shader: support V_CMPX_EQ_U16 (#816)

* shader: support V_CMPX_EQ_U16

Decode gfx11 VOPC 0xba and lower it as an unsigned 16-bit equality
compare with CMPX EXEC-mask semantics.

🤖 Generated with Codebuff 🤖
Co-Authored-By: Codebuff <noreply@codebuff.com>

* shader: correct CMPX EQ U16 runtime expectations

Remove the added CFG tests and correct two EXEC expectations in the compute regression case.

---------

Co-authored-by: Matthew Hurley <171001439+theantipopau@users.noreply.github.com>
Co-authored-by: Codebuff <noreply@codebuff.com>
Co-authored-by: nmzik <Nmzik@mail.ru>

CMakeLists.txt

@@ -677,7 +677,10 @@ if(KYTY_CLANG_CL)
 	)
 	add_custom_command(TARGET kyty_emulator POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${KYTY_THIRD_PARTY_DIR}/winpthread/bin/libwinpthread-1.dll" $<TARGET_FILE_DIR:kyty_emulator>/libwinpthread-1.dll)
 elseif(WIN32 OR LINUX)
-	set_target_properties(kyty_emulator PROPERTIES LINK_FLAGS "${KYTY_LD_OPTIONS} -Wl,-Map=${KYTY_EMULATOR_MAP_LINK_PATH}")
+	set_target_properties(kyty_emulator PROPERTIES LINK_FLAGS "${KYTY_LD_OPTIONS}")
+	# LINK_FLAGS is a space-delimited string: a -Map path containing spaces would
+	# be split into bogus arguments, so pass it as a discrete link option instead.
+	target_link_options(kyty_emulator PRIVATE "-Wl,-Map=${KYTY_EMULATOR_MAP_LINK_PATH}")
 endif()
 
 if(LINUX)

README.md

@@ -4,13 +4,13 @@
 [![Build KytyPS5 (Linux)](https://img.shields.io/github/actions/workflow/status/KytyPS5/KytyPS5/build.yml?branch=main&event=push&label=Build%20KytyPS5%20%28Linux%29)](https://github.com/KytyPS5/KytyPS5/actions/workflows/build.yml)
 [![Build KytyPS5 (macOS)](https://img.shields.io/github/actions/workflow/status/KytyPS5/KytyPS5/build.yml?branch=main&event=push&label=Build%20KytyPS5%20%28macOS%29)](https://github.com/KytyPS5/KytyPS5/actions/workflows/build.yml)
 [![Platform](https://img.shields.io/badge/platform-Windows%20x64%20%7C%20Linux%20x64%20%7C%20macOS%20x86__64-0078D4.svg)](#system-requirements)
-[![Status](https://img.shields.io/badge/status-early%20development-orange.svg)](#current-status)
+[![Status](https://img.shields.io/badge/status-active%20development-orange.svg)](#current-status)
 [![License](https://img.shields.io/badge/license-GPL--2.0-blue.svg)](LICENSE)
 
 KytyPS5 is a free and open-source PlayStation 5 emulator written in C++ for Windows and Linux,
 with experimental macOS support. It is based on a heavily modified version of
-[Kyty](https://github.com/InoriRus/Kyty). The project is in an early stage of development, so
-compatibility is limited and behavior may change significantly between builds.
+[Kyty](https://github.com/InoriRus/Kyty). The project is in active development, and behavior
+can change significantly between builds.
 
 > [!IMPORTANT]
 > KytyPS5 is not affiliated with Sony Interactive Entertainment or PlayStation. The project does
@@ -20,12 +20,12 @@ compatibility is limited and behavior may change significantly between builds.
 ## Current Status
 
 KytyPS5 can boot 2D games and a selection of 3D games, including titles built with Unreal Engine
-4/5, Unity, and custom engines. No external low-level emulation modules are currently required.
+4/5, Unity, and custom engines. External low-level emulation modules are neither required nor
+planned.
 
-Development is focused on compatibility and boot reliability.
+Development is currently focused on expanding game compatibility and improving boot reliability.
 
-Windows is the primary platform and receives the most testing. Linux builds and runs; see
-[Building on Linux](#building-on-linux).
+Windows and Linux are the primary platforms and receive the most testing.
 
 macOS support is experimental. The emulator is built for x86-64 and runs on Apple Silicon under
 Rosetta 2, with Vulkan provided by MoltenVK. A small number of titles have been verified in-game
@@ -36,8 +36,8 @@ Community game test results are available in the
 
 ## Bugs and Issues
 
-The project is in an early stage, so please be mindful when opening new issues. Expect crashes,
-graphical glitches, low compatibility, and poor performance.
+Compatibility, stability, and performance can vary between versions. You may encounter crashes
+or graphical glitches, so please include the version you tested when reporting an issue.
 
 ## Screenshots
 
@@ -370,5 +370,6 @@ licenses included with those components.
 
 - [InoriRus/Kyty](https://github.com/InoriRus/Kyty) — KytyPS5 is based on a heavily modified version
   of the original Kyty project.
-- [shadps4-emu/shadPS4](https://github.com/shadps4-emu/shadPS4) — reference for memory-model
-  understanding and the AVPlayer implementation.
+- [shadps4-emu/shadPS4](https://github.com/shadps4-emu/shadPS4) — reference for understanding PS4
+  memory behavior, GPU resource aliasing and cache coherency,
+  and the AVPlayer implementation.

src/common/timer.cpp

@@ -38,16 +38,7 @@ bool Timer::IsPaused() const {
 
 // return time in milliseconds
 double Timer::GetTimeMs() const {
-	if (m_is_paused) {
-		return 1000.0 * (static_cast<double>(m_PauseTime - m_StartTime)) /
-		       static_cast<double>(m_Frequency);
-	}
-
-	uint64_t current_time = 0;
-	SysQueryPerformanceCounter(&current_time);
-
-	return 1000.0 * (static_cast<double>(current_time - m_StartTime)) /
-	       static_cast<double>(m_Frequency);
+	return GetTimeS() * 1000.0;
 }
 
 // return time in seconds

src/graphics/guest_gpu/graphicsRun.cpp

@@ -976,6 +976,16 @@ void CommandProcessor::DrawIndirectMulti(uint32_t data_offset, uint32_t max_coun
 	const auto args_size = indexed ? sizeof(DrawIndexedIndirectArgs) : sizeof(DrawIndirectArgs);
 	EXIT_NOT_IMPLEMENTED(stride_in_bytes < args_size);
 
+	uint64_t index_size = 0;
+	if (indexed) {
+		switch (m_index_type_and_size) {
+			case 0: index_size = 2; break;
+			case 1: index_size = 4; break;
+			case 2: index_size = 1; break;
+			default: EXIT("unknown index_type_and_size: %u\n", m_index_type_and_size);
+		}
+	}
+
 	for (uint32_t i = 0; i < draw_count; i++) {
 		const auto args_addr = m_draw_indirect_args_base_addr + data_offset +
 		                       static_cast<uint64_t>(i) * stride_in_bytes;
@@ -993,14 +1003,6 @@ void CommandProcessor::DrawIndirectMulti(uint32_t data_offset, uint32_t max_coun
 
 		auto* args = reinterpret_cast<const DrawIndexedIndirectArgs*>(args_addr);
 
-		uint64_t index_size = 0;
-		switch (m_index_type_and_size) {
-			case 0: index_size = 2; break;
-			case 1: index_size = 4; break;
-			case 2: index_size = 1; break;
-			default: EXIT("unknown index_type_and_size: %u\n", m_index_type_and_size);
-		}
-
 		auto* index_addr = reinterpret_cast<const void*>(
 		    m_index_base_addr + static_cast<uint64_t>(args->start_index_location) * index_size);
 

src/graphics/host_gpu/renderer/image/imageInfo.h

@@ -329,7 +329,9 @@ struct VideoOutFormatPolicy {
 	VideoOutPixelFormatInfo info;
 };
 
-inline constexpr std::array<VideoOutFormatPolicy, 6> VIDEO_OUT_FORMAT_POLICIES {{
+inline constexpr uint64_t VIDEO_OUT_PIXEL_FORMAT_R10_G10_B10_A2_BT2100_PQ = 0x8100070422000000ull;
+
+inline constexpr std::array<VideoOutFormatPolicy, 7> VIDEO_OUT_FORMAT_POLICIES {{
     {0x8000000022000000ull,
      {vk::Format::eR8G8B8A8Srgb, Prospero::BufferFormat::k8_8_8_8Srgb, 4, false}},
     {0x8000000000000000ull,
@@ -338,6 +340,8 @@ inline constexpr std::array<VideoOutFormatPolicy, 6> VIDEO_OUT_FORMAT_POLICIES {
      {vk::Format::eA2B10G10R10UnormPack32, Prospero::BufferFormat::k10_10_10_2UNorm, 4, false}},
     {0x8100000000000000ull,
      {vk::Format::eA2R10G10B10UnormPack32, Prospero::BufferFormat::k10_10_10_2UNorm, 4, false}},
+    {VIDEO_OUT_PIXEL_FORMAT_R10_G10_B10_A2_BT2100_PQ,
+     {vk::Format::eA2B10G10R10UnormPack32, Prospero::BufferFormat::k10_10_10_2UNorm, 4, false}},
     {0xc001000622000000ull,
      {vk::Format::eR16G16B16A16Sfloat, Prospero::BufferFormat::k16_16_16_16Float, 8, false}},
     {0xc001000600000000ull,

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

@@ -204,6 +204,7 @@ struct PipelineCache::ProgramCache {
 		ShaderRecompiler::IR::ResourceSnapshot       resources;
 		ShaderRecompiler::IR::ResourceSpecialization specialization;
 		std::vector<Permutation>                    permutations;
+		bool                                        skip_dispatch = false;
 	};
 
 	struct ProgramKeyHash {
@@ -283,6 +284,9 @@ struct PipelineCache::ProgramCache {
 		lookup_key.code_size       = static_cast<uint32_t>(params.code.size());
 		BuildStageStaticKey(input_info, lookup_key.static_state);
 		auto                                         entry = programs.find(lookup_key);
+		if (entry != programs.end() && entry->second.skip_dispatch) {
+			return {};
+		}
 		const ShaderRecompiler::IR::SrtRuntime       runtime {
 		    .user_data                  = user_data,
 		    .shader_base                = params.Base(),
@@ -348,6 +352,11 @@ struct PipelineCache::ProgramCache {
 			options.wave_size = input_info.wave_size;
 		}
 		auto translated = ShaderRecompiler::TranslateProgram(params.code, options);
+		if (translated.skip_dispatch) {
+			entry = programs.try_emplace(lookup_key, ShaderRecompiler::IR::ResourcePlan {}).first;
+			entry->second.skip_dispatch = true;
+			return {};
+		}
 		if (entry == programs.end()) {
 			entry = programs.try_emplace(lookup_key,
 			    ShaderRecompiler::IR::ExtractResourcePlan(translated.program)).first;

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

@@ -368,6 +368,8 @@ void CreatePipelineInternal(GraphicContext& graphics, PipelineCache::Pipeline& p
 	// MoltenVK lacks VK_EXT_depth_clip_enable; omit the depth-clip struct on macOS and accept
 	// Vulkan's default depth clipping (enabled) instead of the PS5's clamp behavior.
 #if !defined(__APPLE__)
+	// The DB clamps depth to the viewport range after polygon offset is applied.
+	rasterizer.depthClampEnable = VK_TRUE;
 	rasterizer.pNext = &clip_ext;
 #endif
 	vk::PipelineRasterizationProvokingVertexStateCreateInfoEXT provoking_vertex {};

src/graphics/host_gpu/renderer/renderCompute.cpp

@@ -256,6 +256,10 @@ void RenderExecutor::DispatchDirect(uint64_t submit_id, CommandBuffer& buffer,
 	input_info.dispatch_thread_dimensions = use_thread_dimensions;
 	const auto compute_program =
 	    m_context.GetPipelineCache().GetComputeProgram(cs_regs, sh_regs, input_info);
+	if (!compute_program) {
+		// Temporary until RT is implemented.
+		return;
+	}
 	if (use_thread_dimensions) {
 		input_info.dispatch_threads_num[0]    = thread_group_x;
 		input_info.dispatch_threads_num[1]    = thread_group_y;
@@ -413,6 +417,10 @@ void RenderExecutor::DispatchIndirect(uint64_t submit_id, CommandBuffer& buffer,
 	ShaderComputeInputInfo input_info {};
 	const auto compute_program = m_context.GetPipelineCache().GetComputeProgram(
 	    cs_regs, buffer.GetRegisters().GetShaderRegisters(), input_info);
+	if (!compute_program) {
+		// Temporary until RT is implemented.
+		return;
+	}
 	buffer.EndRendering();
 	auto& pipeline = m_context.GetPipelineCache().GetComputePipeline(input_info, compute_program);
 	auto& bindings = m_compute_bindings;

src/graphics/host_gpu/renderer/renderDraw.cpp

@@ -686,11 +686,13 @@ static PreparedVertexBuffers AcquireVertexBuffers(CommandBuffer&               b
 	        vs_input_info.buffers_num > ShaderVertexInputInfo::RES_MAX);
 
