kernel: explain a commit-limit failure at startup (#395)

When CreateFileMapping cannot reserve the guest backing store the log only
carries the raw Win32 error, which gives no clue that the paging file is the
thing to change. Print the size that was asked for and say so directly when the
failure is ERROR_NO_SYSTEM_RESOURCES or ERROR_COMMITMENT_LIMIT.

.gitignore

@@ -5,3 +5,4 @@ build/
 _Build/vscode-clang/
 _Build/
 cmake-build-debug/
+_PipelineCache/

src/common/emulatorConfig.h

@@ -59,7 +59,7 @@ struct ConfigOptions {
 	bool                   command_buffer_dump_enabled = false;
 	std::filesystem::path  command_buffer_dump_folder  = "_Buffers";
 	bool                   graphics_debug_dump_enabled = false;
-	OutputDirection        printf_direction            = OutputDirection::Console;
+	OutputDirection        printf_direction            = OutputDirection::Silent;
 	std::filesystem::path  printf_output_file          = "_kyty.txt";
 	ProfilerDirection      profiler_direction          = ProfilerDirection::None;
 	bool                   spirv_debug_printf_enabled  = false;

src/common/file.cpp

@@ -25,9 +25,6 @@
 #ifdef CopyFile
 #undef CopyFile
 #endif
-#ifdef MoveFile
-#undef MoveFile
-#endif
 #endif
 
 namespace Common {
@@ -544,14 +541,14 @@ bool File::CopyFile(const std::filesystem::path& src,
 	return SysFileCopyFile(src, dst);
 }
 
-bool File::MoveFile(const std::filesystem::path& src,
-                    const std::filesystem::path& dst) // @suppress("Member declaration not found")
+bool File::RenameFile(const std::filesystem::path& src,
+                      const std::filesystem::path& dst) // @suppress("Member declaration not found")
 {
 	if (IsFileExisting(dst)) {
 		DeleteFile(dst); // @suppress("Invalid arguments")
 	}
 
-	return SysFileMoveFile(src, dst);
+	return SysFileRenameFile(src, dst);
 }
 
 void File::RemoveReadonly(const std::filesystem::path& name) {

src/common/file.h

@@ -20,9 +20,6 @@
 #ifdef CopyFile
 #undef CopyFile
 #endif
-#ifdef MoveFile
-#undef MoveFile
-#endif
 #endif
 
 namespace Common {
@@ -107,7 +104,7 @@ public:
 	static std::vector<FindInfo> FindFiles(const std::filesystem::path& path);
 	static std::vector<DirEntry> GetDirEntries(const std::filesystem::path& path);
 	static bool CopyFile(const std::filesystem::path& src, const std::filesystem::path& dst);
-	static bool MoveFile(const std::filesystem::path& src, const std::filesystem::path& dst);
+	static bool RenameFile(const std::filesystem::path& src, const std::filesystem::path& dst);
 	static void RemoveReadonly(const std::filesystem::path& name);
 
 	KYTY_CLASS_NO_COPY(File);

src/common/platform/sysFileIO.h

@@ -80,7 +80,7 @@ void SysFileFindFiles(const std::filesystem::path& path, std::vector<sys_file_fi
 // NOLINTNEXTLINE(google-runtime-references)
 void SysFileGetDents(const std::filesystem::path& path, std::vector<sys_dir_entry_t>& out);
 bool SysFileCopyFile(const std::filesystem::path& src, const std::filesystem::path& dst);
-bool SysFileMoveFile(const std::filesystem::path& src, const std::filesystem::path& dst);
+bool SysFileRenameFile(const std::filesystem::path& src, const std::filesystem::path& dst);
 void SysFileRemoveReadonly(const std::filesystem::path& name);
 
 #endif /* KYTY_COMMON_PLATFORM_SYSFILEIO_H_ */

src/common/platform/sysLinuxFileIO.cpp

@@ -693,7 +693,7 @@ bool SysFileCopyFile(const std::filesystem::path& src, const std::filesystem::pa
 	       !error;
 }
 
-bool SysFileMoveFile(const std::filesystem::path& src, const std::filesystem::path& dst) {
+bool SysFileRenameFile(const std::filesystem::path& src, const std::filesystem::path& dst) {
 	auto real_src = get_internal_name(src);
 	auto real_dst = get_internal_name(dst);
 

src/common/platform/sysWindowsFileIO.cpp

@@ -565,7 +565,7 @@ bool SysFileCopyFile(const std::filesystem::path& src, const std::filesystem::pa
 	return CopyFileW(src_wide.c_str(), dst_wide.c_str(), FALSE) != 0;
 }
 
-bool SysFileMoveFile(const std::filesystem::path& src, const std::filesystem::path& dst) {
+bool SysFileRenameFile(const std::filesystem::path& src, const std::filesystem::path& dst) {
 	auto src_wide = src.wstring();
 	auto dst_wide = dst.wstring();
 	return MoveFileW(src_wide.c_str(), dst_wide.c_str()) != 0;

src/generate_version.cmake

@@ -1,5 +1,6 @@
 set(KYTY_GIT_VERSION "unknown")
 set(KYTY_GIT_HASH "unknown")
+set(KYTY_GIT_REVISION "unknown")
 if(GIT_EXECUTABLE)
 	execute_process(
 		COMMAND "${GIT_EXECUTABLE}" describe --tags --always --dirty
@@ -14,16 +15,18 @@ if(GIT_EXECUTABLE)
 	endif()
 
 	execute_process(
-		COMMAND "${GIT_EXECUTABLE}" rev-parse --short=7 HEAD
+		COMMAND "${GIT_EXECUTABLE}" rev-parse HEAD
 		WORKING_DIRECTORY "${GIT_WORKING_DIRECTORY}"
-		OUTPUT_VARIABLE KYTY_GIT_HASH
+		OUTPUT_VARIABLE KYTY_GIT_REVISION
 		OUTPUT_STRIP_TRAILING_WHITESPACE
 		RESULT_VARIABLE GIT_HASH_RESULT
 		ERROR_QUIET
 	)
 	if(NOT GIT_HASH_RESULT EQUAL 0)
 		set(KYTY_GIT_HASH "unknown")
+		set(KYTY_GIT_REVISION "unknown")
 	else()
+		string(SUBSTRING "${KYTY_GIT_REVISION}" 0 7 KYTY_GIT_HASH)
 		execute_process(
 			COMMAND "${GIT_EXECUTABLE}" diff-index --quiet HEAD --
 			WORKING_DIRECTORY "${GIT_WORKING_DIRECTORY}"

src/graphics/host_gpu/renderer/colorRenderTarget.cpp

@@ -219,8 +219,9 @@ void RenderExecutor::ResolveRenderColorTarget(uint64_t submit_id, CommandBuffer&
 		     rt.attrib.num_fragments, bytes_per_element, rt.cmask.addr, rt.fmask.addr,
 		     rt.dcc_addr.addr);
 	}
-	if ((standard64 || depth_tile) && (rt.attrib3.dimension != 1 || rt.attrib3.depth != 0 ||
-	                                   view.base_layer != 0 || view.image_layers != 1)) {
+	if ((standard64 || depth_tile) &&
+	    (rt.attrib3.dimension != 1 || rt.attrib3.depth != 0 ||
+	     (depth_tile && (view.base_layer != 0 || view.image_layers != 1)))) {
 		EXIT("unsupported 64KB texture-tiled render-target view: dimension=%u depth=%u"
 		     " layer=%u/%u\n",
 		     rt.attrib3.dimension, rt.attrib3.depth, view.base_layer, view.image_layers);

src/graphics/host_gpu/renderer/pipeline/pipelineCache.cpp

@@ -1,6 +1,7 @@
 #include "graphics/host_gpu/renderer/pipeline/pipelineCache.h"
 
 #include "common/assert.h"
+#include "common/file.h"
 #include "common/logging/log.h"
 #include "common/profiler.h"
 #include "graphics/guest_gpu/hardwareContext.h"
@@ -11,18 +12,64 @@
 #include "graphics/host_gpu/renderer/render.h"
 #include "graphics/host_gpu/renderer/renderContext.h"
 #include "graphics/shader/shaderCompiler.h"
+#include "kytyGitVersion.h"
+#include "loader/systemContent.h"
 
+#include <algorithm>
 #include <atomic>
+#include <cctype>
 #include <cstdio>
 #include <cstring>
+#include <limits>
 #include <span>
+#include <string_view>
 #include <utility>
 #include <vector>
 
+#include <fmt/format.h>
+#include <xxhash.h>
+
 namespace Libs::Graphics {
 
 namespace {
 
+std::string DriverCacheSignature(const vk::PhysicalDeviceProperties& properties) {
+	constexpr char hex[] = "0123456789abcdef";
+	std::string    uuid(VK_UUID_SIZE * 2, '0');
+	for (size_t i = 0; i < VK_UUID_SIZE; i++) {
+		uuid[i * 2]     = hex[properties.pipelineCacheUUID[i] >> 4u];
+		uuid[i * 2 + 1] = hex[properties.pipelineCacheUUID[i] & 0xfu];
+	}
+	return fmt::format("KytyPC1:{}:{:08x}:{:08x}:{:08x}:{}\n", KYTY_GIT_REVISION,
+	                   properties.vendorID, properties.deviceID, properties.driverVersion, uuid);
+}
+
+std::string PipelineCacheTitleId() {
+	std::string title_id;
+	if ((!Loader::SystemContentParamSfoGetString("TITLE_ID", &title_id) || title_id.empty()) &&
+	    (!Loader::SystemContentParamSfoGetString("CONTENT_ID", &title_id) || title_id.empty())) {
+		return {};
+	}
+	if (!std::ranges::all_of(title_id, [](unsigned char c) {
+		    return std::isalnum(c) != 0 || c == '-' || c == '_';
+	    })) {
+		return {};
+	}
+	return title_id;
+}
+
+template <typename... Args>
+void PipelineCacheLog(fmt::format_string<Args...> format, Args&&... args) {
+	auto message = fmt::format(format, std::forward<Args>(args)...);
+	message += '\n';
+	if (Log::GetDirection() != Log::Direction::Console) {
+		std::fwrite(message.data(), 1, message.size(), stdout);
+		std::fflush(stdout);
+	}
+	Log::Write(message);
+	Log::Flush();
+}
+
 void NormalizeStaticParamsForDynamicState(PipelineStaticParameters& static_params) {
 	static_params.viewport_scale[0]  = 0.5f;
 	static_params.viewport_scale[1]  = 0.5f;
@@ -119,9 +166,11 @@ struct PipelineCache::ProgramCache {
 PipelineCache::PipelineCache(GraphicContext& graphics)
     : m_graphics(graphics), m_program_cache(std::make_unique<ProgramCache>(graphics.device)) {
 	EXIT_NOT_IMPLEMENTED(!Common::Thread::IsMainThread());
+	InitializeDriverCache();
 }
 
