perf(渲染): 优化渲染性能并添加统计功能
- 实现全局UBO双缓冲机制减少CPU-GPU等待 - 添加渲染统计功能，每60帧输出一次性能数据 - 优化命令列表状态缓存减少冗余OpenGL调用 - 改进材质UBO管理，支持批量更新和CPU缓冲区 - 重构命令队列执行逻辑，支持双缓冲和统计收集
This commit is contained in:
parent
ec6ced9db2
commit
717112c437
|
|
@ -123,9 +123,28 @@ struct CommandBatch {
|
|||
*
|
||||
* 对绘制命令进行排序以优化渲染性能
|
||||
* 排序优先级：材质（管线）> 深度 > 层
|
||||
* 使用对象池复用命令内存，减少每帧分配
|
||||
*/
|
||||
class CommandSorter {
|
||||
public:
|
||||
/**
|
||||
* @brief 默认构造函数
|
||||
*/
|
||||
CommandSorter();
|
||||
|
||||
/**
|
||||
* @brief 析构函数
|
||||
*/
|
||||
~CommandSorter();
|
||||
|
||||
// 禁止拷贝
|
||||
CommandSorter(const CommandSorter&) = delete;
|
||||
CommandSorter& operator=(const CommandSorter&) = delete;
|
||||
|
||||
// 允许移动
|
||||
CommandSorter(CommandSorter&&) noexcept;
|
||||
CommandSorter& operator=(CommandSorter&&) noexcept;
|
||||
|
||||
/**
|
||||
* @brief 添加绘制命令
|
||||
* @param cmd 绘制命令
|
||||
|
|
@ -151,16 +170,24 @@ public:
|
|||
* @brief 获取命令数量
|
||||
* @return 命令数量
|
||||
*/
|
||||
uint32_t getCount() const { return static_cast<uint32_t>(commands_.size()); }
|
||||
uint32_t getCount() const { return commandCount_; }
|
||||
|
||||
/**
|
||||
* @brief 清空所有命令
|
||||
* @brief 清空所有命令（保留内存）
|
||||
*/
|
||||
void clear();
|
||||
|
||||
/**
|
||||
* @brief 预分配命令缓冲区
|
||||
* @param capacity 预分配的容量
|
||||
*/
|
||||
void reserve(uint32_t capacity);
|
||||
|
||||
private:
|
||||
std::vector<DrawCommand> commands_;
|
||||
std::vector<uint32_t> sortedIndices_;
|
||||
std::vector<DrawCommand> commands_; // 命令缓冲区（复用）
|
||||
std::vector<uint32_t> sortedIndices_; // 排序索引缓冲区（复用）
|
||||
uint32_t commandCount_ = 0; // 当前命令数量
|
||||
static constexpr uint32_t INITIAL_CAPACITY = 1024; // 初始容量
|
||||
};
|
||||
|
||||
/**
|
||||
|
|
@ -297,8 +324,9 @@ public:
|
|||
* @brief 执行所有命令
|
||||
*
|
||||
* 排序、批处理并执行所有提交的命令
|
||||
* @param frameIndex 当前帧索引（用于双缓冲）
|
||||
*/
|
||||
void execute();
|
||||
void execute(uint32_t frameIndex);
|
||||
|
||||
/**
|
||||
* @brief 更新全局 UBO 数据
|
||||
|
|
@ -306,9 +334,10 @@ public:
|
|||
* @param deltaTime 帧时间
|
||||
* @param screenWidth 屏幕宽度
|
||||
* @param screenHeight 屏幕高度
|
||||
* @param frameIndex 当前帧索引（用于双缓冲）
|
||||
*/
|
||||
void updateGlobalUBO(const Mat4& viewProjection, float deltaTime,
|
||||
uint32_t screenWidth, uint32_t screenHeight);
|
||||
void updateGlobalUBO(const Mat4& viewProjection, float deltaTime,
|
||||
uint32_t screenWidth, uint32_t screenHeight, uint32_t frameIndex);
|
||||
|
||||
/**
|
||||
* @brief 获取当前命令数量
|
||||
|
|
@ -322,6 +351,17 @@ public:
|
|||
*/
|
||||
RHICommandList* getCommandList() const { return commandList_.get(); }
|
||||
|
||||
/**
|
||||
* @brief 获取渲染统计信息
|
||||
* @return 渲染统计
|
||||
*/
|
||||
const RenderStats& getStats() const { return stats_; }
|
||||
|
||||
/**
|
||||
* @brief 重置统计信息
|
||||
*/
|
||||
void resetStats() { stats_ = {}; }
|
||||
|
||||
private:
|
||||
CommandSorter sorter_;
|
||||
CommandBatcher batcher_;
|
||||
|
|
@ -331,6 +371,9 @@ private:
|
|||
// UBO 管理器
|
||||
std::unique_ptr<UniformBufferManager> uboManager_;
|
||||
|
||||
// 渲染统计
|
||||
RenderStats stats_;
|
||||
|
||||
// 全局 UBO 数据 - 必须与着色器中的 std140 布局完全匹配
|
||||
// layout(std140, binding = 0) uniform GlobalUBO {
|
||||
// mat4 uViewProjection; // 64 bytes, offset 0
|
||||
|
|
@ -358,7 +401,7 @@ private:
|
|||
|
||||
// 当前材质 UBO 缓冲区
|
||||
UniformBuffer* currentMaterialUBO_ = nullptr;
|
||||
uint32_t currentMaterialUBOOffset_ = 0;
|
||||
uint32_t materialUBOBufferOffset_ = 0;
|
||||
|
||||
/**
|
||||
* @brief 获取或创建材质 ID
|
||||
|
|
@ -371,15 +414,27 @@ private:
|
|||
* @brief 执行单个批次
|
||||
* @param batchIndex 批次索引
|
||||
* @param batch 命令批次
|
||||
* @param frameIndex 当前帧索引（用于双缓冲）
|
||||
*/
|
||||
void executeBatch(uint32_t batchIndex, const CommandBatch &batch);
|
||||
void executeBatch(uint32_t batchIndex, const CommandBatch &batch, uint32_t frameIndex);
|
||||
|
||||
/**
|
||||
* @brief 分配材质 UBO 空间
|
||||
* @brief 分配材质 UBO 空间（使用 CPU 缓冲区）
|
||||
* @param size 需要的空间大小
|
||||
* @return 分配的 UBO 指针和偏移量
|
||||
* @return 分配的 UBO 指针（nullptr 表示使用 CPU 缓冲区）和偏移量
|
||||
*/
|
||||
std::pair<UniformBuffer*, uint32_t> allocateMaterialUBO(uint32_t size);
|
||||
|
||||
/**
|
||||
* @brief 将材质 UBO CPU 缓冲区数据刷新到 GPU
|
||||
*/
|
||||
void flushMaterialUBOToGPU();
|
||||
|
||||
/**
|
||||
* @brief 获取当前材质 UBO
|
||||
* @return 当前材质 UBO 指针
|
||||
*/
|
||||
UniformBuffer* getCurrentMaterialUBO() const;
|
||||
};
|
||||
|
||||
} // namespace extra2d
|
||||
|
|
|
|||
|
|
@ -89,12 +89,88 @@ public:
|
|||
void setUniform(const char* name, const Mat4& value) override;
|
||||
|
||||
private:
|
||||
// 状态缓存机制 - 避免冗余的 OpenGL 状态切换
|
||||
struct StateCache {
|
||||
// 管线状态
|
||||
GLPipeline* pipeline = nullptr;
|
||||
GLuint shaderProgram = 0;
|
||||
|
||||
// 视口状态
|
||||
Viewport viewport;
|
||||
bool viewportValid = false;
|
||||
|
||||
// 裁剪状态
|
||||
ScissorRect scissor{0, 0, 0, 0};
|
||||
bool scissorValid = false;
|
||||
bool scissorEnabled = false;
|
||||
|
||||
// 缓冲区状态
|
||||
GLBuffer* vertexBuffers[4] = {nullptr, nullptr, nullptr, nullptr}; // 支持最多4个顶点缓冲区槽
|
||||
uint32_t vertexBufferOffsets[4] = {0, 0, 0, 0};
|
||||
GLBuffer* indexBuffer = nullptr;
|
||||
|
||||
// Uniform 缓冲区状态
|
||||
struct UBOBinding {
|
||||
GLBuffer* buffer = nullptr;
|
||||
uint32_t offset = 0;
|
||||
uint32_t size = 0;
|
||||
bool valid = false;
|
||||
};
|
||||
UBOBinding uniformBuffers[4]; // 支持最多4个 UBO 槽
|
||||