 	// Collect the non-empty guest vertex ranges.
+	std::array<uint64_t, ShaderVertexInputInfo::RES_MAX>          sizes {};
 	std::array<VertexBufferRange, ShaderVertexInputInfo::RES_MAX> ranges {};
 	uint32_t                                                      range_count = 0;
 	for (int i = 0; i < vs_input_info.buffers_num; i++) {
 		const auto& vertex = vs_input_info.buffers[i];
 		const auto  size   = VertexBufferDescriptorSize(vertex, vs_input_info);
+		sizes[i]           = size;
 		if (size == 0) {
 			continue;
 		}
@@ -739,7 +741,7 @@ static PreparedVertexBuffers AcquireVertexBuffers(CommandBuffer&               b
 	vk::Buffer null_buffer = nullptr;
 	for (int i = 0; i < vs_input_info.buffers_num; i++) {
 		const auto& vertex = vs_input_info.buffers[i];
-		const auto  size   = VertexBufferDescriptorSize(vertex, vs_input_info);
+		const auto  size   = sizes[i];
 		if (size == 0) {
 			if (null_buffer == nullptr) {
 				null_buffer = cache.GetBuffer(NULL_BUFFER_ID).Handle();

src/graphics/presentation/videoOut.cpp

@@ -24,6 +24,8 @@
 
 #include <algorithm>
 #include <array>
+#include <atomic>
+#include <fmt/format.h>
 #include <list>
 #include <thread>
 #include <vector>
@@ -541,6 +543,14 @@ Graphics::ImageInfo BufferAttributeGroup::ImageInfo(const VideoOutBuffer& buffer
 	if (!Graphics::DecodeVideoOutPixelFormat(attribute.pixel_format, pixel_format)) {
 		EXIT("unsupported video-out pixel format: 0x%016" PRIx64 "\n", attribute.pixel_format);
 	}
+	if (attribute.pixel_format == Graphics::VIDEO_OUT_PIXEL_FORMAT_R10_G10_B10_A2_BT2100_PQ) {
+		static std::atomic_flag warned = ATOMIC_FLAG_INIT;
+		if (!warned.test_and_set(std::memory_order_relaxed)) {
+			Log::WriteToConsoleAndLog(fmt::format(
+			    "Warning: HDR-to-SDR conversion is not implemented; displaying PQ video-out "
+			    "pixels unchanged (format=0x{:016x}).\n", attribute.pixel_format));
+		}
+	}
 	const auto tile_mode = Graphics::Prospero::TileMode::kRenderTarget;
 	const auto pitch =
 	    Graphics::TileGetTexturePitch(pixel_format.guest_format, attribute.width, tile_mode);
@@ -1546,7 +1556,9 @@ KYTY_SYSV_ABI int VideoOutIsFlipPending(int handle) {
 	VideoOutFlipStatus status {};
 	DriverState().GetFlipQueue().GetFlipStatus(*ctx, status);
 
-	LOGF("\t flipPendingNum = %d\n", status.flipPendingNum);
+	if (Config::GraphicsDebugDumpEnabled()) {
+		LOGF("\t flipPendingNum = %d\n", status.flipPendingNum);
+	}
 
 	return status.flipPendingNum;
 }
@@ -1680,21 +1692,6 @@ KYTY_SYSV_ABI int VideoOutGetOutputStatus(int handle, VideoOutOutputStatus* stat
 	return OK;
 }
 
-KYTY_SYSV_ABI int VideoOutGetVrrStatus(int handle, int32_t* status) {
-	PRINT_NAME();
-
-	if (status == nullptr) {
-		return VIDEO_OUT_ERROR_INVALID_ADDRESS;
-	}
-	if (DriverState().Get(handle) == nullptr) {
-		return VIDEO_OUT_ERROR_INVALID_HANDLE;
-	}
-
-	// Kyty currently presents at a fixed refresh rate and does not negotiate VRR.
-	*status = 0;
-	return OK;
-}
-
 static int ValidateOutputConfig(int handle, uint64_t mode, const VideoOutOutputOptions* options,
                                 void* reserved_ptr, uint64_t reserved) {
 	if (!DriverState().IsOpened(handle)) {

src/graphics/presentation/videoOut.h

@@ -87,7 +87,6 @@ KYTY_SYSV_ABI int VideoOutGetEventData(const LibKernel::EventQueue::KernelEvent*
 KYTY_SYSV_ABI int VideoOutGetEventCount(const LibKernel::EventQueue::KernelEvent* ev);
 KYTY_SYSV_ABI int VideoOutWaitVblank(int handle);
 KYTY_SYSV_ABI int VideoOutGetOutputStatus(int handle, VideoOutOutputStatus* status);
-KYTY_SYSV_ABI int VideoOutGetVrrStatus(int handle, int32_t* status);
 KYTY_SYSV_ABI int VideoOutInitializeOutputOptions(VideoOutOutputOptions* options);
 KYTY_SYSV_ABI int VideoOutIsOutputSupported(int handle, uint64_t mode,
                                             const VideoOutOutputOptions* options,

src/graphics/presentation/window/vulkanWindow.cpp

@@ -238,6 +238,10 @@ static void VulkanFindPhysicalDevice(vk::Instance instance, vk::SurfaceKHR surfa
 #endif
 		}
 #if !defined(__APPLE__)
+		if (device_features2.features.depthClamp != VK_TRUE) {
+			LOGF("depthClamp is not supported\n");
+			skip_device = true;
+		}
 		if (fragment_barycentric.fragmentShaderBarycentric != VK_TRUE) {
 			LOGF("fragmentShaderBarycentric is not supported\n");
 			skip_device = true;
@@ -607,6 +611,7 @@ static vk::Device VulkanCreateDevice(GraphicContext& graphics,
 	device_features.robustBufferAccess       = VK_TRUE;
 #if !defined(__APPLE__)
 	device_features.depthBounds = VK_TRUE; // unsupported by MoltenVK
+	device_features.depthClamp  = VK_TRUE;
 #endif
 	device_features.shaderStorageImageWriteWithoutFormat = VK_TRUE;
 	device_features.shaderImageGatherExtended            = VK_TRUE;

src/graphics/shader/recompiler/ShaderRecompiler.cpp

@@ -20,6 +20,7 @@
 
 #include <algorithm>
 #include <array>
+#include <atomic>
 #include <chrono>
 #include <fmt/format.h>
 #include <map>
@@ -523,6 +524,20 @@ TranslateResult TranslateProgram(std::span<const uint32_t> code, const CompileOp
 	     GetDumpLabel(options), StageName(options.stage), options.shader_hash,
 	     static_cast<uint64_t>(decoded.instructions.size()), phase_ms());
 
+	// Temporary workaround for games that compile ray-tracing shaders before
+	// the player can select a mode without ray tracing.
+	if (options.stage == ShaderType::Compute && decoded.has_bvh) {
+		static std::atomic_flag warned = ATOMIC_FLAG_INIT;
+		if (!warned.test_and_set(std::memory_order_relaxed)) {
+			const auto& bvh = decoded.instructions.back();
+			Log::WriteToConsoleAndLog(fmt::format(
+			    "Warning: ray tracing is not implemented; skipping compute dispatches containing "
+			    "BVH intersection instructions (shader=0x{:016x}, pc=0x{:08x}, opcode=0x{:02x}).\n",
+			    options.shader_hash, bvh.pc, bvh.opcode_id));
+		}
+		return {.skip_dispatch = true};
+	}
+
 	std::string decoded_dump;
 	if (options.dump_ir) {
 		decoded_dump = Decoder::ProgramToString(decoded);
@@ -615,6 +630,7 @@ TranslateResult TranslateProgram(std::span<const uint32_t> code, const CompileOp
 CompileResult CompileProgram(TranslateResult translated, const CompileOptions& options,
                              const IR::ResourceSpecialization& specialization,
                              uint32_t push_data_start_dword) {
+	EXIT_IF(translated.skip_dispatch);
 	const auto emit_begin = std::chrono::steady_clock::now();
 	auto& ir = translated.program;
 	IR::ApplyResourceSpecialization(ir, specialization);

src/graphics/shader/recompiler/ShaderRecompiler.h

@@ -28,6 +28,7 @@ struct TranslateResult {
 	IR::Program program;
 	std::string decoded_dump;
 	std::string cfg_dump;
+	bool        skip_dispatch = false;
 };
 
 struct CompileResult {

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

@@ -227,6 +227,7 @@ Emitter::SpirvRequirements Emitter::AnalyzeProgramRequirements(const IR::Program
 					requirements.subgroup_local_invocation_id = true;
 				}
 				if (memory.kind == IR::ResourceKind::Buffer) {
+					requirements.coherent_buffers |= memory.coherent;
 					if (memory.resource >= program.info.buffers.size()) {
 						Fail(program, "buffer operation has invalid resource metadata");
 					}

src/graphics/shader/recompiler/backend/spirv/spirvEmitterInternal.h

@@ -67,6 +67,7 @@ struct SpirvRequirements {
 	bool function_scratch             = false;
 	bool pixel_valid_mask             = false;
 	bool buffer_int64_atomics         = false;
+	bool coherent_buffers             = false;
 };
 
 SpirvRequirements AnalyzeProgramRequirements(const IR::Program& program);
@@ -371,12 +372,13 @@ void EmitMemoryOffsets(EmitterState& state);
 uint32_t LdsDwordCount(const EmitterState& state);
 
 struct MemoryResourceAccess {
-	IR::ResourceKind kind             = IR::ResourceKind::None;
-	uint32_t         object_pointer   = 0;
-	uint32_t         length           = 0;
-	uint32_t         index_offset     = 0;
-	uint32_t         byte_offset      = 0;
-	bool             add_index_offset = false;
+	IR::ResourceKind      kind             = IR::ResourceKind::None;
+	uint32_t              object_pointer   = 0;
+	uint32_t              length           = 0;
+	uint32_t              index_offset     = 0;
+	uint32_t              byte_offset      = 0;
+	bool                  add_index_offset = false;
+	spv::MemoryAccessMask memory_access    = spv::MemoryAccessMaskNone;
 };
 
 MemoryResourceAccess PrepareMemoryResourceAccess(EmitterState& state, const IR::MemoryInfo& mem);

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

@@ -313,7 +313,8 @@ uint32_t LoadWordInBounds(ValueEmitContext& ctx, const MemoryResourceAccess& res
                           uint32_t index) {
 	const auto value   = ctx.state.builder.AllocateId();
 	const auto pointer = EmitMemoryElementPointer(ctx.state, resource, index);
-	ctx.state.builder.AddFunction(spv::OpLoad, TypeU32(ctx.state), value, pointer);
+	ctx.state.builder.AddFunction(spv::OpLoad, TypeU32(ctx.state), value, pointer,
+	                              resource.memory_access);
 	return value;
 }
 
@@ -498,21 +499,21 @@ void StoreSubword(ValueEmitContext& ctx, const IR::Inst& inst, IR::MemoryInfo me
 	});
 }
 
+void StoreWordInBounds(ValueEmitContext& ctx, const MemoryResourceAccess& resource, uint32_t index,
+                       uint32_t data) {
+	ctx.state.builder.AddFunction(spv::OpStore,
+	                              EmitMemoryElementPointer(ctx.state, resource, index), data,
+	                              resource.memory_access);
+}
+
 void StoreWordPrepared(ValueEmitContext& ctx, const IR::Inst& inst, const IR::MemoryInfo& mem,
                        const MemoryResourceAccess& resource, uint32_t data) {
 	const auto index = EmitMemoryElementIndex(ctx.state, resource, DwordIndex(ctx, inst, mem));
 	EmitIfCondition(ctx.state, EmitMemoryElementInBounds(ctx.state, resource, index), [&]() {
-		ctx.state.builder.AddFunction(spv::OpStore,
-		                              EmitMemoryElementPointer(ctx.state, resource, index), data);
+		StoreWordInBounds(ctx, resource, index, data);
 	});
 }
 
-void StoreWordInBounds(ValueEmitContext& ctx, const MemoryResourceAccess& resource, uint32_t index,
-                       uint32_t data) {
-	ctx.state.builder.AddFunction(spv::OpStore,
-	                              EmitMemoryElementPointer(ctx.state, resource, index), data);
-}
-
 void StoreWord(ValueEmitContext& ctx, const IR::Inst& inst, IR::MemoryInfo mem) {
 	EmitIfCondition(ctx.state, ctx.Arg(inst, inst.NumArgs() - 1), [&]() {
 		const auto resource = PrepareMemoryResourceAccess(ctx.state, mem);