 PipelineCache::~PipelineCache() {
+	Save();
 	auto destroy = [this](const auto& pipelines) {
 		for (const auto& [key, pipeline]: pipelines) {
 			(void)key;
@@ -138,6 +187,155 @@ PipelineCache::~PipelineCache() {
 			m_graphics.device.destroyShaderModule(permutation.handle.module, nullptr);
 		}
 	}
+	if (m_driver_cache != nullptr) {
+		m_graphics.device.destroyPipelineCache(m_driver_cache, nullptr);
+	}
+}
+
+void PipelineCache::InitializeDriverCache() {
+	const auto title_id = PipelineCacheTitleId();
+	if (title_id.empty()) {
+		return;
+	}
+	if (KYTY_BUILD != KYTY_BUILD_RELEASE) {
+		PipelineCacheLog("Vulkan pipeline cache: disabled (non-Release build)");
+		return;
+	}
+	const std::string_view git_hash     = KYTY_GIT_HASH;
+	const std::string_view git_revision = KYTY_GIT_REVISION;
+	if (git_hash == "unknown" || git_revision == "unknown") {
+		PipelineCacheLog("Vulkan pipeline cache: disabled (unknown git revision)");
+		return;
+	}
+	if (git_hash.ends_with("-dirty")) {
+		PipelineCacheLog("Vulkan pipeline cache: disabled (dirty build)");
+		return;
+	}
+
+	m_driver_cache_path = std::filesystem::path("_PipelineCache") / (title_id + ".bin");
+	const auto path         = Common::PathToString(m_driver_cache_path);
+	const bool cache_exists = Common::File::IsFileExisting(m_driver_cache_path);
+	if (cache_exists) {
+		PipelineCacheLog("Vulkan pipeline cache: loading {}", path);
+	} else {
+		PipelineCacheLog("Vulkan pipeline cache: initializing {}", path);
+	}
+	std::vector<uint8_t> initial_data;
+	if (cache_exists) {
+		Common::File file(m_driver_cache_path, Common::File::Mode::Read);
+		const auto   file_size = file.IsInvalid() ? 0 : file.Size();
+		const auto signature = DriverCacheSignature(m_graphics.GetPhysicalDeviceProperties());
+		if (file_size >= signature.size() + sizeof(uint64_t) &&
+		    file_size <= std::numeric_limits<uint32_t>::max()) {
+			std::string cached_signature(signature.size(), '\0');
+			uint64_t    payload_hash = 0;
+			initial_data.resize(file_size - signature.size() - sizeof(payload_hash));
+			uint32_t signature_read = 0;
+			uint32_t hash_read      = 0;
+			uint32_t payload_read   = 0;
+			file.Read(cached_signature.data(), static_cast<uint32_t>(cached_signature.size()),
+			          &signature_read);
+			file.Read(&payload_hash, sizeof(payload_hash), &hash_read);
+			file.Read(initial_data.data(), static_cast<uint32_t>(initial_data.size()), &payload_read);
+			file.Close();
+			if (signature_read != cached_signature.size() || hash_read != sizeof(payload_hash) ||
+			    payload_read != initial_data.size() || cached_signature != signature ||
+			    XXH3_64bits(initial_data.data(), initial_data.size()) != payload_hash) {
+				initial_data.clear();
+				PipelineCacheLog(
+				    "Vulkan pipeline cache: invalidating {} (driver, emulator, or data mismatch)",
+				    path);
+			}
+		} else {
+			file.Close();
+			PipelineCacheLog("Vulkan pipeline cache: invalidating {} (invalid file size)",
+			                 path);
+		}
+	}
+
+	vk::PipelineCacheCreateInfo create {};
+	create.sType           = vk::StructureType::ePipelineCacheCreateInfo;
+	create.initialDataSize = initial_data.size();
+	create.pInitialData    = initial_data.empty() ? nullptr : initial_data.data();
+	auto result = m_graphics.device.createPipelineCache(&create, nullptr, &m_driver_cache);
+	if (result != vk::Result::eSuccess && !initial_data.empty()) {
+		PipelineCacheLog("Vulkan pipeline cache: driver rejected {} ({}); starting empty", path,
+		                 VulkanToString(result));
+		initial_data.clear();
+		create.initialDataSize = 0;
+		create.pInitialData    = nullptr;
+		result = m_graphics.device.createPipelineCache(&create, nullptr, &m_driver_cache);
+	}
+	if (result != vk::Result::eSuccess) {
+		PipelineCacheLog("Vulkan pipeline cache: disabled ({})", VulkanToString(result));
+		m_driver_cache = nullptr;
+		return;
+	}
+	if (!initial_data.empty()) {
+		PipelineCacheLog("Vulkan pipeline cache: loaded {} bytes from {}", initial_data.size(),
+		                 path);
+	} else {
+		PipelineCacheLog("Vulkan pipeline cache: initialized empty");
+	}
+}
+
+void PipelineCache::Save() {
+	Common::LockGuard lock(m_mutex);
+	if (m_driver_cache == nullptr) {
+		return;
+	}
+
+	size_t               size = 0;
+	vk::Result           result;
+	std::vector<uint8_t> payload;
+	for (uint32_t attempt = 0; attempt < 3; attempt++) {
+		size   = 0;
+		result = m_graphics.device.getPipelineCacheData(m_driver_cache, &size, nullptr);
+		if (result != vk::Result::eSuccess || size == 0 ||
+		    size > std::numeric_limits<uint32_t>::max()) {
+			break;
+		}
+		payload.resize(size);
+		result = m_graphics.device.getPipelineCacheData(m_driver_cache, &size, payload.data());
+		if (result != vk::Result::eIncomplete) {
+			break;
+		}
+	}
+	if (result != vk::Result::eSuccess || size == 0 ||
+	    size > std::numeric_limits<uint32_t>::max()) {
+		PipelineCacheLog("Vulkan pipeline cache: save failed ({}, {} bytes)",
+		                 VulkanToString(result), size);
+		return;
+	}
+	payload.resize(size);
+	auto prefix = DriverCacheSignature(m_graphics.GetPhysicalDeviceProperties());
+	const auto payload_hash = XXH3_64bits(payload.data(), payload.size());
+	prefix.append(reinterpret_cast<const char*>(&payload_hash), sizeof(payload_hash));
+	if (!Common::File::CreateDirectories(m_driver_cache_path.parent_path())) {
+		PipelineCacheLog("Vulkan pipeline cache: failed to create cache directory");
+		return;
+	}
+	auto temp_path = m_driver_cache_path;
+	temp_path += ".tmp";
+	Common::File file;
+	uint32_t     prefix_written  = 0;
+	uint32_t     payload_written = 0;
+	if (file.Create(temp_path)) {
+		file.Write(prefix.data(), static_cast<uint32_t>(prefix.size()), &prefix_written);
+		file.Write(payload.data(), static_cast<uint32_t>(payload.size()), &payload_written);
+	}
+	const bool flushed = !file.IsInvalid() && file.Flush();
+	file.Close();
+	if (prefix_written != prefix.size() || payload_written != payload.size() || !flushed ||
+	    !Common::File::RenameFile(temp_path, m_driver_cache_path)) {
+		PipelineCacheLog("Vulkan pipeline cache: failed to write {}",
+		                 Common::PathToString(m_driver_cache_path));
+		return;
+	}
+	PipelineCacheLog("Vulkan pipeline cache: saved {} bytes to {}", payload.size(),
+	                 Common::PathToString(m_driver_cache_path));
+	m_graphics.device.destroyPipelineCache(m_driver_cache, nullptr);
+	m_driver_cache = nullptr;
 }
 
 ShaderProgram PipelineCache::GetVertexProgram(const HW::VertexShaderInfo& regs,
@@ -324,7 +522,7 @@ PipelineCache::GraphicsPipeline& PipelineCache::CreateGraphicsPipeline(
 	auto cached = std::make_unique<GraphicsPipeline>(p);
 	LogPipelineTrace("CreatePipelineInternal begin", vs_id, ps_id);
 	CreatePipelineInternal(m_graphics, *cached, rendering, vs_input_info, vertex_program.module,
-	                       ps_input_info, pixel_program.module, static_params);
+	                       ps_input_info, pixel_program.module, static_params, m_driver_cache);
 	LogPipelineTrace("CreatePipelineInternal done", vs_id, ps_id);
 
 	EXIT_NOT_IMPLEMENTED(cached->pipeline == nullptr);
@@ -360,7 +558,7 @@ PipelineCache::CreateComputePipeline(ShaderComputeInputInfo& input_info,
 	}
 
 	auto cached = std::make_unique<ComputePipeline>(p);
-	CreatePipelineInternal(m_graphics, *cached, input_info, compute_program.module);
+	CreatePipelineInternal(m_graphics, *cached, input_info, compute_program.module, m_driver_cache);
 
 	EXIT_NOT_IMPLEMENTED(cached->pipeline == nullptr);
 	EXIT_NOT_IMPLEMENTED(cached->pipeline_layout == nullptr);

src/graphics/host_gpu/renderer/pipeline/pipelineCache.h

@@ -10,6 +10,7 @@
 #include "graphics/shader/shader.h"
 
 #include <cstddef>
+#include <filesystem>
 #include <memory>
 #include <span>
 #include <type_traits>
@@ -109,6 +110,7 @@ public:
 	explicit PipelineCache(GraphicContext& graphics);
 	~PipelineCache();
 	KYTY_CLASS_NO_COPY(PipelineCache);
+	void Save();
 
 	struct Pipeline {
 		vk::PipelineLayout      pipeline_layout       = nullptr;
@@ -214,12 +216,16 @@ private:
 
 	GraphicContext&                m_graphics;
 	std::unique_ptr<ProgramCache> m_program_cache;
+	vk::PipelineCache             m_driver_cache = nullptr;
+	std::filesystem::path         m_driver_cache_path;
 	std::unordered_map<GraphicsPipelineKey, std::unique_ptr<GraphicsPipeline>,
 	                   GraphicsPipelineKeyHash>
 	    m_graphics_pipelines;
 	std::unordered_map<ComputePipelineKey, std::unique_ptr<ComputePipeline>, ComputePipelineKeyHash>
 	              m_compute_pipelines;
 	Common::Mutex m_mutex;
+
+	void InitializeDriverCache();
 };
 
 void LogPipelineTrace(const char* phase, uint64_t vertex_program_id, uint64_t pixel_program_id);
@@ -227,10 +233,11 @@ void CreatePipelineInternal(
     GraphicContext& graphics, PipelineCache::GraphicsPipeline& pipeline,
     const PipelineRenderingState& rendering, const ShaderVertexInputInfo& vs_input_info,
     vk::ShaderModule vertex_module, const ShaderPixelInputInfo* ps_input_info,
-	vk::ShaderModule pixel_module, const PipelineStaticParameters& static_params);
+	vk::ShaderModule pixel_module, const PipelineStaticParameters& static_params,
+	vk::PipelineCache driver_cache);
 void CreatePipelineInternal(GraphicContext& graphics, PipelineCache::ComputePipeline& pipeline,
                             const ShaderComputeInputInfo& input_info,
-                            vk::ShaderModule              compute_module);
+	vk::ShaderModule compute_module, vk::PipelineCache driver_cache);
 
