface.full_cache == 0 && z.htile_surface.htile_uses_preload_win == 0 &&
-	    z.htile_surface.preload == 0 && z.htile_surface.prefetch_width == 0 &&
-	    z.htile_surface.prefetch_height == 0 && z.htile_surface.dst_outside_zero_to_one == 0 &&
-	    z.z_read_base_addr == 0 && z.z_write_base_addr == 0 && z.stencil_read_base_addr == 0 &&
+	    z.z_info.num_samples == 0 &&
+	    z.z_info.texture_compatibility == Prospero::TextureCompatiblePlaneCompression::kDisable &&
+	    !z.z_info.expclear_enabled && !z.z_info.partially_resident && z.z_info.max_mip_level == 0 &&
+	    z.stencil_info.texture_compatibility == Prospero::TextureCompatibleStencil::kDisable &&
+	    !z.stencil_info.expclear_enabled && !z.stencil_info.partially_resident &&
+	    z.depth_view.slice_start == 0 && z.depth_view.slice_max == 0 &&
+	    z.depth_view.current_mip_level == 0 && !z.depth_view.depth_write_disable &&
+	    !z.depth_view.stencil_write_disable && z.depth_info.addr5_swizzle_mask == 0 &&
+	    z.depth_info.array_mode == 0 && z.depth_info.pipe_config == 0 &&
+	    z.depth_info.bank_width == 0 && z.depth_info.bank_height == 0 &&
+	    z.depth_info.macro_tile_aspect == 0 && z.depth_info.num_banks == 0 &&
+	    z.htile_surface.linear == 0 && z.htile_surface.full_cache == 0 &&
+	    z.htile_surface.htile_uses_preload_win == 0 && z.htile_surface.preload == 0 &&
+	    z.htile_surface.prefetch_width == 0 && z.htile_surface.prefetch_height == 0 &&
+	    z.htile_surface.dst_outside_zero_to_one == 0 && z.z_read_base_addr == 0 &&
+	    z.z_write_base_addr == 0 && z.stencil_read_base_addr == 0 &&
 	    z.stencil_write_base_addr == 0 && z.htile_data_base_addr == 0 &&
 	    // DB_DEPTH_SIZE_XY is independent state and may remain programmed after the attachment
 	    // formats and addresses are unbound. A zero encoding is the valid 1x1 value, so its
 	    // presence alone must not manufacture a depth attachment.
-	    !z.z_info.tile_surface_enable && !z.width_height_valid && !z.pitch_height_valid &&
+	    !z.z_info.htile_acceleration && !z.width_height_valid && !z.pitch_height_valid &&
 	    z.size.x_max == 0 && z.size.y_max == 0 && z.pitch_div8_minus1 == 0 &&
 	    z.height_div8_minus1 == 0 && z.slice_div64_minus1 == 0 && z.width == 0 && z.height == 0;
 	if (attachment_unbound) {
@@ -139,13 +141,13 @@ void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 	}
 	const bool has_stencil =
 	    z.stencil_info.format != Prospero::GpuEnumValue(Prospero::StencilFormat::kInvalid);
-	const bool has_htile = z.z_info.tile_surface_enable;
+	const bool has_htile = z.z_info.htile_acceleration;
 	const auto samples   = render_sample_count(z.z_info.num_samples);
 	if (samples == 0) {
 		DepthFatal("unsupported depth fragment count: %u", z.z_info.num_samples);
 	}
 	const bool htile_stencil_compat = depth_htile_stencil_acceleration_compatible(
-	    has_stencil, has_htile, z.stencil_info.tile_stencil_disable);
+	    has_stencil, has_htile, z.stencil_info.htile_stencil_disabled);
 	const auto view = ResolveTargetViewInfo(z.depth_view.slice_start, z.depth_view.slice_max);
 	switch (view.type) {
 		case TargetViewType::Image2D: break;
@@ -156,14 +158,10 @@ void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 			DepthFatal("invalid depth view: base=%u last=%u", z.depth_view.slice_start,
 			           z.depth_view.slice_max);
 	}
-	// Prospero defines the compression-disable bits as tile writeback policy. Vulkan attachments
-	// expose the same logical depth/stencil values regardless of the driver's backing compression.
 	if ((stencil_active && !has_stencil) || rc.resummarize_enable || rc.copy_centroid ||
 	    rc.copy_sample != 0 || z.z_info.expclear_enabled || z.stencil_info.expclear_enabled ||
-	    z.z_info.embedded_sample_locations || z.z_info.partially_resident ||
-	    z.stencil_info.partially_resident || z.z_info.plane_compression != 0 ||
-	    z.z_info.num_mip_levels != 0 || z.z_info.tile_mode_index != 0 ||
-	    z.z_info.zrange_precision > 1 || z.depth_view.current_mip_level != 0 ||
+	    z.z_info.partially_resident || z.stencil_info.partially_resident ||
+	    z.z_info.max_mip_level != 0 || z.depth_view.current_mip_level != 0 ||
 	    z.depth_info.addr5_swizzle_mask != 0 || z.depth_info.array_mode != 0 ||
 	    z.depth_info.pipe_config != 0 || z.depth_info.bank_width != 0 ||
 	    z.depth_info.bank_height != 0 || z.depth_info.macro_tile_aspect != 0 ||
@@ -177,27 +175,16 @@ void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 		DepthFatal("unsupported depth register state");
 	}
 	if (has_stencil) {
-		// Prospero defines Hi-Stencil as HTile-backed acceleration of the logical stencil plane.
-		// Keep the plane native in Vulkan while tracking HTile separately.
 		if (z.stencil_info.format != Prospero::GpuEnumValue(Prospero::StencilFormat::k8UInt) ||
-		    z.stencil_info.tile_mode_index != 0 || z.stencil_info.tile_split != 0 ||
-		    !htile_stencil_compat || z.stencil_info.texture_compatible_stencil ||
-		    z.stencil_read_base_addr == 0 ||
+		    !htile_stencil_compat || z.stencil_read_base_addr == 0 ||
 		    z.stencil_write_base_addr != z.stencil_read_base_addr ||
 		    (z.stencil_read_base_addr & 0xffffu) != 0 || z.depth_view.stencil_write_disable) {
 			DepthFatal("unsupported stencil attachment state");
 		}
-		if (!z.stencil_info.tile_stencil_disable) {
-			static std::atomic_bool logged = false;
-			if (!logged.load(std::memory_order_relaxed) &&
-			    !logged.exchange(true, std::memory_order_relaxed)) {
-				LOGF("DepthTarget: compatibility: using native stencil with PS5 HTILE "
-				     "acceleration\n");
-			}
-		}
 	} else if (z.stencil_read_base_addr != 0 || z.stencil_write_base_addr != 0 ||
-	           z.stencil_info.tile_mode_index != 0 || z.stencil_info.tile_split != 0 ||
-	           !htile_stencil_compat || z.stencil_info.texture_compatible_stencil) {
+	           !htile_stencil_compat ||
+	           z.stencil_info.texture_compatibility !=
+	               Prospero::TextureCompatibleStencil::kDisable) {
 		DepthFatal("stencil state without an active stencil attachment");
 	}
 	if (has_htile) {
@@ -272,28 +259,19 @@ void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 	    (has_htile && htile_backing_size > TRACKER_ADDRESS_SIZE - z.htile_data_base_addr)) {
 		DepthFatal("layered depth backing range is invalid");
 	}
-	r.htile                = has_htile;
-	r.width                = width;
-	r.height               = height;
-	r.samples              = samples;
-	r.depth_buffer_size    = depth_backing_size;
-	r.depth_buffer_vaddr   = z.z_read_base_addr;
-	r.stencil_buffer_size  = has_stencil ? stencil_backing_size : 0;
-	r.stencil_buffer_vaddr = has_stencil ? z.stencil_read_base_addr : 0;
-	r.htile_buffer_size    = has_htile ? htile_backing_size : 0;
-	r.htile_buffer_vaddr   = has_htile ? z.htile_data_base_addr : 0;
-	auto& cache            = GetRenderContext().GetTextureCache();
-	if (has_htile) {
-		cache.RegisterMeta(r.htile_buffer_vaddr, r.htile_buffer_size, view.image_layers);
-	}
-	if (has_htile && rc.depth_clear_enable && !cache.ClearMeta(z.htile_data_base_addr)) {
-		DepthFatal("failed to acquire HTile metadata for a depth clear");
-	}
-	const bool meta_clear =
-	    has_htile && cache.IsMetaCleared(z.htile_data_base_addr, z.depth_view.slice_start);
+	r.htile                   = has_htile;
+	r.width                   = width;
+	r.height                  = height;
+	r.samples                 = samples;
+	r.depth_buffer_size       = depth_backing_size;
+	r.depth_buffer_vaddr      = z.z_read_base_addr;
+	r.stencil_buffer_size     = has_stencil ? stencil_backing_size : 0;
+	r.stencil_buffer_vaddr    = has_stencil ? z.stencil_read_base_addr : 0;
+	r.htile_buffer_size       = has_htile ? htile_backing_size : 0;
+	r.htile_buffer_vaddr      = has_htile ? z.htile_data_base_addr : 0;
 	r.depth_clear_enable      = rc.depth_clear_enable;
-	r.depth_meta_clear_enable = meta_clear;
-	r.depth_load_clear_enable = r.depth_clear_enable || r.depth_meta_clear_enable;
+	r.depth_meta_clear_enable = false;
+	r.depth_load_clear_enable = r.depth_clear_enable;
 	r.depth_clear_value       = hw.GetDepthClearValue();
 	r.depth_test_enable       = dc.z_enable;
 	r.depth_write_enable      = dc.z_write_enable && !z.depth_view.depth_write_disable;
@@ -343,55 +321,93 @@ void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, R
 		r.vaddr[1] = r.stencil_buffer_vaddr;
 		r.size[1]  = r.stencil_buffer_size;
 	}
-	DepthTargetInfo info {};
-	info.address            = r.depth_buffer_vaddr;
-	info.size               = r.depth_buffer_size;
-	info.stencil_address    = r.stencil_buffer_vaddr;
-	info.stencil_size       = r.stencil_buffer_size;
-	info.htile_address      = r.htile_buffer_vaddr;
-	info.htile_size         = r.htile_buffer_size;
-	info.format             = r.format;
-	info.guest_format       = guest_format;
-	info.width              = width;
-	info.height             = height;
-	info.pitch              = pitch;
-	info.bytes_per_element  = bytes;
-	info.tile_mode          = Prospero::GpuEnumValue(Prospero::TileMode::kDepth);
-	info.layers             = view.image_layers;
-	info.samples            = samples;
-	info.depth_load_clear   = r.depth_load_clear_enable;
-	info.depth_access       = depth_active;
-	info.stencil_load_clear = rc.stencil_clear_enable;
-	info.stencil_access =
-	    r.stencil_clear_enable ||
-	    (r.stencil_test_enable &&
-	     (stencil_face_accesses_attachment(r.stencil_static_front, r.stencil_dynamic_front) ||
-	      stencil_face_accesses_attachment(r.stencil_static_back, r.stencil_dynamic_back)));
-	info.stencil_htile_compressed =
-	    has_stencil && has_htile && !z.stencil_info.tile_stencil_disable;
-	r.vulkan_buffer = &cache.FindDepthTarget(buffer, info);
-	r.vulkan_view =
-	    cache.GetDepthTargetAttachmentView(*r.vulkan_buffer, view.base_layer, view.layer_count);
-	if (r.vulkan_buffer->initial_depth_clear_pending) {
-		r.depth_load_clear_enable = true;
-		r.depth_clear_value       = 0.0f;
-	}
-	if (r.vulkan_buffer->initial_stencil_clear_pending) {
-		r.stencil_clear_enable = true;
-		r.stencil_clear_value  = 0;
-	}
-	if (meta_clear && !cache.TouchMeta(z.htile_data_base_addr, z.depth_view.slice_start, false)) {
-		DepthFatal("failed to consume HTile clear state");
-	}
+	TextureCache::ImageDesc desc {};
+	desc.type                 = TextureCache::BindingType::DepthTarget;
+	desc.info.data            = {r.depth_buffer_vaddr, r.depth_buffer_size};
+	desc.info.stencil         = {r.stencil_buffer_vaddr, r.stencil_buffer_size};
+	desc.info.pixel_format    = r.format;
+	desc.info.guest_format    = guest_format;
+	desc.info.type            = Prospero::ImageType::kColor2D;
+	desc.info.extent          = {width, height, 1};
+	desc.info.resources       = {1, view.image_layers};
+	desc.info.pitch           = pitch;
+	desc.info.bytes_per_block = bytes;
+	desc.info.samples         = samples;
+	desc.info.tile_mode       = Prospero::GpuEnumValue(Prospero::TileMode::kDepth);
+	desc.info.mip_layout[0]   = {0, r.depth_buffer_size, pitch, height};
+	desc.info.metadata.range  = {r.htile_buffer_vaddr, r.htile_buffer_size};
+	desc.info.metadata.kind   = has_htile ? ImageMetadataKind::Htile : ImageMetadataKind::None;
+	desc.info.metadata.stencil_compressed =
+	    has_stencil && has_htile && !z.stencil_info.htile_stencil_disabled;
+	desc.view_info.format = r.format;
+	desc.view_info.type =
+	    view.layer_count == 1 ? vk::ImageViewType::e2D : vk::ImageViewType::e2DArray;
+	desc.view_info.aspect      = ImageViewOps::DepthAspectMask(r.format);
+	desc.view_info.base_level  = 0;
+	desc.view_info.level_count = 1;
+	desc.view_info.base_layer  = view.base_layer;
+	desc.view_info.layer_count = view.layer_count;
+	desc.view_info.usage       = vk::ImageUsageFlagBits::eDepthStencilAttachment;
+	r.desc                     = std::move(desc);
+	auto& cache                = m_context.GetTextureCache();
+	r.image_id                 = cache.FindImage(r.desc);
+	r.image_view               = nullptr;
+	BindRenderTarget(r.image_id);
 }
 
-void MarkRenderTargetGpuWritten(const RenderDepthInfo& target) {
-	const bool with_depth =
-	    target.format != vk::Format::eUndefined && target.vulkan_buffer != nullptr;
-
-	if (with_depth && !depth_attachment_read_only(target)) {
-		GetRenderContext().GetTextureCache().MarkGpuWritten(*target.vulkan_buffer);
+vk::ImageAspectFlags RenderDepthInfo::AttachmentWriteAspects() const {
+	if (format == vk::Format::eUndefined) {
+		return {};
 	}
+
+	const auto           available = ImageViewOps::DepthAspectMask(format);
+	vk::ImageAspectFlags writes {};
+	if ((available & vk::ImageAspectFlagBits::eDepth) &&
+	    (depth_load_clear_enable || (depth_test_enable && depth_write_enable))) {
+		writes |= vk::ImageAspectFlagBits::eDepth;
+	}
+	if (!(available & vk::ImageAspectFlagBits::eStencil)) {
+		return writes;
+	}
+
+	const auto face_writes = [&](const PipelineStencilStaticState&  state,
+	                             const PipelineStencilDynamicState& dynamic) {
+		if (dynamic.writeMask == 0) {
+			return false;
+		}
+		bool can_pass = state.compareOp != vk::CompareOp::eNever;
+		bool can_fail = state.compareOp != vk::CompareOp::eAlways;
+		if (dynamic.compareMask == 0) {
+			switch (state.compareOp) {
+				case vk::CompareOp::eEqual:
+				case vk::CompareOp::eLessOrEqual:
+				case vk::CompareOp::eGreaterOrEqual:
+				case vk::CompareOp::eAlways:
+					can_pass = true;
+					can_fail = false;
+					break;
+				case vk::CompareOp::eNever:
+				case vk::CompareOp::eLess:
+				case vk::CompareOp::eGreater:
+				case vk::CompareOp::eNotEqual:
+					can_pass = false;
+					can_fail = true;
+					break;
+				default: break;
+			}
+		}
+		const bool depth_pass = !depth_test_enable || depth_compare_op != vk::CompareOp::eNever;
+		const bool depth_fail = depth_test_enable && depth_compare_op != vk::CompareOp::eAlways;
+		return (can_fail && state.failOp != vk::StencilOp::eKeep) ||
+		       (can_pass && depth_pass && state.passOp != vk::StencilOp::eKeep) ||
+		       (can_pass && depth_fail && state.depthFailOp != vk::StencilOp::eKeep);
+	};
+	if (stencil_clear_enable ||
+	    (stencil_test_enable && (face_writes(stencil_static_front, stencil_dynamic_front) ||
+	                             face_writes(stencil_static_back, stencil_dynamic_back)))) {
+		writes |= vk::ImageAspectFlagBits::eStencil;
+	}
+	return writes;
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/depthRenderTarget.h

@@ -2,7 +2,9 @@
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DEPTHRENDERTARGET_H_
 
 #include "common/assert.h"
+#include "graphics/host_gpu/renderer/imageView.h"
 #include "graphics/host_gpu/renderer/renderTarget.h"
+#include "graphics/host_gpu/renderer/textureCache.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 
 #include <cstdint>
@@ -10,14 +12,14 @@
 namespace Libs::Graphics {
 
 class RenderCommandBuffer;
-struct DepthStencilVulkanImage;
 
 inline constexpr bool depth_htile_stencil_acceleration_compatible(bool has_stencil, bool has_htile,
-                                                                  bool acceleration_disabled) {
-	return acceleration_disabled || (has_stencil && has_htile);
+                                                                  bool htile_stencil_disabled) {
+	return htile_stencil_disabled || (has_stencil && has_htile);
 }
 
 struct RenderDepthInfo {
+	TextureCache::ImageDesc     desc;
 	vk::Format                  format                   = vk::Format::eUndefined;
 	uint32_t                    width                    = 0;
 	uint32_t                    height                   = 0;
@@ -49,29 +51,46 @@ struct RenderDepthInfo {
 	PipelineStencilStaticState  stencil_static_back;
 	PipelineStencilDynamicState stencil_dynamic_front;
 	PipelineStencilDynamicState stencil_dynamic_back;
-	DepthStencilVulkanImage*    vulkan_buffer = nullptr;
-	vk::ImageView               vulkan_view   = nullptr;
-	uint64_t                    vaddr[3]      = {};
-	uint64_t                    size[3]       = {};
-	int                         vaddr_num     = 0;
+	ImageId                     image_id;
+	vk::ImageView               image_view = nullptr;
+	uint64_t                    vaddr[3]   = {};
+	uint64_t                    size[3]    = {};
+	int                         vaddr_num  = 0;
+
+	[[nodiscard]] vk::ImageAspectFlags AttachmentWriteAspects() const;
 };
 
 inline bool depth_attachment_read_only(const RenderDepthInfo& depth) {
-	const bool stencil_write =
-	    depth.stencil_test_enable &&
-	    (depth.stencil_dynamic_front.writeMask != 0 || depth.stencil_dynamic_back.writeMask != 0);
-	return !depth.depth_load_clear_enable && !depth.stencil_clear_enable &&
-	       !depth.depth_write_enable && !stencil_write;
+	return !depth.AttachmentWriteAspects();
 }
 
 inline vk::ImageLayout depth_attachment_layout(const RenderDepthInfo& depth) {
-	return depth_attachment_read_only(depth) ? vk::ImageLayout::eDepthStencilReadOnlyOptimal
-	                                         : vk::ImageLayout::eDepthStencilAttachmentOptimal;
+	const auto available     = ImageViewOps::DepthAspectMask(depth.format);
+	const auto writes        = depth.AttachmentWriteAspects();
+	const bool has_depth     = static_cast<bool>(available & vk::ImageAspectFlagBits::eDepth);
+	const bool has_stencil   = static_cast<bool>(available & vk::ImageAspectFlagBits::eStencil);
+	const bool depth_write   = static_cast<bool>(writes & vk::ImageAspectFlagBits::eDepth);
+	const bool stencil_write = static_cast<bool>(writes & vk::ImageAspectFlagBits::eStencil);
+	if (!has_stencil) {
+		return depth_write ? vk::ImageLayout::eDepthAttachmentOptimal
+		                   : vk::ImageLayout::eDepthReadOnlyOptimal;
+	}
+	if (!has_depth) {
+		return stencil_write ? vk::ImageLayout::eStencilAttachmentOptimal
+		                     : vk::ImageLayout::eStencilReadOnlyOptimal;
+	}
+	if (depth_write && stencil_write) {
+		return vk::ImageLayout::eDepthStencilAttachmentOptimal;
+	}
+	if (depth_write) {
+		return vk::ImageLayout::eDepthAttachmentStencilReadOnlyOptimal;
+	}
+	if (stencil_write) {
+		return vk::ImageLayout::eDepthReadOnlyStencilAttachmentOptimal;
+	}
+	return vk::ImageLayout::eDepthStencilReadOnlyOptimal;
 }
 
-void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer, RenderDepthInfo& r);
-void MarkRenderTargetGpuWritten(const RenderDepthInfo& target);
-
 } // namespace Libs::Graphics
 
 #endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DEPTHRENDERTARGET_H_

src/graphics/host_gpu/renderer/descriptorCache.cpp

@@ -2,7 +2,6 @@
 
 #include "common/assert.h"
 #include "common/profiler.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
 #include "graphics/shader/recompiler/ShaderIR.h"
 
 #include <array>
@@ -23,9 +22,13 @@ vk::ShaderStageFlags StageFlags(DescriptorCache::Stage stage) {
 
 bool IsSampledImage(BindingKind kind) {
 	switch (kind) {
+		case BindingKind::Sampled1D:
+		case BindingKind::Sampled1DArray:
 		case BindingKind::Sampled2D:
 		case BindingKind::Sampled2DArray:
 		case BindingKind::Sampled3D:
+		case BindingKind::SampledUint1D:
+		case BindingKind::SampledUint1DArray:
 		case BindingKind::SampledUint2D:
 		case BindingKind::SampledUint2DArray:
 		case BindingKind::SampledUint3D: return true;
@@ -35,9 +38,13 @@ bool IsSampledImage(BindingKind kind) {
 
 bool IsStorageImage(BindingKind kind) {
 	switch (kind) {
+		case BindingKind::Storage1D:
+		case BindingKind::Storage1DArray:
 		case BindingKind::Storage2D:
 		case BindingKind::Storage2DArray:
 		case BindingKind::Storage3D:
+		case BindingKind::StorageUint1D:
+		case BindingKind::StorageUint1DArray:
 		case BindingKind::StorageUint2D:
 		case BindingKind::StorageUint2DArray:
 		case BindingKind::StorageUint3D: return true;
@@ -76,31 +83,35 @@ std::vector<uint32_t> LayoutKey(DescriptorCache::Stage               stage,
 	return key;
 }
 
-vk::ImageLayout SampledLayout(const VulkanImage& image) {
-	switch (image.layout) {
-		case vk::ImageLayout::eTransferDstOptimal:
-		case vk::ImageLayout::eTransferSrcOptimal:
-		case vk::ImageLayout::eColorAttachmentOptimal: return vk::ImageLayout::eGeneral;
-		default: return image.layout;
-	}
-}
-
 vk::DescriptorBufferInfo BufferInfo(const BufferView& view) {
-	EXIT_IF(view.buffer == nullptr || view.buffer->buffer == nullptr);
-	return {view.buffer->buffer, view.offset, view.range};
-}
-
-vk::DescriptorImageInfo MakeDescriptorImageInfo(const DescriptorCache::TextureBinding& texture,
-                                                vk::ImageLayout                        layout) {
-	EXIT_IF(texture.image == nullptr || texture.view < 0 || texture.view >= VulkanImage::VIEW_MAX);
-	const auto view = texture.image_view != nullptr ? texture.image_view
-	                                                : texture.image->image_view[texture.view];
-	EXIT_IF(view == nullptr);
-	return {nullptr, view, layout};
+	EXIT_IF(view.buffer == nullptr);
+	return {view.buffer, view.offset, view.range};
 }
 
 } // namespace
 
+vk::DescriptorImageInfo DescriptorCache::MakeImageInfo(const TextureBinding& texture) {
+	EXIT_IF(!texture.image_id || texture.image_view == nullptr ||
+	        texture.layout == vk::ImageLayout::eUndefined);
+	return {nullptr, texture.image_view, texture.layout};
+}
+
+DescriptorCache::~DescriptorCache() {
+	for (auto& [layout, sets]: m_free_sets_by_layout) {
+		(void)layout;
+		for (auto* set: sets) {
+			delete set;
+		}
+	}
+	for (const auto& [key, layout]: m_descriptor_set_layouts) {
+		(void)key;
+		m_graphics.device.destroyDescriptorSetLayout(layout, nullptr);
+	}
+	for (const auto& pool: m_pools) {
+		m_graphics.device.destroyDescriptorPool(pool.pool, nullptr);
+	}
+}
+
 vk::DescriptorSetLayout
 DescriptorCache::GetDescriptorSetLayoutInternal(Stage                                stage,
                                                 const ShaderRecompiler::IR::Program& program) {
@@ -256,13 +267,9 @@ VulkanDescriptorSet& DescriptorCache::GetDescriptor(Stage
 				}
 				break;
 			default: {
-				const auto layout = IsStorageImage(binding.kind) ? vk::ImageLayout::eGeneral
-				                                                 : vk::ImageLayout::eUndefined;
 				for (const auto resource: binding.resources) {
 					const auto& texture = data.images.at(resource);
-					image_infos.push_back(MakeDescriptorImageInfo(
-					    texture,
-					    IsSampledImage(binding.kind) ? SampledLayout(*texture.image) : layout));
+					image_infos.push_back(MakeImageInfo(texture));
 				}
 				break;
 			}

src/graphics/host_gpu/renderer/descriptorCache.h

@@ -6,20 +6,27 @@
 #include "common/common.h"
 #include "common/threads.h"
 #include "graphics/host_gpu/graphicContext.h"
+#include "graphics/host_gpu/renderer/textureCache.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 #include "graphics/shader/shaderBindings.h"
 
 #include <map>
+#include <memory>
+#include <span>
 #include <unordered_map>
 #include <vector>
 
 namespace Libs::Graphics {
 
 namespace ShaderRecompiler::IR {
+struct DescriptorValue;
+struct ImageResource;
 struct Program;
-}
+struct ResourceSnapshot;
+} // namespace ShaderRecompiler::IR
 
 class CommandBuffer;
+struct DescriptorCacheTestAccess;
 struct ShaderStageRuntime;
 
 struct VulkanDescriptorSet {
@@ -29,9 +36,10 @@ struct VulkanDescriptorSet {
 };
 
 struct BufferView {
-	VulkanBuffer*  buffer = nullptr;
-	vk::DeviceSize offset = 0;
-	vk::DeviceSize range  = VK_WHOLE_SIZE;
+	std::shared_ptr<void> owner;
+	vk::Buffer            buffer = nullptr;
+	vk::DeviceSize        offset = 0;
+	vk::DeviceSize        range  = VK_WHOLE_SIZE;
 };
 
 class DescriptorCache {
@@ -39,18 +47,10 @@ public:
 	enum class Stage { Unknown, Vertex, Pixel, Compute };
 
 	struct TextureBinding {
-		VulkanImage*  image      = nullptr;
-		int           view       = VulkanImage::VIEW_DEFAULT;
-		vk::ImageView image_view = nullptr;
-	};
-
-	enum class TextureVariant : int {
-		Float2D = 0,
-		Uint2D,
-		FloatArray,
-		UintArray,
-		Float3D,
-		Uint3D,
+		ImageId                 image_id;
+		vk::ImageView           image_view = nullptr;
+		TextureCache::ImageDesc desc;
+		vk::ImageLayout         layout = vk::ImageLayout::eUndefined;
 	};
 
 	struct NativeDescriptors {
@@ -63,10 +63,21 @@ public:
 		BufferView                  user_data;
 	};
 
+	struct PreparedBindings {
+		std::shared_ptr<const ShaderRecompiler::IR::Program>          program;
+		std::shared_ptr<const ShaderRecompiler::IR::ResourceSnapshot> snapshot;
+		NativeDescriptors                                             resources;
+		std::vector<uint32_t>                                         flattened_srt;
+		std::vector<uint32_t>                                         user_data;
+		vk::ShaderStageFlags                                          shader_stage;
+		Stage                                                         stage     = Stage::Unknown;
+		bool                                                          committed = false;
+	};
+
 	explicit DescriptorCache(GraphicContext& graphics): m_graphics(graphics) {
 		EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
 	}
-	~DescriptorCache() { KYTY_NOT_IMPLEMENTED; }
+	~DescriptorCache();
 	KYTY_CLASS_NO_COPY(DescriptorCache);
 
 	vk::DescriptorSetLayout GetDescriptorSetLayout(Stage                                stage,
@@ -76,11 +87,14 @@ public:
 	                                      const NativeDescriptors& descriptors);
 
 private:
+	friend struct DescriptorCacheTestAccess;
+
 	struct Pool {
 		vk::DescriptorPool pool           = nullptr;
 		int                next_free_pool = -1;
 	};
 
+	static vk::DescriptorImageInfo MakeImageInfo(const TextureBinding& texture);
 	void                 CreatePool();
 	VulkanDescriptorSet* Allocate(Stage stage, const ShaderRecompiler::IR::Program& program);
 	vk::DescriptorSetLayout
@@ -95,11 +109,6 @@ private:
 	std::map<std::vector<uint32_t>, vk::DescriptorSetLayout> m_descriptor_set_layouts;
 };
 
-void BindDescriptors(uint64_t submit_id, CommandBuffer& buffer,
-                     vk::PipelineBindPoint pipeline_bind_point, vk::PipelineLayout layout,
-                     const ShaderStageRuntime& runtime, vk::ShaderStageFlags vk_stage,
-                     DescriptorCache::Stage stage);
-
 } // namespace Libs::Graphics
 
 #endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DESCRIPTORCACHE_H_

src/graphics/host_gpu/renderer/descriptors.h

@@ -2,6 +2,7 @@
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DESCRIPTORS_H_
 
 #include "common/assert.h"
+#include "graphics/host_gpu/renderer/image.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 #include "graphics/shader/recompiler/ShaderIR.h"
 #include "graphics/shader/shaderBindings.h"
@@ -12,8 +13,6 @@
 
 namespace Libs::Graphics {
 
-struct VulkanImage;
-
 template <typename T>
 [[nodiscard]] T DecodeNativeDescriptor(const ShaderRecompiler::IR::DescriptorValue& value) {
 	static_assert(std::is_trivially_copyable_v<T>);
@@ -35,13 +34,12 @@ ResolveTargetTextureView(const ShaderRecompiler::IR::ImageResource& resource,
                          Prospero::ImageType type, uint32_t base_layer, uint32_t image_layers);
 
 [[nodiscard]] bool IsSupportedDepthTargetDescriptor(const ShaderTextureResource& descriptor,
-                                                    const VulkanImage&           image);
-[[nodiscard]] bool IsSupportedDepthTextureEncoding(const ShaderTextureResource& descriptor);
+                                                    const Image&                 image);
+[[nodiscard]] bool IsSupportedDepthTextureEncoding(const ShaderTextureResource& descriptor,
+                                                    const Image&                 image);
 [[nodiscard]] bool
 IsSupportedSampledVideoOutView(const ShaderRecompiler::IR::ImageResource& resource,
-                               const ShaderTextureResource& descriptor, const VulkanImage& image);
-void ValidateMetadataReuseTexture(const ShaderRecompiler::IR::ImageResource& resource,
-                                  const ShaderTextureResource& descriptor, uint64_t size);
+                               const ShaderTextureResource& descriptor, const Image& image);
 void ValidateStorageTexture(const ShaderRecompiler::IR::ImageResource& resource,
                             const ShaderTextureResource& descriptor, uint64_t size);
 

src/graphics/host_gpu/renderer/dummyTextureCache.cpp

@@ -1,50 +0,0 @@
-#include "graphics/host_gpu/renderer/dummyTextureCache.h"
-
-#include "common/assert.h"
-#include "graphics/host_gpu/renderer/image.h"
-#include "graphics/host_gpu/transfer.h"
-
-#include <algorithm>
-
-namespace Libs::Graphics {
-
-namespace {
-
-[[nodiscard]] constexpr size_t DummyTextureIndex(bool uint_format, bool image_3d) noexcept {
-	return (image_3d ? 2u : 0u) + (uint_format ? 1u : 0u);
-}
-
-} // namespace
-
-DummyTextureCache::~DummyTextureCache() {
-	Common::LockGuard lock(m_mutex);
-	const auto        populated = [](const auto& slots) {
-		return std::ranges::any_of(slots, [](const auto& slot) { return slot.image != nullptr; });
-	};
-	if (!populated(m_sampled) && !populated(m_storage)) {
-		return;
-	}
-	Transfer::WaitForQueueIdle();
-	const auto destroy = [](auto& slots) {
-		for (auto& slot: slots) {
-			if (slot.image != nullptr) {
-				ImageOps::Destroy(*slot.image);
-				slot.image = nullptr;
-			}
-		}
-	};
-	destroy(m_sampled);
-	destroy(m_storage);
-}
-
-VulkanImage& DummyTextureCache::Get(Usage usage, bool uint_format, bool image_3d) {
-	Common::LockGuard lock(m_mutex);
-	auto&             slots = usage == Usage::Storage ? m_storage : m_sampled;
-	auto&             slot  = slots[DummyTextureIndex(uint_format, image_3d)];
-	if (slot.image == nullptr) {
-		slot.image = ImageOps::CreateDummyTexture(uint_format, image_3d, usage == Usage::Storage);
-	}
-	return *slot.image;
-}
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/dummyTextureCache.h

@@ -1,35 +0,0 @@
-#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DUMMYTEXTURECACHE_H_
-#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DUMMYTEXTURECACHE_H_
-
-#include "common/abi.h"
-#include "common/threads.h"
-#include "graphics/host_gpu/graphicContext.h"
-
-#include <array>
-#include <cstdint>
-
-namespace Libs::Graphics {
-
-class DummyTextureCache final {
-public:
-	enum class Usage : uint8_t { Sampled, Storage };
-
-	DummyTextureCache() = default;
-	~DummyTextureCache();
-	KYTY_CLASS_NO_COPY(DummyTextureCache);
-
-	[[nodiscard]] VulkanImage& Get(Usage usage, bool uint_format, bool image_3d);
-
-private:
-	struct Slot {
-		GpuTextureVulkanImage* image = nullptr;
-	};
-
-	Common::Mutex       m_mutex;
-	std::array<Slot, 4> m_sampled {};
-	std::array<Slot, 4> m_storage {};
-};
-
-} // namespace Libs::Graphics
-
-#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_DUMMYTEXTURECACHE_H_

src/graphics/host_gpu/renderer/framebufferCache.cpp

@@ -1,357 +0,0 @@
-#include "graphics/host_gpu/renderer/framebufferCache.h"
-
-#include "common/assert.h"
-#include "common/logging/log.h"
-#include "common/profiler.h"
-#include "graphics/host_gpu/renderer/colorRenderTarget.h"
-#include "graphics/host_gpu/renderer/depthRenderTarget.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/vulkanCommon.h"
-
-#include <algorithm>
-#include <atomic>
-
-namespace Libs::Graphics {
-
-VulkanFramebuffer* FramebufferCache::CreateFramebuffer(RenderColorInfo* colors,
-                                                       uint32_t         requested_color_count,
-                                                       RenderDepthInfo& depth) {
-	KYTY_PROFILER_FUNCTION();
-
-	Common::LockGuard lock(m_mutex);
-
-	EXIT_IF(colors == nullptr);
-	EXIT_IF(requested_color_count > RENDER_COLOR_ATTACHMENTS_MAX);
-
-	bool with_depth = (depth.format != vk::Format::eUndefined && depth.vulkan_buffer != nullptr);
-	bool with_color[RENDER_COLOR_ATTACHMENTS_MAX] = {};
-	uint32_t     color_count                      = 0;
-	VulkanImage* first_color                      = nullptr;
-	vk::Extent2D first_color_extent               = {};
-	uint32_t     attachment_samples               = 0;
-	for (uint32_t i = 0; i < requested_color_count; i++) {
-		with_color[i] = (colors[i].vulkan_buffer != nullptr);
-		if (!with_color[i]) {
-			break;
-		}
-		if (first_color == nullptr) {
-			first_color        = colors[i].vulkan_buffer;
-			first_color_extent = colors[i].extent;
-			attachment_samples = colors[i].samples;
-		} else if (colors[i].extent.width != first_color_extent.width ||
-		           colors[i].extent.height != first_color_extent.height) {
-			LOGF("Framebuffer: temporary: dropping mismatched MRT%u attachment color0=%ux%u "
-			     "color%u=%ux%u\n",
-			     i, first_color_extent.width, first_color_extent.height, i, colors[i].extent.width,
-			     colors[i].extent.height);
-			with_color[i] = false;
-			break;
-		}
-		if (colors[i].samples != attachment_samples ||
-		    colors[i].vulkan_buffer->samples != colors[i].samples) {
-			EXIT("Framebuffer: mismatched color attachment samples at slot %u, expected=%u "
-			     "requested=%u image=%u\n",
-			     i, attachment_samples, colors[i].samples, colors[i].vulkan_buffer->samples);
-		}
-		color_count++;
-	}
-	if (with_depth) {
-		if (depth.samples != depth.vulkan_buffer->samples) {
-			EXIT("Framebuffer: depth attachment sample identity mismatch, requested=%u image=%u\n",
-			     depth.samples, depth.vulkan_buffer->samples);
-		}
-		if (attachment_samples == 0) {
-			attachment_samples = depth.samples;
-		} else if (attachment_samples != depth.samples) {
-			EXIT(
-			    "Framebuffer: mixed color/depth sample counts are unsupported, color=%u depth=%u\n",
-			    attachment_samples, depth.samples);
-		}
-	}
-	if (!with_depth && color_count == 0) {
-		LOGF("Framebuffer: warning: no color or depth attachment\n");
-		return nullptr;
-	}
-	if (vulkan_sample_count(attachment_samples) == vk::SampleCountFlagBits {}) {
-		EXIT("Framebuffer: invalid attachment sample count %u\n", attachment_samples);
-	}
-	vk::ImageLayout color_layout[RENDER_COLOR_ATTACHMENTS_MAX] = {};
-	for (auto& layout: color_layout) {
-		layout = RENDER_COLOR_IMAGE_LAYOUT;
-	}
-	auto depth_layout = (with_depth ? depth_attachment_layout(depth)
-	                                : vk::ImageLayout::eDepthStencilAttachmentOptimal);
-	auto depth_read_only =
-	    (with_depth && depth_layout == vk::ImageLayout::eDepthStencilReadOnlyOptimal);
-
-	if (with_depth && first_color != nullptr &&
-	    (first_color_extent.width != depth.vulkan_buffer->extent.width ||
-	     first_color_extent.height != depth.vulkan_buffer->extent.height)) {
-		static std::atomic<uint32_t> log_count {0};
-		if (log_count.fetch_add(1, std::memory_order_relaxed) < 16) {
-			LOGF("Framebuffer: temporary: dropping mismatched PS5 depth attachment color=%ux%u "
-			     "depth=%ux%u format=%s\n",
-			     first_color_extent.width, first_color_extent.height,
-			     depth.vulkan_buffer->extent.width, depth.vulkan_buffer->extent.height,
-			     VulkanToString(depth.format).c_str());
-		}
-		depth.format                   = vk::Format::eUndefined;
-		depth.vulkan_buffer            = nullptr;
-		depth.vulkan_view              = nullptr;
-		depth.depth_test_enable        = false;
-		depth.depth_write_enable       = false;
-		depth.depth_bounds_test_enable = false;
-		depth.stencil_test_enable      = false;
-		depth.depth_clear_enable       = false;
-		depth.depth_load_clear_enable  = false;
-		depth.stencil_clear_enable     = false;
-		with_depth                     = false;
-		depth_layout                   = vk::ImageLayout::eDepthStencilAttachmentOptimal;
-		depth_read_only                = false;
-	}
-
-	for (auto& f: m_framebuffers) {
-		bool color_match = (f.framebuffer != nullptr);
-		for (uint32_t i = 0; color_match && i < RENDER_COLOR_ATTACHMENTS_MAX; i++) {
-			const uint64_t image_id =
-			    (i < color_count && with_color[i] ? colors[i].vulkan_buffer->memory.unique_id : 0);
-			color_match =
-			    color_match && f.image_id[i] == image_id &&
-			    f.color_view[i] ==
-			        (i < color_count && with_color[i] ? colors[i].vulkan_view : nullptr) &&
-			    f.color_clear_enable[i] ==
-			        (i < color_count && with_color[i] && colors[i].color_clear_enable) &&
-			    f.color_layout[i] == color_layout[i];
-		}
-		if (color_match && f.depth_id == (with_depth ? depth.vulkan_buffer->memory.unique_id : 0) &&
-		    f.depth_view == (with_depth ? depth.vulkan_view : nullptr) &&
-		    f.depth_clear_enable == depth.depth_load_clear_enable &&
-		    f.stencil_clear_enable == depth.stencil_clear_enable &&
-		    f.depth_read_only == depth_read_only) {
-			return f.framebuffer;
-		}
-	}
-
-	EXIT_NOT_IMPLEMENTED(with_depth && first_color != nullptr &&
-	                     (first_color_extent.width != depth.vulkan_buffer->extent.width ||
-	                      first_color_extent.height != depth.vulkan_buffer->extent.height));
-
-	if (first_color == nullptr) {
-		first_color_extent = depth.vulkan_buffer->extent;
-	}
-
-	auto* framebuffer        = new VulkanFramebuffer;
-	framebuffer->render_pass = nullptr;
-	framebuffer->framebuffer = nullptr;
-	framebuffer->samples     = attachment_samples;
-	for (uint32_t i = 0; i < RENDER_COLOR_ATTACHMENTS_MAX; i++) {
-		framebuffer->color_layout[i] = color_layout[i];
-	}
-	framebuffer->depth_layout = depth_layout;
-
-	vk::AttachmentDescription attachments[RENDER_COLOR_ATTACHMENTS_MAX + 1] = {};
-	for (uint32_t i = 0; i < color_count; i++) {
-		attachments[i].flags         = {};
-		attachments[i].format        = colors[i].format;
-		attachments[i].samples       = vulkan_sample_count(attachment_samples);
-		attachments[i].loadOp        = (colors[i].color_clear_enable ? vk::AttachmentLoadOp::eClear
-		                                                             : vk::AttachmentLoadOp::eLoad);
-		attachments[i].storeOp       = vk::AttachmentStoreOp::eStore;
-		attachments[i].stencilLoadOp = vk::AttachmentLoadOp::eDontCare;
-		attachments[i].stencilStoreOp = vk::AttachmentStoreOp::eDontCare;
-		attachments[i].initialLayout  = color_layout[i];
-		attachments[i].finalLayout    = RENDER_COLOR_IMAGE_LAYOUT;
-	}
-
-	const uint32_t depth_attachment       = color_count;
-	attachments[depth_attachment].flags   = {};
-	attachments[depth_attachment].format  = depth.format;
-	attachments[depth_attachment].samples = vulkan_sample_count(attachment_samples);
-	attachments[depth_attachment].loadOp =
-	    (depth.depth_load_clear_enable ? vk::AttachmentLoadOp::eClear
-	                                   : vk::AttachmentLoadOp::eLoad);
-	attachments[depth_attachment].storeOp = vk::AttachmentStoreOp::eStore;
-	attachments[depth_attachment].stencilLoadOp =
-	    (depth.stencil_clear_enable ? vk::AttachmentLoadOp::eClear : vk::AttachmentLoadOp::eLoad);
-	attachments[depth_attachment].stencilStoreOp = vk::AttachmentStoreOp::eStore;
-	attachments[depth_attachment].initialLayout  = depth_layout;
-	attachments[depth_attachment].finalLayout    = depth_layout;
-
-	vk::AttachmentReference color_attachment_ref[RENDER_COLOR_ATTACHMENTS_MAX] = {};
-	for (uint32_t i = 0; i < RENDER_COLOR_ATTACHMENTS_MAX; i++) {
-		color_attachment_ref[i].attachment = (i < color_count ? i : VK_ATTACHMENT_UNUSED);
-		color_attachment_ref[i].layout     = RENDER_COLOR_IMAGE_LAYOUT;
-	}
-
-	vk::AttachmentReference depth_attachment_ref {};
-	depth_attachment_ref.attachment = depth_attachment;
-	depth_attachment_ref.layout     = depth_layout;
-
-	vk::SubpassDescription subpass {};
-	subpass.flags                   = {};
-	subpass.pipelineBindPoint       = vk::PipelineBindPoint::eGraphics;
-	subpass.inputAttachmentCount    = 0;
-	subpass.pInputAttachments       = nullptr;
-	subpass.colorAttachmentCount    = color_count;
-	subpass.pColorAttachments       = (color_count > 0 ? color_attachment_ref : nullptr);
-	subpass.pResolveAttachments     = nullptr;
-	subpass.pDepthStencilAttachment = (with_depth ? &depth_attachment_ref : nullptr);
-	subpass.preserveAttachmentCount = 0;
-	subpass.pPreserveAttachments    = nullptr;
-
-	const auto attachment_stage_mask =
-	    static_cast<vk::PipelineStageFlags>(vk::PipelineStageFlagBits::eColorAttachmentOutput |
-	                                        vk::PipelineStageFlagBits::eEarlyFragmentTests |
-	                                        vk::PipelineStageFlagBits::eLateFragmentTests);
-	const auto attachment_access_mask = static_cast<vk::AccessFlags>(
-	    vk::AccessFlagBits::eColorAttachmentRead | vk::AccessFlagBits::eColorAttachmentWrite |
-	    vk::AccessFlagBits::eDepthStencilAttachmentRead |
-	    vk::AccessFlagBits::eDepthStencilAttachmentWrite);
-
-	vk::SubpassDependency dependencies[2] = {};
-	dependencies[0].srcSubpass            = VK_SUBPASS_EXTERNAL;
-	dependencies[0].dstSubpass            = 0;
-	dependencies[0].srcStageMask          = vk::PipelineStageFlagBits::eAllCommands;
-	dependencies[0].dstStageMask          = attachment_stage_mask;
-	dependencies[0].srcAccessMask =
-	    vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-	dependencies[0].dstAccessMask   = attachment_access_mask;
-	dependencies[0].dependencyFlags = vk::DependencyFlagBits::eByRegion;
-
-	dependencies[1].srcSubpass    = 0;
-	dependencies[1].dstSubpass    = VK_SUBPASS_EXTERNAL;
-	dependencies[1].srcStageMask  = attachment_stage_mask;
-	dependencies[1].dstStageMask  = vk::PipelineStageFlagBits::eAllCommands;
-	dependencies[1].srcAccessMask = attachment_access_mask;
-	dependencies[1].dstAccessMask =
-	    vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-	dependencies[1].dependencyFlags = vk::DependencyFlagBits::eByRegion;
-
-	vk::RenderPassCreateInfo render_pass_info {};
-	render_pass_info.sType           = vk::StructureType::eRenderPassCreateInfo;
-	render_pass_info.pNext           = nullptr;
-	render_pass_info.flags           = {};
-	render_pass_info.attachmentCount = color_count + (with_depth ? 1u : 0u);
-	render_pass_info.pAttachments    = attachments;
-	render_pass_info.subpassCount    = 1;
-	render_pass_info.pSubpasses      = &subpass;
-	render_pass_info.dependencyCount = 2;
-	render_pass_info.pDependencies   = dependencies;
-
-	auto result =
-	    m_graphics.device.createRenderPass(&render_pass_info, nullptr, &framebuffer->render_pass);
-	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);
-
-	vk::Format color_formats[RENDER_COLOR_ATTACHMENTS_MAX] = {};
-	for (uint32_t i = 0; i < color_count; i++) {
-		color_formats[i] = colors[i].format;
-	}
-	framebuffer->render_pass_id = render_pass_compat_id(
-	    color_count, color_formats, with_depth, depth.format, depth_layout, attachment_samples);
-
-	EXIT_NOT_IMPLEMENTED(framebuffer->render_pass == nullptr);
-
-	vk::ImageView views[RENDER_COLOR_ATTACHMENTS_MAX + 1] = {};
-	for (uint32_t i = 0; i < color_count; i++) {
-		if (colors[i].vulkan_view == nullptr) {
-			EXIT("Framebuffer: color attachment view is missing at slot %u\n", i);
-		}
-		views[i] = colors[i].vulkan_view;
-	}
-	if (with_depth) {
-		if (depth.vulkan_view == nullptr) {
-			EXIT("Framebuffer: depth attachment view is missing\n");
-		}
-		views[color_count] = depth.vulkan_view;
-	}
-
-	vk::FramebufferCreateInfo framebuffer_info {};
-	framebuffer_info.sType           = vk::StructureType::eFramebufferCreateInfo;
-	framebuffer_info.pNext           = nullptr;
-	framebuffer_info.flags           = {};
-	framebuffer_info.renderPass      = framebuffer->render_pass;
-	framebuffer_info.attachmentCount = color_count + (with_depth ? 1u : 0u);
-	framebuffer_info.pAttachments    = views;
-	framebuffer_info.width           = first_color_extent.width;
-	framebuffer_info.height          = first_color_extent.height;
-	framebuffer_info.layers          = 1;
-
-	result =
-	    m_graphics.device.createFramebuffer(&framebuffer_info, nullptr, &framebuffer->framebuffer);
-	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);
-
-	EXIT_NOT_IMPLEMENTED(framebuffer->framebuffer == nullptr);
-
-	Framebuffer fnew;
-	fnew.framebuffer = framebuffer;
-	for (uint32_t i = 0; i < RENDER_COLOR_ATTACHMENTS_MAX; i++) {
-		fnew.image_id[i] =
-		    (i < color_count && with_color[i] ? colors[i].vulkan_buffer->memory.unique_id : 0);
-		fnew.color_view[i] = (i < color_count && with_color[i] ? colors[i].vulkan_view : nullptr);
-		fnew.color_clear_enable[i] =
-		    (i < color_count && with_color[i] && colors[i].color_clear_enable);
-		fnew.color_layout[i] = color_layout[i];
-	}
-	fnew.depth_id             = (with_depth ? depth.vulkan_buffer->memory.unique_id : 0);
-	fnew.depth_view           = (with_depth ? depth.vulkan_view : nullptr);
-	fnew.depth_clear_enable   = depth.depth_load_clear_enable;
-	fnew.stencil_clear_enable = depth.stencil_clear_enable;
-	fnew.depth_read_only      = depth_read_only;
-
-	bool updated = false;
-
-	for (auto& f: m_framebuffers) {
-		if (f.framebuffer == nullptr) {
-			f       = fnew;
-			updated = true;
-			break;
-		}
-	}
-
-	if (!updated) {
-		m_framebuffers.push_back(fnew);
-	}
-
-	return framebuffer;
-}
-
-void FramebufferCache::FreeFramebufferByColor(VulkanImage& image) {
-	Common::LockGuard lock(m_mutex);
-
-	for (auto& f: m_framebuffers) {
-		bool uses_image = false;
-		for (auto image_id: f.image_id) {
-			if (image_id == image.memory.unique_id) {
-				uses_image = true;
-				break;
-			}
-		}
-		if (f.framebuffer != nullptr && uses_image) {
-			m_graphics.device.destroyFramebuffer(f.framebuffer->framebuffer, nullptr);
-
-			m_graphics.device.destroyRenderPass(f.framebuffer->render_pass, nullptr);
-
-			delete f.framebuffer;
-
-			f.framebuffer = nullptr;
-		}
-	}
-}
-
-void FramebufferCache::FreeFramebufferByDepth(DepthStencilVulkanImage& image) {
-	Common::LockGuard lock(m_mutex);
-
-	for (auto& f: m_framebuffers) {
-		if (f.framebuffer != nullptr && f.depth_id == image.memory.unique_id) {
-			m_graphics.device.destroyFramebuffer(f.framebuffer->framebuffer, nullptr);
-
-			m_graphics.device.destroyRenderPass(f.framebuffer->render_pass, nullptr);
-
-			delete f.framebuffer;
-
-			f.framebuffer = nullptr;
-		}
-	}
-}
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/framebufferCache.h