|
||||
// 纹理状态
|
||||
struct TextureBinding {
|
||||
GLTexture* texture = nullptr;
|
||||
bool valid = false;
|
||||
};
|
||||
TextureBinding textures[8]; // 支持最多8个纹理槽
|
||||
|
||||
// 帧缓冲状态
|
||||
GLFramebuffer* framebuffer = nullptr;
|
||||
|
||||
// 重置所有状态缓存
|
||||
void reset() {
|
||||
pipeline = nullptr;
|
||||
shaderProgram = 0;
|
||||
viewportValid = false;
|
||||
scissorValid = false;
|
||||
scissorEnabled = false;
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
vertexBuffers[i] = nullptr;
|
||||
vertexBufferOffsets[i] = 0;
|
||||
uniformBuffers[i] = {};
|
||||
}
|
||||
indexBuffer = nullptr;
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
textures[i] = {};
|
||||
}
|
||||
framebuffer = nullptr;
|
||||
}
|
||||
};
|
||||
|
||||
bool recording_ = false;
|
||||
GLPipeline *currentPipeline_ = nullptr;
|
||||
GLBuffer *currentVertexBuffer_ = nullptr;
|
||||
GLBuffer *currentIndexBuffer_ = nullptr;
|
||||
GLFramebuffer *currentFramebuffer_ = nullptr;
|
||||
GLuint currentShaderProgram_ = 0;
|
||||
StateCache stateCache_;
|
||||
|
||||
// 统计信息（调试用）
|
||||
struct Stats {
|
||||
uint32_t pipelineChanges = 0;
|
||||
uint32_t textureChanges = 0;
|
||||
uint32_t bufferChanges = 0;
|
||||
uint32_t viewportChanges = 0;
|
||||
uint32_t redundantPipelineChanges = 0;
|
||||
uint32_t redundantTextureChanges = 0;
|
||||
uint32_t redundantBufferChanges = 0;
|
||||
|
||||
void reset() {
|
||||
pipelineChanges = 0;
|
||||
textureChanges = 0;
|
||||
bufferChanges = 0;
|
||||
viewportChanges = 0;
|
||||
redundantPipelineChanges = 0;
|
||||
redundantTextureChanges = 0;
|
||||
redundantBufferChanges = 0;
|
||||
}
|
||||
} stats_;
|
||||
};
|
||||
|
||||
} // namespace extra2d
|
||||
|
|
|
|||
|
|
@ -86,6 +86,7 @@ private:
|
|||
*
|
||||
* 管理多个 UBO 的分配和回收
|
||||
* 支持每帧重置和对象池复用
|
||||
* 支持双缓冲机制减少 CPU-GPU 等待
|
||||
*/
|
||||
class UniformBufferManager {
|
||||
public:
|
||||
|
|
@ -119,10 +120,11 @@ public:
|
|||
void shutdown();
|
||||
|
||||
/**
|
||||
* @brief 获取全局 UBO
|
||||
* @brief 获取当前帧的全局 UBO（双缓冲）
|
||||
* @param frameIndex 当前帧索引
|
||||
* @return 全局 UBO 指针
|
||||
*/
|
||||
UniformBuffer* getGlobalUBO();
|
||||
UniformBuffer* getGlobalUBO(uint32_t frameIndex);
|
||||
|
||||
/**
|
||||
* @brief 获取或创建材质 UBO
|
||||
|
|
@ -139,25 +141,57 @@ public:
|
|||
void resetMaterialUBOs();
|
||||
|
||||
/**
|
||||
* @brief 更新全局 UBO 数据
|
||||
* @brief 更新全局 UBO 数据（双缓冲）
|
||||
* @param data 数据指针
|
||||
* @param size 数据大小
|
||||
* @param frameIndex 当前帧索引
|
||||
*/
|
||||
void updateGlobalUBO(const void* data, uint32_t size);
|
||||
void updateGlobalUBO(const void* data, uint32_t size, uint32_t frameIndex);
|
||||
|
||||
/**
|
||||
* @brief 批量更新材质 UBO 数据
|
||||
* @param data 材质数据指针
|
||||
* @param size 数据大小
|
||||
* @param offset 偏移量
|
||||
*/
|
||||
void batchUpdateMaterialUBO(const void* data, uint32_t size, uint32_t offset);
|
||||
|
||||
/**
|
||||
* @brief 获取材质 UBO 的 CPU 缓冲区指针（用于批量更新）
|
||||
* @return CPU 缓冲区指针
|
||||
*/
|
||||
uint8_t* getMaterialUBOBuffer() { return materialUBOBuffer_.data(); }
|
||||
|
||||
/**
|
||||
* @brief 获取材质 UBO 缓冲区大小
|
||||
* @return 缓冲区大小
|
||||
*/
|
||||
uint32_t getMaterialUBOBufferSize() const { return static_cast<uint32_t>(materialUBOBuffer_.size()); }
|
||||
|
||||
/**
|
||||
* @brief 刷新材质 UBO 数据到 GPU
|
||||
*/
|
||||
void flushMaterialUBO();
|
||||
|
||||
private:
|
||||
// 全局 UBO（用于 viewProjection、time 等全局数据）
|
||||
std::unique_ptr<UniformBuffer> globalUBO_;
|
||||
// 全局 UBO 双缓冲（用于 viewProjection、time 等全局数据）
|
||||
std::array<std::unique_ptr<UniformBuffer>, 2> globalUBOs_;
|
||||
|
||||
// 材质 UBO 池
|
||||
std::vector<std::unique_ptr<UniformBuffer>> materialUBOPool_;
|
||||
uint32_t currentUBOIndex_ = 0;
|
||||
|
||||
// 材质 UBO CPU 缓冲区（用于批量更新）
|
||||
std::vector<uint8_t> materialUBOBuffer_;
|
||||
uint32_t materialUBOBufferOffset_ = 0;
|
||||
UniformBuffer* currentMaterialUBO_ = nullptr;
|
||||
|
||||
// 常量
|
||||
static constexpr uint32_t INITIAL_UBO_POOL_SIZE = 16;
|
||||
static constexpr uint32_t GLOBAL_UBO_SIZE = 256; // 足够存储 viewProjection + time + screenSize
|
||||
static constexpr uint32_t GLOBAL_UBO_BINDING = 0; // 全局 UBO 绑定槽位
|
||||
static constexpr uint32_t MATERIAL_UBO_BINDING = 1; // 材质 UBO 绑定槽位
|
||||
static constexpr uint32_t MATERIAL_UBO_BUFFER_SIZE = 1024 * 1024; // 1MB 材质 UBO 缓冲区
|
||||
};
|
||||
|
||||
} // namespace extra2d
|
||||
|
|
|
|||
|
|
@ -21,24 +21,69 @@ namespace extra2d {
|
|||
// CommandSorter 实现
|
||||
// ========================================
|
||||
|
||||
CommandSorter::CommandSorter() {
|
||||
// 预分配初始容量
|
||||
commands_.reserve(INITIAL_CAPACITY);
|
||||
sortedIndices_.reserve(INITIAL_CAPACITY);
|
||||
}
|
||||
|
||||
CommandSorter::~CommandSorter() = default;
|
||||
|
||||
CommandSorter::CommandSorter(CommandSorter&& other) noexcept
|
||||
: commands_(std::move(other.commands_)),
|
||||
sortedIndices_(std::move(other.sortedIndices_)),
|
||||
commandCount_(other.commandCount_) {
|
||||
other.commandCount_ = 0;
|
||||
}
|
||||
|
||||
CommandSorter& CommandSorter::operator=(CommandSorter&& other) noexcept {
|
||||
if (this != &other) {
|
||||
commands_ = std::move(other.commands_);
|
||||
sortedIndices_ = std::move(other.sortedIndices_);
|
||||
commandCount_ = other.commandCount_;
|
||||
other.commandCount_ = 0;
|
||||
}
|
||||
return *this;
|
||||
}
|
||||
|
||||
uint32_t CommandSorter::addCommand(const DrawCommand &cmd) {