 } // namespace Libs::Graphics
 

src/graphics/host_gpu/renderer/pipeline/shaders.cpp

@@ -423,7 +423,8 @@ void CreatePipelineInternal(
     GraphicContext& graphics, PipelineCache::GraphicsPipeline& pipeline,
     const PipelineRenderingState& rendering, const ShaderVertexInputInfo& vs_input_info,
     vk::ShaderModule vertex_module, const ShaderPixelInputInfo* ps_input_info,
-	vk::ShaderModule pixel_module, const PipelineStaticParameters& static_params) {
+	vk::ShaderModule pixel_module, const PipelineStaticParameters& static_params,
+	vk::PipelineCache driver_cache) {
 	const bool ps_active = ps_input_info != nullptr;
 	EXIT_IF(vertex_module == nullptr || (ps_active && pixel_module == nullptr));
 
@@ -940,7 +941,7 @@ void CreatePipelineInternal(
 		     viewport.y, viewport.width, viewport.height, scissor.offset.x, scissor.offset.y,
 		     scissor.extent.width, scissor.extent.height);
 	}
-	result = graphics.device.createGraphicsPipelines(nullptr, 1, &pipeline_info, nullptr,
+	result = graphics.device.createGraphicsPipelines(driver_cache, 1, &pipeline_info, nullptr,
 	                                                 &pipeline.pipeline);
 	if (graphics_debug_dump_enabled()) {
 		LOGF("PipelineTrace: vkCreateGraphicsPipelines done result=%s pipeline=%p\n",
@@ -961,7 +962,7 @@ void CreatePipelineInternal(
 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
 void CreatePipelineInternal(GraphicContext& graphics, PipelineCache::ComputePipeline& pipeline,
                             const ShaderComputeInputInfo& input_info,
-                            vk::ShaderModule              compute_module) {
+	vk::ShaderModule compute_module, vk::PipelineCache driver_cache) {
 	EXIT_IF(compute_module == nullptr);
 
 	vk::PipelineShaderStageCreateInfo                     comp_shader_stage_info {};
@@ -1024,7 +1025,8 @@ void CreatePipelineInternal(GraphicContext& graphics, PipelineCache::ComputePipe
 
 	LOGF("PipelineTrace: vkCreateComputePipelines begin layout=%p\n",
 	     static_cast<void*>(pipeline.pipeline_layout));
-	result = graphics.device.createComputePipelines(nullptr, 1, &info, nullptr, &pipeline.pipeline);
+	result = graphics.device.createComputePipelines(driver_cache, 1, &info, nullptr,
+	                                                &pipeline.pipeline);
 	LOGF("PipelineTrace: vkCreateComputePipelines done result=%s pipeline=%p\n",
 	     VulkanToString(result).c_str(), static_cast<void*>(pipeline.pipeline));
 	EXIT_NOT_IMPLEMENTED(result != vk::Result::eSuccess);

src/graphics/presentation/window/window.cpp

@@ -28,6 +28,7 @@
 #include "common/timer.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 "graphics/presentation/imeOverlay.h"
@@ -858,6 +859,7 @@ void WindowRun() {
 	EXIT_IF(g_window == nullptr);
 
 	g_window->Run();
+	g_window->render_context->GetPipelineCache().Save();
 }
 
 void WindowShutdown() {

src/graphics/shader/recompiler/backend/spirv/spirvEmitterImage.cpp

@@ -439,6 +439,49 @@ uint32_t UnpackImageGather(ValueEmitContext& ctx, const IR::MemoryInfo& mem, uin
 	return result;
 }
 
+uint32_t EmitOneDimensionalGatherLz(ValueEmitContext& ctx, const IR::MemoryInfo& mem, uint32_t pc,
+	                                 uint32_t coord, bool integer) {
+	auto& state = ctx.state;
+	state.builder.RequireCapability(CapabilityImageQuery);
+	const auto image = LoadSampledImageDescriptor(state, mem, pc, ImageViewKind::Dim1D);
+	const auto width = state.builder.AllocateId();
+	state.builder.AddFunction(
+	    {OpImageQuerySizeLod, TypeU32(state), width, image, ConstantU32(state, 0)});
+	const auto width_f32 = state.builder.AllocateId();
+	state.builder.AddFunction({OpConvertUToF, TypeF32(state), width_f32, width});
+	const auto left = state.builder.AllocateId();
+	state.builder.AddFunction(
+	    {OpExtInst, TypeF32(state), left, GlslStd450(state), GlslFloor,
+	     Binary(state, OpFSub, TypeF32(state),
+	            Binary(state, OpFMul, TypeF32(state), coord, width_f32),
+	            ConstantF32(state, 0x3f000000u))});
+
+	const auto sampled = MakeSampledImage(state, mem, pc, ImageViewKind::Dim1D);
+	const auto vector_type = integer ? TypeU32Vector(state, 4) : TypeF32Vector(state, 4);
+	const auto scalar_type = integer ? TypeU32(state) : TypeF32(state);
+	const auto component = ImageConversionFormat(state, mem).format == Prospero::BufferFormat::kInvalid
+	                           ? ImageGatherComponent(mem.dmask)
+	                           : 0u;
+	uint32_t values[2] {};
+	for (uint32_t index = 0; index < 2u; index++) {
+		const auto sample_coord = Binary(
+		    state, OpFDiv, TypeF32(state),
+		    Binary(state, OpFAdd, TypeF32(state), left,
+		           ConstantF32(state, index == 0u ? 0x3f000000u : 0x3fc00000u)),
+		    width_f32);
+		const auto texel = state.builder.AllocateId();
+		state.builder.AddFunction({OpImageSampleExplicitLod, vector_type, texel, sampled, sample_coord,
+		                           ImageOperandsLodMask, ZeroF32(state)});
+		values[index] = state.builder.AllocateId();
+		state.builder.AddFunction(
+		    {OpCompositeExtract, scalar_type, values[index], texel, component});
+	}
+	const auto result = state.builder.AllocateId();
+	state.builder.AddFunction({OpCompositeConstruct, vector_type, result, values[0], values[1],
+	                           values[1], values[0]});
+	return result;
+}
+
 uint32_t PackImageTexel(ValueEmitContext& ctx, const IR::MemoryInfo& mem, uint32_t texel) {
 	const auto info = ImageConversionFormat(ctx.state, mem);
 	if (info.format == Prospero::BufferFormat::kInvalid) return texel;
@@ -613,6 +656,22 @@ bool EmitValueImage(ValueEmitContext& ctx, const IR::Inst& inst) {
 		const auto coord =
 		    CoordF32(ctx, mem, *address, layout.coord, ImageViewCoordinateComponents(view));
 		if (op == IR::ValueOpcode::ImageGatherRaw) {
+			if (view == ImageViewKind::Dim1D) {
+				if (dref || !HasFlag(mem, Decoder::ImageSampleFlagLevelZero) ||
+				    HasFlag(mem, Decoder::ImageSampleFlagOffset) ||
+				    HasFlag(mem, Decoder::ImageSampleFlagGatherHorizontal)) {
+					ctx.Fail(inst, "has an unsupported 1D gather variant");
+					return true;
+				}
+				const auto sample = EmitOneDimensionalGatherLz(ctx, mem, pc, coord, integer);
+				ctx.Define(inst, ResultVector(ctx, UnpackImageGather(ctx, mem, sample), integer,
+				                              false, mem, true));
+				return true;
+			}
+			if (view == ImageViewKind::Dim1DArray) {
+				ctx.Fail(inst, "has an unsupported 1D-array gather");
+				return true;
+			}
 			const auto            sampled = MakeSampledImage(state, mem, pc, view);
 			const auto            sample  = state.builder.AllocateId();
 			std::vector<uint32_t> words =

src/graphics/shader/recompiler/frontend/decode/MemoryOps.cpp

@@ -103,7 +103,9 @@ constexpr MemoryOpcodeInfo DS_OPCODE_LIST[] = {
     {0x4du, Opcode::DS_WRITE_B64, 2, 32},        {0x4eu, Opcode::DS_WRITE2_B64, 4, 32},
     {0x4fu, Opcode::DS_WRITE2ST64_B64, 4, 32},   {0x76u, Opcode::DS_READ_B64, 2, 32},
     {0x77u, Opcode::DS_READ2_B64, 4, 32},        {0x78u, Opcode::DS_READ2ST64_B64, 4, 32},
+    {0xa1u, Opcode::DS_WRITE_B16_D16_HI, 1, 16},
     {0xa6u, Opcode::DS_READ_U16_D16, 1, 16},
+    {0xa7u, Opcode::DS_READ_U16_D16_HI, 1, 16},
     {0xb0u, Opcode::DS_WRITE_ADDTID_B32, 1, 32}, {0xb1u, Opcode::DS_READ_ADDTID_B32, 1, 32},
     {0xdeu, Opcode::DS_WRITE_B96, 3, 32},        {0xdfu, Opcode::DS_WRITE_B128, 4, 32},
     {0xfeu, Opcode::DS_READ_B96, 3, 32},         {0xffu, Opcode::DS_READ_B128, 4, 32},
@@ -147,6 +149,7 @@ bool IsDsWriteOpcode(Opcode opcode) {
 	switch (opcode) {
 		case Opcode::DS_WRITE_B8:
 		case Opcode::DS_WRITE_B16:
+		case Opcode::DS_WRITE_B16_D16_HI:
 		case Opcode::DS_WRITE2_B32:
 		case Opcode::DS_WRITE2ST64_B32:
 		case Opcode::DS_WRITE2_B64:
@@ -421,13 +424,17 @@ void DecodeDs(uint32_t pc, std::span<const uint32_t> code, uint32_t word_index,
 	}
 
 	DecodeVectorGpr(vdst, inst.dst);
-	if (inst.opcode == Opcode::DS_READ_U16_D16) {
+	if (inst.opcode == Opcode::DS_READ_U16_D16 ||
+	    inst.opcode == Opcode::DS_READ_U16_D16_HI) {
 		// Native D16 reads update only the selected destination half. Reuse the partial
-		// destination representation so typed IR translation preserves the upper word.
-		inst.dst.sdwa_sel = 4u;
+		// destination representation so typed IR translation preserves the other half.
+		inst.dst.sdwa_sel = inst.opcode == Opcode::DS_READ_U16_D16 ? 4u : 5u;
 	}
 	DecodeVectorGpr(addr, inst.src0);
 	DecodeVectorGpr(data0, inst.src1);
+	if (inst.opcode == Opcode::DS_WRITE_B16_D16_HI) {
+		inst.src1.sdwa_sel = 5u;
+	}
 	DecodeVectorGpr(data1, inst.src2);
 	inst.src_count = DsSourceCount(inst.opcode);
 }

src/graphics/shader/recompiler/frontend/decode/ShaderDecoder.cpp

@@ -675,6 +675,7 @@ std::string InstructionToString(const Instruction& inst) {
 		case Opcode::DS_READ_B128:
 		case Opcode::DS_WRITE_B8:
 		case Opcode::DS_WRITE_B16:
+		case Opcode::DS_WRITE_B16_D16_HI:
 		case Opcode::DS_WRITE2_B32:
 		case Opcode::DS_WRITE2ST64_B32:
 		case Opcode::DS_WRITE2_B64:

