为什么基于 Dear ImGui 的渲染器这么慢？

Question

我已经完成 class，它基于 Dear ImGui DrawList 渲染 2d 对象，因为它可以绘制许多不同的对象变体，这要归功于索引向量动态数组，并且仍然保持良好的优化。亲爱的 ImGui 可以渲染 30k 未填充的矩形，同时在调试模式下具有 ~36fps 和 ~70MB，没有抗锯齿（我的电脑）。我的非常有限的版本绘制了 30k 未填充的矩形，同时在调试模式下具有 ~3 fps 和 ~130MB。

class Renderer
{
public:
    Renderer();
    ~Renderer();

    void Create();

    void DrawRect(float x, float y, float w, float h, GLuint color, float thickness);

    void Render(float w, float h);

    void Clear();

    void ReserveData(int numVertices, int numElements);

    void CreatePolygon(const Vector2* vertices, const GLuint verticesCount, GLuint color, float thickness);

    GLuint vao, vbo, ebo;
    GLShader shader;

    Vertex* mappedVertex = nullptr;     
    GLuint* mappedElement = nullptr,   
            currentVertexIndex = 0;

    std::vector<Vertex> vertexBuffer;  
    std::vector<GLuint> elementBuffer; 
    std::vector<Vector2> vertices;

};

const char* vtx =
R"(

#version 460 core

layout(location = 0) in vec3 a_position;
layout(location = 1) in vec4 a_color;

out vec3 v_position;
out vec4 v_color;

uniform mat4 projection;

void main()
{
    gl_Position = projection * vec4(a_position, 1.0);

    v_color = a_color;
}

)";

const char* frag =
R"(
#version 460 core

layout (location = 0) out vec4 outColor;

in vec4 v_color;

void main()
{
    outColor = v_color;
}
)";

void Renderer::Clear()
{
    vertexBuffer.resize(0);
    elementBuffer.resize(0);
    vertices.resize(0);
    mappedVertex = nullptr;
    mappedElement = nullptr;
    currentVertexIndex = 0;
}

void Renderer::Create()
{
    glGenBuffers(1, &vbo);
    glGenBuffers(1, &ebo);

   shader.VtxFromFile(vtx);
   shader.FragFromFile(frag);
}

void Renderer::DrawRect(float x, float y, float w, float h, GLuint color,     float thickness)
{
    // Add vertices
    vertices.push_back({ x, y });
    vertices.push_back(Vector2(x, y + w));
    vertices.push_back(Vector2( x, y ) + Vector2(w, h));
    vertices.push_back(Vector2(x + w, y));
    // Create rect
    CreatePolygon(vertices.data(), vertices.size(), color, thickness);
}

void Renderer::Render(float w, float h)
{
    glEnable(GL_BLEND);
    glBlendFunc(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA);

    shader.UseProgram();
    shader.UniformMatrix4fv("projection", glm::ortho(0.0f, w, 0.0f, h));

    GLuint elemCount = elementBuffer.size();

    glGenVertexArrays(1, &vao);
    glBindVertexArray(vao);

    glBindBuffer(GL_ARRAY_BUFFER, vbo);
    glEnableVertexAttribArray(0);
    glEnableVertexAttribArray(1);

    glVertexAttribPointer(0, 2, GL_FLOAT, GL_FALSE, sizeof(Vertex), (const void*)offsetof(Vertex, position));
    glVertexAttribPointer(1, 4, GL_UNSIGNED_BYTE, GL_TRUE, sizeof(Vertex), (const void*)offsetof(Vertex, position));

    glBufferData(GL_ARRAY_BUFFER, vertexBuffer.size() * sizeof(Vertex), vertexBuffer.data(), GL_STREAM_DRAW);

    glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, ebo);
    glBufferData(GL_ELEMENT_ARRAY_BUFFER, elementBuffer.size() * sizeof(GLuint), elementBuffer.data(), GL_STREAM_DRAW);

    const unsigned short* idxBufferOffset = 0;

    glDrawElements(GL_TRIANGLES, elemCount, GL_UNSIGNED_INT, idxBufferOffset);

    idxBufferOffset += elemCount;

    glDeleteVertexArrays(1, &vao);

    glDisable(GL_BLEND);
}

void Renderer::CreatePolygon(const Vector2* vertices, const GLuint     verticesCount, GLuint color, float thickness)
{
    // To create for example unfilled rect, we have to draw 4 rects with small sizes
    // So, unfilled rect is built from 4 rects and each rect contains 4 vertices ( * 4) and 6 indices ( *6)
    ReserveData(verticesCount * 4, verticesCount * 6);

    for (GLuint i = 0; i < verticesCount; ++i)
    {
        const int j = (i + 1) == verticesCount ? 0 : i + 1;

        const Vector2& position1 = vertices[i];
        const Vector2& position2 = vertices[j];