|
||||
uint32_t index = static_cast<uint32_t>(commands_.size());
|
||||
commands_.push_back(cmd);
|
||||
sortedIndices_.push_back(index);
|
||||
uint32_t index = commandCount_;
|
||||
|
||||
// 如果缓冲区不够大，扩展它
|
||||
if (index >= commands_.size()) {
|
||||
commands_.push_back(cmd);
|
||||
sortedIndices_.push_back(index);
|
||||
} else {
|
||||
commands_[index] = cmd;
|
||||
sortedIndices_[index] = index;
|
||||
}
|
||||
|
||||
commandCount_++;
|
||||
return index;
|
||||
}
|
||||
|
||||
void CommandSorter::sort() {
|
||||
if (commandCount_ == 0) return;
|
||||
|
||||
// 只排序有效范围的索引
|
||||
auto indicesBegin = sortedIndices_.begin();
|
||||
auto indicesEnd = sortedIndices_.begin() + commandCount_;
|
||||
|
||||
// 使用稳定排序保持相同键的命令顺序
|
||||
std::stable_sort(sortedIndices_.begin(), sortedIndices_.end(),
|
||||
std::stable_sort(indicesBegin, indicesEnd,
|
||||
[this](uint32_t a, uint32_t b) {
|
||||
return commands_[a].key < commands_[b].key;
|
||||
});
|
||||
}
|
||||
|
||||
void CommandSorter::clear() {
|
||||
commands_.clear();
|
||||
sortedIndices_.clear();
|
||||
// 重置计数器，保留内存
|
||||
commandCount_ = 0;
|
||||
}
|
||||
|
||||
void CommandSorter::reserve(uint32_t capacity) {
|
||||
commands_.reserve(capacity);
|
||||
sortedIndices_.reserve(capacity);
|
||||
}
|
||||
|
||||
// ========================================
|
||||
|
|
@ -117,12 +162,12 @@ CommandQueue::CommandQueue(CommandQueue &&other) noexcept
|
|||
nextMaterialId_(other.nextMaterialId_),
|
||||
materialIds_(std::move(other.materialIds_)),
|
||||
currentMaterialUBO_(other.currentMaterialUBO_),
|
||||
currentMaterialUBOOffset_(other.currentMaterialUBOOffset_) {
|
||||
materialUBOBufferOffset_(other.materialUBOBufferOffset_) {
|
||||
other.context_ = nullptr;
|
||||
other.globalUBOData_ = {};
|
||||
other.nextMaterialId_ = 1;
|
||||
other.currentMaterialUBO_ = nullptr;
|
||||
other.currentMaterialUBOOffset_ = 0;
|
||||
other.materialUBOBufferOffset_ = 0;
|
||||
}
|
||||
|
||||
CommandQueue &CommandQueue::operator=(CommandQueue &&other) noexcept {
|
||||
|
|
@ -139,13 +184,13 @@ CommandQueue &CommandQueue::operator=(CommandQueue &&other) noexcept {
|
|||
nextMaterialId_ = other.nextMaterialId_;
|
||||
materialIds_ = std::move(other.materialIds_);
|
||||
currentMaterialUBO_ = other.currentMaterialUBO_;
|
||||
currentMaterialUBOOffset_ = other.currentMaterialUBOOffset_;
|
||||
materialUBOBufferOffset_ = other.materialUBOBufferOffset_;
|
||||
|
||||
other.context_ = nullptr;
|
||||
other.globalUBOData_ = {};
|
||||
other.nextMaterialId_ = 1;
|
||||
other.currentMaterialUBO_ = nullptr;
|
||||
other.currentMaterialUBOOffset_ = 0;
|
||||
other.materialUBOBufferOffset_ = 0;
|
||||
}
|
||||
return *this;
|
||||
}
|
||||
|
|
@ -204,17 +249,19 @@ void CommandQueue::beginFrame() {
|
|||
batcher_.clear();
|
||||
materialIds_.clear();
|
||||
nextMaterialId_ = 1;
|
||||
materialUBOData_.clear();
|
||||
|
||||
// 重置材质 UBO 分配状态
|
||||
// 重置材质 UBO 缓冲区（保留容量，避免重新分配）
|
||||
materialUBOBufferOffset_ = 0;
|
||||
currentMaterialUBO_ = nullptr;
|
||||
currentMaterialUBOOffset_ = 0;
|
||||
|
||||
// 重置 UBO 管理器的材质 UBO 池
|
||||
if (uboManager_) {
|
||||
uboManager_->resetMaterialUBOs();
|
||||
}
|
||||
|
||||
// 重置统计
|
||||
stats_ = {};
|
||||
|
||||
// 开始录制命令
|
||||
if (commandList_) {
|
||||
commandList_->begin();
|
||||
|
|
@ -244,24 +291,54 @@ std::pair<UniformBuffer*, uint32_t> CommandQueue::allocateMaterialUBO(uint32_t s
|
|||
return {nullptr, 0};
|
||||
}
|
||||
|
||||
// 如果当前 UBO 没有足够的空间，获取一个新的
|
||||
if (currentMaterialUBO_ == nullptr ||
|
||||
currentMaterialUBOOffset_ + size > currentMaterialUBO_->getSize()) {
|
||||
currentMaterialUBO_ = uboManager_->acquireMaterialUBO(size);
|
||||
currentMaterialUBOOffset_ = 0;
|
||||
// OpenGL 要求 UBO 偏移对齐到 GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT (通常是 256)
|
||||
static constexpr uint32_t UBO_ALIGNMENT = 256;
|
||||
|
||||
// 使用批量更新机制：先分配到 CPU 缓冲区
|
||||
uint32_t offset = materialUBOBufferOffset_;
|
||||
// 对齐到 UBO_ALIGNMENT 字节
|
||||
offset = (offset + UBO_ALIGNMENT - 1) & ~(UBO_ALIGNMENT - 1);
|
||||
|
||||
uint32_t alignedSize = (size + UBO_ALIGNMENT - 1) & ~(UBO_ALIGNMENT - 1);
|
||||
|
||||
// 检查 CPU 缓冲区是否有足够空间
|
||||
if (offset + alignedSize > materialUBOData_.capacity()) {
|
||||
// 如果缓冲区已满，先刷新到 GPU
|
||||
flushMaterialUBOToGPU();
|
||||
offset = 0; // 重置偏移量
|
||||
}
|
||||
|
||||
// 确保缓冲区足够大
|
||||
if (offset + alignedSize > materialUBOData_.size()) {
|
||||
materialUBOData_.resize(offset + alignedSize);
|
||||
}
|
||||
|
||||
materialUBOBufferOffset_ = offset + alignedSize;
|
||||
|
||||
return {nullptr, offset}; // 返回 nullptr 表示使用 CPU 缓冲区，offset 是 CPU 缓冲区偏移
|
||||
}
|
||||
|
||||
void CommandQueue::flushMaterialUBOToGPU() {
|
||||
if (materialUBOBufferOffset_ == 0) {
|
||||
return;
|
||||
}
|
||||
|
||||
// 获取一个足够大的 UBO
|
||||
currentMaterialUBO_ = uboManager_->acquireMaterialUBO(materialUBOBufferOffset_);
|
||||
if (!currentMaterialUBO_) {
|
||||
return {nullptr, 0};
|
||||
E2D_LOG_ERROR("Failed to acquire material UBO for flush");
|
||||
return;
|
||||
}
|
||||
|
||||
uint32_t offset = currentMaterialUBOOffset_;
|
||||
currentMaterialUBOOffset_ += size;
|
||||
// 批量更新到 GPU
|
||||
currentMaterialUBO_->update(materialUBOData_.data(), materialUBOBufferOffset_, 0);
|
||||
|
||||
// 对齐到 16 字节（std140 要求）
|
||||
currentMaterialUBOOffset_ = (currentMaterialUBOOffset_ + 15) & ~15;