src/graphics/shader/recompiler/frontend/decode/ShaderDecoder.h

@@ -185,6 +185,7 @@ enum class Opcode {
 	V_BFREV_B32,
 	V_FFBH_U32,
 	V_FFBL_B32,
+	V_FFBH_I32,
 	V_ADD_F32,
 	V_SUB_F32,
 	V_SUBREV_F32,
@@ -391,6 +392,7 @@ enum class Opcode {
 	V_CMP_GE_U32,
 	V_CMP_T_U32,
 	V_CMP_EQ_I64,
+	V_CMP_EQ_U64,
 	V_CMP_GT_U64,
 	V_CMP_NE_U64,
 	V_CMPX_NE_I64,
@@ -497,6 +499,7 @@ enum class Opcode {
 	DS_READ_I16,
 	DS_READ_U16,
 	DS_READ_U16_D16,
+	DS_READ_U16_D16_HI,
 	DS_READ2_B32,
 	DS_READ2ST64_B32,
 	DS_READ_B32,
@@ -507,6 +510,7 @@ enum class Opcode {
 	DS_READ_B128,
 	DS_WRITE_B8,
 	DS_WRITE_B16,
+	DS_WRITE_B16_D16_HI,
 	DS_WRITE2_B32,
 	DS_WRITE2ST64_B32,
 	DS_WRITE2_B64,

src/graphics/shader/recompiler/frontend/decode/VectorAluOps.cpp

@@ -59,7 +59,7 @@ constexpr Vop2OpcodeInfo VOP2_OPCODE_LIST[] = {
     {0x23u, Opcode::V_MBCNT_LO_U32_B32},
     {0x24u, Opcode::V_MBCNT_HI_U32_B32},
     {0x25u, Opcode::V_ADD_NC_U32, Vop2SdwaProfile::IntegerPartialDestination},
-    {0x28u, Opcode::V_ADDC_U32},
+    {0x28u, Opcode::V_ADDC_U32, Vop2SdwaProfile::IntegerFullDestination},
     {0x2au, Opcode::V_SUBREV_CO_CI_U32},
     {0x26u, Opcode::V_SUB_NC_U32, Vop2SdwaProfile::IntegerPartialDestination},
     {0x27u, Opcode::V_SUBREV_NC_U32, Vop2SdwaProfile::IntegerFullDestination},
@@ -119,6 +119,7 @@ constexpr OpcodeMap VOP1_OPCODE_LIST[] = {
     {0x38u, Opcode::V_BFREV_B32},
     {0x39u, Opcode::V_FFBH_U32},
     {0x3au, Opcode::V_FFBL_B32},
+    {0x3bu, Opcode::V_FFBH_I32},
     {0x3fu, Opcode::V_FREXP_EXP_I32_F32},
     {0x40u, Opcode::V_FREXP_MANT_F32},
     {0x42u, Opcode::V_MOVRELD_B32},
@@ -169,6 +170,7 @@ constexpr OpcodeMap VOP3_ENCODED_VOP1_OPCODE_LIST[] = {
     {0x38u, Opcode::V_BFREV_B32},
     {0x39u, Opcode::V_FFBH_U32},
     {0x3au, Opcode::V_FFBL_B32},
+    {0x3bu, Opcode::V_FFBH_I32},
     {0x3fu, Opcode::V_FREXP_EXP_I32_F32},
     {0x40u, Opcode::V_FREXP_MANT_F32},
     {0x42u, Opcode::V_MOVRELD_B32},
@@ -234,7 +236,8 @@ constexpr VopcOpcodeInfo VOPC_OPCODE_LIST[] = {
     {0xd1u, Opcode::V_CMPX_LT_U32},       {0xd2u, Opcode::V_CMPX_EQ_U32},
     {0xd3u, Opcode::V_CMPX_LE_U32},       {0xd4u, Opcode::V_CMPX_GT_U32},
     {0xd5u, Opcode::V_CMPX_NE_U32},       {0xd6u, Opcode::V_CMPX_GE_U32},
-    {0xe4u, Opcode::V_CMP_GT_U64, false}, {0xe5u, Opcode::V_CMP_NE_U64, false},
+    {0xe2u, Opcode::V_CMP_EQ_U64, false}, {0xe4u, Opcode::V_CMP_GT_U64, false},
+    {0xe5u, Opcode::V_CMP_NE_U64, false},
     {0xf5u, Opcode::V_CMPX_NE_U64, false},
     {0xc9u, Opcode::V_CMP_LT_F16},        {0xcau, Opcode::V_CMP_EQ_F16},
     {0xcbu, Opcode::V_CMP_LE_F16},        {0xccu, Opcode::V_CMP_GT_F16},
@@ -515,6 +518,8 @@ constexpr Vop1SdwaRule VOP1_SDWA_RULES[] = {
     {Opcode::V_CVT_F32_U32, SdwaSelBytes() | SdwaSelWords() | SdwaSelFull(), 0, 0, false},
     {Opcode::V_CVT_F32_I32, SdwaSelBytes() | SdwaSelWords() | SdwaSelFull(), 0, 0, false},
     {Opcode::V_CVT_F32_UBYTE0, SdwaSelBytes() | SdwaSelWords() | SdwaSelFull(), 0, 0, false},
+    {Opcode::V_NOT_B32, SdwaSelBytes() | SdwaSelWords() | SdwaSelFull(), 0, 0, false},
+    {Opcode::V_FFBL_B32, SdwaSelBytes() | SdwaSelWords() | SdwaSelFull(), 0, 0, false},
     {Opcode::V_CVT_F32_F16, SdwaSelWords() | SdwaSelFull(), 0, 0, true},
     {Opcode::V_CVT_F16_F32, SdwaSelFull(), SdwaSelWords(), SdwaSelFull(), false},
     {Opcode::V_CVT_F16_U16, SdwaSelWords() | SdwaSelFull(), SdwaSelWords(),
@@ -940,8 +945,8 @@ constexpr Vop2SdwaRule VOP2_SDWA_RULES[] = {
      true, true},
     {SdwaSelFull(), SdwaSelAll(), SdwaSelAll(), false, false},
     {SdwaSelAll(), SdwaSelAll(), SdwaSelAll(), true, false},
-    {SdwaSelFull(), SdwaSelFull(), SdwaSelWords() | SdwaSelFull(), false, false},
-    {SdwaSelFull(), SdwaSelFull(), SdwaSelAll(), false, false},
+    {SdwaSelFull(), SdwaSelAll(), SdwaSelWords() | SdwaSelFull(), false, false},
+    {SdwaSelFull(), SdwaSelAll(), SdwaSelAll(), false, false},
     {SdwaSelWords() | SdwaSelFull(), SdwaSelAll(), SdwaSelAll(), true, false},
 };
 static_assert(sizeof(VOP2_SDWA_RULES) / sizeof(VOP2_SDWA_RULES[0]) ==

src/graphics/shader/recompiler/frontend/translate/Integer.cpp

@@ -224,11 +224,14 @@ bool Translator::S_FF1_I32_B64(const Decoder::Instruction& inst) {
 	return true;
 }
 
-bool Translator::V_FFBH_U32(const Decoder::Instruction& inst) {
-	const auto source   = ReadU32(inst.src0);
-	const auto msb      = IR::U32(ir.Emit(IR::ValueOpcode::FindUMsb32, {source}));
+bool Translator::V_FFBH_32(const Decoder::Instruction& inst, bool sign) {
+	const auto source = ReadU32(inst.src0);
+	const auto value  = sign ? ir.BitwiseXor(
+	                              source, ir.ShiftRightArithmetic(source, IR::U32(IR::Value(31u))))
+	                         : source;
+	const auto msb      = IR::U32(ir.Emit(IR::ValueOpcode::FindUMsb32, {value}));
 	const auto position = ir.ISub(IR::U32(IR::Value(31u)), msb);
-	const auto result   = ir.Select(ir.INotEqual(source, IR::U32(IR::Value(0u))), position,
+	const auto result   = ir.Select(ir.INotEqual(value, IR::U32(IR::Value(0u))), position,
 	                                IR::U32(IR::Value(0xffffffffu)));
 	WriteOperand(DestinationOperand(inst), result);
 	return true;

src/graphics/shader/recompiler/frontend/translate/Memory.cpp

@@ -257,6 +257,7 @@ Decoder::Operand MemorySourceAt(const Decoder::Instruction& decoded, uint32_t in
 				return index == 0u ? decoded.src1 : index == 1u ? decoded.src0 : decoded.src2;
 			case Decoder::Opcode::DS_WRITE_B8:
 			case Decoder::Opcode::DS_WRITE_B16:
+			case Decoder::Opcode::DS_WRITE_B16_D16_HI:
 			case Decoder::Opcode::DS_WRITE_B32:
 			case Decoder::Opcode::DS_WRITE_B64:
 			case Decoder::Opcode::DS_WRITE_B96:
@@ -1050,6 +1051,7 @@ bool Translator::EmitMemory(const Decoder::Instruction& inst, std::string* error
 		case Decoder::Opcode::DS_READ_I16:
 		case Decoder::Opcode::DS_READ_U16:
 		case Decoder::Opcode::DS_READ_U16_D16:
+		case Decoder::Opcode::DS_READ_U16_D16_HI:
 		case Decoder::Opcode::DS_READ_B32:
 		case Decoder::Opcode::DS_READ_B64:
 		case Decoder::Opcode::DS_READ_B96:
@@ -1060,6 +1062,7 @@ bool Translator::EmitMemory(const Decoder::Instruction& inst, std::string* error
 		case Decoder::Opcode::DS_WRITE2ST64_B64: return DS_WRITE2(inst);
 		case Decoder::Opcode::DS_WRITE_B8:
 		case Decoder::Opcode::DS_WRITE_B16:
+		case Decoder::Opcode::DS_WRITE_B16_D16_HI:
 		case Decoder::Opcode::DS_WRITE_B32:
 		case Decoder::Opcode::DS_WRITE_B64:
 		case Decoder::Opcode::DS_WRITE_B96:

src/graphics/shader/recompiler/frontend/translate/Translator.h

@@ -182,7 +182,7 @@ private:
 	bool    V_OR3_B32(const Decoder::Instruction& inst);
 	bool    V_XOR3_B32(const Decoder::Instruction& inst);
 	bool    S_FF1_I32_B64(const Decoder::Instruction& inst);
-	bool    V_FFBH_U32(const Decoder::Instruction& inst);
+	bool    V_FFBH_32(const Decoder::Instruction& inst, bool sign);
 	bool    S_FLBIT_I32_B64(const Decoder::Instruction& inst);
 	bool    Integer24(const Decoder::Instruction& inst, bool sign, bool addend);
 	bool    V_MAD_U64_U32(const Decoder::Instruction& inst);

src/graphics/shader/recompiler/frontend/translate/Vector.cpp

@@ -96,6 +96,7 @@ bool Translator::EmitVector(const Decoder::Instruction& inst, std::string* error
 			EmitIntegerCompare(inst, IR::ValueOpcode::SLessThanEqual32, IR::Type::U32, false, true);
 			return true;
 		case O::V_CMP_EQ_I64:
+		case O::V_CMP_EQ_U64:
 			EmitIntegerCompare(inst, IR::ValueOpcode::IEqual64, IR::Type::U64, false, false);
 			return true;
 		case O::V_CMP_GT_U64:
@@ -490,7 +491,8 @@ bool Translator::EmitVector(const Decoder::Instruction& inst, std::string* error
 		case O::V_AND_OR_B32: return V_AND_OR_B32(inst);
 		case O::V_OR3_B32: return V_OR3_B32(inst);
 		case O::V_XOR3_B32: return V_XOR3_B32(inst);
-		case O::V_FFBH_U32: return V_FFBH_U32(inst);
+		case O::V_FFBH_U32: return V_FFBH_32(inst, false);
+		case O::V_FFBH_I32: return V_FFBH_32(inst, true);
 
 		case O::V_MAD_I32_I24: return Integer24(inst, true, true);
 		case O::V_MAD_U32_U24: return Integer24(inst, false, true);

src/kernel/fileSystem.cpp

@@ -1066,7 +1066,7 @@ int KYTY_SYSV_ABI KernelRename(const char* from, const char* to) {
 		Common::File::DeleteFile(real_to);
 	}
 