@@ -1,85 +0,0 @@
-#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_FRAMEBUFFERCACHE_H_
-#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_FRAMEBUFFERCACHE_H_
-
-#include "common/abi.h"
-#include "common/assert.h"
-#include "common/common.h"
-#include "common/threads.h"
-#include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/renderer/renderTarget.h"
-#include "graphics/host_gpu/vulkanCommon.h"
-
-#include <vector>
-
-namespace Libs::Graphics {
-
-struct RenderColorInfo;
-struct RenderDepthInfo;
-
-static constexpr vk::ImageLayout RENDER_COLOR_IMAGE_LAYOUT = vk::ImageLayout::eGeneral;
-
-struct VulkanFramebuffer {
-	vk::RenderPass  render_pass                                = nullptr;
-	uint64_t        render_pass_id                             = 0;
-	vk::Framebuffer framebuffer                                = nullptr;
-	uint32_t        samples                                    = 1;
-	vk::ImageLayout color_layout[RENDER_COLOR_ATTACHMENTS_MAX] = {};
-	vk::ImageLayout depth_layout = vk::ImageLayout::eDepthStencilAttachmentOptimal;
-};
-
-inline uint64_t render_pass_compat_id(uint32_t color_count, const vk::Format* color_formats,
-                                      bool with_depth, vk::Format depth_format,
-                                      vk::ImageLayout depth_layout, uint32_t samples) {
-	uint64_t id  = 0xcbf29ce484222325ull;
-	auto     mix = [&id](uint64_t v) {
-		id ^= v;
-		id *= 0x100000001b3ull;
-	};
-
-	mix(color_count);
-	for (uint32_t i = 0; i < color_count; i++) {
-		mix(static_cast<uint32_t>(color_formats[i]));
-	}
-	mix(with_depth ? 1u : 0u);
-	mix(static_cast<uint32_t>(depth_format));
-	mix(static_cast<uint32_t>(depth_layout));
-	mix(samples);
-
-	return id;
-}
-
-class FramebufferCache {
-public:
-	explicit FramebufferCache(GraphicContext& graphics): m_graphics(graphics) {
-		EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
-	}
-	~FramebufferCache() { KYTY_NOT_IMPLEMENTED; }
-	KYTY_CLASS_NO_COPY(FramebufferCache);
-
-	VulkanFramebuffer* CreateFramebuffer(RenderColorInfo* colors, uint32_t color_count,
-	                                     RenderDepthInfo& depth);
-	void               FreeFramebufferByColor(VulkanImage& image);
-	void               FreeFramebufferByDepth(DepthStencilVulkanImage& image);
-
-private:
-	struct Framebuffer {
-		VulkanFramebuffer* framebuffer                                      = nullptr;
-		uint64_t           image_id[RENDER_COLOR_ATTACHMENTS_MAX]           = {};
-		vk::ImageView      color_view[RENDER_COLOR_ATTACHMENTS_MAX]         = {};
-		uint64_t           depth_id                                         = 0;
-		vk::ImageView      depth_view                                       = nullptr;
-		bool               color_clear_enable[RENDER_COLOR_ATTACHMENTS_MAX] = {};
-		vk::ImageLayout    color_layout[RENDER_COLOR_ATTACHMENTS_MAX]       = {};
-		bool               depth_clear_enable                               = false;
-		bool               stencil_clear_enable                             = false;
-		bool               depth_read_only                                  = false;
-	};
-
-	GraphicContext&          m_graphics;
-	Common::Mutex            m_mutex;
-	std::vector<Framebuffer> m_framebuffers;
-};
-
-} // namespace Libs::Graphics
-
-#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_FRAMEBUFFERCACHE_H_

src/graphics/host_gpu/renderer/gdsBuffer.cpp

@@ -1,67 +0,0 @@
-#include "graphics/host_gpu/renderer/gdsBuffer.h"
-
-#include "common/assert.h"
-#include "graphics/host_gpu/transfer.h"
-#include "graphics/host_gpu/vma.h"
-
-namespace Libs::Graphics {
-
-void GdsBuffer::Init() {
-	if (m_buffer == nullptr) {
-		m_buffer = std::make_unique<VulkanBuffer>();
-
-		m_buffer->usage           = vk::BufferUsageFlagBits::eStorageBuffer;
-		m_buffer->memory.property = vk::MemoryPropertyFlagBits::eHostVisible |
-		                            vk::MemoryPropertyFlagBits::eHostCoherent |
-		                            vk::MemoryPropertyFlagBits::eHostCached;
-		m_graphics.CreateBuffer(DW_SIZE * 4, *m_buffer);
-	}
-}
-
-void GdsBuffer::Clear(uint64_t dw_offset, uint32_t dw_num, uint32_t clear_value) {
-	Common::LockGuard lock(m_mutex);
-
-	Init();
-
-	EXIT_NOT_IMPLEMENTED(dw_offset >= DW_SIZE);
-	EXIT_NOT_IMPLEMENTED(dw_offset + dw_num > DW_SIZE);
-
-	void* data = nullptr;
-	m_graphics.MapMemory(m_buffer->memory, data);
-
-	for (uint32_t i = 0; i < dw_num; i++) {
-		static_cast<uint32_t*>(data)[dw_offset + i] = clear_value;
-	}
-
-	m_graphics.UnmapMemory(m_buffer->memory);
-}
-
-void GdsBuffer::Read(uint32_t* dst, uint32_t dw_offset, uint32_t dw_size) {
-	EXIT_IF(dst == nullptr);
-
-	Common::LockGuard lock(m_mutex);
-
-	Init();
-
-	EXIT_NOT_IMPLEMENTED(dw_offset >= DW_SIZE);
-	EXIT_NOT_IMPLEMENTED(dw_offset + dw_size > DW_SIZE);
-
-	void* data = nullptr;
-	m_graphics.MapMemory(m_buffer->memory, data);
-
-	for (uint32_t i = 0; i < dw_size; i++) {
-		dst[i] = static_cast<uint32_t*>(data)[dw_offset + i];
-	}
-
-	m_graphics.UnmapMemory(m_buffer->memory);
-}
-
-VulkanBuffer& GdsBuffer::GetBuffer() {
-	Common::LockGuard lock(m_mutex);
-
-	Init();
-
-	return *m_buffer;
-}
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/gdsBuffer.h

@@ -1,39 +0,0 @@
-#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_GDSBUFFER_H_
-#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_GDSBUFFER_H_
-
-#include "common/abi.h"
-#include "common/assert.h"
-#include "common/common.h"
-#include "common/threads.h"
-#include "graphics/host_gpu/graphicContext.h"
-
-#include <memory>
-
-namespace Libs::Graphics {
-
-class GdsBuffer {
-public:
-	explicit GdsBuffer(GraphicContext& graphics): m_graphics(graphics) {
-		EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
-	}
-	~GdsBuffer() { KYTY_NOT_IMPLEMENTED; }
-	KYTY_CLASS_NO_COPY(GdsBuffer);
-
-	void Clear(uint64_t dw_offset, uint32_t dw_num, uint32_t clear_value);
-	void Read(uint32_t* dst, uint32_t dw_offset, uint32_t dw_size);
-
-	VulkanBuffer& GetBuffer();
-
-private:
-	static constexpr uint64_t DW_SIZE = 0x3000;
-
-	void Init();
-
-	GraphicContext&               m_graphics;
-	Common::Mutex                 m_mutex;
-	std::unique_ptr<VulkanBuffer> m_buffer;
-};
-
-} // namespace Libs::Graphics
-
-#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_GDSBUFFER_H_

src/graphics/host_gpu/renderer/gpuResourceManager.cpp

@@ -3,17 +3,14 @@
 #include "common/assert.h"
 #include "graphics/guest_gpu/command_processor/commandProcessor.h"
 #include "graphics/guest_gpu/graphicsRun.h"
-#include "graphics/host_gpu/objects/label.h"
-#include "graphics/host_gpu/renderer/render.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
+#include "graphics/host_gpu/renderer/commandScheduler.h"
 
 namespace Libs::Graphics {
 
-GpuResourceManager::GpuResourceManager(GraphicContext& graphics)
-    : m_page_manager(FaultThunk, this), m_buffer_cache(graphics, m_page_manager, m_resource_mutex),
-      m_texture_cache(graphics, m_page_manager, m_buffer_cache, m_resource_mutex) {
-	m_buffer_cache.SetTextureCache(m_texture_cache);
-}
+GpuResourceManager::GpuResourceManager(GraphicContext& graphics, CommandScheduler& scheduler)
+    : m_page_manager(FaultThunk, this),
+      m_buffer_cache(graphics, scheduler, m_page_manager, m_texture_cache, m_resource_mutex),
+      m_texture_cache(graphics, scheduler, m_page_manager, m_buffer_cache, m_resource_mutex) {}
 
 GpuResourceManager::~GpuResourceManager() = default;
 
@@ -24,6 +21,15 @@ bool GpuResourceManager::FaultThunk(void* context, PageFaultAccess access, uint6
 
 bool GpuResourceManager::InvalidateMemory(PageFaultAccess access, uint64_t vaddr, uint64_t size,
                                           PageFaultPhase phase) noexcept {
+	// Let the authoritative image materialize first. A clean overlapping buffer marks a write
+	// fault CPU-dirty when it begins ownership transfer; doing that before image preflight would
+	// make the image appear to race a real CPU write. Completion and release retain buffer-first
+	// ordering so its pending fault is gone before TextureCache publishes the downloaded backing.
+	if (phase == PageFaultPhase::Invalidate) {
+		const bool image_handled  = m_texture_cache.InvalidateMemory(access, vaddr, size, phase);
+		const bool buffer_handled = m_buffer_cache.InvalidateMemory(access, vaddr, size, phase);
+		return buffer_handled || image_handled;
+	}
 	const bool buffer_handled = m_buffer_cache.InvalidateMemory(access, vaddr, size, phase);
 	const bool image_handled  = m_texture_cache.InvalidateMemory(access, vaddr, size, phase);
 	return buffer_handled || image_handled;
@@ -33,19 +39,23 @@ bool GpuResourceManager::HandleFault(PageFaultAccess access, uint64_t fault_vadd
 	if (!m_page_manager.IsMapped(fault_vaddr, 1)) {
 		return false;
 	}
-	if (LabelInCallback()) {
-		EXIT("unsupported guest-memory fault from an asynchronous GPU label callback, "
+	if (CommandScheduler::InDeferredOperation()) {
+		EXIT("unsupported guest-memory fault from an asynchronous GPU completion, "
 		     "addr=0x%016" PRIx64 " access=%u\n",
 		     fault_vaddr, static_cast<uint32_t>(access));
 	}
-	if (auto* cp = GraphicsRunCurrentCommandProcessor(); cp != nullptr) {
-		cp->BeginReadbackTransaction();
-		bool handled = false;
+	bool       handled = false;
+	const auto resolve = [this, access, fault_vaddr, &handled](CommandProcessor& cp) {
+		cp.BeginReadbackTransaction();
+		(void)m_buffer_cache.SynchronizeBacking(fault_vaddr, 1);
 		{
 			ResourceMutex::FaultScope fault(m_resource_mutex);
 			handled = m_page_manager.HandleFault(access, fault_vaddr);
 		}
-		cp->EndReadbackTransaction();
+		cp.EndReadbackTransaction();
+	};
+	if (auto* cp = Gpu::CurrentCommandProcessor(); cp != nullptr) {
+		resolve(*cp);
 		return handled;
 	}
 	if (m_resource_mutex.IsOwnedByCurrentThread()) {
@@ -53,36 +63,36 @@ bool GpuResourceManager::HandleFault(PageFaultAccess access, uint64_t fault_vadd
 		     " access=%u\n",
 		     fault_vaddr, static_cast<uint32_t>(access));
 	}
-	// Stop command-processor jobs before taking the shared cache transaction. External readback
-	// workers inherit this paused state and therefore never form resource -> submission lock
-	// inversion.
-	GraphicsRunSubmissionLock submissions;
-	ResourceMutex::FaultScope fault(m_resource_mutex);
-	return m_page_manager.HandleFault(access, fault_vaddr);
+	EXIT_IF(m_gpu == nullptr);
+	m_gpu->SendCommandSyncWithProcessor(resolve);
+	return handled;
 }
 
 void GpuResourceManager::PrepareHostWrite(uint64_t vaddr, uint64_t size) {
 	if (!m_page_manager.HasAnyMapping(vaddr, size)) {
 		return;
 	}
-	if (LabelInCallback()) {
-		EXIT("unsupported host write from an asynchronous GPU label callback, addr=0x%016" PRIx64
+	if (CommandScheduler::InDeferredOperation()) {
+		EXIT("unsupported host write from an asynchronous GPU completion, addr=0x%016" PRIx64
 		     " size=0x%016" PRIx64 "\n",
 		     vaddr, size);
 	}
-	const auto handle_range = [this, vaddr, size]() {
+	const auto handle_range = [this, vaddr, size] {
 		if (!m_page_manager.HandleWriteRange(vaddr, size)) {
 			EXIT("failed to prepare host write, addr=0x%016" PRIx64 " size=0x%016" PRIx64 "\n",
 			     vaddr, size);
 		}
 	};
-	if (auto* cp = GraphicsRunCurrentCommandProcessor(); cp != nullptr) {
-		cp->BeginReadbackTransaction();
+	const auto resolve = [this, &handle_range](CommandProcessor& cp) {
+		cp.BeginReadbackTransaction();
 		{
 			ResourceMutex::FaultScope fault(m_resource_mutex);
 			handle_range();
 		}
-		cp->EndReadbackTransaction();
+		cp.EndReadbackTransaction();
+	};
+	if (auto* cp = Gpu::CurrentCommandProcessor(); cp != nullptr) {
+		resolve(*cp);
 		return;
 	}
 	if (m_resource_mutex.IsOwnedByCurrentThread()) {
@@ -90,9 +100,8 @@ void GpuResourceManager::PrepareHostWrite(uint64_t vaddr, uint64_t size) {
 		     " size=0x%016" PRIx64 "\n",
 		     vaddr, size);
 	}
-	GraphicsRunSubmissionLock submissions;
-	ResourceMutex::FaultScope fault(m_resource_mutex);
-	handle_range();
+	EXIT_IF(m_gpu == nullptr);
+	m_gpu->SendCommandSyncWithProcessor(resolve);
 }
 
 bool GpuResourceManager::IsMapped(uint64_t vaddr, uint64_t size) const noexcept {
@@ -107,27 +116,26 @@ void GpuResourceManager::UnmapMemory(uint64_t vaddr, uint64_t size, GpuAccess ac
 	if (!IsMapped(vaddr, size)) {
 		EXIT("cannot unmap an unmapped GPU resource range\n");
 	}
-	m_texture_cache.UnmapMemory(vaddr, size);
-	m_buffer_cache.UnmapMemory(vaddr, size);
-	m_page_manager.OnGpuUnmap(vaddr, size, access);
+	const auto unmap = [this, vaddr, size, access] {
+		m_texture_cache.UnmapMemory(vaddr, size);
+		m_buffer_cache.UnmapMemory(vaddr, size);
+		m_page_manager.OnGpuUnmap(vaddr, size, access);
+	};
+	if (m_gpu == nullptr) {
+		if (m_resource_mutex.IsOwnedByCurrentThread()) {
+			EXIT("cannot synchronously unmap from a resource transaction\n");
+		}
+		unmap();
+		return;
+	}
+	Gpu::SubmissionLock submissions(*m_gpu);
+	m_gpu->SendCommandSync(unmap);
 }
 
-void GpuResourceManager::FillBuffer(CommandBuffer& command, uint64_t vaddr, uint64_t size,
-                                    uint32_t value) {
-	if (command.IsInvalid()) {
-		EXIT("cannot fill a buffer without a valid render command context\n");
-	}
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-	m_buffer_cache.FillBuffer(&command, vaddr, size, value);
-}
-
-void GpuResourceManager::CopyBuffer(CommandBuffer& command, uint64_t dst_vaddr, uint64_t src_vaddr,
-                                    uint64_t size) {
-	if (command.IsInvalid()) {
-		EXIT("cannot copy a buffer without a valid render command context\n");
-	}
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-	m_buffer_cache.CopyBuffer(&command, dst_vaddr, src_vaddr, size);
+void GpuResourceManager::RunGarbageCollector() {
+	m_texture_cache.ProcessDownloadImages();
+	m_texture_cache.RunGarbageCollector();
+	m_buffer_cache.RunGarbageCollector();
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/gpuResourceManager.h

@@ -12,24 +12,25 @@
 
 namespace Libs::Graphics {
 
-class CommandBuffer;
+class CommandScheduler;
+class Gpu;
 
 class GpuResourceManager {
 public:
-	explicit GpuResourceManager(GraphicContext& graphics);
+	GpuResourceManager(GraphicContext& graphics, CommandScheduler& scheduler);
 	~GpuResourceManager();
 	KYTY_CLASS_NO_COPY(GpuResourceManager);
 
 	[[nodiscard]] BufferCache&  GetBufferCache() { return m_buffer_cache; }
 	[[nodiscard]] TextureCache& GetTextureCache() { return m_texture_cache; }
+	void                        SetGpu(Gpu* gpu) noexcept { m_gpu = gpu; }
 
 	[[nodiscard]] bool HandleFault(PageFaultAccess access, uint64_t fault_vaddr) noexcept;
 	void               PrepareHostWrite(uint64_t vaddr, uint64_t size);
 	[[nodiscard]] bool IsMapped(uint64_t vaddr, uint64_t size) const noexcept;
 	void               MapMemory(uint64_t vaddr, uint64_t size, GpuAccess access);
 	void               UnmapMemory(uint64_t vaddr, uint64_t size, GpuAccess access);
-	void FillBuffer(CommandBuffer& command, uint64_t vaddr, uint64_t size, uint32_t value);
-	void CopyBuffer(CommandBuffer& command, uint64_t dst_vaddr, uint64_t src_vaddr, uint64_t size);
+	void               RunGarbageCollector();
 
 private:
 	static bool FaultThunk(void* context, PageFaultAccess access, uint64_t vaddr, uint64_t size,
@@ -41,6 +42,7 @@ private:
 	ResourceMutex m_resource_mutex;
 	BufferCache   m_buffer_cache;
 	TextureCache  m_texture_cache;
+	Gpu*          m_gpu = nullptr;
 };
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/image.h

@@ -2,49 +2,93 @@
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_IMAGE_H_
 
 #include "common/assert.h"
+#include "graphics/host_gpu/graphicContext.h"
 #include "graphics/host_gpu/renderer/imageInfo.h"
 
-#include <algorithm>
-#include <cstddef>
+#include <compare>
+#include <limits>
+#include <mutex>
+#include <optional>
 #include <span>
+#include <utility>
+#include <vector>
 
 namespace Libs::Graphics {
 
-struct DepthStencilVulkanImage;
-struct GpuTextureVulkanImage;
-struct GraphicContext;
-struct RenderTextureVulkanImage;
-struct VideoOutVulkanImage;
-struct VulkanImage;
+class Buffer;
+class CommandScheduler;
+struct ImageTestAccess;
 
-struct Image final: ImageInfo {
-	Image& operator=(const ImageInfo& value) {
-		if (IsCpuDirty()) {
-			EXIT("dirty sampled image cannot be reassigned\n");
-		}
-		static_cast<ImageInfo&>(*this) = value;
-		m_track_begin                  = address;
-		m_track_end                    = address + size;
-		m_maybe_cpu_hash_valid         = false;
-		return *this;
+struct ImageId {
+	uint32_t index      = std::numeric_limits<uint32_t>::max();
+	uint32_t generation = 0;
+
+	[[nodiscard]] explicit operator bool() const noexcept {
+		return index != std::numeric_limits<uint32_t>::max();
 	}
+	auto operator<=>(const ImageId&) const = default;
+};
+
+struct CachedImageView {
+	ImageViewInfo info;
+	vk::ImageView view = nullptr;
+};
+
+struct ImageViewCache {
+	ImageViewCache() = default;
+	KYTY_CLASS_NO_COPY(ImageViewCache);
+
+	std::mutex                   mutex;
+	std::vector<CachedImageView> views;
+};
+
+struct ImageUsage {
+	bool texture       = false;
+	bool storage       = false;
+	bool render_target = false;
+	bool depth_target  = false;
+	bool video_out     = false;
+};
+
+struct ImageBinding {
+	bool is_bound      = false;
+	bool is_target     = false;
+	bool needs_rebind  = false;
+	bool force_general = false;
+};
+
+class Image final {
+public:
+	Image(GraphicContext& graphics, CommandScheduler& scheduler, const ImageInfo& info);
+	~Image();
+	KYTY_CLASS_NO_COPY(Image);
+
+	[[nodiscard]] vk::ImageView FindView(const ImageViewInfo& view_info);
+	void                        AssociateDepth(ImageId image_id) { depth_id = image_id; }
+	using Barriers = std::vector<vk::ImageMemoryBarrier2>;
+	[[nodiscard]] Barriers
+	GetBarriers(vk::ImageLayout destination_layout, vk::AccessFlags2 destination_access,
+	            vk::PipelineStageFlags2 destination_stage,
+	            std::optional<ImageSubresourceRange> range);
+	void Transit(vk::ImageLayout destination_layout, vk::AccessFlags2 destination_access,
+	             std::optional<ImageSubresourceRange> range, vk::CommandBuffer command_buffer);
+	void Upload(std::span<const vk::BufferImageCopy> copies, vk::Buffer buffer,
+	            uint64_t offset, uint64_t size);
+	void Download(std::span<const vk::BufferImageCopy> copies, vk::Buffer buffer,
+	              uint64_t offset, uint64_t size);
+	void CopyImage(Image& source);
+	void Resolve(Image& source, const ImageSubresourceRange& source_range,
+	             const ImageSubresourceRange& destination_range);
+	void CopyImageWithBuffer(Image& source, Buffer& buffer);
+	void CopyMip(Image& source, uint32_t mip, uint32_t layer);
 
 	void InvalidateCpuWrite(uint64_t vaddr, uint64_t size) {
-		if (ImageRangeOverlaps(address, this->size, vaddr, size)) {
-			m_cpu_dirty            = true;
-			m_maybe_cpu_dirty      = false;
-			m_maybe_cpu_hash_valid = false;
-			m_track_begin          = m_track_end;
-		} else if (ImagePageRangesOverlap(address, this->size, vaddr, size)) {
-			constexpr uint64_t page_mask = 4096 - 1;
-			if (vaddr + size <= address) {
-				const auto next_page = (address + page_mask) & ~page_mask;
-				m_track_begin        = std::min(m_track_end, std::max(m_track_begin, next_page));
-			} else if (vaddr >= address + this->size) {
-				const auto page = (address + this->size) & ~page_mask;
-				m_track_end     = std::max(m_track_begin, std::min(m_track_end, page));
-			}
-			m_maybe_cpu_dirty = m_track_begin == m_track_end;
+		if (ImageRangeOverlaps(info.data.address, info.data.size, vaddr, size)) {
+			m_cpu_dirty       = true;
+			m_maybe_cpu_dirty = false;
+			m_maybe_hash_valid = false;
+		} else if (ImagePageRangesOverlap(info.data.address, info.data.size, vaddr, size)) {
+			m_maybe_cpu_dirty = true;
 		}
 	}
 
@@ -52,117 +96,93 @@ struct Image final: ImageInfo {
 	[[nodiscard]] bool IsDefinitelyCpuDirty() const { return m_cpu_dirty; }
 	[[nodiscard]] bool IsMaybeCpuDirty() const { return m_maybe_cpu_dirty; }
 	[[nodiscard]] bool NeedsMaybeCpuHash() const {
-		return m_maybe_cpu_dirty && !m_maybe_cpu_hash_valid;
-	}
-	[[nodiscard]] bool IsCpuTrackingComplete() const {
-		return m_track_begin == address && m_track_end == address + size;
+		return m_maybe_cpu_dirty && !m_maybe_hash_valid;
 	}
 	void SetMaybeCpuHash(uint64_t hash) {
 		if (!NeedsMaybeCpuHash()) {
-			EXIT("sampled image cannot initialize maybe-dirty hash\n");
+			EXIT("image cannot initialize maybe-dirty hash\n");
 		}
-		m_maybe_cpu_hash       = hash;
-		m_maybe_cpu_hash_valid = true;
+		m_maybe_cpu_hash = hash;
+		m_maybe_hash_valid = true;
 	}
 	[[nodiscard]] bool ResolveMaybeCpuHash(uint64_t hash) {
-		if (!m_maybe_cpu_dirty || !m_maybe_cpu_hash_valid || m_cpu_dirty) {
-			EXIT("sampled image cannot resolve maybe-dirty hash\n");
-		}
-		m_maybe_cpu_dirty      = false;
-		m_maybe_cpu_hash_valid = false;
-		m_cpu_dirty            = hash != m_maybe_cpu_hash;
-		if (!m_cpu_dirty) {
-			m_track_begin = address;
-			m_track_end   = address + size;
+		if (!m_maybe_cpu_dirty || !m_maybe_hash_valid || m_cpu_dirty) {
+			EXIT("image cannot resolve maybe-dirty hash\n");
 		}
+		m_maybe_cpu_dirty = false;
+		m_maybe_hash_valid = false;
+		m_cpu_dirty |= hash != m_maybe_cpu_hash;
 		return m_cpu_dirty;
 	}
 
 	void RefreshComplete() {
 		if (!IsCpuDirty()) {
-			EXIT("clean sampled image cannot complete a refresh\n");
+			EXIT("clean image cannot complete a refresh\n");
 		}
-		m_cpu_dirty            = false;
-		m_maybe_cpu_dirty      = false;
-		m_maybe_cpu_hash_valid = false;
-		m_track_begin          = address;
-		m_track_end            = address + size;
+		m_cpu_dirty        = false;
+		m_maybe_cpu_dirty  = false;
+		m_maybe_hash_valid = false;
 	}
 
+	[[nodiscard]] bool IsGpuModified() const noexcept { return m_gpu_modified; }
+	void MarkGpuModified() noexcept { m_gpu_modified = true; }
+	void ClearGpuModified() noexcept { m_gpu_modified = false; }
+
+	[[nodiscard]] bool IsBufferModified() const noexcept { return m_buffer_modified; }
+	void MarkBufferModified() noexcept { m_buffer_modified = true; }
+	void ClearBufferModified() noexcept { m_buffer_modified = false; }
+
+	[[nodiscard]] bool Overlaps(uint64_t address, uint64_t size, bool pages = false) const noexcept {
+		return pages ? ImagePageRangesOverlap(info.data.address, info.data.size, address, size)
+		             : ImageRangeOverlaps(info.data.address, info.data.size, address, size);
+	}
+	[[nodiscard]] bool GpuOverlaps(uint64_t address, uint64_t size) const noexcept {
+		return IsGpuModified() && Overlaps(address, size);
+	}
+	[[nodiscard]] bool SafeToDownload() const noexcept {
+		return IsGpuModified() && !IsBufferModified() && !IsCpuDirty();
+	}
+	[[nodiscard]] uint64_t AccountedSize() const noexcept {
+		return backing.image == nullptr ? 0 : (info.data.size + 1023) & ~uint64_t {1023};
+	}
+	[[nodiscard]] uint64_t HashGuestEdges() const;
+
+	ImageInfo            info;
+	VulkanImage          backing;
+	ImageViewCache       views;
+	ImageUsage           usage;
+	ImageBinding         binding;
+	bool                 registered          = false;
+	ImageId              depth_id {};
+	uint64_t             tick_accessed_last = 0;
+	size_t               lru_id = 0;
+
 private:
-	bool     m_cpu_dirty            = false;
-	bool     m_maybe_cpu_dirty      = false;
-	bool     m_maybe_cpu_hash_valid = false;
-	uint64_t m_track_begin          = 0;
-	uint64_t m_track_end            = 0;
-	uint64_t m_maybe_cpu_hash       = 0;
+	friend struct ImageTestAccess;
+
+	[[nodiscard]] static vk::ImageAspectFlags FullAspectMask(vk::Format format) noexcept;
+	[[nodiscard]] static uint32_t CopyRows(uint64_t row_size, uint32_t rows,
+	                                       uint64_t capacity) noexcept;
+	[[nodiscard]] static std::pair<uint32_t, uint32_t>
+	SanitizeCopyLayers(const Image& source, const Image& destination, uint32_t depth);
+
+	GraphicContext*   m_graphics  = nullptr;
+	CommandScheduler* m_scheduler = nullptr;
+	uint64_t        m_maybe_cpu_hash = 0;
+	bool            m_cpu_dirty = false;
+	bool            m_maybe_cpu_dirty = false;
+	bool            m_maybe_hash_valid = false;
+	bool            m_gpu_modified = false;
+	bool            m_buffer_modified = false;
 };
 
 namespace ImageOps {
 
-[[nodiscard]] GpuTextureVulkanImage* CreateTexture(const ImageInfo& info,
-                                                   bool storage, vk::ComponentMapping& components);
-void CreateTextureViews(GpuTextureVulkanImage& image,
-                        const ImageInfo& info, bool storage, vk::ComponentMapping components);
-
-[[nodiscard]] RenderTextureVulkanImage* CreateRenderTarget(
-                                                           const RenderTargetInfo& info);
-[[nodiscard]] uint32_t                  RenderTargetTransferFormat(uint32_t bytes_per_element);
-void UploadRenderTargetLayers(RenderTextureVulkanImage& image,
-                              const RenderTargetInfo& info, uint32_t base_layer,
-                              uint32_t layer_count, bool refresh);
-void UploadRenderTarget(RenderTextureVulkanImage& image,
-                        const RenderTargetInfo& info, bool refresh);
-
-[[nodiscard]] DepthStencilVulkanImage* CreateDepthTarget(
-                                                         const DepthTargetInfo& info);
-
-void ValidateVideoOut(const VideoOutInfo& info);
-[[nodiscard]] VideoOutVulkanImage* CreateVideoOut(
-                                                  const VideoOutInfo& info);
-void                               SwapVideoOutBgra16(void* data, uint64_t size);
-void UploadVideoOut(VideoOutVulkanImage& image, const VideoOutInfo& info,
-                    bool refresh);
-
-[[nodiscard]] GpuTextureVulkanImage* CreateDummyTexture(bool uint_format,
-                                                        bool image_3d, bool storage);
-
-void Destroy(VulkanImage& image);
+void                   Validate(const ImageInfo& info);
+[[nodiscard]] uint32_t RenderTargetTransferFormat(uint32_t bytes_per_element);
 
 } // namespace ImageOps
 
-struct ImageRetirementRange {
-	uint64_t address = 0;
-	uint64_t size    = 0;
-	bool     retire  = false;
-};
-
-struct ImageRetirementConflict {
-	size_t retired  = SIZE_MAX;
-	size_t retained = SIZE_MAX;
-
-	[[nodiscard]] bool Exists() const { return retired != SIZE_MAX; }
-};
-
-[[nodiscard]] inline ImageRetirementConflict
-FindImageRetirementConflict(std::span<const ImageRetirementRange> ranges) {
-	for (size_t retired = 0; retired < ranges.size(); retired++) {
-		if (!ranges[retired].retire) {
-			continue;
-		}
-		for (size_t retained = 0; retained < ranges.size(); retained++) {
-			if (ranges[retained].retire) {
-				continue;
-			}
-			if (ImageRangeOverlaps(ranges[retired].address, ranges[retired].size,
-			                       ranges[retained].address, ranges[retained].size)) {
-				return {retired, retained};
-			}
-		}
-	}
-	return {};
-}
-
 } // namespace Libs::Graphics
 
 #endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_IMAGE_H_

src/graphics/host_gpu/renderer/imageView.cpp

@@ -1,9 +1,8 @@
 #include "graphics/host_gpu/renderer/imageView.h"
 
 #include "common/assert.h"
-#include "graphics/host_gpu/objects/textureCommon.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/renderer/textureCache.h"
+#include "graphics/host_gpu/graphicContext.h"
+#include "graphics/host_gpu/renderer/image.h"
 
 #include <mutex>
 
@@ -11,62 +10,297 @@ namespace Libs::Graphics {
 
 namespace {
 
-void CreateView(VulkanImage& image, int view_index,
-                vk::ImageViewType view_type, vk::ImageAspectFlags aspect_mask,
-                vk::ComponentMapping components, uint32_t base_array_layer, uint32_t base_mip_level,
-                uint32_t layer_count, uint32_t level_count,
-                vk::Format          view_format = vk::Format::eUndefined,
-	             vk::ImageUsageFlags view_usage  = {}) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	if (view_index < 0 || view_index >= VulkanImage::VIEW_MAX ||
-	    image.image_view[view_index] != nullptr) {
-		EXIT("invalid image-view creation target: image=%p index=%d current_view=%d\n",
-		     static_cast<const void*>(&image), view_index,
-		     view_index >= 0 && view_index < VulkanImage::VIEW_MAX &&
-		         image.image_view[view_index] != nullptr);
-	}
-
-	vk::ImageViewUsageCreateInfo usage_info {};
-	usage_info.sType = vk::StructureType::eImageViewUsageCreateInfo;
-	usage_info.usage = view_usage;
-
-	vk::ImageViewCreateInfo create_info {};
-	create_info.sType      = vk::StructureType::eImageViewCreateInfo;
-	create_info.pNext      = view_usage ? &usage_info : nullptr;
-	create_info.image      = image.image;
-	create_info.viewType   = view_type;
-	create_info.format     = view_format != vk::Format::eUndefined ? view_format : image.format;
-	create_info.components = components;
-	create_info.subresourceRange.aspectMask     = aspect_mask;
-	create_info.subresourceRange.baseArrayLayer = base_array_layer;
-	create_info.subresourceRange.baseMipLevel   = base_mip_level;
-	create_info.subresourceRange.layerCount     = layer_count;
-	create_info.subresourceRange.levelCount     = level_count;
-
-	const auto result =
-	    graphics.device.createImageView(&create_info, nullptr, &image.image_view[view_index]);
-	if (result != vk::Result::eSuccess || image.image_view[view_index] == nullptr) {
-		EXIT("failed to create image view: result=%d image_format=%d view_format=%d index=%d\n",
-		     static_cast<int>(result), static_cast<int>(image.format),
-		     static_cast<int>(create_info.format), view_index);
+[[nodiscard]] bool IsComponentSwizzle(vk::ComponentSwizzle swizzle) {
+	switch (swizzle) {
+		case vk::ComponentSwizzle::eIdentity:
+		case vk::ComponentSwizzle::eZero:
+		case vk::ComponentSwizzle::eOne:
+		case vk::ComponentSwizzle::eR:
+		case vk::ComponentSwizzle::eG:
+		case vk::ComponentSwizzle::eB:
+		case vk::ComponentSwizzle::eA: return true;
+		default: return false;
 	}
 }
 
-void CreateRenderTargetView(VulkanImage& image, int index,
-                            vk::ComponentSwizzle r, vk::ComponentSwizzle g, vk::ComponentSwizzle b,
-                            vk::ComponentSwizzle a, vk::ImageViewType type = vk::ImageViewType::e2D,
-                            vk::Format          view_format = vk::Format::eUndefined,
-                            vk::ImageUsageFlags view_usage = {}, uint32_t level_count = 0) {
-	const auto layer_count = type == vk::ImageViewType::e2DArray ? image.layers : 1u;
-	CreateView(image, index, type, vk::ImageAspectFlagBits::eColor, {r, g, b, a}, 0, 0,
-	           layer_count, level_count == 0 ? image.mip_levels : level_count, view_format,
-	           view_usage);
+[[nodiscard]] bool IsCompatibleViewFormat(vk::Format image_format, vk::Format view_format) {
+	return ImageViewOps::FormatsCompatible(image_format, view_format);
+}
+
+[[nodiscard]] bool IsStencilViewFormat(vk::Format format) {
+	switch (format) {
+		case vk::Format::eS8Uint:
+		case vk::Format::eR8Uint:
+		case vk::Format::eR8Unorm: return true;
+		default: return false;
+	}
+}
+
+[[nodiscard]] bool IsDepthViewFormat(vk::Format format) {
+	switch (format) {
+		case vk::Format::eD16Unorm:
+		case vk::Format::eR16Unorm:
+		case vk::Format::eD32Sfloat:
+		case vk::Format::eR32Sfloat:
+		case vk::Format::eR32Uint: return true;
+		default: return false;
+	}
+}
+
+[[nodiscard]] bool IsValidViewType(const VulkanImage& image, const ImageViewInfo& info) {
+	switch (image.image_type) {
+		case vk::ImageType::e1D:
+			if (info.type != vk::ImageViewType::e1D && info.type != vk::ImageViewType::e1DArray) {
+				return false;
+			}
+			return info.type != vk::ImageViewType::e1D || info.layer_count == 1;
+		case vk::ImageType::e2D:
+			switch (info.type) {
+				case vk::ImageViewType::e2D: return info.layer_count == 1;
+				case vk::ImageViewType::e2DArray: return true;
+				case vk::ImageViewType::eCube:
+					return static_cast<bool>(image.flags &
+					                         vk::ImageCreateFlagBits::eCubeCompatible) &&
+					       info.base_layer % 6 == 0 && info.layer_count == 6;
+				case vk::ImageViewType::eCubeArray:
+					return static_cast<bool>(image.flags &
+					                         vk::ImageCreateFlagBits::eCubeCompatible) &&
+					       info.base_layer % 6 == 0 && info.layer_count % 6 == 0;
+				default: return false;
+			}
+		case vk::ImageType::e3D:
+			switch (info.type) {
+				case vk::ImageViewType::e3D:
+					return info.base_layer == 0 && info.layer_count == 1;
+				case vk::ImageViewType::e2D:
+					return static_cast<bool>(
+					           image.flags & vk::ImageCreateFlagBits::e2DArrayCompatible) &&
+					       info.level_count == 1 && info.layer_count == 1;
+				case vk::ImageViewType::e2DArray:
+					return static_cast<bool>(
+					           image.flags & vk::ImageCreateFlagBits::e2DArrayCompatible) &&
+					       info.level_count == 1;
+				default: return false;
+			}
+		default: return false;
+	}
+}
+
+[[nodiscard]] bool IsValidAspect(const VulkanImage& image, vk::ImageAspectFlags aspect) {
+	const auto depth_format = DepthAspectTransferFormat(image.format);
+	if (depth_format == vk::Format::eUndefined) {
+		return aspect == vk::ImageAspectFlagBits::eColor;
+	}
+	const auto supported = ImageViewOps::DepthAspectMask(image.format);
+	return static_cast<bool>(aspect) && !(aspect & ~supported);
 }
 
 } // namespace
 
 namespace ImageViewOps {
 
+namespace {
+
+enum CompatibilityClass : uint32_t {
+	None    = 0,
+	Bit8    = 1u << 0,
+	Bit16   = 1u << 1,
+	Bit24   = 1u << 2,
+	Bit32   = 1u << 3,
+	Bit48   = 1u << 4,
+	Bit64   = 1u << 5,
+	Bit96   = 1u << 6,
+	Bit128  = 1u << 7,
+	Bit192  = 1u << 8,
+	Bit256  = 1u << 9,
+	Bc1Rgb  = 1u << 10,
+	Bc1Rgba = 1u << 11,
+	Bc2     = 1u << 12,
+	Bc3     = 1u << 13,
+	Bc4     = 1u << 14,
+	Bc5     = 1u << 15,
+	Bc6h    = 1u << 16,
+	Bc7     = 1u << 17,
+	D16     = 1u << 18,
+	D16S8   = 1u << 19,
+	D24     = 1u << 20,
+	D24S8   = 1u << 21,
+	D32     = 1u << 22,
+	D32S8   = 1u << 23,
+	S8      = 1u << 24,
+};
+
+[[nodiscard]] uint32_t FormatClass(vk::Format format) noexcept {
+	switch (format) {
+		case vk::Format::eR4G4UnormPack8:
+		case vk::Format::eR8Sint:
+		case vk::Format::eR8Snorm:
+		case vk::Format::eR8Srgb:
+		case vk::Format::eR8Sscaled:
+		case vk::Format::eR8Uint:
+		case vk::Format::eR8Unorm:
+		case vk::Format::eR8Uscaled: return Bit8;
+
+		case vk::Format::eA1R5G5B5UnormPack16:
+		case vk::Format::eA4B4G4R4UnormPack16:
+		case vk::Format::eA4R4G4B4UnormPack16:
+		case vk::Format::eB4G4R4A4UnormPack16:
+		case vk::Format::eB5G5R5A1UnormPack16:
+		case vk::Format::eB5G6R5UnormPack16:
+		case vk::Format::eR10X6UnormPack16:
+		case vk::Format::eR12X4UnormPack16:
+		case vk::Format::eR16Sfloat:
+		case vk::Format::eR16Sint:
+		case vk::Format::eR16Snorm:
+		case vk::Format::eR16Sscaled:
+		case vk::Format::eR16Uint:
+		case vk::Format::eR16Unorm:
+		case vk::Format::eR16Uscaled:
+		case vk::Format::eR4G4B4A4UnormPack16:
+		case vk::Format::eR5G5B5A1UnormPack16:
+		case vk::Format::eR5G6B5UnormPack16:
+		case vk::Format::eR8G8Sint:
+		case vk::Format::eR8G8Snorm:
+		case vk::Format::eR8G8Srgb:
+		case vk::Format::eR8G8Sscaled:
+		case vk::Format::eR8G8Uint:
+		case vk::Format::eR8G8Unorm:
+		case vk::Format::eR8G8Uscaled: return Bit16;
+
+		case vk::Format::eB8G8R8Sint:
+		case vk::Format::eB8G8R8Snorm:
+		case vk::Format::eB8G8R8Srgb:
+		case vk::Format::eB8G8R8Sscaled:
+		case vk::Format::eB8G8R8Uint:
+		case vk::Format::eB8G8R8Unorm:
+		case vk::Format::eB8G8R8Uscaled:
+		case vk::Format::eR8G8B8Sint:
+		case vk::Format::eR8G8B8Snorm:
+		case vk::Format::eR8G8B8Srgb:
+		case vk::Format::eR8G8B8Sscaled:
+		case vk::Format::eR8G8B8Uint:
+		case vk::Format::eR8G8B8Unorm:
+		case vk::Format::eR8G8B8Uscaled: return Bit24;
+
+		case vk::Format::eA2B10G10R10SintPack32:
+		case vk::Format::eA2B10G10R10SnormPack32:
+		case vk::Format::eA2B10G10R10SscaledPack32:
+		case vk::Format::eA2B10G10R10UintPack32:
+		case vk::Format::eA2B10G10R10UnormPack32:
+		case vk::Format::eA2B10G10R10UscaledPack32:
+		case vk::Format::eA2R10G10B10SintPack32:
+		case vk::Format::eA2R10G10B10SnormPack32:
+		case vk::Format::eA2R10G10B10SscaledPack32:
+		case vk::Format::eA2R10G10B10UintPack32:
+		case vk::Format::eA2R10G10B10UnormPack32:
+		case vk::Format::eA2R10G10B10UscaledPack32:
+		case vk::Format::eA8B8G8R8SintPack32:
+		case vk::Format::eA8B8G8R8SnormPack32:
+		case vk::Format::eA8B8G8R8SrgbPack32:
+		case vk::Format::eA8B8G8R8SscaledPack32:
+		case vk::Format::eA8B8G8R8UintPack32:
+		case vk::Format::eA8B8G8R8UnormPack32:
+		case vk::Format::eA8B8G8R8UscaledPack32:
+		case vk::Format::eB10G11R11UfloatPack32:
+		case vk::Format::eB8G8R8A8Sint:
+		case vk::Format::eB8G8R8A8Snorm:
+		case vk::Format::eB8G8R8A8Srgb:
+		case vk::Format::eB8G8R8A8Sscaled:
+		case vk::Format::eB8G8R8A8Uint:
+		case vk::Format::eB8G8R8A8Unorm:
+		case vk::Format::eB8G8R8A8Uscaled:
+		case vk::Format::eE5B9G9R9UfloatPack32:
+		case vk::Format::eR10X6G10X6Unorm2Pack16:
+		case vk::Format::eR12X4G12X4Unorm2Pack16:
+		case vk::Format::eR16G16Sfloat:
+		case vk::Format::eR16G16Sint:
+		case vk::Format::eR16G16Snorm:
+		case vk::Format::eR16G16Sscaled:
+		case vk::Format::eR16G16Uint:
+		case vk::Format::eR16G16Unorm:
+		case vk::Format::eR16G16Uscaled:
+		case vk::Format::eR32Sfloat:
+		case vk::Format::eR32Sint:
+		case vk::Format::eR32Uint:
+		case vk::Format::eR8G8B8A8Sint:
+		case vk::Format::eR8G8B8A8Snorm:
+		case vk::Format::eR8G8B8A8Srgb:
+		case vk::Format::eR8G8B8A8Sscaled:
+		case vk::Format::eR8G8B8A8Uint:
+		case vk::Format::eR8G8B8A8Unorm:
+		case vk::Format::eR8G8B8A8Uscaled: return Bit32;
+
+		case vk::Format::eR16G16B16Sfloat:
+		case vk::Format::eR16G16B16Sint:
+		case vk::Format::eR16G16B16Snorm:
+		case vk::Format::eR16G16B16Sscaled:
+		case vk::Format::eR16G16B16Uint:
+		case vk::Format::eR16G16B16Unorm:
+		case vk::Format::eR16G16B16Uscaled: return Bit48;
+
+		case vk::Format::eR16G16B16A16Sfloat:
+		case vk::Format::eR16G16B16A16Sint:
+		case vk::Format::eR16G16B16A16Snorm:
+		case vk::Format::eR16G16B16A16Sscaled:
+		case vk::Format::eR16G16B16A16Uint:
+		case vk::Format::eR16G16B16A16Unorm:
+		case vk::Format::eR16G16B16A16Uscaled:
+		case vk::Format::eR32G32Sfloat:
+		case vk::Format::eR32G32Sint:
+		case vk::Format::eR32G32Uint:
+		case vk::Format::eR64Sfloat:
+		case vk::Format::eR64Sint:
+		case vk::Format::eR64Uint: return Bit64;
+
+		case vk::Format::eR32G32B32Sfloat:
+		case vk::Format::eR32G32B32Sint:
+		case vk::Format::eR32G32B32Uint: return Bit96;
+
+		case vk::Format::eR32G32B32A32Sfloat:
+		case vk::Format::eR32G32B32A32Sint:
+		case vk::Format::eR32G32B32A32Uint:
+		case vk::Format::eR64G64Sfloat:
+		case vk::Format::eR64G64Sint:
+		case vk::Format::eR64G64Uint: return Bit128;
+
+		case vk::Format::eR64G64B64Sfloat:
+		case vk::Format::eR64G64B64Sint:
+		case vk::Format::eR64G64B64Uint: return Bit192;
+
+		case vk::Format::eR64G64B64A64Sfloat:
+		case vk::Format::eR64G64B64A64Sint:
+		case vk::Format::eR64G64B64A64Uint: return Bit256;
+
+		case vk::Format::eBc1RgbSrgbBlock:
+		case vk::Format::eBc1RgbUnormBlock: return Bc1Rgb | Bit64;
+		case vk::Format::eBc1RgbaSrgbBlock:
+		case vk::Format::eBc1RgbaUnormBlock: return Bc1Rgba | Bit64;
+		case vk::Format::eBc2SrgbBlock:
+		case vk::Format::eBc2UnormBlock: return Bc2 | Bit128;
+		case vk::Format::eBc3SrgbBlock:
+		case vk::Format::eBc3UnormBlock: return Bc3 | Bit128;
+		case vk::Format::eBc4SnormBlock:
+		case vk::Format::eBc4UnormBlock: return Bc4 | Bit64;
+		case vk::Format::eBc5SnormBlock:
+		case vk::Format::eBc5UnormBlock: return Bc5 | Bit128;
+		case vk::Format::eBc6HSfloatBlock:
+		case vk::Format::eBc6HUfloatBlock: return Bc6h | Bit128;
+		case vk::Format::eBc7SrgbBlock:
+		case vk::Format::eBc7UnormBlock: return Bc7 | Bit128;
+
+		case vk::Format::eD16Unorm: return D16;
+		case vk::Format::eD16UnormS8Uint: return D16S8;
+		case vk::Format::eX8D24UnormPack32: return D24;
+		case vk::Format::eD24UnormS8Uint: return D24S8;
+		case vk::Format::eD32Sfloat: return D32;
+		case vk::Format::eD32SfloatS8Uint: return D32S8;
+		case vk::Format::eS8Uint: return S8;
+		default: return None;
+	}
+}
+
+} // namespace
+
 vk::ImageAspectFlags DepthAspectMask(vk::Format format) {
 	switch (format) {
 		case vk::Format::eD16Unorm:
@@ -79,314 +313,104 @@ vk::ImageAspectFlags DepthAspectMask(vk::Format format) {
 	}
 }
 