|
||||
// 重置 CPU 缓冲区偏移
|
||||
materialUBOBufferOffset_ = 0;
|
||||
}
|
||||
|
||||
return {currentMaterialUBO_, offset};
|
||||
UniformBuffer* CommandQueue::getCurrentMaterialUBO() const {
|
||||
return currentMaterialUBO_;
|
||||
}
|
||||
|
||||
void CommandQueue::submitDraw(Ptr<Material> material, Ptr<Mesh> mesh,
|
||||
|
|
@ -302,28 +379,27 @@ void CommandQueue::submitDraw(Ptr<Material> material, Ptr<Mesh> mesh,
|
|||
}
|
||||
}
|
||||
|
||||
// 分配材质 UBO 空间并更新数据
|
||||
// 分配材质 UBO 空间（使用 CPU 缓冲区）
|
||||
uint32_t materialDataSize = material->getDataSize();
|
||||
if (materialDataSize > 0) {
|
||||
auto [ubo, offset] = allocateMaterialUBO(materialDataSize);
|
||||
if (ubo) {
|
||||
// 复制材质数据到临时缓冲区，以便修改颜色
|
||||
std::vector<uint8_t> uboData(materialDataSize);
|
||||
std::memcpy(uboData.data(), material->getData(), materialDataSize);
|
||||
(void)ubo; // ubo 为 nullptr，使用 CPU 缓冲区
|
||||
|
||||
// 复制材质数据到 CPU 缓冲区，并修改颜色
|
||||
if (offset + materialDataSize <= materialUBOData_.size()) {
|
||||
std::memcpy(materialUBOData_.data() + offset, material->getData(), materialDataSize);
|
||||
|
||||
// 将实例颜色应用到 UBO 数据中的 uColor 参数
|
||||
auto layout = material->getLayout();
|
||||
if (layout) {
|
||||
const auto* param = layout->getParam("uColor");
|
||||
if (param && param->type == MaterialParamType::Color) {
|
||||
std::memcpy(uboData.data() + param->offset, &color.r, sizeof(float) * 4);
|
||||
std::memcpy(materialUBOData_.data() + offset + param->offset, &color.r, sizeof(float) * 4);
|
||||
}
|
||||
}
|
||||
|
||||
ubo->update(uboData.data(), materialDataSize, offset);
|
||||
cmd.materialUBO = BufferHandle(ubo->getRHIBuffer());
|
||||
cmd.materialUBOSize = materialDataSize;
|
||||
cmd.materialUBOOffset = offset;
|
||||
cmd.materialUBOSize = materialDataSize;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -366,15 +442,17 @@ void CommandQueue::submitDrawInstanced(Ptr<Material> material, Ptr<Mesh> mesh,
|
|||
}
|
||||
}
|
||||
|
||||
// 分配材质 UBO 空间并更新数据
|
||||
// 分配材质 UBO 空间（使用 CPU 缓冲区）
|
||||
uint32_t materialDataSize = material->getDataSize();
|
||||
if (materialDataSize > 0) {
|
||||
auto [ubo, offset] = allocateMaterialUBO(materialDataSize);
|
||||
if (ubo) {
|
||||
ubo->update(material->getData(), materialDataSize, offset);
|
||||
cmd.materialUBO = BufferHandle(ubo->getRHIBuffer());
|
||||
cmd.materialUBOSize = materialDataSize;
|
||||
(void)ubo; // ubo 为 nullptr，使用 CPU 缓冲区
|
||||
|
||||
// 复制材质数据到 CPU 缓冲区
|
||||
if (offset + materialDataSize <= materialUBOData_.size()) {
|
||||
std::memcpy(materialUBOData_.data() + offset, material->getData(), materialDataSize);
|
||||
cmd.materialUBOOffset = offset;
|
||||
cmd.materialUBOSize = materialDataSize;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -408,7 +486,7 @@ void CommandQueue::setViewport(int32_t x, int32_t y, int32_t width,
|
|||
}
|
||||
|
||||
void CommandQueue::updateGlobalUBO(const Mat4& viewProjection, float deltaTime,
|
||||
uint32_t screenWidth, uint32_t screenHeight) {
|
||||
uint32_t screenWidth, uint32_t screenHeight, uint32_t frameIndex) {
|
||||
if (!uboManager_) {
|
||||
E2D_LOG_WARN("CommandQueue::updateGlobalUBO: uboManager is null");
|
||||
return;
|
||||
|
|
@ -425,16 +503,19 @@ void CommandQueue::updateGlobalUBO(const Mat4& viewProjection, float deltaTime,
|
|||
globalUBOData_.screenSize[0] = static_cast<float>(screenWidth);
|
||||
globalUBOData_.screenSize[1] = static_cast<float>(screenHeight);
|
||||
|
||||
// 更新 UBO
|
||||
uboManager_->updateGlobalUBO(&globalUBOData_, sizeof(globalUBOData_));
|
||||
// 使用双缓冲更新 UBO
|
||||
uboManager_->updateGlobalUBO(&globalUBOData_, sizeof(globalUBOData_), frameIndex);
|
||||
}
|
||||
|
||||
void CommandQueue::execute() {
|
||||
void CommandQueue::execute(uint32_t frameIndex) {
|
||||
if (!commandList_) {
|
||||
E2D_LOG_ERROR("CommandQueue::execute: commandList is null");
|
||||
return;
|
||||
}
|
||||
|
||||
// 在排序前刷新材质 UBO 数据到 GPU
|
||||
flushMaterialUBOToGPU();
|
||||
|
||||
// 排序命令
|
||||
sorter_.sort();
|
||||
|
||||
|
|
@ -443,14 +524,14 @@ void CommandQueue::execute() {
|
|||
|
||||
// 执行批次
|
||||
for (uint32_t i = 0; i < batcher_.getBatchCount(); ++i) {
|
||||
executeBatch(i, batcher_.getBatch(i));
|
||||
executeBatch(i, batcher_.getBatch(i), frameIndex);
|
||||
}
|
||||
|
||||
// 提交命令到 GPU
|
||||
commandList_->submit();
|
||||
}
|
||||
|
||||
void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch) {
|
||||
void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch, uint32_t frameIndex) {
|
||||
if (!commandList_) {
|
||||
return;
|
||||
}
|
||||
|
|
@ -458,15 +539,17 @@ void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch)
|
|||
// 绑定管线
|
||||
if (batch.pipeline.isValid()) {
|
||||
commandList_->setPipeline(batch.pipeline.get());
|
||||
stats_.pipelineBinds++;
|
||||
} else {
|
||||
E2D_LOG_WARN("Batch has no valid pipeline!");
|
||||
}
|
||||
|
||||
// 绑定全局 UBO (binding = 0)
|
||||
// 绑定全局 UBO (binding = 0) - 使用双缓冲
|
||||
if (uboManager_) {
|
||||
UniformBuffer* globalUBO = uboManager_->getGlobalUBO();
|
||||
UniformBuffer* globalUBO = uboManager_->getGlobalUBO(frameIndex);
|
||||
if (globalUBO) {
|
||||
commandList_->setUniformBuffer(0, globalUBO->getRHIBuffer());
|
||||
stats_.bufferBinds++;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -475,16 +558,9 @@ void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch)
|
|||
