Opengl三角形基准

Opengl Triangles Benchmark

本文关键字:基准 三角形 Opengl      更新时间:2023-10-16

我正在测试如何在笔记本电脑上绘制三角形,所以我在我的系统上做了以下操作:

操作系统:Windows 10CPU:Intel Core i5 5200UGPU:NVIDIA Geforce 820M

代码:

glfwWindowHint(GLFW_SAMPLES, 4);
glfwWindowHint(GLFW_CONTEXT_VERSION_MAJOR, 3);
glfwWindowHint(GLFW_CONTEXT_VERSION_MINOR, 3);
glfwWindowHint(GLFW_OPENGL_FORWARD_COMPAT, GL_TRUE); // To make MacOS happy; should not be needed
glfwWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE);
// Open a window and create its OpenGL context
window = glfwCreateWindow( 1024, 768, "Tutorial 02 - Red triangle", NULL, NULL);
if( window == NULL ){
fprintf( stderr, "Failed to open GLFW window. If you have an Intel GPU, they are not 3.3 compatible. Try the 2.1 version of the tutorials.n" );
getchar();
glfwTerminate();
return -1;
}
glfwMakeContextCurrent(window);
// Initialize GLEW
glewExperimental = true; // Needed for core profile
if (glewInit() != GLEW_OK) {
fprintf(stderr, "Failed to initialize GLEWn");
getchar();
glfwTerminate();
return -1;
}
// Ensure we can capture the escape key being pressed below
glfwSetInputMode(window, GLFW_STICKY_KEYS, GL_TRUE);
// Dark blue background
glClearColor(0.0f, 0.0f, 0.4f, 0.0f);
GLuint VertexArrayID;
glGenVertexArrays(1, &VertexArrayID);
glBindVertexArray(VertexArrayID);
// Create and compile our GLSL program from the shaders
GLuint programID = LoadShaders( "SimpleVertexShader.vertexshader", "SimpleFragmentShader.fragmentshader" );

// Number of triangles
const int v = 200;
static  GLfloat g_vertex_buffer_data[v*9] = { 
-1.0f, -1.0f, 1.0f,
0.8f, 0.f, 0.0f,
0.5f,  1.0f, 0.0f,
};
// fill buffer of triangles
for (int i = 9; i < v * 9; i += 9)
{
g_vertex_buffer_data[i] = g_vertex_buffer_data[0];
g_vertex_buffer_data[i+1] = g_vertex_buffer_data[1];
g_vertex_buffer_data[i+2] = g_vertex_buffer_data[2];
g_vertex_buffer_data[i+3] = g_vertex_buffer_data[3];
g_vertex_buffer_data[i+4] = g_vertex_buffer_data[4];
g_vertex_buffer_data[i+5] = g_vertex_buffer_data[5];
g_vertex_buffer_data[i+6] = g_vertex_buffer_data[6];
g_vertex_buffer_data[i+7] = g_vertex_buffer_data[7];
g_vertex_buffer_data[i+8] = g_vertex_buffer_data[8];
}
GLuint vertexbuffer;
glGenBuffers(1, &vertexbuffer);
glBindBuffer(GL_ARRAY_BUFFER, vertexbuffer);
glBufferData(GL_ARRAY_BUFFER, sizeof(g_vertex_buffer_data), g_vertex_buffer_data, GL_STATIC_DRAW);
int frameNr = 0;
char text[100];
do{
// Clear the screen
glClear( GL_COLOR_BUFFER_BIT );
// Use our shader
glUseProgram(programID);
// 1rst attribute buffer : vertices
glEnableVertexAttribArray(0);
glBindBuffer(GL_ARRAY_BUFFER, vertexbuffer);
glVertexAttribPointer(
0,                  // attribute 0. No particular reason for 0, but must match the layout in the shader.
3,                  // size
GL_FLOAT,           // type
GL_FALSE,           // normalized?
0,                  // stride
(void*)0            // array buffer offset
);
// Draw the triangle !
glDrawArrays(GL_TRIANGLES, 0, v*3); // 3 indices starting at 0 -> 1 triangle
glDisableVertexAttribArray(0);
// Swap buffers
glfwSwapBuffers(window);
glfwPollEvents();
//glBufferData(GL_ARRAY_BUFFER, sizeof(g_vertex_buffer_data), g_vertex_buffer_data, GL_STATIC_DRAW);
frameNr++;
sprintf_s(text, "%d %d %d", frameNr, clock() / 1000, (frameNr * 1000) / (clock() + 1));
glfwSetWindowTitle(window, text);
} // Check if the ESC key was pressed or the window was closed
while( glfwGetKey(window, GLFW_KEY_ESCAPE ) != GLFW_PRESS &&
glfwWindowShouldClose(window) == 0 );
// Cleanup VBO
glDeleteBuffers(1, &vertexbuffer);
glDeleteVertexArrays(1, &VertexArrayID);
glDeleteProgram(programID);
// Close OpenGL window and terminate GLFW
glfwTerminate();
return 0;

让我惊讶的是,在v=200三角形的情况下,我只能获得大约80帧/秒的帧速率。这大约是每秒16000个三角形,这很糟糕,不是吗?

我在代码中做错了什么,或者我的显卡真的只能处理这么少的三角形吗?

像1080ti这样的现代gpu能处理多少个三角形(理论上我听说有110亿个三角形——尽管我知道实际上它要低得多(。

由于我还没有足够的声誉发表评论,让我在这里问:你的三角形有多大?如果没有看过顶点着色器,很难判断,但假设代码中的这些坐标直接映射到标准化的设备坐标,则三角形会覆盖屏幕的很大一部分。如果我没有错的话,你基本上是在它上面一遍又一遍地画同一个三角形。因此,您很可能会受到填充率限制。为了获得更有意义的结果,你可能只想画一个不重叠的三角形网格,或者至少画一个随机的三角形汤。为了进一步减少填充率和帧缓冲区带宽需求,您可能需要确保深度缓冲和混合关闭

如果您对每秒原始三角形感兴趣,为什么要启用MSAA?这样做只是人为地放大光栅化器的负载。正如其他人也注意到的那样,V-Sync可能会被关闭,因为80 Hz的刷新率相当奇怪,但最好确保并通过glfwSwapInterval(0)明确关闭。您可能需要考虑使用GL_TIME_ELAPSED查询来测量GPU上的实际绘制时间,而不是像您那样估计总帧时间。