-bool FormatSupportsStorage(vk::Format format) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	const auto properties = graphics.GetFormatProperties(format);
-	return static_cast<bool>(properties.optimalTilingFeatures &
-	                         vk::FormatFeatureFlagBits::eStorageImage);
-}
-
-void CreateRenderTargetViews(RenderTextureVulkanImage& image) {
-	CreateRenderTargetView(image, VulkanImage::VIEW_DEFAULT,
-	                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-	                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity);
-	if (image.layers > 1) {
-		CreateRenderTargetView(image, VulkanImage::VIEW_DEFAULT_ARRAY,
-		                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-		                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-		                       vk::ImageViewType::e2DArray);
-	}
-	if (image.samples == 1 && FormatSupportsStorage(image.format)) {
-		CreateRenderTargetView(image, VulkanImage::VIEW_STORAGE,
-		                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-		                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-		                       vk::ImageViewType::e2D, vk::Format::eUndefined,
-		                       vk::ImageUsageFlags {}, 1);
-		if (image.layers > 1) {
-			CreateRenderTargetView(image, VulkanImage::VIEW_STORAGE_ARRAY,
-			                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-			                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-			                       vk::ImageViewType::e2DArray, vk::Format::eUndefined,
-			                       vk::ImageUsageFlags {}, 1);
-		}
-	}
-}
-
-void CreateDepthViews(DepthStencilVulkanImage& image) {
-	CreateView(image, VulkanImage::VIEW_DEFAULT, vk::ImageViewType::e2D,
-	           DepthAspectMask(image.format),
-	           {vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-	            vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity},
-	           0, 0, 1, 1);
-}
-
-void CreateVideoOutViews(VideoOutVulkanImage& image) {
-	CreateRenderTargetView(image, VulkanImage::VIEW_DEFAULT,
-	                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-	                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity);
-	if ((image.format == vk::Format::eR8G8B8A8Srgb || image.format == vk::Format::eB8G8R8A8Srgb) &&
-	    FormatSupportsStorage(vk::Format::eR8G8B8A8Uint)) {
-		CreateRenderTargetView(image, VulkanImage::VIEW_STORAGE,
-		                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-		                       vk::ComponentSwizzle::eIdentity, vk::ComponentSwizzle::eIdentity,
-		                       vk::ImageViewType::e2D, vk::Format::eR8G8B8A8Uint,
-		                       vk::ImageUsageFlagBits::eStorage, 1);
-	}
-}
-
-void DestroyViews(VulkanImage& image) {
-	auto& graphics = GetRenderContext().GetGraphics();
-	for (auto& cached: image.view_cache.views) {
-		if (cached.view != nullptr) {
-			graphics.device.destroyImageView(cached.view, nullptr);
-			cached.view = nullptr;
-		}
-	}
-	image.view_cache.views.clear();
-	for (auto& view: image.image_view) {
-		if (view != nullptr) {
-			graphics.device.destroyImageView(view, nullptr);
-			view = nullptr;
-		}
+bool FormatsCompatible(vk::Format base, vk::Format view) noexcept {
+	if (base == view) {
+		return true;
 	}
+	const auto base_class = FormatClass(base);
+	const auto view_class = FormatClass(view);
+	return view_class != None && (base_class & view_class) == view_class;
 }
 
 } // namespace ImageViewOps
 
-vk::ImageView TextureCache::GetRenderTargetAttachmentView(RenderTextureVulkanImage& image,
-                                                          vk::Format format, uint32_t level,
-                                                          uint32_t base_layer,
-                                                          uint32_t layer_count) {
-	if (image.format == vk::Format::eUndefined || level >= image.mip_levels || level >= 16 ||
-	    layer_count == 0 || base_layer >= image.layers || layer_count > image.layers - base_layer) {
-		EXIT("TextureCache: invalid render-target attachment view, image=%p format=%d"
-		     " level=%u image_levels=%u base_layer=%u layer_count=%u image_layers=%u\n",
-		     static_cast<const void*>(&image), static_cast<int>(format), level, image.mip_levels,
-		     base_layer, layer_count, image.layers);
+vk::ImageView Image::FindView(const ImageViewInfo& view_info) {
+	const auto& image = backing;
+	auto        normalized = view_info;
+	const bool  is_storage =
+	    static_cast<bool>(normalized.usage & vk::ImageUsageFlagBits::eStorage);
+	normalized.aspect = FullAspectMask(image.format);
+	if (normalized.aspect & vk::ImageAspectFlagBits::eDepth &&
+	    IsDepthViewFormat(normalized.format)) {
+		normalized.format = image.format;
+		normalized.aspect = vk::ImageAspectFlagBits::eDepth;
 	}
-	if (format != image.format && !IsRgba8SrgbReinterpretation(image.format, format)) {
-		EXIT("TextureCache: incompatible render-target attachment view, image_format=%d"
-		     " view_format=%d level=%u\n",
-		     static_cast<int>(image.format), static_cast<int>(format), level);
+	if (normalized.aspect & vk::ImageAspectFlagBits::eStencil &&
+	    IsStencilViewFormat(normalized.format)) {
+		normalized.format = image.format;
+		normalized.aspect = vk::ImageAspectFlagBits::eStencil;
+	}
+	normalized.usage =
+	    is_storage ? vk::ImageUsageFlagBits::eStorage : vk::ImageUsageFlags {};
+	const bool format_compatible = normalized.format != vk::Format::eUndefined &&
+	                               IsCompatibleViewFormat(image.format, normalized.format);
+	const bool slice_view = image.image_type == vk::ImageType::e3D &&
+	                        (normalized.type == vk::ImageViewType::e2D ||
+	                         normalized.type == vk::ImageViewType::e2DArray);
+	const bool levels_valid = normalized.level_count != 0 &&
+	                          normalized.base_level < image.mip_levels &&
+	                          normalized.level_count <= image.mip_levels - normalized.base_level;
+	const auto view_layers = slice_view && levels_valid
+	                             ? std::max(image.extent.depth >> normalized.base_level, 1u)
+	                             : image.layers;
+	const bool ranges_valid = levels_valid &&
+	                          normalized.layer_count != 0 && normalized.base_layer < view_layers &&
+	                          normalized.layer_count <= view_layers - normalized.base_layer;
+	const bool mapping_valid =
+	    IsComponentSwizzle(normalized.mapping.r) && IsComponentSwizzle(normalized.mapping.g) &&
+	    IsComponentSwizzle(normalized.mapping.b) && IsComponentSwizzle(normalized.mapping.a);
+	if (image.image == nullptr || !format_compatible || !ranges_valid || !mapping_valid ||
+	    !IsValidViewType(image, normalized) ||
+	    !IsValidAspect(image, normalized.aspect)) {
+		EXIT("invalid image view: image_format=%d view_format=%d type=%d aspect=0x%x "
+		     "mip=%u+%u layer=%u+%u usage=0x%x image_levels=%u image_layers=%u\n",
+		     static_cast<int>(image.format), static_cast<int>(normalized.format),
+		     static_cast<int>(normalized.type),
+		     static_cast<vk::ImageAspectFlags::MaskType>(normalized.aspect), normalized.base_level,
+		     normalized.level_count, normalized.base_layer, normalized.layer_count,
+		     static_cast<vk::ImageUsageFlags::MaskType>(normalized.usage), image.mip_levels,
+		     image.layers);
 	}
 
-	return GetImageView(
-	    image, {format, layer_count == 1 ? vk::ImageViewType::e2D : vk::ImageViewType::e2DArray,
-	            vk::ImageAspectFlagBits::eColor, level, 1, base_layer, layer_count,
-	            DstSel(4, 5, 6, 7), vk::ImageUsageFlagBits::eColorAttachment});
-}
-
-vk::ImageView TextureCache::GetDepthTargetAttachmentView(DepthStencilVulkanImage& image,
-                                                         uint32_t                 base_layer,
-                                                         uint32_t                 layer_count) {
-	if (layer_count == 0 || base_layer >= image.layers || layer_count > image.layers - base_layer) {
-		EXIT("TextureCache: invalid depth-target attachment view, image=%p base_layer=%u "
-		     "layer_count=%u image_layers=%u\n",
-		     static_cast<const void*>(&image), base_layer, layer_count, image.layers);
-	}
-	return GetImageView(image,
-	                    {image.format,
-	                     layer_count == 1 ? vk::ImageViewType::e2D : vk::ImageViewType::e2DArray,
-	                     ImageViewOps::DepthAspectMask(image.format), 0, 1, base_layer, layer_count,
-	                     DstSel(4, 5, 6, 7), vk::ImageUsageFlagBits::eDepthStencilAttachment});
-}
-
-vk::ImageView TextureCache::GetImageView(VulkanImage& image, const ImageViewInfo& info) {
-	const bool supported_type  = info.type == vk::ImageViewType::e2D ||
-	                             info.type == vk::ImageViewType::e2DArray ||
-	                             info.type == vk::ImageViewType::e3D;
-	const bool supported_usage = info.usage == vk::ImageUsageFlagBits::eSampled ||
-	                             info.usage == vk::ImageUsageFlagBits::eStorage ||
-	                             info.usage == vk::ImageUsageFlagBits::eColorAttachment ||
-	                             info.usage == vk::ImageUsageFlagBits::eDepthStencilAttachment;
-	const bool valid_shape =
-	    (info.type == vk::ImageViewType::e2D && info.layer_count == 1) ||
-	    info.type == vk::ImageViewType::e2DArray ||
-	    (info.type == vk::ImageViewType::e3D && info.base_layer == 0 && info.layer_count == 1);
-	if (info.format == vk::Format::eUndefined || !info.aspect || info.level_count == 0 ||
-	    info.base_level >= (image.mip_levels) ||
-	    info.level_count > image.mip_levels - info.base_level || info.layer_count == 0 ||
-	    info.base_layer >= image.layers || info.layer_count > image.layers - info.base_layer ||
-	    !supported_type || !valid_shape || !supported_usage) {
-		EXIT("TextureCache: invalid dynamic image view, image=%p format=%d aspect=0x%x"
-		     " swizzle=0x%03x mip=%u+%u layer=%u+%u type=%d usage=0x%x"
-		     " image_levels=%u image_layers=%u\n",
-		     static_cast<const void*>(&image), static_cast<int>(info.format),
-		     static_cast<vk::ImageAspectFlags::MaskType>(info.aspect), info.swizzle,
-		     info.base_level, info.level_count, info.base_layer, info.layer_count,
-		     static_cast<int>(info.type), static_cast<vk::ImageUsageFlags::MaskType>(info.usage),
-		     image.mip_levels, image.layers);
-	}
-
-	auto&           cache = image.view_cache;
-	std::lock_guard lock(cache.mutex);
-	for (const auto& cached: cache.views) {
-		if (cached.info == info) {
+	std::lock_guard lock(views.mutex);
+	for (const auto& cached: views.views) {
+		if (cached.info == normalized) {
 			return cached.view;
 		}
 	}
 
 	vk::ImageViewUsageCreateInfo usage {};
 	usage.sType = vk::StructureType::eImageViewUsageCreateInfo;
-	usage.usage = info.usage;
+	usage.usage = image.usage;
+	if (!is_storage) {
+		usage.usage &= ~vk::ImageUsageFlagBits::eStorage;
+	}
 	vk::ImageViewCreateInfo create {};
 	create.sType                           = vk::StructureType::eImageViewCreateInfo;
 	create.pNext                           = &usage;
 	create.image                           = image.image;
-	create.viewType                        = info.type;
-	create.format                          = info.format;
-	create.components                      = info.usage == vk::ImageUsageFlagBits::eSampled
-	                                             ? TextureGetComponentMapping(info.swizzle)
-	                                             : vk::ComponentMapping {};
-	create.subresourceRange.aspectMask     = info.aspect;
-	create.subresourceRange.baseMipLevel   = info.base_level;
-	create.subresourceRange.levelCount     = info.level_count;
-	create.subresourceRange.baseArrayLayer = info.base_layer;
-	create.subresourceRange.layerCount     = info.layer_count;
-	vk::ImageView view                     = nullptr;
-	const auto    result = m_graphics.device.createImageView(&create, nullptr, &view);
+	create.viewType                        = normalized.type;
+	create.format                          = normalized.format;
+	create.components                      = normalized.mapping;
+	create.subresourceRange.aspectMask     = normalized.aspect;
+	create.subresourceRange.baseMipLevel   = normalized.base_level;
+	create.subresourceRange.levelCount     = normalized.level_count;
+	create.subresourceRange.baseArrayLayer = normalized.base_layer;
+	create.subresourceRange.layerCount     = normalized.layer_count;
+
+	vk::ImageView view   = nullptr;
+	const auto    result = m_graphics->device.createImageView(&create, nullptr, &view);
 	if (result != vk::Result::eSuccess || view == nullptr) {
-		EXIT("TextureCache: failed to create dynamic image view, result=%d format=%d"
-		     " aspect=0x%x swizzle=0x%03x mip=%u+%u layer=%u+%u type=%d usage=0x%x\n",
-		     static_cast<int>(result), static_cast<int>(info.format),
-		     static_cast<vk::ImageAspectFlags::MaskType>(info.aspect), info.swizzle,
-		     info.base_level, info.level_count, info.base_layer, info.layer_count,
-		     static_cast<int>(info.type), static_cast<vk::ImageUsageFlags::MaskType>(info.usage));
+		EXIT("failed to create image view: result=%d image_format=%d view_format=%d type=%d "
+		     "aspect=0x%x mip=%u+%u layer=%u+%u usage=0x%x\n",
+		     static_cast<int>(result), static_cast<int>(image.format),
+		     static_cast<int>(view_info.format), static_cast<int>(view_info.type),
+		     static_cast<vk::ImageAspectFlags::MaskType>(view_info.aspect), view_info.base_level,
+		     view_info.level_count, view_info.base_layer, view_info.layer_count,
+		     static_cast<vk::ImageUsageFlags::MaskType>(view_info.usage));
 	}
-	cache.views.push_back({info, view});
+	views.views.push_back({normalized, view});
 	return view;
 }
 
-vk::ImageView TextureCache::GetDepthTargetSampledView(DepthStencilVulkanImage& image,
-                                                      vk::Format view_format, uint32_t swizzle,
-                                                      uint32_t base_level, uint32_t level_count,
-                                                      vk::ImageViewType type, uint32_t base_layer,
-                                                      uint32_t layer_count) {
-	if (view_format == vk::Format::eUndefined ||
-	    !IsSupportedSampledDepthView(image.format, view_format, swizzle)) {
-		EXIT("TextureCache: invalid sampled depth-target view, image=%p image_format=%d"
-		     " view_format=%d swizzle=0x%03x mip=%u+%u layer=%u+%u type=%d"
-		     " image_levels=%u image_layers=%u\n",
-		     static_cast<const void*>(&image), static_cast<int>(image.format),
-		     static_cast<int>(view_format), swizzle, base_level, level_count, base_layer,
-		     layer_count, static_cast<int>(type), image.mip_levels, image.layers);
-	}
-	return GetImageView(image, {image.format, type, vk::ImageAspectFlagBits::eDepth, base_level,
-	                            level_count, base_layer, layer_count, swizzle});
-}
-
-vk::ImageView TextureCache::GetSampledColorView(VulkanImage& image, vk::Format view_format,
-                                                uint32_t swizzle, uint32_t base_level,
-                                                uint32_t level_count, vk::ImageViewType type,
-                                                uint32_t base_layer, uint32_t layer_count) {
-	if (view_format == vk::Format::eUndefined || base_level >= 16 ||
-	    (type != vk::ImageViewType::e2D && type != vk::ImageViewType::e2DArray) ||
-	    !IsSupportedSampledColorView(image.format, view_format, swizzle)) {
-		EXIT("TextureCache: invalid sampled color view, image=%p swizzle=0x%03x"
-		     " view_format=%d mip=%u+%u layer=%u+%u type=%d image_levels=%u image_layers=%u\n",
-		     static_cast<const void*>(&image), swizzle, static_cast<int>(view_format), base_level,
-		     level_count, base_layer, layer_count, static_cast<int>(type), image.mip_levels,
-		     image.layers);
-	}
-	const auto precreated_view = type == vk::ImageViewType::e2DArray
-	                                 ? VulkanImage::VIEW_DEFAULT_ARRAY
-	                                 : VulkanImage::VIEW_DEFAULT;
-	const bool full_view = base_level == 0 && level_count == image.mip_levels && base_layer == 0 &&
-	                       layer_count == (type == vk::ImageViewType::e2DArray ? image.layers : 1u);
-	if (view_format == image.format && swizzle == DstSel(4, 5, 6, 7) && full_view &&
-	    image.image_view[precreated_view] != nullptr) {
-		return image.image_view[precreated_view];
-	}
-	return GetImageView(image, {view_format, type, vk::ImageAspectFlagBits::eColor, base_level,
-	                            level_count, base_layer, layer_count, swizzle});
-}
-
-vk::ImageView TextureCache::GetRenderTargetStorageView(RenderTextureVulkanImage& image,
-                                                       vk::Format view_format, uint32_t base_level,
-                                                       uint32_t level_count, vk::ImageViewType type,
-                                                       uint32_t base_layer, uint32_t layer_count) {
-	if (view_format == vk::Format::eUndefined ||
-	    (type != vk::ImageViewType::e2D && type != vk::ImageViewType::e2DArray)) {
-		EXIT("TextureCache: invalid render-target storage view, image=%p view_format=%d"
-		     " mip=%u+%u layer=%u+%u type=%d image_levels=%u image_layers=%u\n",
-		     static_cast<const void*>(&image), static_cast<int>(view_format), base_level,
-		     level_count, base_layer, layer_count, static_cast<int>(type), image.mip_levels,
-		     image.layers);
-	}
-	const bool exact      = view_format == image.format;
-	const bool compatible = view_format == BgraSrgbStorageViewFormat(image.format);
-	if (!exact && !compatible) {
-		EXIT("TextureCache: incompatible render-target storage view, image_format=%d"
-		     " view_format=%d base=%u count=%u\n",
-		     static_cast<int>(image.format), static_cast<int>(view_format), base_level,
-		     level_count);
-	}
-	if (exact) {
-		const auto index = type == vk::ImageViewType::e2DArray ? VulkanImage::VIEW_STORAGE_ARRAY
-		                                                       : VulkanImage::VIEW_STORAGE;
-		const bool full_view =
-		    base_level == 0 && level_count == 1 && base_layer == 0 &&
-		    layer_count == (type == vk::ImageViewType::e2DArray ? image.layers : 1u);
-		if (full_view && image.image_view[index] != nullptr) {
-			return image.image_view[index];
-		}
-	}
-
-	if (compatible && !ImageViewOps::FormatSupportsStorage(view_format)) {
-		EXIT("TextureCache: compatible render-target storage format lacks storage support,"
-		     " image_format=%d view_format=%d base=%u count=%u\n",
-		     static_cast<int>(image.format), static_cast<int>(view_format), base_level,
-		     level_count);
-	}
-	return GetImageView(image, {view_format, type, vk::ImageAspectFlagBits::eColor, base_level,
-	                            level_count, base_layer, layer_count, DstSel(4, 5, 6, 7),
-	                            vk::ImageUsageFlagBits::eStorage});
-}
-
-vk::ImageView TextureCache::GetStorageTextureSampledView(StorageTextureVulkanImage& image,
-                                                         const ImageInfo&           info) {
-	const auto shape = SelectStorageSampledViewShape(info.type, info.depth, image.layers);
-	if (image.image == nullptr || shape == StorageSampledViewShape::Unsupported ||
-	    info.base_array != 0 || info.levels != image.mip_levels || info.base_level >= info.levels ||
-	    info.view_levels == 0 || info.base_level + info.view_levels > info.levels) {
-		EXIT("TextureCache: invalid sampled view of storage texture, image=%p type=%u depth=%u"
-		     " base=%u levels=%u view_levels=%u image_levels=%u base_array=%u\n",
-		     static_cast<const void*>(&image), info.type, info.depth, info.base_level, info.levels,
-		     info.view_levels, image.mip_levels, info.base_array);
-	}
-	const auto view_format = TextureGetFormat(info.format);
-	if (view_format != image.format && !IsRgba8SrgbReinterpretation(image.format, view_format) &&
-	    !IsR32UintFloatReinterpretation(image.format, view_format)) {
-		EXIT("TextureCache: incompatible sampled view of storage texture, image_format=%d"
-		     " view_format=%d swizzle=0x%03x\n",
-		     static_cast<int>(image.format), static_cast<int>(view_format), info.swizzle);
-	}
-
-	vk::ImageViewType type = static_cast<vk::ImageViewType>(VK_IMAGE_VIEW_TYPE_MAX_ENUM);
-	switch (shape) {
-		case StorageSampledViewShape::Image2D: type = vk::ImageViewType::e2D; break;
-		case StorageSampledViewShape::Image2DArray: type = vk::ImageViewType::e2DArray; break;
-		case StorageSampledViewShape::Image3D: type = vk::ImageViewType::e3D; break;
-		case StorageSampledViewShape::Unsupported:
-			EXIT("TextureCache: unsupported sampled storage-image view shape\n");
-	}
-	const auto layer_count = shape == StorageSampledViewShape::Image2DArray ? info.depth : 1u;
-	return GetImageView(image, {view_format, type, vk::ImageAspectFlagBits::eColor, info.base_level,
-	                            info.view_levels, 0, layer_count, info.swizzle});
-}
-
-vk::ImageView TextureCache::GetStorageTextureStorageView(StorageTextureVulkanImage& image,
-                                                         uint32_t                   base_level) {
-	if (image.image == nullptr || base_level >= (image.mip_levels)) {
-		EXIT("TextureCache: invalid storage-texture mip view, image=%p level=%u levels=%u\n",
-		     static_cast<const void*>(&image), base_level, image.mip_levels);
-	}
-	if (base_level == 0) {
-		return image.image_view[VulkanImage::VIEW_DEFAULT];
-	}
-	return GetImageView(image, {image.format, vk::ImageViewType::e2D,
-	                            vk::ImageAspectFlagBits::eColor, base_level, 1, 0, 1,
-	                            DstSel(4, 5, 6, 7), vk::ImageUsageFlagBits::eStorage});
-}
-
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/imageView.h

@@ -2,91 +2,19 @@
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_IMAGEVIEW_H_
 
 #include "common/assert.h"
-#include "graphics/host_gpu/graphicContext.h"
 #include "graphics/host_gpu/renderer/imageInfo.h"
 #include "graphics/shader/recompiler/ShaderIR.h"
 #include "graphics/shader/shader.h"
 
 namespace Libs::Graphics {
 
-[[nodiscard]] inline bool IsSupportedStorageSwizzle(uint32_t format, uint32_t swizzle) noexcept {
-	const bool single_channel =
-	    format == Prospero::GpuEnumValue(Prospero::BufferFormat::k8UNorm) ||
-	    format == Prospero::GpuEnumValue(Prospero::BufferFormat::k8UInt) ||
-	    format == Prospero::GpuEnumValue(Prospero::BufferFormat::k16UInt) ||
-	    format == Prospero::GpuEnumValue(Prospero::BufferFormat::k32UInt) ||
-	    format == Prospero::GpuEnumValue(Prospero::BufferFormat::k16Float) ||
-	    format == Prospero::GpuEnumValue(Prospero::BufferFormat::k32Float);
-	return swizzle == DstSel(4, 5, 6, 7) ||
-	       (single_channel && (swizzle == DstSel(4, 0, 0, 0) || swizzle == DstSel(4, 0, 0, 1) ||
-	                           swizzle == DstSel(4, 4, 4, 4))) ||
-	       (format == Prospero::GpuEnumValue(Prospero::BufferFormat::k32_32UInt) &&
-	        swizzle == DstSel(4, 5, 0, 1)) ||
-	       ((format == Prospero::GpuEnumValue(Prospero::BufferFormat::k8_8_8_8UNorm) ||
-	         format == Prospero::GpuEnumValue(Prospero::BufferFormat::k8_8_8_8UInt)) &&
-	        (swizzle == DstSel(4, 5, 6, 1) || swizzle == DstSel(6, 5, 4, 7))) ||
-	       (format == Prospero::GpuEnumValue(Prospero::BufferFormat::k32_32_32_32Float) &&
-	        swizzle == DstSel(5, 6, 7, 4));
-}
+namespace ImageViewOps {
 
-[[nodiscard]] inline bool IsSupportedStorageDepthTile(uint32_t format, uint32_t type,
-                                                      uint32_t width, uint32_t height,
-                                                      uint32_t depth) noexcept {
-	return (format == Prospero::GpuEnumValue(Prospero::BufferFormat::k8UInt) &&
-	        type == Prospero::GpuEnumValue(Prospero::ImageType::kColor2DArray) && width != 0 &&
-	        height != 0 && depth == 1) ||
-	       (format == Prospero::GpuEnumValue(Prospero::BufferFormat::k32UInt) &&
-	        type == Prospero::GpuEnumValue(Prospero::ImageType::kColor2D) && width != 0 &&
-	        height != 0 && depth == 1);
-}
+[[nodiscard]] vk::ImageAspectFlags DepthAspectMask(vk::Format format);
+[[nodiscard]] bool                 FormatsCompatible(vk::Format base, vk::Format view) noexcept;
+} // namespace ImageViewOps
 
-[[noreturn]] inline void UnsupportedColorView(const char* usage, vk::Format image_format,
-                                              vk::Format view_format, uint32_t swizzle) noexcept {
-	EXIT("unsupported %s color image view: image_format=%d view_format=%d swizzle=0x%03x\n", usage,
-	     static_cast<int>(image_format), static_cast<int>(view_format), swizzle);
-}
-
-[[nodiscard]] inline vk::Format BgraToRgbaSampledViewFormat(vk::Format image_format) noexcept {
-	switch (image_format) {
-		case vk::Format::eB8G8R8A8Unorm: return vk::Format::eR8G8B8A8Unorm;
-		case vk::Format::eB8G8R8A8Srgb: return vk::Format::eR8G8B8A8Srgb;
-		case vk::Format::eA2R10G10B10UnormPack32: return vk::Format::eA2B10G10R10UnormPack32;
-		default: return vk::Format::eUndefined;
-	}
-}
-
-[[nodiscard]] inline bool IsBgraToRgbaSampledView(vk::Format image_format,
-                                                  vk::Format view_format) noexcept {
-	switch (image_format) {
-		case vk::Format::eB8G8R8A8Unorm:
-		case vk::Format::eB8G8R8A8Srgb:
-			switch (view_format) {
-				case vk::Format::eR8G8B8A8Unorm:
-				case vk::Format::eR8G8B8A8Srgb: return true;
-				default: return false;
-			}
-		case vk::Format::eA2R10G10B10UnormPack32:
-			return view_format == vk::Format::eA2B10G10R10UnormPack32;
-		default: return false;
-	}
-}
-
-[[nodiscard]] inline vk::Format BgraSrgbStorageViewFormat(vk::Format image_format) noexcept {
-	return image_format == vk::Format::eB8G8R8A8Srgb ? vk::Format::eR8G8B8A8Unorm
-	                                                 : vk::Format::eUndefined;
-}
-
-[[nodiscard]] inline vk::Format SrgbStorageViewFormat(vk::Format image_format) noexcept {
-	return image_format == vk::Format::eR8G8B8A8Srgb ? vk::Format::eR8G8B8A8Unorm
-	                                                 : BgraSrgbStorageViewFormat(image_format);
-}
-
-[[nodiscard]] inline bool IsBgraSrgbStorageView(vk::Format image_format, vk::Format view_format,
-                                                uint32_t swizzle) noexcept {
-	return view_format == BgraSrgbStorageViewFormat(image_format) && swizzle == DstSel(6, 5, 4, 7);
-}
-
-[[nodiscard]] inline bool IsValidSampledColorSwizzle(uint32_t swizzle) noexcept {
+[[nodiscard]] inline bool IsValidImageSwizzle(uint32_t swizzle) noexcept {
 	if ((swizzle & ~0xfffu) != 0) {
 		return false;
 	}
@@ -104,21 +32,25 @@ namespace Libs::Graphics {
 	return true;
 }
 
+[[noreturn]] inline void UnsupportedColorView(const char* usage, vk::Format image_format,
+                                              vk::Format view_format, uint32_t swizzle) noexcept {
+	EXIT("unsupported %s color image view: image_format=%d view_format=%d swizzle=0x%03x\n", usage,
+	     static_cast<int>(image_format), static_cast<int>(view_format), swizzle);
+}
+
+[[nodiscard]] inline vk::Format SrgbStorageViewFormat(vk::Format image_format) noexcept {
+	switch (image_format) {
+		case vk::Format::eR8G8B8A8Srgb:
+		case vk::Format::eB8G8R8A8Srgb: return vk::Format::eR8G8B8A8Unorm;
+		default: return vk::Format::eUndefined;
+	}
+}
+
 [[nodiscard]] inline bool IsSupportedSampledColorView(vk::Format image_format,
                                                       vk::Format view_format,
                                                       uint32_t   swizzle) noexcept {
-	if (!IsValidSampledColorSwizzle(swizzle)) {
-		return false;
-	}
-	if (image_format == view_format || IsRgba8SrgbReinterpretation(image_format, view_format)) {
-		return true;
-	}
-	if ((IsRgba16UintFloatReinterpretation(image_format, view_format) ||
-	     IsRgba8UnormUintReinterpretation(image_format, view_format)) &&
-	    swizzle == DstSel(4, 5, 6, 7)) {
-		return true;
-	}
-	return IsBgraToRgbaSampledView(image_format, view_format) && swizzle == DstSel(6, 5, 4, 7);
+	return IsValidImageSwizzle(swizzle) &&
+	       ImageViewOps::FormatsCompatible(image_format, view_format);
 }
 
 [[nodiscard]] inline uint32_t
@@ -169,33 +101,24 @@ IsSupportedSampledDepthUintResource(const ShaderRecompiler::IR::ImageResource& r
 	       !resource.written && !resource.atomic && !resource.depth_compare;
 }
 
-[[nodiscard]] inline int SelectStorageColorView(vk::Format image_format, vk::Format view_format,
-                                                uint32_t swizzle) noexcept {
-	const bool single_channel =
-	    view_format == vk::Format::eR8Unorm || view_format == vk::Format::eR8Uint ||
-	    view_format == vk::Format::eR16Uint || view_format == vk::Format::eR32Uint ||
-	    view_format == vk::Format::eR16Sfloat || view_format == vk::Format::eR32Sfloat;
-	const bool swizzle_ok =
-	    swizzle == DstSel(4, 5, 6, 7) ||
-	    (single_channel && (swizzle == DstSel(4, 0, 0, 0) || swizzle == DstSel(4, 0, 0, 1) ||
-	                        swizzle == DstSel(4, 4, 4, 4))) ||
-	    (view_format == vk::Format::eR32G32Uint && swizzle == DstSel(4, 5, 0, 1)) ||
-	    ((view_format == vk::Format::eR8G8B8A8Unorm || view_format == vk::Format::eR8G8B8A8Uint) &&
-	     (swizzle == DstSel(4, 5, 6, 1) || swizzle == DstSel(6, 5, 4, 7))) ||
-	    (view_format == vk::Format::eR32G32B32A32Sfloat && swizzle == DstSel(5, 6, 7, 4));
-	if ((image_format != view_format &&
-	     !IsBgraSrgbStorageView(image_format, view_format, swizzle)) ||
-	    !swizzle_ok) {
+inline void ValidateStorageColorView(vk::Format image_format, vk::Format view_format,
+                                     uint32_t swizzle) noexcept {
+	const auto srgb_view = SrgbStorageViewFormat(image_format);
+	const bool srgb_storage_view =
+	    srgb_view != vk::Format::eUndefined && view_format == srgb_view;
+	if ((image_format != view_format && !srgb_storage_view) ||
+	    !IsValidImageSwizzle(swizzle)) {
 		UnsupportedColorView("storage", image_format, view_format, swizzle);
 	}
-	return VulkanImage::VIEW_STORAGE;
 }
 
 [[nodiscard]] inline bool
 IsSupportedStorageImageResource(const ShaderRecompiler::IR::ImageResource& resource) noexcept {
 	return (resource.kind == ShaderRecompiler::IR::ResourceKind::StorageImage ||
 	        resource.kind == ShaderRecompiler::IR::ResourceKind::StorageImageUint) &&
-	       (resource.dimension == ShaderRecompiler::Decoder::ImageDimension::Dim2D ||
+	       (resource.dimension == ShaderRecompiler::Decoder::ImageDimension::Dim1D ||
+	        resource.dimension == ShaderRecompiler::Decoder::ImageDimension::Dim1DArray ||
+	        resource.dimension == ShaderRecompiler::Decoder::ImageDimension::Dim2D ||
 	        resource.dimension == ShaderRecompiler::Decoder::ImageDimension::Dim3D ||
 	        resource.dimension == ShaderRecompiler::Decoder::ImageDimension::Dim2DArray) &&
 	       resource.mip_mode == ShaderRecompiler::IR::ImageMipMode::None && resource.written &&
@@ -213,18 +136,6 @@ ValidateStorageImageResource(const ShaderRecompiler::IR::ImageResource& resource
 	}
 }
 
-namespace ImageViewOps {
-
-[[nodiscard]] vk::ImageAspectFlags DepthAspectMask(vk::Format format);
-[[nodiscard]] bool FormatSupportsStorage(vk::Format format);
-
-void CreateRenderTargetViews(RenderTextureVulkanImage& image);
-void CreateDepthViews(DepthStencilVulkanImage& image);
-void CreateVideoOutViews(VideoOutVulkanImage& image);
-void DestroyViews(VulkanImage& image);
-
-} // namespace ImageViewOps
-
 } // namespace Libs::Graphics
 
 #endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_IMAGEVIEW_H_

src/graphics/host_gpu/renderer/masterSemaphore.cpp

@@ -0,0 +1,60 @@
+#include "graphics/host_gpu/renderer/masterSemaphore.h"
+
+#include "common/assert.h"
+#include "graphics/host_gpu/graphicContext.h"
+
+namespace Libs::Graphics {
+
+MasterSemaphore::MasterSemaphore(GraphicContext& graphics): m_graphics(graphics) {
+	vk::SemaphoreTypeCreateInfo type_info {};
+	type_info.sType         = vk::StructureType::eSemaphoreTypeCreateInfo;
+	type_info.semaphoreType = vk::SemaphoreType::eTimeline;
+	type_info.initialValue  = 0;
+
+	vk::SemaphoreCreateInfo create_info {};
+	create_info.sType = vk::StructureType::eSemaphoreCreateInfo;
+	create_info.pNext = &type_info;
+
+	const auto result = m_graphics.device.createSemaphore(&create_info, nullptr, &m_semaphore);
+	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess || m_semaphore == nullptr);
+}
+
+MasterSemaphore::~MasterSemaphore() {
+	if (m_semaphore != nullptr) {
+		m_graphics.device.destroySemaphore(m_semaphore, nullptr);
+	}
+}
+
+void MasterSemaphore::Refresh() {
+	uint64_t counter = 0;
+	const auto result = m_graphics.device.getSemaphoreCounterValue(m_semaphore, &counter);
+	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);
+
+	auto known = m_gpu_tick.load(std::memory_order_acquire);
+	while (known < counter &&
+	       !m_gpu_tick.compare_exchange_weak(known, counter, std::memory_order_release,
+	                                         std::memory_order_relaxed)) {
+	}
+}
+
+void MasterSemaphore::Wait(uint64_t tick) {
+	if (IsFree(tick)) {
+		return;
+	}
+	Refresh();
+	if (IsFree(tick)) {
+		return;
+	}
+
+	vk::SemaphoreWaitInfo wait_info {};
+	wait_info.sType          = vk::StructureType::eSemaphoreWaitInfo;
+	wait_info.semaphoreCount = 1;
+	wait_info.pSemaphores    = &m_semaphore;
+	wait_info.pValues        = &tick;
+
+	const auto result = m_graphics.device.waitSemaphores(&wait_info, UINT64_MAX);
+	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);
+	Refresh();
+}
+
+} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/masterSemaphore.h

@@ -0,0 +1,43 @@
+#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_MASTERSEMAPHORE_H_
+#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_MASTERSEMAPHORE_H_
+
+#include "common/common.h"
+#include "graphics/host_gpu/vulkanCommon.h"
+
+#include <atomic>
+
+namespace Libs::Graphics {
+
+struct GraphicContext;
+
+class MasterSemaphore {
+public:
+	explicit MasterSemaphore(GraphicContext& graphics);
+	~MasterSemaphore();
+	KYTY_CLASS_NO_COPY(MasterSemaphore);
+
+	[[nodiscard]] uint64_t CurrentTick() const noexcept {
+		return m_current_tick.load(std::memory_order_acquire);
+	}
+	[[nodiscard]] uint64_t KnownGpuTick() const noexcept {
+		return m_gpu_tick.load(std::memory_order_acquire);
+	}
+	[[nodiscard]] bool IsFree(uint64_t tick) const noexcept { return KnownGpuTick() >= tick; }
+	[[nodiscard]] uint64_t NextTick() noexcept {
+		return m_current_tick.fetch_add(1, std::memory_order_release);
+	}
+	[[nodiscard]] vk::Semaphore Handle() const noexcept { return m_semaphore; }
+
+	void Refresh();
+	void Wait(uint64_t tick);
+
+private:
+	GraphicContext&       m_graphics;
+	vk::Semaphore         m_semaphore = nullptr;
+	std::atomic<uint64_t> m_gpu_tick {0};
+	std::atomic<uint64_t> m_current_tick {1};
+};
+
+} // namespace Libs::Graphics
+
+#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_MASTERSEMAPHORE_H_

src/graphics/host_gpu/renderer/multiLevelPageTable.h

@@ -1,13 +1,14 @@
 #ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_MULTILEVELPAGETABLE_H_
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_MULTILEVELPAGETABLE_H_
 
+#include "common/assert.h"
+
 #include <algorithm>
 #include <array>
 #include <cstddef>
 #include <cstdint>
 #include <list>
 #include <memory>
-#include <stdexcept>
 #include <utility>
 #include <vector>
 
@@ -59,7 +60,7 @@ public:
 
 	[[nodiscard]] Entry& GetOrCreate(size_t page) {
 		if (!IsValidPage(page)) {
-			throw std::out_of_range("MultiLevelPageTable page is outside the guest address space");
+			EXIT("MultiLevelPageTable page is outside the guest address space");
 		}
 		auto& bucket = m_first_level[FirstLevelIndex(page)];
 		if (bucket == nullptr) {

src/graphics/host_gpu/renderer/pipelineCache.cpp

@@ -7,7 +7,7 @@
 #include "graphics/host_gpu/renderer/colorRenderTarget.h"
 #include "graphics/host_gpu/renderer/debug.h"
 #include "graphics/host_gpu/renderer/depthRenderTarget.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
+#include "graphics/host_gpu/renderer/imageView.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
 
@@ -36,13 +36,25 @@ void NormalizeStaticParamsForDynamicState(PipelineStaticParameters& static_param
 
 } // namespace
 
+PipelineCache::~PipelineCache() {
+	auto destroy = [this](const auto& pipelines) {
+		for (const auto& [key, pipeline]: pipelines) {
+			(void)key;
+			m_graphics.device.destroyPipeline(pipeline->pipeline, nullptr);
+			m_graphics.device.destroyPipelineLayout(pipeline->pipeline_layout, nullptr);
+		}
+	};
+	destroy(m_graphics_pipelines);
+	destroy(m_compute_pipelines);
+}
+
 bool PipelineStaticParameters::operator==(const PipelineStaticParameters& other) const noexcept {
 	return std::memcmp(this, &other, sizeof(*this)) == 0;
 }
 
 PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
-    VulkanFramebuffer& framebuffer, RenderColorInfo* colors, uint32_t color_count,
-    RenderDepthInfo& depth, ShaderVertexInputInfo& vs_input_info, RenderCommandBuffer& command,
+    RenderColorInfo* colors, uint32_t color_count, RenderDepthInfo& depth,
+    ShaderVertexInputInfo& vs_input_info, RenderCommandBuffer& command,
     ShaderPixelInputInfo* ps_input_info, vk::PrimitiveTopology topology, bool ps_active,
     std::span<const uint32_t> vs_spirv, std::span<const uint32_t> ps_spirv) {
 	KYTY_PROFILER_BLOCK("PipelineCache::CreatePipeline(Gfx)", profiler::colors::DeepOrangeA200);
@@ -61,10 +73,10 @@ PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
 	const HW::BlendColor& bclr                                     = ctx.GetBlendColor();
 	uint32_t              color_mask[RENDER_COLOR_ATTACHMENTS_MAX] = {};
 	for (uint32_t i = 0; i < color_count; i++) {
-		color_mask[i] = (colors[i].vulkan_buffer != nullptr
-		                     ? colors[i].export_mapping.ApplyMask(render_target_mask_slot(
-		                           ctx.GetRenderTargetMask(), colors[i].target_slot))
-		                     : 0);
+		color_mask[i] =
+		    (colors[i].image_id ? colors[i].export_mapping.ApplyMask(render_target_mask_slot(
+		                              ctx.GetRenderTargetMask(), colors[i].target_slot))
+		                        : 0);
 	}
 	const HW::ModeControl& mc = ctx.GetModeControl();
 
@@ -76,11 +88,40 @@ PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
 
 	PipelineStaticParameters static_params {};
 	GraphicsPipeline         p {};
-	p.render_pass_id = framebuffer.render_pass_id;
 	p.ps_shader_id   = ps_id;
 	p.vs_shader_id   = vs_id;
 
 	static_params.color_count = color_count;
+	PipelineRenderingState rendering {};
+	rendering.color_count = color_count;
+	uint32_t attachment_samples = 0;
+	for (uint32_t i = 0; i < color_count; i++) {
+		EXIT_IF(!colors[i].image_id || colors[i].format == vk::Format::eUndefined);
+		rendering.color_formats[i] = colors[i].format;
+		if (attachment_samples == 0) {
+			attachment_samples = colors[i].samples;
+		} else if (attachment_samples != colors[i].samples) {
+			EXIT("mixed color attachment sample counts are unsupported: %u and %u\n",
+			     attachment_samples, colors[i].samples);
+		}
+	}
+	const bool with_depth =
+	    depth.format != vk::Format::eUndefined && static_cast<bool>(depth.image_id);
+	if (with_depth) {
+		const auto aspects = ImageViewOps::DepthAspectMask(depth.format);
+		rendering.depth_format =
+		    aspects & vk::ImageAspectFlagBits::eDepth ? depth.format : vk::Format::eUndefined;
+		rendering.stencil_format =
+		    aspects & vk::ImageAspectFlagBits::eStencil ? depth.format : vk::Format::eUndefined;
+		if (attachment_samples == 0) {
+			attachment_samples = depth.samples;
+		} else if (attachment_samples != depth.samples) {
+			EXIT("mixed color/depth sample counts are unsupported: %u and %u\n",
+			     attachment_samples, depth.samples);
+		}
+	}
+	EXIT_IF(attachment_samples == 0 ||
+	        vulkan_sample_count(attachment_samples) == vk::SampleCountFlagBits {});
 
 	if (ps_active && depth.depth_test_enable && ps_input_info->ps_execute_on_noop) {
 		static std::atomic<uint32_t> log_count {0};
@@ -94,14 +135,13 @@ PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
 	static_params.negative_one_to_one = !clip_control.dx_clip_space;
 	static_params.depth_clip_enable   = clip_control.IsZClipEnabled();
 	static_params.topology            = topology;
-	static_params.samples             = framebuffer.samples;
+	static_params.samples             = attachment_samples;
 	static_params.sample_shading_enable =
-	    ps_active && framebuffer.samples > 1 && ps_input_info->ps_sample_shading;
+	    ps_active && attachment_samples > 1 && ps_input_info->ps_sample_shading;
 	if (static_params.sample_shading_enable && !m_graphics.sample_rate_shading_enabled) {
 		EXIT("Pipeline: sample-rate shading is required but unsupported by the host\n");
 	}
-	static_params.with_depth =
-	    (depth.format != vk::Format::eUndefined && depth.vulkan_buffer != nullptr);
+	static_params.with_depth         = with_depth;
 	static_params.depth_test_enable  = depth.depth_test_enable;
 	static_params.depth_write_enable = (depth.depth_write_enable && !depth.depth_clear_enable);
 	static_params.depth_compare_op   = depth.depth_compare_op;
@@ -139,7 +179,7 @@ PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
 	NormalizeStaticParamsForDynamicState(static_params);
 
 	GraphicsPipelineKey key {};
-	key.render_pass_id = p.render_pass_id;
+	key.rendering      = rendering;
 	key.vs_shader_id   = p.vs_shader_id;
 	key.ps_shader_id   = p.ps_shader_id;
 	key.static_params  = static_params;
@@ -162,7 +202,8 @@ PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
 	auto cached = std::make_unique<GraphicsPipeline>(p);
 	LogPipelineTrace("CreatePipelineInternal begin", vs_id.hash0, vs_id.crc32, ps_id.hash0,
 	                 ps_id.crc32);
-	CreatePipelineInternal(*cached, framebuffer.render_pass, vs_input_info, vs_spirv, ps_input_info,
+	CreatePipelineInternal(m_graphics, m_descriptor_cache, *cached, rendering, vs_input_info,
+	                       vs_spirv, ps_input_info,
 	                       ps_spirv, static_params, vs_id.hash0, vs_id.crc32, ps_id.hash0,
 	                       ps_id.crc32, ps_active);
 	LogPipelineTrace("CreatePipelineInternal done", vs_id.hash0, vs_id.crc32, ps_id.hash0,
@@ -204,7 +245,7 @@ PipelineCache::CreateComputePipeline(ShaderComputeInputInfo&      input_info,
 	}
 
 	auto cached = std::make_unique<ComputePipeline>(p);
-	CreatePipelineInternal(*cached, input_info, cs_spirv);
+	CreatePipelineInternal(m_graphics, m_descriptor_cache, *cached, input_info, cs_spirv);
 
 	EXIT_NOT_IMPLEMENTED(cached->pipeline == nullptr);
 	EXIT_NOT_IMPLEMENTED(cached->pipeline_layout == nullptr);

src/graphics/host_gpu/renderer/pipelineCache.h

@@ -20,8 +20,8 @@ namespace Libs::Graphics {
 struct GraphicContext;
 struct RenderColorInfo;
 struct RenderDepthInfo;
-struct VulkanFramebuffer;
 class RenderCommandBuffer;
+class DescriptorCache;
 
 namespace HW {
 class Context;
@@ -86,12 +86,22 @@ static_assert(sizeof(PipelineStaticParameters) ==
                   sizeof(uint8_t[RENDER_COLOR_ATTACHMENTS_MAX]) * 6 +
                   sizeof(bool[RENDER_COLOR_ATTACHMENTS_MAX]) * 3 + sizeof(float) * 4);
 
+struct PipelineRenderingState {
+	std::array<vk::Format, RENDER_COLOR_ATTACHMENTS_MAX> color_formats {};
+	vk::Format depth_format   = vk::Format::eUndefined;
+	vk::Format stencil_format = vk::Format::eUndefined;
+	uint32_t   color_count    = 0;
+
+	bool operator==(const PipelineRenderingState&) const = default;
+};
+
 class PipelineCache {
 public:
-	explicit PipelineCache(GraphicContext& graphics): m_graphics(graphics) {
+	PipelineCache(GraphicContext& graphics, DescriptorCache& descriptor_cache)
+	    : m_graphics(graphics), m_descriptor_cache(descriptor_cache) {
 		EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
 	}
-	~PipelineCache() { KYTY_NOT_IMPLEMENTED; }
+	~PipelineCache();
 	KYTY_CLASS_NO_COPY(PipelineCache);
 
 	struct Pipeline {
@@ -100,7 +110,6 @@ public:
 	};
 
 	struct GraphicsPipeline: Pipeline {
-		uint64_t render_pass_id = 0;
 		ShaderId vs_shader_id;
 		ShaderId ps_shader_id;
 	};
@@ -110,8 +119,8 @@ public:
 	};
 