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

@@ -86,7 +86,9 @@ MemoryResourceAccess PrepareStorageBufferResourceAccess(EmitterState& state,
 	}
 	const auto array_index =
 	    ResourceForDescriptor(state, IR::DescriptorBindingKind::Buffers, mem.resource);
-	MemoryResourceAccess access {.kind = mem.kind};
+	MemoryResourceAccess access {
+	    .kind = mem.kind,
+	    .memory_access = mem.coherent ? spv::MemoryAccessVolatileMask : spv::MemoryAccessMaskNone};
 	access.object_pointer = state.builder.AllocateId();
 	state.builder.AddFunction(spv::OpAccessChain, pointer_type, access.object_pointer, variable,
 	                          ConstantU32(state, array_index));

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

@@ -201,6 +201,16 @@ void DefineDescriptors(EmitterState& state) {
 					state.builder.AddAnnotation(spv::OpDecorate, state.storage_buffer_u64_variable,
 					                            spv::DecorationAliased);
 				}
+				if (state.requirements.coherent_buffers) {
+					// RDNA2 stores publish to L2 even without GLC; every alias of the buffer
+					// must participate in visibility for cache-bypassing polling loads.
+					state.builder.AddAnnotation(spv::OpDecorate, state.storage_buffer_variable,
+					                            spv::DecorationCoherent);
+					if (state.storage_buffer_u64_variable != 0) {
+						state.builder.AddAnnotation(spv::OpDecorate, state.storage_buffer_u64_variable,
+						                            spv::DecorationCoherent);
+					}
+				}
 				break;
 			case IR::DescriptorBindingKind::BdaPagetable:
 				state.bda_pagetable_variable = Define(StorageBufferU64Type(state), "bda_pagetable");

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

@@ -21,6 +21,7 @@ constexpr MemoryOpcodeInfo SMEM_OPCODE_LIST[] = {
     {0x04u, Opcode::S_LOAD_DWORDX16, 16, 32},      {0x08u, Opcode::S_BUFFER_LOAD_DWORD, 1, 32},
     {0x09u, Opcode::S_BUFFER_LOAD_DWORDX2, 2, 32}, {0x0au, Opcode::S_BUFFER_LOAD_DWORDX4, 4, 32},
     {0x0bu, Opcode::S_BUFFER_LOAD_DWORDX8, 8, 32}, {0x0cu, Opcode::S_BUFFER_LOAD_DWORDX16, 16, 32},
+    {0x25u, Opcode::S_MEMREALTIME, 2, 32},
 };
 
 constexpr MemoryOpcodeInfo MUBUF_OPCODE_LIST[] = {
@@ -245,6 +246,10 @@ void DecodeSmem(uint32_t pc, std::span<const uint32_t> code, uint32_t word_index
 	}
 
 	DecodeScalarDestination(sdst, pc, inst.dst);
+	if (inst.opcode == Opcode::S_MEMREALTIME) {
+		inst.src_count = 0;
+		return;
+	}
 	// SMEM encodes SBASE in SGPR pairs. Scalar-buffer loads still use the same
 	// pair index; their descriptor operand consumes four SGPRs from that base.
 	DecodeScalarSource(sbase * 2u, pc, inst.src0);
@@ -268,6 +273,7 @@ void DecodeMubuf(uint32_t pc, std::span<const uint32_t> code, uint32_t word_inde
 	inst.idxen       = ((word0 >> 13u) & 1u) != 0;
 	inst.offen       = ((word0 >> 12u) & 1u) != 0;
 	inst.glc         = ((word0 >> 14u) & 1u) != 0;
+	inst.dlc         = ((word0 >> 15u) & 1u) != 0;
 	inst.slc         = ((word1 >> 22u) & 1u) != 0;
 	inst.family      = Family::MUBUF;
 	inst.opcode_id   = opcode;
@@ -303,6 +309,7 @@ void DecodeMtbuf(uint32_t pc, std::span<const uint32_t> code, uint32_t word_inde
 	inst.idxen         = ((word0 >> 13u) & 1u) != 0;
 	inst.offen         = ((word0 >> 12u) & 1u) != 0;
 	inst.glc           = ((word0 >> 14u) & 1u) != 0;
+	inst.dlc           = ((word0 >> 15u) & 1u) != 0;
 	inst.slc           = ((word1 >> 22u) & 1u) != 0;
 	inst.family        = Family::MTBUF;
 	inst.opcode_id     = opcode;

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

@@ -73,11 +73,11 @@ std::string FormatMemory(const Instruction& inst) {
 		text += OperandToString(*sources[i]);
 	}
 	text += fmt::format(" ; offset={} offset2={} dwords={} bits={} dfmt={} nfmt={} signed={} "
-	                    "typed={} formatted={} segment={} glc={} slc={} idxen={} offen={}",
+	                    "typed={} formatted={} segment={} glc={} dlc={} slc={} idxen={} offen={}",
 	                    inst.offset, inst.secondary_offset, inst.data_dwords, inst.data_bits,
 	                    inst.data_format, inst.number_format, inst.data_signed ? 1u : 0u,
 	                    inst.typed ? 1u : 0u, inst.formatted ? 1u : 0u, inst.memory_segment,
-	                    inst.glc ? 1u : 0u, inst.slc ? 1u : 0u, inst.idxen ? 1u : 0u,
+	                    inst.glc ? 1u : 0u, inst.dlc ? 1u : 0u, inst.slc ? 1u : 0u, inst.idxen ? 1u : 0u,
 	                    inst.offen ? 1u : 0u);
 	return text;
 }
@@ -403,6 +403,7 @@ void DecodeProgram(std::span<const uint32_t> code, Program& program) {
 	program.instructions.clear();
 	program.instructions.reserve(code.size());
 	program.code = code;
+	program.has_bvh = false;
 
 	std::vector<bool> branch_targets;
 	for (uint32_t word_index = 0; word_index < code.size();) {
@@ -411,6 +412,10 @@ void DecodeProgram(std::span<const uint32_t> code, Program& program) {
 
 		const auto& inst = program.instructions.back();
 		word_index += inst.word_count;
+		if (inst.family == Family::MIMG && (inst.opcode_id == 0xe6u || inst.opcode_id == 0xe7u)) {
+			program.has_bvh = true;
+			return;
+		}
 
 		if (IsDirectBranch(inst.opcode)) {
 			const auto target_index = inst.branch_target / sizeof(uint32_t);

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

@@ -404,6 +404,7 @@ enum class Opcode {
 	V_CMP_LE_U16,
 	V_CMP_GT_U16,
 	V_CMPX_LT_U16,
+	V_CMPX_EQ_U16,
 	V_CMPX_GT_U16,
 	V_CMP_NE_U16,
 	V_CMP_GE_U16,
@@ -439,6 +440,7 @@ enum class Opcode {
 	S_BUFFER_LOAD_DWORDX4,
 	S_BUFFER_LOAD_DWORDX8,
 	S_BUFFER_LOAD_DWORDX16,
+	S_MEMREALTIME,
 	BUFFER_LOAD_FORMAT_X,
 	BUFFER_LOAD_FORMAT_XY,
 	BUFFER_LOAD_FORMAT_XYZ,
@@ -711,6 +713,7 @@ struct Instruction {
 	bool           formatted                                    = false;
 	bool           gds                                          = false;
 	bool           glc                                          = false;
+	bool           dlc                                          = false;
 	bool           slc                                          = false;
 	bool           idxen                                        = false;
 	bool           offen                                        = false;
@@ -729,6 +732,7 @@ struct Instruction {
 struct Program {
 	std::span<const uint32_t> code;
 	std::vector<Instruction>  instructions;
+	bool                     has_bvh = false;
 };
 
 // Code spans are trusted to contain complete instructions, valid branch targets, and 32-bit PCs.

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

@@ -40,7 +40,7 @@ constexpr Vop2OpcodeInfo VOP2_OPCODE_LIST[] = {
     {0x0fu, Opcode::V_MIN_F32},
     {0x10u, Opcode::V_MAX_F32},
     {0x11u, Opcode::V_MIN_I32},
-    {0x12u, Opcode::V_MAX_I32},
+    {0x12u, Opcode::V_MAX_I32, Vop2SdwaProfile::IntegerFullDestination},
     {0x13u, Opcode::V_MIN_U32, Vop2SdwaProfile::IntegerPartialDestination},
     {0x14u, Opcode::V_MAX_U32, Vop2SdwaProfile::IntegerFullDestination},
     {0x15u, Opcode::V_LSHR_B32},
@@ -231,7 +231,7 @@ constexpr VopcOpcodeInfo VOPC_OPCODE_LIST[] = {
     {0xa9u, Opcode::V_CMP_LT_U16},         {0xaau, Opcode::V_CMP_EQ_U16},
     {0xabu, Opcode::V_CMP_LE_U16},         {0xacu, Opcode::V_CMP_GT_U16},
     {0xadu, Opcode::V_CMP_NE_U16},         {0xaeu, Opcode::V_CMP_GE_U16},
-    {0xb9u, Opcode::V_CMPX_LT_U16, false},
+    {0xb9u, Opcode::V_CMPX_LT_U16, false}, {0xbau, Opcode::V_CMPX_EQ_U16, false},
     {0xbcu, Opcode::V_CMPX_GT_U16},        {0xc0u, Opcode::V_CMP_F_U32},
     {0xc1u, Opcode::V_CMP_LT_U32},         {0xc2u, Opcode::V_CMP_EQ_U32},
     {0xc3u, Opcode::V_CMP_LE_U32},         {0xc4u, Opcode::V_CMP_GT_U32},
@@ -1454,6 +1454,7 @@ bool IsVopcCompareExec(Opcode opcode) {
 		case Opcode::V_CMPX_NE_I64:
 		case Opcode::V_CMPX_NE_U64:
 		case Opcode::V_CMPX_LT_U16:
+		case Opcode::V_CMPX_EQ_U16:
 		case Opcode::V_CMPX_GT_U16:
 		case Opcode::V_CMPX_LT_F16:
 		case Opcode::V_CMPX_EQ_F16:

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

@@ -1,8 +1,10 @@
+#include "common/logging/log.h"
 #include "graphics/shader/recompiler/frontend/translate/Translator.h"
 #include "graphics/shader/recompiler/frontend/decode/ImageOps.h"
 
 #include <algorithm>
 #include <array>
+#include <atomic>
 
 namespace Libs::Graphics::ShaderRecompiler::Frontend {
 
@@ -123,6 +125,11 @@ IR::MemoryInfo MemoryInfoFromDecoded(const Decoder::Instruction& decoded) {
 	memory.image_r128    = decoded.image_r128;
 	memory.idxen         = decoded.idxen;
 	memory.offen         = decoded.offen;
+	// Vector loads use GLC/DLC to bypass L0/GL1; atomics use GLC only to return data.
+	const bool buffer_atomic = decoded.opcode >= Decoder::Opcode::BUFFER_ATOMIC_SWAP &&
+	                           decoded.opcode <= Decoder::Opcode::BUFFER_ATOMIC_FMAX;
+	memory.coherent = memory.kind == ResourceKind::Buffer && !buffer_atomic &&
+	                  (decoded.glc || decoded.dlc);
 	memory.resource      = ResourceIndexFromOperand(decoded.src1);
 	memory.sampler       = ResourceIndexFromOperand(decoded.src2);
 	if (memory.kind == ResourceKind::ScalarBuffer) {
@@ -891,6 +898,17 @@ bool Translator::EmitMemory(const Decoder::Instruction& inst) {
 		case Decoder::Opcode::S_BUFFER_LOAD_DWORDX4:
 		case Decoder::Opcode::S_BUFFER_LOAD_DWORDX8:
 		case Decoder::Opcode::S_BUFFER_LOAD_DWORDX16: return S_LOAD(inst, false);
+		case Decoder::Opcode::S_MEMREALTIME: {
+			static std::atomic_flag warned = ATOMIC_FLAG_INIT;
+			if (!warned.test_and_set(std::memory_order_relaxed)) {
+				Log::WriteToConsoleAndLog(
+				    "Warning: S_MEMREALTIME uses placeholder UINT64_MAX; real-time clock not implemented.\n");
+			}
+			for (uint32_t component = 0; component < 2; component++) {
+				WriteOperand(ScalarDestinationOperand(inst.dst, component), IR::Value(UINT32_MAX));
+			}
+			return true;
+		}
 
 		case Decoder::Opcode::BUFFER_LOAD_UBYTE:
 		case Decoder::Opcode::BUFFER_LOAD_SBYTE:

