More hw VAO work

include/PICA/draw_acceleration.hpp

@@ -6,13 +6,28 @@
 
 namespace PICA {
 	struct DrawAcceleration {
+		static constexpr u32 maxAttribCount = 12;
+
+		struct AttributeInfo {
+			u32 offset;
+
+			u8 type;
+			u8 componentCount;
+			bool fixed;
+
+			std::array<float, 4> fixedValue;  // For fixed attributes
+		};
+
 		u8* vertexBuffer;
 		u8* indexBuffer;
 
 		// Minimum and maximum index in the index buffer for a draw call
 		u16 minimumIndex, maximumIndex;
+		u32 totalAttribCount;
 		u32 vertexDataSize;
 
+		std::array<AttributeInfo, maxAttribCount> attributeInfo;
+
 		bool canBeAccelerated;
 		bool indexed;
 	};

src/core/PICA/draw_acceleration.cpp

@@ -7,6 +7,8 @@
 
 void GPU::getAcceleratedDrawInfo(PICA::DrawAcceleration& accel, bool indexed) {
 	accel.indexed = indexed;
+	accel.totalAttribCount = totalAttribCount;
+
 	const u32 vertexBase = ((regs[PICA::InternalRegs::VertexAttribLoc] >> 1) & 0xfffffff) * 16;
 	const u32 vertexCount = regs[PICA::InternalRegs::VertexCountReg];  // Total # of vertices to transfer
 
@@ -47,23 +49,56 @@ void GPU::getAcceleratedDrawInfo(PICA::DrawAcceleration& accel, bool indexed) {
 		accel.maximumIndex = accel.minimumIndex + vertexCount - 1;
 	}
 
+	const u64 vertexCfg = u64(regs[PICA::InternalRegs::AttribFormatLow]) | (u64(regs[PICA::InternalRegs::AttribFormatHigh]) << 32);
 	int buffer = 0;
 	accel.vertexDataSize = 0;
 
 	for (int attrCount = 0; attrCount < totalAttribCount; attrCount++) {
-		bool fixedAttribute = (fixedAttribMask & (1 << attrCount)) != 0;
+		auto& attr = accel.attributeInfo[attrCount];
+		attr.fixed = (fixedAttribMask & (1 << attrCount)) != 0;
 
-		if (!fixedAttribute) {
-			auto& attr = attributeInfo[buffer];  // Get information for this attribute
-
-			if (attr.componentCount != 0) {
+		// Variable attribute attribute
+		if (!attr.fixed) {
+			auto& attrData = attributeInfo[buffer];  // Get information for this attribute
+			u64 attrCfg = attrData.getConfigFull();  // Get config1 | (config2 << 32)
+			u32 attributeOffset = attrData.offset;
+
+			if (attrData.componentCount != 0) {
 				// Size of the attribute in bytes multiplied by the total number of vertices
-				const u32 bytes = attr.size * vertexCount;
+				const u32 bytes = attrData.size * vertexCount;
 				// Add it to the total vertex data size, aligned to 4 bytes.
 				accel.vertexDataSize += (bytes + 3) & ~3;
 			}
 
+			for (int i = 0; i < attrData.componentCount; i++) {
+				uint index = (attrCfg >> (i * 4)) & 0xf;  // Get index of attribute in vertexCfg
+
+				// Vertex attributes used as padding
+				// 12, 13, 14 and 15 are equivalent to 4, 8, 12 and 16 bytes of padding respectively
+				if (index >= 12) [[unlikely]] {
+					Helpers::panic("Padding attribute");
+					// Align attribute address up to a 4 byte boundary
+					attributeOffset = (attributeOffset + 3) & -4;
+					attributeOffset += (index - 11) << 2;
+					continue;
+				}
+
+				u32 attribInfo = (vertexCfg >> (index * 4)) & 0xf;
+				u32 attribType = attribInfo & 0x3;  //  Type of attribute(sbyte/ubyte/short/float)
+				u32 size = (attribInfo >> 2) + 1;   // Total number of components
+
+				attr.componentCount = size;
+				attr.offset = attributeOffset;
+				attr.type = attribType;
+			}
+
 			buffer++;
+		} else {
+			vec4f& fixedAttr = shaderUnit.vs.fixedAttributes[attrCount];
+
+			for (int i = 0; i < 4; i++) {
+				attr.fixedValue[i] = fixedAttr[i].toFloat32();
+			}
 		}
 	}
 

src/core/renderer_gl/renderer_gl.cpp

@@ -1115,5 +1115,15 @@ void RendererGL::initUbershader(OpenGL::Program& program) {
 }
 
 void RendererGL::accelerateVertexUpload(ShaderUnit& shaderUnit, PICA::DrawAcceleration* accel) {
+	u32 buffer = 0;  // Vertex buffer index for non-fixed attributes
+	u32 attrCount = 0;
 
+	const u32 totalAttribCount = accel->totalAttribCount;
+
+	static constexpr GLenum attributeFormats[4] = {
+		GL_BYTE,           // 0: Signed byte
+		GL_UNSIGNED_BYTE,  // 1: Unsigned byte
+		GL_SHORT,          // 2: Short
+		GL_FLOAT,          // 3: Float
+	};
 }