 	GraphicsPipeline& CreateGraphicsPipeline(
-	    VulkanFramebuffer& framebuffer, RenderColorInfo* colors, uint32_t color_count,
-	    RenderDepthInfo& depth, ShaderVertexInputInfo& vs_input_info, RenderCommandBuffer& command,
+	    RenderColorInfo* colors, uint32_t color_count, RenderDepthInfo& depth,
+	    ShaderVertexInputInfo& vs_input_info, RenderCommandBuffer& command,
 	    ShaderPixelInputInfo* ps_input_info, vk::PrimitiveTopology topology, bool ps_active,
 	    std::span<const uint32_t> vs_spirv, std::span<const uint32_t> ps_spirv);
 	ComputePipeline& CreateComputePipeline(ShaderComputeInputInfo&      input_info,
@@ -120,13 +129,13 @@ public:
 
 private:
 	struct GraphicsPipelineKey {
-		uint64_t                 render_pass_id = 0;
+		PipelineRenderingState   rendering;
 		ShaderId                 vs_shader_id;
 		ShaderId                 ps_shader_id;
 		PipelineStaticParameters static_params;
 
 		bool operator==(const GraphicsPipelineKey& other) const {
-			return render_pass_id == other.render_pass_id && vs_shader_id == other.vs_shader_id &&
+			return rendering == other.rendering && vs_shader_id == other.vs_shader_id &&
 			       ps_shader_id == other.ps_shader_id && static_params == other.static_params;
 		}
 	};
@@ -160,12 +169,21 @@ private:
 				Mix(hash, bytes[i]);
 			}
 		}
+
+		static void MixRendering(std::size_t& hash, const PipelineRenderingState& rendering) {
+			Mix(hash, rendering.color_count);
+			for (uint32_t i = 0; i < rendering.color_count; i++) {
+				Mix(hash, static_cast<uint32_t>(rendering.color_formats[i]));
+			}
+			Mix(hash, static_cast<uint32_t>(rendering.depth_format));
+			Mix(hash, static_cast<uint32_t>(rendering.stencil_format));
+		}
 	};
 
 	struct GraphicsPipelineKeyHash {
 		std::size_t operator()(const GraphicsPipelineKey& key) const {
 			std::size_t hash = 0;
-			PipelineKeyHash::Mix(hash, key.render_pass_id);
+			PipelineKeyHash::MixRendering(hash, key.rendering);
 			PipelineKeyHash::MixShaderId(hash, key.vs_shader_id);
 			PipelineKeyHash::MixShaderId(hash, key.ps_shader_id);
 			PipelineKeyHash::MixStaticParams(hash, key.static_params);
@@ -182,6 +200,7 @@ private:
 	};
 
 	GraphicContext& m_graphics;
+	DescriptorCache& m_descriptor_cache;
 	std::unordered_map<GraphicsPipelineKey, std::unique_ptr<GraphicsPipeline>,
 	                   GraphicsPipelineKeyHash>
 	    m_graphics_pipelines;
@@ -192,7 +211,9 @@ private:
 
 void LogPipelineTrace(const char* phase, uint32_t vs_hash0, uint32_t vs_crc32, uint32_t ps_hash0,
                       uint32_t ps_crc32);
-void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::RenderPass render_pass,
+void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descriptor_cache,
+                            PipelineCache::GraphicsPipeline& pipeline,
+                            const PipelineRenderingState&   rendering,
                             const ShaderVertexInputInfo&    vs_input_info,
                             std::span<const uint32_t>       vs_shader,
                             const ShaderPixelInputInfo*     ps_input_info,
@@ -200,7 +221,8 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
                             const PipelineStaticParameters& static_params, uint32_t vs_hash0,
                             uint32_t vs_crc32, uint32_t ps_hash0, uint32_t ps_crc32,
                             bool ps_active);
-void CreatePipelineInternal(PipelineCache::ComputePipeline& pipeline,
+void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descriptor_cache,
+                            PipelineCache::ComputePipeline& pipeline,
                             const ShaderComputeInputInfo&   input_info,
                             std::span<const uint32_t>       cs_shader);
 

src/graphics/host_gpu/renderer/render.h

@@ -2,10 +2,13 @@
 #define EMULATOR_INCLUDE_EMULATOR_GRAPHICS_GRAPHICSRENDER_H_
 
 #include "common/abi.h"
+#include "common/assert.h"
 #include "common/common.h"
-#include "graphics/host_gpu/renderer/streamBuffer.h"
+#include "graphics/host_gpu/renderer/descriptorCache.h"
+#include "graphics/host_gpu/renderer/renderTarget.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 
+#include <array>
 #include <memory>
 #include <vector>
 
@@ -15,29 +18,23 @@ namespace HW {
 class Context;
 class UserConfig;
 class Shader;
-struct DepthRenderTarget;
 } // namespace HW
 
 struct GraphicContext;
 struct ShaderBufferResource;
 struct ShaderComputeInputInfo;
-struct VideoOutVulkanImage;
-struct DepthStencilVulkanImage;
-struct TextureVulkanImage;
-struct StorageTextureVulkanImage;
-struct RenderTextureVulkanImage;
 struct CommandSlot;
 struct VulkanBuffer;
 struct VulkanDescriptorSet;
-struct VulkanFramebuffer;
 struct RenderDepthInfo;
 struct RenderColorInfo;
-class BufferCache;
-
-struct HtileClearTarget {
-	uint64_t address = 0;
-	uint64_t size    = 0;
-};
+struct DrawCallInfo;
+struct DrawEmitInfo;
+struct DrawIndexBufferSource;
+struct DrawRenderState;
+class RenderContext;
+class CommandScheduler;
+struct RenderExecutorTestAccess;
 
 enum class CommandBufferDebugOp : uint32_t {
 	DispatchDirect,
@@ -66,10 +63,36 @@ private:
 	std::vector<std::shared_ptr<void>> m_resources;
 };
 
+struct SubmitInfo {
+	static constexpr uint32_t MaxSemaphores = 3;
+
+	std::array<vk::Semaphore, MaxSemaphores>          wait_semaphores {};
+	std::array<uint64_t, MaxSemaphores>               wait_ticks {};
+	std::array<vk::PipelineStageFlags, MaxSemaphores> wait_stages {};
+	std::array<vk::Semaphore, MaxSemaphores>          signal_semaphores {};
+	std::array<uint64_t, MaxSemaphores>               signal_ticks {};
+	uint32_t                                          num_wait_semaphores   = 0;
+	uint32_t                                          num_signal_semaphores = 0;
+
+	void AddWait(vk::Semaphore semaphore, uint64_t tick = 1,
+	             vk::PipelineStageFlags stage = vk::PipelineStageFlagBits::eAllCommands) {
+		EXIT_IF(semaphore == nullptr || num_wait_semaphores >= MaxSemaphores);
+		wait_semaphores[num_wait_semaphores] = semaphore;
+		wait_ticks[num_wait_semaphores]      = tick;
+		wait_stages[num_wait_semaphores++]   = stage;
+	}
+
+	void AddSignal(vk::Semaphore semaphore, uint64_t tick = 1) {
+		EXIT_IF(semaphore == nullptr || num_signal_semaphores >= MaxSemaphores);
+		signal_semaphores[num_signal_semaphores] = semaphore;
+		signal_ticks[num_signal_semaphores++]    = tick;
+	}
+};
+
 class CommandBuffer {
 public:
-	CommandBuffer();
-	~CommandBuffer() { Release(); }
+	explicit CommandBuffer(CommandScheduler& scheduler);
+	~CommandBuffer();
 
 	KYTY_CLASS_NO_COPY(CommandBuffer);
 
@@ -77,95 +100,144 @@ public:
 
 	void Begin() const;
 	void End() const;
-	void Execute();
-	void ExecuteWithSemaphore(vk::Semaphore wait_semaphore, vk::PipelineStageFlags wait_stage,
-	                          vk::Semaphore signal_semaphore);
+	void Execute(const SubmitInfo& submit = {});
 	void SetDebugInfo(uint32_t op, uint64_t submit_id, uint32_t arg0 = 0, uint32_t arg1 = 0,
 	                  uint32_t arg2 = 0, uint32_t arg3 = 0, uint64_t arg4 = 0);
-	void BeginRenderPass(VulkanFramebuffer& framebuffer, RenderColorInfo* colors,
-	                     uint32_t color_count, RenderDepthInfo& depth) const;
-	void EndRenderPass() const;
+	void BeginRendering(const RenderState& state) const;
+	void EndRendering() const;
 	void WaitForFenceOnly();
 	void WaitForFence();
 	void WaitForFenceAndReset();
-	void DeleteAfterFence(VulkanBuffer& buffer);
+	void RetireBufferAfterFence(std::unique_ptr<VulkanBuffer> buffer);
 	void RetainResourceUntilFence(std::shared_ptr<void> resource);
 	void RecycleDescriptorAfterFence(VulkanDescriptorSet& set);
 
 	[[nodiscard]] vk::CommandBuffer Handle() const;
 	[[nodiscard]] GraphicContext&   GetGraphics() const noexcept { return m_graphics; }
+	[[nodiscard]] RenderContext&    GetContext() const noexcept { return m_context; }
 	[[nodiscard]] bool              IsExecute() const { return m_execute; }
-	[[nodiscard]] uint64_t GetRecordingGeneration() const { return m_recording_generation; }
 
 private:
-	friend class BufferCache;
-
-	void Submit(vk::Semaphore wait_semaphore, vk::PipelineStageFlags wait_stage,
-	            vk::Semaphore signal_semaphore);
 	void Release();
 	void FinalizeFence(bool reset_recording);
 	void ReleaseResourcesAfterFence();
 	void DeleteBuffersAfterFence();
 	void RecycleDescriptorsAfterFence();
 
-	GraphicContext&                   m_graphics;
-	CommandSlot*                      m_slot                 = nullptr;
-	bool                              m_execute              = false;
-	bool                              m_fence_waited         = false;
-	uint64_t                          m_submit_seq           = 0;
-	uint64_t                          m_recording_generation = 0;
-	uint32_t                          m_debug_op             = 0;
-	uint64_t                          m_debug_submit_id      = 0;
-	uint32_t                          m_debug_arg0           = 0;
-	uint32_t                          m_debug_arg1           = 0;
-	uint32_t                          m_debug_arg2           = 0;
-	uint32_t                          m_debug_arg3           = 0;
-	uint64_t                          m_debug_arg4           = 0;
-	std::vector<VulkanBuffer*>        m_delete_after_fence;
-	FenceResourceRetainer             m_fence_resources;
-	std::vector<VulkanDescriptorSet*> m_descriptor_sets_after_fence;
-	HostStreamBuffer                  m_host_stream;
+	RenderContext&                             m_context;
+	CommandScheduler&                          m_scheduler;
+	GraphicContext&                            m_graphics;
+	CommandSlot*                               m_slot            = nullptr;
+	bool                                       m_execute         = false;
+	bool                                       m_fence_waited    = false;
+	uint64_t                                   m_submit_seq      = 0;
+	uint32_t                                   m_debug_op        = 0;
+	uint64_t                                   m_debug_submit_id = 0;
+	uint32_t                                   m_debug_arg0      = 0;
+	uint32_t                                   m_debug_arg1      = 0;
+	uint32_t                                   m_debug_arg2      = 0;
+	uint32_t                                   m_debug_arg3      = 0;
+	uint64_t                                   m_debug_arg4      = 0;
+	std::vector<std::unique_ptr<VulkanBuffer>> m_retired_buffers;
+	FenceResourceRetainer                      m_fence_resources;
+	std::vector<VulkanDescriptorSet*>          m_descriptor_sets_after_fence;
+	mutable RenderState                        m_render_state;
+	mutable bool                               m_rendering = false;
 };
 
 class RenderCommandBuffer final: public CommandBuffer {
 public:
-	RenderCommandBuffer(HW::Context& registers, HW::UserConfig& user_config, HW::Shader& shaders)
-	    : m_registers(registers), m_user_config(user_config), m_shaders(shaders) {}
+	explicit RenderCommandBuffer(CommandScheduler& scheduler): CommandBuffer(scheduler) {}
 
-	[[nodiscard]] HW::Context&    GetRegisters() const noexcept { return m_registers; }
-	[[nodiscard]] HW::UserConfig& GetUserConfig() const noexcept { return m_user_config; }
-	[[nodiscard]] HW::Shader&     GetShaders() const noexcept { return m_shaders; }
+	void Bind(HW::Context& registers, HW::UserConfig& user_config, HW::Shader& shaders) noexcept {
+		m_registers   = &registers;
+		m_user_config = &user_config;
+		m_shaders     = &shaders;
+	}
+
+	[[nodiscard]] HW::Context&    GetRegisters() const noexcept { return *m_registers; }
+	[[nodiscard]] HW::UserConfig& GetUserConfig() const noexcept { return *m_user_config; }
+	[[nodiscard]] HW::Shader&     GetShaders() const noexcept { return *m_shaders; }
 
 private:
-	HW::Context&    m_registers;
-	HW::UserConfig& m_user_config;
-	HW::Shader&     m_shaders;
+	HW::Context*    m_registers   = nullptr;
+	HW::UserConfig* m_user_config = nullptr;
+	HW::Shader*     m_shaders     = nullptr;
 };
 
-void RenderDrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t index_type_and_size,
-                     uint32_t index_count, const void* index_addr, uint32_t flags, uint32_t type,
-                     uint32_t instance_count = 1, uint32_t render_target_slice_offset = 0,
-                     int32_t vertex_offset_add = 0, uint32_t first_instance = 0);
-void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t index_count,
-                         uint32_t flags, uint32_t render_target_slice_offset = 0,
-                         uint32_t instance_count = 1, uint32_t first_vertex = 0,
-                         uint32_t first_instance = 0);
-void RenderDispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t thread_group_x,
-                          uint32_t thread_group_y, uint32_t thread_group_z, uint32_t mode);
+class RenderExecutor {
+public:
+	explicit RenderExecutor(RenderContext& context): m_context(context) {}
+	KYTY_CLASS_NO_COPY(RenderExecutor);
 
-void GraphicsRenderInit(GraphicContext& graphics);
-void GraphicsRenderReleaseThreadCommandPool();
+	void DrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t index_type_and_size,
+	               uint32_t index_count, const void* index_addr, uint32_t flags, uint32_t type,
+	               uint32_t instance_count = 1, uint32_t render_target_slice_offset = 0,
+	               int32_t vertex_offset_add = 0, uint32_t first_instance = 0);
+	void DrawAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t index_count,
+	              uint32_t flags, uint32_t render_target_slice_offset = 0,
+	              uint32_t instance_count = 1, uint32_t first_vertex = 0,
+	              uint32_t first_instance = 0);
+	void DispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t thread_group_x,
+	                    uint32_t thread_group_y, uint32_t thread_group_z, uint32_t mode);
+
+	[[nodiscard]] DescriptorCache::PreparedBindings
+	     PrepareBindings(CommandBuffer& buffer, const ShaderStageRuntime& runtime,
+	                     vk::ShaderStageFlags shader_stage, DescriptorCache::Stage stage);
+	void RebindBuffers(CommandBuffer& buffer, DescriptorCache::PreparedBindings& bindings);
+	void RebindImages(CommandBuffer& buffer, DescriptorCache::PreparedBindings& bindings);
+	void CommitBindings(CommandBuffer& buffer, vk::PipelineBindPoint pipeline_bind_point,
+	                    vk::PipelineLayout layout, DescriptorCache::PreparedBindings& bindings);
+
+private:
+	struct GraphicsBindings {
+		DescriptorCache::PreparedBindings                vertex;
+		std::optional<DescriptorCache::PreparedBindings> pixel;
+	};
+
+	[[nodiscard]] DescriptorCache::TextureBinding
+	ResolveTexture(const ShaderRecompiler::IR::ImageResource&   resource,
+	               const ShaderRecompiler::IR::DescriptorValue& value);
+	[[nodiscard]] GraphicsBindings PrepareGraphicsBindings(CommandBuffer&            buffer,
+	                                                       const ShaderStageRuntime& vertex,
+	                                                       const ShaderStageRuntime& pixel,
+	                                                       bool                      pixel_active);
+	void ResolveRenderColorTarget(uint64_t submit_id, RenderCommandBuffer& buffer,
+	                              RenderColorInfo& target, uint32_t render_target_slice_offset = 0,
+	                              uint32_t render_target_slot = UINT32_MAX,
+	                              bool ignore_target_mask = false, bool exact_format = false);
+	void ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer,
+	                              RenderDepthInfo& target);
+	[[nodiscard]] bool PrepareDrawRenderState(uint64_t submit_id, RenderCommandBuffer& buffer,
+	                                          const DrawCallInfo& draw,
+	                                          uint32_t            render_target_slice_offset,
+	                                          bool log_setup_phases, DrawRenderState& state);
+	void ExecutePreparedDraw(uint64_t submit_id, RenderCommandBuffer& buffer,
+	                         const DrawCallInfo& draw, DrawRenderState& state,
+	                         vk::PrimitiveTopology topology, const DrawEmitInfo& emit,
+	                         const DrawIndexBufferSource& index_source, bool log_pipeline_phase,
+	                         bool set_bind_debug, bool set_auto_debug);
+	[[nodiscard]] RenderState AcquireRenderTargets(CommandBuffer& buffer, RenderColorInfo* colors,
+	                                               uint32_t color_count, RenderDepthInfo& depth);
+	[[nodiscard]] bool        ResolveColorTargets(uint64_t submit_id, RenderCommandBuffer& buffer,
+	                                              uint32_t render_target_slice_offset);
+	void                      BindImage(ImageId id, bool storage);
+	void                      BindRenderTarget(ImageId id);
+	void                      TrackImageBinding(ImageId id);
+	void                      ResetBindings();
+	[[nodiscard]] bool        TryConsumeComputeMetaClear(const ShaderComputeInputInfo& input,
+	                                                     const RenderCommandBuffer&    buffer);
+
+	RenderContext&                      m_context;
+	std::vector<std::shared_ptr<Image>> m_bound_images;
+
+	friend struct RenderExecutorTestAccess;
+};
 
 [[nodiscard]] bool ResolveComputeImageClear(const ShaderComputeInputInfo& input, uint32_t group_x,
                                             uint32_t group_y, uint32_t group_z, uint32_t mode,
                                             ShaderBufferResource& descriptor,
                                             uint32_t& packed_clear, uint64_t& size);
-[[nodiscard]] bool ResolveHtileClearTarget(const HW::DepthRenderTarget& target,
-                                           uint64_t descriptor_size, HtileClearTarget& resolved);
-
-void GraphicsRenderMemoryBarrier(CommandBuffer& buffer);
-void GraphicsRenderTextureBarrier(CommandBuffer& buffer, uint64_t vaddr, uint64_t size);
-void GraphicsRenderDepthStencilBarrier(CommandBuffer& buffer, uint64_t vaddr, uint64_t size);
 
 } // namespace Libs::Graphics
 

src/graphics/host_gpu/renderer/renderCompute.cpp

@@ -9,20 +9,15 @@
 #include "graphics/guest_gpu/gpu_defs.h"
 #include "graphics/guest_gpu/graphicsRun.h"
 #include "graphics/guest_gpu/hardwareContext.h"
-#include "graphics/guest_gpu/tile.h"
 #include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/objects/label.h"
-#include "graphics/host_gpu/renderer/depthRenderTarget.h"
 #include "graphics/host_gpu/renderer/descriptorCache.h"
 #include "graphics/host_gpu/renderer/descriptors.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
 #include "graphics/host_gpu/renderer/imageInfo.h"
 #include "graphics/host_gpu/renderer/pipelineCache.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
 #include "graphics/host_gpu/renderer/shaderResourceBarrier.h"
 #include "graphics/host_gpu/renderer/shaderSubgroup.h"
-#include "graphics/host_gpu/transfer.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 #include "graphics/shader/recompiler/ResourceMaterialization.h"
 #include "graphics/shader/recompiler/ShaderIR.h"
@@ -50,217 +45,35 @@ static uint64_t BufferDescriptorSize(const ShaderBufferResource& descriptor) {
 	return stride == 0 ? records : records * stride;
 }
 
-bool ResolveHtileClearTarget(const HW::DepthRenderTarget& z, uint64_t descriptor_size,
-                             HtileClearTarget& resolved) {
-	resolved = {};
-	const bool has_stencil =
-	    z.stencil_info.format != Prospero::GpuEnumValue(Prospero::StencilFormat::kInvalid);
-	const auto* depth_policy = FindDepthFormatPolicy(z.z_info.format);
-	const bool  supported_depth_state =
-	    z.z_info.tile_surface_enable && depth_policy != nullptr && z.z_info.tile_mode_index == 0 &&
-	    z.z_info.num_samples <= 3 && z.z_info.zrange_precision <= 1 && !z.z_info.expclear_enabled &&
-	    !z.z_info.embedded_sample_locations && !z.z_info.partially_resident &&
-	    z.z_info.num_mip_levels == 0 && z.z_info.plane_compression == 0 &&
-	    z.depth_view.current_mip_level == 0 && z.depth_view.slice_start == 0 &&
-	    z.depth_view.slice_max == 0 && z.depth_info.addr5_swizzle_mask == 0 &&
-	    z.depth_info.array_mode == 0 && z.depth_info.pipe_config == 0 &&
-	    z.depth_info.bank_width == 0 && z.depth_info.bank_height == 0 &&
-	    z.depth_info.macro_tile_aspect == 0 && z.depth_info.num_banks == 0;
-	const bool supported_stencil_state =
-	    z.stencil_info.tile_mode_index == 0 && z.stencil_info.tile_split == 0 &&
-	    !z.stencil_info.expclear_enabled &&
-	    depth_htile_stencil_acceleration_compatible(has_stencil, true,
-	                                                z.stencil_info.tile_stencil_disable) &&
-	    !z.stencil_info.texture_compatible_stencil && !z.stencil_info.partially_resident &&
-	    (!has_stencil ||
-	     (z.stencil_info.format == Prospero::GpuEnumValue(Prospero::StencilFormat::k8UInt) &&
-	      !z.depth_view.stencil_write_disable));
-	const bool supported_htile_state =
-	    z.htile_surface.linear == 0 && z.htile_surface.full_cache == 0 &&
-	    z.htile_surface.htile_uses_preload_win == 0 && z.htile_surface.preload == 0 &&
-	    z.htile_surface.prefetch_width == 0 && z.htile_surface.prefetch_height == 0 &&
-	    z.htile_surface.dst_outside_zero_to_one == 0;
-	const bool supported_addresses =
-	    z.z_read_base_addr != 0 && z.z_write_base_addr == z.z_read_base_addr &&
-	    (z.z_read_base_addr & 0xffffu) == 0 &&
-	    (has_stencil ? z.stencil_read_base_addr != 0 &&
-	                       z.stencil_write_base_addr == z.stencil_read_base_addr &&
-	                       (z.stencil_read_base_addr & 0xffffu) == 0
-	                 : z.stencil_read_base_addr == 0 && z.stencil_write_base_addr == 0) &&
-	    z.htile_data_base_addr != 0 && (z.htile_data_base_addr & 0x7fffu) == 0 &&
-	    descriptor_size != 0 && (descriptor_size & 0x7fffu) == 0 &&
-	    z.htile_data_base_addr < TRACKER_ADDRESS_SIZE &&
-	    descriptor_size <= TRACKER_ADDRESS_SIZE - z.htile_data_base_addr;
-	if (!supported_depth_state || !supported_stencil_state || !supported_htile_state ||
-	    !supported_addresses) {
-		return false;
-	}
-
-	const bool size_xy_valid = z.size.valid;
-	const bool wh_valid      = z.width_height_valid && z.width != 0 && z.height != 0;
-	if (!size_xy_valid && !wh_valid) {
-		// Prospero emits an exact full-surface metadata descriptor even
-		// when the compute context omits depth extent registers. Admit only that wholly absent
-		// layout state; partially programmed layouts remain unsupported.
-		const bool descriptor_backed_state =
-		    !z.size.valid && z.size.x_max == 0 && z.size.y_max == 0 && !z.width_height_valid &&
-		    z.width == 0 && z.height == 0 && !z.pitch_height_valid && z.pitch_div8_minus1 == 0 &&
-		    z.height_div8_minus1 == 0 && z.slice_div64_minus1 == 0;
-		if (!descriptor_backed_state) {
-			return false;
-		}
-		resolved = {.address = z.htile_data_base_addr, .size = descriptor_size};
-		return true;
-	}
-	const uint32_t width  = size_xy_valid ? static_cast<uint32_t>(z.size.x_max) + 1u : z.width;
-	const uint32_t height = size_xy_valid ? static_cast<uint32_t>(z.size.y_max) + 1u : z.height;
-	if (width > 16384 || height > 16384 ||
-	    (size_xy_valid && wh_valid && (width != z.width || height != z.height)) ||
-	    (!z.pitch_height_valid &&
-	     (z.pitch_div8_minus1 != 0 || z.height_div8_minus1 != 0 || z.slice_div64_minus1 != 0))) {
-		return false;
-	}
-	TileSizeAlign htile_size {};
-	if (!TileGetHtileSize(width, height, htile_size) || htile_size.size != descriptor_size) {
-		return false;
-	}
-	resolved = {.address = z.htile_data_base_addr, .size = htile_size.size};
-	return true;
-}
-
-static void ValidateFullHtileClearDispatch(const ShaderComputeInputInfo& input,
-                                           const ShaderBufferResource& metadata, uint32_t group_x,
-                                           uint32_t group_y, uint32_t group_z, uint32_t mode) {
-	const bool thread_dimensions = input.dispatch_thread_dimensions;
-	const bool supported_shape =
-	    input.threads_num[0] == 64 && input.threads_num[1] == 1 && input.threads_num[2] == 1 &&
-	    group_x != 0 && group_y == 1 && group_z == 1 && input.group_id[0] && !input.group_id[1] &&
-	    !input.group_id[2] && input.thread_ids_num == 1 && input.wave_size == 32 &&
-	    !input.tg_size_en && mode == (thread_dimensions ? 0x61u : 0x41u);
-	const bool dimensions_match =
-	    thread_dimensions
-	        ? input.dispatch_threads_num[0] == group_x && input.dispatch_threads_num[1] == 1 &&
-	              input.dispatch_threads_num[2] == 1 && group_x % input.threads_num[0] == 0
-	        : input.dispatch_threads_num[0] == 0 && input.dispatch_threads_num[1] == 0 &&
-	              input.dispatch_threads_num[2] == 0;
-	const uint64_t launched_threads =
-	    thread_dimensions ? group_x : static_cast<uint64_t>(group_x) * input.threads_num[0];
-	if (!supported_shape || !dimensions_match || metadata.Stride() == 0 ||
-	    launched_threads != metadata.NumRecords()) {
-		EXIT("HTile compute clear does not cover the complete metadata surface\n");
-	}
-}
-
-static bool TryConsumeComputeMetaClear(const ShaderComputeInputInfo& input,
-                                       const RenderCommandBuffer& buffer, uint32_t group_x,
-                                       uint32_t group_y, uint32_t group_z, uint32_t mode) {
-	const auto& ctx       = buffer.GetRegisters();
+bool RenderExecutor::TryConsumeComputeMetaClear(const ShaderComputeInputInfo& input,
+                                                const RenderCommandBuffer&    buffer) {
 	const auto& program   = *input.stage.program;
 	const auto& resources = *input.stage.resources;
 	if (resources.buffers.size() != program.info.buffers.size()) {
 		EXIT("compute runtime buffer count does not match shader metadata\n");
 	}
-	const auto&                 z                   = ctx.GetDepthRenderTarget();
-	const uint64_t              meta_addr           = z.htile_data_base_addr;
-	auto&                       cache               = GetRenderContext().GetTextureCache();
-	uint32_t                    current_references  = 0;
-	uint32_t                    registered_writes   = 0;
-	uint64_t                    described_meta_size = 0;
-	HtileClearTarget            registered_target {};
-	TextureCache::MetaRangeInfo registered_meta {};
+	auto& cache = buffer.GetContext().GetTextureCache();
 	for (uint32_t i = 0; i < program.info.buffers.size(); i++) {
 		const auto& resource   = program.info.buffers[i];
 		const auto  descriptor = DecodeNativeDescriptor<ShaderBufferResource>(resources.buffers[i]);
-		const auto  descriptor_size = BufferDescriptorSize(descriptor);
-		if (meta_addr != 0 && descriptor.Base48() == meta_addr) {
-			current_references++;
-			described_meta_size = descriptor_size;
-		}
-		// An exact registered metadata range remains
-		// identifiable even when it is no longer the currently bound depth target.
-		TextureCache::MetaRangeInfo resolved_meta {};
-		if (resource.written &&
-		    cache.ResolveMetaRange(descriptor.Base48(), descriptor_size, resolved_meta)) {
-			registered_writes++;
-			registered_target = {.address = descriptor.Base48(), .size = descriptor_size};
-			registered_meta   = resolved_meta;
+		if (!resource.written && cache.IsMeta(descriptor.Base48())) {
+			return false;
 		}
 	}
-	if (current_references == 0 && registered_writes == 0) {
-		return false;
-	}
-	if (current_references > 1 || (current_references == 0 && registered_writes > 1)) {
-		EXIT("HTile clear has ambiguous metadata descriptors: current=%u registered=%u\n",
-		     current_references, registered_writes);
-	}
-	HtileClearTarget target {};
-	if (current_references != 0) {
-		if (!ResolveHtileClearTarget(z, described_meta_size, target)) {
-			EXIT("unsupported HTile compute-clear target state: current=%u registered=%u "
-			     "meta=0x%016" PRIx64 "+0x%016" PRIx64 " depth=0x%016" PRIx64 "/0x%016" PRIx64
-			     " stencil=0x%016" PRIx64 "/0x%016" PRIx64
-			     " extent=%d:%ux%u wh=%d:%ux%u pitch=%d:%u/%u/%u zfmt=%u sfmt=%u samples=%u\n",
-			     current_references, registered_writes, meta_addr, described_meta_size,
-			     z.z_read_base_addr, z.z_write_base_addr, z.stencil_read_base_addr,
-			     z.stencil_write_base_addr, z.size.valid, static_cast<uint32_t>(z.size.x_max) + 1u,
-			     static_cast<uint32_t>(z.size.y_max) + 1u, z.width_height_valid, z.width, z.height,
-			     z.pitch_height_valid, z.pitch_div8_minus1, z.height_div8_minus1,
-			     z.slice_div64_minus1, z.z_info.format, z.stencil_info.format,
-			     z.z_info.num_samples);
-		}
-		cache.RegisterMeta(target.address, target.size);
-		if (!cache.ResolveMetaRange(target.address, target.size, registered_meta)) {
-			EXIT("failed to resolve registered HTile compute-clear range\n");
-		}
-	} else {
-		target = registered_target;
-	}
-	GetRenderContext().GetBufferCache().ValidateGpuAccess(target.address, target.size, false, true);
 
-	uint32_t             metadata_writes = 0;
-	ShaderBufferResource metadata_descriptor {};
-	if (!program.info.images.empty() || !program.info.samplers.empty() ||
-	    !program.info.addresses.empty()) {
-		EXIT("HTile clear with non-buffer resources is unsupported: images=%zu samplers=%zu "
-		     "addresses=%zu\n",
-		     program.info.images.size(), program.info.samplers.size(),
-		     program.info.addresses.size());
-	}
-	for (uint32_t i = 0; i < program.info.buffers.size(); i++) {
-		const auto& resource   = program.info.buffers[i];
-		const auto  descriptor = DecodeNativeDescriptor<ShaderBufferResource>(resources.buffers[i]);
-		const auto  descriptor_size = BufferDescriptorSize(descriptor);
-		if (descriptor.Base48() == target.address) {
-			if (!resource.written || resource.read || resource.atomic ||
-			    descriptor_size != target.size || descriptor.SwizzleEnabled() ||
-			    descriptor.IndexStride() != 0 || descriptor.AddTid() ||
-			    resource.packed_stride != descriptor.PackedStride()) {
-				EXIT("unsupported HTile compute metadata access\n");
+	if (!program.info.has_bitwise_xor) {
+		for (uint32_t i = 0; i < program.info.buffers.size(); i++) {
+			const auto& resource = program.info.buffers[i];
+			if (resource.written) {
+				const auto descriptor =
+				    DecodeNativeDescriptor<ShaderBufferResource>(resources.buffers[i]);
+				if (cache.ClearMeta(descriptor.Base48())) {
+					return true;
+				}
 			}
-			metadata_descriptor = descriptor;
-			metadata_writes++;
-			continue;
 		}
-		if (resource.written || !resource.read || resource.atomic || descriptor.Base48() == 0 ||
-		    descriptor_size == 0 ||
-		    cache.QueryRegion(descriptor.Base48(), descriptor_size).metadata_pages) {
-			EXIT("unsupported HTile clear side-buffer access\n");
-		}
-		GetRenderContext().GetBufferCache().ValidateGpuAccess(descriptor.Base48(), descriptor_size,
-		                                                      true, false);
 	}
-	if (metadata_writes != 1) {
-		EXIT("HTile clear requires exactly one write-only metadata buffer, writes=%u\n",
-		     metadata_writes);
-	}
-	ValidateFullHtileClearDispatch(input, metadata_descriptor, group_x, group_y, group_z, mode);
-	const bool recorded = registered_meta.full ? cache.ClearMeta(registered_meta.metadata_address)
-	                                           : cache.TouchMeta(registered_meta.metadata_address,
-	                                                             registered_meta.slice, true);
-	if (!recorded) {
-		EXIT("failed to record HTile compute clear\n");
-	}
-	return true;
+	return false;
 }
 
 bool ResolveComputeImageClear(const ShaderComputeInputInfo& input, uint32_t group_x,
@@ -324,7 +137,7 @@ static bool TryConsumeComputeImageClear(const ShaderComputeInputInfo& input, Com
 	                              size)) {
 		return false;
 	}
-	auto& cache = GetRenderContext().GetTextureCache();
+	auto& cache = command.GetContext().GetTextureCache();
 	if (!cache.ClearImageFromBuffer(command, descriptor.Base48(), size, packed_clear)) {
 		return false;
 	}
@@ -337,8 +150,9 @@ static bool TryConsumeComputeImageClear(const ShaderComputeInputInfo& input, Com
 	return true;
 }
 
-void RenderDispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t thread_group_x,
-                          uint32_t thread_group_y, uint32_t thread_group_z, uint32_t mode) {
+void RenderExecutor::DispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer,
+                                    uint32_t thread_group_x, uint32_t thread_group_y,
+                                    uint32_t thread_group_z, uint32_t mode) {
 	EXIT_IF(buffer.IsInvalid());
 	auto& ctx    = buffer.GetRegisters();
 	auto& sh_ctx = buffer.GetShaders();
@@ -347,8 +161,7 @@ void RenderDispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer, uint3
 	                    thread_group_x, thread_group_y, thread_group_z, mode,
 	                    sh_ctx.GetCs().cs_regs.data_addr);
 
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-
+	Common::LockGuard lock(m_context.GetMutex());
 	if (sh_ctx.GetCs().cs_regs.data_addr == 0) {
 		LOGF("GraphicsRenderDispatchDirect: temporary: ignoring dispatch with null CS shader, "
 		     "groups=%ux%ux%u mode=%u\n",
@@ -396,17 +209,18 @@ void RenderDispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer, uint3
 		input_info.dispatch_threads_num[2]    = thread_group_z;
 	}
 
-	const uint32_t frame_num = GraphicsRunGetFrameNum();
+	const uint32_t frame_num = static_cast<uint32_t>(m_context.GetGpu().GetFrameNum());
 	const bool     large_workgroup =
 	    (input_info.threads_num[0] * input_info.threads_num[1] * input_info.threads_num[2] >= 512);
 	const auto& program   = *input_info.stage.program;
 	const auto& resources = *input_info.stage.resources;
-	if (TryConsumeComputeMetaClear(input_info, buffer, thread_group_x, thread_group_y,
-	                               thread_group_z, mode)) {
+	if (TryConsumeComputeMetaClear(input_info, buffer)) {
+		ResetBindings();
 		return;
 	}
 	if (TryConsumeComputeImageClear(input_info, buffer, thread_group_x, thread_group_y,
 	                                thread_group_z, mode)) {
+		ResetBindings();
 		return;
 	}
 	const auto sampled_images = std::count_if(
@@ -501,38 +315,32 @@ void RenderDispatchDirect(uint64_t submit_id, RenderCommandBuffer& buffer, uint3
 		return;
 	}
 
-	for (;;) {
-		const auto recording_generation = buffer.GetRecordingGeneration();
-		auto       vk_buffer            = buffer.Handle();
-		auto&      pipeline = GetRenderContext().GetPipelineCache().CreateComputePipeline(
-		    input_info, sh_ctx.GetCs(), cs_shader);
+	buffer.EndRendering();
+	auto& pipeline =
+	    m_context.GetPipelineCache().CreateComputePipeline(input_info, sh_ctx.GetCs(), cs_shader);
+	auto bindings = PrepareBindings(buffer, input_info.stage, vk::ShaderStageFlagBits::eCompute,
+	                                DescriptorCache::Stage::Compute);
+	RebindBuffers(buffer, bindings);
+	RebindImages(buffer, bindings);
 
-		vk_buffer.bindPipeline(vk::PipelineBindPoint::eCompute, pipeline.pipeline);
+	auto vk_buffer = buffer.Handle();
+	CommitBindings(buffer, vk::PipelineBindPoint::eCompute, pipeline.pipeline_layout, bindings);
+	vk_buffer.bindPipeline(vk::PipelineBindPoint::eCompute, pipeline.pipeline);
+	vk_buffer.dispatch(thread_group_x, thread_group_y, thread_group_z);
 
-		BindDescriptors(submit_id, buffer, vk::PipelineBindPoint::eCompute,
-		                pipeline.pipeline_layout, input_info.stage,
-		                vk::ShaderStageFlagBits::eCompute, DescriptorCache::Stage::Compute);
-		if (buffer.GetRecordingGeneration() != recording_generation) {
-			continue;
-		}
-
-		vk_buffer.dispatch(thread_group_x, thread_group_y, thread_group_z);
-
-		bool has_storage_writes = HasShaderBufferWrites(input_info.stage);
-		has_storage_writes =
-		    std::any_of(
-		        program.info.images.begin(), program.info.images.end(),
-		        [](const auto& image) {
-			        return image.written &&
-			               (image.kind == ShaderRecompiler::IR::ResourceKind::StorageImage ||
-			                image.kind == ShaderRecompiler::IR::ResourceKind::StorageImageUint);
-		        }) ||
-		    has_storage_writes;
-		if (has_storage_writes) {
-			ShaderWriteBarrier(vk_buffer, vk::PipelineStageFlagBits::eComputeShader);
-		}
-		break;
+	bool has_storage_writes = HasShaderBufferWrites(input_info.stage);
+	has_storage_writes =
+	    std::any_of(program.info.images.begin(), program.info.images.end(),
+	                [](const auto& image) {
+		                return image.written &&
+		                       (image.kind == ShaderRecompiler::IR::ResourceKind::StorageImage ||
+		                        image.kind == ShaderRecompiler::IR::ResourceKind::StorageImageUint);
+	                }) ||
+	    has_storage_writes;
+	if (has_storage_writes) {
+		ShaderWriteBarrier(vk_buffer, vk::PipelineStageFlagBits::eComputeShader);
 	}
+	ResetBindings();
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/renderContext.cpp

@@ -2,6 +2,8 @@
 
 #include "common/assert.h"
 #include "common/logging/log.h"
+#include "graphics/guest_gpu/graphicsRun.h"
+#include "graphics/presentation/videoOut.h"
 #include "kernel/pthread.h"
 #include "libs/errno.h"
 
@@ -10,24 +12,66 @@
 namespace Libs::Graphics {
 
 RenderContext::RenderContext(GraphicContext& graphics)
-    : m_graphics(graphics), m_pipeline_cache(graphics), m_descriptor_cache(graphics),
-      m_framebuffer_cache(graphics), m_sampler_cache(graphics), m_gds_buffer(graphics),
-      m_gpu_resources(graphics) {
+    : m_graphics(graphics), m_render_executor(*this), m_command_scheduler(*this, graphics),
+      m_descriptor_cache(graphics), m_pipeline_cache(graphics, m_descriptor_cache),
+      m_sampler_cache(graphics),
+      m_gpu_resources(graphics, m_command_scheduler) {
 	EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
 }
 
+RenderContext::~RenderContext() {
+	ShutdownGpu();
+	m_command_scheduler.Shutdown();
+}
+
+void RenderContext::InitializeGpu(VideoOut::VideoOutDriver* video_out) {
+	EXIT_IF(m_gpu != nullptr);
+	m_video_out = video_out;
+	m_gpu = std::make_unique<Gpu>(*this);
+	m_gpu_resources.SetGpu(m_gpu.get());
+}
+
+void RenderContext::ShutdownGpu() {
+	if (m_gpu != nullptr) {
+		m_gpu_resources.SetGpu(nullptr);
+		m_gpu->Shutdown();
+		m_gpu.reset();
+	}
+	if (m_video_out != nullptr) {
+		if (m_command_scheduler.Active()) {
+			m_command_scheduler.FinishCurrent();
+		}
+		m_command_scheduler.DrainPriorityOperations();
+		m_video_out = nullptr;
+	}
+}
+
+Gpu& RenderContext::GetGpu() const {
+	EXIT_IF(m_gpu == nullptr);
+	return *m_gpu;
+}
+
+VideoOut::VideoOutDriver& RenderContext::GetVideoOut() const {
+	EXIT_IF(m_video_out == nullptr);
+	return *m_video_out;
+}
+
 void RenderContext::AddEopEq(LibKernel::EventQueue::KernelEqueue eq, int id) {
+	auto queue = LibKernel::EventQueue::KernelPinEqueue(eq);
+	if (!queue) {
+		return;
+	}
+
 	Common::LockGuard lock(m_eop_mutex);
 
 	auto it = std::find_if(m_eop_eqs.begin(), m_eop_eqs.end(), [eq, id](const auto& entry) {
 		return entry.eq == eq && entry.id == id;
 	});
 	if (it != m_eop_eqs.end()) {
-		it->count++;
 		return;
 	}
 
-	m_eop_eqs.push_back({eq, id, 1});
+	m_eop_eqs.push_back({eq, std::move(queue), id});
 }
 
 void RenderContext::DeleteEopEq(LibKernel::EventQueue::KernelEqueue eq, int id) {
@@ -40,22 +84,27 @@ void RenderContext::DeleteEopEq(LibKernel::EventQueue::KernelEqueue eq, int id)
 		return;
 	}
 
-	if (--it->count == 0) {
-		m_eop_eqs.erase(it);
-	}
+	m_eop_eqs.erase(it);
 }
 
 void RenderContext::TriggerEopEvent(uint32_t context_id) {
-	Common::LockGuard lock(m_eop_mutex);
+	std::vector<EopEqRegistration> registrations;
+	{
+		Common::LockGuard lock(m_eop_mutex);
+		registrations = m_eop_eqs;
+	}
 
-	for (auto& eop_entry: m_eop_eqs) {
-		if (eop_entry.eq != nullptr) {
-			const auto id     = static_cast<uintptr_t>(eop_entry.id);
-			auto       result = LibKernel::EventQueue::KernelTriggerEvent(
-			    eop_entry.eq, id, LibKernel::EventQueue::KERNEL_EVFILT_GRAPHICS,
-			    reinterpret_cast<void*>(static_cast<uintptr_t>(context_id)));
-			EXIT_NOT_IMPLEMENTED(result != OK && result != LibKernel::KERNEL_ERROR_ENOENT);
+	for (const auto& registration: registrations) {
+		const auto result = LibKernel::EventQueue::KernelTriggerEvent(
+		    registration.eq, static_cast<uintptr_t>(registration.id),
+		    LibKernel::EventQueue::KERNEL_EVFILT_GRAPHICS,
+		    reinterpret_cast<void*>(static_cast<uintptr_t>(context_id)));
+		if (result == LibKernel::KERNEL_ERROR_EBADF ||
+		    result == LibKernel::KERNEL_ERROR_ENOENT) {
+			DeleteEopEq(registration.eq, registration.id);
+			continue;
 		}
+		EXIT_NOT_IMPLEMENTED(result != OK);
 	}
 
 	auto tsc    = LibKernel::KernelReadTsc();

src/graphics/host_gpu/renderer/renderContext.h

@@ -6,38 +6,47 @@
 #include "common/common.h"
 #include "common/threads.h"
 #include "graphics/host_gpu/renderer/bufferCache.h"
+#include "graphics/host_gpu/renderer/commandScheduler.h"
 #include "graphics/host_gpu/renderer/descriptorCache.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
-#include "graphics/host_gpu/renderer/gdsBuffer.h"
 #include "graphics/host_gpu/renderer/gpuResourceManager.h"
 #include "graphics/host_gpu/renderer/pipelineCache.h"
 #include "graphics/host_gpu/renderer/samplerCache.h"
 #include "graphics/host_gpu/renderer/textureCache.h"
 #include "kernel/eventQueue.h"
 
+#include <memory>
 #include <vector>
 
+namespace Libs::VideoOut {
+class VideoOutDriver;
+}
+
 namespace Libs::Graphics {
 
 constexpr int AGC_USER_INTERRUPT_EVENT = 0x1800;
+class Gpu;
 
 class RenderContext {
 public:
 	explicit RenderContext(GraphicContext& graphics);
-	~RenderContext() { KYTY_NOT_IMPLEMENTED; }
+	~RenderContext();
 	KYTY_CLASS_NO_COPY(RenderContext);
 
 	[[nodiscard]] GraphicContext& GetGraphics() const noexcept { return m_graphics; }
+	void                          InitializeGpu(VideoOut::VideoOutDriver* video_out);
+	void                          ShutdownGpu();
+	[[nodiscard]] Gpu&            GetGpu() const;
+	[[nodiscard]] VideoOut::VideoOutDriver& GetVideoOut() const;
 
 	Common::Mutex&      GetMutex() { return m_mutex; }
+	CommandScheduler&   GetCommandScheduler() { return m_command_scheduler; }
 	PipelineCache&      GetPipelineCache() { return m_pipeline_cache; }
 	DescriptorCache&    GetDescriptorCache() { return m_descriptor_cache; }
-	FramebufferCache&   GetFramebufferCache() { return m_framebuffer_cache; }
 	SamplerCache&       GetSamplerCache() { return m_sampler_cache; }
-	GdsBuffer&          GetGdsBuffer() { return m_gds_buffer; }
 	GpuResourceManager& GetGpuResources() { return m_gpu_resources; }
 	BufferCache&        GetBufferCache() { return m_gpu_resources.GetBufferCache(); }
 	TextureCache&       GetTextureCache() { return m_gpu_resources.GetTextureCache(); }
+	RenderExecutor&     GetRenderExecutor() { return m_render_executor; }
 
 	void AddEopEq(LibKernel::EventQueue::KernelEqueue eq, int id);
 	void DeleteEopEq(LibKernel::EventQueue::KernelEqueue eq, int id);
@@ -45,26 +54,26 @@ public:
 
 private:
 	struct EopEqRegistration {
-		LibKernel::EventQueue::KernelEqueue eq    = nullptr;
-		int                                 id    = 0;
-		uint32_t                            count = 0;
+		LibKernel::EventQueue::KernelEqueue    eq = LibKernel::EventQueue::KERNEL_EQUEUE_INVALID;
+		LibKernel::EventQueue::KernelEqueueRef queue;
+		int                                   id = 0;
 	};
 
-	GraphicContext&    m_graphics;
-	Common::Mutex      m_mutex;
-	PipelineCache      m_pipeline_cache;
-	DescriptorCache    m_descriptor_cache;
-	FramebufferCache   m_framebuffer_cache;
-	SamplerCache       m_sampler_cache;
-	GdsBuffer          m_gds_buffer;
-	GpuResourceManager m_gpu_resources;
+	GraphicContext&      m_graphics;
+	Common::Mutex        m_mutex;
+	RenderExecutor       m_render_executor;
+	CommandScheduler     m_command_scheduler;
+	DescriptorCache      m_descriptor_cache;
+	PipelineCache        m_pipeline_cache;
+	SamplerCache         m_sampler_cache;
+	GpuResourceManager   m_gpu_resources;
+	std::unique_ptr<Gpu> m_gpu;
+	VideoOut::VideoOutDriver* m_video_out = nullptr;
 
 	Common::Mutex                  m_eop_mutex;
 	std::vector<EopEqRegistration> m_eop_eqs;
 };
 
-[[nodiscard]] RenderContext& GetRenderContext() noexcept;
-
 } // namespace Libs::Graphics
 