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

@@ -141,6 +141,9 @@ bool Translator::EmitVector(const Decoder::Instruction& inst) {
 		case O::V_CMPX_LT_U16:
 			EmitInteger16Compare(inst, IR::ValueOpcode::ULessThan32, false, true);
 			return true;
+		case O::V_CMPX_EQ_U16:
+			EmitInteger16Compare(inst, IR::ValueOpcode::IEqual32, false, true);
+			return true;
 		case O::V_CMP_LE_U16:
 			EmitInteger16Compare(inst, IR::ValueOpcode::ULessThanEqual32, false, false);
 			return true;

src/graphics/shader/recompiler/ir/Program.cpp

@@ -454,10 +454,8 @@ void ValidateProgram(const Program& program, bool require_ssa) {
 					                        ValueOpcodeName(inst.GetOpcode())));
 				}
 				if (memory.kind == ResourceKind::IndirectBuffer &&
-				    (memory.formatted || memory.typed ||
-				     (inst.GetOpcode() != ValueOpcode::LoadBufferU32x2 &&
-				      inst.GetOpcode() != ValueOpcode::LoadBufferU32x4))) {
-					return Fail("indirect buffer requires a raw DWORD x2/x4 load");
+				    !memory.SupportsIndirectBufferLoad(inst.GetOpcode())) {
+					return Fail("indirect buffer requires a raw DWORD x2/x3/x4 load");
 				}
 				if (buffer_components > 1u &&
 				    (!vector_buffer || memory.data_bits != 32u ||

src/graphics/shader/recompiler/ir/ShaderIR.h

@@ -67,8 +67,15 @@ struct MemoryInfo {
 	bool                    image_r128                                            = false;
 	bool                    idxen                                                 = false;
 	bool                    offen                                                 = false;
+	bool                    coherent                                              = false;
 	bool                    planning_only                                         = false;
 
+	[[nodiscard]] bool SupportsIndirectBufferLoad(ValueOpcode opcode) const {
+		return !formatted && !typed && data_bits == 32u &&
+		       (opcode == ValueOpcode::LoadBufferU32x2 || opcode == ValueOpcode::LoadBufferU32x3 ||
+		        opcode == ValueOpcode::LoadBufferU32x4);
+	}
+
 	bool operator==(const MemoryInfo& other) const = default;
 };
 

src/graphics/shader/recompiler/ir/passes/ResourceTracking.cpp

@@ -1206,11 +1206,10 @@ private:
 		if (buffer != BufferAccess::None) {
 			if (!GetHandle(inst.Arg(0), ValueOpcode::GetBufferResource, 4, flags.pc, handle,
 			               source)) {
-				if (memory.kind != ResourceKind::Buffer || memory.formatted || memory.typed ||
-				    (op != ValueOpcode::LoadBufferU32x2 && op != ValueOpcode::LoadBufferU32x4)) {
+				if (memory.kind != ResourceKind::Buffer || !memory.SupportsIndirectBufferLoad(op)) {
 					Fail(flags.pc,
 					     "buffer descriptor is not a valid runtime value; GPU-selected access "
-					     "requires a raw DWORD x2/x4 load");
+					     "requires a raw DWORD x2/x3/x4 load");
 				}
 				m_program.memory_info[flags.index].kind = ResourceKind::IndirectBuffer;
 				m_info.uses_dma                         = true;

src/graphics/shader/shader.cpp

@@ -388,6 +388,8 @@ static void ShaderApplyAttribSemantics(ShaderVertexInputInfo& info,
 
 	EXIT_IF(attrib == nullptr || buffer == nullptr);
 
+	const bool debug_dump = Config::GraphicsDebugDumpEnabled();
+
 	for (uint32_t i = 0; i < num_input_semantics; i++) {
 		const auto& in = input_semantics[i];
 
@@ -396,7 +398,7 @@ static void ShaderApplyAttribSemantics(ShaderVertexInputInfo& info,
 		uint32_t reg  = in.hardware_mapping;
 		uint32_t size = in.size_in_elements;
 
-		if (Config::GraphicsDebugDumpEnabled()) {
+		if (debug_dump) {
 			LOGF("reg = %u, size = %u, va[%u] = 0x%08" PRIx32 "\n", reg, size, i,
 			     attrib[in.semantic]);
 		}

src/libs/agc.cpp

@@ -2110,7 +2110,7 @@ uint32_t KYTY_SYSV_ABI AgcCbQueueEndOfPipeActionGetSize() {
 uint32_t* KYTY_SYSV_ABI AgcAcbResetQueue(CommandBuffer* buf, uint32_t op) {
 	PRINT_NAME();
 
-	LOGF("\t op    = 0x%08" PRIx32 "\n", op);
+	AgcTrace("\t op    = 0x%08" PRIx32 "\n", op);
 
 	EXIT_NOT_IMPLEMENTED(buf == nullptr);
 	EXIT_NOT_IMPLEMENTED((op & ~0x1c2u) != 0);
@@ -2130,9 +2130,9 @@ uint32_t* KYTY_SYSV_ABI AgcAcbResetQueue(CommandBuffer* buf, uint32_t op) {
 uint32_t* KYTY_SYSV_ABI AgcDcbResetQueue(CommandBuffer* buf, uint32_t op, uint32_t state) {
 	PRINT_NAME();
 
-	LOGF("\t op    = 0x%08" PRIx32 "\n"
-	     "\t state = 0x%08" PRIx32 "\n",
-	     op, state);
+	AgcTrace("\t op    = 0x%08" PRIx32 "\n"
+	         "\t state = 0x%08" PRIx32 "\n",
+	         op, state);
 
 	EXIT_NOT_IMPLEMENTED(buf == nullptr);
 	EXIT_NOT_IMPLEMENTED((op & ~0xfffu) != 0);
@@ -2749,9 +2749,9 @@ uint32_t* KYTY_SYSV_ABI AgcDcbSetBaseIndirectArgs(CommandBuffer* buf, uint32_t s
                                                   const volatile void* indirect_base_addr) {
 	PRINT_NAME();
 
-	LOGF("\t shader_type        = %" PRIu32 "\n"
-	     "\t indirect_base_addr = 0x%016" PRIx64 "\n",
-	     shader_type, reinterpret_cast<uint64_t>(indirect_base_addr));
+	AgcTrace("\t shader_type        = %" PRIu32 "\n"
+	         "\t indirect_base_addr = 0x%016" PRIx64 "\n",
+	         shader_type, reinterpret_cast<uint64_t>(indirect_base_addr));
 
 	EXIT_NOT_IMPLEMENTED(buf == nullptr);
 
@@ -2941,9 +2941,9 @@ uint32_t* KYTY_SYSV_ABI AgcDcbDispatchIndirect(CommandBuffer* buf, uint32_t data
                                                uint32_t flags) {
 	PRINT_NAME();
 
-	LOGF("\t data_offset = 0x%" PRIx32 "\n"
-	     "\t flags       = 0x%08" PRIx32 "\n",
-	     data_offset_in_bytes, flags);
+	AgcTrace("\t data_offset = 0x%" PRIx32 "\n"
+	         "\t flags       = 0x%08" PRIx32 "\n",
+	         data_offset_in_bytes, flags);
 
 	EXIT_NOT_IMPLEMENTED(buf == nullptr);
 
@@ -3294,9 +3294,9 @@ uint32_t* KYTY_SYSV_ABI AgcAcbDispatchIndirect(CommandBuffer*       buf,
                                                uint32_t             modifier) {
 	PRINT_NAME();
 
-	LOGF("\t indirect_args = 0x%016" PRIx64 "\n"
-	     "\t modifier      = 0x%08" PRIx32 "\n",
-	     reinterpret_cast<uint64_t>(indirect_args), modifier);
+	AgcTrace("\t indirect_args = 0x%016" PRIx64 "\n"
+	         "\t modifier      = 0x%08" PRIx32 "\n",
+	         reinterpret_cast<uint64_t>(indirect_args), modifier);
 
 	if (buf == nullptr) {
 		return nullptr;
@@ -3724,9 +3724,9 @@ int KYTY_SYSV_ABI AgcCondExecPatchSetCommandAddress(uint32_t*                cmd
                                                     const volatile uint32_t* command) {
 	PRINT_NAME();
 
-	LOGF("\t cmd     = 0x%016" PRIx64 "\n"
-	     "\t command = 0x%016" PRIx64 "\n",
-	     reinterpret_cast<uint64_t>(cmd), reinterpret_cast<uint64_t>(command));
+	AgcTrace("\t cmd     = 0x%016" PRIx64 "\n"
+	         "\t command = 0x%016" PRIx64 "\n",
+	         reinterpret_cast<uint64_t>(cmd), reinterpret_cast<uint64_t>(command));
 
 	if (cmd == nullptr || command == nullptr) {
 		return GRAPHICS5_ERROR_INVALID_PACKET;
@@ -3868,9 +3868,9 @@ static uint32_t* get_agc_wait_packet(uint32_t* cmd) {
 int KYTY_SYSV_ABI AgcWaitRegMemPatchAddress(uint32_t* cmd, const volatile void* address) {
 	PRINT_NAME();
 
-	LOGF("\t cmd     = 0x%016" PRIx64 "\n"
-	     "\t address = 0x%016" PRIx64 "\n",
-	     reinterpret_cast<uint64_t>(cmd), reinterpret_cast<uint64_t>(address));
+	AgcTrace("\t cmd     = 0x%016" PRIx64 "\n"
+	         "\t address = 0x%016" PRIx64 "\n",
+	         reinterpret_cast<uint64_t>(cmd), reinterpret_cast<uint64_t>(address));
 
 	auto* wait = get_agc_wait_packet(cmd);
 	if (wait == nullptr) {
@@ -3913,9 +3913,9 @@ int KYTY_SYSV_ABI AgcQueueEndOfPipeActionPatchAddress(uint32_t*             cmd,
 
 	// Not sure
 
-	LOGF("\t cmd     = 0x%016" PRIx64 "\n"
-	     "\t address = 0x%016" PRIx64 "\n",
-	     reinterpret_cast<uint64_t>(cmd), reinterpret_cast<uint64_t>(address));
+	AgcTrace("\t cmd     = 0x%016" PRIx64 "\n"
+	         "\t address = 0x%016" PRIx64 "\n",
+	         reinterpret_cast<uint64_t>(cmd), reinterpret_cast<uint64_t>(address));
 
 	EXIT_NOT_IMPLEMENTED(cmd == nullptr);
 
@@ -4246,7 +4246,7 @@ static void submit_acb(uint32_t queue, uint32_t* acb, uint32_t size_in_dwords) {
 	}
 
 	for (uint32_t i = 0; i < std::min<uint32_t>(size_in_dwords, 8); i++) {
-		LOGF("\t acb[%u] = 0x%08" PRIx32 "\n", i, acb[i]);
+		AgcTrace("\t acb[%u] = 0x%08" PRIx32 "\n", i, acb[i]);
 	}
 
 	GraphicsDbgDumpDcb("a", size_in_dwords, acb);
@@ -4322,17 +4322,17 @@ int KYTY_SYSV_ABI AgcDriverSubmitMultiCommandBuffers(void*            queue_cont
 int KYTY_SYSV_ABI AgcDriverSubmitAcb(uint32_t queue, const Packet* packet) {
 	PRINT_NAME();
 
-	LOGF("\t queue  = 0x%08" PRIx32 "\n"
-	     "\t packet = 0x%016" PRIx64 "\n",
-	     queue, reinterpret_cast<uint64_t>(packet));
+	AgcTrace("\t queue  = 0x%08" PRIx32 "\n"
+	         "\t packet = 0x%016" PRIx64 "\n",
+	         queue, reinterpret_cast<uint64_t>(packet));
 
 	if (packet == nullptr) {
 		return OK;
 	}
-	LOGF("\t acb   = 0x%016" PRIx64 "\n"
-	     "\t size  = 0x%08" PRIx32 "\n"
-	     "\t flags = 0x%02" PRIx8 "\n",
-	     reinterpret_cast<uint64_t>(packet->addr), packet->dw_num, packet->flags);
+	AgcTrace("\t acb   = 0x%016" PRIx64 "\n"
+	         "\t size  = 0x%08" PRIx32 "\n"
+	         "\t flags = 0x%02" PRIx8 "\n",
+	         reinterpret_cast<uint64_t>(packet->addr), packet->dw_num, packet->flags);
 
 	submit_acb(queue, packet->addr, packet->dw_num);
 	return OK;

src/libs/ajm.cpp

@@ -682,16 +682,9 @@ static AjmDecodeResult AjmControlInstance(uint32_t instance, uint64_t flags,
 
 static AjmDecodeResult AjmSetGaplessDecode(uint32_t instance, const void* gapless_decode,
                                            int reset) {
-	std::scoped_lock lock(g_ajm_instances_mutex);
-	auto*            state = AjmFindInstanceLocked(instance);
-	if (state == nullptr || state->decoder == nullptr || gapless_decode == nullptr) {
-		AjmDecodeResult result {};
-		result.result = AJM_RESULT_INVALID_PARAMETER;
-		return result;
-	}
-
-	state->gapless.Set(*static_cast<const AjmSidebandGaplessDecode*>(gapless_decode), reset != 0);
-	return state->decoder->MakeResult();
+	const auto flags = AJM_FLAG_SIDEBAND_GAPLESS | (reset != 0 ? AJM_FLAG_CONTROL_RESET : 0);
+	return AjmControlInstance(instance, flags, gapless_decode, sizeof(AjmSidebandGaplessDecode),
+	                          nullptr, nullptr);
 }
 
 static AjmDecodeResult AjmGetGaplessDecode(uint32_t                  instance,
@@ -930,18 +923,8 @@ int KYTY_SYSV_ABI AjmBatchJobClearContext(AjmBatchInfo* info, uint32_t instance,
 	PRINT_NAME();
 	EXIT_NOT_IMPLEMENTED(info == nullptr);
 