for (uint32_t i = 0; i < batch.textureCount; ++i) {
|
||||
if (batch.textures[i].isValid()) {
|
||||
commandList_->setTexture(i, batch.textures[i].get());
|
||||
stats_.textureBinds++;
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// 如果没有纹理，绑定默认的白色纹理
|
||||
auto* rhiModule = RHIModule::get();
|
||||
if (rhiModule && rhiModule->getDevice()) {
|
||||
// 使用默认纹理（白色像素）
|
||||
// 注意：这里应该使用 AssetsModule 的默认纹理
|
||||
// 暂时跳过，因为我们需要访问 AssetsModule
|
||||
}
|
||||
}
|
||||
|
||||
// 执行批次中的所有命令
|
||||
|
|
@ -494,6 +570,7 @@ void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch)
|
|||
// 绑定顶点缓冲区
|
||||
if (cmd.vertexBuffer.isValid()) {
|
||||
commandList_->setVertexBuffer(0, cmd.vertexBuffer.get(), 0);
|
||||
stats_.bufferBinds++;
|
||||
} else {
|
||||
E2D_LOG_WARN("Draw command has no valid vertex buffer!");
|
||||
}
|
||||
|
|
@ -501,16 +578,19 @@ void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch)
|
|||
// 绑定实例缓冲区（实例化渲染）
|
||||
if (cmd.isInstanced() && cmd.instanceBuffer.isValid()) {
|
||||
commandList_->setVertexBuffer(1, cmd.instanceBuffer.get(), 0, cmd.instanceBufferStride);
|
||||
stats_.bufferBinds++;
|
||||
}
|
||||
|
||||
// 绑定索引缓冲区（如果有）
|
||||
if (cmd.isIndexed() && cmd.indexBuffer.isValid()) {
|
||||
commandList_->setIndexBuffer(cmd.indexBuffer.get(), IndexType::UInt16, 0);
|
||||
stats_.bufferBinds++;
|
||||
}
|
||||
|
||||
// 绑定材质 UBO (binding = 1)
|
||||
if (cmd.materialUBO.isValid()) {
|
||||
commandList_->setUniformBuffer(1, cmd.materialUBO.get(), cmd.materialUBOOffset, cmd.materialUBOSize);
|
||||
if (cmd.materialUBOSize > 0 && currentMaterialUBO_) {
|
||||
commandList_->setUniformBuffer(1, currentMaterialUBO_->getRHIBuffer(), cmd.materialUBOOffset, cmd.materialUBOSize);
|
||||
stats_.bufferBinds++;
|
||||
}
|
||||
|
||||
// 设置模型矩阵（仅在非实例化渲染时使用）
|
||||
|
|
@ -522,16 +602,25 @@ void CommandQueue::executeBatch(uint32_t batchIndex, const CommandBatch &batch)
|
|||
if (cmd.isInstanced()) {
|
||||
if (cmd.isIndexed()) {
|
||||
commandList_->drawIndexed(cmd.indexCount, 0, 0, cmd.instanceCount, 0);
|
||||
stats_.drawCalls++;
|
||||
stats_.triangles += (cmd.indexCount / 3) * cmd.instanceCount;
|
||||
} else {
|
||||
commandList_->draw(cmd.vertexCount, 0, cmd.instanceCount, 0);
|
||||
stats_.drawCalls++;
|
||||
stats_.triangles += (cmd.vertexCount / 3) * cmd.instanceCount;
|
||||
}
|
||||
} else {
|
||||
if (cmd.isIndexed()) {
|
||||
commandList_->drawIndexed(cmd.indexCount, 0, 0, 1, 0);
|
||||
stats_.drawCalls++;
|
||||
stats_.triangles += cmd.indexCount / 3;
|
||||
} else {
|
||||
commandList_->draw(cmd.vertexCount, 0, 1, 0);
|
||||
stats_.drawCalls++;
|
||||
stats_.triangles += cmd.vertexCount / 3;
|
||||
}
|
||||
}
|
||||
stats_.vertices += cmd.isInstanced() ? (cmd.vertexCount * cmd.instanceCount) : cmd.vertexCount;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -179,7 +179,7 @@ bool RenderGraph::compile() {
|
|||
return true;
|
||||
}
|
||||
|
||||
void RenderGraph::execute(float deltaTime, const Mat4 &viewProjection) {
|
||||
void RenderGraph::execute(float deltaTime, const Mat4& viewProjection) {
|
||||
if (!compiled_) {
|
||||
if (!compile()) {
|
||||
E2D_LOG_ERROR("Failed to compile RenderGraph");
|
||||
|
|
@ -187,9 +187,9 @@ void RenderGraph::execute(float deltaTime, const Mat4 &viewProjection) {
|
|||
}
|
||||
}
|
||||
|
||||
// 更新全局 UBO
|
||||
// 更新全局 UBO（使用双缓冲）
|
||||
commandQueue_.updateGlobalUBO(viewProjection, deltaTime, outputWidth_,
|
||||
outputHeight_);
|
||||
outputHeight_, frameIndex_);
|
||||
|
||||
// 获取 RHI 上下文
|
||||
auto *rhiModule = RHIModule::get();
|
||||
|
|
@ -213,8 +213,8 @@ void RenderGraph::execute(float deltaTime, const Mat4 &viewProjection) {
|
|||
}
|
||||
}
|
||||
|
||||
// 执行命令队列
|
||||
commandQueue_.execute();
|
||||
// 执行命令队列（传递帧索引用于双缓冲）
|
||||
commandQueue_.execute(frameIndex_);
|
||||
|
||||
// 结束帧
|
||||
commandQueue_.endFrame();
|
||||
|
|
|
|||
|
|
@ -257,7 +257,16 @@ void RendererModule::onRenderEnd() {
|
|||
|
||||
// 获取统计信息
|
||||
if (commandQueue_) {
|
||||
stats_.drawCalls = commandQueue_->getCommandCount();
|
||||
const auto& stats = commandQueue_->getStats();
|
||||
stats_.drawCalls = stats.drawCalls;
|
||||
|
||||
// 每60帧输出一次统计信息
|
||||
static uint32_t frameCount = 0;
|
||||
if (++frameCount % 60 == 0) {
|
||||
E2D_LOG_INFO("Render Stats: DrawCalls={}, Triangles={}, Vertices={}, PipelineBinds={}, TextureBinds={}, BufferBinds={}",
|
||||
stats.drawCalls, stats.triangles, stats.vertices,
|
||||
stats.pipelineBinds, stats.textureBinds, stats.bufferBinds);
|
||||
}
|
||||
}
|
||||
|
||||
// 渲染完成
|
||||
|
|
|
|||
|
|
@ -15,6 +15,12 @@ GLCommandList::~GLCommandList() = default;
|
|||
void GLCommandList::begin() {
|
||||
// 开始记录命令
|
||||
recording_ = true;
|
||||
|
||||
// 重置状态缓存
|
||||
stateCache_.reset();
|
||||
|
||||
// 重置统计
|
||||
stats_.reset();
|
||||
}
|
||||
|
||||
void GLCommandList::end() {
|
||||
|
|
@ -34,21 +40,21 @@ void GLCommandList::beginRenderPass(RHIFramebuffer *framebuffer,
|
|||
if (framebuffer) {
|
||||
auto *glFramebuffer = static_cast<GLFramebuffer *>(framebuffer);
|
||||
glFramebuffer->bind();
|
||||
currentFramebuffer_ = glFramebuffer;
|
||||
stateCache_.framebuffer = glFramebuffer;
|
||||
} else {
|
||||
glBindFramebuffer(GL_FRAMEBUFFER, 0);
|
||||
currentFramebuffer_ = nullptr;
|
||||
stateCache_.framebuffer = nullptr;
|
||||
}
|
||||
|
||||
// 禁用2D渲染不需要的OpenGL状态
|
||||