 #endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_RENDERCONTEXT_H_

src/graphics/host_gpu/renderer/renderDraw.cpp

@@ -13,18 +13,15 @@
 #include "graphics/guest_gpu/hardwareContext.h"
 #include "graphics/guest_gpu/tile.h"
 #include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/objects/label.h"
 #include "graphics/host_gpu/renderer/colorRenderTarget.h"
 #include "graphics/host_gpu/renderer/debug.h"
 #include "graphics/host_gpu/renderer/depthRenderTarget.h"
 #include "graphics/host_gpu/renderer/descriptorCache.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
 #include "graphics/host_gpu/renderer/pipelineCache.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
 #include "graphics/host_gpu/renderer/shaderResourceBarrier.h"
 #include "graphics/host_gpu/renderer/shaderSubgroup.h"
-#include "graphics/host_gpu/transfer.h"
 #include "graphics/host_gpu/vulkanCommon.h"
 #include "graphics/shader/recompiler/ResourceMaterialization.h"
 #include "graphics/shader/recompiler/ShaderIR.h"
@@ -36,9 +33,12 @@
 #include <algorithm>
 #include <array>
 #include <atomic>
+#include <bit>
 #include <cmath>
 #include <cstring>
 #include <limits>
+#include <memory>
+#include <optional>
 #include <span>
 #include <unordered_map>
 #include <vector>
@@ -70,13 +70,9 @@ static std::atomic<uint32_t> g_mrt_state_log_count        = 0;
 static std::atomic<uint32_t> g_shader_stage_log_count     = 0;
 static std::atomic<uint32_t> g_framebuffer_skip_log_count = 0;
 
-static bool ResolveColorTargets(uint64_t submit_id, RenderCommandBuffer& buffer,
-                                uint32_t render_target_slice_offset);
-
 static const char* RenderColorTypeName(RenderColorType type) {
 	switch (type) {
 		case RenderColorType::NoColorOutput: return "NoColorOutput";
-		case RenderColorType::DisplayBuffer: return "DisplayBuffer";
 		case RenderColorType::RenderTexture: return "RenderTexture";
 		default: return "Unknown";
 	}
@@ -105,8 +101,8 @@ static void LogFramebufferSkip(const char* draw_name, const RenderColorInfo& col
 	    " color_image=%s depth_format=%s depth_image=%s depth_vaddr_num=%d target_mask=0x%08" PRIx32
 	    " prim=%u index_count=%u flags=0x%08" PRIx32 "\n",
 	    log_id, draw_name, RenderColorTypeName(color.type), color.base_addr, color.buffer_size,
-	    color.vulkan_buffer != nullptr ? "yes" : "no", VulkanToString(depth.format).c_str(),
-	    depth.vulkan_buffer != nullptr ? "yes" : "no", depth.vaddr_num, ctx.GetRenderTargetMask(),
+	    color.image_id ? "yes" : "no", VulkanToString(depth.format).c_str(),
+	    depth.image_id ? "yes" : "no", depth.vaddr_num, ctx.GetRenderTargetMask(),
 	    ucfg.GetPrimType(), index_count, flags);
 }
 
@@ -181,7 +177,7 @@ static void LogDrawTargetState(const char* draw_name, const RenderColorInfo& col
 	}
 
 	auto log_id = g_draw_state_log_count.fetch_add(1);
-	if (log_id >= 192 && color.type != RenderColorType::DisplayBuffer) {
+	if (log_id >= 192) {
 		return;
 	}
 
@@ -197,7 +193,7 @@ static void LogDrawTargetState(const char* draw_name, const RenderColorInfo& col
 		           image.kind == ShaderRecompiler::IR::ResourceKind::ImageUint;
 	    });
 
-	vk::Extent2D extent = color.vulkan_buffer != nullptr ? color.extent : vk::Extent2D {};
+	vk::Extent2D extent = color.image_id ? color.extent : vk::Extent2D {};
 	auto         sc     = calc_final_scissor(vp, ctx.GetScanModeControl(), extent);
 
 	LOGF(
@@ -207,12 +203,13 @@ static void LogDrawTargetState(const char* draw_name, const RenderColorInfo& col
 	    " blend=%s src=%u dst=%u comb=%u ps_tex=%d sampled=%d storage=%d ps_kill=%s target_mode0=%u"
 	    " depth_test=%s depth_write=%s depth_func=%u depth_clear=%s viewport=(%.1f,%.1f %.1fx%.1f) "
 	    "scissor=(%d,%d)-(%d,%d)\n",
-	    log_id, GraphicsRunGetFrameNum(), draw_name, RenderColorTypeName(color.type),
-	    color.base_addr, extent.width, extent.height, ucfg.GetPrimType(), index_count, flags,
-	    ctx.GetRenderTargetMask(), color.color_clear_enable ? "true" : "false",
-	    color.color_clear_value.float32[0], color.color_clear_value.float32[1],
-	    color.color_clear_value.float32[2], color.color_clear_value.float32[3], cc.mode, cc.op,
-	    bc.enable ? "true" : "false", bc.color_srcblend, bc.color_destblend, bc.color_comb_fcn,
+	    log_id, buffer.GetContext().GetGpu().GetFrameNum(), draw_name,
+	    RenderColorTypeName(color.type), color.base_addr, extent.width, extent.height,
+	    ucfg.GetPrimType(), index_count, flags, ctx.GetRenderTargetMask(),
+	    color.color_clear_enable ? "true" : "false", color.color_clear_value.float32[0],
+	    color.color_clear_value.float32[1], color.color_clear_value.float32[2],
+	    color.color_clear_value.float32[3], cc.mode, cc.op, bc.enable ? "true" : "false",
+	    bc.color_srcblend, bc.color_destblend, bc.color_comb_fcn,
 	    static_cast<int>(ps_resources.images.size()), static_cast<int>(sampled_images),
 	    static_cast<int>(ps_resources.images.size() - sampled_images),
 	    ps_input_info.ps_pixel_kill_enable ? "true" : "false", ps_input_info.target_output_mode[0],
@@ -224,20 +221,21 @@ static void LogDrawTargetState(const char* draw_name, const RenderColorInfo& col
 	LogMrtState(draw_name, buffer, ps_input_info);
 }
 
-static void LogDrawInputState(const RenderColorInfo&       color,
+static void LogDrawInputState(const RenderCommandBuffer&   buffer,
+                               const RenderColorInfo&       color,
                               const ShaderVertexInputInfo& vs_input_info,
                               uint32_t index_type_and_size, uint32_t index_count,
                               const void* index_addr) {
 	auto log_id = g_draw_input_log_count.fetch_add(1);
-	if (log_id >= 64 && color.type != RenderColorType::DisplayBuffer) {
+	if (log_id >= 64) {
 		return;
 	}
 
 	LOGF("DrawInputState[%u]: frame=%d target=%s addr=0x%010" PRIx64
 	     " index_type=%u index_count=%u index_addr=0x%016" PRIx64
 	     " vs_resources=%d vs_buffers=%d\n",
-	     log_id, GraphicsRunGetFrameNum(), RenderColorTypeName(color.type), color.base_addr,
-	     index_type_and_size, index_count, reinterpret_cast<uint64_t>(index_addr),
+	     log_id, buffer.GetContext().GetGpu().GetFrameNum(), RenderColorTypeName(color.type),
+	     color.base_addr, index_type_and_size, index_count, reinterpret_cast<uint64_t>(index_addr),
 	     vs_input_info.resources_num, vs_input_info.buffers_num);
 
 	for (int bi = 0; bi < vs_input_info.buffers_num; bi++) {
@@ -303,15 +301,6 @@ static void LogDrawInputState(const RenderColorInfo&       color,
 	}
 }
 
-static void VulkanCmdSetColorWriteEnableEXT(vk::CommandBuffer          command_buffer,
-                                            uint32_t                   attachment_count,
-                                            const vk::Bool32*          p_color_write_enables) {
-	if (VULKAN_HPP_DEFAULT_DISPATCHER.vkCmdSetColorWriteEnableEXT == nullptr) {
-		EXIT("vkCmdSetColorWriteEnableEXT not present\n");
-	}
-	command_buffer.setColorWriteEnableEXT(attachment_count, p_color_write_enables);
-}
-
 static PipelineDynamicParameters BuildGraphicsDynamicParams(const RenderCommandBuffer& buffer,
                                                             const RenderColorInfo*     colors,
                                                             uint32_t                   color_count,
@@ -325,10 +314,10 @@ static PipelineDynamicParameters BuildGraphicsDynamicParams(const RenderCommandB
 
 	const auto&  vp = ctx.GetScreenViewport();
 	vk::Extent2D framebuffer_extent {};
-	if (color_count > 0 && colors[0].vulkan_buffer != nullptr) {
+	if (color_count > 0 && colors[0].image_id) {
 		framebuffer_extent = colors[0].extent;
-	} else if (depth.vulkan_buffer != nullptr) {
-		framebuffer_extent = depth.vulkan_buffer->extent;
+	} else if (depth.image_id) {
+		framebuffer_extent = {depth.width, depth.height};
 	}
 
 	const auto final_scissor = calc_final_scissor(vp, ctx.GetScanModeControl(), framebuffer_extent);
@@ -410,7 +399,9 @@ static void SetDynamicParams(const RenderCommandBuffer& buffer, vk::CommandBuffe
 	for (uint32_t i = 0; i < dynamic_params.color_write_count; i++) {
 		enable[i] = (dynamic_params.color_write_enable[i] ? VK_TRUE : VK_FALSE);
 	}
-	VulkanCmdSetColorWriteEnableEXT(vk_buffer, dynamic_params.color_write_count, enable);
+	if (dynamic_params.color_write_count != 0) {
+		vk_buffer.setColorWriteEnableEXT(dynamic_params.color_write_count, enable);
+	}
 }
 
 static bool DrawHasValidVertexShader(const HW::Shader& sh_ctx) {
@@ -486,8 +477,7 @@ struct DrawRenderState {
 	RenderColorInfo           color_info[RENDER_COLOR_ATTACHMENTS_MAX] = {};
 	uint32_t                  color_count                              = 0;
 	bool                      ps_active                                = true;
-	VulkanFramebuffer*        framebuffer                              = nullptr;
-	vk::CommandBuffer         vk_buffer                                = nullptr;
+	RenderState               rendering;
 	ShaderVertexInputInfo     vs_input_info;
 	ShaderPixelInputInfo      ps_input_info;
 	std::span<const uint32_t> vs_shader;
@@ -503,6 +493,123 @@ struct DrawCallInfo {
 	uint32_t             first_instance = 0;
 };
 
+RenderState RenderExecutor::AcquireRenderTargets(CommandBuffer& buffer, RenderColorInfo* colors,
+                                             uint32_t color_count, RenderDepthInfo& depth) {
+	EXIT_IF(colors == nullptr || color_count > RENDER_COLOR_ATTACHMENTS_MAX);
+	auto& cache = m_context.GetTextureCache();
+	RenderState state {};
+	state.width                 = std::numeric_limits<uint32_t>::max();
+	state.height                = std::numeric_limits<uint32_t>::max();
+	state.num_layers            = std::numeric_limits<uint32_t>::max();
+	state.num_color_attachments = color_count;
+	uint32_t attachment_samples = 0;
+	for (uint32_t i = 0; i < color_count; i++) {
+		auto& target = colors[i];
+		EXIT_IF(!target.image_id);
+		const auto old_image = cache.ResolveOwner(target.image_id);
+		if (old_image == nullptr ||
+		    (!old_image->registered && !old_image->info.data.Empty()) ||
+		    old_image->binding.needs_rebind) {
+			if (old_image != nullptr) {
+				old_image->binding = {};
+			}
+			target.image_id = cache.FindImage(target.desc);
+			BindRenderTarget(target.image_id);
+		}
+		target.image_view = cache.FindRenderTarget(target.image_id, target.desc);
+		auto& image = cache.GetImage(target.image_id);
+		EXIT_IF(image.backing.samples != target.samples || target.image_view == nullptr);
+		if (attachment_samples == 0) {
+			attachment_samples = target.samples;
+		} else if (attachment_samples != target.samples) {
+			EXIT("mixed color attachment sample counts are unsupported: %u and %u\n",
+			     attachment_samples, target.samples);
+		}
+		const auto& view = target.desc.view_info;
+		const auto layout =
+		    image.binding.is_bound ? vk::ImageLayout::eGeneral
+		                           : vk::ImageLayout::eColorAttachmentOptimal;
+		image.Transit(layout,
+		              vk::AccessFlagBits2::eColorAttachmentRead |
+		                  vk::AccessFlagBits2::eColorAttachmentWrite,
+		              ImageSubresourceRange {view.base_level, view.level_count, view.base_layer,
+		                                     view.layer_count},
+		              buffer.Handle());
+		state.width      = std::min(state.width, target.extent.width);
+		state.height     = std::min(state.height, target.extent.height);
+		state.num_layers = std::min(state.num_layers, view.layer_count);
+		auto& attachment = state.color_attachments[i];
+		attachment.image_view   = target.image_view;
+		attachment.image_layout = layout;
+		attachment.clear_value  = target.color_clear_value.uint32;
+		attachment.is_clear     = target.color_clear_enable;
+	}
+	if (depth.image_id) {
+		const auto owner = cache.ResolveOwner(depth.image_id);
+		if (owner == nullptr || !owner->registered || owner->binding.needs_rebind) {
+			EXIT("depth target changed after render-state discovery\n");
+		}
+		depth.image_view = cache.FindDepthTarget(depth.image_id, depth.desc);
+		if (depth.htile && depth.depth_clear_enable && !cache.ClearMeta(depth.htile_buffer_vaddr)) {
+			EXIT("failed to acquire HTile metadata for a depth clear\n");
+		}
+		depth.depth_meta_clear_enable =
+		    depth.htile &&
+		    cache.IsMetaCleared(depth.htile_buffer_vaddr, depth.desc.view_info.base_layer);
+		depth.depth_load_clear_enable =
+		    depth.depth_clear_enable || depth.depth_meta_clear_enable;
+		if (depth.depth_meta_clear_enable &&
+		    !cache.TouchMeta(depth.htile_buffer_vaddr, depth.desc.view_info.base_layer, false)) {
+			EXIT("failed to consume HTile clear state\n");
+		}
+		auto& image = cache.GetImage(depth.image_id);
+		EXIT_IF(depth.image_view == nullptr || image.backing.samples != depth.samples);
+		if (attachment_samples == 0) {
+			attachment_samples = depth.samples;
+		} else if (attachment_samples != depth.samples) {
+			EXIT("mixed color/depth sample counts are unsupported: %u and %u\n",
+			     attachment_samples, depth.samples);
+		}
+		const auto layout = depth_attachment_layout(depth);
+		const auto writes = depth.AttachmentWriteAspects();
+		auto access = vk::AccessFlags2 {vk::AccessFlagBits2::eDepthStencilAttachmentRead};
+		if (writes) {
+			access |= vk::AccessFlagBits2::eDepthStencilAttachmentWrite;
+		}
+		const auto& view = depth.desc.view_info;
+		image.Transit(layout, access,
+		              ImageSubresourceRange {view.base_level, view.level_count, view.base_layer,
+		                                     view.layer_count},
+		              buffer.Handle());
+		state.width      = std::min(state.width, depth.width);
+		state.height     = std::min(state.height, depth.height);
+		state.num_layers = std::min(state.num_layers, view.layer_count);
+		const auto aspects = ImageViewOps::DepthAspectMask(depth.format);
+		auto& attachment = state.depth_stencil_attachment;
+		attachment.image_view     = depth.image_view;
+		attachment.image_layout   = layout;
+		attachment.clear_value[0] = std::bit_cast<uint32_t>(depth.depth_clear_value);
+		attachment.clear_value[1] = depth.stencil_clear_value;
+		attachment.has_depth =
+		    static_cast<bool>(aspects & vk::ImageAspectFlagBits::eDepth);
+		attachment.depth_clear = depth.depth_load_clear_enable;
+		attachment.has_stencil =
+		    static_cast<bool>(aspects & vk::ImageAspectFlagBits::eStencil);
+		attachment.stencil_clear = depth.stencil_clear_enable;
+	}
+	if (attachment_samples == 0 ||
+	    vulkan_sample_count(attachment_samples) == vk::SampleCountFlagBits {}) {
+		EXIT("render state has no valid attachments\n");
+	}
+	if (state.num_layers == std::numeric_limits<uint32_t>::max()) {
+		state.num_layers = 1;
+	}
+	EXIT_IF(state.width == 0 || state.height == 0 || state.num_layers == 0 ||
+	        state.width == std::numeric_limits<uint32_t>::max() ||
+	        state.height == std::numeric_limits<uint32_t>::max());
+	return state;
+}
+
 static bool DrawHasActivePixelShader(const RenderCommandBuffer& buffer,
                                      const DrawRenderState& state, const DrawCallInfo& draw) {
 	EXIT_IF(draw.name == nullptr);
@@ -510,7 +617,7 @@ static bool DrawHasActivePixelShader(const RenderCommandBuffer& buffer,
 	const auto& sh_ctx = buffer.GetShaders();
 
 	const bool with_depth = (state.depth_info.format != vk::Format::eUndefined &&
-	                         state.depth_info.vulkan_buffer != nullptr);
+	                         static_cast<bool>(state.depth_info.image_id));
 	if (state.color_count != 0 || !with_depth) {
 		return true;
 	}
@@ -558,6 +665,16 @@ struct DrawIndexBufferSource {
 	vk::IndexType type      = vk::IndexType::eUint16;
 };
 
+struct PreparedIndexBuffer {
+	std::shared_ptr<void> owner;
+	vk::Buffer            buffer   = nullptr;
+	uint64_t              address  = 0;
+	uint64_t              size     = 0;
+	vk::DeviceSize        offset   = 0;
+	vk::IndexType         type     = vk::IndexType::eUint16;
+	bool                  streamed = false;
+};
+
 static uint64_t VertexBufferDescriptorSize(const ShaderVertexInputBuffer& buffer) {
 	return (buffer.stride != 0 ? static_cast<uint64_t>(buffer.stride) * buffer.num_records
 	                           : buffer.num_records);
@@ -613,24 +730,16 @@ static bool GetDrawTopology(const HW::UserConfig& ucfg, bool auto_draw, bool use
 	return true;
 }
 
-static bool PrepareDrawRenderState(uint64_t submit_id, RenderCommandBuffer& buffer,
-                                   const DrawCallInfo& draw, uint32_t render_target_slice_offset,
-                                   bool skip_null_framebuffer, bool log_setup_phases,
-                                   DrawRenderState& state) {
+bool RenderExecutor::PrepareDrawRenderState(uint64_t submit_id, RenderCommandBuffer& buffer,
+                                        const DrawCallInfo& draw,
+                                        uint32_t render_target_slice_offset,
+                                        bool log_setup_phases, DrawRenderState& state) {
 	EXIT_IF(draw.name == nullptr);
 	auto& ctx = buffer.GetRegisters();
 
-	if (log_setup_phases) {
-		LogDrawPhase(draw.name, "ResolveRenderDepthTarget");
-	}
-	ResolveRenderDepthTarget(submit_id, buffer, state.depth_info);
-
 	if (ResolveColorTargets(submit_id, buffer, render_target_slice_offset)) {
-		MarkRenderTargetGpuWritten(state.depth_info);
 		return false;
 	}
-	MarkRenderTargetGpuWritten(state.depth_info);
-
 	if (log_setup_phases) {
 		LogDrawPhase(draw.name, "ResolveRenderColorTarget");
 	}
@@ -639,15 +748,18 @@ static bool PrepareDrawRenderState(uint64_t submit_id, RenderCommandBuffer& buff
 		                  ctx.GetRenderTarget(slot).base.addr != 0)) {
 			ResolveRenderColorTarget(submit_id, buffer, state.color_info[state.color_count],
 			                         render_target_slice_offset, slot);
-			if (state.color_info[state.color_count].vulkan_buffer != nullptr) {
-				MarkRenderTargetGpuWritten(state.color_info[state.color_count]);
+			if (state.color_info[state.color_count].image_id) {
 				state.color_count++;
 			}
 		}
 	}
+	if (log_setup_phases) {
+		LogDrawPhase(draw.name, "ResolveRenderDepthTarget");
+	}
+	ResolveRenderDepthTarget(submit_id, buffer, state.depth_info);
 
 	const bool with_depth = (state.depth_info.format != vk::Format::eUndefined &&
-	                         state.depth_info.vulkan_buffer != nullptr);
+	                         static_cast<bool>(state.depth_info.image_id));
 	if (state.color_count == 0 && !with_depth) {
 		LogFramebufferSkip(draw.name, state.color_info[0], state.depth_info, buffer,
 		                   draw.index_count, draw.flags);
@@ -655,22 +767,6 @@ static bool PrepareDrawRenderState(uint64_t submit_id, RenderCommandBuffer& buff
 	}
 	state.ps_active = DrawHasActivePixelShader(buffer, state, draw);
 
-	if (log_setup_phases) {
-		LogDrawPhase(draw.name, "CreateFramebuffer");
-	}
-	state.framebuffer = GetRenderContext().GetFramebufferCache().CreateFramebuffer(
-	    state.color_info, state.color_count, state.depth_info);
-
-	if (state.framebuffer == nullptr && skip_null_framebuffer) {
-		LogFramebufferSkip(draw.name, state.color_info[0], state.depth_info, buffer,
-		                   draw.index_count, draw.flags);
-		return false;
-	}
-	EXIT_NOT_IMPLEMENTED(state.framebuffer == nullptr);
-	EXIT_NOT_IMPLEMENTED(state.framebuffer->render_pass == nullptr);
-
-	state.vk_buffer = buffer.Handle();
-
 	return true;
 }
 
@@ -714,56 +810,107 @@ static void RefreshShaders(RenderCommandBuffer& buffer, const DrawCallInfo& draw
 	}
 }
 
-static void BindDrawVertexBuffers(uint64_t submit_id, RenderCommandBuffer& buffer,
-                                  const DrawCallInfo& draw, vk::CommandBuffer vk_buffer,
-                                  const ShaderVertexInputInfo& vs_input_info) {
+static std::vector<BufferBinding> PrepareVertexBuffers(uint64_t                     submit_id,
+                                                       RenderCommandBuffer&         buffer,
+                                                       const DrawCallInfo&          draw,
+                                                       const ShaderVertexInputInfo& vs_input_info) {
 	EXIT_IF(draw.name == nullptr);
 	(void)submit_id;
 
-	LogDrawPhase(draw.name, "BindVertexBuffers");
+	LogDrawPhase(draw.name, "PrepareVertexBuffers");
+	std::vector<BufferBinding> bindings;
+	bindings.reserve(vs_input_info.buffers_num);
 	for (int i = 0; i < vs_input_info.buffers_num; i++) {
-		const auto&    b        = vs_input_info.buffers[i];
-		uint64_t       addr     = b.addr;
-		uint64_t       size     = VertexBufferDescriptorSize(b);
-		VulkanBuffer*  vertices = nullptr;
-		vk::DeviceSize offset   = 0;
-
+		const auto& b    = vs_input_info.buffers[i];
+		const auto  size = VertexBufferDescriptorSize(b);
 		if (size == 0) {
-			vertices = &GetRenderContext().GetBufferCache().ObtainNullBuffer(buffer);
+			auto owner = buffer.GetContext().GetBufferCache().ObtainNullBuffer();
+			bindings.push_back({owner, owner->Handle(), 0});
 		} else {
-			auto binding = GetRenderContext().GetBufferCache().ObtainBuffer(buffer, addr, size);
-			vertices     = &binding.buffer;
-			offset       = binding.offset;
+			bindings.push_back(
+			    buffer.GetContext().GetBufferCache().ObtainBuffer(buffer, b.addr, size));
 		}
-		EXIT_NOT_IMPLEMENTED(vertices == nullptr);
+	}
+	return bindings;
+}
 
-		vk_buffer.bindVertexBuffers(i, 1, &vertices->buffer, &offset);
+static void RebindVertexBuffers(RenderCommandBuffer&         buffer,
+                                const ShaderVertexInputInfo& vs_input_info,
+                                std::vector<BufferBinding>&  bindings) {
+	EXIT_IF(bindings.size() != static_cast<size_t>(vs_input_info.buffers_num));
+	for (int i = 0; i < vs_input_info.buffers_num; i++) {
+		const auto& vertex = vs_input_info.buffers[i];
+		const auto  size   = VertexBufferDescriptorSize(vertex);
+		if (size == 0) {
+			auto owner  = buffer.GetContext().GetBufferCache().ObtainNullBuffer();
+			bindings[i] = {owner, owner->Handle(), 0};
+		} else {
+			bindings[i] =
+			    buffer.GetContext().GetBufferCache().ObtainBuffer(buffer, vertex.addr, size);
+		}
 	}
 }
 
-static void BindDrawIndexBuffer(RenderCommandBuffer& buffer, vk::CommandBuffer vk_buffer,
-                                const DrawIndexBufferSource& source) {
+static PreparedIndexBuffer PrepareIndexBuffer(RenderCommandBuffer&         buffer,
+                                              const DrawIndexBufferSource& source) {
+	PreparedIndexBuffer prepared;
 	if (!source.enabled) {
-		return;
+		return prepared;
 	}
 	EXIT_IF(source.size == 0);
-
-	VulkanBuffer*  index_buffer = nullptr;
-	vk::DeviceSize index_offset = 0;
+	prepared.address = source.address;
+	prepared.size    = source.size;
+	prepared.type    = source.type;
 	if (source.host_data != nullptr) {
-		vk::DeviceSize range = 0;
-		if (!GetRenderContext().GetBufferCache().UploadHostData(
-		        buffer, source.host_data, source.size, 16, index_buffer, index_offset, range)) {
-			EXIT("failed to upload host index buffer\n");
-		}
+		auto binding =
+		    buffer.GetContext().GetBufferCache().UploadTransient(source.host_data, source.size, 16);
+		prepared.owner    = std::move(binding.owner);
+		prepared.buffer   = binding.buffer;
+		prepared.offset   = binding.offset;
+		prepared.streamed = true;
 	} else {
 		auto binding =
-		    GetRenderContext().GetBufferCache().ObtainBuffer(buffer, source.address, source.size);
-		index_buffer = &binding.buffer;
-		index_offset = binding.offset;
+		    buffer.GetContext().GetBufferCache().ObtainBuffer(buffer, source.address, source.size);
+		prepared.owner  = std::move(binding.owner);
+		prepared.buffer = binding.buffer;
+		prepared.offset = binding.offset;
 	}
-	EXIT_IF(index_buffer == nullptr);
-	vk_buffer.bindIndexBuffer(index_buffer->buffer, index_offset, source.type);
+	return prepared;
+}
+
+static void RebindIndexBuffer(RenderCommandBuffer& buffer, PreparedIndexBuffer& prepared) {
+	if (prepared.size == 0 || prepared.streamed) {
+		return;
+	}
+	auto binding =
+	    buffer.GetContext().GetBufferCache().ObtainBuffer(buffer, prepared.address, prepared.size);
+	prepared.owner  = std::move(binding.owner);
+	prepared.buffer = binding.buffer;
+	prepared.offset = binding.offset;
+}
+
+static void CommitVertexBuffers(RenderCommandBuffer& buffer, vk::CommandBuffer vk_buffer,
+                                std::vector<BufferBinding>& bindings) {
+	for (uint32_t slot = 0; slot < bindings.size(); slot++) {
+		auto& binding = bindings[slot];
+		if (binding.owner != nullptr) {
+			buffer.RetainResourceUntilFence(binding.owner);
+		}
+		EXIT_IF(binding.buffer == nullptr);
+		vk_buffer.bindVertexBuffers(slot, 1, &binding.buffer, &binding.offset);
+	}
+}
+
+static void CommitIndexBuffer(RenderCommandBuffer& buffer, vk::CommandBuffer vk_buffer,
+                              const PreparedIndexBuffer& prepared) {
+	if (prepared.size == 0) {
+		return;
+	}
+	if (prepared.owner != nullptr) {
+		buffer.RetainResourceUntilFence(prepared.owner);
+	}
+	EXIT_IF(prepared.buffer == nullptr);
+	vk_buffer.bindIndexBuffer(prepared.buffer, prepared.offset, prepared.type);
 }
 
 static void LogDrawStateIfNeeded(const RenderCommandBuffer& buffer, const DrawCallInfo& draw,
@@ -784,7 +931,7 @@ static void LogDrawStateIfNeeded(const RenderCommandBuffer& buffer, const DrawCa
 		LogDrawTargetState(draw.name, state.color_info[0], state.depth_info, buffer,
 		                   state.ps_input_info, draw.index_count, draw.flags);
 	}
-	LogDrawInputState(state.color_info[0], state.vs_input_info, index_type_and_size,
+	LogDrawInputState(buffer, state.color_info[0], state.vs_input_info, index_type_and_size,
 	                  draw.index_count, index_addr);
 	// LogDrawTextureState(draw.name, state.color_info[0], state.ps_input_info);
 }
@@ -858,102 +1005,94 @@ static void EmitDrawPrimitives(const HW::UserConfig& ucfg, vk::CommandBuffer vk_
 	}
 }
 
-static void ExecutePreparedDraw(uint64_t submit_id, RenderCommandBuffer& buffer,
-                                const DrawCallInfo& draw, DrawRenderState& state,
-                                vk::PrimitiveTopology topology, const DrawEmitInfo& emit,
-                                const DrawIndexBufferSource& index_source, bool log_pipeline_phase,
-                                bool set_bind_debug, bool set_auto_debug) {
+void RenderExecutor::ExecutePreparedDraw(uint64_t submit_id, RenderCommandBuffer& buffer,
+                                     const DrawCallInfo& draw, DrawRenderState& state,
+                                     vk::PrimitiveTopology topology, const DrawEmitInfo& emit,
+                                     const DrawIndexBufferSource& index_source,
+                                     bool log_pipeline_phase, bool set_bind_debug,
+                                     bool set_auto_debug) {
 	EXIT_IF(draw.name == nullptr);
 	auto& ucfg = buffer.GetUserConfig();
 
-	for (;;) {
-		const auto recording_generation = buffer.GetRecordingGeneration();
-		if (log_pipeline_phase) {
-			LogDrawPhase(draw.name, "CreatePipeline");
-		}
-		auto& pipeline = GetRenderContext().GetPipelineCache().CreateGraphicsPipeline(
-		    *state.framebuffer, state.color_info, state.color_count, state.depth_info,
-		    state.vs_input_info, buffer, &state.ps_input_info, topology, state.ps_active,
-		    state.vs_shader, state.ps_shader);
+	LogDrawPhase(draw.name, "PrepareBindings");
+	auto bindings = PrepareGraphicsBindings(buffer, state.vs_input_info.stage,
+	                                        state.ps_input_info.stage, state.ps_active);
+	auto vertex_bindings = PrepareVertexBuffers(submit_id, buffer, draw, state.vs_input_info);
+	auto index_binding   = PrepareIndexBuffer(buffer, index_source);
+	RebindVertexBuffers(buffer, state.vs_input_info, vertex_bindings);
+	RebindIndexBuffer(buffer, index_binding);
+	state.rendering =
+	    AcquireRenderTargets(buffer, state.color_info, state.color_count, state.depth_info);
 
-		if (set_bind_debug) {
-			SetDrawDebugPhase(buffer, submit_id, draw, 0x100u);
-		}
-		state.vk_buffer.bindPipeline(vk::PipelineBindPoint::eGraphics, pipeline.pipeline);
-		const auto dynamic_params = BuildGraphicsDynamicParams(buffer, state.color_info,
-		                                                       state.color_count, state.depth_info);
-		SetDynamicParams(buffer, state.vk_buffer, dynamic_params);
+	if (log_pipeline_phase) {
+		LogDrawPhase(draw.name, "CreatePipeline");
+	}
+	auto& pipeline = m_context.GetPipelineCache().CreateGraphicsPipeline(
+	    state.color_info, state.color_count, state.depth_info, state.vs_input_info, buffer,
+	    &state.ps_input_info, topology, state.ps_active, state.vs_shader, state.ps_shader);
 
-		// EXIT_NOT_IMPLEMENTED(vs_input_info.buffers_num > 1);
-		BindDrawVertexBuffers(submit_id, buffer, draw, state.vk_buffer, state.vs_input_info);
-
-		LogDrawPhase(draw.name, "BindDescriptorsVS");
+	// Resource preparation above may synchronously finish and restart the scheduler. From this
+	// point onward, every operation targets the current command buffer and cannot touch guest
+	// memory.
+	auto vk_buffer = buffer.Handle();
+	if (set_bind_debug) {
+		SetDrawDebugPhase(buffer, submit_id, draw, 0x100u);
+	}
+	if (set_auto_debug) {
+		SetDrawDebugPhase(buffer, submit_id, draw, 0x200u);
+	}
+	CommitVertexBuffers(buffer, vk_buffer, vertex_bindings);
+	CommitBindings(buffer, vk::PipelineBindPoint::eGraphics, pipeline.pipeline_layout,
+	               bindings.vertex);
+	if (bindings.pixel.has_value()) {
 		if (set_auto_debug) {
-			SetDrawDebugPhase(buffer, submit_id, draw, 0x200u);
+			SetDrawDebugPhase(buffer, submit_id, draw, 0x300u);
 		}
-		BindDescriptors(submit_id, buffer, vk::PipelineBindPoint::eGraphics,
-		                pipeline.pipeline_layout, state.vs_input_info.stage,
-		                vk::ShaderStageFlagBits::eVertex, DescriptorCache::Stage::Vertex);
+		CommitBindings(buffer, vk::PipelineBindPoint::eGraphics, pipeline.pipeline_layout,
+		               *bindings.pixel);
+	}
+	CommitIndexBuffer(buffer, vk_buffer, index_binding);
 
-		if (state.ps_active) {
-			LogDrawPhase(draw.name, "BindDescriptorsPS");
-			if (set_auto_debug) {
-				SetDrawDebugPhase(buffer, submit_id, draw, 0x300u);
-			}
-			BindDescriptors(submit_id, buffer, vk::PipelineBindPoint::eGraphics,
-			                pipeline.pipeline_layout, state.ps_input_info.stage,
-			                vk::ShaderStageFlagBits::eFragment, DescriptorCache::Stage::Pixel);
-		}
-		if (buffer.GetRecordingGeneration() != recording_generation) {
-			continue;
-		}
-		// Index data may use this command buffer's host stream. Resolve it only after the other
-		// fault-capable bindings, and rebuild it whenever a fault reset changes the generation.
-		BindDrawIndexBuffer(buffer, state.vk_buffer, index_source);
-		if (buffer.GetRecordingGeneration() != recording_generation) {
-			continue;
-		}
+	const auto dynamic_params =
+	    BuildGraphicsDynamicParams(buffer, state.color_info, state.color_count, state.depth_info);
+	SetDynamicParams(buffer, vk_buffer, dynamic_params);
 
-		LogDrawPhase(draw.name, "BeginRenderPass");
-		if (set_auto_debug) {
-			SetDrawDebugPhase(buffer, submit_id, draw, 0x400u);
-		}
-		buffer.BeginRenderPass(*state.framebuffer, state.color_info, state.color_count,
-		                       state.depth_info);
-		if (set_auto_debug) {
-			SetDrawDebugPhase(buffer, submit_id, draw, 0x500u);
-		}
+	LogDrawPhase(draw.name, "BeginRendering");
+	if (set_auto_debug) {
+		SetDrawDebugPhase(buffer, submit_id, draw, 0x400u);
+	}
+	m_context.GetCommandScheduler().BeginRendering(state.rendering);
+	vk_buffer.bindPipeline(vk::PipelineBindPoint::eGraphics, pipeline.pipeline);
+	if (set_auto_debug) {
+		SetDrawDebugPhase(buffer, submit_id, draw, 0x500u);
+	}
+	EmitDrawPrimitives(ucfg, vk_buffer, state.vs_input_info, draw, emit);
 
-		EmitDrawPrimitives(ucfg, state.vk_buffer, state.vs_input_info, draw, emit);
-
-		if (set_auto_debug) {
-			SetDrawDebugPhase(buffer, submit_id, draw, 0x600u);
-		}
-		buffer.EndRenderPass();
-		vk::PipelineStageFlags shader_write_stages = {};
-		if (HasShaderBufferWrites(state.vs_input_info.stage)) {
-			shader_write_stages |= vk::PipelineStageFlagBits::eVertexShader;
-		}
-		if (state.ps_active) {
-			if (HasShaderBufferWrites(state.ps_input_info.stage)) {
-				shader_write_stages |= vk::PipelineStageFlagBits::eFragmentShader;
-			}
-		}
-		if (shader_write_stages) {
-			ShaderWriteBarrier(state.vk_buffer, shader_write_stages);
-		}
-		LogDrawPhase(draw.name, "EndRenderPass");
-		if (set_auto_debug) {
-			SetDrawDebugPhase(buffer, submit_id, draw, 0x700u);
-		}
-		break;
+	if (set_auto_debug) {
+		SetDrawDebugPhase(buffer, submit_id, draw, 0x600u);
+	}
+	vk::PipelineStageFlags shader_write_stages = {};
+	if (HasShaderBufferWrites(state.vs_input_info.stage)) {
+		shader_write_stages |= vk::PipelineStageFlagBits::eVertexShader;
+	}
+	if (state.ps_active && HasShaderBufferWrites(state.ps_input_info.stage)) {
+		shader_write_stages |= vk::PipelineStageFlagBits::eFragmentShader;
+	}
+	if (shader_write_stages) {
+		m_context.GetCommandScheduler().EndRendering();
+		ShaderWriteBarrier(vk_buffer, shader_write_stages);
+	}
+	LogDrawPhase(draw.name, "DrawComplete");
+	if (set_auto_debug) {
+		SetDrawDebugPhase(buffer, submit_id, draw, 0x700u);
 	}
 }
 
-void RenderDrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t index_type_and_size,
-                     uint32_t index_count, const void* index_addr, uint32_t flags, uint32_t type,
-                     uint32_t instance_count, uint32_t render_target_slice_offset,
-                     int32_t vertex_offset_add, uint32_t first_instance) {
+void RenderExecutor::DrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer,
+                           uint32_t index_type_and_size, uint32_t index_count,
+                           const void* index_addr, uint32_t flags, uint32_t type,
+                           uint32_t instance_count, uint32_t render_target_slice_offset,
+                           int32_t vertex_offset_add, uint32_t first_instance) {
 	KYTY_PROFILER_FUNCTION();
 
 	EXIT_IF(buffer.IsInvalid());
@@ -964,13 +1103,13 @@ void RenderDrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t i
 	                    index_count, flags, type, instance_count,
 	                    reinterpret_cast<uint64_t>(index_addr));
 
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-
+	Common::LockGuard lock(m_context.GetMutex());
 	if (index_count == 0) {
 		return;
 	}
 
 	if (ConsumeMetadataColorOperation(buffer)) {
+		ResetBindings();
 		return;
 	}
 
@@ -1001,7 +1140,6 @@ void RenderDrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t i
 		     instance_count, render_target_slice_offset, static_cast<uint32_t>(vertex_offset_add),
 		     first_instance);
 	}
-	sh_check(sh_ctx);
 
 	uc_check(ucfg);
 
@@ -1063,8 +1201,8 @@ void RenderDrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t i
 	index_source.type = index_type;
 
 	DrawRenderState state {};
-	if (!PrepareDrawRenderState(submit_id, buffer, draw, render_target_slice_offset, false, true,
-	                            state)) {
+	if (!PrepareDrawRenderState(submit_id, buffer, draw, render_target_slice_offset, true, state)) {
+		ResetBindings();
 		return;
 	}
 
@@ -1081,12 +1219,15 @@ void RenderDrawIndex(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t i
 
 	ExecutePreparedDraw(submit_id, buffer, draw, state, topology, emit, index_source, true, true,
 	                    false);
+	ResetBindings();
 }
 
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
-void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32_t index_count,
-                         uint32_t flags, uint32_t render_target_slice_offset,
-                         uint32_t instance_count, uint32_t first_vertex, uint32_t first_instance) {
+void RenderExecutor::DrawAuto(uint64_t submit_id, RenderCommandBuffer& buffer,
+                              uint32_t index_count,
+                          uint32_t flags, uint32_t render_target_slice_offset,
+                          uint32_t instance_count, uint32_t first_vertex,
+                          uint32_t first_instance) {
 	KYTY_PROFILER_FUNCTION();
 
 	EXIT_IF(buffer.IsInvalid());
@@ -1096,13 +1237,13 @@ void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32
 	buffer.SetDebugInfo(static_cast<uint32_t>(CommandBufferDebugOp::DrawIndexAuto), submit_id,
 	                    index_count, flags, first_vertex, instance_count, first_instance);
 
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-
+	Common::LockGuard lock(m_context.GetMutex());
 	if (index_count == 0) {
 		return;
 	}
 
 	if (ConsumeMetadataColorOperation(buffer)) {
+		ResetBindings();
 		return;
 	}
 
@@ -1129,7 +1270,6 @@ void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32
 		     index_count, flags, render_target_slice_offset, instance_count, first_vertex,
 		     first_instance);
 	}
-	sh_check(sh_ctx);
 
 	uc_check(ucfg);
 
@@ -1145,8 +1285,8 @@ void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32
 	                         instance_count,  first_instance};
 
 	DrawRenderState state {};
-	if (!PrepareDrawRenderState(submit_id, buffer, draw, render_target_slice_offset, true, false,
-	                            state)) {
+	if (!PrepareDrawRenderState(submit_id, buffer, draw, render_target_slice_offset, false, state)) {
+		ResetBindings();
 		return;
 	}
 
@@ -1154,6 +1294,7 @@ void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32
 	const bool            use_ngg_rectlist_draw = Config::NggRectlistDrawEnabled();
 
 	if (!GetDrawTopology(ucfg, true, use_ngg_rectlist_draw, topology)) {
+		ResetBindings();
 		return;
 	}
 	const bool draw_prim7_as_ngg =
@@ -1170,6 +1311,7 @@ void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32
 			     state.ps_input_info.input_num, sh_ctx.GetPs().ps_regs.chksum,
 			     sh_ctx.GetVs().es_regs.data_addr, sh_ctx.GetVs().gs_regs.data_addr);
 		}
+		ResetBindings();
 		return;
 	}
 
@@ -1189,27 +1331,11 @@ void RenderDrawIndexAuto(uint64_t submit_id, RenderCommandBuffer& buffer, uint32
 	DrawIndexBufferSource index_source {};
 	ExecutePreparedDraw(submit_id, buffer, draw, state, topology, emit, index_source, false, false,
 	                    true);
+	ResetBindings();
 }
 
-bool IsSameColorResolveSubresource(const RenderColorInfo& src, const RenderColorInfo& dst) {
-	return src.base_addr == dst.base_addr && src.base_mip_level == dst.base_mip_level &&
-	       src.base_array_layer == dst.base_array_layer;
-}
-
-ImageImageCopy MakeColorResolveCopy(const RenderColorInfo& src, const RenderColorInfo& dst,
-                                    uint32_t width, uint32_t height) {
-	ImageImageCopy region {*src.vulkan_buffer};
-	region.src_level = src.base_mip_level;
-	region.dst_level = dst.base_mip_level;
-	region.width     = width;
-	region.height    = height;
-	region.src_layer = src.base_array_layer;
-	region.dst_layer = dst.base_array_layer;
-	return region;
-}
-
-static bool ResolveColorTargets(uint64_t submit_id, RenderCommandBuffer& buffer,
-                                uint32_t render_target_slice_offset) {
+bool RenderExecutor::ResolveColorTargets(uint64_t submit_id, RenderCommandBuffer& buffer,
+                                     uint32_t render_target_slice_offset) {
 	const auto& hw = buffer.GetRegisters();
 	if (hw.GetColorControl().mode != 3) {
 		return false;
@@ -1224,25 +1350,23 @@ static bool ResolveColorTargets(uint64_t submit_id, RenderCommandBuffer& buffer,
 	RenderColorInfo src {};
 	RenderColorInfo dst {};
 	ResolveRenderColorTarget(submit_id, buffer, src, render_target_slice_offset, 0, true, true);
-	ResolveRenderColorTarget(submit_id, buffer, dst, render_target_slice_offset, 1, true);
-	if (src.vulkan_buffer == nullptr || dst.vulkan_buffer == nullptr ||
-	    src.type == RenderColorType::NoColorOutput || dst.type == RenderColorType::NoColorOutput) {
+	ResolveRenderColorTarget(submit_id, buffer, dst, render_target_slice_offset, 1, true, true);
+	if (!src.image_id || !dst.image_id || src.type == RenderColorType::NoColorOutput ||
+	    dst.type == RenderColorType::NoColorOutput) {
 		return false;
 	}
-	if (IsSameColorResolveSubresource(src, dst)) {
+	if (src.base_addr == dst.base_addr && src.base_mip_level == dst.base_mip_level &&
+	    src.base_array_layer == dst.base_array_layer) {
 		return true;
 	}
 
-	const uint32_t width  = std::min(src.extent.width, dst.extent.width);
-	const uint32_t height = std::min(src.extent.height, dst.extent.height);
-	if (width == 0 || height == 0) {
-		return false;
-	}
-
-	const std::array regions {MakeColorResolveCopy(src, dst, width, height)};
-
-	MarkRenderTargetGpuWritten(dst);
-	Transfer::CopyImage(buffer, regions, *dst.vulkan_buffer, dst.vulkan_buffer->layout);
+	auto& cache = m_context.GetTextureCache();
+	cache.MarkGpuWritten(dst.image_id);
+	auto& source      = cache.GetImage(src.image_id);
+	auto& destination = cache.GetImage(dst.image_id);
+	destination.Resolve(source,
+	                    {src.base_mip_level, 1, src.base_array_layer, 1},
+	                    {dst.base_mip_level, 1, dst.base_array_layer, 1});
 	return true;
 }
 

src/graphics/host_gpu/renderer/renderDraw.h

@@ -8,7 +8,6 @@
 
 namespace Libs::Graphics {
 
-struct ImageImageCopy;
 struct RenderColorInfo;
 struct ShaderVertexInputInfo;
 
@@ -39,13 +38,8 @@ static_assert(sizeof(PipelineDynamicParameters) ==
                   sizeof(uint32_t) + sizeof(bool[RENDER_COLOR_ATTACHMENTS_MAX]) +
                   sizeof(PipelineStencilDynamicState) * 2);
 
-[[nodiscard]] bool           IsSameColorResolveSubresource(const RenderColorInfo& src,
-                                                           const RenderColorInfo& dst);
-[[nodiscard]] ImageImageCopy MakeColorResolveCopy(const RenderColorInfo& src,
-                                                  const RenderColorInfo& dst, uint32_t width,
-                                                  uint32_t height);
-[[nodiscard]] int32_t        ResolveVertexOffset(uint32_t                     index_offset,
-                                                 const ShaderVertexInputInfo& vs_input_info);
+[[nodiscard]] int32_t ResolveVertexOffset(uint32_t                     index_offset,
+                                          const ShaderVertexInputInfo& vs_input_info);
 
 } // namespace Libs::Graphics
 

src/graphics/host_gpu/renderer/renderTarget.h

@@ -3,6 +3,7 @@
 
 #include "graphics/host_gpu/vulkanCommon.h"
 
+#include <array>
 #include <cstdint>
 #include <type_traits>
 
@@ -10,6 +11,30 @@ namespace Libs::Graphics {
 
 static constexpr uint32_t RENDER_COLOR_ATTACHMENTS_MAX = 8;
 