-	if (!Common::File::MoveFile(real_from, real_to)) {
+	if (!Common::File::RenameFile(real_from, real_to)) {
 		return KERNEL_ERROR_EIO;
 	}
 

src/kernel/memoryAddressSpace.inc

@@ -44,9 +44,9 @@ public:
 
 	explicit GuestBackingStore(uint64_t size): m_size(size) {
 #if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
-		m_handle = CreateFileMappingA(INVALID_HANDLE_VALUE, nullptr, PAGE_EXECUTE_READWRITE,
-		                              static_cast<DWORD>(m_size >> 32u),
-		                              static_cast<DWORD>(m_size & 0xffffffffu), nullptr);
+		m_handle = CreateFileMappingA(
+		    INVALID_HANDLE_VALUE, nullptr, PAGE_EXECUTE_READWRITE | SEC_COMMIT,
+		    static_cast<DWORD>(m_size >> 32u), static_cast<DWORD>(m_size & 0xffffffffu), nullptr);
 		if (m_handle == nullptr) {
 			LOGF_COLOR(Log::Color::Red,
 			           "\t direct-memory backing: CreateFileMapping failed: 0x%08" PRIx32 "\n",
@@ -659,7 +659,16 @@ public:
 #endif
 		ReserveGuestRegions();
 		m_backing = new GuestBackingStore(backing_size);
-		EXIT_IF(!m_backing->IsAvailable());
+		if (!m_backing->IsAvailable()) {
+#if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
+			EXIT("could not reserve %" PRIu64 " MB for guest direct memory. Windows commits\n"
+			     "this up front, so the paging file is usually what needs to be larger.\n",
+			     backing_size / (1024U * 1024U));
+#else
+			EXIT("could not reserve %" PRIu64 " MB for guest direct memory\n",
+			     backing_size / (1024U * 1024U));
+#endif
+		}
 	}
 
 	~GuestAddressSpace() {

src/kytyGitVersion.h.in

@@ -1,7 +1,10 @@
 #include "cmake_config.h"
 
 #define KYTY_GIT_VERSION "@KYTY_GIT_VERSION@"
+// Short, human-facing commit name used in build labels.
 #define KYTY_GIT_HASH "@KYTY_GIT_HASH@"
+// Full commit identity used for compatibility checks.
+#define KYTY_GIT_REVISION "@KYTY_GIT_REVISION@"
 
 /* Build provenance, shown in the window title and in crash reports. */
 #if defined(KYTY_OFFICIAL_BUILD)

src/libs/controller.cpp

@@ -1,5 +1,6 @@
 #include "libs/controller.h"
 
+#include "SDL.h"
 #include "common/assert.h"
 #include "common/common.h"
 #include "common/emulatorConfig.h"
@@ -22,6 +23,9 @@ LIB_NAME("Pad", "Pad");
 constexpr int PAD_ERROR_INVALID_ARG    = -2137915391; /* 0x80920001 */
 constexpr int PAD_ERROR_INVALID_HANDLE = -2137915389; /* 0x80920003 */
 
+// SDL limits rumble commands to 0xffff ms; zero strengths stop immediately.
+constexpr uint32_t RUMBLE_DURATION_MS = 0xffff;
+
 struct PadControllerInformation {
 	float    touch_pixel_density;
 	uint16_t touch_resolution_x;
@@ -59,6 +63,7 @@ public:
 	void Axis(int id, Axis axis, int value);
 	void ResetInputState();
 	void GetConnectionInfo(bool* flag, int* count);
+	void SetVibration(uint8_t large_motor, uint8_t small_motor);
 	void ReadState(ControllerState* state, bool* flag, int* count);
 	int  ReadStates(ControllerState* states, int states_num, bool* flag, int* count);
 
@@ -269,6 +274,25 @@ void GameController::ResetInputState() {
 	AddState(state);
 }
 
+void GameController::SetVibration(uint8_t large_motor, uint8_t small_motor) {
+	Common::LockGuard lock(m_mutex);
+
+	if (m_active_id == HOST_INPUT_CONTROLLER_ID) {
+		return;
+	}
+
+	auto* pad = SDL_GameControllerFromInstanceID(static_cast<SDL_JoystickID>(m_active_id));
+	if (pad == nullptr) {
+		return;
+	}
+
+	const auto large = static_cast<uint16_t>(large_motor * 0x101U);
+	const auto small = static_cast<uint16_t>(small_motor * 0x101U);
+	if (SDL_GameControllerRumble(pad, large, small, RUMBLE_DURATION_MS) != 0) {
+		LOGF("\t rumble failed: %s\n", SDL_GetError());
+	}
+}
+
 void GameController::GetConnectionInfo(bool* flag, int* count) {
 	EXIT_IF(flag == nullptr);
 	EXIT_IF(count == nullptr);
@@ -544,6 +568,9 @@ int KYTY_SYSV_ABI PadSetVibration(int handle, const PadVibrationParam* param) {
 	     "\t small_motor = %d\n",
 	     static_cast<int>(param->large_motor), static_cast<int>(param->small_motor));
 
+	EXIT_IF(g_controller == nullptr);
+	g_controller->SetVibration(param->large_motor, param->small_motor);
+
 	return OK;
 }
 

src/libs/libNet.cpp

@@ -113,6 +113,10 @@ int KYTY_SYSV_ABI NetResolverCreate(const char* name, int memid, int flags) {
 	return NET_CALL(Net::NetResolverCreate(name, memid, flags));
 }
 
+int KYTY_SYSV_ABI NetResolverDestroy(int rid) {
+	return NET_CALL(Net::NetResolverDestroy(rid));
+}
+
 int KYTY_SYSV_ABI NetResolverStartNtoa(int rid, const char* hostname, void* addr, int timeout,
                                        int retry, int flags) {
 	return NET_CALL(Net::NetResolverStartNtoa(rid, hostname, addr, timeout, retry, flags));
@@ -194,6 +198,7 @@ LIB_DEFINE(InitNet_1_Net) {
 	LIB_FUNC("dgJBaeJnGpo", LibNet::NetPoolCreate);
 	LIB_FUNC("K7RlrTkI-mw", LibNet::NetPoolDestroy);
 	LIB_FUNC("C4UgDHHPvdw", LibNet::NetResolverCreate);
+	LIB_FUNC("kJlYH5uMAWI", LibNet::NetResolverDestroy);
 	LIB_FUNC("Nd91WaWmG2w", LibNet::NetResolverStartNtoa);
 	LIB_FUNC("8Kcp5d-q1Uo", LibNet::NetInetPton);
 	LIB_FUNC("9vA2aW+CHuA", LibNet::NetInetNtop);

src/libs/network.cpp

@@ -101,6 +101,7 @@ public:
 	int  PoolCreate(const char* name, int size);
 	bool PoolDestroy(int memid);
 	int  ResolverCreate(const char* name, int memid);
+	bool ResolverDestroy(int rid);
 	bool ResolverValid(int rid);
 
 	Id   SslInit(uint64_t pool_size);
@@ -291,6 +292,17 @@ int Network::ResolverCreate(const char* name, int memid) {
 	return -1;
 }
 
+bool Network::ResolverDestroy(int rid) {
+	Common::LockGuard lock(m_mutex);
+
+	if (rid >= 0 && rid < RESOLVERS_MAX && m_resolvers[rid].used) {
+		m_resolvers[rid] = {};
+		return true;
+	}
+
+	return false;
+}
+
 bool Network::ResolverValid(int rid) {
 	Common::LockGuard lock(m_mutex);
 
@@ -1231,6 +1243,19 @@ int KYTY_SYSV_ABI NetResolverCreate(const char* name, int memid, int flags) {
 	return id;
 }
 
+int KYTY_SYSV_ABI NetResolverDestroy(int rid) {
+	PRINT_NAME();
+
+	LOGF("\t rid = %d\n", rid);
+
+	EXIT_IF(g_net == nullptr);
+	if (!g_net->ResolverDestroy(rid)) {
+		return NET_ERROR_EBADF;
+	}
+
+	return OK;
+}
+
 int KYTY_SYSV_ABI NetResolverStartNtoa(int rid, const char* hostname, void* addr, int timeout,
                                        int retry, int flags) {
 	PRINT_NAME();

src/libs/network.h

@@ -40,6 +40,7 @@ int KYTY_SYSV_ABI NetTerm();
 int KYTY_SYSV_ABI NetPoolCreate(const char* name, int size, int flags);
 int KYTY_SYSV_ABI NetPoolDestroy(int memid);
 int KYTY_SYSV_ABI NetResolverCreate(const char* name, int memid, int flags);
+int KYTY_SYSV_ABI NetResolverDestroy(int rid);
 int KYTY_SYSV_ABI NetResolverStartNtoa(int rid, const char* hostname, void* addr, int timeout,
                                        int retry, int flags);
 int KYTY_SYSV_ABI NetInetPton(int af, const char* src, void* dst);

src/loader/runtimeLinker.cpp

@@ -801,7 +801,10 @@ static bool KytyExceptionHandler(const Common::HostException::ExceptionInfo& exc
 			return true;
 		}
 	}
-	return false;
+	EXIT("Unhandled host exception: type=%u code=%u pc=0x%016" PRIx64
+	     " access=%u address=0x%016" PRIx64 "\n",
+	     static_cast<unsigned>(info->type), info->native_code, info->exception_address,
+	     static_cast<unsigned>(info->access_violation_type), info->access_violation_vaddr);
 }
 
 static void EncodeId64(uint16_t in_id, std::string* out_id) {

tests/ShaderRecompilerComputeTests.cpp

@@ -7283,26 +7283,30 @@ public:
     std::printf("[gpu]     %-32s ok\n", name);
   }
 
