Moar shader decompiler

.gitmodules

@@ -76,3 +76,6 @@
 [submodule "third_party/metal-cpp"]
 	path = third_party/metal-cpp
 	url = https://github.com/Panda3DS-emu/metal-cpp
+[submodule "third_party/fmt"]
+	path = third_party/fmt
+	url = https://github.com/fmtlib/fmt

CMakeLists.txt

@@ -93,6 +93,7 @@ if (NOT ANDROID)
     target_link_libraries(AlberCore PUBLIC SDL2-static)
 endif()
 
+add_subdirectory(third_party/fmt)
 add_subdirectory(third_party/toml11)
 include_directories(${SDL2_INCLUDE_DIR})
 include_directories(third_party/toml11)
@@ -255,6 +256,7 @@ set(HEADER_FILES include/emulator.hpp include/helpers.hpp include/termcolor.hpp
                  include/audio/miniaudio_device.hpp include/ring_buffer.hpp include/bitfield.hpp include/audio/dsp_shared_mem.hpp
                  include/audio/hle_core.hpp include/capstone.hpp include/audio/aac.hpp include/PICA/pica_frag_config.hpp
                  include/PICA/pica_frag_uniforms.hpp include/PICA/shader_gen_types.hpp include/PICA/shader_decompiler.hpp
+                 include/PICA/pica_vert_config.hpp
 )
 
 cmrc_add_resource_library(
@@ -419,7 +421,7 @@ set(ALL_SOURCES ${SOURCE_FILES} ${FS_SOURCE_FILES} ${CRYPTO_SOURCE_FILES} ${KERN
 target_sources(AlberCore PRIVATE ${ALL_SOURCES})
 
 target_link_libraries(AlberCore PRIVATE dynarmic cryptopp glad resources_console_fonts teakra)
-target_link_libraries(AlberCore PUBLIC glad capstone)
+target_link_libraries(AlberCore PUBLIC glad capstone fmt::fmt)
 
 if(ENABLE_DISCORD_RPC AND NOT ANDROID)
     target_compile_definitions(AlberCore PUBLIC "PANDA3DS_ENABLE_DISCORD_RPC=1")

include/PICA/gpu.hpp

@@ -13,6 +13,12 @@
 #include "memory.hpp"
 #include "renderer.hpp"
 
+enum class ShaderExecMode {
+	Interpreter,  // Interpret shaders on the CPU
+	JIT,          // Recompile shaders to CPU machine code
+	Hardware,     // Recompiler shaders to host shaders and run them on the GPU
+};
+
 class GPU {
 	static constexpr u32 regNum = 0x300;
 	static constexpr u32 extRegNum = 0x1000;
@@ -45,7 +51,7 @@ class GPU {
 	uint immediateModeVertIndex;
 	uint immediateModeAttrIndex;  // Index of the immediate mode attribute we're uploading
 
-	template <bool indexed, bool useShaderJIT>
+	template <bool indexed, ShaderExecMode mode>
 	void drawArrays();
 
 	// Silly method of avoiding linking problems. TODO: Change to something less silly

include/PICA/pica_vert_config.hpp

@@ -0,0 +1,31 @@
+#pragma once
+#include <array>
+#include <cstring>
+#include <type_traits>
+#include <unordered_map>
+
+#include "PICA/pica_hash.hpp"
+#include "PICA/regs.hpp"
+#include "bitfield.hpp"
+#include "helpers.hpp"
+
+namespace PICA {
+	// Configuration struct used 
+	struct VertConfig {
+		PICAHash::HashType shaderHash;
+		PICAHash::HashType opdescHash;
+		u32 entrypoint;
+		bool usingUbershader;
+
+		bool operator==(const VertConfig& config) const {
+			// Hash function and equality operator required by std::unordered_map
+			return std::memcmp(this, &config, sizeof(VertConfig)) == 0;
+		}
+	};
+}  // namespace PICA
+
+// Override std::hash for our vertex config class
+template <>
+struct std::hash<PICA::VertConfig> {
+	std::size_t operator()(const PICA::VertConfig& config) const noexcept { return PICAHash::computeHash((const char*)&config, sizeof(config)); }
+};

include/PICA/shader.hpp

@@ -107,6 +107,11 @@ class PICAShader {
 	alignas(16) std::array<vec4f, 16> inputs;           // Attributes passed to the shader
 	alignas(16) std::array<vec4f, 16> outputs;
 	alignas(16) vec4f dummy = vec4f({f24::zero(), f24::zero(), f24::zero(), f24::zero()});  // Dummy register used by the JIT
+
+	// We use a hashmap for matching 3DS shaders to their equivalent compiled code in our shader cache in the shader JIT
+	// We choose our hash type to be a 64-bit integer by default, as the collision chance is very tiny and generating it is decently optimal
+	// Ideally we want to be able to support multiple different types of hash depending on compilation settings, but let's get this working first
+	using Hash = PICAHash::HashType;
 
   protected:
 	std::array<u32, 128> operandDescriptors;
@@ -125,11 +130,6 @@ class PICAShader {
 	std::array<CallInfo, 4> callInfo;
 	ShaderType type;
 