glDisable(GL_DEPTH_TEST); // 禁用深度测试
|
||||
glDisable(GL_CULL_FACE); // 禁用面剔除
|
||||
glDisable(GL_STENCIL_TEST); // 禁用模板测试
|
||||
|
||||
|
||||
// 启用混合（2D渲染通常需要透明度混合）
|
||||
glEnable(GL_BLEND);
|
||||
glBlendFunc(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA);
|
||||
|
||||
|
||||
// 禁用裁剪测试（除非需要）
|
||||
glDisable(GL_SCISSOR_TEST);
|
||||
|
||||
|
|
@ -60,13 +66,27 @@ void GLCommandList::beginRenderPass(RHIFramebuffer *framebuffer,
|
|||
|
||||
void GLCommandList::endRenderPass() {
|
||||
// 结束渲染通道
|
||||
currentFramebuffer_ = nullptr;
|
||||
stateCache_.framebuffer = nullptr;
|
||||
}
|
||||
|
||||
void GLCommandList::setViewport(const Viewport &viewport) {
|
||||
// 状态缓存检查
|
||||
if (stateCache_.viewportValid &&
|
||||
stateCache_.viewport.x == viewport.x &&
|
||||
stateCache_.viewport.y == viewport.y &&
|
||||
stateCache_.viewport.width == viewport.width &&
|
||||
stateCache_.viewport.height == viewport.height) {
|
||||
stats_.redundantPipelineChanges++;
|
||||
return;
|
||||
}
|
||||
|
||||
glViewport(static_cast<GLint>(viewport.x), static_cast<GLint>(viewport.y),
|
||||
static_cast<GLsizei>(viewport.width),
|
||||
static_cast<GLsizei>(viewport.height));
|
||||
|
||||
stateCache_.viewport = viewport;
|
||||
stateCache_.viewportValid = true;
|
||||
stats_.viewportChanges++;
|
||||
}
|
||||
|
||||
void GLCommandList::setScissor(const ScissorRect &scissor) {
|
||||
|
|
@ -74,28 +94,40 @@ void GLCommandList::setScissor(const ScissorRect &scissor) {
|
|||
}
|
||||
|
||||
void GLCommandList::setPipeline(RHIPipeline *pipeline) {
|
||||
if (pipeline) {
|
||||
auto *glPipeline = static_cast<GLPipeline *>(pipeline);
|
||||
glPipeline->bind();
|
||||
currentPipeline_ = glPipeline;
|
||||
|
||||
// 获取 shader program
|
||||
currentShaderProgram_ = glPipeline->getGLProgram();
|
||||
if (!pipeline) return;
|
||||
|
||||
auto *glPipeline = static_cast<GLPipeline *>(pipeline);
|
||||
|
||||
// 状态缓存检查
|
||||
if (stateCache_.pipeline == glPipeline) {
|
||||
stats_.redundantPipelineChanges++;
|
||||
return;
|
||||
}
|
||||
|
||||
glPipeline->bind();
|
||||
stateCache_.pipeline = glPipeline;
|
||||
stateCache_.shaderProgram = glPipeline->getGLProgram();
|
||||
stats_.pipelineChanges++;
|
||||
}
|
||||
|
||||
void GLCommandList::setVertexBuffer(uint32_t slot, RHIBuffer *buffer,
|
||||
uint32_t offset, uint32_t stride) {
|
||||
if (!buffer || !currentPipeline_) {
|
||||
if (!buffer || slot >= 4) return;
|
||||
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
|
||||
// 状态缓存检查
|
||||
if (stateCache_.vertexBuffers[slot] == glBuffer &&
|
||||
stateCache_.vertexBufferOffsets[slot] == offset) {
|
||||
stats_.redundantBufferChanges++;
|
||||
return;
|
||||
}
|
||||
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
glBindBuffer(GL_ARRAY_BUFFER, glBuffer->getGLBuffer());
|
||||
|
||||
// 只配置属于当前 slot 的属性
|
||||
const auto &layout = currentPipeline_->getVertexLayout();
|
||||
// 使用传入的步长，如果为0则使用布局中的步长
|
||||
// 配置属于当前 slot 的属性
|
||||
// 注意：虽然 VAO 缓存了部分配置，但我们需要绑定具体的缓冲区
|
||||
const auto &layout = stateCache_.pipeline ? stateCache_.pipeline->getVertexLayout() : VertexLayout{};
|
||||
uint32_t actualStride = stride > 0 ? stride : layout.stride;
|
||||
|
||||
for (const auto &attr : layout.attributes) {
|
||||
|
|
@ -132,44 +164,95 @@ void GLCommandList::setVertexBuffer(uint32_t slot, RHIBuffer *buffer,
|
|||
// 设置实例化除数
|
||||
glVertexAttribDivisor(attr.location, attr.divisor);
|
||||
}
|
||||
|
||||
stateCache_.vertexBuffers[slot] = glBuffer;
|
||||
stateCache_.vertexBufferOffsets[slot] = offset;
|
||||
stats_.bufferChanges++;
|
||||
}
|
||||
|
||||
void GLCommandList::setIndexBuffer(RHIBuffer *buffer, IndexType type,
|
||||
uint32_t offset) {
|
||||
if (buffer) {
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, glBuffer->getGLBuffer());
|
||||
currentIndexBuffer_ = glBuffer;
|
||||
if (!buffer) return;
|
||||
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
|
||||
// 状态缓存检查
|
||||
if (stateCache_.indexBuffer == glBuffer) {
|
||||
stats_.redundantBufferChanges++;
|
||||
return;
|
||||
}
|
||||
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, glBuffer->getGLBuffer());
|
||||
stateCache_.indexBuffer = glBuffer;
|
||||
stats_.bufferChanges++;
|
||||
}
|
||||
|
||||
void GLCommandList::setUniformBuffer(uint32_t slot, RHIBuffer *buffer) {
|
||||
if (buffer) {
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
glBindBufferBase(GL_UNIFORM_BUFFER, slot, glBuffer->getGLBuffer());
|
||||
if (!buffer || slot >= 4) return;
|
||||
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
|
||||
// 状态缓存检查
|
||||
if (stateCache_.uniformBuffers[slot].valid &&
|
||||
stateCache_.uniformBuffers[slot].buffer == glBuffer &&
|
||||
stateCache_.uniformBuffers[slot].offset == 0) {
|
||||
return;
|
||||
}
|
||||
|
||||
glBindBufferBase(GL_UNIFORM_BUFFER, slot, glBuffer->getGLBuffer());
|
||||
|
||||
stateCache_.uniformBuffers[slot].buffer = glBuffer;
|
||||
stateCache_.uniformBuffers[slot].offset = 0;
|
||||
stateCache_.uniformBuffers[slot].size = 0;
|
||||
stateCache_.uniformBuffers[slot].valid = true;
|
||||
}
|
||||
|
||||
void GLCommandList::setUniformBuffer(uint32_t slot, RHIBuffer *buffer, uint32_t offset, uint32_t size) {
|
||||
if (buffer) {
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
GLuint glBufferId = glBuffer->getGLBuffer();
|
||||
if (size == 0) {
|
||||
// 绑定整个缓冲区
|
||||