-	AjmDecodeResult decode_result {};
-	{
-		std::scoped_lock lock(g_ajm_instances_mutex);
-		auto*            state = AjmFindInstanceLocked(instance);
-		if (state != nullptr && state->decoder != nullptr) {
-			state->gapless.Reset();
-			state->decoder->Reset();
-			decode_result = state->decoder->MakeResult();
-		} else {
-			decode_result.result = AJM_RESULT_INVALID_PARAMETER;
-		}
-	}
+	const auto decode_result =
+	    AjmControlInstance(instance, AJM_FLAG_CONTROL_RESET, nullptr, 0, nullptr, nullptr);
 
 	AjmWriteResult(result, AJM_SIDEBAND_RESULT_SIZE, decode_result);
 	LOGF("\t instance = 0x%08" PRIx32 "\n", instance);

src/libs/libVideoOut.cpp

@@ -1,5 +1,6 @@
 #include "common/abi.h"
 #include "graphics/presentation/videoOut.h"
+#include "libs/errno.h"
 #include "libs/libs.h"
 #include "loader/symbolDatabase.h"
 
@@ -51,8 +52,14 @@ namespace LibGen5::VrrStatus {
 
 LIB_VERSION("VideoOutVrrStatus", 1, "VideoOut", 1, 1);
 
+static KYTY_SYSV_ABI int VideoOutVrrStatus_kP2L8t3j_aM() {
+	// The observed guest call passes no arguments.
+	// Return success for Kyty's fixed-refresh path.
+	return OK;
+}
+
 LIB_DEFINE(InitVideoOutVrrStatus_1) {
-	LIB_FUNC("kP2L8t3j-aM", VideoOut::VideoOutGetVrrStatus);
+	LIB_FUNC("kP2L8t3j-aM", VideoOutVrrStatus_kP2L8t3j_aM);
 }
 
 } // namespace LibGen5::VrrStatus

src/libs/libs.h

@@ -7,6 +7,8 @@
 #include "common/threads.h"
 #include "loader/timer.h" // IWYU pragma: keep
 
+#include <fmt/format.h>
+
 // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
 #define PRINT_NAME_ENABLED g_print_name
 
@@ -49,12 +51,7 @@
 // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
 #define PRINT_NAME()                                                                               \
 	if (PRINT_NAME_ENABLED) {                                                                      \
-		if (Log::GetDirection() != Log::Direction::Silent) {                                       \
-			const auto print_name_time = Loader::Timer::GetTime().ToString("HH24:MI:SS.FFF");      \
-			LOGF_COLOR(Log::Color::Cyan, "[%d][%s] %s::%s::%s()\n",                                \
-			           Common::Thread::GetThreadIdUnique(), print_name_time.c_str(), g_library,    \
-			           g_module, __func__);                                                        \
-		}                                                                                          \
+		Libs::PrintName(g_library, g_module, __func__);                                              \
 	}
 
 namespace Loader {
@@ -63,6 +60,19 @@ class SymbolDatabase;
 
 namespace Libs {
 
+// Keep the formatting path from inflating fiber functions' stack frames under LTO.
+[[gnu::noinline]] inline void PrintName(const char* library, const char* module, const char* function) {
+	if (Log::GetDirection() != Log::Direction::Silent) {
+		const auto elapsed_ms      = static_cast<uint64_t>(Loader::Timer::GetTimeMs());
+		const auto print_name_time = fmt::format(
+		    "{:02}:{:02}:{:02}.{:03}", elapsed_ms / 3600000, (elapsed_ms / 60000) % 60,
+		    (elapsed_ms / 1000) % 60, elapsed_ms % 1000);
+		LOGF_COLOR(Log::Color::Cyan, "[%d][%s] %s::%s::%s()\n",
+		           Common::Thread::GetThreadIdUnique(), print_name_time.c_str(), library, module,
+		           function);
+	}
+}
+
 void InitAll(Loader::SymbolDatabase* s);
 
 } // namespace Libs

src/libs/ngs2.cpp

@@ -10,6 +10,7 @@
 #include <algorithm>
 #include <array>
 #include <atomic>
+#include <cmath>
 #include <cstring>
 #include <deque>
 #include <limits>
@@ -428,11 +429,19 @@ struct Ngs2VoiceInternal {
 	std::unique_ptr<Ajm::AjmAt9Decoder> decoder;
 	std::vector<float>                 decoded_frame;
 	bool                               accepts_blocks = true;
+	uint32_t                           sample_rate    = 0;
+	uint64_t                           sample_phase   = 0;
+	uint64_t                           sample_step    = 0;
 
 	void SetupSampler(const Ngs2WaveformFormat& format) {
-		EXIT_NOT_IMPLEMENTED(format.sample_rate != rack->ngs->option.sample_rate ||
-		                     format.frame_margin != 0 || format.frame_offset != 0);
+		EXIT_NOT_IMPLEMENTED(format.frame_margin != 0 || format.frame_offset != 0 ||
+		                     format.sample_rate == 0 ||
+		                     (format.waveform_type == NGS2_WAVEFORM_TYPE_ATRAC9 &&
+		                      format.sample_rate != rack->ngs->option.sample_rate));
 		channels = format.num_channels;
+		sample_rate = format.sample_rate;
+		sample_phase = 0;
+		sample_step = uint64_t(sample_rate) << 32u;
 		blocks.clear();
 		decoder.reset();
 		decoded_frame.clear();
@@ -563,6 +572,16 @@ struct Ngs2SamplerVoiceState {
 	const void*    waveform_data;
 };
 
+struct Ngs2CustomSamplerVoiceState {
+	Ngs2VoiceState voice_state;
+	const void*    waveform_data;
+	uint64_t       num_decoded_samples;
+	uint64_t       decoded_data_size;
+	uint64_t       user_data;
+	uint32_t       reserved;
+	uint32_t       reserved2;
+};
+
 static Ngs2Internal*        g_ngs_list     = nullptr;
 static Ngs2RackInternal*    g_racks_list   = nullptr;
 static std::atomic_uint32_t g_next_ngs_uid = 1;
@@ -578,6 +597,7 @@ static_assert(sizeof(Ngs2VoiceState) == 8);
 static_assert(sizeof(Ngs2SubmixerVoiceState) == 20);
 static_assert(sizeof(Ngs2CustomMasteringVoiceState) == 16);
 static_assert(sizeof(Ngs2SamplerVoiceState) == 56);
+static_assert(sizeof(Ngs2CustomSamplerVoiceState) == 48);
 static_assert(sizeof(Ngs2WaveformFormat) == 24);
 static_assert(sizeof(Ngs2WaveformBlock) == 40);
 static_assert(sizeof(Ngs2WaveformInfo) == 232);
@@ -1244,76 +1264,118 @@ static void Ngs2ApplyEvent(Ngs2VoiceInternal& voice) {
 	voice.event = Ngs2VoicePlayEvent::None;
 }
 
+static void Ngs2FinishBlock(Ngs2VoiceInternal& voice) {
+	const auto& block = voice.blocks.front();
+	struct CallbackInfo {
+		uintptr_t   data, voice;
+		uint32_t    flag, reserved;
+		uintptr_t   user;
+		const void* block_data;
+		size_t      size;
+		uint32_t    repeats, attributes;
+	} info {voice.callback_data,
+	        reinterpret_cast<uintptr_t>(&voice),
+	        1,
+	        0,
+	        block.info.user_data,
+	        block.data,
+	        block.info.data_size,
+	        0,
+	        0};
+	static_assert(sizeof(CallbackInfo) == 56);
+	voice.blocks.pop_front();
+	if (voice.blocks.empty() && !voice.accepts_blocks) {
+		voice.state = Ngs2VoicePlayState::Empty;
+	}
+	if (voice.callback != 0 && (voice.callback_flags & 1u) != 0) {
+		reinterpret_cast<void KYTY_SYSV_ABI (*)(const CallbackInfo*)>(voice.callback)(&info);
+	}
+}
+
+static void Ngs2AdvancePcm(Ngs2VoiceInternal& voice) {
+	const auto output_rate = uint64_t(voice.rack->ngs->option.sample_rate) << 32u;
+	while (!voice.blocks.empty() && voice.sample_phase >= output_rate) {
+		auto&      block     = voice.blocks.front();
+		const auto available = block.info.num_samples - block.cursor;
+		const auto advance   = std::min(voice.sample_phase / output_rate,
+		                                uint64_t(available));
+		block.cursor += static_cast<uint32_t>(advance);
+		voice.sample_phase -= advance * output_rate;
+		if (block.cursor == block.info.num_samples) {
+			Ngs2FinishBlock(voice);
+		}
+	}
+}
+
 static void Ngs2ConsumeSamples(Ngs2VoiceInternal& voice, uint32_t grain) {
 	uint32_t output = 0;
 	while (output < grain && !voice.blocks.empty()) {
+		if (voice.decoder == nullptr) {
+			Ngs2AdvancePcm(voice);
+			if (voice.blocks.empty()) {
+				break;
+			}
+			const auto& block = voice.blocks.front();
+			const auto* pcm = reinterpret_cast<const int16_t*>(block.data) +
+			                  (block.info.num_skip_samples + block.cursor) * voice.channels;
+			const auto* next = pcm;
+			if (block.cursor + 1 < block.info.num_samples) {
+				next += voice.channels;
+			} else if (voice.blocks.size() > 1) {
+				const auto& next_block = voice.blocks[1];
+				next = reinterpret_cast<const int16_t*>(next_block.data) +
+				       next_block.info.num_skip_samples * voice.channels;
+			}
+			const float fraction = static_cast<float>(voice.sample_phase) /
+			                       static_cast<float>(uint64_t(voice.rack->ngs->option.sample_rate)
+			                                          << 32u);
+			for (uint32_t c = 0; c < voice.channels; ++c) {
+				voice.samples[c * grain + output] =
+				    (static_cast<float>(pcm[c]) +
+				     (static_cast<float>(next[c]) - pcm[c]) * fraction) /
+				    32768.0f;
+			}
+			voice.sample_phase += voice.sample_step;
+			++output;
+			continue;
+		}
 		auto&          block   = voice.blocks.front();
 		auto           count   = std::min(grain - output, block.info.num_samples - block.cursor);
-		const int16_t* pcm     = nullptr;
-		const float*   decoded = nullptr;
-		if (voice.decoder != nullptr) {
-			const auto skip =
-			    std::min(block.skip_remaining,
-			             static_cast<uint32_t>(voice.decoded_frame.size() / voice.channels));
-			Ajm::AjmGaplessState gapless;
-			gapless.Set({block.info.num_samples - block.cursor, static_cast<uint16_t>(skip), 0},
-			            true);
-			const auto result = voice.decoder->Decode(
-			    block.data + block.data_cursor, block.info.data_size - block.data_cursor,
-			    voice.decoded_frame.data(), voice.decoded_frame.size() * sizeof(float), false,
-			    &gapless);
-			EXIT_NOT_IMPLEMENTED(result.result != OK || result.input_consumed == 0);
-			block.data_cursor += result.input_consumed;
-			block.skip_remaining -= skip - gapless.current.skip_samples;
-			const auto decoded_samples =
-			    static_cast<uint32_t>(result.output_written / (sizeof(float) * voice.channels));
-			if (decoded_samples == 0) {
-				continue;
-			}
-			EXIT_NOT_IMPLEMENTED(decoded_samples > count);
-			count   = decoded_samples;
-			decoded = voice.decoded_frame.data();
-		} else {
-			pcm = reinterpret_cast<const int16_t*>(block.data) +
-			      (block.info.num_skip_samples + block.cursor) * voice.channels;
+		const auto skip =
+		    std::min(block.skip_remaining,
+		             static_cast<uint32_t>(voice.decoded_frame.size() / voice.channels));
+		Ajm::AjmGaplessState gapless;
+		gapless.Set({block.info.num_samples - block.cursor, static_cast<uint16_t>(skip), 0},
+		            true);
+		const auto result = voice.decoder->Decode(
+		    block.data + block.data_cursor, block.info.data_size - block.data_cursor,
+		    voice.decoded_frame.data(), voice.decoded_frame.size() * sizeof(float), false,
+		    &gapless);
+		EXIT_NOT_IMPLEMENTED(result.result != OK || result.input_consumed == 0);
+		block.data_cursor += result.input_consumed;
+		block.skip_remaining -= skip - gapless.current.skip_samples;
+		const auto decoded_samples =
+		    static_cast<uint32_t>(result.output_written / (sizeof(float) * voice.channels));
+		if (decoded_samples == 0) {
+			continue;
 		}
+		EXIT_NOT_IMPLEMENTED(decoded_samples > count);
+		count = decoded_samples;
 		for (uint32_t c = 0; c < voice.channels; ++c) {
 			for (uint32_t i = 0; i < count; ++i) {
 				const auto index = i * voice.channels + c;
-				voice.samples[c * grain + output + i] =
-				    decoded != nullptr ? decoded[index] : pcm[index] / 32768.0f;
+				voice.samples[c * grain + output + i] = voice.decoded_frame[index];
 			}
 		}
 		output += count;
 		block.cursor += count;
 		if (block.cursor == block.info.num_samples) {
-			struct CallbackInfo {
-				uintptr_t   data, voice;
-				uint32_t    flag, reserved;
-				uintptr_t   user;
-				const void* block_data;
-				size_t      size;
-				uint32_t    repeats, attributes;
-			} info {voice.callback_data,
-			        reinterpret_cast<uintptr_t>(&voice),
-			        1,
-			        0,
-			        block.info.user_data,
-			        block.data,
-			        block.info.data_size,
-			        0,
-			        0};
-			static_assert(sizeof(CallbackInfo) == 56);
-			voice.blocks.pop_front();
-			if (voice.blocks.empty() && !voice.accepts_blocks) {
-				voice.state = Ngs2VoicePlayState::Empty;
-			}
-			if (voice.callback != 0 && (voice.callback_flags & 1u) != 0) {
-				reinterpret_cast<void KYTY_SYSV_ABI (*)(const CallbackInfo*)>(voice.callback)(
-				    &info);
-			}
+			Ngs2FinishBlock(voice);
 		}
 	}
+	if (voice.decoder == nullptr) {
+		Ngs2AdvancePcm(voice);
+	}
 	voice.has_samples = output != 0;
 }
 