+struct RenderAttachment {
+	vk::ImageView           image_view   = nullptr;
+	vk::ImageLayout         image_layout = vk::ImageLayout::eUndefined;
+	std::array<uint32_t, 4> clear_value  = {};
+	bool                    is_clear      = false;
+	bool                    has_depth    = false;
+	bool                    depth_clear  = false;
+	bool                    has_stencil  = false;
+	bool                    stencil_clear = false;
+
+	bool operator==(const RenderAttachment&) const = default;
+};
+
+struct RenderState {
+	std::array<RenderAttachment, RENDER_COLOR_ATTACHMENTS_MAX> color_attachments;
+	RenderAttachment                                           depth_stencil_attachment;
+	uint32_t                                                   width                 = 0;
+	uint32_t                                                   height                = 0;
+	uint32_t                                                   num_layers            = 1;
+	uint32_t                                                   num_color_attachments = 0;
+
+	bool operator==(const RenderState&) const = default;
+};
+
 [[nodiscard]] inline constexpr uint32_t render_sample_count(uint32_t encoded_samples) {
 	return encoded_samples <= 3 ? 1u << encoded_samples : 0;
 }

src/graphics/host_gpu/renderer/renderTargetBarriers.cpp

@@ -1,221 +0,0 @@
-#include "graphics/host_gpu/renderer/renderTargetBarriers.h"
-
-#include "common/assert.h"
-#include "common/common.h"
-#include "common/logging/log.h"
-#include "common/profiler.h"
-#include "common/stringUtils.h"
-#include "common/threads.h"
-#include "graphics/guest_gpu/gpu_defs.h"
-#include "graphics/guest_gpu/hardwareContext.h"
-#include "graphics/guest_gpu/tile.h"
-#include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/objects/textureCommon.h"
-#include "graphics/host_gpu/renderer/framebufferCache.h"
-#include "graphics/host_gpu/renderer/imageView.h"
-#include "graphics/host_gpu/renderer/render.h"
-#include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/host_gpu/transfer.h"
-#include "graphics/host_gpu/vulkanCommon.h"
-#include "graphics/presentation/displayBuffer.h"
-
-#include <algorithm>
-#include <atomic>
-#include <cmath>
-#include <cstdarg>
-#include <cstdio>
-#include <limits>
-
-namespace Libs::Graphics {
-
-void GraphicsRenderMemoryBarrier(CommandBuffer& buffer) {
-	EXIT_IF(buffer.IsInvalid());
-
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-
-	auto vk_buffer = buffer.Handle();
-
-	VulkanMemoryBarrier mem_barrier {};
-	mem_barrier.sType         = vk::StructureType::eMemoryBarrier;
-	mem_barrier.pNext         = nullptr;
-	mem_barrier.srcAccessMask = vk::AccessFlagBits::eMemoryWrite;
-	mem_barrier.dstAccessMask = vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-
-	vk_buffer.pipelineBarrier(vk::PipelineStageFlagBits::eAllCommands,
-	                          vk::PipelineStageFlagBits::eAllCommands, vk::DependencyFlags {}, 1,
-	                          &mem_barrier, 0, nullptr, 0, nullptr);
-}
-
-void GraphicsRenderTextureBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image) {
-
-	vk::ImageMemoryBarrier image_memory_barrier {};
-	image_memory_barrier.sType = vk::StructureType::eImageMemoryBarrier;
-	image_memory_barrier.pNext = nullptr;
-	image_memory_barrier.srcAccessMask =
-	    vk::AccessFlagBits::eColorAttachmentWrite | vk::AccessFlagBits::eTransferWrite |
-	    vk::AccessFlagBits::eShaderWrite | vk::AccessFlagBits::eMemoryRead;
-	image_memory_barrier.dstAccessMask                   = vk::AccessFlagBits::eShaderRead;
-	image_memory_barrier.oldLayout                       = image.layout;
-	image_memory_barrier.newLayout                       = RENDER_COLOR_IMAGE_LAYOUT;
-	image_memory_barrier.srcQueueFamilyIndex             = VK_QUEUE_FAMILY_IGNORED;
-	image_memory_barrier.dstQueueFamilyIndex             = VK_QUEUE_FAMILY_IGNORED;
-	image_memory_barrier.image                           = image.image;
-	image_memory_barrier.subresourceRange.aspectMask     = vk::ImageAspectFlagBits::eColor;
-	image_memory_barrier.subresourceRange.baseMipLevel   = 0;
-	image_memory_barrier.subresourceRange.levelCount     = VK_REMAINING_MIP_LEVELS;
-	image_memory_barrier.subresourceRange.baseArrayLayer = 0;
-	image_memory_barrier.subresourceRange.layerCount     = image.layers;
-
-	vk_buffer.pipelineBarrier(
-	    vk::PipelineStageFlagBits::eColorAttachmentOutput |
-	        vk::PipelineStageFlagBits::eComputeShader | vk::PipelineStageFlagBits::eTransfer |
-	        vk::PipelineStageFlagBits::eFragmentShader,
-	    vk::PipelineStageFlagBits::eVertexShader | vk::PipelineStageFlagBits::eFragmentShader |
-	        vk::PipelineStageFlagBits::eComputeShader,
-	    vk::DependencyFlags {}, 0, nullptr, 0, nullptr, 1, &image_memory_barrier);
-
-	image.layout = image_memory_barrier.newLayout;
-}
-
-void GraphicsRenderColorImageBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image,
-                                     vk::ImageLayout new_layout) {
-	if (image.layout != new_layout) {
-		if (image.type == VulkanImageType::VideoOut &&
-		    image.layout == vk::ImageLayout::eTransferDstOptimal) {
-			static std::atomic<uint32_t> log_count {0};
-			if (log_count.fetch_add(1, std::memory_order_relaxed) < 128) {
-				LOGF("GraphicsRenderColorImageBarrier: image=%p type=%d layout=%s -> %s\n",
-				     VulkanHandleToPointer(image.image), static_cast<int>(image.type),
-				     VulkanToString(image.layout).c_str(), VulkanToString(new_layout).c_str());
-			}
-		}
-		vk::ImageMemoryBarrier image_memory_barrier {};
-		image_memory_barrier.sType = vk::StructureType::eImageMemoryBarrier;
-		image_memory_barrier.pNext = nullptr;
-		image_memory_barrier.srcAccessMask =
-		    vk::AccessFlagBits::eMemoryWrite | vk::AccessFlagBits::eMemoryRead;
-		image_memory_barrier.dstAccessMask =
-		    vk::AccessFlagBits::eMemoryWrite | vk::AccessFlagBits::eMemoryRead;
-		image_memory_barrier.oldLayout                       = image.layout;
-		image_memory_barrier.newLayout                       = new_layout;
-		image_memory_barrier.srcQueueFamilyIndex             = VK_QUEUE_FAMILY_IGNORED;
-		image_memory_barrier.dstQueueFamilyIndex             = VK_QUEUE_FAMILY_IGNORED;
-		image_memory_barrier.image                           = image.image;
-		image_memory_barrier.subresourceRange.aspectMask     = vk::ImageAspectFlagBits::eColor;
-		image_memory_barrier.subresourceRange.baseMipLevel   = 0;
-		image_memory_barrier.subresourceRange.levelCount     = VK_REMAINING_MIP_LEVELS;
-		image_memory_barrier.subresourceRange.baseArrayLayer = 0;
-		image_memory_barrier.subresourceRange.layerCount     = image.layers;
-
-		const auto stages = static_cast<vk::PipelineStageFlags>(
-		    vk::PipelineStageFlagBits::eAllGraphics | vk::PipelineStageFlagBits::eComputeShader |
-		    vk::PipelineStageFlagBits::eTransfer);
-		vk_buffer.pipelineBarrier(stages, stages, vk::DependencyFlags {}, 0, nullptr, 0, nullptr, 1,
-		                          &image_memory_barrier);
-
-		image.layout = image_memory_barrier.newLayout;
-	}
-}
-
-void GraphicsRenderDepthStencilImageBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image,
-                                            vk::ImageLayout new_layout) {
-	EXIT_IF(image.type != VulkanImageType::DepthStencil);
-	if (new_layout == vk::ImageLayout::eUndefined ||
-	    new_layout == vk::ImageLayout::ePreinitialized) {
-		EXIT("invalid destination depth/stencil image layout: %s\n",
-		     VulkanToString(new_layout).c_str());
-	}
-	if (image.layout == new_layout) {
-		return;
-	}
-	vk::ImageMemoryBarrier barrier {};
-	barrier.sType         = vk::StructureType::eImageMemoryBarrier;
-	barrier.srcAccessMask = vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-	barrier.dstAccessMask = vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-	barrier.oldLayout     = image.layout;
-	barrier.newLayout     = new_layout;
-	barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-	barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-	barrier.image               = image.image;
-	barrier.subresourceRange    = {ImageViewOps::DepthAspectMask(image.format), 0,
-	                               VK_REMAINING_MIP_LEVELS, 0, image.layers};
-	const auto stages           = static_cast<vk::PipelineStageFlags>(
-	    vk::PipelineStageFlagBits::eAllGraphics | vk::PipelineStageFlagBits::eComputeShader |
-	    vk::PipelineStageFlagBits::eTransfer);
-	vk_buffer.pipelineBarrier(stages, stages, vk::DependencyFlags {}, 0, nullptr, 0, nullptr, 1,
-	                          &barrier);
-	image.layout = new_layout;
-}
-
-void GraphicsRenderDepthStencilBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image) {
-	EXIT_IF(image.type != VulkanImageType::DepthStencil);
-
-	auto& depth = static_cast<DepthStencilVulkanImage&>(image);
-	if (depth.compressed) {
-		static std::atomic<uint32_t> log_count {0};
-		if (log_count.fetch_add(1, std::memory_order_relaxed) < 16) {
-			LOGF(
-			    "DepthTexture: decompressing depth target for shader read format=%s extent=%ux%u\n",
-			    VulkanToString(depth.format).c_str(), depth.extent.width, depth.extent.height);
-		}
-		depth.compressed = false;
-	}
-
-	if (image.layout != vk::ImageLayout::eDepthStencilReadOnlyOptimal) {
-		vk::ImageMemoryBarrier image_memory_barrier {};
-		image_memory_barrier.sType = vk::StructureType::eImageMemoryBarrier;
-		image_memory_barrier.pNext = nullptr;
-		image_memory_barrier.srcAccessMask =
-		    vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite;
-		image_memory_barrier.dstAccessMask       = vk::AccessFlagBits::eShaderRead;
-		image_memory_barrier.oldLayout           = image.layout;
-		image_memory_barrier.newLayout           = vk::ImageLayout::eDepthStencilReadOnlyOptimal;
-		image_memory_barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-		image_memory_barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-		image_memory_barrier.image               = image.image;
-		image_memory_barrier.subresourceRange.aspectMask =
-		    ImageViewOps::DepthAspectMask(image.format);
-		image_memory_barrier.subresourceRange.baseMipLevel   = 0;
-		image_memory_barrier.subresourceRange.levelCount     = VK_REMAINING_MIP_LEVELS;
-		image_memory_barrier.subresourceRange.baseArrayLayer = 0;
-		image_memory_barrier.subresourceRange.layerCount     = image.layers;
-
-		vk_buffer.pipelineBarrier(
-		    vk::PipelineStageFlagBits::eAllGraphics | vk::PipelineStageFlagBits::eComputeShader |
-		        vk::PipelineStageFlagBits::eTransfer,
-		    vk::PipelineStageFlagBits::eVertexShader | vk::PipelineStageFlagBits::eFragmentShader |
-		        vk::PipelineStageFlagBits::eComputeShader,
-		    vk::DependencyFlags {}, 0, nullptr, 0, nullptr, 1, &image_memory_barrier);
-
-		image.layout = image_memory_barrier.newLayout;
-	}
-}
-
-void GraphicsRenderTextureBarrier(CommandBuffer& buffer, uint64_t vaddr, uint64_t size) {
-	EXIT_IF(buffer.IsInvalid());
-
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-
-	auto vk_buffer = buffer.Handle();
-
-	auto* native = GetRenderContext().GetTextureCache().FindRenderTargetByRange(buffer, vaddr, size);
-	if (native == nullptr) {
-		EXIT("render-target barrier range has no cached image\n");
-	}
-	GraphicsRenderTextureBarrier(vk_buffer, *native);
-}
-
-void GraphicsRenderDepthStencilBarrier(CommandBuffer& buffer, uint64_t vaddr, uint64_t size) {
-	EXIT_IF(buffer.IsInvalid());
-
-	Common::LockGuard lock(GetRenderContext().GetMutex());
-
-	auto  vk_buffer = buffer.Handle();
-	auto* native    = GetRenderContext().GetTextureCache().FindDepthTargetByRange(buffer, vaddr, size);
-	if (native == nullptr) {
-		EXIT("depth-target barrier range has no cached image\n");
-	}
-	GraphicsRenderDepthStencilBarrier(vk_buffer, *native);
-}
-
-} // namespace Libs::Graphics

src/graphics/host_gpu/renderer/renderTargetBarriers.h

@@ -1,19 +0,0 @@
-#ifndef EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_RENDERTARGETBARRIERS_H_
-#define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_RENDERTARGETBARRIERS_H_
-
-#include "graphics/host_gpu/vulkanCommon.h"
-
-namespace Libs::Graphics {
-
-struct VulkanImage;
-
-void GraphicsRenderTextureBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image);
-void GraphicsRenderColorImageBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image,
-                                     vk::ImageLayout new_layout);
-void GraphicsRenderDepthStencilImageBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image,
-                                            vk::ImageLayout new_layout);
-void GraphicsRenderDepthStencilBarrier(vk::CommandBuffer vk_buffer, VulkanImage& image);
-
-} // namespace Libs::Graphics
-
-#endif // EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_RENDERTARGETBARRIERS_H_

src/graphics/host_gpu/renderer/samplerCache.cpp

@@ -7,6 +7,13 @@
 
 namespace Libs::Graphics {
 
+SamplerCache::~SamplerCache() {
+	for (const auto& [key, sampler]: m_samplers) {
+		(void)key;
+		m_graphics.device.destroySampler(sampler, nullptr);
+	}
+}
+
 vk::Sampler SamplerCache::GetSampler(const ShaderSamplerResource& r) {
 	Common::LockGuard lock(m_mutex);
 

src/graphics/host_gpu/renderer/samplerCache.h

@@ -21,7 +21,7 @@ public:
 	explicit SamplerCache(GraphicContext& graphics): m_graphics(graphics) {
 		EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
 	}
-	~SamplerCache() { KYTY_NOT_IMPLEMENTED; }
+	~SamplerCache();
 	KYTY_CLASS_NO_COPY(SamplerCache);
 
 	vk::Sampler GetSampler(const ShaderSamplerResource& r);

src/graphics/host_gpu/renderer/shaderResourceBarrier.cpp

@@ -36,36 +36,8 @@ VulkanMemoryBarrier MakeShaderWriteDependency() {
 	return barrier;
 }
 
-vk::ImageMemoryBarrier MakeStorageImageDependency(const VulkanImage& image, bool read,
-                                                  bool written) {
-	EXIT_IF(image.image == nullptr || image.type == VulkanImageType::DepthStencil);
-
-	vk::ImageMemoryBarrier barrier {};
-	barrier.sType         = vk::StructureType::eImageMemoryBarrier;
-	barrier.srcAccessMask = vk::AccessFlagBits::eMemoryWrite;
-	barrier.dstAccessMask = {};
-	if (read) {
-		barrier.dstAccessMask |= vk::AccessFlagBits::eShaderRead;
-	}
-	if (written) {
-		barrier.dstAccessMask |= vk::AccessFlagBits::eShaderWrite;
-	}
-	barrier.oldLayout                       = image.layout;
-	barrier.newLayout                       = vk::ImageLayout::eGeneral;
-	barrier.srcQueueFamilyIndex             = VK_QUEUE_FAMILY_IGNORED;
-	barrier.dstQueueFamilyIndex             = VK_QUEUE_FAMILY_IGNORED;
-	barrier.image                           = image.image;
-	barrier.subresourceRange.aspectMask     = vk::ImageAspectFlagBits::eColor;
-	barrier.subresourceRange.baseMipLevel   = 0;
-	barrier.subresourceRange.levelCount     = VK_REMAINING_MIP_LEVELS;
-	barrier.subresourceRange.baseArrayLayer = 0;
-	barrier.subresourceRange.layerCount     = image.layers;
-	EXIT_IF(!barrier.dstAccessMask || barrier.subresourceRange.layerCount == 0);
-	return barrier;
-}
-
-vk::BufferMemoryBarrier MakeGdsDependency(const VulkanBuffer& buffer) {
-	EXIT_IF(buffer.buffer == nullptr);
+vk::BufferMemoryBarrier MakeGdsDependency(vk::Buffer buffer) {
+	EXIT_IF(buffer == nullptr);
 
 	vk::BufferMemoryBarrier barrier {};
 	barrier.sType         = vk::StructureType::eBufferMemoryBarrier;
@@ -74,7 +46,7 @@ vk::BufferMemoryBarrier MakeGdsDependency(const VulkanBuffer& buffer) {
 	barrier.dstAccessMask = vk::AccessFlagBits::eShaderRead | vk::AccessFlagBits::eShaderWrite;
 	barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
 	barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-	barrier.buffer              = buffer.buffer;
+	barrier.buffer              = buffer;
 	barrier.offset              = 0;
 	barrier.size                = VK_WHOLE_SIZE;
 	return barrier;

src/graphics/host_gpu/renderer/shaderResourceBarrier.h

@@ -19,9 +19,7 @@ struct ShaderBufferWriteRange {
 
 vk::PipelineStageFlags  ShaderPipelineStages(vk::ShaderStageFlags stages);
 VulkanMemoryBarrier     MakeShaderWriteDependency();
-vk::ImageMemoryBarrier  MakeStorageImageDependency(const VulkanImage& image, bool read,
-                                                   bool written);
-vk::BufferMemoryBarrier MakeGdsDependency(const VulkanBuffer& buffer);
+vk::BufferMemoryBarrier MakeGdsDependency(vk::Buffer buffer);
 std::vector<ShaderBufferWriteRange>
 CollectShaderBufferWrites(const ShaderRecompiler::IR::Program&          program,
                           const ShaderRecompiler::IR::ResourceSnapshot& resources);

src/graphics/host_gpu/renderer/shaders.cpp

@@ -385,7 +385,9 @@ static vk::BlendOp GetBlendOp(uint32_t op) {
 	return vk::BlendOp::eAdd;
 }
 
-static void CreateLayout(std::span<vk::DescriptorSetLayout> set_layouts, uint32_t& set_layouts_num,
+static void CreateLayout(DescriptorCache& descriptor_cache,
+                         std::span<vk::DescriptorSetLayout> set_layouts,
+                         uint32_t& set_layouts_num,
                          std::span<vk::PushConstantRange>     push_constant_info,
                          uint32_t&                            push_constant_info_num,
                          const ShaderRecompiler::IR::Program& program,
@@ -405,17 +407,16 @@ static void CreateLayout(std::span<vk::DescriptorSetLayout> set_layouts, uint32_
 	if (need_descriptor) {
 		EXIT_IF(bindings.descriptor_set != set_layouts_num);
 
-		set_layouts[set_layouts_num] =
-		    GetRenderContext().GetDescriptorCache().GetDescriptorSetLayout(stage, program);
+		set_layouts[set_layouts_num] = descriptor_cache.GetDescriptorSetLayout(stage, program);
 		set_layouts_num++;
 	}
 }
 
-static void ConfigureSubgroupSize(vk::ShaderStageFlagBits                                vk_stage,
+static void ConfigureSubgroupSize(const GraphicContext&                                  graphics,
+                                  vk::ShaderStageFlagBits                                vk_stage,
                                   const ShaderRecompiler::IR::Program&                   program,
                                   vk::PipelineShaderStageRequiredSubgroupSizeCreateInfo& required,
                                   vk::PipelineShaderStageCreateInfo&                     stage) {
-	const auto& graphics = GetRenderContext().GetGraphics();
 	const auto  config =
 	    ConfigureShaderSubgroup(ShaderSubgroupCapabilities {graphics}, vk_stage, program);
 	switch (config.mode) {
@@ -455,7 +456,9 @@ static void ConfigureSubgroupSize(vk::ShaderStageFlagBits
 }
 
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
-void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::RenderPass render_pass,
+void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descriptor_cache,
+                            PipelineCache::GraphicsPipeline& pipeline,
+                            const PipelineRenderingState&   rendering,
                             const ShaderVertexInputInfo&    vs_input_info,
                             std::span<const uint32_t>       vs_shader,
                             const ShaderPixelInputInfo*     ps_input_info,
@@ -463,11 +466,8 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
                             const PipelineStaticParameters& static_params, uint32_t vs_hash0,
                             uint32_t vs_crc32, uint32_t ps_hash0, uint32_t ps_crc32,
                             bool ps_active) {
-	EXIT_IF(render_pass == nullptr);
 	EXIT_IF(ps_active && ps_input_info == nullptr);
 
-	auto& graphics = GetRenderContext().GetGraphics();
-
 	vk::ShaderModule vert_shader_module = nullptr;
 	vk::ShaderModule frag_shader_module = nullptr;
 
@@ -511,7 +511,8 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 	vert_shader_stage_info.pName               = "main";
 	vert_shader_stage_info.pSpecializationInfo = nullptr;
 	EXIT_IF(!vs_input_info.stage);
-	ConfigureSubgroupSize(vk::ShaderStageFlagBits::eVertex, *vs_input_info.stage.program,
+	ConfigureSubgroupSize(graphics, vk::ShaderStageFlagBits::eVertex,
+	                      *vs_input_info.stage.program,
 	                      vert_subgroup_size, vert_shader_stage_info);
 
 	vk::PipelineShaderStageCreateInfo                     frag_shader_stage_info {};
@@ -525,7 +526,8 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 	frag_shader_stage_info.pSpecializationInfo = nullptr;
 	if (ps_active) {
 		EXIT_IF(!ps_input_info->stage);
-		ConfigureSubgroupSize(vk::ShaderStageFlagBits::eFragment, *ps_input_info->stage.program,
+		ConfigureSubgroupSize(graphics, vk::ShaderStageFlagBits::eFragment,
+		                      *ps_input_info->stage.program,
 		                      frag_subgroup_size, frag_shader_stage_info);
 	}
 
@@ -620,10 +622,13 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 					break;
 				}
 				case 3: {
-					auto swizzle = vs_input_info.resources[index].DstSelXYZ();
-					auto expected =
-					    (attr_size == 1 ? DstSel(4, 0, 0)
-					                    : (attr_size == 2 ? DstSel(4, 5, 0) : DstSel(4, 5, 6)));
+					auto swizzle  = vs_input_info.resources[index].DstSelXYZ();
+					auto expected = DstSel(4, 5, 6);
+					switch (attr_size) {
+						case 1: expected = DstSel(4, 0, 0); break;
+						case 2: expected = DstSel(4, 5, 0); break;
+						default: break;
+					}
 					if (swizzle != expected) {
 						log_unsupported_vertex_swizzle(swizzle, expected);
 					}
@@ -820,12 +825,14 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 	uint32_t              push_constant_info_num = 0;
 
 	EXIT_IF(!vs_input_info.stage);
-	CreateLayout(set_layouts, set_layouts_num, push_constant_info, push_constant_info_num,
+	CreateLayout(descriptor_cache, set_layouts, set_layouts_num, push_constant_info,
+	             push_constant_info_num,
 	             *vs_input_info.stage.program, vk::ShaderStageFlagBits::eVertex,
 	             DescriptorCache::Stage::Vertex);
 	if (ps_active) {
 		EXIT_IF(!ps_input_info->stage);
-		CreateLayout(set_layouts, set_layouts_num, push_constant_info, push_constant_info_num,
+		CreateLayout(descriptor_cache, set_layouts, set_layouts_num, push_constant_info,
+		             push_constant_info_num,
 		             *ps_input_info->stage.program, vk::ShaderStageFlagBits::eFragment,
 		             DescriptorCache::Stage::Pixel);
 	}
@@ -899,8 +906,14 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 	dynamic_state.pDynamicStates    = dynamic_states;
 
 	vk::GraphicsPipelineCreateInfo pipeline_info {};
+	vk::PipelineRenderingCreateInfo rendering_info {};
+	rendering_info.sType                   = vk::StructureType::ePipelineRenderingCreateInfo;
+	rendering_info.colorAttachmentCount    = rendering.color_count;
+	rendering_info.pColorAttachmentFormats = rendering.color_formats.data();
+	rendering_info.depthAttachmentFormat   = rendering.depth_format;
+	rendering_info.stencilAttachmentFormat = rendering.stencil_format;
 	pipeline_info.sType               = vk::StructureType::eGraphicsPipelineCreateInfo;
-	pipeline_info.pNext               = nullptr;
+	pipeline_info.pNext               = &rendering_info;
 	pipeline_info.flags               = {};
 	pipeline_info.stageCount          = shader_stage_count;
 	pipeline_info.pStages             = shader_stages;
@@ -914,7 +927,7 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 	pipeline_info.pColorBlendState    = &color_blending;
 	pipeline_info.pDynamicState       = &dynamic_state;
 	pipeline_info.layout              = pipeline.pipeline_layout;
-	pipeline_info.renderPass          = render_pass;
+	pipeline_info.renderPass          = nullptr;
 	pipeline_info.subpass             = 0;
 	pipeline_info.basePipelineHandle  = nullptr;
 	pipeline_info.basePipelineIndex   = -1;
@@ -949,11 +962,10 @@ void CreatePipelineInternal(PipelineCache::GraphicsPipeline& pipeline, vk::Rende
 }
 
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
-void CreatePipelineInternal(PipelineCache::ComputePipeline& pipeline,
+void CreatePipelineInternal(GraphicContext& graphics, DescriptorCache& descriptor_cache,
+                            PipelineCache::ComputePipeline& pipeline,
                             const ShaderComputeInputInfo&   input_info,
                             std::span<const uint32_t>       cs_shader) {
-	auto& graphics = GetRenderContext().GetGraphics();
-
 	vk::ShaderModule comp_shader_module = nullptr;
 
 	vk::ShaderModuleCreateInfo create_info {};
@@ -982,7 +994,8 @@ void CreatePipelineInternal(PipelineCache::ComputePipeline& pipeline,
 	comp_shader_stage_info.pName               = "main";
 	comp_shader_stage_info.pSpecializationInfo = nullptr;
 	EXIT_IF(!input_info.stage);
-	ConfigureSubgroupSize(vk::ShaderStageFlagBits::eCompute, *input_info.stage.program,
+	ConfigureSubgroupSize(graphics, vk::ShaderStageFlagBits::eCompute,
+	                      *input_info.stage.program,
 	                      comp_subgroup_size, comp_shader_stage_info);
 
 	vk::DescriptorSetLayout set_layouts[1]  = {};
@@ -992,7 +1005,8 @@ void CreatePipelineInternal(PipelineCache::ComputePipeline& pipeline,
 	uint32_t              push_constant_info_num = 0;
 
 	EXIT_IF(!input_info.stage);
-	CreateLayout(set_layouts, set_layouts_num, push_constant_info, push_constant_info_num,
+	CreateLayout(descriptor_cache, set_layouts, set_layouts_num, push_constant_info,
+	             push_constant_info_num,
 	             *input_info.stage.program, vk::ShaderStageFlagBits::eCompute,
 	             DescriptorCache::Stage::Compute);
 

src/graphics/host_gpu/renderer/streamBuffer.cpp

@@ -1,95 +1,360 @@
 #include "graphics/host_gpu/renderer/streamBuffer.h"
 
 #include "common/assert.h"
-#include "common/logging/log.h"
 #include "common/profiler.h"
 #include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/transfer.h"
+#include "graphics/host_gpu/renderer/commandScheduler.h"
 #include "graphics/host_gpu/vma.h"
 
-#include <atomic>
 #include <cstring>
+#include <limits>
+#include <numeric>
+#include <vk_mem_alloc.h>
 
 namespace Libs::Graphics {
 
 namespace {
-std::atomic<uint64_t> g_stream_buffer_count {0};
-} // namespace
 
-HostStreamBuffer::HostStreamBuffer(GraphicContext& graphics): m_graphics(graphics) {}
+constexpr size_t WATCHES_INITIAL_RESERVE = 0x4000;
+constexpr size_t WATCHES_RESERVE_CHUNK   = 0x1000;
 
-HostStreamBuffer::~HostStreamBuffer() {
-	Release();
+[[nodiscard]] VmaAllocationCreateFlags AllocationFlags(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 {};
 }
 
-void HostStreamBuffer::EnsureBuffer() {
-	if (m_buffer != nullptr) {
-		if (m_mapped == nullptr) {
-			EXIT("host stream buffer lost its mapped storage\n");
-		}
-		return;
+[[nodiscard]] VmaMemoryUsage AllocationUsage(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;
 	}
-	KYTY_PROFILER_BLOCK("HostStreamBuffer::create");
-	m_buffer        = std::make_unique<VulkanBuffer>();
-	m_buffer->usage = vk::BufferUsageFlagBits::eStorageBuffer |
-	                  vk::BufferUsageFlagBits::eVertexBuffer |
-	                  vk::BufferUsageFlagBits::eIndexBuffer |
-	                  vk::BufferUsageFlagBits::eTransferSrc | vk::BufferUsageFlagBits::eTransferDst;
-	m_buffer->memory.property = vk::MemoryPropertyFlagBits::eHostVisible |
-	                            vk::MemoryPropertyFlagBits::eHostCoherent |
-	                            vk::MemoryPropertyFlagBits::eHostCached;
-	m_graphics.CreateBuffer(CAPACITY, *m_buffer);
-	m_graphics.MapMemory(m_buffer->memory, m_mapped);
-	const auto count = g_stream_buffer_count.fetch_add(1, std::memory_order_relaxed) + 1;
-	LOGF("HostStreamBuffer: created serial=%" PRIu64 " capacity=%" PRIu64 "\n", count, CAPACITY);
+	return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
 }
 
-bool HostStreamBuffer::Copy(const void* src, uint64_t size, uint64_t alignment,
-                            VulkanBuffer*& out_buffer, uint64_t& out_offset, uint64_t& out_range) {
-	KYTY_PROFILER_FUNCTION();
-	if (src == nullptr) {
-		EXIT("invalid host stream upload\n");
-	}
-	std::lock_guard lock(m_mutex);
-	if (size == 0) {
-		return false;
-	}
+[[nodiscard]] bool AlignUp(uint64_t value, uint64_t alignment, uint64_t& result) {
 	if (alignment == 0) {
-		alignment = 1;
+		result = value;
+		return true;
 	}
-	if ((alignment & (alignment - 1)) != 0 || m_offset > UINT64_MAX - (alignment - 1)) {
+	const auto remainder = value % alignment;
+	if (remainder == 0) {
+		result = value;
+		return true;
+	}
+	const auto increment = alignment - remainder;
+	if (value > std::numeric_limits<uint64_t>::max() - increment) {
 		return false;
 	}
-	const auto offset = (m_offset + alignment - 1) & ~(alignment - 1);
-	if (offset > CAPACITY || size > CAPACITY - offset) {
-		return false;
-	}
-	EnsureBuffer();
-	std::memcpy(static_cast<uint8_t*>(m_mapped) + offset, src, static_cast<size_t>(size));
-	m_offset   = offset + size;
-	out_buffer = m_buffer.get();
-	out_offset = offset;
-	out_range  = size;
+	result = value + increment;
 	return true;
 }
 
-void HostStreamBuffer::Reset() noexcept {
-	std::lock_guard lock(m_mutex);
-	m_offset = 0;
+} // namespace
+
+Buffer::Buffer(GraphicContext& graphics, CommandScheduler& scheduler, MemoryUsage usage,
+               uint64_t cpu_address, vk::BufferUsageFlags flags, uint64_t size)
+    : m_graphics(&graphics), m_scheduler(&scheduler), m_usage(usage), m_cpu_address(cpu_address),
+      m_size(size), m_buffer(std::make_unique<VulkanBuffer>()) {
+	KYTY_PROFILER_FUNCTION();
+	EXIT_IF(graphics.allocator == nullptr || size == 0);
+
+	vk::BufferCreateInfo buffer_info {};
+	buffer_info.size        = size;
+	buffer_info.usage       = flags;
+	buffer_info.sharingMode = vk::SharingMode::eExclusive;
+
+	VmaAllocationCreateInfo allocation_info {};
+	allocation_info.flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | AllocationFlags(usage);
+	allocation_info.usage = AllocationUsage(usage);
+	allocation_info.preferredFlags = usage == MemoryUsage::DeviceLocal
+	                                     ? VkMemoryPropertyFlags {}
+	                                     : VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+
+	VmaAllocationInfo allocation_result {};
+	VkBuffer          native_buffer = VK_NULL_HANDLE;
+	const auto        result        = static_cast<vk::Result>(vmaCreateBuffer(
+	    graphics.allocator, static_cast<const VkBufferCreateInfo*>(buffer_info), &allocation_info,
+	    &native_buffer, &m_buffer->memory.allocation, &allocation_result));
+	if (result != vk::Result::eSuccess) {
+		graphics.LogMemoryBudget();
+	}
+	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);
+
+	m_buffer->buffer                 = native_buffer;
+	m_buffer->usage                  = flags;
+	m_buffer->buffer_size            = size;
+	m_buffer->memory.allocation_info = allocation_result;
+	m_buffer->memory.memory          = allocation_result.deviceMemory;
+	m_buffer->memory.offset          = allocation_result.offset;
+	m_buffer->memory.type            = allocation_result.memoryType;
+	m_buffer->memory.unique_id       = VulkanNextMemoryUniqueId();
+	graphics.device.getBufferMemoryRequirements(m_buffer->buffer, &m_buffer->memory.requirements);
+
+	VkMemoryPropertyFlags properties = 0;
+	vmaGetAllocationMemoryProperties(graphics.allocator, m_buffer->memory.allocation, &properties);
+	m_buffer->memory.property = vk::MemoryPropertyFlags(properties);
+	m_is_coherent             = (properties & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) != 0;
+	if (allocation_result.pMappedData != nullptr) {
+		m_mapped = {static_cast<uint8_t*>(allocation_result.pMappedData),
+		            static_cast<size_t>(size)};
+	}
+	VulkanTrackAllocation(m_buffer->memory);
 }
 
-void HostStreamBuffer::Release() noexcept {
-	std::lock_guard lock(m_mutex);
-	if (m_buffer != nullptr) {
-		if (m_mapped == nullptr) {
-			EXIT("invalid host stream buffer release state\n");
-		}
-		m_graphics.UnmapMemory(m_buffer->memory);
-		m_graphics.DeleteBuffer(*m_buffer);
-		m_buffer.reset();
+Buffer::~Buffer() {
+	if (m_buffer->buffer != nullptr) {
+		VulkanUntrackAllocation(m_buffer->memory);
+		vmaDestroyBuffer(m_graphics->allocator, m_buffer->buffer, m_buffer->memory.allocation);
 	}
-	m_mapped = nullptr;
-	m_offset = 0;
+}
+
+vk::Buffer Buffer::Handle() const noexcept {
+	return m_buffer->buffer;
+}
+
+bool Buffer::IsInBounds(uint64_t address, uint64_t size) const noexcept {
+	return address >= m_cpu_address && size <= m_size && address - m_cpu_address <= m_size - size;
+}
+
+void Buffer::Write(uint64_t offset, const void* source, uint64_t size) {
+	EXIT_IF(source == nullptr || m_mapped.empty() || offset > m_size || size > m_size - offset);
+	std::memcpy(m_mapped.data() + offset, source, static_cast<size_t>(size));
+	Flush(offset, size);
+}
+
+void Buffer::Flush(uint64_t offset, uint64_t size) {
+	EXIT_IF(m_mapped.empty() || offset > m_size || size > m_size - offset);
+	if (!m_is_coherent && size != 0) {
+		const auto result = vmaFlushAllocation(m_graphics->allocator, m_buffer->memory.allocation,
+		                                      offset, size);
+		EXIT_NOT_IMPLEMENTED(static_cast<vk::Result>(result) != vk::Result::eSuccess);
+	}
+}
+
+vk::BufferMemoryBarrier Buffer::Barrier(uint64_t offset, uint64_t size, vk::AccessFlags source,
+                                        vk::AccessFlags destination) const {
+	if (Handle() == nullptr || size == 0 || offset > m_size || size > m_size - offset) {
+		EXIT("Buffer: invalid DMA barrier, handle=%p offset=0x%016" PRIx64
+		     " size=0x%016" PRIx64 " capacity=0x%016" PRIx64 "\n",
+		     static_cast<const void*>(Handle()), offset, size, m_size);
+	}
+	vk::BufferMemoryBarrier barrier {};
+	barrier.sType               = vk::StructureType::eBufferMemoryBarrier;
+	barrier.srcAccessMask       = source;
+	barrier.dstAccessMask       = destination;
+	barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barrier.buffer              = Handle();
+	barrier.offset              = offset;
+	barrier.size                = size;
+	return barrier;
+}
+
+void Buffer::CopyFrom(CommandBuffer& command, const Buffer& source, uint64_t source_offset,
+                      uint64_t destination_offset, uint64_t size, vk::AccessFlags source_before,
+                      vk::AccessFlags destination_before, vk::AccessFlags source_after,
+                      vk::AccessFlags destination_after) {
+	if (size == 0 || source_offset > source.m_size || size > source.m_size - source_offset ||
+	    destination_offset > m_size || size > m_size - destination_offset) {
+		EXIT("Buffer: invalid copy range\n");
+	}
+	if (source.Handle() == Handle() && source_offset < destination_offset + size &&
+	    destination_offset < source_offset + size) {
+		EXIT("Buffer: overlapping self-copy\n");
+	}
+	command.EndRendering();
+	const vk::BufferMemoryBarrier before[] = {
+	    source.Barrier(source_offset, size, source_before, vk::AccessFlagBits::eTransferRead),
+	    Barrier(destination_offset, size, destination_before,
+	            vk::AccessFlagBits::eTransferWrite),
+	};
+	const auto host_access = vk::AccessFlagBits::eHostRead | vk::AccessFlagBits::eHostWrite;
+	auto       before_stage = vk::PipelineStageFlags {vk::PipelineStageFlagBits::eAllCommands};
+	if (static_cast<bool>((source_before | destination_before) & host_access)) {
+		before_stage |= vk::PipelineStageFlagBits::eHost;
+	}
+	const auto native = command.Handle();
+	native.pipelineBarrier(before_stage, vk::PipelineStageFlagBits::eTransfer,
+	                       vk::DependencyFlagBits::eByRegion, 0, nullptr, 2, before, 0, nullptr);
+	const vk::BufferCopy copy {source_offset, destination_offset, size};
+	native.copyBuffer(source.Handle(), Handle(), 1, &copy);
+	const vk::BufferMemoryBarrier after[] = {
+	    source.Barrier(source_offset, size, vk::AccessFlagBits::eTransferRead, source_after),
+	    Barrier(destination_offset, size, vk::AccessFlagBits::eTransferWrite, destination_after),
+	};
+	auto after_stage = vk::PipelineStageFlags {vk::PipelineStageFlagBits::eAllCommands};
+	if (static_cast<bool>((source_after | destination_after) & host_access)) {
+		after_stage |= vk::PipelineStageFlagBits::eHost;
+	}
+	native.pipelineBarrier(vk::PipelineStageFlagBits::eTransfer, after_stage,
+	                       vk::DependencyFlagBits::eByRegion, 0, nullptr, 2, after, 0, nullptr);
+}
+
+void Buffer::Fill(uint64_t offset, uint64_t size, uint32_t value) {
+	if (((offset | size) & 3u) != 0) {
+		EXIT("Buffer: fill range must be dword aligned\n");
+	}
+	auto& command = Scheduler().Current();
+	command.EndRendering();
+	const auto before =
+	    Barrier(offset, size, vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite,
+	            vk::AccessFlagBits::eTransferWrite);
+	const auto native = command.Handle();
+	native.pipelineBarrier(vk::PipelineStageFlagBits::eAllCommands,
+	                       vk::PipelineStageFlagBits::eTransfer, vk::DependencyFlagBits::eByRegion,
+	                       0, nullptr, 1, &before, 0, nullptr);
+	native.fillBuffer(Handle(), offset, size, value);
+	const auto after =
+	    Barrier(offset, size, vk::AccessFlagBits::eTransferWrite,
+	            vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite);
+	native.pipelineBarrier(vk::PipelineStageFlagBits::eTransfer,
+	                       vk::PipelineStageFlagBits::eAllCommands,
+	                       vk::DependencyFlagBits::eByRegion, 0, nullptr, 1, &after, 0, nullptr);
+}
+
+StreamBuffer::StreamBuffer(GraphicContext& graphics, CommandScheduler& scheduler, MemoryUsage usage,
+                           uint64_t size)
+    : Buffer(graphics, scheduler, usage, 0, AllFlags, size) {
+	ReserveWatches(m_current_watches, WATCHES_INITIAL_RESERVE);
+	ReserveWatches(m_previous_watches, WATCHES_INITIAL_RESERVE);
+}
+
+bool StreamBuffer::NormalizeReservation(bool coherent, uint64_t atom, uint64_t& size,
+                                        uint64_t& alignment) {
+	if (coherent) {
+		return true;
+	}
+	if (!AlignUp(size, atom, size)) {
+		return false;
+	}
+	const auto divisor = std::gcd(alignment, atom);
+	if (alignment != 0 && alignment / divisor > UINT64_MAX / atom) {
+		return false;
+	}
+	alignment = alignment == 0 ? atom : alignment / divisor * atom;
+	return true;
+}
+
+std::pair<uint8_t*, uint64_t> StreamBuffer::Map(uint64_t size, uint64_t alignment,
+                                                bool allow_wait) {
+	if (Mapped().empty()) {
+		return {nullptr, 0};
+	}
+	uint64_t mapped_size = size;
+	const auto atom = Graphics().physical_device_properties.limits.nonCoherentAtomSize;
+	if (!NormalizeReservation(IsCoherent(), atom, mapped_size, alignment)) {
+		return {nullptr, 0};
+	}
+	if (mapped_size > Size()) {
+		return {nullptr, 0};
+	}
+
+	uint64_t aligned_offset = 0;
+	if (!AlignUp(m_offset, alignment, aligned_offset)) {
+		return {nullptr, 0};
+	}
+
+	const bool wrap = aligned_offset > Size() - mapped_size;
+	if (wrap) {
+		aligned_offset = 0;
+	}
+
+	auto wait_cursor = wrap ? size_t {0} : m_wait_cursor;
+	auto wait_bound  = wrap ? uint64_t {0} : m_wait_bound;
+	auto invalidation_mark =
+	    wrap ? std::optional<size_t> {m_current_watch_cursor} : m_invalidation_mark;
+	auto& pending_watches = wrap ? m_current_watches : m_previous_watches;
+	if (!WaitPendingOperations(pending_watches, invalidation_mark, aligned_offset + mapped_size,
+	                           allow_wait, wait_cursor, wait_bound)) {
+		return {nullptr, 0};
+	}
+
+	if (wrap) {
+		m_invalidation_mark    = invalidation_mark;
+		m_current_watch_cursor = 0;
+		std::swap(m_previous_watches, m_current_watches);
+	}
+	m_wait_cursor = wait_cursor;
+	m_wait_bound  = wait_bound;
+	m_offset      = aligned_offset;
+	m_mapped_size = mapped_size;
+	return {Mapped().data() + m_offset, m_offset};
+}
+
+void StreamBuffer::Commit() {
+	if (!IsCoherent() && Usage() != MemoryUsage::Download && m_mapped_size != 0) {
+		const auto result = vmaFlushAllocation(
+		    Graphics().allocator, NativeBuffer().memory.allocation, m_offset, m_mapped_size);
+		EXIT_NOT_IMPLEMENTED(static_cast<vk::Result>(result) != vk::Result::eSuccess);
+	}
+
+	m_offset += m_mapped_size;
+	const auto tick = Scheduler().CurrentTick();
+	if (m_current_watch_cursor != 0 && m_current_watches[m_current_watch_cursor - 1].tick == tick) {
+		m_current_watches[m_current_watch_cursor - 1].upper_bound = m_offset;
+		return;
+	}
+	if (m_current_watch_cursor + 1 >= m_current_watches.size()) {
+		ReserveWatches(m_current_watches, WATCHES_RESERVE_CHUNK);
+	}
+	auto& watch       = m_current_watches[m_current_watch_cursor++];
+	watch.upper_bound = m_offset;
+	watch.tick        = tick;
+}
+
+void StreamBuffer::Invalidate(uint64_t offset, uint64_t size) {
+	EXIT_IF(Usage() != MemoryUsage::Download || offset > Size() || size > Size() - offset);
+	if (IsCoherent() || size == 0) {
+		return;
+	}
+	const auto result = vmaInvalidateAllocation(Graphics().allocator,
+	                                            NativeBuffer().memory.allocation, offset, size);
+	EXIT_NOT_IMPLEMENTED(static_cast<vk::Result>(result) != vk::Result::eSuccess);
+}
+
+uint64_t StreamBuffer::Copy(const void* source, uint64_t size, uint64_t alignment) {
+	EXIT_IF(source == nullptr);
+	const auto [data, offset] = Map(size, alignment);
+	EXIT_IF(data == nullptr);
+	std::memcpy(data, source, static_cast<size_t>(size));
+	Commit();
+	return offset;
+}
+
+void StreamBuffer::ReserveWatches(std::vector<Watch>& watches, size_t grow_size) {
+	watches.resize(watches.size() + grow_size);
+}
+
+bool StreamBuffer::WaitPendingOperations(const std::vector<Watch>& watches,
+                                         std::optional<size_t>     invalidation_mark,
+                                         uint64_t requested_upper_bound, bool allow_wait,
+                                         size_t& wait_cursor, uint64_t& wait_bound) {
+	if (!invalidation_mark.has_value()) {
+		return true;
+	}
+	while (requested_upper_bound > wait_bound && wait_cursor < *invalidation_mark) {
+		const auto& watch = watches[wait_cursor];
+		if (!Scheduler().IsFree(watch.tick) && !allow_wait) {
+			return false;
+		}
+		Scheduler().Wait(watch.tick);
+		if (Usage() == MemoryUsage::Download) {
+			Scheduler().WaitPriorityOperations(watch.tick);
+		}
+		wait_bound = watch.upper_bound;
+		++wait_cursor;
+	}
+	return true;
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/streamBuffer.h

@@ -3,43 +3,126 @@
 
 #include "common/abi.h"
 #include "common/common.h"
+#include "graphics/host_gpu/vulkanCommon.h"
 
 #include <cstdint>
 #include <memory>
-#include <mutex>
+#include <optional>
+#include <span>
+#include <utility>
+#include <vector>
 
 namespace Libs::Graphics {
 
+class CommandBuffer;
+class CommandScheduler;
+struct StreamBufferTestAccess;
 struct GraphicContext;
 struct VulkanBuffer;
 
-// Host-only mapped stream mechanism. BufferCache owns the upload policy/API; one backend remains
-// attached to each CommandBuffer so Reset is provably after that command's fence. Replacing this
-// backend with scheduler watches will not change descriptor/render call sites.
-class HostStreamBuffer final {
-public:
-	explicit HostStreamBuffer(GraphicContext& graphics);
-	~HostStreamBuffer();
-	KYTY_CLASS_NO_COPY(HostStreamBuffer);
+enum class MemoryUsage : uint8_t {
+	DeviceLocal,
+	Upload,
+	Download,
+	Stream,
+};
 
-	[[nodiscard]] bool Copy(const void* src, uint64_t size, uint64_t alignment,
-	                        VulkanBuffer*& out_buffer, uint64_t& out_offset, uint64_t& out_range);
-	void               Reset() noexcept;
-	void               Release() noexcept;
+inline constexpr vk::BufferUsageFlags ReadFlags =
+    vk::BufferUsageFlagBits::eTransferSrc | vk::BufferUsageFlagBits::eUniformBuffer |
+    vk::BufferUsageFlagBits::eIndexBuffer | vk::BufferUsageFlagBits::eVertexBuffer |
+    vk::BufferUsageFlagBits::eIndirectBuffer;
+
+inline constexpr vk::BufferUsageFlags AllFlags =
+    ReadFlags | vk::BufferUsageFlagBits::eTransferDst | vk::BufferUsageFlagBits::eStorageBuffer;
+
+class Buffer {
+public:
+	Buffer(GraphicContext& graphics, CommandScheduler& scheduler, MemoryUsage usage,
+	       uint64_t cpu_address, vk::BufferUsageFlags flags, uint64_t size);
+	~Buffer();
+	KYTY_CLASS_NO_COPY(Buffer);
+
+	[[nodiscard]] vk::Buffer         Handle() const noexcept;
+	[[nodiscard]] uint64_t           Size() const noexcept { return m_size; }
+	[[nodiscard]] std::span<uint8_t> Mapped() const noexcept { return m_mapped; }
+	[[nodiscard]] bool               IsCoherent() const noexcept { return m_is_coherent; }
+	[[nodiscard]] MemoryUsage        Usage() const noexcept { return m_usage; }
+	[[nodiscard]] uint64_t           CpuAddress() const noexcept { return m_cpu_address; }
+	[[nodiscard]] uint64_t           Offset(uint64_t address) const noexcept {
+		return address - m_cpu_address;
+	}
+	[[nodiscard]] bool IsInBounds(uint64_t address, uint64_t size) const noexcept;
+	void               Write(uint64_t offset, const void* source, uint64_t size);
+	void               Flush(uint64_t offset, uint64_t size);
+	void               CopyFrom(
+	                  CommandBuffer& command, const Buffer& source, uint64_t source_offset,
+	                  uint64_t destination_offset, uint64_t size,
+	                  vk::AccessFlags source_before = vk::AccessFlagBits::eMemoryWrite,
+	                  vk::AccessFlags destination_before =
+	                      vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite,
+	                  vk::AccessFlags source_after =
+	                      vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite,
+	                  vk::AccessFlags destination_after =
+	                      vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite);
+	void Fill(uint64_t offset, uint64_t size, uint32_t value);
+
+protected:
+	[[nodiscard]] GraphicContext&   Graphics() const noexcept { return *m_graphics; }
+	[[nodiscard]] CommandScheduler& Scheduler() const noexcept { return *m_scheduler; }
+	[[nodiscard]] VulkanBuffer&     NativeBuffer() noexcept { return *m_buffer; }
 
 private:
-	void EnsureBuffer();
+	[[nodiscard]] vk::BufferMemoryBarrier Barrier(uint64_t offset, uint64_t size,
+	                                              vk::AccessFlags source,
+	                                              vk::AccessFlags destination) const;
 
-	// Interim fence-scoped backend: one command processor's eight live command buffers reserve up
-	// to 128 MiB lazily. Additional active processors scale that aggregate until this backend is
-	// replaced by a single 64 MiB scheduler-watched ring; the BufferCache seam stays fixed.
-	static constexpr uint64_t CAPACITY = 16ull * 1024ull * 1024ull;
-
-	mutable std::mutex            m_mutex;
-	GraphicContext&               m_graphics;
+	GraphicContext*               m_graphics    = nullptr;
+	CommandScheduler*             m_scheduler   = nullptr;
+	MemoryUsage                   m_usage       = MemoryUsage::DeviceLocal;
+	uint64_t                      m_cpu_address = 0;
+	uint64_t                      m_size        = 0;
 	std::unique_ptr<VulkanBuffer> m_buffer;
-	void*                         m_mapped = nullptr;
-	uint64_t                      m_offset = 0;
+	std::span<uint8_t>            m_mapped;
+	bool                          m_is_coherent = false;
+};
+
+class StreamBuffer final: public Buffer {
+public:
+	StreamBuffer(GraphicContext& graphics, CommandScheduler& scheduler, MemoryUsage usage,
+	             uint64_t size);
+
+	[[nodiscard]] std::pair<uint8_t*, uint64_t> Map(uint64_t size, uint64_t alignment = 0,
+	                                                bool allow_wait = true);
+	void                                        Commit();
+	// Download mappings become visible to the CPU only after their GPU completion tick is free.
+	// Call this from the scheduler's deferred completion operation before reading Mapped().
+	void                   Invalidate(uint64_t offset, uint64_t size);
+	[[nodiscard]] uint64_t Copy(const void* source, uint64_t size, uint64_t alignment = 0);
+
+private:
+	friend struct StreamBufferTestAccess;
+
+	struct Watch {
+		uint64_t tick        = 0;
+		uint64_t upper_bound = 0;
+	};
+
+	void               ReserveWatches(std::vector<Watch>& watches, size_t grow_size);
+	[[nodiscard]] static bool NormalizeReservation(bool coherent, uint64_t atom, uint64_t& size,
+	                                               uint64_t& alignment);
+	[[nodiscard]] bool WaitPendingOperations(const std::vector<Watch>& watches,
+	                                         std::optional<size_t>     invalidation_mark,
+	                                         uint64_t requested_upper_bound, bool allow_wait,
+	                                         size_t& wait_cursor, uint64_t& wait_bound);
+
+	uint64_t              m_offset      = 0;
+	uint64_t              m_mapped_size = 0;
+	std::vector<Watch>    m_current_watches;
+	size_t                m_current_watch_cursor = 0;
+	std::optional<size_t> m_invalidation_mark;
+	std::vector<Watch>    m_previous_watches;
+	size_t                m_wait_cursor = 0;
+	uint64_t              m_wait_bound  = 0;
 };
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/sync.cpp