-  void CheckRenderExecutorColorStandard4TileDiscovery() {
-    constexpr const char *name = "RenderExecutorColorStandard4Tile";
+  void CheckRenderExecutorColorStandardTileDiscovery() {
+    constexpr const char *name = "RenderExecutorColorStandardTile";
     constexpr uintptr_t base = 0x0000000203b00000ull;
-    constexpr uint64_t target_address = base + 0x4000;
-    constexpr uint64_t target_size = 0x180000;
-    constexpr uint64_t allocation_size = 0x184000;
-    constexpr uint64_t allocation_alignment = 0x4000;
+    constexpr uint64_t allocation_size = 0x190000;
+    constexpr uint64_t allocation_alignment = 0x10000;
     constexpr auto format = Prospero::BufferFormat::k32Float;
-    constexpr auto tile = Prospero::TileMode::kStandard4KB;
+    struct TileCase {
+      Prospero::TileMode tile;
+      uint64_t target_offset;
+      uint64_t alignment;
+    };
+    constexpr std::array cases{
+        TileCase{Prospero::TileMode::kStandard4KB, 0x4000, 0x1000},
+        TileCase{Prospero::TileMode::kStandard64KB, 0x10000, 0x10000},
+    };
     EnsureRuntimeContext();
 
-    const auto pitch = TileGetTexturePitch(format, 256, tile);
-    TileSizeAlign slice{};
-    TileGetTextureSize(format, 256, 256, 1, tile, &slice, nullptr, nullptr);
-    const auto odd_pitch = TileGetTexturePitch(format, 257, tile);
+    const auto odd_pitch =
+        TileGetTexturePitch(format, 257, Prospero::TileMode::kStandard4KB);
     TileSizeAlign odd_slice{};
-    TileGetTextureSize(format, 257, 131, 1, tile, &odd_slice, nullptr, nullptr);
+    TileGetTextureSize(format, 257, 131, 1, Prospero::TileMode::kStandard4KB,
+                       &odd_slice, nullptr, nullptr);
     Require(name, "tile layout",
-            pitch == 256 && slice.size == 0x40000 && slice.align == 0x1000 &&
-                odd_pitch == 288 && odd_slice.size == 0x2d000 &&
+            odd_pitch == 288 && odd_slice.size == 0x2d000 &&
                 odd_slice.align == 0x1000,
             "Standard4KB pitch, footprint, or block alignment is incorrect");
 
@@ -7311,17 +7315,29 @@ public:
             Libs::LibKernel::Memory::KernelAllocateDirectMemory(
                 0, Libs::LibKernel::Memory::KernelGetDirectMemorySize(),
                 allocation_size, allocation_alignment, 0, &direct_offset) == 0,
-            "Standard4KB color allocation failed");
+            "standard-tiled color allocation failed");
     void *mapped = reinterpret_cast<void *>(base);
     Require(name, "direct mapping",
             Libs::LibKernel::Memory::KernelMapDirectMemory(
                 &mapped, allocation_size, 0x3, 0x10, direct_offset,
                 allocation_alignment) == 0 &&
                 mapped == reinterpret_cast<void *>(base),
-            "Standard4KB color mapping failed");
+            "standard-tiled color mapping failed");
     std::memset(mapped, 0, allocation_size);
 
-    {
+    for (const auto &tile_case : cases) {
+      const auto pitch = TileGetTexturePitch(format, 256, tile_case.tile);
+      TileSizeAlign slice{};
+      TileGetTextureSize(format, 256, 256, 1, tile_case.tile, &slice, nullptr,
+                         nullptr);
+      Require(
+          name, "tile layout",
+          pitch == 256 && slice.size == 0x40000 &&
+              slice.align == tile_case.alignment,
+          "standard tile pitch, footprint, or block alignment is incorrect");
+
+      const auto target_address = base + tile_case.target_offset;
+      const auto target_size = slice.size * 6ull;
       RenderContext context(m_runtime_context);
       auto &scheduler = context.GetCommandScheduler();
       HW::Context registers{};
@@ -7335,7 +7351,7 @@ public:
       registers.SetColorView(
           0, {.base_array_slice_index = 5, .last_array_slice_index = 5});
       registers.SetColorAttrib2(0, {.height = 255, .width = 255});
-      registers.SetColorAttrib3(0, {.tile_mode = tile,
+      registers.SetColorAttrib3(0, {.tile_mode = tile_case.tile,
                                     .dimension = 1,
                                     .cmask_pipe_aligned = true,
                                     .dcc_pipe_aligned = true});
@@ -7358,7 +7374,7 @@ public:
                   color.base_array_layer == 5 &&
                   color.desc.info.data.address == target_address &&
                   color.desc.info.data.size == target_size &&
-                  color.desc.info.tile_mode == tile &&
+                  color.desc.info.tile_mode == tile_case.tile &&
                   color.desc.info.extent == vk::Extent3D{256, 256, 1} &&
                   color.desc.info.resources == ImageSubresources{1, 6} &&
                   color.desc.info.pitch == pitch &&
@@ -7367,9 +7383,9 @@ public:
                   color.desc.view_info.type == vk::ImageViewType::e2D &&
                   color.desc.view_info.base_layer == 5 &&
                   color.desc.view_info.layer_count == 1 &&
-                  (target_address & 0xffffu) == 0x4000 &&
+                  (target_address & (tile_case.alignment - 1)) == 0 &&
                   image.usage.render_target && image.IsGpuModified(),
-              "slice 5 Standard4KB render target was not resolved");
+              "slice 5 standard-tiled render target was not resolved");
 
       RenderExecutorTestAccess::ResetBindings(executor);
       resources.UnmapMemory(base, allocation_size);
@@ -7378,11 +7394,11 @@ public:
 
     Require(name, "unmap direct backing",
             Libs::LibKernel::Memory::KernelMunmap(base, allocation_size) == 0,
-            "Standard4KB color mapping release failed");
+            "standard-tiled color mapping release failed");
     Require(name, "release direct backing",
             Libs::LibKernel::Memory::KernelReleaseDirectMemory(
                 direct_offset, allocation_size) == 0,
-            "Standard4KB color allocation release failed");
+            "standard-tiled color allocation release failed");
     std::printf("[gpu]     %-32s ok\n", name);
   }
 
@@ -12018,6 +12034,7 @@ CoverageClass ClassifyOpcode(ShaderOpcode opcode,
   case Opcode::DS_READ_I16:
   case Opcode::DS_READ_U16:
   case Opcode::DS_READ_U16_D16:
+  case Opcode::DS_READ_U16_D16_HI:
   case Opcode::DS_READ2_B32:
   case Opcode::DS_READ_B32:
   case Opcode::DS_READ_B64:
@@ -12026,6 +12043,7 @@ CoverageClass ClassifyOpcode(ShaderOpcode opcode,
   case Opcode::DS_READ_B128:
   case Opcode::DS_WRITE_B8:
   case Opcode::DS_WRITE_B16:
+  case Opcode::DS_WRITE_B16_D16_HI:
   case Opcode::DS_WRITE2_B32:
   case Opcode::DS_WRITE2ST64_B32:
   case Opcode::DS_WRITE_B32:
@@ -13355,6 +13373,83 @@ TestCase VectorIntegerOps() {
            O::S_ENDPGM}};
 }
 
+TestCase VectorFfbhI32NativeAndVop3OnGpu() {
+  using O = ShaderOpcode;
+
+  constexpr std::array inputs = {0x00000000u, 0x40000000u, 0x80000000u,
+                                 0x0fffffffu, 0xffff0000u, 0xfffffffeu,
+                                 0xffffffffu, 0x80000000u};
+  std::vector<u32> code;
+  for (u32 i = 0; i < inputs.size() - 1u; i++) {
+    AppendVMovU32(&code, 30, i * 4u);
+    AppendBufferLoadDword(&code, 14, 30);
+    code.push_back(0x7e1c770eu); // v_ffbh_i32 v14, v14
+    AppendStoreVgpr(&code, 14, i);
+  }
+  AppendVMovU32(&code, 30, (inputs.size() - 1u) * 4u);
+  AppendBufferLoadDword(&code, 14, 30);
+  AppendVop3(&code, 0x1bbu, 15, Vgpr(14), 0);
+  AppendStoreVgpr(&code, 15, inputs.size() - 1u);
+  AppendEnd(&code);
+
+  TestCase test;
+  test.name = "VectorFfbhI32NativeAndVop3OnGpu";
+  test.code = std::move(code);
+  test.initial.assign(inputs.begin(), inputs.end());
+  test.expected = {0xffffffffu, 1u, 1u, 4u, 16u, 31u, 0xffffffffu, 1u};
+  test.opcodes = {O::V_MOV_B32, O::BUFFER_LOAD_DWORD, O::V_FFBH_I32,
+                  O::BUFFER_STORE_DWORD, O::S_ENDPGM};
+  test.decoded_counts = {{"V_FFBH_I32 v14, v14", inputs.size() - 1u},
+                         {"V_FFBH_I32 v15, v14", 1u}};
+  return test;
+}
+
+TestCase Vop1SdwaFfblCapturedHighWordSource() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  AppendBufferLoadDword(&code, 2, 30);
+  code.push_back(0x7e2074f9u);
+  code.push_back(0x00050602u); // v_ffbl_b32 v16, v2.word1
+  AppendStoreVgpr(&code, 16, 0);
+  AppendEnd(&code);
+
+  TestCase test;
+  test.name = "Vop1SdwaFfblCapturedHighWordSource";
+  test.code = std::move(code);
+  test.initial = {0x00400000u};
+  test.expected = {6u};
+  test.opcodes = {O::BUFFER_LOAD_DWORD, O::V_FFBL_B32, O::BUFFER_STORE_DWORD,
+                  O::S_ENDPGM};
+  test.decoded_counts = {{"V_FFBL_B32 v16, v2.sdwa(sel=5,sext=0)", 1}};
+  test.ir_counts = {{" = BitFieldUExtract ", 1}, {" = FindILsb32 ", 1}};
+  test.required_spirv = {"OpBitFieldUExtract"};
+  return test;
+}
+
+TestCase Vop1SdwaNotCapturedByte0Source() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  AppendBufferLoadDword(&code, 2, 30);
+  code.push_back(0x7e046ef9u);
+  code.push_back(0x00000602u); // v_not_b32 v2, v2.byte0
+  AppendStoreVgpr(&code, 2, 0);
+  AppendEnd(&code);
+
+  TestCase test;
+  test.name = "Vop1SdwaNotCapturedByte0Source";
+  test.code = std::move(code);
+  test.initial = {0x12345678u};
+  test.expected = {0xffffff87u};
+  test.opcodes = {O::BUFFER_LOAD_DWORD, O::V_NOT_B32, O::BUFFER_STORE_DWORD,
+                  O::S_ENDPGM};
+  test.decoded_counts = {{"V_NOT_B32 v2, v2.sdwa(sel=0,sext=0)", 1}};
+  test.ir_counts = {{" = BitFieldUExtract ", 1}, {" = BitwiseNot32 ", 1}};
+  test.required_spirv = {"OpBitFieldUExtract", "OpNot"};
+  return test;
+}
+
 TestCase Vop2SdwaSubNcExactByte2Destination() {
   using O = ShaderOpcode;
 
@@ -13862,37 +13957,35 @@ TestCase VectorAddcUsesPerLaneCarryIn() {
 TestCase VectorAddcWritesPerLaneCarryOut() {
   using O = ShaderOpcode;
 