@@ -1925,7 +1987,12 @@ int KYTY_SYSV_ABI Ngs2VoiceControl(uintptr_t voice_handle, const Ngs2VoiceParamH
 						};
 						const auto& blocks = *reinterpret_cast<const BlocksParam*>(param);
 						EXIT_NOT_IMPLEMENTED(!voice->accepts_blocks ||
-						                     (blocks.flags != 0 && blocks.flags != 0x11));
+						                     (blocks.flags != 0 && blocks.flags != 0x11 &&
+						                      blocks.flags != 0x4));
+						if (blocks.flags == 0x4) {
+							voice->blocks.clear();
+							voice->sample_phase = 0;
+						}
 						voice->accepts_blocks = (blocks.flags & 1u) != 0;
 						for (uint32_t i = 0; i < blocks.count; ++i) {
 							const auto& block = blocks.blocks[i];
@@ -1939,9 +2006,14 @@ int KYTY_SYSV_ABI Ngs2VoiceControl(uintptr_t voice_handle, const Ngs2VoiceParamH
 						}
 						break;
 					}
-					case 5:
-						EXIT_NOT_IMPLEMENTED(*reinterpret_cast<const float*>(param + 1) != 1.0f);
+					case 5: {
+						const float ratio = *reinterpret_cast<const float*>(param + 1);
+						EXIT_NOT_IMPLEMENTED(!std::isfinite(ratio) || ratio < 0.0f || ratio > 4.0f ||
+						                     (voice->decoder != nullptr && ratio != 1.0f));
+						voice->sample_step = static_cast<uint64_t>(std::llround(
+						    static_cast<double>(voice->sample_rate) * ratio * 4294967296.0));
 						break;
+					}
 					default: EXIT("unsupported sampler control: 0x%08" PRIx32 "\n", param->id);
 				}
 				break;
@@ -2041,8 +2113,17 @@ int KYTY_SYSV_ABI Ngs2VoiceGetState(uintptr_t voice_handle, Ngs2VoiceState* stat
 			mastering->voice_state.state_flags = Ngs2GetStateFlags(voice);
 			break;
 		}
-		case Ngs2RackType::Sampler:
 		case Ngs2RackType::CustomSampler: {
+			const auto configured_size =
+			    voice->rack->option.custom_sampler.custom_rack_option.state_size;
+			EXIT_NOT_IMPLEMENTED(configured_size < sizeof(Ngs2CustomSamplerVoiceState));
+			EXIT_NOT_IMPLEMENTED(state_size != configured_size);
+			std::memset(state, 0, state_size);
+			auto* sampler = reinterpret_cast<Ngs2CustomSamplerVoiceState*>(state);
+			sampler->voice_state.state_flags = Ngs2GetStateFlags(voice);
+			break;
+		}
+		case Ngs2RackType::Sampler: {
 			if (state_size != sizeof(Ngs2SamplerVoiceState)) {
 				LOGF("\t warning: sampler state_size = 0x%016" PRIx64 ", expected 0x%016" PRIx64
 				     "\n",

src/loader/timer.cpp

@@ -1,7 +1,5 @@
 #include "common/timer.h"
 
-#include "common/abi.h"
-#include "common/dateTime.h"
 #include "loader/timer.h"
 
 namespace Loader::Timer {
@@ -16,8 +14,4 @@ double GetTimeMs() {
 	return g_timer.GetTimeMs();
 }
 
-Common::Time GetTime() {
-	return Common::Time(static_cast<int>(GetTimeMs()));
-}
-
 } // namespace Loader::Timer

src/loader/timer.h

@@ -1,14 +1,10 @@
 #ifndef EMULATOR_INCLUDE_EMULATOR_LOADER_TIMER_H_
 #define EMULATOR_INCLUDE_EMULATOR_LOADER_TIMER_H_
 
-#include "common/abi.h"
-#include "common/common.h"
-#include "common/dateTime.h"
 namespace Loader::Timer {
 
-void         Start();
-double       GetTimeMs();
-Common::Time GetTime();
+void   Start();
+double GetTimeMs();
 
 struct Lifecycle {
 	static constexpr const char* name       = "Timer";

tests/SaveDataMemoryTests.cpp

@@ -27,8 +27,8 @@ bool SystemContentParamSfoGetString(const char*, std::string* value) {
 }
 void SymbolDatabase::Add(const SymbolResolve&, uint64_t, const std::string&) {}
 namespace Timer {
-Common::Time GetTime() {
-	return Common::Time(0);
+double GetTimeMs() {
+	return 0.0;
 }
 } // namespace Timer
 } // namespace Loader

tests/ShaderRayTracingTests.inc

@@ -0,0 +1,87 @@
+void TestRayTracingDispatchDetection() {
+  namespace D = ShaderRecompiler::Decoder;
+  const auto check_decoded = [](std::span<const uint32_t> code, bool expected,
+                                const char *message) {
+    D::Program decoded;
+    D::DecodeProgram(code, decoded);
+    Check(decoded.has_bvh == expected, message);
+    if (expected) {
+      const auto &last = decoded.instructions.back();
+      Check(last.family == D::Family::MIMG &&
+                (last.opcode_id == 0xe6u || last.opcode_id == 0xe7u),
+            "decoder continued past the first BVH instruction");
+      const auto result = ShaderRecompiler::TranslateProgram(
+          code, MakeCompileOptions(ShaderType::Compute));
+      Check(result.skip_dispatch && result.program.blocks.empty() && result.cfg_dump.empty(),
+            "BVH compute shader reached IR translation");
+    }
+  };
+  const auto check = [&](std::initializer_list<uint32_t> code, bool expected,
+                         const char *message) {
+    check_decoded(std::span<const uint32_t>{code.begin(), code.size()}, expected, message);
+  };
+
+  check({0xf1989f01u, 0x00081014u, EncodeSopp(0x01)}, true,
+        "captured contiguous BVH instruction did not skip dispatch");
+  check({0xf1989f07u, 0x00071001u, 0x3d3e3c15u, 0x38095851u, 0x00003a39u,
+         EncodeSopp(0x01)}, true,
+        "captured NSA BVH instruction did not skip dispatch");
+  check({0xf19c9f01u, 0x00081014u, EncodeSopp(0x01)}, true,
+        "RDNA2 BVH64 instruction did not skip dispatch");
+  check({0xbe8e210eu, 0xf1989f01u, 0x00081014u, EncodeSopp(0x01)}, true,
+        "unsupported SWAPPC before BVH prevented dispatch detection");
+  check({0xf1989f01u, 0x00081014u, 0xc0000000u, EncodeSopp(0x01)}, true,
+        "unknown instruction after BVH prevented dispatch skipping");
+
+  for (uint32_t opcode : {0xe6u, 0xe7u}) {
+    for (uint32_t nsa = 0; nsa < 4; ++nsa) {
+      for (uint32_t slc = 0; slc < 2; ++slc) {
+        std::array<uint32_t, 6> code{
+            EncodeMimg0(opcode, 0xf, true) | (nsa << 1u) | (slc << 25u),
+            EncodeMimg1(0, 0, 0, 0)};
+        code[2 + nsa] = EncodeSopp(0x01);
+        check_decoded(std::span(code).first(3 + nsa), true,
+                      "BVH cache flags or NSA length prevented dispatch detection");
+      }
+    }
+  }
+  for (uint32_t opcode : {0x66u, 0x67u, 0xe4u, 0xe5u, 0xe8u, 0xe9u}) {
+    check({EncodeMimg0(opcode, 0xf), EncodeMimg1(0, 0, 0, 0), EncodeSopp(0x01)},
+          false, "non-BVH image opcode was incorrectly skipped");
+  }
+
+  check({EncodeSMovB32(0, 255), 0xf1989f01u, EncodeSopp(0x01)}, false,
+        "scalar literal was mistaken for a BVH instruction");
+  check({EncodeMimg0(0x20, 0xf) | 6u, EncodeMimg1(0, 0, 0, 0),
+         0xf1989f01u, 0xf19c9f01u, 0u, EncodeSopp(0x01)}, false,
+        "NSA address words were mistaken for BVH instructions");
+  check({EncodeMimg0(0x20, 0xf), 0xf1989f01u, EncodeSopp(0x01)}, false,
+        "MIMG operand word was mistaken for a BVH instruction");
+  check({EncodeSopp(0x01), 0xf1989f01u, 0x00081014u}, false,
+        "data after the shader end was mistaken for a BVH instruction");
+  check({EncodeMimg0(0x20, 0xf), EncodeMimg1(0, 0, 0, 0), EncodeSopp(0x01)},
+        false, "ordinary image shader was incorrectly skipped");
+
+  // An end instruction on one branch does not end another branch's code.
+  check({EncodeSopp(0x04, 1), EncodeSopp(0x01), 0xf1989f01u, 0x00081014u,
+         EncodeSopp(0x01)}, true,
+        "BVH at a branch target after an early end was not detected");
+
+  const std::array bvh_code{0xf1989f01u, 0x00081014u, 0xf19c9f01u, 0x00081014u,
+                            EncodeSopp(0x01)};
+  const std::array ordinary_code{EncodeSMovB32(0, 255), 0xf1989f01u, EncodeSopp(0x01)};
+  D::Program reused;
+  D::DecodeProgram(bvh_code, reused);
+  Check(reused.has_bvh && reused.instructions.size() == 1,
+        "decoder did not stop at the first BVH instruction");
+  D::DecodeProgram(ordinary_code, reused);
+  Check(!reused.has_bvh, "decoder retained stale BVH metadata");
+  for (const auto stage : {ShaderType::Compute, ShaderType::Vertex, ShaderType::Pixel}) {
+    const auto options = MakeCompileOptions(stage);
+    Check(!ShaderRecompiler::TranslateProgram(ordinary_code, options).skip_dispatch,
+          "BVH-shaped literal marked an ordinary shader for skipping");
+    const auto compiled = RecompileForTest(ordinary_code, options);
+    Check(!compiled.spirv.empty(), "ordinary shader did not compile");
+    CheckSpirvBinaryValidates(compiled.spirv);
+  }
+}

tests/ShaderRecompilerComputeTests.cpp

@@ -19018,6 +19018,52 @@ TestCase Vop2SdwaAshrrevCapturedWord0SignExtends() {
   return test;
 }
 