@@ -5,16 +5,16 @@
 #include "common/logging/log.h"
 #include "common/threads.h"
 #include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/objects/label.h"
 #include "graphics/host_gpu/renderer/bufferCache.h"
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
-#include "graphics/presentation/displayBuffer.h"
+#include "graphics/presentation/videoOut.h"
 #include "kernel/eventQueue.h"
 #include "kernel/pthread.h"
 #include "libs/errno.h"
 
 #include <array>
+#include <cstring>
 #include <limits>
 #include <optional>
 
@@ -57,19 +57,6 @@ uint64_t ReadReferenceClock() {
 	return value;
 }
 
-static void SubmitLabel(CommandBuffer& buffer, LabelCallback callback_1 = nullptr,
-                        LabelCallback callback_2 = nullptr, const uint64_t* args = nullptr) {
-	auto* label = LabelCreate(callback_1, callback_2, args);
-	LabelSet(buffer, *label);
-	LabelDelete(*label);
-}
-
-static bool CompleteDisplayBufferFlip(const uint64_t* args) {
-	EXIT_IF(args == nullptr);
-	Presentation::DisplayBufferCompleteFlipFromGpu(args[0]);
-	return true;
-}
-
 enum class EndOfPipeCompletion { None, Interrupt, Flip, FlipAndInterrupt };
 
 struct EndOfPipeSignal {
@@ -86,17 +73,6 @@ struct EndOfPipeSignal {
 enum class EndOfPipeWriteSize : uint32_t { Dword = 4, Qword = 8 };
 enum class EndOfPipeWriteAction { Write, WriteBack, Interrupt, InterruptWriteBack };
 
-static bool TriggerEopEventCallback(const uint64_t* args) {
-	EXIT_IF(args == nullptr);
-	GetRenderContext().TriggerEopEvent(static_cast<uint32_t>(args[0]));
-	return true;
-}
-
-static bool TriggerDefaultEopEventCallback(const uint64_t* /*args*/) {
-	GetRenderContext().TriggerEopEvent(0);
-	return true;
-}
-
 static void ValidateEndOfPipeSignal(const EndOfPipeSignal& signal) {
 	if (signal.destination.has_value()) {
 		EXIT_IF(*signal.destination == 0);
@@ -111,19 +87,33 @@ static void RecordEndOfPipeSignal(const EndOfPipeSignal& signal) {
 	                            signal.debug_args[0], signal.debug_args[1], signal.debug_args[2],
 	                            signal.debug_args[3], signal.debug_data);
 
-	const uint64_t args[LABEL_ARGS_MAX] = {signal.completion_data};
+	auto& renderer  = signal.buffer->GetContext();
+	auto& scheduler = renderer.GetCommandScheduler();
+	if (signal.completion != EndOfPipeCompletion::None) {
+		EXIT_IF(!scheduler.Active() || signal.buffer != &scheduler.Current());
+	}
 	switch (signal.completion) {
 		case EndOfPipeCompletion::None: return;
-		case EndOfPipeCompletion::Interrupt:
-			SubmitLabel(*signal.buffer, nullptr, TriggerEopEventCallback, args);
+		case EndOfPipeCompletion::Interrupt: {
+			const auto context_id = static_cast<uint32_t>(signal.completion_data);
+			scheduler.DeferPriorityOperation(
+			    [&renderer, context_id] { renderer.TriggerEopEvent(context_id); });
 			return;
-		case EndOfPipeCompletion::Flip:
-			SubmitLabel(*signal.buffer, CompleteDisplayBufferFlip, nullptr, args);
+		}
+		case EndOfPipeCompletion::Flip: {
+			const auto request_id = signal.completion_data;
+			scheduler.DeferPriorityOperation(
+			    [&renderer, request_id] { renderer.GetVideoOut().CompleteFlip(request_id); });
 			return;
-		case EndOfPipeCompletion::FlipAndInterrupt:
-			SubmitLabel(*signal.buffer, CompleteDisplayBufferFlip, TriggerDefaultEopEventCallback,
-			            args);
+		}
+		case EndOfPipeCompletion::FlipAndInterrupt: {
+			const auto request_id = signal.completion_data;
+			scheduler.DeferPriorityOperation([&renderer, request_id] {
+				renderer.GetVideoOut().CompleteFlip(request_id);
+				renderer.TriggerEopEvent(0);
+			});
 			return;
+		}
 	}
 }
 
@@ -172,10 +162,6 @@ void TriggerAgcUserInterrupt() {
 	EXIT_NOT_IMPLEMENTED(result != OK && result != LibKernel::KERNEL_ERROR_ENOENT);
 }
 
-void TriggerEopEvent(uint32_t context_id) {
-	GetRenderContext().TriggerEopEvent(context_id);
-}
-
 void WriteAtEndOfPipe32(uint64_t submit_id, CommandBuffer& buffer, uint32_t* dst_gpu_addr,
                         uint32_t value) {
 	RecordEndOfPipeWrite(submit_id, buffer, reinterpret_cast<uint64_t>(dst_gpu_addr), value,
@@ -261,11 +247,12 @@ void WriteAtEndOfPipeWithInterrupt32(uint64_t submit_id, CommandBuffer& buffer,
 	                     EndOfPipeWriteSize::Dword, EndOfPipeWriteAction::Interrupt, context_id);
 }
 
-uint64_t PrepareDisplayBufferFlip(CommandBuffer& buffer, int handle, int index, int flip_mode,
-                                  int64_t flip_arg) {
+uint64_t PrepareVideoOutFlip(CommandBuffer& buffer, int handle, int index, int flip_mode,
+                             int64_t flip_arg) {
 	for (;;) {
 		uint64_t   request_id = 0;
-		const auto result     = Presentation::DisplayBufferSubmitFlipFromGpu(
+		auto&      video_out = buffer.GetContext().GetVideoOut();
+		const auto result = video_out.SubmitFlipFromGpu(
 		    buffer, handle, index, flip_mode, flip_arg, request_id);
 		if (result == OK) {
 			EXIT_IF(request_id == 0);
@@ -276,7 +263,7 @@ uint64_t PrepareDisplayBufferFlip(CommandBuffer& buffer, int handle, int index,
 			     "\n",
 			     result, handle, index, flip_mode, flip_arg);
 		}
-		Presentation::DisplayBufferWaitForFlipQueueSlot();
+		video_out.WaitForSubmitSlot();
 	}
 }
 
@@ -331,9 +318,11 @@ void WriteAtEndOfPipeOnlyFlip(uint64_t submit_id, CommandBuffer& buffer, int han
 
 void TriggerEopEventAtEndOfPipe(CommandBuffer& buffer, uint32_t context_id) {
 	ValidateEndOfPipeSignal({.buffer = &buffer});
-
-	uint64_t args[LABEL_ARGS_MAX] = {static_cast<uint64_t>(context_id)};
-	SubmitLabel(buffer, nullptr, TriggerEopEventCallback, args);
+	auto& renderer  = buffer.GetContext();
+	auto& scheduler = renderer.GetCommandScheduler();
+	EXIT_IF(!scheduler.Active() || &buffer != &scheduler.Current());
+	scheduler.DeferPriorityOperation(
+	    [&renderer, context_id] { renderer.TriggerEopEvent(context_id); });
 }
 
 static void EopEventResetFunc(LibKernel::EventQueue::KernelEqueueEvent* event) {
@@ -349,7 +338,9 @@ static void EopEventDeleteFunc(LibKernel::EventQueue::KernelEqueue       eq,
 	EXIT_NOT_IMPLEMENTED(event->event.filter != LibKernel::EventQueue::KERNEL_EVFILT_GRAPHICS);
 	if (event->event.ident == GRAPHICS_EVENT_QUEUED_GRAPHICS_INTERRUPT ||
 	    event->event.ident == GRAPHICS_EVENT_EOP) {
-		GetRenderContext().DeleteEopEq(eq, static_cast<int>(event->event.ident));
+		auto* renderer = static_cast<RenderContext*>(event->filter.data);
+		EXIT_IF(renderer == nullptr);
+		renderer->DeleteEopEq(eq, static_cast<int>(event->event.ident));
 	}
 }
 
@@ -368,7 +359,8 @@ static void EopEventTriggerFunc(LibKernel::EventQueue::KernelEqueueEvent* event,
 	}
 }
 
-int AddEqEvent(LibKernel::EventQueue::KernelEqueue eq, int id, void* udata) {
+int AddEqEvent(RenderContext& renderer, LibKernel::EventQueue::KernelEqueue eq, int id,
+               void* udata) {
 	LibKernel::EventQueue::KernelEqueueEvent event;
 	event.triggered                = false;
 	event.event.ident              = static_cast<uintptr_t>(id);
@@ -379,13 +371,13 @@ int AddEqEvent(LibKernel::EventQueue::KernelEqueue eq, int id, void* udata) {
 	event.filter.delete_event_func = EopEventDeleteFunc;
 	event.filter.reset_func        = EopEventResetFunc;
 	event.filter.trigger_func      = EopEventTriggerFunc;
-	event.filter.data              = nullptr;
+	event.filter.data              = &renderer;
 
 	int result = LibKernel::EventQueue::KernelAddEvent(eq, event);
 
 	if (result == 0 &&
 	    (id == GRAPHICS_EVENT_QUEUED_GRAPHICS_INTERRUPT || id == GRAPHICS_EVENT_EOP)) {
-		GetRenderContext().AddEopEq(eq, id);
+		renderer.AddEopEq(eq, id);
 	}
 
 	return result;
@@ -398,12 +390,12 @@ int DeleteEqEvent(LibKernel::EventQueue::KernelEqueue eq, int id) {
 	return result;
 }
 
-void ReadGds(uint32_t* dst, uint32_t dw_offset, uint32_t dw_size) {
-	GetRenderContext().GetGdsBuffer().Read(dst, dw_offset, dw_size);
-}
-
-void DeleteBuffers() {
-	GetRenderContext().GetBufferCache().ResetNullBuffer();
+void ReadGds(Buffer& gds, uint32_t* dst, uint32_t dw_offset, uint32_t dw_size) {
+	const auto offset = uint64_t {dw_offset} * sizeof(uint32_t);
+	const auto size   = uint64_t {dw_size} * sizeof(uint32_t);
+	EXIT_IF(dst == nullptr || offset > gds.Size() || size > gds.Size() - offset ||
+	        gds.Mapped().empty());
+	std::memcpy(dst, gds.Mapped().data() + offset, static_cast<size_t>(size));
 }
 
 } // namespace Libs::Graphics::Sync

src/graphics/host_gpu/renderer/sync.h

@@ -8,6 +8,8 @@
 namespace Libs::Graphics {
 
 class CommandBuffer;
+class Buffer;
+class RenderContext;
 
 namespace Sync {
 
@@ -16,7 +18,6 @@ namespace Sync {
 [[nodiscard]] uint64_t ReadReferenceClock();
 
 void TriggerAgcUserInterrupt();
-void TriggerEopEvent(uint32_t context_id);
 void TriggerEopEventAtEndOfPipe(CommandBuffer& buffer, uint32_t context_id);
 
 void WriteAtEndOfPipe32(uint64_t submit_id, CommandBuffer& buffer, uint32_t* dst_gpu_addr,
@@ -46,8 +47,8 @@ void WriteAtEndOfPipeWithInterruptWriteBack64(uint64_t submit_id, CommandBuffer&
                                               uint64_t* dst_gpu_addr, uint64_t value,
                                               uint32_t context_id = 0);
 
-[[nodiscard]] uint64_t PrepareDisplayBufferFlip(CommandBuffer& buffer, int handle, int index,
-                                                int flip_mode, int64_t flip_arg);
+[[nodiscard]] uint64_t PrepareVideoOutFlip(CommandBuffer& buffer, int handle, int index,
+                                           int flip_mode, int64_t flip_arg);
 void WriteAtEndOfPipeOnlyFlip(uint64_t submit_id, CommandBuffer& buffer, int handle, int index,
                               int flip_mode, int64_t flip_arg, uint64_t request_id);
 void WriteAtEndOfPipeWithFlip32(uint64_t submit_id, CommandBuffer& buffer, uint32_t* dst_gpu_addr,
@@ -58,10 +59,10 @@ void WriteAtEndOfPipeWithInterruptWriteBackFlip32(uint64_t submit_id, CommandBuf
                                                   int handle, int index, int flip_mode,
                                                   int64_t flip_arg, uint64_t request_id);
 
-int  AddEqEvent(LibKernel::EventQueue::KernelEqueue eq, int id, void* udata);
+int  AddEqEvent(RenderContext& renderer, LibKernel::EventQueue::KernelEqueue eq, int id,
+                void* udata);
 int  DeleteEqEvent(LibKernel::EventQueue::KernelEqueue eq, int id);
-void ReadGds(uint32_t* dst, uint32_t dw_offset, uint32_t dw_size);
-void DeleteBuffers();
+void ReadGds(Buffer& gds, uint32_t* dst, uint32_t dw_offset, uint32_t dw_size);
 
 } // namespace Sync
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/textureCache.h

@@ -3,173 +3,184 @@
 
 #include "common/abi.h"
 #include "common/common.h"
-#include "common/threads.h"
+#include "common/lruCache.h"
 #include "graphics/host_gpu/memoryTracker.h"
-#include "graphics/host_gpu/renderer/imageInfo.h"
+#include "graphics/host_gpu/renderer/blitHelper.h"
+#include "graphics/host_gpu/renderer/image.h"
 #include "graphics/host_gpu/renderer/multiLevelPageTable.h"
-#include "graphics/host_gpu/renderer/tiler.h"
-#include "graphics/host_gpu/vulkanCommon.h"
 
+#include <compare>
 #include <map>
 #include <memory>
-#include <mutex>
+#include <optional>
+#include <set>
+#include <span>
+#include <utility>
 #include <vector>
 
 namespace Libs::Graphics {
 
-struct DepthStencilVulkanImage;
-struct GpuTextureVulkanImage;
 struct GraphicContext;
-struct ImageViewInfo;
-struct RenderTextureVulkanImage;
-struct StorageTextureVulkanImage;
-struct VideoOutVulkanImage;
-struct VulkanImage;
-struct VulkanMemory;
+class Buffer;
 class BufferCache;
 class CommandBuffer;
-class DummyTextureCache;
+class CommandScheduler;
 class ResourceMutex;
-
-[[nodiscard]] bool IsExactRenderTargetMipStorage(const ImageInfo& sampled, const ImageInfo& storage,
-                                                 vk::Format sampled_view_format,
-                                                 vk::Format storage_image_format) noexcept;
+class RenderExecutor;
+class StreamBuffer;
+class TileManager;
+struct TextureCacheTestAccess;
 
 class TextureCache {
 public:
-	struct RegionInfo {
-		bool image_pages        = false;
-		bool image_bytes        = false;
-		bool gpu_image_bytes    = false;
-		bool non_sampled_pages  = false;
-		bool metadata_pages     = false;
-		bool metadata_bytes     = false;
-		bool gpu_metadata_bytes = false;
-	};
-	struct MetaRangeInfo {
-		uint64_t metadata_address = 0;
-		uint64_t metadata_size    = 0;
-		uint32_t slice            = 0;
-		bool     full             = false;
+	enum class BindingType : uint8_t { Texture, Storage, RenderTarget, DepthTarget, VideoOut };
+
+	struct ImageDesc {
+		ImageInfo     info;
+		ImageViewInfo view_info;
+		BindingType   type = BindingType::Texture;
 	};
 
-	TextureCache(GraphicContext& graphics, PageManager& page_manager, BufferCache& buffer_cache,
-	             ResourceMutex& resource_mutex);
+	struct RegionInfo {
+		bool image_pages     = false;
+		bool image_bytes     = false;
+		bool gpu_image_bytes = false;
+	};
+
+	TextureCache(GraphicContext& graphics, CommandScheduler& scheduler, PageManager& page_manager,
+	             BufferCache& buffer_cache, ResourceMutex& resource_mutex);
 	~TextureCache();
 	KYTY_CLASS_NO_COPY(TextureCache);
 
-	[[nodiscard]] VulkanImage& FindTexture(CommandBuffer& command, const ImageInfo& info,
-	                                       bool metadata_read);
-	[[nodiscard]] StorageTextureVulkanImage& FindStorageTexture(CommandBuffer&   command,
-	                                                            const ImageInfo& info);
-	[[nodiscard]] RenderTextureVulkanImage&  FindRenderTarget(CommandBuffer&          command,
-	                                                          const RenderTargetInfo& info);
-	[[nodiscard]] DepthStencilVulkanImage&   FindDepthTarget(CommandBuffer&         command,
-	                                                         const DepthTargetInfo& info);
-	[[nodiscard]] std::vector<VideoOutVulkanImage*>
-	                   RegisterVideoOutSurfaces(const std::vector<VideoOutInfo>& infos);
-	void               RefreshVideoOut(VideoOutVulkanImage& image, bool render_target = false);
-	void               UnregisterVideoOutSurfaces(const std::vector<VideoOutVulkanImage*>& images);
-	[[nodiscard]] bool ClearImageFromBuffer(CommandBuffer& command, uint64_t vaddr, uint64_t size,
-	                                        uint32_t packed_clear);
-	void               MarkGpuWritten(VulkanImage& image);
-	void               PrepareHostWrite(uint64_t vaddr, uint64_t size);
-	[[nodiscard]] bool InvalidateMemoryFromGPU(uint64_t vaddr, uint64_t size,
-	                                           bool formatted_buffer_write = false);
-	[[nodiscard]] RenderTextureVulkanImage* FindRenderTargetByRange(CommandBuffer& command,
-	                                                                uint64_t vaddr, uint64_t size);
-	[[nodiscard]] vk::ImageView GetRenderTargetAttachmentView(RenderTextureVulkanImage& image,
-	                                                          vk::Format format, uint32_t level,
-	                                                          uint32_t base_layer,
-	                                                          uint32_t layer_count);
-	[[nodiscard]] vk::ImageView GetDepthTargetAttachmentView(DepthStencilVulkanImage& image,
-	                                                         uint32_t                 base_layer,
-	                                                         uint32_t                 layer_count);
-	[[nodiscard]] vk::ImageView
-	GetDepthTargetSampledView(DepthStencilVulkanImage& image, vk::Format view_format,
-	                          uint32_t swizzle, uint32_t base_level, uint32_t level_count,
-	                          vk::ImageViewType type, uint32_t base_layer, uint32_t layer_count);
-	[[nodiscard]] vk::ImageView GetSampledColorView(VulkanImage& image, vk::Format view_format,
-	                                                uint32_t swizzle, uint32_t base_level,
-	                                                uint32_t level_count, vk::ImageViewType type,
-	                                                uint32_t base_layer, uint32_t layer_count);
-	[[nodiscard]] vk::ImageView
-	GetRenderTargetStorageView(RenderTextureVulkanImage& image, vk::Format view_format,
-	                           uint32_t base_level, uint32_t level_count, vk::ImageViewType type,
-	                           uint32_t base_layer, uint32_t layer_count);
-	[[nodiscard]] vk::ImageView GetStorageTextureSampledView(StorageTextureVulkanImage& image,
-	                                                         const ImageInfo&           info);
-	[[nodiscard]] vk::ImageView GetStorageTextureStorageView(StorageTextureVulkanImage& image,
-	                                                         uint32_t                   base_level);
-	[[nodiscard]] DepthStencilVulkanImage*
-	FindDepthTargetByRange(CommandBuffer& command, uint64_t vaddr, uint64_t size,
-	                       bool allow_containing_sampled = false);
-	[[nodiscard]] RegionInfo QueryRegion(uint64_t vaddr, uint64_t size);
-	[[nodiscard]] bool       ResolveMetaRange(uint64_t vaddr, uint64_t size, MetaRangeInfo& info);
-	void                     RegisterMeta(uint64_t vaddr, uint64_t size, uint32_t layers = 1);
-	[[nodiscard]] bool       IsMeta(uint64_t vaddr);
-	[[nodiscard]] bool       IsMetaRange(uint64_t vaddr, uint64_t size);
-	[[nodiscard]] bool       IsMetaCleared(uint64_t vaddr, uint32_t slice);
-	[[nodiscard]] bool       ClearMeta(uint64_t vaddr);
-	[[nodiscard]] bool       TouchMeta(uint64_t vaddr, uint32_t slice, bool is_clear);
-	[[nodiscard]] bool       InvalidateMemory(PageFaultAccess access, uint64_t vaddr, uint64_t size,
-	                                          PageFaultPhase phase) noexcept;
-	void                     UnmapMemory(uint64_t vaddr, uint64_t size);
+	[[nodiscard]] ImageId       FindImage(ImageDesc& desc, bool exact_format = false);
+	[[nodiscard]] ImageId       FindImageFromRange(uint64_t address, uint64_t size,
+	                                               bool ensure_valid = true);
+	[[nodiscard]] vk::ImageView FindTexture(ImageId id, const ImageDesc& desc);
+	[[nodiscard]] vk::ImageView FindRenderTarget(ImageId id, const ImageDesc& desc);
+	[[nodiscard]] vk::ImageView FindDepthTarget(ImageId id, const ImageDesc& desc);
+	[[nodiscard]] Image&        GetImage(ImageId id);
+	[[nodiscard]] const Image&  GetImage(ImageId id) const;
+	void                        MarkGpuWritten(ImageId id);
 
-	VulkanImage& GetDummySampledTexture(bool uint_format, bool image_3d);
-	VulkanImage& GetDummyStorageTexture(bool uint_format, bool image_3d);
+	[[nodiscard]] bool ClearImageFromBuffer(CommandBuffer& command, uint64_t address, uint64_t size,
+	                                        uint32_t packed_clear);
+	void               PrepareHostWrite(uint64_t address, uint64_t size);
+	[[nodiscard]] bool SynchronizeImageToBuffer(uint64_t address, uint64_t size);
+	[[nodiscard]] bool InvalidateMemoryFromGPU(uint64_t address, uint64_t size,
+	                                           bool formatted_buffer_write = false);
+	[[nodiscard]] RegionInfo QueryRegion(uint64_t address, uint64_t size);
+
+	[[nodiscard]] bool IsMeta(uint64_t address);
+	[[nodiscard]] bool IsMetaCleared(uint64_t address, uint32_t slice);
+	[[nodiscard]] bool ClearMeta(uint64_t address);
+	[[nodiscard]] bool TouchMeta(uint64_t address, uint32_t slice, bool is_clear);
+
+	[[nodiscard]] bool InvalidateMemory(PageFaultAccess access, uint64_t address, uint64_t size,
+	                                    PageFaultPhase phase) noexcept;
+	void               UnmapMemory(uint64_t address, uint64_t size);
+	void               ProcessDownloadImages();
+	void               RunGarbageCollector();
 
 private:
-	struct CachedImage;
-	using ImageOwnerIndex = MultiRangePageOwnerIndex<CachedImage*>;
-	struct ReadbackWorker;
-	struct MetaDataInfo {
-		uint64_t size         = 0;
-		uint32_t layers       = 1;
-		uint32_t clear_mask   = 0;
-		bool     gpu_modified = false;
-	};
-	[[nodiscard]] vk::ImageView GetImageView(VulkanImage& image, const ImageViewInfo& info);
-	[[nodiscard]] bool          HasMetaOverlapLocked(uint64_t vaddr, uint64_t size) const;
-	[[nodiscard]] CachedImage*  FindGpuReadbackPageCandidateLocked(uint64_t vaddr, uint64_t size);
-	void                        RequireNoMetaOverlapLocked(uint64_t vaddr, uint64_t size) const;
-	void                        ResolveImageMetadataOverlapsLocked(uint64_t vaddr, uint64_t size);
-	void                        MarkSampledAliasesCpuDirtyLocked(uint64_t vaddr, uint64_t size);
-	void                        RetireSampledTargetAliases(const ImageInfo& requested);
-	void                        ResolveStorageImageOverlaps(const ImageInfo& requested);
-	void                        RetireStorageDepthAliasLocked(const ImageInfo& requested);
-	void                        RegisterImageLocked(CachedImage& image);
-	void                        UnregisterImageLocked(CachedImage& image, bool release_tracking);
-	[[nodiscard]] VulkanImage&  PublishImage(CommandBuffer&               command,
-	                                         std::shared_ptr<CachedImage> image);
-	[[nodiscard]] std::vector<CachedImage*> FindImagesInRegionLocked(uint64_t vaddr, uint64_t size,
-	                                                                 bool page_overlap);
-	void RequireRetirementIsolation(const std::vector<CachedImage*>& retire, const char* operation,
-	                                uint64_t address, uint64_t size) const;
-	void RetireImages(const std::vector<CachedImage*>& retire,
-	                  const CachedImage*               native_image_source = nullptr);
-	void RetireDepthMetadataLocked(const std::vector<CachedImage*>& retire,
-	                               uint64_t                         preserve_address = 0);
-	void MaterializeImagesToGuestLocked(const std::vector<std::shared_ptr<CachedImage>>& images);
-	void SynchronizeColorImageToBufferLocked(CachedImage& cached, uint64_t write_address,
-	                                         uint64_t write_size);
-	void SynchronizeDepthImageToBufferLocked(CachedImage& cached, uint64_t write_address,
-	                                         uint64_t write_size);
+	enum class TransferDirection { Upload, Download };
+	struct ColorTransferPlan;
+	struct DownloadPlan;
 
-	GraphicContext&                           m_graphics;
-	std::unique_ptr<DummyTextureCache>        m_dummy_textures;
-	TrackingSpinLock                          m_lock;
-	std::mutex                                m_fault_mutex;
-	MemoryTracker                             m_memory_tracker;
-	MemoryTracker                             m_metadata_tracker;
-	Tiler                                     m_tiler;
-	BufferCache&                              m_buffer_cache;
-	ResourceMutex&                            m_resource_mutex;
-	std::vector<std::shared_ptr<CachedImage>> m_images;
-	ImageOwnerIndex                           m_image_owner_index;
-	std::map<uint64_t, MetaDataInfo>          m_surface_metas;
-	std::unique_ptr<ReadbackWorker>           m_readback;
-	std::vector<uint8_t>                      m_buffer_transition_guest;
+	struct Slot {
+		std::shared_ptr<Image> image;
+		uint32_t               generation = 1;
+	};
+
+	struct MetaDataInfo {
+		uint32_t clear_mask = 0;
+	};
+
+	struct OverlapResult {
+		ImageId image;
+		int32_t mip   = -1;
+		int32_t layer = -1;
+	};
+
+	using ImageOwnerIndex = MultiRangePageOwnerIndex<ImageId>;
+
+	[[nodiscard]] Image&                 ResolveImage(ImageId id);
+	[[nodiscard]] const Image&           ResolveImage(ImageId id) const;
+	[[nodiscard]] std::shared_ptr<Image> ResolveOwner(ImageId id) const;
+	[[nodiscard]] ImageId                InsertImage(const ImageInfo& info);
+	[[nodiscard]] ImageId                GetNullImage(const ImageDesc& desc);
+	void                                 RegisterImage(ImageId id);
+	void                                 UnregisterImage(ImageId id, bool release_tracking);
+	void                                 DeleteImage(ImageId id, bool release_tracking = true);
+	void DeleteImages(std::span<const ImageId> ids, std::optional<ImageId> native_source = {});
+	void RetainImage(CommandBuffer& command, ImageId id);
+	void TouchImage(Image& image);
+	void TrackImageDownload(ImageId id);
+	void TrackImageDownloadLocked(ImageId id, Image& image);
+	[[nodiscard]] static bool SameBacking(const ImageInfo& cached, const ImageInfo& requested,
+	                                      bool exact_format);
+	[[nodiscard]] static BindingType UploadBinding(const Image& image);
+	[[nodiscard]] bool               SafeToDownload(const Image& image);
+
+	[[nodiscard]] std::vector<ImageId> FindImagesInRegion(uint64_t address, uint64_t size,
+	                                                      bool page_overlap) const;
+	[[nodiscard]] OverlapResult ResolveOverlap(const ImageInfo& requested, BindingType binding,
+	                                           ImageId cached, ImageId merged);
+	[[nodiscard]] ImageId       ResolveDepthOverlap(const ImageInfo& requested, BindingType binding,
+	                                                ImageId cached);
+	[[nodiscard]] ImageId       ExpandImage(const ImageInfo& info, ImageId source);
+	void                        RefreshImage(ImageId id, const ImageDesc& desc);
+	void                        InitializeImage(ImageId id, const ImageDesc& desc);
+	[[nodiscard]] ColorTransferPlan BuildColorTransfer(const Image& image, BindingType binding,
+	                                                   TransferDirection direction) const;
+	[[nodiscard]] DownloadPlan      BuildDownload(const Image& image) const;
+	void UploadImage(Image& image, const ImageDesc& desc, Buffer& source, uint64_t source_offset);
+	void DownloadImageData(Image& image, Buffer& destination, uint64_t destination_offset,
+	                       DownloadPlan plan);
+	void DownloadDepth(Image& image, Buffer& destination, uint64_t destination_offset);
+	void CommitGpuWrite(Image& image);
+	void PrepareImageCopy(Image& image);
+	void RefreshCopySource(ImageId id);
+	[[nodiscard]] bool CopyD16(Image& destination, Image& source);
+	void               CopyImage(ImageId destination, ImageId source);
+	void               AssociateStencil(ImageId depth, GuestRange stencil);
+	void               AssociateStencilLocked(ImageId depth, GuestRange stencil);
+	void CopyImageMip(ImageId destination, ImageId source, uint32_t mip, uint32_t layer);
+	void ValidateImageDesc(const ImageDesc& desc) const;
+
+	void InvalidateCpuAliases(uint64_t address, uint64_t size);
+	void RestoreGpuTracking(const Image& image);
+	void ReleaseGpuTracking(ImageId id);
+
+	[[nodiscard]] bool                          SynchronizeImageToBuffer(ImageId id);
+	void                                        DownloadImage(ImageId id);
+	[[nodiscard]] bool                          TryDownloadImage(ImageId id);
+	[[nodiscard]] std::pair<uint8_t*, uint64_t> MapDownload(uint64_t size, uint64_t alignment);
+	void QueueDownload(GuestRange range, StreamBuffer& download, uint8_t* mapped, uint64_t offset);
+
+	GraphicContext&                                   m_graphics;
+	CommandScheduler&                                 m_scheduler;
+	TrackingSpinLock                                  m_lock;
+	MemoryTracker                                     m_memory_tracker;
+	BlitHelper                                        m_blit_helper;
+	std::unique_ptr<TileManager>                      m_tiler;
+	BufferCache&                                      m_buffer_cache;
+	ResourceMutex&                                    m_resource_mutex;
+	std::vector<Slot>                                 m_slots;
+	std::vector<uint32_t>                             m_free_slots;
+	ImageOwnerIndex                                   m_image_owner_index;
+	std::map<vk::Format, ImageId>                     m_null_images;
+	Common::LeastRecentlyUsedCache<ImageId, uint64_t> m_lru_cache;
+	std::set<ImageId>                                 m_download_images;
+	std::map<uint64_t, MetaDataInfo>                  m_surface_metas;
+	uint64_t                                          m_total_used_memory  = 0;
+	uint64_t                                          m_trigger_gc_memory  = 0;
+	uint64_t                                          m_pressure_gc_memory = 1536ull * 1024 * 1024;
+	uint64_t m_critical_gc_memory     = 3ull * 1024 * 1024 * 1024;
+	uint64_t m_gc_tick                = 0;
+	bool     m_readback_linear_images = false;
+
+	friend struct TextureCacheTestAccess;
+	friend class RenderExecutor;
 };
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/tiler.cpp

@@ -1,161 +1,718 @@
 #include "graphics/host_gpu/renderer/tiler.h"
 
 #include "common/assert.h"
-#include "graphics/guest_gpu/gpu_defs.h"
-#include "graphics/guest_gpu/gpu_format.h"
-#include "graphics/guest_gpu/tile.h"
-#include "graphics/host_gpu/gpuTiler.h"
+#include "gpu_tiler_shaders/gpu_tiler_demote_d16_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_depth_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_promote_d16_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_prt_3d_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_prt_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_render_target_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_standard256_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_standard4_3d_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_standard4_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_standard64_3d_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_standard64_spv.h"
+#include "gpu_tiler_shaders/gpu_tiler_swap_bgra16_spv.h"
 #include "graphics/host_gpu/graphicContext.h"
-#include "graphics/host_gpu/objects/textureCommon.h"
+#include "graphics/host_gpu/renderer/commandScheduler.h"
 #include "graphics/host_gpu/renderer/image.h"
-#include "graphics/host_gpu/transfer.h"
+#include "graphics/host_gpu/renderer/streamBuffer.h"
 
-#include <vector>
+#include <algorithm>
+#include <array>
+#include <bit>
+#include <cstring>
+#include <limits>
 
 namespace Libs::Graphics {
-namespace {
 
-struct DepthTransfer {
-	std::vector<GpuTileInfo>     infos;
-	std::vector<BufferImageCopy> regions;
-};
-
-DepthTransfer MakeDepthTransfer(uint64_t size, uint32_t layers, uint32_t format,
-                                uint32_t bytes_per_element, uint32_t width, uint32_t height,
-                                uint32_t pitch, uint32_t base_layer, vk::ImageAspectFlags aspect) {
-	EXIT_IF(size == 0 || layers == 0 || size % layers != 0);
-	TileBlockLayout block {};
-	EXIT_NOT_IMPLEMENTED(
-	    !TileGetBlockLayout(TileBlockFamily::Depth64KB, bytes_per_element, block) ||
-	    Prospero::NumBytesPerElement(format) != bytes_per_element);
-
-	const uint64_t slice_size = size / layers;
-	DepthTransfer  transfer;
-	transfer.infos.reserve(layers);
-	transfer.regions.reserve(layers);
-	for (uint32_t layer = 0; layer < layers; layer++) {
-		const uint64_t offset = slice_size * layer;
-		GpuTileInfo    info {block.family,
-		                     block.bytes_per_element,
-		                     offset,
-		                     slice_size,
-		                     offset,
-		                     slice_size,
-		                     0,
-		                     width,
-		                     height,
-		                     1,
-		                     pitch};
-		info.surface_z = base_layer + layer;
-		transfer.infos.push_back(info);
-
-		BufferImageCopy region {};
-		region.offset    = static_cast<uint32_t>(offset);
-		region.pitch     = pitch;
-		region.width     = width;
-		region.height    = height;
-		region.dst_layer = base_layer + layer;
-		region.aspect    = aspect;
-		transfer.regions.push_back(region);
+TileManager::TileManager(GraphicContext& graphics, CommandScheduler& scheduler,
+                         StreamBuffer& stream_buffer)
+    : m_graphics(graphics), m_scheduler(scheduler), m_stream_buffer(stream_buffer) {
+	static_assert(FamilyCount == 9);
+	static_assert(sizeof(Push) == 52);
+	std::array<vk::DescriptorSetLayoutBinding, 3> bindings {};
+	for (uint32_t index = 0; index < 2; index++) {
+		bindings[index] = {index, vk::DescriptorType::eStorageBuffer, 1,
+		                   vk::ShaderStageFlagBits::eCompute, nullptr};
 	}
-	return transfer;
+	bindings[2] = {2, vk::DescriptorType::eUniformBuffer, 1, vk::ShaderStageFlagBits::eCompute,
+	               nullptr};
+
+	vk::DescriptorSetLayoutCreateInfo descriptor_info {};
+	descriptor_info.sType        = vk::StructureType::eDescriptorSetLayoutCreateInfo;
+	descriptor_info.flags        = vk::DescriptorSetLayoutCreateFlagBits::ePushDescriptorKHR;
+	descriptor_info.bindingCount = static_cast<uint32_t>(bindings.size());
+	descriptor_info.pBindings    = bindings.data();
+	RequireVulkanSuccess(m_graphics.device.createDescriptorSetLayout(&descriptor_info, nullptr,
+	                                                                 &m_descriptor_layout),
+	                     "create TileManager descriptor layout");
+
+	const vk::PushConstantRange  push_range {vk::ShaderStageFlagBits::eCompute, 0, sizeof(Push)};
+	vk::PipelineLayoutCreateInfo layout_info {};
+	layout_info.sType                  = vk::StructureType::ePipelineLayoutCreateInfo;
+	layout_info.setLayoutCount         = 1;
+	layout_info.pSetLayouts            = &m_descriptor_layout;
+	layout_info.pushConstantRangeCount = 1;
+	layout_info.pPushConstantRanges    = &push_range;
+	RequireVulkanSuccess(
+	    m_graphics.device.createPipelineLayout(&layout_info, nullptr, &m_pipeline_layout),
+	    "create TileManager pipeline layout");
 }
 
-void UploadDepth(DepthStencilVulkanImage& image, uint64_t source_address, uint64_t size,
-                 uint32_t layers, uint32_t format, uint32_t bytes_per_element, uint32_t width,
-                 uint32_t height, uint32_t pitch, uint32_t base_layer,
-                 vk::ImageAspectFlags aspect) {
-	auto transfer = MakeDepthTransfer(size, layers, format, bytes_per_element, width, height, pitch,
-	                                  base_layer, aspect);
-	Transfer::UploadTiledImage(image, reinterpret_cast<const void*>(source_address), size, size,
-	                           transfer.infos, transfer.regions,
-	                           vk::ImageLayout::eDepthStencilAttachmentOptimal);
-}
-
-template <uint32_t (*Encode)(uint16_t)>
-void UploadPromotedD16Depth(DepthStencilVulkanImage& image, const DepthTargetInfo& info,
-                            const BufferImageCopySource& source, uint32_t base_layer) {
-	const uint64_t guest_slice_size = info.size / info.layers;
-	const uint64_t texels           = static_cast<uint64_t>(info.pitch) * info.height;
-	const uint64_t host_slice_size  = texels * sizeof(uint32_t);
-	const uint64_t host_upload_size = host_slice_size * info.layers;
-	EXIT_IF(host_upload_size > UINT32_MAX);
-
-	auto transfer = MakeDepthTransfer(info.size, info.layers, info.guest_format,
-	                                  info.bytes_per_element, info.width, info.height, info.pitch,
-	                                  base_layer, vk::ImageAspectFlagBits::eDepth);
-	std::vector<uint16_t> guest_linear(info.size / sizeof(uint16_t));
-	GpuDetile(reinterpret_cast<const void*>(source.address), guest_linear.data(), info.size,
-	          info.size, transfer.infos);
-
-	Transfer::ScratchBuffer host_linear(host_upload_size);
-	for (uint32_t layer = 0; layer < info.layers; layer++) {
-		const auto* guest = guest_linear.data() + guest_slice_size / sizeof(uint16_t) * layer;
-		auto*       host  = reinterpret_cast<uint32_t*>(static_cast<uint8_t*>(host_linear.Data()) +
-		                                                host_slice_size * layer);
-		for (uint64_t texel = 0; texel < texels; texel++) {
-			host[texel] = Encode(guest[texel]);
-		}
-		transfer.regions[layer].offset = static_cast<uint32_t>(host_slice_size * layer);
-	}
-	Transfer::UploadImage(image, host_linear.Data(), host_upload_size, transfer.regions,
-	                      vk::ImageLayout::eDepthStencilAttachmentOptimal);
-}
-
-} // namespace
-
-void Tiler::DetileImage(GpuTextureVulkanImage& image, const ImageInfo& info,
-                        const BufferImageCopySource& source, bool refresh, bool storage) const {
-	if (refresh) Transfer::WaitForQueueIdle();
-
-	const bool array_texture  = TextureIsLayeredTexture(info.type);
-	const bool volume_texture = TextureIs3DTexture(info.type);
-	auto       layout         = TextureCalcUploadLayout(
-	    info.format, info.width, info.height, info.levels, info.depth, info.pitch, info.tile,
-	    info.size, true, volume_texture, storage ? "StorageTextureCache" : "TextureCache");
-	auto regions = TextureBuildUploadRegions(layout, image.format, info.width, info.height,
-	                                         info.depth, info.levels, array_texture, volume_texture,
-	                                         TextureUploadDestination::MipLevels);
-	TextureUploadGuestImage(image, reinterpret_cast<const void*>(source.address), info.size,
-	                        regions, layout, info.format, info.width, info.height, info.depth,
-	                        info.levels, storage ? "StorageTextureCache" : "TextureCache",
-	                        storage ? vk::ImageLayout::eGeneral
-	                                : vk::ImageLayout::eShaderReadOnlyOptimal);
-}
-
-void Tiler::DetileImage(DepthStencilVulkanImage& image, const DepthTargetInfo& info,
-                        const BufferImageCopySource& source, bool refresh,
-                        uint32_t base_layer) const {
-	EXIT_NOT_IMPLEMENTED(info.samples != 1 || image.samples != 1);
-	if (refresh) Transfer::WaitForQueueIdle();
-
-	if (DepthAspectTransferBytes(info.format) != info.bytes_per_element) {
-		switch (info.format) {
-			case vk::Format::eD24UnormS8Uint:
-				UploadPromotedD16Depth<EncodeD16AsD24>(image, info, source, base_layer);
-				return;
-			case vk::Format::eD32SfloatS8Uint:
-				UploadPromotedD16Depth<EncodeD16AsD32>(image, info, source, base_layer);
-				return;
-			default: EXIT_NOT_IMPLEMENTED(true);
+TileManager::~TileManager() {
+	for (auto pipeline: m_pipelines) {
+		if (pipeline != nullptr) {
+			m_graphics.device.destroyPipeline(pipeline, nullptr);
 		}
 	}
-	UploadDepth(image, source.address, info.size, info.layers, info.guest_format,
-	            info.bytes_per_element, info.width, info.height, info.pitch, base_layer,
-	            vk::ImageAspectFlagBits::eDepth);
+	if (m_d16_to_d24 != nullptr) {
+		m_graphics.device.destroyPipeline(m_d16_to_d24, nullptr);
+	}
+	if (m_d16_to_d32 != nullptr) {
+		m_graphics.device.destroyPipeline(m_d16_to_d32, nullptr);
+	}
+	if (m_d24_to_d16 != nullptr) {
+		m_graphics.device.destroyPipeline(m_d24_to_d16, nullptr);
+	}
+	if (m_d32_to_d16 != nullptr) {
+		m_graphics.device.destroyPipeline(m_d32_to_d16, nullptr);
+	}
+	if (m_swap_bgra16 != nullptr) {
+		m_graphics.device.destroyPipeline(m_swap_bgra16, nullptr);
+	}
+	if (m_pipeline_layout != nullptr) {
+		m_graphics.device.destroyPipelineLayout(m_pipeline_layout, nullptr);
+	}
+	if (m_descriptor_layout != nullptr) {
+		m_graphics.device.destroyDescriptorSetLayout(m_descriptor_layout, nullptr);
+	}
 }
 
-void Tiler::DetileStencil(DepthStencilVulkanImage& image, const DepthTargetInfo& info,
-                          const BufferImageCopySource& source, bool refresh,
-                          uint32_t base_layer) const {
-	EXIT_NOT_IMPLEMENTED(info.samples != 1 || image.samples != 1);
-	if (refresh) Transfer::WaitForQueueIdle();
+TileManager::Scratch TileManager::AllocateScratch(uint64_t size) {
+	EXIT_IF(size == 0);
+	vk::BufferCreateInfo create {};
+	create.sType = vk::StructureType::eBufferCreateInfo;
+	create.size  = size;
+	create.usage = vk::BufferUsageFlagBits::eStorageBuffer | vk::BufferUsageFlagBits::eTransferSrc |
+	               vk::BufferUsageFlagBits::eTransferDst;
+	create.sharingMode = vk::SharingMode::eExclusive;
 