-  std::vector<u32> code = {
-      EncodeVop1(0x01, 1, 0),
-      EncodeVop2(0x1a, 1, InlineU32(2), 1),
-      EncodeVop2(0x25, 1, Vgpr(0), 1),
-      EncodeVopc(0xc0, Vgpr(0), 0),
-  };
-  AppendVMovLiteral(&code, 2, 0xffffffffu);
-  code.push_back(EncodeVop1(0x01, 3, InlineU32(1)));
-  code.push_back(EncodeVop2(0x28, 5, Vgpr(2), 3));
+  std::vector<u32> code = {EncodeVop1(0x01, 1, Vgpr(0)),
+                           EncodeVop2(0x1a, 4, InlineU32(2), 1),
+                           EncodeVopc(0xc7, Vgpr(0), 0)};
+  AppendBufferLoadDword(&code, 26, 4);
+  code.push_back(0x500434f9u);
+  code.push_back(0x0c860680u);
   code.push_back(EncodeVop1(0x01, 6, 106));
-  code.push_back(EncodeVop2(0x1a, 4, InlineU32(2), 1));
   AppendBufferStoreDword(&code, 6, 4);
   AppendEnd(&code);
 
   TestCase test;
   test.name = "VectorAddcWritesPerLaneCarryOut";
   test.code = code;
+  test.initial = {0x0000ffffu, 0u, 0x0000ffffu, 0u};
   // VCC is represented as the current invocation's carry bit, not a shared
   // four-lane ballot word.
-  test.expected = std::vector<u32>(8, 1u);
-  test.opcodes = {O::V_MOV_B32,   O::V_LSHLREV_B32, O::V_ADD_NC_U32,
-                  O::V_CMP_F_U32, O::V_ADDC_U32,    O::BUFFER_STORE_DWORD,
+  test.expected = {1u, 0u, 1u, 0u};
+  test.opcodes = {O::V_MOV_B32,         O::V_LSHLREV_B32, O::V_CMP_T_U32,
+                  O::BUFFER_LOAD_DWORD, O::V_ADDC_U32,    O::BUFFER_STORE_DWORD,
                   O::S_ENDPGM};
+  test.decoded_counts = {
+      {"V_ADDC_U32 v2, vcc_lo, 0, v26.sdwa(sel=4,sext=1), vcc_lo", 1}};
+  test.ir_counts = {{" = BitFieldSExtract ", 1}, {" = IAddCarry32 ", 2}};
+  test.required_spirv = {"OpBitFieldSExtract"};
   test.compute_info.threads_num[0] = 4;
   test.compute_info.threads_num[1] = 1;
   test.compute_info.threads_num[2] = 1;
-  test.compute_info.group_id[0] = true;
   test.compute_info.thread_ids_num = 1;
-  test.compute_info.workgroup_register = 0;
   test.has_compute_info = true;
-  test.dispatch_x = 2;
   return test;
 }
 
@@ -15367,6 +15460,36 @@ TestCase VectorCompareOps() {
            O::V_CMP_T_U32,   O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
 }
 
+TestCase VectorVop3CompareEqU64OnGpu() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  code.push_back(EncodeVop1(0x01, 1, InlineU32(1)));
+
+  code.push_back(EncodeSop1(0x04, 106, 126)); // s_mov_b64 vcc, exec
+  code.push_back(0xd4e2006au);
+  code.push_back(0x0000d47eu); // v_cmp_eq_u64 vcc, exec, vcc
+  code.push_back(EncodeVop2(0x01, 2, InlineU32(0), 1));
+  AppendStoreVgpr(&code, 2, 0);
+
+  AppendSMovLiteral(&code, 107, 1); // high-dword mismatch
+  code.push_back(0xd4e2006au);
+  code.push_back(0x0000d47eu); // v_cmp_eq_u64 vcc, exec, vcc
+  code.push_back(EncodeVop2(0x01, 3, InlineU32(0), 1));
+  AppendStoreVgpr(&code, 3, 1);
+  AppendEnd(&code);
+
+  TestCase test{"VectorVop3CompareEqU64OnGpu",
+                code,
+                {},
+                {1, 0},
+                {O::V_MOV_B32, O::S_MOV_B64, O::V_CMP_EQ_U64,
+                 O::V_CNDMASK_B32, O::S_MOV_B32, O::BUFFER_STORE_DWORD,
+                 O::S_ENDPGM}};
+  test.decoded_counts = {{"V_CMP_EQ_U64 vcc_lo, exec_lo, vcc_lo", 2}};
+  return test;
+}
+
 TestCase VectorVop3CompareNeU64OnGpu() {
   using O = ShaderOpcode;
 
@@ -17992,6 +18115,64 @@ TestCase DsReadU16D16CapturedPreservesHighHalf() {
   return test;
 }
 
+TestCase DsWriteB16D16HiCapturedUsesHighHalf() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  AppendVMovU32(&code, 1, 0);
+  AppendVMovLiteral(&code, 3, 0xdeadbeefu);
+  code.push_back(EncodeDs0(0x0d));
+  code.push_back(EncodeDs1(0, 3, 1)); // ds_write_b32 v1, v3
+
+  AppendVMovU32(&code, 20, 2);
+  AppendVMovLiteral(&code, 2, 0x1234abcdu);
+  AppendVMovLiteral(&code, 0, 0x87654321u);
+  code.push_back(0xda840000u);
+  code.push_back(0x00000214u); // captured ds_write_b16_d16_hi v20, v2
+
+  code.push_back(EncodeDs0(0x36));
+  code.push_back(EncodeDs1(4, 0, 1)); // ds_read_b32 v4, v1
+  AppendStoreVgpr(&code, 4, 0);
+  AppendStoreVgpr(&code, 0, 1);
+  AppendEnd(&code);
+
+  TestCase test{"DsWriteB16D16HiCapturedUsesHighHalf",
+                code,
+                std::vector<u32>(2, 0),
+                {0x1234beefu, 0x87654321u},
+                {O::V_MOV_B32, O::DS_WRITE_B32, O::DS_WRITE_B16_D16_HI,
+                 O::DS_READ_B32, O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
+  test.decoded_counts = {{"DS_WRITE_B16_D16_HI", 1}};
+  return test;
+}
+
+TestCase DsReadU16D16HiCapturedPreservesLowHalf() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  AppendVMovU32(&code, 1, 0);
+  AppendVMovLiteral(&code, 2, 0x89abcdefu);
+  code.push_back(EncodeDs0(0x0d));
+  code.push_back(EncodeDs1(0, 2, 1)); // ds_write_b32 v2, v1
+
+  AppendVMovLiteral(&code, 5, 0x12345678u);
+  AppendVMovU32(&code, 6, 0);
+  code.push_back(0xda9c0000u);
+  code.push_back(0x05000006u); // captured ds_read_u16_d16_hi v5, v6
+
+  AppendStoreVgpr(&code, 5, 0);
+  AppendEnd(&code);
+
+  TestCase test{"DsReadU16D16HiCapturedPreservesLowHalf",
+                code,
+                std::vector<u32>(1, 0),
+                {0xcdef5678u},
+                {O::V_MOV_B32, O::DS_WRITE_B32, O::DS_READ_U16_D16_HI,
+                 O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
+  test.decoded_counts = {{"DS_READ_U16_D16_HI", 1}};
+  return test;
+}
+
 TestCase DsReadWrite2Variants() {
   using O = ShaderOpcode;
 
@@ -18936,6 +19117,44 @@ TestCase ImageLoad1DUsesScalarCoordinate() {
   return test;
 }
 
+TestCase ImageGather2DInstructionWith1DDescriptor() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  AppendVMovLiteral(&code, 20, 0x3f000000u);
+  AppendVMovLiteral(&code, 21, 0x3f000000u);
+  code.push_back(EncodeMimg0(0x47, 0x1));
+  code.push_back(EncodeMimg1(0, 20));
+  for (u32 i = 0; i < 4u; i++) {
+    AppendStoreVgpr(&code, i, i);
+  }
+  AppendEnd(&code);
+
+  auto image = MakeRgbaImage(4, 1);
+  SetRgbaPixel(&image, 4, 1, 0, 0x40000000u, 0, 0, 0);
+  SetRgbaPixel(&image, 4, 2, 0, 0x40400000u, 0, 0, 0);
+
+  TestCase test;
+  test.name = "ImageGather2DInstructionWith1DDescriptor";
+  test.code = code;
+  test.expected = {0x40000000u, 0x40400000u, 0x40400000u, 0x40000000u};
+  test.opcodes = {O::V_MOV_B32, O::IMAGE_GATHER4_LZ, O::BUFFER_STORE_DWORD,
+                  O::S_ENDPGM};
+  test.image_width = 4;
+  test.image_height = 1;
+  test.sampled_image_rgba = image;
+  test.sampled_image_type = vk::ImageType::e1D;
+  test.sampled_image_view_type = vk::ImageViewType::e1D;
+  test.user_data = MakeSampledTextureData(Prospero::BufferFormat::k32Float);
+  test.user_data[3] = static_cast<uint32_t>(Prospero::ImageType::kColor1D)
+                      << 28u;
+  test.has_user_data = true;
+  test.required_spirv = {"sampled_1d", "OpImageQuerySizeLod",
+                         "OpImageSampleExplicitLod", "Floor"};
+  test.forbidden_spirv = {"OpImageGather"};
+  return test;
+}
+
 TestCase ImageLoad1DArrayUsesLayerCoordinate() {
   using O = ShaderOpcode;
 