+TestCase Vop2SdwaMaxI32CapturedHighWord(u32 wave_size) {
+  using O = ShaderOpcode;
+  struct MaxCase { u32 lhs, packed_rhs, expected, exec = 1; };
+  constexpr std::array<MaxCase, 9> cases{{
+      {0xfffffffbu, 0xfffe1234u, 0xfffffffeu}, // -5 versus sign-extended -2.
+      {0xffffffffu, 0x80007fffu, 0xffffffffu},
+      {3, 0x0007ffffu, 7},                  // Ignore the low word.
+      {0xffffffffu, 0x0000ffffu, 0},
+      {0x80000000u, 0x80000000u, 0xffff8000u},
+      {0x7fffffffu, 0x8000ffffu, 0x7fffffffu},
+      {0x0000ffffu, 0x7fffffffu, 0x0000ffffu}, // Source 0 stays 32-bit.
+      {0x00007fffu, 0x7fff8000u, 0x00007fffu},
+      {0x80000001u, 0x7fff0123u, 0x80000001u, 0}, // Inactive destination.
+  }};
+  TestCase test;
+  test.name = wave_size == 64 ? "Vop2SdwaMaxI32HighWordWave64"
+                             : "Vop2SdwaMaxI32HighWordWave32";
+  for (const auto &entry : cases) {
+    test.initial.insert(test.initial.end(), {entry.lhs, entry.packed_rhs});
+  }
+  test.initial.resize(cases.size() * 3u, 0xdeadbeefu);
+  test.expected = test.initial;
+  auto &code = test.code;
+  for (u32 i = 0; i < cases.size(); ++i) {
+    AppendVMovU32(&code, 30, i * 8u);
+    AppendBufferLoadDword(&code, 11, 30);
+    AppendVMovU32(&code, 30, i * 8u + 4u);
+    AppendBufferLoadDword(&code, 22, 30);
+    code.push_back(EncodeSMovB32(126, InlineU32(cases[i].exec)));
+    // Exact game encoding: v11 = max(v11, sign_extend(v22.word1)).
+    code.insert(code.end(), {0x24162cf9u, 0x0d06060bu});
+    code.push_back(EncodeSMovB32(126, InlineU32(1)));
+    const u32 out = cases.size() * 2u + i;
+    AppendStoreVgpr(&code, 11, out);
+    test.expected[out] = cases[i].expected;
+  }
+  AppendEnd(&code);
+  test.opcodes = {O::V_MOV_B32, O::S_MOV_B32, O::BUFFER_LOAD_DWORD,
+                  O::V_MAX_I32, O::BUFFER_STORE_DWORD, O::S_ENDPGM};
+  test.decoded_counts = {{"V_MAX_I32 v11, v11, v22.sdwa(sel=5,sext=1)", cases.size()}};
+  test.required_spirv = {"OpBitFieldSExtract"};
+  test.compute_info.wave_size = wave_size;
+  test.has_compute_info = true;
+  return test;
+}
+
 TestCase Vop2SdwaLshrrevCapturedByte1Source() {
   using O = ShaderOpcode;
 
@@ -22446,6 +22492,74 @@ TestCase VectorVopcCmpxLtU16CapturedSdwaExecMask() {
   return test;
 }
 
+TestCase VectorVopcCmpxEqU16SdwaCompactVop3ExecMask() {
+  using O = ShaderOpcode;
+  struct CompareCase {
+    u32 lhs;
+    u32 rhs;
+    u32 incoming_exec;
+    u32 expected_exec;
+    u32 encoding = 0; // 0: SDWA, 1: compact, 2: VOP3, 3: SDWA sign-extend.
+  };
+  const std::array<CompareCase, 12> cases{{
+      {0x12340000u, 0x56780000u, 1, 1}, // Equal low half; ignore high half.
+      {0xffff0001u, 0xabcd0001u, 1, 1},
+      {0x00000000u, 0x12340000u, 1, 1},
+      {0xaaaa5555u, 0xbbbb5555u, 1, 1},
+      {0x00000000u, 0x00000001u, 1, 0},
+      {0x0000ffffu, 0x00000000u, 1, 0},
+      {0x7fff8000u, 0x00018000u, 1, 1}, // Equal low halves despite different high halves.
+      {0x00000000u, 0x00010000u, 1, 1},
+      {0x12340001u, 0x12340002u, 1, 0, 1},
+      {0x00008000u, 0x0000ffffu, 1, 0, 2},
+      {0x0001ffffu, 0x12340001u, 1, 0, 3}, // Sign-extended low halves differ.
+      {0x00000001u, 0x00010001u, 0, 0}, // CMPX cannot reactivate an inactive lane.
+  }};
+  constexpr u32 vcc_hi = 0x89abcdefu;
+  TestCase test;
+  test.name = "VectorVopcCmpxEqU16SdwaCompactVop3ExecMask";
+  for (const auto &entry : cases) {
+    test.initial.push_back(entry.lhs);
+  }
+  test.expected = test.initial;
+  auto &code = test.code;
+  for (u32 i = 0; i < cases.size(); ++i) {
+    const auto &entry = cases[i];
+    AppendVMovU32(&code, 30, i * 4u);
+    AppendBufferLoadDword(&code, 0, 30); // Runtime input prevents constant folding.
+    AppendVMovU32(&code, 1, entry.rhs);
+    AppendSMovLiteral(&code, 106, entry.rhs);
+    AppendSMovLiteral(&code, 107, vcc_hi);
+    code.push_back(EncodeSMovB32(126, InlineU32(entry.incoming_exec)));
+    switch (entry.encoding) {
+    case 1: code.push_back(0x7d740300u); break; // compact v0, v1
+    case 2: code.insert(code.end(), {0xd4ba007eu, 0x00020300u}); break;
+    case 3:
+      code.push_back(EncodeVopc(0xba, 249u, 1u));
+      code.push_back(EncodeVopcSdwa(0u, 0u, 0u, 6u, 6u, 1u, 1u));
+      break;
+    default:
+      code.push_back(EncodeVopc(0xba, 249u, 1u));
+      code.push_back(EncodeVopcSdwa(0u));
+      break;
+    }
+    code.push_back(EncodeSMovB32(20, 126)); // Snapshot EXEC before restoring it.
+    code.push_back(EncodeSMovB32(21, 127));
+    code.push_back(EncodeSMovB32(126, InlineU32(1u)));
+    const u32 out = static_cast<u32>(cases.size()) + i * 4u;
+    AppendStoreSgprPair(&code, 20, out);
+    AppendStoreSgprPair(&code, 106, out + 2u); // CMPX must not overwrite either VCC half.
+    test.expected.insert(test.expected.end(),
+                         {entry.expected_exec, 0u, entry.rhs, vcc_hi});
+  }
+  AppendEnd(&code);
+  test.opcodes = {O::V_MOV_B32, O::S_MOV_B32, O::BUFFER_LOAD_DWORD,
+                  O::V_CMPX_EQ_U16, O::BUFFER_STORE_DWORD, O::S_ENDPGM};
+  test.decoded_counts = {{"V_CMPX_EQ_U16", cases.size()}};
+  test.required_spirv = {"OpIEqual"};
+  return test;
+}
+
 TestCase VectorVopcCmpNgtF16CapturedSdwaAndEdges() {
   using O = ShaderOpcode;
   enum Encoding { Captured, Compact, Vop3NegAbs, HighWord, ScalarDst, SdwaNegAbs };
@@ -22783,6 +22897,31 @@ TestCase BranchVccnzUsesWaveMask() {
   return test;
 }
 
+TestCase ScalarMemRealtimeCapturedPlaceholder() {
+  using O = ShaderOpcode;
+  namespace D = ShaderRecompiler::Decoder;
+
+  std::vector<u32> code = {0xf4940300u, 0xfa000000u};
+  D::Instruction decoded;
+  D::DecodeInstruction(code, 0, decoded);
+  Require("ScalarMemRealtimeCapturedPlaceholder", "decode",
+          decoded.opcode == O::S_MEMREALTIME && decoded.word_count == 2 &&
+              decoded.dst.kind == D::OperandKind::Sgpr && decoded.dst.reg == 12 &&
+              decoded.data_dwords == 2 && decoded.src_count == 0 &&
+              decoded.src0.kind == D::OperandKind::Unknown &&
+              decoded.src1.kind == D::OperandKind::Unknown,
+          "captured clock instruction must write s12:s13 without memory operands");
+  AppendStoreSgprPair(&code, 12, 0);
+  code.insert(code.end(), {0xf4940300u, 0xfa000000u});
+  AppendStoreSgprPair(&code, 12, 2);
+  AppendEnd(&code);
+  return {"ScalarMemRealtimeCapturedPlaceholder",
+          code,
+          {},
+          {UINT32_MAX, UINT32_MAX, UINT32_MAX, UINT32_MAX},
+          {O::S_MEMREALTIME, O::V_MOV_B32, O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
+}
+
 TestCase ScalarMemoryLoadVariants() {
   using O = ShaderOpcode;
 
@@ -23171,7 +23310,7 @@ TestCase BufferLoadDwordx4ZeroesOnlyOutOfBoundsTail() {
   return test;
 }
 
-TestCase BufferLoadsGpuSelectedDescriptors() {
+TestCase BufferLoadsGpuSelectedDescriptors(bool xyz) {
   using O = ShaderOpcode;
   constexpr uint64_t GuestBase = 0x0000000110000000ull;
   struct DescriptorCase {
@@ -23181,6 +23320,8 @@ TestCase BufferLoadsGpuSelectedDescriptors() {
   };
   const DescriptorCase cases[] = {
       {24, 2, 0, 0, false, true, {7, 8, 9, 10, 11, 12}},
+      // PPSA01417 selects XYZ vertices from a table of stride-16 descriptors.
+      {16, 2, 0, 0, false, true, {5, 6, 7, 8, 0, 0}},
       {12, 2, 0, 0, false, true, {4, 5, 6, 0, 0, 0}},
       {12, 2, 1, 0, false, true, {4, 5, 6, 7, 8, 9}},
       {12, 1, 2, 0, false, true, {4, 5, 6, 7, 8, 9}},
@@ -23194,7 +23335,8 @@ TestCase BufferLoadsGpuSelectedDescriptors() {
       {12, 4, 3, 4, true, true, {}},
   };
   TestCase test;
-  test.name = "BufferLoadsGpuSelectedDescriptors";
+  test.name = xyz ? "BufferLoadDwordx3GpuSelectedDescriptors"
+                  : "BufferLoadsGpuSelectedDescriptors";
   test.initial.resize(2048);
   for (u32 i = 0; i < std::size(cases); ++i) {
     const auto &input = cases[i];
@@ -23220,10 +23362,10 @@ TestCase BufferLoadsGpuSelectedDescriptors() {
     test.code.push_back(EncodeSmem1(520, 20));
     AppendSMovLiteral(&test.code, 22, cases[selected].soffset);
     AppendVMovU32(&test.code, 21, 1);
-    test.code.push_back(EncodeMubuf0(0x0e, 0, true, false));
+    test.code.push_back(EncodeMubuf0(xyz ? 0x0f : 0x0e, 0, true, false));
     test.code.push_back(EncodeMubuf1(0, 2, 21, 22));
-    test.code.push_back(EncodeMubuf0(0x0d, 16, true, false));
-    test.code.push_back(EncodeMubuf1(4, 2, 21, 22));
+    test.code.push_back(EncodeMubuf0(xyz ? 0x0f : 0x0d, xyz ? 12 : 16, true, false));
+    test.code.push_back(EncodeMubuf1(xyz ? 3 : 4, 2, 21, 22));
     for (u32 component = 0; component < 6; ++component) {
       AppendStoreVgpr(&test.code, component, i * 6 + component);
       const u32 expected = cases[selected].expected[component];
@@ -23234,12 +23376,24 @@ TestCase BufferLoadsGpuSelectedDescriptors() {
   test.bda_mappings = {{GuestBase, 0}};
   test.opcodes = {O::V_MOV_B32, O::S_MOV_B32, O::BUFFER_LOAD_DWORD,
                   O::V_READFIRSTLANE_B32, O::S_MUL_I32, O::S_BUFFER_LOAD_DWORDX4,
-                  O::BUFFER_LOAD_DWORDX4, O::BUFFER_LOAD_DWORDX2,
                   O::BUFFER_STORE_DWORD, O::S_ENDPGM};
+  if (xyz) {
+    test.opcodes.push_back(O::BUFFER_LOAD_DWORDX3);
+  } else {
+    test.opcodes.insert(test.opcodes.end(), {O::BUFFER_LOAD_DWORDX4, O::BUFFER_LOAD_DWORDX2});
+  }
   test.required_spirv = {"OpConvertUToPtr", "PhysicalStorageBuffer"};
   return test;
 }
 