-	const auto format = Prospero::GpuEnumValue(Prospero::BufferFormat::k8UInt);
-	const auto pitch  = TileGetTexturePitch(format, info.width, 1,
-	                                        Prospero::GpuEnumValue(Prospero::TileMode::kDepth));
-	UploadDepth(image, source.address, info.stencil_size, info.layers, format, 1, info.width,
-	            info.height, pitch, base_layer, vk::ImageAspectFlagBits::eStencil);
+	VmaAllocationCreateInfo allocate {};
+	allocate.usage       = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+	VkBuffer      buffer = VK_NULL_HANDLE;
+	VmaAllocation memory = nullptr;
+	const auto    raw    = static_cast<VkBufferCreateInfo>(create);
+	RequireVulkanSuccess(static_cast<vk::Result>(vmaCreateBuffer(
+	                         m_graphics.allocator, &raw, &allocate, &buffer, &memory, nullptr)),
+	                     "allocate TileManager scratch buffer");
+	return {buffer, memory, size};
+}
+
+void TileManager::DeferDestroy(Scratch scratch) {
+	auto allocator = m_graphics.allocator;
+	m_scheduler.DeferOperation(
+	    [allocator, scratch] { vmaDestroyBuffer(allocator, scratch.buffer, scratch.allocation); });
+}
+
+void TileManager::Prepare(bool tile, uint64_t tiled_capacity, uint64_t linear_capacity,
+                          std::span<const GpuTileInfo> infos, uint64_t source_base,
+                          uint64_t target_base, std::vector<Dispatch>& dispatches) {
+	EXIT_IF(infos.empty() || tiled_capacity == 0 || linear_capacity == 0);
+	const auto& limits = m_graphics.GetPhysicalDeviceProperties().limits;
+	EXIT_NOT_IMPLEMENTED(tiled_capacity > UINT32_MAX || linear_capacity > UINT32_MAX);
+
+	const auto checked_multiply = [](uint64_t left, uint64_t right, uint64_t& result) {
+		return (left == 0 || right <= UINT64_MAX / left) && (result = left * right, true);
+	};
+	const auto checked_add = [](uint64_t left, uint64_t right, uint64_t& result) {
+		return right <= UINT64_MAX - left && (result = left + right, true);
+	};
+	const auto valid_range = [](uint64_t offset, uint64_t size, uint64_t capacity) {
+		return size != 0 && offset <= capacity && size <= capacity - offset;
+	};
+
+	dispatches.clear();
+	dispatches.reserve(infos.size());
+	for (const auto& info: infos) {
+		TileBlockLayout block {};
+		const uint32_t  tiled_width  = info.tiled_width != 0 ? info.tiled_width : info.pitch;
+		const uint32_t  tiled_height = info.tiled_height != 0 ? info.tiled_height : info.height;
+		const uint64_t  groups_x     = (static_cast<uint64_t>(info.width) + 7u) / 8u;
+		const uint64_t  groups_y     = (static_cast<uint64_t>(info.height) + 7u) / 8u;
+		EXIT_NOT_IMPLEMENTED(
+		    !TileGetBlockLayout(info.family, info.bytes_per_element, block) || info.width == 0 ||
+		    info.height == 0 || info.depth == 0 || info.pitch < info.width ||
+		    groups_x > limits.maxComputeWorkGroupCount[0] ||
+		    groups_y > limits.maxComputeWorkGroupCount[1] ||
+		    info.depth > limits.maxComputeWorkGroupCount[2] ||
+		    (!info.tail && (tiled_width < info.width || tiled_height < info.height)) ||
+		    !valid_range(info.linear_offset, info.linear_size, linear_capacity) ||
+		    !valid_range(info.tiled_offset, info.tiled_size, tiled_capacity) ||
+		    (block.block_depth == 1 && info.depth != 1));
+
+		uint64_t pitch_bytes = 0;
+		EXIT_NOT_IMPLEMENTED(!checked_multiply(info.pitch, info.bytes_per_element, pitch_bytes) ||
+		                     pitch_bytes > UINT32_MAX);
+		uint64_t slice_bytes   = info.linear_slice_stride;
+		uint64_t minimum_slice = 0;
+		EXIT_NOT_IMPLEMENTED(!checked_multiply(pitch_bytes, info.height, minimum_slice));
+		if (slice_bytes == 0) {
+			slice_bytes = minimum_slice;
+		}
+		uint64_t linear_used = 0;
+		uint64_t bytes       = 0;
+		EXIT_NOT_IMPLEMENTED((info.depth > 1 && slice_bytes < minimum_slice) ||
+		                     !checked_multiply(info.depth - 1u, slice_bytes, bytes) ||
+		                     !checked_add(linear_used, bytes, linear_used) ||
+		                     !checked_multiply(info.height - 1u, pitch_bytes, bytes) ||
+		                     !checked_add(linear_used, bytes, linear_used) ||
+		                     !checked_multiply(info.width, info.bytes_per_element, bytes) ||
+		                     !checked_add(linear_used, bytes, linear_used) ||
+		                     linear_used > info.linear_size || slice_bytes > UINT32_MAX);
+
+		const uint64_t columns =
+		    (static_cast<uint64_t>(tiled_width) + block.block_width - 1u) / block.block_width;
+		const uint64_t rows =
+		    (static_cast<uint64_t>(tiled_height) + block.block_height - 1u) / block.block_height;
+		uint64_t blocks_per_slice = 0;
+		EXIT_NOT_IMPLEMENTED(!checked_multiply(columns, rows, blocks_per_slice) ||
+		                     columns > UINT32_MAX || blocks_per_slice > UINT32_MAX);
+		if (info.tail) {
+			EXIT_NOT_IMPLEMENTED(
+			    info.family == TileBlockFamily::Standard256B || info.depth > block.block_depth ||
+			    info.tail_x >= block.block_width || info.width > block.block_width - info.tail_x ||
+			    info.tail_y >= block.block_height ||
+			    info.height > block.block_height - info.tail_y ||
+			    info.tiled_size < block.block_size);
+		} else {
+			const uint64_t slices =
+			    (static_cast<uint64_t>(info.depth) + block.block_depth - 1u) / block.block_depth;
+			uint64_t tiled_used = 0;
+			EXIT_NOT_IMPLEMENTED(!checked_multiply(blocks_per_slice, slices, tiled_used) ||
+			                     !checked_multiply(tiled_used, block.block_size, tiled_used) ||
+			                     tiled_used > info.tiled_size);
+		}
+
+		const uint32_t alignment = std::min(info.bytes_per_element, 4u);
+		EXIT_NOT_IMPLEMENTED(((info.linear_offset | info.tiled_offset | pitch_bytes | slice_bytes) &
+		                      (alignment - 1u)) != 0);
+		const uint64_t src = source_base + (tile ? info.linear_offset : info.tiled_offset);
+		const uint64_t dst = target_base + (tile ? info.tiled_offset : info.linear_offset);
+		EXIT_NOT_IMPLEMENTED(src > UINT32_MAX || dst > UINT32_MAX);
+
+		const uint32_t family_index  = static_cast<uint32_t>(info.family);
+		const uint32_t element_index = std::countr_zero(info.bytes_per_element);
+		EXIT_NOT_IMPLEMENTED(family_index >= FamilyCount || element_index >= BytesPerElementCount);
+		Dispatch dispatch {};
+		dispatch.pipeline_slot =
+		    ((tile ? FamilyCount : 0u) + family_index) * BytesPerElementCount + element_index;
+		dispatch.push.src_base         = static_cast<uint32_t>(src);
+		dispatch.push.dst_base         = static_cast<uint32_t>(dst);
+		dispatch.push.width            = info.width;
+		dispatch.push.height           = info.height;
+		dispatch.push.depth            = info.depth;
+		dispatch.push.surface_z        = info.surface_z;
+		dispatch.push.pitch_bytes      = static_cast<uint32_t>(pitch_bytes);
+		dispatch.push.slice_bytes      = static_cast<uint32_t>(slice_bytes);
+		dispatch.push.blocks_per_row   = static_cast<uint32_t>(columns);
+		dispatch.push.blocks_per_slice = static_cast<uint32_t>(blocks_per_slice);
+		dispatch.push.tail_x           = info.tail_x;
+		dispatch.push.tail_y           = info.tail_y;
+		dispatch.push.tail             = info.tail;
+		dispatches.push_back(dispatch);
+	}
+
+	const uint64_t uniform_alignment =
+	    std::max<uint64_t>(limits.minUniformBufferOffsetAlignment, 1);
+	const uint64_t stride = (sizeof(Push) + uniform_alignment - 1) & ~(uniform_alignment - 1);
+	EXIT_NOT_IMPLEMENTED(dispatches.size() > UINT64_MAX / stride);
+	const uint64_t bytes  = dispatches.size() * stride;
+	auto [mapped, offset] = m_stream_buffer.Map(bytes, uniform_alignment);
+	EXIT_IF(mapped == nullptr);
+	for (size_t index = 0; index < dispatches.size(); index++) {
+		std::memcpy(mapped + index * stride, &dispatches[index].push, sizeof(Push));
+		dispatches[index].params_offset = offset + index * stride;
+	}
+	m_stream_buffer.Commit();
+}
+
+vk::Pipeline TileManager::GetPipeline(uint32_t slot) {
+	EXIT_IF(slot >= m_pipelines.size());
+	if (m_pipelines[slot] != nullptr) {
+		return m_pipelines[slot];
+	}
+	struct Shader {
+		const uint32_t* code;
+		size_t          words;
+	};
+	static constexpr std::array<Shader, FamilyCount> shaders {{
+	    {GPU_TILER_STANDARD256_SPV, std::size(GPU_TILER_STANDARD256_SPV)},
+	    {GPU_TILER_STANDARD4_SPV, std::size(GPU_TILER_STANDARD4_SPV)},
+	    {GPU_TILER_STANDARD4_3D_SPV, std::size(GPU_TILER_STANDARD4_3D_SPV)},
+	    {GPU_TILER_STANDARD64_SPV, std::size(GPU_TILER_STANDARD64_SPV)},
+	    {GPU_TILER_STANDARD64_3D_SPV, std::size(GPU_TILER_STANDARD64_3D_SPV)},
+	    {GPU_TILER_PRT_SPV, std::size(GPU_TILER_PRT_SPV)},
+	    {GPU_TILER_PRT_3D_SPV, std::size(GPU_TILER_PRT_3D_SPV)},
+	    {GPU_TILER_RENDER_TARGET_SPV, std::size(GPU_TILER_RENDER_TARGET_SPV)},
+	    {GPU_TILER_DEPTH_SPV, std::size(GPU_TILER_DEPTH_SPV)},
+	}};
+	const uint32_t                                   element_index = slot % BytesPerElementCount;
+	const uint32_t                   direction_index = slot / (FamilyCount * BytesPerElementCount);
+	const uint32_t                   family_index    = (slot / BytesPerElementCount) % FamilyCount;
+	const uint32_t                   values[] {1u << element_index, direction_index};
+	const vk::SpecializationMapEntry entries[] {{0, 0, 4}, {1, 4, 4}};
+	const vk::SpecializationInfo     specialization {2, entries, sizeof(values), values};
+	vk::ShaderModuleCreateInfo       module_info {};
+	module_info.sType       = vk::StructureType::eShaderModuleCreateInfo;
+	module_info.codeSize    = shaders[family_index].words * sizeof(uint32_t);
+	module_info.pCode       = shaders[family_index].code;
+	vk::ShaderModule module = nullptr;
+	RequireVulkanSuccess(m_graphics.device.createShaderModule(&module_info, nullptr, &module),
+	                     "create TileManager shader module");
+	vk::PipelineShaderStageCreateInfo stage {};
+	stage.sType               = vk::StructureType::ePipelineShaderStageCreateInfo;
+	stage.stage               = vk::ShaderStageFlagBits::eCompute;
+	stage.module              = module;
+	stage.pName               = "main";
+	stage.pSpecializationInfo = &specialization;
+	vk::ComputePipelineCreateInfo create {};
+	create.sType  = vk::StructureType::eComputePipelineCreateInfo;
+	create.stage  = stage;
+	create.layout = m_pipeline_layout;
+	const auto result =
+	    m_graphics.device.createComputePipelines(nullptr, 1, &create, nullptr, &m_pipelines[slot]);
+	m_graphics.device.destroyShaderModule(module, nullptr);
+	RequireVulkanSuccess(result, "create TileManager pipeline");
+	return m_pipelines[slot];
+}
+
+void TileManager::Record(bool tile, vk::Buffer source, uint64_t source_offset,
+                         uint64_t source_capacity, vk::Buffer target, uint64_t target_offset,
+                         uint64_t target_capacity, std::span<Dispatch> dispatches,
+                         bool clear_target) {
+	const auto&    limits = m_graphics.GetPhysicalDeviceProperties().limits;
+	const uint64_t descriptor_alignment =
+	    std::max<uint64_t>(limits.minStorageBufferOffsetAlignment, 4);
+	const uint64_t source_descriptor_offset = source_offset & ~(descriptor_alignment - 1);
+	const uint64_t target_descriptor_offset = target_offset & ~(descriptor_alignment - 1);
+	const uint64_t source_base              = source_offset - source_descriptor_offset;
+	const uint64_t target_base              = target_offset - target_descriptor_offset;
+	const uint64_t source_range             = (source_base + source_capacity + 3u) & ~uint64_t {3};
+	const uint64_t target_range             = (target_base + target_capacity + 3u) & ~uint64_t {3};
+	EXIT_NOT_IMPLEMENTED(source_range > limits.maxStorageBufferRange ||
+	                     target_range > limits.maxStorageBufferRange || target_offset % 4 != 0 ||
+	                     target_capacity % 4 != 0);
+
+	m_scheduler.EndRendering();
+	auto                    command = m_scheduler.Current().Handle();
+	vk::BufferMemoryBarrier barriers[3] {};
+	barriers[0].sType         = vk::StructureType::eBufferMemoryBarrier;
+	barriers[0].srcAccessMask = vk::AccessFlagBits::eMemoryWrite | vk::AccessFlagBits::eHostWrite;
+	barriers[0].dstAccessMask = vk::AccessFlagBits::eShaderRead;
+	barriers[0].srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barriers[0].dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barriers[0].buffer              = source;
+	barriers[0].offset              = source_offset;
+	barriers[0].size                = source_capacity;
+	barriers[1]                     = barriers[0];
+	barriers[1].srcAccessMask = vk::AccessFlagBits::eMemoryWrite | vk::AccessFlagBits::eHostWrite;
+	barriers[1].dstAccessMask =
+	    clear_target ? vk::AccessFlagBits::eTransferWrite
+	                 : vk::AccessFlagBits::eShaderRead | vk::AccessFlagBits::eShaderWrite;
+	barriers[1].buffer        = target;
+	barriers[1].offset        = target_offset;
+	barriers[1].size          = target_capacity;
+	barriers[2]               = barriers[0];
+	barriers[2].srcAccessMask = vk::AccessFlagBits::eHostWrite;
+	barriers[2].dstAccessMask = vk::AccessFlagBits::eUniformRead;
+	barriers[2].buffer        = m_stream_buffer.Handle();
+	barriers[2].offset        = dispatches.front().params_offset;
+	barriers[2].size =
+	    dispatches.back().params_offset - dispatches.front().params_offset + sizeof(Push);
+	command.pipelineBarrier(
+	    vk::PipelineStageFlagBits::eAllCommands | vk::PipelineStageFlagBits::eHost,
+	    vk::PipelineStageFlagBits::eComputeShader | vk::PipelineStageFlagBits::eTransfer, {}, 0,
+	    nullptr, 3, barriers, 0, nullptr);
+	if (clear_target) {
+		command.fillBuffer(target, target_offset, target_capacity, 0);
+		barriers[1].srcAccessMask = vk::AccessFlagBits::eTransferWrite;
+		barriers[1].dstAccessMask =
+		    vk::AccessFlagBits::eShaderRead | vk::AccessFlagBits::eShaderWrite;
+		command.pipelineBarrier(vk::PipelineStageFlagBits::eTransfer,
+		                        vk::PipelineStageFlagBits::eComputeShader, {}, 0, nullptr, 1,
+		                        &barriers[1], 0, nullptr);
+	}
+
+	const vk::DescriptorBufferInfo source_info {source, source_descriptor_offset, source_range};
+	const vk::DescriptorBufferInfo target_info {target, target_descriptor_offset, target_range};
+	for (auto& dispatch: dispatches) {
+		const vk::DescriptorBufferInfo        params_info {m_stream_buffer.Handle(),
+		                                                   dispatch.params_offset, sizeof(Push)};
+		const vk::DescriptorBufferInfo        infos[] {source_info, target_info, params_info};
+		std::array<vk::WriteDescriptorSet, 3> writes {};
+		for (uint32_t index = 0; index < writes.size(); index++) {
+			writes[index].sType           = vk::StructureType::eWriteDescriptorSet;
+			writes[index].dstBinding      = index;
+			writes[index].descriptorCount = 1;
+			writes[index].descriptorType  = index == 2 ? vk::DescriptorType::eUniformBuffer
+			                                           : vk::DescriptorType::eStorageBuffer;
+			writes[index].pBufferInfo     = &infos[index];
+		}
+		command.pushDescriptorSetKHR(vk::PipelineBindPoint::eCompute, m_pipeline_layout, 0,
+		                             static_cast<uint32_t>(writes.size()), writes.data());
+		command.bindPipeline(vk::PipelineBindPoint::eCompute, GetPipeline(dispatch.pipeline_slot));
+		command.dispatch((dispatch.push.width + 7u) / 8u, (dispatch.push.height + 7u) / 8u,
+		                 dispatch.push.depth);
+	}
+
+	barriers[1].srcAccessMask = vk::AccessFlagBits::eShaderWrite;
+	barriers[1].dstAccessMask = vk::AccessFlagBits::eTransferRead | vk::AccessFlagBits::eMemoryRead;
+	command.pipelineBarrier(vk::PipelineStageFlagBits::eComputeShader,
+	                        vk::PipelineStageFlagBits::eAllCommands, {}, 0, nullptr, 1,
+	                        &barriers[1], 0, nullptr);
+}
+
+TileManager::Result TileManager::Detile(vk::Buffer tiled, uint64_t tiled_offset,
+                                        uint64_t tiled_capacity, uint64_t linear_capacity,
+                                        std::span<const GpuTileInfo> infos) {
+	const auto&    limits = m_graphics.GetPhysicalDeviceProperties().limits;
+	const uint64_t descriptor_alignment =
+	    std::max<uint64_t>(limits.minStorageBufferOffsetAlignment, 4);
+	const uint64_t        source_base = tiled_offset & (descriptor_alignment - 1);
+	std::vector<Dispatch> dispatches;
+	Prepare(false, tiled_capacity, linear_capacity, infos, source_base, 0, dispatches);
+	auto scratch = AllocateScratch((linear_capacity + 3u) & ~uint64_t {3});
+	DeferDestroy(scratch);
+	Record(false, tiled, tiled_offset, tiled_capacity, scratch.buffer, 0, scratch.size, dispatches,
+	       true);
+	return {scratch.buffer, 0, linear_capacity};
+}
+
+void TileManager::Tile(vk::Buffer linear, uint64_t linear_offset, uint64_t linear_capacity,
+                       vk::Buffer tiled, uint64_t tiled_offset, uint64_t tiled_capacity,
+                       std::span<const GpuTileInfo> infos) {
+	const auto&    limits = m_graphics.GetPhysicalDeviceProperties().limits;
+	const uint64_t descriptor_alignment =
+	    std::max<uint64_t>(limits.minStorageBufferOffsetAlignment, 4);
+	const uint64_t        source_base = linear_offset & (descriptor_alignment - 1);
+	const uint64_t        target_base = tiled_offset & (descriptor_alignment - 1);
+	std::vector<Dispatch> dispatches;
+	Prepare(true, tiled_capacity, linear_capacity, infos, source_base, target_base, dispatches);
+	Record(true, linear, linear_offset, linear_capacity, tiled, tiled_offset, tiled_capacity,
+	       dispatches, false);
+}
+
+void TileManager::TileImage(Image& image, std::span<const vk::BufferImageCopy> regions,
+                            vk::Buffer tiled, uint64_t tiled_offset, uint64_t tiled_capacity,
+                            uint64_t linear_capacity, std::span<const GpuTileInfo> infos,
+                            ColorTransform transform) {
+	EXIT_IF(regions.empty());
+	const auto&    limits = m_graphics.GetPhysicalDeviceProperties().limits;
+	const uint64_t descriptor_alignment =
+	    std::max<uint64_t>(limits.minStorageBufferOffsetAlignment, 4);
+	const uint64_t        target_base = tiled_offset & (descriptor_alignment - 1);
+	std::vector<Dispatch> dispatches;
+	// Reserve all stream parameters before creating a scheduler-lived scratch dependency:
+	// StreamBuffer::Map is allowed to submit the current tick when it wraps.
+	Prepare(true, tiled_capacity, linear_capacity, infos, 0, target_base, dispatches);
+	auto linear = AllocateScratch((linear_capacity + 3u) & ~uint64_t {3});
+	DeferDestroy(linear);
+	image.Download(regions, linear.buffer, 0, linear.size);
+	Result source {linear.buffer, 0, linear.size};
+	if (transform == ColorTransform::SwapBgra16) {
+		source = SwapBgra16(source);
+	}
+	Record(true, source.buffer, source.offset, linear_capacity, tiled, tiled_offset, tiled_capacity,
+	       dispatches, false);
+}
+
+TileManager::Result TileManager::GetScratchBuffer(uint64_t size) {
+	auto scratch = AllocateScratch((size + 3u) & ~uint64_t {3});
+	DeferDestroy(scratch);
+	return {scratch.buffer, 0, scratch.size};
+}
+
+TileManager::StorageBinding TileManager::BindStorage(Result buffer, uint64_t size) const {
+	const auto& limits            = m_graphics.GetPhysicalDeviceProperties().limits;
+	const auto  alignment         = std::max<uint64_t>(limits.minStorageBufferOffsetAlignment, 4);
+	const auto  descriptor_offset = buffer.offset - buffer.offset % alignment;
+	const auto  base              = buffer.offset - descriptor_offset;
+	EXIT_IF(buffer.buffer == nullptr || size == 0 || buffer.size < size || base > UINT32_MAX ||
+	        size > UINT64_MAX - base || base + size > UINT64_MAX - 3);
+	const auto range = (base + size + 3) & ~uint64_t {3};
+	EXIT_IF(range > limits.maxStorageBufferRange || range > UINT32_MAX);
+	return {{buffer.buffer, descriptor_offset, range}, static_cast<uint32_t>(base)};
+}
+
+uint32_t TileManager::ConversionRows(uint64_t offset, uint64_t row_stride, uint64_t active,
+                                     uint32_t remaining, uint64_t alignment, uint64_t max_range,
+                                     uint32_t max_groups) noexcept {
+	if (row_stride == 0 || active == 0 || remaining == 0 || alignment == 0 || max_groups == 0) {
+		return 0;
+	}
+	const auto prefix = offset % alignment;
+	if (prefix >= max_range || active > max_range - prefix) {
+		return 0;
+	}
+	const auto descriptor_rows = 1 + (max_range - prefix - active) / row_stride;
+	return static_cast<uint32_t>(std::min<uint64_t>({remaining, descriptor_rows, max_groups}));
+}
+
+void TileManager::ConvertD16(Result source, Result target, D16Direction direction, bool d32,
+                             const D16Layout& layout) {
+	vk::Pipeline* pipeline_pointer = nullptr;
+	if (direction == D16Direction::Promote) {
+		pipeline_pointer = d32 ? &m_d16_to_d32 : &m_d16_to_d24;
+	} else {
+		pipeline_pointer = d32 ? &m_d32_to_d16 : &m_d24_to_d16;
+	}
+	auto& pipeline = *pipeline_pointer;
+	if (pipeline == nullptr) {
+		const uint32_t                   value = d32 ? 1u : 0u;
+		const vk::SpecializationMapEntry entry {0, 0, sizeof(value)};
+		const vk::SpecializationInfo     specialization {1, &entry, sizeof(value), &value};
+		const uint32_t*                  code  = nullptr;
+		size_t                           words = 0;
+		if (direction == D16Direction::Promote) {
+			code  = GPU_TILER_PROMOTE_D16_SPV;
+			words = std::size(GPU_TILER_PROMOTE_D16_SPV);
+		} else {
+			code  = GPU_TILER_DEMOTE_D16_SPV;
+			words = std::size(GPU_TILER_DEMOTE_D16_SPV);
+		}
+		vk::ShaderModuleCreateInfo module_info {};
+		module_info.sType       = vk::StructureType::eShaderModuleCreateInfo;
+		module_info.codeSize    = words * sizeof(uint32_t);
+		module_info.pCode       = code;
+		vk::ShaderModule module = nullptr;
+		RequireVulkanSuccess(m_graphics.device.createShaderModule(&module_info, nullptr, &module),
+		                     "create D16 conversion shader module");
+		vk::PipelineShaderStageCreateInfo stage {};
+		stage.sType               = vk::StructureType::ePipelineShaderStageCreateInfo;
+		stage.stage               = vk::ShaderStageFlagBits::eCompute;
+		stage.module              = module;
+		stage.pName               = "main";
+		stage.pSpecializationInfo = &specialization;
+		vk::ComputePipelineCreateInfo create {};
+		create.sType  = vk::StructureType::eComputePipelineCreateInfo;
+		create.stage  = stage;
+		create.layout = m_pipeline_layout;
+		const auto result =
+		    m_graphics.device.createComputePipelines(nullptr, 1, &create, nullptr, &pipeline);
+		m_graphics.device.destroyShaderModule(module, nullptr);
+		RequireVulkanSuccess(result, "create D16 conversion pipeline");
+	}
+
+	const uint64_t source_element =
+	    direction == D16Direction::Promote ? sizeof(uint16_t) : sizeof(uint32_t);
+	const uint64_t target_element =
+	    direction == D16Direction::Promote ? sizeof(uint32_t) : sizeof(uint16_t);
+	const uint64_t source_active = static_cast<uint64_t>(layout.width) * source_element;
+	const uint64_t target_active = static_cast<uint64_t>(layout.width) * target_element;
+	const auto     required      = [](uint32_t height, uint32_t layers, uint64_t row_stride,
+	                                  uint64_t slice_stride, uint64_t active) {
+		EXIT_IF(height == 0 || layers == 0 || row_stride < active ||
+		        (height - 1) > (UINT64_MAX - active) / row_stride);
+		const auto slice = static_cast<uint64_t>(height - 1) * row_stride + active;
+		EXIT_IF(slice_stride < slice || (layers - 1) > (UINT64_MAX - slice) / slice_stride);
+		return static_cast<uint64_t>(layers - 1) * slice_stride + slice;
+	};
+	EXIT_IF(layout.width == 0 || layout.source_row_stride > UINT32_MAX ||
+	        layout.target_row_stride > UINT32_MAX);
+	const auto source_required = required(layout.height, layout.layers, layout.source_row_stride,
+	                                      layout.source_slice_stride, source_active);
+	const auto target_required = required(layout.height, layout.layers, layout.target_row_stride,
+	                                      layout.target_slice_stride, target_active);
+	EXIT_IF(source_required > UINT64_MAX - 3 || target_required > UINT64_MAX - 3);
+	const auto source_barrier_size = (source_required + 3) & ~uint64_t {3};
+	const auto target_barrier_size = (target_required + 3) & ~uint64_t {3};
+	EXIT_IF(source.size < source_barrier_size || target.size < target_barrier_size);
+
+	m_scheduler.EndRendering();
+	auto                    command = m_scheduler.Current().Handle();
+	vk::BufferMemoryBarrier barriers[2] {};
+	barriers[0].sType               = vk::StructureType::eBufferMemoryBarrier;
+	barriers[0].srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barriers[0].dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barriers[0].buffer              = source.buffer;
+	barriers[0].offset              = source.offset;
+	barriers[0].size                = source_barrier_size;
+	barriers[0].srcAccessMask = vk::AccessFlagBits::eMemoryWrite | vk::AccessFlagBits::eHostWrite |
+	                            vk::AccessFlagBits::eTransferWrite |
+	                            vk::AccessFlagBits::eShaderWrite;
+	barriers[0].dstAccessMask = vk::AccessFlagBits::eShaderRead;
+	barriers[1].sType         = vk::StructureType::eBufferMemoryBarrier;
+	barriers[1].srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barriers[1].dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+	barriers[1].buffer              = target.buffer;
+	barriers[1].offset              = target.offset;
+	barriers[1].size                = target_barrier_size;
+	barriers[1].srcAccessMask = vk::AccessFlagBits::eMemoryRead | vk::AccessFlagBits::eMemoryWrite |
+	                            vk::AccessFlagBits::eHostWrite |
+	                            vk::AccessFlagBits::eTransferWrite |
+	                            vk::AccessFlagBits::eShaderWrite;
+	barriers[1].dstAccessMask = vk::AccessFlagBits::eShaderRead | vk::AccessFlagBits::eShaderWrite;
+	command.pipelineBarrier(
+	    vk::PipelineStageFlagBits::eAllCommands | vk::PipelineStageFlagBits::eHost,
+	    vk::PipelineStageFlagBits::eComputeShader, {}, 0, nullptr, 2, barriers, 0, nullptr);
+	command.bindPipeline(vk::PipelineBindPoint::eCompute, pipeline);
+	const auto& limits              = m_graphics.GetPhysicalDeviceProperties().limits;
+	const auto descriptor_alignment = std::max<uint64_t>(limits.minStorageBufferOffsetAlignment, 4);
+	const auto rows_for = [&](Result buffer, uint64_t relative, uint64_t stride, uint64_t active,
+	                          uint32_t remaining) {
+		EXIT_IF(relative > buffer.size || buffer.offset > UINT64_MAX - relative);
+		const auto offset = buffer.offset + relative;
+		return ConversionRows(offset, stride, active, remaining, descriptor_alignment,
+		                      limits.maxStorageBufferRange, limits.maxComputeWorkGroupCount[1]);
+	};
+	const auto groups_x = (static_cast<uint64_t>(layout.width) + 63u) / 64u;
+	EXIT_IF(groups_x == 0 || groups_x > limits.maxComputeWorkGroupCount[0]);
+	for (uint32_t layer = 0; layer < layout.layers; layer++) {
+		for (uint32_t row = 0; row < layout.height;) {
+			const auto source_relative =
+			    layout.source_slice_stride * layer + layout.source_row_stride * row;
+			const auto target_relative =
+			    layout.target_slice_stride * layer + layout.target_row_stride * row;
+			const auto remaining = layout.height - row;
+			const auto rows = std::min(rows_for(source, source_relative, layout.source_row_stride,
+			                                    source_active, remaining),
+			                           rows_for(target, target_relative, layout.target_row_stride,
+			                                    target_active, remaining));
+			EXIT_IF(rows == 0);
+			const auto source_span =
+			    static_cast<uint64_t>(rows - 1) * layout.source_row_stride + source_active;
+			const auto target_span =
+			    static_cast<uint64_t>(rows - 1) * layout.target_row_stride + target_active;
+			const auto source_binding = BindStorage(
+			    {source.buffer, source.offset + source_relative, source.size - source_relative},
+			    source_span);
+			const auto target_binding = BindStorage(
+			    {target.buffer, target.offset + target_relative, target.size - target_relative},
+			    target_span);
+			const vk::DescriptorBufferInfo infos[] {
+			    source_binding.info,
+			    target_binding.info,
+			};
+			std::array<vk::WriteDescriptorSet, 2> writes {};
+			for (uint32_t index = 0; index < writes.size(); index++) {
+				writes[index].sType           = vk::StructureType::eWriteDescriptorSet;
+				writes[index].dstBinding      = index;
+				writes[index].descriptorCount = 1;
+				writes[index].descriptorType  = vk::DescriptorType::eStorageBuffer;
+				writes[index].pBufferInfo     = &infos[index];
+			}
+			command.pushDescriptorSetKHR(vk::PipelineBindPoint::eCompute, m_pipeline_layout, 0,
+			                             static_cast<uint32_t>(writes.size()), writes.data());
+			Push push {};
+			push.src_base    = source_binding.base;
+			push.dst_base    = target_binding.base;
+			push.width       = layout.width;
+			push.height      = rows;
+			push.pitch_bytes = static_cast<uint32_t>(layout.source_row_stride);
+			push.slice_bytes = static_cast<uint32_t>(layout.target_row_stride);
+			command.pushConstants(m_pipeline_layout, vk::ShaderStageFlagBits::eCompute, 0,
+			                      sizeof(push), &push);
+			command.dispatch(static_cast<uint32_t>(groups_x), rows, 1);
+			row += rows;
+		}
+	}
+	barriers[1].srcAccessMask = vk::AccessFlagBits::eShaderWrite;
+	barriers[1].dstAccessMask = vk::AccessFlagBits::eTransferRead | vk::AccessFlagBits::eMemoryRead;
+	command.pipelineBarrier(vk::PipelineStageFlagBits::eComputeShader,
+	                        vk::PipelineStageFlagBits::eAllCommands, {}, 0, nullptr, 1,
+	                        &barriers[1], 0, nullptr);
+}
+
+void TileManager::SwapBgra16(Result input, Result output, uint32_t pixels) {
+	if (m_swap_bgra16 == nullptr) {
+		vk::ShaderModuleCreateInfo module_info {};
+		module_info.sType       = vk::StructureType::eShaderModuleCreateInfo;
+		module_info.codeSize    = std::size(GPU_TILER_SWAP_BGRA16_SPV) * sizeof(uint32_t);
+		module_info.pCode       = GPU_TILER_SWAP_BGRA16_SPV;
+		vk::ShaderModule module = nullptr;
+		RequireVulkanSuccess(m_graphics.device.createShaderModule(&module_info, nullptr, &module),
+		                     "create BGRA16 swap shader module");
+		vk::PipelineShaderStageCreateInfo stage {};
+		stage.sType  = vk::StructureType::ePipelineShaderStageCreateInfo;
+		stage.stage  = vk::ShaderStageFlagBits::eCompute;
+		stage.module = module;
+		stage.pName  = "main";
+		vk::ComputePipelineCreateInfo create {};
+		create.sType  = vk::StructureType::eComputePipelineCreateInfo;
+		create.stage  = stage;
+		create.layout = m_pipeline_layout;
+		const auto result =
+		    m_graphics.device.createComputePipelines(nullptr, 1, &create, nullptr, &m_swap_bgra16);
+		m_graphics.device.destroyShaderModule(module, nullptr);
+		RequireVulkanSuccess(result, "create BGRA16 swap pipeline");
+	}
+	const uint64_t bytes = static_cast<uint64_t>(pixels) * 8u;
+	EXIT_IF(pixels == 0);
+	const auto input_binding  = BindStorage(input, bytes);
+	const auto output_binding = BindStorage(output, bytes);
+
+	const vk::DescriptorBufferInfo infos[] {
+	    input_binding.info,
+	    output_binding.info,
+	};
+	std::array<vk::WriteDescriptorSet, 2> writes {};
+	for (uint32_t index = 0; index < writes.size(); index++) {
+		writes[index].sType           = vk::StructureType::eWriteDescriptorSet;
+		writes[index].dstBinding      = index;
+		writes[index].descriptorCount = 1;
+		writes[index].descriptorType  = vk::DescriptorType::eStorageBuffer;
+		writes[index].pBufferInfo     = &infos[index];
+	}
+	vk::BufferMemoryBarrier barriers[2] {};
+	for (uint32_t index = 0; index < 2; index++) {
+		barriers[index].sType               = vk::StructureType::eBufferMemoryBarrier;
+		barriers[index].srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+		barriers[index].dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
+		barriers[index].buffer              = infos[index].buffer;
+		barriers[index].offset              = infos[index].offset;
+		barriers[index].size                = infos[index].range;
+	}
+	barriers[0].srcAccessMask = vk::AccessFlagBits::eMemoryWrite | vk::AccessFlagBits::eHostWrite |
+	                            vk::AccessFlagBits::eShaderWrite;
+	barriers[0].dstAccessMask = vk::AccessFlagBits::eShaderRead;
+	barriers[1].srcAccessMask = vk::AccessFlagBits::eMemoryRead;
+	barriers[1].dstAccessMask = vk::AccessFlagBits::eShaderWrite;
+	m_scheduler.EndRendering();
+	auto command = m_scheduler.Current().Handle();
+	command.pipelineBarrier(
+	    vk::PipelineStageFlagBits::eAllCommands | vk::PipelineStageFlagBits::eHost,
+	    vk::PipelineStageFlagBits::eComputeShader, {}, 0, nullptr, 2, barriers, 0, nullptr);
+	command.bindPipeline(vk::PipelineBindPoint::eCompute, m_swap_bgra16);
+	command.pushDescriptorSetKHR(vk::PipelineBindPoint::eCompute, m_pipeline_layout, 0,
+	                             static_cast<uint32_t>(writes.size()), writes.data());
+	Push push {};
+	push.src_base = input_binding.base;
+	push.dst_base = output_binding.base;
+	push.width    = pixels;
+	command.pushConstants(m_pipeline_layout, vk::ShaderStageFlagBits::eCompute, 0, sizeof(push),
+	                      &push);
+	command.dispatch((pixels + 63u) / 64u, 1, 1);
+	barriers[1].srcAccessMask = vk::AccessFlagBits::eShaderWrite;
+	barriers[1].dstAccessMask = vk::AccessFlagBits::eTransferRead;
+	command.pipelineBarrier(vk::PipelineStageFlagBits::eComputeShader,
+	                        vk::PipelineStageFlagBits::eTransfer, {}, 0, nullptr, 1, &barriers[1],
+	                        0, nullptr);
+}
+
+TileManager::Result TileManager::SwapBgra16(Result input) {
+	EXIT_NOT_IMPLEMENTED(input.size == 0 || input.size % 8u != 0 || input.size / 8u > UINT32_MAX);
+	auto output = AllocateScratch(input.size);
+	DeferDestroy(output);
+	Result result {output.buffer, 0, output.size};
+	SwapBgra16(input, result, static_cast<uint32_t>(input.size / 8u));
+	return result;
+}
+
+void TileManager::SwapBgra16(Result input, Result output) {
+	EXIT_NOT_IMPLEMENTED(input.size == 0 || input.size % 8u != 0 || input.size / 8u > UINT32_MAX ||
+	                     output.size < input.size);
+	SwapBgra16(input, output, static_cast<uint32_t>(input.size / 8u));
 }
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/renderer/tiler.h

@@ -2,26 +2,146 @@
 #define EMULATOR_SRC_GRAPHICS_HOST_GPU_RENDERER_TILER_H_
 
 #include "common/common.h"
-#include "graphics/host_gpu/renderer/bufferCache.h"
-#include "graphics/host_gpu/renderer/imageInfo.h"
+#include "graphics/guest_gpu/tile.h"
+#include "graphics/host_gpu/vulkanCommon.h"
+
+#include <array>
+#include <span>
+#include <vector>
+#include <vk_mem_alloc.h>
 
 namespace Libs::Graphics {
 
-struct DepthStencilVulkanImage;
-struct GpuTextureVulkanImage;
-class Tiler final {
-public:
-	Tiler() = default;
-	KYTY_CLASS_NO_COPY(Tiler);
+class CommandScheduler;
+class Image;
+class StreamBuffer;
+struct GraphicContext;
+struct TileManagerTestAccess;
 
-	void DetileImage(GpuTextureVulkanImage& image, const ImageInfo& info,
-	                 const BufferImageCopySource& source, bool refresh, bool storage) const;
-	void DetileImage(DepthStencilVulkanImage& image, const DepthTargetInfo& info,
-	                 const BufferImageCopySource& source, bool refresh,
-	                 uint32_t base_layer = 0) const;
-	void DetileStencil(DepthStencilVulkanImage& image, const DepthTargetInfo& info,
-	                   const BufferImageCopySource& source, bool refresh,
-	                   uint32_t base_layer = 0) const;
+struct GpuTileInfo {
+	TileBlockFamily family              = TileBlockFamily::Count;
+	uint32_t        bytes_per_element   = 0;
+	uint64_t        linear_offset       = 0;
+	uint64_t        linear_size         = 0;
+	uint64_t        tiled_offset        = 0;
+	uint64_t        tiled_size          = 0;
+	uint64_t        linear_slice_stride = 0;
+	uint32_t        width               = 0;
+	uint32_t        height              = 0;
+	uint32_t        depth               = 1;
+	uint32_t        pitch               = 0;
+	uint32_t        tail_x              = 0;
+	uint32_t        tail_y              = 0;
+	bool            tail                = false;
+	uint32_t        tiled_width         = 0;
+	uint32_t        tiled_height        = 0;
+	uint32_t        surface_z           = 0;
+};
+
+class TileManager final {
+public:
+	enum class D16Direction { Promote, Demote };
+	enum class ColorTransform { None, SwapBgra16 };
+
+	struct Result {
+		vk::Buffer buffer = nullptr;
+		uint64_t   offset = 0;
+		uint64_t   size   = 0;
+	};
+	struct D16Layout {
+		uint32_t width               = 0;
+		uint32_t height              = 0;
+		uint32_t layers              = 0;
+		uint64_t source_row_stride   = 0;
+		uint64_t target_row_stride   = 0;
+		uint64_t source_slice_stride = 0;
+		uint64_t target_slice_stride = 0;
+	};
+
+	TileManager(GraphicContext& graphics, CommandScheduler& scheduler, StreamBuffer& stream_buffer);
+	~TileManager();
+	KYTY_CLASS_NO_COPY(TileManager);
+
+	// The returned device-local buffer remains alive through the current scheduler tick.
+	[[nodiscard]] Result Detile(vk::Buffer tiled, uint64_t tiled_offset, uint64_t tiled_capacity,
+	                            uint64_t linear_capacity, std::span<const GpuTileInfo> infos);
+	void Tile(vk::Buffer linear, uint64_t linear_offset, uint64_t linear_capacity, vk::Buffer tiled,
+	          uint64_t tiled_offset, uint64_t tiled_capacity, std::span<const GpuTileInfo> infos);
+	void TileImage(Image& image, std::span<const vk::BufferImageCopy> regions, vk::Buffer tiled,
+	               uint64_t tiled_offset, uint64_t tiled_capacity, uint64_t linear_capacity,
+	               std::span<const GpuTileInfo> infos,
+	               ColorTransform               transform = ColorTransform::None);
+	[[nodiscard]] Result GetScratchBuffer(uint64_t size);
+	void                 ConvertD16(Result source, Result target, D16Direction direction, bool d32,
+	                                const D16Layout& layout);
+	[[nodiscard]] Result SwapBgra16(Result input);
+	void                 SwapBgra16(Result input, Result output);
+
+private:
+	friend struct TileManagerTestAccess;
+
+	static constexpr uint32_t FamilyCount          = static_cast<uint32_t>(TileBlockFamily::Count);
+	static constexpr uint32_t BytesPerElementCount = 5;
+	static constexpr uint32_t DirectionCount       = 2;
+	static constexpr uint32_t PipelineCount = FamilyCount * BytesPerElementCount * DirectionCount;
+
+	struct Push {
+		uint32_t src_base;
+		uint32_t dst_base;
+		uint32_t width;
+		uint32_t height;
+		uint32_t depth;
+		uint32_t surface_z;
+		uint32_t pitch_bytes;
+		uint32_t slice_bytes;
+		uint32_t blocks_per_row;
+		uint32_t blocks_per_slice;
+		uint32_t tail_x;
+		uint32_t tail_y;
+		uint32_t tail;
+	};
+	struct Dispatch {
+		Push     push {};
+		uint32_t pipeline_slot = 0;
+		uint64_t params_offset = 0;
+	};
+	struct Scratch {
+		vk::Buffer    buffer     = nullptr;
+		VmaAllocation allocation = nullptr;
+		uint64_t      size       = 0;
+	};
+	struct StorageBinding {
+		vk::DescriptorBufferInfo info;
+		uint32_t                 base = 0;
+	};
+
+	[[nodiscard]] Scratch         AllocateScratch(uint64_t size);
+	[[nodiscard]] StorageBinding  BindStorage(Result buffer, uint64_t size) const;
+	[[nodiscard]] static uint32_t ConversionRows(uint64_t offset, uint64_t row_stride,
+	                                             uint64_t active, uint32_t remaining,
+	                                             uint64_t alignment, uint64_t max_range,
+	                                             uint32_t max_groups) noexcept;
+	void                          DeferDestroy(Scratch scratch);
+	void Prepare(bool tile, uint64_t tiled_capacity, uint64_t linear_capacity,
+	             std::span<const GpuTileInfo> infos, uint64_t source_base, uint64_t target_base,
+	             std::vector<Dispatch>& dispatches);
+	void Record(bool tile, vk::Buffer source, uint64_t source_offset, uint64_t source_capacity,
+	            vk::Buffer target, uint64_t target_offset, uint64_t target_capacity,
+	            std::span<Dispatch> dispatches, bool clear_target);
+	[[nodiscard]] vk::Pipeline GetPipeline(uint32_t slot);
+	void                       SwapBgra16(Result input, Result output, uint32_t pixels);
+
+	GraphicContext&                         m_graphics;
+	CommandScheduler&                       m_scheduler;
+	StreamBuffer&                           m_stream_buffer;
+	vk::DescriptorSetLayout                 m_descriptor_layout = nullptr;
+	vk::PipelineLayout                      m_pipeline_layout   = nullptr;
+	std::array<vk::Pipeline, PipelineCount> m_pipelines {};
+	vk::Pipeline                            m_d16_to_d24  = nullptr;
+	vk::Pipeline                            m_d16_to_d32  = nullptr;
+	vk::Pipeline                            m_d24_to_d16  = nullptr;
+	vk::Pipeline                            m_d32_to_d16  = nullptr;
+	vk::Pipeline                            m_swap_bgra16 = nullptr;
 };
 
 } // namespace Libs::Graphics

src/graphics/host_gpu/shaders/gpu_blit_color_to_ms_depth.frag

@@ -0,0 +1,10 @@
+#version 450 core
+#extension GL_EXT_samplerless_texture_functions : require
+
+layout(binding = 0, set = 0) uniform texture2D color;
+layout(location = 0) in vec2 uv;
+
+void main() {
+	ivec2 coord  = ivec2(uv * vec2(textureSize(color, 0)));
+	gl_FragDepth = texelFetch(color, coord, 0)[gl_SampleID];
+}

src/graphics/host_gpu/shaders/gpu_blit_fs_triangle.vert

@@ -0,0 +1,9 @@
+#version 450
+
+layout(location = 0) out vec2 uv;
+
+void main() {
+	vec2 position = vec2(float((gl_VertexIndex & 1u) << 2u), float((gl_VertexIndex & 2u) << 1u));
+	gl_Position   = vec4(position - vec2(1.0), 0.0, 1.0);
+	uv            = position * 0.5;
+}

src/graphics/host_gpu/shaders/gpu_test_ms_depth.comp

@@ -0,0 +1,23 @@
+#version 450
+#extension GL_EXT_samplerless_texture_functions : require
+
+layout(local_size_x = 4) in;
+
+layout(set = 0, binding = 0) uniform texture2DMS input_depth;
+layout(set = 0, binding = 1, std430) buffer Output {
+	uint value[];
+}
+output_data;
+
+layout(push_constant) uniform Push {
+	uint samples;
+}
+push;
+
+void main() {
+	const uint sample_id = gl_LocalInvocationID.x;
+	if (sample_id < push.samples) {
+		output_data.value[sample_id] =
+		    floatBitsToUint(texelFetch(input_depth, ivec2(0), int(sample_id)).x);
+	}
+}

src/graphics/host_gpu/shaders/gpu_tiler_common.inc

@@ -1,9 +1,9 @@
-layout(local_size_x = 64) in;
+layout(local_size_x = 8, local_size_y = 8) in;
 
 layout(set = 0, binding = 0, std430) readonly buffer Input { uint data[]; } input_buffer;
 layout(set = 0, binding = 1, std430) buffer Output { uint data[]; } output_buffer;
 
-layout(push_constant) uniform Push {
+layout(set = 0, binding = 2, std140) uniform Push {
 	uint src_base;
 	uint dst_base;
 	uint width;
@@ -17,8 +17,6 @@ layout(push_constant) uniform Push {
 	uint tail_x;
 	uint tail_y;
 	uint tail;
-	uint first;
-	uint count;
 } params;
 
 void copy_element(uint src, uint dst) {
@@ -29,24 +27,18 @@ void copy_element(uint src, uint dst) {
 	} else {
 		uint mask = ELEMENT_BYTES == 1 ? 0xffu : 0xffffu;
 		uint value = (input_buffer.data[src >> 2] >> ((src & 3u) * 8u)) & mask;
-		atomicOr(output_buffer.data[dst >> 2], value << ((dst & 3u) * 8u));
+		uint shift = (dst & 3u) * 8u;
+		atomicAnd(output_buffer.data[dst >> 2], ~(mask << shift));
+		atomicOr(output_buffer.data[dst >> 2], value << shift);
 	}
 }
 
 void main() {
-	uint index = gl_GlobalInvocationID.x;
-	if (index >= params.count) {
+	uvec3 p = gl_GlobalInvocationID;
+	if (p.x >= params.width || p.y >= params.height || p.z >= params.depth) {
 		return;
 	}
 
-	uint element = params.first + index;
-	uint plane = params.width * params.height;
-	uvec3 p;
-	p.z = element / plane;
-	element -= p.z * plane;
-	p.y = element / params.width;
-	p.x = element - p.y * params.width;
-
 	uvec3 extent = block_extent();
 	uvec3 swizzle = p;
 	uvec3 block = uvec3(0);

src/graphics/host_gpu/shaders/gpu_tiler_demote_d16.comp

@@ -0,0 +1,45 @@
+#version 450
+
+layout(constant_id = 0) const uint D32 = 0u;
+layout(local_size_x = 64) in;
+
+layout(set = 0, binding = 0, std430) readonly buffer Input { uint data[]; } input_buffer;
+layout(set = 0, binding = 1, std430) buffer Output { uint data[]; } output_buffer;
+
+layout(push_constant, std430) uniform Push {
+	uint src_base;
+	uint dst_base;
+	uint width;
+	uint height;
+	uint depth;
+	uint surface_z;
+	uint pitch_bytes;
+	uint slice_bytes;
+	uint blocks_per_row;
+	uint blocks_per_slice;
+	uint tail_x;
+	uint tail_y;
+	uint tail;
+} params;
+
+uint decode(uint value) {
+	float normalized = D32 != 0u
+		? clamp(uintBitsToFloat(value), 0.0, 1.0)
+		: float(value & 0x00ffffffu) / 16777215.0;
+	return uint(round(normalized * 65535.0));
+}
+
+void main() {
+	uint x = gl_GlobalInvocationID.x;
+	uint y = gl_GlobalInvocationID.y;
+	if (x >= params.width || y >= params.height) {
+		return;
+	}
+	uint src = params.src_base + y * params.pitch_bytes + x * 4u;
+	uint dst = params.dst_base + y * params.slice_bytes + x * 2u;
+	uint shift = (dst & 2u) * 8u;
+	uint mask = 0xffffu << shift;
+	uint word = dst >> 2u;
+	atomicAnd(output_buffer.data[word], ~mask);
+	atomicOr(output_buffer.data[word], decode(input_buffer.data[src >> 2u]) << shift);
+}

src/graphics/host_gpu/shaders/gpu_tiler_promote_d16.comp

@@ -0,0 +1,39 @@
+#version 450
+
+layout(constant_id = 0) const uint D32 = 0u;
+layout(local_size_x = 64) in;
+
+layout(set = 0, binding = 0, std430) readonly buffer Input { uint data[]; } input_buffer;
+layout(set = 0, binding = 1, std430) buffer Output { uint data[]; } output_buffer;
+
+layout(push_constant, std430) uniform Push {
+	uint src_base;
+	uint dst_base;
+	uint width;
+	uint height;
+	uint depth;
+	uint surface_z;
+	uint pitch_bytes;
+	uint slice_bytes;
+	uint blocks_per_row;
+	uint blocks_per_slice;
+	uint tail_x;
+	uint tail_y;
+	uint tail;
+} params;
+
+void main() {
+	uint x = gl_GlobalInvocationID.x;
+	uint y = gl_GlobalInvocationID.y;
+	if (x >= params.width || y >= params.height) {
+		return;
+	}
+	uint src = params.src_base + y * params.pitch_bytes + x * 2u;
+	uint packed = input_buffer.data[src >> 2u];
+	uint value = (packed >> ((src & 2u) * 8u)) & 0xffffu;
+	uint encoded = D32 != 0u
+		? floatBitsToUint(float(value) / 65535.0)
+		: value * 256u + (value + 128u) / 257u;
+	uint dst = params.dst_base + y * params.slice_bytes + x * 4u;
+	output_buffer.data[dst >> 2u] = encoded;
+}

src/graphics/host_gpu/shaders/gpu_tiler_swap_bgra16.comp

@@ -0,0 +1,35 @@
+#version 450
+
+layout(local_size_x = 64) in;
+
+layout(set = 0, binding = 0, std430) readonly buffer Input { uint data[]; } input_buffer;
+layout(set = 0, binding = 1, std430) buffer Output { uint data[]; } output_buffer;
+
+layout(push_constant, std430) uniform Push {
+	uint src_base;
+	uint dst_base;
+	uint width;
+	uint height;
+	uint depth;
+	uint surface_z;
+	uint pitch_bytes;
+	uint slice_bytes;
+	uint blocks_per_row;
+	uint blocks_per_slice;
+	uint tail_x;
+	uint tail_y;
+	uint tail;
+} params;
+
+void main() {
+	uint pixel = gl_GlobalInvocationID.x;
+	if (pixel >= params.width) {
+		return;
+	}
+	uint src = (params.src_base >> 2u) + pixel * 2u;
+	uint dst = (params.dst_base >> 2u) + pixel * 2u;
+	uint bg = input_buffer.data[src];
+	uint ra = input_buffer.data[src + 1u];
+	output_buffer.data[dst] = (ra & 0x0000ffffu) | (bg & 0xffff0000u);
+	output_buffer.data[dst + 1u] = (bg & 0x0000ffffu) | (ra & 0xffff0000u);
+}