glBindBufferBase(GL_UNIFORM_BUFFER, slot, glBufferId);
|
||||
} else {
|
||||
// 绑定缓冲区范围
|
||||
glBindBufferRange(GL_UNIFORM_BUFFER, slot, glBufferId, offset, size);
|
||||
}
|
||||
if (!buffer || slot >= 4) return;
|
||||
|
||||
auto *glBuffer = static_cast<GLBuffer *>(buffer);
|
||||
GLuint glBufferId = glBuffer->getGLBuffer();
|
||||
|
||||
// 状态缓存检查
|
||||
if (stateCache_.uniformBuffers[slot].valid &&
|
||||
stateCache_.uniformBuffers[slot].buffer == glBuffer &&
|
||||
stateCache_.uniformBuffers[slot].offset == offset &&
|
||||
stateCache_.uniformBuffers[slot].size == size) {
|
||||
return;
|
||||
}
|
||||
|
||||
if (size == 0) {
|
||||
// 绑定整个缓冲区
|
||||
glBindBufferBase(GL_UNIFORM_BUFFER, slot, glBufferId);
|
||||
} else {
|
||||
// 绑定缓冲区范围
|
||||
glBindBufferRange(GL_UNIFORM_BUFFER, slot, glBufferId, offset, size);
|
||||
}
|
||||
|
||||
stateCache_.uniformBuffers[slot].buffer = glBuffer;
|
||||
stateCache_.uniformBuffers[slot].offset = offset;
|
||||
stateCache_.uniformBuffers[slot].size = size;
|
||||
stateCache_.uniformBuffers[slot].valid = true;
|
||||
}
|
||||
|
||||
void GLCommandList::setTexture(uint32_t slot, RHITexture *texture) {
|
||||
if (texture) {
|
||||
auto *glTexture = static_cast<GLTexture *>(texture);
|
||||
glActiveTexture(GL_TEXTURE0 + slot);
|
||||
glBindTexture(GL_TEXTURE_2D, glTexture->getGLTexture());
|
||||
if (!texture || slot >= 8) return;
|
||||
|
||||
auto *glTexture = static_cast<GLTexture *>(texture);
|
||||
|
||||
// 状态缓存检查
|
||||
if (stateCache_.textures[slot].valid &&
|
||||
stateCache_.textures[slot].texture == glTexture) {
|
||||
stats_.redundantTextureChanges++;
|
||||
return;
|
||||
}
|
||||
|
||||
glActiveTexture(GL_TEXTURE0 + slot);
|
||||
glBindTexture(GL_TEXTURE_2D, glTexture->getGLTexture());
|
||||
|
||||
stateCache_.textures[slot].texture = glTexture;
|
||||
stateCache_.textures[slot].valid = true;
|
||||
stats_.textureChanges++;
|
||||
}
|
||||
|
||||
void GLCommandList::setSampler(uint32_t slot, TextureFilter minFilter,
|
||||
|
|
@ -192,7 +275,7 @@ void GLCommandList::drawIndexed(uint32_t indexCount, uint32_t firstIndex,
|
|||
int32_t vertexOffset, uint32_t instanceCount,
|
||||
uint32_t firstInstance) {
|
||||
GLenum indexType = GL_UNSIGNED_SHORT;
|
||||
if (currentIndexBuffer_) {
|
||||
if (stateCache_.indexBuffer) {
|
||||
// 根据缓冲区类型确定索引类型
|
||||
// 这里简化处理，使用 GL_UNSIGNED_SHORT
|
||||
}
|
||||
|
|
@ -237,8 +320,8 @@ bool GLCommandList::isRecording() const {
|
|||
}
|
||||
|
||||
void GLCommandList::setUniform(const char* name, float value) {
|
||||
if (currentShaderProgram_ != 0) {
|
||||
GLint location = glGetUniformLocation(currentShaderProgram_, name);
|
||||
if (stateCache_.shaderProgram != 0) {
|
||||
GLint location = glGetUniformLocation(stateCache_.shaderProgram, name);
|
||||
if (location != -1) {
|
||||
glUniform1f(location, value);
|
||||
}
|
||||
|
|
@ -246,8 +329,8 @@ void GLCommandList::setUniform(const char* name, float value) {
|
|||
}
|
||||
|
||||
void GLCommandList::setUniform(const char* name, const Vec2& value) {
|
||||
if (currentShaderProgram_ != 0) {
|
||||
GLint location = glGetUniformLocation(currentShaderProgram_, name);
|
||||
if (stateCache_.shaderProgram != 0) {
|
||||
GLint location = glGetUniformLocation(stateCache_.shaderProgram, name);
|
||||
if (location != -1) {
|
||||
glUniform2f(location, value.x, value.y);
|
||||
}
|
||||
|
|
@ -255,8 +338,8 @@ void GLCommandList::setUniform(const char* name, const Vec2& value) {
|
|||
}
|
||||
|
||||
void GLCommandList::setUniform(const char* name, const Vec3& value) {
|
||||
if (currentShaderProgram_ != 0) {
|
||||
GLint location = glGetUniformLocation(currentShaderProgram_, name);
|
||||
if (stateCache_.shaderProgram != 0) {
|
||||
GLint location = glGetUniformLocation(stateCache_.shaderProgram, name);
|
||||
if (location != -1) {
|
||||
glUniform3f(location, value.x, value.y, value.z);
|
||||
}
|
||||
|
|
@ -264,8 +347,8 @@ void GLCommandList::setUniform(const char* name, const Vec3& value) {
|
|||
}
|
||||
|
||||
void GLCommandList::setUniform(const char* name, const Color& value) {
|
||||
if (currentShaderProgram_ != 0) {
|
||||
GLint location = glGetUniformLocation(currentShaderProgram_, name);
|
||||
if (stateCache_.shaderProgram != 0) {
|
||||
GLint location = glGetUniformLocation(stateCache_.shaderProgram, name);
|
||||
if (location != -1) {
|
||||
glUniform4f(location, value.r, value.g, value.b, value.a);
|
||||
}
|
||||
|
|
@ -273,8 +356,8 @@ void GLCommandList::setUniform(const char* name, const Color& value) {
|
|||
}
|
||||
|
||||
void GLCommandList::setUniform(const char* name, const Mat4& value) {
|
||||
if (currentShaderProgram_ != 0) {
|
||||
GLint location = glGetUniformLocation(currentShaderProgram_, name);
|
||||
if (stateCache_.shaderProgram != 0) {
|
||||
GLint location = glGetUniformLocation(stateCache_.shaderProgram, name);
|
||||
if (location != -1) {
|
||||
glUniformMatrix4fv(location, 1, GL_FALSE, glm::value_ptr(value));
|
||||
}
|
||||
|
|
|
|||
|
|
@ -62,9 +62,10 @@ void GLPipeline::bind() {
|
|||
if (shaderProgram_ != 0) {
|
||||
glUseProgram(shaderProgram_);
|
||||
}
|
||||
|
||||
// 注意：不再绑定VAO，因为我们使用动态顶点属性配置
|
||||
// 顶点属性在 GLCommandList::setVertexBuffer 中配置
|
||||
|
||||
// 注意：VAO 需要与具体的顶点缓冲区绑定才能工作
|
||||
// 所以我们不在此处绑定 VAO，而是在渲染时动态配置顶点属性
|
||||
// 这样可以支持不同的 Mesh 使用相同的 Pipeline
|
||||
|
||||
// 应用混合状态
|
||||