@@ -20350,6 +20569,9 @@ std::vector<TestCase> MakeCases() {
   AddCase(VectorMoves);
   AddCase(VectorVop3MoveAppliesFloatSourceModifiers);
   AddCase(VectorIntegerOps);
+  AddCase(VectorFfbhI32NativeAndVop3OnGpu);
+  AddCase(Vop1SdwaFfblCapturedHighWordSource);
+  AddCase(Vop1SdwaNotCapturedByte0Source);
   AddCase(Vop2SdwaSubNcExactByte2Destination);
   AddCase(Vop2SdwaAddNcCapturedHighWordDestination);
   AddCase(Vop2SdwaAshrrevCapturedWord0SignExtends);
@@ -20411,6 +20633,7 @@ std::vector<TestCase> MakeCases() {
   AddCase(VectorSinCosMaxFiniteSpecialCases);
   AddCase(VectorCompareOps);
   AddCase(VectorVop3CompareEqI64OnGpu);
+  AddCase(VectorVop3CompareEqU64OnGpu);
   AddCase(VectorVop3CompareGtU64OnGpu);
   AddCase(VectorVop3CompareNeU64OnGpu);
   AddCase(VectorVopcCmpxNeU64CapturedExecMask);
@@ -20507,7 +20730,9 @@ std::vector<TestCase> MakeCases() {
   AddCase(ScratchIsPrivatePerInvocation);
   AddCase(FlatStoreVariants);
   AddCase(DsReadWriteVariants);
+  AddCase(DsWriteB16D16HiCapturedUsesHighHalf);
   AddCase(DsReadU16D16CapturedPreservesHighHalf);
+  AddCase(DsReadU16D16HiCapturedPreservesLowHalf);
   AddCase(DsAppendConsumeUsesEncodedLdsSelector);
   AddCase(DsAppendUsesEncodedGdsSelector);
   AddCase(DsGdsSubdwordAndAtomicWrites);
@@ -20535,6 +20760,7 @@ std::vector<TestCase> MakeCases() {
   AddCase(ImageSamplePackedUintConvertsSampleAndGather);
   AddCase(ImageLoadR128IgnoresAdjacentMaskSgprs);
   AddCase(ImageLoad1DUsesScalarCoordinate);
+  AddCase(ImageGather2DInstructionWith1DDescriptor);
   AddCase(ImageLoad1DArrayUsesLayerCoordinate);
   AddCase(ImageLoad1DArrayDescriptorUsesSelectedLayer);
   AddCase(ImageLoadMipUsesVaddr2Lod2D);
@@ -24290,6 +24516,11 @@ int main(int argc, char **argv) {
     RunCase(&vulkan, Vop2SdwaAshrrevCapturedWord0SignExtends());
     return 0;
   }
+  if (argc == 2 && std::strcmp(argv[1], "--sdwa-addc-only") == 0) {
+    VulkanHarness vulkan;
+    RunCase(&vulkan, VectorAddcWritesPerLaneCarryOut());
+    return 0;
+  }
   if (argc == 2 && std::strcmp(argv[1], "--cvt-pk-i16-only") == 0) {
     VulkanHarness vulkan;
     RunCase(&vulkan, Vop3CvtPkI16I32Captured());
@@ -24391,9 +24622,9 @@ int main(int argc, char **argv) {
     CheckStandard64RenderTargetTileRoundTrip();
     return 0;
   }
-  if (argc == 2 && std::strcmp(argv[1], "--standard4-rt-only") == 0) {
+  if (argc == 2 && std::strcmp(argv[1], "--standard-tile-rt-only") == 0) {
     VulkanHarness vulkan;
-    vulkan.CheckRenderExecutorColorStandard4TileDiscovery();
+    vulkan.CheckRenderExecutorColorStandardTileDiscovery();
     return 0;
   }
   if (argc == 2 && std::strcmp(argv[1], "--image-view-only") == 0) {
@@ -24514,7 +24745,7 @@ int main(int argc, char **argv) {
 #if KYTY_PLATFORM == KYTY_PLATFORM_WINDOWS
   vulkan.CheckRenderExecutorColor1DDiscovery();
   vulkan.CheckRenderExecutorColorVolumeDiscovery();
-  vulkan.CheckRenderExecutorColorStandard4TileDiscovery();
+  vulkan.CheckRenderExecutorColorStandardTileDiscovery();
   vulkan.CheckRenderExecutorColorDepthTileDiscovery();
   vulkan.CheckRenderExecutorStencilBindingDiscovery();
   vulkan.CheckUnifiedTextureCacheFlow();

tests/shaderCfgTests.cpp

@@ -4007,6 +4007,30 @@ void TestNewShaderDecoderArchitecture() {
                 program_direct.word_count,
         "program decoder diverged from the single-instruction decoder");
 
+  const uint32_t cmp_eq_u64_code[] = {0xd4e2006au, 0x0000d47eu};
+  Instruction cmp_eq_u64;
+  Check(DecodeInstruction(cmp_eq_u64_code, 0u, cmp_eq_u64, &error),
+        error.c_str());
+  Check(cmp_eq_u64.family == Family::VOP3 &&
+            cmp_eq_u64.opcode == Opcode::V_CMP_EQ_U64 &&
+            cmp_eq_u64.dst.kind == OperandKind::VccLo &&
+            cmp_eq_u64.src_count == 2u &&
+            cmp_eq_u64.src0.kind == OperandKind::ExecLo &&
+            cmp_eq_u64.src1.kind == OperandKind::VccLo,
+        "decoder rejected the captured VOP3 V_CMP_EQ_U64 instruction");
+
+  const uint32_t ffbh_i32_code[] = {0x7e1c770eu};
+  Instruction ffbh_i32;
+  Check(DecodeInstruction(ffbh_i32_code, 0u, ffbh_i32, &error),
+        error.c_str());
+  Check(ffbh_i32.family == Family::VOP1 &&
+            ffbh_i32.opcode == Opcode::V_FFBH_I32 &&
+            ffbh_i32.dst.kind == OperandKind::Vgpr && ffbh_i32.dst.reg == 14u &&
+            ffbh_i32.src_count == 1u &&
+            ffbh_i32.src0.kind == OperandKind::Vgpr &&
+            ffbh_i32.src0.reg == 14u,
+        "decoder rejected the captured VOP1 V_FFBH_I32 instruction");
+
   const uint32_t literal_code[] = {EncodeVop1(0x01, 2, 255u), 0x12345678u};
   Instruction literal;
   Check(DecodeInstruction(literal_code, 0u, literal, &error), error.c_str());
@@ -4043,6 +4067,40 @@ void TestNewShaderDecoderArchitecture() {
         "decoder rejected or misdecoded captured partial-destination "
         "V_ADD_NC_U32");
 
+  const uint32_t vop2_sdwa_byte_shift[] = {
+      0x2c0910f9u,
+      0x86000613u, // v_lshrrev_b32 v4, v19.byte0, 8
+  };
+  Instruction byte_shift;
+  Check(DecodeInstruction(vop2_sdwa_byte_shift, 0u, byte_shift, &error),
+        error.c_str());
+  Check(byte_shift.family == Family::VOP2 &&
+            byte_shift.opcode == Opcode::V_LSHRREV_B32 &&
+            byte_shift.word_count == 2u && byte_shift.dst.reg == 4u &&
+            byte_shift.src0.kind == OperandKind::Vgpr &&
+            byte_shift.src0.reg == 19u && byte_shift.src0.sdwa_sel == 0u &&
+            byte_shift.src1.kind == OperandKind::IntegerInlineConstant &&
+            byte_shift.src1.value == 8u,
+        "decoder rejected or misdecoded captured V_LSHRREV_B32 byte shift");
+
+  const uint32_t vop2_sdwa_byte_left_shift[] = {
+      0x340d02f9u,
+      0x86030607u, // v_lshlrev_b32 v6, v7.byte3, 1
+  };
+  Instruction byte_left_shift;
+  Check(DecodeInstruction(vop2_sdwa_byte_left_shift, 0u, byte_left_shift,
+                          &error),
+        error.c_str());
+  Check(byte_left_shift.family == Family::VOP2 &&
+            byte_left_shift.opcode == Opcode::V_LSHLREV_B32 &&
+            byte_left_shift.word_count == 2u && byte_left_shift.dst.reg == 6u &&
+            byte_left_shift.src0.kind == OperandKind::Vgpr &&
+            byte_left_shift.src0.reg == 7u &&
+            byte_left_shift.src0.sdwa_sel == 3u &&
+            byte_left_shift.src1.kind == OperandKind::IntegerInlineConstant &&
+            byte_left_shift.src1.value == 1u,
+        "decoder rejected or misdecoded captured V_LSHLREV_B32 byte shift");
+
   const uint32_t mimg_nsa[] = {EncodeMimg0(0x20, 0xf) | (3u << 1u),
                                EncodeMimg1(4, 0, 1, 8), 0x03020100u,
                                0x07060504u, 0x0b0a0908u};
@@ -4065,6 +4123,28 @@ void TestNewShaderDecoderArchitecture() {
   Check(boot.opcode == Opcode::DS_SWIZZLE_B32 && boot.offset == 0xc480u,
         "DS decoder rejected a captured boot-shader instruction");
 
+  const uint32_t d16_hi_ds[] = {0xda9c0000u, 0x05000006u};
+  Instruction d16_hi;
+  Check(DecodeInstruction(d16_hi_ds, 0u, d16_hi, &error), error.c_str());
+  Check(d16_hi.opcode == Opcode::DS_READ_U16_D16_HI &&
+            d16_hi.src_count == 1u && d16_hi.data_bits == 16u &&
+            d16_hi.dst.reg == 5u && d16_hi.dst.sdwa_sel == 5u &&
+            d16_hi.dst.sdwa_dst_unused == 2u && d16_hi.src0.reg == 6u,
+        "DS decoder rejected the captured high-half D16 read");
+
+  const uint32_t d16_hi_write_ds[] = {0xda840000u, 0x00000214u};
+  Instruction d16_hi_write;
+  Check(DecodeInstruction(d16_hi_write_ds, 0u, d16_hi_write, &error),
+        error.c_str());
+  Check(d16_hi_write.family == Family::DS &&
+            d16_hi_write.opcode == Opcode::DS_WRITE_B16_D16_HI &&
+            d16_hi_write.word_count == 2u && d16_hi_write.src_count == 2u &&
+            d16_hi_write.data_dwords == 1u && d16_hi_write.data_bits == 16u &&
+            d16_hi_write.offset == 0u && !d16_hi_write.gds &&
+            d16_hi_write.src0.reg == 20u && d16_hi_write.src1.reg == 2u &&
+            d16_hi_write.src1.sdwa_sel == 5u,
+        "DS decoder rejected the captured high-half D16 write");
+
   constexpr uint32_t packed_source_selectors[][2] = {
       {0xcc0e0000u, 0x0c0a0300u}, // Source 0: instruction bit 59.
       {0xcc0e0000u, 0x140a0300u}, // Source 1: instruction bit 60.
@@ -4083,8 +4163,8 @@ void TestNewShaderDecoderArchitecture() {
 
 void TestNewShaderRecompilerRejectsDppOn64BitCompares() {
   const uint32_t opcodes[] = {
-      0xa2u, 0xb5u, 0xe4u, 0xe5u,
-      0xf5u}; // eq_i64, cmpx_ne_i64, gt_u64, ne_u64, cmpx_ne_u64
+      0xa2u, 0xb5u, 0xe2u, 0xe4u, 0xe5u,
+      0xf5u}; // eq_i64, cmpx_ne_i64, eq_u64, gt_u64, ne_u64, cmpx_ne_u64
   for (const auto opcode : opcodes) {
     const uint32_t shader[] = {
         EncodeVopc(opcode, 250u, 0u), // DPP escape in SRC0
@@ -5054,30 +5134,6 @@ void TestNewShaderRecompilerNullImageUsesCanonical2DView() {
         "null image retained the decoded 1D descriptor binding");
 }
 
-void TestNewShaderRecompilerRejectsOneDimensionalGather() {
-  constexpr std::array cases{
-      std::pair{0u, Prospero::ImageType::kColor1D},
-      std::pair{4u, Prospero::ImageType::kColor1DArray},
-  };
-  for (const auto &[dimension, type] : cases) {
-    const uint32_t shader[] = {
-        EncodeMimg0(0x47, 0x1, false, dimension),
-        EncodeMimg1(0, 0, 1, 0),
-        0xbf810000u,
-    };
-    auto user_data = ImageTestUserData(type);
-    auto options = MakeCompileOptions(ShaderType::Compute);
-    options.user_data = user_data.data();
-
-    ShaderRecompiler::CompileResult result;
-    std::string error;
-    Check(!ShaderRecompiler::TryRecompile(shader, options, result, &error) &&
-              Common::ContainsStr(error,
-                                  "1D image gather is not supported by SPIR-V"),
-          "1D image gather escaped as invalid SPIR-V");
-  }
-}
-
 void TestNewShaderRecompilerImageGatherVariants() {
   const uint32_t shader[] = {
       EncodeMimg0(0x47, 0x1),