-	// We use a hashmap for matching 3DS shaders to their equivalent compiled code in our shader cache in the shader JIT
-	// We choose our hash type to be a 64-bit integer by default, as the collision chance is very tiny and generating it is decently optimal
-	// Ideally we want to be able to support multiple different types of hash depending on compilation settings, but let's get this working first
-	using Hash = PICAHash::HashType;
-
 	Hash lastCodeHash = 0;    // Last hash computed for the shader code (Used for the JIT caching mechanism)
 	Hash lastOpdescHash = 0;  // Last hash computed for the operand descriptors (Also used for the JIT)
 

include/PICA/shader_gen.hpp

@@ -30,6 +30,8 @@ namespace PICA::ShaderGen {
 		FragmentGenerator(API api, Language language) : api(api), language(language) {}
 		std::string generate(const PICA::FragmentConfig& config);
 		std::string getDefaultVertexShader();
+		// For when PICA shader is acceleration is enabled. Turn the PICA shader source into a proper vertex shader
+		std::string getVertexShaderAccelerated(const std::string& picaSource, bool usingUbershader);
 
 		void setTarget(API api, Language language) {
 			this->api = api;

include/PICA/shader_unit.hpp

@@ -2,10 +2,9 @@
 #include "PICA/shader.hpp"
 
 class ShaderUnit {
-
-public:
-	PICAShader vs; // Vertex shader
-	PICAShader gs; // Geometry shader
+  public:
+	PICAShader vs;  // Vertex shader
+	PICAShader gs;  // Geometry shader
 
 	ShaderUnit() : vs(ShaderType::Vertex), gs(ShaderType::Geometry) {}
 	void reset();

include/config.hpp

@@ -20,11 +20,13 @@ struct EmulatorConfig {
 #else
 	static constexpr bool ubershaderDefault = true;
 #endif
-
+	static constexpr bool accelerateShadersDefault = false;
+
 	bool shaderJitEnabled = shaderJitDefault;
-	bool discordRpcEnabled = false;
 	bool useUbershaders = ubershaderDefault;
+	bool accelerateShaders = accelerateShadersDefault;
 	bool accurateShaderMul = false;
+	bool discordRpcEnabled = false;
 
 	// Toggles whether to force shadergen when there's more than N lights active and we're using the ubershader, for better performance
 	bool forceShadergenForLights = true;

include/renderer.hpp

@@ -21,9 +21,11 @@ enum class RendererType : s8 {
 };
 
 struct EmulatorConfig;
-class GPU;
 struct SDL_Window;
 
+class GPU;
+class ShaderUnit;
+
 class Renderer {
   protected:
 	GPU& gpu;
@@ -77,7 +79,11 @@ class Renderer {
 	virtual std::string getUbershader() { return ""; }
 	virtual void setUbershader(const std::string& shader) {}
 
-	virtual void setUbershaderSetting(bool value) {}
+	// This function is called on every draw call before parsing vertex data.
+	// It is responsible for things like looking up which vertex/fragment shaders to use, recompiling them if they don't exist, choosing between
+	// ubershaders and shadergen, and so on.
+	// Returns whether this draw is eligible for using hardware-accelerated shaders or if shaders should run on the CPU
+	virtual bool prepareForDraw(ShaderUnit& shaderUnit, bool isImmediateMode) { return false; }
 
 	// Functions for initializing the graphics context for the Qt frontend, where we don't have the convenience of SDL_Window
 #ifdef PANDA3DS_FRONTEND_QT

include/renderer_gl/renderer_gl.hpp

@@ -3,11 +3,14 @@
 #include <array>
 #include <cstring>
 #include <functional>
+#include <optional>
 #include <span>
 #include <unordered_map>
+#include <utility>
 
 #include "PICA/float_types.hpp"
 #include "PICA/pica_frag_config.hpp"
+#include "PICA/pica_vert_config.hpp"
 #include "PICA/pica_hash.hpp"
 #include "PICA/pica_vertex.hpp"
 #include "PICA/regs.hpp"
@@ -28,9 +31,11 @@ class RendererGL final : public Renderer {
 	OpenGL::Program triangleProgram;
 	OpenGL::Program displayProgram;
 