if (desc_.blendState.enabled) {
|
||||
|
|
@ -83,7 +84,7 @@ void GLPipeline::bind() {
|
|||
} else {
|
||||
glDisable(GL_DEPTH_TEST);
|
||||
}
|
||||
|
||||
|
||||
// 应用光栅化状态
|
||||
if (desc_.rasterizerState.cullEnabled) {
|
||||
glEnable(GL_CULL_FACE);
|
||||
|
|
|
|||
|
|
@ -87,10 +87,15 @@ UniformBufferManager::~UniformBufferManager() { shutdown(); }
|
|||
|
||||
UniformBufferManager::UniformBufferManager(
|
||||
UniformBufferManager &&other) noexcept
|
||||
: globalUBO_(std::move(other.globalUBO_)),
|
||||
: globalUBOs_(std::move(other.globalUBOs_)),
|
||||
materialUBOPool_(std::move(other.materialUBOPool_)),
|
||||
currentUBOIndex_(other.currentUBOIndex_) {
|
||||
currentUBOIndex_(other.currentUBOIndex_),
|
||||
materialUBOBuffer_(std::move(other.materialUBOBuffer_)),
|
||||
materialUBOBufferOffset_(other.materialUBOBufferOffset_),
|
||||
currentMaterialUBO_(other.currentMaterialUBO_) {
|
||||
other.currentUBOIndex_ = 0;
|
||||
other.materialUBOBufferOffset_ = 0;
|
||||
other.currentMaterialUBO_ = nullptr;
|
||||
}
|
||||
|
||||
UniformBufferManager &
|
||||
|
|
@ -98,40 +103,59 @@ UniformBufferManager::operator=(UniformBufferManager &&other) noexcept {
|
|||
if (this != &other) {
|
||||
shutdown();
|
||||
|
||||
globalUBO_ = std::move(other.globalUBO_);
|
||||
globalUBOs_ = std::move(other.globalUBOs_);
|
||||
materialUBOPool_ = std::move(other.materialUBOPool_);
|
||||
currentUBOIndex_ = other.currentUBOIndex_;
|
||||
materialUBOBuffer_ = std::move(other.materialUBOBuffer_);
|
||||
materialUBOBufferOffset_ = other.materialUBOBufferOffset_;
|
||||
currentMaterialUBO_ = other.currentMaterialUBO_;
|
||||
|
||||
other.currentUBOIndex_ = 0;
|
||||
other.materialUBOBufferOffset_ = 0;
|
||||
other.currentMaterialUBO_ = nullptr;
|
||||
}
|
||||
return *this;
|
||||
}
|
||||
|
||||
bool UniformBufferManager::initialize() {
|
||||
// 创建全局 UBO
|
||||
globalUBO_ = std::make_unique<UniformBuffer>();
|
||||
if (!globalUBO_->create(UniformBufferManager::GLOBAL_UBO_SIZE,
|
||||
UniformBufferManager::GLOBAL_UBO_BINDING)) {
|
||||
E2D_LOG_ERROR("Failed to create global UBO");
|
||||
return false;
|
||||
// 创建全局 UBO 双缓冲
|
||||
for (size_t i = 0; i < globalUBOs_.size(); ++i) {
|
||||
globalUBOs_[i] = std::make_unique<UniformBuffer>();
|
||||
if (!globalUBOs_[i]->create(UniformBufferManager::GLOBAL_UBO_SIZE,
|
||||
UniformBufferManager::GLOBAL_UBO_BINDING)) {
|
||||
E2D_LOG_ERROR("Failed to create global UBO {}", i);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// 预分配材质 UBO 池
|
||||
materialUBOPool_.reserve(INITIAL_UBO_POOL_SIZE);
|
||||
|
||||
E2D_LOG_INFO("UniformBufferManager initialized");
|
||||
// 预分配材质 UBO CPU 缓冲区
|
||||
materialUBOBuffer_.resize(MATERIAL_UBO_BUFFER_SIZE);
|
||||
|
||||
E2D_LOG_INFO("UniformBufferManager initialized with double buffering");
|
||||
return true;
|
||||
}
|
||||
|
||||
void UniformBufferManager::shutdown() {
|
||||
materialUBOPool_.clear();
|
||||
globalUBO_.reset();
|
||||
for (auto& ubo : globalUBOs_) {
|
||||
ubo.reset();
|
||||
}
|
||||
currentUBOIndex_ = 0;
|
||||
materialUBOBuffer_.clear();
|
||||
materialUBOBufferOffset_ = 0;
|
||||
currentMaterialUBO_ = nullptr;
|
||||
|
||||
E2D_LOG_INFO("UniformBufferManager shutdown");
|
||||
}
|
||||
|
||||
UniformBuffer *UniformBufferManager::getGlobalUBO() { return globalUBO_.get(); }
|
||||
UniformBuffer *UniformBufferManager::getGlobalUBO(uint32_t frameIndex) {
|
||||
// 使用双缓冲，根据帧索引选择 UBO
|
||||
size_t index = frameIndex % 2;
|
||||
return globalUBOs_[index].get();
|
||||
}
|
||||
|
||||
UniformBuffer *UniformBufferManager::acquireMaterialUBO(uint32_t size) {
|
||||
// 查找或创建合适大小的 UBO
|
||||
|
|
@ -156,13 +180,39 @@ UniformBuffer *UniformBufferManager::acquireMaterialUBO(uint32_t size) {
|
|||
return result;
|
||||
}
|
||||
|
||||
void UniformBufferManager::resetMaterialUBOs() { currentUBOIndex_ = 0; }
|
||||
void UniformBufferManager::resetMaterialUBOs() {
|
||||
currentUBOIndex_ = 0;
|
||||
materialUBOBufferOffset_ = 0;
|
||||
currentMaterialUBO_ = nullptr;
|
||||
}
|
||||
|
||||
void UniformBufferManager::updateGlobalUBO(const void *data, uint32_t size) {
|
||||
if (globalUBO_) {
|
||||
globalUBO_->update(data, size);
|
||||
globalUBO_->bind(UniformBufferManager::GLOBAL_UBO_BINDING);
|
||||
void UniformBufferManager::updateGlobalUBO(const void *data, uint32_t size, uint32_t frameIndex) {
|
||||
// 使用双缓冲更新全局 UBO
|
||||
size_t index = frameIndex % 2;
|
||||
if (globalUBOs_[index]) {
|
||||
globalUBOs_[index]->update(data, size);
|
||||
globalUBOs_[index]->bind(UniformBufferManager::GLOBAL_UBO_BINDING);
|
||||
}
|
||||
}
|
||||
|
||||
void UniformBufferManager::batchUpdateMaterialUBO(const void *data, uint32_t size, uint32_t offset) {
|
||||
if (!data || size == 0 || offset + size > materialUBOBuffer_.size()) {
|
||||
E2D_LOG_WARN("Invalid batch update parameters");
|
||||
return;
|
||||
}
|
||||
|
||||
// 复制数据到 CPU 缓冲区
|
||||
std::memcpy(materialUBOBuffer_.data() + offset, data, size);
|
||||
}
|
||||
|
||||
void UniformBufferManager::flushMaterialUBO() {
|
||||
if (materialUBOBufferOffset_ == 0 || !currentMaterialUBO_) {
|
||||
return;
|
||||
}
|
||||
|
||||
// 一次性将 CPU 缓冲区数据更新到 GPU
|
||||
currentMaterialUBO_->update(materialUBOBuffer_.data(), materialUBOBufferOffset_, 0);
|
||||
materialUBOBufferOffset_ = 0;
|
||||
}
|
||||
|
||||
} // namespace extra2d
|
||||
|
|
|
|||
Loading…
Reference in New Issue