+TestCase BufferLoadsGpuSelectedDescriptors() {
+  return BufferLoadsGpuSelectedDescriptors(false);
+}
+
+TestCase BufferLoadDwordx3GpuSelectedDescriptors() {
+  return BufferLoadsGpuSelectedDescriptors(true);
+}
+
 TestCase BufferStoreDwordx4DropsOnlyOutOfBoundsTail() {
   using O = ShaderOpcode;
 
@@ -25905,6 +26059,76 @@ TestCase Wave64AppendConsumeHighHalf() {
   return test;
 }
 
+TestCase BufferWorkgroupPublication(u32 wave_size, bool dlc_only = false) {
+  using O = ShaderOpcode;
+  constexpr u32 groups = 31;
+  TestCase test;
+  test.name = dlc_only ? "BufferWorkgroupPublicationDlc"
+             : wave_size == 64 ? "BufferWorkgroupPublicationWave64"
+                               : "BufferWorkgroupPublicationWave32";
+  auto &code = test.code;
+  // Allocate work in execution order so every polled predecessor has started.
+  // Only one lane per workgroup owns a ticket and publishes its prefix total.
+  code.push_back(EncodeSop1(0x04, 126, InlineU32(1)));
+  AppendVMovU32(&code, 1, 1);
+  AppendVMovU32(&code, 20, 0);
+  AppendBufferStoreOpcode(&code, 0x32, 1, 20, true);
+  code.push_back(EncodeVop1(0x02, 20, Vgpr(1)));
+  code.push_back(EncodeVop2(0x1a, 20, InlineU32(2), 1));
+  AppendVMovU32(&code, 2, 0);
+  code.push_back(EncodeSMovB32(21, InlineU32(0)));
+  AppendSMovLiteral(&code, 22, 1000000);
+  code.push_back(EncodeSopc(0x06, 20, InlineU32(0)));
+  const auto first_ticket = code.size();
+  code.push_back(0);
+
+  const auto poll = code.size();
+  code.push_back(EncodeMubuf0(0x0c, 0, false, true, !dlc_only) | (1u << 15u));
+  code.push_back(EncodeMubuf1(2, 12, 20));
+  code.push_back(EncodeSopp(0x0c, 0)); // S_WAITCNT vmcnt(0).
+  code.push_back(EncodeVop1(0x02, 23, Vgpr(2)));
+  code.push_back(EncodeSopc(0x07, 23, InlineU32(0)));
+  const auto ready = code.size();
+  code.push_back(0);
+  code.push_back(EncodeSop2(0x00, 21, 21, InlineU32(1)));
+  code.push_back(EncodeSopc(0x0a, 21, 22));
+  code.push_back(EncodeSopp(0x05, static_cast<u32>(poll - code.size() - 1)));
+  // A broken poll reports an incorrect result instead of hanging the test GPU.
+  AppendVMovLiteral(&code, 2, 0x80000000u);
+  const auto publish = code.size();
+  code[first_ticket] = EncodeSopp(0x05, publish - first_ticket - 1);
+  code[ready] = EncodeSopp(0x05, publish - ready - 1);
+  code.push_back(EncodeVop2(0x25, 2, Vgpr(1), 2));
+  code.push_back(EncodeVop2(0x25, 2, InlineU32(1), 2));
+  code.push_back(EncodeVop2(0x25, 20, InlineU32(4), 20));
+  // RDNA2 stores publish to L2 even without GLC/DLC on the producer.
+  AppendBufferStoreDword(&code, 2, 20);
+  AppendEnd(&code);
+
+  test.initial.assign(groups + 1, 0);
+  test.expected = {groups};
+  for (u32 ticket = 0; ticket < groups; ++ticket) {
+    test.expected.push_back((ticket + 1) * (ticket + 2) / 2);
+  }
+  test.opcodes = {O::S_MOV_B64, O::S_MOV_B32, O::V_MOV_B32,
+                  O::BUFFER_ATOMIC_ADD, O::V_READFIRSTLANE_B32,
+                  O::V_LSHLREV_B32, O::S_CMP_EQ_U32, O::S_CMP_LG_U32,
+                  O::S_CMP_LT_U32, O::S_CBRANCH_SCC1, O::S_ADD_U32,
+                  O::S_WAITCNT, O::BUFFER_LOAD_DWORD, O::V_ADD_NC_U32,
+                  O::BUFFER_STORE_DWORD, O::S_ENDPGM};
+  test.required_spirv = {"Coherent", "Volatile", "OpAtomicIAdd", "OpLoopMerge"};
+  test.compute_info.threads_num[0] = wave_size;
+  test.compute_info.threads_num[1] = 1;
+  test.compute_info.threads_num[2] = 1;
+  test.compute_info.thread_ids_num = 1;
+  test.compute_info.wave_size = wave_size;
+  test.has_compute_info = true;
+  test.dispatch_x = groups;
+  // DLC alone does not bypass RDNA2's L0, so only check its translated policy.
+  test.compile_only = dlc_only;
+  return test;
+}
+
 TestCase BufferAtomicVariants() {
   using O = ShaderOpcode;
 
@@ -28265,6 +28489,9 @@ std::vector<TestCase> MakeCases() {
   auto AddCase = [&cases](TestCase (*factory)()) {
     cases.push_back(factory());
   };
+  cases.push_back(BufferWorkgroupPublication(32));
+  cases.push_back(BufferWorkgroupPublication(64));
+  cases.push_back(BufferWorkgroupPublication(32, true));
 
   AddCase(IntegerAddSubMul);
   AddCase(BitwiseOps);
@@ -28330,6 +28557,8 @@ std::vector<TestCase> MakeCases() {
   AddCase(Vop2SdwaSubNcExactByte2Destination);
   AddCase(Vop2SdwaAddNcCapturedHighWordDestination);
   AddCase(Vop2SdwaAshrrevCapturedWord0SignExtends);
+  cases.push_back(Vop2SdwaMaxI32CapturedHighWord(32));
+  cases.push_back(Vop2SdwaMaxI32CapturedHighWord(64));
   AddCase(Vop2SdwaLshrrevCapturedByte1Source);
   AddCase(Vop2SdwaSubNcPreservesByteAndWordDestinations);
   AddCase(Vop3CvtPkI16I32Captured);
@@ -28427,6 +28656,7 @@ std::vector<TestCase> MakeCases() {
   AddCase(VectorVopcSdwaCmpxWritesExecMask);
   AddCase(VectorVopcCmpxGtU16CapturedSdwaExecMask);
   AddCase(VectorVopcCmpxLtU16CapturedSdwaExecMask);
+  AddCase(VectorVopcCmpxEqU16SdwaCompactVop3ExecMask);
   AddCase(VectorVopcCmpNgtF16CapturedSdwaAndEdges);
   AddCase(VectorVopcCmpNltF16CapturedSdwaAndEdges);
   AddCase(VectorVopcCmpxNgtF16CapturedSdwaExecMask);
@@ -28436,6 +28666,7 @@ std::vector<TestCase> MakeCases() {
   AddCase(SharedReturnKeepsSelectedValues);
   AddCase(BranchVccnzUsesWaveMask);
   AddCase(BranchVccnzUsesCarryProducedWaveMask);
+  AddCase(ScalarMemRealtimeCapturedPlaceholder);
   AddCase(ScalarMemoryLoadVariants);
   AddCase(ScalarLoadSignedImmediateOffsetAddsSoffset);
   AddCase(ScalarLoadAlignsComponentsAndMasksAddress);
@@ -28453,6 +28684,7 @@ std::vector<TestCase> MakeCases() {
   AddCase(BufferLoadDwordx4SnapshotsOverlappingAddress);
   AddCase(BufferLoadDwordx4ZeroesOnlyOutOfBoundsTail);
   AddCase(BufferLoadsGpuSelectedDescriptors);
+  AddCase(BufferLoadDwordx3GpuSelectedDescriptors);
   AddCase(BufferStoreDwordx4DropsOnlyOutOfBoundsTail);
   AddCase(BufferLoadFormatXyzwRejectsPartialRecord);
   AddCase(BufferStoreFormatXyzwDropsPartialRecord);
@@ -33172,6 +33404,11 @@ int main(int argc, char **argv) {
   std::setvbuf(stdout, nullptr, _IONBF, 0);
   EnsureConfigInitialized();
   CheckLeastRecentlyUsedCacheOrdering();
+  if (argc == 2 && std::strcmp(argv[1], "--s-memrealtime-only") == 0) {
+    VulkanHarness vulkan;
+    RunCase(&vulkan, ScalarMemRealtimeCapturedPlaceholder());
+    return 0;
+  }
   if (argc == 2 && std::strcmp(argv[1], "--packed-integer-neg-only") == 0) {
     VulkanHarness vulkan;
     RunCase(&vulkan, Vop3pIntegerNegationCapturedAndSelectedHalves());
@@ -33218,6 +33455,11 @@ int main(int argc, char **argv) {
     CheckEmbeddedFetchVertexOffset();
     return 0;
   }
+  if (argc == 2 && std::strcmp(argv[1], "--cmpx-eq-u16-only") == 0) {
+    VulkanHarness vulkan;
+    RunCase(&vulkan, VectorVopcCmpxEqU16SdwaCompactVop3ExecMask());
+    return 0;
+  }
   if (argc == 2 && std::strcmp(argv[1], "--cmpx-lt-u16-only") == 0) {
     VulkanHarness vulkan;
     RunCase(&vulkan, VectorVopcCmpxLtU16CapturedSdwaExecMask());
@@ -33276,6 +33518,7 @@ int main(int argc, char **argv) {
   if (argc == 2 && std::strcmp(argv[1], "--indirect-buffer-only") == 0) {
     VulkanHarness vulkan;
     RunCase(&vulkan, BufferLoadsGpuSelectedDescriptors());
+    RunCase(&vulkan, BufferLoadDwordx3GpuSelectedDescriptors());
     RunCase(&vulkan, BufferLoadDwordx4SnapshotsOverlappingAddress());
     RunCase(&vulkan, BufferLoadDwordx4ZeroesOnlyOutOfBoundsTail());
     RunCase(&vulkan, BufferLoadDwordIdxenUsesDescriptorStride());
@@ -33383,6 +33626,14 @@ int main(int argc, char **argv) {
     RunCase(&vulkan, BufferOffsetsUsePackedLaneAndStorageFallback());
     return 0;
   }
+  if (argc == 2 && std::strcmp(argv[1], "--buffer-publication-only") == 0) {
+    VulkanHarness vulkan;
+    RunCase(&vulkan, BufferWorkgroupPublication(32));
+    RunCase(&vulkan, BufferWorkgroupPublication(64));
+    RunCase(&vulkan, BufferWorkgroupPublication(32, true));
+    RunCase(&vulkan, BufferAtomicVariants());
+    return 0;
+  }
   if (argc == 2 && std::strcmp(argv[1], "--buffer-cmpswap-only") == 0) {
     VulkanHarness vulkan;
     RunCase(&vulkan, BufferAtomicCmpSwapExactRaw());
@@ -33442,6 +33693,13 @@ int main(int argc, char **argv) {
     RunCase(&vulkan, Vop2SdwaAshrrevCapturedWord0SignExtends());
     return 0;
   }
+  if (argc == 2 && std::strcmp(argv[1], "--sdwa-max-i32-only") == 0) {
+    VulkanHarness vulkan;
+    RunCase(&vulkan, Vop2SdwaMaxI32CapturedHighWord(32));
+    RunCase(&vulkan, Vop2SdwaMaxI32CapturedHighWord(64));
+    RunCase(&vulkan, VectorIntegerOps());
+    return 0;
+  }
   if (argc == 2 && std::strcmp(argv[1], "--sdwa-addc-only") == 0) {
     VulkanHarness vulkan;
     RunCase(&vulkan, VectorAddcWritesPerLaneCarryOut());

tests/shaderCfgTests.cpp

@@ -13517,6 +13517,8 @@ void TestNewShaderRecompilerSpirvSizeBaselines() {
   CheckSpirvPhiParents(dispatcher_result.spirv);
 }
 
+#include "ShaderRayTracingTests.inc"
+
 } // namespace
 } // namespace Libs::Graphics
 
@@ -13524,6 +13526,7 @@ int main() {
   using namespace Libs::Graphics;
 
   EnsureConfigInitialized();
+  TestRayTracingDispatchDetection();
   TestResourceDescriptorClassification();
   TestShaderBufferResourceSize();
   TestNativeShaderResourceDependencies();