-	OpenGL::VertexArray vao;
+	// VAO for when not using accelerated vertex shaders. Contains attribute declarations matching to the PICA fixed function fragment attributes
+	OpenGL::VertexArray defaultVAO;
+	// VAO for when using accelerated vertex shaders. The PICA vertex shader inputs are passed as attributes without CPU processing.
+	OpenGL::VertexArray hwShaderVAO;
 	OpenGL::VertexBuffer vbo;
-	bool enableUbershader = true;
 
 	// Data 
 	struct {
@@ -53,6 +58,11 @@ class RendererGL final : public Renderer {
 	float oldDepthScale = -1.0;
 	float oldDepthOffset = 0.0;
 	bool oldDepthmapEnable = false;
+	// Set by prepareDraw, tells us whether the current draw is using hw-accelerated shader
+	bool usingAcceleratedShader = false;
+
+	// Cached pointer to the current vertex shader when using HW accelerated shaders
+	OpenGL::Shader* generatedVertexShader = nullptr;
 
 	SurfaceCache<DepthBuffer, 16, true> depthBufferCache;
 	SurfaceCache<ColourBuffer, 16, true> colourBufferCache;
@@ -75,7 +85,37 @@ class RendererGL final : public Renderer {
 	struct CachedProgram {
 		OpenGL::Program program;
 	};
-	std::unordered_map<PICA::FragmentConfig, CachedProgram> shaderCache;
+
+	struct ShaderCache {
+		std::unordered_map<PICA::VertConfig, std::optional<OpenGL::Shader>> vertexShaderCache;
+		std::unordered_map<PICA::FragmentConfig, OpenGL::Shader> fragmentShaderCache;
+
+		// Program cache indexed by GLuints for the vertex and fragment shader to use
+		// Top 32 bits are the vertex shader GLuint, bottom 32 bits are the fs GLuint
+		std::unordered_map<u64, CachedProgram> programCache;
+
+		void clear() {
+			for (auto& it : programCache) {
+				CachedProgram& cachedProgram = it.second;
+				cachedProgram.program.free();
+			}
+
+			for (auto& it : vertexShaderCache) {
+				if (it.second.has_value()) {
+					it.second->free();
+				}
+			}
+
+			for (auto& it : fragmentShaderCache) {
+				it.second.free();
+			}
+
+			programCache.clear();
+			vertexShaderCache.clear();
+			fragmentShaderCache.clear();
+		}
+	};
+	ShaderCache shaderCache;
 
 	OpenGL::Framebuffer getColourFBO();
 	OpenGL::Texture getTexture(Texture& tex);
@@ -110,15 +150,13 @@ class RendererGL final : public Renderer {
 	virtual bool supportsShaderReload() override { return true; }
 	virtual std::string getUbershader() override;
 	virtual void setUbershader(const std::string& shader) override;
-
-	virtual void setUbershaderSetting(bool value) override { enableUbershader = value; }
+	virtual bool prepareForDraw(ShaderUnit& shaderUnit, bool isImmediateMode) override;
 
 	std::optional<ColourBuffer> getColourBuffer(u32 addr, PICA::ColorFmt format, u32 width, u32 height, bool createIfnotFound = true);
 
 	// Note: The caller is responsible for deleting the currently bound FBO before calling this
 	void setFBO(uint handle) { screenFramebuffer.m_handle = handle; }
 	void resetStateManager() { gl.reset(); }
-	void clearShaderCache();
 	void initUbershader(OpenGL::Program& program);
 
 #ifdef PANDA3DS_FRONTEND_QT

src/config.cpp

@@ -64,6 +64,7 @@ void EmulatorConfig::load() {
 			vsyncEnabled = toml::find_or<toml::boolean>(gpu, "EnableVSync", true);
 			useUbershaders = toml::find_or<toml::boolean>(gpu, "UseUbershaders", ubershaderDefault);
 			accurateShaderMul = toml::find_or<toml::boolean>(gpu, "AccurateShaderMultiplication", false);
+			accelerateShaders = toml::find_or<toml::boolean>(gpu, "AccelerateShaders", accelerateShadersDefault);
 
 			forceShadergenForLights = toml::find_or<toml::boolean>(gpu, "ForceShadergenForLighting", true);
 			lightShadergenThreshold = toml::find_or<toml::integer>(gpu, "ShadergenLightThreshold", 1);
@@ -135,6 +136,7 @@ void EmulatorConfig::save() {
 	data["GPU"]["UseUbershaders"] = useUbershaders;
 	data["GPU"]["ForceShadergenForLighting"] = forceShadergenForLights;
 	data["GPU"]["ShadergenLightThreshold"] = lightShadergenThreshold;
+	data["GPU"]["AccelerateShaders"] = accelerateShaders;
 
 	data["Audio"]["DSPEmulation"] = std::string(Audio::DSPCore::typeToString(dspType));
 	data["Audio"]["EnableAudio"] = audioEnabled;