        Vector2 difference = position2 - position1;

        difference *= difference.Magnitude() > 0 ? 1.0f / difference.Magnitude() : 1.0f;

        const float dx = difference.x * (thickness * 0.5f);
        const float dy = difference.y * (thickness * 0.5f);

        mappedVertex[0].position = Vector2(position1.x + dy, position1.y - dx);
        mappedVertex[1].position = Vector2(position2.x + dy, position2.y - dx);
        mappedVertex[2].position = Vector2(position2.x - dy, position2.y + dx);
        mappedVertex[3].position = Vector2(position1.x - dy, position1.y + dx);

        mappedVertex[0].color = color;
        mappedVertex[1].color = color;
        mappedVertex[2].color = color;
        mappedVertex[3].color = color;

        mappedVertex += 4;

        mappedElement[0] = currentVertexIndex;
        mappedElement[1] = currentVertexIndex + 1;
        mappedElement[2] = currentVertexIndex + 2;
        mappedElement[3] = currentVertexIndex + 2;
        mappedElement[4] = currentVertexIndex + 3;
        mappedElement[5] = currentVertexIndex;

        mappedElement += 6;
        currentVertexIndex += 4;
    }

    this->vertices.clear();
}

void Renderer::ReserveData(int numVertices, int numElements)
{
    currentVertexIndex = vertexBuffer.size();

    // Map vertex buffer
    int oldVertexSize = vertexBuffer.size();
    vertexBuffer.resize(oldVertexSize + numVertices);
    mappedVertex = vertexBuffer.data() + oldVertexSize;

    // Map element buffer
    int oldIndexSize = elementBuffer.size();
    elementBuffer.resize(oldIndexSize + numElements);
    mappedElement = elementBuffer.data() + oldIndexSize;
}


int main()
{
    //Create window, init opengl, etc.
    Renderer renderer;
    renderer.Create();
    bool quit=false;
    while(!quit) {
        //Events
        //Clear color bit

        renderer.Clear();

        for(int i = 0; i < 30000; ++i)
            renderer.DrawRect(100.0f, 100.0f, 50.0f, 50.0f, 0xffff0000, 1.5f);

        renderer.Render(windowW, windowH);        

        //swap buffers
    }
    return 0;
}

为什么这么慢？我怎样才能让它更快，占用内存更少？

Answer 1

该代码中最大的瓶颈似乎是您的分配永远不会跨帧摊销，因为您正在清除缓冲区容量而不是重用它们，导致您出现很多 realloc/copies（可能是 Log2(n) reallocs/copies 如果你的向量实现增长了 2)。尝试使用 .resize(0) 更改您的 .clear() 调用，也许您可以在未使用的情况下对 .clear() 进行更多 lazy/rare 调用。

In debug or in release mode? Vectors are terribly slow in debug due to memory checking. Profiling should always be done in Release.

如果您打算在 Debug/Unoptimized 模式下使用和使用您的应用程序，则应该在 Release 和 Debug/Unoptimized 模式下进行分析。现代 C++ 的严重 "zero-cost abstraction" 谎言是它使使用调试器变得很痛苦，因为大型应用程序不再运行在 "Debug" 模式下以正确的帧速率。理想情况下，您应该始终运行所有应用程序处于调试模式。帮自己提高工作效率，也为最糟糕的情况做一些事情 profiling/optimization。

祝您学习顺利！ :)

Answer 2

解决方案

我不再使用 std::vector。我改用 ImVector（它也可能是你自己的实现），
我直接设置position为一个Vector2.x/.y

为什么基于 Dear ImGui 的渲染器这么慢？

Why Dear ImGui based renderer is so slow?

c++

opengl

optimization

2d

renderer